diff --git a/.i18n-state.json b/.i18n-state.json
index 6324375b3d..bf398a4f8c 100644
--- a/.i18n-state.json
+++ b/.i18n-state.json
@@ -87,11 +87,6 @@
           "target_hash": "251fbf9d851b20c0878bd809f6e380ac0e3e4842cc7afc33e7e55d710630fe0d",
           "updated_at": "2026-09-02T11:01:21.738Z"
         },
-        "in": {
-          "source_hash": "b90b22873977a250f16576a05ee3eae11b4a6be0882674d3d368985032201a88",
-          "target_hash": "fc8d684c84ba5106e7a217e1e93b935ef63b48a7a45e8d8cd2b566fcdd4aabd5",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
         "it": {
           "source_hash": "b90b22873977a250f16576a05ee3eae11b4a6be0882674d3d368985032201a88",
           "target_hash": "2ae6b313c6a3bc34eaeee5d333ba8d501d72504d01b1be77403a520f5235df2a",
@@ -302,11 +297,6 @@
           "target_hash": "656c1f78610522085f23d6c58fdd86c998c6b2007cfc1238ddd6367f595a7bee",
           "updated_at": "2026-09-02T11:01:21.738Z"
         },
-        "in": {
-          "source_hash": "151cd0ae57fb50b8a7363c084ecc4593f59c6bf73f7ef632c077e7b8c41923ea",
-          "target_hash": "3834876eb20b5fbc042fba2d0a0093a2aa3e30c93d77a2c9308d60427bfddde2",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
         "it": {
           "source_hash": "151cd0ae57fb50b8a7363c084ecc4593f59c6bf73f7ef632c077e7b8c41923ea",
           "target_hash": "c733815b8ec1439fed16c975890fd6b4d8ebc9e059b78eb5d4fd456d34654c8d",
@@ -517,11 +507,6 @@
           "target_hash": "4d3e569f63c4507881a25302cb8ef94ce0db1e311e3385381abc9705838778ef",
           "updated_at": "2026-09-02T11:01:21.738Z"
         },
-        "in": {
-          "source_hash": "0da9cb7b6ec091538e7fbafbdf8d7e3a3e7e2c12ea352c56722cec883596f8e1",
-          "target_hash": "7316128c140a8ae9614629be7d362efc679bc356aad0bc4414de7f69bc0fcf3c",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
         "it": {
           "source_hash": "0da9cb7b6ec091538e7fbafbdf8d7e3a3e7e2c12ea352c56722cec883596f8e1",
           "target_hash": "6939f754455353038c94a3d00075dbf7c518dbb5ccf3a87a8b265d1f41c88636",
@@ -732,11 +717,6 @@
           "target_hash": "2d6dd5109ce9fd70543192ceea344ec062de82987b458ef242de5db6f2277f07",
           "updated_at": "2026-09-02T11:01:21.738Z"
         },
-        "in": {
-          "source_hash": "8ce18538a6fafc686015b9d5c69e0f9f0f9ec4465173b96d09f5502067abaf1e",
-          "target_hash": "bc3c37bd69ef911668b82dadf3f329ab949bcf2e975cad38b6c68c831335c2f1",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
         "it": {
           "source_hash": "8ce18538a6fafc686015b9d5c69e0f9f0f9ec4465173b96d09f5502067abaf1e",
           "target_hash": "0dd81b43479c140220204c2df91866eeca70013d6e9cdbf819adca6ce0e12dcf",
@@ -865,217 +845,212 @@
       }
     },
     "README.md": {
-      "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+      "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
       "locales": {
         "ar": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "107ff0e8f5e82cbcdf49a8a247868b41f45a5a1b23b6dd7c6acdf1ea12265939",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "az": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "242334674919dfa94de49b14d137352256391dc974b3d8687489bdce2198f6aa",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "bg": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "3f8ccbe6c78036aa61a450f9231e256ab2bf16bdacf26a791209caadeaa052e7",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "bn": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "1ac123a7082363a85b40843a5f348680dc0245cb7f7783ad045ea1d4ac7baa8c",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "cs": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "7645f7920e3864d715c76c21af328bb5d3df4ddcbc0e8f91bf756b5923cda344",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "da": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "28a90b1b70c20e7c3b6737876cca5f83a427acbf142d8217ad145d87c5386019",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "de": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "754fb7b342f6f4b5637552eac603a2d90458ab6165dc1cbb985fcd2b7f7ddee7",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "es": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "2675da25b0a7b89d0e26e7e53853dcca3476bcf2feac92848c0e437e2a3d1c7c",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "fa": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "d771149c2b79d7f8d95e30279e4f87cc260d9854de191561ef36558d4cd98ede",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "fi": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "738f2a3e518b4ae7d7eb109246b88a1af8f00cc6c2eb4e1777dfc929b478f5e7",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "fr": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "a040c572e5026a27d61acb137cd1c848fc6910c7d7d950728e18d9303472197d",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "gu": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "278f12d74d99757ba4b67f61d78a2613091e281142d6fac8001a26b333e0518e",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "he": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "6dea00d6b62b5f264a4ce38df6502f2140dc58de833be79e6781b457bf23992b",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "hi": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "49724624db928fdedc36edf853ecf9443567373157e00e781eefe45e0ab0d56a",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "hu": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "193b563d6ce8395d8ab6cb43eb20ad7500c50f63cb74c2e4af93667a0fce3332",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "id": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "00d3a822133d5c0db228ed60c76f8dfcddca087d0f44a9889ede1d57dcdc3cf2",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
-        "in": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
-          "target_hash": "efa7fb288ddbfbf3da3f2bfa371f69223d25628213164403dd3ad06c55b94585",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "it": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "d6f021064acfe781ffc57ddfa463f9892e2fdaf947492c325404972363b4ef58",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ja": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "566103833ed8c891f75b17bdf6ca6b014a5e117fd89dff581104f5b0356ccb6a",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ko": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "0a35bedda20b5f488537d8ba5dcbebc06ebed7239e1351c9896b5aa214522cbc",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "mr": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "a499cbb8086384779e4fad27ce083e950a78a795b2804f3d1e8dc87b6582c71c",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ms": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "ada58fca99f5fccc1b46b607aeb38ba044a60e294656e3523df5281665dca698",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "nl": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "4c6efc86109f440491671fc486f175f7f2fac308d39185da96843816596a2f6d",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "no": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "9a8cf1cf44b1e97d82b45622f28d963238042ad496063f8407fe1e65c0ced38f",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "phi": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "759f1bffea2e90127e8c55e48de9900880fe6537e0d57d3bc7987b54b39aad2b",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "pl": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "126d1a85ea4ee3adba35c61d84720ef627e3ee18e2245d4efe8b0ab00ac126cc",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "pt": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "63ffc0c89d7feb019221af675875e4ecf7da705f0a52cd880eb90d9539578fe9",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "pt-BR": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "3924045956ee4ac443e82adfd0eb0e12dd1e753e4756ec61dc4f85eb66d073a9",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ro": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "b816b20e8bc298a97b3ed964d0230f423c05822e059b149999280f643c931c93",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ru": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "637bcb827e7136c76e862d8886278bd21cbbd70c0a6505ffe0a6c73cb6c24552",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "sk": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "401408cbbfb987f0fbcbd6181f7f070aa0e3f9c115c1df28ce6354ab58915e96",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "sv": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "135d72d5a57824d133f7c8f5ca0b9e2e58ee513a0acf1fcf6f66cc6cac11006e",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "sw": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "63a088b6d32b2addb96e1e510a187edc972cf8b9294f3ad71f1e3847adeddb02",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ta": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "63bffe72fd0eb65fce078cc09bcead200f2e38d029a078115ef397169afec733",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "te": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "04ebc737b28ba81bf1b252a472487c82bf7de94c410b5a4f5c77ad532c6cdf37",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "th": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "bdd53c1414ae95838f703235bf1ee5771e68e41dc378f8678b504a7253670958",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "tr": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "8a229647130b154a6d9770c856b48e53f899b8969e3e95108c6934c7072163e2",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "uk-UA": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "0bd7fd100176830ec47180efb16fefe8745a12e51153db0c655bb04f9e1a80f6",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ur": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "8177e982ee7ffe08c8ab3d524aec2b81caf4501c39096808732e2f07a039acfa",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "vi": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "8c41701f327dcb76b08d25c03557a330ec4e833c0c0e5fcf057bd1e18075f6d0",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "zh-CN": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "cfb66f66a51113c1cb30f4cf975134bf500307988cb9a57913a3fb86d4188de2",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "zh-TW": {
-          "source_hash": "4633e157e0be272722eeeb1a2b16398b567b5e0de0e9934ec9be90bb466ff833",
+          "source_hash": "77187fa7a55f8e72092ee0910432be9768a44a67839b9130ff274a6be9963af1",
           "target_hash": "466da2a72e24a3e406c3eb4d92a953d90d63c263d34a025a159357b8a8219041",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         }
       }
     },
@@ -1162,11 +1137,6 @@
           "target_hash": "cbbd5c1a0f2da50d2515c4dee9f3a5d0da07205e7aa3c3c7e42f70b5c6e7ac0e",
           "updated_at": "2026-09-02T11:01:21.738Z"
         },
-        "in": {
-          "source_hash": "ed52d4c7fb85610c3f534535153b643ea645e588a747a7fffd729b16013f8e55",
-          "target_hash": "72161de6920f30a3203858c8a88b6199926486a9d3ab9f389e27e38daf1ecb04",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
         "it": {
           "source_hash": "ed52d4c7fb85610c3f534535153b643ea645e588a747a7fffd729b16013f8e55",
           "target_hash": "4da05ea0b2de8b38839ac2036194dd443412ad08c0ba4c5b073ab0efae326371",
@@ -1323,217 +1293,212 @@
       "locales": {}
     },
     "docs/architecture/ARCHITECTURE.md": {
-      "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+      "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
       "locales": {
         "ar": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "0cfbd1fea3750e71f525142a10866fe09674d87e02d24eed271c916be96b1c2a",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "az": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "f86e32631496b4e9d3535804938615ec290b58aa2a257c611bc60f83ec310a42",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "bg": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "f86e32631496b4e9d3535804938615ec290b58aa2a257c611bc60f83ec310a42",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "bn": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "1fc494a58105b828fa57b54898305c37a1c769b0cf1ac620648b1d9d8774f512",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "cs": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "aab2fc29c6eb88458192d6360a57ac0924d342716e0937de2305e5bd029e4440",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "da": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "647eeb115b911acf7ac841bf7e14fde1e48646d775066d41eaf459fd19d3f3bd",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "de": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "1ea1edd2be9ae6431614a0eb860c28c997558bfdee011b9a9286bf3b34bc24b1",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "es": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "7aba22fa4bd16e7355e1ffea7acbcc223e497c798d876ee4df8cad16be5a4b51",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "fa": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "775bbf5309759d0b7bb8e293419af4f3f3023cd597d7cb41cfee173fcf018c59",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "fi": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "19a1de7abad344d3591b24926812777ef46e97203e089bf8934e7e0bc39e9ffd",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "fr": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "b00c49b794056d59476d68d8fb24d903c5499eb26b912716c64bb5b24e30c820",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "gu": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "ee7d4703d1146b1c344a0fa7029c5202d603854d0f3599c6b5271de627e40fe7",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "he": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "4f5c40bb5958be33b391d9e7a6a07c78086dc19313bac5ee60015b00f1224064",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "hi": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "eab21ed3a2a34697f3f137a5cf660deb805b3b86afbd2d5d73040d056ed8aad2",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "hu": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "3b451387e92585d94a76735f36c08a654bbbb15243bbf1da9edb005a8afb10f3",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "id": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "597b0c0d5adcea6d5d5198f04172f609e92b9c4d378b6705e72a759e49460736",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
-        "in": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
-          "target_hash": "6917d5a91826cb170456e22353fc140232c677b004fd4117ae5bc5cd0413401f",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "it": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "acf07ddb7b62fea5edc4a06cc0ef01b6b6488fee556dfb6329650dd335e34b8c",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ja": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "ce7e286d1e09676e104b16c9878f411385642ffaa8e6a9b9abe7e6fdd1990317",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ko": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "4fcc81682a1e572b3e152108b9b2f2a561c95ad21d70cc8d2cec2f4b19803cb5",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "mr": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "3ff18982f4028348c8ea99b0b00985c79c883466d2e736c4c39f25f85722d7c6",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ms": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "f82e08173a1dd065507ea8add7a6fccf8e79844100fd1ddc4323aa4547dc7986",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "nl": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "495284071ffc4f46152eb2afef7573c1df1dfe94eaf2310ff2e21ee72066644e",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "no": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "0e632203b36d4bd87071ff7980f0ccaf6a296a1986c226bf1caa96d8aed06a25",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "phi": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "445bd8a270e1305f7d17a757708c1b1d148ba7c1e9d695aa31ad2e871e117448",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "pl": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "c8add808d2cc60054ba71553a3fc3a8e709ae1ac03594d4b4f8c0a6b5b4401de",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "pt": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "c540e3ff9356abcee4282e02a1a0bfbbe518a6c8fa4b1cc2a428f6395d5c5821",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "pt-BR": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "bcc603df8cbad9075a1236bd1d5f74b50fd7195d54fc7af482b463b5b932b9c9",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ro": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "a71726ae182c83b454815b97031200195167aeea65d2fcb7a918e06345078003",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ru": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "0c3ed3f8dddae83ba92a4ee453c41e50db03e30c0868dec8be315b4eddcff52a",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "sk": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "66e67d25cc408b164e69ba97100a30d4c17d7ba2c9433e6ae1e0fd7fa8b7206e",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "sv": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "2b286a17f682c6aae2238770057c2df320e244fa57280fdb527025c31272e4c4",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "sw": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "3ce45897f7962f78c4a51d73d83ab2246d9fb0e6bb1ed8f6dc3a7f22fd19b308",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ta": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "9ae8bab3190508b4301e4e117e14c6e1f964bc8bff6acf3a59b445114eb3f5a7",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "te": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "3d0373a997da8fd8c14f2f279b615a8afd9e26eaf22a76e8fecc1b39c098d85e",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "th": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "4b45a034ea84b35798e2d9821572e3342feb2c4f36538bb7d5e981c5f9fb056a",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "tr": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "d0b79bf4caf38f66f17f7c4ad1ad52b720fbd4f8c9c122999f796c44234d968a",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "uk-UA": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "e499e5944867b31c9d5b5e16ea6e07d0b45ad73f7d4e036a8c0ee2f5f5463c32",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ur": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "06235cfa89828f780557f8e5d831fb1d11db1705623292b3036c40dc9169796c",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "vi": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "99e484d482dce9587ef2b7dd4a9fd47fd81ea512bcae9e18269feeaabae31f74",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "zh-CN": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "c997489698ff8954d12f00d02752596c8a5ee241c1f0bd2618e80bfbb7afa9d9",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "zh-TW": {
-          "source_hash": "8611c0025cead1584f68e57abbdabe37f35b657565ca1d88e6d73e65a598a14e",
+          "source_hash": "b418138fc165ef6a64502b493daf231ba11e8ecbaf69bc786961e7366ec07c00",
           "target_hash": "01349e90326f3e5a5680305905102853969205104122f214771b0a84d817afc2",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         }
       }
     },
@@ -1630,11 +1595,6 @@
           "target_hash": "6c526522b5f87fc46528e7620556ad06bc85e2cdae239927017fceb1b98bbc85",
           "updated_at": "2026-09-02T11:01:21.738Z"
         },
-        "in": {
-          "source_hash": "29f14f650b4f66fc3eefbdbb066d18e7a83623c9e279589f5e6a578fbfffe8ae",
-          "target_hash": "c1a1996b984e480501a626d58e8b109e27336a44f4f38e19447d2ad6fd53b376",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
         "it": {
           "source_hash": "29f14f650b4f66fc3eefbdbb066d18e7a83623c9e279589f5e6a578fbfffe8ae",
           "target_hash": "ee40bab15c9cbf60ea6ba3a49ea2ac3d92fc4574d3dc70cf838c399dea5a42f7",
@@ -2009,11 +1969,6 @@
           "target_hash": "b83447d90fd0af3902da5525211b0b62805ffbc225b2618acdcdae8efbdfd2a6",
           "updated_at": "2026-09-02T11:01:21.738Z"
         },
-        "in": {
-          "source_hash": "9c132a2f85f7d809acfc51d38efc7f5c077ad83f3b162f68e0d470c2fcff74c1",
-          "target_hash": "8c851422bd686859c7a2a55dd1a65870fe734b65d836e4a7e48c2a60253c48a3",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
         "it": {
           "source_hash": "9c132a2f85f7d809acfc51d38efc7f5c077ad83f3b162f68e0d470c2fcff74c1",
           "target_hash": "9d264258729d74c592412f9c34c950a4a147defffda3d15a19f6574ea8a20633",
@@ -2318,11 +2273,6 @@
           "target_hash": "780b2eb8896b813b26abc1c541d2b05c8dbd0302571e9b754ce30c9297a4a2a7",
           "updated_at": "2026-09-02T11:01:21.738Z"
         },
-        "in": {
-          "source_hash": "4d20a05a10845f6a532b668760207006be46fa3061431e126c5365aca5df2eb1",
-          "target_hash": "8465a491e407d2b951ef1b2a0918886c2e3d5ed60d88d6d74b31f84e42922e30",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
         "it": {
           "source_hash": "4d20a05a10845f6a532b668760207006be46fa3061431e126c5365aca5df2eb1",
           "target_hash": "6a2719ab24facd38d9af047f1afb084483ccc10152a97ac812a1811fd036c92b",
@@ -2735,11 +2685,6 @@
           "target_hash": "a2c6a20b6f1afbe964db9828bc386c2ff3d5f6b2a208fdd397ab28c5f5199cb5",
           "updated_at": "2026-09-02T11:01:21.738Z"
         },
-        "in": {
-          "source_hash": "85cacfcda8bee9d01cd963afe2b492fea03db061ac4512b572ce9ec573e02aec",
-          "target_hash": "caa07cd129cc6adee9a6cdb1dd2d160265467cfa51ba7b0e22c285323968ff6d",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
         "it": {
           "source_hash": "85cacfcda8bee9d01cd963afe2b492fea03db061ac4512b572ce9ec573e02aec",
           "target_hash": "b82782fc40445ce11d68fc7e5cfec9bac88e310ef1021d0f21acd18357fe62b6",
@@ -2912,217 +2857,212 @@
       }
     },
     "docs/guides/FEATURES.md": {
-      "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+      "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
       "locales": {
         "ar": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "b283a3d54569c1a604829cb12a68fc19ff998435c62b71bf9bf5c27f15af4780",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "az": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "ae1839de16fc92e5d16da0603f1a59fc4d7f371ede01c479cd564e5f84fe514a",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "bg": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "ae1839de16fc92e5d16da0603f1a59fc4d7f371ede01c479cd564e5f84fe514a",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "bn": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "b469f360575a62b1e2dee266496811d1bde9335b2410c505cfd2cd53438a63ea",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "cs": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "2c4e04bc87b1eb599bed7e63703e596f4b67cdffa718f8b985b70c00eafb51b1",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "da": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "7fd4aa6a5c7198273e8113aef11abc0916970c0bf1b5a18b64e9771d5e6521bd",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "de": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "7d0c381be6745c682b6af19b1682c0f84bdb6f1b7cf70e599b465112ff8d34d0",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "es": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "2542e536c39a6f6aa273f4801812e327a40d2080da117c666518a42d2f44b22f",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "fa": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "858d775975cdf3fb74936bcd6c024d4cc023f9706ce0fbafeef3a61de63d49bb",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "fi": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "117a7d9fcd5b2e8b79fb740d9f7a4545df6d883be4eee66e59e18b446aeeca66",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "fr": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "024de74e164df8f4c22fcc6104c95b84253c66b1eaadcfd4f0a0460094eeee4c",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "gu": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "0b5a3df19009b5a77396315b6a5e423bb4b0ebda4724bda605d1d47039a08153",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "he": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "86f0222930ff6b86c4c46b289224273d6f6d452f5e158caa64a2e78d078a2c6d",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "hi": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "73127a62eefd9f20f976bb91cacc0c5c811a9bf1d65df703b6b308fdf51d13a0",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "hu": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "80f0f444730334434171411e78abb24426a32397b754add6ec55796979171c67",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "id": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "3510a707c18a0b9154dd8075c0aa8bad4805cbe4eff72a579450662b43d1714b",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
-        "in": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
-          "target_hash": "bf94ce8c70e0c9997ce4d107b977940086a9664130135fd9159a85a13094e0a9",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "it": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "c39ab119eb2ff3fa9f820e88373269d7069a4ff7916133e274de50377f48689b",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ja": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "325c600e8ca585fca46d5d132d61b5d20871800ea479887aebad6d226f0cdaf5",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ko": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "d2b9759606a23c8c237904919d1f4d755ce003a4d9cd8aa40117a6202c6d33ce",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "mr": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "c5f418ce6cde4600a0eb00cfa2c1f6211d83d8b59563860f729810cb6f9d9960",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ms": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "57aea387eb1f30e8d1d06a5be34bbeba8d4e230bb79e66ef26186f18141495dc",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "nl": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "fb398ed235d0cd326728594bd6f903388cdc5e7b54c231fa194bff6c3970af2b",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "no": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "114f0adbd019e0bb4151432b5c9187cf3cd7e00e77df92a37e9a7b9c6f9f41ee",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "phi": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "f5bb5a02865f5360cb68462758e3a0d5339107795702fb6d44051cc6239e683e",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "pl": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "96f523f724e0b94c6b999d4ce40fd9ca7585312a7ddc25e2b3f634fb5ddf35d0",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "pt": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "b688cfa63b73481fc9f25a9f096c204378b717e05b07638d82bcfb7a386dee4d",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "pt-BR": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "2403fdd40cd03907884716e54c83262a359b32045dc8f7be0da48e36b072b4a2",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ro": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "106ce9378b169abf7097540bcff0721ed34ce7b09361c7e8aa4e811bd420506c",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ru": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "7823b2e72c982b589003461c6f1ad29ce55a321b6f3a89014b6e2c970d2fb134",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "sk": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "a91ed63da016ff4fdd0a11f2b3a14aefed09c3f6b1d4cc3478a69ba1f96545e0",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "sv": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "0b4d74cfd011330aeac559c8f89f3870689a876fcbe7f2bac1ad4cb2c18b7828",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "sw": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "c3a4e481a016a55c32acef6e1a0330b55172e7195fba4d7db2dbb6683db7c206",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ta": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "0ca744dcb1d18444637df0a1e456ae798a5a743c6fe5d1163fad8c6da3b47d83",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "te": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "c8923facb687b657356adb1b9a912adfa0bbfbe17901500362b42665f3900593",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "th": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "c9d830ffe985cf9455024027d7ed87de4c3d7c0fa76190d26c557aae2301e1cc",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "tr": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "ba4c3e8f685b11cd69bde527530986af309f4302943e4d13af3093a616ce47dc",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "uk-UA": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "3fb55165687ce0f2791198854e7249807a25a66b1e96b37aa3a317d8f33f0d2d",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ur": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "25951bd3e5222a831d2e471eb2db0a41413712d4499dad592cd3d4cb9ee5d5a5",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "vi": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "a4293cfee8f06b52b771fd5b4c2b8084e7a450005b4f11f91fdd9d95473d4a41",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "zh-CN": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "830628346bc1c7e58769b1423fcef53f8d6515945a8011c7e148c80a3d0688a4",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "zh-TW": {
-          "source_hash": "3c820ef38a0487bcc7403b5d5a2fd6ae206526c8c499be48b95214b995d700e9",
+          "source_hash": "d51436ba886e4f55e51a7b1ab4e7d75eb0c66d17a0b74a658ead2b5d06afe431",
           "target_hash": "3afbd2094f2c390787df5fac4e965d2c4da748e15922380ed1190830c7fb787f",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         }
       }
     },
@@ -3205,432 +3145,422 @@
       }
     },
     "docs/guides/TROUBLESHOOTING.md": {
-      "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+      "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
       "locales": {
         "ar": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "cd63ebbff34f6ff8c9d0e8407ad555d1e2242a010d23fe641bd0f2b86575cad8",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "az": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "162e599ebb2729540d34642b0a7b71b55f5968a4f72c0a87c4feb227f87773dd",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "bg": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "162e599ebb2729540d34642b0a7b71b55f5968a4f72c0a87c4feb227f87773dd",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "bn": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "2799dcb4673dbdd4f08f29e9343e7d7e5acd9d4b554fd588ccf5cb60de100b96",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "cs": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "c0ef491ead07edd7f58d452ed11ef51445586af9db1f9f265be2d603d1999fc4",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "da": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "854859eb845f4bb08ce8a530416e9a8604a3b3653a6d3d3cc89668919d4e5f2a",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "de": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "76acc11790e7d9b5512ef0d7aa0a60c4ec4abe61967e87460ffb6e8754dee971",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "es": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "d998f8261a1b537a24537eb8cfdc6cf07791c515846be5c02e85b56143a9e8d9",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "fa": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "a37a638af2b9a3840db05b3dbd206795f52fe130ad8065da22d7e92f8d06fec9",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "fi": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "7dff830011dc7993a6700efbd1093c4c89da8f1fe0f7503c8390ddfe112cb8cf",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "fr": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "527525f0e524f256fd5792f3df1a2e2c964b16603912bb09e4cfca4343cc2d71",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "gu": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "d8d844ec797de9cdd4ee04beab9abe4fbdf383a328a774f36721619bd499061f",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "he": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "33fe8a1f5970deeb3e100f43b6716f6c76e3580d8370805b6df4ff209fd047b5",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "hi": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "eb69611cc6cf84551fc8e997c6c93ca33ec621584d08e4d225aa5a2a5c90a798",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "hu": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "e3883e5900df533e0462743ce7f275609732dd0a39e94cddfe369eded6362bd0",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "id": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "946195befb51226e3cc575e6d1978be46c04db83da803e851fbfb70e68eceb1a",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
-        "in": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
-          "target_hash": "9c04734e6a07fca0f2fc60a6f901ccfc02b429ec314e31d6428a90a455fcbc8f",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "it": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "f2151ed4f958b67d9f8b88c8247f488bafa8f7fca57b1c65c821e6b21650d9c2",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ja": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "3acdb7f2a5440091ede2e51241a4ff77b006d9e7d24fd3c3703cf49afc68b4d6",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ko": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "3f23630aafe958f2b9fa86d88d6784ece8dddd5d3e1b7aba6335f19ac885e571",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "mr": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "eb90367568472cdce262d6dacc91c8a8930cc7b4839b8799dea6134f0714aefd",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ms": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "dfda1f8cde1f2273959a7e0a0db4166731aae3e0e7629175a5cda24c21405e79",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "nl": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "7e111a6c208987b8d67e160035c19f9bfa544c359fdffa5931373e3132c968ab",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "no": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "af49c588460a15825bff4d26fe5041f380fe8a44f79d63d15fa0a6fe6915b29d",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "phi": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "da40dec35591edd9765a3ee064b1c1e5fcec8c21b6738561f1294bc2dc0af429",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "pl": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "4472ee0264652acc5d08092e980fa5f1b590acd7cb90da44b48ed26f53ddb389",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "pt": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "35ac60ea23125e760a458b5420ae00ddb7964ca8723445b010441208c24df113",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "pt-BR": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "bcc44b406844dba04a2c8f1bef86a019b5bbee762b1362ce9541d38041babdcf",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ro": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "9d561a4e1ebb176adad2a546145df93a1a649bda8347a1f5409c848b59a203a3",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ru": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "a29965b6124a2666c3abda27d086cb416e83b28f2effa90e26883ca6c64c46ec",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "sk": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "79f688e33331ec86656e6ba8de9e449c8d6f1dec8e701f0681fa4d09ac4ade7a",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "sv": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "73769cdd2515d62ea78628ad8c8e9327f911579bbb4edb2371a786a2c369e963",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "sw": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "1a18503179a3c32d28056b00463bbabc71a6fe8277d5f0366f5554f5fbd22e9c",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ta": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "7b7f93d45a01341557b5d3e2019851b5573ccd5fef6b6c95c9d6d91b3ada91eb",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "te": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "032c7ab51dcc9c04543b020b3cdb759d3678c553806e36da065d44f5e6e446fc",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "th": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "11378db94a95b213ec6097dabbfae1589472aeea689dfc649f6b5d598ec0b4ca",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "tr": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "3548313567c72abddf0174c2bef6d372c18950a6b8aa4e47cc331101a0017746",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "uk-UA": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "64749b508bf9b75c9bffe1c1fcd06f9813cec77e5cc052d26fb378d069373d33",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ur": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "b473afeae5777cf528c9d11e195547f64d0c424459a3c54c45428421c4b7072b",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "vi": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "880529729a832547fcd81d3f12928fc581dd0f5299e46b60a7a0f23e4d931bf3",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "zh-CN": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "4ac9812eac62174d46fe58ab00518dabc18ce4ca8c49d5b9c3dc9583d26f851b",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "zh-TW": {
-          "source_hash": "9815fc9e88ef5527676db77e2de48edc9035c29a9e6172e77ebbee12243bb7e6",
+          "source_hash": "990f27b7d545603732cdb9698ffa89888d96a1b567c2911757e25047226ea6b2",
           "target_hash": "c36e832f0353baea90c59c6e0b7531dcb38385b24a2ef2837195e635af325e58",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         }
       }
     },
     "docs/guides/UNINSTALL.md": {
-      "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+      "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
       "locales": {
         "ar": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "533e76fad7b0800289af6c76d1c2adb772fd4f9432bb48aa2153a82a34835776",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "az": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "6237e19130ce92659fbf599f6dfb6f2aa5531bcf6e85c5abd9555ca405a23421",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "bg": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "6237e19130ce92659fbf599f6dfb6f2aa5531bcf6e85c5abd9555ca405a23421",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "bn": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "b17eb4facb66e2d65335593770c069d9d29d38c686ebe9fb851bf9a33d1e07be",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "cs": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "5b1572a21c1473bfe054b1b7ce7c5b2318e720c8c826e9861cc7e14412018ab5",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "da": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "d0e2d57582c306ddaa0010a1d144279b651a52abb1cb1f92ebabeb68588486dc",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "de": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "31e84d078d98aad29639162ce3125271f8e81e790812a85e464f85fdd034cd65",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "es": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "34b6802bd6ff09eb2d2d9e7da15e9a8a2d42d27976f63b5f92fdf5c04b93d7f8",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "fa": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "6465b2c48b7af9ed2ecb6d7c3a67167f7b143632db7cdef5004912e0a9763d8a",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "fi": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "82e345fec7270dddb3df48a2388e3afd0b771e4117e167c813796fcfdd9b22e4",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "fr": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "49ecb0b82000f77d638ff9c6e95bd1e2bef87db5fffecf417ea428d39adb297c",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "gu": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "7cdde8d3435d94d72d4e3757cb276c96726993db176671e93a3d06ce9bf3c700",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "he": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "d18b2d622ce33f31a0d131e70dc0ce7f8854062ff48daecb1f6fa0b9db6cc122",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "hi": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "fca1972d3eba422f50971668d23af0f8166de450a263a735b3407dfb9bbf86a9",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "hu": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "c67abebc8a0e04ce9799a8452f678fe56f3f208fcd735744784fff3f068d9539",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "id": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "855352c41c74ed939128789c9e59f567b7c68b4732eab14b54d430c8df09917e",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
-        "in": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
-          "target_hash": "54c8bf68b1cd051d2647097071dbc6faa98b0f9567d6d1e23ac104f3ef279452",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "it": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "ae54fad38942943fd969647d13e87c332839b9b11891f05ca7754884637bd89d",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ja": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "7eeb47ad93be5cde03aa2981ddd44a023236d6fba35098281b95beb773c77c74",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ko": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "659c1ce618f69e7335205b54e5ad62c13e2189c344a399820e8fb0a78bd585be",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "mr": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "143a06952b573001f686285da893e9333c44eb664541a002de5c13c3982d4894",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ms": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "90fcbe1b930ad3ea66addaffbfad58c15e65a9afa65d924a60a88502f6d9553f",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "nl": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "b98673ea5c178788c753c97c1b0d3d2a9be9b2f969652a9a52386330f04463a5",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "no": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "f83a8c7430e1a1e6fcd313c69d26bcc187c6026a618611bfa24d4074b22d33f9",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "phi": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "5cd6777a8e21981fd756c0763f2dab0def03718e130510a69aac503d7d326e19",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "pl": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "4ad19e6514a737bd3644ffa218d294c11419121de89c4a6b1ed05d1b5d5df103",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "pt": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "f83f7dcd4c54b25de06f1620db33bfe8397e44824dc6a3f77d8d4aa4b3685c01",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "pt-BR": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "b85ab2e132f8ce7cccd7861cea0bf4d4b4865557c589b8f97cad422765503c4b",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ro": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "fe8c884f6567bfc0cd8357e2661756563b308049713c74bc8db29b1c397bc411",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ru": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "55498c7aeaa1b8ddb1cc6a01acd3ce940bad9c256e41223d10669345bb1c5f17",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "sk": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "b04d7ecc3dcd81637c82fdfcc9f701e12378212d28e66e21343f76348a4d2e9b",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "sv": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "ad1f91d30a9fb31d15fc43fc4896821e4555f46f1155740543cd4bdbcd24a122",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "sw": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "c40dac1e2dd620c65d3d218164b8bcf4949fcc3b2287f6e5076e2b43d9457f75",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ta": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "0a181084a4040e97ec236c4a0ebdca0adba648a1a9a7ffb77a05cc2f08967467",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "te": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "c67a3c0e73569b3ad82f7ce08c0a6ce676658b76732b2fdab3c0f70fe3a91ec6",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "th": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "ce3030d4466f7a757ae15a91de0cfc13637946e3bc1f0ad51c0af368e0d04a9c",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "tr": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "717b22c979cf3e1028347bcf75265a6d089f081698df0a73f9e57d5bba8ebf0e",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "uk-UA": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "e1cc1bf557bc6b6ae8644930c678dacc2d9ca8dc8568bd2062e61dba94d149ee",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ur": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "848159250e8a6777c9e5501fc12e6c9350894cd2ccafbf1ec2b3102fab1dd6b9",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "vi": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "3f1961623f47afc943cd3b44ce2309e812442f12e9c3ceddfde8d007ec2dd537",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "zh-CN": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "0597a8ba5278ed3ff4cf3e4b297d67a2816aa656adee8174ad3bd26e7c50343c",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "zh-TW": {
-          "source_hash": "3240ff45e973c2942c52d785d1280c913144f3c51250315dbb6ffb55396c8688",
+          "source_hash": "55d7877b0738737abb74045bbcbacf47e9d24f1da97ca6beb44f903e2446fc4a",
           "target_hash": "5a83a5ff8edee5c816290e368a25b55747467a7ed81926d1d0a6f9223f8ecf34",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         }
       }
     },
@@ -3645,217 +3575,212 @@
       }
     },
     "docs/guides/USER_GUIDE.md": {
-      "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+      "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
       "locales": {
         "ar": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "254ce5eba5d9784c8d897730a8a2ab39b3bf54fdb1bba72b898f840e395ff546",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "az": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "b64cff9a43d7515f2ca4906341166c31fe26b56ea6398312c501979c846b13e6",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "bg": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "b64cff9a43d7515f2ca4906341166c31fe26b56ea6398312c501979c846b13e6",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "bn": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "5fe3ed4eee3164665731b3531e7312b298275ff2394a87e3b2ab48af00b61bfd",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "cs": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "5212a526f383adec41e0be38f66b95737eefaf3879f0ef2e6620a37faa2e252f",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "da": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "e810d77dd8fdc8ab0469c7024fc0ed58dbaace22635c34b14f111e91a8e874d2",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "de": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "b993d430ed739303fbe5cb35a165676b2be6f3e40652cdf9ab28029c1f209924",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "es": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "b84ae0ef252fce1769108a7623db0603bea3c0b0c435ca6f24ad04da82eafea9",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "fa": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "f2cb8502618a3220517abefc0868123ceb8f25ab8523c737599e39243e1d8d62",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "fi": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "ead988ae0dace91fcb2e2a219fd1ab3567980b8d58648b1869dd21b6732e675c",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "fr": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "9b5a54c3719921e12896dd47b321a80def5eca62aba42d6f6532530541bccf21",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "gu": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "7d70cd633717441edd9d59a6a158fdeb68832806b3791391d5bf184b5e08d1ac",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "he": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "33b047de5992fbc197fca407836e21c64c8459b8eae0a2ac9b07c747473b521e",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "hi": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "c824e70e0a83276cc08b2cdfce0bfa856524b7ab06381dc9ed050bd0b4805649",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "hu": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "4f94ffaa25ed5ac976222ae6e1546ff675161e5a2570bceb905b4518f6218a96",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "id": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "dd3f478d07ad79ed15b3ebe174b32d59fc5128236a34dc4bfbed92784b013533",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
-        "in": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
-          "target_hash": "7eb9711a660e6d7fb7b6063c86891f3f775f26bf18899be30181823f35a8f7e2",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "it": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "aa3746c25b0b4a91bff93481a69764d286394ed43c6435a2038c6d4d34ac7f01",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "ja": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "cdb76ed73ae6e1fd63e7f728514cbe468a31901083b3f6c6aea6764f6ef10d0b",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "ko": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "303020c68925860ee3321f4a7f75ee6108f8fe8eff45cc3860c72b120f698df0",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "mr": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "80ece9482feeae4e7855d06157ccbabdf7601ba5b3d881e573468d8d22cf83c9",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "ms": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "488209c33ebec03272cbc622938b5ea7f10744d1a078a4e4039b53bb6fdb2464",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "nl": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "27b043b0928ce5ad13dcb7e46ac8919284aab5cbd00e6b92df25d79b7e0e9c30",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "no": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "b936e6d03688974078c1b1255726b0e719ef07a72375e13a54727c8f0f2a4260",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "phi": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "74088a4acfadb0152a20de7ee1a47ddb79dbe475ff110cc5fc5944982375c7a7",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "pl": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "02704e4ac2af540f821b62cd16fbdafb8aeb6feb4adb88dbd6a8028decc381f6",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "pt": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "7fd3a4ecd0bb16edc6c8d581fbe73925aea94d4ca4d834e36edd869fb615c61c",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "pt-BR": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "f40fc62ef765c59ecca511d5b52dcfe46ae8045b47bf356143e0458d5702c7c8",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "ro": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "2aca23fb79d6f2674cd67709a3f3df3680101eb3b167621d3bceb9c3ec4ad978",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "ru": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "9d5f3f7782eefb0ab78f379e586704ca4fb19a501ab65fd88beb4291bc0bf463",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "sk": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "5d408832cd604a29d255288c57a8e420f94f43bdd5baaa69d337b39efce57b22",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "sv": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "e3a0f0b3feba73b5043c2f4f0933842de4bde9b32aeef7c7b7a5a341602d3c5d",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "sw": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "fc8cd551fa55452ebf2d3d49dd81d40693e3d0c788393260d80f62bece9f66a6",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "ta": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "41b933d8e3ea0dd6d026cea4fa1e87333fbe4f4c007dd3e4fac8c538b9e85a77",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "te": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "17c4967ad296456ee69cd7d8919d009d0e7949859980f5da3b7639774824efdf",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "th": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "221441ad70dbe7b9acf74518bb8ce6efd3659fe8ace8163a638869531d9d2828",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "tr": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "325dd7a884b824776944fbd30b9d2e9a6025c1d686de3e1f18b662e2189c9a3d",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "uk-UA": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "2539e02b5fd4d9d125afe9eb8bbcbba0711ef8b728f4faac3be166930d127198",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "ur": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "52a4fff40119c16ba76b9ce84ae0e05dbb40ef7182b04c1ce0f9bb72f4eb2ac2",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "vi": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "d99a67134383bfe60ac2decefb48f36562ceb583e202e2a3f02f53f050e090d0",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "zh-CN": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "1ff4fc148d73109abaacfa14211a65e3a58d6eb095d9b02f43e6614a59810029",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         },
         "zh-TW": {
-          "source_hash": "150bce942c3c4c23c17b1ccff642ec4d280e9f2c813889573ab48823d51f3df4",
+          "source_hash": "e5da1e16ede84577bcfd8a3c53a9167d8393415a1112cf72dc51f9c5c07a615c",
           "target_hash": "89f9feb3ea3ed42f2583dfa6c12a6c082bb4642065fc528a6a920e2f95e94c76",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:42:16.251Z"
         }
       }
     },
@@ -3970,11 +3895,6 @@
           "target_hash": "99752fe20a3e0e8d2d3de2d103640ef3612eb2e39ba52a576cf0bdb1e066d421",
           "updated_at": "2026-09-02T11:01:21.738Z"
         },
-        "in": {
-          "source_hash": "c4baff7b3acbf3851df536092938b2d75b15c1ea374a7a8d55b8a7d08f72f775",
-          "target_hash": "54c8be148667928c4827ca717d9de6fecbacebbba85f3ecd3e3b041c7190bcc4",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
         "it": {
           "source_hash": "c4baff7b3acbf3851df536092938b2d75b15c1ea374a7a8d55b8a7d08f72f775",
           "target_hash": "76d67f20d0ca095ce11c432d4c26e1b8269b0b3149cbc2154cb601f6f7814aaf",
@@ -4195,11 +4115,6 @@
           "target_hash": "caa96783e7ae66cb5c599a36fa852d77aefcdb0ac476d712a6bd5ac4e4c953bb",
           "updated_at": "2026-09-02T11:01:21.738Z"
         },
-        "in": {
-          "source_hash": "bea4a7166194e8ed25e75d91deb2cff7f6e370abad1265258b60ffdcb193980a",
-          "target_hash": "69dcba555bbc007645c508cddd204226d2774a1d56a51601327cbd2e43ef720b",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
         "it": {
           "source_hash": "bea4a7166194e8ed25e75d91deb2cff7f6e370abad1265258b60ffdcb193980a",
           "target_hash": "e8adf925fccea4c39c8241a7ab34293d389cfb813a316fb91578cc6bef25b204",
@@ -4464,11 +4379,6 @@
           "target_hash": "5f6fa1cb1f13e7fd3730f5b6dde273caf9bed78e07c9ab042211ed1f3ac64b01",
           "updated_at": "2026-09-02T11:01:21.738Z"
         },
-        "in": {
-          "source_hash": "906dd95c14121b25af569be5c79a498e061155d2d7a13869389d89b04d3dc576",
-          "target_hash": "7b634a36e2ea7ac5e5f61a2f9af5d4a0b430a99647ace758ac760d7b6f43e40d",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
         "it": {
           "source_hash": "906dd95c14121b25af569be5c79a498e061155d2d7a13869389d89b04d3dc576",
           "target_hash": "17296ccc2b94f2e203686dbbf9555d02a9b65ee8f8acb3cfe8b204247478aca9",
@@ -4637,217 +4547,212 @@
       }
     },
     "docs/ops/VM_DEPLOYMENT_GUIDE.md": {
-      "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+      "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
       "locales": {
         "ar": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "50efd1e5eb8f5003cd561ac3dd3a0071135a0c5e1ad630a4a67741fae91b6cf2",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "az": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "3321019a925915c8d9440ad63726f305dcdcf26360fcdcb11376b9f1632b5d58",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "bg": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "3321019a925915c8d9440ad63726f305dcdcf26360fcdcb11376b9f1632b5d58",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "bn": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "7ba98ee3ee278776357ebe63521acb8c8748e1983af61cbf36a01482edde08a0",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "cs": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "e03c9ea6e51a72fef428543128f3e780c46488ba072325577ec68d98a064d158",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "da": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "4187a04ac1eaa67d92e60f44206d23eab7db89779fab4c8b4d3db0747f2141bb",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "de": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "30165270f35d7dad745aaaf10cc0c48682f862ea65f0629afeb7c60e0468876e",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "es": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "9e68617f43926335a03f0d90cd8a093f82e58ba80e719b470977183321e4383c",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "fa": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "30953855f06e79ab9c7fb7ad0a84a2adf36405db57a020ecb4f6577654ca52fa",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "fi": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "7a7acf3b0f6690ee950f576d01216172de05aeb3b76cc4808833598b667914b5",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "fr": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "1910219f2bc7881e826c405d851ab79b59c3ca245ef31025ef9271dce9476ed9",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "gu": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "9230c02ad8cc386ecf172173f8e4d8764706765243d23b6032a31f4fd59f77ca",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "he": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "1df917532d2bc26ad1ac86afef5b3dd0873597d830370995d73a7db07aa1271a",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "hi": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "b00ae64827d1385987379a0c9a6085b56209ff7d40efaedd7230dc3fdaaa85f5",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "hu": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "e66a80ec63ae2302a22be801d2db83c4ddec6517d79b58bc40306a42a9721a52",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "id": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "2fa7cd75d745283a4f03b62e7ddf373c42eedff667c682581db369e08553d5b5",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
-        "in": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
-          "target_hash": "3d4419193fa2108b04c1a18d5cbc3b45a8064002190a0f0bd717b9f1e677b1c9",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "it": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "689abb32a2ce2dd5060f1ce0f7d32b034588f9a5e0f95818afc6397c2e24e6a0",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ja": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "6dbf5b41d6ca0a15c4cbc46966b78173d250f0176fb86e14ad66f1045dc4524a",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ko": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "f98d958506034999adefcff2bcc93f4d1cea285be46182a4b9f8798575cb6782",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "mr": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "bdaaacd338d117b07968434a2855bb859c413fb081e655765ea9d071c7318b35",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ms": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "117a893cd3a5ff7765a79bb31bd0f3a8f9180ea1b23ea50e0b4e2403b045b068",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "nl": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "768c4624679ab09ecd18830c882be7f7b9168cb29c0f927edea1fa22c4adf53b",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "no": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "82aeb8add471466be7fd1de74ad3a24d88d5fe148e70bb050dc5121ce213dd5d",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "phi": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "a933ba9d50cb3c376dd62672a699f448b723033c2483514def26e982c69a2329",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "pl": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "e6ff41641fe9b0d6f03ffd286ab461aca403231273ff2d2c696957cdcfa2a916",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "pt": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "ac964ed34d69a6c51bc3070b0f45c776404d0aa0bc868fdde5cb6ad16c55c481",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "pt-BR": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "913f3d4b7673037873e7b8508143e161eac431f4578ce571c98f4f4249029317",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ro": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "4ab4a9e672f083255e1f52b6437aeda2fe208052d71a280db1813ce62021c556",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ru": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "096216973f4786c375a714f216ada2f8b108d13ffa256bf331acfa064bdf51cb",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "sk": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "357afbfabbf0169412ba602e3e499d3e22c2b207f6da20e04339701cc9753f85",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "sv": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "f4f80afcb532024f8b5f30e303fa1bd01d454d16fc4f1bd9c863a6ea16e53ce7",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "sw": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "fb3dc0a9e346deea794c860f69690133173496d9034463d77a0d79675b12cba5",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ta": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "7027a66abd3ad51fd3b8ccd9054b17efbbb8a918592f3c129c8ce0d7b0abec3a",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "te": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "ca301864817cfc52de94a705773a5a049d79d3c8f07daf4cb92255fcf5752712",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "th": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "7ffa59b9ee81c1fb7ed8c93ce7a17c1ad6ffb656bffafff92bfa2c073b5ed9c0",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "tr": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "14968c6ceda31753761b06276cfe9356ab239b3ee5918c97308a6c68853bca26",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "uk-UA": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "9d664dc00134d096ed0bfb04517db6b24836bfa96a5861b98d6c01991ff0737a",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ur": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "842a75b6e038838aac5600a4fc87e48377fe33a4242e04a4c5915d9cee79676d",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "vi": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "58405ff98c013f354a0129dbd6b7d49b437601f4d8797b563b95f936a37f12a9",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "zh-CN": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "a570dde7e1a031335cd831f965de82e20c94c95349af6760345bd0a778433bbc",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "zh-TW": {
-          "source_hash": "2280dfeec85191eaca8fb1720dd2d8f745d9837ee1928de62eb95e8825e9e6d9",
+          "source_hash": "fd936983bfbb83c64337d61dcbb4da19deebc9ae2299b86f4d40ac659297923f",
           "target_hash": "d771e7f5ca85aa87eaae3ccfc456bc6afd4cb72301bf45eb6cc654226952e451",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         }
       }
     },
@@ -4916,217 +4821,212 @@
       }
     },
     "docs/reference/API_REFERENCE.md": {
-      "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+      "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
       "locales": {
         "ar": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "96c69cdcd76aaed70025a03a790439d19aec5d5f095894962c53b95fb01bf416",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "az": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "0fec809db87f28d9d247b57d152b85af8cf770bf473ab9a59038c018dc4294fc",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "bg": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "0fec809db87f28d9d247b57d152b85af8cf770bf473ab9a59038c018dc4294fc",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "bn": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "529a9dbb1753edd1ad66cd45d9f3ed48c9493e15ee5b0a109ee5e602bcf46f20",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "cs": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "2750315741b485c950d7da802c81cbcd1082fd6a0862f81e2b3ff4cca0d76087",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "da": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "4fb1bc2e884ea9dcc164efe99a13f3de9ad7e76121817541af8e2d79d4c8752d",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "de": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "70978a5a11ae5654eab0656f3a5b3a25f814a1e71f107f810adf9b85e84734f1",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "es": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "34f2150e1bdbcffdc6e97082c28ca8c346f9c294d4bd7940e7c0b14aa3d0f361",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "fa": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "032ea8a05f4b50f7710bebf8cd51ea058af53147dcf7c819d6a073b95e966839",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "fi": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "511efaea0972e6e7a3c169371d1d0ca3d8513dee6b68c944ec86744cb806a0c6",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "fr": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "7d16e0bb336fdead0ac48b44729d7353458f10cf10a7d0b4488623b33843f535",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "gu": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "7c5a1f44597c6a2de8a8687d417f76b0864df6f8b8d34b29ae49eca628bf1e38",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "he": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "93f03acd2ab17530fa085c78b33ee2ecf025fd1ea4cdc9a9abcba9dabc0e27ca",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "hi": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "299982c9c5c556f5586ab4305bf739c5a67b68714f2a0746ded41dbfba430f19",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "hu": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "8fe358a29ea38dd7e37e11ca00a8d1f33a851a55ce3a1626c9e8123ccedf12f3",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "id": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "d38e4225a6cf15e80b75df3f3255645edef5b5ae44c3b33835b3dff899e86493",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
-        "in": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
-          "target_hash": "bbbe677505070c450dddf4ddf453046acb59ffa4c01f87d50f921500c720ee7a",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "it": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "61e4321962e3609e9285ec530aa062180eb282d9266b133facdc1ab04a2dcb2a",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ja": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "3bd7ffe1fbc2d77c4d4a6bd37403fe81c95293c2ea37c9992f4ac449b210d6f9",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ko": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "bb9975982b04b0e82944f12123553ec9ed7a9c82768fcecb25982e9ba276d26a",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "mr": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "3d23e32f09e781a23adfa65f5ef02f1bb992e7a1846a9c4f8f310a648f2618e0",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ms": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "15f899061a04f51288944fc82a898dfde10c189138da3aad6eeb68790eccfd58",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "nl": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "d3a33c7ee6d071839fd143cf940fd5b447eb2a4265ec3d057f4937cb6b034303",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "no": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "5e2ba35dd0a7f5b382f8c3113c38f63177189d8ed5eda02f4a664146c7b64b1d",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "phi": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "0b4cd106f1886d8b26076b17bd5d46c995b21f906e5e003a74510e52621e3fb7",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "pl": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "c8711fcee0dec1dc4e0b8ea39fb31686e4ec7a7f24797801b477d503c8a42c3d",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "pt": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "a45c803d0ab44206da89703831d497ad50612fcb89bc71c702234f623f79b0c7",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "pt-BR": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "80dde36e73b0368efcf29c58e5c5a866ee108bd99e62a2f8aaa233d874711769",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ro": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "a10b27182e3f10fbf9897653eab230ffa55acd50cf575d1c983a27d1e4ed4d59",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ru": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "c5ca6b0c33c132e723a7fac6e586bbbcc2361d749655a6cc2d2528209a961784",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "sk": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "cfa290211905b1e6dfb5288edd24a82ccae30e7e14f8c64da15a0b30f431a76c",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "sv": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "dde1b65fff47f3b65f1a808f34c96a3c56b885f5a08ccfc5b7a24c9bc47a5a23",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "sw": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "f96073f4573b36cc5da6e440add6d006515079bdec40116037132c58e69de916",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ta": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "d5741ace4e4fb2bb6eebd62b23cada1fbd4df3a26c84a268b791c6f205169515",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "te": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "baf9854bc449bdbc8d8bd06a332783c09ce482b91c8df6375ae3310e2bc49378",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "th": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "531da2f0f4b72e2646871224b84bd590d235070648900c4b375686c1592653c3",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "tr": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "3141aee891ada4e3da6258fe790cb9081a21ab304fde1cc940af9c828400f815",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "uk-UA": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "a00daeeffe16e958c84211e9dcb6d4684264cca8bd45a46499a3a5793384a7fd",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "ur": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "e616b7d14e34fc5bddb9654accbc4cdf93862912f88d966744b2aa3bdd0feadc",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "vi": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "e579ee9554d5f02af881b0f58808e0d6749d00815ad54efbc3a5342b920ffee1",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "zh-CN": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "2b6fd009471b11be33039358410a8400b2547f363cd71caf363ee7320266ee4b",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         },
         "zh-TW": {
-          "source_hash": "d712f0d0dcbf99b7b220268c1ed7ef55e2966c58108ab3ebf1935edbf125628d",
+          "source_hash": "2fd67048d12bba5bcbda8ab468fc57fef0878de98b197ea140910d4a4d54c10a",
           "target_hash": "ef3e17d436d443792e3ca35f475ad813c891cab385ba7521f61d14e9a38e8b0e",
-          "updated_at": "2026-09-02T11:01:21.738Z"
+          "updated_at": "2026-09-02T13:38:28.854Z"
         }
       }
     },
@@ -5213,11 +5113,6 @@
           "target_hash": "d70c3ceaef12480a49342ee34007654a29c8d9e703bee143d0141646cf92661f",
           "updated_at": "2026-09-02T11:01:21.738Z"
         },
-        "in": {
-          "source_hash": "b34753a696f448a27f8fe356fca6ec99bb89082df5211a43952b6f28540e1820",
-          "target_hash": "28d1c92aef2d7ca036e4d1b0d64d426d600ddf4419f62ad6ee0d4d518a5539b5",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
         "it": {
           "source_hash": "b34753a696f448a27f8fe356fca6ec99bb89082df5211a43952b6f28540e1820",
           "target_hash": "43a201ab84c38957a1e8d94dc85ac48e4628697d71d8af747c1864b5b32475b2",
@@ -5432,11 +5327,6 @@
           "target_hash": "0beb58920ffc3d43fd4cb486a6c5a3bb4fc08bf9e467a748a20e073375d71fca",
           "updated_at": "2026-09-02T11:01:21.738Z"
         },
-        "in": {
-          "source_hash": "41231186c0ad37eb1b8fd9ae04b09ce10e62fc232918cedd3f538b563cab6ea3",
-          "target_hash": "6803119249c62a01daea932b4caa3edca6b0d2fab39ce111a219f9a4355b7e4d",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
         "it": {
           "source_hash": "41231186c0ad37eb1b8fd9ae04b09ce10e62fc232918cedd3f538b563cab6ea3",
           "target_hash": "47e7c37b41dc2b969ea99600997833ab277ab7d244670d225b957365f5f4793e",
@@ -5670,11 +5560,6 @@
           "target_hash": "2d06645ec326f7caa665307df071e01f8545637ad9f005db736d6e916a282370",
           "updated_at": "2026-09-02T11:01:21.738Z"
         },
-        "in": {
-          "source_hash": "2a04dfd84a25c5d9464555ee6c2fd539454ab00f477d8f926d595c625b6c04b5",
-          "target_hash": "81971d30ad1f07880a5372ac6cbc7c1adae1739a19dca738f3cab6e3fd4ae84f",
-          "updated_at": "2026-09-02T11:01:21.738Z"
-        },
         "it": {
           "source_hash": "2a04dfd84a25c5d9464555ee6c2fd539454ab00f477d8f926d595c625b6c04b5",
           "target_hash": "3a6d9397fc2c03066684c0972ec5c2487ae0b8e49cd0791c23b39dcc71856082",
diff --git a/README.md b/README.md
index 8fe723c816..63c57a6dc5 100644
--- a/README.md
+++ b/README.md
@@ -133,7 +133,7 @@
 </div>
 
 <div align="center">
-  <b>🌐 In 43 languages</b>
+  <b>🌐 In 42 languages</b>
   <br/><br/>
   <a href="README.md"><img src="docs/assets/flags/us.svg" width="30" alt="English (en)" title="English (en)"></a>
   <a href="docs/i18n/pt-BR/README.md"><img src="docs/assets/flags/br.svg" width="30" alt="Português — Brasil (pt-BR)" title="Português — Brasil (pt-BR)"></a>
@@ -164,7 +164,6 @@
   <a href="docs/i18n/id/README.md"><img src="docs/assets/flags/id.svg" width="30" alt="Bahasa Indonesia (id)" title="Bahasa Indonesia (id)"></a>
   <a href="docs/i18n/ms/README.md"><img src="docs/assets/flags/my.svg" width="30" alt="Bahasa Melayu (ms)" title="Bahasa Melayu (ms)"></a>
   <a href="docs/i18n/phi/README.md"><img src="docs/assets/flags/ph.svg" width="30" alt="Filipino (phi)" title="Filipino (phi)"></a>
-  <a href="docs/i18n/in/README.md"><img src="docs/assets/flags/in.svg" width="30" alt="हिन्दी (in)" title="हिन्दी (in)"></a>
   <a href="docs/i18n/hi/README.md"><img src="docs/assets/flags/in.svg" width="30" alt="हिन्दी (hi)" title="हिन्दी (hi)"></a>
   <a href="docs/i18n/gu/README.md"><img src="docs/assets/flags/in.svg" width="30" alt="ગુજરાતી (gu)" title="ગુજરાતી (gu)"></a>
   <a href="docs/i18n/mr/README.md"><img src="docs/assets/flags/in.svg" width="30" alt="मराठी (mr)" title="मराठी (mr)"></a>
diff --git a/bin/cli/locales/in.json b/bin/cli/locales/in.json
deleted file mode 100644
index fe79d60fd0..0000000000
--- a/bin/cli/locales/in.json
+++ /dev/null
@@ -1,5 +0,0 @@
-{
-  "redis": {
-    "description": "Luncurkan kontainer Redis lokal dengan satu klik (Podman atau Docker) untuk caching dan pelacakan kuota OmniRoute"
-  }
-}
diff --git a/bin/cli/scripts/generate-locales.mjs b/bin/cli/scripts/generate-locales.mjs
index 0da62a4618..00e1d10b37 100644
--- a/bin/cli/scripts/generate-locales.mjs
+++ b/bin/cli/scripts/generate-locales.mjs
@@ -890,7 +890,7 @@ const TRANSLATIONS = {
 
 // Languages with no translation in this script — will be created as empty objects
 // All keys fall back to `en` via i18n.mjs's fallback mechanism.
-const SCAFFOLD_ONLY = ["bn", "gu", "he", "in", "mr", "ms", "phi", "sw", "ta", "te", "ur"];
+const SCAFFOLD_ONLY = ["bn", "gu", "he", "mr", "ms", "phi", "sw", "ta", "te", "ur"];
 
 let created = 0;
 let skipped = 0;
diff --git a/config/i18n.json b/config/i18n.json
index 941ea0577e..f96fea7eba 100644
--- a/config/i18n.json
+++ b/config/i18n.json
@@ -139,15 +139,8 @@
       "name": "Bahasa Indonesia",
       "native": "Bahasa Indonesia",
       "english": "Indonesian",
-      "flag": "🇮🇩"
-    },
-    {
-      "code": "in",
-      "label": "IN",
-      "name": "Bahasa Indonesia (Alt)",
-      "native": "Bahasa Indonesia (Alt)",
-      "english": "Indonesian (Legacy)",
-      "flag": "🇮🇩"
+      "flag": "🇮🇩",
+      "aliases": ["in"]
     },
     {
       "code": "it",
diff --git a/config/quality/i18n-translation-baseline.json b/config/quality/i18n-translation-baseline.json
index 4d69932369..af889f10df 100644
--- a/config/quality/i18n-translation-baseline.json
+++ b/config/quality/i18n-translation-baseline.json
@@ -18,7 +18,6 @@
     "hi": 25.8,
     "hu": 27.1,
     "id": 27.2,
-    "in": 45.1,
     "it": 27,
     "ja": 25.6,
     "ko": 26.9,
diff --git a/docs/README.md b/docs/README.md
index 6e531b9828..da1b32355f 100644
--- a/docs/README.md
+++ b/docs/README.md
@@ -203,7 +203,7 @@ Mermaid sources and exported SVG/PNG diagrams referenced from the docs above. Se
 
 ## i18n/
 
-Translated mirrors of the documentation in 42 locales (plus the English originals — 43 languages in total). See [i18n/README.md](i18n/README.md) for the supported language list.
+Translated mirrors of the documentation in 41 locales (plus the English originals — 42 languages in total). See [i18n/README.md](i18n/README.md) for the supported language list.
 
 ## screenshots/
 
diff --git a/docs/architecture/ARCHITECTURE.md b/docs/architecture/ARCHITECTURE.md
index 4aefc1a06a..6841f375b2 100644
--- a/docs/architecture/ARCHITECTURE.md
+++ b/docs/architecture/ARCHITECTURE.md
@@ -6,7 +6,7 @@ lastUpdated: 2026-06-28
 
 # OmniRoute Architecture
 
-🌐 **Languages:** 🇺🇸 [English](./ARCHITECTURE.md) | 🇧🇷 [Português (Brasil)](../i18n/pt-BR/docs/architecture/ARCHITECTURE.md) | 🇪🇸 [Español](../i18n/es/docs/architecture/ARCHITECTURE.md) | 🇫🇷 [Français](../i18n/fr/docs/architecture/ARCHITECTURE.md) | 🇮🇹 [Italiano](../i18n/it/docs/architecture/ARCHITECTURE.md) | 🇷🇺 [Русский](../i18n/ru/docs/architecture/ARCHITECTURE.md) | 🇨🇳 [中文 (简体)](../i18n/zh-CN/docs/architecture/ARCHITECTURE.md) | 🇩🇪 [Deutsch](../i18n/de/docs/architecture/ARCHITECTURE.md) | 🇮🇳 [हिन्दी](../i18n/in/docs/architecture/ARCHITECTURE.md) | 🇹🇭 [ไทย](../i18n/th/docs/architecture/ARCHITECTURE.md) | 🇺🇦 [Українська](../i18n/uk-UA/docs/architecture/ARCHITECTURE.md) | 🇸🇦 [العربية](../i18n/ar/docs/architecture/ARCHITECTURE.md) | 🇯🇵 [日本語](../i18n/ja/docs/architecture/ARCHITECTURE.md) | 🇻🇳 [Tiếng Việt](../i18n/vi/docs/architecture/ARCHITECTURE.md) | 🇧🇬 [Български](../i18n/bg/docs/architecture/ARCHITECTURE.md) | 🇩🇰 [Dansk](../i18n/da/docs/architecture/ARCHITECTURE.md) | 🇫🇮 [Suomi](../i18n/fi/docs/architecture/ARCHITECTURE.md) | 🇮🇱 [עברית](../i18n/he/docs/architecture/ARCHITECTURE.md) | 🇭🇺 [Magyar](../i18n/hu/docs/architecture/ARCHITECTURE.md) | 🇮🇩 [Bahasa Indonesia](../i18n/id/docs/architecture/ARCHITECTURE.md) | 🇰🇷 [한국어](../i18n/ko/docs/architecture/ARCHITECTURE.md) | 🇲🇾 [Bahasa Melayu](../i18n/ms/docs/architecture/ARCHITECTURE.md) | 🇳🇱 [Nederlands](../i18n/nl/docs/architecture/ARCHITECTURE.md) | 🇳🇴 [Norsk](../i18n/no/docs/architecture/ARCHITECTURE.md) | 🇵🇹 [Português (Portugal)](../i18n/pt/docs/architecture/ARCHITECTURE.md) | 🇷🇴 [Română](../i18n/ro/docs/architecture/ARCHITECTURE.md) | 🇵🇱 [Polski](../i18n/pl/docs/architecture/ARCHITECTURE.md) | 🇸🇰 [Slovenčina](../i18n/sk/docs/architecture/ARCHITECTURE.md) | 🇸🇪 [Svenska](../i18n/sv/docs/architecture/ARCHITECTURE.md) | 🇵🇭 [Filipino](../i18n/phi/docs/architecture/ARCHITECTURE.md) | 🇨🇿 [Čeština](../i18n/cs/docs/architecture/ARCHITECTURE.md)
+🌐 **Languages:** 🇺🇸 [English](./ARCHITECTURE.md) | 🇧🇷 [Português (Brasil)](../i18n/pt-BR/docs/architecture/ARCHITECTURE.md) | 🇪🇸 [Español](../i18n/es/docs/architecture/ARCHITECTURE.md) | 🇫🇷 [Français](../i18n/fr/docs/architecture/ARCHITECTURE.md) | 🇮🇹 [Italiano](../i18n/it/docs/architecture/ARCHITECTURE.md) | 🇷🇺 [Русский](../i18n/ru/docs/architecture/ARCHITECTURE.md) | 🇨🇳 [中文 (简体)](../i18n/zh-CN/docs/architecture/ARCHITECTURE.md) | 🇩🇪 [Deutsch](../i18n/de/docs/architecture/ARCHITECTURE.md) | 🇹🇭 [ไทย](../i18n/th/docs/architecture/ARCHITECTURE.md) | 🇺🇦 [Українська](../i18n/uk-UA/docs/architecture/ARCHITECTURE.md) | 🇸🇦 [العربية](../i18n/ar/docs/architecture/ARCHITECTURE.md) | 🇯🇵 [日本語](../i18n/ja/docs/architecture/ARCHITECTURE.md) | 🇻🇳 [Tiếng Việt](../i18n/vi/docs/architecture/ARCHITECTURE.md) | 🇧🇬 [Български](../i18n/bg/docs/architecture/ARCHITECTURE.md) | 🇩🇰 [Dansk](../i18n/da/docs/architecture/ARCHITECTURE.md) | 🇫🇮 [Suomi](../i18n/fi/docs/architecture/ARCHITECTURE.md) | 🇮🇱 [עברית](../i18n/he/docs/architecture/ARCHITECTURE.md) | 🇭🇺 [Magyar](../i18n/hu/docs/architecture/ARCHITECTURE.md) | 🇮🇩 [Bahasa Indonesia](../i18n/id/docs/architecture/ARCHITECTURE.md) | 🇰🇷 [한국어](../i18n/ko/docs/architecture/ARCHITECTURE.md) | 🇲🇾 [Bahasa Melayu](../i18n/ms/docs/architecture/ARCHITECTURE.md) | 🇳🇱 [Nederlands](../i18n/nl/docs/architecture/ARCHITECTURE.md) | 🇳🇴 [Norsk](../i18n/no/docs/architecture/ARCHITECTURE.md) | 🇵🇹 [Português (Portugal)](../i18n/pt/docs/architecture/ARCHITECTURE.md) | 🇷🇴 [Română](../i18n/ro/docs/architecture/ARCHITECTURE.md) | 🇵🇱 [Polski](../i18n/pl/docs/architecture/ARCHITECTURE.md) | 🇸🇰 [Slovenčina](../i18n/sk/docs/architecture/ARCHITECTURE.md) | 🇸🇪 [Svenska](../i18n/sv/docs/architecture/ARCHITECTURE.md) | 🇵🇭 [Filipino](../i18n/phi/docs/architecture/ARCHITECTURE.md) | 🇨🇿 [Čeština](../i18n/cs/docs/architecture/ARCHITECTURE.md)
 
 _Last updated: 2026-06-28_
 
diff --git a/docs/diagrams/exported/i18n-flow.svg b/docs/diagrams/exported/i18n-flow.svg
index 95031ef4a4..bbca60b0c1 100644
--- a/docs/diagrams/exported/i18n-flow.svg
+++ b/docs/diagrams/exported/i18n-flow.svg
@@ -1 +1 @@
-<svg id="my-svg" width="100%" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" class="flowchart" style="max-width: 2218px; background-color: white;" viewBox="0 0 2218 288.19140625" role="graphics-document document" aria-roledescription="flowchart-v2"><style>#my-svg{font-family:"trebuchet ms",verdana,arial,sans-serif;font-size:16px;fill:#333;}@keyframes edge-animation-frame{from{stroke-dashoffset:0;}}@keyframes dash{to{stroke-dashoffset:0;}}#my-svg .edge-animation-slow{stroke-dasharray:9,5!important;stroke-dashoffset:900;animation:dash 50s linear infinite;stroke-linecap:round;}#my-svg .edge-animation-fast{stroke-dasharray:9,5!important;stroke-dashoffset:900;animation:dash 20s linear infinite;stroke-linecap:round;}#my-svg .error-icon{fill:#552222;}#my-svg .error-text{fill:#552222;stroke:#552222;}#my-svg .edge-thickness-normal{stroke-width:1px;}#my-svg .edge-thickness-thick{stroke-width:3.5px;}#my-svg .edge-pattern-solid{stroke-dasharray:0;}#my-svg .edge-thickness-invisible{stroke-width:0;fill:none;}#my-svg .edge-pattern-dashed{stroke-dasharray:3;}#my-svg .edge-pattern-dotted{stroke-dasharray:2;}#my-svg .marker{fill:#333333;stroke:#333333;}#my-svg .marker.cross{stroke:#333333;}#my-svg svg{font-family:"trebuchet ms",verdana,arial,sans-serif;font-size:16px;}#my-svg p{margin:0;}#my-svg .label{font-family:"trebuchet ms",verdana,arial,sans-serif;color:#333;}#my-svg .cluster-label text{fill:#333;}#my-svg .cluster-label span{color:#333;}#my-svg .cluster-label span p{background-color:transparent;}#my-svg .label text,#my-svg span{fill:#333;color:#333;}#my-svg .node rect,#my-svg .node circle,#my-svg .node ellipse,#my-svg .node polygon,#my-svg .node path{fill:#ECECFF;stroke:#9370DB;stroke-width:1px;}#my-svg .rough-node .label text,#my-svg .node .label text,#my-svg .image-shape .label,#my-svg .icon-shape .label{text-anchor:middle;}#my-svg .node .katex path{fill:#000;stroke:#000;stroke-width:1px;}#my-svg .rough-node .label,#my-svg .node .label,#my-svg .image-shape .label,#my-svg .icon-shape .label{text-align:center;}#my-svg .node.clickable{cursor:pointer;}#my-svg .root .anchor path{fill:#333333!important;stroke-width:0;stroke:#333333;}#my-svg .arrowheadPath{fill:#333333;}#my-svg .edgePath .path{stroke:#333333;stroke-width:1px;}#my-svg .flowchart-link{stroke:#333333;fill:none;}#my-svg .edgeLabel{background-color:rgba(232,232,232, 0.8);text-align:center;}#my-svg .edgeLabel p{background-color:rgba(232,232,232, 0.8);}#my-svg .edgeLabel rect{opacity:0.5;background-color:rgba(232,232,232, 0.8);fill:rgba(232,232,232, 0.8);}#my-svg .labelBkg{background-color:rgba(232, 232, 232, 0.5);}#my-svg .cluster rect{fill:#ffffde;stroke:#aaaa33;stroke-width:1px;}#my-svg .cluster text{fill:#333;}#my-svg .cluster span{color:#333;}#my-svg div.mermaidTooltip{position:absolute;text-align:center;max-width:200px;padding:2px;font-family:"trebuchet ms",verdana,arial,sans-serif;font-size:12px;background:hsl(80, 100%, 96.2745098039%);border:1px solid #aaaa33;border-radius:2px;pointer-events:none;z-index:100;}#my-svg .flowchartTitleText{text-anchor:middle;font-size:18px;fill:#333;}#my-svg rect.text{fill:none;stroke-width:0;}#my-svg .icon-shape,#my-svg .image-shape{background-color:rgba(232,232,232, 0.8);text-align:center;}#my-svg .icon-shape p,#my-svg .image-shape p{background-color:rgba(232,232,232, 0.8);padding:2px;}#my-svg .icon-shape .label rect,#my-svg .image-shape .label rect{opacity:0.5;background-color:rgba(232,232,232, 0.8);fill:rgba(232,232,232, 0.8);}#my-svg .label-icon{display:inline-block;height:1em;overflow:visible;vertical-align:-0.125em;}#my-svg .node .label-icon path{fill:currentColor;stroke:revert;stroke-width:revert;}#my-svg .node .neo-node{stroke:#9370DB;}#my-svg [data-look="neo"].node rect,#my-svg [data-look="neo"].cluster rect,#my-svg [data-look="neo"].node polygon{stroke:#9370DB;filter:drop-shadow(1px 2px 2px rgba(185, 185, 185, 1));}#my-svg [data-look="neo"].node path{stroke:#9370DB;stroke-width:1px;}#my-svg [data-look="neo"].node .outer-path{filter:drop-shadow(1px 2px 2px rgba(185, 185, 185, 1));}#my-svg [data-look="neo"].node .neo-line path{stroke:#9370DB;filter:none;}#my-svg [data-look="neo"].node circle{stroke:#9370DB;filter:drop-shadow(1px 2px 2px rgba(185, 185, 185, 1));}#my-svg [data-look="neo"].node circle .state-start{fill:#000000;}#my-svg [data-look="neo"].icon-shape .icon{fill:#9370DB;filter:drop-shadow(1px 2px 2px rgba(185, 185, 185, 1));}#my-svg [data-look="neo"].icon-shape .icon-neo path{stroke:#9370DB;filter:drop-shadow(1px 2px 2px rgba(185, 185, 185, 1));}#my-svg :root{--mermaid-font-family:"trebuchet ms",verdana,arial,sans-serif;}</style><g><marker id="my-svg_flowchart-v2-pointEnd" class="marker flowchart-v2" viewBox="0 0 10 10" refX="5" refY="5" markerUnits="userSpaceOnUse" markerWidth="8" markerHeight="8" orient="auto"><path d="M 0 0 L 10 5 L 0 10 z" class="arrowMarkerPath" style="stroke-width: 1; stroke-dasharray: 1, 0;"/></marker><marker id="my-svg_flowchart-v2-pointStart" class="marker flowchart-v2" viewBox="0 0 10 10" refX="4.5" refY="5" markerUnits="userSpaceOnUse" markerWidth="8" markerHeight="8" orient="auto"><path d="M 0 5 L 10 10 L 10 0 z" class="arrowMarkerPath" style="stroke-width: 1; stroke-dasharray: 1, 0;"/></marker><marker id="my-svg_flowchart-v2-pointEnd-margin" class="marker flowchart-v2" viewBox="0 0 11.5 14" refX="11.5" refY="7" markerUnits="userSpaceOnUse" markerWidth="10.5" markerHeight="14" orient="auto"><path d="M 0 0 L 11.5 7 L 0 14 z" class="arrowMarkerPath" style="stroke-width: 0; stroke-dasharray: 1, 0;"/></marker><marker id="my-svg_flowchart-v2-pointStart-margin" class="marker flowchart-v2" viewBox="0 0 11.5 14" refX="1" refY="7" markerUnits="userSpaceOnUse" markerWidth="11.5" markerHeight="14" orient="auto"><polygon points="0,7 11.5,14 11.5,0" class="arrowMarkerPath" style="stroke-width: 0; stroke-dasharray: 1, 0;"/></marker><marker id="my-svg_flowchart-v2-circleEnd" class="marker flowchart-v2" viewBox="0 0 10 10" refX="11" refY="5" markerUnits="userSpaceOnUse" markerWidth="11" markerHeight="11" orient="auto"><circle cx="5" cy="5" r="5" class="arrowMarkerPath" style="stroke-width: 1; stroke-dasharray: 1, 0;"/></marker><marker id="my-svg_flowchart-v2-circleStart" class="marker flowchart-v2" viewBox="0 0 10 10" refX="-1" refY="5" markerUnits="userSpaceOnUse" markerWidth="11" markerHeight="11" orient="auto"><circle cx="5" cy="5" r="5" class="arrowMarkerPath" style="stroke-width: 1; stroke-dasharray: 1, 0;"/></marker><marker id="my-svg_flowchart-v2-circleEnd-margin" class="marker flowchart-v2" viewBox="0 0 10 10" refY="5" refX="12.25" markerUnits="userSpaceOnUse" markerWidth="14" markerHeight="14" orient="auto"><circle cx="5" cy="5" r="5" class="arrowMarkerPath" style="stroke-width: 0; stroke-dasharray: 1, 0;"/></marker><marker id="my-svg_flowchart-v2-circleStart-margin" class="marker flowchart-v2" viewBox="0 0 10 10" refX="-2" refY="5" markerUnits="userSpaceOnUse" markerWidth="14" markerHeight="14" orient="auto"><circle cx="5" cy="5" r="5" class="arrowMarkerPath" style="stroke-width: 0; stroke-dasharray: 1, 0;"/></marker><marker id="my-svg_flowchart-v2-crossEnd" class="marker cross flowchart-v2" viewBox="0 0 11 11" refX="12" refY="5.2" markerUnits="userSpaceOnUse" markerWidth="11" markerHeight="11" orient="auto"><path d="M 1,1 l 9,9 M 10,1 l -9,9" class="arrowMarkerPath" style="stroke-width: 2; stroke-dasharray: 1, 0;"/></marker><marker id="my-svg_flowchart-v2-crossStart" class="marker cross flowchart-v2" viewBox="0 0 11 11" refX="-1" refY="5.2" markerUnits="userSpaceOnUse" markerWidth="11" markerHeight="11" orient="auto"><path d="M 1,1 l 9,9 M 10,1 l -9,9" class="arrowMarkerPath" style="stroke-width: 2; stroke-dasharray: 1, 0;"/></marker><marker id="my-svg_flowchart-v2-crossEnd-margin" class="marker cross flowchart-v2" viewBox="0 0 15 15" refX="17.7" refY="7.5" markerUnits="userSpaceOnUse" markerWidth="12" markerHeight="12" orient="auto"><path d="M 1,1 L 14,14 M 1,14 L 14,1" class="arrowMarkerPath" style="stroke-width: 2.5;"/></marker><marker id="my-svg_flowchart-v2-crossStart-margin" class="marker cross flowchart-v2" viewBox="0 0 15 15" refX="-3.5" refY="7.5" markerUnits="userSpaceOnUse" markerWidth="12" markerHeight="12" orient="auto"><path d="M 1,1 L 14,14 M 1,14 L 14,1" class="arrowMarkerPath" style="stroke-width: 2.5; stroke-dasharray: 1, 0;"/></marker><g class="root"><g class="clusters"/><g class="edgePaths"><path d="M267.172,166.043L271.339,166.043C275.505,166.043,283.839,166.043,291.505,166.043C299.172,166.043,306.172,166.043,309.672,166.043L313.172,166.043" id="my-svg-L_Src_Hash_0" class="edge-thickness-normal edge-pattern-solid edge-thickness-normal edge-pattern-solid flowchart-link" style=";" data-edge="true" data-et="edge" data-id="L_Src_Hash_0" data-points="W3sieCI6MjY3LjE3MTg3NSwieSI6MTY2LjA0Mjk2ODc1fSx7IngiOjI5Mi4xNzE4NzUsInkiOjE2Ni4wNDI5Njg3NX0seyJ4IjozMTcuMTcxODc1LCJ5IjoxNjYuMDQyOTY4NzV9XQ==" data-look="classic" marker-end="url(#my-svg_flowchart-v2-pointEnd)"/><path d="M468.813,166.043L472.979,166.043C477.146,166.043,485.479,166.043,493.146,166.043C500.813,166.043,507.813,166.043,511.313,166.043L514.813,166.043" id="my-svg-L_Hash_State_0" class="edge-thickness-normal edge-pattern-solid edge-thickness-normal edge-pattern-solid flowchart-link" style=";" data-edge="true" data-et="edge" data-id="L_Hash_State_0" data-points="W3sieCI6NDY4LjgxMjUsInkiOjE2Ni4wNDI5Njg3NX0seyJ4Ijo0OTMuODEyNSwieSI6MTY2LjA0Mjk2ODc1fSx7IngiOjUxOC44MTI1LCJ5IjoxNjYuMDQyOTY4NzV9XQ==" data-look="classic" marker-end="url(#my-svg_flowchart-v2-pointEnd)"/><path d="M653.333,139.043L664.921,132.818C676.509,126.594,699.684,114.145,716.527,107.92C733.37,101.695,743.88,101.695,749.135,101.695L754.391,101.695" id="my-svg-L_State_Dirty_0" class="edge-thickness-normal edge-pattern-solid edge-thickness-normal edge-pattern-solid flowchart-link" style=";" data-edge="true" data-et="edge" data-id="L_State_Dirty_0" data-points="W3sieCI6NjUzLjMzMzI4ODI3ODU0NjcsInkiOjEzOS4wNDI5Njg3NX0seyJ4Ijo3MjIuODU5Mzc1LCJ5IjoxMDEuNjk1MzEyNX0seyJ4Ijo3NTguMzkwNjI1LCJ5IjoxMDEuNjk1MzEyNX1d" data-look="classic" marker-end="url(#my-svg_flowchart-v2-pointEnd)"/><path d="M941.094,101.695L945.26,101.695C949.427,101.695,957.76,101.695,965.427,101.695C973.094,101.695,980.094,101.695,983.594,101.695L987.094,101.695" id="my-svg-L_Dirty_Loop_0" class="edge-thickness-normal edge-pattern-solid edge-thickness-normal edge-pattern-solid flowchart-link" style=";" data-edge="true" data-et="edge" data-id="L_Dirty_Loop_0" data-points="W3sieCI6OTQxLjA5Mzc1LCJ5IjoxMDEuNjk1MzEyNX0seyJ4Ijo5NjYuMDkzNzUsInkiOjEwMS42OTUzMTI1fSx7IngiOjk5MS4wOTM3NSwieSI6MTAxLjY5NTMxMjV9XQ==" data-look="classic" marker-end="url(#my-svg_flowchart-v2-pointEnd)"/><path d="M1178.484,101.695L1182.651,101.695C1186.818,101.695,1195.151,101.695,1202.818,101.695C1210.484,101.695,1217.484,101.695,1220.984,101.695L1224.484,101.695" id="my-svg-L_Loop_LLM_0" class="edge-thickness-normal edge-pattern-solid edge-thickness-normal edge-pattern-solid flowchart-link" style=";" data-edge="true" data-et="edge" data-id="L_Loop_LLM_0" data-points="W3sieCI6MTE3OC40ODQzNzUsInkiOjEwMS42OTUzMTI1fSx7IngiOjEyMDMuNDg0Mzc1LCJ5IjoxMDEuNjk1MzEyNX0seyJ4IjoxMjI4LjQ4NDM3NSwieSI6MTAxLjY5NTMxMjV9XQ==" data-look="classic" marker-end="url(#my-svg_flowchart-v2-pointEnd)"/><path d="M1413,101.695L1417.167,101.695C1421.333,101.695,1429.667,101.695,1438.576,103.664C1447.486,105.633,1456.972,109.571,1461.715,111.54L1466.457,113.509" id="my-svg-L_LLM_Target_0" class="edge-thickness-normal edge-pattern-solid edge-thickness-normal edge-pattern-solid flowchart-link" style=";" data-edge="true" data-et="edge" data-id="L_LLM_Target_0" data-points="W3sieCI6MTQxMywieSI6MTAxLjY5NTMxMjV9LHsieCI6MTQzOCwieSI6MTAxLjY5NTMxMjV9LHsieCI6MTQ3MC4xNTE3MDI3ODYzNzc3LCJ5IjoxMTUuMDQyOTY4NzV9XQ==" data-look="classic" marker-end="url(#my-svg_flowchart-v2-pointEnd)"/><path d="M1470.152,217.043L1464.793,219.268C1459.434,221.492,1448.717,225.941,1423.816,228.166C1398.914,230.391,1359.828,230.391,1320.742,230.391C1281.656,230.391,1242.57,230.391,1203.245,230.391C1163.919,230.391,1124.354,230.391,1084.789,230.391C1045.224,230.391,1005.659,230.391,966.484,230.391C927.31,230.391,888.526,230.391,847.987,230.391C807.448,230.391,765.154,230.391,733.006,224.481C700.859,218.572,678.858,206.754,667.857,200.845L656.857,194.936" id="my-svg-L_Target_State_0" class="edge-thickness-normal edge-pattern-solid edge-thickness-normal edge-pattern-solid flowchart-link" style=";" data-edge="true" data-et="edge" data-id="L_Target_State_0" data-points="W3sieCI6MTQ3MC4xNTE3MDI3ODYzNzc3LCJ5IjoyMTcuMDQyOTY4NzV9LHsieCI6MTQzOCwieSI6MjMwLjM5MDYyNX0seyJ4IjoxMzIwLjc0MjE4NzUsInkiOjIzMC4zOTA2MjV9LHsieCI6MTIwMy40ODQzNzUsInkiOjIzMC4zOTA2MjV9LHsieCI6MTA4NC43ODkwNjI1LCJ5IjoyMzAuMzkwNjI1fSx7IngiOjk2Ni4wOTM3NSwieSI6MjMwLjM5MDYyNX0seyJ4Ijo4NDkuNzQyMTg3NSwieSI6MjMwLjM5MDYyNX0seyJ4Ijo3MjIuODU5Mzc1LCJ5IjoyMzAuMzkwNjI1fSx7IngiOjY1My4zMzMyODgyNzg1NDY3LCJ5IjoxOTMuMDQyOTY4NzV9XQ==" data-look="classic" marker-end="url(#my-svg_flowchart-v2-pointEnd)"/><path d="M1723,166.043L1727.167,166.043C1731.333,166.043,1739.667,166.043,1747.333,166.043C1755,166.043,1762,166.043,1765.5,166.043L1769,166.043" id="my-svg-L_Target_CI_0" class="edge-thickness-normal edge-pattern-solid edge-thickness-normal edge-pattern-solid flowchart-link" style=";" data-edge="true" data-et="edge" data-id="L_Target_CI_0" data-points="W3sieCI6MTcyMywieSI6MTY2LjA0Mjk2ODc1fSx7IngiOjE3NDgsInkiOjE2Ni4wNDI5Njg3NX0seyJ4IjoxNzczLCJ5IjoxNjYuMDQyOTY4NzV9XQ==" data-look="classic" marker-end="url(#my-svg_flowchart-v2-pointEnd)"/><path d="M1971.481,136.227L1984.766,131.529C1998.052,126.832,2024.624,117.438,2046.818,112.74C2069.013,108.043,2086.831,108.043,2095.74,108.043L2104.648,108.043" id="my-svg-L_CI_Pass_0" class="edge-thickness-normal edge-pattern-solid edge-thickness-normal edge-pattern-solid flowchart-link" style=";" data-edge="true" data-et="edge" data-id="L_CI_Pass_0" data-points="W3sieCI6MTk3MS40ODA2MDU5MTI2NzM0LCJ5IjoxMzYuMjI2Njk5NjYyNjczMjd9LHsieCI6MjA1MS4xOTUzMTI1LCJ5IjoxMDguMDQyOTY4NzV9LHsieCI6MjEwOC42NDg0Mzc1LCJ5IjoxMDguMDQyOTY4NzV9XQ==" data-look="classic" marker-end="url(#my-svg_flowchart-v2-pointEnd)"/><path d="M1971.481,195.859L1984.766,200.557C1998.052,205.254,2024.624,214.648,2045.559,219.346C2066.495,224.043,2081.794,224.043,2089.444,224.043L2097.094,224.043" id="my-svg-L_CI_Fail_0" class="edge-thickness-normal edge-pattern-solid edge-thickness-normal edge-pattern-solid flowchart-link" style=";" data-edge="true" data-et="edge" data-id="L_CI_Fail_0" data-points="W3sieCI6MTk3MS40ODA2MDU5MTI2NzM0LCJ5IjoxOTUuODU5MjM3ODM3MzI2NzN9LHsieCI6MjA1MS4xOTUzMTI1LCJ5IjoyMjQuMDQyOTY4NzV9LHsieCI6MjEwMS4wOTM3NSwieSI6MjI0LjA0Mjk2ODc1fV0=" data-look="classic" marker-end="url(#my-svg_flowchart-v2-pointEnd)"/></g><g class="edgeLabels"><g class="edgeLabel"><g class="label" data-id="L_Src_Hash_0" transform="translate(0, 0)"><foreignObject width="0" height="0"><div xmlns="http://www.w3.org/1999/xhtml" class="labelBkg" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="edgeLabel"></span></div></foreignObject></g></g><g class="edgeLabel"><g class="label" data-id="L_Hash_State_0" transform="translate(0, 0)"><foreignObject width="0" height="0"><div xmlns="http://www.w3.org/1999/xhtml" class="labelBkg" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="edgeLabel"></span></div></foreignObject></g></g><g class="edgeLabel" transform="translate(722.859375, 101.6953125)"><g class="label" data-id="L_State_Dirty_0" transform="translate(-10.53125, -12)"><foreignObject width="21.0625" height="24"><div xmlns="http://www.w3.org/1999/xhtml" class="labelBkg" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="edgeLabel"><p>diff</p></span></div></foreignObject></g></g><g class="edgeLabel"><g class="label" data-id="L_Dirty_Loop_0" transform="translate(0, 0)"><foreignObject width="0" height="0"><div xmlns="http://www.w3.org/1999/xhtml" class="labelBkg" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="edgeLabel"></span></div></foreignObject></g></g><g class="edgeLabel"><g class="label" data-id="L_Loop_LLM_0" transform="translate(0, 0)"><foreignObject width="0" height="0"><div xmlns="http://www.w3.org/1999/xhtml" class="labelBkg" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="edgeLabel"></span></div></foreignObject></g></g><g class="edgeLabel"><g class="label" data-id="L_LLM_Target_0" transform="translate(0, 0)"><foreignObject width="0" height="0"><div xmlns="http://www.w3.org/1999/xhtml" class="labelBkg" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="edgeLabel"></span></div></foreignObject></g></g><g class="edgeLabel"><g class="label" data-id="L_Target_State_0" transform="translate(0, 0)"><foreignObject width="0" height="0"><div xmlns="http://www.w3.org/1999/xhtml" class="labelBkg" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="edgeLabel"></span></div></foreignObject></g></g><g class="edgeLabel"><g class="label" data-id="L_Target_CI_0" transform="translate(0, 0)"><foreignObject width="0" height="0"><div xmlns="http://www.w3.org/1999/xhtml" class="labelBkg" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="edgeLabel"></span></div></foreignObject></g></g><g class="edgeLabel" transform="translate(2051.1953125, 108.04296875)"><g class="label" data-id="L_CI_Pass_0" transform="translate(-24.8984375, -12)"><foreignObject width="49.796875" height="24"><div xmlns="http://www.w3.org/1999/xhtml" class="labelBkg" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="edgeLabel"><p>in sync</p></span></div></foreignObject></g></g><g class="edgeLabel" transform="translate(2051.1953125, 224.04296875)"><g class="label" data-id="L_CI_Fail_0" transform="translate(-13.3359375, -12)"><foreignObject width="26.671875" height="24"><div xmlns="http://www.w3.org/1999/xhtml" class="labelBkg" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="edgeLabel"><p>drift</p></span></div></foreignObject></g></g></g><g class="nodes"><g class="node default" id="my-svg-flowchart-Src-0" data-look="classic" transform="translate(137.5859375, 166.04296875)"><rect class="basic label-container" style="" x="-129.5859375" y="-39" width="259.171875" height="78"/><g class="label" style="" transform="translate(-99.5859375, -24)"><rect/><foreignObject width="199.171875" height="48"><div xmlns="http://www.w3.org/1999/xhtml" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="nodeLabel"><p>Source MDs<br />(CLAUDE.md, docs/**/*.md)</p></span></div></foreignObject></g></g><g class="node default" id="my-svg-flowchart-Hash-1" data-look="classic" transform="translate(392.9921875, 166.04296875)"><rect class="basic label-container" style="" x="-75.8203125" y="-27" width="151.640625" height="54"/><g class="label" style="" transform="translate(-45.8203125, -12)"><rect/><foreignObject width="91.640625" height="24"><div xmlns="http://www.w3.org/1999/xhtml" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="nodeLabel"><p>sha256 hash</p></span></div></foreignObject></g></g><g class="node default" id="my-svg-flowchart-State-3" data-look="classic" transform="translate(603.0703125, 166.04296875)"><rect class="basic label-container" style="" x="-84.2578125" y="-27" width="168.515625" height="54"/><g class="label" style="" transform="translate(-54.2578125, -12)"><rect/><foreignObject width="108.515625" height="24"><div xmlns="http://www.w3.org/1999/xhtml" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="nodeLabel"><p>.i18n-state.json</p></span></div></foreignObject></g></g><g class="node default" id="my-svg-flowchart-Dirty-5" data-look="classic" transform="translate(849.7421875, 101.6953125)"><rect class="basic label-container" style="" x="-91.3515625" y="-27" width="182.703125" height="54"/><g class="label" style="" transform="translate(-61.3515625, -12)"><rect/><foreignObject width="122.703125" height="24"><div xmlns="http://www.w3.org/1999/xhtml" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="nodeLabel"><p>Mark source dirty</p></span></div></foreignObject></g></g><g class="node default" id="my-svg-flowchart-Loop-7" data-look="classic" transform="translate(1084.7890625, 101.6953125)"><polygon points="93.6953125,0 187.390625,-93.6953125 93.6953125,-187.390625 0,-93.6953125" class="label-container" transform="translate(-93.1953125, 93.6953125)"/><g class="label" style="" transform="translate(-54.6953125, -24)"><rect/><foreignObject width="109.390625" height="48"><div xmlns="http://www.w3.org/1999/xhtml" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="nodeLabel"><p>For each locale<br />(43 langs)</p></span></div></foreignObject></g></g><g class="node default" id="my-svg-flowchart-LLM-9" data-look="classic" transform="translate(1320.7421875, 101.6953125)"><rect class="basic label-container" style="" x="-92.2578125" y="-51" width="184.515625" height="102"/><g class="label" style="" transform="translate(-62.2578125, -36)"><rect/><foreignObject width="124.515625" height="72"><div xmlns="http://www.w3.org/1999/xhtml" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="nodeLabel"><p>OmniRoute<br />/chat/completions<br />(cx/gpt-5.4-mini)</p></span></div></foreignObject></g></g><g class="node default" id="my-svg-flowchart-Target-11" data-look="classic" transform="translate(1593, 166.04296875)"><rect class="basic label-container" style="" x="-130" y="-51" width="260" height="102"/><g class="label" style="" transform="translate(-100, -36)"><rect/><foreignObject width="200" height="72"><div xmlns="http://www.w3.org/1999/xhtml" style="display: table; white-space: break-spaces; line-height: 1.5; max-width: 200px; text-align: center; width: 200px;"><span class="nodeLabel"><p>Write<br />docs/i18n/&lt;locale&gt;/&lt;rel-path&gt;.md</p></span></div></foreignObject></g></g><g class="node default" id="my-svg-flowchart-CI-15" data-look="classic" transform="translate(1887.1484375, 166.04296875)"><polygon points="114.1484375,0 228.296875,-114.1484375 114.1484375,-228.296875 0,-114.1484375" class="label-container" transform="translate(-113.6484375, 114.1484375)"/><g class="label" style="" transform="translate(-75.1484375, -24)"><rect/><foreignObject width="150.296875" height="48"><div xmlns="http://www.w3.org/1999/xhtml" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="nodeLabel"><p>CI drift check<br />(npm run i18n:check)</p></span></div></foreignObject></g></g><g class="node default" id="my-svg-flowchart-Pass-17" data-look="classic" transform="translate(2155.546875, 108.04296875)"><rect class="basic label-container" style="" x="-46.8984375" y="-27" width="93.796875" height="54"/><g class="label" style="" transform="translate(-16.8984375, -12)"><rect/><foreignObject width="33.796875" height="24"><div xmlns="http://www.w3.org/1999/xhtml" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="nodeLabel"><p>pass</p></span></div></foreignObject></g></g><g class="node default" id="my-svg-flowchart-Fail-19" data-look="classic" transform="translate(2155.546875, 224.04296875)"><rect class="basic label-container" style="" x="-54.453125" y="-39" width="108.90625" height="78"/><g class="label" style="" transform="translate(-24.453125, -24)"><rect/><foreignObject width="48.90625" height="48"><div xmlns="http://www.w3.org/1999/xhtml" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="nodeLabel"><p>fail<br />(exit 1)</p></span></div></foreignObject></g></g></g></g></g><defs><filter id="my-svg-drop-shadow" height="130%" width="130%"><feDropShadow dx="4" dy="4" stdDeviation="0" flood-opacity="0.06" flood-color="#000000"/></filter></defs><defs><filter id="my-svg-drop-shadow-small" height="150%" width="150%"><feDropShadow dx="2" dy="2" stdDeviation="0" flood-opacity="0.06" flood-color="#000000"/></filter></defs></svg>
\ No newline at end of file
+<svg id="my-svg" width="100%" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" class="flowchart" style="max-width: 2218px; background-color: white;" viewBox="0 0 2218 288.19140625" role="graphics-document document" aria-roledescription="flowchart-v2"><style>#my-svg{font-family:"trebuchet ms",verdana,arial,sans-serif;font-size:16px;fill:#333;}@keyframes edge-animation-frame{from{stroke-dashoffset:0;}}@keyframes dash{to{stroke-dashoffset:0;}}#my-svg .edge-animation-slow{stroke-dasharray:9,5!important;stroke-dashoffset:900;animation:dash 50s linear infinite;stroke-linecap:round;}#my-svg .edge-animation-fast{stroke-dasharray:9,5!important;stroke-dashoffset:900;animation:dash 20s linear infinite;stroke-linecap:round;}#my-svg .error-icon{fill:#552222;}#my-svg .error-text{fill:#552222;stroke:#552222;}#my-svg .edge-thickness-normal{stroke-width:1px;}#my-svg .edge-thickness-thick{stroke-width:3.5px;}#my-svg .edge-pattern-solid{stroke-dasharray:0;}#my-svg .edge-thickness-invisible{stroke-width:0;fill:none;}#my-svg .edge-pattern-dashed{stroke-dasharray:3;}#my-svg .edge-pattern-dotted{stroke-dasharray:2;}#my-svg .marker{fill:#333333;stroke:#333333;}#my-svg .marker.cross{stroke:#333333;}#my-svg svg{font-family:"trebuchet ms",verdana,arial,sans-serif;font-size:16px;}#my-svg p{margin:0;}#my-svg .label{font-family:"trebuchet ms",verdana,arial,sans-serif;color:#333;}#my-svg .cluster-label text{fill:#333;}#my-svg .cluster-label span{color:#333;}#my-svg .cluster-label span p{background-color:transparent;}#my-svg .label text,#my-svg span{fill:#333;color:#333;}#my-svg .node rect,#my-svg .node circle,#my-svg .node ellipse,#my-svg .node polygon,#my-svg .node path{fill:#ECECFF;stroke:#9370DB;stroke-width:1px;}#my-svg .rough-node .label text,#my-svg .node .label text,#my-svg .image-shape .label,#my-svg .icon-shape .label{text-anchor:middle;}#my-svg .node .katex path{fill:#000;stroke:#000;stroke-width:1px;}#my-svg .rough-node .label,#my-svg .node .label,#my-svg .image-shape .label,#my-svg .icon-shape .label{text-align:center;}#my-svg .node.clickable{cursor:pointer;}#my-svg .root .anchor path{fill:#333333!important;stroke-width:0;stroke:#333333;}#my-svg .arrowheadPath{fill:#333333;}#my-svg .edgePath .path{stroke:#333333;stroke-width:1px;}#my-svg .flowchart-link{stroke:#333333;fill:none;}#my-svg .edgeLabel{background-color:rgba(232,232,232, 0.8);text-align:center;}#my-svg .edgeLabel p{background-color:rgba(232,232,232, 0.8);}#my-svg .edgeLabel rect{opacity:0.5;background-color:rgba(232,232,232, 0.8);fill:rgba(232,232,232, 0.8);}#my-svg .labelBkg{background-color:rgba(232, 232, 232, 0.5);}#my-svg .cluster rect{fill:#ffffde;stroke:#aaaa33;stroke-width:1px;}#my-svg .cluster text{fill:#333;}#my-svg .cluster span{color:#333;}#my-svg div.mermaidTooltip{position:absolute;text-align:center;max-width:200px;padding:2px;font-family:"trebuchet ms",verdana,arial,sans-serif;font-size:12px;background:hsl(80, 100%, 96.2745098039%);border:1px solid #aaaa33;border-radius:2px;pointer-events:none;z-index:100;}#my-svg .flowchartTitleText{text-anchor:middle;font-size:18px;fill:#333;}#my-svg rect.text{fill:none;stroke-width:0;}#my-svg .icon-shape,#my-svg .image-shape{background-color:rgba(232,232,232, 0.8);text-align:center;}#my-svg .icon-shape p,#my-svg .image-shape p{background-color:rgba(232,232,232, 0.8);padding:2px;}#my-svg .icon-shape .label rect,#my-svg .image-shape .label rect{opacity:0.5;background-color:rgba(232,232,232, 0.8);fill:rgba(232,232,232, 0.8);}#my-svg .label-icon{display:inline-block;height:1em;overflow:visible;vertical-align:-0.125em;}#my-svg .node .label-icon path{fill:currentColor;stroke:revert;stroke-width:revert;}#my-svg .node .neo-node{stroke:#9370DB;}#my-svg [data-look="neo"].node rect,#my-svg [data-look="neo"].cluster rect,#my-svg [data-look="neo"].node polygon{stroke:#9370DB;filter:drop-shadow(1px 2px 2px rgba(185, 185, 185, 1));}#my-svg [data-look="neo"].node path{stroke:#9370DB;stroke-width:1px;}#my-svg [data-look="neo"].node .outer-path{filter:drop-shadow(1px 2px 2px rgba(185, 185, 185, 1));}#my-svg [data-look="neo"].node .neo-line path{stroke:#9370DB;filter:none;}#my-svg [data-look="neo"].node circle{stroke:#9370DB;filter:drop-shadow(1px 2px 2px rgba(185, 185, 185, 1));}#my-svg [data-look="neo"].node circle .state-start{fill:#000000;}#my-svg [data-look="neo"].icon-shape .icon{fill:#9370DB;filter:drop-shadow(1px 2px 2px rgba(185, 185, 185, 1));}#my-svg [data-look="neo"].icon-shape .icon-neo path{stroke:#9370DB;filter:drop-shadow(1px 2px 2px rgba(185, 185, 185, 1));}#my-svg :root{--mermaid-font-family:"trebuchet ms",verdana,arial,sans-serif;}</style><g><marker id="my-svg_flowchart-v2-pointEnd" class="marker flowchart-v2" viewBox="0 0 10 10" refX="5" refY="5" markerUnits="userSpaceOnUse" markerWidth="8" markerHeight="8" orient="auto"><path d="M 0 0 L 10 5 L 0 10 z" class="arrowMarkerPath" style="stroke-width: 1; stroke-dasharray: 1, 0;"/></marker><marker id="my-svg_flowchart-v2-pointStart" class="marker flowchart-v2" viewBox="0 0 10 10" refX="4.5" refY="5" markerUnits="userSpaceOnUse" markerWidth="8" markerHeight="8" orient="auto"><path d="M 0 5 L 10 10 L 10 0 z" class="arrowMarkerPath" style="stroke-width: 1; stroke-dasharray: 1, 0;"/></marker><marker id="my-svg_flowchart-v2-pointEnd-margin" class="marker flowchart-v2" viewBox="0 0 11.5 14" refX="11.5" refY="7" markerUnits="userSpaceOnUse" markerWidth="10.5" markerHeight="14" orient="auto"><path d="M 0 0 L 11.5 7 L 0 14 z" class="arrowMarkerPath" style="stroke-width: 0; stroke-dasharray: 1, 0;"/></marker><marker id="my-svg_flowchart-v2-pointStart-margin" class="marker flowchart-v2" viewBox="0 0 11.5 14" refX="1" refY="7" markerUnits="userSpaceOnUse" markerWidth="11.5" markerHeight="14" orient="auto"><polygon points="0,7 11.5,14 11.5,0" class="arrowMarkerPath" style="stroke-width: 0; stroke-dasharray: 1, 0;"/></marker><marker id="my-svg_flowchart-v2-circleEnd" class="marker flowchart-v2" viewBox="0 0 10 10" refX="11" refY="5" markerUnits="userSpaceOnUse" markerWidth="11" markerHeight="11" orient="auto"><circle cx="5" cy="5" r="5" class="arrowMarkerPath" style="stroke-width: 1; stroke-dasharray: 1, 0;"/></marker><marker id="my-svg_flowchart-v2-circleStart" class="marker flowchart-v2" viewBox="0 0 10 10" refX="-1" refY="5" markerUnits="userSpaceOnUse" markerWidth="11" markerHeight="11" orient="auto"><circle cx="5" cy="5" r="5" class="arrowMarkerPath" style="stroke-width: 1; stroke-dasharray: 1, 0;"/></marker><marker id="my-svg_flowchart-v2-circleEnd-margin" class="marker flowchart-v2" viewBox="0 0 10 10" refY="5" refX="12.25" markerUnits="userSpaceOnUse" markerWidth="14" markerHeight="14" orient="auto"><circle cx="5" cy="5" r="5" class="arrowMarkerPath" style="stroke-width: 0; stroke-dasharray: 1, 0;"/></marker><marker id="my-svg_flowchart-v2-circleStart-margin" class="marker flowchart-v2" viewBox="0 0 10 10" refX="-2" refY="5" markerUnits="userSpaceOnUse" markerWidth="14" markerHeight="14" orient="auto"><circle cx="5" cy="5" r="5" class="arrowMarkerPath" style="stroke-width: 0; stroke-dasharray: 1, 0;"/></marker><marker id="my-svg_flowchart-v2-crossEnd" class="marker cross flowchart-v2" viewBox="0 0 11 11" refX="12" refY="5.2" markerUnits="userSpaceOnUse" markerWidth="11" markerHeight="11" orient="auto"><path d="M 1,1 l 9,9 M 10,1 l -9,9" class="arrowMarkerPath" style="stroke-width: 2; stroke-dasharray: 1, 0;"/></marker><marker id="my-svg_flowchart-v2-crossStart" class="marker cross flowchart-v2" viewBox="0 0 11 11" refX="-1" refY="5.2" markerUnits="userSpaceOnUse" markerWidth="11" markerHeight="11" orient="auto"><path d="M 1,1 l 9,9 M 10,1 l -9,9" class="arrowMarkerPath" style="stroke-width: 2; stroke-dasharray: 1, 0;"/></marker><marker id="my-svg_flowchart-v2-crossEnd-margin" class="marker cross flowchart-v2" viewBox="0 0 15 15" refX="17.7" refY="7.5" markerUnits="userSpaceOnUse" markerWidth="12" markerHeight="12" orient="auto"><path d="M 1,1 L 14,14 M 1,14 L 14,1" class="arrowMarkerPath" style="stroke-width: 2.5;"/></marker><marker id="my-svg_flowchart-v2-crossStart-margin" class="marker cross flowchart-v2" viewBox="0 0 15 15" refX="-3.5" refY="7.5" markerUnits="userSpaceOnUse" markerWidth="12" markerHeight="12" orient="auto"><path d="M 1,1 L 14,14 M 1,14 L 14,1" class="arrowMarkerPath" style="stroke-width: 2.5; stroke-dasharray: 1, 0;"/></marker><g class="root"><g class="clusters"/><g class="edgePaths"><path d="M267.172,166.043L271.339,166.043C275.505,166.043,283.839,166.043,291.505,166.043C299.172,166.043,306.172,166.043,309.672,166.043L313.172,166.043" id="my-svg-L_Src_Hash_0" class="edge-thickness-normal edge-pattern-solid edge-thickness-normal edge-pattern-solid flowchart-link" style=";" data-edge="true" data-et="edge" data-id="L_Src_Hash_0" data-points="W3sieCI6MjY3LjE3MTg3NSwieSI6MTY2LjA0Mjk2ODc1fSx7IngiOjI5Mi4xNzE4NzUsInkiOjE2Ni4wNDI5Njg3NX0seyJ4IjozMTcuMTcxODc1LCJ5IjoxNjYuMDQyOTY4NzV9XQ==" data-look="classic" marker-end="url(#my-svg_flowchart-v2-pointEnd)"/><path d="M468.813,166.043L472.979,166.043C477.146,166.043,485.479,166.043,493.146,166.043C500.813,166.043,507.813,166.043,511.313,166.043L514.813,166.043" id="my-svg-L_Hash_State_0" class="edge-thickness-normal edge-pattern-solid edge-thickness-normal edge-pattern-solid flowchart-link" style=";" data-edge="true" data-et="edge" data-id="L_Hash_State_0" data-points="W3sieCI6NDY4LjgxMjUsInkiOjE2Ni4wNDI5Njg3NX0seyJ4Ijo0OTMuODEyNSwieSI6MTY2LjA0Mjk2ODc1fSx7IngiOjUxOC44MTI1LCJ5IjoxNjYuMDQyOTY4NzV9XQ==" data-look="classic" marker-end="url(#my-svg_flowchart-v2-pointEnd)"/><path d="M653.333,139.043L664.921,132.818C676.509,126.594,699.684,114.145,716.527,107.92C733.37,101.695,743.88,101.695,749.135,101.695L754.391,101.695" id="my-svg-L_State_Dirty_0" class="edge-thickness-normal edge-pattern-solid edge-thickness-normal edge-pattern-solid flowchart-link" style=";" data-edge="true" data-et="edge" data-id="L_State_Dirty_0" data-points="W3sieCI6NjUzLjMzMzI4ODI3ODU0NjcsInkiOjEzOS4wNDI5Njg3NX0seyJ4Ijo3MjIuODU5Mzc1LCJ5IjoxMDEuNjk1MzEyNX0seyJ4Ijo3NTguMzkwNjI1LCJ5IjoxMDEuNjk1MzEyNX1d" data-look="classic" marker-end="url(#my-svg_flowchart-v2-pointEnd)"/><path d="M941.094,101.695L945.26,101.695C949.427,101.695,957.76,101.695,965.427,101.695C973.094,101.695,980.094,101.695,983.594,101.695L987.094,101.695" id="my-svg-L_Dirty_Loop_0" class="edge-thickness-normal edge-pattern-solid edge-thickness-normal edge-pattern-solid flowchart-link" style=";" data-edge="true" data-et="edge" data-id="L_Dirty_Loop_0" data-points="W3sieCI6OTQxLjA5Mzc1LCJ5IjoxMDEuNjk1MzEyNX0seyJ4Ijo5NjYuMDkzNzUsInkiOjEwMS42OTUzMTI1fSx7IngiOjk5MS4wOTM3NSwieSI6MTAxLjY5NTMxMjV9XQ==" data-look="classic" marker-end="url(#my-svg_flowchart-v2-pointEnd)"/><path d="M1178.484,101.695L1182.651,101.695C1186.818,101.695,1195.151,101.695,1202.818,101.695C1210.484,101.695,1217.484,101.695,1220.984,101.695L1224.484,101.695" id="my-svg-L_Loop_LLM_0" class="edge-thickness-normal edge-pattern-solid edge-thickness-normal edge-pattern-solid flowchart-link" style=";" data-edge="true" data-et="edge" data-id="L_Loop_LLM_0" data-points="W3sieCI6MTE3OC40ODQzNzUsInkiOjEwMS42OTUzMTI1fSx7IngiOjEyMDMuNDg0Mzc1LCJ5IjoxMDEuNjk1MzEyNX0seyJ4IjoxMjI4LjQ4NDM3NSwieSI6MTAxLjY5NTMxMjV9XQ==" data-look="classic" marker-end="url(#my-svg_flowchart-v2-pointEnd)"/><path d="M1413,101.695L1417.167,101.695C1421.333,101.695,1429.667,101.695,1438.576,103.664C1447.486,105.633,1456.972,109.571,1461.715,111.54L1466.457,113.509" id="my-svg-L_LLM_Target_0" class="edge-thickness-normal edge-pattern-solid edge-thickness-normal edge-pattern-solid flowchart-link" style=";" data-edge="true" data-et="edge" data-id="L_LLM_Target_0" data-points="W3sieCI6MTQxMywieSI6MTAxLjY5NTMxMjV9LHsieCI6MTQzOCwieSI6MTAxLjY5NTMxMjV9LHsieCI6MTQ3MC4xNTE3MDI3ODYzNzc3LCJ5IjoxMTUuMDQyOTY4NzV9XQ==" data-look="classic" marker-end="url(#my-svg_flowchart-v2-pointEnd)"/><path d="M1470.152,217.043L1464.793,219.268C1459.434,221.492,1448.717,225.941,1423.816,228.166C1398.914,230.391,1359.828,230.391,1320.742,230.391C1281.656,230.391,1242.57,230.391,1203.245,230.391C1163.919,230.391,1124.354,230.391,1084.789,230.391C1045.224,230.391,1005.659,230.391,966.484,230.391C927.31,230.391,888.526,230.391,847.987,230.391C807.448,230.391,765.154,230.391,733.006,224.481C700.859,218.572,678.858,206.754,667.857,200.845L656.857,194.936" id="my-svg-L_Target_State_0" class="edge-thickness-normal edge-pattern-solid edge-thickness-normal edge-pattern-solid flowchart-link" style=";" data-edge="true" data-et="edge" data-id="L_Target_State_0" data-points="W3sieCI6MTQ3MC4xNTE3MDI3ODYzNzc3LCJ5IjoyMTcuMDQyOTY4NzV9LHsieCI6MTQzOCwieSI6MjMwLjM5MDYyNX0seyJ4IjoxMzIwLjc0MjE4NzUsInkiOjIzMC4zOTA2MjV9LHsieCI6MTIwMy40ODQzNzUsInkiOjIzMC4zOTA2MjV9LHsieCI6MTA4NC43ODkwNjI1LCJ5IjoyMzAuMzkwNjI1fSx7IngiOjk2Ni4wOTM3NSwieSI6MjMwLjM5MDYyNX0seyJ4Ijo4NDkuNzQyMTg3NSwieSI6MjMwLjM5MDYyNX0seyJ4Ijo3MjIuODU5Mzc1LCJ5IjoyMzAuMzkwNjI1fSx7IngiOjY1My4zMzMyODgyNzg1NDY3LCJ5IjoxOTMuMDQyOTY4NzV9XQ==" data-look="classic" marker-end="url(#my-svg_flowchart-v2-pointEnd)"/><path d="M1723,166.043L1727.167,166.043C1731.333,166.043,1739.667,166.043,1747.333,166.043C1755,166.043,1762,166.043,1765.5,166.043L1769,166.043" id="my-svg-L_Target_CI_0" class="edge-thickness-normal edge-pattern-solid edge-thickness-normal edge-pattern-solid flowchart-link" style=";" data-edge="true" data-et="edge" data-id="L_Target_CI_0" data-points="W3sieCI6MTcyMywieSI6MTY2LjA0Mjk2ODc1fSx7IngiOjE3NDgsInkiOjE2Ni4wNDI5Njg3NX0seyJ4IjoxNzczLCJ5IjoxNjYuMDQyOTY4NzV9XQ==" data-look="classic" marker-end="url(#my-svg_flowchart-v2-pointEnd)"/><path d="M1971.481,136.227L1984.766,131.529C1998.052,126.832,2024.624,117.438,2046.818,112.74C2069.013,108.043,2086.831,108.043,2095.74,108.043L2104.648,108.043" id="my-svg-L_CI_Pass_0" class="edge-thickness-normal edge-pattern-solid edge-thickness-normal edge-pattern-solid flowchart-link" style=";" data-edge="true" data-et="edge" data-id="L_CI_Pass_0" data-points="W3sieCI6MTk3MS40ODA2MDU5MTI2NzM0LCJ5IjoxMzYuMjI2Njk5NjYyNjczMjd9LHsieCI6MjA1MS4xOTUzMTI1LCJ5IjoxMDguMDQyOTY4NzV9LHsieCI6MjEwOC42NDg0Mzc1LCJ5IjoxMDguMDQyOTY4NzV9XQ==" data-look="classic" marker-end="url(#my-svg_flowchart-v2-pointEnd)"/><path d="M1971.481,195.859L1984.766,200.557C1998.052,205.254,2024.624,214.648,2045.559,219.346C2066.495,224.043,2081.794,224.043,2089.444,224.043L2097.094,224.043" id="my-svg-L_CI_Fail_0" class="edge-thickness-normal edge-pattern-solid edge-thickness-normal edge-pattern-solid flowchart-link" style=";" data-edge="true" data-et="edge" data-id="L_CI_Fail_0" data-points="W3sieCI6MTk3MS40ODA2MDU5MTI2NzM0LCJ5IjoxOTUuODU5MjM3ODM3MzI2NzN9LHsieCI6MjA1MS4xOTUzMTI1LCJ5IjoyMjQuMDQyOTY4NzV9LHsieCI6MjEwMS4wOTM3NSwieSI6MjI0LjA0Mjk2ODc1fV0=" data-look="classic" marker-end="url(#my-svg_flowchart-v2-pointEnd)"/></g><g class="edgeLabels"><g class="edgeLabel"><g class="label" data-id="L_Src_Hash_0" transform="translate(0, 0)"><foreignObject width="0" height="0"><div xmlns="http://www.w3.org/1999/xhtml" class="labelBkg" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="edgeLabel"></span></div></foreignObject></g></g><g class="edgeLabel"><g class="label" data-id="L_Hash_State_0" transform="translate(0, 0)"><foreignObject width="0" height="0"><div xmlns="http://www.w3.org/1999/xhtml" class="labelBkg" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="edgeLabel"></span></div></foreignObject></g></g><g class="edgeLabel" transform="translate(722.859375, 101.6953125)"><g class="label" data-id="L_State_Dirty_0" transform="translate(-10.53125, -12)"><foreignObject width="21.0625" height="24"><div xmlns="http://www.w3.org/1999/xhtml" class="labelBkg" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="edgeLabel"><p>diff</p></span></div></foreignObject></g></g><g class="edgeLabel"><g class="label" data-id="L_Dirty_Loop_0" transform="translate(0, 0)"><foreignObject width="0" height="0"><div xmlns="http://www.w3.org/1999/xhtml" class="labelBkg" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="edgeLabel"></span></div></foreignObject></g></g><g class="edgeLabel"><g class="label" data-id="L_Loop_LLM_0" transform="translate(0, 0)"><foreignObject width="0" height="0"><div xmlns="http://www.w3.org/1999/xhtml" class="labelBkg" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="edgeLabel"></span></div></foreignObject></g></g><g class="edgeLabel"><g class="label" data-id="L_LLM_Target_0" transform="translate(0, 0)"><foreignObject width="0" height="0"><div xmlns="http://www.w3.org/1999/xhtml" class="labelBkg" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="edgeLabel"></span></div></foreignObject></g></g><g class="edgeLabel"><g class="label" data-id="L_Target_State_0" transform="translate(0, 0)"><foreignObject width="0" height="0"><div xmlns="http://www.w3.org/1999/xhtml" class="labelBkg" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="edgeLabel"></span></div></foreignObject></g></g><g class="edgeLabel"><g class="label" data-id="L_Target_CI_0" transform="translate(0, 0)"><foreignObject width="0" height="0"><div xmlns="http://www.w3.org/1999/xhtml" class="labelBkg" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="edgeLabel"></span></div></foreignObject></g></g><g class="edgeLabel" transform="translate(2051.1953125, 108.04296875)"><g class="label" data-id="L_CI_Pass_0" transform="translate(-24.8984375, -12)"><foreignObject width="49.796875" height="24"><div xmlns="http://www.w3.org/1999/xhtml" class="labelBkg" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="edgeLabel"><p>in sync</p></span></div></foreignObject></g></g><g class="edgeLabel" transform="translate(2051.1953125, 224.04296875)"><g class="label" data-id="L_CI_Fail_0" transform="translate(-13.3359375, -12)"><foreignObject width="26.671875" height="24"><div xmlns="http://www.w3.org/1999/xhtml" class="labelBkg" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="edgeLabel"><p>drift</p></span></div></foreignObject></g></g></g><g class="nodes"><g class="node default" id="my-svg-flowchart-Src-0" data-look="classic" transform="translate(137.5859375, 166.04296875)"><rect class="basic label-container" style="" x="-129.5859375" y="-39" width="259.171875" height="78"/><g class="label" style="" transform="translate(-99.5859375, -24)"><rect/><foreignObject width="199.171875" height="48"><div xmlns="http://www.w3.org/1999/xhtml" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="nodeLabel"><p>Source MDs<br />(CLAUDE.md, docs/**/*.md)</p></span></div></foreignObject></g></g><g class="node default" id="my-svg-flowchart-Hash-1" data-look="classic" transform="translate(392.9921875, 166.04296875)"><rect class="basic label-container" style="" x="-75.8203125" y="-27" width="151.640625" height="54"/><g class="label" style="" transform="translate(-45.8203125, -12)"><rect/><foreignObject width="91.640625" height="24"><div xmlns="http://www.w3.org/1999/xhtml" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="nodeLabel"><p>sha256 hash</p></span></div></foreignObject></g></g><g class="node default" id="my-svg-flowchart-State-3" data-look="classic" transform="translate(603.0703125, 166.04296875)"><rect class="basic label-container" style="" x="-84.2578125" y="-27" width="168.515625" height="54"/><g class="label" style="" transform="translate(-54.2578125, -12)"><rect/><foreignObject width="108.515625" height="24"><div xmlns="http://www.w3.org/1999/xhtml" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="nodeLabel"><p>.i18n-state.json</p></span></div></foreignObject></g></g><g class="node default" id="my-svg-flowchart-Dirty-5" data-look="classic" transform="translate(849.7421875, 101.6953125)"><rect class="basic label-container" style="" x="-91.3515625" y="-27" width="182.703125" height="54"/><g class="label" style="" transform="translate(-61.3515625, -12)"><rect/><foreignObject width="122.703125" height="24"><div xmlns="http://www.w3.org/1999/xhtml" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="nodeLabel"><p>Mark source dirty</p></span></div></foreignObject></g></g><g class="node default" id="my-svg-flowchart-Loop-7" data-look="classic" transform="translate(1084.7890625, 101.6953125)"><polygon points="93.6953125,0 187.390625,-93.6953125 93.6953125,-187.390625 0,-93.6953125" class="label-container" transform="translate(-93.1953125, 93.6953125)"/><g class="label" style="" transform="translate(-54.6953125, -24)"><rect/><foreignObject width="109.390625" height="48"><div xmlns="http://www.w3.org/1999/xhtml" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="nodeLabel"><p>For each locale<br />(42 langs)</p></span></div></foreignObject></g></g><g class="node default" id="my-svg-flowchart-LLM-9" data-look="classic" transform="translate(1320.7421875, 101.6953125)"><rect class="basic label-container" style="" x="-92.2578125" y="-51" width="184.515625" height="102"/><g class="label" style="" transform="translate(-62.2578125, -36)"><rect/><foreignObject width="124.515625" height="72"><div xmlns="http://www.w3.org/1999/xhtml" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="nodeLabel"><p>OmniRoute<br />/chat/completions<br />(cx/gpt-5.4-mini)</p></span></div></foreignObject></g></g><g class="node default" id="my-svg-flowchart-Target-11" data-look="classic" transform="translate(1593, 166.04296875)"><rect class="basic label-container" style="" x="-130" y="-51" width="260" height="102"/><g class="label" style="" transform="translate(-100, -36)"><rect/><foreignObject width="200" height="72"><div xmlns="http://www.w3.org/1999/xhtml" style="display: table; white-space: break-spaces; line-height: 1.5; max-width: 200px; text-align: center; width: 200px;"><span class="nodeLabel"><p>Write<br />docs/i18n/&lt;locale&gt;/&lt;rel-path&gt;.md</p></span></div></foreignObject></g></g><g class="node default" id="my-svg-flowchart-CI-15" data-look="classic" transform="translate(1887.1484375, 166.04296875)"><polygon points="114.1484375,0 228.296875,-114.1484375 114.1484375,-228.296875 0,-114.1484375" class="label-container" transform="translate(-113.6484375, 114.1484375)"/><g class="label" style="" transform="translate(-75.1484375, -24)"><rect/><foreignObject width="150.296875" height="48"><div xmlns="http://www.w3.org/1999/xhtml" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="nodeLabel"><p>CI drift check<br />(npm run i18n:check)</p></span></div></foreignObject></g></g><g class="node default" id="my-svg-flowchart-Pass-17" data-look="classic" transform="translate(2155.546875, 108.04296875)"><rect class="basic label-container" style="" x="-46.8984375" y="-27" width="93.796875" height="54"/><g class="label" style="" transform="translate(-16.8984375, -12)"><rect/><foreignObject width="33.796875" height="24"><div xmlns="http://www.w3.org/1999/xhtml" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="nodeLabel"><p>pass</p></span></div></foreignObject></g></g><g class="node default" id="my-svg-flowchart-Fail-19" data-look="classic" transform="translate(2155.546875, 224.04296875)"><rect class="basic label-container" style="" x="-54.453125" y="-39" width="108.90625" height="78"/><g class="label" style="" transform="translate(-24.453125, -24)"><rect/><foreignObject width="48.90625" height="48"><div xmlns="http://www.w3.org/1999/xhtml" style="display: table-cell; white-space: nowrap; line-height: 1.5; max-width: 200px; text-align: center;"><span class="nodeLabel"><p>fail<br />(exit 1)</p></span></div></foreignObject></g></g></g></g></g><defs><filter id="my-svg-drop-shadow" height="130%" width="130%"><feDropShadow dx="4" dy="4" stdDeviation="0" flood-opacity="0.06" flood-color="#000000"/></filter></defs><defs><filter id="my-svg-drop-shadow-small" height="150%" width="150%"><feDropShadow dx="2" dy="2" stdDeviation="0" flood-opacity="0.06" flood-color="#000000"/></filter></defs></svg>
\ No newline at end of file
diff --git a/docs/diagrams/i18n-flow.mmd b/docs/diagrams/i18n-flow.mmd
index 9d0437aa63..e0bd6f5c8d 100644
--- a/docs/diagrams/i18n-flow.mmd
+++ b/docs/diagrams/i18n-flow.mmd
@@ -5,7 +5,7 @@ flowchart LR
   Src["Source MDs<br/>(CLAUDE.md, docs/**/*.md)"] --> Hash["sha256 hash"]
   Hash --> State[".i18n-state.json"]
   State -->|diff| Dirty["Mark source dirty"]
-  Dirty --> Loop{"For each locale<br/>(43 langs)"}
+  Dirty --> Loop{"For each locale<br/>(42 langs)"}
   Loop --> LLM["OmniRoute<br/>/chat/completions<br/>(cx/gpt-5.4-mini)"]
   LLM --> Target["Write<br/>docs/i18n/&lt;locale&gt;/&lt;rel-path&gt;.md"]
   Target --> State
diff --git a/docs/guides/FEATURES.md b/docs/guides/FEATURES.md
index 0df04fe6cb..3689806978 100644
--- a/docs/guides/FEATURES.md
+++ b/docs/guides/FEATURES.md
@@ -6,7 +6,7 @@ lastUpdated: 2026-06-28
 
 # OmniRoute — Dashboard Features Gallery
 
-🌐 **Main README translations:** 🇺🇸 [English](../README.md) | 🇧🇷 [Português (Brasil)](../i18n/pt-BR/README.md) | 🇪🇸 [Español](../i18n/es/README.md) | 🇫🇷 [Français](../i18n/fr/README.md) | 🇮🇹 [Italiano](../i18n/it/README.md) | 🇷🇺 [Русский](../i18n/ru/README.md) | 🇨🇳 [中文 (简体)](../i18n/zh-CN/README.md) | 🇩🇪 [Deutsch](../i18n/de/README.md) | 🇮🇳 [हिन्दी](../i18n/in/README.md) | 🇹🇭 [ไทย](../i18n/th/README.md) | 🇺🇦 [Українська](../i18n/uk-UA/README.md) | 🇸🇦 [العربية](../i18n/ar/README.md) | 🇯🇵 [日本語](../i18n/ja/README.md) | 🇻🇳 [Tiếng Việt](../i18n/vi/README.md) | 🇧🇬 [Български](../i18n/bg/README.md) | 🇩🇰 [Dansk](../i18n/da/README.md) | 🇫🇮 [Suomi](../i18n/fi/README.md) | 🇮🇱 [עברית](../i18n/he/README.md) | 🇭🇺 [Magyar](../i18n/hu/README.md) | 🇮🇩 [Bahasa Indonesia](../i18n/id/README.md) | 🇰🇷 [한국어](../i18n/ko/README.md) | 🇲🇾 [Bahasa Melayu](../i18n/ms/README.md) | 🇳🇱 [Nederlands](../i18n/nl/README.md) | 🇳🇴 [Norsk](../i18n/no/README.md) | 🇵🇹 [Português (Portugal)](../i18n/pt/README.md) | 🇷🇴 [Română](../i18n/ro/README.md) | 🇵🇱 [Polski](../i18n/pl/README.md) | 🇸🇰 [Slovenčina](../i18n/sk/README.md) | 🇸🇪 [Svenska](../i18n/sv/README.md) | 🇵🇭 [Filipino](../i18n/phi/README.md) | 🇨🇿 [Čeština](../i18n/cs/README.md)
+🌐 **Main README translations:** 🇺🇸 [English](../README.md) | 🇧🇷 [Português (Brasil)](../i18n/pt-BR/README.md) | 🇪🇸 [Español](../i18n/es/README.md) | 🇫🇷 [Français](../i18n/fr/README.md) | 🇮🇹 [Italiano](../i18n/it/README.md) | 🇷🇺 [Русский](../i18n/ru/README.md) | 🇨🇳 [中文 (简体)](../i18n/zh-CN/README.md) | 🇩🇪 [Deutsch](../i18n/de/README.md) | 🇹🇭 [ไทย](../i18n/th/README.md) | 🇺🇦 [Українська](../i18n/uk-UA/README.md) | 🇸🇦 [العربية](../i18n/ar/README.md) | 🇯🇵 [日本語](../i18n/ja/README.md) | 🇻🇳 [Tiếng Việt](../i18n/vi/README.md) | 🇧🇬 [Български](../i18n/bg/README.md) | 🇩🇰 [Dansk](../i18n/da/README.md) | 🇫🇮 [Suomi](../i18n/fi/README.md) | 🇮🇱 [עברית](../i18n/he/README.md) | 🇭🇺 [Magyar](../i18n/hu/README.md) | 🇮🇩 [Bahasa Indonesia](../i18n/id/README.md) | 🇰🇷 [한국어](../i18n/ko/README.md) | 🇲🇾 [Bahasa Melayu](../i18n/ms/README.md) | 🇳🇱 [Nederlands](../i18n/nl/README.md) | 🇳🇴 [Norsk](../i18n/no/README.md) | 🇵🇹 [Português (Portugal)](../i18n/pt/README.md) | 🇷🇴 [Română](../i18n/ro/README.md) | 🇵🇱 [Polski](../i18n/pl/README.md) | 🇸🇰 [Slovenčina](../i18n/sk/README.md) | 🇸🇪 [Svenska](../i18n/sv/README.md) | 🇵🇭 [Filipino](../i18n/phi/README.md) | 🇨🇿 [Čeština](../i18n/cs/README.md)
 
 Visual guide to every section of the OmniRoute dashboard.
 
diff --git a/docs/guides/TROUBLESHOOTING.md b/docs/guides/TROUBLESHOOTING.md
index e512afbfee..95c0d59dcf 100644
--- a/docs/guides/TROUBLESHOOTING.md
+++ b/docs/guides/TROUBLESHOOTING.md
@@ -8,7 +8,7 @@ lastUpdated: 2026-07-15
 
 > **For Users**: Looking for quick fixes? See the [Quick Reference](#quick-reference) below.
 
-🌐 **Languages:** 🇺🇸 [English](./TROUBLESHOOTING.md) | 🇧🇷 [Português (Brasil)](../i18n/pt-BR/docs/guides/TROUBLESHOOTING.md) | 🇪🇸 [Español](../i18n/es/docs/guides/TROUBLESHOOTING.md) | 🇫🇷 [Français](../i18n/fr/docs/guides/TROUBLESHOOTING.md) | 🇮🇹 [Italiano](../i18n/it/docs/guides/TROUBLESHOOTING.md) | 🇷🇺 [Русский](../i18n/ru/docs/guides/TROUBLESHOOTING.md) | 🇨🇳 [中文 (简体)](../i18n/zh-CN/docs/guides/TROUBLESHOOTING.md) | 🇩🇪 [Deutsch](../i18n/de/docs/guides/TROUBLESHOOTING.md) | 🇮🇳 [हिन्दी](../i18n/in/docs/guides/TROUBLESHOOTING.md) | 🇹🇭 [ไทย](../i18n/th/docs/guides/TROUBLESHOOTING.md) | 🇺🇦 [Українська](../i18n/uk-UA/docs/guides/TROUBLESHOOTING.md) | 🇸🇦 [العربية](../i18n/ar/docs/guides/TROUBLESHOOTING.md) | 🇯🇵 [日本語](../i18n/ja/docs/guides/TROUBLESHOOTING.md) | 🇻🇳 [Tiếng Việt](../i18n/vi/docs/guides/TROUBLESHOOTING.md) | 🇧🇬 [Български](../i18n/bg/docs/guides/TROUBLESHOOTING.md) | 🇩🇰 [Dansk](../i18n/da/docs/guides/TROUBLESHOOTING.md) | 🇫🇮 [Suomi](../i18n/fi/docs/guides/TROUBLESHOOTING.md) | 🇮🇱 [עברית](../i18n/he/docs/guides/TROUBLESHOOTING.md) | 🇭🇺 [Magyar](../i18n/hu/docs/guides/TROUBLESHOOTING.md) | 🇮🇩 [Bahasa Indonesia](../i18n/id/docs/guides/TROUBLESHOOTING.md) | 🇰🇷 [한국어](../i18n/ko/docs/guides/TROUBLESHOOTING.md) | 🇲🇾 [Bahasa Melayu](../i18n/ms/docs/guides/TROUBLESHOOTING.md) | 🇳🇱 [Nederlands](../i18n/nl/docs/guides/TROUBLESHOOTING.md) | 🇳🇴 [Norsk](../i18n/no/docs/guides/TROUBLESHOOTING.md) | 🇵🇹 [Português (Portugal)](../i18n/pt/docs/guides/TROUBLESHOOTING.md) | 🇷🇴 [Română](../i18n/ro/docs/guides/TROUBLESHOOTING.md) | 🇵🇱 [Polski](../i18n/pl/docs/guides/TROUBLESHOOTING.md) | 🇸🇰 [Slovenčina](../i18n/sk/docs/guides/TROUBLESHOOTING.md) | 🇸🇪 [Svenska](../i18n/sv/docs/guides/TROUBLESHOOTING.md) | 🇵🇭 [Filipino](../i18n/phi/docs/guides/TROUBLESHOOTING.md) | 🇨🇿 [Čeština](../i18n/cs/docs/guides/TROUBLESHOOTING.md)
+🌐 **Languages:** 🇺🇸 [English](./TROUBLESHOOTING.md) | 🇧🇷 [Português (Brasil)](../i18n/pt-BR/docs/guides/TROUBLESHOOTING.md) | 🇪🇸 [Español](../i18n/es/docs/guides/TROUBLESHOOTING.md) | 🇫🇷 [Français](../i18n/fr/docs/guides/TROUBLESHOOTING.md) | 🇮🇹 [Italiano](../i18n/it/docs/guides/TROUBLESHOOTING.md) | 🇷🇺 [Русский](../i18n/ru/docs/guides/TROUBLESHOOTING.md) | 🇨🇳 [中文 (简体)](../i18n/zh-CN/docs/guides/TROUBLESHOOTING.md) | 🇩🇪 [Deutsch](../i18n/de/docs/guides/TROUBLESHOOTING.md) | 🇹🇭 [ไทย](../i18n/th/docs/guides/TROUBLESHOOTING.md) | 🇺🇦 [Українська](../i18n/uk-UA/docs/guides/TROUBLESHOOTING.md) | 🇸🇦 [العربية](../i18n/ar/docs/guides/TROUBLESHOOTING.md) | 🇯🇵 [日本語](../i18n/ja/docs/guides/TROUBLESHOOTING.md) | 🇻🇳 [Tiếng Việt](../i18n/vi/docs/guides/TROUBLESHOOTING.md) | 🇧🇬 [Български](../i18n/bg/docs/guides/TROUBLESHOOTING.md) | 🇩🇰 [Dansk](../i18n/da/docs/guides/TROUBLESHOOTING.md) | 🇫🇮 [Suomi](../i18n/fi/docs/guides/TROUBLESHOOTING.md) | 🇮🇱 [עברית](../i18n/he/docs/guides/TROUBLESHOOTING.md) | 🇭🇺 [Magyar](../i18n/hu/docs/guides/TROUBLESHOOTING.md) | 🇮🇩 [Bahasa Indonesia](../i18n/id/docs/guides/TROUBLESHOOTING.md) | 🇰🇷 [한국어](../i18n/ko/docs/guides/TROUBLESHOOTING.md) | 🇲🇾 [Bahasa Melayu](../i18n/ms/docs/guides/TROUBLESHOOTING.md) | 🇳🇱 [Nederlands](../i18n/nl/docs/guides/TROUBLESHOOTING.md) | 🇳🇴 [Norsk](../i18n/no/docs/guides/TROUBLESHOOTING.md) | 🇵🇹 [Português (Portugal)](../i18n/pt/docs/guides/TROUBLESHOOTING.md) | 🇷🇴 [Română](../i18n/ro/docs/guides/TROUBLESHOOTING.md) | 🇵🇱 [Polski](../i18n/pl/docs/guides/TROUBLESHOOTING.md) | 🇸🇰 [Slovenčina](../i18n/sk/docs/guides/TROUBLESHOOTING.md) | 🇸🇪 [Svenska](../i18n/sv/docs/guides/TROUBLESHOOTING.md) | 🇵🇭 [Filipino](../i18n/phi/docs/guides/TROUBLESHOOTING.md) | 🇨🇿 [Čeština](../i18n/cs/docs/guides/TROUBLESHOOTING.md)
 
 Common problems and solutions for OmniRoute.
 
diff --git a/docs/guides/UNINSTALL.md b/docs/guides/UNINSTALL.md
index c4d351e83b..1a1dec42a6 100644
--- a/docs/guides/UNINSTALL.md
+++ b/docs/guides/UNINSTALL.md
@@ -6,7 +6,7 @@ lastUpdated: 2026-06-28
 
 # OmniRoute — Uninstall Guide
 
-🌐 **Languages:** 🇺🇸 [English](./UNINSTALL.md) | 🇧🇷 [Português (Brasil)](../i18n/pt-BR/docs/guides/UNINSTALL.md) | 🇪🇸 [Español](../i18n/es/docs/guides/UNINSTALL.md) | 🇫🇷 [Français](../i18n/fr/docs/guides/UNINSTALL.md) | 🇮🇹 [Italiano](../i18n/it/docs/guides/UNINSTALL.md) | 🇷🇺 [Русский](../i18n/ru/docs/guides/UNINSTALL.md) | 🇨🇳 [中文 (简体)](../i18n/zh-CN/docs/guides/UNINSTALL.md) | 🇩🇪 [Deutsch](../i18n/de/docs/guides/UNINSTALL.md) | 🇮🇳 [हिन्दी](../i18n/in/docs/guides/UNINSTALL.md) | 🇹🇭 [ไทย](../i18n/th/docs/guides/UNINSTALL.md) | 🇺🇦 [Українська](../i18n/uk-UA/docs/guides/UNINSTALL.md) | 🇸🇦 [العربية](../i18n/ar/docs/guides/UNINSTALL.md) | 🇯🇵 [日本語](../i18n/ja/docs/guides/UNINSTALL.md) | 🇻🇳 [Tiếng Việt](../i18n/vi/docs/guides/UNINSTALL.md) | 🇧🇬 [Български](../i18n/bg/docs/guides/UNINSTALL.md) | 🇩🇰 [Dansk](../i18n/da/docs/guides/UNINSTALL.md) | 🇫🇮 [Suomi](../i18n/fi/docs/guides/UNINSTALL.md) | 🇮🇱 [עברית](../i18n/he/docs/guides/UNINSTALL.md) | 🇭🇺 [Magyar](../i18n/hu/docs/guides/UNINSTALL.md) | 🇮🇩 [Bahasa Indonesia](../i18n/id/docs/guides/UNINSTALL.md) | 🇰🇷 [한국어](../i18n/ko/docs/guides/UNINSTALL.md) | 🇲🇾 [Bahasa Melayu](../i18n/ms/docs/guides/UNINSTALL.md) | 🇳🇱 [Nederlands](../i18n/nl/docs/guides/UNINSTALL.md) | 🇳🇴 [Norsk](../i18n/no/docs/guides/UNINSTALL.md) | 🇵🇹 [Português (Portugal)](../i18n/pt/docs/guides/UNINSTALL.md) | 🇷🇴 [Română](../i18n/ro/docs/guides/UNINSTALL.md) | 🇵🇱 [Polski](../i18n/pl/docs/guides/UNINSTALL.md) | 🇸🇰 [Slovenčina](../i18n/sk/docs/guides/UNINSTALL.md) | 🇸🇪 [Svenska](../i18n/sv/docs/guides/UNINSTALL.md) | 🇵🇭 [Filipino](../i18n/phi/docs/guides/UNINSTALL.md) | 🇨🇿 [Čeština](../i18n/cs/docs/guides/UNINSTALL.md)
+🌐 **Languages:** 🇺🇸 [English](./UNINSTALL.md) | 🇧🇷 [Português (Brasil)](../i18n/pt-BR/docs/guides/UNINSTALL.md) | 🇪🇸 [Español](../i18n/es/docs/guides/UNINSTALL.md) | 🇫🇷 [Français](../i18n/fr/docs/guides/UNINSTALL.md) | 🇮🇹 [Italiano](../i18n/it/docs/guides/UNINSTALL.md) | 🇷🇺 [Русский](../i18n/ru/docs/guides/UNINSTALL.md) | 🇨🇳 [中文 (简体)](../i18n/zh-CN/docs/guides/UNINSTALL.md) | 🇩🇪 [Deutsch](../i18n/de/docs/guides/UNINSTALL.md) | 🇹🇭 [ไทย](../i18n/th/docs/guides/UNINSTALL.md) | 🇺🇦 [Українська](../i18n/uk-UA/docs/guides/UNINSTALL.md) | 🇸🇦 [العربية](../i18n/ar/docs/guides/UNINSTALL.md) | 🇯🇵 [日本語](../i18n/ja/docs/guides/UNINSTALL.md) | 🇻🇳 [Tiếng Việt](../i18n/vi/docs/guides/UNINSTALL.md) | 🇧🇬 [Български](../i18n/bg/docs/guides/UNINSTALL.md) | 🇩🇰 [Dansk](../i18n/da/docs/guides/UNINSTALL.md) | 🇫🇮 [Suomi](../i18n/fi/docs/guides/UNINSTALL.md) | 🇮🇱 [עברית](../i18n/he/docs/guides/UNINSTALL.md) | 🇭🇺 [Magyar](../i18n/hu/docs/guides/UNINSTALL.md) | 🇮🇩 [Bahasa Indonesia](../i18n/id/docs/guides/UNINSTALL.md) | 🇰🇷 [한국어](../i18n/ko/docs/guides/UNINSTALL.md) | 🇲🇾 [Bahasa Melayu](../i18n/ms/docs/guides/UNINSTALL.md) | 🇳🇱 [Nederlands](../i18n/nl/docs/guides/UNINSTALL.md) | 🇳🇴 [Norsk](../i18n/no/docs/guides/UNINSTALL.md) | 🇵🇹 [Português (Portugal)](../i18n/pt/docs/guides/UNINSTALL.md) | 🇷🇴 [Română](../i18n/ro/docs/guides/UNINSTALL.md) | 🇵🇱 [Polski](../i18n/pl/docs/guides/UNINSTALL.md) | 🇸🇰 [Slovenčina](../i18n/sk/docs/guides/UNINSTALL.md) | 🇸🇪 [Svenska](../i18n/sv/docs/guides/UNINSTALL.md) | 🇵🇭 [Filipino](../i18n/phi/docs/guides/UNINSTALL.md) | 🇨🇿 [Čeština](../i18n/cs/docs/guides/UNINSTALL.md)
 
 This guide covers how to cleanly remove OmniRoute from your system.
 
diff --git a/docs/guides/USER_GUIDE.md b/docs/guides/USER_GUIDE.md
index 520e3229f3..31045aaea9 100644
--- a/docs/guides/USER_GUIDE.md
+++ b/docs/guides/USER_GUIDE.md
@@ -6,7 +6,7 @@ lastUpdated: 2026-06-28
 
 # User Guide
 
-🌐 **Languages:** 🇺🇸 [English](./USER_GUIDE.md) | 🇧🇷 [Português (Brasil)](../i18n/pt-BR/docs/guides/USER_GUIDE.md) | 🇪🇸 [Español](../i18n/es/docs/guides/USER_GUIDE.md) | 🇫🇷 [Français](../i18n/fr/docs/guides/USER_GUIDE.md) | 🇮🇹 [Italiano](../i18n/it/docs/guides/USER_GUIDE.md) | 🇷🇺 [Русский](../i18n/ru/docs/guides/USER_GUIDE.md) | 🇨🇳 [中文 (简体)](../i18n/zh-CN/docs/guides/USER_GUIDE.md) | 🇩🇪 [Deutsch](../i18n/de/docs/guides/USER_GUIDE.md) | 🇮🇳 [हिन्दी](../i18n/in/docs/guides/USER_GUIDE.md) | 🇹🇭 [ไทย](../i18n/th/docs/guides/USER_GUIDE.md) | 🇺🇦 [Українська](../i18n/uk-UA/docs/guides/USER_GUIDE.md) | 🇸🇦 [العربية](../i18n/ar/docs/guides/USER_GUIDE.md) | 🇯🇵 [日本語](../i18n/ja/docs/guides/USER_GUIDE.md) | 🇻🇳 [Tiếng Việt](../i18n/vi/docs/guides/USER_GUIDE.md) | 🇧🇬 [Български](../i18n/bg/docs/guides/USER_GUIDE.md) | 🇩🇰 [Dansk](../i18n/da/docs/guides/USER_GUIDE.md) | 🇫🇮 [Suomi](../i18n/fi/docs/guides/USER_GUIDE.md) | 🇮🇱 [עברית](../i18n/he/docs/guides/USER_GUIDE.md) | 🇭🇺 [Magyar](../i18n/hu/docs/guides/USER_GUIDE.md) | 🇮🇩 [Bahasa Indonesia](../i18n/id/docs/guides/USER_GUIDE.md) | 🇰🇷 [한국어](../i18n/ko/docs/guides/USER_GUIDE.md) | 🇲🇾 [Bahasa Melayu](../i18n/ms/docs/guides/USER_GUIDE.md) | 🇳🇱 [Nederlands](../i18n/nl/docs/guides/USER_GUIDE.md) | 🇳🇴 [Norsk](../i18n/no/docs/guides/USER_GUIDE.md) | 🇵🇹 [Português (Portugal)](../i18n/pt/docs/guides/USER_GUIDE.md) | 🇷🇴 [Română](../i18n/ro/docs/guides/USER_GUIDE.md) | 🇵🇱 [Polski](../i18n/pl/docs/guides/USER_GUIDE.md) | 🇸🇰 [Slovenčina](../i18n/sk/docs/guides/USER_GUIDE.md) | 🇸🇪 [Svenska](../i18n/sv/docs/guides/USER_GUIDE.md) | 🇵🇭 [Filipino](../i18n/phi/docs/guides/USER_GUIDE.md) | 🇨🇿 [Čeština](../i18n/cs/docs/guides/USER_GUIDE.md)
+🌐 **Languages:** 🇺🇸 [English](./USER_GUIDE.md) | 🇧🇷 [Português (Brasil)](../i18n/pt-BR/docs/guides/USER_GUIDE.md) | 🇪🇸 [Español](../i18n/es/docs/guides/USER_GUIDE.md) | 🇫🇷 [Français](../i18n/fr/docs/guides/USER_GUIDE.md) | 🇮🇹 [Italiano](../i18n/it/docs/guides/USER_GUIDE.md) | 🇷🇺 [Русский](../i18n/ru/docs/guides/USER_GUIDE.md) | 🇨🇳 [中文 (简体)](../i18n/zh-CN/docs/guides/USER_GUIDE.md) | 🇩🇪 [Deutsch](../i18n/de/docs/guides/USER_GUIDE.md) | 🇹🇭 [ไทย](../i18n/th/docs/guides/USER_GUIDE.md) | 🇺🇦 [Українська](../i18n/uk-UA/docs/guides/USER_GUIDE.md) | 🇸🇦 [العربية](../i18n/ar/docs/guides/USER_GUIDE.md) | 🇯🇵 [日本語](../i18n/ja/docs/guides/USER_GUIDE.md) | 🇻🇳 [Tiếng Việt](../i18n/vi/docs/guides/USER_GUIDE.md) | 🇧🇬 [Български](../i18n/bg/docs/guides/USER_GUIDE.md) | 🇩🇰 [Dansk](../i18n/da/docs/guides/USER_GUIDE.md) | 🇫🇮 [Suomi](../i18n/fi/docs/guides/USER_GUIDE.md) | 🇮🇱 [עברית](../i18n/he/docs/guides/USER_GUIDE.md) | 🇭🇺 [Magyar](../i18n/hu/docs/guides/USER_GUIDE.md) | 🇮🇩 [Bahasa Indonesia](../i18n/id/docs/guides/USER_GUIDE.md) | 🇰🇷 [한국어](../i18n/ko/docs/guides/USER_GUIDE.md) | 🇲🇾 [Bahasa Melayu](../i18n/ms/docs/guides/USER_GUIDE.md) | 🇳🇱 [Nederlands](../i18n/nl/docs/guides/USER_GUIDE.md) | 🇳🇴 [Norsk](../i18n/no/docs/guides/USER_GUIDE.md) | 🇵🇹 [Português (Portugal)](../i18n/pt/docs/guides/USER_GUIDE.md) | 🇷🇴 [Română](../i18n/ro/docs/guides/USER_GUIDE.md) | 🇵🇱 [Polski](../i18n/pl/docs/guides/USER_GUIDE.md) | 🇸🇰 [Slovenčina](../i18n/sk/docs/guides/USER_GUIDE.md) | 🇸🇪 [Svenska](../i18n/sv/docs/guides/USER_GUIDE.md) | 🇵🇭 [Filipino](../i18n/phi/docs/guides/USER_GUIDE.md) | 🇨🇿 [Čeština](../i18n/cs/docs/guides/USER_GUIDE.md)
 
 Complete guide for configuring providers, creating combos, integrating CLI tools, and deploying OmniRoute.
 
@@ -35,27 +35,27 @@ Complete guide for configuring providers, creating combos, integrating CLI tools
 
 ## 💰 Pricing at a Glance
 
-| Tier                | Provider          | Cost        | Quota Reset    | Best For             |
-| ------------------- | ----------------- | ----------- | -------------- | -------------------- |
-| **💳 SUBSCRIPTION** | Claude Code (Pro) | $20/mo      | 5h + weekly    | Already subscribed   |
-|                     | Codex (Plus/Pro)  | $20-200/mo  | 5h + weekly    | OpenAI users         |
-|                     | GitHub Copilot    | $10-19/mo   | Monthly        | GitHub users         |
-| **🔑 API KEY**      | DeepSeek          | Pay per use | None           | Cheap reasoning      |
-|                     | Groq              | Pay per use | None           | Ultra-fast inference |
-|                     | xAI (Grok)        | Pay per use | None           | Grok 4 reasoning     |
-|                     | Mistral           | Pay per use | None           | EU-hosted models     |
-|                     | Perplexity        | Pay per use | None           | Search-augmented     |
-|                     | Together AI       | Pay per use | None           | Open-source models   |
-|                     | Fireworks AI      | Pay per use | None           | Fast FLUX images     |
-|                     | Cerebras          | Pay per use | None           | Wafer-scale speed    |
-|                     | Cohere            | Pay per use | None           | Command R+ RAG       |
-|                     | NVIDIA NIM        | Pay per use | None           | Enterprise models    |
-|                     | Baidu Qianfan     | Pay per use | None           | ERNIE models         |
-| **💰 CHEAP**        | GLM-4.7           | $0.6/1M     | Daily 10AM     | Budget backup        |
-|                     | MiniMax M2.1      | $0.2/1M     | 5-hour rolling | Cheapest option      |
-|                     | Kimi K2           | $9/mo flat  | 10M tokens/mo  | Predictable cost     |
+| Tier                | Provider          | Cost        | Quota Reset           | Best For               |
+| ------------------- | ----------------- | ----------- | --------------------- | ---------------------- |
+| **💳 SUBSCRIPTION** | Claude Code (Pro) | $20/mo      | 5h + weekly           | Already subscribed     |
+|                     | Codex (Plus/Pro)  | $20-200/mo  | 5h + weekly           | OpenAI users           |
+|                     | GitHub Copilot    | $10-19/mo   | Monthly               | GitHub users           |
+| **🔑 API KEY**      | DeepSeek          | Pay per use | None                  | Cheap reasoning        |
+|                     | Groq              | Pay per use | None                  | Ultra-fast inference   |
+|                     | xAI (Grok)        | Pay per use | None                  | Grok 4 reasoning       |
+|                     | Mistral           | Pay per use | None                  | EU-hosted models       |
+|                     | Perplexity        | Pay per use | None                  | Search-augmented       |
+|                     | Together AI       | Pay per use | None                  | Open-source models     |
+|                     | Fireworks AI      | Pay per use | None                  | Fast FLUX images       |
+|                     | Cerebras          | Pay per use | None                  | Wafer-scale speed      |
+|                     | Cohere            | Pay per use | None                  | Command R+ RAG         |
+|                     | NVIDIA NIM        | Pay per use | None                  | Enterprise models      |
+|                     | Baidu Qianfan     | Pay per use | None                  | ERNIE models           |
+| **💰 CHEAP**        | GLM-4.7           | $0.6/1M     | Daily 10AM            | Budget backup          |
+|                     | MiniMax M2.1      | $0.2/1M     | 5-hour rolling        | Cheapest option        |
+|                     | Kimi K2           | $9/mo flat  | 10M tokens/mo         | Predictable cost       |
 | **🆓 FREE**         | Qoder             | $0          | Provider limits apply | Verify current catalog |
-|                     | Kiro              | $0          | ~50 credits/mo | Claude free          |
+|                     | Kiro              | $0          | ~50 credits/mo        | Claude free            |
 
 ---
 
diff --git a/docs/i18n/README.md b/docs/i18n/README.md
index 276a42213c..109a0fdaa7 100644
--- a/docs/i18n/README.md
+++ b/docs/i18n/README.md
@@ -1,6 +1,6 @@
 # 🌐 Multilingual Documentation — OmniRoute
 
-Translations of documentation into 42 languages; together with the English source, the UI supports 43 locales. Code blocks remain in English.
+Translations of documentation into 41 languages; together with the English source, the UI supports 42 locales. Code blocks remain in English.
 
 ---
 
@@ -20,7 +20,6 @@ Translations of documentation into 42 languages; together with the English sourc
 - 🇮🇳 **हिन्दी** (`hi`): [Docs Root](./hi/README.md)
 - 🇭🇺 **Magyar** (`hu`): [Docs Root](./hu/README.md)
 - 🇮🇩 **Bahasa Indonesia** (`id`): [Docs Root](./id/README.md)
-- 🇮🇩 **Bahasa Indonesia (Alt)** (`in`): [Docs Root](./in/README.md)
 - 🇮🇹 **Italiano** (`it`): [Docs Root](./it/README.md)
 - 🇯🇵 **日本語** (`ja`): [Docs Root](./ja/README.md)
 - 🇰🇷 **한국어** (`ko`): [Docs Root](./ko/README.md)
diff --git a/docs/i18n/ar/llm.txt b/docs/i18n/ar/llm.txt
index 20123a9d69..87ab262fbf 100644
--- a/docs/i18n/ar/llm.txt
+++ b/docs/i18n/ar/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/az/llm.txt b/docs/i18n/az/llm.txt
index 41f114138f..fc42edb077 100644
--- a/docs/i18n/az/llm.txt
+++ b/docs/i18n/az/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/bg/llm.txt b/docs/i18n/bg/llm.txt
index 41f114138f..fc42edb077 100644
--- a/docs/i18n/bg/llm.txt
+++ b/docs/i18n/bg/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/bn/llm.txt b/docs/i18n/bn/llm.txt
index 11ea0f8513..465b775ff3 100644
--- a/docs/i18n/bn/llm.txt
+++ b/docs/i18n/bn/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/cs/llm.txt b/docs/i18n/cs/llm.txt
index ed922553d6..fb94e01bdf 100644
--- a/docs/i18n/cs/llm.txt
+++ b/docs/i18n/cs/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/da/llm.txt b/docs/i18n/da/llm.txt
index 51e98c8dbe..a42f0d8cf0 100644
--- a/docs/i18n/da/llm.txt
+++ b/docs/i18n/da/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/de/llm.txt b/docs/i18n/de/llm.txt
index 949de1e465..353c1155eb 100644
--- a/docs/i18n/de/llm.txt
+++ b/docs/i18n/de/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/es/llm.txt b/docs/i18n/es/llm.txt
index bf98130ebe..c11bca8370 100644
--- a/docs/i18n/es/llm.txt
+++ b/docs/i18n/es/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/fa/llm.txt b/docs/i18n/fa/llm.txt
index 487087c5fe..9287cb4485 100644
--- a/docs/i18n/fa/llm.txt
+++ b/docs/i18n/fa/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/fi/llm.txt b/docs/i18n/fi/llm.txt
index 29535373bb..ab10af2104 100644
--- a/docs/i18n/fi/llm.txt
+++ b/docs/i18n/fi/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/fr/llm.txt b/docs/i18n/fr/llm.txt
index d25a9f0a08..207dfb71a6 100644
--- a/docs/i18n/fr/llm.txt
+++ b/docs/i18n/fr/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/gu/llm.txt b/docs/i18n/gu/llm.txt
index db1b62755f..62e45720e2 100644
--- a/docs/i18n/gu/llm.txt
+++ b/docs/i18n/gu/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/he/llm.txt b/docs/i18n/he/llm.txt
index 67f152fb90..e67cd37cf9 100644
--- a/docs/i18n/he/llm.txt
+++ b/docs/i18n/he/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/hi/llm.txt b/docs/i18n/hi/llm.txt
index 25e1a61464..267cd8c738 100644
--- a/docs/i18n/hi/llm.txt
+++ b/docs/i18n/hi/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/hu/llm.txt b/docs/i18n/hu/llm.txt
index 9d3622b254..5ce7046b4a 100644
--- a/docs/i18n/hu/llm.txt
+++ b/docs/i18n/hu/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/id/llm.txt b/docs/i18n/id/llm.txt
index f7dd30f547..affbf06dd6 100644
--- a/docs/i18n/id/llm.txt
+++ b/docs/i18n/id/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/in/CHANGELOG.md b/docs/i18n/in/CHANGELOG.md
deleted file mode 100644
index d864c07e8a..0000000000
--- a/docs/i18n/in/CHANGELOG.md
+++ /dev/null
@@ -1,12094 +0,0 @@
-# Changelog (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../CHANGELOG.md) · 🇪🇸 [es](../es/CHANGELOG.md) · 🇫🇷 [fr](../fr/CHANGELOG.md) · 🇩🇪 [de](../de/CHANGELOG.md) · 🇮🇹 [it](../it/CHANGELOG.md) · 🇷🇺 [ru](../ru/CHANGELOG.md) · 🇨🇳 [zh-CN](../zh-CN/CHANGELOG.md) · 🇯🇵 [ja](../ja/CHANGELOG.md) · 🇰🇷 [ko](../ko/CHANGELOG.md) · 🇸🇦 [ar](../ar/CHANGELOG.md) · 🇮🇳 [hi](../hi/CHANGELOG.md) · 🇮🇳 [in](../in/CHANGELOG.md) · 🇹🇭 [th](../th/CHANGELOG.md) · 🇻🇳 [vi](../vi/CHANGELOG.md) · 🇮🇩 [id](../id/CHANGELOG.md) · 🇲🇾 [ms](../ms/CHANGELOG.md) · 🇳🇱 [nl](../nl/CHANGELOG.md) · 🇵🇱 [pl](../pl/CHANGELOG.md) · 🇸🇪 [sv](../sv/CHANGELOG.md) · 🇳🇴 [no](../no/CHANGELOG.md) · 🇩🇰 [da](../da/CHANGELOG.md) · 🇫🇮 [fi](../fi/CHANGELOG.md) · 🇵🇹 [pt](../pt/CHANGELOG.md) · 🇷🇴 [ro](../ro/CHANGELOG.md) · 🇭🇺 [hu](../hu/CHANGELOG.md) · 🇧🇬 [bg](../bg/CHANGELOG.md) · 🇸🇰 [sk](../sk/CHANGELOG.md) · 🇺🇦 [uk-UA](../uk-UA/CHANGELOG.md) · 🇮🇱 [he](../he/CHANGELOG.md) · 🇵🇭 [phi](../phi/CHANGELOG.md) · 🇧🇷 [pt-BR](../pt-BR/CHANGELOG.md) · 🇨🇿 [cs](../cs/CHANGELOG.md) · 🇹🇷 [tr](../tr/CHANGELOG.md)
-
----
-
-## [3.8.31] — 2026-06-20
-
-## [3.8.51] — TBD
-
-_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
-
-### ✨ New Features
-
-### 🐛 Bug Fixes
-
-### 📝 Maintenance
-
----
-
-## [3.8.50] — 2026-08-25
-
-_Living section — regenerated 2026-08-12 from all cycle commits (cycle open `ed2db6cb19` → tip). Bullets carry the merged PR and its author; direct pushes listed separately._
-
-### 📊 Release by the numbers
-
-| | |
-| --- | ---: |
-| 👥 People who contributed | **248** |
-| 📝 Commits in the cycle | **1,714** |
-| 🔀 Pull requests referenced | **1,666** |
-| 📋 Changelog entries | **1,182** |
-| 🙌 Contributors credited in entries | **256** |
-| 🤖 Automated dependency commits | 22 |
-
-**Entries by type**
-
-| Type | Count |
-| --- | ---: |
-| 🐛 Fixes | 779 |
-| ✨ Features | 169 |
-| 📚 Docs | 29 |
-| 🧹 Chore | 27 |
-| 🧪 Tests | 15 |
-| ♻️ Refactor | 5 |
-| ⚡ Performance | 3 |
-| providers | 2 |
-| 🔒 Security | 2 |
-| ⚙️ CI | 2 |
-| deps | 2 |
-| maint | 2 |
-
-### 🏆 Top 25 contributors this cycle
-
-_By commits in `ed2db6cb19..v3.8.50`, author identities consolidated via `.mailmap`. Bots excluded._
-
-| # | Contributor | Commits |
-| ---: | --- | ---: |
-| 🥇 | diegosouzapw | 738 |
-| 🥈 | backryun | 88 |
-| 🥉 | Dizzle | 66 |
-| 4 | Ravi Tharuma | 52 |
-| 5 | Markus Hartung | 48 |
-| 6 | Bob.Hou | 42 |
-| 7 | Rouzbeh† | 38 |
-| 8 | Xiangzhe | 31 |
-| 9 | Paco Cartones | 28 |
-| 10 | Nguyen Thanh Dat | 23 |
-| 11 | Aman | 22 |
-| 12 | Will Gordon | 19 |
-| 13 | 小妍儿 ✨ | 17 |
-| 14 | adevwithpurpose | 16 |
-| 15 | Andrew B. | 10 |
-| 16 | NOXX - Commiter | 10 |
-| 17 | ignamiranda | 10 |
-| 18 | Jonathan Bailey | 9 |
-| 19 | Ke Jin | 9 |
-| 20 | Austin Liu | 8 |
-| 21 | Chewji | 8 |
-| 22 | Prudhvi Vuda | 7 |
-| 23 | benzntech | 7 |
-| 24 | rinseaid | 7 |
-| 25 | stanley | 7 |
-
-
-### ✨ New Features
-- **feat(search):** first-class X Search provider (`x-search`) on `POST /v1/search` and MCP `omniroute_x_search` using SuperGrok / xAI server-side `x_search`. Explicit provider or `search_type: "x"` only — never auto-selected for web. Reuses `xai-oauth` / `xao` / `xai` credentials. Not the X Developer Platform MCP. ([#10985](https://github.com/diegosouzapw/OmniRoute/issues/10985))
-- **feat(core):** add Layer A capability filter at router (#5696)
-- **feat(providers):** add DeepAI as paid API-key image provider ([#6671](https://github.com/diegosouzapw/OmniRoute/issues/6671))
-- **feat(providers):** add Naga.ac and ChatAnywhere aggregator gateway providers (#6674 — thanks @chirag127)
-- **feat(api):** add response content encoding verification — confirms Next.js compress:true and documents stripStaleForwardingHeaders behavior ([#6736](https://github.com/diegosouzapw/OmniRoute/issues/6736))
-- **feat(api):** add plugins marketplace install endpoint with checksum verification ([#6752](https://github.com/diegosouzapw/OmniRoute/issues/6752))
-- **feat(chatgpt-web):** harden prompt-emulated tool contract for thinking models (#7679 — thanks @horacecar)
-- **docs:** add management authentication terminology guide ([#7786](https://github.com/diegosouzapw/OmniRoute/issues/7786))
-- feat(a2a): Conductor bridge — long-lived SSE consumer that mirrors OmniConductor hub tasks into the A2A TaskManager (explicit `canceled→cancelled` mapping with tests, persisted `last_event_id` cursor in the `key_value` table, exponential-backoff reconnection; opt-in via `CONDUCTOR_HUB_URL`/`CONDUCTOR_HUB_TOKEN`) ([#8080](https://github.com/diegosouzapw/OmniRoute/pull/8080))
-- feat(a2a): the Agent Card (`/.well-known/agent.json`) now announces skills derived from the OmniConductor fleet (`GET /v1/runners` OASF capabilities — one skill per online CLI profile + declared fleet skills), cached ~60s and fail-open when the hub is unset/offline ([#8119](https://github.com/diegosouzapw/OmniRoute/pull/8119))
-- feat(dashboard): "Conductor" panel — OmniConductor fleet (runners + task queue) live via server-side proxy routes (`/api/conductor/*`, management auth, hub token never reaches the browser), task detail with manifest/council and cancel-with-confirmation; sidebar entry under Tools ([#8221](https://github.com/diegosouzapw/OmniRoute/pull/8221))
-- feat(dashboard): Faro chat with voice on the Conductor panel — text via `/api/conductor/ask` (server-side proxy to the spokesperson; hub credential never reaches the browser; `pending` → Sim/Não confirmation buttons) and a guaranteed push-to-talk voice cycle (MediaRecorder → `/api/v1/audio/transcriptions` → ask → `/api/v1/audio/speech` playback), with operator-configurable STT/TTS models ([#8222](https://github.com/diegosouzapw/OmniRoute/pull/8222))
-- feat(a2a): inbound delegation to the OmniConductor fleet — `POST /api/a2a/tasks` translates an external A2A task into the hub's `POST /v1/tasks` (fleet skills only, repo required, `CONDUCTOR_ORCHESTRATOR_TOKEN` with hub-token fallback); states flow back through the SSE→A2A mirror ([#8223](https://github.com/diegosouzapw/OmniRoute/pull/8223))
-- **docs:** add low-memory/small VPS optimization guide ([#8237](https://github.com/diegosouzapw/OmniRoute/issues/8237))
-- **feat(providers):** add connection-level custom upstream headers via `provider_specific_data.customHeaders` — applied to every request through that connection, with model-level headers overriding on the same case-insensitive name. (#8369 — thanks @Benson-mk)
-- feat(copilot): add approval gate for runOmniRouteCli commands (#8461)
-- feat(ci): add windows-latest leg to test-bun-sqlite job (#8468)
-- **feat(electron):** Desktop app can now attach to an already-running OmniRoute server (e.g. a Docker/OrbStack container) instead of always spawning its own bundled server — configurable via the tray's "Remote Server → Connect to Remote Server…" or the `OMNIROUTE_REMOTE_URL` env var ([#8799](https://github.com/diegosouzapw/OmniRoute/pull/8799)) — thanks @soulhakr
-- **Database**: The `node:sqlite` fallback now uses SQLite's native backup API and real immediate write transactions, improving backup consistency and concurrent-write behavior when `better-sqlite3` is unavailable ([#8870](https://github.com/diegosouzapw/OmniRoute/pull/8870)) — thanks @artickc
-- **feat(models):** add exact per-model `context_length`, `max_input_tokens`, and `max_output_tokens` overrides across model discovery and runtime enforcement, with automatic migration from the retired output-only `max_token` key ([#8908](https://github.com/diegosouzapw/OmniRoute/pull/8908)) — thanks @xz-dev
-- **Providers**: expands the Novita AI catalog from a single Llama 3.1 8B entry to 19 curated serving models (DeepSeek V4, Kimi K3, GLM 5.2, MiniMax M3, Qwen3.7 Max, Qwen3 Coder 480B, MiMo V2.5 Pro, gpt-oss-120b, Gemma 4 31B and more), each carrying its real context window, output cap and reasoning flag from the live `/openai/v1/models` listing, and each vision flag confirmed by an actual image request rather than the listing's self-reported modalities ([#8913](https://github.com/diegosouzapw/OmniRoute/pull/8913)) — thanks @jax-novita
-- **feat(providers):** native xAI Agent Tools passthrough on `/v1/responses` for `xai` / `xai-oauth` (`xao`) — forward `web_search` + `x_search` to `api.x.ai` instead of rewriting or rejecting them ([#8964](https://github.com/diegosouzapw/OmniRoute/issues/8964))
-- **feat(providers): add UnoRouter provider** — UnoRouter is an OpenAI-compatible routing gateway supporting hundreds of models. It is now registered as an API-key provider. ([#8978](https://github.com/diegosouzapw/OmniRoute/issues/8978))
-- **feat(sse):** deprecated the legacy `gemini-cli` **upstream provider**. It was not routable (no registry entry, no executor), yet the scheduler kept refreshing its token against Google — maintaining a credential that could never serve a request. A stored connection now becomes terminal with a legible reason and a working migration path: re-add the account under `gemini`, which uses the same Google OAuth client. The `gemini-cli` **client identity** (requests arriving *from* the Gemini CLI, issue #7034) is untouched ([#8980](https://github.com/diegosouzapw/OmniRoute/pull/8980))
-- Add a default-off connection setting for Codex, OpenAI, and OpenAI-compatible Responses API providers that preserves client-supplied `reasoning.encrypted_content` items for replay, including per-target combo routing.
-- Omit opaque encrypted reasoning values from persisted call logs while retaining compact diagnostic markers. (#9000)
-- **feat(providers):** add Regolo AI OpenAI-compatible provider ([#9031](https://github.com/diegosouzapw/OmniRoute/issues/9031))
-- **feat(db):** add provider-scoped model aliases that survive rediscovery ([#9068](https://github.com/diegosouzapw/OmniRoute/issues/9068))
-- feat(cursor): surface a dismissible dashboard banner suggesting `cursor-agent` installation when it isn't available, so Cursor connections needing periodic manual reconnection aren't a silent surprise (#9173)
-- feat(cursor): proactively renew Cursor sessions before their ~24h token expires via the token health-check sweep, nudging `cursor-agent` and re-scraping IDE/agent credential sources so connections stop silently expiring (#9173)
-- **feat(codex):** accept parenthesized GPT-5.6 reasoning overrides. (thanks @seakleangnhak) ([#9208](https://github.com/diegosouzapw/OmniRoute/pull/9208))
-- **feat(usage):** surface Claude thinking token counts to clients. (thanks @luoyide) ([#9214](https://github.com/diegosouzapw/OmniRoute/pull/9214))
-- **feat(ollama):** add Ollama Local embedding support via /v1/embeddings. (thanks @HaoNgo232) ([#9225](https://github.com/diegosouzapw/OmniRoute/pull/9225))
-- feat(images): execute full combo strategy + fallback in /v1/images/generations (#9239)
-
-  Adds open-sse/services/imageCombo.ts that expands combo targets, filters to images-capable, executes the priority strategy with handleImageGeneration per target, and returns the first success or last failure. Route patches detect combo names before model resolution and divert to the new execution path.
-- feat: make forwarded upstream response-header budget configurable via env var (#9243)
-- **feat(providers):** filter provider detail connections server-side while preserving full-page search and pagination. (thanks @RobertsXML) ([#9247](https://github.com/diegosouzapw/OmniRoute/pull/9247))
-- **feat(providers):** make video_url passthrough configurable per provider/model via compat override ([#9248](https://github.com/diegosouzapw/OmniRoute/issues/9248)) — thanks @HellFiveOsborn
-- **feat(gemini):** recursive type:object injection in schema normalizer + empty choices interceptor for streaming (#9268)
-- **feat(dashboard):** render a conditional "Get API key" link on the provider detail page, surfaced from the existing `notice.apiKeyUrl` / `notice.signupUrl` catalog metadata (e.g. `pioneer`, `jina`, `together`). The link opens in a new tab and is hidden when neither URL is present, so existing providers are unaffected. Tracks the notice field in `ProviderCatalogMetadata` ([#9270](https://github.com/diegosouzapw/OmniRoute/pull/9270))
-- **feat(providers):** accept JSON cookie objects in normalizeSessionCookieHeader (#9284 — thanks @AIB1TAL0S)
-- **feat(providers):** support max reasoning effort for opencode-zen DeepSeek models (#9318)
-- **feat(providers):** expanded the NanoGPT (`nano-gpt.com`) upstream provider from chat-only to the full OpenAI-compatible endpoint surface: audio transcriptions (`/api/v1/audio/transcriptions`), audio speech (`/api/v1/audio/speech`), video generation (`/api/v1/video/generations`), embeddings (`/v1/embeddings`), and the Responses API (`responsesBaseUrl` → `/api/v1/responses`) ([#9322](https://github.com/diegosouzapw/OmniRoute/issues/9322))
-- **feat(sse):** combo `system_message` supports server-side `{{MODEL_ID}}`, `{{PROVIDER_ID}}`, `{{ACCOUNT}}` and `{{FINGERPRINT}}` template expansion from the actually-routed target ([#5501](https://github.com/diegosouzapw/OmniRoute/issues/5501))
-- **feat(sse):** template expansion covers the standard dispatch loop, round-robin and pinned context-cache sessions; fusion, chaos, pipeline and nested-execute strategies do not expand yet ([#5501](https://github.com/diegosouzapw/OmniRoute/issues/5501)) ([#9414](https://github.com/diegosouzapw/OmniRoute/pull/9414)) — thanks @maxmad64bis
-- **feat(sse):** New-API/One-API/Sub2API aggregator balance detection for compatible provider nodes — when the "Aggregator Gateway" toggle is enabled, OmniRoute queries the aggregator's `/api/user/self` endpoint to detect the account balance; the dashboard shows a balance badge and quota-preflight routing skips exhausted accounts. Gated by the `NEWAPI_AGGREGATOR_BALANCE` feature flag (default: off), with a custom `quotaPerUnit` override for aggregators that use a different rate than the default 500000 units/$1 ([#9415](https://github.com/diegosouzapw/OmniRoute/issues/9415))
-- **feat(catalog):** added opt-in settings `hideAutoCombos` and `hideNoThinkVariants` (default off) to filter built-in `auto/*` virtual combos and `no-think/*` gateway variants from the `/v1/models` catalog — user-defined combos and original provider models stay listed; routing is unaffected ([#9418](https://github.com/diegosouzapw/OmniRoute/issues/9418))
-- **feat(opencode-plugin):** added `features.visibleModels` (allowlist) and `features.hiddenModels` (blocklist) to `@omniroute/opencode-plugin` — curate the OpenCode TUI/CLI model picker from 600+ catalog entries down to an operator-defined ID list that persists in `opencode.json` across config resets ([#9473](https://github.com/diegosouzapw/OmniRoute/issues/9473))
-- **feat(providers):** add native DeepSeek V4 Flash and Pro thinking-effort aliases for their documented per-model tiers, including Combo Builder exposure ([#9485](https://github.com/diegosouzapw/OmniRoute/pull/9485)).
-- feat(opencode-plugin): warm catalog startup from disk snapshot + parallel refresh (#9490)
-
-  The config-shim hook now reads the last disk snapshot before fetching, so the provider registers immediately with the last-known-good catalog (~1-2s vs ~30s on a warm gateway). All six fetchers run concurrently via Promise.allSettled instead of sequentially. A failed refresh keeps the snapshot (no overwrite). An in-flight guard prevents concurrent refreshes for the same cache key. The features.diskCache: false opt-out disables the warm read entirely.
-- **feat(models):** Test All's "Auto-hide failed models" no longer hides quota errors — daily-quota-exhausted and credits-exhausted responses are now classified via the routing path's existing quota detectors, so an evening Test All on a free-tier provider no longer silently wipes the catalog. Quota results stay visible with a distinct amber badge ([#9511](https://github.com/diegosouzapw/OmniRoute/issues/9511))
-- Add an advisory forgotten-sibling-tests report to pull-request quality checks. The report traces changed modules through their static consumers to candidate sibling tests, while keeping barrel and dynamic-import cases non-blocking and requiring reviewed, referenced exceptions. (#9530)
-- feat(providers): add Muse Code CLI provider preset (#9544)
-- feat(plugins): expose client request headers in plugin onRequest/onResponse context (#9570)
-- **feat(plugins):** add onStreamComplete built-in event exposing streaming usage and timing (#9571)
-
-  Adds a new `onStreamComplete` plugin event that fires after an SSE stream is fully
-  consumed, carrying usage token counts and timing metrics (latency, TTFT). Built-in
-  events now include `onStreamComplete` as a fire-and-forget lifecycle hook.
-
-  Payload: `status`, `usage` (prompt_tokens, completion_tokens, reasoning_tokens,
-  cache_read_input_tokens, cache_creation_input_tokens), `timing` (latencyMs, ttft),
-  `model`, `provider`, `errorCode`.
-
-  Non-breaking — existing `onResponse` hooks with `{ streamed: true }` remain unchanged.
-- **feat(audio):** Soniox STT + TTS provider (`sx`) — async speech-to-text (`stt-async-v5`, `stt-async-v4`) and real-time text-to-speech (`tts-rt-v1`) ([#9579](https://github.com/diegosouzapw/OmniRoute/pull/9579))
-- Show cache-read and cache-write token counts in request log rows and details when providers
-  report them. (#9620)
-- feat(memory): support custom OpenAI-compatible endpoints for Memory embeddings (#9622)
-- feat(resilience): add an opt-in watchdog for persistently slow upstream streams (#9709)
-- **Onboarding:** add an explicit, reviewable one-click setup for eligible no-auth LLM providers,
-  with per-provider caution links, selectable confirmation, idempotent creation, and safe partial
-  retries. Existing provider connections are never changed and setup completion never enables
-  providers silently. ([#9752](https://github.com/diegosouzapw/OmniRoute/issues/9752))
-- **feat(settings):** add a dedicated Modality Bridge settings page with Vision controls, runtime stats, and URL-addressable Audio and Video tabs ([#9782](https://github.com/diegosouzapw/OmniRoute/pull/9782))
-- **feat(modality bridge):** Transcribe chat audio for text-only models through the existing speech-to-text providers, with configurable limits, caching, runtime stats, and a dashboard self-test ([#9807](https://github.com/diegosouzapw/OmniRoute/pull/9807))
-- **feat(memory):** `PROVIDERS_SYSTEM_MUST_BE_FIRST` (the #6135/#7293 fix for backends that reject any non-leading `system` message) was hardcoded to `xiaomi-mimo`/`mimo`. Added `OMNIROUTE_STRICT_SYSTEM_PROVIDERS` (comma-separated provider ids) so self-hosted deployments can flag additional strict backends — e.g. a custom OpenAI-compatible connection in front of a self-hosted Qwen3.5+/3.6 model — without forking and rebuilding the image ([#9924](https://github.com/diegosouzapw/OmniRoute/pull/9924))
-- **feat(api):** API keys can disable prompt compression from the dashboard, including for clients that cannot send custom headers ([#10001](https://github.com/diegosouzapw/OmniRoute/pull/10001)) — thanks @shixi-li
-- **Add cliproxy provider exposure controls and manifest injection** (#7329) — thanks @KooshaPari
-- **feat(infra): add a systemd autostart unit for Linux** (#8635)
-- **feat(db): add node sqlite adapter parity** ([#8871](https://github.com/diegosouzapw/OmniRoute/pull/8871)) — thanks @epsilonode
-- **feat(alibaba): free-tier routing with live quota sync** ([#8893](https://github.com/diegosouzapw/OmniRoute/pull/8893)) — thanks @AndrianBalanescu
-- **feat(oauth): add Raycast Pro provider with local auto-import** ([#8895](https://github.com/diegosouzapw/OmniRoute/pull/8895)) — thanks @AndrianBalanescu
-- **feat(executors): add isolated Claude Code bridge over Devin ACP** ([#8914](https://github.com/diegosouzapw/OmniRoute/pull/8914)) — thanks @McLuck
-- **feat: improve provider quota layouts** ([#8916](https://github.com/diegosouzapw/OmniRoute/pull/8916)) — thanks @apoapostolov
-- **feat(mcp): add omniroute_create_combo tool** ([#8925](https://github.com/diegosouzapw/OmniRoute/pull/8925)) — thanks @lucasmellos
-- **feat(ci): gate the publish on clean-install AND upgrade-over-previous** ([#8953](https://github.com/diegosouzapw/OmniRoute/pull/8953))
-- **feat(providers): add Conol (conol.ai) web session provider** ([#8974](https://github.com/diegosouzapw/OmniRoute/pull/8974)) — thanks @artickc
-- **Feat/combo provider wise model test** ([#9011](https://github.com/diegosouzapw/OmniRoute/pull/9011)) — thanks @JoshimOfficial
-- **feat(model-alias): add runtime Model Alias Resolver middleware** ([#9020](https://github.com/diegosouzapw/OmniRoute/pull/9020)) — thanks @Egorich-print
-- **feat(i18n): complete zh-CN localization for compression engines and dashboard UI** ([#9038](https://github.com/diegosouzapw/OmniRoute/pull/9038)) — thanks @qianze0628
-- **feat: Cheaper Inference provider (chat + native Responses + images, sponsor rail 2nd)** ([#9043](https://github.com/diegosouzapw/OmniRoute/pull/9043))
-- **feat(providers): add comprehensive support for self-hosted Firecrawl via FIRECRAWL_BASE_URL and custom base URLs** ([#9052](https://github.com/diegosouzapw/OmniRoute/pull/9052)) — thanks @mad-gooze
-- **feat(dahl): add manual API key option alongside auto-generated token** ([#9077](https://github.com/diegosouzapw/OmniRoute/pull/9077)) — thanks @pizzav-xyz
-- **feat(ci): G0 — reforça o trilho PR→release/**** ([#9108](https://github.com/diegosouzapw/OmniRoute/pull/9108))
-- **feat(providers): native xAI Agent Tools passthrough for /v1/responses** ([#9111](https://github.com/diegosouzapw/OmniRoute/pull/9111)) — thanks @VXNCXNX
-- **feat(.50): completa itens restantes — G13, G14, gap34, docs, R0.2** ([#9126](https://github.com/diegosouzapw/OmniRoute/pull/9126))
-- **feat(g1): rewrite combo-strategy check to runtime-import approach** ([#9131](https://github.com/diegosouzapw/OmniRoute/pull/9131))
-- **feat(test:scoped): TIA-based local test runner (#8084 D1)** ([#9143](https://github.com/diegosouzapw/OmniRoute/pull/9143))
-- **feat(docker): publish next from active release branches** ([#9181](https://github.com/diegosouzapw/OmniRoute/pull/9181)) — thanks @Zartharas
-- **feat(usage): show Grok Build billing limits** ([#9205](https://github.com/diegosouzapw/OmniRoute/pull/9205)) — thanks @xz-dev
-- **feat(models): functional gateway mirrors + fix synced-substitution** ([#9217](https://github.com/diegosouzapw/OmniRoute/pull/9217))
-- **feat(admission): add adaptive overload protection for LLM routes** ([#9262](https://github.com/diegosouzapw/OmniRoute/pull/9262)) — thanks @xz-dev
-- **feat(i18n): update italian translations** ([#9280](https://github.com/diegosouzapw/OmniRoute/pull/9280)) — thanks @Gecky2102
-- **feat(dashboard): persist provider screen filters to URL for bookmarking** ([#9307](https://github.com/diegosouzapw/OmniRoute/pull/9307)) — thanks @swingtempo
-- **feat(api-manager): add provider-level model permissions** ([#9313](https://github.com/diegosouzapw/OmniRoute/pull/9313)) — thanks @xz-dev
-- **feat(warmup): proactive Claude warmup scheduler (#8848)** ([#9449](https://github.com/diegosouzapw/OmniRoute/pull/9449)) — thanks @HouMinXi
-- **feat(infra): add systemd autostart unit for Linux (#8635)** ([#9466](https://github.com/diegosouzapw/OmniRoute/pull/9466))
-- **feat(lib): make MODELS_DEV_SYNC_ENABLED actually control the sync** ([#9483](https://github.com/diegosouzapw/OmniRoute/pull/9483)) — thanks @HouMinXi
-- **feat(radar): flag-gated signed free-model catalog overlay** ([#9515](https://github.com/diegosouzapw/OmniRoute/pull/9515))
-- **feat(compression): add Russian language pack** ([#9581](https://github.com/diegosouzapw/OmniRoute/pull/9581)) — thanks @vinogradovnet
-- **feat(providers): integrate wave4 free-tier gateways** ([#9584](https://github.com/diegosouzapw/OmniRoute/pull/9584))
-- **feat(providers): add Zylo UnoRouter and Poolside registries** ([#9585](https://github.com/diegosouzapw/OmniRoute/pull/9585))
-- **feat(providers): add FastRouter AnyAPI and ElectronHub registries** ([#9586](https://github.com/diegosouzapw/OmniRoute/pull/9586))
-- **feat(providers): add LLMGateway and LLM Kiwi registries** ([#9587](https://github.com/diegosouzapw/OmniRoute/pull/9587))
-- **feat(providers): add FreeInference registry** ([#9594](https://github.com/diegosouzapw/OmniRoute/pull/9594))
-- **feat(radar): contributor + supporter claim buttons on the activation screen (F4/T7)** ([#9710](https://github.com/diegosouzapw/OmniRoute/pull/9710))
-- **feat(radar): paste-key input on the activation screen (F4)** ([#9758](https://github.com/diegosouzapw/OmniRoute/pull/9758))
-- **feat(guardrails): modality bridge core — vision mode/task-aware/cache/input_image + modalityBridge settings** ([#9759](https://github.com/diegosouzapw/OmniRoute/pull/9759))
-- **feat(radar): referrals from standalone /v1/referrals feed (no 30-day delay)** ([#9762](https://github.com/diegosouzapw/OmniRoute/pull/9762))
-- **feat: generic OpenAI-compatible video custom provider** ([#9844](https://github.com/diegosouzapw/OmniRoute/pull/9844), original [#9818](https://github.com/diegosouzapw/OmniRoute/pull/9818)) — thanks @oyi77
-- **feat(logging): make the chat-log truncation limit configurable, bumped default 128x** ([#9863](https://github.com/diegosouzapw/OmniRoute/pull/9863), original [#9738](https://github.com/diegosouzapw/OmniRoute/pull/9738)) — thanks @hartmark
-- **feat(logging): bump CHAT_LOG_ARRAY_TAIL_ITEMS default 24 -> 128** ([#9864](https://github.com/diegosouzapw/OmniRoute/pull/9864), original [#9735](https://github.com/diegosouzapw/OmniRoute/pull/9735)) — thanks @hartmark
-- **feat(oauth): add Openference OAuth and API key provider integration** ([#9869](https://github.com/diegosouzapw/OmniRoute/pull/9869), original [#9722](https://github.com/diegosouzapw/OmniRoute/pull/9722)) — thanks @AnhLead
-- **feat(src): proxy-pool-toolbar-minor-improvements** ([#9870](https://github.com/diegosouzapw/OmniRoute/pull/9870), original [#9718](https://github.com/diegosouzapw/OmniRoute/pull/9718)) — thanks @AgnesRiber
-- **feat(resilience): expose providerQuotaOverrides via /api/resilience** ([#9871](https://github.com/diegosouzapw/OmniRoute/pull/9871), original [#9714](https://github.com/diegosouzapw/OmniRoute/pull/9714)) — thanks @herjarsa
-- **feat(responses): add encrypted reasoning replay opt-in** ([#9876](https://github.com/diegosouzapw/OmniRoute/pull/9876), original [#9601](https://github.com/diegosouzapw/OmniRoute/pull/9601)) — thanks @jackjinke
-- **feat(resilience): add per-account resilience connections view (API + dashboard)** ([#9880](https://github.com/diegosouzapw/OmniRoute/pull/9880), original [#9510](https://github.com/diegosouzapw/OmniRoute/pull/9510)) — thanks @HouMinXi
-- **feat(db): add a job registry for scheduled background work** ([#9886](https://github.com/diegosouzapw/OmniRoute/pull/9886), original [#9631](https://github.com/diegosouzapw/OmniRoute/pull/9631)) — thanks @HouMinXi
-- **feat(telegram): Mini App chat bridge — initData auth, update webhook, chat proxy** ([#9907](https://github.com/diegosouzapw/OmniRoute/pull/9907), original [#9812](https://github.com/diegosouzapw/OmniRoute/pull/9812)) — thanks @benzntech
-- **feat(cursor): exclusive live listing + verbatim AgentRun model ids** ([#9911](https://github.com/diegosouzapw/OmniRoute/pull/9911)) — thanks @yansigit
-- **feat(usage): add Command Code quota tracking** ([#9921](https://github.com/diegosouzapw/OmniRoute/pull/9921)) — thanks @yansigit
-- **feat(combo): add quota-only priority fallback** ([#9983](https://github.com/diegosouzapw/OmniRoute/pull/9983)) — thanks @xz-dev
-- **feat(onboarding): add one-click free provider setup** ([#10014](https://github.com/diegosouzapw/OmniRoute/pull/10014))
-- **feat(admission) — direct pushes:** adaptive overload/pressure controls with shared admission wired across the LLM routes, plus mutation-test registration for the capability-filter suite
-- **feat(agentrouter) — direct pushes:** support Claude and Codex protocols — infer the protocol from the client endpoint and honor the alternate protocol through the chat pipeline
-- **feat(providers) — direct pushes:** ChatGPT Web session credential guide with a Cookie Editor fast-path (canonical chromewebstore install link) and web-session fast-path test coverage
-- **feat(sse):** honor provider-rule lock scope for agentrouter (connection vs model) ([#10419](https://github.com/diegosouzapw/OmniRoute/pull/10419))
-- **feat(ocr):** Vertex AI DeepSeek-OCR provider ([#10398](https://github.com/diegosouzapw/OmniRoute/pull/10398))
-- **feat(providers):** derive imageToText from the OCR registry + chutes dots.ocr seed ([#10400](https://github.com/diegosouzapw/OmniRoute/pull/10400))
-- **feat(ocr):** multi-provider /v1/ocr with transformation layer (Azure Document Intelligence) ([#10283](https://github.com/diegosouzapw/OmniRoute/pull/10283))
-- **feat(providers):** declare imageToText serviceKind on major vision providers ([#10275](https://github.com/diegosouzapw/OmniRoute/pull/10275))
-- **feat(bridge):** native-vision skip guard + configurable describe output cap ([#10289](https://github.com/diegosouzapw/OmniRoute/pull/10289))
-- **feat(bridge):** normalize images to 2048px long edge before vision describe self-call ([#10287](https://github.com/diegosouzapw/OmniRoute/pull/10287))
-- **feat(sse):** restate agentrouter quota 403/400 as retryable 429 with provider-scoped error rules ([#10335](https://github.com/diegosouzapw/OmniRoute/pull/10335))
-- **feat(sse):** add i-have-adhd output style to compression catalog ([#10271](https://github.com/diegosouzapw/OmniRoute/pull/10271))
-- **feat(codex):** add OAuth fingerprint convergence modes ([#10243](https://github.com/diegosouzapw/OmniRoute/pull/10243)) — thanks @xz-dev
-- **feat(i18n):** complete Portuguese (PT-PT) translation ([#10250](https://github.com/diegosouzapw/OmniRoute/pull/10250)) — thanks @DarkEsteves
-- **feat(providers):** publish Poolside's probed Laguna Preview catalog ([#10216](https://github.com/diegosouzapw/OmniRoute/pull/10216)) — thanks @pacocartones
-- **feat(crof):** advertise reasoning effort tiers incl. max from live discovery and registry ([#10062](https://github.com/diegosouzapw/OmniRoute/pull/10062)) — thanks @excessivechaos
-- **feat(open-sse):** expose provider-level circuit breaker thresholds via env vars (#10040) ([#10046](https://github.com/diegosouzapw/OmniRoute/pull/10046)) — thanks @tiangao88
-- **feat(dashboard):** Kimi 15% first-top-up campaign — dedicated tracked link + discount-first banner copy ([#10240](https://github.com/diegosouzapw/OmniRoute/pull/10240))
-- **feat(providers):** integrate audited free-tier gateways ([#9210](https://github.com/diegosouzapw/OmniRoute/pull/9210))
-
-<!-- reconciliation pass 2 (Phase 0a.1): commits that landed in the cycle without a bullet -->
-
-- **feat(radar):** **OmniRoute Radar** — the signed free-model catalog overlay — landed end to end this cycle: local catalog state is persisted, guided combo suggestions feed a guided combos page, guided provider setup walks a new operator through connecting, verified model metadata and an owner-only admin link are surfaced, signed supporter offers get their own dashboard and sync path, signed Intel insights arrive with a supporter-recognition UI, a launch-news surface was added, and catalog export runs through a stable workflow that carries provenance ([#10826](https://github.com/diegosouzapw/OmniRoute/issues/10826)). The catalog is also reachable as an MCP tool and through the new `radar status` / `radar sync` CLI commands.
-- **feat(video):** Video Bridge gained a full sampling and caching stack — scene-aware and segment-aware sampling with a structural fallback, conservative frame deduplication, validated focus windows, timestamped contact sheets, and an optional audio-fusion timeline that preserves transcript provenance, reports fusion telemetry, and degrades to *partial* on invalid audio. Results are cached with metadata (the key includes the audio transcript and focus window), and drill-downs use an isolated cache bounded by a global byte budget; a sampler/contact-sheet benchmark script ships alongside ([#10483](https://github.com/diegosouzapw/OmniRoute/issues/10483)) — thanks @backryun
-- **feat(volcengine):** Volcengine **Ark plan providers** — live model discovery through `ListAgentPlanLatestModel` (retaining only API-callable Agent Plan models) and phone/SMS console auto-login with MFA and identity selection ([#11333](https://github.com/diegosouzapw/OmniRoute/issues/11333) — thanks @rengaryang)
-- **feat(providers):** new upstreams this cycle — **Token Kiosk** as an OpenAI-compatible provider ([#10722](https://github.com/diegosouzapw/OmniRoute/issues/10722) — thanks @hgaib), a local **ZCode ACP** backend ([#10184](https://github.com/diegosouzapw/OmniRoute/issues/10184) — thanks @megamen32), and the **tencent-aistudio-web** cookie provider (`tasw`) ([#10174](https://github.com/diegosouzapw/OmniRoute/issues/10174) — thanks @MeRezaRezaei)
-- **feat(providers):** Cursor PKCE login with Bearer quota reporting, automatic router selection and explicit empty-turn errors ([#9909](https://github.com/diegosouzapw/OmniRoute/issues/9909) — thanks @yansigit); `cursor` also discovers the account's Agent endpoint instead of assuming one ([#10804](https://github.com/diegosouzapw/OmniRoute/issues/10804) — thanks @tuandinh0801)
-- **feat(providers):** tool calling for `copilot-m365-web` via router planning ([#10948](https://github.com/diegosouzapw/OmniRoute/issues/10948) — thanks @acc0mplish)
-- **feat(providers):** per-connection upstream timeout tier is back — a connection can again override the provider-wide request timeout ([#10885](https://github.com/diegosouzapw/OmniRoute/issues/10885) — thanks @maxmad64bis)
-- **feat(providers):** catalog refreshes — Qwen3.8 model catalogs ([#10226](https://github.com/diegosouzapw/OmniRoute/issues/10226)), Grok 4.6 plus a DeepSeek V4 refresh ([#10195](https://github.com/diegosouzapw/OmniRoute/issues/10195)) — thanks @backryun — and the `agnes` chat catalog moved to the 2026-07-30 listing ([#10942](https://github.com/diegosouzapw/OmniRoute/issues/10942) — thanks @oyi77)
-- **feat(providers):** the web-session credential guide gained a Cookie Editor fast path, so cookie-based providers can be connected without hand-copying headers — thanks @benzntech
-- **feat(sse):** explicit `glm-5.3-max` reasoning-effort tier ([#11415](https://github.com/diegosouzapw/OmniRoute/issues/11415) — thanks @phuongddx)
-- **feat(sse):** discover Anthropic partner models served through Vertex AI ([#11279](https://github.com/diegosouzapw/OmniRoute/issues/11279) — thanks @maci0)
-- **feat(sse):** opt-in `STRICT_ZERO_COST` free-access policy — refuses any target that is not verifiably zero-cost ([#10965](https://github.com/diegosouzapw/OmniRoute/issues/10965) — thanks @mymusicmyspace)
-- **feat(sse):** Kimi Web token lifecycle manager — rolling auto-refresh and 401 recovery, so `kimi-web` connections stop expiring silently ([#10944](https://github.com/diegosouzapw/OmniRoute/issues/10944) — thanks @MeRezaRezaei)
-- **feat(sse):** Cursor plan images through the Agent CLI (`IMAGE_PROVIDERS.cursor`) ([#10842](https://github.com/diegosouzapw/OmniRoute/issues/10842)), and the `i-have-adhd` output style reached vi/ja/id parity behind a style × language guard matrix ([#10425](https://github.com/diegosouzapw/OmniRoute/issues/10425))
-- **feat(api):** health and liveness surface — `GET /livez` as a process-alive probe ([#10819](https://github.com/diegosouzapw/OmniRoute/issues/10819)), `GET/HEAD /readyz` aliased to `/healthz` ([#10977](https://github.com/diegosouzapw/OmniRoute/issues/10977)), and `GET /api/health` answering without a key ([#10771](https://github.com/diegosouzapw/OmniRoute/issues/10771)) — thanks @RaviTharuma and @maxmad64bis
-- **feat(api):** `/v1/multimodal-embeddings` is now an alias of `/v1/embeddings` ([#10568](https://github.com/diegosouzapw/OmniRoute/issues/10568) — thanks @RaviTharuma), and `/v1/combos` steps flag a pinned account without leaking its id ([#11076](https://github.com/diegosouzapw/OmniRoute/issues/11076) — thanks @ntdatt812)
-- **feat(audio):** native ElevenLabs HTTP compatibility routes ([#11312](https://github.com/diegosouzapw/OmniRoute/issues/11312)), Google AI Studio Gemini TTS ([#11315](https://github.com/diegosouzapw/OmniRoute/issues/11315)), and `response_format=ogg` accepted as an opus alias on `/v1/audio/speech` ([#10822](https://github.com/diegosouzapw/OmniRoute/issues/10822)) — thanks @RaviTharuma
-- **feat(gemini-web):** image generation exposed through `/v1/images/generations` ([#10494](https://github.com/diegosouzapw/OmniRoute/issues/10494) — thanks @Abhishek4512009)
-- **feat(cli):** native Bun backend support plus `Dockerfile.bun` ([#11039](https://github.com/diegosouzapw/OmniRoute/issues/11039) — thanks @rqzbeh), with matching `-bun` / `-web-bun` container images published by the Docker workflow ([#11168](https://github.com/diegosouzapw/OmniRoute/issues/11168))
-- **feat(cli):** tray mode detaches from the terminal ([#11230](https://github.com/diegosouzapw/OmniRoute/issues/11230) — thanks @tuandinh0801), Grok Build accepts a custom host ([#10830](https://github.com/diegosouzapw/OmniRoute/issues/10830) — thanks @tuandinh0801), and Linux autostart inherits the login shell `PATH` ([#11372](https://github.com/diegosouzapw/OmniRoute/issues/11372) — thanks @ziuus)
-- **feat(cli):** relay-like CLI closure — a target manifest, Codex TOML generation, a Gemini launcher and drift guards, so `omniroute run <cli>` covers the documented agent surface — thanks @backryun
-- **feat(dashboard):** beginner-oriented UX pass across the app — a guided endpoint-connection header ([#11228](https://github.com/diegosouzapw/OmniRoute/issues/11228)), a stable outcome header on the batch page ([#11227](https://github.com/diegosouzapw/OmniRoute/issues/11227)), plain-language verdicts for health status ([#11224](https://github.com/diegosouzapw/OmniRoute/issues/11224)) and for the resilience page ([#11215](https://github.com/diegosouzapw/OmniRoute/issues/11215)), orientation before API-key management ([#11195](https://github.com/diegosouzapw/OmniRoute/issues/11195)), and ACP framed as optional advanced setup ([#11206](https://github.com/diegosouzapw/OmniRoute/issues/11206)) — thanks @ignamiranda
-- **feat(dashboard):** agentic conversation tracking ([#10263](https://github.com/diegosouzapw/OmniRoute/issues/10263) — thanks @hartmark), a Recent Requests panel on the home page ([#10900](https://github.com/diegosouzapw/OmniRoute/issues/10900)), a VS Code Copilot Chat home banner replacing the Provider Quota card ([#10520](https://github.com/diegosouzapw/OmniRoute/issues/10520)), a CheaperInference sponsor banner with its links routed through the branded shortener ([#11196](https://github.com/diegosouzapw/OmniRoute/issues/11196), [#11329](https://github.com/diegosouzapw/OmniRoute/issues/11329)), and Auto-Combo snapshot generation/duplication in the UX ([#10354](https://github.com/diegosouzapw/OmniRoute/issues/10354) — thanks @swingtempo)
-- **feat(routing):** quota-aware provider scheduling, phase 2 ([#10126](https://github.com/diegosouzapw/OmniRoute/issues/10126) — thanks @benzntech); exclusive managed-session connection leases so two sessions cannot claim the same account ([#10362](https://github.com/diegosouzapw/OmniRoute/issues/10362) — thanks @KaspaPulse); an adaptive feedback loop v2 scoring operational and semantic quality, confidence and TTFT/ITL ([#10881](https://github.com/diegosouzapw/OmniRoute/issues/10881) — thanks @Egorich-print); and a `DISABLE_CONTEXT_WINDOW_CHECKS` bypass for the direct-request input/context check ([#10927](https://github.com/diegosouzapw/OmniRoute/issues/10927))
-- **feat(combo):** an opaque per-invocation decision trace for priority fallbacks, so an operator can see why a combo picked the target it picked without exposing account identities ([#10730](https://github.com/diegosouzapw/OmniRoute/issues/10730) — thanks @stanleytejakusuma)
-- **feat(admission):** adaptive overload and pressure controls wired across the LLM routes, with a monitoring snapshot exposing the structural chat-admission state and shed counters ([#11268](https://github.com/diegosouzapw/OmniRoute/issues/11268)); Responses and Messages bodies are reserved before clone ([#10814](https://github.com/diegosouzapw/OmniRoute/issues/10814) — thanks @RaviTharuma) and structural chat-admission shedding is gated on real heap pressure ([#10437](https://github.com/diegosouzapw/OmniRoute/issues/10437)) — thanks @xz-dev
-- **feat(compression):** adopts omniglyph 1.4.0 with semantic profiles and evidence-backed accounting ([#10647](https://github.com/diegosouzapw/OmniRoute/issues/10647)), and the sync engines now run in a bounded worker pool instead of on the request thread ([#11318](https://github.com/diegosouzapw/OmniRoute/issues/11318) — thanks @RaviTharuma)
-- **feat(models):** learned `reasoning_effort` sets are surfaced in the catalog, in model variants and at dispatch ([#11252](https://github.com/diegosouzapw/OmniRoute/issues/11252) — thanks @maxmad64bis); `opencode-go` and `command-code` expose Muse Spark reasoning-effort aliases/suffixes ([#10883](https://github.com/diegosouzapw/OmniRoute/issues/10883), [#10884](https://github.com/diegosouzapw/OmniRoute/issues/10884) — thanks @excessivechaos)
-- **feat(search):** `context7` added as a library-docs search and fetch provider ([#11140](https://github.com/diegosouzapw/OmniRoute/issues/11140) — thanks @HouMinXi)
-- **feat(mcp):** dynamic runtime tool-schema plumbing so blocked providers are removed from the advertised enums instead of failing at call time ([#11155](https://github.com/diegosouzapw/OmniRoute/issues/11155) — thanks @rqzbeh), plus a Radar catalog tool
-- **feat(a2a):** A2A v1.0 client compatibility — a `SendMessage` alias and a v1.0-shaped agent card ([#10839](https://github.com/diegosouzapw/OmniRoute/issues/10839) — thanks @wpec)
-- **feat(server):** native systemd `sd_notify` watchdog support (`Type=notify`), so a stalled process is restarted by the supervisor rather than hanging ([#10662](https://github.com/diegosouzapw/OmniRoute/issues/10662) — thanks @maxmad64bis)
-- **feat(redis):** configurable key namespace prefix, so several OmniRoute instances can share one Redis ([#11042](https://github.com/diegosouzapw/OmniRoute/issues/11042) — thanks @MeRezaRezaei)
-- **feat(docker):** hardened Linux VPS deployment recipe ([#10623](https://github.com/diegosouzapw/OmniRoute/issues/10623) — thanks @freudantunes)
-- **feat(proxy):** anonymous egress-IP sharing surfaced in the health sweep and the egress API ([#10876](https://github.com/diegosouzapw/OmniRoute/issues/10876) — thanks @maxmad64bis), and a non-destructive auto-disable mode for the proxy health scheduler ([#10342](https://github.com/diegosouzapw/OmniRoute/issues/10342) — thanks @Gi99lin)
-- **feat(services):** sanitized CLIProxyAPI account health exposed to the dashboard ([#11314](https://github.com/diegosouzapw/OmniRoute/issues/11314) — thanks @RaviTharuma)
-- **feat(db):** the DB health check now reports which SQLite driver is active and what durability it gives you ([#10652](https://github.com/diegosouzapw/OmniRoute/issues/10652) — thanks @maxmad64bis)
-- **feat(codex):** sync with Codex v178 identity mechanisms — turn-state relay, persisted seeds and identity faces ([#10716](https://github.com/diegosouzapw/OmniRoute/issues/10716) — thanks @xz-dev)
-- **feat(usage):** Kimi Coding "Extra Usage" is shown on the provider card ([#10712](https://github.com/diegosouzapw/OmniRoute/issues/10712) — thanks @xz-dev)
-- **feat(oauth):** `gemini-3.7-flash` models added for the `antigravity` and `agy` providers ([#10305](https://github.com/diegosouzapw/OmniRoute/issues/10305) — thanks @Chewji9875)
-- **feat(cli-tools):** Prime Agent added to the CLI agents catalog ([#11166](https://github.com/diegosouzapw/OmniRoute/issues/11166) — thanks @arminanton)
-- **feat(guardrails):** a focused video-analysis mode for the vision guardrail, so long videos are judged on the requested window instead of the whole timeline
-- **feat(ops):** canary deploy path with a provenance gate, a real smoke run and a rollback anchor ([#10446](https://github.com/diegosouzapw/OmniRoute/issues/10446)), backed by artifact provenance verification and a `buildSha` on the health endpoint ([#10444](https://github.com/diegosouzapw/OmniRoute/issues/10444))
-- **feat(api):** list embeddings models from the configured providers ([#11249](https://github.com/diegosouzapw/OmniRoute/issues/11249)) and guided Qdrant memory configuration ([#11213](https://github.com/diegosouzapw/OmniRoute/issues/11213)) — thanks @rafacpti23
-- **feat(responses):** `previous_response_id` continuation is virtualized even when the upstream does not support it ([#10262](https://github.com/diegosouzapw/OmniRoute/issues/10262) — thanks @hartmark)
-
-### 🐛 Bug Fixes
-
-- **fix(build):** every route no longer answers HTTP 500 on artifacts built from the release tip ([#11343](https://github.com/diegosouzapw/OmniRoute/issues/11343)) — `next.config.mjs` aliased `better-sqlite3` to its build-time stub **unconditionally**, on the premise that `serverExternalPackages` still won at runtime. It does not: a Turbopack `resolveAlias` rewrites the request *before* the externals check, so the request stopped matching the `better-sqlite3` external entry and the stub was baked into the shipped bundle. The sync driver then failed with `r(...) is not a constructor`, fell through `node:sqlite` and sql.js, and the instrumentation hook aborted at boot. Same failure shape as [#6344](https://github.com/diegosouzapw/OmniRoute/issues/6344), so it gets the same treatment: the alias is opt-in via `OMNIROUTE_BETTER_SQLITE3_STUB=1` through the shared `scripts/build/better-sqlite3-stub-flag.mjs` helper — set it only on a build host that actually hits the SIGABRT build-worker teardown ([#10060](https://github.com/diegosouzapw/OmniRoute/issues/10060)); default builds externalize the real native addon. Regression guards: `tests/unit/better-sqlite3-stub-alias-11343.test.mjs` (5) and the env matrix in `tests/unit/next-config.test.ts`.
-- **security(search)**: block SSRF via `/v1/search` `provider_options.baseUrl` for the Firecrawl search provider — the client-controlled override is now validated as a public URL before it is used to build the server-side fetch target, so a caller with a valid API key can no longer redirect search requests at loopback, RFC1918, or cloud-metadata hosts — thanks @zmf963
-- **providers**: honor `PATCH /api/providers/[id]` so `omniroute providers rotate` stops 405ing (the OpenAPI spec and CLI already use PATCH) (PR #10366)
-- **cli**: route provider test commands through configured connection test endpoints (#10570)
-- **executors**: fix internal timeout misclassified as client disconnect (499) for 7 niche executors — pass TimeoutError reason to controller.abort() (#8197 side-finding)
-- test(combo): guard auto/best-free never leaks the combo name as a model (#7754)
-- fix(vision-bridge): describe-model no longer returns unreachable "openai/gpt-4o-mini" when every vision-capable provider is unreachable on the instance — returns null instead and surfaces a clear error (#8430)
-- fix(vision-bridge): validate fixedModel against usable credentials before short-circuiting in getBestVisionModel, so the default "openai/gpt-4o-mini" is not unconditionally selected when no OpenAI connection exists (#8430)
-- fix(vision-bridge): in the combo describe path, replace raw images with an error text stub when all describe attempts fail, instead of forwarding images to a confirmed non-vision backend that would reject them with an opaque serde error (#8430)
-- fix(quality): add base-relative file-size check so inherited drift does not red innocent PRs (#8522)
-- fix(ci): aggregate all fast-gates into non-fail-fast loop so one red gate no longer masks later gates (#8542)
-- fix(tests): make machineId tests macOS-compatible by stubbing ioreg in test helper (#8577)
-- fix(scripts): replace bash 4+ readarray with compatible while-read loop in restore-policies.sh (#8577)
-- fix(cli): enable systray2 on Windows for Norton-friendly tray (#8609)
-- fix(executor): guard claude/anthropic buildHeaders against empty credentials and extend dual-Bearer parity for third-party baseUrls (#8653)
-- fix(providers): gate premium opencode-zen/opencode-go models behind an API key (#8681)
-- **fix(api):** make `/v1/models` stale refresh response-safe and generation-safe, with narrow synced-model invalidation ([#8728](https://github.com/diegosouzapw/OmniRoute/pull/8728)). Related to #8697.
-- fix(yuanbao-web): accept `content` field in SSE text events (upstream format change) (#8739)
-- fix(build): remove misleading open-sse/package.json facade and add workspace typecheck gate (#8781)
-- fix(errorClassifier): classify ChatGPT Web SENTINEL_BLOCKED 403 as terminal FORBIDDEN, enabling proper combo fallback (#8813)
-- fix(cli): fall back to node:sqlite when better-sqlite3 constructor throws at runtime (#8826)
-- fix(opencode): prefix provider id with "opencode-" for auth login command (#8830)
-- fix(opencode-zen): add current free-tier models to registry to enable combo context pre-filtering (#8841)
-- **fix(api):** Let image and video providers enforce their own request-size limits instead of rejecting media payloads at OmniRoute's 10 MB global default ([#8843](https://github.com/diegosouzapw/OmniRoute/pull/8843)) — thanks @artickc
-- fix(build): include better-sqlite3 prebuilds in standalone bun bundle (#8847)
-- fix(proxy-health): include credentials in proxy health check URLs (#8853)
-- **fix(build):** `prepublish` no longer spawns the Windows `.cmd` shims for npm/npx, which Node >= 20 refuses to launch without a shell (`EINVAL`). On Node 24 that silently skipped the MITM utilities, the MCP server bundle, the LLMLingua ONNX worker and `@omniroute/opencode-plugin` while `build:cli` still exited 0 and reported success. Build tools are now resolved to their own JS entry point and run with the current Node binary — no shim, no shell, no unescaped arguments. (thanks @maisdesign) ([#8858](https://github.com/diegosouzapw/OmniRoute/pull/8858)) — thanks @maisdesign
-- **fix(opencode):** generate schema-complete model limits so OpenCode accepts catalog entries without an explicit output cap ([#8869](https://github.com/diegosouzapw/OmniRoute/pull/8869)) — thanks @xiaoyaner0201
-- **fix(cli):** default omitted Codex CLI wire API settings to Responses and clear stale Chat state after reset ([#8876](https://github.com/diegosouzapw/OmniRoute/pull/8876)) — thanks @xiaoyaner0201
-- **fix(proxy):** isolate new proxy credential fields from browser and password-manager autofill after form reset ([#8883](https://github.com/diegosouzapw/OmniRoute/pull/8883)) — thanks @xiaoyaner0201
-- fix(db): invalidate stale LKGP pins when provider connections are deleted (#8887)
-- fix(tests): update stale nightly compat fixtures and goldens to match current source constants (#8901)
-- **fix(quota):** Deleting a quota pool now removes its scoped managed combos without racing in-flight pool mutations ([#8906](https://github.com/diegosouzapw/OmniRoute/pull/8906)) — thanks @xiaoyaner0201
-- **fix(executors):** Vertex AI now routes Claude models through the native Anthropic `rawPredict` endpoint instead of the generic OpenAI-compatible partner endpoint, and synthesizes a real streaming response so Claude-via-Vertex works with `stream: true` ([#8909](https://github.com/diegosouzapw/OmniRoute/pull/8909)) — thanks @wgordon17
-- **fix(providers):** expose both OAuth Connect and manual API-key actions for dual-auth providers such as CodeBuddy CN ([#8921](https://github.com/diegosouzapw/OmniRoute/pull/8921)) — thanks @Llliao1113
-- fix(compression): drop orphan custom_tool_call/local_shell_call/apply_patch_call on compaction restore (#8946)
-- fix(auth): setting first dashboard login password no longer fails with HTTP 400 PASSWORD_REQUIRED (#8950)
-- fix(github): add targetFormat to GPT-5.6 Sol/Terra/Luna models (#8951)
-- fix(auto-update): skip synthetic Next.js standalone package.json without `name` field in resolveProjectRoot (#8956)
-- fix(opencode): propagate vision capability from live catalog into opencode.json (#8960)
-- fix(providers): switch Antigravity quota RPCs to iterate ANTIGRAVITY_RUNTIME_BASE_URLS (#8965)
-- **fix(oauth):** GHE Copilot OAuth lifecycle — connecting an account and refreshing its token both failed. Adding a connection died with `gheUrl is required for GHE Copilot OAuth` because the poll handler's `ghe-copilot` branch was unreachable dead code: the provider is listed in `NO_PKCE_DEVICE_CODE_PROVIDERS`, and that set-based check ran first, calling `pollForToken()` without the `extraData` carrying `gheUrl`. Separately, every manual `Refresh` click surfaced `Token refresh failed — provider returned no new token`, and the proactive pre-request refresh never fired for GHE connections — the manual route, the health-check sweep and `checkAndRefreshToken()` all still special-cased plain `github`, while GHE Copilot's device-code flow never yields a `refresh_token` (only a GitHub access token plus a short-lived Copilot sub-token). `refreshCopilotToken()` now takes an optional `baseUrl` so it can target a GHE host's `<gheUrl>/api/v3` Copilot token endpoint, and `ghe-copilot` is wired in alongside `github` at all four sites.
-- **fix(health-check):** the access-token-only branch of the token health-check sweep no longer logs an unconditional `has no refresh token but has a GitHub access token` line on every tick. That path runs once per 60 s sweep for every `github` / `ghe-copilot` connection, so it emitted ~1440 identical entries per day per connection reporting that nothing had changed. It now logs only when the sweep actually attempted a Copilot sub-token refresh, and says whether that refresh succeeded or failed — so a genuine failure still surfaces instead of being buried in steady-state noise. ([#8970](https://github.com/diegosouzapw/OmniRoute/pull/8970)) — thanks @hppsc1215
-- fix(providers): copilot-m365-web enterprise turns send disconnectBehavior=continue (#8971)
-- **fix(ci):** the reconciliation helper no longer bounds its scan with `git describe --tags` — releases squash-merge, so that range re-listed 1361 commits instead of the cycle's real 22, which is how ~200 PRs once slipped through without a changelog bullet. The base is now resolved from the commit that opened the cycle, and a new `sweep:stale-fragments` gate removes `changelog.d/` fragments that a back-merge from `main` resurrected after they had already been folded in ([#8985](https://github.com/diegosouzapw/OmniRoute/pull/8985))
-- **fix(ci):** fixed a live auto-update defect where **Intel Macs downloaded the ARM dmg** — the two macOS jobs each emitted their own `latest-mac.yml` and `merge-multiple` let one silently overwrite the other by arrival order, leaving `electron-updater`'s arch fallback pointing at the wrong build. The manifests are now merged deliberately, un-suffixed entry first. Also: test jobs pinned to hosted runners (`setup-node` measured 20m06s self-hosted vs 16s hosted), the npm publish no longer discards a valid build artifact because an unrelated shard was flaky, the agent-skills gate now runs on pushes to `main` instead of PRs only, and the CI summary names every job that ended cancelled ([#8988](https://github.com/diegosouzapw/OmniRoute/pull/8988))
-- **fix(sse):** `stripResponsesLifecycleEcho` no longer strips `tools` from the `response.completed` snapshot — that terminal event is what Codex CLI rebuilds its tool list from, so stripping it left the client with zero tools. `tools` is still stripped from `response.created`/`response.in_progress`, and `instructions` (the >100KB size lever) is still stripped from all three ([#8990](https://github.com/diegosouzapw/OmniRoute/pull/8990))
-- fix(vertex): route Claude models to native rawPredict endpoint and respect custom targetFormat overrides (#8994)
-- fix(proxies): resolveProxyForConnection now returns the proxy name, so the dashboard badge shows the name instead of the hostname (#8995)
-- **fix(translator):** the Responses-to-Chat promotion path called `normalizeResponsesReasoningEffort` without the model argument, so GPT-5.6 Sol/Terra/Luna requests with `reasoning.effort: "max""` were downgraded to `"xhigh"`. The model is now threaded through, preserving `max` for GPT-5.6 while keeping the legacy downgrade for older models ([#8997](https://github.com/diegosouzapw/OmniRoute/pull/8997))
-- **fix(sse):** Claude reasoning-effort suffix ids (`-high`/`-low`/`-medium`/`-xhigh`) now strip
-  correctly on any provider serving a real Claude model, not just the direct Anthropic provider
-  ([#9006](https://github.com/diegosouzapw/OmniRoute/pull/9006))
-- **fix(sse):** the no-thinking (`no-think/`) catalog variant's provider-qualification bug — which
-  made it unusable outside the direct provider, both in the discovery catalog and the dashboard
-  playground — is fixed ([#9006](https://github.com/diegosouzapw/OmniRoute/pull/9006))
-- **fix(sse):** a single unrecognized model id on a Vertex connection no longer cools down every
-  other model on that connection for 2 minutes — Vertex 404s are now scoped to a per-model
-  lockout via `passthroughModels` instead of a connection-wide cooldown
-  ([#9006](https://github.com/diegosouzapw/OmniRoute/pull/9006))
-- **fix(sse):** Vertex `PERMISSION_DENIED` 403s are now disambiguated using Google's own
-  documented error format — a genuinely connection-wide cause (API disabled, project-level IAM
-  denial) still cools the whole connection, while a model-specific denial locks out only that
-  model ([#9006](https://github.com/diegosouzapw/OmniRoute/pull/9006))
-- **fix(sse):** error-only streams now preserve sanitized executor diagnostics for operators without changing stream-readiness fallback classification ([#9022](https://github.com/diegosouzapw/OmniRoute/pull/9022)) — thanks @shixi-li
-- fix(cursor): preserve tool context across multi-turn conversations when client lacks conversation_id (#9029)
-- fix(sse): move Antigravity client system content to first user message to avoid upstream 429 RESOURCE_EXHAUSTED on oversized systemInstruction (#9030)
-- fix(auth): IP blacklist now blocks on direct connections via trusted peer stamp and re-reads config without restart (#9033)
-- fix(api): use configured prefix instead of raw node UUID for alias-backed model id in /v1/models (#9034)
-- **fix(resilience):** Detect and reset idle-capacity rate-limit queue wedges on an eligible watchdog scan so routing can fall back promptly ([#9041](https://github.com/diegosouzapw/OmniRoute/pull/9041))
-- fix(db): stream DB backup export instead of buffering entire file into memory (#9045)
-- fix(ui): normalize Free Pool API response payload to read from data.proxies (#9046)
-- **fix(translator):** pass `output_config.effort="max"` through verbatim instead of unconditionally rewriting it to `xhigh`, so Anthropic → OpenAI-shape upstream calls reach `sanitizeReasoningEffortForProvider` with the carrier intact and providers that accept `max` literally (Ollama Cloud, opencode-go DeepSeek, Moonshot K3, native Claude) no longer 400 on `invalid reasoning value: 'xhigh'`. Regression guard: end-to-end test in `tests/unit/base-executor-sanitize-effort.test.ts`. ([#9053](https://github.com/diegosouzapw/OmniRoute/pull/9053)) — thanks @ikelvingo
-- fix(api/analytics): stop charging :free models at arbitrary fallback price (#9054)
-- fix(api): auto/* routing aliases bypass API-key allowedConnections/disableNonPublicModels (#9057)
-- fix(providers): anthropic strips code-execution/skills beta flag, causing container rejection (#9064)
-- **fix(batches):** `GET /v1/batches` now validates the `limit` query param instead of passing `Number.parseInt(limit)` straight to the SQLite `LIMIT` bind. Previously `?limit=abc` threw an unhandled `datatype mismatch` (→ HTTP 500), `?limit=-1`/`0` returned an incoherent `has_more:true` empty page with `last_id:null`, and a large `?limit` read the entire `batches` table into memory. It now returns a `400` for any non-integer or out-of-range value (1–100, default 20), matching the `POST` handler's Zod validation and the OpenAI Batches contract ([#9073](https://github.com/diegosouzapw/OmniRoute/pull/9073))
-- **fix(a2a):** the A2A JSON-RPC router now compares the bearer token against `OMNIROUTE_API_KEY` in constant time (`crypto.timingSafeEqual`) instead of `===`, closing a token-length timing side-channel, and no longer logs the request URL to server logs on every call ([#9083](https://github.com/diegosouzapw/OmniRoute/pull/9083))
-- **fix(api/skills):** the `/api/skills/**` routes now run caught error messages through `sanitizeErrorMessage` before returning them, so a filesystem failure no longer leaks an absolute path (e.g. `/home/<user>/.omniroute/skills/...`) to the client; the `{ error: string }` response shape is preserved for the dashboard ([#9088](https://github.com/diegosouzapw/OmniRoute/pull/9088))
-- fix(providers): admit audio-speech/audio-transcriptions apiType in audio route provider-node filters (#9096)
-- fix(providers): modal.com validation returns clear error when Base URL is missing, instead of leaking "Invalid outbound URL" (#9102)
-- **fix(providers):** GitHub Copilot no longer re-imports or routes cached Gemini 2.5 Pro and Gemini 3 Flash model IDs after their retirement ([#9103](https://github.com/diegosouzapw/OmniRoute/pull/9103))
-- fix(providers): resolve combo names in audio transcriptions route so /v1/models stays honest (#9134)
-- fix(vscode): allow built-in auto-routing models in VS Code model filter (#9140)
-- fix(background): detect Anthropic top-level system prompts for background task detection (#9142)
-- **fix(dashboard):** the provider "Auto Sync" toggle now applies to every active connection and each connection gets its own Auto Sync toggle — previously only the lowest-priority connection was updated. ([#9149](https://github.com/diegosouzapw/OmniRoute/pull/9149))
-- fix(cli): use process.execPath for macOS launchd autostart (#9156)
-- fix(management): authorize mcp:connect-only keys on loopback/LAN when requireLogin is enabled (#9159)
-- fix(model-discovery): ingest capabilities.effort_tiers for synced models (#9160)
-- **fix(translator):** Honor configured Chat targets for Responses-shaped clients while preserving native Responses providers and outbound token fields ([#9161](https://github.com/diegosouzapw/OmniRoute/pull/9161)) — thanks @Zartharas
-- fix(translator): buffer and normalize upstream tool-call argument deltas so optional null values are stripped before reaching the client (#9168)
-- fix(cursor): the manual "Refresh" button on Cursor connections now calls the dedicated Cursor renewal route instead of silently returning a 502 every time (#9173)
-- fix(translator): avoid double-normalizing tool names in Gemini-to-Claude response path (#9177)
-- **fix(dashboard):** the "Default Model" of an OpenAI-compatible connection is now visible and editable after creation (was set once, then invisible), and it is no longer required when creating a connection — matching the API which always treated it as optional. ([#9179](https://github.com/diegosouzapw/OmniRoute/pull/9179))
-- **fix(db):** honor the `ENABLE_REQUEST_LOGS` environment override for detailed request persistence. (thanks @RobertsXML) ([#9187](https://github.com/diegosouzapw/OmniRoute/pull/9187))
-- **fix(model):** normalize client context-window suffixes for combo routing. (thanks @b1nhm1nh) ([#9193](https://github.com/diegosouzapw/OmniRoute/pull/9193))
-- fix(catalog): repair dead guard and synced-first ordering for custom model Vision capable override (#9195)
-- fix(routing): consult customModels supportsVision flag in Combo vision filter (#9195)
-- **fix(models):** Preserve published model catalogs during session-affinity bookkeeping so routine affinity updates do not force unnecessary cold rebuilds ([#9199](https://github.com/diegosouzapw/OmniRoute/pull/9199)) — thanks @xz-dev
-- **fix(models):** Reuse one build-local virtual-auto candidate snapshot across built-in catalog entries and cooperatively yield during cold catalog generation, while detaching invalidated in-flight generations so policy changes cannot publish stale results ([#9199](https://github.com/diegosouzapw/OmniRoute/pull/9199)) — thanks @xz-dev
-- **fix(models):** Resolve token limits and model capabilities once per unique candidate in that build-local snapshot, eliminating repeated SQLite lookups across the 38 built-in auto entries while preserving fresh runtime preparation and hard invalidation ([#9199](https://github.com/diegosouzapw/OmniRoute/pull/9199)) — thanks @xz-dev
-- **fix(models):** Read and parse models.dev pricing once per cold catalog build, then yield before final enrichment so queued health checks are not starved while every model in that build shares one coherent pricing snapshot ([#9199](https://github.com/diegosouzapw/OmniRoute/pull/9199)) — thanks @xz-dev
-- **fix(compression):** honor the global compression-off setting for proactive and last-resort context compaction, preventing disabled compression from rewriting tool-call histories ([#9200](https://github.com/diegosouzapw/OmniRoute/pull/9200)) — thanks @joachimBrindeau
-- fix(web-search): bind each search provider attempt to its connection proxy (#9201)
-- fix(auth): make antigravity and agy equivalent in credential selection (#9204)
-- **fix(cli):** prefer IPv4 DNS for spawned Node servers. (thanks @dsitmilis) ([#9209](https://github.com/diegosouzapw/OmniRoute/pull/9209))
-- **fix(pricing):** stop billing reasoning tokens twice. (thanks @yidecode) ([#9212](https://github.com/diegosouzapw/OmniRoute/pull/9212))
-- **fix(models):** `/v1/models` now publishes one contiguous provider-grouped block per provider instead of interleaved fragments. The catalog is assembled by many independent push loops (auto-combos, named combos, static registry, codex-native, synced, OpenRouter, specialty, custom, alias-backed, connection-fallback), so one provider's models previously landed in several separated blocks. A single stable, provider-grouped sort is applied at serialization, keyed by `owned_by` (canonical owner identity) rather than the model-id prefix — so a single routable public prefix that differs from its owner (e.g. no-auth OpenCode publishing `oc/<model>` while keeping `owned_by: "opencode"`) stays contiguous. Combos are pinned first (preserving #4164); then providers in registry precedence (OAuth → NoAuth → API-key); then unknown providers in locale-independent code-unit order. The sort is stable and pure (reorders rows only, no mutation, no DB/IO), preserving combo `sort_order`, connection priority, custom append-order, and equal-id audio twins ([#9215](https://github.com/diegosouzapw/OmniRoute/pull/9215)) — thanks @nguyenha935
-- **fix(combo):** the Combo "Add model" picker now respects hidden-model visibility for every model source — system catalog, fallback, passthrough/node aliases, custom rows and auto-fetched models — instead of drowning the list in 500+ unavailable entries ([#9218](https://github.com/diegosouzapw/OmniRoute/pull/9218)) — thanks @szzhoujiarui
-- **fix(codex):** normalize additional_tools passthrough items. (thanks @SalyyS1) ([#9219](https://github.com/diegosouzapw/OmniRoute/pull/9219))
-- **fix(codex):** preserve quota window duration in usage shape. (thanks @HectorBernstorff) ([#9222](https://github.com/diegosouzapw/OmniRoute/pull/9222))
-- **fix(azure):** normalize GPT-5 chat completion parameters. (thanks @royanrosyad85) ([#9223](https://github.com/diegosouzapw/OmniRoute/pull/9223))
-- **fix(codex):** strip orphaned tool outputs from compacted conversations. (thanks @raflyazf) ([#9228](https://github.com/diegosouzapw/OmniRoute/pull/9228))
-- **fix(i18n):** completed the French UI catalog by adding all missing keys and replacing every placeholder translation ([#9235](https://github.com/diegosouzapw/OmniRoute/pull/9235)) — thanks @alex-jordan547
-- **fix(nvidia):** normalize tool names and call ids for NVIDIA compatibility. (thanks @minhnhat166) ([#9236](https://github.com/diegosouzapw/OmniRoute/pull/9236))
-- fix(lmarena): emit Uint8Array SSE chunks instead of strings to satisfy shared pipeline contract (#9237)
-- **fix(db):** `validateRegisteredKey` no longer rejects the first request of a fresh budget window when the previous window's usage already met the daily/hourly budget — the reset `UPDATE` zeroed the counters in the DB but the budget check still read the stale pre-reset snapshot, so the reset is now mirrored into the row before checking ([#9241](https://github.com/diegosouzapw/OmniRoute/pull/9241))
-- **fix(i18n):** localized hardcoded web UI copy across public pages, dashboard views, and shared components, with complete French and Vietnamese coverage ([#9245](https://github.com/diegosouzapw/OmniRoute/pull/9245)) — thanks @alex-jordan547
-- **fix(db):** deleting a provider connection (single, batch, or provider-scoped) now purges its account-scoped `proxy_assignments` rows inside an atomic transaction — no more orphan assignments pointing at deleted connections ([#9246](https://github.com/diegosouzapw/OmniRoute/pull/9246)) — thanks @maxmad64bis
-- **fix(cli-tools):** keep Apply enabled for active OpenAI-compatible and Anthropic-compatible providers without static catalog entries. (thanks @lazysaltyfish) ([#9250](https://github.com/diegosouzapw/OmniRoute/pull/9250))
-- **fix(translator):** harden Claude format detection for relative message endpoints and kebab-case version metadata. (thanks @ervareza) ([#9253](https://github.com/diegosouzapw/OmniRoute/pull/9253))
-- **fix(minimax):** add the required empty signature placeholder to unsigned thinking block starts. (thanks @rixzkiye) ([#9256](https://github.com/diegosouzapw/OmniRoute/pull/9256))
-- **fix(resilience):** Enforce RPM limits with rolling leases and atomic global/provider/account admission ([#9259](https://github.com/diegosouzapw/OmniRoute/pull/9259)). The configured global RPM budget is shared across all enabled provider connections within one process; provider/account overrides add narrower scopes.
-- **fix(classify429):** add missing `have exhausted their quota` pattern so the synthetic 429 from auth.ts is recognized as quota exhaustion, preventing the combo loop from burning retries against the same provider instead of falling back to a healthy one ([#9269](https://github.com/diegosouzapw/OmniRoute/issues/9269))
-- fix(claude): remove unconditional "always" return in claudeClassifierCompat so normal chat requests are not swallowed (#9276)
-- fix(qoder): include actionable CLI_QODER_BIN hint in connection test when qodercli is not found (#9277)
-- **fix(providers):** the web search fallback detector in `webSearchFallback.ts` used an exact `Set` (`web_search`, `web_search_preview`) that missed Anthropic's date-suffixed server-tool variant `web_search_20250305` (sent by Claude Code 2.1.220+). Changed to prefix regex `/^web_search/`, matching the two other detectors in the codebase, so the fallback intercepts versioned web search tools for OpenAI-compatible upstreams ([#9279](https://github.com/diegosouzapw/OmniRoute/pull/9279))
-- **fix(docker):** the bundled Redis sidecar no longer publishes on `0.0.0.0`. `docker-compose.yml`, `omniroute redis up` and the dashboard's 1-click launcher all built an unqualified `-p <port>:6379` spec, which the container runtime expands to every interface — and none of them sets `requirepass`, so any host on the LAN could reach the rate-limiter/cache store. All three now default to `127.0.0.1`, with exposure opt-in via `REDIS_BIND_HOST` (compose), `--bind` (CLI) and `OMNIROUTE_REDIS_BIND_HOST` (launcher); the CLI warns when a non-loopback bind is requested without `--password` ([#9286](https://github.com/diegosouzapw/OmniRoute/pull/9286))
-- fix(credential-health): scheduler never retries failed connections due to static interval comparison (#9289)
-- **fix(db):** persist the account egress IP into `proxy_logs.egress_ip` (migration 134 + schema reconciler) so real traffic stays attributable to the actual node/IP even after restart — the egress IP was previously computed and logged but silently dropped from persistence ([#9291](https://github.com/diegosouzapw/OmniRoute/pull/9291)) — thanks @maxmad64bis
-- fix(api): specialty model catalog ignores hidden OpenRouter model flags (#9293)
-- fix(mcp): break circular import between googApiKeyAuth.ts and auth.ts to fix esbuild SyntaxError in MCP server bundle (#9297)
-- fix(catalog): cache getModelsDevPricing() to prevent OOM at startup (#9300)
-- fix(providers): bump qwen-web SPA version header from 0.2.66 to 0.2.81 (#9304)
-- fix(sse): broaden OMNIROUTE_SSE_COMMENTS to accept 'false','0','no' and gate metadata comment emission (#9305)
-- fix(lmarena): encode SSE stream chunks as Uint8Array to prevent TextDecoder TypeError (#9306)
-- **fix(claude):** reconcile compacted tool results against the preceding tool use. (thanks @ryanngit) ([#9308](https://github.com/diegosouzapw/OmniRoute/pull/9308))
-- **fix(kiro):** validate completed nested tool-call payloads before forwarding them. (thanks @SemonCat) ([#9314](https://github.com/diegosouzapw/OmniRoute/pull/9314))
-- fix(backend): use accumulated responseBody for provider payload in dashboard log viewer to avoid stale data from truncated SSE events (#9315)
-- fix(qoder): surface qodercli stderr in error message instead of generic 502 (#9319)
-- fix(security): require auth for /v1/models when management auth is configured (#9320)
-- **fix(claude):** normalize nested Claude server tool model ids (`cc/` and `claude/` prefixes) on native passthrough, covering non-versioned server tools (Task/subagent). (thanks @AlanSyue) ([#9332](https://github.com/diegosouzapw/OmniRoute/pull/9332))
-- fix(providers): map kimi-web/K3 to K2D5 scenario instead of OK Computer premium mode to fix resource_exhausted on non-subscriber accounts (#9338)
-- fix(security): require explicit tool envelope to prevent bare JSON from being promoted to real tool_calls (#9343)
-- fix(api): consult LiteLLM pricing_synced layer in resolveCatalogPricing so deployed models absent from models.dev and defaults get pricing in /v1/models (#9364)
-- fix(providers): treat claude-web 429 as unhealthy and forward upstream Retry-After header (#9406)
-- fix(providers): treat muse-spark-web 429 as unhealthy (#9406)
-- fix(providers): detect expired gemini-web sessions via ServiceLogin redirect and add testConnection override (#9407)
-- fix(providers): add tool_use block handling to claude-web stream parser for OpenAI tool_calls projection (#9408)
-- fix(api): fall back to slugified provider name when prefix is empty to prevent UUID leak in /v1/models (#9416)
-- **fix(providers):** Codex GPT-5.6 model metadata reports the 1M context window and 922K input limit ([#9431](https://github.com/diegosouzapw/OmniRoute/issues/9431)).
-- fix(oauth): Kiro import token endpoint no longer overwrites existing connection when using shared cached OIDC clientId (#9435)
-- **fix(sse):** hoisting a mid-conversation `system`/`developer` message into the top-level `system` field no longer carries its `cache_control` marker along, which left the conversation history without a cache breakpoint and forced a full re-read plus a rebuild on the next turn. The boundary is moved to the nearest preceding block that can carry one, and now survives the rewrites that turn `tool_result` and inlined file/document blocks into plain text; if the target block is already marked, both markers are kept unless Anthropic's TTL ordering forbids it. Both hoisting paths are fixed — `extractSystemRoleMessages` and `extractSystemMessagesToBody`. Regression guard: `tests/unit/claude-system-role-cache-boundary.test.ts`. ([#9436](https://github.com/diegosouzapw/OmniRoute/issues/9436))
-- fix(backend): force system MITM CA cert to 0644 on Linux regardless of umask and repair on re-install (#9442)
-- **fix(routing):** a Codex-native bare model id (`gpt-5.5`, the `gpt-5.6-sol`/`terra`/`luna` tiers) no longer routes to `codex` when no codex connection is active — an OpenAI-only install was getting `no active credentials for provider: codex` for a model OpenAI serves, and an install whose codex connection was merely inactive failed the same way. With codex active the Codex preference still wins over OpenAI, and ids only codex catalogs (`codex-auto-review`) still resolve to codex with no connection at all ([#9447](https://github.com/diegosouzapw/OmniRoute/pull/9447))
-- fix(docker): ship MITM `_internal/` shims and `selfsigned` package in standalone bundle (#9451)
-- fix(cli): probe PATH for claude.exe/codex.exe on Windows before falling back to the .cmd shim (#9454)
-- fix(cli): stop the supervisor before the child so omniroute stop no longer reports success while the supervisor respawns the server (#9455)
-- fix(cli): route claude-code OAuth to the Anthropic `claude` browser-PKCE flow instead of the unrelated command-code provider (#9474)
-- fix(cli): re-verify running binary version after `omniroute update` install and warn instead of lying about success when a local install shadows the global one (#9475)
-- fix(providers): classify 400 out of extra usage as quota_exhausted for Anthropic OAuth (#9486)
-- **fix(auth):** redirect active sessions from /login by checking the session cookie before showing the login form. (thanks @DaDecky) ([#9491](https://github.com/diegosouzapw/OmniRoute/pull/9491))
-- fix(api): make the 800-message chat history cap opt-in so long conversations reach compression instead of a terminal 413 (#9494)
-- fix(translator): preserve authentic K3 Responses reasoning by model across providers, keep it on the matching assistant turn, and make Kimi Coding prefer client reasoning then cached replay before its empty-marker fallback (#9496)
-- fix(translator): join reasoning summary segments with newline separators (#9500)
-- fix(muse-spark-web): document the ecto1: WS auth token requirement in the credential hint, spec, and error message (#9502)
-- fix(sse): stop force-injecting advanced-tool-use beta via the effort-2025-11-24 gate; forward client-negotiated effort through the allowlist (#9505)
-- fix(sse): stop the reasoning-token buffer from enlarging a client's explicit max_tokens upward (x1.5) (#9507)
-- fix(ci): include combo-matrix tests in test-integration job (#9531)
-- **fix(ci):** tighten unit suite ceiling from 100min to 80min as a conservative step (#9532)
-- **fix(ratelimit):** added queue-wait timeout tests and updateFromResponseBody sequencing tests for the existing RATE_LIMIT_QUEUE_TIMEOUT feature in withRateLimit (#9533)
-- fix(test): prevent flaky modelsDevSync timer assertions by serializing test execution within the file (#9534)
-- fix(backend): map cache tokens in OpenAI-to-Claude non-streaming usage translation (#9536)
-- fix(db): add transient-error retry to corruption probe to prevent data loss under concurrent load (#9541)
-- fix(search): mark searxng-search as fallbackOnly to prevent auto-select without instance (#9543)
-- fix(providers): strip provider prefix in getModelTargetFormat to route GPT-5.6 models to /v1/responses (#9545)
-- fix(model): add "aq" alias for amazon-q provider so parseModel resolves it instead of falling back to OpenAI (#9550)
-- fix(proxy): NO_PROXY now bypasses context-level proxy in resolveProxyForRequest (#9551)
-- **fix(build):** `npm run build:cli` (prepublish) no longer fails on POSIX with "npm-cli.js not found next to the running Node binary". The #8858 shim-free npm resolver only knew the Windows layout (`<dir(node.exe)>\node_modules\npm`); on GitHub hosted runners, nvm and system installs npm lives at `<prefix>/lib/node_modules/npm` while node is `<prefix>/bin/node`, so every fresh CI checkout died installing `@omniroute/opencode-plugin` deps (Fast Production Build + dast-smoke red on all PRs). The resolver, extracted to `scripts/build/resolveNpmEntry.ts`, now tries `npm_execpath` (exported by `npm run` itself) first, then the Windows layout, then the POSIX layout — covered by `tests/unit/build/resolve-npm-entry.test.ts` including a live POSIX regression guard. ([#9553](https://github.com/diegosouzapw/OmniRoute/pull/9553))
-- **fix(quality):** reconcile the accumulated file-size drift on `release/v3.8.50` — 13 files sat above their frozen LOC on the clean tip (measured by the gate itself), turning the absolute-mode check (nightly / local) permanently red while the PR-mode base-relative check (#8522) let every innocent PR pass. The per-PR rebaselines were lost across successive conflict resolutions of this hot file during the 08-05/06 merge batch. Frozen values updated to the measured tip for the 11 grown files (each annotated with its owning merged PR: #9024 #9324 #9329 #9193 #9332 #9228 #9260 #8934 #9196 #9163) and `open-sse/executors/default.ts` / `kiro.ts` (above the 1000 cap with no entry) added to the frozen set. ([#9554](https://github.com/diegosouzapw/OmniRoute/pull/9554))
-- fix(build): exec native esbuild binary directly in prepublish — esbuild ≥0.25 ships an ELF at bin/esbuild and running it through node crashed every build:cli (dast-smoke red on all PRs) ([#9558](https://github.com/diegosouzapw/OmniRoute/pull/9558))
-- **fix(mcp):** the 3 `audit.test.ts` shutdown/fallback tests fail deterministically since #8959 switched the audit DB loader to `createRequire("better-sqlite3")` — `vi.doMock` only patches Vitest's ESM module graph, so the old better-sqlite3 mock never engaged and the tests hit a real empty sqlite file ("no such table: mcp_tool_audit"), redding the `Vitest (fast-path)` job on every PR (long misdiagnosed as a flake). Shutdown tests now inject the mock through the audit connection cache (`globalThis.__omnirouteMcpAuditDb`), and the node:sqlite fallback test drives a new test-only loader seam (`__setBetterSqliteLoaderForTests`) — the production `createRequire` path is unchanged. 3/3 red → 3/3 green; full `open-sse/mcp-server` vitest suite 88/88. ([#9559](https://github.com/diegosouzapw/OmniRoute/pull/9559))
-- fix(build): lazy-resolve module-level fs paths to avoid Turbopack NFT whole-source trace (#9560)
-- fix(sse): replace timer-based waits with polling to fix flaky chatCore/SSE tests under CI load (#9567)
-- **fix(translator):** restore original tool name casing in Gemini/Antigravity response translators ([#9568](https://github.com/diegosouzapw/OmniRoute/issues/9568))
-- fix(translator): add case-insensitive fallback for upstream tool call name lookups (#9575)
-- **fix(standalone):** multipart uploads (`POST /v1/audio/transcriptions`) no longer hang — the WebDAV wrapper hands non-WebDAV requests to Next synchronously instead of losing the start of a streaming body ([#9580](https://github.com/diegosouzapw/OmniRoute/pull/9580))
-- **fix(docker):** standalone co-location now completes packages Next's file tracing materialized partially (package.json without its `main` payload) — unblocks the Docker Hub publish that failed on every v3.8.50 push with `Cannot find module '@atjsh/llmlingua-2/dist/index.js'` ([#9615](https://github.com/diegosouzapw/OmniRoute/pull/9615))
-- fix(resilience): failed connection test now sets a short cooldown so connections recover after transient outages (#9623)
-- fix(db): wire telemetry cleanup scheduler in Next.js startup path (#9624)
-- fix(db): align domain_cost_history cleanup cutoff with millisecond column (#9625)
-- fix(playground): surface provider model loading errors and offer retry (#9626)
-- fix(combo): distinguish pre-dispatch skips from genuine failures to prevent false 503 ALL_ACCOUNTS_INACTIVE (#9630)
-- fix(build): add build-next-isolated.mjs sibling imports to package.json files array (#9633)
-- **fix(providers):** new per-provider `noAuthFallbackDisabledProviders` setting lets operators disable the synthetic anonymous (no-auth) credential fallback for API-key providers whose static definition declares `anonymousFallback: true` (e.g. `opencode-go`, `opencode-zen`) — upstream endpoints now reject anonymous requests with `401 Missing API key`, so the fallback added latency and caused UI health/reconnect churn. Real keyed connections keep working and recover automatically once quota state clears; true no-auth providers (`opencode`, `mimocode`, …) are unaffected, with `blockedProviders` remaining their disable mechanism. Default behavior is unchanged ([#9675](https://github.com/diegosouzapw/OmniRoute/pull/9675))
-- **fix(docker):** `--build-arg OMNIROUTE_USE_TURBOPACK=0` now reaches the builder stage — a bare `ENV` was shadowing the `ARG`, so the documented webpack escape hatch was silently ignored and memory-constrained hosts were OOM-killed with no error output ([#9695](https://github.com/diegosouzapw/OmniRoute/pull/9695))
-- **fix(translator):** restore TitleCase tool names on the Claude → Gemini/Antigravity request path so Claude Code no longer fails with `No such tool available: read` ([#9713](https://github.com/diegosouzapw/OmniRoute/issues/9713))
-- fix(db): clear stale combo connection pins when provider connections are deleted (#9719)
-- fix(compression): persist `enableRenderers` through `normalizeRtkConfig` so RTK renderer settings survive a DB round-trip ([#9730](https://github.com/diegosouzapw/OmniRoute/pull/9730))
-- Fixed `GET`/`PUT`/`DELETE /api/memory/[id]` always failing with a 500 (`Primary backend "sqlite" not registered`) when the route was reached before any other memory endpoint in the same process. (#9737)
-- Replaced hand-rolled body type checks with Zod validation in the plugins marketplace install route and the three Dario admin routes, restoring the `t06:route-validation` gate (Hard Rule #7). (#9737)
-- Restore Vietnamese locale parity after the entity-normalization sync dropped Radar, provider, and mini-playground messages. (#9737)
-- **fix(radar):** refresh signed catalog/referral caches when supporter entitlement changes, preserve the one-time live-to-community downgrade, and test real provider connection IDs from the setup tour ([#9776](https://github.com/diegosouzapw/OmniRoute/pull/9776))
-- **Translator**: keep the Responses namespace identity map across the hub-and-spoke pivot — namespace sub-tool calls routed to non-OpenAI targets (Kiro, Cursor) no longer come back flattened (`unsupported call: functions__exec` in Codex CLI) (#9783 — thanks @VXNCXNX)
-- **fix(api):** Model catalogs no longer expose functional gateway mirrors unless the API key permits the mirror's final public model ID ([#9788](https://github.com/diegosouzapw/OmniRoute/pull/9788)) — thanks @xz-dev
-- **fix(executors):** preserve Command Code usage in `/v1/responses` streams so Codex clients receive real input, output, cache, and reasoning token counts ([#9826](https://github.com/diegosouzapw/OmniRoute/pull/9826)) — thanks @MrShitFox
-- **fix(executors):** prevent intermittent Codex `upstream_empty_response` errors for tool schemas that combine `oneOf` const branches with a matching sibling `enum` by removing only the semantically redundant `oneOf`; bare, narrowing, non-matching, and type-discriminated `oneOf` schemas remain unchanged. ([#9828](https://github.com/diegosouzapw/OmniRoute/pull/9828))
-- **fix(cursor):** SelectedImage uses `blobIdWithData` + session blobStore, with JPEG soft-cap prep via sharp ([#9834](https://github.com/diegosouzapw/OmniRoute/pull/9834)) — thanks @yansigit
-- **fix(test):** reconcile test expectations that drifted from the code they guard on `release/v3.8.50` — auth/vision/provider schema snapshots, and three context-aware combo compatibility assertions that contradicted the same file's own stated contract (catalog-too-small targets stay available as runtime fallback rather than being dropped). The combo assertions were masked by an unresolved import that stopped `combo.ts` from loading at all, so they only become reachable once that import is repaired. ([#9874](https://github.com/diegosouzapw/OmniRoute/pull/9874))
-- fix(search): nest Exa contents options (text/highlights) for /search API (#9914)
-- fix(i18n): re-escape CC discovery-alias `claude/<provider>/<model>` to HTML entities so next-intl stops logging INVALID_MESSAGE: UNCLOSED_TAG on provider detail pages (#8747 regression) ([#9917](https://github.com/diegosouzapw/OmniRoute/pull/9917)) — thanks @yansigit
-- fix(encryption): name failing credential + recovery path in decrypt errors, dedupe per connection (#9927)
-- **fix(executors):** preserve non-strict function-tool semantics when translating Chat Completions requests to Codex Responses, avoiding intermittent streamed failures without rewriting tool schemas or dropping branch-level descriptions and annotations. ([#9931](https://github.com/diegosouzapw/OmniRoute/pull/9931))
-- fix(migrations): don't abort on fresh install with only the 001 seed (#9934)
-- **fix(admission):** per-connection virtual admission lanes with idle TTL eviction — guards `expireEntry` null deref, adds `deleteLane()` for safe LRU eviction, and passes `sessionId` to byte-level admission (fixes #9654) ([#9940](https://github.com/diegosouzapw/OmniRoute/pull/9940)) — thanks @branben
-- Repair release-sweep regressions in locale and environment contracts, package metadata, scripts, dependency, size and dead-code ratchets, OpenAPI coverage, Telegram error sanitization, Openference public-credential handling, DB-module classification, resilience UI test assertions, strict CodeBuddy CN tests, Lite compression typing, and the job-registry migration number. ([#9945](https://github.com/diegosouzapw/OmniRoute/pull/9945))
-- Let the release-green validator finish the test-masking gate on loaded runners while preserving the existing timeout for every other full-CI gate, and report Node.js `ETIMEDOUT` errors as explicit timeout failures. ([#9964](https://github.com/diegosouzapw/OmniRoute/pull/9964))
-- fix(chat): don't misclassify content-less thinking/redacted Claude bodies as empty_choices (#9971)
-- fix(images): normalize terminal upstream errors via OpenAI-standard type/code (#9981)
-- fix(quality): green release/v3.8.50 base-reds — sync 4 env vars into .env.example/ENVIRONMENT.md and freeze the new proxied-TLS proxyFetch helper in the file-size baseline (#9985)
-- **fix(sse): replay Gemini `thought_signature` on the direct Claude→Gemini path** — with the #3440 assertion coverage preserved under signature replay (#2504, #3440) — thanks @csoftware-arigpt
-- **fix(security): bump adm-zip >=0.6.0 + exact host matching in the mitm DNS test** (#7733)
-- **fix(i18n): polish zh-CN/zh-TW translations and fix over-translation of proper nouns** ([#8872](https://github.com/diegosouzapw/OmniRoute/pull/8872)) — thanks @ikelvingo
-- **fix(build): support npm v11 allowScripts for optional native deps** ([#8877](https://github.com/diegosouzapw/OmniRoute/pull/8877)) — thanks @configurowebmax
-- **fix(combo): exclude hidden leaves from catalog and dispatch** ([#8878](https://github.com/diegosouzapw/OmniRoute/pull/8878)) — thanks @ahmet-cetinkaya
-- **fix(antigravity): add onboardUser fallback for accounts missing Cloud Code project** ([#8886](https://github.com/diegosouzapw/OmniRoute/pull/8886)) — thanks @HouMinXi
-- **fix(sse): brand-neutral keepalive frames** ([#8888](https://github.com/diegosouzapw/OmniRoute/pull/8888)) — thanks @AndrianBalanescu
-- **fix(deepseek-web): enable toolCalling on all models** ([#8889](https://github.com/diegosouzapw/OmniRoute/pull/8889)) — thanks @AndrianBalanescu
-- **fix(combo): fail-fast concurrency gate and execute-mode overflow** ([#8890](https://github.com/diegosouzapw/OmniRoute/pull/8890)) — thanks @AndrianBalanescu
-- **fix(antigravity): quota-aware account selection and projectId persistence** ([#8891](https://github.com/diegosouzapw/OmniRoute/pull/8891)) — thanks @AndrianBalanescu
-- **fix(usage): aggregate provider window costs in SQL** ([#8892](https://github.com/diegosouzapw/OmniRoute/pull/8892)) — thanks @AndrianBalanescu
-- **fix(combo): least-used quota strategy and wildcard UI preservation** ([#8894](https://github.com/diegosouzapw/OmniRoute/pull/8894)) — thanks @AndrianBalanescu
-- **fix(test): stop autostart tests from disabling the developer's real systemd service** ([#8900](https://github.com/diegosouzapw/OmniRoute/pull/8900)) — thanks @nosolosoft
-- **fix(combos): include id column in getCombos query** ([#8905](https://github.com/diegosouzapw/OmniRoute/pull/8905)) — thanks @HouMinXi
-- **fix: prevent false 'Failed to save connection' error when adding providers** ([#8912](https://github.com/diegosouzapw/OmniRoute/pull/8912)) — thanks @ziuus
-- **fix: add Termux/Android support for playwright-core and better-sqlite3** ([#8922](https://github.com/diegosouzapw/OmniRoute/pull/8922)) — thanks @Kaedo17
-- **fix(i18n): localize SubscriptionTab UI strings instead of hardcoded Chinese** ([#8930](https://github.com/diegosouzapw/OmniRoute/pull/8930)) — thanks @Hdiaktoros
-- **fix(kiro): keep interleaved tool results grouped without dropping assistant text (#8903)** ([#8931](https://github.com/diegosouzapw/OmniRoute/pull/8931)) — thanks @xiaoyaner0201
-- **Fix custom tool output pairing during context compression** ([#8933](https://github.com/diegosouzapw/OmniRoute/pull/8933)) — thanks @JxnLexn
-- **fix(routing): account for active OAuth sessions** ([#8940](https://github.com/diegosouzapw/OmniRoute/pull/8940)) — thanks @JxnLexn
-- **fix(vision): prevent bridge streaming and normalize OMP effort** ([#8945](https://github.com/diegosouzapw/OmniRoute/pull/8945)) — thanks @rinseaid
-- **fix(ci): stop one failing platform from taking the whole desktop channel down** ([#8957](https://github.com/diegosouzapw/OmniRoute/pull/8957))
-- **fix(api): alias-backed models leak raw node UUID prefix in /v1/models (#8958)** ([#8961](https://github.com/diegosouzapw/OmniRoute/pull/8961)) — thanks @Rahulsharma0810
-- **fix(sse): default OpenAI Chat Completions to non-stream when stream omitted** ([#8976](https://github.com/diegosouzapw/OmniRoute/pull/8976)) — thanks @HouMinXi
-- **fix(cache): add latency marker + per-key bypass for semantic cache** ([#8984](https://github.com/diegosouzapw/OmniRoute/pull/8984)) — thanks @HouMinXi
-- **fix(perplexity-web): update catalog to use 'copilot' mode and fix model IDs** (#8989)
-- **fix(docker): move entrypoint script to /app to avoid tmpfs masking** ([#8999](https://github.com/diegosouzapw/OmniRoute/pull/8999)) — thanks @yutuknown
-- **fix(executors): backfill missing tool message names for Kimi K3 and strict BYOK providers** ([#9005](https://github.com/diegosouzapw/OmniRoute/pull/9005)) — thanks @Zenlyte
-- **fix(command-code): enable vision flags for CC models and fix vision-bridge reroute** ([#9007](https://github.com/diegosouzapw/OmniRoute/pull/9007)) — thanks @Stazyu
-- **fix(sse): route Poe API-key traffic through DefaultExecutor (#8969)** ([#9014](https://github.com/diegosouzapw/OmniRoute/pull/9014)) — thanks @Prudhvivuda
-- **fix(sse): preserve Gemini thought_signature on Claude Desktop tool turns** ([#9015](https://github.com/diegosouzapw/OmniRoute/pull/9015)) — thanks @Prudhvivuda
-- **fix(sse): preserve Claude Code tool-name casing via Gemini/Antigravity** ([#9016](https://github.com/diegosouzapw/OmniRoute/pull/9016)) — thanks @Prudhvivuda
-- **fix(dashboard): make quota providers expandable** ([#9025](https://github.com/diegosouzapw/OmniRoute/pull/9025)) — thanks @jktan0504
-- **fix(chat): resolve stored combo names before image-model validation (#8986)** ([#9027](https://github.com/diegosouzapw/OmniRoute/pull/9027)) — thanks @xiaoyaner0201
-- **fix(kiro): read usage from the frames Kiro actually sends** ([#9035](https://github.com/diegosouzapw/OmniRoute/pull/9035)) — thanks @ddarkr
-- **fix(kiro): keep relocated tool documentation on multi-turn requests** ([#9036](https://github.com/diegosouzapw/OmniRoute/pull/9036)) — thanks @ddarkr
-- **fix(vision): preserve images for text-only routes** ([#9037](https://github.com/diegosouzapw/OmniRoute/pull/9037)) — thanks @rinseaid
-- **fix(db): bundle and verify the sql.js fallback** ([#9044](https://github.com/diegosouzapw/OmniRoute/pull/9044)) — thanks @nguyenha935
-- **fix(open-sse): route GitHub Copilot gpt-5.6 sol/terra/luna to /responses** ([#9050](https://github.com/diegosouzapw/OmniRoute/pull/9050)) — thanks @marchlhw
-- **fix: skills & memory — tool-name encoding, schema normalization, warm-cache, combo id, Ponytail catalog** ([#9058](https://github.com/diegosouzapw/OmniRoute/pull/9058)) — thanks @Egorich-print
-- **fix(classify): recognize Modal 'usage limit reached' as quota exhausted** ([#9079](https://github.com/diegosouzapw/OmniRoute/pull/9079)) — thanks @HouMinXi
-- **Fix/issue #8656** ([#9095](https://github.com/diegosouzapw/OmniRoute/pull/9095)) — thanks @infinit-X
-- **fix(adobe-firefly): open browser sign-in and resolve provider slug in /login** ([#9097](https://github.com/diegosouzapw/OmniRoute/pull/9097)) — thanks @artickc
-- **fix(providers): make model Check/Test honor the node apiType, and show upstream model names** ([#9099](https://github.com/diegosouzapw/OmniRoute/pull/9099)) — thanks @zhiru
-- **fix(audio): let the audio routes use audio-typed provider nodes, and gate remote ones behind a default-off flag** ([#9101](https://github.com/diegosouzapw/OmniRoute/pull/9101)) — thanks @zhiru
-- **fix(antigravity): alias gemini-3.1-pro-high to gemini-pro-agent** ([#9106](https://github.com/diegosouzapw/OmniRoute/pull/9106)) — thanks @HouMinXi
-- **fix(api): flatten single-row embedding vectors to OpenAI shape** ([#9148](https://github.com/diegosouzapw/OmniRoute/pull/9148)) — thanks @aniketshukla1
-- **fix(proxy): restore connection pooling on proxy/relay paths (#9100)** ([#9158](https://github.com/diegosouzapw/OmniRoute/pull/9158)) — thanks @oyi77
-- **fix(rate-limit): separate queue wait from execution timeout** ([#9164](https://github.com/diegosouzapw/OmniRoute/pull/9164)) — thanks @Zartharas
-- **fix(translator): translate Codex agent messages for Chat** ([#9171](https://github.com/diegosouzapw/OmniRoute/pull/9171)) — thanks @Gioxaa
-- **fix(settings): allow hidePaidModels updates** ([#9182](https://github.com/diegosouzapw/OmniRoute/pull/9182)) — thanks @Zartharas
-- **fix(routing): evict affinity after terminal stream EOF** ([#9184](https://github.com/diegosouzapw/OmniRoute/pull/9184)) — thanks @Zartharas
-- **fix(docker): bundle LLMLingua optional dependencies** ([#9185](https://github.com/diegosouzapw/OmniRoute/pull/9185)) — thanks @Zartharas
-- **fix(health): skip disabled provider connections** ([#9186](https://github.com/diegosouzapw/OmniRoute/pull/9186)) — thanks @Zartharas
-- **fix(claude): preserve standalone whitespace deltas** ([#9189](https://github.com/diegosouzapw/OmniRoute/pull/9189)) — thanks @Zartharas
-- **fix(sse): evict a principal's own CCR blocks before another principal's (#9146)** ([#9191](https://github.com/diegosouzapw/OmniRoute/pull/9191)) — thanks @fajarhide
-- **fix(responses): normalize terminal usage for Codex** ([#9192](https://github.com/diegosouzapw/OmniRoute/pull/9192))
-- **fix(sse): back the CCR block store with a durable tier (#9061)** ([#9198](https://github.com/diegosouzapw/OmniRoute/pull/9198)) — thanks @fajarhide
-- **fix(combo): recover provider circuit breaker from HALF_OPEN on success** ([#9207](https://github.com/diegosouzapw/OmniRoute/pull/9207)) — thanks @HouMinXi
-- **fix(vision-bridge): improve compatibility with Anthropic image blocks and self-loop describe requests** ([#9226](https://github.com/diegosouzapw/OmniRoute/pull/9226)) — thanks @Stazyu
-- **fix(images): refresh OAuth credentials and rotate accounts after 401** ([#9231](https://github.com/diegosouzapw/OmniRoute/pull/9231)) — thanks @Bl0ck154
-- **fix(ci): merge-queue tolerance for Build (advisory), drops paid-tier batching** ([#9233](https://github.com/diegosouzapw/OmniRoute/pull/9233)) — thanks @wgordon17
-- **fix(token-refresh): exempt transient errors from exponential backoff** ([#9242](https://github.com/diegosouzapw/OmniRoute/pull/9242)) — thanks @HouMinXi
-- **fix(resilience): count STREAM_EARLY_EOF as a provider failure in combo routing** ([#9251](https://github.com/diegosouzapw/OmniRoute/pull/9251)) — thanks @TechNickAI
-- **fix(command-code): preserve literal max effort for command-code provider** ([#9257](https://github.com/diegosouzapw/OmniRoute/pull/9257)) — thanks @Chewji9875
-- **fix(dashboard): open webhook wizard in edit mode** ([#9272](https://github.com/diegosouzapw/OmniRoute/pull/9272)) — thanks @khoazero123
-- **fix(mcp): remove non-standard x-provider field from omniroute_test_combo body** ([#9274](https://github.com/diegosouzapw/OmniRoute/pull/9274)) — thanks @Sam280903
-- **fix(routing): bare model ids route to codex first; validate synced candidates** ([#9275](https://github.com/diegosouzapw/OmniRoute/pull/9275))
-- **fix(mcp): stop DB init logging from corrupting the stdio JSON-RPC stream** ([#9281](https://github.com/diegosouzapw/OmniRoute/pull/9281)) — thanks @Sam280903
-- **fix(reasoning): forward Ollama Cloud thinking** ([#9290](https://github.com/diegosouzapw/OmniRoute/pull/9290)) — thanks @xz-dev
-- **fix(models): reconcile active live model catalogs** ([#9294](https://github.com/diegosouzapw/OmniRoute/pull/9294)) — thanks @Zartharas
-- **fix: update Baichuan website URL to baichuan-ai.com** ([#9312](https://github.com/diegosouzapw/OmniRoute/pull/9312)) — thanks @zabrodschiipavel-sketch
-- **fix(agentrouter): retry on 400 content-blocked + burst guard** ([#9323](https://github.com/diegosouzapw/OmniRoute/pull/9323))
-- **fix:nanogpt model discovery** ([#9326](https://github.com/diegosouzapw/OmniRoute/pull/9326)) — thanks @TheFrenchGhosty
-- **fix(rate-limit): patch Bottleneck doExpire capacity leak** ([#9328](https://github.com/diegosouzapw/OmniRoute/pull/9328)) — thanks @HouMinXi
-- **fix(auth): let an agy request find the connection it authorized** ([#9340](https://github.com/diegosouzapw/OmniRoute/pull/9340)) — thanks @HouMinXi
-- **fix(combo): network errors must not trip provider circuit breaker** ([#9342](https://github.com/diegosouzapw/OmniRoute/pull/9342)) — thanks @HouMinXi
-- **fix(antigravity): propagate switchAuth signal from 429 engine to retry guard** ([#9351](https://github.com/diegosouzapw/OmniRoute/pull/9351)) — thanks @HouMinXi
-- **fix(routing): correct reset-window strategy prioritization (#9330)** ([#9353](https://github.com/diegosouzapw/OmniRoute/pull/9353)) — thanks @Iammilansoni
-- **fix(sse): drop the localDb barrel imports from chat and auth** ([#9380](https://github.com/diegosouzapw/OmniRoute/pull/9380)) — thanks @HouMinXi
-- **fix(providers): enforce gemini-web reasoning and tool constraints (#9356)** ([#9397](https://github.com/diegosouzapw/OmniRoute/pull/9397)) — thanks @Iammilansoni
-- **fix(combo): complete #8400 — preserve full fallback order + per-model account affinity for deterministic combos** ([#9420](https://github.com/diegosouzapw/OmniRoute/pull/9420)) — thanks @Chewji9875
-- **fix(translator): normalize streamed optional tool arguments** ([#9423](https://github.com/diegosouzapw/OmniRoute/pull/9423)) — thanks @KittisakT
-- **fix(providers): correct Codex GPT-5.6 context limits** ([#9432](https://github.com/diegosouzapw/OmniRoute/pull/9432)) — thanks @PixmaNts
-- **fix(usage): stop double-counting cache-read tokens in Command Code executor** ([#9438](https://github.com/diegosouzapw/OmniRoute/pull/9438)) — thanks @Stazyu
-- **fix(deps): bumps transitive deps for 8 CVEs surfaced by vuln-ratchet** ([#9441](https://github.com/diegosouzapw/OmniRoute/pull/9441)) — thanks @wgordon17
-- **fix(ui): preserve request log position** ([#9452](https://github.com/diegosouzapw/OmniRoute/pull/9452)) — thanks @xiaoyaner0201
-- **fix(sse): preserve client cache boundaries when hoisting system roles** ([#9457](https://github.com/diegosouzapw/OmniRoute/pull/9457)) — thanks @LeonG606
-- **fix(providers): switch minimax from claude to openai format so images work** ([#9463](https://github.com/diegosouzapw/OmniRoute/pull/9463))
-- **fix(sse): take the Antigravity output ceiling from the model, not a constant** ([#9482](https://github.com/diegosouzapw/OmniRoute/pull/9482)) — thanks @HouMinXi
-- **fix(docs): add required MDX frontmatter to AGENTROUTER_WAF.md** ([#9503](https://github.com/diegosouzapw/OmniRoute/pull/9503))
-- **fix(quality): prune a stale entry from the ESLint suppressions baseline** ([#9509](https://github.com/diegosouzapw/OmniRoute/pull/9509)) — thanks @HouMinXi
-- **fix(classify): honor upstream retry windows on Gemini free-tier 429s** ([#9513](https://github.com/diegosouzapw/OmniRoute/pull/9513)) — thanks @shixi-li
-- **fix(quality): 2 production bugs + 24 unit base-reds + measured gate ceilings** ([#9529](https://github.com/diegosouzapw/OmniRoute/pull/9529))
-- **fix(providers): support data URL icons** ([#9555](https://github.com/diegosouzapw/OmniRoute/pull/9555)) — thanks @xz-dev
-- **fix(sse): shrink chat.ts back under the frozen file-size cap (base-red drain)** ([#9598](https://github.com/diegosouzapw/OmniRoute/pull/9598))
-- **fix(ci): clear base-reds on release/v3.8.50 (migration collision + 4 masked gates)** ([#9600](https://github.com/diegosouzapw/OmniRoute/pull/9600))
-- **fix(resilience): enforce RPM with rolling leases** ([#9604](https://github.com/diegosouzapw/OmniRoute/pull/9604))
-- **fix(backend): stop reasoning replay placeholder from self-poisoning** ([#9610](https://github.com/diegosouzapw/OmniRoute/pull/9610)) — thanks @stanleytejakusuma
-- **fix(providers): mint a Zed LLM token for zed-hosted model discovery** ([#9628](https://github.com/diegosouzapw/OmniRoute/pull/9628)) — thanks @ARC345
-- **fix(test): reconcile base-drifted test expectations on release/v3.8.50** ([#9634](https://github.com/diegosouzapw/OmniRoute/pull/9634)) — thanks @HouMinXi
-- **fix(openrouter): scope model failures per-model instead of poisoning the whole connection** ([#9635](https://github.com/diegosouzapw/OmniRoute/pull/9635)) — thanks @hartmark
-- **fix(radar): close the audit gaps — auth, merged feed fields, opt-in state, sidebar gate, size cap + daily scheduler** ([#9686](https://github.com/diegosouzapw/OmniRoute/pull/9686))
-- **fix(ci): clear the NEW base-reds from the 08-06 merge batch (migration collision #2 + broken import)** ([#9688](https://github.com/diegosouzapw/OmniRoute/pull/9688))
-- **fix(codebuddy-cn): replace agent system prompts to bypass Tencent content filter** ([#9723](https://github.com/diegosouzapw/OmniRoute/pull/9723)) — thanks @zuckdorsey
-- **fix(db): resolve migration version 135 numbering collision** ([#9745](https://github.com/diegosouzapw/OmniRoute/pull/9745)) — thanks @hartmark
-- **fix(ci): clear the 08-08 base-red layers — dead-code, prod crash in chat.ts, Responses payload regression, born-red stdio test, gate drifts** ([#9757](https://github.com/diegosouzapw/OmniRoute/pull/9757))
-- **fix(bun): make server child and outbound fetch Bun-safe** ([#9761](https://github.com/diegosouzapw/OmniRoute/pull/9761)) — thanks @Arul-
-- **fix(sse): preserve original body for semantic cache signature — fixes 0% hit rate** ([#9775](https://github.com/diegosouzapw/OmniRoute/pull/9775))
-- **fix(api): validate request bodies with Zod in 4 routes — restores the t06 gate (#9737)** ([#9779](https://github.com/diegosouzapw/OmniRoute/pull/9779))
-- **fix(ci): restore current release test integrity** ([#9819](https://github.com/diegosouzapw/OmniRoute/pull/9819))
-- **fix(ci): close remaining release-green gaps** ([#9835](https://github.com/diegosouzapw/OmniRoute/pull/9835))
-- **fix(proxy): isolate wreq TLS sessions by account** ([#9837](https://github.com/diegosouzapw/OmniRoute/pull/9837)) — thanks @agisota
-- **fix(cursor): SelectedImage blobIdWithData + JPEG soft-cap prep** ([#9840](https://github.com/diegosouzapw/OmniRoute/pull/9840), original [#9834](https://github.com/diegosouzapw/OmniRoute/pull/9834)) — thanks @yansigit
-- **fix(executors): strip redundant oneOf matching sibling enum** ([#9841](https://github.com/diegosouzapw/OmniRoute/pull/9841), original [#9828](https://github.com/diegosouzapw/OmniRoute/pull/9828)) — thanks @larin-vas
-- **fix(executors): preserve Command Code usage in Responses streams** ([#9842](https://github.com/diegosouzapw/OmniRoute/pull/9842), original [#9826](https://github.com/diegosouzapw/OmniRoute/pull/9826)) — thanks @MrShitFox
-- **fix(responses-api): tool call after a text message collided on the same output_index** ([#9843](https://github.com/diegosouzapw/OmniRoute/pull/9843), original [#9822](https://github.com/diegosouzapw/OmniRoute/pull/9822)) — thanks @hartmark
-- **fix(admission): queue heavyweight chat requests before 503 busy** ([#9845](https://github.com/diegosouzapw/OmniRoute/pull/9845), original [#9816](https://github.com/diegosouzapw/OmniRoute/pull/9816)) — thanks @herjarsa
-- **[TS7] fix(types): accept synced catalog model rows** ([#9846](https://github.com/diegosouzapw/OmniRoute/pull/9846), original [#9798](https://github.com/diegosouzapw/OmniRoute/pull/9798)) — thanks @backryun
-- **[TS7] fix(types): normalize DuckDuckGo request messages** ([#9847](https://github.com/diegosouzapw/OmniRoute/pull/9847), original [#9797](https://github.com/diegosouzapw/OmniRoute/pull/9797)) — thanks @backryun
-- **[TS7] fix(types): expose SQLite transaction state** ([#9848](https://github.com/diegosouzapw/OmniRoute/pull/9848), original [#9796](https://github.com/diegosouzapw/OmniRoute/pull/9796)) — thanks @backryun
-- **[TS7] fix(types): validate default executor pool config** ([#9849](https://github.com/diegosouzapw/OmniRoute/pull/9849), original [#9795](https://github.com/diegosouzapw/OmniRoute/pull/9795)) — thanks @backryun
-- **[TS7] fix(types): preserve The Old LLM proxy contracts** ([#9850](https://github.com/diegosouzapw/OmniRoute/pull/9850), original [#9793](https://github.com/diegosouzapw/OmniRoute/pull/9793)) — thanks @backryun
-- **[TS7] fix(types): normalize Gemini Business credentials** ([#9851](https://github.com/diegosouzapw/OmniRoute/pull/9851), original [#9792](https://github.com/diegosouzapw/OmniRoute/pull/9792)) — thanks @backryun
-- **[TS7] fix(types): preserve Claude thinking body contracts** ([#9852](https://github.com/diegosouzapw/OmniRoute/pull/9852), original [#9791](https://github.com/diegosouzapw/OmniRoute/pull/9791)) — thanks @backryun
-- **fix(response): strip internal reasoning placeholder from all reasoning fields** ([#9853](https://github.com/diegosouzapw/OmniRoute/pull/9853), original [#9790](https://github.com/diegosouzapw/OmniRoute/pull/9790)) — thanks @adevwithpurpose
-- **fix(api): enforce model permissions on gateway mirrors** ([#9854](https://github.com/diegosouzapw/OmniRoute/pull/9854), original [#9788](https://github.com/diegosouzapw/OmniRoute/pull/9788)) — thanks @xz-dev
-- **fix(sse): apply Azure param rules on azure-ai and clamp gpt-4o-mini output tokens** ([#9855](https://github.com/diegosouzapw/OmniRoute/pull/9855), original [#9787](https://github.com/diegosouzapw/OmniRoute/pull/9787)) — thanks @Michael-Rocco-Goldmann
-- **fix(sse): route claude discovery aliases for catalog-only providers** ([#9856](https://github.com/diegosouzapw/OmniRoute/pull/9856), original [#9777](https://github.com/diegosouzapw/OmniRoute/pull/9777)) — thanks @Michael-Rocco-Goldmann
-- **fix(i18n): translate validation model keys in 34 locales** ([#9857](https://github.com/diegosouzapw/OmniRoute/pull/9857), original [#9773](https://github.com/diegosouzapw/OmniRoute/pull/9773)) — thanks @Michael-Rocco-Goldmann
-- **[TS7] fix(skills): normalize web fetch credentials** ([#9859](https://github.com/diegosouzapw/OmniRoute/pull/9859), original [#9755](https://github.com/diegosouzapw/OmniRoute/pull/9755)) — thanks @backryun
-- **[TS7] fix(types): narrow DeepSeek tool calls** ([#9860](https://github.com/diegosouzapw/OmniRoute/pull/9860), original [#9751](https://github.com/diegosouzapw/OmniRoute/pull/9751)) — thanks @backryun
-- **fix(pricing): memoize getSyncedPricing() across catalog cache versions** ([#9861](https://github.com/diegosouzapw/OmniRoute/pull/9861), original [#9746](https://github.com/diegosouzapw/OmniRoute/pull/9746)) — thanks @chloeassistant
-- **fix(logging): use configurable max-depth when bounding logged tool_calls** ([#9865](https://github.com/diegosouzapw/OmniRoute/pull/9865), original [#9734](https://github.com/diegosouzapw/OmniRoute/pull/9734)) — thanks @hartmark
-- **fix(executors): repair DuckDuckGo AI Chat challenge solver (418 ERR_CHALLENGE)** ([#9866](https://github.com/diegosouzapw/OmniRoute/pull/9866), original [#9733](https://github.com/diegosouzapw/OmniRoute/pull/9733)) — thanks @Mynacol
-- **fix(compression): persist RTK renderer configuration** ([#9867](https://github.com/diegosouzapw/OmniRoute/pull/9867), original [#9730](https://github.com/diegosouzapw/OmniRoute/pull/9730)) — thanks @isaaclb98
-- **fix(dashboard): unregister leftover service workers in dev mode** ([#9868](https://github.com/diegosouzapw/OmniRoute/pull/9868), original [#9727](https://github.com/diegosouzapw/OmniRoute/pull/9727)) — thanks @hartmark
-- **fix(docker): make the webpack build-arg escape hatch actually work** ([#9872](https://github.com/diegosouzapw/OmniRoute/pull/9872), original [#9695](https://github.com/diegosouzapw/OmniRoute/pull/9695)) — thanks @HouMinXi
-- **fix(providers): per-provider opt-out for anonymous no-auth fallback (opencode-go/zen 401s)** ([#9873](https://github.com/diegosouzapw/OmniRoute/pull/9873), original [#9675](https://github.com/diegosouzapw/OmniRoute/pull/9675)) — thanks @chloeassistant
-- **fix(providers): reject the dashboard password as a connection API key** ([#9877](https://github.com/diegosouzapw/OmniRoute/pull/9877), original [#9572](https://github.com/diegosouzapw/OmniRoute/pull/9572)) — thanks @HouMinXi
-- **fix(settings): use provider prefixes in model overrides** ([#9878](https://github.com/diegosouzapw/OmniRoute/pull/9878), original [#9569](https://github.com/diegosouzapw/OmniRoute/pull/9569)) — thanks @xz-dev
-- **fix(translator): preserve Kimi K3 Responses reasoning** ([#9879](https://github.com/diegosouzapw/OmniRoute/pull/9879), original [#9556](https://github.com/diegosouzapw/OmniRoute/pull/9556)) — thanks @jackjinke
-- **fix(adobe-firefly): harden CDP warm, risk session, and browser sign-in** ([#9881](https://github.com/diegosouzapw/OmniRoute/pull/9881), original [#9549](https://github.com/diegosouzapw/OmniRoute/pull/9549)) — thanks @artickc
-- **fix: pass max reasoning effort through by default, add global model registry fallback** ([#9883](https://github.com/diegosouzapw/OmniRoute/pull/9883), original [#9612](https://github.com/diegosouzapw/OmniRoute/pull/9612)) — thanks @Momen4444
-- **fix(db): resolve CCR migration version collision** ([#9884](https://github.com/diegosouzapw/OmniRoute/pull/9884), original [#9618](https://github.com/diegosouzapw/OmniRoute/pull/9618)) — thanks @fenix007
-- **fix(compression): add Lite tool truncation toggle** ([#9885](https://github.com/diegosouzapw/OmniRoute/pull/9885), original [#9629](https://github.com/diegosouzapw/OmniRoute/pull/9629)) — thanks @xz-dev
-- **fix(web-tools): anchor tool contract at prompt tail + user-turn reminder for large prompts** ([#9887](https://github.com/diegosouzapw/OmniRoute/pull/9887), original [#9693](https://github.com/diegosouzapw/OmniRoute/pull/9693)) — thanks @ryan-brosas
-- **fix(sse): persist per-tool-call JSON escape state across SSE delta chunks** ([#9889](https://github.com/diegosouzapw/OmniRoute/pull/9889), original [#9704](https://github.com/diegosouzapw/OmniRoute/pull/9704)) — thanks @hartmark
-- **fix(db,combo): renumber ccr_blocks 134→139 + restore antigravity pool filter** ([#9890](https://github.com/diegosouzapw/OmniRoute/pull/9890), original [#9707](https://github.com/diegosouzapw/OmniRoute/pull/9707)) — thanks @matiasbaglieri
-- **fix(sse): grace period before finalizing a client disconnect as 499** ([#9891](https://github.com/diegosouzapw/OmniRoute/pull/9891), original [#9711](https://github.com/diegosouzapw/OmniRoute/pull/9711)) — thanks @hartmark
-- **fix(build): standalone bundle misses LLMLingua dist + onnxruntime native binaries** ([#9892](https://github.com/diegosouzapw/OmniRoute/pull/9892), original [#9712](https://github.com/diegosouzapw/OmniRoute/pull/9712)) — thanks @hartmark
-- **fix(responses-api): sync reasoning-cache write index with the fixed read side** ([#9895](https://github.com/diegosouzapw/OmniRoute/pull/9895), original [#9741](https://github.com/diegosouzapw/OmniRoute/pull/9741)) — thanks @hartmark
-- **fix(ci): repair release lint test regressions** ([#9896](https://github.com/diegosouzapw/OmniRoute/pull/9896), original [#9813](https://github.com/diegosouzapw/OmniRoute/pull/9813)) — thanks @alex-jordan547
-- **fix(command-code): include tool call arguments** ([#9897](https://github.com/diegosouzapw/OmniRoute/pull/9897), original [#9821](https://github.com/diegosouzapw/OmniRoute/pull/9821)) — thanks @Chewji9875
-- **fix(providers): remove retired NVIDIA NIM catalog entries** ([#9898](https://github.com/diegosouzapw/OmniRoute/pull/9898), original [#9825](https://github.com/diegosouzapw/OmniRoute/pull/9825)) — thanks @Zartharas
-- **fix(nvidia): keep 410 failures model-scoped** ([#9899](https://github.com/diegosouzapw/OmniRoute/pull/9899), original [#9833](https://github.com/diegosouzapw/OmniRoute/pull/9833)) — thanks @Zartharas
-- **fix: retry CodeBuddy large-tool requests in compact form** ([#9900](https://github.com/diegosouzapw/OmniRoute/pull/9900), original [#9542](https://github.com/diegosouzapw/OmniRoute/pull/9542)) — thanks @mvanhorn
-- **fix(quality): clears two release/v3.8.50 base-red gates** ([#9901](https://github.com/diegosouzapw/OmniRoute/pull/9901), original [#9619](https://github.com/diegosouzapw/OmniRoute/pull/9619)) — thanks @wgordon17
-- **fix: resolve hollow external package directory crashes and implement …** ([#9913](https://github.com/diegosouzapw/OmniRoute/pull/9913)) — thanks @SupremeNexas
-- **fix(i18n): restore Vietnamese locale parity** ([#9925](https://github.com/diegosouzapw/OmniRoute/pull/9925))
-- **fix(combo): classify Cloudflare 1010 fingerprint rejection as non-auth** ([#9929](https://github.com/diegosouzapw/OmniRoute/pull/9929)) — thanks @HouMinXi
-- **fix(image): return Fal images as base64 by default** ([#9932](https://github.com/diegosouzapw/OmniRoute/pull/9932)) — thanks @rinseaid
-- **fix(image): support Fal reference-image edits** ([#9933](https://github.com/diegosouzapw/OmniRoute/pull/9933)) — thanks @rinseaid
-- **fix(db): invalidate LKGP pins on provider connection delete** ([#9936](https://github.com/diegosouzapw/OmniRoute/pull/9936)) — thanks @Zartharas
-- **fix(services): stop embedded-service supervisor retry loop when binary cannot spawn** ([#9937](https://github.com/diegosouzapw/OmniRoute/pull/9937)) — thanks @herjarsa
-- **fix(backend): retain streaming usage for providers with choices:[{delta:{}}] final chunk** ([#9938](https://github.com/diegosouzapw/OmniRoute/pull/9938)) — thanks @sadSanta-07
-- **fix(antigravity): ban-safety hardening — bounded onboarding retries, gate thought-signature bypass sentinel** ([#9939](https://github.com/diegosouzapw/OmniRoute/pull/9939)) — thanks @benzntech
-- **fix(guardrails): vision bridge reroute/pool/self-loop fixes (auto/best-vision, claude-wire base64)** ([#9946](https://github.com/diegosouzapw/OmniRoute/pull/9946)) — thanks @herjarsa
-- **fix(mcp): stop omniroute_get_health silently discarding real data** ([#9959](https://github.com/diegosouzapw/OmniRoute/pull/9959)) — thanks @tald26
-- **fix(build): bump @huggingface/transformers to 4.2.0 + onnxruntime-node 1.24.3** ([#9962](https://github.com/diegosouzapw/OmniRoute/pull/9962)) — thanks @witt3rd
-- **fix(cleanup): prune mcp_tool_audit/a2a_task_events by created_at column** ([#9963](https://github.com/diegosouzapw/OmniRoute/pull/9963)) — thanks @witt3rd
-- **fix(db): avoid skipping pending job registry migration 146** ([#9965](https://github.com/diegosouzapw/OmniRoute/pull/9965)) — thanks @Zartharas
-- **fix(video): support Fal-hosted Grok Imagine Video** ([#9969](https://github.com/diegosouzapw/OmniRoute/pull/9969)) — thanks @rinseaid
-- **fix(i18n): escape angle brackets in denoRelayOrgDomainHint across all 43 locales** ([#9976](https://github.com/diegosouzapw/OmniRoute/pull/9976)) — thanks @AgnesRiber
-- **fix(media): support Gemini Omni Flash video** ([#9982](https://github.com/diegosouzapw/OmniRoute/pull/9982)) — thanks @rinseaid
-- **fix(copilot-web): restore browser authentication** ([#9984](https://github.com/diegosouzapw/OmniRoute/pull/9984)) — thanks @backryun
-- **fix(opencode): fallback unsupported DeepSeek json schema output** ([#9992](https://github.com/diegosouzapw/OmniRoute/pull/9992)) — thanks @Zartharas
-- **fix(translator): restore TitleCase tool names on the Claude to Gemini path** ([#9993](https://github.com/diegosouzapw/OmniRoute/pull/9993)) — thanks @engmarcosjr
-- **fix(providers): scope model-level targetFormat to declaring provider catalog** ([#9994](https://github.com/diegosouzapw/OmniRoute/pull/9994)) — thanks @Chewji9875
-- **fix(kimi): apply K3 effort policy to aliases** ([#10005](https://github.com/diegosouzapw/OmniRoute/pull/10005)) — thanks @jackjinke
-- **fix(adobe-firefly) — direct pushes:** harden credential parsing and login hostname comparison (parse-and-compare instead of substring match), sync models/media capabilities, and retain the Topaz catalog models
-- **fix(combo/sse) — direct pushes:** ignore benign empty error fields in streaming-quality validation, classify local target timeouts as gateway timeouts, avoid the usage-normalization short-circuit in Responses, and type empty-choice collector events
-- **fix(logging) — direct pushes:** make stream-chunk capture and request-shape logging opt-in diagnostics
-- **fix(i18n) — direct pushes:** restore/unescape HTML entities in UI strings, translate capability-filter messages, complete web-session guide translations and Vietnamese parity
-- **fix(providers) — direct pushes:** repair the DeepAI registry import + executor
-- **fix(deps) — direct pushes:** CVE-driven bumps (nanoid, dompurify, mermaid, js-yaml + transitive deps for 26 Dependabot alerts) and retained isolated-build runtime dependencies in the pack
-- **fix(ci):** pin Build (advisory) to a hosted runner with memory provisioning ([#10408](https://github.com/diegosouzapw/OmniRoute/pull/10408))
-- **fix(providers):** refresh the translate-path golden for the bailian Token Plan endpoint ([#10410](https://github.com/diegosouzapw/OmniRoute/pull/10410))
-- **fix(sse):** surface Qwen/Alibaba personal Token Plan quota in dashboard and preflight ([#10290](https://github.com/diegosouzapw/OmniRoute/pull/10290))
-- **fix(deps):** pin next to an exact version so a fresh upstream release cannot break installs ([#10340](https://github.com/diegosouzapw/OmniRoute/pull/10340))
-- **fix(types):** restore custom model output limit contract ([#10339](https://github.com/diegosouzapw/OmniRoute/pull/10339)) — thanks @backryun
-- **fix(sse):** stop the executor-contract guard from hot-looping the router ([#10373](https://github.com/diegosouzapw/OmniRoute/pull/10373))
-- **fix(types):** validate nonstreaming JSON contracts ([#10258](https://github.com/diegosouzapw/OmniRoute/pull/10258)) — thanks @backryun
-- **fix(types):** narrow refresh token rotation inputs ([#10257](https://github.com/diegosouzapw/OmniRoute/pull/10257)) — thanks @backryun
-- **fix(types):** normalize executor result contracts ([#10256](https://github.com/diegosouzapw/OmniRoute/pull/10256)) — thanks @backryun
-- **fix(types):** align Responses stream options ([#10255](https://github.com/diegosouzapw/OmniRoute/pull/10255)) — thanks @backryun
-- **fix(types):** narrow combo credential preflight ([#10254](https://github.com/diegosouzapw/OmniRoute/pull/10254)) — thanks @backryun
-- **fix(compression):** cap countTextTokens at 50k chars and strip base64 data URIs ([#10118](https://github.com/diegosouzapw/OmniRoute/pull/10118)) — thanks @adevwithpurpose
-- **fix(ci):** clear base-reds on release/v3.8.50 (round 4) ([#10260](https://github.com/diegosouzapw/OmniRoute/pull/10260))
-- **fix(sse):** extract perplexity-web answers from workflow_block ([#10259](https://github.com/diegosouzapw/OmniRoute/pull/10259)) — thanks @jeyhunfaslanov
-- **fix(mcp):** persist and re-attach Gemini thoughtSignature on the direct Claude<->Gemini path ([#9448](https://github.com/diegosouzapw/OmniRoute/pull/9448)) — thanks @Sam280903
-- **fix(opencode-plugin):** respect log level for lifecycle output (#8982) ([#9316](https://github.com/diegosouzapw/OmniRoute/pull/9316)) — thanks @xiaoyaner0201
-- **fix(providers):** raise default provider probe timeout from 5s to 8s ([#9283](https://github.com/diegosouzapw/OmniRoute/pull/9283)) — thanks @Sam280903
-- **fix(opencode-plugin):** stop warning when an auto combo replaces its expected /v1/models twin (#8983) ([#9042](https://github.com/diegosouzapw/OmniRoute/pull/9042)) — thanks @xiaoyaner0201
-- **fix(opencode):** force CLI User-Agent when CLI identity synthesis is enabled ([#10222](https://github.com/diegosouzapw/OmniRoute/pull/10222)) — thanks @adevwithpurpose
-- **fix(deepseek-web):** classify business auth rejection as 401 ([#10218](https://github.com/diegosouzapw/OmniRoute/pull/10218)) — thanks @Zartharas
-- **fix(combo):** make failoverBeforeRetry actually skip the same-model retry ([#10217](https://github.com/diegosouzapw/OmniRoute/pull/10217)) — thanks @hartmark
-- **fix(responses):** preserve case-insensitive combo names before Codex rewrite ([#10177](https://github.com/diegosouzapw/OmniRoute/pull/10177)) — thanks @ddarkr
-- **fix(discovery):** parse reasoning tiers nested under metadata.reasoning.supported_efforts ([#10138](https://github.com/diegosouzapw/OmniRoute/pull/10138)) — thanks @excessivechaos
-- **fix(combo):** isolate session stickiness by combo ([#10137](https://github.com/diegosouzapw/OmniRoute/pull/10137)) — thanks @hydraxman
-- **fix(combo):** default chaos SSE to comment-only for OpenAI-compatible clients ([#10128](https://github.com/diegosouzapw/OmniRoute/pull/10128)) — thanks @herjarsa
-- **fix(kimi):** normalize MFJS tool schemas ([#10079](https://github.com/diegosouzapw/OmniRoute/pull/10079)) — thanks @xz-dev
-- **fix(mcp):** move pack validation out of unit suite ([#10065](https://github.com/diegosouzapw/OmniRoute/pull/10065)) — thanks @yansigit
-- **fix(zed-hosted):** send the provider wire values cloud.zed.dev accepts ([#10051](https://github.com/diegosouzapw/OmniRoute/pull/10051)) — thanks @ARC345
-- **fix(ci):** repair and wire the two live-server E2E suites ([#10050](https://github.com/diegosouzapw/OmniRoute/pull/10050)) — thanks @ARC345
-- **fix(reasoning):** preserve and replay assistant turns ([#10045](https://github.com/diegosouzapw/OmniRoute/pull/10045)) — thanks @jackjinke
-- **fix(types):** tighten chatCore helper contracts ([#10175](https://github.com/diegosouzapw/OmniRoute/pull/10175)) — thanks @backryun
-- **fix(cli):** read the full provider catalog instead of the 6-entry fallback ([#10097](https://github.com/diegosouzapw/OmniRoute/pull/10097)) — thanks @amartinawi
-- **fix(cli):** stop swallowing non-2xx responses into benign-looking results ([#10092](https://github.com/diegosouzapw/OmniRoute/pull/10092)) — thanks @amartinawi
-- **fix(cli):** openapi endpoints/paths/validate accept the served catalog shape ([#10091](https://github.com/diegosouzapw/OmniRoute/pull/10091)) — thanks @amartinawi
-- **fix(cli):** doctor detects prebuilt better-sqlite3 binaries ([#10090](https://github.com/diegosouzapw/OmniRoute/pull/10090)) — thanks @amartinawi
-- **fix(providers):** kilo-gateway authType should be optional, not apikey ([#10086](https://github.com/diegosouzapw/OmniRoute/pull/10086)) — thanks @TengSivtean
-- **fix(cli):** strip inline comments when parsing .env values ([#10101](https://github.com/diegosouzapw/OmniRoute/pull/10101)) — thanks @amartinawi
-- **fix(logging):** document CHAT_LOG_MAX_BODY_KB, capture messageCount for Responses API bodies ([#10038](https://github.com/diegosouzapw/OmniRoute/pull/10038)) — thanks @hartmark
-- **fix(dashboard):** expose OpenAI Responses store toggle for non-Codex connections ([#10121](https://github.com/diegosouzapw/OmniRoute/pull/10121)) — thanks @hartmark
-- **fix(combo):** clear LKGP pin when its target fails, not only set it on success ([#10034](https://github.com/diegosouzapw/OmniRoute/pull/10034)) — thanks @hartmark
-- **fix(sse):** provider-response summary format bugs (dashboard Provider Response panel) ([#10037](https://github.com/diegosouzapw/OmniRoute/pull/10037)) — thanks @hartmark
-- **fix(responses-api):** tool call after reasoning collided on the same output_index ([#10025](https://github.com/diegosouzapw/OmniRoute/pull/10025)) — thanks @hartmark
-- **fix(responses-api):** explicit function-tool declaration must win over apply_patch-is-custom fallback ([#10041](https://github.com/diegosouzapw/OmniRoute/pull/10041)) — thanks @hartmark
-- **fix(kimi):** recupera limite temporario sem bloquear conta ([#10058](https://github.com/diegosouzapw/OmniRoute/pull/10058)) — thanks @bortolidiego
-- **fix(translator):** preserve Responses custom tools for OpenAI-compatible providers ([#10114](https://github.com/diegosouzapw/OmniRoute/pull/10114)) — thanks @mtb-ninja
-- **fix(providers):** xai-oauth chat→responses body + missing breaker import (#10165) ([#10170](https://github.com/diegosouzapw/OmniRoute/pull/10170)) — thanks @nordz0r
-- **fix(ollama-cloud):** map xhigh reasoning effort to max ([#10160](https://github.com/diegosouzapw/OmniRoute/pull/10160)) — thanks @Chewji9875
-- **fix(translator):** strip Codex encrypted tool-schema key for Gemini/Antigravity ([#10053](https://github.com/diegosouzapw/OmniRoute/pull/10053)) — thanks @XDayonline
-- **fix(combo):** preserve OpenCode Free oc/ prefix for connections ([#10180](https://github.com/diegosouzapw/OmniRoute/pull/10180)) — thanks @AStupidBear
-- **fix(sse):** apply free-tier filter to auto/best-free on chat path ([#10199](https://github.com/diegosouzapw/OmniRoute/pull/10199)) — thanks @ggdayup
-- **fix(providers):** default missing cache_control.ttl to 1h on the native Claude OAuth path ([#10221](https://github.com/diegosouzapw/OmniRoute/pull/10221)) — thanks @jeff-alves
-- **fix(ci):** clear base-reds on release/v3.8.50 (round 3) ([#10213](https://github.com/diegosouzapw/OmniRoute/pull/10213))
-- **fix(security):** correct XML double-unescape and non-CSPRNG nonce from CodeQL sweep ([#10154](https://github.com/diegosouzapw/OmniRoute/pull/10154))
-- **fix(docker):** eliminate npm-bundled CVEs from the published image ([#10182](https://github.com/diegosouzapw/OmniRoute/pull/10182))
-- **fix(security):** resolve open CodeQL alerts ([#10188](https://github.com/diegosouzapw/OmniRoute/pull/10188))
-- **fix(dashboard):** retarget Kimi promo CTA to the API platform aff link ([#10200](https://github.com/diegosouzapw/OmniRoute/pull/10200))
-- **fix(build):** repair broken production build, red lint gate and SWR crash ([#10198](https://github.com/diegosouzapw/OmniRoute/pull/10198))
-- fix(cli): repair hollow externalized package dirs in the nested `<distDir>/node_modules` bundle location too, not just the top-level one, fixing macOS/Linux Electron `ERR_MODULE_NOT_FOUND` on Turbopack-externalized packages (#7346)
-- **Electron packaged smoke test:** add a cold-restart mode (`ELECTRON_SMOKE_COLD_RESTART=1`, wired blocking on the Linux release leg) that relaunches the packaged app against its own persisted `DATA_DIR` and asserts a native SQLite driver was selected instead of the sql.js WASM fallback, closing the regression-test gap flagged in the stale-ABI `better-sqlite3` investigation ([#7592](https://github.com/diegosouzapw/OmniRoute/issues/7592)).
-- **fix(usage):** keep session/weekly/monthly quota windows in chronological order on every provider card. The order is now derived from the quota keys themselves instead of a provider whitelist, so Claude, MiniMax, Z.ai and Command Code stop rendering the two bars in opposite positions across sibling accounts ([#7764](https://github.com/diegosouzapw/OmniRoute/issues/7764))
-- **fix(images):** retry Codex image generation on a sibling ChatGPT account when the requested model isn't entitled on the current account, instead of failing the request outright ([#8307](https://github.com/diegosouzapw/OmniRoute/pull/8307)).
-- fix(dashboard): treat UncloseAI as a no-auth provider so the connect form no longer forces a fake API key (#8864)
-- **fix(dashboard):** model-level allowed/blocked param edits now persist when the compatibility popover is closed by clicking outside, and a failed save no longer clears the edit or reports success ([#9013](https://github.com/diegosouzapw/OmniRoute/pull/9013))
-- fix(ssrf): make `getProviderOutboundGuard()` (used for search-provider connection validation, image generation and remote image fetch) honor the local-first default `OMNIROUTE_ALLOW_LOCAL_PROVIDER_URLS` the same way the chat validation guard already does, so a LAN-hosted SearXNG/Brave search provider works with only the LOCAL flag set instead of silently requiring `OMNIROUTE_ALLOW_PRIVATE_PROVIDER_URLS` ([#9123](https://github.com/diegosouzapw/OmniRoute/issues/9123)).
-- fix(compression): preserve unfenced raw code (e.g. Copilot #file references) from Caveman's prose recapitalization/whitespace cleanup, which was corrupting keyword casing and indentation (#9144)
-- fix(api): yield the event loop during catalog builds and bulk-load override/hidden-model tables (#9147)
-- fix(combo): recovery hint for all_targets_skipped now points at provider quota/availability instead of 'transient, just retry' (#9303)
-- fix(providers): strip uniqueItems from Gemini tool schemas (Gemini rejects it with 400 'Unknown name uniqueItems') (#9617)
-- **fix(translator):** convert OpenAI `image_url` blocks nested in `role: "tool"` / `tool_result` content to Claude `image` source blocks so OpenAI-compatible clients (Kimi Code CLI `ReadMediaFile`, and any other tool that returns media) no longer 400 the next Claude-format upstream turn ([#9692](https://github.com/diegosouzapw/OmniRoute/issues/9692))
-- **fix(resilience):** retry a retryable Codex pre-output 502/503/504/507 once on the same account (2–3s jitter) before cooling the connection, and stop translating that mixed pool into an all-accounts quota `429` ([#9708](https://github.com/diegosouzapw/OmniRoute/issues/9708))
-- **fix(ratelimit):** respect operator `minTimeBetweenRequestsMs` floor when relaxing the limiter on headroom — the adaptive rate-limit learning no longer silently erases a configured minimum gap between requests when the upstream reports plenty of remaining capacity ([#9763](https://github.com/diegosouzapw/OmniRoute/issues/9763)).
-- **fix(test):** remove live `npm pack` from MCP files unit test (it stalled concurrent `test:unit` via prepare→husky + monorepo pack walk); keep the static #3578 `files` allowlist + negation guards in unit and fold #3821 pack assertions into `check:pack-artifact` / `check:pack-policy` (already `--ignore-scripts`).
-- fix(dashboard): media mini-playgrounds authenticate via session instead of sending the masked API key as Bearer, fixing 401s under REQUIRE_API_KEY (#9935)
-- fix(sse): exclude search providers from credential-health scheduler sweep to stop burning billed API queries (#9970)
-- **Passthrough streaming:** stop leaking upstream SSE control lines (`id:`/`event:`/`retry:`/`:` comments) to plain OpenAI Chat-Completions-format clients, while preserving `event:` framing for OpenAI Responses API and Claude Messages API passthrough ([#10017](https://github.com/diegosouzapw/OmniRoute/issues/10017)).
-- fix(cli): stop diagnosing every Next.js instrumentation-hook failure as the Android/Termux cache bug — only the Android "Unsupported platform: android" signal now triggers the Android hint, so a win32/desktop instrumentation error surfaces its real cause instead of a useless `mkdir -p ~/.cache` (#10028)
-- **fix(build):** stop the native `better-sqlite3` addon from loading during the Next.js production build (#10060). Its `Statement` destructor aborts with `SIGABRT` when a build worker thread exits (assertion in `node::RemoveEnvironmentCleanupHook`, `env == nullptr`), which can leave the build with no standalone bundle. Every DB entry point now keys off a reliable `OMNIROUTE_BUILDING=1` signal (set by `build-next-isolated.mjs` and inherited by every spawned build worker, because Next.js workers sometimes drop `NEXT_PHASE`): `getDbInstance()` returns a no-op SQLite stub during build, `driverFactory` skips the native driver and falls through to `node:sqlite`, and the `codegraph`/`kiro-import` lazy loaders fail closed. A build-time `better-sqlite3` alias to a stub (`next.config.mjs`, turbopack) backs this up without changing runtime behaviour (the real package is still `require()`d natively via `serverExternalPackages`). Also raises the default build heap 4096→6144 MB and caps Next build worker pools (`CIRCLE_NODE_TOTAL=8`) to avoid the many-core page-data-collection SIGSEGV, and adds `.gitattributes` (`*.sh text eol=lf`) so kernel-exec'd shell scripts never ship with CRLF shebangs. Deliberately does NOT downgrade the Node base image: per the maintainer's review on #10060, `release/v3.8.50` moved to `node:26-trixie-slim` through several considered commits, so the `OMNIROUTE_BUILDING` guard is re-derived against the current base rather than reverting the FROM line; the npm pin and binary-hide dance from the original PR are dropped because our build already rebuilds `better-sqlite3` deterministically via `node-gyp` and floats `npm@latest` for the CVE overlay.
-- **fix(providers):** the five g4f.space sub-providers (Groq, Gemini, Pollinations, Ollama, NVIDIA) no longer advertise a free tier — a keyless `POST /v1/chat/completions` now returns `402 insufficient_credits` behind a proof-of-work "cake" wall (re-verified live 2026-08-22), so `hasFree` is `false` and the notes point at `g4f.dev/members.html`. The gateway still works with a member key, so its registry wiring and `authType: "optional"` are unchanged ([#10071](https://github.com/diegosouzapw/OmniRoute/issues/10071)) — thanks @chirag127
-- **fix(chatgpt-web):** Preserve native `max` thinking effort through ChatGPT Web routing ([#10077](https://github.com/diegosouzapw/OmniRoute/pull/10077)) — thanks @zannen7
-- Fix: wire AgentRouter's existing console balance fetcher into the Dashboard Quota UI (visibility gate + provider-limits data path + background sync) so its wallet balance renders instead of falling back to "Usage API not implemented" (#10078)
-- Fix: AgentRouter's dollar balance now renders as a currency-formatted "$X.XX" credits row in the Dashboard Quota UI instead of a bare percentage, and an exhausted wallet always shows exactly $0.00 (#10078)
-- fix(sse): bridge generic openai-compatible/anthropic-compatible provider type ids to their concrete uuid node id in credential lookup (#10085)
-- fix(domain): stop treating an unreported Antigravity quota fraction (`fractionReported:false`) as 0% remaining in `quotaCache.ts`, which was falsely marking every fresh/newly-connected account as exhausted and blocking multi-account rotation (#10095)
-- fix(dashboard): remap unified Kimi Code card API-key save to the admitted `kimi-coding-apikey` connection id, fixing 400 "Invalid provider" on Save (#10096)
-- fix(antigravity): strip trailing model turn for native Gemini requests too, not just Claude (#10104)
-- **fix(admission):** stop the adaptive latency-gradient collapse from permanently locking out ordinary requests — individually valid requests now make solo progress when the system is idle and normal pressure, and the collapsed limit actively recovers on sustained idle windows instead of being stuck; the critical-pressure fuse still wins over solo progress (#10111)
-- fix(sse): downgrade client-supplied `thinking:{type:"adaptive"}` to `enabled` and gate the `context-1m-2025-08-07` beta on model eligibility when a combo/fallback re-routes a request to a non-adaptive/non-1M model like claude-haiku-4-5 (avoids "adaptive thinking is not supported on this model" and "long context beta is not yet available" 400s, #10119)
-- **fix(logging):** move call-log artifact serialization and filesystem writes to a bounded singleton worker to keep request handling responsive (#10123)
-- **perf(logging):** bound each scheduled call-log rotation pass to incremental database and filesystem work (#10125)
-- **fix(streaming):** start early SSE heartbeats when Responses or Messages requests opt into streaming through the request body (#10127)
-- **fix(combo):** scope session-stickiness bindings to their owning Combo so identical first messages cannot carry a successful target into another priority chain and bypass its configured order (fixes #10136)
-- **fix(translator):** resolve the Claude thinking output cap with the routed provider so a provider-scoped-only `max_output_tokens` override is no longer invisible to `fitThinkingToMaxTokens()`, which previously let the synthesized `max_tokens` (caller room + thinking budget) go out unbounded and 400 upstream ([#10139](https://github.com/diegosouzapw/OmniRoute/issues/10139))
-- fix(providers): correct the conol-web registry fallback-models import depth, which pointed at a
-  non-existent `open-sse/config/services/` and made any suite loading the provider registry fail to
-  resolve (#10140)
-- **fix(oauth):** Claude connections created via `claude-auth/import` now send required CLI headers on the bootstrap identity call and persist a `cliUserID` device identity, fixing intermittent "Third-party apps now draw from your extra usage" 400s on otherwise valid imported subscription tokens ([#10144](https://github.com/diegosouzapw/OmniRoute/pull/10144), fixes [#10143](https://github.com/diegosouzapw/OmniRoute/issues/10143))
-- **fix(sse):** Responses-passthrough `response.completed` snapshots now drop `phase:"commentary"` items the same way live SSE frames already do, so the terminal `response.output` array no longer echoes internal commentary text that was already suppressed from the stream (#10156).
-- fix(proxy-subscriptions): allow local/loopback proxy-subscription fetch URLs (local-first, cloud-metadata still blocked) (#10158)
-- **fix(routing):** keep approximate Combo context estimates advisory so requests reach concrete targets instead of returning a pre-dispatch 400 ([#10162](https://github.com/diegosouzapw/OmniRoute/pull/10162)) — thanks @xz-dev
-- **docs(settings):** document Thinking Budget modes (passthrough vs auto-strip); fix dashboard i18n key collision that showed Auto Combo routing copy on the thinking tab; clarify independence from compression/cache ([#10169](https://github.com/diegosouzapw/OmniRoute/pull/10169))
-- fix(cli): guarantee a non-empty `[STARTUP] Fatal:` log line for any instrumentation-hook boot throw, not just DB-driver init failures (#10171)
-- fix(sse): gate structural chat admission shedding on real heap pressure instead of unconditional capacity, with a bounded headroom budget so a healthy heap can no longer bypass admission control indefinitely (#10183, #10268)
-- **fix(guardrails):** Vision Bridge handles OpenAI Responses `input`/`input_image` requests before combo vision filtering ([#10202](https://github.com/diegosouzapw/OmniRoute/pull/10202)) — thanks @Zartharas
-- **fix(cursor):** Stop truncating pending tool calls on non-composer models when a KV checkpoint arrives after text but before the `exec_mcp` frame — the KV short-circuit is now gated to the composer family where it was verified ([#10215](https://github.com/diegosouzapw/OmniRoute/issues/10215)).
-- **fix(responses):** repair corrupted SSE deltas for non-ASCII streams by keeping a single stream-aware `TextDecoder` (`{ stream: true }`) across `transform()` calls instead of recreating it per chunk and decoding without the `stream` flag. When a multi-byte UTF-8 character (CJK/emoji) was split across two TCP chunks — common in Chinese streaming text — the per-chunk decoder truncated it to `U+FFFD`, corrupting every delta while the rebuilt `*.done` snapshot stayed internally identical ([#10223](https://github.com/diegosouzapw/OmniRoute/issues/10223))
-- **fix(combo):** defer the known-context-overflow hard rejection for compressible requests so compression runs before the final context gate, instead of a raw-body estimate 400'ing generic Responses clients targeting a large model before OmniRoute can shrink it ([#10225](https://github.com/diegosouzapw/OmniRoute/issues/10225))
-- **fix(api):** deleting a manually-added custom model no longer tombstones a provider-synced model that shares its id. `DELETE /api/provider-models` is addressed by `provider` + `model` alone, so when both a custom row and a synced row existed for one id it removed both and wrote `isDeleted:true`. `replaceSyncedAvailableModelsForConnection` then filtered that id out of every subsequent re-import, so the provider could never resync — model sync kept reporting `added: N` while the catalog stayed empty and `/v1/models` never listed the model again, even though routing to it still worked. The custom row is now removed first and its presence is treated as the operator's intent, leaving the synced sibling importable; a synced-only delete still tombstones as before (#3199, #3782 unaffected) ([#10228](https://github.com/diegosouzapw/OmniRoute/pull/10228)) — thanks @Neuron-Mr-White
-- **Audio Bridge:** fix production transcription self-loop uploads so real audio reaches the configured STT provider instead of falling back to an unavailable-provider stub ([#10229](https://github.com/diegosouzapw/OmniRoute/pull/10229)).
-- **fix(api):** DeepSeek V4's native `max` reasoning tier is now reachable. DeepSeek accepts `reasoning_effort` `low`/`high`/`max` and maps `medium`/`xhigh` down to `high`, while OmniRoute's canonical vocabulary collapses `max` onto `xhigh` — so `{"effort":"max"}` silently resolved to `high` and the catalog never advertised a `max` tier (or its `<model>-max` variant). Following the existing `extendCodexGpt56EffortValues` precedent, the native tier is now preserved for `deepseek`/`ds` V4 models only; the global effort vocabulary is unchanged, routed namespaces (`openrouter/deepseek/…`, `tllm/deepseek_v4`, `oc/deepseek-v4-flash-free`) keep the canonical behavior, and an explicit client `reasoning_effort` still wins ([#10230](https://github.com/diegosouzapw/OmniRoute/pull/10230)) — thanks @Neuron-Mr-White
-- **fix(providers):** FreeAIAPIKey now targets `api.freeaiapikey.com`, the host upstream names in its `410 endpoint_moved` response — every request through the provider was failing — and its catalog is resynced to the 10 models the live `/v1/models` actually serves ([#10233](https://github.com/diegosouzapw/OmniRoute/pull/10233))
-- **fix(providers):** MonsterAPI's deprecation now actually applies — the flag was written as `isDeprecated`, a key no consumer or schema reads, so the provider kept rendering as healthy in the dashboard, the onboarding wizard and the generated provider reference ([#10234](https://github.com/diegosouzapw/OmniRoute/pull/10234))
-- **fix(cliproxy):** read platform/arch at runtime via `os.platform()`/`os.arch()` in `binaryManager` so the embedded installer selects the Windows/ARM assets even when the release bundle is built on a Linux runner (fixes #10244)
-- **fix(providers):** compatible/custom providers now save valid Data URL icons and show Add/Edit save failures instead of silently doing nothing ([#10247](https://github.com/diegosouzapw/OmniRoute/pull/10247)) — thanks @xz-dev
-- **fix(models):** custom model metadata and compatible-provider context overrides now take precedence over discovered metadata, while deleting a synced model no longer creates a permanent tombstone so a later provider sync can restore it ([#10248](https://github.com/diegosouzapw/OmniRoute/pull/10248)) — thanks @jackjinke
-- fix(open-sse): stop concurrent requests colliding on the same dedup hash for non-OpenAI target formats (#10249)
-- **fix(translator):** Text-format tool calls emitted inline by some models are now converted to proper `tool_use` blocks. Certain models (DeepSeek, Qwen) return tool invocations as `<tool_call>{"name":"Bash","arguments":{…}}</tool_call>` or `TOOL_CALL Read: {"file_path":"…"}` inside the text stream instead of the structured `tool_calls` field. Both formats leaked through the Claude translators as plain text, so Claude Code rendered the raw block and stalled instead of executing the tool. `extractXmlInvokeBlocks` (previously `<invoke>`-only) now scans for all three shapes in a single pass and emits `content_block_start`/`input_json_delta`/`content_block_stop` events, in both `openai-to-claude` and `gemini-to-claude` (Antigravity) paths ([#10251](https://github.com/diegosouzapw/OmniRoute/pull/10251))
-- fix(dashboard): make provider card warning indicators expose the interaction they advertise (#10261)
-- fix(command-code): route chat to the documented /provider/v1/chat/completions endpoint instead of the CLI-only /alpha/generate, which Command Code gates/blocks for external callers (#10265)
-- **fix(providers):** preserve validator HTTP status codes in API-key and web connection-test results so callers can distinguish authentication, rate-limit, and upstream failures ([#10272](https://github.com/diegosouzapw/OmniRoute/pull/10272)) — thanks @Zartharas
-- **fix(sse):** tiny-budget reasoning probes (e.g. Claude Code's `/model` check sends `max_tokens: 1`) are answered with a valid truncated 200 instead of relaying the upstream 5xx "empty response content" — which previously also marked the connection unavailable and poisoned fallback/cooldown bookkeeping for a request that is only a probe ([#10281](https://github.com/diegosouzapw/OmniRoute/issues/10281)) — thanks @harkaranbrar7
-- fix(video): stop advertising the googleflow (Veo) video provider as working and fail fast with a clear diagnostic — its submit/poll endpoints 404 and no server-side OAuth transport can satisfy the working endpoint (#10285)
-- **fix(build):** stop Turbopack from dead-code-eliminating the Windows Tailscale branches of `src/lib/tailscaleTunnel.ts` in the published build (#10293). The release `dist` is bundled on a Linux runner, and the bundler constant-folds `process.platform`, pruning every non-Linux branch — the Windows installers shipped with no `where` lookup, an always-injected `--socket`, and a lost `net start Tailscale`/windows-default-binary path. The module now reads the platform at runtime via `os.platform()` (a function call a bundler cannot fold), so the Windows branches survive on any build machine; a vitest regression test mocking `os.platform()` → `win32` guards the anti-fold invariant (RED before, GREEN after).
-- **fix(ops):** Docker HEALTHCHECK defaults to the lightweight `/healthz` lifecycle probe instead of the heavy `/api/monitoring/health` path, with an `OMNIROUTE_HEALTHCHECK_PATH` opt-in override ([#10311](https://github.com/diegosouzapw/OmniRoute/pull/10311))
-- fix(api): hash the API key before using it as the model-catalog cache Map key (no raw credentials in process heap) (#10313)
-- fix(resilience): keep combo quality and auth failure reasons separate and redact connection labels in terminal errors (#10314)
-- fix(dashboard): send periodic WS heartbeat pings so live dashboard connections stop dropping every ~35s (#10319)
-- **fix(chat-body-admission):** restore a single process-wide admission budget — heavyweight leases and queued bytes are now bounded once for the whole process instead of per session, so one session can no longer mint extra capacity or starve others; per-session fairness is preserved via round-robin dispatch ([#10110](https://github.com/diegosouzapw/OmniRoute/issues/10110))
-- **fix(providers):** validate Z.ai web Local Storage sessions against the authenticated user-settings endpoint and preserve exact upstream status codes ([#10329](https://github.com/diegosouzapw/OmniRoute/pull/10329)) — thanks @Zartharas
-- **fix(opencode-plugin):** publish bare combo model ids without the plugin provider prefix so OpenCode can select them ([#10345](https://github.com/diegosouzapw/OmniRoute/issues/10345))
-- **fix(backend):** log `auto/<family> matched no connected models` once per process per label instead of every minute ([#10346](https://github.com/diegosouzapw/OmniRoute/issues/10346))
-- fix(backend): redact client IPs and account prefixes from default proxy logs (#10348)
-- **fix(github):** proactive credential health now verifies GitHub access tokens through the existing Copilot token exchange, marks only a confirmed `401 Unauthorized` as expired, and leaves rate limits, permission failures, upstream failures, and network errors routable ([#10352](https://github.com/diegosouzapw/OmniRoute/issues/10352)) — thanks @RaviTharuma
-- **fix(docker):** warn at boot when `OMNIROUTE_MEMORY_MB` disagrees with `NODE_OPTIONS --max-old-space-size`, and document that the standalone/Docker launcher appends `OMNIROUTE_MEMORY_MB` last ([#10353](https://github.com/diegosouzapw/OmniRoute/issues/10353))
-- fix(providers): GitLab Duo falls back to the public Code Suggestions endpoint when direct_access returns 401 (#10365)
-- **fix(db):** `getSettings()` defaults `debugMode` to `false` — fresh installs no longer run in debug mode (persisted `debugMode: true` is preserved) ([#10372](https://github.com/diegosouzapw/OmniRoute/pull/10372) — thanks @lamchun1110)
-- **fix(translator):** Consolidate tool-name casing normalization into a single `restoreClaudeToolName` helper reused across every response path (`openai-to-claude`, `gemini-to-claude`, `stream` passthrough, xAI and Antigravity handlers), replacing six hand-copied 7-entry casing maps. The shared helper resolves via the request-side `toolNameMap` first (preserving declared PascalCase and MCP/alias names), then the complete `TOOL_RENAME_MAP` (which already covers `glob`/`grep`/`task`/`todowrite`/`skill`/`askuserquestion`/etc.), then the `#7926` TitleCase→lowercase fallback for map-less clients. This closes the coverage gap that left `TodoWrite` and other tools failing with `Error: No such tool available: todowrite`, fixes a `ReferenceError` in `remapToolNamesInResponse`, and preserves the Gemini thought-signature persistence (`#8979`) and OpenAI→Claude `toolNameMap` restoration that must not regress ([#10374](https://github.com/diegosouzapw/OmniRoute/issues/10374))
-- **fix(responses):** preserve native tool definitions for custom OpenAI-compatible providers when using the Responses API (`/v1/responses`). When `apiType` is set to `"responses"` (or `_omnirouteForceResponsesUpstream` is enabled), OmniRoute passes native tool shapes (`custom` with lark grammars, `namespace`, `local_shell`) directly upstream without running a lossy Responses→Chat→Responses conversion ([#10374](https://github.com/diegosouzapw/OmniRoute/issues/10374))
-- fix(dashboard): Free Tier 'used this month' now includes live usage_history rows, not just the rolled-up daily summary (#10381)
-- **fix(executors):** OpencodeExecutor and MimocodeExecutor now rotate to the next account on network exceptions (timeout, connection refused/reset) when the failed account has a dedicated proxy, not only on 429 — a throw on one account no longer fails the whole request when other accounts remain. Accounts sharing the default egress (no proxy) fail fast instead of retrying the same outage against every account. The shared rotation mechanics (`pickAccount`/`markCooldown`/`markSuccess`) are now extracted into `accountRotation.ts`, fixing an identical unconditional-cooldown gap that pre-dated this PR in MimocodeExecutor ([#10393](https://github.com/diegosouzapw/OmniRoute/pull/10393))
-- **fix(sse):** the header-budget drop warning fires once per unique dropped-header set instead of on every SSE response (warn-storm fix) ([#10397](https://github.com/diegosouzapw/OmniRoute/pull/10397) — thanks @lamchun1110)
-- fix(sse): fail over combo streaming responses that reach `finish_reason` with zero content, reasoning, or tool_calls instead of forwarding a terminated-but-empty completion (#10404)
-- **fix(guardrails):** Vision Bridge now reroutes whole requests for named combos whose targets have zero vision-capable models (previously such image requests died with `capability_mismatch` when the describe path could not run), and when the fallback describe path also fails for every image the request degrades to explicit `(unavailable)` stub text instead of preserving images the combo cannot consume ([#10415](https://github.com/diegosouzapw/OmniRoute/pull/10415)) — thanks @rqzbeh
-- **fix(antigravity):** geo-blocked egress (Google "User location is not supported") is now classified (scoped to the Google AI surfaces that emit it: Cloud Code/Gemini Code Assist, Gemini API, Vertex), cached as a 24h per-account exclusion so routing continues with other accounts, and surfaced with an actionable message; the dashboard connection test now probes the real `streamGenerateContent` model surface instead of the non-geo-restricted OAuth userinfo endpoint ([#10420](https://github.com/diegosouzapw/OmniRoute/pull/10420)) — thanks @rqzbeh
-- **fix(antigravity):** strip competing-agent identity sentences from system prompts (e.g. "You are a Claude agent, built on Anthropic's Claude Agent SDK.") that Antigravity flags and answers with 429 RESOURCE_EXHAUSTED (port of decolua/9router b566b20) ([#10420](https://github.com/diegosouzapw/OmniRoute/pull/10420)) — thanks @rqzbeh
-- **fix(antigravity):** accounts with an empty Cloud Code `projectId` now heal themselves — failed auto-onboarding (`onboardUser`) attempts are retried after a short backoff instead of being memoized forever, so the missing Google project is created without user action on a later request or token refresh ([#10424](https://github.com/diegosouzapw/OmniRoute/pull/10424)) — thanks @rqzbeh
-- **fix(antigravity):** Google deprecated automatic project creation for standard-tier (personal) accounts — when `onboardUser` completes without a project id the account now fails fast with a clear `403 GCP_PROJECT_REQUIRED` message (no more generic 422 or delayed 429 RESOURCE_EXHAUSTED), and a manual GCP Project ID override is available in the connection editor so operators can enter their own project id ([#10424](https://github.com/diegosouzapw/OmniRoute/pull/10424)) — thanks @rqzbeh
-- **fix(usage):** read Gemini `usageMetadata` out of the antigravity `{ response: {...} }` envelope so non-streaming requests log real token usage instead of `IN 0 | OUT 0` (port of decolua/9router#59d858b) ([#10430](https://github.com/diegosouzapw/OmniRoute/pull/10430)) — thanks @rqzbeh
-- **fix(usage):** surface Gemini `cachedContentTokenCount` into `cached_tokens` for non-streaming requests so cache-hit accounting matches the OpenAI/Claude/Responses branches and the streaming path (follow-up to the #10430 envelope fix) ([#10465](https://github.com/diegosouzapw/OmniRoute/pull/10465)) — thanks @rqzbeh
-- **fix(antigravity):** automatically rotate to a sibling account when one is BYOP (GCP Project ID required, `gcp_project_required` 422) — the account is excluded from selection for 24h and the request succeeds via another account instead of failing fast; the actionable 422 is surfaced only when no sibling exists (follow-up to the #10424 BYOP fast-fail) ([#10470](https://github.com/diegosouzapw/OmniRoute/pull/10470)) — thanks @rqzbeh
-- fix(mitm): forward passthrough traffic to the actual requested Host instead of misrouting every non-TARGET_HOSTS request to the hardcoded Antigravity sandbox host (#10479)
-- **fix(docker):** point the bifrost sidecar at the real `ghcr.io/maximhq/bifrost:v1.6.11` tag and the cliproxyapi sidecar at the official `docker.io/eceasy/cli-proxy-api:v6.9.7` image (the previously pinned tags never existed), and complete the runtime `OMNIROUTE_BASE_PATH` subpath patch for Next 16 standalone (assetPrefix + client env + baked asset URLs) so prebuilt images respect the webpath env var ([#10482](https://github.com/diegosouzapw/OmniRoute/pull/10482))
-- fix(sse): stop ZWJ-obfuscating the substring "hermes" in user messages and hostnames (#10484)
-- **fix(memory):** auto-check Qdrant health on mount and stop the false-red status badge on `/dashboard/memory?tab=engine` — the badge treated "not yet checked" (`health === null`) as a failure, so a healthy Qdrant showed red after every page refresh until "Test connection" was clicked; settings changes now also invalidate the stale result and re-check after the save persists, so a health check racing the settings PUT can no longer keep the badge red until a manual re-test ([#10489](https://github.com/diegosouzapw/OmniRoute/pull/10489))
-- **test(compression):** align source-contract tests with the merged `release/v3.8.50` base (`aa912c42a`) — accept the multi-line `providerTransport` shape in `omniglyph-chatcore-plumbing` and give the pipeline-circuit-breaker fixture a `metadata.executionStages` (both structural changes landed in the base merge) ([#10489](https://github.com/diegosouzapw/OmniRoute/pull/10489))
-- fix(cli): use 127.0.0.1 for the readiness health-check poll instead of localhost, avoiding Windows DNS-resolution delays that made a healthy server report as never-ready (#10508)
-- **fix(providers):** zed-hosted OAuth now redirects the browser back to the dashboard's own loopback port (auto-completing the login), and the manual paste path accepts Zed's user_id/access_token callback URL instead of erroring with "No authorization code found" ([#10517](https://github.com/diegosouzapw/OmniRoute/pull/10517)) - thanks @phatchau036
-- **fix(providers):** allow token-backed web sessions stored with `authType: "cookie"` to refresh their token through the provider update API ([#10518](https://github.com/diegosouzapw/OmniRoute/pull/10518)) — thanks @Zartharas
-- **fix(providers):** test token-backed web sessions through their provider validator instead of the OAuth path ([#10519](https://github.com/diegosouzapw/OmniRoute/pull/10519)) — thanks @Zartharas
-- **fix(compliance):** redact additional provider API keys from audit-log payloads ([#10521](https://github.com/diegosouzapw/OmniRoute/pull/10521)) — thanks @Zartharas
-- fix(providers): register a real Firefly auth probe under both the `firefly` alias and the `adobe-firefly` canonical id, and normalize the provider id before the generic web-cookie fallback, so a Firefly connection stops always reporting "Provider validation not supported" (#10522)
-- fix(services): isolate probeBeforeSpawn adoption tests on distinct ports to stop the order-dependent flake (#10523)
-- fix(sse): auto-replay a bounded multi-turn trajectory in the DeepSeek Web prompt builder for clients that never send `tools[]`, so agentic clients like Cline stop losing the original task after a couple of turns (#10527)
-- **fix(network):** direct (no-proxy) egress now bounds each attempt's response-start window (default 30s, `OMNIROUTE_DIRECT_HEADERS_TIMEOUT_MS`) and retries once on a fresh no-keep-alive socket, so a silently-dropped pooled keep-alive connection can no longer stall direct providers (opencode-go, command-code) until a service restart ([#10214](https://github.com/diegosouzapw/OmniRoute/issues/10214))
-- **fix(models):** align Codex GPT-5.6 context limits with the Codex catalog and honor model context overrides when advertising combos ([#10530](https://github.com/diegosouzapw/OmniRoute/issues/10530))
-- **fix(deps):** upgrade `@atjsh/llmlingua-2` from 2.0.3 to 2.0.5 and remove `@tensorflow/tfjs` from the LLMLingua SLM stack — 2.0.5 adds official Transformers.js v4 support (peers `@huggingface/transformers` at `^3.5.2 || ^4.0.0`) and 2.0.4+ no longer requires TensorFlow.js, restoring compatibility with OmniRoute's Transformers.js v4 while dropping the largest single contributor to the optional runtime footprint ([#10536](https://github.com/diegosouzapw/OmniRoute/issues/10536))
-- **fix(deepseek):** Advertise `none`, `low`, `high`, and `max` for V4 Pro and Flash, derive OpenCode Go effort aliases from base-model metadata, and route those models through native Responses ([#10540](https://github.com/diegosouzapw/OmniRoute/pull/10540)) — thanks @jackjinke
-- **fix(a2a):** use a constant-time bearer compare in `/api/a2a/tasks` via `crypto.timingSafeEqual`, matching the `tokensMatch` helper already used in `src/app/a2a/route.ts` and removing the last non-constant secret comparison in the repo ([#10544](https://github.com/diegosouzapw/OmniRoute/pull/10544))
-- Preserve portable plaintext reasoning by default across streaming and non-streaming Chat Completions and Responses routes while keeping provider-bound opaque state target-compatible. Direct requests drop incompatible continuation reasoning by default; combos can explicitly skip incompatible targets without mutating the request. Known providers no longer show redundant encrypted-reasoning controls. (#10550, #10959)
-- fix(dashboard): show the real model count on the "List Models" endpoint card instead of a permanent "—" (#10553)
-- **fix(cli):** ignore the operating system `HOSTNAME` when choosing the server bind address on Linux and macOS, preventing startup failures when the shell hostname differs from `os.hostname()`; use `OMNIROUTE_SERVER_HOST` for explicit non-Windows configuration while preserving the legacy `HOSTNAME` fallback on Windows ([#10557](https://github.com/diegosouzapw/OmniRoute/pull/10557), closes [#10492](https://github.com/diegosouzapw/OmniRoute/issues/10492)) — thanks @redzrush101
-- **fix(providers):** OpenCode `x-opencode-session` now derives a stable, conversation-scoped fingerprint via `generateSessionId()` instead of a fresh random UUID per request, so upstream prompt caching can hit across requests in the same conversation; bare `big-pickle`/`*-free` model ids now keep routing to an active opencode-family connection even when its synced catalog is temporarily stale; and bare requests to no-auth catalog providers (e.g. `opencode`) now echo the listing-valid `<alias>/<model>` form in `response.model` so clients validating against `/v1/models` don't warn ([#10571](https://github.com/diegosouzapw/OmniRoute/pull/10571))
-- **fix(mcp):** make GitHub skill tools discoverable through `omniroute_tool_search`
-- fix(providers): remove 10 retired model ids from the crof seed catalog so /v1/models stops advertising models crof.ai no longer serves (#10577)
-- **fix(audio):** when a prefix-matched STT provider has no credentials, retry gateways that list the same nested model id (e.g. `deepgram/nova-3` → `openrouter/deepgram/nova-3`) and mention those ids in the 400; stop documenting bare `deepgram/nova-3` as the default example ([#10583](https://github.com/diegosouzapw/OmniRoute/issues/10583))
-- fix(sse): resolve the short provider-alias prefix (e.g. `el/`) advertised by GET /v1/models for audio speech, transcription and translation model ids (#10586)
-- fix(sse): map OpenAI-compat voice names to real ElevenLabs voice_ids in direct TTS (#10589)
-- fix(dashboard): route the Playground's ChatTab "Send" through the endpoint actually selected in StudioConfigPane (`search`, `web.fetch`, etc.) instead of always POSTing to `/api/v1/chat/completions`, fixing the false "No active credentials for provider" 404 when testing search-only providers (#10592)
-- **fix(providers):** Magnific Mystic is now the canonical provider (`/dashboard/providers/magnific`, `magnific/<model>`). It uses the Magnific API (`api.magnific.com` + `x-magnific-api-key`), dashboard Test Connection validates keys without starting a paid generation, and the old `freepik` slug remains a legacy alias ([#10594](https://github.com/diegosouzapw/OmniRoute/pull/10594))
-- **fix(sse):** Include the redacted upstream error body in the per-target COMBO failure log (`Model X failed, trying next`) so operators can triage a 400/500 without reproducing the request ([#10597](https://github.com/diegosouzapw/OmniRoute/issues/10597))
-- **fix(xai):** trim Chat Completions `messages` and Responses `input` to xAI's 800-item history cap before dispatch, so long tool loops no longer die on `413 Chat history exceeds the 800-message limit` ([#10601](https://github.com/diegosouzapw/OmniRoute/pull/10601))
-- **fix(cli):** derive the machine-id token correctly under plain Node — `await import("node-machine-id")` puts the CJS exports on `.default`, so the destructured `machineIdSync` was `undefined` and the catch blanked the token, sending every management request unauthenticated; `OMNIROUTE_CLI_SALT` rotation is now honored too ([#10612](https://github.com/diegosouzapw/OmniRoute/pull/10612))
-- **fix(cli):** `omniroute setup --add-provider --api-key <key>` no longer aborts with "Provider API key is required" — Commander bound the value to the program-level `--api-key` (the OmniRoute server key), leaving the subcommand's own option undefined; `OMNIROUTE_API_KEY` now works as the error message advertised ([#10613](https://github.com/diegosouzapw/OmniRoute/pull/10613))
-- fix(dashboard): make /api/models agree with /v1/models on synced-catalog coverage instead of reporting stale models as available (#10615)
-- **Combo routing:** await each connection's token limit before reserving quota. The old lookup treated the `Promise` as a connection and dropped `rateLimitOverrides.tpm` ([#10686](https://github.com/diegosouzapw/OmniRoute/pull/10686)).
-- fix(guardrails): resolve the public provider alias before querying credentials in the Vision Bridge router, so command-code/opencode (and any alias!=id provider) are no longer reported as "unusable" despite active connections (#10702)
-- fix(dashboard): filter the Modality Bridge Vision model picker to vision-capable models, matching the sibling Video/Audio tabs (#10703)
-- fix(usage): repair provider-reported input_tokens: 0 on non-trivial requests instead of passing it through unrepaired (#10705)
-- fix(cli): distinguish a CLI-probe timeout from a genuinely absent binary in locateCommand, and resolve the Hermes Agent Apply flow's `keyId` server-side instead of writing the `YOUR_OMNIROUTE_API_KEY_HERE` placeholder (#10710, #10711)
-- fix(cli): pass --allow-scripts for the runtime's own npm-installed dependencies, so npm 12+'s default install-scripts block no longer silently skips better-sqlite3's native build (#10713)
-- fix(db): filter `getProviderMetrics()` to providers with a live `provider_connections` row so a deleted provider stops permanently ghost-haunting the Home "Provider Topology" widget (#10714)
-- fix(proxy): keep password-only proxy credentials instead of dropping them when no username is set (#10720)
-- **fix(executors):** the Meta AI (muse-spark-web) WebSocket send-message timeout now reports the socket's `readyState` at the moment it fires, so a "Meta AI WS timed out" failure can be told apart as either the connection never opening (`readyState=0`) or opening successfully and then going silent (`readyState=1`) — the exact ambiguity that made #10727 undiagnosable from logs alone (#10727).
-- **fix(providers):** copilot-m365-web chat turns no longer surface as `(empty response)` — the type:4 invocation is aligned with the 2026-08 wire shape and now carries its type:1 Metrics follow-up in the same socket write, and the access token pre-flight-refreshes from a stored refresh_token instead of requiring a DevTools re-capture every ~75 minutes ([#10732](https://github.com/diegosouzapw/OmniRoute/pull/10732) — thanks @acc0mplish)
-- **fix(catalog):** stop counting `getTokenLimit()`'s generic 128k catch-all as a known combo window, so `/v1/models` advertises the min of sourced member contexts instead of collapsing a 500k combo to 128k ([#10734](https://github.com/diegosouzapw/OmniRoute/issues/10734))
-- **fix(search):** name `/v1/search` 502s with provider id and sanitized Node cause code, without hostnames ([#10735](https://github.com/diegosouzapw/OmniRoute/issues/10735))
-- **fix(db):** pause call-log rotation and record SQLITE_CORRUPT on `/api/db/health` instead of retrying writes against a malformed pager ([#10736](https://github.com/diegosouzapw/OmniRoute/issues/10736))
-- fix(compression): skip the expensive `createCompressionStats()` pass in RTK when no message was actually compressed, matching every sibling stacked engine (#10765)
-- **fix(api):** `/api/cache/stats` reported the prompt-cache LRU, which no request path ever writes to — it answered `0 hit / 0 miss, size 0` while the semantic cache served real traffic, and the Health and Usage dashboards rendered that as fact. It now reports the semantic cache's in-memory entries, with the same response shape ([#PRNUM](https://github.com/diegosouzapw/OmniRoute/pull/10769)) — thanks @Poid-ZA, who first fixed this in #9446.
-- **fix(logging):** the app log is filterable and readable again. Entries from the tagged logger (`[LEVEL] [TAG] message`) were filed under the level instead of the component, and printf format strings were never applied, so `%s`/`%d` stayed literal with the values trailing behind them unlabelled — including every LiveWS connection line, where the format is deliberate hardening against injected format specifiers ([#PRNUM](https://github.com/diegosouzapw/OmniRoute/pull/10770)).
-- **fix(analytics):** Claude Code (`claude`/`cc`) is a flat-rate subscription, so cost analytics reports `$0` for it instead of estimating Anthropic list prices — the metered `anthropic` API keeps its real cost, and budget/quota/routing still estimate as before ([#10774](https://github.com/diegosouzapw/OmniRoute/pull/10774)) — thanks @electrumguy
-- fix(db): periodically run `wal_checkpoint(TRUNCATE)` so the SQLite WAL file shrinks on long-running servers (default 6h, override with `OMNIROUTE_WAL_TRUNCATE_INTERVAL_MS`, `0` disables) (#10781)
-- fix(sse): replace LiveWS's application-only liveness check with a protocol-level `ws.ping()`/`pong` heartbeat (RFC 6455 §5.5.2) alongside the existing one, so a read-only dashboard subscriber that never sends anything survives the connection timeout — a socket that stops reading frames entirely is still reaped exactly as before (#10782)
-- **fix(open-sse):** declare `supportedThinkingEfforts` (`low`/`medium`/`high`/`max`) on Ollama Cloud's `glm-5.1`, `glm-5.2`, `deepseek-v4-pro` and `deepseek-v4-flash` registry entries so the catalog's `appendSyncedEffortVariants()` pass — which only synthesizes selectable `-low`/`-high`/`-max` model ids from an already-populated `capabilities.effort_tiers` — can expose an effort selector for these reasoning-capable models, matching what `gpt-oss:20b`/`gpt-oss:120b` already had (#10788)
-- **fix(resilience):** scope the same-account transport retry (#9708) out of emergency-fallback and combo hops — it was retrying the free fallback model and combo targets too, doubling upstream calls and corrupting the terminal error status on those paths.
-- **fix(opencode-plugin):** respect log level in provider.models() catalog path so debug/info/warn messages are suppressed when `features.logLevel` is set to `"error"` ([#10798](https://github.com/diegosouzapw/OmniRoute/pull/10798)) — thanks @tientien17
-- **fix(providers):** Keep NVIDIA timeout probes and generic Antigravity/AGY HTTP 400 probes from poisoning credential health while preserving explicit Google geo-block handling ([#10799](https://github.com/diegosouzapw/OmniRoute/pull/10799)) — thanks @Zartharas
-- fix(db): disambiguate `createProviderConnection()`'s OAuth email dedup by `providerSpecificData.profileArn` in addition to `username`, so adding a second Kiro/AWS profile with the same email creates a new connection instead of silently merging into the first (#10815)
-- fix(oauth): stop treating the Kiro profile ARN as an account identity in `findKiroConnectionByIdentity()`, so a second Google/GitHub social login creates a new connection instead of overwriting the first — distinct Builder ID accounts share the same CodeWhisperer profile ARN, and the social token is not a JWT, so no e-mail was available to disambiguate them (#10815)
-- **fix(images):** register OpenAI `dall-e-3` in the image registry so unprefixed `dall-e-3` (and `openai/dall-e-3`) route to OpenAI Images instead of Microsoft Designer Web, and so the chat catalog no longer lists `openai/dall-e-3` as a 128k chat model ([#10832](https://github.com/diegosouzapw/OmniRoute/issues/10832))
-- **fix(security):** Outbound URL guard now resolves IPv4-mapped IPv6 literals to their embedded address, so `[::ffff:169.254.169.254]` is refused by the unconditional cloud-metadata block like its dotted spelling; `[::]` is refused alongside `0.0.0.0` ([#10843](https://github.com/diegosouzapw/OmniRoute/pull/10843)) — thanks @ntdat812
-- fix(config): exclude cookie-auth image bridges (chatgpt-web, gemini-web) from the unprefixed model scan so a bare id never silently binds to an unofficial web bridge (#10848)
-- fix(api): POST /v1/search now replies with a named `Unknown search provider: <id>` error (and field-named validation messages) instead of an opaque `Invalid request` for unrecognized or short-alias provider ids like `brave`/`serper` (#10849)
-- **fix(api):** alias `GET`/`HEAD` `/readyz` to `/healthz` so Kubernetes readiness probes do not 404 ([#10850](https://github.com/diegosouzapw/OmniRoute/issues/10850))
-- Document the conditional management authentication and 401/403 responses for `GET /api/openapi/spec`.
-- **fix(i18n):** The "Disabled" status no longer renders as the noun for a person with a disability in Japanese, Spanish, Hindi, Polish, Telugu, Urdu and both Chinese locales — 24 strings now use each catalog's existing wording (ja 無効, es Deshabilitado, hi अक्षम, pl Wyłączone, te నిలిపివేయబడింది, ur غیر فعال, zh-CN 已禁用, zh-TW 已停用) ([#10812](https://github.com/diegosouzapw/OmniRoute/issues/10812), [#10853](https://github.com/diegosouzapw/OmniRoute/pull/10853)) — thanks @ntdat812
-- **fix(skills):** Marketplace-installed skills are available to API-key-scoped requests, including existing SkillsMP and skills.sh installs ([#10854](https://github.com/diegosouzapw/OmniRoute/pull/10854)) — thanks @kriptoburak
-- **fix(catalog):** `/v1/models` no longer advertises the built-in `auto/*` ids while auto routing is disabled — they were listed but rejected at request time with `Auto routing is disabled` ([#10831](https://github.com/diegosouzapw/OmniRoute/issues/10831), [#10857](https://github.com/diegosouzapw/OmniRoute/pull/10857)) — thanks @ntdat812
-- **fix(context):** Base64 file payloads (OpenAI `file` parts, Responses `input_file`, Claude `document` blocks) are budgeted like the Gemini `inlineData` path instead of being counted as prompt text — a ~1MB PDF estimated at 350k tokens and was rejected on the context limit before reaching the provider's document pipeline ([#10840](https://github.com/diegosouzapw/OmniRoute/issues/10840), [#10858](https://github.com/diegosouzapw/OmniRoute/pull/10858)) — thanks @ntdat812
-- **fix(mcp):** MCP tool calls that wait on a model provider no longer abort after 10 seconds. `omniRouteFetch` applied a single hardcoded `AbortSignal.timeout(10000)` to every internal hop, and `omniroute_route_request` — which posts to `/v1/chat/completions` and waits on the upstream provider, plus auto-combo candidate probing before a provider is even chosen — passed no signal of its own, so it inherited it. Any route slower than 10s failed from the MCP side while the identical request succeeded through the REST API. `omniroute_web_search` and `omniroute_web_fetch` in the same file already carried an explicit 60s signal, so that value is now shared by all three provider-bound calls instead of being repeated as a literal, while management reads (health, resilience, rate limits, combos, quota, usage) keep their fast-fail 10s budget so a stalled local endpoint still cannot hold a tool call open. Both budgets are overridable through `OMNIROUTE_MCP_FETCH_TIMEOUT_MS` and `OMNIROUTE_MCP_UPSTREAM_TIMEOUT_MS`, replacing the reported workaround of patching the compiled `dist/.build/next/server/chunks/*.js`; a malformed or non-positive override falls back to the default rather than disabling the timeout
-- **fix(providers):** importing models with an expired API key now surfaces the credential error instead of reporting "No new models were added". The Import button posts to `/api/providers/{id}/sync-models`, which self-fetches the models route; that route does not fail on an upstream 401 but degrades to a catalog it already has, preferring the cache and using the local catalog only when there is no cache. A provider that imported successfully once therefore has a cache, so an expired key produced `{ source: "cache", warning: "Models probe failed (401) — using cached catalog" }` with HTTP 200 — and the #5460/#5465 degradation guard only recognised the `local_catalog` branch, so model-sync accepted it as a successful discovery, found every cached model already imported, and returned the empty-diff result. Retest does not go through this path, which is why it failed correctly and made the import look like a genuine "nothing to do". The existing rule — a degraded discovery must not be persisted as the synced catalog — is now applied to the branch it missed rather than special-casing 401/403, discriminating on the warning the fallback builder always attaches (an ordinary non-refresh cache hit attaches none, and model-sync always requests `refresh=true`). `isDegradedLocalCatalog` keeps its exact meaning and its existing tests
-- fix(api): reject a combo update that removes every model, and store the copilot's combo targets where the router reads them (#10866)
-- **fix(proxy):** proxy "Test connection" no longer reports an IPv4-only SOCKS5/SSH proxy as dead. #1255 moved every egress probe from `api.ipify.org` to `api64.ipify.org` so proxies with IPv6 egress could be tested, but `api64` is IPv6-first: a tunnel with no IPv6 route has nothing to connect to, so the probe hung until the caller's deadline and a proxy that was carrying live LLM traffic came back as a failure. Swapping the target to `api4` fixes that case and re-breaks the one #1255 fixed, so the probe now tries the targets in order instead — `api64` first, so a proxy with working IPv6 answers on the first attempt and keeps the exact behaviour #1255 introduced, including which of its addresses is reported (the egress IP is used as an identity to detect accounts of one rotation group sharing an address, so the attempts are sequential rather than raced). The attempts split the budget each call site already enforced, so no probe can take longer than it could before, and each attempt gets its own `AbortController` so exhausting the budget on an unreachable target does not abort the next one. `OMNIROUTE_PROXY_ECHO_URL` pins a single target — including a self-hosted echo — replacing the workaround of rewriting the compiled bundle after every upgrade. The relay branch of the test route still targets `api64` through `x-relay-target`, since that request egresses from the relay worker rather than the operator's tunnel
-- fix(cli): warn when a .env line never takes effect, and stop swallowing an unreadable .env (#10870)
-- **fix(db):** Remove stale MiMoCode provider configuration, including the legacy `mcode` alias, left after provider retirement while preserving historical usage and call logs ([#10873](https://github.com/diegosouzapw/OmniRoute/pull/10873)) — thanks @Zartharas
-- **fix(sse):** `getResetAwareProvider()` and the auto-combo quota lookup in `combo.ts` now canonicalize the provider id via `resolveProviderId()` before calling `getQuotaFetcher()`, so a fetcher registered under a provider's canonical id (e.g. `ollama-cloud`, `codex`) is found for combo targets stored under an alias spelling (e.g. `ollamacloud`, `cx`) instead of silently degrading reset-aware/reset-window/auto quota-aware routing to plain priority ordering (#10877)
-- **fix(provider-health):** Keep unsupported 404/405 validation probes neutral so they do not poison stored credential health or scheduler failure state, while still honoring per-connection health-check pacing ([#10878](https://github.com/diegosouzapw/OmniRoute/pull/10878)) — thanks @Zartharas
-- **fix(antigravity):** map Gemini 3.7 Flash tier ids (`gemini-3.7-flash-high/medium/low`, bare `gemini-3.7-flash`) to the upstream `gemini-3.7-flash-tiered` model id Google's Cloud Code endpoint expects, and configure per-tier thinking budgets ([#10882](https://github.com/diegosouzapw/OmniRoute/pull/10882)) — thanks @adevwithpurpose
-- **fix(memory):** enable agent memory save/update via MCP tools (`memory_save`/`update`/`search`/`delete` builtins with per-provider schemas, `apiKeyId` optional with caller-principal fallback) and gate server-side memory builtin injection to non-stream requests only ([#10887](https://github.com/diegosouzapw/OmniRoute/pull/10887)) — thanks @Egorich-print
-- **fix(perplexity-web):** make the built-in-search hint appended to every system message opt-in via `OMNIROUTE_PPLX_SEARCH_HINT` (off by default) — Perplexity's answer engine searches anyway, and the hint leaked into replies as meta-commentary for coding clients ([#10902](https://github.com/diegosouzapw/OmniRoute/pull/10902), extracted from [#8634](https://github.com/diegosouzapw/OmniRoute/pull/8634)) — thanks @danscMax
-- **fix(providers):** the loopback readiness gate no longer memorizes a failed probe — the next caller after 30s starts a fresh probe, and a readiness failure is logged once per probe instead of once per caller ([#10903](https://github.com/diegosouzapw/OmniRoute/pull/10903))
-- **fix(relay):** the Cloudflare proxy-relay worker now resolves `x-relay-path` through the shared `resolveRelayTarget()` guard instead of concatenating it onto the validated target. PR #4643 and its follow-up applied that guard to the Deno and Vercel workers; the Cloudflare generator, ported separately from upstream `decolua/9router` PR #1360, kept `fetch(targetBase + relayPath)`. Validating `x-relay-target` and then concatenating is not sufficient — the path re-points the request past the host that was just checked, through userinfo (`/x@evil.com`), a backslash (`\evil.com`), or a protocol-relative path (`//evil.com/x`). The guard is embedded verbatim under a literal `const resolveRelayTarget =` binding so the hardcoded call site still resolves when the SWC-minified standalone build mangles the source function's own name (#6149), and the new regression test pins that property for this worker by renaming the embedded function and re-evaluating the emitted source. The auth check and the private/loopback target guard are unchanged
-- **fix(build):** the `next` Docker image no longer crashes on boot with `ReferenceError: require is not defined in ES module scope`. The standalone `server.js` is CommonJS, but the `postbuild` colocate step was re-adding `"type":"module"` to the standalone root `package.json` (undoing `assembleStandalone`'s strip) to make its ESM worker bundles load. The `type:module` scope is now written per-worker-directory instead of on the root, so `server.js` stays CommonJS while the workers stay ESM ([#10936](https://github.com/diegosouzapw/OmniRoute/pull/10936), fixes [#10933](https://github.com/diegosouzapw/OmniRoute/issues/10933)) — thanks @arminanton
-- fix(cli): always emit limit.output in generated OpenCode config so schema validation passes for metadata-less models (#10940)
-- **fix(relay):** the private/loopback guard the three proxy-relay workers embed no longer misses four host spellings, and now lives in one place instead of three byte-identical inline copies. Driving `new URL(target).hostname` the way the workers do, the previous guard allowed `::` (the unspecified address, which reaches a service bound to the IPv6 loopback), `localhost.` (the FQDN root dot defeated the exact match and every `.localhost`/`.local`/`.internal` suffix rule, so `svc.internal.` slipped too), `::127.0.0.1` (the deprecated IPv4-compatible form — only `::ffff:` was checked), and `feb0::1` (link-local is `fe80::/10`, spanning `fe80`–`febf`, but only the literal `fe80:` spelling matched). The policy moved to `src/lib/proxyRelay/privateHostname.ts` and is embedded verbatim via `Function#toString` under a literal const name, the same mechanism `resolveRelayTarget` already uses for these workers, so a minified standalone build cannot break the call site (#6149). Nothing previously blocked is now allowed. Severity is low — reaching a worker needs the `x-relay-auth` secret and these are edge runtimes where loopback has nothing listening — but the suffix-rule bypass held regardless of runtime
-- **Account rotation:** make `fallbackStrategy: "least-used"` actually rotate. The strategy sorts on `lastUsedAt` but never wrote it — only the round-robin branch committed — so on a pool where every `last_used_at` was still `NULL` the tie-break fell through to `priority` and returned the same connection on every dispatch ([#10945](https://github.com/diegosouzapw/OmniRoute/issues/10945)).
-- **Desktop auto-update (Windows):** stop the in-app updater 404ing on every release. NSIS used electron-builder's default artifact name, whose spaces GitHub rewrites to `.` on upload while `latest.yml` keeps `-`, so the manifest pointed at `OmniRoute-Setup-X.Y.Z.exe` while the published asset was `OmniRoute.Setup.X.Y.Z.exe`. The name is now set explicitly to the dot form the asset already has, so nothing published changes name ([#10947](https://github.com/diegosouzapw/OmniRoute/issues/10947)).
-- Preserve explicit plaintext reasoning when a Responses reasoning item also carries opaque provider state (rare OpenCode Go `deepseek-v4-flash` responses). Mixed plaintext + opaque input is projected onto the target transport: plaintext targets keep portable text, opaque targets keep provider state. Opaque-only reasoning is dropped when the selected target cannot replay it, allowing cross-model conversations to continue. (#10949, #10959)
-- **fix(catalog):** preserve provider-declared reasoning effort tiers instead of replacing them with generic defaults ([#10953](https://github.com/diegosouzapw/OmniRoute/pull/10953)) — thanks @xz-dev
-- fix(cli): combo create accepts --models and no longer creates empty combos (#10954)
-- fix(cli): resolve $ref path params and add PATCH combos requestBody in generated API commands (#10955)
-- fix(sse): default single-target incompatible reasoning to drop for agentic replay — single-target requests to opaque reasoning targets now gracefully strip incompatible plaintext reasoning history instead of returning HTTP 400, matching combo default behavior while preserving operator and per-request overrides ([#10959](https://github.com/diegosouzapw/OmniRoute/issues/10959))
-- fix(sse): combo diagnostics no longer truncate `exhausted_connection` entries to a hardcoded `provider: "unknown"` with the provider prefix eaten by an 8-char slice — the real provider id is preserved and only the connection id is truncated (#10967)
-- fix(sse): combo terminal failures caused entirely by quota/account-balance exhaustion (including a durable HTTP 403 `insufficient_quota` / `AUTHZ_INSUFFICIENT_BALANCE`) now stamp a stable `quota_exhausted` diagnostics reason with a `switch-combo` recovery hint instead of the misleading default `retry` action (#10966)
-- **fix(search):** skip catalog-default SearXNG `http://localhost:8888/search` so Docker/K8s search does not ECONNREFUSED then 502 into the next provider ([#10976](https://github.com/diegosouzapw/OmniRoute/issues/10976))
-- fix(command-code): surface reasoning-only output as content when a model emits no text-delta (#10986)
-- **fix(ci):** clear inherited `release/v3.8.50` quality-gate reds on the X Search PR: drop the stale `copilot-m365-web.ts:330` public-creds allowlist, document six missing env vars, register four covering Stryker tap tests, prune leftover ESLint suppressions, replace the phantom `@/lib/db/connections` Utilization import with `getProviderConnectionById`, and fix open-sse/dashboard typecheck regressions in freebuff, browser-backed chat, auth, health matrix, and Monaco ([#10988](https://github.com/diegosouzapw/OmniRoute/pull/10988)).
-- **fix(ci):** clear remaining `release/v3.8.50` unit-shard reds on the X Search PR: pin `onnxruntime-node` to the transformers 1.24.3 copy, rebaseline OpenAPI coverage, sync goldens/i18n, honor eye-hidden no-auth models across provider aliases, await rejected-request call-log writes, absorb catalog event-loop shard contention in #9147, and align inherited tests with advisory context estimates, #10501 combo terminal-status aggregation, and current catalog/auth behavior ([#10988](https://github.com/diegosouzapw/OmniRoute/pull/10988)).
-- **Static model catalog for v0-vercel-web:** seed a static catalog for the v0-vercel-web web-cookie provider (v0-1.0-md, v0-1.5-lg, v0-1.5-md) so its dashboard "Available Models" / "Import from /models" UI serves a usable list instead of falling through to the route's 400 "does not support models listing" ([#10990](https://github.com/diegosouzapw/OmniRoute/issues/10990)).
-- fix(providers): mark the blackbox provider deprecated — api.blackbox.ai returns HTTP 404 on every path variant (sweep 2026-08-21), so the public inference surface is dead and the catalog entry now carries a deprecation notice. ([#10997](https://github.com/diegosouzapw/OmniRoute/issues/10997))
-- fix(providers): validate Dify keys against its native /v1/chat-messages endpoint (#11002)
-- **fix(accounts):** `markCooldown` now carries the failure origin (`transient` vs `terminal`) — transient 429/network only cools down, repeated terminal failures evict and are skipped by `pickAccount` until a success or operator clear ([#11008](https://github.com/diegosouzapw/OmniRoute/pull/11008)) — thanks @maxmad64bis
-- **fix(providers):** route terminal `testStatus` writes (`banned`, `deactivated`, `credits_exhausted`) through a single origin-aware passage — probe failures are recorded but never deactivate the connection ([#11009](https://github.com/diegosouzapw/OmniRoute/pull/11009)) — thanks @maxmad64bis
-- **fix(codex):** drop non-standard `codex.*` SSE events by default so OpenAI SDK / Codex CLI `/v1/responses` clients are not 502'd by `event: codex.rate_limits` ([#11014](https://github.com/diegosouzapw/OmniRoute/issues/11014)) — thanks @RaviTharuma
-- **fix(resilience):** count heavyweight `/v1` admission leases in the SIGTERM drain and send `Retry-After` on shutdown 503s so Recreate no longer looks like an empty 502 ([#11015](https://github.com/diegosouzapw/OmniRoute/issues/11015)) — thanks @RaviTharuma
-- **fix(startup):** log `Credential health scheduler disabled` when `OMNIROUTE_DISABLE_CREDENTIAL_HEALTH_CHECK` is set instead of lying with `started` ([#11016](https://github.com/diegosouzapw/OmniRoute/issues/11016)) — thanks @RaviTharuma
-- **docs(api-keys):** document that unset `DEFAULT_RATE_LIMIT_PER_DAY` is unlimited (#2289), not a hidden 1000/day cap ([#11017](https://github.com/diegosouzapw/OmniRoute/issues/11017)) — thanks @RaviTharuma
-- **fix(webhooks):** remove 3 declared-but-never-emitted events (`provider.error`, `provider.recovered`, `combo.switched`) from `WebhookEvent` — catalog now `request.completed | request.failed | quota.exceeded | test.ping`; `POST /api/webhooks` and `PUT /api/webhooks/[id]` reject ghost values with 400; OpenAPI webhook description updated across 43 locales ([11050](https://github.com/diegosouzapw/OmniRoute/pull/11050))
-- fix(providers): filter Perplexity model import to the Sonar family so Agent-API catalog ids stop surfacing as routable chat models (#11060)
-- **fix(claude):** restore canonical tool names (`bash` → `Bash`, `croncreate` → `CronCreate`) on non-streaming OpenAI→Claude conversion and through identity-echo alias maps, so Claude Code stops rejecting tool calls with "No such tool available" ([#11085](https://github.com/diegosouzapw/OmniRoute/pull/11085)) — thanks @linhdmn
-- **fix(resilience):** filter chat connection selection by each connection's *synced* model inventory on multi-host self-hosted providers (`ollama-local`, `lm-studio`, `vllm`, …), so a request for a model only one host advertises is pinned to that host instead of failing over onto a host that never had it ([#11089](https://github.com/diegosouzapw/OmniRoute/issues/11089))
-- fix(install): make the ONNX dependency chain optional so Termux/Android installs succeed again (#11095)
-- **fix(providers):** Reject silent validation degradation on provider connection patch — unknown `rateLimitOverrides` keys (e.g. a typo'd `tpm`) and empty/non-numeric values now return `400` with the rejected key list instead of being silently dropped ([#11101](https://github.com/diegosouzapw/OmniRoute/pull/11101))
-- **Autopilot suggestion counter:** the combo health autopilot summary now reports `suggestionCount` (the real number of suggested actions across all issues) instead of conflating it with link counts, while keeping `actionableCount` as a deprecated alias for backward compatibility. The `run_combo_test` action now links to the dashboard with the combo id (`/dashboard/combos?test=<comboId>`) rather than the read-only API route, so operators can actually trigger a test from the UI ([#11102](https://github.com/diegosouzapw/OmniRoute/pull/11102)).
-- **Config audit persistence:** persist the configuration audit trail to SQLite (`config_audit_log`) instead of an in-memory buffer capped at 1000 volatile entries, and bound its growth with `cleanupConfigAudit()` driven by the `retention.configAudit` setting (default 30 days), wired into `runAutoCleanup` ([#11103](https://github.com/diegosouzapw/OmniRoute/pull/11103)).
-- fix(sse): resume mid-stream recovery after a _completed_ tool call — `finish_reason: "tool_calls"` is now tracked per-call instead of as a general terminal marker, so truncation of trailing prose after a fully-delivered tool call is recoverable while in-flight calls stay blocked ([#11109](https://github.com/diegosouzapw/OmniRoute/pull/11109))
-- **fix(providers):** `reasoning_effort` now learns the accepted values from a provider's own 400/422 response and clamps to the highest one instead of forwarding an unsupported `xhigh`/`max` (or a hardcoded `"high"` fallback) — fixes custom OpenAI-compatible connections and registered providers with no reasoning metadata ([#11116](https://github.com/diegosouzapw/OmniRoute/pull/11116)) — thanks @maxmad64bis
-- **fix(sse):** parallel `function_call` items in a Responses API stream (e.g. several tool calls dispatched in the same turn) now each get a stable, distinct `index`/`id` when translated to Chat Completions streaming deltas, instead of colliding on index 0 and tripping strict stream parsers with `Expected 'id' to be a string.` ([#11144](https://github.com/diegosouzapw/OmniRoute/pull/11144))
-- **fix(analytics):** `opencode-go` is now classified as a flat-rate subscription, so cost analytics shows $0 for it instead of billing every call at the underlying model’s metered rate — it resells GLM, Kimi, Grok, DeepSeek, MiniMax, Qwen and GPT-5.x under one flat monthly fee, which made the overstatement large rather than marginal ([#11149](https://github.com/diegosouzapw/OmniRoute/pull/11149)) — thanks @electrumguy
-- fix(dashboard): keep `open-sse/config/providerRegistry.ts` free of `node:net` so the provider detail client bundle builds again — the host classification moved to a platform-free `src/shared/network/privateHost.ts` with a pure-JS `isIP` equivalent, leaving the #11122 routing behaviour unchanged (#11154)
-- **Combo create:** creating a routing combo without any model is now refused (`400`) — the CLI requires `--models`/`--model` on `combo create`, matching the dashboard which already rejected empty combos.
-- **fix(resilience):** a missing-model `404` on a provider that declares `passthroughModels: true` in the shared registry (novita, uncloseai, orcarouter and 37 others) now locks out only that model instead of cooling the entire connection — `hasPerModelQuota()` previously read only the open-sse registry and the local/self-hosted families ([#11165](https://github.com/diegosouzapw/OmniRoute/pull/11165)) — thanks @yourspraveen
-- **fix(routing):** a custom `openai-compatible-*` / `anthropic-compatible-*` connection pointing at a keyless self-hosted backend (llama.cpp, Ollama, vLLM started without an API key) now stays in the `auto/*` candidate pool instead of being silently dropped by the credential gate — for those IDs "no credential" is the normal configuration, not an unconfigured connection ([#11180](https://github.com/diegosouzapw/OmniRoute/pull/11180)) — thanks @marcs7
-- **fix(routing):** the Routing tab's "last known good provider" toggle now actually takes effect — `lkgpEnabled` was persisted and the `lkgp` strategy guarded on it, but the setting was never forwarded into the `RoutingContext` built in `resolveAutoStrategyOrder()`, so `context.lkgpEnabled` was always `undefined` and the off-switch was unreachable ([#11181](https://github.com/diegosouzapw/OmniRoute/issues/11181))
-- **fix(ollama):** Ollama Local models are no longer flattened to `chat` at sync time — the synced store persists every advertised capability and chat filtering moves to read time, so `/v1/embeddings` and `/v1/images/generations` stop rejecting models the daemon reports as capable ([#11271](https://github.com/diegosouzapw/OmniRoute/pull/11271)) — thanks @yourspraveen
-- **fix(providers):** Antigravity OAuth marks connects with no Cloud Code projectId as degraded instead of a false "Connected"; BYOP detection at connect time, auto-disable of confirmed-missing accounts, and selection-side rotation ([#11284](https://github.com/diegosouzapw/OmniRoute/issues/11284))
-- **fix(translator):** preserve omitted OpenCode `subagent.sessionID` values — optional default-less plain strings now use the Responses `null = omit` sentinel and are stripped before the client sees the tool call, so Codex/Responses no longer invent filler session IDs ([#11297](https://github.com/diegosouzapw/OmniRoute/pull/11297)) — thanks @ofonseca-pyming
-- **fix(db):** group model patterns escape regex metacharacters, so `gpt-4.1*` no longer matches `gpt-4o1-preview` and a pattern like `gpt-4(*` no longer throws `SyntaxError` out of the completion and `/v1/models` paths ([#11311](https://github.com/diegosouzapw/OmniRoute/pull/11311))
-- **fix(db):** the upstream proxy URL check judges the host by address instead of by spelling, so `http://[::ffff:169.254.169.254]`, `[::ffff:10.0.0.5]`, ULA/link-local and CGNAT targets are refused like their dotted equivalents ([#11319](https://github.com/diegosouzapw/OmniRoute/pull/11319))
-- **fix(i18n):** three `pt` strings had dropped their placeholders — the cache tile's subtitle repeated its own label instead of showing `{total}` — and a unit test now enforces placeholder parity with `en` across all locales ([#11325](https://github.com/diegosouzapw/OmniRoute/pull/11325))
-- **fix(kie):** map the remaining `google-imagen/*` KIE Market catalog ids (`nano-banana`, `nano-banana-pro`, `nano-banana-edit`) to their real, KIE-documented upstream `model` values — `#11225`'s fix only covered `nano-banana-2` ([#11326](https://github.com/diegosouzapw/OmniRoute/pull/11326)).
-- **fix(security):** `proxy-authorization` and `proxy-authenticate` are refused as upstream/custom headers, so a proxy credential is no longer forwarded to the model provider — the canonical denylist now matches the RFC 7230 §6.1 set the rest of the codebase already strips ([#11328](https://github.com/diegosouzapw/OmniRoute/pull/11328))
-- **fix(video-bridge):** fall back to the deterministic active-window midpoint when a one-frame scene-aware budget cannot preserve both timeline ends; a real FFmpeg fixture matrix now covers rapid cuts, gradual changes, static and short clips, and detector failure ([#11344](https://github.com/diegosouzapw/OmniRoute/pull/11344)).
-- **fix(translator):** Codex Responses tool calls translated for Claude clients no longer emit a duplicate `tool_use` block with the same ID and an empty name, preventing Claude Code from terminating with `No such tool available` ([#11347](https://github.com/diegosouzapw/OmniRoute/pull/11347))
-- **fix(video-bridge):** burn high-contrast timestamps into every bounded contact-sheet cell and add a real-model A/B harness whose promotion verdict stays `HOLD` until token, latency, and quality evidence is actually executed ([#11350](https://github.com/diegosouzapw/OmniRoute/pull/11350))
-- **fix(video):** fingerprint protected Video Bridge bytes, coalesce concurrent work, and fail open when the bounded TTL/LRU result cache is unavailable or corrupt ([#11362](https://github.com/diegosouzapw/OmniRoute/pull/11362))
-- **fix(catalog):** keep large `/v1/models` builds responsive by reusing the build-local capability snapshot throughout enrichment and Auto-Combo preparation, yielding cooperatively while constructing virtual candidate pools, and avoiding unrelated synchronous database diagnostics on the cache-TTL read path ([#11367](https://github.com/diegosouzapw/OmniRoute/pull/11367))
-- **fix(video):** apply the caption-frame cap after bounded visual deduplication, preserve first/final candidates plus small high-contrast motion and text changes, and version the dedup policy in result-cache identity ([#11382](https://github.com/diegosouzapw/OmniRoute/pull/11382)).
-- **Live dashboard:** honour the WebSocket port reported by `/api/v1/ws?handshake=1` instead of the port compiled into the bundle, so a `LIVE_WS_PORT` override reaches prebuilt Docker/npm images and Combo Studio Live connects behind a reverse proxy ([#11331](https://github.com/diegosouzapw/OmniRoute/issues/11331)).
-- **fix(dashboard):** Model Database sync interval slider ticks now match the thumb position — checkpoint-space slider with magnetic snap on release ([#11394](https://github.com/diegosouzapw/OmniRoute/pull/11394)) — thanks @An0nym0us92
-- **fix(api-manager):** Allowed Combos can now be restricted to zero entries: **All** is stored explicitly as `combo/*`, while **Restrict** with no selection saves an empty allowlist that denies Combo routes without blocking direct models. Existing keys are migrated to preserve their previous allow-all behavior.
-- fix(build): tolerate a same-realpath symlink or stale-typed dest in the standalone bundle assembler, fixing non-deterministic `ERR_FS_CP_EINVAL`/`ERR_FS_CP_DIR_TO_NON_DIR` crashes under heavy concurrent build I/O
-- **fix(auto):** rate-limit `auto/<family> matched no connected models` warnings to once per minute per label (`open-sse/services/autoCombo/virtualFactory.ts`)
-- fix(cli): drop the orphaned `resolveOpencodeConfigDir` re-export from `cliRuntime` — it lost its last consumer in #10246 and diverged from the canonical resolver by one directory level (#9985)
-- fix(ci): make `Build (advisory)` produce a signal again — pinned to a hosted runner with the swap/heap provisioning `Fast Production Build` proves sufficient, and scoped to fork PRs, which are the only ones `build.yml` cannot cover (72 of the last 100 PRs into `release/**`)
-- **fix(api):** hash API keys in the `/v1/models` catalog cache Map key so heap dumps cannot leak bearer tokens (`src/app/api/v1/models/catalogCache.ts`)
-- **fix(providers):** register live OpenRouter Gemini Embedding 2 ids (`google/gemini-embedding-2` and `google/gemini-embedding-2-preview`, 3072-d) in the curated embeddings catalog so `GET /v1/models` and `GET /v1/embeddings` list the ids that already serve — thanks @RaviTharuma
-- **fix(translator):** merge consecutive same-role contents in direct Claude to Gemini request translation to prevent upstream HTTP 400 errors
-- **fix(cli):** `omniroute update` now finds npm on Windows. It called `execFile("npm", …)` with no shell, and on Node ≥ 24 a `.cmd` wrapper cannot be spawned that way (nodejs/node#52554) — while a bare `npm` can also resolve to an extensionless shim `CreateProcess` refuses. The result was `✖ Could not check latest version. Is npm available?` in a terminal where `npm view omniroute version` worked fine, so the updater was unusable on Windows even though nothing was wrong with the install. This is the same class as #5379/#5542, which fixed the server-side calls; the CLI entry points were missed because they are plain `.mjs` and cannot import the TypeScript helper. `bin/cli/npm-exec.mjs` now states the same rule for them: `npm.cmd` plus a shell on win32, no shell anywhere else. Both npm lookups in `update.mjs` (version and changelog) pass a literal argv array, so enabling the shell cannot splice a runtime value into the command line — a test asserts that and fails if a future edit interpolates one. (#11335)
-- **fix(cline):** Preserve client-supplied Cline task IDs and omit the header when clients provide none, preventing request-scoped proxy IDs from being reported as tasks.
-- Hardened the Codex app-server transport after the post-merge security review of #11205: approval prompts from the app-server (its own command/file/permission execution — not the harness tool passthrough) are now auto-denied by default, with opt-in auto-approval via `providerSpecificData.codexAppServerAutoApprove` / `OMNIROUTE_CODEX_APPSERVER_AUTO_APPROVE`; the default codex sandbox changed from `danger-full-access` to `workspace-write` (override per connection or env); env-sourced capability tokens are now only sent to env-sourced URLs or operator-local hosts (loopback/RFC1918/link-local/ULA/localhost/single-label LAN names/*.local/*.ts.net/*.internal), so a connection's providerSpecificData URL can no longer exfiltrate the operator's env token; and the `/readyz` health probe no longer follows redirects while carrying the bearer token.
-- fix(codex): prefer `max_context_window` over the `context_window` pricing tier as the usable input limit in discovery, and raise the static Codex OAuth catalog to the same usable window so the conservative discovery merge no longer caps live values at the 272K pricing tier
-- **fix(catalog):** derive combo reasoning-effort tiers from the exact runtime-selectable connection scope, intersecting dynamic, pinned, allowlisted, and compatible provider-node evidence while failing closed on unknown capabilities.
-- fix(combo): evict in-memory session-stickiness bindings when a combo disables stickiness, so stale pins stop overriding the declared priority order until TTL/restart
-- fix(combo): resolve effort-suffixed command-code variants (e.g. `deepseek-v4-flash-max`) to their base model for capability lookups, so tool-bearing combo requests keep the declared priority order instead of reordering behind models with confirmed capabilities
-- **fix(db):** the `compression_run_telemetry` retention sweep now actually deletes expired rows. Its cutoff was computed in epoch seconds while the column stores epoch milliseconds, so `WHERE timestamp < cutoff` never matched and the table added by #6848 to bound `storage.sqlite` growth was unbounded in practice. Same unit mismatch as #9625, which corrected the sibling `domain_cost_history` sweep and missed this call site
-- **fix(compression):** use `pathToFileURL` in `compressionWorkerPool` so bundlers (Webpack / Turbopack) do not attempt static asset resolution of missing `compressionWorker.js` during build
-- **fix(db):** database settings API no longer returns HTTP 500 on SQLite builds compiled without the optional `dbstat` virtual table (sql.js/WASM); per-table sizes degrade to 0 instead of failing the whole stats call
-- fix(discovery): parse upstream reasoning tiers nested under metadata.reasoning.supported_efforts (neuralwatt /v1/models shape) so synced openai-compatible models advertise effort aliases
-- **fix(ops):** Docker HEALTHCHECK probes lightweight `/healthz` instead of `/api/monitoring/health` so a busy event loop does not mark the container Unhealthy (`scripts/dev/healthcheck.mjs`)
-- **fix(api):** `/v1/embeddings` 400s for native `gemini-embedding-2` now name the working OpenRouter ids (`openrouter/google/gemini-embedding-2` and the preview alias) instead of only `No credentials for embedding provider: gemini` — thanks @RaviTharuma
-- **fix(sse):** keep Codex/Anthropic quota headers under the upstream forwarding budget; drop `x-codex-turn-state` and raise the 768-byte cap (`open-sse/handlers/chatCore/responseHeaders.ts`)
-- **fix(usage):** z.ai/GLM coding-plan subscription keys now render their quota cards again, with absolute credits. Z.ai's `/api/monitor/usage/quota/limit` switched these keys from `TOKENS_LIMIT` to `CREDIT_LIMIT` rows (same `unit`/`number` semantics: unit=3/number=5 → 5-hour window, unit=6/number=1 → weekly), and the parser only matched `TOKENS_LIMIT`/`TIME_LIMIT`, so both rows were dropped and the subscription card rendered empty. `CREDIT_LIMIT` is now accepted alongside `TOKENS_LIMIT`, and when the row carries absolute credit fields (`usage`/`currentValue`/`remaining`) they are preferred over the percent-only scale, so the card shows `3341 / 28000` like z.ai's own dashboard instead of `11 / 100`
-- **fix(auth):** a connection's `lastError` now names the real upstream failure instead of the bare string `Provider error`. `markAccountUnavailable` kept the reason only when it was already a string, so every other shape collapsed to that literal — and the shape that matters most is not a string: a failed `fetch` arrives as `TypeError: fetch failed` with the actionable part on `error.cause.code`, which means a wrong port, a firewall, a DNS failure and a blocked proxy all looked identical in the dashboard and in the console line. `describeUpstreamFailure` (in `src/shared/utils/upstreamError.ts`, reusing the `extractErrorMessage` that already parsed provider bodies) reads Error messages and appends the transport code when the message does not already carry it, reads the usual provider JSON shapes (`error.message`, `message`, string `error`, `detail`, `errors[]`), and falls back to the code alone before giving up. It never serializes the error object wholesale, so a request body or header attached to an error cannot leak into the stored reason — pinned by a test.
-- **fix(live-ws):** the Live dashboard socket can now be pointed at a reverse proxy without rebuilding the image. `NEXT_PUBLIC_*` is inlined at BUILD time, so a prebuilt Docker or npm image never carries an operator's `NEXT_PUBLIC_LIVE_WS_PUBLIC_URL` — which is exactly why the browser discovers the socket through `/api/v1/ws?handshake=1` instead. The server side of that handshake, however, read only the `NEXT_PUBLIC_`-prefixed name, so it had nothing to echo: behind Traefik the dashboard kept dialling `wss://<host>:20132/live-ws` and sat on "Live disabled — WebSocket disconnected. Showing last known state." `LIVE_WS_PUBLIC_URL` is now read at runtime alongside the existing `LIVE_WS_HOST` / `LIVE_WS_PORT`, and the prefixed name stays supported as the fallback, so deployments that already set it are unaffected. Only `ws://` and `wss://` values are accepted, matching the guard the client already applies. (#11331)
-- **fix(sse):** MiniMax music models now generate audio instead of failing with `Unsupported music format: minimax-music` — the provider entry was registered in the music registry (and advertised by `/v1/models`), but `handleMusicGeneration` had no branch for its format, so every `minimax/*` music request fell through the dispatch chain to a 400. Adds the missing dispatch: a single synchronous POST with the `base_resp` envelope check (a non-zero `status_code` arrives on HTTP 200 too), `data.status` handling (an unfinished generation is reported instead of polled — the operation has no task id and no query endpoint), `url` and `hex` output formats (hex normalized to base64), `mp3`/`wav`/`pcm` containers via `audio_setting`, and the regional endpoint through the per-connection base-URL override, which is also the only host that accepts `aigc_watermark`. The registry entry gains the generation and cover model ids it was missing and drops a query URL that does not exist for this operation. Regression guard: `tests/unit/minimax-music-generation.test.ts` (9 tests).
-- **fix(models):** honor `MODELS_DEV_SYNC_ENABLED=0` as a hard kill switch over the dashboard setting so a wedged `/healthz` / UI can be recovered without HTTP (`src/lib/modelsDevSync.ts`)
-- **fix(providers):** when `OPENCODE_SYNTHESIZE_CLI_HEADERS=true`, a non-CLI client User-Agent (e.g. `curl/8.5.0`, SDKs) on opencode-go/opencode-zen/opencode-free requests is now REPLACED with the synthesized `opencode-cli/1.0.0` instead of being honored — opencode.ai's free tier (`/zen/v1`) returns `FreeUsageLimitError` 429 for generic client UAs egressing from datacenter IPs, which made the #5997 CLI-identity synthesis ineffective for non-CLI clients. Client UAs already matching `opencode-cli/…` are preserved (the real CLI's versioned identity stays intact); all other client-supplied `x-opencode-*` headers keep client-wins. Regression guard: `tests/unit/opencode-cli-headers-synthesis-5997.test.ts` (7, incl. non-CLI UA replaced + CLI UA preserved). (#5997 follow-up)
-- **OpenCode config merge:** stop `mergeOpenCodeConfig` splaying a malformed `provider` block into index keys. The root was already guarded against a non-object; the `provider` branch it spreads one level down was not, so an existing `"provider": ["a", "b"]` merged to `{"0": "a", "1": "b", …}`. Its sibling `mergeOpenCodeConfigText` already refuses the same input.
-- **fix(models):** a model synced from a provider's own `/models` discovery is now enforced at its real context window immediately, instead of waiting up to 24h for the Feature 5004 reconciler's next tick. The request-time token-limit chain resolves the window from `auto:discovery` overrides, which previously were only written at startup and on a 24h interval — so any model synced mid-cycle (models.dev not indexing it yet, no static registry entry) fell through to the provider's static `defaultContextLength` (128K for OpenRouter) while `/v1/models` simultaneously advertised the real window from the same discovery data. Measured: `openrouter/stealth/ox-alpha` advertised `context_length: 1048576` but rejected requests over 128K with `context_length_exceeded` for a full day after its sync. The reconcile now also runs opportunistically (debounced, fire-and-forget) right after a synced catalog write changes. Companion fix: discovery now captures the vendor-declared `reasoning.default_effort` (e.g. OpenRouter `stealth/ox-alpha` declares `max`, normalized to `xhigh`) as `defaultThinkingEffort`, and the OpenAI dispatch path injects it when a request carries no reasoning field of any shape — the lowest-priority default behind a `-{effort}` suffix alias and a static `ModelSpec.defaultReasoningEffort` — so a reasoning model that returns an empty response without an explicit effort gets the vendor default instead of `upstream_empty_response`.
-- **fix(providers):** Claude Code / CC-protocol-compatible clients sending `cache_control` with no `ttl` on the native Claude OAuth path (`claude`/`cc`) now default to the 1h extended cache TTL instead of silently falling back to Anthropic's 5-minute default, even though the 1h beta is always negotiated on this path — thanks @jeff-alves
-- **fix(electron):** desktop window stays hidden on Windows because the embedded Next.js server binds to the machine hostname instead of loopback ([#PENDING](https://github.com/diegosouzapw/OmniRoute/pull/PENDING))
-- **fix(executors):** OpencodeExecutor rotates (or retries once on a single-account direct path) on upstream 400 empty-body rejections — malformed completion envelopes with no error field were propagated as success and killed client sessions. Bounded +1 attempt per request; body reads are conditioned on status 400 so successful/streaming responses are never buffered. 400s carrying an error field keep propagating immediately.
-- **fix(cli):** recognize native `opencode.jsonc` files in OpenCode detection, generated-provider setup, and dashboard save/apply flows; preserve unrelated JSONC comments and provider settings, write updates back to the selected file, and refuse to overwrite invalid config ([#10227](https://github.com/diegosouzapw/OmniRoute/issues/10227)) — thanks @tito13kfm
-- fix(i18n): complete Vietnamese translations for recently added UI strings (#9985)
-- fix(api): repair broken `@/lib/db/connections` import in the usage utilization route that failed the production build (#10939 follow-up)
-- chore(docs): regenerate PROVIDER_REFERENCE and refresh README diagram SVGs to the real provider count (347)
-- chore(lint): prune ESLint suppressions orphaned on the release branch
-- **fix(build):** repair the broken Turbopack production build, the red lint gate and a runtime crash on `release/v3.8.50`. Six independent module-level defects, each from a different PR, had accumulated because the `Build` CI job is advisory rather than blocking: a lost closing brace in `modelSelectModalHelpers.ts` that swallowed `PROVIDER_TEST_CHUNK_SIZE` into a function body (#9011); `handleFalVideoGeneration` imported twice in `videoGeneration.ts` after the provider-neutral Fal module superseded the standalone handler (#9982 over #9969); `catalog.ts` still re-exporting and calling the injectable stale-while-revalidate policy that #9199 deliberately replaced with a fixed 30 s bound when it landed on top of #8728 — the consumer and the #8728 test suite were never realigned; two dangling statements left in `catalogCache.ts::scheduleBackgroundRefresh` referencing undeclared `inFlight`/`promise`, which made **every** stale-while-revalidate read throw a `ReferenceError` at runtime (a defect the build never caught, surfaced here by the realigned test); a generated wasm-bindgen sidecar URL in `tinycmsSigner.ts` that Turbopack resolves at build time even though the WASM module ships inlined as base64 (#8736/#10087); `conolDiscovery.ts` importing `getProviderOutboundGuard` from `outboundUrlGuard` instead of the sibling `outboundUrlGuardPolicy` module that actually exports it (#8974) — fixed on the consumer side, since re-exporting it would put a `@/`-aliased import into the module the packaged CLI loads without a tsconfig (#7682); and an unbalanced brace in `tests/unit/db-adapters/driverFactory.test.ts` where a new case was inserted between the preceding test's `finally` block and its `});`, so the whole file stopped parsing and the SQLite driver-cascade coverage silently stopped running since 2026-08-11 (#9173).
-- **fix(security):** harden three secret-leak paths surfaced by an audit of the error/log surface. (1) `upstreamErrorPassthrough` relays an upstream provider's 4xx body verbatim to Claude-Code-format clients (the capability-recovery contract needs the exact wording); it now refuses passthrough when the body actually carries a credential pattern (`Bearer`/`Basic` token, `sk-…`, or an `api_key`/`token`/`authorization`/`cookie`/`secret` assignment) so a provider that echoes the offending request can't relay a key to the client, falling back to the sanitized error path. The credential regex is bounded (ReDoS-safe, verified linear at 60k chars). (2) The OCR and moderations handlers no longer forward an upstream error body byte-for-byte; they run it through the (now exported) structure-preserving `redactSensitiveErrorText` first. (3) `protectPayloadForLog`'s sensitive-key set gains `cookie`/`storageState`/`runtimeKey`/`capability` so web-impersonation credentials (Meta AI `ecto_1_sess`, chatgpt-web `storageState`) that land in a request/response body field are redacted before the call-log artifact is written to disk. No behavior change for secret-free error bodies; the Claude Code verbatim-wording contract is preserved.
-- **fix(db):** the sql.js fallback now publishes the database atomically — temp file in the same directory, `fsync`, then `rename()` — instead of rewriting it in place with `writeFileSync`. sql.js has no incremental write path, so every save rewrote the whole image through an `O_TRUNC` open: for the duration of the write the on-disk database was 0 bytes and then partial, a window that scales with database size and recurs on every save. Unlike better-sqlite3 / node:sqlite, that window is not covered by SQLite's locking protocol, so it was visible to every OTHER process reading the same file (a backup job, a metrics exporter, an operator running `sqlite3`), which got `SQLITE_CORRUPT` — "database disk image is malformed" — while `PRAGMA integrity_check` passed moments later. It also closes a total-loss window: a crash mid-write used to leave the real database truncated, and now only leaves a stale temp file
-
-<!-- reconciliation pass 2 (Phase 0a.1): commits that landed in the cycle without a bullet -->
-
-- **fix(sse):** streaming-integrity cluster — a split `<think` open tag can no longer leak into content ([#10441](https://github.com/diegosouzapw/OmniRoute/issues/10441) — thanks @geek007git); a low-overlap stream-recovery continuation is rejected instead of being concatenated raw ([#11152](https://github.com/diegosouzapw/OmniRoute/issues/11152)) and recovery resumes after a clean stop that produced only reasoning ([#11151](https://github.com/diegosouzapw/OmniRoute/issues/11151)) — thanks @maxmad64bis; OpenAI streams that close with content but no terminal marker are flagged ([#10475](https://github.com/diegosouzapw/OmniRoute/issues/10475) — thanks @HouMinXi); a bare upstream close is surfaced to Responses clients as `response.failed` ([#10980](https://github.com/diegosouzapw/OmniRoute/issues/10980) — thanks @linhdmn); and a graceful silent-close no longer reads as a truncation ([#10805](https://github.com/diegosouzapw/OmniRoute/issues/10805) — thanks @minhlongs)
-- **fix(sse):** tool-call and Responses-item correctness — concatenated `tool_call` arguments are split apart when two calls collide on the same name/index ([#11043](https://github.com/diegosouzapw/OmniRoute/issues/11043)), kept Responses input items get a default summary and lose a malformed id ([#11110](https://github.com/diegosouzapw/OmniRoute/issues/11110)), freshly built Chat→Responses reasoning items get a default summary ([#11129](https://github.com/diegosouzapw/OmniRoute/issues/11129)) — thanks @maxmad64bis — and the synthetic keepalive reasoning item is closed properly with hardened `output_index` allocation ([#10330](https://github.com/diegosouzapw/OmniRoute/issues/10330) — thanks @hartmark), with the synthetic keepalive itself replaced ([#10806](https://github.com/diegosouzapw/OmniRoute/issues/10806) — thanks @xz-dev)
-- **fix(sse):** prompt-shaping fixes for strict upstreams — a synthetic user turn is appended for GLM-family upstreams that reject the shape with `400 [1214]` ([#11209](https://github.com/diegosouzapw/OmniRoute/issues/11209)), the muse-spark output budget is floored so it stops returning empty-content 502s ([#11214](https://github.com/diegosouzapw/OmniRoute/issues/11214)) — thanks @linhdmn; the strict system hoist re-runs after format translation ([#10803](https://github.com/diegosouzapw/OmniRoute/issues/10803) — thanks @Kizuno18); directive-only messages are relocated off `messages[0]` ([#10457](https://github.com/diegosouzapw/OmniRoute/issues/10457) — thanks @HouMinXi); and the `purify_history` compression notice is merged into the leading system message instead of being injected as its own turn ([#11113](https://github.com/diegosouzapw/OmniRoute/issues/11113) — thanks @ggdayup)
-- **fix(sse):** routing and credential edge cases — keyless Pollinations 401s stop poisoning the no-auth pool ([#11194](https://github.com/diegosouzapw/OmniRoute/issues/11194) — thanks @jonlwheat2-gif); `:free` OpenRouter models bypass a connection-wide `credits_exhausted` lock ([#10445](https://github.com/diegosouzapw/OmniRoute/issues/10445) — thanks @killmonger2317-coder); the `OpencodeExecutor` target format resolves through the provider alias ([#11047](https://github.com/diegosouzapw/OmniRoute/issues/11047) — thanks @maxmad64bis); search providers are excluded from the credential-health scheduler sweep ([#10435](https://github.com/diegosouzapw/OmniRoute/issues/10435)); bare `qwen3.8-max` routes to the canonical `-preview` id ([#10632](https://github.com/diegosouzapw/OmniRoute/issues/10632)); the missing `minimax-music` dispatch was added to music generation ([#10650](https://github.com/diegosouzapw/OmniRoute/issues/10650) — thanks @octo-patch); `gemini-3.5-flash` is marked thinking-capable ([#10450](https://github.com/diegosouzapw/OmniRoute/issues/10450)); a generic compatible-provider type id is bridged to the concrete node id during credential lookup ([#10434](https://github.com/diegosouzapw/OmniRoute/issues/10434)); and `localDb` is imported through its real `.ts` extension so the release build stops breaking ([#10691](https://github.com/diegosouzapw/OmniRoute/issues/10691), [#10674](https://github.com/diegosouzapw/OmniRoute/issues/10674))
-- **fix(sse):** Antigravity's static `sessionId` is no longer pinned and DNS failures are classified as retryable ([#11177](https://github.com/diegosouzapw/OmniRoute/issues/11177) — thanks @rqzbeh); prompt-cache usage fields are included on the `message_stop` fallback path ([#10545](https://github.com/diegosouzapw/OmniRoute/issues/10545) — thanks @NahuSaruf); Claude cache breakpoints advance on growing tails ([#10684](https://github.com/diegosouzapw/OmniRoute/issues/10684) — thanks @cryptiklemur); the reasoning-cache write is guarded by the same predicate its readers use ([#10978](https://github.com/diegosouzapw/OmniRoute/issues/10978) — thanks @maxmad64bis); Codex quota headers stay under the forwarding budget ([#10306](https://github.com/diegosouzapw/OmniRoute/issues/10306)) and the substring "hermes" is no longer ZWJ-obfuscated in user text ([#10488](https://github.com/diegosouzapw/OmniRoute/issues/10488)) — thanks @RaviTharuma
-- **fix(sse):** the Adobe Firefly sign-in helper kills the whole process tree on Linux so no orphan browser is left behind ([#11387](https://github.com/diegosouzapw/OmniRoute/issues/11387)), and every aggressive-compression sub-path spares the live user message ([#11386](https://github.com/diegosouzapw/OmniRoute/issues/11386)) — thanks @HouMinXi
-- **fix(providers):** catalog and lifecycle corrections — reserved provider prefixes are rejected on compatible-node create/update ([#11375](https://github.com/diegosouzapw/OmniRoute/issues/11375) — thanks @ggdayup); the **Hack Club AI** provider was removed and purged from the shared catalog ([#11123](https://github.com/diegosouzapw/OmniRoute/issues/11123) — thanks @rqzbeh, [#11262](https://github.com/diegosouzapw/OmniRoute/issues/11262)); Pollinations now requires an API key with corrected optional-key i18n labels ([#11117](https://github.com/diegosouzapw/OmniRoute/issues/11117) — thanks @rqzbeh); `hailuo-web` moved to `chat.minimax.io` ([#11055](https://github.com/diegosouzapw/OmniRoute/issues/11055) — thanks @rqzbeh); the invalid CodeBuddy CN `glm-4.7` entry was dropped and `hy3` added ([#10356](https://github.com/diegosouzapw/OmniRoute/issues/10356) — thanks @rizxfrog); the phantom Gemini 3.5 Flash entry was eliminated (thanks @backryun); OpenRouter Gemini Embedding 2 ids were catalogued ([#10566](https://github.com/diegosouzapw/OmniRoute/issues/10566) — thanks @RaviTharuma); and `bailian-coding-plan` is validated against the Token Plan host ([#10634](https://github.com/diegosouzapw/OmniRoute/issues/10634))
-- **fix(providers):** reasoning-effort handling is consistent — `reasoning_effort` is clamped to the vocabulary a model actually declares ([#11274](https://github.com/diegosouzapw/OmniRoute/issues/11274) — thanks @linhdmn) and learned and declared clamps now share nearest-tier semantics ([#11305](https://github.com/diegosouzapw/OmniRoute/issues/11305))
-- **fix(providers):** hidden models no longer leak into `GET /v1/models` ([#11309](https://github.com/diegosouzapw/OmniRoute/issues/11309)); rate-limit protection is not silently enabled by a `PATCH` unless it is actually persisted ([#11302](https://github.com/diegosouzapw/OmniRoute/issues/11302)); a degraded cached catalog counts as a failed model sync rather than a success ([#10862](https://github.com/diegosouzapw/OmniRoute/issues/10862) — thanks @ntdat812); expired terminal `grok-cli` credentials answer 401 ([#10971](https://github.com/diegosouzapw/OmniRoute/issues/10971) — thanks @RaviTharuma); model target formats are scoped to their provider ([#10072](https://github.com/diegosouzapw/OmniRoute/issues/10072) — thanks @xz-dev); combo names resolve on `/v1/audio/speech` and `/v1/videos/generations` ([#10471](https://github.com/diegosouzapw/OmniRoute/issues/10471) — thanks @sha367); Muse Spark is routed to the Responses API on `opencode-zen` too ([#11049](https://github.com/diegosouzapw/OmniRoute/issues/11049)); and two dead knobs were removed — the `existingConnections` lookups on connection creation ([#10973](https://github.com/diegosouzapw/OmniRoute/issues/10973)) and `ALLOW_MULTI_CONNECTIONS_PER_COMPAT_NODE`, a flag that governed nothing ([#10974](https://github.com/diegosouzapw/OmniRoute/issues/10974)) — thanks @maxmad64bis
-- **fix(resilience):** cooldown and quota-recovery hardening across the cycle — active cooldowns are preserved during recovery and probes ([#11355](https://github.com/diegosouzapw/OmniRoute/issues/11355) — thanks @sprintberlin); an active rate-limit cooldown is not cleared for non-`quota_exhausted` errors ([#11310](https://github.com/diegosouzapw/OmniRoute/issues/11310)); the `quota_exhausted` cooldown is cleared when the real window recovers ([#10534](https://github.com/diegosouzapw/OmniRoute/issues/10534) — thanks @SnCr90); Ollama model-not-found failures stay scoped to per-model lockout instead of disabling the connection ([#11078](https://github.com/diegosouzapw/OmniRoute/issues/11078) — thanks @rqzbeh); dashboard quota snapshots are honored in the `opencode-go` preflight ([#11267](https://github.com/diegosouzapw/OmniRoute/issues/11267)); shared passthrough providers are honored ([#11075](https://github.com/diegosouzapw/OmniRoute/issues/11075) — thanks @yourspraveen); an embed connection is marked terminal on a hard upstream failure so dead accounts stop being re-hit ([#10506](https://github.com/diegosouzapw/OmniRoute/issues/10506)); same-account transport retry is scoped out of emergency fallback and combo hops (thanks @hartmark); and heavyweight SSE is drained on `SIGTERM` ([#11020](https://github.com/diegosouzapw/OmniRoute/issues/11020) — thanks @RaviTharuma)
-- **fix(quota):** absolute ISO datetime reset timestamps are parsed in the weekly quota fallback ([#11353](https://github.com/diegosouzapw/OmniRoute/issues/11353) — thanks @sprintberlin), and `CREDIT_LIMIT` rows are parsed from the z.ai coding-plan quota API ([#11378](https://github.com/diegosouzapw/OmniRoute/issues/11378) — thanks @Neuron-Mr-White)
-- **fix(combo):** targets carrying a persisted connection cooldown are pre-skipped and re-checked on retry ([#11360](https://github.com/diegosouzapw/OmniRoute/issues/11360) — thanks @sprintberlin); combo loops always terminate with an actionable error instead of hanging silently ([#10463](https://github.com/diegosouzapw/OmniRoute/issues/10463)) and auto-combo pools are restricted to user-visible models ([#10456](https://github.com/diegosouzapw/OmniRoute/issues/10456)) — thanks @herjarsa; SSE comment lines (OpenRouter keep-alives) are accepted by response-quality validation ([#11036](https://github.com/diegosouzapw/OmniRoute/issues/11036) — thanks @asorourx); stale sticky pins are cleared when stickiness is disabled ([#10907](https://github.com/diegosouzapw/OmniRoute/issues/10907) — thanks @excessivechaos); an `unhandledRejection` from the per-model-timeout abort is prevented ([#10846](https://github.com/diegosouzapw/OmniRoute/issues/10846) — thanks @HouMinXi); a combo per-model timeout evicts the sticky session pin ([#10016](https://github.com/diegosouzapw/OmniRoute/issues/10016) — thanks @fenix007); local target timeouts are classified as gateway timeouts; and benign empty error fields no longer fail streaming quality validation
-- **fix(auto):** empty auto-family pools warn once per process instead of on every request ([#10820](https://github.com/diegosouzapw/OmniRoute/issues/10820), [#10344](https://github.com/diegosouzapw/OmniRoute/issues/10344) — thanks @RaviTharuma); auto scoring order and the auto-selected first target are preserved ([#11400](https://github.com/diegosouzapw/OmniRoute/issues/11400), [#11399](https://github.com/diegosouzapw/OmniRoute/issues/11399) — thanks @jacobsparts)
-- **fix(routing):** combo precedence is preserved and hidden models are skipped in the alias resolver ([#11107](https://github.com/diegosouzapw/OmniRoute/issues/11107) — thanks @SCys); keyless custom-compatible connections stay in the `auto/*` pool ([#11198](https://github.com/diegosouzapw/OmniRoute/issues/11198)) and `lkgpEnabled` is forwarded into `RoutingContext` so the LKGP toggle actually works ([#11193](https://github.com/diegosouzapw/OmniRoute/issues/11193)) — thanks @pacocartones; unmapped model aliases fall back to the default seeds ([#10124](https://github.com/diegosouzapw/OmniRoute/issues/10124) — thanks @benzntech)
-- **fix(models):** a synced model's real context window and default effort take effect immediately ([#10957](https://github.com/diegosouzapw/OmniRoute/issues/10957) — thanks @Neuron-Mr-White); `apiFormat`, `targetFormat` and `supportsVision` overrides persist for catalog models ([#10898](https://github.com/diegosouzapw/OmniRoute/issues/10898) — thanks @rqzbeh); media endpoint metadata is normalized ([#11397](https://github.com/diegosouzapw/OmniRoute/issues/11397) — thanks @marcelokarval); Ollama Cloud native effort tiers are exposed ([#11307](https://github.com/diegosouzapw/OmniRoute/issues/11307) — thanks @ekinnee); Codex context and combo limit resolution were corrected ([#10533](https://github.com/diegosouzapw/OmniRoute/issues/10533) — thanks @jackjinke); `MODELS_DEV_SYNC_ENABLED=0` wins over the dashboard setting ([#10299](https://github.com/diegosouzapw/OmniRoute/issues/10299)) and `getModelsDevPricing` is memoized so it stops stalling the event loop and `/healthz` ([#10055](https://github.com/diegosouzapw/OmniRoute/issues/10055)) — thanks @RaviTharuma
-- **fix(catalog):** GLM reasoning-effort tiers are declared ([#10963](https://github.com/diegosouzapw/OmniRoute/issues/10963)) and combo reasoning efforts are scoped by connection ([#10723](https://github.com/diegosouzapw/OmniRoute/issues/10723)) — thanks @xz-dev; Stealth Ox Alpha (`stealth/ox-alpha`) was added to the OpenRouter free roster ([#11337](https://github.com/diegosouzapw/OmniRoute/issues/11337) — thanks @stanleytejakusuma)
-- **fix(pricing):** DeepSeek V4 static defaults were stale by four days and off by ~1.6–2.4× ([#10635](https://github.com/diegosouzapw/OmniRoute/issues/10635)), and three dead entries in `LITELLM_PROVIDER_MAP` were silently dropping synced pricing ([#10636](https://github.com/diegosouzapw/OmniRoute/issues/10636)) — thanks @stanleytejakusuma. DeepSeek off-peak pricing is documented as weekdays-only ([#11210](https://github.com/diegosouzapw/OmniRoute/issues/11210) — thanks @xyzs996)
-- **fix(api):** proxy and probe correctness — both proxy health checks share one probe-target resolution ([#10657](https://github.com/diegosouzapw/OmniRoute/issues/10657)), a target that refuses the egress IP is no longer reported as a healthy proxy ([#10654](https://github.com/diegosouzapw/OmniRoute/issues/10654)), `/api/cache/stats` reports the cache requests actually use ([#10769](https://github.com/diegosouzapw/OmniRoute/issues/10769)) — thanks @maxmad64bis; an OAuth probe timeout is classified as `network_error` ([#10663](https://github.com/diegosouzapw/OmniRoute/issues/10663) — thanks @HouMinXi); pool usage snapshot limits scale by pool member count ([#10253](https://github.com/diegosouzapw/OmniRoute/issues/10253) — thanks @dpozimski); the MCP SSE singleton resets on a new client `initialize` ([#10772](https://github.com/diegosouzapw/OmniRoute/issues/10772) — thanks @sadSanta-07); `.opus` uploads are accepted on `/v1/audio/transcriptions` ([#10607](https://github.com/diegosouzapw/OmniRoute/issues/10607) — thanks @pucedoteth); working OpenRouter ids are named when Gemini embed credentials are missing ([#10565](https://github.com/diegosouzapw/OmniRoute/issues/10565) — thanks @RaviTharuma); a routing combo can no longer be created with no model at all ([#11162](https://github.com/diegosouzapw/OmniRoute/issues/11162) — thanks @maxmad64bis); call logs are saved and an endpoint fallback added for local rerank providers ([#11081](https://github.com/diegosouzapw/OmniRoute/issues/11081) — thanks @AndrianBalanescu); and API keys are hashed in the `/v1/models` catalog cache key
-- **fix(security):** four rounds of CodeQL and advisory remediation landed this cycle — cookie domains are matched by suffix rather than substring ([#11429](https://github.com/diegosouzapw/OmniRoute/issues/11429)); the agent-card topology is sanitized, the login rate limiter uses an anti-spoofed peer IP and 429s carry `Retry-After` ([#11418](https://github.com/diegosouzapw/OmniRoute/issues/11418) — thanks @HouMinXi); round-3 advisories were closed ([#11261](https://github.com/diegosouzapw/OmniRoute/issues/11261)) along with rounds 2 and 4 of the code-scanning alerts ([#10888](https://github.com/diegosouzapw/OmniRoute/issues/10888), [#11293](https://github.com/diegosouzapw/OmniRoute/issues/11293)); an eleven-finding advisory batch ([#11040](https://github.com/diegosouzapw/OmniRoute/issues/11040)) and four still-real findings — ACP RCE hardening, the db-backups route tier, an uppercase authz bypass and spawn-veto drift ([#11028](https://github.com/diegosouzapw/OmniRoute/issues/11028)) — were fixed; Adobe Firefly login compares a parsed hostname instead of a substring and its credential-parsing gates were hardened; an SSRF through the `/v1/search` Firecrawl `provider_options.baseUrl` was blocked ([#10738](https://github.com/diegosouzapw/OmniRoute/issues/10738)) and the open CodeQL code-scanning alerts were zeroed out ([#10739](https://github.com/diegosouzapw/OmniRoute/issues/10739)) with the test regex sanitized and the hash false-positives annotated ([#10380](https://github.com/diegosouzapw/OmniRoute/issues/10380)); and Tier 1 local-only route-guard process-spawning endpoints gained test coverage ([#11189](https://github.com/diegosouzapw/OmniRoute/issues/11189) — thanks @rqzbeh)
-- **fix(authz):** exact public routes are matched exactly instead of as prefixes, so `/api/healthz-something` no longer inherits `/api/healthz`'s public tier ([#11417](https://github.com/diegosouzapw/OmniRoute/issues/11417))
-- **fix(auth):** the real upstream reason is kept in `lastError` instead of a generic string ([#11376](https://github.com/diegosouzapw/OmniRoute/issues/11376) — thanks @ntdat812); login navigates with `window.location` instead of `router.push` so the session cookie is picked up ([#11175](https://github.com/diegosouzapw/OmniRoute/issues/11175)) and `opencode`/`opencode-zen` were added to the credential-resolution search pairs ([#10899](https://github.com/diegosouzapw/OmniRoute/issues/10899)) — thanks @rqzbeh; the OIDC authorization URL carries its missing `state` parameter ([#10614](https://github.com/diegosouzapw/OmniRoute/issues/10614) — thanks @MeRezaRezaei)
-- **fix(oauth):** connections stuck on an upstream 400 after token staleness recover ([#11141](https://github.com/diegosouzapw/OmniRoute/issues/11141) — thanks @HouMinXi); the Kiro `profileArn` survives IAM Identity Center logins ([#10725](https://github.com/diegosouzapw/OmniRoute/issues/10725) — thanks @MichaelYcJo) and a Kiro social poll status is treated as an alias of `error` for pending states ([#10620](https://github.com/diegosouzapw/OmniRoute/issues/10620) — thanks @krishna3554)
-- **fix(cli):** Windows support pass — `omniroute update` spawns npm the way Windows needs ([#11374](https://github.com/diegosouzapw/OmniRoute/issues/11374) — thanks @ntdat812); the tray runtime and the DB fallback resolve dynamic imports as `file://` URLs so `--tray` works ([#11332](https://github.com/diegosouzapw/OmniRoute/issues/11332), [#11238](https://github.com/diegosouzapw/OmniRoute/issues/11238) — thanks @pacocartones); the `DEP0190` child-process spawn deprecation is avoided ([#10835](https://github.com/diegosouzapw/OmniRoute/issues/10835) — thanks @adevwithpurpose); and cliproxy platform handling plus the pid probe were completed ([#11263](https://github.com/diegosouzapw/OmniRoute/issues/11263))
-- **fix(cli):** OAuth start no longer shows a blank device code and an undefined verification URL ([#11173](https://github.com/diegosouzapw/OmniRoute/issues/11173)); `setup-opencode` understands the OpenCode V2 config format ([#11079](https://github.com/diegosouzapw/OmniRoute/issues/11079)) and defaults `limit.context` to 128k when unknown ([#11054](https://github.com/diegosouzapw/OmniRoute/issues/11054)) — thanks @rqzbeh; provider tests route through the connection API ([#10572](https://github.com/diegosouzapw/OmniRoute/issues/10572) — thanks @hydraxman); packaged machine-token authentication was restored ([#10468](https://github.com/diegosouzapw/OmniRoute/issues/10468) — thanks @xiaoyaner0201); a non-empty `[STARTUP] Fatal` log is guaranteed when the instrumentation hook throws at boot ([#10447](https://github.com/diegosouzapw/OmniRoute/issues/10447)); real OpenRouter key validation and the auth-export argument wiring were fixed ([#11264](https://github.com/diegosouzapw/OmniRoute/issues/11264)); and a tmpfs mount is no longer taken as proof that a config path reaches the host
-- **fix(dashboard):** custom mode-pack options are exposed ([#11407](https://github.com/diegosouzapw/OmniRoute/issues/11407)) and explicit auto weights are normalized ([#11402](https://github.com/diegosouzapw/OmniRoute/issues/11402)) — thanks @jacobsparts; unique connection names are computed from the array so one no longer overwrites another ([#11067](https://github.com/diegosouzapw/OmniRoute/issues/11067)) and key validation triggers on Enter in the Add API Key modal ([#11056](https://github.com/diegosouzapw/OmniRoute/issues/11056)) — thanks @rqzbeh; a non-string `apiKey` in the CLI tool cards is guarded ([#10872](https://github.com/diegosouzapw/OmniRoute/issues/10872) — thanks @Rahulsharma0810); the live dashboard sends periodic WebSocket heartbeats to stop reconnect churn ([#10452](https://github.com/diegosouzapw/OmniRoute/issues/10452)); provider-card warning indicators actually expose the interaction they advertise ([#10448](https://github.com/diegosouzapw/OmniRoute/issues/10448)); and media-playground cards stop sending the masked API key as a Bearer token ([#10449](https://github.com/diegosouzapw/OmniRoute/issues/10449))
-- **fix(live-ws):** the public socket URL is resolved at runtime instead of baked in at build ([#11377](https://github.com/diegosouzapw/OmniRoute/issues/11377) — thanks @ntdat812), and a `0.0.0.0` dashboard origin is allowed while non-square SVG image warnings are silenced ([#11269](https://github.com/diegosouzapw/OmniRoute/issues/11269) — thanks @Minamaged18)
-- **fix(db):** call-log rotation pauses on `SQLITE_CORRUPT` instead of compounding the damage ([#10979](https://github.com/diegosouzapw/OmniRoute/issues/10979) — thanks @RaviTharuma); a Windows native-driver hang no longer stalls requests ([#10709](https://github.com/diegosouzapw/OmniRoute/issues/10709) — thanks @jonlwheat2-gif); native runtime drivers are preserved in standalone bundles ([#10552](https://github.com/diegosouzapw/OmniRoute/issues/10552) — thanks @excessivechaos); the sql.js database is published atomically instead of rewritten in place ([#10278](https://github.com/diegosouzapw/OmniRoute/issues/10278) — thanks @maxmad64bis); pre-migration backups are pruned so `db_backups` stops growing without bound ([#10423](https://github.com/diegosouzapw/OmniRoute/issues/10423)); and test runs are kept off the operator's real `DATA_DIR` ([#10432](https://github.com/diegosouzapw/OmniRoute/issues/10432))
-- **fix(build):** the postbuild hook spawns esbuild cross-platform ([#11159](https://github.com/diegosouzapw/OmniRoute/issues/11159) — thanks @aliyosufi); the standalone `package.json` declares its module type for Node 24 worker compatibility ([#10836](https://github.com/diegosouzapw/OmniRoute/issues/10836) — thanks @adevwithpurpose); `assembleStandalone` tolerates a same-realpath symlink and a stale-typed destination ([#10776](https://github.com/diegosouzapw/OmniRoute/issues/10776)); pack-boot sql.js expectations align with dependency-based packaging ([#11266](https://github.com/diegosouzapw/OmniRoute/issues/11266)); and the SQLite driver is kept out of the client bundle ([#10695](https://github.com/diegosouzapw/OmniRoute/issues/10695))
-- **fix(docker):** the Next build worker pool is sized for a 16 GB runner ([#11419](https://github.com/diegosouzapw/OmniRoute/issues/11419)); a warning fires when `OMNIROUTE_MEMORY_MB` disagrees with the `NODE_OPTIONS` heap ([#10818](https://github.com/diegosouzapw/OmniRoute/issues/10818) — thanks @RaviTharuma); and cache mount ids are prefixed with the Railway service scope ([#10288](https://github.com/diegosouzapw/OmniRoute/issues/10288) — thanks @anudeepadi)
-- **fix(electron):** the embedded server is pinned to loopback so the window shows on Windows ([#10717](https://github.com/diegosouzapw/OmniRoute/issues/10717) — thanks @echoriver89)
-- **fix(compression):** `pathToFileURL` is used for the worker URL so bundler resolution stops failing ([#11364](https://github.com/diegosouzapw/OmniRoute/issues/11364) — thanks @TheDemonTuan); CCR no longer strands prompts for callers without the retrieve tool ([#11084](https://github.com/diegosouzapw/OmniRoute/issues/11084) — thanks @HouMinXi); the vendored GCF was bumped with numeric-domain and surplus fixes ([#10807](https://github.com/diegosouzapw/OmniRoute/issues/10807) — thanks @blackwell-systems); the RTK raw-output store is bounded and pointer reads are O(bucket) ([#10660](https://github.com/diegosouzapw/OmniRoute/issues/10660) — thanks @stanleytejakusuma); the Lite and Caveman whitespace/artifact cleaners were accelerated with native V8 RegExp ([#10834](https://github.com/diegosouzapw/OmniRoute/issues/10834) — thanks @adevwithpurpose); i18n was added for `less-code` and `terse-prose` ([#10498](https://github.com/diegosouzapw/OmniRoute/issues/10498) — thanks @abhijeetnardele24-hash); and a stage gate with a metadata-less engine no longer brings the pipeline down ([#10655](https://github.com/diegosouzapw/OmniRoute/issues/10655))
-- **fix(translator):** the `functionCall` id survives Gemini→OpenAI request translation ([#11365](https://github.com/diegosouzapw/OmniRoute/issues/11365)) and consecutive same-role contents are merged in the direct `claudeToGeminiRequest` path ([#10658](https://github.com/diegosouzapw/OmniRoute/issues/10658)) — thanks @Siva010; tool-call names are normalized from lowercase to PascalCase when translating upstream responses into the Claude Messages format ([#10392](https://github.com/diegosouzapw/OmniRoute/issues/10392) — thanks @giauphan); and Claude tool-call state is preserved across a translation round-trip
-- **fix(gemini):** a missing `items` schema is injected for array-typed MCP tools ([#10605](https://github.com/diegosouzapw/OmniRoute/issues/10605) — thanks @sadSanta-07)
-- **fix(codex):** `max_context_window` is preferred over `context_window` as the usable input limit ([#11179](https://github.com/diegosouzapw/OmniRoute/issues/11179) — thanks @excessivechaos); remote compaction V2 completes reliably ([#11041](https://github.com/diegosouzapw/OmniRoute/issues/11041) — thanks @jackjinke); completed Codex tool handoffs survive streaming ([#10608](https://github.com/diegosouzapw/OmniRoute/issues/10608) — thanks @JxnLexn); the header budget, Codex failover and `kv_after_text` handling were corrected together ([#10573](https://github.com/diegosouzapw/OmniRoute/issues/10573) — thanks @HouMinXi); Codex image generation retries on a sibling ChatGPT account ([#10838](https://github.com/diegosouzapw/OmniRoute/issues/10838)); and `apiType="chat"` is respected in `forceResponsesUpstream` ([#10946](https://github.com/diegosouzapw/OmniRoute/issues/10946) — thanks @YunyunZhai)
-- **fix(opencode):** Muse Spark 1.2 models route to the OpenAI Responses API ([#10874](https://github.com/diegosouzapw/OmniRoute/issues/10874) — thanks @zoser69); the provider block is guarded when merging an existing config ([#11004](https://github.com/diegosouzapw/OmniRoute/issues/11004) — thanks @ntdat812); Muse Responses streams are closed at completion ([#11385](https://github.com/diegosouzapw/OmniRoute/issues/11385) — thanks @AStupidBear); the `models[0]` default and its guards were restored ([#11133](https://github.com/diegosouzapw/OmniRoute/issues/11133) — thanks @maxmad64bis); bare combo ids stay unprefixed in the OpenCode plugin ([#10821](https://github.com/diegosouzapw/OmniRoute/issues/10821) — thanks @RaviTharuma); and `opencode-go` is classified as a flat-rate subscription in analytics ([#11199](https://github.com/diegosouzapw/OmniRoute/issues/11199) — thanks @pacocartones)
-- **fix(executors):** an account rotates on an upstream 400 with an empty body (opencode) ([#11158](https://github.com/diegosouzapw/OmniRoute/issues/11158)) and on a network throw when the account has a dedicated proxy ([#10402](https://github.com/diegosouzapw/OmniRoute/issues/10402)) — thanks @maxmad64bis; probe-origin failures are isolated from every deactivation site ([#10694](https://github.com/diegosouzapw/OmniRoute/issues/10694) — thanks @maxmad64bis); and the direct-path response-start timeout is bounded (thanks @excessivechaos)
-- **fix(search):** the `blockedProviders` setting is enforced on the search endpoint ([#10901](https://github.com/diegosouzapw/OmniRoute/issues/10901), [#11125](https://github.com/diegosouzapw/OmniRoute/issues/11125) — thanks @rqzbeh); a `/v1/search` 502 names its provider and cause ([#10756](https://github.com/diegosouzapw/OmniRoute/issues/10756)) and the catalog-default SearXNG `localhost:8888` target is skipped ([#10981](https://github.com/diegosouzapw/OmniRoute/issues/10981)) — thanks @RaviTharuma; with no search provider configured the request falls back to `duckduckgo-free` ([#11097](https://github.com/diegosouzapw/OmniRoute/issues/11097) — thanks @Egorich-print)
-- **fix(mcp):** the `mcp:connect` carve-out is honored in the transport route guards ([#11139](https://github.com/diegosouzapw/OmniRoute/issues/11139) — thanks @HouMinXi); provider-bound tool calls get their own fetch budget ([#10860](https://github.com/diegosouzapw/OmniRoute/issues/10860) — thanks @ntdat812); GitHub skill tools are discoverable through `omniroute_tool_search` ([#10575](https://github.com/diegosouzapw/OmniRoute/issues/10575) — thanks @branben); and the web-search provider enum is generated from the registry ([#10209](https://github.com/diegosouzapw/OmniRoute/issues/10209) — thanks @sadSanta-07)
-- **fix(memory):** a mid-conversation system injection is no longer sent to Claude when the preceding turn is not a tool result ([#11303](https://github.com/diegosouzapw/OmniRoute/issues/11303)), and TokenRouter is treated as system-must-be-first — confirmed against a live HTTP 400 ([#11114](https://github.com/diegosouzapw/OmniRoute/issues/11114) — thanks @ggdayup)
-- **fix(embeddings):** an account is cooled down on hard errors (402/401/5xx) ([#10529](https://github.com/diegosouzapw/OmniRoute/issues/10529) — thanks @HouMinXi), and the configured LM Studio connection URL is honored via the `lm-studio` alias ([#11260](https://github.com/diegosouzapw/OmniRoute/issues/11260))
-- **fix(video-bridge):** structural segment sampling is validated, contact sheets render their timestamps, captions route through provider connections, the fetch size broker sizes bodies, and the remote runtime status is clarified; the result-cache identity and bounds were hardened, download flights are keyed with a process HMAC and tenant scope is separated from the download hash
-- **fix(images):** bare `dall-e-3` routes to OpenAI ([#10847](https://github.com/diegosouzapw/OmniRoute/issues/10847) — thanks @RaviTharuma); OpenRouter reference-image edits are supported ([#10363](https://github.com/diegosouzapw/OmniRoute/issues/10363) — thanks @tiangao88); and inline images keep high detail ([#10554](https://github.com/diegosouzapw/OmniRoute/issues/10554) — thanks @rinseaid)
-- **fix(fusion):** the vision-compatibility filter is applied to both the fusion panel and the judge, so a fan-out with images cannot land on a text-only model ([#10737](https://github.com/diegosouzapw/OmniRoute/issues/10737))
-- **fix(proxy):** proxy log batching is non-blocking and asynchronous ([#11182](https://github.com/diegosouzapw/OmniRoute/issues/11182) — thanks @rqzbeh); IPv4-only proxies stop being reported as dead ([#10868](https://github.com/diegosouzapw/OmniRoute/issues/10868) — thanks @ntdat812); a proxy is probed against its assigned provider host instead of a generic target ([#10664](https://github.com/diegosouzapw/OmniRoute/issues/10664) — thanks @maxmad64bis); and local/loopback proxy-subscription fetch URLs are allowed ([#10416](https://github.com/diegosouzapw/OmniRoute/issues/10416))
-- **fix(relay):** one private-host guard is shared across the three relay workers ([#10941](https://github.com/diegosouzapw/OmniRoute/issues/10941)) and `x-relay-path` resolves through that same guard in the Cloudflare worker ([#10935](https://github.com/diegosouzapw/OmniRoute/issues/10935)) — thanks @ntdat812; Bifrost errors are normalized, a credential 404 is remapped and analytics were corrected ([#10797](https://github.com/diegosouzapw/OmniRoute/issues/10797))
-- **fix(logging):** the component field and printf formats are preserved in the app log ([#10770](https://github.com/diegosouzapw/OmniRoute/issues/10770) — thanks @maxmad64bis); early-keepalive bytes are captured in the call-log artifact ([#10331](https://github.com/diegosouzapw/OmniRoute/issues/10331) — thanks @hartmark); and stream-chunk capture, request-shape logging and other diagnostics are opt-in (thanks @benzntech)
-- **fix(logs):** filter predicates are applied to merged in-memory call-log rows ([#11082](https://github.com/diegosouzapw/OmniRoute/issues/11082) — thanks @AndrianBalanescu); auto-routing is queried from the call logs in analytics ([#10685](https://github.com/diegosouzapw/OmniRoute/issues/10685) — thanks @cryptiklemur)
-- **fix(webhooks):** three declared-but-never-emitted ghost events were removed ([#11050](https://github.com/diegosouzapw/OmniRoute/issues/11050)) with follow-up dispatcher tests and vi i18n ([#11130](https://github.com/diegosouzapw/OmniRoute/issues/11130)) — thanks @maxmad64bis
-- **fix(antigravity):** live chat models are discovered dynamically ([#10422](https://github.com/diegosouzapw/OmniRoute/issues/10422) — thanks @JxnLexn); Gemini and Claude reasoning capabilities are unblocked ([#10376](https://github.com/diegosouzapw/OmniRoute/issues/10376) — thanks @Chewji9875); and a trailing model turn is stripped for native Gemini requests too ([#10436](https://github.com/diegosouzapw/OmniRoute/issues/10436))
-- **fix(adobe-firefly):** sessions renew through a durable CDP connection ([#9255](https://github.com/diegosouzapw/OmniRoute/issues/9255) — thanks @artickc), models and media capabilities were synced, and the Topaz catalog models are retained
-- **fix(cline):** proxy task ids are no longer generated ([#10279](https://github.com/diegosouzapw/OmniRoute/issues/10279)) and internal health checks are labelled as such ([#10706](https://github.com/diegosouzapw/OmniRoute/issues/10706)) — thanks @arafatkatze; Cline provider models use a valid `modelType`/`model` format ([#11132](https://github.com/diegosouzapw/OmniRoute/issues/11132) — thanks @rqzbeh)
-- **fix(agentrouter):** the protocol is inferred from the client endpoint, an alternate protocol is honored through the chat pipeline, and both the Claude and Codex protocols are supported
-- **fix(services):** the CLIProxy executable is used on Windows ([#10371](https://github.com/diegosouzapw/OmniRoute/issues/10371) — thanks @tkgo11), and port discovery falls back to `ss` and `netstat` when `lsof` is absent ([#10459](https://github.com/diegosouzapw/OmniRoute/issues/10459) — thanks @aron-intframe)
-- **fix(monitoring):** provider aliases are canonicalized in the health matrix ([#10370](https://github.com/diegosouzapw/OmniRoute/issues/10370) — thanks @tkgo11); the Docker `HEALTHCHECK` probes `/healthz` rather than deep monitoring ([#10307](https://github.com/diegosouzapw/OmniRoute/issues/10307) — thanks @RaviTharuma); a slow `/healthz` event-loop lag warns ([#10827](https://github.com/diegosouzapw/OmniRoute/issues/10827) — thanks @RaviTharuma); and the canary install is judged by the SHA on disk instead of npm's exit code ([#10699](https://github.com/diegosouzapw/OmniRoute/issues/10699))
-- **fix(github):** GitHub access tokens are verified during health checks instead of being assumed valid ([#11320](https://github.com/diegosouzapw/OmniRoute/issues/11320) — thanks @RaviTharuma)
-- **fix(i18n):** locale parity work — the zh-CN/zh-TW CLI locales were completed with a parity guard ([#11339](https://github.com/diegosouzapw/OmniRoute/issues/11339)) and the three missing pt-BR CLI keys added ([#11322](https://github.com/diegosouzapw/OmniRoute/issues/11322)) — thanks @pacocartones; missing routing and compression messages were added ([#10546](https://github.com/diegosouzapw/OmniRoute/issues/10546) — thanks @rizxfrog); HTML entities in UI strings were unescaped and `gatesDescription` restored ([#9721](https://github.com/diegosouzapw/OmniRoute/issues/9721) — thanks @dionjoshualobo); vi parity was completed for the sponsor banner ([#11208](https://github.com/diegosouzapw/OmniRoute/issues/11208)); and the capability-filter messages and web-session guide were translated
-- **fix(chat):** the severity-classifier format is detected in the `claudeClassifierCompat` short-circuit ([#11304](https://github.com/diegosouzapw/OmniRoute/issues/11304)); search providers are guarded from the OpenAI fallback ([#10394](https://github.com/diegosouzapw/OmniRoute/issues/10394) — thanks @azzaouiomar19-sketch); and concurrent requests stop colliding on the dedup hash for non-OpenAI formats ([#10438](https://github.com/diegosouzapw/OmniRoute/issues/10438))
-- **fix(providers):** small per-provider corrections — Groq strips unsupported message metadata ([#11026](https://github.com/diegosouzapw/OmniRoute/issues/11026) — thanks @sanforex24h); `sensenova` clamps max reasoning effort to `xhigh` ([#10733](https://github.com/diegosouzapw/OmniRoute/issues/10733) — thanks @InkshadeWoods); Zed Hosted Models gained connection-test support ([#10810](https://github.com/diegosouzapw/OmniRoute/issues/10810) — thanks @Hsia97); `kilocode` strips an unsupported `response_format` for DeepSeek V4 Flash ([#10458](https://github.com/diegosouzapw/OmniRoute/issues/10458) — thanks @benzntech); `kimi-web` points at the international `www.kimi.ai` ([#11045](https://github.com/diegosouzapw/OmniRoute/issues/11045) — thanks @MeRezaRezaei); "insufficient credits" is classified as credits-exhausted ([#10116](https://github.com/diegosouzapw/OmniRoute/issues/10116) — thanks @Chewji9875); the ChatGPT Web catalog was refreshed ([#10637](https://github.com/diegosouzapw/OmniRoute/issues/10637) — thanks @backryun); Ollama routes models by advertised capability ([#11088](https://github.com/diegosouzapw/OmniRoute/issues/11088) — thanks @yourspraveen); the Perplexity Web built-in-search hint became opt-in ([#10904](https://github.com/diegosouzapw/OmniRoute/issues/10904)); nested STT models fall back when the prefix provider has no credentials ([#10584](https://github.com/diegosouzapw/OmniRoute/issues/10584) — thanks @RaviTharuma); the mimocode provider was retired ([#10186](https://github.com/diegosouzapw/OmniRoute/issues/10186) — thanks @Tushar49); AWS Polly signing credentials were added ([#11207](https://github.com/diegosouzapw/OmniRoute/issues/11207) — thanks @rafacpti23); and `model_not_found` is returned for an unrecognized prefix model when the provider is inactive ([#10894](https://github.com/diegosouzapw/OmniRoute/issues/10894) — thanks @rqzbeh)
-- **fix(radar):** feature availability is separated from opt-in ([#10487](https://github.com/diegosouzapw/OmniRoute/issues/10487)) and stale flag-off responses are bypassed ([#10464](https://github.com/diegosouzapw/OmniRoute/issues/10464)); the aggregate sync body is validated and the remaining client trust boundaries closed — thanks @backryun
-- **fix(usage):** quota windows are ordered chronologically on every provider card ([#11241](https://github.com/diegosouzapw/OmniRoute/issues/11241) — thanks @pacocartones)
-- **fix(files):** the list `limit` query parameter is validated ([#10673](https://github.com/diegosouzapw/OmniRoute/issues/10673) — thanks @pacocartones), and the gamification leaderboard validates `limit`/`offset` before the SQLite bind ([#11059](https://github.com/diegosouzapw/OmniRoute/issues/11059) — thanks @pacocartones)
-- **fix(onboarding):** the setup wizard warns when the password step is skipped ([#10855](https://github.com/diegosouzapw/OmniRoute/issues/10855) — thanks @krishna3554)
-- **fix(settings):** `customSystemPrompt` fields were missing from `updateSettingsSchema` and were silently dropped ([#10890](https://github.com/diegosouzapw/OmniRoute/issues/10890) — thanks @rqzbeh); `debugMode` defaults to false and account rotation is skipped on a model-unsupported 400 ([#10525](https://github.com/diegosouzapw/OmniRoute/issues/10525) — thanks @HouMinXi)
-- **fix(conversations):** the reconnect walk is bounded and turn hashes are memoized ([#10800](https://github.com/diegosouzapw/OmniRoute/issues/10800) — thanks @adevwithpurpose)
-- **fix(reasoning):** compatible response state is preserved across a provider hop ([#10574](https://github.com/diegosouzapw/OmniRoute/issues/10574) — thanks @jackjinke)
-- **fix(agent-bridge):** the regenerate-cert endpoint actually mints a new certificate ([#10715](https://github.com/diegosouzapw/OmniRoute/issues/10715) — thanks @ntdatt812)
-- **fix(api-manager):** empty combo restrictions are allowed instead of rejected ([#10066](https://github.com/diegosouzapw/OmniRoute/issues/10066) — thanks @xz-dev)
-- **fix(db):** the Database settings page no longer answers HTTP 500 when SQLite lacks the optional `dbstat` table ([#10558](https://github.com/diegosouzapw/OmniRoute/issues/10558) — thanks @TechNickAI)
-- **fix(models):** health-check-excluded models are hidden from the `/v1/models` catalog ([#10026](https://github.com/diegosouzapw/OmniRoute/issues/10026) — thanks @ritheshcn25)
-- **fix(skills):** the CLI skills left stale by the quota subcommands are regenerated ([#10698](https://github.com/diegosouzapw/OmniRoute/issues/10698))
-- **fix(mcp):** CLI MCP call protocol issues were resolved ([#10960](https://github.com/diegosouzapw/OmniRoute/issues/10960) — thanks @YunyunZhai)
-- **fix(dashboard):** expert mode in the Combo Builder can type a provider/model pair by hand again ([#8875](https://github.com/diegosouzapw/OmniRoute/pull/8875)) — [#8285](https://github.com/diegosouzapw/OmniRoute/pull/8285) (global model search) replaced the "Manual model" block positionally with the new search panel, removing the only way to enter a model that is not in the catalog. The state and handlers behind it survived as dead code, so neither typecheck nor lint noticed the loss. The block is restored above the search panel, unchanged from its pre-#8285 form, and guarded by `tests/e2e/combos-flow.spec.ts` ("expert mode shows a single-page combo form with manual model entry").
-- **fix(sse):** a combo step pinned to an explicit connection (or a request pinned with `x-omniroute-connection`) is honored on fallback instead of silently rotating to a sibling account ([#8875](https://github.com/diegosouzapw/OmniRoute/pull/8875)) — the generic account-fallback branch excluded the pinned connection after an upstream failure and re-selected another account of the same provider, so a priority combo repeating one provider/model with two different fixed accounts ran **both** attempts under the first step; the second step and its own pin never executed, and per-step attribution (`comboStepId` / `comboExecutionKey`) was wrong. Rotation is now gated on there being no forced connection, matching the stream-readiness, pre-response-timeout and account-semaphore branches. Cooldown recording is unchanged, and unpinned selection still skips burned connections.
-- **fix(cli):** the local CLI sees the full `/api/monitoring/health` payload again — `version` included — restoring the `check:pack-boot` release gate. [#11040](https://github.com/diegosouzapw/OmniRoute/pull/11040) reduced that route to a liveness-only view for non-management callers (GHSA-mvf8-qc78-5mxm), but the route is classified PUBLIC and `runAuthzPipeline` strips the machine-token header for every route class — so the PUBLIC policy stamped `anonymous` and the loopback CLI could never be recognized as a management principal. The PUBLIC policy now stamps the same loopback-gated `local-cli-token` subject the MANAGEMENT policy already did; anonymous callers still get liveness only.
-- **fix(search):** a configured search connection (Serper, Brave, Tavily…) is now used instead of being silently passed over for the free `duckduckgo-free` fallback ([#11524](https://github.com/diegosouzapw/OmniRoute/issues/11524)) — when no provider was named explicitly and the cheapest auto-selected one had no credentials, the last-resort loop ran first and `duckduckgo-free` (cost 0, no auth) always won it with empty credentials. On `/v1/responses` the call then returned `success: true` with **zero results**, so web search looked healthy while the paid connection the operator had set up was never called. Credentialed regular providers are now swept before the last-resort loop, and fallback-only providers can no longer outrank a configured one on price.
-- **fix(api):** `/v1/models` no longer blocks the stale response while it rebuilds the catalog ([#11551](https://github.com/diegosouzapw/OmniRoute/issues/11551)) — the route has been passing a `scheduleBackgroundRefresh` option since #10198, but the parameter had already been removed from `getUnifiedModelsResponse()`, so the object was silently dropped and the stale-while-revalidate rebuild still ran on a `setTimeout(..., 0)`. The builder is essentially synchronous under the App Router, so it pinned the event loop **before** the cached response was flushed — the [#8728](https://github.com/diegosouzapw/OmniRoute/pull/8728) guarantee did not actually exist for operators with large catalogs. `catalogCache` now schedules through `after()` (with a macrotask fallback outside a request scope) and the option is threaded end to end. The extra argument was invisible to CI because `typecheck:core` is a curated allowlist and `next.config.mjs` sets `ignoreBuildErrors: true`.
-- **fix(sse):** a universal handoff whose summary comes back unusable is no longer regenerated on every single model switch, which was burning paid quota on upstream calls whose answers were thrown away ([#11552](https://github.com/diegosouzapw/OmniRoute/issues/11552)) — nothing is persisted when the summary does not parse, so the next switch in the same session re-issued the same full-history summarization request and discarded it again, forever. With a switch-heavy combo strategy (weighted, random, round-robin, p2c) that landed on a large share of requests: measured at n=200, roughly **one request in four carried an extra discarded upstream call**, and that traffic skewed a weighted 70/30 combo to an observed 0.895 share for one provider even though the share actually delivered to the client was a correct 0.70. There is now an exponential back-off per (session, combo) — 5 min up to 1 h, cleared on the first successful handoff, capped at 500 tracked keys. A transient upstream failure is deliberately **not** tracked, so it still retries immediately. After the fix: 201 upstream calls for 200 requests, and the measured share matches the delivered one.
-
-### 📝 Maintenance
-
-- **refactor(providers):** removed the Puter provider (id `puter`, alias `pu`) entirely — registry entry, `PuterExecutor`, API-key preset, 33 free-catalog models, i18n auth hints and docs — at the request of Puter's owner, Nariman Jelveh. Migration 152 cleans up any locally stored Puter connections/keys/custom models; historical usage records are preserved.
-- **fix(types):** preserve the client response format contract while estimating usage for non-streaming responses (#8484)
-- Preserve the Responses API transform options contract under TypeScript 7.
-- **fix(types):** preserved the known first-failure record while reading Anthropic thinking-signature recovery details so TypeScript 7 keeps the retry result union narrow ([#8484](https://github.com/diegosouzapw/OmniRoute/issues/8484))
-- **fix(types):** reuse the validation failure predicate when building malformed-body responses so the existing error envelope remains type-safe and unchanged. (#8484)
-- **fix(types):** preserve the literal `capabilities.vision: true` contract for catalog vision fields so custom-model capability composition remains type-safe under TypeScript 7 ([#9121](https://github.com/diegosouzapw/OmniRoute/pull/9121)) (#8484)
-- chore(quality): add an RTL layout ratchet — counts physical directional Tailwind classes (ml/mr/pl/pr/left/right/text-left/border-l/rounded-l) that do not mirror under `dir=rtl`, seeded at 1011 so the backlog behind `tests/unit/ui/rtl-logical-classes.test.tsx` ("#3541, partial, core layout") cannot grow while it is worked through ([#8828](https://github.com/diegosouzapw/OmniRoute/pull/8828)) — thanks @lukiod
-- **chore(sse):** dropped the leftover `iflow` entry from the token-refresh TTL map — the provider was removed from the product but its 24-hour refresh lead outlived it, and the identifier had exactly two occurrences left repo-wide ([#8966](https://github.com/diegosouzapw/OmniRoute/pull/8966))
-- **chore(ci):** removed two fork-owned image-publish workflows that had ridden into the repo as unrelated extra files in on-topic PRs — `build-fork.yml` (`ghcr.io/kang-heewon`, job-level guard, so it instantiated a skipped run on every push to main and every tag) and `build-rinseaid-image.yml` (`ghcr.io/rinseaid`, no guard, never fired). Neither could authenticate against this repository's token; a new policy guard now fails CI on any workflow targeting a foreign registry namespace ([#8967](https://github.com/diegosouzapw/OmniRoute/pull/8967))
-- **test(ci):** fixed the intermittent `spawnSync bash EPIPE` failure in the `:latest` promotion guard — the script exits on a pre-release version before reading stdin, so the harness's pipe-backed `input:` raced that exit; stdin is now file-backed, which makes the race structurally impossible ([#8977](https://github.com/diegosouzapw/OmniRoute/pull/8977))
-- **refactor(providers):** removed the retired GitHub Models provider and its catalog, discovery, embedding, free-tier, UI, and documentation surfaces; upgrades now run a durable, idempotent purge of its stored credentials, usage state, structured configuration, and call-log artifacts while preserving GitHub Copilot and live members of mixed configurations ([#9023](https://github.com/diegosouzapw/OmniRoute/pull/9023))
-- **test(sse):** added the first test suite for `open-sse/services/specificityRules.ts` — the
-  module was hotspot #7 in the coverage plan at 11.28% lines with no dedicated test; the 14 pure
-  detectors are now pinned edge-to-edge (token ladders, per-domain max-not-sum scoring, and the
-  min/max clamps), taking the file to ~100% line coverage. The suite also documents two quirks
-  left unchanged: `detectReasoningDepth` scores above 0 on marker-free input via its
-  always-applied message-depth bonus, and `detectErrorContext` returns non-integer scores because
-  it never rounds ([#9063](https://github.com/diegosouzapw/OmniRoute/pull/9063))
-- **fix(types):** preserved the Veo polling delay promise result as `void` for TypeScript 7 compatibility without changing runtime polling behavior ([#9104](https://github.com/diegosouzapw/OmniRoute/pull/9104))
-- **fix(types):** imported compression analytics statistics from their defining module so TypeScript 7 resolves the existing interface correctly ([#9105](https://github.com/diegosouzapw/OmniRoute/pull/9105))
-- **chore(types):** align semantic cache signature inputs with the numeric request contract so both cache-write paths remain runtime-equivalent while TypeScript 7 checks them safely ([#9117](https://github.com/diegosouzapw/OmniRoute/pull/9117))
-- **fix(types):** narrowed non-streaming chat response metadata inputs to the shared header contract without changing emitted metadata headers ([#9118](https://github.com/diegosouzapw/OmniRoute/pull/9118))
-- **docs(readme):** replace Roo Code branding with Zoo Code. (thanks @taltas) ([#9229](https://github.com/diegosouzapw/OmniRoute/pull/9229))
-- **chore(ci):** stopped dependabot from grouping `ioredis` majors with routine production bumps — the package is resolved through a dynamic import in the distributed quota store, so a breaking major passes build, typecheck and both test suites and only surfaces at runtime for operators running Redis-backed quota ([#9425](https://github.com/diegosouzapw/OmniRoute/pull/9425))
-- **chore(tests):** cleared two base-reds sitting on `release/v3.8.50` itself, both of which turned every open PR red the moment it merged the release. `tests/snapshots/provider/translate-path.json` was stale: #9064 added the `code-execution-2025-08-25` and `skills-2025-10-02` beta flags to the Anthropic header without regenerating the golden, so `provider-translate-path-golden` failed on the bare release tip (2 pass / 1 fail with zero PRs boarded). And `tests/unit/v1-models-auth-leak-9320.test.ts:83` shipped a `(k: any)` in a file new enough that `config/quality/eslint-suppressions.json` does not cover it — with `@typescript-eslint/no-explicit-any` set to `error` under `tests/`, that single cast failed the `No new ESLint warnings` gate repo-wide. Same class in `tests/unit/issue-9407-gemini-web-validation-false-positive.test.ts:50` (`(executor as any).testConnection`), which entered at `f1ea77fd04` — `testConnection` is a declared public method on `GeminiWebExecutor`, so that cast was redundant too. Regenerating the snapshot and dropping both casts restores the gates. ([#9488](https://github.com/diegosouzapw/OmniRoute/pull/9488))
-- **test(cli):** OpenCode plugin suite realigned to the bare-key static-catalog contract from #9178/#9175 (21 tests were red on every opencode-plugin CI run; 287/287 after) ([#9614](https://github.com/diegosouzapw/OmniRoute/pull/9614))
-- Removed the unused `RadarReferrals` type export left by the radar referral-links feature (#9697), returning the dead-code ratchet to its 227 baseline. (#9738)
-- Reconcile the final v3.8.50 bundle-size and file-size ratchets against the measured release tip, preserving exact direction-down ceilings and their source attribution. ([#9839](https://github.com/diegosouzapw/OmniRoute/pull/9839))
-- **chore(quality):** expand all file-size baselines by +30% ahead of v3.8.51 (authorized DRIFT rebaseline) to unblock the pre-release queue; no functionality changes. (#9950)
-- fix(quality): tighten eslintWarnings baseline 5000->0 to match the gate's suppressions-applied measurement (unblocks require-tighten on every code PR)
-- **[v3.8.50] feat: add RTL layout compatibility CSS (fixes #7680)** ([#7987](https://github.com/diegosouzapw/OmniRoute/pull/7987)) — thanks @Dingding-leo
-- **[v3.8.50] feat(devin-desktop): replace public Windsurf provider** ([#8228](https://github.com/diegosouzapw/OmniRoute/pull/8228)) — thanks @backryun
-- **[v3.8.50] feat(ci): extend i18n glossary-consistency gate to ko** ([#8244](https://github.com/diegosouzapw/OmniRoute/pull/8244)) — thanks @MichaelYcJo
-- **[v3.8.50] test(tail): realign 3 stale base-red guards + note 2 env-only false positives (slice 6)** ([#8263](https://github.com/diegosouzapw/OmniRoute/pull/8263))
-- **[v3.8.50] feat(ui): add global model search to Combo builder** ([#8285](https://github.com/diegosouzapw/OmniRoute/pull/8285)) — thanks @corefusiion
-- **[v3.8.50] feat: extract CloakBrowser/browser-pool into optional plugin package** ([#8299](https://github.com/diegosouzapw/OmniRoute/pull/8299)) — thanks @oyi77
-- **[v3.8.50] fix(i18n): clean up and naturalize Spanish translations** ([#8339](https://github.com/diegosouzapw/OmniRoute/pull/8339)) — thanks @Dragost
-- **[v3.8.50] fix(compression): bound session-dedup suffix-block scan to prevent OOM** ([#8438](https://github.com/diegosouzapw/OmniRoute/pull/8438)) — thanks @adrianojiu
-- **[v3.8.50] Fix Z.ai web browser transport and model capabilities** ([#8451](https://github.com/diegosouzapw/OmniRoute/pull/8451)) — thanks @backryun
-- **[v3.8.50] feat(services): add Dario as a 5th embedded service (Claude Code toggle/failover)** ([#8523](https://github.com/diegosouzapw/OmniRoute/pull/8523)) — thanks @seanford
-- **[v3.8.50] fix(adobe-firefly): live x-arp-session-id / Arkose wire (stop HTTP 408)** ([#8571](https://github.com/diegosouzapw/OmniRoute/pull/8571)) — thanks @artickc
-- **[v3.8.50] fix(adobe-firefly): durable session, Chrome recovery, browser sign-in** ([#8578](https://github.com/diegosouzapw/OmniRoute/pull/8578)) — thanks @artickc
-- **[v3.8.50] fix: passthrough non-standard cache token fields for DeepSeek / MiniMax / Bedrock across streaming, non-streaming, and Dashboard paths** ([#8591](https://github.com/diegosouzapw/OmniRoute/pull/8591)) — thanks @ikelvingo
-- **[v3.8.50] fix: treat zero-reset Antigravity 429s as transient** ([#8626](https://github.com/diegosouzapw/OmniRoute/pull/8626)) — thanks @costaeder
-- **[v3.8.50] fix: enforce OpenAI model lifecycle without silent reroutes** ([#8627](https://github.com/diegosouzapw/OmniRoute/pull/8627)) — thanks @backryun
-- **[v3.8.50] fix(claude): preserve signed thinking turns during obfuscation** ([#8629](https://github.com/diegosouzapw/OmniRoute/pull/8629)) — thanks @costaeder
-- **[v3.8.50] fix(antigravity): lock full quota per exact model** ([#8630](https://github.com/diegosouzapw/OmniRoute/pull/8630)) — thanks @costaeder
-- **[v3.8.50] fix(errorConfig): add status 499 metadata mapping (fixes #8535)** ([#8640](https://github.com/diegosouzapw/OmniRoute/pull/8640)) — thanks @Dingding-leo
-- **[v3.8.50] fix(auth): accept x-api-key without anthropic-version for claude-code user-agent (fixes #8655)** ([#8678](https://github.com/diegosouzapw/OmniRoute/pull/8678)) — thanks @Dingding-leo
-- **[v3.8.50] fix(open-sse): add 'has been exhausted' to CREDITS_EXHAUSTED_SIGNALS (fixes #8631)** ([#8704](https://github.com/diegosouzapw/OmniRoute/pull/8704)) — thanks @Dingding-leo
-- **[v3.8.50] fix(github): honor per-model targetFormat override for Copilot custom models** ([#8713](https://github.com/diegosouzapw/OmniRoute/pull/8713)) — thanks @Witroch4
-- **[v3.8.50] fix(test): revive orphaned vitest tests and fix CI routing** ([#8718](https://github.com/diegosouzapw/OmniRoute/pull/8718)) — thanks @MohitRawat017
-- **[v3.8.50] feat(providers): add support for TinyCMS Web** ([#8736](https://github.com/diegosouzapw/OmniRoute/pull/8736)) — thanks @jhordanjw123
-- **[v3.8.50] feat(memory): MemoryBackend provider pattern with generic HTTP connector** ([#8752](https://github.com/diegosouzapw/OmniRoute/pull/8752)) — thanks @oyi77
-- **[v3.8.50] refactor(db): add combo repository boundary** ([#8757](https://github.com/diegosouzapw/OmniRoute/pull/8757)) — thanks @xiaoyaner0201
-- **[v3.8.50] fix(test): revive orphaned open-sse vitest tests** ([#8772](https://github.com/diegosouzapw/OmniRoute/pull/8772)) — thanks @MohitRawat017
-- **[v3.8.50] fix(open-sse): filter non-numeric values in comboTargetLimits before min calculation** ([#8774](https://github.com/diegosouzapw/OmniRoute/pull/8774)) — thanks @Dingding-leo
-- **[v3.8.50] feat(compression): add Italian (it) Caveman rule pack** ([#8776](https://github.com/diegosouzapw/OmniRoute/pull/8776)) — thanks @Anjielon
-- **[v3.8.50] feat(combo): add maxContextWindow to contextRequirements (fixes #8777)** ([#8790](https://github.com/diegosouzapw/OmniRoute/pull/8790)) — thanks @Dingding-leo
-- **[v3.8.50] feat(images): add POST /v1/images/upscale (Adobe Firefly Topaz + Stability + Topaz Labs)** ([#8791](https://github.com/diegosouzapw/OmniRoute/pull/8791)) — thanks @artickc
-- **[v3.8.50] fix(providers): drop dead Cloudflare Workers AI free catalog IDs (#8717)** ([#8804](https://github.com/diegosouzapw/OmniRoute/pull/8804)) — thanks @DinonowDev
-- **[v3.8.50] fix(sse): stop fabricating encrypted Codex reasoning summary text** ([#8807](https://github.com/diegosouzapw/OmniRoute/pull/8807)) — thanks @Prudhvivuda
-- **[v3.8.50] fix(backend): update Cloudflare Workers AI model catalog & remove dead model IDs (#8717)** ([#8808](https://github.com/diegosouzapw/OmniRoute/pull/8808)) — thanks @Dingding-leo
-- **[TS7] [v3.8.50] refactor(db): preserve normalized combo model types** ([#8809](https://github.com/diegosouzapw/OmniRoute/pull/8809)) — thanks @backryun
-- **[v3.8.50] fix(db/apiKeys): respect provider parameter in group model permission checks (fixes #8803)** ([#8817](https://github.com/diegosouzapw/OmniRoute/pull/8817)) — thanks @Dingding-leo
-- **[TS7] [v3.8.50] fix(types): preserve browser abort handling** ([#8818](https://github.com/diegosouzapw/OmniRoute/pull/8818)) — thanks @backryun
-- **[v3.8.50] feat(cli): deliver the Antigravity credential straight to the remote install** ([#8834](https://github.com/diegosouzapw/OmniRoute/pull/8834))
-- **[v3.8.50] docs: slim AGENTS.md** ([#8839](https://github.com/diegosouzapw/OmniRoute/pull/8839)) — thanks @MumuTW
-- **docs(guides): add Antigravity (Google One AI) onboarding guide** ([#8904](https://github.com/diegosouzapw/OmniRoute/pull/8904)) — thanks @HouMinXi
-- **[v3.8.50] fix(usage): reject impossible provider token counts** ([#8927](https://github.com/diegosouzapw/OmniRoute/pull/8927)) — thanks @artickc
-- **Treat context metadata as a routing hint** ([#8944](https://github.com/diegosouzapw/OmniRoute/pull/8944)) — thanks @JxnLexn
-- **docs(db): specify MySQL conformance semantics** ([#8947](https://github.com/diegosouzapw/OmniRoute/pull/8947)) — thanks @rushsinging
-- **Add native ChatGPT Web provider for Codex clients** ([#8949](https://github.com/diegosouzapw/OmniRoute/pull/8949)) — thanks @JxnLexn
-- **i18n(ru): complete Russian locale — 100% coverage** ([#9001](https://github.com/diegosouzapw/OmniRoute/pull/9001)) — thanks @Egorich-print
-- **docs(troubleshooting): document the chat_admission_busy 503 and how to tune heavyweight chat concurrency** ([#9021](https://github.com/diegosouzapw/OmniRoute/pull/9021)) — thanks @xiaoyaner0201
-- **Security: Update Redis to fix critical vunerability** ([#9065](https://github.com/diegosouzapw/OmniRoute/pull/9065)) — thanks @tuxmonteiro
-- **[TS7] fix(types): validate chat context estimation inputs** ([#9084](https://github.com/diegosouzapw/OmniRoute/pull/9084)) — thanks @backryun
-- **[TS7] fix(types): narrow stream response output** ([#9086](https://github.com/diegosouzapw/OmniRoute/pull/9086)) — thanks @backryun
-- **docs: clarify free-provider model refresh outcomes** ([#9087](https://github.com/diegosouzapw/OmniRoute/pull/9087)) — thanks @AbdullahFageeh
-- **[TS7] [v3.8.50] fix(types): preserve SSE tool call function shape** ([#9090](https://github.com/diegosouzapw/OmniRoute/pull/9090)) — thanks @backryun
-- **[TS7] fix(types): narrow CCR store rejections** ([#9091](https://github.com/diegosouzapw/OmniRoute/pull/9091)) — thanks @backryun
-- **[TS7] fix(types): preserve array-buffer response bodies** ([#9092](https://github.com/diegosouzapw/OmniRoute/pull/9092)) — thanks @backryun
-- **[TS7] fix(types): narrow media generation failures** ([#9093](https://github.com/diegosouzapw/OmniRoute/pull/9093)) — thanks @backryun
-- **[TS7] fix(types): preserve thinking signature recovery failure** ([#9114](https://github.com/diegosouzapw/OmniRoute/pull/9114)) — thanks @backryun
-- **[TS7] fix(types): preserve Responses transform options** ([#9119](https://github.com/diegosouzapw/OmniRoute/pull/9119)) — thanks @backryun
-- **[TS7] fix(types): preserve validation failure narrowing** ([#9120](https://github.com/diegosouzapw/OmniRoute/pull/9120)) — thanks @backryun
-- **[TS7] fix(types): preserve client usage format contract** ([#9122](https://github.com/diegosouzapw/OmniRoute/pull/9122)) — thanks @backryun
-- **[TS7] fix(types): preserve request rule input contracts** ([#9135](https://github.com/diegosouzapw/OmniRoute/pull/9135)) — thanks @backryun
-- **[TS7] fix(types): simplify Codex service tier narrowing** ([#9136](https://github.com/diegosouzapw/OmniRoute/pull/9136)) — thanks @backryun
-- **[TS7] fix(types): tighten extracted chatCore contracts** ([#9137](https://github.com/diegosouzapw/OmniRoute/pull/9137)) — thanks @backryun
-- **[TS7] fix(types): align web executor event and model contracts** ([#9138](https://github.com/diegosouzapw/OmniRoute/pull/9138)) — thanks @backryun
-- **[TS7] fix(types): align web provider support contracts** ([#9139](https://github.com/diegosouzapw/OmniRoute/pull/9139)) — thanks @backryun
-- **[TS7] fix(types): type media provider request payloads** ([#9141](https://github.com/diegosouzapw/OmniRoute/pull/9141)) — thanks @backryun
-- **test(dashboard): drop stale next-intl mock breaking ProviderDetailPageClient smoke** ([#9150](https://github.com/diegosouzapw/OmniRoute/pull/9150)) — thanks @maxmad64bis
-- **test(mcp): guard Node 24 bundled MCP startup** ([#9162](https://github.com/diegosouzapw/OmniRoute/pull/9162)) — thanks @Gioxaa
-- **test(compression): lock in stacked RTK+Caveman savings on redundant tool_result content** ([#9278](https://github.com/diegosouzapw/OmniRoute/pull/9278)) — thanks @Sam280903
-- **chore: bump better-sqlite3 and add provider DB query scripts** ([#9325](https://github.com/diegosouzapw/OmniRoute/pull/9325)) — thanks @jowimila
-- **test(quota): wait for the hot-path consumption instead of sleeping** ([#9365](https://github.com/diegosouzapw/OmniRoute/pull/9365)) — thanks @HouMinXi
-- **refactor(sse): move the thinking-budget helpers out of base.ts** ([#9381](https://github.com/diegosouzapw/OmniRoute/pull/9381)) — thanks @HouMinXi
-- **test(sse): expect the trailing period in the no-credentials message** ([#9392](https://github.com/diegosouzapw/OmniRoute/pull/9392)) — thanks @HouMinXi
-- **chore(db): raise sqlite cache_size/mmap_size defaults** ([#9467](https://github.com/diegosouzapw/OmniRoute/pull/9467)) — thanks @Poid-ZA
-- **[TS7] fix(types): align stream failure callback contracts** ([#9561](https://github.com/diegosouzapw/OmniRoute/pull/9561)) — thanks @backryun
-- **[TS7] fix(types): narrow chatCore local contracts** ([#9562](https://github.com/diegosouzapw/OmniRoute/pull/9562)) — thanks @backryun
-- **[TS7] fix(types): validate Azure OpenAI base URLs** ([#9563](https://github.com/diegosouzapw/OmniRoute/pull/9563)) — thanks @backryun
-- **[TS7] fix(types): preserve sanitized tool array contracts** ([#9564](https://github.com/diegosouzapw/OmniRoute/pull/9564)) — thanks @backryun
-- **[TS7] fix(types): validate Vision Bridge combo names** ([#9565](https://github.com/diegosouzapw/OmniRoute/pull/9565)) — thanks @backryun
-- **[TS7] fix(types): preserve streaming PII choice keys** ([#9566](https://github.com/diegosouzapw/OmniRoute/pull/9566)) — thanks @backryun
-- **[TS7] test(types): use Vitest expectations in tier resolver** ([#9742](https://github.com/diegosouzapw/OmniRoute/pull/9742)) — thanks @backryun
-- **[TS7] fix(translator): preserve video URL override contracts** ([#9747](https://github.com/diegosouzapw/OmniRoute/pull/9747)) — thanks @backryun
-- **[TS7] fix(codex): preserve narrowed input arrays** ([#9748](https://github.com/diegosouzapw/OmniRoute/pull/9748)) — thanks @backryun
-- **[TS7] fix(kiro): complete cache-only usage totals** ([#9753](https://github.com/diegosouzapw/OmniRoute/pull/9753)) — thanks @backryun
-- **chore(repo): ignore Electron build output unpacked into repo root** ([#9858](https://github.com/diegosouzapw/OmniRoute/pull/9858), original [#9770](https://github.com/diegosouzapw/OmniRoute/pull/9770)) — thanks @Michael-Rocco-Goldmann
-- **test(integration): add general live-test tool for the real "default" combo + rootless wire capture** ([#9862](https://github.com/diegosouzapw/OmniRoute/pull/9862), original [#9744](https://github.com/diegosouzapw/OmniRoute/pull/9744)) — thanks @hartmark
-- **ci(test): route orphaned Vitest tests through blocking CI** ([#9875](https://github.com/diegosouzapw/OmniRoute/pull/9875), original [#9605](https://github.com/diegosouzapw/OmniRoute/pull/9605)) — thanks @MohitRawat017
-- **docs(proposals): Telegram Mini App integration feasibility analysis** ([#9906](https://github.com/diegosouzapw/OmniRoute/pull/9906), original [#9810](https://github.com/diegosouzapw/OmniRoute/pull/9810)) — thanks @benzntech
-- **chore: ignore docker-compose.override.yml** ([#9919](https://github.com/diegosouzapw/OmniRoute/pull/9919)) — thanks @lucasalx
-- **[TS7] fix(types): stabilize skill token extraction** ([#9920](https://github.com/diegosouzapw/OmniRoute/pull/9920)) — thanks @backryun
-- **docs: add quickstart code examples for Python, Node.js, PHP and cURL** ([#9922](https://github.com/diegosouzapw/OmniRoute/pull/9922)) — thanks @Hariprajwal
-- **[TS7] fix(types): narrow combo model collections** ([#9972](https://github.com/diegosouzapw/OmniRoute/pull/9972)) — thanks @backryun
-- **[TS7] fix(types): align Claude message contracts** ([#9973](https://github.com/diegosouzapw/OmniRoute/pull/9973)) — thanks @backryun
-- **[TS7] fix(types): type Copilot WebSocket construction** ([#9974](https://github.com/diegosouzapw/OmniRoute/pull/9974)) — thanks @backryun
-- **[TS7] chore(types): remove orphan combo manifest metrics** ([#9975](https://github.com/diegosouzapw/OmniRoute/pull/9975)) — thanks @backryun
-- **[TS7] fix(types): normalize stream usage before cost calculation** ([#9977](https://github.com/diegosouzapw/OmniRoute/pull/9977)) — thanks @backryun
-- **[TS7] fix(stream): collect synthesized Responses tool events** ([#9978](https://github.com/diegosouzapw/OmniRoute/pull/9978)) — thanks @backryun
-- **[TS7] fix(types): complete Responses stream failure contract** ([#9979](https://github.com/diegosouzapw/OmniRoute/pull/9979)) — thanks @backryun
-- **[TS7] fix(types): narrow chat dispatch contracts** ([#9986](https://github.com/diegosouzapw/OmniRoute/pull/9986)) — thanks @backryun
-- **[TS7] fix(types): narrow chatCore local contracts** ([#9987](https://github.com/diegosouzapw/OmniRoute/pull/9987)) — thanks @backryun
-- **[TS7] fix(types): preserve GHE Copilot executor configuration** ([#9988](https://github.com/diegosouzapw/OmniRoute/pull/9988)) — thanks @backryun
-- **[TS7] fix(types): validate Fal video result URLs** ([#9989](https://github.com/diegosouzapw/OmniRoute/pull/9989)) — thanks @backryun
-- **[TS7] fix(types): narrow Claude stream deltas** ([#9990](https://github.com/diegosouzapw/OmniRoute/pull/9990)) — thanks @backryun
-- **provider(agnes):refresh model catalog** ([#9998](https://github.com/diegosouzapw/OmniRoute/pull/9998)) — thanks @backryun
-- **docs: fix duplicated word in MCP server audit logging section** ([#10000](https://github.com/diegosouzapw/OmniRoute/pull/10000)) — thanks @TengSivtean
-- **docs: fix stale tool count (105 -> 104) in MCP server docs** ([#10002](https://github.com/diegosouzapw/OmniRoute/pull/10002)) — thanks @TengSivtean
-- **Document default behavior for ToS-flagged free-tier providers** ([#10013](https://github.com/diegosouzapw/OmniRoute/pull/10013)) — thanks @yulinlina
-- **[TS7] fix(tinycms): align executor and signer contracts** ([#10087](https://github.com/diegosouzapw/OmniRoute/pull/10087)) — thanks @backryun
-- **[TS7] fix(types): restore provider breaker predicate import** ([#10088](https://github.com/diegosouzapw/OmniRoute/pull/10088)) — thanks @backryun
-- **[TS7] ci: block new TypeScript 7 diagnostics** ([#10134](https://github.com/diegosouzapw/OmniRoute/pull/10134)) — thanks @backryun
-- **chore(repo): remove tracked local artifacts** ([#10178](https://github.com/diegosouzapw/OmniRoute/pull/10178)) — thanks @backryun
-- **maintenance — direct pushes (rollup):** release-gate and base-red repairs pushed straight to the release branch (typecheck, unit, quality-ratchet, file-size and ESLint-baseline corrections, stale assertion updates), repository hygiene (`_tasks` symlink untracking, `.source`/`.playwright-cli`/`.cbmignore` ignore entries, Electron build-output ignores, Open Collective link removal) and CI re-triggers after GitHub Actions incidents
-- **deps (rollup):** dependency bumps and lockfile maintenance across the cycle — Dependabot groups and manual CVE-driven bumps ([#9081](https://github.com/diegosouzapw/OmniRoute/pull/9081), [#9082](https://github.com/diegosouzapw/OmniRoute/pull/9082), [#9427](https://github.com/diegosouzapw/OmniRoute/pull/9427), [#9458](https://github.com/diegosouzapw/OmniRoute/pull/9458), [#9459](https://github.com/diegosouzapw/OmniRoute/pull/9459), [#9461](https://github.com/diegosouzapw/OmniRoute/pull/9461), [#9462](https://github.com/diegosouzapw/OmniRoute/pull/9462), [#9472](https://github.com/diegosouzapw/OmniRoute/pull/9472))
-- **docs/chore (rollup):** documentation, refactoring and repository-hygiene upkeep across the cycle ([#8954](https://github.com/diegosouzapw/OmniRoute/pull/8954), [#8991](https://github.com/diegosouzapw/OmniRoute/pull/8991), [#9059](https://github.com/diegosouzapw/OmniRoute/pull/9059), [#9194](https://github.com/diegosouzapw/OmniRoute/pull/9194), [#9258](https://github.com/diegosouzapw/OmniRoute/pull/9258), [#9508](https://github.com/diegosouzapw/OmniRoute/pull/9508))
-- **main-branch plumbing (rollup):** work that landed on `main` between cycles and was carried into this one — the Mergify merge-queue migration and tuning (#7168, #7179, #7216, #7220, #7225), npm-publish unblock via dynamic runner + CI build reuse (#8941), CodeQL-driven e2e mock hardening (#7559), hermetic self-ref guard (#6634, #7341), coverage-baseline tightening (#7347), Dependabot alert resolutions via npm overrides (#8067, #8070), README flag/doc-link polish (#8317), and the v3.8.49 release plumbing itself (#7076)
-- **deps:** bump the development group across 1 directory with 22 updates ([#10043](https://github.com/diegosouzapw/OmniRoute/pull/10043)) — thanks @app/dependabot
-- **deps:** bump electron from 43.2.0 to 43.3.0 in /electron ([#10042](https://github.com/diegosouzapw/OmniRoute/pull/10042)) — thanks @app/dependabot
-- **maint(release):** 45 direct pushes to the release branch with no PR ref — base-red and quality-gate repairs, i18n string completion and stream/type fixes (quality ×6, i18n ×5, deps ×3, agentrouter ×3, providers ×2, release ×2, security ×2, logging ×2)
-- **maint(repo):** 29 chore/ci/test/docs commits rolled up — quality baselines, mutation registration, CI re-triggers, doc restructure and repo hygiene (#10187, #10189, #10190, #10193, #10196, #10203, #10204, #10205, #10207, #10210, #10236, #10318)
-- **docs(auth):** distinguish dashboard sessions, `oma_live_…` Access Tokens, manage-scoped API keys, and inference keys ([#7786](https://github.com/diegosouzapw/OmniRoute/issues/7786))
-- **docs(ops):** document Kubernetes probe recommendations — TCP (or soft HTTP) liveness, HTTP `/healthz` readiness, avoid `/api/monitoring/health` as kubelet liveness ([#10297](https://github.com/diegosouzapw/OmniRoute/pull/10297)) — thanks @RaviTharuma
-- **docs(docker):** spell out that `:latest` tracks the highest **published** stable SemVer (not git `main`), and that GitOps should pin `X.Y.Z` ([#10317](https://github.com/diegosouzapw/OmniRoute/issues/10317))
-- **docs(backend):** document that memory extraction, skills injection, and token refresh share the request event loop, plus dashboard kill switches ([#10349](https://github.com/diegosouzapw/OmniRoute/issues/10349))
-- **docs(docker):** document default SQLite as single-replica / HA-unsupported, including Recreate and HEALTHCHECK session blast radius ([#10350](https://github.com/diegosouzapw/OmniRoute/issues/10350))
-- **docs(backend):** document that pre-write SQLite backups (including models.dev pricing) are throttled to once per 60 minutes and can be disabled with `DISABLE_SQLITE_AUTO_BACKUP` ([#10351](https://github.com/diegosouzapw/OmniRoute/issues/10351))
-- **fix(tests):** drain three base-reds on the release branch — the Vietnamese locale regained parity with English (6 keys added), the chatCore SSE test now asserts the comment-free default that #10539 introduced instead of the trailer it replaced, and the Antigravity cloudcode test asserts the missing-messages guard it is named for instead of a `/ok/` regex that only ever matched the "ok" inside `: x-omniroute-tokens-in` ([#10704](https://github.com/diegosouzapw/OmniRoute/pull/10704))
-- chore(security): remove the unused `enforceSecrets()` duplicate of the boot secret check and pin the live `enforceWebRuntimeEnv()` wiring with a regression test (#10775)
-- fix(quality): register GrokBuildToolCard.tsx react-hooks/set-state-in-effect suppression (dropped in #10778's uncommitted fix)
-- **docs:** Custom combos are only invoked by their exact name in the `model` field — `auto` remains a separate zero-config router, and `openrouter/auto` is a paid OpenRouter product, not an alias ([#10779](https://github.com/diegosouzapw/OmniRoute/pull/10779)) — thanks @maxmad64bis
-- chore(startup): remove `src/server-init.ts` (183 lines, never imported — the boot path is `src/instrumentation-node.ts`) and correct four `"called from server-init.ts"` comments left pointing at the dead entry point (#10780)
-- fix(quality): rebaseline file-size for #10859's own modelCapabilities.ts/commandCode.ts growth (missed at merge time)
-- **docs(openapi):** document the `GET` and `PUT` operations on `/api/combos/{id}`, and add an operation-level coverage floor so a missing verb can no longer hide behind a path that already counts as covered ([#10875](https://github.com/diegosouzapw/OmniRoute/pull/10875))
-- fix(quality): bump EXPECTED_FEATURE_FLAG_COUNT to 52 for #10889's own new flag (missed at merge time)
-- **test(db):** replace three empty `test.skip` placeholders in the critical DB-state suite with real assertions — `resetDbInstance` must swap the singleton while the on-disk row survives, the on-disk DB must open in WAL journal mode, and `db_meta` must hold the seeded `schema_version` — so a regression in any of those invariants can no longer pass as silently green ([#10906](https://github.com/diegosouzapw/OmniRoute/pull/10906))
-- **docs(docker):** document runtime RAM for coding-agent `/v1/responses` (image default 1 GiB heap is dashboard-only; 8–12 GiB heap for agents) ([#10982](https://github.com/diegosouzapw/OmniRoute/issues/10982))
-- **docs(database):** align the SQLite cache guide with the 65,536 KiB runtime default, supported 1–1,000,000 KiB range, and live Settings application behavior ([#11018](https://github.com/diegosouzapw/OmniRoute/issues/11018))
-- **docs(docker):** document N independent `DATA_DIR`s as the supported large `/v1/responses` scale-out (one V8 heap ≠ host RAM; do not `replicas>1` on one SQLite file) ([#11024](https://github.com/diegosouzapw/OmniRoute/issues/11024)) — thanks @RaviTharuma
-- fix(quality): rebaseline file-size for modelCapabilities.ts (1016->1072) drift from merged tip fixes (#11034 et al)
-- fix(quality): register `tests/unit/authz/oauth-autoimport-local-only.test.ts` in stryker `tap.testFiles` (residual of #11053)
-- chore(quality): drain two `release/v3.8.50` base-reds — refresh the drifted doc counts (159 migrations, 56 free-forever providers, 40 free-tier pools, incl. the 42 `llm.txt` locale mirrors) and move `uncloseai-noauth.test.ts` to a collected path so the UncloseAI no-auth regression guard actually runs (#11160)
-- **chore(lint):** ratchet `@typescript-eslint/no-unused-vars` scoped to `src/` + `open-sse/` + `tests/` (`args: "all"`, `_`-prefix escape hatch) and freeze the 1393 pre-existing violations via bulk suppressions — same pattern as the #7879 `toNumber` ratchet. New unused bindings now fail lint. ([#11247](https://github.com/diegosouzapw/OmniRoute/pull/11247))
-- **fix(deps):** prevent pnpm from auto-installing the unused `@lobehub/ui` peer subtree of
-  `@lobehub/icons`, keeping six unneeded packages with incompatible or unverifiable license
-  metadata out of production installs ([#11342](https://github.com/diegosouzapw/OmniRoute/pull/11342)).
-- **ci(changelog):** replace the broad removal bypass with an exact, hash-bound reconciliation ledger and bind merge-train checks to their requested release base ([#11345](https://github.com/diegosouzapw/OmniRoute/pull/11345)).
-- **docs(readme):** reconcile live v3.8.50 provider, free-tier, CLI, routing, test,
-  community, sponsor, acknowledgment, and SVG metrics with their audited source
-  denominators, including a deduplicated OmniRoute-in-Action snapshot and distinct
-  contributor rankings for merged pull requests, GitHub-attributed commits, and Git history
-  ([#11356](https://github.com/diegosouzapw/OmniRoute/pull/11356)).
-- **docs(openapi):** document the conditionally management-authenticated, same-origin `POST /api/openapi/try` proxy contract and restore the release branch's operation-coverage ratchet ([#11363](https://github.com/diegosouzapw/OmniRoute/pull/11363))
-- **fix(video-bridge):** make opt-in segment-aware sampling use one bounded structural FFmpeg pass (scene, freeze, blur, exposure, and SI/TI), preserve long trailing segments, fail open to uniform sampling, and add real-media structural-oracle, overhead, post-dedup caption-call, and false-positive evidence while holding unconfigured model quality and gain-versus-cost claims ([#11381](https://github.com/diegosouzapw/OmniRoute/pull/11381)).
-- **docs:** add an embeddings client runbook with live-verified working/broken model ids and Hindsight 0.9.1 / Memorix 1.6.0 notes — thanks @RaviTharuma
-- **chore(ci):** ignore ad-hoc `BOT_TOKEN`/`BOT_URL` in env-doc-sync (scripts/ad-hoc mesh helpers, not runtime config)
-- **test(kimi):** the Kimi background health sweep no longer draws its refresh window inside the assertion. `checkKimiWebConnectionIfNeeded` spreads the refresh over `[60, 240)` seconds before expiry so a fleet of connections does not stampede the token endpoint, and the test used a token expiring in 90 seconds and asserted that a refresh happened — which is true only when the draw lands at 90 or above, i.e. 150 of the 180 possible values. Measured: the test fails 1 run in 6 (16.7% by construction; 4 of 20 local runs), and it is what the Node 26 nightly hit and reported as a Node-compat break (#11361). The spread is now `defaultKimiRefreshJitterSec()` and the window is injectable as `jitterSecFn`, so the test decides it instead of rolling for it; production behaviour is unchanged. Cases were added for a token outside the window and for the default spread's range.
-- chore(test): regenerate the provider/translate-path golden snapshot to reflect freebuff (#10531), fixing a base-red left by that merge (freebuff/freeinference key ordering only, no value changes).
-- **chore(release):** resync the v3.8.50 provider and CLI catalogs, register the existing ChatCore mutation-coverage test, and document the local ZCode handshake identifier so the release quality gates reflect the current tree without changing ratchet baselines.
-- **fix(ci):** route `open-sse/handlers/imageGeneration/providers/geminiWeb.ts`'s b64_json
-  download-failure message through `sanitizeErrorMessage()` instead of embedding a raw
-  `err.message`, clearing the `check:error-helper` base-red on `release/v3.8.50` (#9985).
-- **fix(ci):** drain three more base-reds on `release/v3.8.50` (#9985). ESLint was reporting
-  219 errors locally (vs. 25 in the last CI run) — all from `react-hooks/set-state-in-effect`,
-  `react-hooks/preserve-manual-memoization`, `react-hooks/immutability`,
-  `react-hooks/static-components`, `react-hooks/refs` and `react-hooks/purity`, six React
-  Compiler lint rules that `eslint-plugin-react-hooks` v7 turns on by default and that were
-  never frozen in `config/quality/eslint-suppressions.json` after the dependency bump. Froze
-  the pre-existing violations for those six rules via ESLint's native
-  `--suppress-rule`/`--suppressions-location` mechanism (the same pattern already used for
-  `@next/next/no-location-assign-relative-destination`) — no application code changed, no rule
-  disabled, only genuinely-new violations stay blocking. `check:dead-code` was at 418 against a
-  415 baseline: removed the unused `src/lib/quota/providerCapabilities.ts` file and the unused
-  `ProviderQuotaMonitor` interface in `providerQuotaTelemetry.ts` (both dead since PR #10148,
-  2026-08-18, confirmed via `grep`/knip cross-reference), landing at 416; the residual +1 could
-  not be attributed to a single recent commit after checking every dead-list entry touched
-  since the 2026-08-14 baseline measurement, so it is rebaselined with the investigation
-  recorded in `quality-baseline.json`. `tests/unit/autoCombo/tieredRotation.test.ts`'s
-  "rotates across all 43 Cerebras connection IDs" case was hitting vitest's 5000ms default
-  timeout on a 200-iteration synchronous `selectProvider()` loop under shared-devbox
-  contention (load average 40-60+ observed) — widened its explicit timeout to 20000ms; the
-  assertion itself is unchanged.
-- **fix(tests):** drain two base-reds on the release branch — `auto/glm` now expects the Cloudflare AI Playground backend (its registry advertises `zai-org/glm-5.2` and `zai-org/glm-4.7-flash`, so it belongs in the family pool by the same rule already documented for `auggie`, `devin-cli-agentic` and `zcode`), and the ESLint gate is green again after the GitLab executor test dropped its five `as any` casts for a declared response shape and the CLI OAuth suppression count caught up with the two casts #10491 added.
-- **fix(tests):** realign the two `stream-utils` passthrough cases that still asserted the pre-#10017 SSE framing — the event-boundary case declares the OpenAI Responses client format it actually exercises, and the metadata case now pins that surviving lines stay inside one event instead of expecting the `:`/`id:` control lines that #10473 stopped forwarding to every client format.
-- **fix(tests):** drain several base-reds on `release/v3.8.50` (#9985) that were all instances
-  of the same pattern — a legitimate product change landed without updating the test that
-  asserted the old behavior: `tests/unit/glm-provider-model-import-route.test.ts` (12 tests)
-  and `tests/unit/model-sync-route.test.ts` (2 tests) predate #10603's "upstream model sync is
-  opt-in and manual overrides are preserved" change; `tests/unit/antigravity-model-aliases.test.ts`
-  predated #10537 retiring the collapsed `gemini-3.7-flash` alias in favor of its three tiered
-  ids. Also fixes a real data drift in `open-sse/config/freeModelCatalog.data.ts` (the `qwen-web`
-  free-catalog entry still pointed at the retired `qwen3.8-max-preview` id instead of the
-  current `qwen3.8-max`), corrects the zh-TW `providers.autoFetchModelsTooltip` string to the
-  glossary-canonical 快取 instead of 緩存, and removes an unused default export from
-  `src/lib/oauth/providers/zed-hosted.ts` (the named export already covers every consumer) to
-  shave one symbol off the `check:dead-code` ratchet regression.
-- **chore(release):** synchronize migration-count documentation and document the opt-in `PROXY_LOG_INCLUDE_IPS` logging flag so the v3.8.50 quality gates match the release tree.
-- fix(i18n): translate the 14 `providers.harImport*` keys into Vietnamese (parity gap left by #11069)
-
-<!-- reconciliation pass 2 (Phase 0a.1): commits that landed in the cycle without a bullet -->
-
-- **fix(release):** release pre-flight and base-red drains for v3.8.50 — the build-breaking `localDb` import, stale provider docs and orphaned suppressions ([#11038](https://github.com/diegosouzapw/OmniRoute/issues/11038)); the docs/golden/GLM cluster with a masked assert restored; the volcengine vision metadata and antigravity BYOP contract pair; the #10534 quota-recovery restoration plus volcengine connect-body validation; the onnxruntime dependency contract test; the post-sweep base regressions; the remaining Adobe and typecheck gates; the base-red tail after the latest root lift ([#10964](https://github.com/diegosouzapw/OmniRoute/issues/10964) — thanks @backryun); the agent-skills catalog tests and base quality reds (thanks @adevwithpurpose); a stray conflict leftover in `managedModelImport` was dropped ([#11259](https://github.com/diegosouzapw/OmniRoute/issues/11259) — thanks @hartmark); and the sweep-stale summary counting matches by their real category ([#11338](https://github.com/diegosouzapw/OmniRoute/issues/11338) — thanks @pacocartones)
-- **fix(quality):** quality-gate maintenance — the two Fast Quality Gates base-reds ([#11438](https://github.com/diegosouzapw/OmniRoute/issues/11438)) and the three inventory/coverage base-reds were drained; the gate reports the real failure line and stops double-counting `ci.yml` gates ([#11321](https://github.com/diegosouzapw/OmniRoute/issues/11321) — thanks @pacocartones); file-size baselines were rebaselined for `modelCapabilities.ts`, `imageRegistry.ts`, `AddApiKeyModal` and `combo-routing-engine.test.ts` drift (thanks @hartmark, @adevwithpurpose, @wgordon17); a stale ESLint suppression for `search.ts` was pruned and the `eslintWarnings` baseline tightened to the gate's real measurement (0); the capability gate frozen cap was updated; and the gateway duplication between `chatanywhere` and `regolo` was resolved to unblock typecheck (thanks @backryun)
-- **fix(tests):** stale-assertion and isolation repairs — the compression/kiro/memory/i18n base-red mini-cluster ([#11306](https://github.com/diegosouzapw/OmniRoute/issues/11306)); the auto/GLM family pool and ESLint gate pair ([#10726](https://github.com/diegosouzapw/OmniRoute/issues/10726) — thanks @MichaelYcJo); the `translate-path` golden snapshot for `hailuo-web` ([#11161](https://github.com/diegosouzapw/OmniRoute/issues/11161) — thanks @rqzbeh); the provider count realigned to 230 after a merge-train collision (thanks @hartmark); the stale `ALL_ACCOUNTS_INACTIVE` → `ALL_TARGETS_SKIPPED` assertions and six pre-existing typecheck errors (thanks @wgordon17); an exclusive-connection-lease uniqueness test made self-contained ([#11341](https://github.com/diegosouzapw/OmniRoute/issues/11341)); the DB singleton reset made to survive the full suite, un-skipping three DB-state tests ([#11327](https://github.com/diegosouzapw/OmniRoute/issues/11327)); the CLI suite made to pass on Windows ([#11240](https://github.com/diegosouzapw/OmniRoute/issues/11240)); the Kimi refresh window no longer drawn inside its own assertion ([#11380](https://github.com/diegosouzapw/OmniRoute/issues/11380)); the GLM absolute-ISO-reset regression test given a frozen clock; spawned router-eval CLI children given an explicit `DATA_DIR`; the agent-card route handlers called with a real `NextRequest`; queued call-log writes awaited ([#10683](https://github.com/diegosouzapw/OmniRoute/issues/10683)); the aihorde client browser bundles guarded ([#10682](https://github.com/diegosouzapw/OmniRoute/issues/10682)); the env precondition of the CCR/MCP principal tests declared explicitly ([#10689](https://github.com/diegosouzapw/OmniRoute/issues/10689)); the client-bundle guard widened to every `"use client"` entry point ([#11135](https://github.com/diegosouzapw/OmniRoute/issues/11135), [#10700](https://github.com/diegosouzapw/OmniRoute/issues/10700)); standalone fixture paths resolved from file URLs ([#10451](https://github.com/diegosouzapw/OmniRoute/issues/10451)); and the services adoption tests aligned with the opt-in contract from #11040 ([#11147](https://github.com/diegosouzapw/OmniRoute/issues/11147))
-- **fix(ci):** Windows packaged-smoke process trees are cleaned up ([#10453](https://github.com/diegosouzapw/OmniRoute/issues/10453) — thanks @backryun); the coverage-pack and unit gate regressions were cleared; the OpenCode plugin CI tracks the active release branch and its combo-id fixture was aligned ([#11301](https://github.com/diegosouzapw/OmniRoute/issues/11301)); the ad-hoc `BOT_TOKEN`/`BOT_URL` env-doc-sync ignore was added, reverted and then locked by a test ([#10828](https://github.com/diegosouzapw/OmniRoute/issues/10828)); and the Electron release dependency setup was streamlined ([#10325](https://github.com/diegosouzapw/OmniRoute/issues/10325))
-- **perf(electron):** desktop packaging and startup pass — the Next standalone is built once and natives hydrated per leg ([#10390](https://github.com/diegosouzapw/OmniRoute/issues/10390)), `better-sqlite3` v13 Node-API prebuilds are verified instead of rebuilt from source ([#10367](https://github.com/diegosouzapw/OmniRoute/issues/10367)), optional ML/browser dependencies ship as installable packs ([#10382](https://github.com/diegosouzapw/OmniRoute/issues/10382)), authoring docs are pruned from the packages ([#10359](https://github.com/diegosouzapw/OmniRoute/issues/10359)), hidden-start renderer creation is deferred ([#10327](https://github.com/diegosouzapw/OmniRoute/issues/10327)) with an option to unload the renderer on close ([#10328](https://github.com/diegosouzapw/OmniRoute/issues/10328)), and lightweight readiness polling is bounded ([#10324](https://github.com/diegosouzapw/OmniRoute/issues/10324)) — thanks @backryun
-- **perf(providers):** provider schema validation is lazy and on demand, cutting startup heap ([#11334](https://github.com/diegosouzapw/OmniRoute/issues/11334), [#11220](https://github.com/diegosouzapw/OmniRoute/issues/11220))
-- **refactor(sse):** executor lookup routes through a runtime `ExecutorRegistry` (R0.3) ([#10633](https://github.com/diegosouzapw/OmniRoute/issues/10633)); the six TLS client providers were consolidated into a shared factory with wrappers ([#10910](https://github.com/diegosouzapw/OmniRoute/issues/10910) — thanks @oyi77); the Codex virtual quota pools were isolated ([#8367](https://github.com/diegosouzapw/OmniRoute/issues/8367) — thanks @xz-dev); the xAI authentication entry point was unified ([#10201](https://github.com/diegosouzapw/OmniRoute/issues/10201)); duplicate `opencode-zen`/`opencode-go` model entries were deduped ([#11051](https://github.com/diegosouzapw/OmniRoute/issues/11051)); the Radar catalog MCP tool was modularized; and the Video Bridge broker extract route moved to the structured pino logger
-- **refactor(dashboard):** custom provider quota keys are formatted into title-cased labels ([#11188](https://github.com/diegosouzapw/OmniRoute/issues/11188)), and the Add API Key modal's Enter handler mirrors the check button's disabled state ([#11156](https://github.com/diegosouzapw/OmniRoute/issues/11156))
-- **chore(security):** the self-hosted operator security tier and its blockers were integrated ([#10952](https://github.com/diegosouzapw/OmniRoute/issues/10952) — thanks @arminanton), and test fixtures were sanitized with developer `.env` guidance plus a gitleaks pass ([#10411](https://github.com/diegosouzapw/OmniRoute/issues/10411) — thanks @blarovse)
-- **chore(deps):** Dependabot batches landed across the cycle — production and development groups ([#10931](https://github.com/diegosouzapw/OmniRoute/issues/10931), [#10932](https://github.com/diegosouzapw/OmniRoute/issues/10932), [#10625](https://github.com/diegosouzapw/OmniRoute/issues/10625), [#10626](https://github.com/diegosouzapw/OmniRoute/issues/10626), [#10403](https://github.com/diegosouzapw/OmniRoute/issues/10403)), Electron 43.3.0 → 43.4.0 ([#10622](https://github.com/diegosouzapw/OmniRoute/issues/10622)) and `github/codeql-action` 4.37.4 → 4.37.7 ([#10405](https://github.com/diegosouzapw/OmniRoute/issues/10405), [#10406](https://github.com/diegosouzapw/OmniRoute/issues/10406), [#10407](https://github.com/diegosouzapw/OmniRoute/issues/10407), [#10928](https://github.com/diegosouzapw/OmniRoute/issues/10928), [#10929](https://github.com/diegosouzapw/OmniRoute/issues/10929), [#10930](https://github.com/diegosouzapw/OmniRoute/issues/10930)). Security bumps also went out directly: nanoid, DOMPurify, mermaid and js-yaml, plus transitive lifts closing 20 and then 6 more Dependabot CVE alerts
-- **fix(deps):** `@atjsh/llmlingua-2` was upgraded to 2.0.5 and `@tensorflow/tfjs` dropped ([#10610](https://github.com/diegosouzapw/OmniRoute/issues/10610) — thanks @jonlwheat2-gif), and `onnxruntime-node` is pinned to the exact version `@huggingface/transformers` requires ([#10543](https://github.com/diegosouzapw/OmniRoute/issues/10543) — thanks @dcox79)
-- **docs:** documentation pass across the cycle — a VS Code Copilot Chat guide with the `/v1/models` prefix modes ([#10648](https://github.com/diegosouzapw/OmniRoute/issues/10648)) and its platform-table entry ([#10512](https://github.com/diegosouzapw/OmniRoute/issues/10512)); an embeddings client runbook for Gemini 2 and Jina omni ([#10569](https://github.com/diegosouzapw/OmniRoute/issues/10569)); a free-provider rate-limiting troubleshooting guide ([#10112](https://github.com/diegosouzapw/OmniRoute/issues/10112)); the compression output-style catalog and its extension point ([#10649](https://github.com/diegosouzapw/OmniRoute/issues/10649)); Docker `latest` tag semantics ([#10816](https://github.com/diegosouzapw/OmniRoute/issues/10816)) and SQLite single-replica HA limits ([#10817](https://github.com/diegosouzapw/OmniRoute/issues/10817)); the distinction between access tokens, API keys and management credentials ([#10823](https://github.com/diegosouzapw/OmniRoute/issues/10823)); throttled pre-write SQLite backups ([#10824](https://github.com/diegosouzapw/OmniRoute/issues/10824)); the memory/skills/token-refresh event-loop cost ([#10825](https://github.com/diegosouzapw/OmniRoute/issues/10825)); runtime RAM for the coding-agent `/v1/responses` path ([#10983](https://github.com/diegosouzapw/OmniRoute/issues/10983)); `DEFAULT_RATE_LIMIT_PER_DAY` unset meaning unlimited ([#11031](https://github.com/diegosouzapw/OmniRoute/issues/11031)); the management-auth requirement on the spec endpoint ([#11299](https://github.com/diegosouzapw/OmniRoute/issues/11299)); embedded services explained for beginners ([#11204](https://github.com/diegosouzapw/OmniRoute/issues/11204)); the ChatGPT Web session credential guide with a canonical Cookie Editor install link; the Radar Intel/CLI contract, guided combos, supporter key recovery and end-to-end activation; the Video Bridge fusion telemetry, drill-down byte budget, cache-key dimensions and contact sheets; the OpenCode 128k context fallback JSDoc ([#11157](https://github.com/diegosouzapw/OmniRoute/issues/11157)); and the post-relay CLI documentation audit (run/configure surface, Gemini launcher, smoke harness). Drifted counts were corrected and the free-forever number gated ([#10433](https://github.com/diegosouzapw/OmniRoute/issues/10433)), the accepted doc-drift backlog closed, and the provider count synced to 343
-- **docs(i18n):** localization contributions — a complete Persian user guide ([#11254](https://github.com/diegosouzapw/OmniRoute/issues/11254)), improved and completed Turkish documentation ([#11237](https://github.com/diegosouzapw/OmniRoute/issues/11237)), the Italian README restored ([#11246](https://github.com/diegosouzapw/OmniRoute/issues/11246)), a Farsi README ([#10777](https://github.com/diegosouzapw/OmniRoute/issues/10777) — thanks @farshidrezaei), a `SETUP_GUIDE.md` correction ([#10490](https://github.com/diegosouzapw/OmniRoute/issues/10490) — thanks @realize000), a `python_requests.py` example fix ([#10731](https://github.com/diegosouzapw/OmniRoute/issues/10731) — thanks @pandaaaa1990), and a retranslation of the CLI reference and integrations guide across all 42 locales
-- **chore(repo):** repository hygiene — the self-referential `_tasks` symlink was untracked and `.gitignore` anchored so a `_tasks` symlink can never be tracked again, `.source/dynamic.ts`, `.source`, `/output/` and the Playwright CLI artifact directory were ignored, an initial `.cbmignore` was added for codebase-memory indexing, unused `.source/dynamic.ts` and `source.config.mjs` files were removed, the stray unresolved conflict marker in `ENVIRONMENT.md` was cleaned up, and the Open Collective sponsorship link was removed from the README
-- **chore(release):** localized `llm.txt` mirrors and the v3.8.50 base quality docs were synchronized, and the 363 `changelog.d` fragments were aggregated into this section
-- **fix(ci):** the pack-artifact provenance gate now checks the branch under test instead of `origin/main` ([#8875](https://github.com/diegosouzapw/OmniRoute/pull/8875)) — the guard added for [#10427](https://github.com/diegosouzapw/OmniRoute/issues/10427) is correct at publish time (that workflow runs on `main`), but in a `pull_request` context the head is by construction not an ancestor of `main` and the shallow checkout never fetches it, so the probe always answered false and the job failed 100% of the time. It became visible only once it stopped being cancelled behind Build. Pre-merge it resolves the ref from `refs/pull/<N>/head`, which exists on origin even for fork PRs.
-- **test(dashboard):** the proxy-registry e2e smoke flow opens the toolbar's "More actions" overflow menu before clicking bulk assign ([#8875](https://github.com/diegosouzapw/OmniRoute/pull/8875)) — [#9870](https://github.com/diegosouzapw/OmniRoute/pull/9870) moved the action into that menu, which only renders its items while open, so the locator never resolved and the test burned its full 180 s budget. Every existing assertion is unchanged.
-- **test(api):** the `/v1/models` e2e check accepts the auth gate introduced by [#9320](https://github.com/diegosouzapw/OmniRoute/pull/9320) ([#8875](https://github.com/diegosouzapw/OmniRoute/pull/8875)) — the catalog now requires auth whenever management auth is configured, and the harness boots with `INITIAL_PASSWORD` set, so the endpoint had been answering 401 since 2026-08-04 and the check was red the whole time, hidden behind a cancelled job. It now mirrors the sibling `/api/providers` check: assert the catalog shape when the catalog is served, otherwise pin the gate by status **and** error type so an unrelated 401 cannot pass for the deliberate one.
-- **chore(quality):** refreshed the combos-page ESLint suppressions after the manual-model restore ([#8875](https://github.com/diegosouzapw/OmniRoute/pull/8875)) — three `no-unused-vars` suppressions existed only because #8285 had deleted the JSX consuming that state; with the block back they are live again, and a stale suppression makes ESLint exit 2, which is what actually turned the Lint job red. The 7 `react-hooks/set-state-in-effect` plus 1 `react-hooks/immutability` errors in the same file are pre-existing (reproducible on the file's `091e2ba4da` content) and surfaced only because touching the file evicted it from the restored `.eslintcache`; they are frozen here and tracked separately rather than refactored mid-release.
-
-
-### 🙌 Contributors
-
-Thanks to everyone whose work landed in v3.8.50:
-
-| Contributor | PRs / Issues |
-| --- | --- |
-| [@AbdullahFageeh](https://github.com/AbdullahFageeh) | #9087 |
-| [@abhijeetnardele24-hash](https://github.com/abhijeetnardele24-hash) | #10498 |
-| [@Abhishek4512009](https://github.com/Abhishek4512009) | #10494 |
-| [@acc0mplish](https://github.com/acc0mplish) | #10732, #10948 |
-| [@adevwithpurpose](https://github.com/adevwithpurpose) | #9790, #10118, #10222, #10800, #10834, #10835, #10836, #10882 |
-| [@adrianojiu](https://github.com/adrianojiu) | #8438 |
-| [@agisota](https://github.com/agisota) | #9837 |
-| [@AgnesRiber](https://github.com/AgnesRiber) | #9718, #9976 |
-| [@ahmet-cetinkaya](https://github.com/ahmet-cetinkaya) | #8878 |
-| [@AIB1TAL0S](https://github.com/AIB1TAL0S) | #9284 |
-| [@AlanSyue](https://github.com/AlanSyue) | direct commit / report |
-| [@alex-jordan547](https://github.com/alex-jordan547) | #9235, #9245, #9813 |
-| [@aliyosufi](https://github.com/aliyosufi) | #11159 |
-| [@amartinawi](https://github.com/amartinawi) | #10090, #10091, #10092, #10097, #10101 |
-| [@An0nym0us92](https://github.com/An0nym0us92) | #11394 |
-| [@AndrianBalanescu](https://github.com/AndrianBalanescu) | #8888, #8889, #8890, #8891, #8892, #8893, #8894, #8895, #11081, #11082 |
-| [@AnhLead](https://github.com/AnhLead) | #9722 |
-| [@aniketshukla1](https://github.com/aniketshukla1) | #9148 |
-| [@Anjielon](https://github.com/Anjielon) | #8776 |
-| [@anudeepadi](https://github.com/anudeepadi) | #10288 |
-| [@apoapostolov](https://github.com/apoapostolov) | #8916 |
-| [@app](https://github.com/app) | #10042, #10043 |
-| [@arafatkatze](https://github.com/arafatkatze) | #10706 |
-| [@ARC345](https://github.com/ARC345) | #9628, #10050, #10051 |
-| [@arminanton](https://github.com/arminanton) | #10933, #10952, #11166 |
-| [@aron-intframe](https://github.com/aron-intframe) | #10459 |
-| [@artickc](https://github.com/artickc) | #8571, #8578, #8791, #8843, #8870, #8927, #8974, #9097, #9255, #9549 |
-| [@Arul-](https://github.com/Arul-) | #9761 |
-| [@asorourx](https://github.com/asorourx) | #11036 |
-| [@AStupidBear](https://github.com/AStupidBear) | #10180, #11385 |
-| [@azzaouiomar19-sketch](https://github.com/azzaouiomar19-sketch) | #10394 |
-| [@b1nhm1nh](https://github.com/b1nhm1nh) | direct commit / report |
-| [@backryun](https://github.com/backryun) | #8228, #8451, #8627, #8809, #8818, #9084, #9086, #9090, #9091, #9092, #9093, #9114, #9119, #9120, #9122, #9135, #9136, #9137, #9138, #9139, #9141, #9561, #9562, #9563, #9564, #9565, #9566, #9742, #9747, #9748, #9751, #9753, #9755, #9791, #9792, #9793, #9795, #9796, #9797, #9798, #9920, #9972, #9973, #9974, #9975, #9977, #9978, #9979, #9984, #9986, #9987, #9988, #9989, #9990, #9998, #10087, #10088, #10134, #10175, #10178, #10195, #10254, #10255, #10256, #10257, #10258, #10324, #10339, #10453, #10464, #10483, #10637, #10964 |
-| [@Benson-mk](https://github.com/Benson-mk) | #8369 |
-| [@benzntech](https://github.com/benzntech) | #9810, #9812, #9939, #10124, #10126, #10458 |
-| [@Bl0ck154](https://github.com/Bl0ck154) | #9231 |
-| [@blackwell-systems](https://github.com/blackwell-systems) | #10807 |
-| [@blarovse](https://github.com/blarovse) | #10411 |
-| [@bortolidiego](https://github.com/bortolidiego) | #10058 |
-| [@branben](https://github.com/branben) | #9940, #10575 |
-| [@Chewji9875](https://github.com/Chewji9875) | #9257, #9420, #9821, #9994, #10116, #10160, #10305, #10376 |
-| [@chirag127](https://github.com/chirag127) | #6674, #10071 |
-| [@chloeassistant](https://github.com/chloeassistant) | #9675, #9746 |
-| [@configurowebmax](https://github.com/configurowebmax) | #8877 |
-| [@corefusiion](https://github.com/corefusiion) | #8285 |
-| [@costaeder](https://github.com/costaeder) | #8626, #8629, #8630 |
-| [@cryptiklemur](https://github.com/cryptiklemur) | #10684, #10685 |
-| [@csoftware-arigpt](https://github.com/csoftware-arigpt) | #3440 |
-| [@DaDecky](https://github.com/DaDecky) | direct commit / report |
-| [@danscMax](https://github.com/danscMax) | #8634 |
-| [@DarkEsteves](https://github.com/DarkEsteves) | #10250 |
-| [@dcox79](https://github.com/dcox79) | #10543 |
-| [@ddarkr](https://github.com/ddarkr) | #9035, #9036, #10177 |
-| [@Dingding-leo](https://github.com/Dingding-leo) | #7987, #8640, #8678, #8704, #8774, #8790, #8808, #8817 |
-| [@DinonowDev](https://github.com/DinonowDev) | #8804 |
-| [@dionjoshualobo](https://github.com/dionjoshualobo) | #9721 |
-| [@dpozimski](https://github.com/dpozimski) | #10253 |
-| [@Dragost](https://github.com/Dragost) | #8339 |
-| [@dsitmilis](https://github.com/dsitmilis) | direct commit / report |
-| [@echoriver89](https://github.com/echoriver89) | #10717 |
-| [@Egorich-print](https://github.com/Egorich-print) | #9001, #9020, #9058, #10881, #10887, #11097 |
-| [@ekinnee](https://github.com/ekinnee) | #11307 |
-| [@electrumguy](https://github.com/electrumguy) | #10774, #11149 |
-| [@engmarcosjr](https://github.com/engmarcosjr) | #9993 |
-| [@epsilonode](https://github.com/epsilonode) | #8871 |
-| [@ervareza](https://github.com/ervareza) | direct commit / report |
-| [@excessivechaos](https://github.com/excessivechaos) | #10062, #10138, #10552, #10883, #10884, #10907, #11179 |
-| [@fajarhide](https://github.com/fajarhide) | #9191, #9198 |
-| [@farshidrezaei](https://github.com/farshidrezaei) | #10777 |
-| [@fenix007](https://github.com/fenix007) | #9618, #10016 |
-| [@freudantunes](https://github.com/freudantunes) | #10623 |
-| [@Gecky2102](https://github.com/Gecky2102) | #9280 |
-| [@geek007git](https://github.com/geek007git) | #10441 |
-| [@ggdayup](https://github.com/ggdayup) | #10199, #11113, #11114, #11375 |
-| [@Gi99lin](https://github.com/Gi99lin) | #10342 |
-| [@giauphan](https://github.com/giauphan) | #10392 |
-| [@Gioxaa](https://github.com/Gioxaa) | #9162, #9171 |
-| [@HaoNgo232](https://github.com/HaoNgo232) | direct commit / report |
-| [@Hariprajwal](https://github.com/Hariprajwal) | #9922 |
-| [@harkaranbrar7](https://github.com/harkaranbrar7) | #10281 |
-| [@hartmark](https://github.com/hartmark) | #9635, #9704, #9711, #9712, #9727, #9734, #9735, #9738, #9741, #9744, #9745, #9822, #10025, #10034, #10037, #10038, #10041, #10121, #10217, #10262, #10263, #10330, #10331, #11259 |
-| [@Hdiaktoros](https://github.com/Hdiaktoros) | #8930 |
-| [@HectorBernstorff](https://github.com/HectorBernstorff) | direct commit / report |
-| [@HellFiveOsborn](https://github.com/HellFiveOsborn) | #9248 |
-| [@herjarsa](https://github.com/herjarsa) | #9714, #9816, #9937, #9946, #10128, #10456 |
-| [@hgaib](https://github.com/hgaib) | #10722 |
-| [@horacecar](https://github.com/horacecar) | #7679 |
-| [@HouMinXi](https://github.com/HouMinXi) | #8886, #8904, #8905, #8976, #8984, #9079, #9106, #9207, #9242, #9328, #9340, #9342, #9351, #9365, #9380, #9381, #9392, #9449, #9482, #9483, #9509, #9510, #9572, #9631, #9634, #9695, #9929, #10457, #10475, #10525, #10529, #10573, #10663, #10846, #11084, #11139, #11140, #11141, #11386, #11418 |
-| [@hppsc1215](https://github.com/hppsc1215) | #8970 |
-| [@Hsia97](https://github.com/Hsia97) | #10810 |
-| [@hydraxman](https://github.com/hydraxman) | #10137, #10572 |
-| [@Iammilansoni](https://github.com/Iammilansoni) | #9353, #9397 |
-| [@ignamiranda](https://github.com/ignamiranda) | #11206 |
-| [@ikelvingo](https://github.com/ikelvingo) | #8591, #8872, #9053 |
-| [@infinit-X](https://github.com/infinit-X) | #9095 |
-| [@InkshadeWoods](https://github.com/InkshadeWoods) | #10733 |
-| [@isaaclb98](https://github.com/isaaclb98) | #9730 |
-| [@jackjinke](https://github.com/jackjinke) | #9556, #9601, #10005, #10045, #10248, #10533, #10540, #10574, #11041 |
-| [@jacobsparts](https://github.com/jacobsparts) | #11399, #11400, #11402 |
-| [@jax-novita](https://github.com/jax-novita) | #8913 |
-| [@jeff-alves](https://github.com/jeff-alves) | #10221 |
-| [@jeyhunfaslanov](https://github.com/jeyhunfaslanov) | #10259 |
-| [@jhordanjw123](https://github.com/jhordanjw123) | #8736 |
-| [@jktan0504](https://github.com/jktan0504) | #9025 |
-| [@joachimBrindeau](https://github.com/joachimBrindeau) | #9200 |
-| [@jonlwheat2-gif](https://github.com/jonlwheat2-gif) | #10610, #10709, #11194 |
-| [@JoshimOfficial](https://github.com/JoshimOfficial) | #9011 |
-| [@jowimila](https://github.com/jowimila) | #9325 |
-| [@JxnLexn](https://github.com/JxnLexn) | #8933, #8940, #8944, #8949, #10422, #10608 |
-| [@Kaedo17](https://github.com/Kaedo17) | #8922 |
-| [@KaspaPulse](https://github.com/KaspaPulse) | #10362 |
-| [@khoazero123](https://github.com/khoazero123) | #9272 |
-| [@killmonger2317-coder](https://github.com/killmonger2317-coder) | #10445 |
-| [@KittisakT](https://github.com/KittisakT) | #9423 |
-| [@Kizuno18](https://github.com/Kizuno18) | #10803 |
-| [@KooshaPari](https://github.com/KooshaPari) | #7329 |
-| [@kriptoburak](https://github.com/kriptoburak) | #10854 |
-| [@krishna3554](https://github.com/krishna3554) | #10620, #10855 |
-| [@lamchun1110](https://github.com/lamchun1110) | #10372, #10397 |
-| [@larin-vas](https://github.com/larin-vas) | #9828 |
-| [@lazysaltyfish](https://github.com/lazysaltyfish) | direct commit / report |
-| [@LeonG606](https://github.com/LeonG606) | #9457 |
-| [@linhdmn](https://github.com/linhdmn) | #10980, #11085, #11214, #11274 |
-| [@Llliao1113](https://github.com/Llliao1113) | #8921 |
-| [@lucasalx](https://github.com/lucasalx) | #9919 |
-| [@lucasmellos](https://github.com/lucasmellos) | #8925 |
-| [@lukiod](https://github.com/lukiod) | #8828 |
-| [@luoyide](https://github.com/luoyide) | direct commit / report |
-| [@maci0](https://github.com/maci0) | #11279 |
-| [@mad-gooze](https://github.com/mad-gooze) | #9052 |
-| [@maisdesign](https://github.com/maisdesign) | #8858 |
-| [@marcelokarval](https://github.com/marcelokarval) | #11397 |
-| [@marchlhw](https://github.com/marchlhw) | #9050 |
-| [@marcs7](https://github.com/marcs7) | #11180 |
-| [@matiasbaglieri](https://github.com/matiasbaglieri) | #9707 |
-| [@maxmad64bis](https://github.com/maxmad64bis) | #9150, #9246, #9291, #9414, #10278, #10402, #10652, #10662, #10664, #10694, #10769, #10770, #10779, #10876, #10885, #10974, #10978, #11008, #11009, #11047, #11116, #11129, #11130, #11133, #11151, #11162, #11252 |
-| [@McLuck](https://github.com/McLuck) | #8914 |
-| [@megamen32](https://github.com/megamen32) | #10184 |
-| [@MeRezaRezaei](https://github.com/MeRezaRezaei) | #10174, #10614, #10944, #11042, #11045 |
-| [@Michael-Rocco-Goldmann](https://github.com/Michael-Rocco-Goldmann) | #9770, #9773, #9777, #9787 |
-| [@MichaelYcJo](https://github.com/MichaelYcJo) | #8244, #10725, #10726 |
-| [@Minamaged18](https://github.com/Minamaged18) | #11269 |
-| [@minhlongs](https://github.com/minhlongs) | #10805 |
-| [@minhnhat166](https://github.com/minhnhat166) | direct commit / report |
-| [@MohitRawat017](https://github.com/MohitRawat017) | #8718, #8772, #9605 |
-| [@Momen4444](https://github.com/Momen4444) | #9612 |
-| [@MrShitFox](https://github.com/MrShitFox) | #9826 |
-| [@mtb-ninja](https://github.com/mtb-ninja) | #10114 |
-| [@MumuTW](https://github.com/MumuTW) | #8839 |
-| [@mvanhorn](https://github.com/mvanhorn) | #9542 |
-| [@mymusicmyspace](https://github.com/mymusicmyspace) | #10965 |
-| [@Mynacol](https://github.com/Mynacol) | #9733 |
-| [@NahuSaruf](https://github.com/NahuSaruf) | #10545 |
-| [@Neuron-Mr-White](https://github.com/Neuron-Mr-White) | #10228, #10230, #10957, #11378 |
-| [@nguyenha935](https://github.com/nguyenha935) | #9044, #9215 |
-| [@nordz0r](https://github.com/nordz0r) | #10170 |
-| [@nosolosoft](https://github.com/nosolosoft) | #8900 |
-| [@ntdat812](https://github.com/ntdat812) | #10843, #10853, #10857, #10858, #10860, #10862, #10868, #10935, #11004, #11374, #11376, #11377 |
-| [@ntdatt812](https://github.com/ntdatt812) | #10715, #11076 |
-| [@octo-patch](https://github.com/octo-patch) | #10650 |
-| [@ofonseca-pyming](https://github.com/ofonseca-pyming) | #11297 |
-| [@oyi77](https://github.com/oyi77) | #8299, #8752, #9158, #9818, #10910, #10942 |
-| [@pacocartones](https://github.com/pacocartones) | #10216, #10673, #11059, #11193, #11199, #11238, #11241, #11321, #11322, #11332, #11338 |
-| [@pandaaaa1990](https://github.com/pandaaaa1990) | #10731 |
-| [@phatchau036](https://github.com/phatchau036) | #10517 |
-| [@phuongddx](https://github.com/phuongddx) | #11415 |
-| [@PixmaNts](https://github.com/PixmaNts) | #9432 |
-| [@pizzav-xyz](https://github.com/pizzav-xyz) | #9077 |
-| [@Poid-ZA](https://github.com/Poid-ZA) | #9467 |
-| [@Prudhvivuda](https://github.com/Prudhvivuda) | #8807, #9014, #9015, #9016 |
-| [@pucedoteth](https://github.com/pucedoteth) | #10607 |
-| [@qianze0628](https://github.com/qianze0628) | #9038 |
-| [@rafacpti23](https://github.com/rafacpti23) | #11207, #11213 |
-| [@raflyazf](https://github.com/raflyazf) | direct commit / report |
-| [@Rahulsharma0810](https://github.com/Rahulsharma0810) | #8961, #10872 |
-| [@RaviTharuma](https://github.com/RaviTharuma) | #10055, #10297, #10307, #10344, #10352, #10488, #10565, #10566, #10568, #10584, #10771, #10814, #10818, #10820, #10821, #10822, #10827, #10847, #10971, #10979, #10981, #11014, #11015, #11016, #11017, #11020, #11024, #11314, #11318, #11320 |
-| [@realize000](https://github.com/realize000) | #10490 |
-| [@redzrush101](https://github.com/redzrush101) | #10492 |
-| [@rengaryang](https://github.com/rengaryang) | #11333 |
-| [@rinseaid](https://github.com/rinseaid) | #8945, #9037, #9932, #9933, #9969, #9982, #10554 |
-| [@ritheshcn25](https://github.com/ritheshcn25) | #10026 |
-| [@rixzkiye](https://github.com/rixzkiye) | direct commit / report |
-| [@rizxfrog](https://github.com/rizxfrog) | #10356, #10546 |
-| [@RobertsXML](https://github.com/RobertsXML) | direct commit / report |
-| [@royanrosyad85](https://github.com/royanrosyad85) | direct commit / report |
-| [@rqzbeh](https://github.com/rqzbeh) | #10415, #10420, #10424, #10430, #10465, #10470, #10890, #10894, #10898, #10899, #10901, #11039, #11054, #11055, #11056, #11078, #11117, #11123, #11125, #11132, #11155, #11161, #11177, #11182, #11189, #11262 |
-| [@rushsinging](https://github.com/rushsinging) | #8947 |
-| [@ryan-brosas](https://github.com/ryan-brosas) | #9693 |
-| [@ryanngit](https://github.com/ryanngit) | direct commit / report |
-| [@sadSanta-07](https://github.com/sadSanta-07) | #9938, #10209, #10605, #10772 |
-| [@SalyyS1](https://github.com/SalyyS1) | direct commit / report |
-| [@Sam280903](https://github.com/Sam280903) | #9274, #9278, #9281, #9283, #9448 |
-| [@sanforex24h](https://github.com/sanforex24h) | #11026 |
-| [@SCys](https://github.com/SCys) | #11107 |
-| [@seakleangnhak](https://github.com/seakleangnhak) | direct commit / report |
-| [@seanford](https://github.com/seanford) | #8523 |
-| [@SemonCat](https://github.com/SemonCat) | direct commit / report |
-| [@sha367](https://github.com/sha367) | #10471 |
-| [@shixi-li](https://github.com/shixi-li) | #9022, #9513, #10001 |
-| [@Siva010](https://github.com/Siva010) | #10658 |
-| [@SnCr90](https://github.com/SnCr90) | #10534 |
-| [@soulhakr](https://github.com/soulhakr) | #8799 |
-| [@sprintberlin](https://github.com/sprintberlin) | #11353, #11355, #11360 |
-| [@stanleytejakusuma](https://github.com/stanleytejakusuma) | #9610, #10636, #10660, #10730, #11337 |
-| [@Stazyu](https://github.com/Stazyu) | #9007, #9226, #9438 |
-| [@SupremeNexas](https://github.com/SupremeNexas) | #9913 |
-| [@swingtempo](https://github.com/swingtempo) | #9307, #10354 |
-| [@szzhoujiarui](https://github.com/szzhoujiarui) | #9218 |
-| [@tald26](https://github.com/tald26) | #9959 |
-| [@taltas](https://github.com/taltas) | direct commit / report |
-| [@TechNickAI](https://github.com/TechNickAI) | #9251, #10558 |
-| [@TengSivtean](https://github.com/TengSivtean) | #10000, #10002, #10086 |
-| [@TheDemonTuan](https://github.com/TheDemonTuan) | #11364 |
-| [@TheFrenchGhosty](https://github.com/TheFrenchGhosty) | #9326 |
-| [@tiangao88](https://github.com/tiangao88) | #10046, #10363 |
-| [@tientien17](https://github.com/tientien17) | #10798 |
-| [@tito13kfm](https://github.com/tito13kfm) | #10227 |
-| [@tkgo11](https://github.com/tkgo11) | #10370, #10371 |
-| [@tuandinh0801](https://github.com/tuandinh0801) | #10804, #10830, #11230 |
-| [@Tushar49](https://github.com/Tushar49) | #10186 |
-| [@tuxmonteiro](https://github.com/tuxmonteiro) | #9065 |
-| [@vinogradovnet](https://github.com/vinogradovnet) | #9581 |
-| [@VXNCXNX](https://github.com/VXNCXNX) | #9111, #9783 |
-| [@wgordon17](https://github.com/wgordon17) | #8909, #9233, #9441, #9619 |
-| [@Witroch4](https://github.com/Witroch4) | #8713 |
-| [@witt3rd](https://github.com/witt3rd) | #9962, #9963 |
-| [@wpec](https://github.com/wpec) | #10839 |
-| [@XDayonline](https://github.com/XDayonline) | #10053 |
-| [@xiaoyaner0201](https://github.com/xiaoyaner0201) | #8757, #8869, #8876, #8883, #8906, #8931, #9021, #9027, #9042, #9316, #9452, #10468 |
-| [@xyzs996](https://github.com/xyzs996) | #11210 |
-| [@xz-dev](https://github.com/xz-dev) | #8367, #8908, #9199, #9205, #9262, #9290, #9313, #9555, #9569, #9629, #9788, #9983, #10066, #10072, #10079, #10162, #10243, #10247, #10437, #10712, #10716, #10723, #10806, #10953 |
-| [@yansigit](https://github.com/yansigit) | #9834, #9909, #9911, #9917, #9921, #10065 |
-| [@yidecode](https://github.com/yidecode) | direct commit / report |
-| [@yourspraveen](https://github.com/yourspraveen) | #11075, #11088, #11165, #11271 |
-| [@yulinlina](https://github.com/yulinlina) | #10013 |
-| [@YunyunZhai](https://github.com/YunyunZhai) | #10946, #10960 |
-| [@yutuknown](https://github.com/yutuknown) | #8999 |
-| [@zabrodschiipavel-sketch](https://github.com/zabrodschiipavel-sketch) | #9312 |
-| [@zannen7](https://github.com/zannen7) | #10077 |
-| [@Zartharas](https://github.com/Zartharas) | #9161, #9164, #9181, #9182, #9184, #9185, #9186, #9189, #9294, #9825, #9833, #9936, #9965, #9992, #10202, #10218, #10272, #10329, #10518, #10519, #10521, #10799, #10873, #10878 |
-| [@Zenlyte](https://github.com/Zenlyte) | #9005 |
-| [@zhiru](https://github.com/zhiru) | #9099, #9101 |
-| [@ziuus](https://github.com/ziuus) | #8912, #11372 |
-| [@zmf963](https://github.com/zmf963) | direct commit / report |
-| [@zoser69](https://github.com/zoser69) | #10874 |
-| [@zuckdorsey](https://github.com/zuckdorsey) | #9723 |
-| [@diegosouzapw](https://github.com/diegosouzapw) | maintainer |
-
----
-
-## [3.8.49] — 2026-07-28
-
-_Living section — regenerated 2026-07-19 from all 306 cycle commits (bump 2c62333b0 → tip). Bullets carry the merged PR and its author; direct pushes listed separately. Finalized at the v3.8.49 release._
-
-### ✨ New Features
-
-- **feat:** generalize ensureThinkingBudget to all providers + preserve server-side tool invocations on antigravity ([#6979](https://github.com/diegosouzapw/OmniRoute/pull/6979)) — thanks @rafaumeu
-- **feat(6922):** effort-tier aliases for glm-5.2 & mimo-v2.5 on opencode-go ([#6987](https://github.com/diegosouzapw/OmniRoute/pull/6987)) — thanks @rafaumeu
-- **feat(providers):** curated OpenRouter embeddings catalog + specialty merge in live discovery (#6976) ([#6994](https://github.com/diegosouzapw/OmniRoute/pull/6994))
-- **feat(quota):** opt-in auto-ping to keep Codex quota windows warm (#6977) ([#6995](https://github.com/diegosouzapw/OmniRoute/pull/6995))
-- **feat(providers):** add Agnes AI native provider support ([#7035](https://github.com/diegosouzapw/OmniRoute/pull/7035)) — thanks @HouMinXi
-- **feat(sse):** allow disabling `:` comment heartbeats via OMNIROUTE_SSE_COMMENTS=off ([#7036](https://github.com/diegosouzapw/OmniRoute/pull/7036)) — thanks @xier2012
-- **feat(perf):** add performance.mark/measure to SSE pipeline + request-size metric ([#7045](https://github.com/diegosouzapw/OmniRoute/pull/7045)) — thanks @oyi77
-- **feat(providers):** add Dahl free inference provider ([#7062](https://github.com/diegosouzapw/OmniRoute/pull/7062)) — thanks @growab
-- **feat(ci):** boot-smoke the packed npm tarball (check:pack-boot, #7065 class killer) ([#7086](https://github.com/diegosouzapw/OmniRoute/pull/7086))
-- **feat(ci):** hotfix fast-lane + tests-only E2E skip (WS3.1) ([#7088](https://github.com/diegosouzapw/OmniRoute/pull/7088))
-- **feat(ci):** continuous release-green — on-push quick gate + 3x/day full sweep (WS5.1) ([#7089](https://github.com/diegosouzapw/OmniRoute/pull/7089))
-- **feat(ci):** duration-balanced E2E shards via LPT bin-packing (WS4.1) ([#7090](https://github.com/diegosouzapw/OmniRoute/pull/7090))
-- **feat(ci):** TypeScript 7 native shadow for typecheck:core (WS4.2, advisory) ([#7091](https://github.com/diegosouzapw/OmniRoute/pull/7091))
-- **feat(release):** npm staged publishing + pre-publish boot-smoke (WS1.3) ([#7092](https://github.com/diegosouzapw/OmniRoute/pull/7092))
-- **feat(release):** post-publish verifier — clean-container install + boot (WS1.4) ([#7109](https://github.com/diegosouzapw/OmniRoute/pull/7109))
-- **feat(ci):** Mergify merge queue + manual-train fallback runbook (WS3.4/WS3.2) ([#7112](https://github.com/diegosouzapw/OmniRoute/pull/7112))
-- **feat(ci):** Windows leg for Electron prepare smoke (WS1.5) ([#7113](https://github.com/diegosouzapw/OmniRoute/pull/7113))
-- **feat(ci):** Codecov patch coverage (informational) + fix missing lcov reporter (WS5.6) ([#7114](https://github.com/diegosouzapw/OmniRoute/pull/7114))
-- **feat(sidecar):** support conditional provider manifest refresh ([#7130](https://github.com/diegosouzapw/OmniRoute/pull/7130)) — thanks @KooshaPari
-- **feat(homolog):** real-environment E2E homologation suite (npm run homolog) ([#7133](https://github.com/diegosouzapw/OmniRoute/pull/7133))
-- **feat(usage):** add Codex reset credit picker ([#7154](https://github.com/diegosouzapw/OmniRoute/pull/7154)) — thanks @JxnLexn
-- **feat(ci):** Trunk Flaky Tests uploads for vitest + Playwright E2E (WS5.2/5.3) ([#7175](https://github.com/diegosouzapw/OmniRoute/pull/7175))
-- **feat(ci):** Trunk Flaky Tests upload on the fast-path vitest job (per-PR volume) ([#7205](https://github.com/diegosouzapw/OmniRoute/pull/7205))
-- **feat(kiro):** register GPT-5.6 Sol/Terra/Luna model family ([#7209](https://github.com/diegosouzapw/OmniRoute/pull/7209))
-- **feat(dashboard):** show Codex plan label in provider and quota views ([#7210](https://github.com/diegosouzapw/OmniRoute/pull/7210))
-- **feat(dashboard):** add reorder connections by availability button ([#7211](https://github.com/diegosouzapw/OmniRoute/pull/7211))
-- **feat(dashboard):** add 180D and 365D usage/cost analytics periods (#7213) ([#7213](https://github.com/diegosouzapw/OmniRoute/pull/7213))
-- **feat(api):** add Vary: Accept-Encoding to token-authenticated /v1* responses (#6737) ([#7217](https://github.com/diegosouzapw/OmniRoute/pull/7217))
-- **feat(api):** expose GET /api/usage/model-latency-stats (#6873) ([#7218](https://github.com/diegosouzapw/OmniRoute/pull/7218))
-- **feat(dashboard):** add compression-mode selector to Context & Cache combos page (#6760) ([#7219](https://github.com/diegosouzapw/OmniRoute/pull/7219))
-- **feat(sse):** route GitHub Copilot Claude models through native /v1/messages ([#7223](https://github.com/diegosouzapw/OmniRoute/pull/7223))
-- **feat(mitm):** add Antigravity reasoning-effort overrides ([#7228](https://github.com/diegosouzapw/OmniRoute/pull/7228))
-- **feat:** replace free-text model inputs with hidePaid-aware Selects (#6540) ([#7229](https://github.com/diegosouzapw/OmniRoute/pull/7229))
-- **feat:** editable ComfyUI base-URL field + per-connection override for image/video/music generation (#6928) ([#7232](https://github.com/diegosouzapw/OmniRoute/pull/7232))
-- **feat(sse):** add optional-enum null-omission idiom for codex strict-mode tools (#7023) ([#7233](https://github.com/diegosouzapw/OmniRoute/pull/7233))
-- **feat(sse):** preserve tools/tool_choice for tool-bearing requests through fusion combos (#6771) ([#7235](https://github.com/diegosouzapw/OmniRoute/pull/7235))
-- **feat(api):** accept x-goog-api-key header for client-facing auth (#7034) ([#7236](https://github.com/diegosouzapw/OmniRoute/pull/7236))
-- **feat(sse):** add native xAI Grok Imagine video generation provider ([#7238](https://github.com/diegosouzapw/OmniRoute/pull/7238))
-- **feat:** add Type filter and easiest-first sort to Free Provider Rankings (#6915) ([#7240](https://github.com/diegosouzapw/OmniRoute/pull/7240))
-- **feat(cli):** add Grok Build CLI tool setup (~/.grok/config.toml) ([#7241](https://github.com/diegosouzapw/OmniRoute/pull/7241))
-- **feat(provider):** add Chenzk API OpenAI-compatible gateway ([#7246](https://github.com/diegosouzapw/OmniRoute/pull/7246))
-- **feat(providers):** let custom connections opt into prompt-cache capability (#6880) ([#7257](https://github.com/diegosouzapw/OmniRoute/pull/7257))
-- **feat(db):** include xp_audit_log in automatic retention/prune (#6801) ([#7260](https://github.com/diegosouzapw/OmniRoute/pull/7260))
-- **feat(api):** structured X-Routing-Fallback-Reason header for relay routing (#6872) ([#7262](https://github.com/diegosouzapw/OmniRoute/pull/7262))
-- **feat(compression):** support RTK TOML schema v1 filters ([#7281](https://github.com/diegosouzapw/OmniRoute/pull/7281)) — thanks @JxnLexn
-- **feat:** add principal-scoped CCR MCP lifecycle ([#7282](https://github.com/diegosouzapw/OmniRoute/pull/7282)) — thanks @JxnLexn
-- **feat(morph):** refresh curated models ([#7314](https://github.com/diegosouzapw/OmniRoute/pull/7314)) — thanks @backryun
-- **feat(issue-agent):** surface RecordedTriageTimeoutError as 504 ([#7315](https://github.com/diegosouzapw/OmniRoute/pull/7315)) — thanks @KooshaPari
-- **feat(incident-response):** structured incident response templates ([#7334](https://github.com/diegosouzapw/OmniRoute/pull/7334)) — thanks @KooshaPari
-- **feat(providers):** add xAI OAuth PKCE provider ([#7399](https://github.com/diegosouzapw/OmniRoute/pull/7399)) — thanks @fenix007
-- **feat(models):** advertise Claude reasoning-effort variants in /v1/models ([#7497](https://github.com/diegosouzapw/OmniRoute/pull/7497)) — thanks @thepigdestroyer
-- **feat(kimi):** sync Code, Web, and Moonshot providers ([#7531](https://github.com/diegosouzapw/OmniRoute/pull/7531)) — thanks @backryun
-- **feat(resilience):** guard OmniRoute peer routing loops ([#7555](https://github.com/diegosouzapw/OmniRoute/pull/7555)) — thanks @isiahw1
-- **feat:** add Mixedbread AI as embeddings provider (#6660) ([#7595](https://github.com/diegosouzapw/OmniRoute/pull/7595))
-- **feat(providers):** add Rev AI speech-to-text provider (#6655) ([#7596](https://github.com/diegosouzapw/OmniRoute/pull/7596))
-- **feat:** add Freepik (Magnific Mystic) image generation provider (#6654) ([#7597](https://github.com/diegosouzapw/OmniRoute/pull/7597))
-- **feat(sse):** add DeepInfra as a video-generation provider (#6653) ([#7598](https://github.com/diegosouzapw/OmniRoute/pull/7598))
-- **feat(providers):** add Felo chat-aggregator provider (#6666) ([#7599](https://github.com/diegosouzapw/OmniRoute/pull/7599))
-- **feat(sse):** add Notion AI Web (Unofficial/Experimental) provider (#6758) ([#7600](https://github.com/diegosouzapw/OmniRoute/pull/7600))
-- **feat:** add FreeTheAi as OpenAI-compatible gateway provider (#6670) ([#7602](https://github.com/diegosouzapw/OmniRoute/pull/7602))
-- **feat:** add Gladia as an async speech-to-text provider (#6657) ([#7603](https://github.com/diegosouzapw/OmniRoute/pull/7603))
-- **feat:** add EdgeTTS audio-tts provider (#6668) ([#7605](https://github.com/diegosouzapw/OmniRoute/pull/7605))
-- **feat(video):** add Novita AI as video-generation provider (#6658) ([#7606](https://github.com/diegosouzapw/OmniRoute/pull/7606))
-- **feat:** add Segmind image+video provider (#6656) ([#7608](https://github.com/diegosouzapw/OmniRoute/pull/7608))
-- **feat:** add Microsoft Designer as image provider (#6672) ([#7609](https://github.com/diegosouzapw/OmniRoute/pull/7609))
-- **feat:** per-model default reasoning_effort + no-think none on OpenAI path (#6879) ([#7631](https://github.com/diegosouzapw/OmniRoute/pull/7631))
-- **feat(sse):** per-model upstream header-response timeout override (#6354) ([#7632](https://github.com/diegosouzapw/OmniRoute/pull/7632))
-- **feat(dashboard):** in-product guidance for prompt compression engines (#7530) ([#7634](https://github.com/diegosouzapw/OmniRoute/pull/7634))
-- **feat(usage):** add TTFT/E2E-latency/tokens-per-second to model latency stats (#6875) ([#7635](https://github.com/diegosouzapw/OmniRoute/pull/7635))
-- **feat:** import providers from CSV/JSON file (#6836) ([#7636](https://github.com/diegosouzapw/OmniRoute/pull/7636))
-- **feat:** confirm before removing a single connection (#7361) ([#7640](https://github.com/diegosouzapw/OmniRoute/pull/7640))
-- **feat(sse):** honor excluded models in no-auth auto-combo candidate pool (#7622) ([#7646](https://github.com/diegosouzapw/OmniRoute/pull/7646))
-- **feat(providers):** add g4f.space no-key gateway (groq/gemini/pollinations/ollama/nvidia) (#6650) ([#7647](https://github.com/diegosouzapw/OmniRoute/pull/7647))
-- **feat:** rate-limit queue admission control (maxQueueDepth + 15s default) (#6593) ([#7649](https://github.com/diegosouzapw/OmniRoute/pull/7649))
-- **feat(sse):** generalize session affinity TTL to all providers (#7274) ([#7650](https://github.com/diegosouzapw/OmniRoute/pull/7650))
-- **feat:** OpenRouter quota tracking (key/credits + free-window counter) (#6842) ([#7651](https://github.com/diegosouzapw/OmniRoute/pull/7651))
-- **feat(sse):** quota tracking for AgentRouter, v0 (Vercel), FreeModel (#6850, #6845, #7075) ([#7653](https://github.com/diegosouzapw/OmniRoute/pull/7653))
-- **feat(providers):** Speechmatics STT, gTTS, VibeProxy preset (#6659, #6667, #6874) ([#7655](https://github.com/diegosouzapw/OmniRoute/pull/7655))
-- **feat(api):** route Google AI Studio Imagen through /v1/images/generations ([#7656](https://github.com/diegosouzapw/OmniRoute/pull/7656)) — thanks @danscMax
-
-- **feat(auth):** OIDC as optional dashboard admin login gate (password fallback preserved) ([#6973](https://github.com/diegosouzapw/OmniRoute/pull/6973)) — thanks @mikolaj92
-- **feat(api):** add pagination params to 8 DB modules + recharts code-split ([#7046](https://github.com/diegosouzapw/OmniRoute/pull/7046)) — thanks @oyi77
-- **feat(proxy):** operator-level proxy subscriptions (Karing-style) — hardened, ready for review ([#7299](https://github.com/diegosouzapw/OmniRoute/pull/7299)) — thanks @xier2012
-- **feat(grok-cli):** align with official Grok Build client ([#7358](https://github.com/diegosouzapw/OmniRoute/pull/7358)) — thanks @backryun
-- **feat(providers):** Complete GHE Copilot OAuth provider implementation ([#7546](https://github.com/diegosouzapw/OmniRoute/pull/7546)) — thanks @hppsc1215
-- **feat(guardrails):** add CredentialMaskerGuardrail for API key/secret redaction ([#7683](https://github.com/diegosouzapw/OmniRoute/pull/7683)) — thanks @Securiteru
-- **feat(perplexity):** refresh provider integrations ([#7687](https://github.com/diegosouzapw/OmniRoute/pull/7687)) — thanks @backryun
-- **feat(providers):** notion-web live model discovery via getAvailableModels ([#7696](https://github.com/diegosouzapw/OmniRoute/pull/7696)) — thanks @artickc
-- **feat(providers):** add proactive cf_clearance/User-Agent hint to grok-web connection dialog (#7567) ([#7713](https://github.com/diegosouzapw/OmniRoute/pull/7713))
-- **feat:** add live gRPC-web quota fetcher for grok-cli (#6844) ([#7714](https://github.com/diegosouzapw/OmniRoute/pull/7714))
-- **feat(api):** add opt-in auto-sync scheduler for free-proxy sources (#7079) ([#7716](https://github.com/diegosouzapw/OmniRoute/pull/7716))
-- **feat(dashboard):** show proxy name in badge, sort saved-proxy picker, default to Saved tab (#7643) ([#7720](https://github.com/diegosouzapw/OmniRoute/pull/7720))
-- **feat(cli):** add auth export command for decrypted provider credentials (#6683) ([#7724](https://github.com/diegosouzapw/OmniRoute/pull/7724))
-- **feat(oauth):** accept full ChatGPT session JSON for Codex manual import (#6636) ([#7725](https://github.com/diegosouzapw/OmniRoute/pull/7725))
-- **feat(sse):** add nvidia NIM local RPM budget + concurrency cap (#6846) ([#7726](https://github.com/diegosouzapw/OmniRoute/pull/7726))
-- **feat(gemini-web):** emulate OpenAI tool calling via the webTools prompt shim (#7286) ([#7727](https://github.com/diegosouzapw/OmniRoute/pull/7727))
-- **feat(services):** introduce pluggable service-provider contract, migrate 9router (#7333) ([#7730](https://github.com/diegosouzapw/OmniRoute/pull/7730))
-- **feat(mitm):** root-CA + per-host leaf certs for AgentBridge static server (#6684) ([#7731](https://github.com/diegosouzapw/OmniRoute/pull/7731))
-- **feat(providers):** add hailuo-web (MiniMax web) chat provider (#6673) ([#7734](https://github.com/diegosouzapw/OmniRoute/pull/7734))
-- **feat:** browser login for Grok Build provider (#7013) ([#7735](https://github.com/diegosouzapw/OmniRoute/pull/7735))
-- **feat(routing):** wire interceptFetch tool interception into the chat pipeline (#7339) ([#7736](https://github.com/diegosouzapw/OmniRoute/pull/7736))
-- **feat(sse):** add X-OmniRoute-Decision routing trace header (#6022) ([#7765](https://github.com/diegosouzapw/OmniRoute/pull/7765))
-- **feat(providers):** zai-web live model discovery with local-catalog fallback (#7678) ([#7766](https://github.com/diegosouzapw/OmniRoute/pull/7766))
-- **feat(api):** sync upstream reasoning.supported_efforts into synced-model catalog (#7694) ([#7767](https://github.com/diegosouzapw/OmniRoute/pull/7767))
-- **feat(dashboard):** pin Kimi providers first in category + official supporter card accent ([#7775](https://github.com/diegosouzapw/OmniRoute/pull/7775))
-- **feat(chaos+ponytail):** parallel chaos-mode dispatch + ponytail output … ([#7781](https://github.com/diegosouzapw/OmniRoute/pull/7781)) — thanks @Moseyuh333
-- **feat(perf):** IC2 — cache provider connections by ID + lazy-decrypt credentials ([#7787](https://github.com/diegosouzapw/OmniRoute/pull/7787)) — thanks @oyi77
-- **feat(quality):** gate the free-tier headline so it can never silently drift again ([#7798](https://github.com/diegosouzapw/OmniRoute/pull/7798))
-- **feat(providers):** expose an explicit tier override for any provider connection (#7818) ([#7838](https://github.com/diegosouzapw/OmniRoute/pull/7838))
-- **feat(routing):** read-only auto/* candidate transparency + per-API-key exclusions (#7819) ([#7839](https://github.com/diegosouzapw/OmniRoute/pull/7839))
-- **feat(catalog):** map unmapped free tiers, add navy + aihorde, surface keyless providers ([#7840](https://github.com/diegosouzapw/OmniRoute/pull/7840))
-- **feat(providers):** add OpenRouter speech-to-text (audio transcription) provider ([#7861](https://github.com/diegosouzapw/OmniRoute/pull/7861)) — thanks @Tasogarre
-- **feat(qwen):** add Qwen3.8 Max Preview catalogs [Part 2/3] ([#7874](https://github.com/diegosouzapw/OmniRoute/pull/7874)) — thanks @backryun
-- **feat:** support Bun bundled SQLite runtime ([#7878](https://github.com/diegosouzapw/OmniRoute/pull/7878)) — thanks @Arul-
-- **feat(providers):** add 5 free-tier providers (ainative, aion, sealion, routeway, nara) ([#7887](https://github.com/diegosouzapw/OmniRoute/pull/7887))
-- **feat(vnc-session):** persistent noVNC browser login for web-cookie providers ([#7892](https://github.com/diegosouzapw/OmniRoute/pull/7892)) — thanks @Capslockb
-- **feat(sse):** add PromptQL playground provider (unofficial) ([#7911](https://github.com/diegosouzapw/OmniRoute/pull/7911)) — thanks @artickc
-- **feat(cline):** align ClinePass catalog and request protocol ([#7914](https://github.com/diegosouzapw/OmniRoute/pull/7914)) — thanks @backryun
-- **feat:** narrow mcp:connect scope + per-key HTTP tool-scope binding (#7895) ([#7967](https://github.com/diegosouzapw/OmniRoute/pull/7967))
-- **feat:** provider tab account search + mirrored top pagination (#7937) ([#7968](https://github.com/diegosouzapw/OmniRoute/pull/7968))
-- **feat:** canonical numeric helpers + tier-1 (analytics) migration (#7879) ([#7969](https://github.com/diegosouzapw/OmniRoute/pull/7969))
-- **feat(sse):** add HyperAgent (hyperagent.com) unofficial web provider ([#7994](https://github.com/diegosouzapw/OmniRoute/pull/7994)) — thanks @artickc
-- **feat:** copilot-m365-web tone-selected model variants (#7872) ([#7997](https://github.com/diegosouzapw/OmniRoute/pull/7997))
-- **feat(media):** Adobe Firefly image + video generation provider ([#8006](https://github.com/diegosouzapw/OmniRoute/pull/8006)) — thanks @artickc
-- **feat(routing):** add prompt-cache affinity ([#8008](https://github.com/diegosouzapw/OmniRoute/pull/8008)) — thanks @JxnLexn
-- **feat(compression):** select model-aware tokenizers ([#8009](https://github.com/diegosouzapw/OmniRoute/pull/8009)) — thanks @JxnLexn
-- **feat(compression):** add Responses tool-output engine ([#8010](https://github.com/diegosouzapw/OmniRoute/pull/8010)) — thanks @JxnLexn
-- **feat(dashboard):** Kimi sponsor banner, Kimi Coding preset, official logomarks and partner links ([#8039](https://github.com/diegosouzapw/OmniRoute/pull/8039))
-- **feat(dashboard):** make Codex quota card windows reflect reality ([#8054](https://github.com/diegosouzapw/OmniRoute/pull/8054)) — thanks @insoln
-- **feat(compression):** teach the model the CCR retrieve protocol on first marker (#8033) ([#8063](https://github.com/diegosouzapw/OmniRoute/pull/8063))
-- **feat(compression):** per-model/endpoint compression exclusion filter (#8034) ([#8064](https://github.com/diegosouzapw/OmniRoute/pull/8064))
-- **feat(providers):** add CLOVA Studio, InternLM and Ant Ling API-key providers ([#8077](https://github.com/diegosouzapw/OmniRoute/pull/8077)) — thanks @alvaretto
-- **feat(codex):** support reference image edits ([#8122](https://github.com/diegosouzapw/OmniRoute/pull/8122)) — thanks @xiaoyaner0201
-- **feat(providers):** add weekly quota tracking for grok-web ([#8127](https://github.com/diegosouzapw/OmniRoute/pull/8127)) — thanks @apoapostolov
-- **feat(providers):** add Sarvam AI, Writer Palmyra and PLaMo API-key providers ([#8161](https://github.com/diegosouzapw/OmniRoute/pull/8161)) — thanks @alvaretto
-- **feat:** native Fish Audio TTS provider on /v1/audio/speech (#8099) ([#8164](https://github.com/diegosouzapw/OmniRoute/pull/8164))
-- **feat:** zh-CN terminology glossary + consistency gate + normalization pass (#8038) ([#8166](https://github.com/diegosouzapw/OmniRoute/pull/8166))
-- **feat(providers):** add Typhoon (Thailand) and Inception Mercury diffusion LLM ([#8170](https://github.com/diegosouzapw/OmniRoute/pull/8170)) — thanks @alvaretto
-- **feat(sse):** restrict auto-combo no-auth pool to allowlist (opencode, felo) + docs ([#8183](https://github.com/diegosouzapw/OmniRoute/pull/8183))
-- **feat(sre):** add tcp-close-analyzer.py for debugging client-vs-server TCP close order ([#8208](https://github.com/diegosouzapw/OmniRoute/pull/8208)) — thanks @hartmark
-- **feat(settings):** configurable model catalog cache TTL ([#8219](https://github.com/diegosouzapw/OmniRoute/pull/8219)) — thanks @oyi77
-- **feat(github-models):** refresh catalog and compatibility ([#8225](https://github.com/diegosouzapw/OmniRoute/pull/8225)) — thanks @backryun
-- **feat(github):** refresh Copilot model catalog ([#8226](https://github.com/diegosouzapw/OmniRoute/pull/8226)) — thanks @backryun
-- **feat:** classify grok-web Cloudflare anti-bot blocks + gated browser-backed cf_clearance path (#8019) ([#8241](https://github.com/diegosouzapw/OmniRoute/pull/8241))
-- **feat(providers):** weekly quota for xAI OAuth (Grok) (`xai-oauth` / `xao`) via shared cli-chat-proxy billing (`creditUsagePercent`), with fail-open self-tracked fallback ([#8471](https://github.com/diegosouzapw/OmniRoute/pull/8471)) — thanks @allanvb
-- **feat(sse):** every completion response now carries an `X-OmniRoute-Decision: strategy=<name>; provider=<alias>; latency_ms=<n>` header exposing the routing decision — `<name>` is the combo strategy (`priority`, `weighted`, `fusion`, etc.) or `single` for a non-combo request — for client-side debugging/analytics without server log access (#6022 — thanks @chirag127).
-- **feat(ws):** the live-dashboard WebSocket server now auto-starts in-process (via `instrumentation-node.ts`) across every deployment mode — dev, production, Docker, Electron — with no separate sidecar script; the default WS port moved from 20129 to **20132** to avoid colliding with `API_PORT` in split-port setups, the deprecated `OMNIROUTE_DISABLE_LIVE_WS` env was consolidated into `OMNIROUTE_ENABLE_LIVE_WS` (default enabled), and the WS path is now derived from `NEXT_PUBLIC_LIVE_WS_PUBLIC_URL`'s pathname (`/live-ws` fallback) (#6072 — thanks @ianriizky).
-- feat(sse): configurable per-model upstream header-response timeout override, precedence model > provider > global; applied to codex reasoning-heavy tiers (gpt-5.5-high/xhigh, gpt-5.6-\*-high/xhigh) (#6354)
-- **feat(dashboard):** Replace free-text model inputs in the Routing (web search route), Combo Defaults (handoff model), and Background Degradation tabs with a `hidePaidModels`-aware `ModelSelectField`, add a fail-open "paid-only pattern" warning to the per-model routing rule pattern field, and reject paid-only model targets at save time on `PATCH /api/settings`, `PATCH /api/settings/combo-defaults`, and `PUT /api/settings/background-degradation` when `hidePaidModels` is on ([#6540](https://github.com/diegosouzapw/OmniRoute/issues/6540))
-- **feat(compression):** new **omniglyph** engine (context-as-image) — renders system prompt, tool docs, and dense history as compact PNG pages the model reads instead of text (~10× fewer tokens on the converted block; 59–70% end-to-end measured). Works stacked with RTK/Caveman (`stackPriority: 90`) or standalone (`mode: omniglyph`); restricted to Claude Fable 5 over the direct Anthropic route, fail-closed gates with `skip:<reason>` techniques, preview (`stable: false`, off by default) (#6556). Dependency bumped to `omniglyph@^1.0.2` for upstream ReDoS fixes (#6661).
-- **feat(sse):** rate-limit request queue admission control — `resilienceSettings.requestQueue.maxQueueDepth` (default `0` = disabled, opt-in 0–100000) fast-rejects a request with a typed `RATE_LIMIT_QUEUE_FULL` error once the local per-provider+connection queue already holds `maxQueueDepth` requests, instead of growing the queue unboundedly; the factory default for `requestQueue.maxWaitMs` (how long a request may wait before being dropped) also fell from 120s to 15s so a saturated queue fails fast (#6593 — thanks @chirag127).
-- **feat(sandbox):** the skill sandbox gained a container-provider abstraction that auto-detects and uses the best native runtime per host — Apple Container (macOS 26+), WSL container (`wslc.exe`), OrbStack, Podman — instead of hardcoding `docker run`, removing the Docker Desktop requirement on macOS/Windows (#6611 — thanks @KooshaPari).
-- feat(oauth): accept the full ChatGPT session JSON (not just a bare access token) when pasting Codex credentials manually or via `POST /api/oauth/codex/import-token` (#6636)
-- feat(sse): add 5 no-key g4f.space gateway providers — `g4f-groq`, `g4f-gemini`, `g4f-pollinations`, `g4f-ollama`, `g4f-nvidia` — a free, no-signup reverse proxy (gpt4free project) fronting Groq, Gemini, Pollinations, Ollama, and NVIDIA NIM, rate-limited to 5 req/min per IP (#6650 — thanks @chirag127).
-- feat(sse): add DeepInfra as a video-generation provider via its native synchronous inference endpoint (#6653)
-- feat(providers): add Freepik (Magnific Mystic) API-key image generation provider — async submit/poll flow with realism/fluid/zen/flexible/super_real/editorial_portraits models (#6654)
-- feat(providers): add Rev AI speech-to-text provider with async job upload/poll/transcript flow (#6655)
-- **feat(providers):** add **Segmind** as an image + video generation provider — `x-api-key` auth against `POST https://api.segmind.com/v1/{model}`, with a curated starter model list (Flux, Stable Diffusion XL/3.5, Kandinsky for image; Wan, Hunyuan, LTX, Kling for video) (#6656).
-- feat(providers): add Gladia as an async speech-to-text provider (#6657)
-- feat(video): add Novita AI as a video-generation provider (Wan/Kling async submit-poll) (#6658)
-- **feat(providers):** add Speechmatics as an STT provider — async batch transcription (Enhanced operating point), 8 hours/month free tier, no credit card required. Streaming (real-time) mode is out of scope for v1. (#6659)
-- feat(providers): add Mixedbread AI as an embeddings provider (`mxbai-embed-large-v1`, `mxbai-embed-2d-large-v1`, free tier) (#6660)
-- **feat(providers):** add Felo (felo.ai) as a free, no-signup, no-API-key chat/search-agent aggregator provider (`felo-web`) — joins the existing `-web` family (DuckDuckGo AI Chat, Blackbox, etc). Five models (`felo-chat`, `felo-search`, `felo-scholar`, `felo-social`, `felo-document`) map to Felo's search categories; the executor opens a search thread then translates Felo's bespoke SSE stream into OpenAI-compatible chunks (#6666).
-- **feat(providers):** add gTTS (Google Translate TTS) as a free, no-signup audio-speech provider — routes through Google's current `batchexecute` RPC endpoint (the previously proposed `translate_tts` endpoint is deprecated), splitting input at the 100-char-per-request limit. (#6667)
-- **feat(sse):** add EdgeTTS (Microsoft Edge "Read Aloud") as a free, no-API-key `audio-tts` provider — the first WebSocket-transport speech provider, with per-client-IP rate limiting. (#6668)
-- feat(providers): add FreeTheAi as an OpenAI-compatible gateway provider with a free Discord-signup tier (#6670)
-- feat(sse): add Microsoft Designer as an unofficial web-session image provider, reverse-engineered submit-then-poll DallE.ashx flow (#6672)
-- **feat(providers):** add Hailuo Web (`hailuo-web`) — a free, `_token`-based web-cookie chat provider for the MiniMax consumer chat product at hailuo.ai, ported from the g4f reference implementation (MD5-chain request signing, custom `event:`/`data:` SSE parsing). Distinct from the existing paid API-key `minimax`/`minimax-cn` providers. (#6673)
-- **feat(cli):** new `omniroute auth export` command dumps DECRYPTED provider credentials (`apiKey`/`accessToken`/`refreshToken`/`idToken`) for one connection (`--id <id>`) or all connections, as `json` or `env` (`--format`), local-only and gated behind `--force` — no DB access happens without it, a stderr warning banner prints before any plaintext, `--out <file>` writes with `0600` permissions, and per-field decrypt failures surface as a `<field>DecryptFailed` boolean instead of aborting the export or leaking the caught error text (#6683)
-- **feat(mitm):** the AgentBridge static MITM server (`server.cjs`) can now issue a per-host TLS leaf from a persisted local root CA (`src/mitm/cert/rootCa.ts`, reusing the CA/leaf crypto already proven for TPROXY in `tproxy/dynamicCert.ts`) instead of a single static self-signed leaf scoped only to the 4 antigravity hosts — a fresh install covers the full `MITM_TOOL_HOSTS` set automatically; an install that already trusted the old leaf keeps using it until the operator opts in via `MITM_ROOT_CA_ENABLED=true` (`src/mitm/cert/migration.ts`), so no existing install is silently upgraded to the more powerful any-host-signing CA trust model (#6684).
-- **fix(sse):** skip `thinkingConfig` for Gemma models on the OpenAI→Gemini path so OpenAI-shape clients no longer get a 400 from Vertex. (thanks @chy1211)
-- **feat(xai):** route xAI clients to Grok's native `/v1/responses` endpoint instead of the chat-completions bridge. (thanks @ryanngit)
-- **feat(models):** add a Settings → AI "Model Overrides" UI plus `/api/model-capability-overrides` CRUD and a `model_capability_overrides` table, letting operators set a manual max-output-token override per provider/model (#6727 — thanks @xz-dev).
-- **feat(api):** add `Vary: Accept-Encoding` to token-authenticated `/v1*`/`/v1beta*` responses so downstream caches distinguish compressed vs uncompressed variants (RFC 9110 §12.5.5). (thanks @chirag127)
-- feat(sse): add Notion AI Web (Unofficial/Experimental) cookie-session provider (#6758)
-- **feat(dashboard):** add per-routing-combo compression-mode override to the Compression Combos page under Context & Cache, alongside the existing combo-card quick override. (#6760)
-- **feat(resilience):** operator-configurable account rotation policy — a new `rotationConfig` layer lets operators tune how connections rotate on failure, wired into `accountFallback` (#6763 — thanks @artickc).
-- **feat(sse):** preserve `tools`/`tool_choice` for tool-bearing requests through fusion combos — bypass panel synthesis and route straight to the judge with tools intact (#6771 — thanks @chirag127).
-- **chore(cursor): add Grok 4.5 effort/fast model IDs** (#6774 — thanks @andrewmunsell).
-- **feat(codex):** Codex provider model discovery now fetches the live catalog from `chatgpt.com/backend-api/codex/models` using Codex-shaped headers, falling back to a GitHub-hosted model manifest and then to the local static catalog when the live/GitHub sources are unavailable or return an unexpected shape — new `src/app/api/providers/[id]/models/discovery/codex.ts` (normalization, version-gating, merge/enrich against the local catalog) covered by `tests/unit/provider-models-discovery-split.test.ts` and `tests/unit/provider-models-route-codex.test.ts` (#6776 — thanks @JxnLexn).
-- **feat(cursor):** register the Opus 4.8, Fable 5, and Sonnet 5 model families for the Cursor Agent provider so the latest Claude/Fable model ids route correctly (#6779 — thanks @andrewmunsell).
-- **Changelog fragments (`changelog.d/`)**: PRs now add their changelog entry as a new fragment file (`changelog.d/{features|fixes|maintenance}/<PR>-<slug>.md`) instead of editing `CHANGELOG.md` — two PRs never touch the same file, structurally eliminating the CHANGELOG-eat merge conflicts that forced a re-sync push + full CI re-run after every sibling merge (O(N²) CI runs in a merge-storm). `scripts/release/aggregate-changelog.mjs` (npm run changelog:aggregate) folds fragments into the living section at release reconciliation, and `check:changelog-integrity` now also validates fragment well-formedness. Regression guard: `tests/unit/changelog-fragments.test.ts`.
-- **feat(proxy):** add a latency-optimized proxy rotation strategy that ranks pool entries by measured round-trip latency, extending the existing round-robin/random/sticky proxy-pool selection (#6798 — thanks @iamraydoan).
-- feat(db): include `xp_audit_log` in the automatic retention/prune cycle, with a configurable `retention.xpAuditLog` setting (#6801)
-- **feat(fusion):** the fusion judge may now draw on its own knowledge and override the panel when every panel answer is wrong or incomplete, instead of being restricted to synthesizing only from panel output (#6804 — thanks @chirag127).
-- **feat(dashboard):** search box on the Playground's raw model `<select>` (#4086) — the shared `ModelSelectModal` (combo builder + CLI-code cards) already had search, but Playground's `StudioConfigPane` model dropdown stayed a flat unsearchable list, unusable once a provider like OpenRouter contributed 50+ models. Typing now filters the dropdown (Turkish-safe accent/case-insensitive match via `matchesSearch`), while the currently selected model always stays pinned in the list even if it no longer matches the query, so typing never silently swaps the active selection. Reuses the existing `common.search` i18n key (already translated in all 42 locales) — no new translation key needed. Regression guard: `tests/unit/playground-model-selection-3731.test.ts` (`filterModelsByQuery`), `tests/unit/ui/playground-model-search-4086.test.tsx`. ([#6811](https://github.com/diegosouzapw/OmniRoute/pull/6811))
-- **feat(usage):** Antigravity/agy quota widget now surfaces the **weekly** window alongside the existing per-model 5-hour window ([#4017](https://github.com/diegosouzapw/OmniRoute/issues/4017)) — the weekly limit isn't part of the per-model `retrieveUserQuota` response the fetcher already calls; it only appears in a separate, undocumented `retrieveUserQuotaSummary` RPC that groups models into families ("Gemini Models", "Claude and GPT models") with one weekly bucket per family. A new `usage/antigravityWeeklyQuota.ts` leaf fetches that RPC (cached, best-effort — a failure or unavailable RPC never breaks the existing per-model quotas) and parses the weekly bucket per group into `gemini_weekly`/`claude_gpt_weekly` quota entries, merged into the same `quotas` map the widget already renders generically. Regression guard: `tests/unit/antigravity-weekly-quota-4017.test.ts` (bucket parsing, the alternate `quotaSummary`-nested envelope, and end-to-end merge via `getUsageForProvider`). ([#6818](https://github.com/diegosouzapw/OmniRoute/pull/6818))
-- **feat(codex):** Codex CLI compatibility shim — the Responses API `response.created`/`response.in_progress`/`response.completed` payloads now carry a `model` field (previously absent), and for Codex-CLI-originated requests it echoes the client-requested, effort-suffixed model id (e.g. `gpt-5.5-xhigh`) instead of the bare upstream id (`gpt-5.5`), so the Codex CLI status line/model button shows the active reasoning effort ([#3697](https://github.com/diegosouzapw/OmniRoute/issues/3697)). `openaiToOpenAIResponsesResponse` (`open-sse/translator/response/openai-responses.ts`) now threads the upstream model into the Responses event objects; a new `isCodexOriginatedHeaders()` (`open-sse/config/codexIdentity.ts`, reusing PR #3481's `originator`/User-Agent detection) makes chatCore's existing opt-in `echoRequestedModelName` (#1311) model-echo pipeline fire automatically for Codex clients regardless of the setting, detected by request headers so it still applies when `codex/gpt-5.5-xhigh` is routed through a combo to a non-codex upstream; `echoModelInObject`/`echoModelInSseLine` (`open-sse/services/responseModelEcho.ts`) now also rewrite the nested `response.model` field the Responses API uses. `/v1/models` still returns `models: []` for Codex (unchanged). Regression guard: `tests/unit/codex-effort-model-echo-3697.test.ts`. ([#6820](https://github.com/diegosouzapw/OmniRoute/pull/6820))
-- **Z.ai Web (free web-session provider)**: new `zai-web` web-cookie provider drives the free chat.z.ai consumer chat UI via a pasted browser session cookie, distinct from the existing API-key `zai`/`glm`/`glm-cn`/`glmt` providers (`api.z.ai`) — modeled on the `doubao-web`/`venice-web` cookie executors and the pre-existing `chatglm-web` credential requirement/token-extraction entries. `ZaiWebExecutor` (`open-sse/executors/zai-web.ts`) posts to `chat.z.ai/api/chat/completions` with the cookie forwarded both as `Cookie` and as `Authorization: Bearer <token>`, and normalizes both z.ai's internal `delta_content`/`phase` SSE envelope and a pass-through OpenAI-shaped `choices[].delta` frame into standard chat-completion chunks. Registered in `WEB_COOKIE_PROVIDERS`, `WEB_SESSION_CREDENTIAL_REQUIREMENTS`, the provider registry (`zai-web` entry, GLM-4.6/4.5/4.5V models), and `tokenExtractionConfig.ts` for in-app cookie capture. Regression guard: `tests/unit/executor-zai-web.test.ts` (16 tests — token extraction, frame parsing for both SSE shapes, streaming and non-streaming aggregation, error paths). (#4056) ([#6823](https://github.com/diegosouzapw/OmniRoute/pull/6823))
-- feat(dashboard): import multiple, possibly different providers from a CSV/JSON file — per-row validation, a checklist to pick which parsed rows to import, and a new `POST /api/providers/import` route with partial-failure results (#6836)
-- **feat(compression):** update the vendored **GCF** codec behind the **Headroom** engine to spec **v3.2 (nested flattening)** ([#6837](https://github.com/diegosouzapw/OmniRoute/issues/6837)). Homogeneous arrays whose rows carry nested objects/arrays now tabularize via `>`-prefixed path fields instead of a low-yield per-row fallback, so nested MCP tool-result rows (`meta:{...}`, `tags:[...]`) compact like flat rows. On representative shapes the update takes deeply-nested payloads the old codec left near-uncompressed from ~3% to ~32% vs JSON (k8s pods, `cl100k_base`), with shallow-nested rows seeing a small bump and flat arrays unchanged. Re-vendored from current gcf-typescript (zero runtime deps, MIT, SPDX-marked, generic-profile only); also folds in the `[N]:` inline-array quoting fix and canonical decimal formatting. Round-trip stays lossless (order-insensitive), and the decoder is hardened against prototype pollution (a `__proto__`/`constructor` path segment never mutates `Object.prototype`, and keys shadowing built-ins like `toString` now round-trip correctly instead of misparsing). Regression guard: `tests/unit/compression/headroom-smartcrusher.test.ts` (deep-nested + prototype-pollution cases).
-- **feat(sse):** OpenRouter quota tracking — a dedicated fetcher polls `/api/v1/key` + `/api/v1/credits` (per-key credit cap/remaining/reset, daily/weekly/monthly USD spend, BYOK usage) with a 45s cache and graceful degradation, a local per-account counter tracks the `:free`-model 50-or-1000-per-day + 20 RPM windows (corrected from `X-RateLimit-*` headers and `Retry-After` on 429), and OpenRouter `402` responses now lock the connection with a real cooldown instead of triggering an immediate reselection of the same credit-exhausted key (#6842).
-- **feat(sse):** live gRPC-web quota fetcher for Grok Build (`grok-cli`) — polls xAI's shared weekly credit pool (`grok.com/grok_api_v2.GrokBuildBilling/GetGrokCreditsConfig`) with the connection's existing bearer token, hand-decoding the framed/raw protobuf response (proto3 omission = 0% used, malformed/expired-token fails open) instead of relying solely on the static 864 req/day estimate, which now serves as an explicit fallback when the live fetch is unavailable (#6844).
-- feat(sse): add dual-window quota tracking for the `v0-vercel` provider — polls the credits (`/v1/user/billing`) and daily Platform-API operation (`/v1/rate-limits`) endpoints with the existing routing API key, defensively degrading to an `unknown` billing type rather than misparsing a future v0 billing-model migration, feeding preflight + the dashboard's Provider Quota card (#6845).
-- feat(sse): add a static local RPM budget (default 40/min, operator-overridable), per-model 429 scoping (already covered by #6773's `passthroughModels`), and a per-connection concurrency cap (default 6, operator-overridable) for the `nvidia` (NVIDIA NIM) provider, which sends no rate-limit headers and has no usage API — Phase 1 of client-side quota tracking; adaptive AIMD learning and the dashboard quota card are deferred follow-ups (#6846).
-- feat(sse): add quota tracking for the `agentrouter` provider — polls the New-API `/api/user/self` balance endpoint with a separate System Access Token + `New-Api-User` id (configured via `providerSpecificData.consoleApiKey` / `newApiUserId`), converting raw quota units into a dollar balance and feeding preflight + the dashboard's Provider Quota card (#6850).
-- **feat(providers):** Add GPT-5.6 support across OpenAI API, Codex, and ChatGPT Web, including Codex Max/Ultra efforts, VS Code metadata, Fast-tier credit accounting, curated live discovery, the Codex 0.144.1 client identity, and correct chat routing for models that also support image generation ([#6862](https://github.com/diegosouzapw/OmniRoute/pull/6862)) - thanks @backryun
-- **chore(providers):** Align emitted Claude Code identity headers, bridge fingerprints, provider profiles, and documented defaults with claude-cli 2.1.207 ([#6862](https://github.com/diegosouzapw/OmniRoute/pull/6862)) - thanks @backryun
-- feat(api): add a structured `X-Routing-Fallback-Reason` header to relay routing responses, exposing a stable machine-readable reason code alongside the legacy `X-Routing-Fallback` detail string (#6872)
-- **feat(api):** new **GET /api/usage/model-latency-stats** management endpoint exposes the existing rolling per-provider/model latency aggregate (avg/p50/p95/p99, success rate) already used internally by auto-combo routing — supports `windowHours`/`minSamples`/`maxRows`/`provider`/`model` filters (#6873).
-- **feat(providers):** add a `vibeproxy-openai` provider-node preset to `POST /api/provider-nodes` — defaults name/prefix/apiType for VibeProxy's local OpenAI-compatible gateway and normalizes the caller-supplied base URL to its `/v1` root; `baseUrl` remains mandatory. (#6874, idea from #6137 by @KooshaPari)
-- feat(usage): add avgTtftMs/avgE2ELatencyMs/avgTokensPerSecond to `getModelLatencyStats()` and feed them into auto-combo's speed-ranking factor (#6875)
-- feat(sse): per-model default `reasoning_effort` (`ModelSpec.defaultReasoningEffort`, injected only when the request carries no reasoning field) and make `no-think/` express `reasoning_effort:"none"` instead of deleting the field on the OpenAI path, so thinks-by-default models actually stop thinking (#6879)
-- **feat(providers):** let a custom/openai-compatible connection opt into prompt-cache behavior via a per-connection `cache` capability override, unblocking `prompt_cache_key` injection, the compression cache-aware guard, and `cache_control` passthrough for `openai-compatible-chat-<uuid>`-style connections. (thanks @andrea-kingautomation)
-- **feat(dashboard):** add a Type filter (No Signup / OAuth Login / API Key) and an "Easiest first" sort toggle to Free Provider Rankings, so zero-setup NOAUTH providers can be surfaced without eyeballing the Type column. (#6915)
-- **feat(providers):** expose an editable base-URL field on the ComfyUI connection so Docker-network setups (e.g. `http://comfyui:8188`) work for image, video, and music generation ([#6928](https://github.com/diegosouzapw/OmniRoute/issues/6928))
-- **feat(providers):** refresh the curated OpenRouter embeddings catalog (`open-sse/config/embeddingRegistry.ts`) with the current lineup — `openai/text-embedding-3-small`/`-large`, `qwen/qwen3-embedding-8b`/`-4b`, `baai/bge-m3`, `mistralai/mistral-embed-2312`, `google/gemini-embedding-001` — and fold curated embedding/rerank entries into OpenRouter's live model-discovery response (`src/app/api/providers/[id]/models/route.ts`), additively and deduped by id, so they no longer only appear on the no-config `local_catalog` fallback. OpenRouter serves embeddings via a dedicated `/api/v1/embeddings` endpoint (omitted from `/v1/models`), so the live-discovery success path previously returned chat models only ([#6976](https://github.com/diegosouzapw/OmniRoute/issues/6976)). Regression guard: `tests/unit/openrouter-embeddings-catalog-6976.test.ts`.
-- **feat(quota):** Add opt-in auto-ping to keep Codex quota windows warm — per-connection toggle in Settings → AI that sends a tiny request right after a Codex session window resets, so it isn't cold on the next real request ([#6977](https://github.com/diegosouzapw/OmniRoute/issues/6977))
-- **feat(oauth):** Add a one-click browser (PKCE) login for Grok Build (`grok-cli`) ALONGSIDE the existing device-code flow — reusing the same `auth.x.ai` authorize/token endpoints and public client id as the sibling `xai-oauth` provider on its own loopback port — while keeping the pre-existing device-code method and the paste-token/`auth.json` import flow both available; the connect modal lets the user pick "Device Code", "Browser Login", or "JWT Token" ([#7013](https://github.com/diegosouzapw/OmniRoute/issues/7013))
-- **feat(sse):** Add optional-enum `null`-omission idiom for Responses-API (codex) strict-mode tool schemas, closing the #6951 follow-up ([#7023](https://github.com/diegosouzapw/OmniRoute/issues/7023))
-- **feat(auth):** accept the `x-goog-api-key` header for client-facing auth so `gemini-cli` and other `@google/genai`-based clients can use OmniRoute as a native `/v1beta` gateway (#7034 — thanks @QRcode1337).
-- feat(sse): add a local dual-window (5h + 7d, per-account) quota tracker for the `freemodel-dev` provider, feeding preflight + the dashboard's Provider Quota card with user-overridable request caps (`FREEMODEL_5H_REQUEST_LIMIT` / `FREEMODEL_7D_REQUEST_LIMIT`) since FreeModel publishes no usage API — phase 1 of #7075 (tracker + registration); live hot-path request metering and the forward-compatible endpoint prober are tracked as follow-ups.
-- **feat(api):** opt-in scheduled auto-sync for free-proxy sources (`src/lib/freeProxyProviders/scheduler.ts`) — periodically re-runs the free-proxy provider `sync()` calls (iplocate, proxifly, oneproxy, webshare) that previously only ran via a manual `POST /api/settings/free-proxies/sync`, so a seeded pool no longer goes stale as free-proxy lists rotate; gated by `FREE_PROXY_AUTO_SYNC_ENABLED` (default `false`) and `FREE_PROXY_AUTO_SYNC_INTERVAL_MS` (default 30min, floor-clamped to 5min), reuses the existing `isBuildProcess()`/`OMNIROUTE_DISABLE_BACKGROUND_SERVICES` guards, and shares one `runFreeProxySyncCycle()` code path with the manual route; `GET /api/settings/free-proxies/stats` now also reports `autoSync: { enabled, intervalMs }` (#7079 — thanks @chirag127).
-- **feat(kiro):** register the GPT-5.6 Sol/Terra/Luna model family (272k context window). (thanks @SemonCat)
-- **feat(dashboard):** show the Codex subscription plan label in provider connection rows and the quota view, falling back to the plan captured at OAuth import when the live usage endpoint doesn't report one. (thanks @CarmeloCampos)
-- **feat(dashboard):** add a "Reorder" button to provider connections that sorts them by availability (using OmniRoute's connection-cooldown/testStatus model), persisting the new priority order. (thanks @fzrilsh)
-- **feat(dashboard):** add 180D and 365D periods to the Cost Explorer range selector. The new ranges thread through `parseCostRange`/`COST_RANGE_VALUES` and the `getRangeStartIso` handlers in the analytics and requests-by-provider-date usage routes, so cost/usage analytics can be viewed over a half-year and full-year window (#7213)
-- **feat(sse):** GitHub Copilot Claude models now route through Copilot's native `/v1/messages` endpoint (prompt-cache token counts, no more lossy tool-call round-trip). (thanks @yidecode)
-- **feat(mitm):** Antigravity MITM model mappings now support an optional per-model reasoning-effort override (Default/None/Low/Medium/High/XHigh) alongside the destination-model remap. (thanks @trfi)
-- **feat(sse):** add native xAI Grok Imagine video generation provider — `xai/grok-imagine-video` on `/v1/videos/generations` using your own xAI key, instead of only via the kie proxy market. (thanks @anndev-69)
-- **feat(cli):** add Grok Build CLI tool setup — writes a `[model.omniroute]` custom model into `~/.grok/config.toml` and restores your previous default on Reset. (thanks @rixzkiye)
-- **feat(provider):** add Chenzk API OpenAI-compatible gateway. (thanks @CahyokPutraDev99)
-- **feat(dashboard):** add a per-operator "hide this quota row" toggle to the usage dashboard's provider limit cards, persisted per-provider in settings. (thanks @nguyenha935)
-- **feat(sse):** session affinity (`X-Session-Id` / `x-codex-session-id` / `x-omniroute-session`) now works for **any** provider, not just Codex — the `codex`-only early-return in `resolveSessionAffinityTtlMs()` was removed, and the global TTL setting was renamed `codexSessionAffinityTtlMs` → `sessionAffinityTtlMs` (dashboard label updated to "Session affinity") with a backward-compatible migration that carries over an existing Codex TTL as the new default (#7274 — thanks @tenshiak).
-- **feat(sse):** `gemini-web` now honors the OpenAI `tools` array by wiring the existing `webTools.ts` prompt-emulation shim (already used by 11 other web-cookie executors) — the tool contract is serialized into the prompt typed into the Gemini web UI, and `<tool>{...}</tool>` blocks in the response are parsed back into `tool_calls` (malformed JSON degrades to ordinary chat content, never an error), including for streaming requests; `docs/reference/PROVIDER_REFERENCE.md` gained a "Tool calling" column (`native`/`emulated`/`none`) for providers with confirmed ground truth. `claude-web` still silently drops `tools` pending a separate emulate-vs-native design decision (#7286).
-- **feat(eval):** added a router-eval harness (`npm run eval:router`, `eval:router:compare`, `eval:router:patch-compare`, `eval:router:search`, `eval:router:trends`, `check:router-eval`) that replays routing decisions — from NDJSON corpora or the `usage_history`/`call_logs` SQLite tables — into an AIQ (success/latency/cost) score, compares baseline vs. candidate router configs with a retained-run regression gate, and ranks Pareto-optimal candidates; a sibling tool to the existing `eval:compression` harness (#7318 — thanks @KooshaPari).
-- **feat(services):** introduce a `ServiceProviderPlugin` contract (`src/lib/services/providerPlugins/`) that packages what was previously spread across `bootstrap.ts`'s inline `SERVICES[]` config and `serviceBackends.ts`'s manifest template into one shape per embedded-service backend; migrates `9router` through it end to end as the first proof, with `cliproxy`/`mux`/`bifrost` left completely unchanged on their pre-existing code paths — `cliproxyapi` migration, executor-routing consolidation, and manifest-path wiring are follow-up work (#7333).
-- feat(routing): wire `interceptFetch` into the chat pipeline — `resolveInterceptFetch(provider, model)` (a structural twin of `resolveInterceptSearch`) and the new `open-sse/services/webFetchInterception.ts` module rewrite a provider-native `web_fetch` tool declaration into a synthetic `omniroute_web_fetch` function tool, dispatched through the existing tool-call execution path to OmniRoute's own `/v1/web/fetch` instead of the upstream provider running it natively; strictly opt-in per provider/model (undefined/off leaves the request byte-identical to today), with a new dashboard toggle on the provider detail page covering both `interceptSearch` and `interceptFetch` (#7339, Phases 3-4 of #3384)
-- feat(dashboard): confirm before removing a single connection, naming the account, mirroring the existing batch-delete confirm UX (#7361)
-- **feat(providers):** Add a first-class xAI OAuth PKCE provider for `api.x.ai` models, including Grok 4.5 and refresh-token rotation ([#7399](https://github.com/diegosouzapw/OmniRoute/pull/7399)) — thanks @fenix007
-- **feat(dashboard):** surface in-product guidance for the Settings → Prompt Compression engines — each `engineCatalog.ts` entry now carries a `guidance` block (quality/latency tradeoffs, lossy flag, cache impact) sourced from `docs/compression/*.md`, rendered as an expandable per-engine detail with a "safe default" indicator for lossless engines (Session Dedup, CCR, Lite, Headroom) plus a link to the full compression guide (#7530).
-- **feat(providers):** Complete GHE Copilot OAuth provider implementation with device-code flow, validation, error sanitization, and DNS provisioning mapping ([#7546](https://github.com/diegosouzapw/OmniRoute/pull/7546))
-- feat(providers): grok-web's add-connection dialog now shows a proactive hint explaining that grok.com's `cf_clearance` cookie is pinned to the IP, User-Agent, and TLS fingerprint of the browser that earned it — on a 403, paste the exact browser User-Agent into the existing Custom User-Agent field under Advanced Settings and reuse the same IP/proxy (#7567)
-- **feat(providers):** register `lmstudio` in the embedding provider registry (`open-sse/config/embeddingRegistry.ts`) — LM Studio's local OpenAI-compatible `/v1/embeddings` endpoint, no auth required, passthrough model list (a user-configured provider_node still takes priority). Previously any `lmstudio/<model>` embedding request failed with `"Unknown embedding provider: lmstudio"` even though the model appeared fine in `/v1/models` ([#7601](https://github.com/diegosouzapw/OmniRoute/issues/7601) — thanks @ekinnee). Regression guard: `tests/unit/lmstudio-embedding-provider-7601.test.ts`.
-- feat(sse): honor a no-auth provider connection's **Excluded Models** field (`providerSpecificData.excludedModels`) in the auto-combo/fusion candidate pool builder, so an excluded no-auth model (e.g. `minimax-m3-free`) is filtered out upfront instead of only failing over after being picked (#7622).
-- **feat(dashboard):** proxy-assignment UX quality-of-life fixes — the per-connection proxy badge now shows the saved proxy's **name** instead of always falling back to its hostname (so distinct proxies sharing a domain no longer render identically), the "Proxy Config" modal's saved-proxy dropdown is now alphabetized by name, and the modal defaults to the **Saved** tab (instead of Custom) whenever the target scope has no assignment yet and at least one saved proxy already exists (#7643 — thanks @tenshiak).
-- feat(providers): `zai-web` (chat.z.ai) now wires live `/models` discovery through the shared PROVIDER_MODELS_CONFIG pipeline (cache → hardcoded local-catalog fallback), instead of only serving a static 3-model catalog whose ids had started 404ing upstream (#7678 — thanks @andrea-kingautomation). The `chat.z.ai/api/models` response shape and Bearer-only auth are unverified pending a live cookie check before merge.
-- **feat(perplexity):** Refresh Perplexity Web model mappings and Search API filters while keeping `/v1/models` scoped to API-key validation instead of curated catalog discovery ([#7687](https://github.com/diegosouzapw/OmniRoute/pull/7687)) — thanks @backryun
-- Generic OpenAI-compatible model sync now captures a provider's upstream `reasoning.supported_efforts` (in addition to the pre-existing flat `supportedThinkingEfforts` shape), surfaces it in the model catalog as `capabilities.effort_tiers`, and advertises `<prefix>/<model>-{effort}` request-time alias ids for catalog-only clients — mirroring the existing per-model reasoning-effort plumbing (#6879). Codex and Kimi are excluded since they already own their own effort-suffix mechanism.
-- **feat(dashboard):** Kimi (Moonshot AI) official-partnership highlight on the providers dashboard — Kimi-family providers (`kimi-coding`, `kimi-web`, `moonshot`) now render first within their category/group, and their card gets a Kimi-blue (`#1783FF`) accent border/glow plus an "Official Supporter" badge; presentation-only, routing/fallback order is unaffected (#7775).
-- feat(providers): let any provider connection — built-in or custom — be pinned to an explicit routing tier (free/cheap/premium) via a new `/api/settings/tier-config` route and an Advanced Settings tier selector; `TierCoverageWidget` now honors the override too (#7818)
-- feat(routing): add a read-only `GET /v1/auto-combo/{channel}/candidates` endpoint listing an `auto/*` channel's candidate pool with live reachability (provider circuit breaker, connection cooldown, model lockout), plus a per-API-key candidate exclusion list enforced in the `auto/*` candidate-pool builder — users with no overrides configured see byte-identical routing to today (#7819).
-- feat(providers): copilot-m365-web tone-selected model variants (#7872)
-- **feat(shared):** Add canonical numeric coercion helpers (`toNumber`, `toNumberOrNull`, `toNumberArray`) in `src/shared/utils/numeric.ts` with table-driven tests and a lint rule barring new local `toNumber` definitions, then migrate the report/analytics tier (usage analytics route, provider metrics route, usage stats, usage history helpers, call-log formatting, cost-analysis A2A skill) off their local duplicates ([#7879](https://github.com/diegosouzapw/OmniRoute/issues/7879))
-- feat(mcp): add a narrow `mcp:connect` API-key scope for the `/api/mcp/` LOCAL_ONLY carve-out (separate from `manage`/`admin`) and populate `authInfo.scopes` from the caller's real per-key scopes over HTTP/SSE so `scopeEnforcement.ts` prefers per-key scopes over the `OMNIROUTE_MCP_SCOPES` env fallback when enforcement is enabled (#7895).
-- feat(dashboard): provider tab account search (id/tag/name/email substring, cross-page) + mirrored top pagination bar + pagination for the tagged/grouped connections view (#7937)
-- feat(sse): classify grok-web Cloudflare anti-bot blocks + gated browser-backed cf_clearance path (#8019)
-- Teach the model the CCR retrieve protocol (marker → `omniroute_ccr_retrieve`, verbatim 24-char hash, `dedup:ref` look-back) on the first marker, gated on MCP-tool capability (#8033)
-- Add a per-model/endpoint compression exclusion filter: name model ids or `provider/model` patterns (`*` wildcard) that must never be compressed, checked before any engine runs so the request passes through byte-identical; configurable from a new Dashboard → Compression → Exclusions tab (#8034)
-- **feat(i18n):** zh-CN terminology glossary + consistency gate + 提供商→提供者 normalization — one-shot pass across `src/i18n/messages/zh-CN.json` (679 substitutions) and `bin/cli/locales/zh-CN.json` (54) mirroring #8024's zh-TW pass, a new versioned glossary (`scripts/i18n/glossary/zh-CN.json`) and protected-terms list (`scripts/i18n/glossary/protected-terms.json`), a pure-function consistency check (`scripts/i18n/check-glossary-consistency.mjs`, `npm run i18n:check-glossary`) wired into CI as `i18n-glossary-zhcn`, and zh-CN added to the visual-QA harness default locales (#8038).
-- **feat(dashboard):** The Codex quota card no longer shows latent, never-used per-feature rate-limit ceilings (e.g. `GPT-5.3-Codex-Spark`) as permanent 100% rows with a meaningless always-full reset — they now appear only once the feature is actually used. Per-feature window labels track the payload's `limit_name`, and each window is labeled by its real `limit_window_seconds` (so a 7-day `primary_window` shows "Weekly" instead of "Session"). ([#8051](https://github.com/diegosouzapw/OmniRoute/issues/8051))
-- feat(providers): native Fish Audio TTS provider on /v1/audio/speech (#8099)
-- **feat(codex):** add bounded multi-reference PNG/JPEG/WebP image editing (up to 8 references and 20 MiB decoded in aggregate) through the OpenAI-compatible `/v1/images/edits` route by reusing Codex Responses hosted-image tooling, OAuth, proxies, sanitized logs/errors, and OpenAI Images response formatting ([#8122](https://github.com/diegosouzapw/OmniRoute/pull/8122)) — thanks @xiaoyaner0201
-- refactor(sse): classify SSE critical-path empty catches + add CONTRIBUTING convention (#8142)
-- feat(db): persist caller session tag into call_logs for per-session cost attribution (#8249)
-- feat(api): quota-aware fallback routing for web-fetch providers (#8297)
-- feat(providers): map upstream reasoning-level metadata in openai-compatible discovery (#8347)
-- **feat(providers):** weekly quota for xAI OAuth (Grok) (`xai-oauth` / `xao`) via shared cli-chat-proxy billing (`creditUsagePercent`), with fail-open self-tracked fallback ([#8471](https://github.com/diegosouzapw/OmniRoute/pull/8471)) — thanks @allanvb
-- feat(jobs): `backup auto enable` schedule is now executed server-side — the cron expression, cloud/encrypt/retention settings written by the CLI are consumed by a new `startBackupScheduleJob()` tick registered alongside `startBudgetResetJob()` in `instrumentation-node.ts`; includes a zero-dependency 5-field cron matcher ([#8513](https://github.com/diegosouzapw/OmniRoute/issues/8513))
-- **feat(ci):** automate ratchet shrink-banking so file-size/complexity caps stop outliving their files after successful shrinks (#8584) ([#8612](https://github.com/diegosouzapw/OmniRoute/pull/8612)) — thanks @MumuTW
-- **feat(providers):** live monthly credit quota for Firecrawl (`GET /v2/team/credit-usage`) in Provider Limits / preflight ([#8759](https://github.com/diegosouzapw/OmniRoute/pull/8759)) — thanks @allanvb
-- **feat(search):** add Firecrawl to `POST /v1/search` supported providers with two sources (web|news) ([#8814](https://github.com/diegosouzapw/OmniRoute/pull/8814)) — thanks @allanvb
-- **feat(adobe-firefly):** reference-image attach for generate + OpenAI `/v1/images/edits` support (follow-up to #8006). Uploads sources to Firefly storage (`POST /v2/storage/image`), then submits `referenceBlobs` on 3P generate-async (nano multi-ref `usage:general`; gpt-image `usage:subject`). Wire matches live `firefly.adobe.com` captures. Also routes built-in edits to the same path (up to 4 refs).
-- **Homologation suite**: new `npm run homolog` runs the full release-homologation battery against the deployed VPS — health/version parity, API + real SSE streaming with an ephemeral API key (created and revoked by the run), minimal-cost real-provider smoke (promptfoo generated from the live catalog), and a Playwright sweep that loads every dashboard route and exercises the API-key UI flow — emitting a unified CTRF report that backs the release STOP #2 checklist
-- **feat(mcp):** add a read-only Local Corpus context source with bounded incremental text indexing, path-containment controls, an authenticated settings API, and three scoped MCP tools.
-- feat(providers): notion-web live model discovery via getAvailableModels (spaceId + token_v2 cookie)
-- Provider connections can now be shown or hidden individually on the Provider Quota page. The
-  visibility setting is available on each account in the provider detail view and does not affect
-  routing or account activation.
-- docs(i18n): rewrite Russian README as a full native manual (structure aligned with modern EN/zh-CN, fixed relative asset links).
-- **Providers**: adds the Xiaomi MiMo Token Plan provider and a per-connection API-protocol selector — some providers publish the same models over more than one protocol, and a connection can now pick the alternative instead of being locked to the OpenAI-compatible default ([#8861](https://github.com/diegosouzapw/OmniRoute/pull/8861))
-- **feat(opencode-plugin):** auto-discover models while running + force sync ([#8101](https://github.com/diegosouzapw/OmniRoute/pull/8101)) — thanks @RaviTharuma
-- **feat(combo):** enforce provider and model family invariants ([#8304](https://github.com/diegosouzapw/OmniRoute/pull/8304)) — thanks @RaviTharuma
-- **feat(cli):** replace ANTHROPIC_SMALL_FAST_MODEL with Fable default ([#8343](https://github.com/diegosouzapw/OmniRoute/pull/8343)) — thanks @leszek3737
-- **feat:** read INITIAL_PASSWORD env var during setup ([#8439](https://github.com/diegosouzapw/OmniRoute/pull/8439)) — thanks @linhdmn
-- **feat(providers):** add missing opencode-go reasoning effort variants ([#8441](https://github.com/diegosouzapw/OmniRoute/pull/8441)) — thanks @Prudhvivuda
-- **feat:** add Claude Opus 5 support ([#8464](https://github.com/diegosouzapw/OmniRoute/pull/8464)) — thanks @backryun
-- **feat(combos):** add select all / unselect all in Browse Catalog ([#8526](https://github.com/diegosouzapw/OmniRoute/pull/8526)) — thanks @JoshimOfficial
-- **feat(cli-tools):** add all Hermes Agent auxiliary model roles ([#8543](https://github.com/diegosouzapw/OmniRoute/pull/8543)) — thanks @leszek3737
-- **feat(ci):** block stale UI translations when an English value is rewritten ([#8574](https://github.com/diegosouzapw/OmniRoute/pull/8574))
-- **feat(providers):** flatten multi-turn history for gemini-web ([#8607](https://github.com/diegosouzapw/OmniRoute/pull/8607)) — thanks @Prudhvivuda
-- **feat(sse):** relay upstream 4xx error bodies verbatim on the Anthropic request path ([#8622](https://github.com/diegosouzapw/OmniRoute/pull/8622))
-- **feat:** Claude Code discovery aliases (surface non-Claude models in the /model picker) ([#8666](https://github.com/diegosouzapw/OmniRoute/pull/8666))
-- **feat(dashboard):** copy-paste settings.json block for Claude Code discovery ([#8722](https://github.com/diegosouzapw/OmniRoute/pull/8722))
-- **feat(quality):** temporary relax of complexity/file-size ratchets for v3.8.50-3.8.54 PREPARE phase ([#8767](https://github.com/diegosouzapw/OmniRoute/pull/8767))
-- **feat(db):** let the migration runner scan extra namespaced directories ([#8770](https://github.com/diegosouzapw/OmniRoute/pull/8770))
-- **feat(api):** prompt-cache health summary endpoint and analytics tab ([#8827](https://github.com/diegosouzapw/OmniRoute/pull/8827))
-### ⚡ Performance
-
-- **perf(db):** project columns + composite index in getProviderConnections ([#6918](https://github.com/diegosouzapw/OmniRoute/pull/6918)) — thanks @oyi77
-- **perf(db):** add jitter to stagger due-on-restart connections ([#6919](https://github.com/diegosouzapw/OmniRoute/pull/6919)) — thanks @oyi77
-- **perf(startup):** warm model catalog cache at module init ([#6920](https://github.com/diegosouzapw/OmniRoute/pull/6920)) — thanks @oyi77
-- **perf(db):** add temp_store=MEMORY pragma to SQLite init ([#6921](https://github.com/diegosouzapw/OmniRoute/pull/6921)) — thanks @oyi77
-- **perf(db):** cap modelLockouts eviction at 1000 entries ([#6923](https://github.com/diegosouzapw/OmniRoute/pull/6923)) — thanks @oyi77
-- **perf:** wrap ComboCard, HeroSection in React.memo ([#7070](https://github.com/diegosouzapw/OmniRoute/pull/7070)) — thanks @oyi77
-
-- **perf:** Date.now hoist, hasActiveDeltaValue hoist, buffer.split guard in SSE stream ([#7066](https://github.com/diegosouzapw/OmniRoute/pull/7066)) — thanks @oyi77
-- **perf(memory):** mitigate event-loop starvation under 3000+ provider connections ([#7719](https://github.com/diegosouzapw/OmniRoute/pull/7719)) — thanks @oyi77
-- **perf:** reduce long-context request copies ([#7862](https://github.com/diegosouzapw/OmniRoute/pull/7862)) — thanks @RaviTharuma
-- **perf:** lazy provider init, P2C quota cache, structuredClone elimination, getSettings→getCachedSettings (batch 2) ([#7893](https://github.com/diegosouzapw/OmniRoute/pull/7893)) — thanks @oyi77
-- **perf(api):** singleflight version lookups ([#8301](https://github.com/diegosouzapw/OmniRoute/pull/8301)) — thanks @RaviTharuma
-- **perf(api):** skip the full catalog build for quota-exclusive keys ([#8771](https://github.com/diegosouzapw/OmniRoute/pull/8771))
-### 🐛 Bug Fixes
-
-- **fix:** add re-entrancy guard to token health check sweep ([#6917](https://github.com/diegosouzapw/OmniRoute/pull/6917)) — thanks @oyi77
-- **fix(grok):** strip reasoningEffort for grok cli models ([#6938](https://github.com/diegosouzapw/OmniRoute/pull/6938)) — thanks @CitrusIce
-- **fix(6954,6953):** preserve system role + strip empty-signature thinking blocks ([#6982](https://github.com/diegosouzapw/OmniRoute/pull/6982)) — thanks @rafaumeu
-- **fix(6980):** classify Cloudflare AI neuron exhaustion as quota_exhausted ([#6983](https://github.com/diegosouzapw/OmniRoute/pull/6983)) — thanks @rafaumeu
-- **fix(dashboard):** hide disabled provider connections from combo builder ([#6984](https://github.com/diegosouzapw/OmniRoute/pull/6984))
-- **fix(providers):** cap grok-cli tools at 200 for cli-chat-proxy ([#6986](https://github.com/diegosouzapw/OmniRoute/pull/6986))
-- **fix(6848):** auto-cleanup for telemetry tables causing OOM ([#6988](https://github.com/diegosouzapw/OmniRoute/pull/6988)) — thanks @rafaumeu
-- **fix(models):** preserve direct-model combo metadata ([#6993](https://github.com/diegosouzapw/OmniRoute/pull/6993)) — thanks @JxnLexn
-- **fix:** DDG circuit breaker (#6999) + null content validation (#7000) ([#7001](https://github.com/diegosouzapw/OmniRoute/pull/7001)) — thanks @rafaumeu
-- **fix(models):** preserve chat-capable image model rows ([#7004](https://github.com/diegosouzapw/OmniRoute/pull/7004)) — thanks @xz-dev
-- **fix(codex):** preserve GPT-5.6 reasoning contract ([#7012](https://github.com/diegosouzapw/OmniRoute/pull/7012)) — thanks @xz-dev
-- **fix(base-red):** align least-used combo tests with executionKey usage keying ([#7015](https://github.com/diegosouzapw/OmniRoute/pull/7015))
-- **fix:** infer bare models from active synced catalogs ([#7028](https://github.com/diegosouzapw/OmniRoute/pull/7028)) — thanks @guanbear
-- **fix(auggie):** update model registry to match v0.32.0 CLI model IDs ([#7032](https://github.com/diegosouzapw/OmniRoute/pull/7032)) — thanks @oyi77
-- **fix(sse):** register ollama-cloud in USAGE_FETCHER_PROVIDERS (#7026) ([#7041](https://github.com/diegosouzapw/OmniRoute/pull/7041)) — thanks @alltomatos
-- **fix(quality):** read cognitiveComplexity= machine line in validate-release-green (#7009) ([#7042](https://github.com/diegosouzapw/OmniRoute/pull/7042)) — thanks @alltomatos
-- **fix(providers):** sanitize Claude native output_config.effort (#7044) ([#7050](https://github.com/diegosouzapw/OmniRoute/pull/7050)) — thanks @xier2012
-- **fix(combo):** treat maxInputTokens as an input-only cap in the context filter (#7039) ([#7052](https://github.com/diegosouzapw/OmniRoute/pull/7052)) — thanks @xier2012
-- **fix(antigravity):** collect native part.functionCall into tool calls (#7037) ([#7053](https://github.com/diegosouzapw/OmniRoute/pull/7053)) — thanks @xier2012
-- **fix(responses):** map mid-conversation system turns to developer role (#6954) ([#7056](https://github.com/diegosouzapw/OmniRoute/pull/7056)) — thanks @xier2012
-- **fix(combo):** least-used sorts by per-account executionKey (#7015) ([#7059](https://github.com/diegosouzapw/OmniRoute/pull/7059)) — thanks @xier2012
-- **fix(providers):** AgentRouter model import applies Claude Code wire image to /v1/models (#7016) ([#7060](https://github.com/diegosouzapw/OmniRoute/pull/7060)) — thanks @xier2012
-- **fix(translator):** preserve thinking.budget_tokens: 0 in Claude->Gemini (#6813) ([#7061](https://github.com/diegosouzapw/OmniRoute/pull/7061)) — thanks @xier2012
-- **fix(cloudflare-relay):** avoid invalid regex syntax in generated worker ([#7063](https://github.com/diegosouzapw/OmniRoute/pull/7063)) — thanks @SeaXen
-- **fix(dashboard):** strip browser-extension attrs before hydration ([#7073](https://github.com/diegosouzapw/OmniRoute/pull/7073)) — thanks @MrFadiAi
-- **fix(relay):** bound Bifrost stream lifetime ([#7093](https://github.com/diegosouzapw/OmniRoute/pull/7093)) — thanks @KooshaPari
-- **fix(sse):** recognize xiaomi-tokenplan mimo as a thinking-mode model ([#7098](https://github.com/diegosouzapw/OmniRoute/pull/7098))
-- **fix(codex):** strip regex lookaround from tool schema patterns ([#7100](https://github.com/diegosouzapw/OmniRoute/pull/7100))
-- **fix(openai):** strip reasoning_effort when GPT-5.x models carry function tools ([#7101](https://github.com/diegosouzapw/OmniRoute/pull/7101))
-- **fix(compression):** Headroom SmartCrusher skips developer-role messages (port from 9router#2132) ([#7102](https://github.com/diegosouzapw/OmniRoute/pull/7102))
-- **fix(providers):** surface a warning on 404 model_not_found in OpenAI-compatible Check (port from 9router#2032) ([#7103](https://github.com/diegosouzapw/OmniRoute/pull/7103))
-- **fix(executors):** forward X-Session-ID/X-Title agent metadata headers ([#7104](https://github.com/diegosouzapw/OmniRoute/pull/7104))
-- **fix(cli):** verify better-sqlite3 native binary is actually loadable ([#7105](https://github.com/diegosouzapw/OmniRoute/pull/7105))
-- **fix(sse):** sanitize non-ok Antigravity streaming error body (port from 9router#2461) ([#7106](https://github.com/diegosouzapw/OmniRoute/pull/7106))
-- **fix(providers):** add MiniMax image-generation provider ([#7108](https://github.com/diegosouzapw/OmniRoute/pull/7108))
-- **fix(sse):** handle space-separated arg name/value in Composer tool calls (port from 9router#1811) ([#7116](https://github.com/diegosouzapw/OmniRoute/pull/7116))
-- **fix(cli):** remove MITM DNS spoof entries before killing server process ([#7117](https://github.com/diegosouzapw/OmniRoute/pull/7117))
-- **fix(dashboard):** include never-tested connections in combo builder active-provider list (port from 9router#2057) ([#7118](https://github.com/diegosouzapw/OmniRoute/pull/7118))
-- **fix(api):** check Vercel SSO-protection PATCH response on relay deploy ([#7119](https://github.com/diegosouzapw/OmniRoute/pull/7119))
-- **fix(combos):** reject oversized fusion panels before fan-out (port from 9router#1905) ([#7120](https://github.com/diegosouzapw/OmniRoute/pull/7120))
-- **fix(combo):** detect empty content_block in streaming SSE peek ([#7121](https://github.com/diegosouzapw/OmniRoute/pull/7121))
-- **fix(oauth):** resolve Kiro AWS SSO cache client credentials by clientId match (port from 9router#1253) ([#7122](https://github.com/diegosouzapw/OmniRoute/pull/7122))
-- **fix(tests):** vitest UI suite back to green (69 fails triaged — WS6.1) ([#7127](https://github.com/diegosouzapw/OmniRoute/pull/7127))
-- **fix(auto):** use p95 fallback in speed factors ([#7128](https://github.com/diegosouzapw/OmniRoute/pull/7128)) — thanks @KooshaPari
-- **fix(models):** update Anthropic model contextLength to 1M ([#7129](https://github.com/diegosouzapw/OmniRoute/pull/7129)) — thanks @HouMinXi
-- **fix(ci):** raise dast-smoke timeout 12->25min (build alone eats up to 11min) ([#7139](https://github.com/diegosouzapw/OmniRoute/pull/7139))
-- **fix(compression):** lazy-load typescript in RTK codeStripper so prod-lean deploys don't break (#7096) ([#7164](https://github.com/diegosouzapw/OmniRoute/pull/7164)) — thanks @alltomatos
-- **fix(providers):** accept m365.cloud.microsoft for copilot-m365-web token (#7078) ([#7166](https://github.com/diegosouzapw/OmniRoute/pull/7166)) — thanks @xier2012
-- **fix(executors):** disable parallel tools for Codex Responses Lite ([#7171](https://github.com/diegosouzapw/OmniRoute/pull/7171)) — thanks @fenix007
-- **fix(tests+providers):** env-dependent tests exposed by GH-hosted runners (#6634 selfref shallow checkout + yuanbao live-network 401) ([#7174](https://github.com/diegosouzapw/OmniRoute/pull/7174))
-- **fix(combo):** reject known context overflow without exhausting providers ([#7177](https://github.com/diegosouzapw/OmniRoute/pull/7177)) — thanks @JxnLexn
-- **fix:** add static.cloudflareinsights.com to CSP script-src ([#7178](https://github.com/diegosouzapw/OmniRoute/pull/7178)) — thanks @oyi77
-- **fix:** extend turbopack ignoreIssue suppression to compression module (#7051) ([#7180](https://github.com/diegosouzapw/OmniRoute/pull/7180))
-- **fix:** recognize Ollama Cloud session usage-limit 429 as quota-exhausted (#7071) ([#7181](https://github.com/diegosouzapw/OmniRoute/pull/7181))
-- **fix:** preserve relayAuth for pool-referenced relay proxies (#5716) ([#7182](https://github.com/diegosouzapw/OmniRoute/pull/7182))
-- **fix:** wire adaptive context-budget dial into settings schema and DB (#7005) ([#7183](https://github.com/diegosouzapw/OmniRoute/pull/7183))
-- **fix(providers):** DuckDuckGo VQD 429 misclassified as 503 (#6996) ([#7185](https://github.com/diegosouzapw/OmniRoute/pull/7185))
-- **fix(db):** cap OOM probe-failure cycle in getDbInstance() (#6835) ([#7186](https://github.com/diegosouzapw/OmniRoute/pull/7186))
-- **fix:** stop opencode-go quota lookup defaulting to Z.AI endpoint (#7022) ([#7187](https://github.com/diegosouzapw/OmniRoute/pull/7187))
-- **fix(providers):** refresh OpenCode (oc) free-tier model catalog (#6998) ([#7188](https://github.com/diegosouzapw/OmniRoute/pull/7188))
-- **fix:** include proxyId when testing a saved registry proxy (#7080) ([#7189](https://github.com/diegosouzapw/OmniRoute/pull/7189))
-- **fix:** sanitize non-Latin1 chars in combo diagnostic headers (#6612) ([#7190](https://github.com/diegosouzapw/OmniRoute/pull/7190))
-- **fix:** raise main server keepAliveTimeout/headersTimeout above Node's 5s default (#7003) ([#7191](https://github.com/diegosouzapw/OmniRoute/pull/7191))
-- **fix:** route zai-web (and other registry-entry web-cookie providers) connection-test cookie probe through the configured proxy (#7058) ([#7192](https://github.com/diegosouzapw/OmniRoute/pull/7192))
-- **fix(providers):** reject chat requests for cloud-agent-only jules provider (#6699) ([#7193](https://github.com/diegosouzapw/OmniRoute/pull/7193))
-- **fix:** restore mobile grid-cols-1 fallback on quota page card grid (#7072) ([#7194](https://github.com/diegosouzapw/OmniRoute/pull/7194))
-- **fix:** wire modelAliases fetch into HermesAgentToolCard (#7151) ([#7195](https://github.com/diegosouzapw/OmniRoute/pull/7195))
-- **fix:** surface real claude-web error body for non-SSE 400s (#7134) ([#7196](https://github.com/diegosouzapw/OmniRoute/pull/7196))
-- **fix(dashboard):** agent bridge dns toggle uses POST, not PUT (#7157) ([#7197](https://github.com/diegosouzapw/OmniRoute/pull/7197))
-- **fix:** stop duplicating text in Gemini Web streamed responses (#7163) ([#7198](https://github.com/diegosouzapw/OmniRoute/pull/7198))
-- **fix:** filter hidden custom models out of legacy combo model picker (#7156) ([#7199](https://github.com/diegosouzapw/OmniRoute/pull/7199))
-- **fix(dashboard):** implement missing handleToggleSource on Free Pool tab (#7161) ([#7200](https://github.com/diegosouzapw/OmniRoute/pull/7200))
-- **fix:** honor combo-level proxy assignments from the registry (#7149) ([#7201](https://github.com/diegosouzapw/OmniRoute/pull/7201))
-- **fix(ci):** run quality gates on Mergify merge-queue draft PRs (anchor check never ran, queue always dequeued) ([#7202](https://github.com/diegosouzapw/OmniRoute/pull/7202))
-- **fix:** add dashboard-scoped typecheck gate covering src/app/(dashboard) TSX (#7033) ([#7203](https://github.com/diegosouzapw/OmniRoute/pull/7203))
-- **fix(guardrails/chat):** stop Vision Bridge hijacking credentialed models to opencode-zen ([#7204](https://github.com/diegosouzapw/OmniRoute/pull/7204)) — thanks @artickc
-- **fix(translator):** preserve Gemini thought parts as reasoning_content on the OpenAI bridge ([#7206](https://github.com/diegosouzapw/OmniRoute/pull/7206))
-- **fix(translator):** register openai response projection for gemini clients ([#7207](https://github.com/diegosouzapw/OmniRoute/pull/7207))
-- **fix(cli):** fast-path --version to skip full CLI bootstrap ([#7208](https://github.com/diegosouzapw/OmniRoute/pull/7208))
-- **fix:** honor PROVIDER_LIMITS_SYNC_SPACING_MS for local/API-key connections (#6916) ([#7214](https://github.com/diegosouzapw/OmniRoute/pull/7214))
-- **fix(api):** bulk-add API keys no longer overwrite existing connections ([#7234](https://github.com/diegosouzapw/OmniRoute/pull/7234))
-- **fix(sse):** route the public OpenAI GPT-5.6 family through the Responses API ([#7242](https://github.com/diegosouzapw/OmniRoute/pull/7242))
-- **fix(providers):** honor configured proxy on Grok Build egress ([#7244](https://github.com/diegosouzapw/OmniRoute/pull/7244))
-- **fix(nvidia):** expand NIM chat model catalog ([#7247](https://github.com/diegosouzapw/OmniRoute/pull/7247))
-- **fix(sse):** reconstruct Claude-format content in synthetic bypass responses ([#7248](https://github.com/diegosouzapw/OmniRoute/pull/7248))
-- **fix(build):** isolate Windows HOME/AppData during next build ([#7249](https://github.com/diegosouzapw/OmniRoute/pull/7249))
-- **fix(cli):** omniroute dashboard respects PORT env when --port is omitted (#7049) ([#7252](https://github.com/diegosouzapw/OmniRoute/pull/7252))
-- **fix(sse):** project non-streaming JSON back to the Gemini/Antigravity envelope ([#7255](https://github.com/diegosouzapw/OmniRoute/pull/7255))
-- **fix(combo):** fall back on Responses SSE failures ([#7256](https://github.com/diegosouzapw/OmniRoute/pull/7256)) — thanks @rushsinging
-- **fix(routing):** resolve nested combo-ref panel members in fusion strategy (#6764) ([#7259](https://github.com/diegosouzapw/OmniRoute/pull/7259))
-- **fix(usage):** reset logs and show provider names in analytics ([#7264](https://github.com/diegosouzapw/OmniRoute/pull/7264)) — thanks @SeaXen
-- **fix(sse):** silence noisy proxy-failure log on caller-initiated abort ([#7266](https://github.com/diegosouzapw/OmniRoute/pull/7266))
-- **fix(codex):** normalize nested Responses output content ([#7269](https://github.com/diegosouzapw/OmniRoute/pull/7269)) — thanks @JxnLexn
-- **fix(combo):** derive session stickiness key from Responses API .input, not just .messages (#7270) ([#7277](https://github.com/diegosouzapw/OmniRoute/pull/7277)) — thanks @alltomatos
-- **fix(antigravity):** wrap Pro fallback chain in try/catch for timeout resilience ([#7290](https://github.com/diegosouzapw/OmniRoute/pull/7290)) — thanks @HouMinXi
-- **fix(logs):** show saved provider names in request/provider log views ([#7294](https://github.com/diegosouzapw/OmniRoute/pull/7294)) — thanks @SeaXen
-- **fix(stream):** reconcile encrypted Codex reasoning visibility without mutating upstream item ([#7304](https://github.com/diegosouzapw/OmniRoute/pull/7304))
-- **fix(build):** packed tarball boot crash — server-ws timeout import escaped the package (#7065 class) ([#7308](https://github.com/diegosouzapw/OmniRoute/pull/7308))
-- **fix(skills):** register cli-skill-collector in the agent-skills catalog (Integration 2/2 base-red) ([#7310](https://github.com/diegosouzapw/OmniRoute/pull/7310))
-- **fix(db):** tolerate unavailable virtual table modules in stats ([#7313](https://github.com/diegosouzapw/OmniRoute/pull/7313)) — thanks @megamen32
-- **fix(router-eval):** retained-optimization gate cleanup ([#7318](https://github.com/diegosouzapw/OmniRoute/pull/7318)) — thanks @KooshaPari
-- **fix(ci):** Coverage job timeout 10->20min (lcov reporter pushed it past the old cap) ([#7342](https://github.com/diegosouzapw/OmniRoute/pull/7342))
-- **fix(electron):** normalize hashed standalone externals ([#7353](https://github.com/diegosouzapw/OmniRoute/pull/7353)) — thanks @tianrking
-- **fix(db):** stop a 'latest' path segment from disabling backups and migrations ([#7359](https://github.com/diegosouzapw/OmniRoute/pull/7359)) — thanks @danscMax
-- **fix(branding):** regenerate raster favicons — white mark was shipped without its gradient tile ([#7390](https://github.com/diegosouzapw/OmniRoute/pull/7390)) — thanks @vzts
-- **fix(test):** skip real DNS writes in MITM dynamic-import test ([#7398](https://github.com/diegosouzapw/OmniRoute/pull/7398)) — thanks @HouMinXi
-- **fix(antigravity):** streaming passthrough for non-streaming clients ([#7408](https://github.com/diegosouzapw/OmniRoute/pull/7408)) — thanks @HouMinXi
-- **fix(build):** align engines.node with SUPPORTED_NODE_RANGE (#7446) ([#7490](https://github.com/diegosouzapw/OmniRoute/pull/7490)) — thanks @alltomatos
-- **fix(api):** await params in Agent Bridge DNS route (Next.js 16) (#7271) ([#7492](https://github.com/diegosouzapw/OmniRoute/pull/7492)) — thanks @alltomatos
-- **fix(dashboard):** show Obsidian context source card ([#7500](https://github.com/diegosouzapw/OmniRoute/pull/7500)) — thanks @DKotsyuba
-- **fix(ci):** fetch full base history in pr-test-policy (shallow graft broke merge-base) ([#7501](https://github.com/diegosouzapw/OmniRoute/pull/7501))
-- **fix(sse):** preserve chat quota across mixed windows ([#7504](https://github.com/diegosouzapw/OmniRoute/pull/7504)) — thanks @webmasterarbez
-- **fix(oauth):** surface sanitized device-code error instead of a generic 500 ([#7511](https://github.com/diegosouzapw/OmniRoute/pull/7511)) — thanks @danscMax
-- **fix(oauth):** repair qwen + codebuddy-cn device-code endpoints ([#7517](https://github.com/diegosouzapw/OmniRoute/pull/7517)) — thanks @danscMax
-- **fix(mitm):** strip trailing assistant prefill to prevent upstream Anthropic 400 errors ([#7520](https://github.com/diegosouzapw/OmniRoute/pull/7520)) — thanks @chirag127
-- **fix(codex):** Test probe uses a ChatGPT-account-supported model (#7521) ([#7524](https://github.com/diegosouzapw/OmniRoute/pull/7524))
-- **fix(codex):** validate refresh_token on import before persisting (#7522) ([#7525](https://github.com/diegosouzapw/OmniRoute/pull/7525))
-- **fix(codex):** non-stream chat 502 'Response body is already used' (single-reader peek) ([#7526](https://github.com/diegosouzapw/OmniRoute/pull/7526))
-- **fix(oauth):** surface tunnel hint when Codex OAuth runs on a remote host (#7523) ([#7527](https://github.com/diegosouzapw/OmniRoute/pull/7527))
-- **fix(sse):** preserve custom tool output images ([#7540](https://github.com/diegosouzapw/OmniRoute/pull/7540)) — thanks @loulanyue
-- **fix(combo):** failover when upstream SSE is truncated mid-lifecycle ([#7545](https://github.com/diegosouzapw/OmniRoute/pull/7545)) — thanks @Chewji9875
-- **fix(dashboard):** prefer public endpoint URLs ([#7547](https://github.com/diegosouzapw/OmniRoute/pull/7547)) — thanks @nguyenha935
-- **fix(cli):** refresh runtime detection accurately ([#7552](https://github.com/diegosouzapw/OmniRoute/pull/7552)) — thanks @nguyenha935
-- **fix(ui):** improve React Flow dark theme ([#7553](https://github.com/diegosouzapw/OmniRoute/pull/7553)) — thanks @nguyenha935
-- **fix(i18n):** treat **MISSING** sync placeholders as absent in EN fallback (#7258) ([#7556](https://github.com/diegosouzapw/OmniRoute/pull/7556))
-- **fix(cli):** Windows cert check/uninstall key off the real CA identity, not a hardcoded legacy host (#7275) ([#7557](https://github.com/diegosouzapw/OmniRoute/pull/7557))
-- **fix(sse):** feed compression pipeline the authoritative vision capability (#7237) ([#7560](https://github.com/diegosouzapw/OmniRoute/pull/7560))
-- **fix(dashboard):** providers model-name filter matches live/synced catalog (#7250) ([#7561](https://github.com/diegosouzapw/OmniRoute/pull/7561))
-- **fix(db):** pre-init sql.js WASM ahead of any getDbInstance() consumer (#7288) ([#7562](https://github.com/diegosouzapw/OmniRoute/pull/7562))
-- **fix(dashboard):** resolve costs page 500 from out-of-scope t() in TopListCard (#7272) ([#7564](https://github.com/diegosouzapw/OmniRoute/pull/7564))
-- **fix(dashboard):** surface rate-limit warning on 429 chat-probe (#7284) ([#7565](https://github.com/diegosouzapw/OmniRoute/pull/7565))
-- **fix(sse):** lazy-load playwright in claudeTurnstileSolver (#7265) ([#7566](https://github.com/diegosouzapw/OmniRoute/pull/7566))
-- **fix(sse):** combo failover for OpenAI streams truncated without finish_reason (#7285) ([#7568](https://github.com/diegosouzapw/OmniRoute/pull/7568))
-- **fix(cli):** reuse win32-aware locateCommand in tool-detector (#7279) ([#7569](https://github.com/diegosouzapw/OmniRoute/pull/7569))
-- **fix(codex):** #7536 check content-type before touching response.body in peek ([#7570](https://github.com/diegosouzapw/OmniRoute/pull/7570))
-- **fix(sse):** stop dropping tool_search and leaking OpenAI-only params in Responses->Chat translation ([#7571](https://github.com/diegosouzapw/OmniRoute/pull/7571))
-- **fix(api):** resolve provider display name and dedup byModel on normalized key (#7534, #7535) ([#7573](https://github.com/diegosouzapw/OmniRoute/pull/7573))
-- **fix(mitm):** route Claude Code standalone MITM traffic ([#7574](https://github.com/diegosouzapw/OmniRoute/pull/7574)) — thanks @dongwook-chan
-- **fix(sse):** stop per-byte enumeration of binary image bytes in log redaction (#7297) ([#7576](https://github.com/diegosouzapw/OmniRoute/pull/7576))
-- **fix(sse):** split effort/reasoning suffix off pinned cursor model ids (#7289) ([#7577](https://github.com/diegosouzapw/OmniRoute/pull/7577))
-- **fix(chatgpt-web):** recognize update_content.messages[] celsius WS frames (#7357) ([#7578](https://github.com/diegosouzapw/OmniRoute/pull/7578))
-- **fix(sse):** 401 model-not-supported lockout + sticky quota-exhausted release (#7268, #7387) ([#7580](https://github.com/diegosouzapw/OmniRoute/pull/7580))
-- **fix(antigravity):** allow cloudcode envelope through messages guard ([#7582](https://github.com/diegosouzapw/OmniRoute/pull/7582)) — thanks @dongwook-chan
-- **fix(sse):** sanitize empty-signature thinking blocks + hoist strict-provider system messages ([#7583](https://github.com/diegosouzapw/OmniRoute/pull/7583))
-- **fix(sse):** honor per-model targetFormat override for zai/glm-coding-apikey (#7364) ([#7584](https://github.com/diegosouzapw/OmniRoute/pull/7584))
-- **fix(sse):** clamp glm-4.6v max_tokens to the 32768 ceiling (#7364) ([#7585](https://github.com/diegosouzapw/OmniRoute/pull/7585))
-- **fix(cli):** log Codex Responses WebSocket history/usage per logical turn, not per connection ([#7588](https://github.com/diegosouzapw/OmniRoute/pull/7588))
-- **fix(providers):** derive static model catalogs for search providers from searchTypes ([#7589](https://github.com/diegosouzapw/OmniRoute/pull/7589))
-- **fix(stream-readiness):** bump timeout for heavy Claude-format reasoning replicas ([#7612](https://github.com/diegosouzapw/OmniRoute/pull/7612)) — thanks @herjarsa
-- **fix(translator):** synthesize tool call chunks from response.completed batched output ([#7613](https://github.com/diegosouzapw/OmniRoute/pull/7613)) — thanks @ekinnee
-- **fix(embeddings):** add lmstudio to embedding provider registry ([#7614](https://github.com/diegosouzapw/OmniRoute/pull/7614)) — thanks @ekinnee
-- **fix(combo):** auto-clear stale session pins and emit recovery hints on combo exhaustion ([#7625](https://github.com/diegosouzapw/OmniRoute/pull/7625)) — thanks @herjarsa
-- **fix(providers):** unify connection and routing flows ([#7629](https://github.com/diegosouzapw/OmniRoute/pull/7629)) — thanks @nguyenha935
-- **fix(db):** dedupe bulk-imported proxies by full credential tuple (#7594) ([#7644](https://github.com/diegosouzapw/OmniRoute/pull/7644)) — thanks @alltomatos
-- **fix(api):** allow text-to-image on dual-modality models + revive HuggingFace image host ([#7648](https://github.com/diegosouzapw/OmniRoute/pull/7648)) — thanks @danscMax
-- **fix(stryker):** add Microsoft Designer test to tap.testFiles ([#7659](https://github.com/diegosouzapw/OmniRoute/pull/7659))
-- **fix(dashboard):** cut UI import chain from connection persist module (CI shard base-red) ([#7677](https://github.com/diegosouzapw/OmniRoute/pull/7677))
-
-- **fix(perplexity-web):** stop empty-content responses from live schematized SSE ([#6955](https://github.com/diegosouzapw/OmniRoute/pull/6955)) — thanks @artickc
-- **fix(dashboard):** make quota cards container responsive ([#7027](https://github.com/diegosouzapw/OmniRoute/pull/7027)) — thanks @xz-dev
-- **fix(nvidia):** restore GLM-5.2 reasoning on NIM (#7215) ([#7296](https://github.com/diegosouzapw/OmniRoute/pull/7296)) — thanks @backryun
-- **fix(i18n):** complete Vietnamese dashboard localization and runtime fixes ([#7493](https://github.com/diegosouzapw/OmniRoute/pull/7493)) — thanks @nguyenha935
-- **fix(providers):** migrate muse-spark-web from GraphQL to WebSocket protocol ([#7528](https://github.com/diegosouzapw/OmniRoute/pull/7528)) — thanks @Ajeesh25353646
-- **fix(combo):** expose computed context_length via /api/combos for accurate OC plugin display ([#7633](https://github.com/diegosouzapw/OmniRoute/pull/7633)) — thanks @herjarsa
-- **fix(api):** enumerate tiered auto combo endpoints in /api/combos/auto ([#7662](https://github.com/diegosouzapw/OmniRoute/pull/7662)) — thanks @ekinnee
-- **fix(dashboard):** topology reflects connection health + clears finished requests ([#7672](https://github.com/diegosouzapw/OmniRoute/pull/7672)) — thanks @danscMax
-- **fix(kimi-coding):** capture and replay reasoning for thinking-mode turns ([#7673](https://github.com/diegosouzapw/OmniRoute/pull/7673)) — thanks @xz-dev
-- **fix(ci):** merge-train --fast mirrors test:unit subdir allowlist ([#7688](https://github.com/diegosouzapw/OmniRoute/pull/7688))
-- **fix(sse):** start credential-health sweep at boot so stale web sessions recover ([#7689](https://github.com/diegosouzapw/OmniRoute/pull/7689)) — thanks @danscMax
-- **fix(cursor):** discover models via official CLI command ([#7692](https://github.com/diegosouzapw/OmniRoute/pull/7692)) — thanks @makcimbx
-- **fix(quota):** fix antigravity/agy multi-model quota skipping in combos ([#7695](https://github.com/diegosouzapw/OmniRoute/pull/7695)) — thanks @irvandikky
-- **fix(usage):** preserve account identity history ([#7700](https://github.com/diegosouzapw/OmniRoute/pull/7700)) — thanks @xz-dev
-- **fix(db):** update proxies on password rotation ([#7707](https://github.com/diegosouzapw/OmniRoute/pull/7707)) — thanks @floze-the-genius
-- **fix(providers):** correct Chutes registry baseUrl (#7621) ([#7708](https://github.com/diegosouzapw/OmniRoute/pull/7708))
-- **fix(routing):** strip prompt_cache_key for NVIDIA NIM (#7617) ([#7709](https://github.com/diegosouzapw/OmniRoute/pull/7709))
-- **fix(providers):** degrade Arena (lmarena) cookie validation redirect to unsupported (#7542) ([#7710](https://github.com/diegosouzapw/OmniRoute/pull/7710))
-- **fix(claude-web):** unify Turnstile/executor/fast-path User-Agents behind one fingerprint (#7548) ([#7711](https://github.com/diegosouzapw/OmniRoute/pull/7711))
-- **fix(sse):** authenticate CLIProxyAPI fallback/passthrough legs with a dedicated credential (#7645) ([#7712](https://github.com/diegosouzapw/OmniRoute/pull/7712))
-- **fix(sse):** proactively refresh Grok Build OAuth token before dispatch (#7610) ([#7715](https://github.com/diegosouzapw/OmniRoute/pull/7715))
-- **fix(providers):** classify ambiguous Mistral 401 instead of hard auth error (#7638) ([#7718](https://github.com/diegosouzapw/OmniRoute/pull/7718))
-- **fix(security):** bump adm-zip >=0.6.0 + exact host matching in mitm DNS test ([#7732](https://github.com/diegosouzapw/OmniRoute/pull/7732))
-- **fix(icons):** fall back to Stepfun Mono when Color component is absent … ([#7743](https://github.com/diegosouzapw/OmniRoute/pull/7743)) — thanks @Dan-ex-hub
-- **fix(stream):** suppress `</think>` close marker for Responses API clients ([#7747](https://github.com/diegosouzapw/OmniRoute/pull/7747)) — thanks @xz-dev
-- **fix(sse):** wire settings.wildcardAliases into model resolution (#7693) ([#7748](https://github.com/diegosouzapw/OmniRoute/pull/7748))
-- **fix(authz):** classify forge/jcode CLI settings routes as LOCAL_ONLY (#7263) ([#7749](https://github.com/diegosouzapw/OmniRoute/pull/7749))
-- **fix(routing):** honor eye-icon hidden models for no-auth providers in auto-combo (#7620) ([#7750](https://github.com/diegosouzapw/OmniRoute/pull/7750))
-- **fix(sse):** persist rotated Gemini web-session cookies via onCredentialsRefreshed (#7676) ([#7751](https://github.com/diegosouzapw/OmniRoute/pull/7751))
-- **fix(docs):** heal release-green docs drift + eslint any-suppression drift (#7253) ([#7755](https://github.com/diegosouzapw/OmniRoute/pull/7755))
-- **fix(mcp):** copy undici into dist/node_modules to prevent hollow-package shadowing crash (#7701) ([#7756](https://github.com/diegosouzapw/OmniRoute/pull/7756))
-- **fix(packaging):** move fumadocs-mdx to devDependencies (#7661) ([#7757](https://github.com/diegosouzapw/OmniRoute/pull/7757))
-- **fix(ci):** build API-only smoke workflows backend-only to fix dast-smoke timeouts (#7226) ([#7758](https://github.com/diegosouzapw/OmniRoute/pull/7758))
-- **fix(cli):** load DATA_DIR/server.env as fallback for .env on Electron migration (#7302) ([#7759](https://github.com/diegosouzapw/OmniRoute/pull/7759))
-- **fix(cli):** split outboundUrlGuard's DB helpers so setup-opencode packages cleanly (#7682) ([#7760](https://github.com/diegosouzapw/OmniRoute/pull/7760))
-- **fix(notion-web):** production-ready labels, multi-workspace, inference, usage (FINAL) ([#7768](https://github.com/diegosouzapw/OmniRoute/pull/7768)) — thanks @artickc
-- **fix(kimi):** expose K3 reasoning effort levels ([#7776](https://github.com/diegosouzapw/OmniRoute/pull/7776)) — thanks @xz-dev
-- **fix(compression):** apply compression combo assignments to routing combos ([#7779](https://github.com/diegosouzapw/OmniRoute/pull/7779)) — thanks @ekinnee
-- **fix(i18n):** regenerate Polish UI locale from English ([#7782](https://github.com/diegosouzapw/OmniRoute/pull/7782)) — thanks @leszek3737
-- **fix(combo):** retry transient errors in pipeline strategy ([#7794](https://github.com/diegosouzapw/OmniRoute/pull/7794)) — thanks @AndrianBalanescu
-- **fix(quality):** register nvidia-quota-phase1 and service-provider-plugin-registry in stryker tap.testFiles ([#7796](https://github.com/diegosouzapw/OmniRoute/pull/7796))
-- **fix(stream):** synthesize terminal finish_reason chunk when upstream omits it (#7800) ([#7804](https://github.com/diegosouzapw/OmniRoute/pull/7804)) — thanks @AndrianBalanescu
-- **fix(plugins):** 5 bugs on the plugin path (3 Windows-only, 2 all-platform) ([#7806](https://github.com/diegosouzapw/OmniRoute/pull/7806)) — thanks @tmone
-- **fix(cli):** register ESM alias resolver for @/ paths under global install ([#7808](https://github.com/diegosouzapw/OmniRoute/pull/7808)) — thanks @rafaumeu
-- **fix(auth):** gate invalid-key check on isRequireApiKeyEnabled for embeddings and web-fetch (#7785) ([#7810](https://github.com/diegosouzapw/OmniRoute/pull/7810)) — thanks @AndrianBalanescu
-- **fix(ci):** repair release regressions exposed by clean runs ([#7812](https://github.com/diegosouzapw/OmniRoute/pull/7812)) — thanks @backryun
-- **fix(rerank):** add voyage format adapter for request/response translation (#7809) ([#7813](https://github.com/diegosouzapw/OmniRoute/pull/7813)) — thanks @AndrianBalanescu
-- **fix(antigravity):** attempt onboarding when projectId is empty (#5193 regression of #2541) ([#7815](https://github.com/diegosouzapw/OmniRoute/pull/7815)) — thanks @rafaumeu
-- **fix(stream):** emit terminal SSE frames on mid-stream upstream failure (#7699) ([#7816](https://github.com/diegosouzapw/OmniRoute/pull/7816)) — thanks @AndrianBalanescu
-- **fix(sse):** strip orphaned tool_use before antigravity/Vertex Claude dispatch (#7752) ([#7822](https://github.com/diegosouzapw/OmniRoute/pull/7822))
-- **fix(translator):** sanitize tool_result.tool_use_id symmetrically with tool_use.id (#7705) ([#7823](https://github.com/diegosouzapw/OmniRoute/pull/7823))
-- **fix(oauth):** require chatgptUserId agreement for Codex account dedup (#7737) ([#7825](https://github.com/diegosouzapw/OmniRoute/pull/7825))
-- **fix(db):** purge in-memory key-health state when a provider connection is deleted (#7740) ([#7826](https://github.com/diegosouzapw/OmniRoute/pull/7826))
-- **fix(compression):** keep a retrievable preamble instead of a bare CCR marker (#7746) ([#7827](https://github.com/diegosouzapw/OmniRoute/pull/7827))
-- **fix(db):** log fatal boot-time SQLite driver-cascade failure before propagating (#7773) ([#7828](https://github.com/diegosouzapw/OmniRoute/pull/7828))
-- **fix(docker):** repair tls-client-node native binary after --ignore-scripts (#7802) ([#7829](https://github.com/diegosouzapw/OmniRoute/pull/7829))
-- **fix(auth):** restore TICK_MS in tokenHealthCheck (ReferenceError on startup) ([#7830](https://github.com/diegosouzapw/OmniRoute/pull/7830))
-- **fix(cli):** fix Windows CLI detection false negatives (#7753, #7774) ([#7831](https://github.com/diegosouzapw/OmniRoute/pull/7831))
-- **fix(docs):** document CREDENTIAL_REDACTION_ENABLED and GHE_COPILOT_OAUTH_CLIENT_ID (#7793) ([#7833](https://github.com/diegosouzapw/OmniRoute/pull/7833))
-- **fix(dashboard):** fix collapsed quota card session/weekly order (#7764) ([#7834](https://github.com/diegosouzapw/OmniRoute/pull/7834))
-- **fix(dashboard):** mirror connection-row action-icon spacing under RTL (#7680) ([#7835](https://github.com/diegosouzapw/OmniRoute/pull/7835))
-- **fix:** avoid cmd.exe spawn on Windows by using os.hostname() before execSync fallback ([#7841](https://github.com/diegosouzapw/OmniRoute/pull/7841)) — thanks @tientien17
-- **fix(usage):** harden account identity reconciliation ([#7843](https://github.com/diegosouzapw/OmniRoute/pull/7843)) — thanks @xz-dev
-- **fix(cli):** use rundll32 instead of cmd.exe for Windows browser fallback in dashboard command ([#7844](https://github.com/diegosouzapw/OmniRoute/pull/7844)) — thanks @tientien17
-- **fix:** add native lifecycle-aware health endpoint ([#7852](https://github.com/diegosouzapw/OmniRoute/pull/7852)) — thanks @RaviTharuma
-- **fix:** reserve chat admission before body parsing ([#7853](https://github.com/diegosouzapw/OmniRoute/pull/7853)) — thanks @RaviTharuma
-- **fix:** bound quadratic session-dedup memory growth ([#7855](https://github.com/diegosouzapw/OmniRoute/pull/7855)) — thanks @RaviTharuma
-- **fix(compression):** enable OmniGlyph for Claude Fable 5 ([#7863](https://github.com/diegosouzapw/OmniRoute/pull/7863)) — thanks @enjoyer-hub
-- **fix(notion-web):** add browser fingerprint headers to reduce Cloudflare challenges ([#7864](https://github.com/diegosouzapw/OmniRoute/pull/7864)) — thanks @HassiyYT
-- **fix(mitm):** gate Agent Bridge Repair on sudo password (#7836) ([#7865](https://github.com/diegosouzapw/OmniRoute/pull/7865)) — thanks @skutanjir
-- **fix(rerank):** honor the connection's pinned proxy on rerank calls (#7350) ([#7867](https://github.com/diegosouzapw/OmniRoute/pull/7867))
-- **fix(compression):** skip CCR on tool outputs to preserve agent loop ([#7869](https://github.com/diegosouzapw/OmniRoute/pull/7869)) — thanks @herjarsa
-- **fix(vision-bridge):** reroute auto/ prefix to vision model when images present ([#7871](https://github.com/diegosouzapw/OmniRoute/pull/7871)) — thanks @herjarsa
-- **fix(opencode-plugin):** support separate management read token ([#7885](https://github.com/diegosouzapw/OmniRoute/pull/7885)) — thanks @RaviTharuma
-- **fix(sse):** CC bridge loses OpenAI-format image input (OpenCode/Kilo/Cline → AgentRouter) ([#7888](https://github.com/diegosouzapw/OmniRoute/pull/7888))
-- **fix(combo):** strip boolean reasoning field for opencode-go providers ([#7891](https://github.com/diegosouzapw/OmniRoute/pull/7891)) — thanks @AndrianBalanescu
-- **fix(notion-web):** accept OpenAI content-parts arrays in transcript ([#7896](https://github.com/diegosouzapw/OmniRoute/pull/7896)) — thanks @artickc
-- **fix(notion-web):** reuse threadId across OpenAI multi-turn (no new chat each request) ([#7900](https://github.com/diegosouzapw/OmniRoute/pull/7900)) — thanks @artickc
-- **fix(gemini):** strip OpenAI "strict" tool-schema keyword for Antigravity ([#7901](https://github.com/diegosouzapw/OmniRoute/pull/7901)) — thanks @Witroch4
-- **fix(antigravity):** collect native functionCall parts in SSE collector ([#7902](https://github.com/diegosouzapw/OmniRoute/pull/7902)) — thanks @Witroch4
-- **fix(sse):** recover invalid Anthropic thinking signatures once ([#7906](https://github.com/diegosouzapw/OmniRoute/pull/7906)) — thanks @insoln
-- **fix(resilience):** don't cool down accounts or trip the breaker on client aborts ([#7908](https://github.com/diegosouzapw/OmniRoute/pull/7908)) — thanks @insoln
-- **fix(dashboard):** preserve quota cutoff drafts ([#7909](https://github.com/diegosouzapw/OmniRoute/pull/7909)) — thanks @hydraxman
-- **fix(providers):** treat public-host 302 as valid in Gemini Web connection test (#7859) ([#7917](https://github.com/diegosouzapw/OmniRoute/pull/7917))
-- **fix(providers):** read reasoning_text in Claude-format response translator (#7856) ([#7919](https://github.com/diegosouzapw/OmniRoute/pull/7919))
-- **fix(dashboard):** safely render structured error objects in Request Logs detail (#7845) ([#7920](https://github.com/diegosouzapw/OmniRoute/pull/7920))
-- **fix(dashboard):** repair monaco deep import broken by 0.56 exports map (#7897) ([#7922](https://github.com/diegosouzapw/OmniRoute/pull/7922))
-- **fix(autostart):** adopt 9Router VBS startup to suppress console flash on Windows ([#7925](https://github.com/diegosouzapw/OmniRoute/pull/7925)) — thanks @tientien17
-- **fix(translators):** normalize TitleCase tool names for non-Anthropic models ([#7926](https://github.com/diegosouzapw/OmniRoute/pull/7926)) — thanks @nramabad
-- **fix(api):** resolve local provider models via dashboard catalog fallback ([#7927](https://github.com/diegosouzapw/OmniRoute/pull/7927)) — thanks @ekinnee
-- **fix(auto):** pool accounts by provider model ([#7928](https://github.com/diegosouzapw/OmniRoute/pull/7928)) — thanks @adrianaryaputra
-- **fix(perplexity-web):** multi-step empty content + advanced-quota cooldown ([#7930](https://github.com/diegosouzapw/OmniRoute/pull/7930)) — thanks @artickc
-- **fix(ccr):** resolve principal via OMNIROUTE_API_KEY env var on stdio MCP transport ([#7932](https://github.com/diegosouzapw/OmniRoute/pull/7932)) — thanks @ekinnee
-- **fix(combo):** context-aware fallback ignores model_context_override ([#7933](https://github.com/diegosouzapw/OmniRoute/pull/7933)) — thanks @tmone
-- **fix(i18n):** preserve remaining Vietnamese localization ([#7935](https://github.com/diegosouzapw/OmniRoute/pull/7935)) — thanks @nguyenha935
-- **fix(mitm):** gate Agent Bridge DNS and Trust Cert on sudo password (#7938) ([#7939](https://github.com/diegosouzapw/OmniRoute/pull/7939)) — thanks @skutanjir
-- **fix(providers):** route iflytek/sparkdesk to Spark's OpenAI-compatible host ([#7942](https://github.com/diegosouzapw/OmniRoute/pull/7942)) — thanks @FenjuFu
-- **fix(sse):** preserve parallel_tool_calls for GPT-5.6 delegation under Codex Responses Lite (#7821) ([#7957](https://github.com/diegosouzapw/OmniRoute/pull/7957))
-- **fix(providers):** copilot-m365-web fails loudly on empty turns + tier-aware enterprise invocation (#7858, #7870) ([#7958](https://github.com/diegosouzapw/OmniRoute/pull/7958))
-- **fix(providers):** treat unreliable web-cookie /models probe status as unsupported, not valid (#7857) ([#7959](https://github.com/diegosouzapw/OmniRoute/pull/7959))
-- **fix(api):** add amazon-q to the static model catalog (#7820) ([#7960](https://github.com/diegosouzapw/OmniRoute/pull/7960))
-- **fix:** parse Gemini 429 RetryInfo.retryDelay for model lockout (#7940) ([#7961](https://github.com/diegosouzapw/OmniRoute/pull/7961))
-- **fix(quality):** tolerate ESLint's trailing unpruned-suppressions text in validate-release-green (#7837) ([#7962](https://github.com/diegosouzapw/OmniRoute/pull/7962))
-- **fix(cli):** translate missing sqlite bindings error into actionable guidance (#7868) ([#7963](https://github.com/diegosouzapw/OmniRoute/pull/7963))
-- **fix(cli):** spawn opencode.cmd shim with shell:true on win32 (#7913) ([#7964](https://github.com/diegosouzapw/OmniRoute/pull/7964))
-- **fix(dashboard):** correct block-extra-Claude-usage toggle copy to match quarantine behavior (#7918) ([#7965](https://github.com/diegosouzapw/OmniRoute/pull/7965))
-- **fix(api):** classify /api/acp/agents as loopback-only (#7948) ([#7966](https://github.com/diegosouzapw/OmniRoute/pull/7966))
-- **fix(auth):** restore configurable HEALTHCHECK_BATCH_SIZE dropped by #7719 (#7875) ([#7970](https://github.com/diegosouzapw/OmniRoute/pull/7970))
-- **fix(test):** widen ratelimit-admission pollUntil deadline to 10s (#7842) ([#7971](https://github.com/diegosouzapw/OmniRoute/pull/7971))
-- **fix(pricing):** clarify disabled automatic sync status ([#7972](https://github.com/diegosouzapw/OmniRoute/pull/7972)) — thanks @RaviTharuma
-- **fix(combo):** exempt content_filter from empty-content detection ([#7973](https://github.com/diegosouzapw/OmniRoute/pull/7973)) — thanks @HouMinXi
-- **fix(embeddings):** support secure multimodal inputs ([#7978](https://github.com/diegosouzapw/OmniRoute/pull/7978)) — thanks @RaviTharuma
-- **fix(resilience):** cap exactCooldownMs against maxCooldownMs (#7940) ([#7980](https://github.com/diegosouzapw/OmniRoute/pull/7980)) — thanks @ekinnee
-- **fix(electron):** derive macOS Helper name from execPath to remove 2nd Dock icon (#7941) ([#8002](https://github.com/diegosouzapw/OmniRoute/pull/8002))
-- **fix(chatcore):** report string-reason client aborts as 499, not 502 (#7907) ([#8011](https://github.com/diegosouzapw/OmniRoute/pull/8011)) — thanks @Long-Feeds
-- **fix(models):** drop generic catalog siblings of specialty surfaces (#8015) ([#8021](https://github.com/diegosouzapw/OmniRoute/pull/8021)) — thanks @RaviTharuma
-- **fix(models):** stop inventing chat capabilities for specialty surfaces (#8016) ([#8022](https://github.com/diegosouzapw/OmniRoute/pull/8022)) — thanks @RaviTharuma
-- **fix(capabilities):** resolve models.dev specialty rows across provider keys (#8017) ([#8023](https://github.com/diegosouzapw/OmniRoute/pull/8023)) — thanks @RaviTharuma
-- **fix(models):** attach models.dev pricing to GET /v1/models entries (#8018) ([#8025](https://github.com/diegosouzapw/OmniRoute/pull/8025)) — thanks @RaviTharuma
-- **fix(grok-cli):** require full auth.json on OAuth paste import (#7610) ([#8027](https://github.com/diegosouzapw/OmniRoute/pull/8027)) — thanks @RaviTharuma
-- **fix(grok-cli):** sanitize function_call_output before Grok Build dispatch (#7611) ([#8030](https://github.com/diegosouzapw/OmniRoute/pull/8030)) — thanks @RaviTharuma
-- **fix(sse):** bound forwarded response headers ([#8041](https://github.com/diegosouzapw/OmniRoute/pull/8041)) — thanks @insoln
-- **fix(sse):** replace spoofable .includes() PromptQL issuer check with hostname comparison (#8029) ([#8042](https://github.com/diegosouzapw/OmniRoute/pull/8042))
-- **fix(sse):** bound Codex SSE peek read with per-read timeout (#8020) ([#8043](https://github.com/diegosouzapw/OmniRoute/pull/8043))
-- **fix(cli):** stop double-prefixing combo model ids in opencode plugin static catalog (#7976) ([#8047](https://github.com/diegosouzapw/OmniRoute/pull/8047))
-- **fix(antigravity):** scope 404 model-not-found lockout to exact model + bare-model autopick ([#8050](https://github.com/diegosouzapw/OmniRoute/pull/8050)) — thanks @AndrianBalanescu
-- **fix:** repair pre-existing red gates on the release/v3.8.49 tip ([#8055](https://github.com/diegosouzapw/OmniRoute/pull/8055))
-- **fix(oauth):** honor connectionId on token refresh so email-less providers don't duplicate ([#8062](https://github.com/diegosouzapw/OmniRoute/pull/8062)) — thanks @insoln
-- **fix:** classify Google quota exhaustion responses ([#8071](https://github.com/diegosouzapw/OmniRoute/pull/8071)) — thanks @rafaumeu
-- **fix(providers):** refresh duckduckgo-web catalog to current Duck.ai wire ids (#8000) ([#8079](https://github.com/diegosouzapw/OmniRoute/pull/8079))
-- **fix(security):** decouple request PII redaction from injection mode ([#8102](https://github.com/diegosouzapw/OmniRoute/pull/8102)) — thanks @RaviTharuma
-- **fix(providers):** discover live AGY models ([#8123](https://github.com/diegosouzapw/OmniRoute/pull/8123)) — thanks @adevwithpurpose
-- **fix(guardrails):** align INPUT_SANITIZER request masking gate (#8093) ([#8124](https://github.com/diegosouzapw/OmniRoute/pull/8124)) — thanks @RaviTharuma
-- **fix(providers):** refresh Baidu ERNIE and Qianfan website URLs (#6271) ([#8128](https://github.com/diegosouzapw/OmniRoute/pull/8128)) — thanks @TrackCrewGalore
-- **fix(stream):** add logging to empty catch blocks in stream error handling ([#8143](https://github.com/diegosouzapw/OmniRoute/pull/8143)) — thanks @chirag127
-- **fix(sse):** stop Codex/Responses sanitizer turning system image_url into output_text (#8089) ([#8147](https://github.com/diegosouzapw/OmniRoute/pull/8147))
-- **fix(db):** register SIGHUP handler and stop force-killing server on win32 stop paths (#8045) ([#8148](https://github.com/diegosouzapw/OmniRoute/pull/8148))
-- **fix(providers):** add missing poe registry baseUrl entry (#8082) ([#8149](https://github.com/diegosouzapw/OmniRoute/pull/8149))
-- **fix(routing):** anchor quota cache on globalThis for cross-chunk consistency (#8065) ([#8150](https://github.com/diegosouzapw/OmniRoute/pull/8150))
-- **fix(responses):** close namespace round-trip for Responses-Chat translation (#7936) ([#8151](https://github.com/diegosouzapw/OmniRoute/pull/8151)) — thanks @RCrushMe
-- **fix(oauth):** warn instead of silently opening unreachable localhost redirect for LAN-IP Codex/xAI/Grok OAuth (#8046) ([#8152](https://github.com/diegosouzapw/OmniRoute/pull/8152))
-- **fix(db):** stop closing the sql.js singleton in getDbInstance() probe/reopen (#7494) ([#8153](https://github.com/diegosouzapw/OmniRoute/pull/8153))
-- **fix(sse):** run compression pipeline per turn in Codex Responses WS bridge (#8052) ([#8154](https://github.com/diegosouzapw/OmniRoute/pull/8154))
-- **fix(cli):** merge node bin dir into CLI healthcheck PATH for codex detection (#8036) ([#8156](https://github.com/diegosouzapw/OmniRoute/pull/8156))
-- **fix(sse):** anonymous fingerprint fallback for keyless Pollinations image gen (#8085) ([#8157](https://github.com/diegosouzapw/OmniRoute/pull/8157))
-- **fix(cli):** surface the real spawn error in process supervisor (#8091) ([#8158](https://github.com/diegosouzapw/OmniRoute/pull/8158))
-- **fix:** strip internal reasoning placeholder from user-visible content (#8081) ([#8162](https://github.com/diegosouzapw/OmniRoute/pull/8162)) — thanks @Dingding-leo
-- **fix(combos):** expose synced reasoning-effort variants in Combo Builder model picker (#8072) ([#8165](https://github.com/diegosouzapw/OmniRoute/pull/8165)) — thanks @Dingding-leo
-- **fix(windows):** add windowsHide to all child process spawns (#8131) ([#8167](https://github.com/diegosouzapw/OmniRoute/pull/8167)) — thanks @Dingding-leo
-- **fix(cursor):** bridge native tools to client calls ([#8171](https://github.com/diegosouzapw/OmniRoute/pull/8171)) — thanks @makcimbx
-- **fix(security):** bound JWT-extraction regexes to prevent polynomial ReDoS (CodeQL #754/#755/#756) ([#8173](https://github.com/diegosouzapw/OmniRoute/pull/8173))
-- **fix(#8141):** log pending request counter decrement failures ([#8179](https://github.com/diegosouzapw/OmniRoute/pull/8179)) — thanks @rafaumeu
-- **fix(#8135):** suppress sql.js build warning via non-analyzable dynamic import ([#8184](https://github.com/diegosouzapw/OmniRoute/pull/8184)) — thanks @rafaumeu
-- **fix(#8093):** align INPUT_SANITIZER_ENABLED default to true across all docs ([#8185](https://github.com/diegosouzapw/OmniRoute/pull/8185)) — thanks @rafaumeu
-- **fix(combo):** skip remaining same-provider targets on 401/403 auth failure ([#8195](https://github.com/diegosouzapw/OmniRoute/pull/8195)) — thanks @rafaumeu
-- **fix(compression):** make memo key model-independent for non-vision engines ([#8196](https://github.com/diegosouzapw/OmniRoute/pull/8196)) — thanks @rafaumeu
-- **fix(resilience):** add max/step to NumberField for provider cooldown inputs (#8107) ([#8203](https://github.com/diegosouzapw/OmniRoute/pull/8203)) — thanks @rafaumeu
-- **fix(providers):** fix Azure AI Foundry multi-model discovery and per-deployment connection testing (#8174) ([#8206](https://github.com/diegosouzapw/OmniRoute/pull/8206)) — thanks @not-knope
-- **fix(logs):** stop the async-EPIPE log-flood loop at its ignition point ([#8207](https://github.com/diegosouzapw/OmniRoute/pull/8207)) — thanks @Tasogarre
-- **fix(sse):** surface OpenRouter mid-stream error chunks instead of a false empty success ([#8210](https://github.com/diegosouzapw/OmniRoute/pull/8210)) — thanks @hartmark
-- **fix(sse):** Gemini malformed function-call handling + tool_choice translation ([#8211](https://github.com/diegosouzapw/OmniRoute/pull/8211)) — thanks @hartmark
-- **fix(sse):** tool-incapable provider handling (AI Horde + Responses content-collapse scoping) ([#8212](https://github.com/diegosouzapw/OmniRoute/pull/8212)) — thanks @hartmark
-- **fix(sse):** Gemini TPM/RPD quota classification + combo cooldown-wait resilience ([#8213](https://github.com/diegosouzapw/OmniRoute/pull/8213)) — thanks @hartmark
-- **fix(services):** resolve and record a real pid when adopting a service ([#8218](https://github.com/diegosouzapw/OmniRoute/pull/8218)) — thanks @seanford
-- **fix(memory):** resolve remote embedding dimensions for reindex (#8074) ([#8220](https://github.com/diegosouzapw/OmniRoute/pull/8220)) — thanks @Prudhvivuda
-- **fix(dashboard):** correct machine-translated Korean UI strings in ko.json ([#8224](https://github.com/diegosouzapw/OmniRoute/pull/8224)) — thanks @MichaelYcJo
-- **fix(devin-cli):** refresh shared model catalog ([#8227](https://github.com/diegosouzapw/OmniRoute/pull/8227)) — thanks @backryun
-- **fix(claude-web):** align session transport and fallback ([#8230](https://github.com/diegosouzapw/OmniRoute/pull/8230)) — thanks @backryun
-- **fix:** restore OAuth auto-refresh for gemini-cli connections ([#8232](https://github.com/diegosouzapw/OmniRoute/pull/8232)) — thanks @seanford
-- **fix:** normalize Codex URLs and dashboard regressions ([#8233](https://github.com/diegosouzapw/OmniRoute/pull/8233)) — thanks @nguyenha935
-- **fix(api):** narrow claudeClassifierCompat auto trigger so stop_sequences alone no longer short-circuits (#8189) ([#8236](https://github.com/diegosouzapw/OmniRoute/pull/8236))
-- **fix(gemini):** drop HARM_CATEGORY_CIVIC_INTEGRITY from the default Gemini safety settings (#8231) ([#8238](https://github.com/diegosouzapw/OmniRoute/pull/8238))
-- **fix(backend):** word-boundary-safe tool-result truncation in lite compression mode (#8169) ([#8239](https://github.com/diegosouzapw/OmniRoute/pull/8239))
-- **fix(providers):** filter unsupported family-fallback candidates against the provider catalog (#8134) ([#8240](https://github.com/diegosouzapw/OmniRoute/pull/8240))
-- **fix(translator):** synthesize tool call chunks from `response.completed` batched output when upstream omits individual `output_item.added`/`done` events, fixing `finish_reason: "stop"` instead of `"tool_calls"` for agentic clients ([#180](https://github.com/diegosouzapw/OmniRoute/issues/180), [#3980](https://github.com/diegosouzapw/OmniRoute/issues/3980))
-- **fix(api):** Vercel Relay deploy now checks the Deployment Protection (SSO) PATCH response and surfaces `ssoProtectionWarning` when Vercel rejects it, instead of silently activating a relay that later returns an undiagnosed `403 Access denied`. (thanks @ricatix) ([#1037](https://github.com/diegosouzapw/OmniRoute/issues/1037))
-- **fix(oauth):** resolve Kiro AWS SSO cache client credentials by matching the token's own `clientId` (including tokens with a direct `clientId` field instead of `clientIdHash`) instead of a region/latest-expiry guess, fixing spurious "Bad credentials" on refresh when multiple stale SSO client registrations are cached (thanks @XCrag).
-- **fix(combo):** streaming Claude responses whose content block opens (`content_block_start`) and closes with no usable text/tool_use — a shape some upstreams return for tool-heavy requests on HTTP 200 — are now detected by `validateResponseQuality`'s SSE peek and trigger combo failover instead of being forwarded to the client as a silent empty completion (thanks @heishen6). ([#1382](https://github.com/diegosouzapw/OmniRoute/issues/1382))
-- **fix(codex):** strip regex `pattern` lookaround (lookahead/lookbehind) from tool JSON Schemas on the Codex/OpenAI native passthrough path — previously only the translated-request path coerced tool schemas, so a `pattern` like `^(?=.*@).+$` reached OpenAI unmodified and was rejected with `regex lookaround is not supported`. (thanks @evinjohnn) (#7100)
-- **fix(cli):** `stopMitm()` now removes /etc/hosts DNS-spoof entries before killing the MITM server process, closing the window where a client's DNS still resolved a target host to `127.0.0.1` while nothing was listening there — the cause of `connect ECONNREFUSED 127.0.0.1:443` right after stopping the MITM proxy (thanks @dionisius95).
-- **fix(sse):** Cursor Composer/Auto tool calls that separate the arg name and value with a space instead of a newline (e.g. `path /Users/.../test`) no longer produce empty-valued, malformed argument keys, fixing silent no-op Write/tool calls. (thanks @way-art)
-- **fix(dashboard):** the "Custom Models" add/edit form now has a "Vision capable" toggle so a custom OpenAI-compatible model can be manually flagged as vision-capable when the provider's discovery metadata doesn't report an image input modality (thanks @nguyenphi37)
-- **fix(combos):** fusion combos now reject an oversized panel (>40 models by default, tunable via `fusionTuning.maxPanel`) with a clean 400 before fanning out, instead of buffering dozens of concurrent full responses in memory and OOM-crashing the whole container. (thanks @fontvu)
-- **fix(providers):** the OpenAI-compatible "Check" validation flow now surfaces a warning when the chat-completions probe returns `404` (e.g. `model_not_found`) instead of silently passing as `Valid` — a bogus/non-standard model id (Featherless/OpenRouter-style `vendor/model` typos) previously went undetected at Check time and only surfaced once a real request tripped the per-model lockout. (thanks @advane204f)
-- **fix(dashboard):** include never-tested custom provider connections in the combo builder's active-provider list so their models load without requiring a manual connection test first. (thanks @fajarbossit)
-- **fix(executors):** forward agent-supplied `X-Session-ID`/`X-Title` metadata headers to upstream providers — previously dropped for every client outside the `x-opencode-*` allowlist. (thanks @chitholian) (#7104)
-- **fix(sse):** Antigravity streaming requests that hit a non-ok upstream response (e.g. a 403) no longer pipe the raw upstream bytes straight through to the client — a binary/non-UTF8 error body (observed as gzip-magic-byte garbage) is now routed through the same sanitized `buildAntigravityUpstreamError()` path the non-streaming branch already used, instead of corrupting the client-visible error message. Regression guard: `tests/unit/antigravity-streaming-error-body-sanitized-2461.test.ts` — thanks @Duongkhanhtool
-- **fix(providers):** MiniMax Text-to-Image now works — a `minimax` image-generation provider (`minimax-image` format, `image-01`/`image-01-live` models) was registered, since MiniMax previously had entries in the music/audio/video registries but none in the image registry, so any MiniMax image-model request fell through to a 404/unmatched-format response. (thanks @felipeleite)
-- **fix(cli):** the runtime self-heal now verifies a cached `better-sqlite3` native binary actually loads for the running Node before trusting it — the old check only inspected the file's magic bytes (ELF/Mach-O/PE header), so a binary built for a different Node ABI passed validation and segfaulted the process on first use instead of triggering a rebuild. (thanks @mrprohack) (#7105) ([#2493](https://github.com/diegosouzapw/OmniRoute/issues/2493))
-- **fix(openai):** strip `reasoning_effort`/`reasoning` for GPT-5.x models on the raw `openai` Chat Completions surface when the request carries function `tools` — upstream rejects that combination with HTTP 400 ("Function tools with reasoning_effort are not supported ... Please use /v1/responses instead"), and the dashboard has no `reasoning_effort:"none"` override to work around it client-side — thanks @techsolutionmta
-- fix(providers): preserve relayAuth for vercel/deno/cloudflare relay proxies referenced by-id from the no-auth-provider Proxy Pool dropdown (#5716)
-- fix(providers): wire the Devin cloud-agent provider into the generic provider-page validator and static model catalog, matching the existing `jules` cloud-agent pattern (#6142)
-- **fix(providers):** refresh Baidu ERNIE + Qianfan provider website URLs to current developer landing pages ([#6271](https://github.com/diegosouzapw/OmniRoute/issues/6271)) — thanks @TrackCrewGalore
-- fix(providers): honor a provider-level proxy assigned to no-auth providers like MiMoCode Free (#6272)
-- fix(api): merge tool_call continuation deltas that carry only `id` (no `index`) so tool-call arguments are no longer split/lost in request/response logs (#6276)
-- **fix(providers):** modernize the `lmarena` provider for the Arena.ai rebrand — route chat through `arena.ai` create-evaluation with Chrome TLS impersonation, seed a static Direct-chat Text/Search + Image catalog, and keep the `lmarena`/`lma` wire id for back-compat ([#6280](https://github.com/diegosouzapw/OmniRoute/pull/6280)) — thanks @backryun
-- **fix(providers):** web-provider model discovery updated — qwen-web uses the slash-terminated models endpoint (avoiding a blocked 307 redirect), and kimi-web matches the current request shape (POST with bearer + `kimi-auth` cookie replay) with its catalog refreshed to the current non-agent models (#6308 — thanks @janeza2).
-- **fix(logs):** the request-log detail modal no longer reopens by itself after being closed — a stale in-flight detail refresh resolved after close and re-triggered the modal open state (#6323 — thanks @xz-dev).
-- **fix(providers):** update SenseNova Token Plan support — register the token-plan model ids/constants and adjust the SenseNova registry so token-plan accounts route correctly (#6330 — thanks @xz-dev).
-- fix(providers): give v0-vercel-web its own alias so its credentials are detected (#6343)
-- fix(providers): route AgentRouter key validation through the CC wire image so a valid key no longer 403s as "Invalid API key" (#6377)
-- fix(db): stop legacy log-archive migration from deleting the live app-logger directory and crashing startup on a stat/stream race (#6401, #6799)
-- fix(docs): document Turbopack build memory tradeoff and `OMNIROUTE_USE_TURBOPACK=0` webpack fallback for RAM-constrained machines (#6409)
-- fix(compression): surface silently-dropped stacked-pipeline steps (session-dedup, ccr) and stop the aggregate inflation guard from misfiring on a genuine no-op (#6479, #6480, #6491)
-- fix(providers): honor the `max_token` capability override in the reasoning-token-buffer output cap (#6524)
-- **fix(dashboard):** the onboarding tier-flow diagram rendered broken — its SVGs lived in the repo-root `images/` (not a served path); moved to `public/images/` so Next.js serves them (#6538 — thanks @ianriizky).
-- **fix(routing):** the `auto` combo's no-auth candidate pool now honors a disabled provider connection's own `isActive=false` (the toggle on the main Providers grid card), not just the separate global `blockedProviders` setting — disabling opencode/mimocode/etc. via the grid toggle no longer leaves it in rotation ([#6557](https://github.com/diegosouzapw/OmniRoute/issues/6557)).
-- **fix(sse):** server-tool literal names (e.g. `web_search`) are preserved in message history and `tool_choice` instead of being namespaced/rewritten, so follow-up turns referencing those tools keep working (#6586 — thanks @MikeTuev).
-- fix(sse): sanitize non-Latin1 characters before embedding combo diagnostics in HTTP headers, preventing a ByteString crash on quality-check failure (#6612)
-- fix(api): recognize OpenRouter reasoning/reasoning_details in non-streaming OpenAI-to-Claude conversion (#6623)
-- fix(db): share one in-flight sql.js load across concurrent `preInitSqlJs()` callers to stop the boot-time thundering-herd re-decode of the whole database file (#6628)
-- fix(db): unwrap lone named-parameter objects before `sql.js` `stmt.bind()` so `@`/`:`/`$`-style named placeholders bind correctly instead of throwing "Wrong API use" (#6802)
-- **fix(db): break probe-failed/restore loop on large storage.sqlite** (#6632 — thanks @KooshaPari).
-- fix(ci): exclude check-test-masking.test.ts's own tautology fixtures from the diff-based test-masking gate and recognize `✗` in validate-release-green's failure-line detector (#6634)
-- fix(routing): recognize Kimi-style "exceeded model token limit" 400 as context overflow so combo fallback continues to the next target (#6637)
-- **fix(cli):** Claude Code installed via WinGet is now detected on Windows (the WinGet install path was missing from the binary lookup) (#6647 — thanks @enjoyer-hub).
-- **fix(providers):** removed obsolete/defunct providers from the catalog (glhf, kluster, cablyai, inclusionai) (#6675 — thanks @backryun).
-- **fix(sse):** requests rejected before `handleChatCore` (circuit-breaker/cooldown gate or combo with all targets exhausted) are now recorded in `usage_history` too, so a key whose traffic was entirely gate-rejected no longer shows "zero requests" in the per-API-key usage counter (#6698).
-- fix(providers): reject chat-completions requests for cloud-agent-only providers like jules instead of silently mis-routing them to OpenAI's endpoint (#6699)
-- **fix(sse):** unwrap bare `{function:{…}}` tools so OpenAI-shape clients no longer have tools silently dropped in Claude translation. (thanks @samir-abis)
-- **fix(oauth):** stop merging distinct Codex OAuth logins that share an email but lack a verifiable account id, preventing silent token overwrite. (thanks @lucasjustinudin)
-- **fix(codex):** detect "model at capacity"/overloaded errors embedded in a 200-OK SSE stream and surface them as a real error so account fallback rotates, instead of passing them through as a successful response. (thanks @ryanngit)
-- **fix(volcengine):** clamp `max_tokens` to the VolcEngine Ark endpoint cap for the Kimi model so oversized values no longer 400. (thanks @whale9820)
-- **fix(antigravity):** surface aborted/malformed Gemini tool calls (e.g. `MALFORMED_FUNCTION_CALL`) as an explicit non-`end_turn` finish reason instead of a silent clean completion. (thanks @anhdiepmmk)
-- **fix(routing):** the reasoning-token headroom buffer clamps to the model's explicit output cap instead of inflating past it, and `getExplicitModelOutputCap` falls through to the registry/spec cap when a synced capability row exists without a numeric `limit_output` ([#6714](https://github.com/diegosouzapw/OmniRoute/pull/6714)) — thanks @xz-dev
-- **fix(api):** `omniroute health` (and `health components`/`health watch`) returned `Error: HTTP 404` ([#6677](https://github.com/diegosouzapw/OmniRoute/issues/6677)) — `bin/cli/commands/health.mjs` called `apiFetch("/api/health", ...)`, a route that was moved to `GET /api/monitoring/health` (`src/app/api/monitoring/health/route.ts`) without updating the CLI; `src/app/api/health/` on disk only has `degradation/route.ts` and `ping/route.ts`, no top-level handler. `runHealthCommand()`/`runHealthComponentsCommand()` now call `/api/monitoring/health` and read its actual payload shape (`activeConnections`, `circuitBreakers: {open, halfOpen, closed}`, `memoryUsage`) instead of the old, nonexistent `requests`/`breakers`/`cache`/`memory` fields. Regression guard: `tests/unit/cli-health-monitoring-route.test.ts`. ([#6717](https://github.com/diegosouzapw/OmniRoute/pull/6717))
-- **fix(startup):** webpack build broke on case-insensitive filesystems (macOS APFS default, Windows) with a casing-collision warning plus "not exported" errors in `StudioConfigPane.tsx`/`ChatTab.tsx` (#6584) — `src/app/(dashboard)/dashboard/playground/components/ReasoningControls.tsx` (the component) and `reasoningControls.ts` (the utils module) shared the same lower-cased stem in the same directory, and two importers used the extensionless form `from "./reasoningControls"`, the exact resolution path that becomes ambiguous once casing is folded. Renamed the utils module to `reasoningControlUtils.ts` (no collision) and updated the 3 import sites. Regression guard: `tests/unit/case-collision-6584.test.ts` (scans `src/`/`open-sse/` for any same-directory, case-only filename collision). (#6584) ([#6718](https://github.com/diegosouzapw/OmniRoute/pull/6718))
-- **fix(build):** Turbopack production build emitted an "Overly broad patterns can lead to build performance issues" warning per entry point importing `src/lib/agentSkills/generator.ts` (603 warnings reported on v3.8.46, up from 379 on v3.8.45) ([#6582](https://github.com/diegosouzapw/OmniRoute/issues/6582)) — `generator.ts`'s `outputBase` is built as `path.isAbsolute(outputDir) ? outputDir : path.join(process.cwd(), outputDir)`, where `outputDir` is a runtime function parameter, not a compile-time literal, so Turbopack's build-time file-tracing analyzer can't statically narrow the several dynamic `readdirSync`/`rmSync`/`readFileSync`/`writeFileSync` call sites a few lines below and falls back to a project-wide glob; #6366's commit message claimed to "anchor the base path with a literal" but the shipped code never did. Since this fs access is legitimate and bounded (`skills/<id>/SKILL.md`, ~48 known IDs), `next.config.mjs`'s `turbopack.ignoreIssue` (Next.js 16.2+) now suppresses this specific, known-benign diagnostic, mirroring the existing `webpack.ignoreWarnings`/`isNextIntlExtractorDynamicImportWarning` precedent already in the same file for the webpack path. Regression guard: `tests/unit/next-config.test.ts` (asserts the `turbopack.ignoreIssue` rule shape targeting `src/lib/agentSkills/**`). ([#6720](https://github.com/diegosouzapw/OmniRoute/pull/6720))
-- **fix(providers):** Codex Desktop requests to `gpt-5.3-codex-spark` failed with `[400]: Tool 'image_generation' is not supported with gpt-5.3-codex-spark`, even on paid-plan accounts ([#6651](https://github.com/diegosouzapw/OmniRoute/issues/6651)) — `CodexExecutor.transformRequest` (`open-sse/executors/codex.ts`) only dropped the Codex Desktop-injected `image_generation` hosted tool when `isCodexFreePlan()` matched the account's plan, with no awareness that Spark-scope Codex models reject `image_generation` upstream regardless of plan. `dropImageGeneration` now also drops it when `getCodexModelScope(model) === "spark"` (the existing Spark classifier from `open-sse/config/codexQuotaScopes.ts`), independent of account plan. Regression guard: `tests/unit/codex-spark-image-generation.test.ts` (thanks @alltomatos for independently catching and fixing it via #6819). ([#6721](https://github.com/diegosouzapw/OmniRoute/pull/6721))
-- **fix(providers):** the provider quota card's weekly/session bars re-sorted by remaining percentage instead of staying in a fixed, deterministic order ([#6687](https://github.com/diegosouzapw/OmniRoute/issues/6687)) — `QuotaCardExpanded.tsx`'s `sortQuotasByRemaining()` (added in #5977) was applied unconditionally via `useMemo(() => sortQuotasByRemaining(quotas), [quotas])`, undoing the deterministic `CODEX_QUOTA_ORDER`/`GLM_QUOTA_ORDER` window order `quotaParsing.ts`'s `sortCodexOrder()`/`sortGlmOrder()` (added in #6336) already established for Codex and the GLM family — since #6336 never touched `QuotaCardExpanded.tsx`, the two orderings never composed, so e.g. a Codex `session` window with less headroom than `weekly` rendered after it instead of staying first. A new `hasFixedQuotaOrder()` (`quotaParsing.ts`) and `resolveQuotaDisplayOrder()` (`QuotaCardExpanded.tsx`) now skip the remaining-% re-sort for providers with a fixed window order, threading `providerId` from `QuotaCard.tsx` through to the display layer; every other provider still gets the remaining-% sort. Regression guard: `tests/unit/quota-card-expanded-fixed-order-6687.test.ts`. ([#6722](https://github.com/diegosouzapw/OmniRoute/pull/6722))
-- **fix(i18n):** pt-BR was missing 194 UI keys present in `en.json` — a real, silent data-sync gap, not covered by any duplicate/mislabeled #6694 (that issue's 9 `providers.*` keys are disjoint, present-but-untranslated sentinels caused by a separate `providerText()` fallback bug) ([#6695](https://github.com/diegosouzapw/OmniRoute/issues/6695)) — `scripts/i18n/sync-ui-keys.mjs` (which mirrors newly-added `en.json` keys into every locale) wasn't re-run after recent `en.json` additions, and the CI `i18n:check-ui-coverage` gate only fails a locale below an 80% threshold, so pt-BR stayed green at 93.8% coverage despite the gap. Backfilled all 194 missing keys into `src/i18n/messages/pt-BR.json` (translated to Brazilian Portuguese, no leftover `__MISSING__` markers) via `npm run i18n:sync-ui -- --locale=pt-BR` + manual translation. Regression guard: `tests/unit/i18n-pt-br.test.ts` (new case asserting full `en.json`→`pt-BR.json` key parity, so a future drift fails a fast unit test instead of silently degrading the coverage percentage). ([#6723](https://github.com/diegosouzapw/OmniRoute/pull/6723))
-- **fix(startup):** `omniroute --mcp` crashed at Node ESM link time with `ERR_MODULE_NOT_FOUND` for `ioredis` on installs where the published MCP bundle didn't happen to have `ioredis` rescued from a parent `node_modules` ([#6559](https://github.com/diegosouzapw/OmniRoute/issues/6559)) — `src/shared/utils/rateLimiter.ts` had a top-level static `import Redis from "ioredis"`; that module is only ever reached via a lazy `await import(...)` several call-sites deep in the MCP tool chain, but esbuild's `--packages=external` bundling of the MCP server (`scripts/build/prepublish.ts` Step 8.5) still hoisted rateLimiter.ts's own static import into a real top-level ESM import in the compiled `dist/open-sse/mcp-server/server.js`, forcing Node to resolve `ioredis` at module-link time — before any `--mcp` startup code runs — and `ioredis` is not guaranteed to ship in the MCP-only bundle's `node_modules`. `getRedisClient()` now lazily imports `ioredis` on first use (matching the established soft-dependency pattern in `src/lib/quota/redisQuotaStore.ts`) while still throwing synchronously when Redis isn't configured. Regression guard: `tests/unit/build/mcp-bundle-no-eager-ioredis.test.ts` (bundles the real MCP server entrypoint with the exact publish-time esbuild flags and asserts no top-level static `ioredis` import remains, while the pre-existing lazy `await import("ioredis")` in `redisQuotaStore.ts` stays intact). ([#6725](https://github.com/diegosouzapw/OmniRoute/pull/6725))
-- **fix(providers):** Kiro sent the adaptive-thinking `additionalModelRequestFields` envelope for `claude-sonnet-4.5`/`claude-haiku-4.5`, which Kiro/CodeWhisperer rejects upstream with a raw `[400]: additionalModelRequestFields is not supported for this model` ([#6576](https://github.com/diegosouzapw/OmniRoute/issues/6576)) — `buildKiroPayload()` (`open-sse/translator/request/openai-to-kiro.ts`) gated the field on the generic Anthropic-API `supportsReasoning()` capability flag, which is `true` for both models on Anthropic's direct API but does not reflect what Kiro's CodeWhisperer backend actually accepts; only `claude-sonnet-5` is confirmed adaptive-thinking-capable there. A new Kiro-specific allowlist (`supportsKiroAdaptiveThinking()` in `open-sse/translator/request/openai-to-kiro/adaptiveThinking.ts`) now gates the envelope instead. Regression guard: `tests/unit/repro-6576-kiro-thinking-unsupported-model.test.ts`. ([#6726](https://github.com/diegosouzapw/OmniRoute/pull/6726))
-- **fix(translator):** Cursor's local **Subagent** tool call is no longer rejected with `cloud_base_branch may only be specified when environment equals cloud` — the Responses→Chat tool-arg cleanup (`stripEmptyOptionalToolArgs`) was scoped to Claude Code's `Read` tool only, so Cursor's `Subagent` tool passed through with the cloud-only `cloud_base_branch: ""` (Cursor treats an empty string as "specified" and rejects the call before starting the local subagent). The cleanup now covers an allowlist of `Read` + `Subagent`; arbitrary tools are still left untouched (empty strings/arrays can be valid payloads for them). Regression guard: `tests/unit/openai-responses-subagent-strip-2446.test.ts`. (thanks @like3213934360-lab)
-- **fix(translator):** GLM 5.2 (and other OpenAI-compatible upstreams that stream a tool call's `id` and `function.name` in **separate** SSE chunks) no longer produce an empty tool name / `No such tool available:` error through the Claude `/messages` path — the `openai-to-claude` streaming translator emitted `content_block_start` immediately on the id-only chunk with an empty `name`, and the Claude SSE protocol cannot patch a block after it is emitted, so the later name-only chunk was silently dropped. It now **defers** `content_block_start` until the tool name arrives (falling back to starting the block when arguments arrive first), so the emitted `tool_use` always carries the real name. Regression guard: `tests/unit/openai-to-claude-glm-split-tool-name-2077.test.ts`. (thanks @itiwant)
-- **fix(resilience):** OmniRoute didn't respect an exhausted Ollama Cloud (or any other apikey-category provider) quota — it retried the account seconds later instead of waiting out the real reset window ([#6638](https://github.com/diegosouzapw/OmniRoute/issues/6638)) — `shouldPreserveQuotaSignalsFor429()`/`checkFallbackError()` (`open-sse/services/accountFallback.ts`) only applied body-text quota classification (daily/monthly/weekly quota-exhausted detection) to OAuth-category providers; apikey-category 429s (Ollama Cloud, OpenAI, etc.) always fell through to the generic short rate-limit cooldown regardless of what the error body said, and `parseRetryFromErrorText()` also had no support for day-granularity reset hints ("Your quota will reset in 3 days.") — only Xh/Ym/Zs combos. An explicit quota-exhausted signal in the body (`looksLikeQuotaExhausted()`) now overrides the apikey-category default via the new `shouldPreserveQuotaSignals()` (`open-sse/services/quotaResetParsing.ts`), and `parseDayGranularityResetMs()` parses whole-day reset countdowns so the real multi-day window is honored instead of a few seconds of backoff. Regression guard: `tests/unit/issue-6638-ollama-quota.test.ts` + 2 aligned `tests/unit/account-fallback-service.test.ts` cases that previously asserted the buggy rate_limit_exceeded/undefined-dailyQuotaExhausted behavior for apikey-provider quota text. ([#6731](https://github.com/diegosouzapw/OmniRoute/pull/6731))
-- **fix(resilience):** a combo step "pinned" to one fingerprint account (mimocode/mcode/opencode multi-account providers) never actually resolved to that account, so it couldn't fail over when the pinned account was depleted ([#6696](https://github.com/diegosouzapw/OmniRoute/issues/6696), relates #6612) — the combo builder UI encodes an account pin as a composite connectionId (`${rowId}|fp|${fingerprint}`, `src/lib/combos/builderOptions.ts`), but `expandTargetsByFingerprints()` (`open-sse/services/combo/fingerprintExpansion.ts`) looked that composite string up directly in `connectionById` (keyed by real DB row ids), got `undefined`, and passed the target through unchanged, still carrying the bogus composite id — so downstream credential resolution could never match it either. `expandTargetsByFingerprints()` now splits the `|fp|` composite id back into the real connection row id + the pinned fingerprint (new `splitFingerprintPin()` helper) before any lookup, resolving the target to the real connectionId (with the pinned fingerprint carried on the new `pinnedFingerprint` field) instead of the inert composite string. Regression guard: `tests/unit/combo-fingerprint-pin-6696.test.ts`. ([#6732](https://github.com/diegosouzapw/OmniRoute/pull/6732))
-- **fix(api):** Responses passthrough emitted event-only SSE frames (no `data:` line) for every dropped commentary event, breaking the OpenAI Python SDK's `sse.json()` parser ([#6561](https://github.com/diegosouzapw/OmniRoute/issues/6561)), follow-up to #6199/#6232 — the commentary-drop `continue;` branches in `open-sse/utils/stream.ts` skipped the `data:` line for a dropped commentary event but never cleared the already-buffered `event:` line for that same frame, so the next blank line flushed the stale `event:` line alone. Both drop sites now call `clearPendingPassthroughEvent()` before `continue`, discarding the buffered prefix along with the dropped payload; the commentary-drop decision itself was extracted into a new `open-sse/utils/responsesCommentaryDrop.ts` so the fix does not grow the frozen `stream.ts`. Regression guard: `tests/unit/responses-commentary-event-frame-6561.test.ts` (realistic `event:\ndata:\n\n` frames — the existing #6199 test only used bare `data:` lines and never exercised this path). ([#6735](https://github.com/diegosouzapw/OmniRoute/pull/6735))
-- **fix(compression):** `/api/compression/preview`'s top-level `originalTokens`/`compressedTokens` diverged from `engineBreakdown[0]`'s counts for the same single-engine run (tiktoken outer counts vs the `JSON.stringify(...).length/4` estimate per engine), worst on small inputs. A new `reconcileSingleEngineTokens()` overwrites the single-engine breakdown entry with the outer, more accurate figures; multi-step pipeline breakdowns are left untouched ([#6488](https://github.com/diegosouzapw/OmniRoute/issues/6488)). Regression guard: `tests/unit/compression/preview-outer-engine-token-reconcile-6488.test.ts`. ([#6741](https://github.com/diegosouzapw/OmniRoute/pull/6741))
-- **fix(resilience):** account selection could pick an account already out of quota upstream on every credentialed route except `chat`/`codex` ([#6686](https://github.com/diegosouzapw/OmniRoute/issues/6686)) — `getProviderCredentials()` (`src/sse/services/auth.ts`) only skips a connection when a *local cache* already flags it exhausted (`isQuotaExhaustedForRequest`/`src/domain/quotaCache.ts`); it never itself calls the registered upstream `QuotaFetcher`. Only `getProviderCredentialsWithQuotaPreflight()` performs that live upstream check, and it was wired into exactly 2 call sites (`src/sse/handlers/chat.ts`, `src/app/api/internal/codex-responses-ws/route.ts`) — every other credentialed route (`rerank`, `images/generations`, `images/edits`, `audio/transcriptions|speech|translations`, `videos/generations`, `music/generations`, `ocr`, `providers/[provider]/embeddings`, `providers/[provider]/images/generations`, `web/fetch`, `moderations`, `search`) called the plain, cache-only selector, so an account whose cache entry was never populated (e.g. its first request landed on one of these routes) could be selected even at 0% quota remaining. Those 14 call sites now go through `getProviderCredentialsWithQuotaPreflight()` instead, matching chat/codex coverage. Regression guard: `tests/unit/issue-6686-quota-preflight-coverage.test.ts` (static check that none of the routes call the plain selector anymore + a behavioral check that the preflight-aware selector blocks a 100%-used account). ([#6742](https://github.com/diegosouzapw/OmniRoute/pull/6742))
-- **fix(api):** `reasoning_content` (extended-thinking text) was silently dropped from `/v1/chat/completions` SSE on the `claude-web` and `v0-vercel-web` executors ([#6662](https://github.com/diegosouzapw/OmniRoute/issues/6662)) — every chunk builder in both adapters hardcoded `delta: { content: ... }` with no reasoning path, unlike the established pattern already used by `default.ts`/`deepseek-web.ts`/`bedrock.ts` and the real-Anthropic-API `claude-to-openai.ts` translator (`thinking_delta` → `reasoning_content`). `v0-vercel-web.ts` now forwards an upstream `delta.reasoning_content` field (streaming and non-streaming) the same way `deepseek-web.ts` does. `claude-web.ts`'s `buildClaudeStreamingResponse` now maps a `content_block_start`(`type: "thinking"`)/`content_block_delta`(`delta.thinking`) pair onto `delta.reasoning_content`, and `claude-web/payload.ts`'s `transformToClaude()` no longer hardcodes `thinking_mode: "off"` — a new `wantsExtendedThinking()` derives it from the request's `reasoning_effort`/`reasoning.effort`/`thinking.type` signal, so extended thinking can actually be requested. Regression guard: `tests/unit/issue-6662-repro.test.ts` (RED→GREEN for both adapters). ([#6743](https://github.com/diegosouzapw/OmniRoute/pull/6743))
-- **fix(api):** the compression config PUT schema now accepts `enableRenderers` for the RTK engine instead of rejecting the documented option (#6703, #6757 — thanks @alltomatos, with an independent duplicate fix from @chirag127 via #6756).
-- **fix(api):** raised the provider `apiKey` length cap for cookie-based web providers, whose session-cookie credentials legitimately exceed the previous limit (#6715, #6759 — thanks @alltomatos).
-- **fix(routing):** fusion combos no longer silently drop `combo-ref` panel members — a referenced combo is now dispatched as one black-box panel voice instead of being dropped (#6764)
-- fix(ci): publish electron-updater `latest*.yml` manifests in electron release assets so auto-update can find them ([#6766](https://github.com/diegosouzapw/OmniRoute/issues/6766))
-- **fix(i18n): translate hardcoded Portuguese dashboard strings to English (#6761, #6768)** (#6769 — thanks @chirag127).
-- fix(providers): strip redundant node prefix when resolving custom OpenAI/Anthropic-compatible connections by raw connection id, preventing double-namespaced model ids from 400ing upstream (#6772)
-- fix(providers): scope nvidia NIM 404s to the single failing model instead of cooling down the whole connection (#6773)
-- **fix(codex):** bump the default Codex CLI client identity from `0.142.0` to `0.144.0` for compatibility with newer Codex-backed models ([#6780](https://github.com/diegosouzapw/OmniRoute/pull/6780)) — thanks @quanturbo
-- **fix(ci):** the blocking "Impacted unit tests (TIA)" step false-redded any PR whose impact graph reached a dashboard component — it ran every selected test under `--import tsx/esm`, but `tests/unit/dashboard/**` requires the `--import tsx` CJS transform (ESM-only deep imports like `@lobehub/icons/es/*`), exactly as the canonical `test:unit:ci:shard` already does per segment. The impacted selection is now split by segment with matching loaders (closes #6787). ([#6788](https://github.com/diegosouzapw/OmniRoute/pull/6788))
-- **fix(translator):** read PDF/video `file_data` attachments on the OpenAI→Gemini/Antigravity and OpenAI→Claude paths so multimodal documents (not just images) reach the upstream — PDFs map to `document`/`inlineData` and videos keep their `video/mp4` mime instead of being dropped (#6790 — thanks @Witroch4, with an independent report/fix from @samimozcan via #6762/#6753).
-- **fix(providers): ensure DeepSeek Web SSE emits [DONE] after FINISHED** (#6791 — thanks @Pitchfork-and-Torch).
-- **fix(api):** the compression config `PUT` schema (`stackedPipelineStepSchema`) now accepts every `ENGINE_CATALOG` id — the structural engines `session-dedup`/`ccr`/`headroom`/`relevance`/`llmlingua`/`omniglyph` and the `aggressive` `ultra` intensity — so a `GET`→`PUT` round-trip of a stacked pipeline no longer 400s on a valid engine the discriminated union had omitted (#6747 — thanks @Pitchfork-and-Torch).
-- **fix(electron): materialize Turbopack hashed-module symlinks during packaging (#6724, #6594)** (#6794 — thanks @huohua-dev).
-- **fix(cursor):** send the Agent CLI build id as `x-cursor-client-version` so Cursor upstream accepts requests from the current CLI build instead of a stale hardcoded version (#6795 — thanks @andrewmunsell).
-- fix(cli): waitForServer() no longer reports ready from a raw TCP accept alone — requires a fast HTTP rejection or a real health response, so the "OmniRoute is running!" banner no longer fires 30-60s before the server can actually answer requests (#6800)
-- fix(sse): de-flake timing-sensitive combo cooldown/breaker tests + add explicit MCP audit shutdown timeout (#6803)
-- **fix(codex): strip include from compact responses requests** (#6805 — thanks @yinaoxiong).
-- fix(dashboard): surface Claude extraUsage credits in quota card when quotas is empty (#6806)
-- **Request count by provider & date**: Dashboard → Analytics now shows a dedicated table of request counts grouped by provider and calendar date (plus token totals), for providers that bill per-request rather than per-token — sortable columns and a single-date filter. New `getProviderDailyUsageRows()` query (`src/lib/db/usageAnalytics.ts`) and its own `GET /api/usage/requests-by-provider-date` route (kept separate from the frozen `/api/usage/analytics` route). Regression guard: `tests/unit/db-provider-daily-usage-4009.test.ts`. (#4009 — thanks @tjengbudi) ([#6812](https://github.com/diegosouzapw/OmniRoute/pull/6812))
-- **fix(resilience):** an Ollama Cloud (or any apikey-category provider) account that hit a weekly usage cap kept getting retried every few minutes instead of backing off ([#3709](https://github.com/diegosouzapw/OmniRoute/issues/3709)) — the upstream 429 body ("you (\<account\>) have reached your weekly usage limit") was invisible to `checkFallbackError`'s existing subscription-quota-text classifier (Issue #2321) because that branch is gated by `shouldUseQuotaSignal`, which is oauth-only, so apikey providers like `ollama-cloud` fell through to the generic exponential backoff (~1s, capped at 2min) — one account took 285x429 in 48h. A new `isWeeklyUsageLimitText`/`buildWeeklyQuotaFallback` classifier (extracted, with the existing subscription-quota logic, into a new `open-sse/services/quotaTextCooldowns.ts` module so the frozen `accountFallback.ts` didn't have to grow) runs unconditionally and applies a 24h `QUOTA_EXHAUSTED` cooldown regardless of provider category. Regression guard: `tests/unit/ollama-cloud-weekly-quota-cooldown-3709.test.ts`. ([#6817](https://github.com/diegosouzapw/OmniRoute/pull/6817))
-- **fix(providers):** an explicit `thinking.budget_tokens: 0` is now honored in the OpenAI→Gemini transform (thinking disabled) instead of being treated as unset (#6813, #6821 — thanks @alltomatos).
-- **fix(bootstrap):** filter empty `process.env` values before spawning embedded services so a blank env var no longer crashes the Docker bootstrap in a restart loop (#6828 — thanks @AndrianBalanescu).
-- **fix(providers):** classify upstream `404` responses as `MODEL_NOT_FOUND` (model lockout) instead of a retryable provider error, stopping the retry storm when a single model is missing (#6829 — thanks @AndrianBalanescu).
-- **fix(db):** cap the sql.js OOM-during-probe path in `getDbInstance()` at 3 attempts with a terminal diagnostic — previously only the generic-corruption probe-failure path had a cycle-breaker (#6632), so a persistently OOMing `storage.sqlite` probe re-threw the identical error forever on every call from every background poller, hanging the app with "Internal Server Error" and no self-recovery (#6835).
-- fix(mcp): de-duplicate `TOTAL_MCP_TOOL_COUNT` by tool name instead of double-counting collections (#6854)
-- **fix(usage):** xAI's exact provider-reported `cost_in_usd_ticks` no longer silently accepts `null`/`""`/negative values as a valid `$0` exact cost — `extractUsageFromResponse()` (`open-sse/handlers/usageExtractor.ts`) and `normalizeUsage()` (`open-sse/utils/usageTracking.ts`) now require `typeof value === "number" && Number.isFinite(value) && value >= 0` instead of coercing with `Number(x)`, so a malformed exact cost correctly falls back to the token-based estimate instead of masking it with a bogus `$0`. Regression guard: `tests/unit/xai-exact-cost-2453.test.ts` (rejects null/empty/negative exact costs on both call sites). ([#6856](https://github.com/diegosouzapw/OmniRoute/pull/6856) — thanks @KooshaPari)
-- **fix(plugin):** the `@omniroute/opencode-plugin` dynamic provider hook stopped embedding its OC-1.17.8+-gate-compatible `opencode-`-prefixed provider id into model routing fields (`ModelV2.id`/`providerID`, combo catalog keys) — OmniRoute's server has no `opencode-<x>` provider alias, so every dispatched model failed credential lookup with "No credentials for opencode-omniroute" (#6859).
-- fix(sse): apply cliproxyapiModelMapping at CLIProxyAPI dispatch time (#6876)
-- fix(sse): defer `response.completed` until a trailing usage-only chunk arrives on `/v1/responses` streams (#6906)
-- **fix(cli):** ship `head-response-guard.cjs` into the standalone bundle — `server-ws.mjs` imported it without a matching `EXTRA_MODULE_ENTRIES` entry, so every `build:release` dist crashed at boot with `ERR_MODULE_NOT_FOUND`; a new regression test derives the required sidecars from `server-ws.mjs` imports (#6908)
-- fix(sse): wire the shared quota-fetch throttle into DeepSeek, Bailian, OpenCode, and Crof quota fetchers, not just Codex (#6911)
-- fix(sse): rename client-sent `max_completion_tokens` to `max_tokens` for providers/models that only accept the legacy field (e.g. Volcengine Ark / DeepSeek), mirroring the existing reverse rename from #1961 (#6912)
-- fix(providers): `PROVIDER_LIMITS_SYNC_SPACING_MS` now also throttles local / API-key (Ollama) connections, not just OAuth — spaced between concurrency chunks so a local endpoint isn't hit by a simultaneous refresh burst (#6916)
-- fix(sse): classify LAN embeddings providers (10/8, 192.168/16, CGNAT) as no-auth instead of forcing bearer auth (#6925)
-- fix(sse): Qwen Web executor no longer sends `[object Object]` when a message uses structured (array) content — the text parts are now flattened (#6927)
-- perf(api): relay chat-completions routes now thread the already-fetched `RelayToken` into `checkRateLimit`, skipping a redundant `SELECT * FROM relay_tokens WHERE id = ?` re-query on every request (#6930)
-- fix(sse): `normalizeCodexMessageContentPart` now rewrites explicit `type: "input_text"` (not just `type: "text"`) to `output_text` on assistant-role Codex Responses input parts, so replayed assistant history sent by codex-cli as `input_text` is no longer rejected by the Codex/OpenAI backend (#6932)
-- fix(sse): omit removed `attachments` field from Muse Spark Web (Meta AI) persisted GraphQL query to fix `Unknown type "AttachmentInput"` 502s (#6935)
-- fix(dashboard): label audio/embeddings/image compatible providers by kind instead of "Chat" on ProviderCard (#6936)
-- fix(api): model-list discovery for LAN-local OpenAI-compatible providers (e.g. LM Studio) now uses the same local-first SSRF guard as the connection test, instead of the stricter guard that always blocked LAN hosts (#6939)
-- fix(providers): `openai->gemini` transform now maps `reasoning_effort: "none"` to `thinkingConfig.thinkingBudget: 0` (with `includeThoughts: false`), giving callers an explicit, documented off-switch for Gemini thinking; the no-knob-at-all default injection (#4170) is unchanged (#6813, thanks @rafaumeu)
-- **fix(sse):** escape backslash before brackets in ChatGPT-web citation link text, preventing a citation label containing `\` from corrupting the generated Markdown link ([#6944](https://github.com/diegosouzapw/OmniRoute/pull/6944)) — thanks @brick30llc-ctrl
-- fix(oauth): tokenHealthCheck now lowercase-normalizes `conn.provider` before checking `ROTATING_REFRESH_PROVIDERS.has()` and the GitHub Copilot sub-token refresh guard, so mixed-case provider values (e.g. "OpenAI", "Github") no longer bypass the rotating-refresh-token skip or the Copilot sub-token refresh (#6947)
-- fix(sse): make Codex Responses tool-arg normalization schema-aware — drop values equal to the tool's declared JSON Schema `default`, generalize empty-optional stripping to any tool (not just `Read`/`Subagent`) via `schema.required`, and thread each tool's schema from the request's `tools[]` into the streaming response translator (#6951)
-- fix(sse): drop internal commentary-phase Responses output in TRANSLATE-mode streams, not just PASSTHROUGH — codex/Responses-upstream routes translated into another client format (e.g. Claude Code) no longer leak duplicate prose and narrated tool-call arguments into the client text channel (#6952)
-- fix(sse): stop forwarding empty-signature thinking blocks verbatim to Anthropic-native legs, which permanently poisoned combo fallback (#6953)
-- **fix(sse):** `perplexity-web`'s default `pplx-auto`/`pplx-sonar` targets now post `mode: "copilot"` (with `pplx-sonar` mapped to `model_preference: "turbo"` instead of `experimental`), match Perplexity's `event: end_of_stream` SSE terminator instead of OpenAI's `[DONE]`, and fall back to the COMPLETED frame's double-encoded FINAL step-blob when no `diff_block`/`markdown_block` streamed — fixing `[perplexity-web/pplx-sonar] Provider returned empty content` against the current schematized `www.perplexity.ai` SSE API. (thanks @artickc)
-- **fix(combos):** embeddings-only and rerank-only models (e.g. JinaAI, Gemini auto-imported, OpenRouter custom, reranker models) no longer disappear from the combo builder's model picker — the leftover chat-only `isChatCapable` gate in `addModelOption()` has been removed (#6975).
-- **fix(combos):** when 2+ distinct model ids from the same provider would render an identical display name in the combo builder picker (e.g. Mistral's `codestral-latest`/`codestral-2508` aliases sharing one upstream catalog name), each colliding entry now falls back to its own id as the display label so every row stays visually distinguishable and findable (#6957).
-- **fix(dashboard):** the combos builder now hides provider connections the user has explicitly disabled, instead of relying only on stale test-status (#6984 — thanks @attid).
-- **fix(providers):** cap grok-cli tools at 200 per request, matching xAI's cli-chat-proxy limit, and document the non-reasoning capability of grok-build/grok-composer-2.5-fast in the registry (#6986, thanks @gitcommit90)
-- fix(providers): DuckDuckGo AI Chat executor propagates the real upstream status (429 rate limit with `Retry-After`) instead of misclassifying VQD-token acquisition failures as a hardcoded 503 (#6996)
-- fix(providers): refresh OpenCode (`oc`) free-tier model catalog — 6 delisted IDs replaced with the 4 currently-live free models (#6998)
-- fix(api): raise the main server's `keepAliveTimeout`/`headersTimeout` well above Node's 5s default so pooled keep-alive clients (e.g. JetBrains AI Assistant's JVM `HttpClient`) stop getting 0 bytes back on a reused connection (#7003)
-- fix(compression): wire the adaptive context-budget "dial" (`contextBudget`) into the settings schema and DB so it can actually be persisted via `PUT /api/settings/compression`, instead of being silently rejected (#7005)
-- fix(usage): stop opencode-go quota lookup from defaulting to an unrelated Z.AI endpoint (#7022)
-- **fix(providers):** Auggie (Augment CLI) model registry updated to the real v0.32.0 CLI model IDs, with a live `auggie model list` auto-discovery fallback for future renames; the old pre-v0.32.0 IDs (`claude-sonnet-4.6`, `claude-opus-4.6`, `claude-haiku-4.5`, `gemini-3.1-pro`, `gemini-3.0-flash`, the `gpt-5.4`/`gpt-5.5` high/medium variants) are a **breaking rename**, but a backward-compat alias map in `resolveAuggieModel()` transparently remaps them to their v0.32.0 equivalents so existing saved combos keep working without any manual update (#7032 — thanks @oyi77).
-- fix(ci): add a dashboard-scoped typecheck gate covering `src/app/(dashboard)` TSX, previously invisible to `typecheck:core` and `next build` (#7033)
-- **fix(cli):** `omniroute dashboard` (no `--port` flag) now respects `PORT` from the environment instead of always opening `localhost:20128`, matching `serve`/`launch` precedence (`--port` > `PORT` env > `20128` default) (#7049 — thanks @kaon0388v1).
-- fix(build): extend the Turbopack `ignoreIssue` suppression to `open-sse/services/compression/**`, matching the `getModuleDir()` dynamic-path fs pattern already suppressed for `src/lib/agentSkills/**` in #6582, eliminating the remaining 610 "Overly broad patterns" warnings (#7051)
-- fix(providers): web-cookie connection-test/cookie-validation probe (zai-web and every other registry-entry web-cookie provider) now honors the configured HTTP/SOCKS proxy — the `/models` probe routed through `directHttpsRequest`'s hardcoded native-fetch bypass, silently skipping proxy resolution even though the executor's actual chat traffic already respected it (#7058)
-- fix(resilience): recognize Ollama Cloud's 5-hour session usage-limit 429 as quota-exhausted instead of a generic rate limit (#7071)
-- fix(dashboard): restore mobile single-column fallback on the Provider Quota page card grid, fixing clipped labels/buttons on phone-width viewports (#7072)
-- fix(dashboard): include proxyId when testing a saved registry proxy so SOCKS5/auth credentials are loaded (#7080)
-- **fix(sse):** xiaomi-tokenplan `mimo` models (e.g. `mimo-v2.5-pro`) are now recognized as thinking-mode upstreams that require `reasoning_content` echoed back on every assistant turn, fixing a persistent `400 reasoning_content must be passed back` error on multi-turn conversations ([#7098](https://github.com/diegosouzapw/OmniRoute/pull/7098)) — thanks @xxue-z
-- **fix(dashboard):** align onboarding tier descriptions and localize the tier step header and flow copy ([#7125](https://github.com/diegosouzapw/OmniRoute/pull/7125)) — thanks @Wibias
-- **fix(sse):** claude-web now surfaces the real upstream error body for non-SSE 400/403/429/500 responses instead of reporting "no response body" — the streaming client was discarding the already-captured temp-file bytes and reading the native binding's empty in-memory body field instead (#7134).
-- fix(db): honor combo-level proxy assignments from the registry when resolving a connection's proxy (#7149)
-- fix(dashboard): wire modelAliases fetch into HermesAgentToolCard so OpenRouter and other passthrough providers appear in the Hermes Agent role picker (#7151)
-- fix(dashboard): filter hidden custom models out of the legacy combo model picker (#7156)
-- fix(dashboard): Agent Bridge DNS toggle now sends POST (was PUT), fixing HTTP 405 on Start/Stop DNS (#7157)
-- fix(dashboard): implement missing `handleToggleSource` callback on the Free Pool tab so the page no longer crashes with a `ReferenceError` (#7161)
-- fix(sse): stop duplicating text in Gemini Web streamed responses (#7163)
-- **fix(executors):** Codex Responses Lite requests force serial tool calls required by the upstream API ([#7171](https://github.com/diegosouzapw/OmniRoute/pull/7171)) — thanks @fenix007
-- **fix(translator):** preserve Gemini thinking-mode `thought:true` parts as `reasoning_content` instead of leaking them into visible assistant text on the OpenAI request bridge. (thanks @warelik)
-- **fix(translator):** register the missing OpenAI→Gemini response projection so combo-routed OpenAI-native providers no longer leak raw `chat.completion.chunk` shapes to Gemini-format clients. (thanks @warelik)
-- **fix(cli):** `omniroute --version` now fast-paths before the tsx/esm + polyfill imports, env-file loading, and Commander's full command registration, cutting local runtime from ~1.5s to ~0.3s. (thanks @Jordannst)
-- fix(ci): build dast-smoke and nightly API-only smoke workflows with `OMNIROUTE_BUILD_BACKEND_ONLY=1` to skip the unused dashboard UI graph and stop the multi-minute build variance/timeouts (#7226)
-- **api:** bulk-add API keys no longer overwrite existing provider connections — a colliding auto- or custom-generated name now gap-fills a free suffix instead of silently replacing a saved connection's key/state. (thanks @asynx6)
-- fix(sse): feed the compression pipeline the authoritative vision capability instead of the conservative model-id heuristic, so vision models absent from the fragment list (e.g. gpt-5.5) no longer have their image_url blocks silently stripped (#7237)
-- **fix(sse):** route the public OpenAI GPT-5.6 family (`gpt-5.6`, `-sol`, `-terra`, `-luna`) through the Responses API — Chat Completions rejects GPT-5.6 requests that combine function tools with an active `reasoning_effort`. (thanks @Jordannst)
-- **fix(providers):** honor a configured proxy on Grok Build egress — the grok-cli executor used raw `https.request()` and bypassed the proxy context, leaking the host IP on chat inference and OAuth token refresh. (thanks @ryanngit)
-- **fix(nvidia):** expand NIM chat model catalog with newly-observed models. (thanks @spacesky-cell)
-- **fix(sse):** synthetic bypass responses for Claude-format clients no longer drop their content — `mergeChunksToResponse()` now reconstructs the message from streamed content blocks instead of returning an empty array. (thanks @KunN-21)
-- **fix(build):** isolate Windows HOME/AppData during next build. (thanks @KunN-21)
-- fix(dashboard): providers model-name filter now matches an aggregator's live/synced catalog, not just the static curated registry (#7250)
-- fix(docs): correct stale `/api/version` and migration-125 references + realign `no-explicit-any` suppression counts drifted by base-red realignment commits (#7253)
-- fix(sse): project non-streaming JSON responses back to the Gemini/Antigravity `{response:{candidates}}` envelope instead of leaking the raw OpenAI `choices[]` shape, so tool calls are no longer dropped for Gemini-family clients on the JSON path (#7255) (thanks @warelik)
-- fix(i18n): treat `__MISSING__:` sync-script placeholders as absent so the EN fallback renders instead of the raw sentinel (#7258)
-- fix(authz): classify /api/cli-tools/forge-settings and /api/cli-tools/jcode-settings as LOCAL_ONLY, closing an RCE-via-tunnel gap where getCliRuntimeStatus() spawns a child process without loopback enforcement (#7263)
-- fix(sse): lazy-load playwright in claudeTurnstileSolver so unsupported platforms (e.g. Termux/Android) don't crash on boot (#7265)
-- **fix(sse):** stop logging a caller-initiated request abort/timeout as a noisy proxy transport failure in `proxyFetch`. (thanks @TuyulSpam)
-- fix(sse): classify 401 "model X is not supported" as model-not-found so it locks the model out instead of looping forever (#7268)
-- fix(dashboard): resolve `ReferenceError: t is not defined` crashing `/dashboard/costs` when a filtered slice has zero-cost rows (#7272)
-- fix(cli): Windows MITM root-CA check/uninstall keyed off the hardcoded legacy hostname `daily-cloudcode-pa.googleapis.com` instead of the actual generated CA's identity — they now derive a SHA-1 thumbprint from the real `certPath` file (same pattern `#6338` used for the DNS side of this anti-pattern) (#7275)
-- fix(cli): reuse cliRuntime's win32-aware `locateCommand`/`shell:true` probe in tool-detector so installed CLIs (npm `.cmd` shims) are no longer reported as absent on native Windows (#7279)
-- fix(dashboard): connection Test surfaces a rate-limit warning on 429 chat-probe responses instead of an unqualified pass (#7284)
-- fix(sse): combo failover now detects OpenAI-shape streams truncated without `finish_reason`/`[DONE]` (#7285)
-- **fix(db):** `getDbInstance()` now guarantees sql.js WASM has already been pre-initialized (via a top-level await in `src/lib/db/core.ts`) before ANY consumer can reach it, closing an ordering gap where early startup steps (`ensureSecrets()`, `clearStaleCrashCooldowns()`, `getSettings()`, `initAuditLog()`) called `getDbInstance()` before `ensureDbReadyForBoot()` had a chance to run `preInitSqlJs()` — turning a recoverable driver failure into a hard boot crash (`sql.js WASM ainda não foi pré-inicializado`) whenever both `better-sqlite3` and `node:sqlite` failed to open an existing `storage.sqlite`. `tryOpenSync()` also now logs the real underlying cause of each swallowed sync-driver failure instead of an empty `catch {}`. (#7288, #7494)
-- fix(sse): split effort/reasoning suffix off pinned Claude/GPT model ids before sending to cursor's server (#7289)
-- fix(sse): hoist client-injected `system` messages to index 0 for strict OpenAI-compatible providers (xiaomi-mimo) regardless of origin (#7293)
-- fix(sse): treat Uint8Array/Buffer as opaque binary in log redaction to stop per-byte enumeration on Bedrock Converse image requests (#7297)
-- fix(cli): load DATA_DIR/server.env as a fallback for .env when migrating from Electron, so STORAGE_ENCRYPTION_KEY/JWT_SECRET/API_KEY_SECRET survive an Electron→CLI install migration (#7302)
-- **fix(rerank):** Honor the connection's pinned proxy on rerank calls, so a provider that geo-blocks the host IP (Voyage AI) works on the same connection where chat and embeddings already did ([#7350](https://github.com/diegosouzapw/OmniRoute/issues/7350)) — thanks @kamenkadmitry
-- **fix(electron):** Normalize hashed Turbopack external imports in packaged desktop builds, preventing instrumentation startup failures ([#7353](https://github.com/diegosouzapw/OmniRoute/pull/7353)) — thanks @tianrking
-- fix(chatgpt-web): recognize `update_content.messages[]` (plural array) celsius WebSocket frames so async image_gen pointers are no longer silently dropped (#7357)
-- fix(sse): clamp glm-4.6v max_tokens to the 32768 ceiling for zai and glm providers, wiring stripUnsupportedParams into GlmExecutor's own transform path (#7364)
-- fix(sse): honor per-model targetFormat override for zai/glm-coding-apikey buildUrl and make custom-model id lookup case-insensitive (#7364)
-- fix(sse): combo session stickiness now releases a connection whose per-window quota is exhausted, matching the provider-level session-affinity pin (#7387)
-- fix(cli): log Codex Responses WebSocket history/usage per logical turn instead of once per connection (#7388)
-- fix(embeddings): remove the non-existent `voyage-multilingual-3.5` from the embedding registry and add the missing Voyage models (#7425 — thanks @kamenkadmitry)
-- fix(providers): expose a base-URL override for Kimi/Moonshot so CN-region API keys (issued on platform.kimi.com / moonshot.cn) can be pointed at api.moonshot.cn instead of being rejected by the international host (#7447)
-- fix(build): align `engines.node` supported range (>=22.22.2 <23 || >=24.0.0 <27) across package.json, lockfile, README engine references and the node-runtime support test, so install-time engine checks match the actually-tested runtimes (#7446)
-- fix(i18n): replace machine-bulk-filled Vietnamese UI strings with human-quality translations — 5411 values improved, technical literals (RPC methods, endpoints) no longer over-translated (#7493)
-- fix(db): stop closing the single sql.js singleton during getDbInstance()'s probe/reopen sequence, which poisoned every boot with "Database closed" once both sync SQLite drivers were unavailable (#7494)
-- fix(sse): stop stream readiness from treating a choices-less mid-stream error frame as a successful stream, so combo can fail over instead of returning zero `choices` (#7503)
-- Fixed the Codex connection **Test** button always reporting success for ChatGPT-account tokens: the probe used `gpt-5.3-codex`, a codex-only model ChatGPT accounts reject with a 400 — the same status the probe treats as "auth OK", so a bad token was indistinguishable from a good one. It now probes with `gpt-5.5`, a model ChatGPT-account sessions actually support (#7521).
-- The Codex account import (`POST /api/oauth/codex/import`) now validates each record's `refresh_token` against OpenAI's OAuth endpoint before persisting the connection: an already-invalidated session (`refresh_token_invalidated` / a dead `auth.json`) is rejected with a clear "run `codex login` again and re-import" message instead of importing as `active` and failing confusingly on first use. Valid tokens import as before, with any rotated tokens applied (#7522).
-- The PKCE OAuth start (`/api/oauth/[provider]/start-callback-server`, used by Codex/Windsurf/Devin) now detects when OmniRoute is being driven from a remote host and returns a reverse-tunnel hint (`remoteHost`, `tunnelCommand`, `message`) instead of hanging silently: the callback server binds the *server's* localhost:PORT, so a browser on a different machine would redirect to its own localhost and never complete. Loopback access is unchanged (#7523).
-- fix(providers): search providers now expose a static model catalog derived from `searchTypes`, fixing "does not support models listing" 400 for serper-search, brave-search, perplexity-search, exa-search, tavily-search, google-pse-search, youcom-search, searxng-search, zai-search (#7529)
-- fix(sse): map `tool_search` to a Chat function tool instead of dropping it during Responses->Chat translation (#7532)
-- fix(sse): gate `verbosity`/`prompt_cache_key` on OpenAI destination during Responses->Chat translation, stopping the leak to non-OpenAI upstreams like NVIDIA (#7533)
-- fix(api): Usage page "by provider" table now shows the configured provider display name (e.g. "OpenAI Codex") instead of the raw internal provider id (e.g. "codex") (#7534)
-- fix(api): Usage page "model usage" table no longer lists the same logical model twice when it was recorded under both a bare and a provider-prefixed spelling (e.g. `glm-5.2` and `z-ai/glm-5.2`) — the in-memory dedup key now uses the normalized model name (#7535)
-- fix(codex): non-stream Codex (ChatGPT-account) chat no longer 502s with "Response body is already used". `peekCodexSseTransientError` now checks the content-type before touching `response.body`: on the wreq-js TLS-fingerprint transport the Response is backed by a native body handle and merely accessing `.body` disturbs it, so the empty-content-type non-stream response was being consumed by the peek guard and then re-read by `readNonStreamingResponseBody`. Streaming was unaffected. Validated live on the VPS (`codex/gpt-5.5` + `codex/gpt-5.6-terra` non-stream now return 200) (#7536)
-- **fix(sse):** preserve `input_image` parts in array-valued Codex `custom_tool_call_output` payloads instead of rewriting them to invalid `output_text` parts ([#7540](https://github.com/diegosouzapw/OmniRoute/pull/7540)) - thanks @loulanyue
-- fix(providers): stop reporting Arena (lmarena) cookie validation as Invalid when the `/models` probe hits a 307 redirect — degrade to `unsupported` instead, and drop the stale "no registry entry" comment for lmarena (#7542)
-- **fix(combo):** streaming combo failover now fails over when an upstream SSE response is truncated mid-lifecycle with no recognised terminator (`data: [DONE]`, `finish_reason`, `message_stop`/`message_delta` with `stop_reason`, or a terminal `usage`-only chunk) and no structured SSE frame at all — previously any byte, even unparseable garbage, satisfied the generic done-branch gate and the truncated stream was passed through, leaving the client hung waiting for events that never arrived ([#7545](https://github.com/diegosouzapw/OmniRoute/pull/7545)) — thanks @Chewji9875
-- **fix(dashboard):** Public and managed tunnel endpoints now take precedence over loopback URLs in dashboard setup and copyable API configuration ([#7547](https://github.com/diegosouzapw/OmniRoute/pull/7547)) — thanks @nguyenha935
-- fix(claude-web): unify Turnstile solver, executor and httpBackedChat fast-path User-Agents behind one shared fingerprint module so `cf_clearance` is never solved under a different UA than the one that replays it (#7548)
-- fix(cli): fall back to the node:sqlite driver cascade in `bin/cli/sqlite.mjs` so `omniroute doctor` no longer reports a false "FAIL Database"/"FAIL Storage/encryption" on machines without a working better-sqlite3 native binary (#7586)
-- fix(api): expose Responses-API-format (OpenAI/Codex) chat models on every VS Code Ollama-compatible listing route, not just `/models` (#7587)
-- **grok-cli:** OAuth paste-import now requires the full `~/.grok/auth.json` (with `refresh_token`) instead of a bare JWT `key`, preventing connections that can never auto-refresh (#7610).
-- fix(sse): proactively refresh Grok Build's expiring OAuth token before dispatch, and add it to the connection-test config so "Test Connection" no longer reports "unsupported" (#7610)
-- **grok-cli:** sanitize Responses `function_call_output.output` values before dispatch so incomplete `\u` escapes / malformed tool results no longer cause intermittent 400 body-parse failures on cli-chat-proxy (#7611).
-- **fix(translator):** guard against double-emission when `response.completed` echoes `function_call` items already streamed via incremental `output_item.added`/`done` events — skip synthesis for `call_id`s already tracked, preventing duplicate tool call chunks for incrementally-streaming providers
-- fix(routing): strip `prompt_cache_key` for NVIDIA NIM — Codex CLI injects it, NIM's OpenAI-compatible wrapper 400s on it (#7617)
-- fix(routing): honor eye-icon hidden models for no-auth providers in auto-combo candidate pools (#7620)
-- fix(providers): correct Chutes registry baseUrl from api.chutesai.com to llm.chutes.ai (#7621)
-- fix(providers): unify connection status across dashboard surfaces, deduplicate provider cards, preserve no-auth model discovery for metadata-only rows, and route playground models through the provider alias (#7629)
-- fix(providers): classify Mistral ambiguous 401 (quota vs revoked key) instead of asserting hard auth failure (#7638)
-- fix(sse): route CLIProxyAPI fallback/passthrough legs through a dedicated `cliproxyapi_api_key` credential instead of the failed native provider's own key (#7645)
-- fix(packaging): move fumadocs-mdx from dependencies to devDependencies to avoid pulling its build-only yuku-analyzer/yuku-ast toolchain into `npm install -g omniroute` (#7661)
-- GET /api/combos/auto now enumerates template variants (auto/best-coding, auto/pro-_, auto/claude-_, auto/best-free) and family variants (auto/glm, auto/llama, auto/gemini, etc.) in addition to the flat and suffix variants it already exposed. Previously these 27 variants were advertised by /v1/models but missing from the combos endpoint, causing 404s when clients tried to use them.
-- fix(sse): persist rotated Gemini web-session cookies via onCredentialsRefreshed (#7676)
-- fix(dashboard): mirror connection-row action-icon spacing under RTL via Tailwind logical utility (#7680)
-- fix(cli): split `outboundUrlGuard.ts`'s DB/feature-flag helpers into `outboundUrlGuardPolicy.ts` so `omniroute setup-opencode` no longer crashes with `Cannot find package '@/shared'` on a global npm install (#7682)
-- fix(sse): wire settings.wildcardAliases into model resolution so wildcard model aliases created in Settings actually take effect (#7693)
-- fix(mcp): copy undici into dist/node_modules to prevent hollow-package shadowing crash (#7701)
-- **fix(translator):** sanitize `tool_result.tool_use_id` symmetrically with the assistant's `tool_use.id` in the OpenAI→Claude request translator — a raw tool-call id containing characters outside `[a-zA-Z0-9_-]` (e.g. dots, colons) previously diverged from its sanitized `tool_use.id` counterpart, causing `enforceToolResultAdjacency()` to silently drop the `tool_result` and Anthropic to reject the request with HTTP 400 (#7705)
-- **fix(db):** bulk proxy imports now update an existing proxy when only its password changes instead of creating a duplicate ([#7707](https://github.com/diegosouzapw/OmniRoute/pull/7707)) — thanks @floze-the-genius
-- fix(oauth): stop Codex OAuth completion from collapsing distinct accounts that share an email but have no workspaceId, by requiring chatgptUserId agreement before merging (#7737)
-- fix(db): purge in-memory API-key health/rotation state when a provider connection is deleted (#7740)
-- **perf(db):** the 5 provider-connection/node call sites [#7787](https://github.com/diegosouzapw/OmniRoute/pull/7787)'s IC2 conversion missed — `providers/[id]/models`, `v1/provider-plugin-manifest`, `localHealthCheck.ts`, `sync/bundle.ts` — now read through `getCachedProviderConnectionById`/`getCachedProviderNodes`; `tokenHealthCheck.ts` keeps uncached `getProviderConnectionById` reads at the unrecoverable-refresh-error and GitHub Copilot sub-token-refresh call sites to avoid a CAS-staleness regression. ([#7744](https://github.com/diegosouzapw/OmniRoute/pull/7744) — thanks @oyi77)
-- fix(compression): CCR no longer collapses a whole prompt into a bare, unretrievable `[CCR retrieve hash=...]` marker on non-MCP upstreams — a short preamble of the original text is always kept alongside the marker (#7746)
-- fix(sse): strip orphaned tool_use blocks before dispatching to Antigravity/Vertex Claude models, mirroring the mainline Claude executor's #2382 guard (#7752)
-- fix(cli): resolve Windows CLI detection false negatives — nvm-windows symlinked binaries no longer rejected as symlink_escape, and a stray known-path artifact no longer hides a genuinely runnable Claude CLI on the PATH fallback (#7753, #7774)
-- fix(dashboard): keep session/weekly quota rows in a stable fixed order on collapsed provider-quota cards, matching the already-fixed expanded view (#7764)
-- fix(db): log the fatal boot-time SQLite driver-cascade failure before it propagates instead of swallowing it silently, so `app.log` captures the real cause on Termux/Android (#7773)
-- **fix(sse):** Claude-Code-compatible bridge (AgentRouter and any CC provider) no longer loses vision input from OpenAI-format clients (OpenCode/Kilo/Cline): `image_url`, AI-SDK `image` and Chat Completions `file` parts are now converted to Claude `image`/`document` blocks before dispatch, and media-only user turns are no longer dropped by the empty-content filter. (thanks @beingshafin) ([#7777](https://github.com/diegosouzapw/OmniRoute/issues/7777))
-- **perf(db):** `getProviderConnections` now reads from a shared `rawConnectionsCache` (500-entry LRU, 5s TTL) and returns lazy-decrypting proxies — encrypted credential fields (`apiKey`, `accessToken`, `refreshToken`, `idToken`) are only AES-GCM decrypted on first property access instead of eagerly for every cached row. `getCachedProviderConnections` now delegates through this single raw cache instead of maintaining its own, and `deleteProviderConnectionsByProvider` gained a missing `invalidateDbCache` call. ([#7787](https://github.com/diegosouzapw/OmniRoute/pull/7787) — thanks @oyi77)
-- fix(docs): document CREDENTIAL_REDACTION_ENABLED and GHE_COPILOT_OAUTH_CLIENT_ID in .env.example/ENVIRONMENT.md, closing the env-doc-sync gate drift (#7793)
-- fix(combo): retry intermediate pipeline-strategy steps on transient upstream errors (429/502/503/504), gated by `combo.config.maxRetries`/`retryDelayMs`, without retrying terminal auth/request errors (#7794 — thanks @AndrianBalanescu)
-- fix(docker): repair tls-client-node native binary after --ignore-scripts, retry rate-limited GitHub fetches (#7802)
-- **fix(runtime):** Apply refreshed request-queue settings, restore inter-batch health-check jitter, and invalidate database read caches when the SQLite singleton resets; refresh stale CI baselines and fixtures exposed by clean release runs ([#7812](https://github.com/diegosouzapw/OmniRoute/pull/7812) by [@backryun](https://github.com/backryun)).
-- fix(oauth): attempt Antigravity onboarding inline when `projectId` is empty, fixing a regression from #5193 that re-introduced the #2541 catch-22 for new accounts (#7814)
-- fix(api): add amazon-q to the static model catalog so "Available Models" no longer 400s (#7820)
-- fix(sse): preserve parallel_tool_calls for GPT-5.6 ultra/max delegation under Codex Responses Lite (#7821)
-- fix(quality): tolerate ESLint's trailing unpruned-suppressions stderr text in validate-release-green (#7837)
-- fix(test): widen ratelimit-admission pollUntil deadline to 10s to end nightly-compat flake (#7842)
-- **fix(cli):** Windows `omniroute dashboard` browser fallback uses `rundll32` instead of `cmd.exe` to open the dashboard URL, avoiding an unnecessary shell spawn ([#7844](https://github.com/diegosouzapw/OmniRoute/pull/7842))
-- fix(dashboard): Request Logs detail modal no longer crashes when the persisted error is a structured object (#7845)
-- fix(backend): stop `buildClientRawRequest` deep-cloning the whole request body on every chat request (#7847) — every consumer of `clientRawRequest.body` is observability and keeps at most a bounded copy, so the unbounded clone retained ~41x more than anything used it (3.19 MiB vs 0.08 MiB on a 3.05 MiB / 729-message agent request). Also makes `cloneBoundedForLog` idempotent: arrays, objects and strings all exceeded their own bounds once the truncation marker was added, so re-bounding an already bounded payload silently dropped a further item and misreported the original length
-- fix(sse): copy the combo attempt body shallowly instead of deep-cloning it per target (#7847) — the deep clone cost 9.53 MiB at 3 targets and scaled linearly with the target count (31.78 MiB at 10) on a 3.05 MiB agent request, while the isolation it provided only ever needed to contain top-level scalar writes. Also fixes a real cross-target leak in round-robin, which copied the body only when the reasoning buffer changed `max_tokens` and otherwise shared the caller's object, so a Background Task Redirection on one target rewrote `body.model` for the next
-- fix(sse): estimate the combo fallback-compression trigger from the request object instead of `JSON.stringify(...)` (#7847) — the string path charged an inline base64 image as if every character were prose (~50k tokens instead of ~1.2k on a 200 KB image), falsely tripping compression on requests nowhere near the context window; the same over-count #8368/#8401 fixed elsewhere. Adds `jsonLength()`, an exact serialized-length walker (property-tested against `JSON.stringify`), and uses it for the readiness-timeout and token estimates so a multi-megabyte body is no longer materialized as a string just to be measured
-- fix(providers): Copilot reasoning_text now surfaces in Claude-format non-stream responses, fixing spurious 502s (#7856)
-- fix(providers): treat a non-401/403 response from the web-cookie `/models` validation probe (redirect, login-HTML 200, 404, 405, 429) as `unsupported` instead of `valid: true` for providers whose registry `baseUrl` is a conversation/completion endpoint rather than a real API root (#7857)
-- fix(providers): copilot-m365-web now fails loudly on a fully-empty turn instead of a silent `stop`, and the enterprise tier threads its own `optionsSets`/`tone`/`allowedMessageTypes` into the chat invocation instead of only changing the WS URL (#7858, #7870)
-- fix(providers): Gemini Web connection test now accepts the expected 302 redirect instead of failing with 'Redirect blocked' (#7859)
-- fix(cli): translate missing better-sqlite3 native bindings error into actionable `omniroute runtime repair` guidance in `reset-password`/setup CLI commands (#7868)
-- fix(auth): restore `HEALTHCHECK_BATCH_SIZE` env-var configurability of the OAuth token-health-check sweep batch size, dropped as a hardcoded constant by #7719 (#7875)
-- **fix(opencode-plugin):** the official `@omniroute/opencode-plugin` now accepts an optional `managementReadToken` for management-plane catalog GETs while keeping inference requests on the connected `apiKey` — existing configurations continue to fall back to `apiKey`, and MCP token selection remains independent. (thanks @RaviTharuma) ([#7884](https://github.com/diegosouzapw/OmniRoute/issues/7884))
-- **fix(dashboard):** Provider Quota cutoff inputs preserve unsaved values across quota refreshes instead of reverting while the operator is typing ([#7889](https://github.com/diegosouzapw/OmniRoute/issues/7889)).
-- **fix(sse):** Anthropic requests that reject a completed historical thinking signature now retry once with only that historical thinking omitted, while valid requests and active tool-use cycles remain unchanged. ([#7906](https://github.com/diegosouzapw/OmniRoute/pull/7906))
-- **Chat Core**: client aborts that reject the upstream fetch with a raw string reason (e.g. `request_signal_aborted`, `Client disconnected`) are now reported as `499 Request aborted` in the response, request logs, and usage records instead of `FAILED 502 / Bad Gateway`. Follow-up to #7908 for #7907.
-- **fix(resilience):** Client-aborted requests are now treated as client lifecycle events rather than provider failures. They no longer cool down the serving connection or feed the provider circuit breaker, so a client that cancels a stream mid-flight (a routine occurrence with Claude Code) can no longer mark healthy accounts unavailable. Genuine upstream failures are still counted. ([#7907](https://github.com/diegosouzapw/OmniRoute/issues/7907))
-- fix(cli): spawn the win32 `opencode.cmd` shim with `shell:true` in `omniroute setup opencode --auth` to avoid the Node `spawnSync EINVAL` hardening error (#7913)
-- fix(dashboard): correct "Block extra Claude usage" toggle copy to describe the connection-quarantine/fallback behavior it actually performs, instead of the non-existent display-dedup behavior it previously described (en/az/zh-CN/zh-TW/vi/pl) (#7918)
-- **fix(autostart):** Windows auto-start no longer flashes a console window — writes a `.vbs` launcher to the Startup folder instead of the `HKCU\Run` registry key, adopting the same approach as 9Router ([#7925](https://github.com/diegosouzapw/OmniRoute/pull/7925))
-- **fix(providers):** perplexity-web now detects the `advanced_models_quota_low` upsell surfaced when a stream never materializes answer text, returning HTTP 429 with `reset_seconds`/`Retry-After` instead of a silent empty-content error, and reconstructs plan-goal reasoning from RFC-6902 diff-patched `plan_block` frames (live multi-step streams), not just materialized ones ([#7930](https://github.com/diegosouzapw/OmniRoute/pull/7930)) — thanks @artickc
-- fix(sse): parse Gemini 429 RetryInfo.retryDelay / "please retry in Ns" so model lockout honors the short upstream hint instead of falling back to a ~19h until-midnight cooldown (#7940)
-- fix(electron): resolve macOS Helper by binary name to remove second inert Dock icon (#7941)
-- **fix(providers):** iFlytek Spark (`iflytek`, `sparkdesk`) now target the OpenAI-compatible host `spark-api-open.xf-yun.com/v1`; the previous `spark-api.xf-yun.com` is the WebSocket host and rejects bearer auth ([#7942](https://github.com/diegosouzapw/OmniRoute/pull/7942)) — thanks @FenjuFu
-- fix(api): classify `/api/acp/agents` as loopback-only to close an RCE-via-tunnel gap in the ACP custom-agent registry (#7948)
-- fix(cli): stop double-prefixing combo model ids in the opencode plugin's static provider catalog (#7976)
-- fix(providers): route noauth opencode-zen connections through their assigned proxy ([#7993](https://github.com/diegosouzapw/OmniRoute/issues/7993))
-- fix(providers): refresh duckduckgo-web free model catalog to Duck.ai's current wire ids, fixing 400 ERR_BAD_REQUEST (#8000)
-- fix(providers): repoint the zai-web executor at chat.z.ai's current v2 chat-completions endpoint, fixing model-independent 404s (#8014)
-- fix(sse): bound the Codex SSE peek/passthrough body reads with a per-read timeout so a silently stalled upstream body settles in FETCH_BODY_TIMEOUT_MS instead of hanging ~15min and returning a generic 502 (#8020)
-- fix(sse): replace spoofable `.includes()` PromptQL issuer check with hostname comparison (#8029)
-- **fix(providers):** path-shaped multimodal model ids (e.g. `cp/cline-pass/kimi-k3`) resolve native vision via leaf/registry metadata instead of triggering Vision Bridge ([#8032](https://github.com/diegosouzapw/OmniRoute/issues/8032)) — thanks @Prudhvivuda
-- fix(cli): merge Node's own bin dir into the CLI healthcheck spawn PATH so npm-shebang tools like codex resolve under a minimal launcher PATH (#8036)
-- **fix(sse):** Bound forwarded upstream response headers so large provider metadata cannot turn successful streaming requests into reverse-proxy errors ([#8041](https://github.com/diegosouzapw/OmniRoute/pull/8041)) — thanks @insoln
-- fix(db): register SIGHUP handler and stop force-killing the server on win32 stop paths so storage.sqlite's WAL gets checkpointed on shutdown (#8045)
-- fix(oauth): warn instead of silently opening an unreachable localhost:1455 redirect for Codex/xAI/Grok CLI OAuth when the dashboard is reached from a LAN IP (#8046)
-- **fix(sse):** run the prompt-compression pipeline per turn in the Codex Responses WebSocket bridge instead of skipping it entirely — a reused WebSocket connection now re-runs `prepare()` (auth/policy/memory/reasoning-routing/compression) for every logical `response.create` turn, not just the first (#8052)
-- **fix(oauth):** Refreshing the token on an email-less OAuth connection (e.g. GitHub Copilot, whose identity lives under `providerSpecificData`) no longer creates a duplicate connection. `persistOAuthConnection` gated its whole dedup behind `if (tokenData.email)`, so the explicit `connectionId` passed on refresh was discarded and a new connection was created every time; the connectionId is now honored regardless of email, and email dedup only applies when a non-empty email is present. ([#8059](https://github.com/diegosouzapw/OmniRoute/issues/8059))
-- fix(routing): anchor quota routing cache on globalThis so cross-chunk reads/writes stay consistent (#8065)
-- **fix(providers):** add the missing `poe` REGISTRY entry so built-in Poe model discovery resolves a base URL instead of failing with "No base URL configured for provider" ([#8082](https://github.com/diegosouzapw/OmniRoute/issues/8082))
-- fix(translator): set `status: "completed"` on translated OpenAI Responses `input` items so strict Responses-compatible upstreams stop rejecting them with 400 MissingParameter input.status (#8083)
-- fix(sse): give keyless Pollinations image requests the same anonymous fingerprint-pool fallback the chat path already uses, instead of a real upstream 401 (#8085)
-- fix(sse): stop Codex/Responses sanitizer from turning system/developer image_url parts into invalid output_text (#8089)
-- fix(cli): surface the real spawn error (err.code/path/syscall/message) in the process supervisor instead of silently swallowing it on a child spawn failure (#8091)
-- **fix(antigravity):** preserve request/tool fidelity, make credits modes explicit, and separate runtime endpoints from discovery/bootstrap ([#8098](https://github.com/diegosouzapw/OmniRoute/pull/8098)) — thanks @nguyenha935
-- fix(dashboard): clamp provider-cooldown min/max ms to their field bounds before Save so an out-of-range typed value can never reach the resilience settings API (#8107)
-- fix(providers): filter unsupported family-fallback candidates against the provider catalog (#8134)
-- fix(providers): classify HTTP 400 model-unavailable as MODEL_NOT_FOUND so Antigravity Pro fallback locks out the deprecated model ([#8136](https://github.com/diegosouzapw/OmniRoute/issues/8136))
-- fix(backend): word-boundary-safe tool-result truncation in lite compression mode (#8169)
-- fix(api): narrow claudeClassifierCompat auto trigger so stop_sequences alone no longer short-circuits (#8189)
-- fix(providers): carve cookie-auth providers out of terminal 401 'expired' classification so one 401 cooldowns instead of killing the connection ([#8200](https://github.com/diegosouzapw/OmniRoute/issues/8200))
-- fix(gemini): drop HARM_CATEGORY_CIVIC_INTEGRITY from the default Gemini safety settings (#8231)
-- **fix(dashboard):** Normalize Codex client URLs, restore the analytics input-bar color, resolve OAuth modal TypeScript regressions, synchronize the documented compression-engine count, and sanitize Muse Spark fetch errors ([#8233](https://github.com/diegosouzapw/OmniRoute/pull/8233)) — thanks @nguyenha935
-- fix(providers): classify per-model-quota 403 and DEGRADED 400 as model-unhealthy in checkFallbackError (#8247, #8248)
-- **fix(providers):** reconcile Kimi K3 vision metadata when synced `attachment=false` contradicts image/video `modalities_input`, so `supportsVision`, `attachment`, and exposed modalities agree ([#8250](https://github.com/diegosouzapw/OmniRoute/issues/8250)) — thanks @Prudhvivuda
-- **fix(providers):** the Providers page Learn more button now opens the maintained GitHub documentation instead of the retired `docs.omniroute.io` page ([#8284](https://github.com/diegosouzapw/OmniRoute/pull/8284)) - thanks @KaynXu
-- fix(api): fold namespace into the flattened Chat tool name so cross-namespace leaves do not collide ([#8295](https://github.com/diegosouzapw/OmniRoute/issues/8295))
-- **fix(runtime):** sanitize Muse Spark fetch failures before logging and resolve the sql.js WASM asset without the unexported package metadata subpath ([#8298](https://github.com/diegosouzapw/OmniRoute/pull/8298)) — thanks @backryun
-- **fix(sse):** Combo middleware preserves OpenAI Responses request bodies and maps combo system overrides to `instructions`, preventing Responses-native fallbacks from receiving an unsupported `messages` parameter. ([#8310](https://github.com/diegosouzapw/OmniRoute/pull/8310)) — thanks @ridho9
-- fix(api): accept the current compatible-provider connection id scheme in the models test route (#8326)
-- fix(api): stop leaking the internal provider UUID in /v1/models and honor the configured prefix (#8327)
-- fix(dashboard): show custom provider_nodes providers in the Topology view instead of only AI_PROVIDERS (#8328)
-- fix(api): stop the 2000-token safety buffer from inflating usage.prompt_tokens in the client response (#8331)
-- fix(backend): keep combo routing from dispatching image requests to text-only targets (#8332)
-- fix(sse): strip third-party-agent signals from the Hermes system prompt that trigger Anthropic 400 extra-usage (#8350)
-- **fix(i18n):** Restore brand/model proper nouns (Claude, OpenAI, Anthropic, Gemini, MiniMax, etc.) in zh-CN and zh-TW — replace Chinese phonetic/translation forms (克劳德/打开Ai/人择/双子座) with original English, unify "provider" translation to "供应商/供應商", and apply zh-TW localized terminology (網路/設定/檔案/新增/啟用/搜尋/儲存) instead of mainland defaults (#8355 — thanks @ikelvingo).
-- fix(api): estimate inline base64 image tokens instead of counting the data URL as text so it does not falsely exceed the context window (#8368)
-- fix(backend): stop prompt-cache affinity from silently reordering an explicit priority combo across models (#8370)
-- fix(api): accept a missing status query-param on GET /api/plugins instead of rejecting null with Invalid status value (#8374)
-- fix(resilience): treat an unreachable-proxy ECONNREFUSED as a circuit-breaker event so combo fails over instead of hitting the 503 max-retry limit (#8376)
-- fix(backend): make disabling the global per-key proxy toggle override existing per-key proxy assignments (#8385)
-- fix(dashboard): persist compression engine detail settings (Headroom / session dedup / CCR) instead of dropping them on save (#8388)
-- fix(plugins): fire registered+active plugin hooks (onRequest/onResponse/onError) during proxying instead of never invoking them (#8395)
-- fix(resilience): cap the connection cooldown after a 429 burst so combo fallback is not blacked out past the real rate-limit window (#8396)
-- fix(api): reach synced model_capabilities rows for canonical provider ids that only appear as an alias in MODELS_DEV_PROVIDER_MAP, e.g. codex/claude (#8429)
-- fix(providers): stop marking a multi-quota-window provider exhausted when only some windows are depleted (LIMIT-200 snapshot eviction drops idle healthy windows) (#8431)
-- fix(backend): compute AgentBridge diagnose `dnsConfigured` per-agent instead of hard-coded to Antigravity hosts (#8466)
-- **fix(providers):** OpencodeExecutor honors Extra API Keys rotation via `resolveEffectiveKey` (empty primary + extras no longer omit Authorization) ([#8467](https://github.com/diegosouzapw/OmniRoute/issues/8467)) — thanks @Prudhvivuda
-- fix(sse): stop combo's "all targets failed" response from attaching one target's retry-after window to an unrelated target's error message (#8486)
-- **fix(backend):** capability filters fail closed when every combo target is incompatible, with opt-in `compatFilterFailOpen` ([#8488](https://github.com/diegosouzapw/OmniRoute/issues/8488)) — thanks @Prudhvivuda
-- fix(providers): persist a runtime-discovered Antigravity projectId back onto the connection so it survives token refreshes and restarts instead of being rediscovered or lost (#8491)
-- fix(cli): `backup create` / `backup auto enable` — option shadowing by the parent `backup` command removed; all flags (`--cloud`, `--encrypt`, `--retention`, `--name`, `--exclude`, `--key-file`) now reach the subcommand handler with their actual values instead of being silently discarded ([#8512](https://github.com/diegosouzapw/OmniRoute/issues/8512))
-- **fix(dashboard):** Endpoint/API base URL display honors `OMNIROUTE_BASE_PATH` (e.g. `https://host/omniroute/v1` instead of `https://host/v1` under reverse-proxy subpath deploys) ([#8514](https://github.com/diegosouzapw/OmniRoute/pull/8514)) — thanks @rqzbeh
-- **fix(client):** Absolute `fetch("/api/...")` and `EventSource("/api/...")` honor `OMNIROUTE_BASE_PATH` under reverse-proxy subpath deploys (no domain-root 404s for dashboard health/SSE) ([#8515](https://github.com/diegosouzapw/OmniRoute/pull/8515)) — thanks @rqzbeh
-- fix(cli): create `~/.cache` (and set `XDG_CACHE_HOME`) before Next.js loads on Android/Termux so `getCacheDirectory()` no longer aborts with `Unsupported platform: android`, which previously left every request as a silent HTTP 500 after the CLI still looked "running" (#8519)
-- fix(api): surface a non-blocking warning + startup scan when a combo name shadows a real model id, instead of silently routing with zero signal (#8530)
-- **fix(kiro):** support profileless Builder ID quota, preserve CLI auth identity, stabilize social OAuth polling, and use the live model catalog ([#8565](https://github.com/diegosouzapw/OmniRoute/pull/8565)) — thanks @nguyenha935
-- fix(test): isolate `context-manager` unit tests on a temp `DATA_DIR` so `getTokenLimit` resolves against the registry fallback instead of the developer's local models.dev sync ([#8568](https://github.com/diegosouzapw/OmniRoute/issues/8568))
-- **fix(quality):** `check:file-size --update` now removes baseline entries that already fit the new-file cap even when LOC equals the frozen value (`redundant` path) — closes the #8584 gap where at-cap entries were stuck forever ([#8589](https://github.com/diegosouzapw/OmniRoute/pull/8589)) — thanks @MumuTW
-- **fix(sse):** restore Task-Aware Routing config from `settings.taskRouting` at boot and keep it on `globalThis` so multi-graph imports share one store — stops the feature silently reverting to disabled on every restart (#8601) ([#8604](https://github.com/diegosouzapw/OmniRoute/pull/8604)) — thanks @MumuTW
-- **fix(sse):** task-aware routing defaults use `auto/*` intents instead of hardcoded provider/model ids (#8602), and the longest-pattern-first fitness table match that landed upstream in 9f5be229b gains a direct regression guard, so rows like `gpt-4o-mini` cannot be shadowed by `gpt-4o` again (#8603) ([#8605](https://github.com/diegosouzapw/OmniRoute/pull/8605)) — thanks @MumuTW
-- **fix(providers):** keep registered OpenCode Go effort aliases in the Playground catalog when synced base models are present, and preserve Hunyuan3's 256K context metadata for combo routing ([#8610](https://github.com/diegosouzapw/OmniRoute/pull/8610)).
-- **fix(resilience):** report local request-queue expirations as service-unavailable capacity failures instead of upstream 502 errors, preventing incorrect provider cooldowns and same-target retries ([#8613](https://github.com/diegosouzapw/OmniRoute/pull/8613)).
-- **fix(docker):** Honor `OMNIROUTE_BASE_PATH` behind reverse-proxy subpaths by baking the subpath into the standalone bundle at image build time (`ARG OMNIROUTE_BASE_PATH`) and patching the published root-path image at container start (`scripts/docker/ensure-docker-base-path.mjs`); healthcheck probes the prefixed `/api/monitoring/health` route ([#8615](https://github.com/diegosouzapw/OmniRoute/pull/8615)) — thanks @DinonowDev
-- **fix(resilience):** recover a wedged local request limiter after an idle-capacity queue expiry by retrying the request on a fresh limiter ([#8616](https://github.com/diegosouzapw/OmniRoute/pull/8616)).
-- **fix(providers):** Kimi Coding billing-cycle quota errors now recover automatically at the cached reset instead of remaining unavailable ([#8632](https://github.com/diegosouzapw/OmniRoute/pull/8632)) — thanks @glazec
-- **fix(oauth):** show GitLab Duo OAuth app / env setup instructions in the Add Connection modal _before_ authorize, using a shared recipe with catalog `authHint` and the authorize-route error fallback (#8688)
-- **fix(sse):** combo compression-limit resolution falls back to `ResolvedComboTarget.provider` when `modelStr` lacks a `provider/` prefix, so `getTokenLimit` no longer crashes with `null.toUpperCase()` (#8716) — thanks @DinonowDev
-- **fix(db):** fall back to Node's built-in SQLite driver when better-sqlite3 is unavailable, while preserving read-only and existing-file safeguards ([#8724](https://github.com/diegosouzapw/OmniRoute/pull/8724)) — thanks @epsilonode
-- **fix(resilience):** keep missing request resources such as Files API ids from triggering model-family fallback, model lockout, or provider/account cooldown (thanks @wilsonicdev) ([#8756](https://github.com/diegosouzapw/OmniRoute/pull/8756))
-- **fix(api):** `GET /v1/models` no longer rebuilds the whole catalog on almost every request. The response cache added by [#6408](https://github.com/diegosouzapw/OmniRoute/pull/6408) memoized the body for `modelCatalogCacheTtlMs`, defaulted to 1500 ms — shorter than a single build (~49 s for a 1.3 MB / 2645-model catalog on a real install), so any two requests more than 1.5 s apart both missed the fresh window and the second fell into a stale-while-revalidate rebuild that pins the single-threaded event loop, delaying even the "immediate" stale response. The default is now 60 s, matching the ceiling the settings schema already allows for the override. A short TTL was redundant with the cache's existing invalidation: `invalidateDbCache()` bumps the catalog cache version on every settings/connections/combos/pricing write, so post-write freshness never depended on the TTL. ([#8833](https://github.com/diegosouzapw/OmniRoute/pull/8833))
-- **GHE Copilot**: OpenAI-native models now route to `<gheUrl>/responses` instead of failing with `model "..." is not accessible via the /chat/completions endpoint` — `gpt-5.4-mini`, `gpt-5.3-codex`, `mai-code-1-flash` and `oswe-vscode-prime` carry `targetFormat: "openai-responses"`, and `gpt-5.6-sol`/`terra`/`luna` are registered. Claude and Gemini models under `ghe-copilot` keep using `/chat/completions` ([#8835](https://github.com/diegosouzapw/OmniRoute/pull/8835)) — thanks @hppsc1215
-- **CLI**: `omniroute launch` no longer truncates pass-through arguments at the first space on Windows — each argument is escaped for cmd.exe (CRT argv rules plus a double caret pass, required because `claude.cmd` re-parses `%*`). A non-zero child exit also stops aborting the process with a libuv assertion: the exit code is set on `process.exitCode` so the loop drains the inherited stdio handles first ([#8837](https://github.com/diegosouzapw/OmniRoute/pull/8837)) — thanks @sumanxg
-- **Providers**: Codex GPT-5.6 Sol/Terra/Luna report the current upstream context window of 272000 instead of a stale 372000, so catalog consumers stop compacting past the Codex backend real input limit. Public OpenAI API GPT-5.6 metadata is unchanged ([#8838](https://github.com/diegosouzapw/OmniRoute/pull/8838)) — thanks @TitoTFP
-- **Antigravity**: a token refresh now recovers a missing `projectId` instead of leaving the connection stuck on 422 — when the initial OAuth exchange fails to populate it (network timeout, account not yet onboarded to Gemini Code Assist), `refreshCredentials` retries discovery via `ensureAntigravityProjectAssigned` and persists the result, mirroring the runtime `transformRequest` path. Best-effort: a failed discovery leaves the next request to retry ([#8842](https://github.com/diegosouzapw/OmniRoute/pull/8842)) — thanks @HouMinXi
-- **CI**: `check:tracked-artifacts` raises the `git ls-files` stdout ceiling to 64 MiB — the default 1 MiB `execFileSync` buffer had only ~6 KB of headroom against the tracked tree, and overflowing it throws ENOBUFS in the pre-commit hook, breaking `git commit` for everyone working the repo ([#8844](https://github.com/diegosouzapw/OmniRoute/pull/8844))
-- **OAuth**: `ANTIGRAVITY_OAUTH_CLIENT_TYPE=web` lets a remote deployment use a Google Web application OAuth client, upgrading the loopback redirect to `OMNIROUTE_PUBLIC_BASE_URL` instead of leaving the operator to hand-edit the callback URL. Opt-in and requires custom credentials — unset or `desktop` keeps the existing loopback behaviour untouched ([#8845](https://github.com/diegosouzapw/OmniRoute/pull/8845)) — thanks @HouMinXi
-- **fix(executors):** Vertex AI now routes current-generation Claude models (`claude-sonnet-4-6`, `claude-haiku-4-5`, etc.) through the partner endpoint instead of misrouting them as Google-publisher models ([#8852](https://github.com/diegosouzapw/OmniRoute/pull/8852)) — thanks @wgordon17
-- **CLI**: `omniroute launch-codex` no longer corrupts the codex argv on Windows — every invocation was affected, not just multi-word ones, because `buildCodexProviderArgs()` injects `-c` flags whose TOML values are quoted and cmd.exe stripped those quotes. The escaping helper introduced for `launch` is now shared from `bin/cli/utils/winShellArgs.mjs` and applied to the whole codex argv. A non-zero child exit also sets `process.exitCode` instead of calling `process.exit()`, which aborted with a libuv assertion while the inherited stdio handles were still closing ([#8856](https://github.com/diegosouzapw/OmniRoute/pull/8856)) — thanks @sumanxg
-- **Providers**: AGY model sync now discovers newly announced chat models from the live Antigravity catalog while filtering internal and tab-completion-only models, with the bundled catalog retained as an offline fallback
-- fix(security): bound JWT-extraction regexes in adobeFireflyClient to prevent polynomial ReDoS (CodeQL #754/#755/#756)
-- Fixed every non-streaming Codex (ChatGPT-account) chat request failing with `[502]: Response body is already used (reset after 1m)`: `peekCodexSseTransientError` re-acquired a reader on the upstream `response.body` after `releaseLock()` to continue draining it, which throws on undici. It now keeps the single reader it already holds. The thrown TypeError was also being mis-classified as a 60s rate limit (cooldown + circuit breaker) — that misfire disappears with the double-read fixed.
-- **Logging**: a broken stdout/stderr pipe no longer drives a self-sustaining log-flood loop — `consoleInterceptor` attaches `'error'` listeners to both std streams so an async EPIPE stops becoming an `uncaughtException` the framework re-logs through the patched console (measured 3,387 uncaught exceptions in 1.5s, now 0), non-EPIPE stream errors are re-raised so conditions like `ENOSPC` stay fatal, `structuredLogger`'s raw stderr writes skip a stream already known dead, interceptor disk writes are rate limited at `error` level only so ordinary logging is untouched, and a log directory removed at runtime is recreated instead of silently ending file logging (#8181)
-- docs: correct three stale references caught by the fabricated-docs gate (`/api/version` → `/api/monitoring/health`, migration `125_` → `126_reasoning_routing_rules.sql`)
-- Fix the Turbopack `next build` breaking with "Module not found: Can't resolve 'child_process'": the Kimi sponsor banner's client-side version gate imported semver helpers from `versionCheck.ts` (a server module with a top-level `child_process` import), dragging Node built-ins into the browser bundle. The pure `isNewer`/`normalizeVersion` helpers now live in a dependency-free `versionCompare.ts`; `versionCheck.ts` re-exports them for back-compat.
-- Fix `mitm-dnsConfig` unit tests failing when the suite runs as root (or with `OMNIROUTE_NO_SUDO` / no `sudo` installed): they hardcoded `sudo` as the spawned command, but `resolveSudoSpawn()` deliberately strips the `sudo -S` prefix in those environments (#6122). The tests now assert the effective invocation (`tee -a <hosts file>`, elevated or not).
-- muse-spark-web: the WebSocket 401 auth-failure message now names the live `ecto_1_sess` cookie (the retired `abra_sess` name was dropped in the GraphQL→WS migration), so users know which cookie to re-paste.
-- Harden the Notion web provider thread-session cache against cross-tenant access: the cache is now namespaced per caller (hash of the caller's cookie) instead of only by Notion space id, and client-supplied thread ids are validated as real Notion UUIDs before use — closing an IDOR where two users of the same Notion space could pin/read each other's thread (#7900 security review).
-- fix(security): OIDC login gate now requires `email_verified` before honoring the email claim against the allowlist (an unverified IdP email matching an allowlisted address no longer bypasses the gate), and error redirects resolve against the parsed request URL instead of the raw Host header
-- **Build**: the packed tarball boots again — #7191's `../../src/…runtimeTimeouts.ts` import in `standalone-server-ws.mjs` escaped the package after the dist-root copy (`ERR_MODULE_NOT_FOUND` on every boot, #7065 class, caught live by the new `check:pack-boot` gate); the helper now lives in the shipped sibling `main-server-timeouts.mjs` (parity-tested against the canonical TS implementation) and the closure test bans package-escaping `../` imports in npm-shipped wrappers
-- **Packaging**: new `check:pack-boot` gate packs the real npm tarball, installs it into a clean prefix (postinstall runs for real) and boots the installed CLI until `/api/monitoring/health` returns 200 with the packed version — the runtime gate that structure checks could not provide (3 releases shipped boot-crashing tarballs with green packaging lists: tls-options/3.8.41, #7040, #7065). Wired into the CI `package-artifact` job and `check:release-green --with-build`
-- **Packaging**: pack-artifact closure tests now cover EVERY npm-shipped dist wrapper (derived from `EXTRA_MODULE_ENTRIES`) and the `bin/omniroute.mjs` CLI entry — including dynamic `import()` and `require()` forms the original server-ws test missed — requiring each local import in both the prepublish prune allowlist and `check:pack-artifact`; `bin/cli/data-dir.mjs` and `bin/cli/utils/storageKeyProvision.mjs` are now required tarball paths (#7065 class hardening, WS1.1)
-- **fix(cli):** CLI detection now refreshes stale cached results, reports discovered versions, and checks the Continue `cn` binary instead of assuming it is installed.
-- **fix(docker):** Podman deployment guidance now distinguishes local Linux rootless engines from macOS/Windows Podman Machine, corrects Quadlet and local-build instructions, and avoids unsupported remote-client `podman unshare` hints ([#8497](https://github.com/diegosouzapw/OmniRoute/issues/8497)).
-- **fix(ui):** Theme React Flow controls correctly in dark mode, improve idle connector contrast, and localize the provider topology legend.
-- **fix(plugins):** the generated plugin host script is now deleted synchronously — an async `rm()` lost the race against process exit, so every plugin load under `node --test --test-force-exit` leaked one temp `.mjs` into the OS temp dir; two plugin manager tests also stopped leaking child processes
-- **fix(compression):** the Headroom SmartCrusher tabular-compaction guard now also skips `role: "developer"` messages, not just `role: "system"` — Codex CLI sends its instructions/tool-schema turn as `developer` (the Responses-API equivalent of `system`), so an embedded JSON array (e.g. an `update_plan` example) could get tabular-compacted, corrupting the model's tool-calling instructions and breaking Codex CLI plan mode. (thanks @SingCJ)
-- **Skills**: register `cli-skill-collector` in the agent-skills catalog (types union, curated entry, CLI id list) — #6294 shipped the `skills/cli-skill-collector/` directory without the catalog registration, so it was unreachable via the API and Integration CI failed on the catalog-integrity test; counts aligned (44 API+CLI, 45 with config)
-- **fix(responses):** Make Responses API to Chat Completions downgrades provider-neutral and loss-aware. Tools declared through `additional_tools` are preserved, structured output and `allowed_tools` are translated, refusal history is normalized, unsupported input item types fail explicitly instead of disappearing, and Responses-only execution/cache fields no longer leak to strict Chat endpoints.
-- **fix(stream):** Responses API clients (`/v1/responses`) no longer receive a stray `</think>` text delta at the start of the assistant message on Claude-format upstreams (observed with kimi-coding). The `</think>` close marker (#4633) exists for Chat Completions clients that scan content for it; Responses API clients receive reasoning as structured reasoning items, so the marker is now always suppressed on that path — including the GLM and zed-hosted executors, which do their own Claude→OpenAI translation.
-- fix(security): bump adm-zip to ^0.6.0 (dev transitive via promptfoo/onnxruntime-node) to clear the crafted-ZIP 4GB-allocation advisory, and tighten mitm DNS test host assertions to exact/suffix matching (CodeQL js/incomplete-url-substring-sanitization)
-- chore(deps): bump fast-uri≥3.1.3, hono≥4.12.27, @hono/node-server≥2.0.5, body-parser≥2.3.0 to clear 7 Dependabot alerts
-- chore(deps): bump dompurify≥3.4.12, fast-xml-parser≥5.10.1, sharp≥0.35.0 to clear 3 Dependabot alerts
-- fix(quality): register the two covering unit tests missing from stryker tap.testFiles (#6846, #7333)
-- fix(auth): restore the TICK_MS constant dropped by #7719, which made initTokenHealthCheck() throw a ReferenceError at startup
-- fix(guardrails/chat): do not whole-request-reroute Vision Bridge away from credentialed models (e.g. combo target zai/glm-5.2 or grok-cli → opencode-zen noauth 401); align body.model with X-Route-Model so post-guardrail cannot undo the routing header
-- **Providers**: yuanbao-web no longer forwards a foreign single cookie pair upstream — `buildYuanbaoCookie` only trusts `hy_user`/`hy_token` extractions the input explicitly names, so a missing session token now fails fast with the local 401 guidance instead of a live Tencent round-trip
-- **Antigravity**: the shared token-refresh service now recovers a missing `projectId` too — #8842 fixed the executor path, but the Dashboard and the health check refresh through `open-sse/services/tokenRefresh.ts`, which kept returning credentials with an empty project and left those accounts on 422 ([#8860](https://github.com/diegosouzapw/OmniRoute/pull/8860)) — thanks @HouMinXi
-- **Adobe Firefly**: `gpt-image` requests now default `detailLevel` to maximal (5) instead of leaving the upstream default, so generations come back at the quality the model is capable of ([#8863](https://github.com/diegosouzapw/OmniRoute/pull/8863)) — thanks @artickc
-- **Combos**: deleting a provider connection now clears the combo steps that referenced it — `connectionId` and `allowedConnectionIds` entries pointing at the removed connection were left behind, so combo routing kept trying a connection that no longer existed ([#8865](https://github.com/diegosouzapw/OmniRoute/pull/8865)) — thanks @HouMinXi
-- **Auto routing**: `auto/<family>` combos (`auto/glm`, `auto/gemini`, `auto/llama`, …) are recognized as built-in auto models again — the family suffix failed the category/tier parser and fell through as an unknown model instead of routing to that family ([#8866](https://github.com/diegosouzapw/OmniRoute/pull/8866)) — thanks @rafaeldrincon
-- **fix(oauth):** wire Test Connection for xAI OAuth (`xai-oauth` / `xao`) so dashboard no longer returns "Provider test not supported" ([#8862](https://github.com/diegosouzapw/OmniRoute/pull/8862)) — thanks @allanvb
-- **Logs**: a failed `auto/<family>` request no longer writes every attempted model into `call_logs.provider` — the logs page builds its quick-filter pills from that column, so one failure produced a giant chip that flooded the filter row. Rejected combo requests are now labelled `auto` (for `auto/*`) or by the combo's own name ([#8867](https://github.com/diegosouzapw/OmniRoute/pull/8867)) — thanks @rafaeldrincon
-- **fix(usage):** correct token/request counting for 30D/90D/YTD/ALL ranges ([#7300](https://github.com/diegosouzapw/OmniRoute/pull/7300)) — thanks @growab
-- **fix(notion-web):** use Chrome TLS impersonation for runInferenceTranscript ([#8159](https://github.com/diegosouzapw/OmniRoute/pull/8159)) — thanks @artickc
-- **fix(bifrost):** send v-prefixed transport version, not bare semver ([#8194](https://github.com/diegosouzapw/OmniRoute/pull/8194)) — thanks @seanford
-- **fix(resilience,translator):** three release/v3.8.49 base-red regressions + eslint baseline — conflict resolved ([#8254](https://github.com/diegosouzapw/OmniRoute/pull/8254))
-- **fix(sse):** export PROVIDER_BREAKER_FAILURE_STATUSES — fix ReferenceError in chat.ts (base-red slice 4) ([#8258](https://github.com/diegosouzapw/OmniRoute/pull/8258))
-- **fix(providers):** limit Gemini CLI to legacy OAuth refresh ([#8275](https://github.com/diegosouzapw/OmniRoute/pull/8275)) — thanks @backryun
-- **fix(cli):** resolve claude.cmd on Windows in omniroute launch ([#8283](https://github.com/diegosouzapw/OmniRoute/pull/8283)) — thanks @Dingding-leo
-- **fix(resilience):** skip terminal connections in token health check sweep ([#8286](https://github.com/diegosouzapw/OmniRoute/pull/8286)) — thanks @Dingding-leo
-- **fix(sanitizer):** strip zero-width chars from Anthropic-native streaming text_delta ([#8287](https://github.com/diegosouzapw/OmniRoute/pull/8287)) — thanks @Dingding-leo
-- **fix(i18n):** re-sync and complete es-ES translations with latest release/v3.8.49 ([#8289](https://github.com/diegosouzapw/OmniRoute/pull/8289)) — thanks @Dragost
-- **fix(antigravity):** add missing gemini-3.6-flash pricing rows to ag OAuth pricing ([#8290](https://github.com/diegosouzapw/OmniRoute/pull/8290)) — thanks @HouMinXi
-- **fix(dashboard):** stop sidebar RSC prefetch storms ([#8292](https://github.com/diegosouzapw/OmniRoute/pull/8292)) — thanks @RaviTharuma
-- **fix(backend):** add structure-aware chat admission ([#8296](https://github.com/diegosouzapw/OmniRoute/pull/8296)) — thanks @RaviTharuma
-- **fix(providers):** adapt Kimi nonstream requests internally ([#8302](https://github.com/diegosouzapw/OmniRoute/pull/8302)) — thanks @RaviTharuma
-- **fix(mcp):** keep POST SSE responses uncompressed ([#8303](https://github.com/diegosouzapw/OmniRoute/pull/8303)) — thanks @RaviTharuma
-- **fix(api):** enforce image generation API key auth ([#8306](https://github.com/diegosouzapw/OmniRoute/pull/8306)) — thanks @fenix007
-- **fix(cpa):** isolate credential-pool failures ([#8308](https://github.com/diegosouzapw/OmniRoute/pull/8308)) — thanks @RaviTharuma
-- **fix(sse):** suppress </think> by default on Chat Completions ([#8309](https://github.com/diegosouzapw/OmniRoute/pull/8309)) — thanks @Prudhvivuda
-- **fix(translator):** cap thinking budget on explicit budget_tokens path ([#8312](https://github.com/diegosouzapw/OmniRoute/pull/8312)) — thanks @HouMinXi
-- **fix(providers):** classify HTTP 400 model-unavailable as MODEL_NOT_FOUND so Antigravity Pro fallback locks out the deprecated model ([#8319](https://github.com/diegosouzapw/OmniRoute/pull/8319))
-- **fix(providers):** carve cookie-auth providers out of terminal 401 'expired' classification so one 401 cooldowns instead of killing the connection ([#8321](https://github.com/diegosouzapw/OmniRoute/pull/8321))
-- **fix(api):** fold namespace into the flattened Chat tool name so cross-namespace leaves do not collide ([#8322](https://github.com/diegosouzapw/OmniRoute/pull/8322))
-- **fix(providers):** route noauth opencode-zen connections through their assigned proxy ([#8324](https://github.com/diegosouzapw/OmniRoute/pull/8324))
-- **fix(security):** remove quadratic trailing-slash trim in Alibaba endpoint normalization ([#8333](https://github.com/diegosouzapw/OmniRoute/pull/8333))
-- **fix(memory):** self-heal upsertVector/deleteVector from a raced vec_memories drop ([#8337](https://github.com/diegosouzapw/OmniRoute/pull/8337)) — thanks @hartmark
-- **fix(sse):** stop stripInternalReasoningPlaceholder from eating inter-word spaces ([#8341](https://github.com/diegosouzapw/OmniRoute/pull/8341)) — thanks @hartmark
-- **fix(compression):** rank codex-responses in adaptive-ladder maps ([#8381](https://github.com/diegosouzapw/OmniRoute/pull/8381))
-- **fix(sse):** gate reasoning-placeholder strip to chunks that contain the sentinel ([#8382](https://github.com/diegosouzapw/OmniRoute/pull/8382))
-- **fix(resilience):** terminal-skip spares the recoverable GitHub Copilot no_refresh_token state ([#8389](https://github.com/diegosouzapw/OmniRoute/pull/8389))
-- **fix(sse):** re-export PROVIDER_BREAKER_FAILURE_STATUSES for the orphaned all-rate-limited breaker path ([#8390](https://github.com/diegosouzapw/OmniRoute/pull/8390))
-- **fix(sse):** family auto-combos include any backend that serves the family (no-auth allowlist scoped to tier pools) ([#8391](https://github.com/diegosouzapw/OmniRoute/pull/8391))
-- **fix(sse):** cap exact cooldowns only when synthetic — verified upstream resets pass uncapped ([#8393](https://github.com/diegosouzapw/OmniRoute/pull/8393))
-- **fix(devin-cli):** update ACP JSON-RPC protocol for Devin CLI 3000.2.x (Fixes #8406) ([#8425](https://github.com/diegosouzapw/OmniRoute/pull/8425)) — thanks @MumuTW
-- **fix(auth):** exclude local CLI providers from tokenHealthCheck expiration (Fixes #8407) ([#8426](https://github.com/diegosouzapw/OmniRoute/pull/8426)) — thanks @MumuTW
-- **fix(oauth):** add devin-cli and agy entries to OAUTH_TEST_CONFIG ([#8427](https://github.com/diegosouzapw/OmniRoute/pull/8427)) — thanks @MumuTW
-- **fix(dashboard):** preserve connection health visual on last routed topology node ([#8428](https://github.com/diegosouzapw/OmniRoute/pull/8428)) — thanks @MumuTW
-- **fix(cursor):** bridge native TodoWrite completions ([#8432](https://github.com/diegosouzapw/OmniRoute/pull/8432)) — thanks @makcimbx
-- **fix(guardrails):** Vision Bridge describe-fallback ignores unreachable candidates ([#8433](https://github.com/diegosouzapw/OmniRoute/pull/8433)) — thanks @guhcostan
-- **fix(sse):** record tool calls into shared state for openai->openai-responses call-log summary ([#8462](https://github.com/diegosouzapw/OmniRoute/pull/8462)) — thanks @hartmark
-- **fix(oauth):** actionable guidance for LAN-origin loopback mismatches (codex + Antigravity) ([#8463](https://github.com/diegosouzapw/OmniRoute/pull/8463))
-- **fix(hyperagent):** sticky thread for agentic tool loops (Claude Code) ([#8470](https://github.com/diegosouzapw/OmniRoute/pull/8470)) — thanks @artickc
-- **fix:** combo input-bound, Responses->Chat image strip, qwen-web toolCalling, empty-response exhaustion ([#8476](https://github.com/diegosouzapw/OmniRoute/pull/8476)) — thanks @herjarsa
-- **fix(sse):** call the real abort-signal helper in the Gemini Business executor ([#8485](https://github.com/diegosouzapw/OmniRoute/pull/8485)) — thanks @backryun
-- **fix(providers):** honor Extra API Keys rotation in OpencodeExecutor ([#8493](https://github.com/diegosouzapw/OmniRoute/pull/8493)) — thanks @Prudhvivuda
-- **fix(backend):** fail closed when capability filters empty the combo pool ([#8494](https://github.com/diegosouzapw/OmniRoute/pull/8494)) — thanks @Prudhvivuda
-- **fix(providers):** resolve native vision for path-shaped multimodal model ids ([#8495](https://github.com/diegosouzapw/OmniRoute/pull/8495)) — thanks @Prudhvivuda
-- **fix(hyperagent):** default 1M context for fable/opus/sonnet ([#8496](https://github.com/diegosouzapw/OmniRoute/pull/8496)) — thanks @artickc
-- **fix(notion-web):** mint fresh thread for new OpenAI sessions with same opener ([#8511](https://github.com/diegosouzapw/OmniRoute/pull/8511)) — thanks @artickc
-- **fix(db):** classify compressionDetailNormalizers as db-internal in check-db-rules ([#8534](https://github.com/diegosouzapw/OmniRoute/pull/8534)) — thanks @MumuTW
-- **fix(sse):** label HTTP 499 disconnects as client_disconnected ([#8552](https://github.com/diegosouzapw/OmniRoute/pull/8552)) — thanks @DinonowDev
-- **fix(resilience):** honor comboCooldownWait for every combo strategy ([#8559](https://github.com/diegosouzapw/OmniRoute/pull/8559)) — thanks @DinonowDev
-- **fix(backend):** add error.code to synthOpenAIErrorChunk for guard compatibility ([#8570](https://github.com/diegosouzapw/OmniRoute/pull/8570)) — thanks @marceli1404
-- **fix(video):** validate Veo AI Free artifacts before success ([#8581](https://github.com/diegosouzapw/OmniRoute/pull/8581)) — thanks @brunnolouzada
-- **fix(routing):** exclude locked-out models from auto-combo candidates ([#8586](https://github.com/diegosouzapw/OmniRoute/pull/8586)) — thanks @Prudhvivuda
-- **fix(api):** prevent silent lost updates on concurrent settings writes ([#8587](https://github.com/diegosouzapw/OmniRoute/pull/8587)) — thanks @Prudhvivuda
-- **fix(auto-combo):** short-circuit expandAutoComboCandidatePool when models[] is non-empty ([#8598](https://github.com/diegosouzapw/OmniRoute/pull/8598)) — thanks @mikeiagents
-- **fix(auth):** tag internal/loopback-origin failed logins in the audit log ([#8606](https://github.com/diegosouzapw/OmniRoute/pull/8606)) — thanks @Prudhvivuda
-- **fix(providers):** declare explicit OpenCode plugin feature-flag defaults ([#8608](https://github.com/diegosouzapw/OmniRoute/pull/8608)) — thanks @Prudhvivuda
-- **fix(ci):** use webpack fallback for Node 26 compat build to stop OOM ([#8611](https://github.com/diegosouzapw/OmniRoute/pull/8611)) — thanks @Prudhvivuda
-- **fix(claude):** classify native subscription quota 429 ([#8628](https://github.com/diegosouzapw/OmniRoute/pull/8628)) — thanks @costaeder
-- **fix(windows):** request shell when spawning bare qoder binary name on Windows (fixes #8590) ([#8633](https://github.com/diegosouzapw/OmniRoute/pull/8633)) — thanks @Dingding-leo
-- **fix(middleware):** declare withInjectionGuard's context parameter optional ([#8644](https://github.com/diegosouzapw/OmniRoute/pull/8644)) — thanks @backryun
-- **fix(providers):** handle space-separated search queries via matchesAnyToken ([#8660](https://github.com/diegosouzapw/OmniRoute/pull/8660)) — thanks @maxmad64bis
-- **fix(dashboard):** broken icon allignment in `SegmentedControl.tsx` ([#8679](https://github.com/diegosouzapw/OmniRoute/pull/8679)) — thanks @0x2f0
-- **fix(providers):** deprecate Monster API provider (fixes #8676) ([#8691](https://github.com/diegosouzapw/OmniRoute/pull/8691)) — thanks @Dingding-leo
-- **fix(quality):** register the #8494 covering test in stryker tap.testFiles ([#8692](https://github.com/diegosouzapw/OmniRoute/pull/8692))
-- **fix(sse):** clamp max_tokens to the model output cap on every path ([#8698](https://github.com/diegosouzapw/OmniRoute/pull/8698))
-- **fix(executors):** pass TimeoutError reason to controller.abort() in 7 niche executors ([#8699](https://github.com/diegosouzapw/OmniRoute/pull/8699))
-- **fix(api):** serve /v1/models stale-first and sanitize its error bodies ([#8703](https://github.com/diegosouzapw/OmniRoute/pull/8703))
-- **fix(sse):** stop thrashing the provider prompt cache for caching-aware clients ([#8705](https://github.com/diegosouzapw/OmniRoute/pull/8705))
-- **fix:** repair five base-red failures on release/v3.8.49 ([#8706](https://github.com/diegosouzapw/OmniRoute/pull/8706))
-- **fix(oauth):** show GitLab Duo setup before authorize error ([#8710](https://github.com/diegosouzapw/OmniRoute/pull/8710)) — thanks @DinonowDev
-- **fix:** hydration mismatch, duplicate React keys, and missing ponytail i18n ([#8723](https://github.com/diegosouzapw/OmniRoute/pull/8723)) — thanks @Mananz90
-- **fix(sse):** hide synthetic OpenAI startup reasoning ([#8729](https://github.com/diegosouzapw/OmniRoute/pull/8729)) — thanks @rinseaid
-- **fix(guardrails):** check feature flag helper in PIIMasker to honor DB overrides ([#8730](https://github.com/diegosouzapw/OmniRoute/pull/8730)) — thanks @Dingding-leo
-- **fix(sse):** report a stream that completes without any content ([#8732](https://github.com/diegosouzapw/OmniRoute/pull/8732)) — thanks @backryun
-- **fix(plugins):** delete the generated host script synchronously so plugin loads stop leaking temp files ([#8749](https://github.com/diegosouzapw/OmniRoute/pull/8749)) — thanks @MumuTW
-- **fix(sse):** update ANTHROPIC_PING heartbeat data payload to {"type":"ping"} (fixes #8750) ([#8762](https://github.com/diegosouzapw/OmniRoute/pull/8762)) — thanks @Dingding-leo
-- **fix(cloudflare-ai):** sync missing free catalog models (fixes #8725) ([#8763](https://github.com/diegosouzapw/OmniRoute/pull/8763)) — thanks @Dingding-leo
-- **fix(bedrock):** preserve additionalModelRequestFields in converse payload (fixes #8746) ([#8764](https://github.com/diegosouzapw/OmniRoute/pull/8764)) — thanks @Dingding-leo
-- **fix(docs):** use correct kebab-case CLI flags in OpenCode guide (take 2) ([#8766](https://github.com/diegosouzapw/OmniRoute/pull/8766)) — thanks @swingtempo
-- **fix(db):** repair the extra-migration-dirs test and env contract on CI ([#8773](https://github.com/diegosouzapw/OmniRoute/pull/8773))
-- **fix(electron):** use NEXT_DIST_DIR when stripping stale native modules ([#8794](https://github.com/diegosouzapw/OmniRoute/pull/8794)) — thanks @NBN-N3
-- **fix(resilience):** add UND_ERR_SOCKET to PROXY_UNREACHABLE_ERROR_CODES ([#8795](https://github.com/diegosouzapw/OmniRoute/pull/8795)) — thanks @Dingding-leo
-- **fix(combo):** fail open when strict context filter empties unknown-only pools ([#8798](https://github.com/diegosouzapw/OmniRoute/pull/8798)) — thanks @DinonowDev
-- **fix(resilience):** honor Cloudflare 1010 retryable:false — skip COOLDOWN_RETRY ([#8800](https://github.com/diegosouzapw/OmniRoute/pull/8800)) — thanks @DinonowDev
-- **fix(dashboard):** restore Usage Model Breakdown column sorting ([#8802](https://github.com/diegosouzapw/OmniRoute/pull/8802)) — thanks @DinonowDev
-- **fix(api):** treat cx/* and codex/* as equivalent API-key model permissions ([#8805](https://github.com/diegosouzapw/OmniRoute/pull/8805)) — thanks @Prudhvivuda
-- **fix(sse):** pass real response payload into plugin onResponse hooks ([#8806](https://github.com/diegosouzapw/OmniRoute/pull/8806)) — thanks @Prudhvivuda
-- **fix(types):** export web executor types from their module ([#8810](https://github.com/diegosouzapw/OmniRoute/pull/8810)) — thanks @backryun
-- **fix(types):** preserve reasoning policy record shapes ([#8811](https://github.com/diegosouzapw/OmniRoute/pull/8811)) — thanks @backryun
-- **fix(types):** preserve compression detail config shapes ([#8812](https://github.com/diegosouzapw/OmniRoute/pull/8812)) — thanks @backryun
-- **fix(types):** declare virtual chaos combo config ([#8815](https://github.com/diegosouzapw/OmniRoute/pull/8815)) — thanks @backryun
-- **fix(types):** type memory skills injection logger ([#8816](https://github.com/diegosouzapw/OmniRoute/pull/8816)) — thanks @backryun
-- **fix(types):** align web fallback contracts ([#8819](https://github.com/diegosouzapw/OmniRoute/pull/8819)) — thanks @backryun
-- **fix(types):** declare idempotency input contracts ([#8820](https://github.com/diegosouzapw/OmniRoute/pull/8820)) — thanks @backryun
-- **fix(reasoning):** sanitize streamed K3 think tags ([#8821](https://github.com/diegosouzapw/OmniRoute/pull/8821)) — thanks @rinseaid
-- **fix(types):** normalize Kie transcription results ([#8824](https://github.com/diegosouzapw/OmniRoute/pull/8824)) — thanks @backryun
-- **fix(dashboard):** surface quota pool delete failures instead of failing silently ([#8829](https://github.com/diegosouzapw/OmniRoute/pull/8829))
-- **fix(autoCombo):** normalize -free suffix in task fitness lookups ([#8636](https://github.com/diegosouzapw/OmniRoute/pull/8636)) — thanks @Dingding-leo
-- **fix(sse):** split the reasoning-decision guards so the error arm actually narrows ([#8641](https://github.com/diegosouzapw/OmniRoute/pull/8641)) — thanks @backryun
-- **fix(openai-to-claude):** skip empty reasoning_content string deltas ([#8642](https://github.com/diegosouzapw/OmniRoute/pull/8642)) — thanks @Dingding-leo
-- **fix(autoCombo):** match longest pattern first in lookupStaticFitnessTable ([#8651](https://github.com/diegosouzapw/OmniRoute/pull/8651)) — thanks @Dingding-leo
-- **fix(providers):** sync search query to URL query param ([#8652](https://github.com/diegosouzapw/OmniRoute/pull/8652)) — thanks @Dingding-leo
-- **fix(maritalk):** refresh supported model catalog ([#8663](https://github.com/diegosouzapw/OmniRoute/pull/8663)) — thanks @backryun
-- **fix(agentSkills):** scope command slice before nested subcommands to prevent flag mis-attribution ([#8667](https://github.com/diegosouzapw/OmniRoute/pull/8667)) — thanks @Dingding-leo
-- **fix(guardrails):** ensure request PII masking respects DB feature flag overrides ([#8715](https://github.com/diegosouzapw/OmniRoute/pull/8715)) — thanks @Dingding-leo
-- **fix(reasoning):** sanitize Kimi Code K3 think tags ([#8721](https://github.com/diegosouzapw/OmniRoute/pull/8721)) — thanks @rinseaid
-- **fix(sse):** clamp out-of-range Gemini thinking_budget and learn the cap ([#8726](https://github.com/diegosouzapw/OmniRoute/pull/8726)) — thanks @fuko2935
-- **fix(providers):** support multi-token search in provider filter ([#8731](https://github.com/diegosouzapw/OmniRoute/pull/8731)) — thanks @Dingding-leo
-- **fix(api):** stop JSON.stringify-ing messages before estimateTokens (restores #8368 image estimate) [recovered from #8599] ([#8740](https://github.com/diegosouzapw/OmniRoute/pull/8740))
-- **fix(quality):** let --update remove baseline entries that already fit the cap ([#8741](https://github.com/diegosouzapw/OmniRoute/pull/8741)) — thanks @MumuTW
-- **fix:** escape angle brackets in i18n messages to prevent next-intl INVALID_MESSAGE errors ([#8747](https://github.com/diegosouzapw/OmniRoute/pull/8747)) — thanks @SteeleHu
-- **fix(dashboard):** Request Logs detail no longer crashes on a structured error object — #7920 introduced `formatErrorForDisplay` for exactly this, but the combo-503 / cooldown checks added by #8213 read the raw field and called `.toLowerCase()` on it. Both paths now share the helper.
-- **fix(dashboard):** the logs detail modal stops reopening on first close again — #6830 fixed it by reading the deep-link id once, and the #8354 page rewrite regressed it by reading the live `searchParams` on every render, flipping the prop mid-session.
-### 📚 Docs
-
-- **docs(quality):** codify retry policy per runner + release-level drift rule (WS5.4/WS5.5) ([#7107](https://github.com/diegosouzapw/OmniRoute/pull/7107))
-- **docs(troubleshooting):** document Avast/AVG README.md false positive (#5946) ([#7295](https://github.com/diegosouzapw/OmniRoute/pull/7295))
-- **docs(perf):** add per-endpoint p50/p95/p99 latency + cost budget reference ([#7336](https://github.com/diegosouzapw/OmniRoute/pull/7336)) — thanks @KooshaPari
-- **docs:** refresh revoked Discord invite + WhatsApp Brasil link ([#7604](https://github.com/diegosouzapw/OmniRoute/pull/7604))
-- **docs(readme):** animated SVG for the 4-tier auto-fallback cascade ([#7615](https://github.com/diegosouzapw/OmniRoute/pull/7615))
-- **docs:** sync provider count to 259 (unblocks docs-counts strict gate) ([#7616](https://github.com/diegosouzapw/OmniRoute/pull/7616))
-- **docs(readme):** animate pool + combo ASCII blocks as SMIL SVG diagrams ([#7626](https://github.com/diegosouzapw/OmniRoute/pull/7626))
-- **docs(readme):** animate CLI command list + compression flow as SMIL SVGs ([#7637](https://github.com/diegosouzapw/OmniRoute/pull/7637))
-- **docs(readme):** replace free-tier budget mockup with animated SMIL card ([#7665](https://github.com/diegosouzapw/OmniRoute/pull/7665))
-- **docs(readme):** standardize all README tables to full content width ([#7666](https://github.com/diegosouzapw/OmniRoute/pull/7666))
-
-- **docs:** fix three stale references failing the fabricated-docs gate ([#7728](https://github.com/diegosouzapw/OmniRoute/pull/7728))
-- **docs(readme):** unified animated card system — audited v3.8.49 numbers, style contract across all cards, 5 new cards + rebuilt terminal ([#7769](https://github.com/diegosouzapw/OmniRoute/pull/7769))
-- **docs(readme):** add Kimi (Moonshot AI) official supporter section ([#7770](https://github.com/diegosouzapw/OmniRoute/pull/7770))
-- **docs(getting-started):** reorder Verify It Works before IDE/CLI setup + add examples ([#7790](https://github.com/diegosouzapw/OmniRoute/pull/7790)) — thanks @swingtempo
-- **docs(readme):** audit every number against the live code + refresh contributors and acknowledgments ([#7795](https://github.com/diegosouzapw/OmniRoute/pull/7795))
-- **docs(readme):** evolve supporter section into sub2api-style Sponsors section ([#7799](https://github.com/diegosouzapw/OmniRoute/pull/7799))
-- **docs(readme):** contributors 360+ -> 350+ (audited) ([#7803](https://github.com/diegosouzapw/OmniRoute/pull/7803))
-- **docs(i18n):** refresh Polish README and fix relative links ([#7807](https://github.com/diegosouzapw/OmniRoute/pull/7807)) — thanks @leszek3737
-- **docs:** add general Web Cookie provider setup guide ([#7881](https://github.com/diegosouzapw/OmniRoute/pull/7881)) — thanks @arpit-jaiswal-dev
-- **docs(guides):** document Kaspersky PDM behavioral false positive on the Desktop installer (#7903) ([#7923](https://github.com/diegosouzapw/OmniRoute/pull/7923))
-- **docs:** document npm install ERESOLVE/peer/deprecated warnings as harmless (fixes #7951) ([#7988](https://github.com/diegosouzapw/OmniRoute/pull/7988)) — thanks @Dingding-leo
-- **docs:** fix Docker IPv6 connection reset with -p 127.0.0.1 bind (fixes #7722) ([#7989](https://github.com/diegosouzapw/OmniRoute/pull/7989)) — thanks @Dingding-leo
-- **docs(readme):** Kimi partner tracking links (aff=omniroute) + first-Brazilian-project line + disclosure ([#8028](https://github.com/diegosouzapw/OmniRoute/pull/8028))
-- **docs:** add AgentRouter multi-provider routing troubleshooting ([#8049](https://github.com/diegosouzapw/OmniRoute/pull/8049)) — thanks @leninejunior
-- **docs(security):** correct prompt-injection severity table + heuristic-limitations disclaimer (#8097) ([#8113](https://github.com/diegosouzapw/OmniRoute/pull/8113)) — thanks @rafaumeu
-- **docs(ops):** publish public branching and release model (#7627) ([#8129](https://github.com/diegosouzapw/OmniRoute/pull/8129)) — thanks @c4usal
-- **docs(i18n):** full Russian README rewrite ([#8217](https://github.com/diegosouzapw/OmniRoute/pull/8217)) — thanks @MonteNegroX
-- **docs(readme):** re-audit numbers, fix table scroll, refresh contributors ([#8243](https://github.com/diegosouzapw/OmniRoute/pull/8243))
-- **docs(db):** propose pluggable persistence boundary ([#8261](https://github.com/diegosouzapw/OmniRoute/pull/8261)) — thanks @xiaoyaner0201
-- **docs(db):** add reproducible SQLite coupling inventory ([#8262](https://github.com/diegosouzapw/OmniRoute/pull/8262)) — thanks @xiaoyaner0201
-- **docs:** add public ROADMAP (3.8.5x rail -> 3.9.0 LTS -> 4.0 modular platform) ([#8348](https://github.com/diegosouzapw/OmniRoute/pull/8348))
-- **docs:** sync env-var contract (chaos panel, notion TLS, grok auth path) + repair glued VNC line in .env.example ([#8362](https://github.com/diegosouzapw/OmniRoute/pull/8362))
-- **docs:** one golden path across PR template, CONTRIBUTING, GEMINI, AGENTS + CI milestones in ROADMAP ([#8380](https://github.com/diegosouzapw/OmniRoute/pull/8380))
-- **docs(claude-code):** document unprefixed model IDs and the Ambiguous model error ([#8410](https://github.com/diegosouzapw/OmniRoute/pull/8410)) — thanks @dvirarad
-- **docs(podman):** clarify Podman Machine deployment ([#8569](https://github.com/diegosouzapw/OmniRoute/pull/8569)) — thanks @shixi-li
-- **docs(env):** document NEXT_PUBLIC_OMNIROUTE_BASE_PATH and OMNIROUTE_BACKUP_SCHEDULE_JOB_INTERVAL_MS ([#8690](https://github.com/diegosouzapw/OmniRoute/pull/8690)) — thanks @MumuTW
-- **docs(codex):** document session affinity and stream idle for long tasks ([#8709](https://github.com/diegosouzapw/OmniRoute/pull/8709)) — thanks @DinonowDev
-- **docs:** replace outdated Polish docs with translation from latest English ([#8823](https://github.com/diegosouzapw/OmniRoute/pull/8823)) — thanks @leszek3737
-- **docs:** restore the Polish API_REFERENCE removed by #8823 ([#8831](https://github.com/diegosouzapw/OmniRoute/pull/8831))
-### 🧪 Tests & Quality
-
-- **test(build):** derive pack-artifact closures for all npm-shipped entrypoints (#7065 class) ([#7081](https://github.com/diegosouzapw/OmniRoute/pull/7081))
-- **test(dashboard):** dedicated regression guard for #6815 density guarantee ([#7291](https://github.com/diegosouzapw/OmniRoute/pull/7291))
-- **test(ci):** make #6634 selfref guard hermetic — read file from disk, no git ref ([#7327](https://github.com/diegosouzapw/OmniRoute/pull/7327))
-- **test(ci):** mock route bridge surfaces error message, not raw stack ([#7354](https://github.com/diegosouzapw/OmniRoute/pull/7354))
-- **test(ci):** static body in codex e2e mock route bridge (CodeQL #737) ([#7558](https://github.com/diegosouzapw/OmniRoute/pull/7558))
-- **test(ci):** exact-line assert in grok-build config test (CodeQL #740/#741) ([#7628](https://github.com/diegosouzapw/OmniRoute/pull/7628))
-
-- **test(codex):** cover image tool output replay (#7698) ([#7704](https://github.com/diegosouzapw/OmniRoute/pull/7704)) — thanks @dongwook-chan
-- **test(security):** exact SAN-entry match in mitm leaf-cert test (CodeQL #746) ([#7824](https://github.com/diegosouzapw/OmniRoute/pull/7824))
-- **test(#8140):** verify keepalive interval cleanup on disconnect, resolve, and reject ([#8190](https://github.com/diegosouzapw/OmniRoute/pull/8190)) — thanks @rafaumeu
-- **test:** realign catalog snapshot tests to current deliberate catalog state ([#8386](https://github.com/diegosouzapw/OmniRoute/pull/8386))
-- **test:** hermetic notion thread-session mocks + drop duplicated usage-analytics suite ([#8392](https://github.com/diegosouzapw/OmniRoute/pull/8392))
-- **test(e2e):** contract test for the full provider journey ([#8444](https://github.com/diegosouzapw/OmniRoute/pull/8444)) — thanks @HoneyTyagii
-- **test(sse):** repair two base-red gates on release/v3.8.49 ([#8490](https://github.com/diegosouzapw/OmniRoute/pull/8490)) — thanks @backryun
-- **test(context):** isolate context-manager suite from local DATA_DIR ([#8596](https://github.com/diegosouzapw/OmniRoute/pull/8596)) — thanks @DinonowDev
-### 🔧 Chores / CI
-
-- **chore(release):** gate the sync-back push on release-green --quick (WS0.3) ([#7083](https://github.com/diegosouzapw/OmniRoute/pull/7083))
-- **chore(ci):** gate hygiene — secrets baseline 0, semgrep drop, hadolint (WS6/D3 + WS1.7) ([#7099](https://github.com/diegosouzapw/OmniRoute/pull/7099))
-- **chore(ops):** runner-box janitor + operations runbook (WS3.3) ([#7115](https://github.com/diegosouzapw/OmniRoute/pull/7115))
-- **chore(ci):** promote test:vitest:ui to blocking (suite green after #7127) ([#7147](https://github.com/diegosouzapw/OmniRoute/pull/7147))
-- **chore(ci):** stop dependabot proposing typescript majors — peer-blocked by typescript-eslint ([#7306](https://github.com/diegosouzapw/OmniRoute/pull/7306))
-- **chore(release):** script the 0a.0b PR re-home with a verified read-back ([#7312](https://github.com/diegosouzapw/OmniRoute/pull/7312))
-- **chore(quality):** tighten the coverage ratchet to the CI's real numbers ([#7326](https://github.com/diegosouzapw/OmniRoute/pull/7326))
-- **chore(ci):** make the Electron Windows leg advisory with bash stderr capture (first-run failure diagnosis) ([#7340](https://github.com/diegosouzapw/OmniRoute/pull/7340))
-- **chore(deps):** bump actions/setup-node from 6 to 7 ([#7348](https://github.com/diegosouzapw/OmniRoute/pull/7348))
-- **chore(deps):** bump codecov/codecov-action ([#7350](https://github.com/diegosouzapw/OmniRoute/pull/7350))
-- **ci(release-green):** add a main-green arm to detect when main goes red ([#7355](https://github.com/diegosouzapw/OmniRoute/pull/7355))
-- **chore(deps):** bump github/codeql-action/analyze from 4.37.0 to 4.37.1 ([#7641](https://github.com/diegosouzapw/OmniRoute/pull/7641))
-- **chore(deps):** bump github/codeql-action/init from 4.37.0 to 4.37.1 ([#7642](https://github.com/diegosouzapw/OmniRoute/pull/7642))
-- **chore(quality):** register #6672 test in stryker tap.testFiles (base-red unblock) ([#7652](https://github.com/diegosouzapw/OmniRoute/pull/7652))
-- **chore(release):** merge-train box-speed suite + --fast mode ([#7670](https://github.com/diegosouzapw/OmniRoute/pull/7670))
-
-- **chore:** [defer] fix embedded CLIProxyAPI config handling ([#6877](https://github.com/diegosouzapw/OmniRoute/pull/6877)) — thanks @professional-ALFIE
-- **chore:** [defer] fix(grok): align responses tool-call shape for grok models ([#6937](https://github.com/diegosouzapw/OmniRoute/pull/6937)) — thanks @CitrusIce
-- **chore:** [needs-vps] feat(dashboard): add per-operator quota row visibility on usage tab ([#7251](https://github.com/diegosouzapw/OmniRoute/pull/7251))
-- **chore:** [defer] feat(combo): universal cooldown-aware retry & auto-strategy combo-ref guard ([#7301](https://github.com/diegosouzapw/OmniRoute/pull/7301)) — thanks @ViFigueiredo
-- **chore:** Completing Arabic language ([#7686](https://github.com/diegosouzapw/OmniRoute/pull/7686)) — thanks @mustafa-phd
-- **chore:** IC2: Cache provider connections by ID + provider nodes ([#7744](https://github.com/diegosouzapw/OmniRoute/pull/7744)) — thanks @oyi77
-- **chore:** [Emergency Fix] fix(build): repair release build blockers ([#7772](https://github.com/diegosouzapw/OmniRoute/pull/7772)) — thanks @backryun
-- **chore:** [Part 1/3]refactor(qwen): replace legacy Qwen Code and remove OAuth provider ([#7866](https://github.com/diegosouzapw/OmniRoute/pull/7866)) — thanks @backryun
-- **chore:** [Part 3/3] feat(qwen): add regional Alibaba and Qwen Cloud providers ([#7882](https://github.com/diegosouzapw/OmniRoute/pull/7882)) — thanks @backryun
-- **chore:** Preserve supported Responses behavior in Chat translation ([#7894](https://github.com/diegosouzapw/OmniRoute/pull/7894)) — thanks @JxnLexn
-- **chore:** Restore Responses API custom tool calls ([#7905](https://github.com/diegosouzapw/OmniRoute/pull/7905)) — thanks @JxnLexn
-- **chore:** Hide internal reasoning replay placeholders ([#7912](https://github.com/diegosouzapw/OmniRoute/pull/7912)) — thanks @JxnLexn
-- **chore(deps):** bump js-yaml, brace-expansion, shell-quote, tar (security) ([#7915](https://github.com/diegosouzapw/OmniRoute/pull/7915))
-- **chore:** i18n(zh-TW): complete Traditional Chinese (Taiwan) translation overhaul ([#8024](https://github.com/diegosouzapw/OmniRoute/pull/8024)) — thanks @lunkerchen
-- **chore:** i18n: bring 40 locales to full parity with en.json ([#8031](https://github.com/diegosouzapw/OmniRoute/pull/8031)) — thanks @nguyenha935
-- **chore(deps):** resolve 7 open Dependabot alerts via npm overrides ([#8066](https://github.com/diegosouzapw/OmniRoute/pull/8066))
-- **chore(deps):** resolve 3 more Dependabot alerts (dompurify, fast-xml-parser, sharp) ([#8069](https://github.com/diegosouzapw/OmniRoute/pull/8069))
-- **chore(dashboard):** reframe Kimi partnership as "Open Source Friends" ([#8117](https://github.com/diegosouzapw/OmniRoute/pull/8117))
-- **chore(quality):** fix 2 pre-existing lint/suppression drift issues ([#8209](https://github.com/diegosouzapw/OmniRoute/pull/8209)) — thanks @hartmark
-- **chore:** add K3banner-1.png banner asset ([#8242](https://github.com/diegosouzapw/OmniRoute/pull/8242))
-- **chore(quality):** rebaseline accountFallback+combo for #8252 own-growth (post-merge follow-up) ([#8252](https://github.com/diegosouzapw/OmniRoute/pull/8252)) — thanks @RaviTharuma
-- **optimize(chaos+ponytail):** i18n ponytail, dedupl dispatch, provider diversity ([#8264](https://github.com/diegosouzapw/OmniRoute/pull/8264)) — thanks @Moseyuh333
-- **chore(deps):** bump next to 16.2.11 (9 security advisories) ([#8265](https://github.com/diegosouzapw/OmniRoute/pull/8265))
-- **chore:** Add Alibaba-family media model support ([#8266](https://github.com/diegosouzapw/OmniRoute/pull/8266)) — thanks @backryun
-- **chore:** Clicking a provider card hitting back loses scroll position ([#8349](https://github.com/diegosouzapw/OmniRoute/pull/8349)) — thanks @swingtempo
-- **chore:** feat(log): Added new visual scrolling log page ([#8354](https://github.com/diegosouzapw/OmniRoute/pull/8354)) — thanks @hartmark
-- **chore:** [BUG] enforceOutputTokenBudget ignores combo-resolved context limit, silently truncates responses ([#8378](https://github.com/diegosouzapw/OmniRoute/pull/8378)) — thanks @RCrushMe
-- **chore(ci):** cancel superseded runs, skip DAST on docs-only PRs, persist TIA shadow evidence ([#8379](https://github.com/diegosouzapw/OmniRoute/pull/8379))
-- **chore(quality):** drop stale muse-spark-web allowlist entry + sync sidebar order snapshots ([#8383](https://github.com/diegosouzapw/OmniRoute/pull/8383))
-- **chore:** i18n(zh-TW): translate missing Reasoning Routing strings ([#8423](https://github.com/diegosouzapw/OmniRoute/pull/8423)) — thanks @MumuTW
-- **chore(deps):** bump codecov/codecov-action from 5.5.5 to 7.0.0 ([#8452](https://github.com/diegosouzapw/OmniRoute/pull/8452))
-- **chore(deps):** bump github/codeql-action/analyze from 4.37.1 to 4.37.3 ([#8453](https://github.com/diegosouzapw/OmniRoute/pull/8453))
-- **chore(deps):** bump ossf/scorecard-action from 2.4.3 to 2.4.4 ([#8454](https://github.com/diegosouzapw/OmniRoute/pull/8454))
-- **chore(deps):** bump github/codeql-action/init from 4.37.1 to 4.37.3 ([#8455](https://github.com/diegosouzapw/OmniRoute/pull/8455))
-- **chore(deps):** bump actions/setup-python from 6 to 7 ([#8456](https://github.com/diegosouzapw/OmniRoute/pull/8456))
-- **chore(sse):** drop deprecated baseUrl from open-sse tsconfig for TS 7.0 ([#8473](https://github.com/diegosouzapw/OmniRoute/pull/8473)) — thanks @backryun
-- **refactor(sse):** resolve open-sse utils/translator type diagnostics for TS 7 ([#8483](https://github.com/diegosouzapw/OmniRoute/pull/8483)) — thanks @backryun
-- **refactor(sse):** declare the executor execute() result contract ([#8489](https://github.com/diegosouzapw/OmniRoute/pull/8489)) — thanks @backryun
-- **refactor(sse):** stop three executors shadowing BaseExecutor.buildHeaders ([#8498](https://github.com/diegosouzapw/OmniRoute/pull/8498)) — thanks @backryun
-- **refactor(sse):** narrow three result unions via type predicates ([#8499](https://github.com/diegosouzapw/OmniRoute/pull/8499)) — thanks @backryun
-- **refactor(sse):** restore three executor types the runtime already relied on ([#8520](https://github.com/diegosouzapw/OmniRoute/pull/8520)) — thanks @backryun
-- **refactor(dashboard):** clear file-size base-red by extracting provider-card highlight wiring ([#8524](https://github.com/diegosouzapw/OmniRoute/pull/8524)) — thanks @MumuTW
-- **refactor(guardrails):** narrow the documented void return at the dispatch site ([#8525](https://github.com/diegosouzapw/OmniRoute/pull/8525)) — thanks @backryun
-- **refactor(sse):** type the rerank response adapter's options parameter ([#8528](https://github.com/diegosouzapw/OmniRoute/pull/8528)) — thanks @backryun
-- **refactor(sse):** retag the designer-web result unions with string discriminants ([#8531](https://github.com/diegosouzapw/OmniRoute/pull/8531)) — thanks @backryun
-- **refactor(sse):** declare the multipart/gRPC frame bodies as ArrayBuffer-backed ([#8533](https://github.com/diegosouzapw/OmniRoute/pull/8533)) — thanks @backryun
-- **chore(ci):** resync stale no-explicit-any suppression count for proxy-registry.test.ts ([#8544](https://github.com/diegosouzapw/OmniRoute/pull/8544)) — thanks @MumuTW
-- **chore(usage):** decompose services/usage.ts into per-provider usage/* leaves (999 → 253) ([#8545](https://github.com/diegosouzapw/OmniRoute/pull/8545)) — thanks @MumuTW
-- **chore(validation):** decompose providers/validation.ts into validation/* leaves (→ 442) ([#8546](https://github.com/diegosouzapw/OmniRoute/pull/8546)) — thanks @MumuTW
-- **chore(token-refresh):** decompose services/tokenRefresh.ts into tokenRefresh/* leaves (999 → 724) ([#8547](https://github.com/diegosouzapw/OmniRoute/pull/8547)) — thanks @MumuTW
-- **chore(combo):** extract pure error predicates and quota status helpers to comboPredicates ([#8548](https://github.com/diegosouzapw/OmniRoute/pull/8548)) — thanks @MumuTW
-- **chore(i18n):** normalize zh-TW terminology and sync stale README figures ([#8554](https://github.com/diegosouzapw/OmniRoute/pull/8554)) — thanks @MumuTW
-- **refactor(sse):** stop isClaudeEventPayload claiming a narrowing it never performs ([#8557](https://github.com/diegosouzapw/OmniRoute/pull/8557)) — thanks @backryun
-- **chore(quality):** rebaseline file-size for inherited base growth ([#8561](https://github.com/diegosouzapw/OmniRoute/pull/8561)) — thanks @fenix007
-- **chore(deps):** patch js-yaml + postcss for 2 high Dependabot alerts ([#8572](https://github.com/diegosouzapw/OmniRoute/pull/8572))
-- **refactor(tls):** update TLSClient instantiation to use buildNativeTlsClientOptions across multiple services ([#8583](https://github.com/diegosouzapw/OmniRoute/pull/8583)) — thanks @DinonowDev
-- **refactor(sse):** peel the bare Response off handleChatCore's union in responsesHandler ([#8647](https://github.com/diegosouzapw/OmniRoute/pull/8647)) — thanks @backryun
-- **refactor(sse):** guard the KIE task-id and callback-url reads at their source ([#8661](https://github.com/diegosouzapw/OmniRoute/pull/8661)) — thanks @backryun
-- **refactor(sse):** declare the ArrayBuffer backing on media byte producers ([#8665](https://github.com/diegosouzapw/OmniRoute/pull/8665)) — thanks @backryun
-- **merge:** resolve conflicts for #7904 local corpus context ([#8685](https://github.com/diegosouzapw/OmniRoute/pull/8685)) — thanks @terrafirmbot-source (original author of #7904)
-- **chore(quality):** update baselines after v3.8.49 merge-train ([#8686](https://github.com/diegosouzapw/OmniRoute/pull/8686))
-- **chore:** Dependabot updates ([#8695](https://github.com/diegosouzapw/OmniRoute/pull/8695)) — thanks @justdoGIT
-- **chore:** Create AMIT ([#8727](https://github.com/diegosouzapw/OmniRoute/pull/8727)) — thanks @amitgolan60-coder
-- **chore(ci):** add release PR build gate ([#8735](https://github.com/diegosouzapw/OmniRoute/pull/8735)) — thanks @ekinnee
-- **chore:** Stabilize Notion web sessions and JSON output ([#8751](https://github.com/diegosouzapw/OmniRoute/pull/8751)) — thanks @0xheycat
-- **deps:** bump electron from 43.1.1 to 43.2.0 in /electron ([#8782](https://github.com/diegosouzapw/OmniRoute/pull/8782))
-- **deps:** bump the production group across 1 directory with 18 updates ([#8793](https://github.com/diegosouzapw/OmniRoute/pull/8793))
-- **refactor(sse):** retag the Adobe Firefly IMS token-check union ([#8638](https://github.com/diegosouzapw/OmniRoute/pull/8638)) — thanks @backryun
-- **refactor(db):** let the provider-nodes cache keep the row type it already returns ([#8639](https://github.com/diegosouzapw/OmniRoute/pull/8639)) — thanks @backryun
-- **refactor(sse):** use the shared ApiKeyMetadata in reasoningRouting instead of a local duck-type ([#8643](https://github.com/diegosouzapw/OmniRoute/pull/8643)) — thanks @backryun
-- **refactor(sse):** narrow three media-generation result unions ([#8645](https://github.com/diegosouzapw/OmniRoute/pull/8645)) — thanks @backryun
-- **refactor(sse):** declare the semantic-cache read path's parameters ([#8646](https://github.com/diegosouzapw/OmniRoute/pull/8646)) — thanks @backryun
-### 🔀 Other
-
-- [needs-vps] fix(electron): materialize Turbopack hashed-module symlinks during packaging (#6724, #6594) ([#6794](https://github.com/diegosouzapw/OmniRoute/pull/6794)) — thanks @huohua-dev
-- [codex] Keep mode-pack weights consistent in auto fallback ranking ([#7008](https://github.com/diegosouzapw/OmniRoute/pull/7008)) — thanks @KooshaPari
-- Explain effective auto-combo scoring weights ([#7087](https://github.com/diegosouzapw/OmniRoute/pull/7087)) — thanks @KooshaPari
-- [needs-vps] fix(dashboard): add vision-capability toggle for custom OpenAI-compatible models ([#7124](https://github.com/diegosouzapw/OmniRoute/pull/7124))
-- [needs-vps] fix(dashboard): align onboarding tier content ([#7125](https://github.com/diegosouzapw/OmniRoute/pull/7125)) — thanks @Wibias
-- Use OpenAI chunks for early chat keepalives ([#7136](https://github.com/diegosouzapw/OmniRoute/pull/7136)) — thanks @KooshaPari
-- Fix Codex Responses compression analytics ([#7273](https://github.com/diegosouzapw/OmniRoute/pull/7273)) — thanks @JxnLexn
-- Add cache-aligned Live Zone compression ([#7280](https://github.com/diegosouzapw/OmniRoute/pull/7280)) — thanks @JxnLexn
-- Fix routed target request parameters ([#7323](https://github.com/diegosouzapw/OmniRoute/pull/7323)) — thanks @JxnLexn
-- deps: bump electron from 43.1.0 to 43.1.1 in /electron ([#7349](https://github.com/diegosouzapw/OmniRoute/pull/7349))
-- deps: bump the development group with 8 updates ([#7351](https://github.com/diegosouzapw/OmniRoute/pull/7351))
-- deps: bump the production group across 1 directory with 12 updates ([#7352](https://github.com/diegosouzapw/OmniRoute/pull/7352))
-- Add per-connection Provider Quota visibility ([#7360](https://github.com/diegosouzapw/OmniRoute/pull/7360)) — thanks @JxnLexn
-- Stream model health probes for slow providers ([#7377](https://github.com/diegosouzapw/OmniRoute/pull/7377)) — thanks @JxnLexn
-- Refresh NVIDIA free metadata and detect catalog drift ([#7378](https://github.com/diegosouzapw/OmniRoute/pull/7378)) — thanks @JxnLexn
-- Reject invalid output token budgets ([#7379](https://github.com/diegosouzapw/OmniRoute/pull/7379)) — thanks @JxnLexn
-- Honor provider proxies for The Old LLM Vercel blocks ([#7380](https://github.com/diegosouzapw/OmniRoute/pull/7380)) — thanks @JxnLexn
-- Restore proxy navigation and sidebar accordion state ([#7381](https://github.com/diegosouzapw/OmniRoute/pull/7381)) — thanks @JxnLexn
-- Expose proxy controls for no-auth providers ([#7419](https://github.com/diegosouzapw/OmniRoute/pull/7419)) — thanks @JxnLexn
-- Add reasoning-based model and effort routing ([#7607](https://github.com/diegosouzapw/OmniRoute/pull/7607)) — thanks @JxnLexn
-
-- **refactor(sse):** extract per-provider token-refresh functions from tokenRefresh.ts ([#7817](https://github.com/diegosouzapw/OmniRoute/pull/7817))
-- **deps:** bump the production group with 8 updates ([#7897](https://github.com/diegosouzapw/OmniRoute/pull/7897)) — thanks @dependabot[bot]
-- **deps:** bump the development group with 5 updates ([#7898](https://github.com/diegosouzapw/OmniRoute/pull/7898)) — thanks @dependabot[bot]
-- **refactor(antigravity):** align official clients and callable catalog ([#8013](https://github.com/diegosouzapw/OmniRoute/pull/8013)) — thanks @backryun
-- **refactor(compression):** extract resolveHeadroomDetail to keep dispatchCompression under the complexity gate ([#8058](https://github.com/diegosouzapw/OmniRoute/pull/8058))
-- **deps:** bump next from 16.2.10 to 16.2.11 ([#8235](https://github.com/diegosouzapw/OmniRoute/pull/8235)) — thanks @dependabot[bot]
-### 🩹 Direct release-branch fixes (no PR — authorized base-red sweep, 2026-07-18)
-
-- **fix(base-red):** full-suite realignment after the 102-PR merge campaign: two real production fixes (legacy `refresh_token` column healed before its index is created; `shouldSkipCloudSyncInitialization` no longer swaps its `(env, argv)` arguments) plus 13 test files, goldens, provider counts, and env docs realigned to the live-validated behavior of the merged PRs.
-- **chore(release-branch):** cycle maintenance pushed directly to `release/v3.8.49` with no PR of its own — 19 merge-train landings validated on the `.113` box, 14 quality-ratchet re-pins (file-size / complexity / cognitive) absorbing the drift of the merged batches, 8 base-red realignments (build, oauth, embeddings, security, mitm, combo, antigravity, router-eval), the `changelog.d` aggregation passes and the 42 i18n CHANGELOG mirrors.
-- **test(ui):** the `vitest:ui` suite was red across the whole cycle and nobody saw it — the job kept being cancelled by successive pushes, so a blocking gate never ran to completion. Root cause: #7935 instrumented ~180 shared/dashboard components with `next-intl` without updating the tests that mount them. Fixed at the shared setup (`tests/_setup/vitestUiPolyfills.ts`) with a translator backed by the real `en.json`, memoized per namespace so components whose `useCallback`/`useEffect` depend on `t` no longer loop; 15 test files realigned to the real strings. 194→198 files green.
-
-### 📝 Maintenance
-- **Merge-train script** (`scripts/release/merge-train.sh`): batch-validates N queued PRs as ONE merged result on the runner box — merges every queued PR into a throwaway worktree cut from the release tip, runs the fast-gates parity suite once, and prints the `--admin` evidence block per PR (merge-gates §7). Replaces O(N²) per-PR CI re-runs in merge-storms. Regression guard: `tests/unit/merge-train-plan.test.ts`. ([#6784](https://github.com/diegosouzapw/OmniRoute/pull/6784))
-- **release:** `list-uncovered-commits.mjs` now unions the CHANGELOG scan window with `changelog.d/` fragment refs (filename `<PR>-` prefix + every `#N` in the body), so a commit covered only by a fragment is no longer reported as an uncovered reconciliation gap ([#6857](https://github.com/diegosouzapw/OmniRoute/issues/6857) via [#6878](https://github.com/diegosouzapw/OmniRoute/pull/6878))
-- **chore(ci):** stop dependabot from proposing `typescript` majors — `typescript-eslint` pins a hard peer upper bound (`>=4.8.4 <6.1.0`), so a TS 7 bump violates the peer and takes the whole toolchain red at once. #7068 grouped it with 6 harmless dev bumps and blocked all of them. TS majors now migrate intentionally, in their own PR.
-- **maintenance(quality):** re-baseline `file-size` for two legitimately-grown files from the v3.8.49 owner-PR campaign — `src/app/api/usage/analytics/route.ts` 942→948 (180d/365d range cases, #7213) and `tests/unit/audio-transcription-handler.test.ts` added to `testFrozen` at 824 (Gladia STT test cases, #7603). Fast-gates PR→release skip `check:file-size`, so this only surfaced on re-sync; no behavior change.
-- **fix(i18n):** backfill the four `usage.*` quota-visibility keys #7251 added to en.json into vi.json (hideQuotaRow, showQuotaRow, hiddenQuotaRowsLabel, quotaVisibilityUpdateFailed) — their absence left `__MISSING__` markers that failed `i18n-vi-completeness` on the release tip for every fresh PR run.
-- **docs(codex):** document session affinity (`sessionAffinityTtlMs`) and stream idle timeout (`STREAM_IDLE_TIMEOUT_MS`) for multi-hour Codex CLI tasks, with a concrete recommended config, diagnosability string, and an explicit "defaults stay opt-in" decision — mirrored in `skills/config-codex-cli` (#7287)
-- **test(dashboard):** restore dedicated regression coverage for #6815's `QuotaCardGrid` multi-column density guarantee, decoupled from the specific Tailwind token so it survives the #7027 auto-fit migration ([#7291](https://github.com/diegosouzapw/OmniRoute/pull/7291))
-- **Antivirus false-positive note** (`docs/guides/TROUBLESHOOTING.md`): documents why Avast/AVG quarantine the packaged `README.md` with `MD:HttpRequest-inf[Susp]` — a heuristic false positive on the ~15 `http://localhost:20128` examples the file ships with (via `package.json` → `files`). Covers how to stop the notifications, how to report the false positive upstream, and why the localhost examples are deliberately left alone. (#7295 — reported by @DemonNCoding, #5946)
-- **chore(release):** add `scripts/release/rehome-open-prs.mjs` — the Phase 0a.0b PR re-home, scripted with a read-back after every retarget. `gh pr edit --base` exits 0 without applying (v3.8.42), `gh pr list` silently caps at 30, and the v3.8.49 freeze had 148 open PRs to move — none of which a hand-run loop survives reliably. ([#7307](https://github.com/diegosouzapw/OmniRoute/issues/7307))
-- Add an advisory production build to the PR-to-release quality workflow for non-draft code
-  changes and Mergify queue branches, mirroring the Node 24 Turbopack build path from full CI.
-- **docs:** Add `docs/INCIDENT_RESPONSE.md` — a non-security incident-response runbook (severity ladder, first-15-minutes checklist, and per-failure-mode mitigation steps for provider outages, latency regressions, and auth/data-layer incidents) ([#7334](https://github.com/diegosouzapw/OmniRoute/pull/7334)) — thanks @KooshaPari
-- **docs:** Add `docs/PERF_BUDGETS.md` — per-endpoint p50/p95/p99 latency, throughput, resource, and cold-start budget reference targets ([#7336](https://github.com/diegosouzapw/OmniRoute/pull/7336)) — thanks @KooshaPari
-- **README tier-cascade diagram animated** (`docs/diagrams/tier-cascade.svg`): the ASCII 4-tier auto-fallback block in the README is now a self-contained animated SVG (SMIL-only, 16 KB, 16s loop in 4 acts — quota-out/budget-hit hand-offs down to the always-on free tier) that plays inside GitHub's `<img>` sandbox; full flow preserved in the img alt text, hand-authored-diagrams section added to `docs/diagrams/README.md` (#7615).
-- **Docs provider-count sync** (`README.md`, `AGENTS.md`, `CLAUDE.md`): provider-count mentions bumped 253 → 259 to match the auto-generated catalog, un-blocking the strict `check:docs-counts` gate that had started failing on every PR targeting the release branch (#7616).
-- **README animated diagrams** (`docs/diagrams/pool-fair-share.svg`, `docs/diagrams/combo-always-on.svg`): the last two ASCII blocks in the root README — the `"team-codex"` key-pool fair-share example and the `"always-on"` priority combo — are now hand-authored SMIL SVG animations (16s loops, DESIGN_SYSTEM.md palette, GitHub `<img>`-sandbox safe), completing the set started by tier-cascade.svg (#7615). Full block copy preserved verbatim in the `img` alt text; both registered in `docs/diagrams/README.md`.
-- **docs(ops):** publish public branching/release model (`release/*` = active cycle, `main` = published line, tag = ship marker) ([#7627](https://github.com/diegosouzapw/OmniRoute/issues/7627)) — thanks @c4usal
-- **README animated diagrams, round 3** (`docs/diagrams/cli-terminal.svg`, `docs/diagrams/compression-pipeline.svg`): the CLI subcommand list becomes a mini animated terminal (3 real commands typed and answered with formats copied from the actual `bin/cli` printers + a scrolling 30-subcommand ticker), and the compression flow line becomes an animated 10-engine funnel (10,000→~1,080 tok, RTK → Caveman stack highlighted, code token always preserved). SMIL-only, DESIGN_SYSTEM.md palette, GitHub `<img>`-sandbox safe — completing the set from #7615/#7626. Both registered in `docs/diagrams/README.md`.
-- README: replaced the free-tier budget preview mockup with a single detailed animated SMIL card (`docs/diagrams/free-tier-budget.svg`) — ~1.6B/mo hero, honest-math panel (15 providers ToS-flagged), 21-pool budget bar, full per-model grid, ~616M signup-credit chips, un-countable providers + $10 OpenRouter top-up, live footer (#7665)
-- README: standardized all 28 tables to the same full content width — 13 tables received a calibrated invisible header spacer (`docs/screenshots/spacer.svg`), 15 already rendered full-width naturally; zero data cells changed (#7666)
-- Realigned 13 test files that had drifted red on the release tip after the 102-PR merge campaign (full-suite sweep): provider counts/goldens/docs regenerated, 1M-beta assertions caught up with the live-validated behavior, and two real fixes — legacy `refresh_token` column healed before its index is created, and `shouldSkipCloudSyncInitialization` no longer swaps its `(env, argv)` arguments. ([#7690](https://github.com/diegosouzapw/OmniRoute/issues/7690))
-- README: unified animated card system — numbers audited against the v3.8.49 tree (268 providers, 104 MCP tools, 25k+ tests, 26 CLIs, 40+ free-forever, 43 locales, regenerated provider reference); one flat style contract across all cards; 5 new SMIL cards (hero fused with the budget card, "Why" 10-row pain-vs-fix ledger, 18-strategy flow grid, "Private & Local-First" 11-row guarantee ledger, 3-layer resilience card replacing the always-on combo card) plus a rebuilt compact half-height CLI terminal; every animation is pause-at-t0-safe — the first frame is always the finished composition (includes the budget-bar freeze fix on the shipped free-tier card) (#7769)
-- **chore(quality):** fix two release-tip base-reds blocking every fresh PR run: rename `providerTierField.ts` → `providerTierFieldApi.ts` (case-only filename collision with `ProviderTierField.tsx` from #7838 — breaks webpack on case-insensitive filesystems, caught by the #6584 guard) and register `combo-skip-conn-disable-plugin-block-7806.test.ts` (from merged #7806) in stryker `tap.testFiles`.
-- **fix(i18n):** backfill the six `providers.tierOverride*` keys #7838 added to en.json into vi.json (translated with the locale's existing tier vocabulary) — their absence failed `i18n-vi-completeness` (key parity + both ICU checks) on the release tip for every fresh PR run.
-- **chore(quality):** regenerate the provider translate-path golden snapshot for the navy/aihorde entries and the liquid inference URL added by #7840 — the missing regen left the golden gate (Unit shard 4/4) red on the release tip for every fresh PR run.
-- **chore(quality):** prune a stale ESLint suppression for `tests/unit/db-migration-runner-account-identity.test.ts` (2 `no-explicit-any` entries that no longer occur after #7843 reorganized that test) — the leftover suppression failed `lint:json --max-warnings 0` (exit 2, "suppressions left that do not occur anymore") on the release tip for every fresh PR run.
-- Extract `resolveHeadroomDetail()` from the compression-preview `dispatchCompression` dispatcher so it stays under the cognitive-complexity gate after the #8056 headroom-minRows threading (pure refactor, no behavior change).
-- **chore(quality):** rebaseline complexity (2130→2183) and cognitive-complexity (951→968) across the v3.8.49 `/merge-prs` queue-drain. The first step (→2169/→956) cleared inherited base drift measured on the pristine release tip (the PR→release fast-path never ratchets these). The second step (→2183/→968) absorbs the aggregate own-growth of the 41-PR merge-train (each PR under-ceiling individually; the combined batch adds +14/+12). Owner-approved (2026-07-25); structural shrink tracked in [#3501](https://github.com/diegosouzapw/OmniRoute/issues/3501). ([#8566](https://github.com/diegosouzapw/OmniRoute/pull/8566)) — thanks @MisileLab
-- **refactor(sse):** extract combo dispatch prelude (pin/fusion/pipeline/runtime-unit short-circuits) into `combo/dispatchPrelude.ts` — pure move, no behaviour change; #3501 god-file decomposition ([#8582](https://github.com/diegosouzapw/OmniRoute/pull/8582)) — thanks @MumuTW
-- **chore(quality):** bank completed file-size shrinks into `file-size-baseline.json` via shrink-only `--update` on current tip (no raised caps) ([#8585](https://github.com/diegosouzapw/OmniRoute/pull/8585)) — thanks @MumuTW
-- **refactor(sse):** extract combo target resolution into `combo/targetResolution.ts` (`resolveComboTargetPipeline`) — pure move, no behaviour change; #3501 PR 2 of ~7 ([#8592](https://github.com/diegosouzapw/OmniRoute/pull/8592)) — thanks @MumuTW
-- **Source-scanner negative guards** (`tests/unit/source-scanner-guards.test.ts`): hard gate (no baseline, no allowlist) that fails any test variable holding project source read as text whose usages are _all_ negative guards (`assert.doesNotMatch` / `.includes(…) === false`). Those assertions pass against an empty string, so extracting the guarded code into a new file keeps them green while they protect nothing — silently deleting regression coverage during the file-splitting campaign. Classification runs on logical statements with strings, regexes, and comments blanked out, so a guard wrapped across lines cannot slip past. Fixes the 7 existing violations across 6 files with one positive anchor each; two are security scope guards that were held only by multi-line negative assertions — the SSRF guards on `/api/sync/initialize` (`providers-autosync-ssrf-323`) and the proxy-bypass guards on `chatHelpers.ts` / `chatCore.ts` (`proxy-bypass-scope-guard-3226`), the latter pinned to `handleChatCore` precisely because that file is a decomposition target. Adds `tests/_helpers/readSrc.ts`, a repo-root-relative reader that throws on a missing or empty file instead of returning `""`. Regression guards: two synthetic multi-line cases in the gate's own suite. First step of the god-file decomposition campaign tracked in #8617. ([#8619](https://github.com/diegosouzapw/OmniRoute/pull/8619)) — thanks @MumuTW
-- **chore(skills):** regenerate `skills/cli-backup-sync/SKILL.md` so it matches the agent-skills catalog — drops stale `backup status` flags the generator no longer emits; unblocks Merge integrity (`check:agent-skills-sync`) for every PR against `release/v3.8.49` ([#8657](https://github.com/diegosouzapw/OmniRoute/pull/8657)) — thanks @MumuTW
-- chore(quality): extract pure provider input parsers to a leaf module so the agentrouter persist test no longer drags the UI import graph (@lobehub/icons ESM build crashed Node 24's CJS require in the CI unit shard)
-- Realign the Antigravity non-streaming 429-retry test with the executor's actual contract: it returns the already-converted OpenAI `chat.completion` payload, so the test asserts that payload directly instead of re-parsing it as raw SSE (which returned `null` and failed the release-tip unit suite).
-- chore(quality): restore no-explicit-any severity to error (silently downgraded by #6786, broke 439 bulk suppressions), fix 2 unsuppressed anys in repro-6912 test, allowlist migration gap 121, freeze-bump stream.ts/ProxyRegistryManager/tokenHealthCheck (combined-merge drift)
-- chore(base): pt-BR/en i18n keys for #6909 relay-repair/free-pool UI + align Cloud Code Gemini defaults test with the #6943 non-thinking-model contract
-- chore(base): re-export relayProbeStats from localDb (db-rules gate, #6909 follow-up) and document OMNI_MAX_CONCURRENT_CONNECTIONS in .env.example/ENVIRONMENT.md (env-doc gate, #6590 follow-up)
-- fix(tests): realign the disabled-compression combo integration test with the #7379 pre-dispatch context-window boundary (body resized into the 70%-threshold↔window corridor) and add an integration lock (`chatcore-context-window-boundary`) asserting over-window requests are rejected with 400 `context_length_exceeded` before any upstream fetch
-- CI: `pr-test-policy` fetches the base branch with full history instead of `--depth=1` — the shallow graft made `merge-base` resolve wrong for PR branches that recently merged the release, so the three-dot diff blamed the PR for OTHER merged PRs' changes (false "deleted test"/"weakened asserts" reds; observed on #7329 being blamed for #7106's files).
-- **ci:** unit fast-path sharding doubled 2→4 (halves the heaviest job's wall time) (#6781); the 3 heaviest fast-path jobs can route to the self-hosted VPS runner pool behind `USE_VPS_RUNNER` (#6691); `VPS_ALWAYS_ON` keeps the dedicated 24/7 CI host up across releases (teardown becomes a no-op) (#6693).
-- **CI**: Codecov patch-coverage on every PR diff (informational during calibration — `codecov.yml` sets nothing blocking; strict-patch/lenient-project philosophy on top of the existing 60% c8 floor + ratchet); the CI coverage job now actually emits `coverage/lcov.info` (the `lcov` reporter was missing, so the artifact silently skipped it — the same file Sonar consumes)
-- Classify upstream dispatches by host instead of URL path shape in the combo-routing integration harness, and close the `auto` test pool to its seeded connections. The path heuristic mislabelled every OpenAI-compatible upstream as `openai` and stopped recognising OpenAI's own `/v1/responses` calls, which made `combo-matrix/auto.test.ts` fail on a release tip whose routing was in fact correct.
-- **chore(combo):** extract 8 pure error predicates and quota status helpers (`clampPercent`, `quotaRemainingPercentFromQuota`, `normalizeConnectionStatus`, `hasFutureRateLimitUntil`, `getConnectionStatusQuotaCutoffReason`, `isContextOverflow400`, `isParamValidation400`, `isModelScoped400`) from `open-sse/services/combo.ts` into `open-sse/services/combo/comboPredicates.ts` — pure move, zero behavior change; `combo.ts` shrinks from 3,651 to 3,554 lines while maintaining backward-compatible re-exports.
-- **CI**: raise the Coverage job timeout 10→20min — the lcov reporter added for Codecov/Sonar (#7114) pushed the 8-shard report merge past the old cap, and three release-tip runs died at exactly 10min as job-timeout "cancelled"
-- **CI**: raise the dast-smoke job timeout 12→25min — the CLI bundle build alone varies 6-11min on GitHub-hosted runners, so the old cap killed Schemathesis mid-run (3 consecutive false-negative timeouts on 2026-07-14)
-- chore(validation): decompose `src/lib/providers/validation.ts` (→ 442 lines) by extracting the web-cookie, kiro and specialty inline validators into `validation/*` leaves — behavior-preserving move; the specialty validators that captured `isLocal` from the enclosing closure now take it as an explicit parameter, with the host dispatcher passing it at each call site
-- chore(token-refresh): decompose `open-sse/services/tokenRefresh.ts` (999 → 724 lines) by extracting the rotation-map, CAS guard and circuit-breaker refresh logic into `tokenRefresh/*` leaves — behavior-preserving move; `tokenRefresh.ts` still re-exports the moved symbols so the public surface is unchanged
-- chore(usage): decompose `open-sse/services/usage.ts` (999 → 253 lines) by extracting the crof, nanogpt, qoder, opencode, deepseek, bailian, vertex, xiaomi-mimo, xai and github usage fetchers into `usage/*` leaves — behavior-preserving move, the file is now a thin provider→fetcher dispatcher and the public import surface is unchanged
-- **docs:** routing-strategy count reconciled to 18 across AUTO-COMBO.md, README and AGENTS.md, and `p2c` casing fixed to match `ROUTING_STRATEGY_VALUES` (#6643, #6644, #6646 — thanks @chirag127); CLAUDE.md updated with the renamed review/triage/implement skill-family names (#6663).
-- **CI**: E2E matrix shards are now duration-balanced (LPT bin-packing over `config/quality/e2e-timings.json`) instead of Playwright's count-based `--shard` — measured skew was 14× (24m47s vs 1m47s), making E2E the CI critical path; the balancer self-verifies that every spec lands in exactly one shard and falls back to plain `--shard` on any inconsistency
-- **CI**: the new Electron Windows prepare-bundle leg (WS1.5) is advisory while it matures — its first real run failed with the error swallowed by pwsh; the step now runs under bash (stderr captured) with `continue-on-error`, tracked for promotion once green
-- **CI**: the Electron Package Smoke job now runs a Windows leg that executes `prepare:bundle` (the native ABI rebuild + spawn plan) per release PR — the v3.8.48 Windows bug (`npx.cmd` spawned without shell) could previously only surface on the release tag, its first-ever execution
-- **Quality gates hygiene (WS6/D3 + WS1.7)**: gitleaks baseline zeroed — the 3 frozen `generic-api-key` false positives (latency field names + the public Anthropic beta-header value) are allowlisted with justification, so any NEW secret finding now regresses the ratchet from 0; the orphaned `semgrepFindings` baseline metric was dropped (never wired to a gate; CodeQL covers the OWASP families); Dockerfile now has a hadolint gate in the lint job (digest-pinned, error-threshold — the 5 pre-existing warnings stay visible without blocking)
-- fix(oauth): register `ghe-copilot` in the OAuth provider id map and the client-safe MITM host mirror, which #7546 left out of both — the gap turned the whole release branch red on `oauth-providers-config` and `mitm-tool-hosts`
-- fix(dashboard): add the ghe-copilot entry to the traffic-inspector agent map and type `GheConfigStep`'s `error` prop as a renderable string, clearing the two dashboard-typecheck regressions #7546 left behind
-- chore(perf): add `npm run bench:heap-body` — a deterministic benchmark that attributes retained V8 heap to each request-body copy on the chat path (entry log clone, combo per-target clone, token-estimation string), reproducing the #7847 incident shape (3.05 MiB / 729 messages / 86 tools) so the clone-amplification work can be justified and regression-guarded with numbers instead of intuition
-- **CI**: hotfix fast-lane — PRs labeled `hotfix` (owner-applied, production-broken only; entry policy in `docs/ops/RELEASE_CHECKLIST.md`) skip the 9-shard E2E matrix, coverage ratchet and extended gates while keeping build, unit/integration/vitest, lint/typecheck and the tarball boot-smoke (~15min instead of ~33min); tests-only diffs outside `tests/e2e/` skip the E2E matrix automatically via the new `testsOnly` change-classification output
-- chore(ci): resync the stale `no-explicit-any` suppression count for `tests/unit/proxy-registry.test.ts` (frozen at 55, actual 54 since #8447) — ESLint was failing the whole run with "There are suppressions left that do not occur anymore", turning `npm run lint` red on `release/v3.8.49` for every PR branched off it
-- chore(release): merge-train runs the box-tuned `test:unit` (concurrency 20) instead of two sequential 4-core CI shards (~5× faster suite) and gains an owner-approved `--fast` mode (static gates + changed tests + vitest) for intra-day mega-train drains
-- **chore(release):** merge-train `--fast` now classifies changed tests with the same
-  `tests/unit/{…}` subdir allowlist `test:unit` runs — vitest-only subdirs (e.g.
-  `tests/unit/autoCombo/`) are skipped instead of misrun under node:test, and
-  `tests/unit/ui/**/*.test.ts` (node:test) is no longer over-excluded.
-- **CI**: quality.yml draft guards now also match Mergify speculative merge-queue PRs (`mergify/merge-queue/*` heads are drafts by design) — without this every queued batch failed its anchor check in 2s and dequeued
-- **Merge queue (D5)**: reviewed PRs now merge through the Mergify queue (`.mergify.yml`, Open Source plan) — entry is the owner-applied `queue` label AFTER the pre-merge ⭐ gate; batches of up to 10 validate together with automatic bisection of red batches (~log2(N) instead of N revalidations); the manual merge-train is codified as the fallback runbook in `docs/ops/MERGE_TRAIN.md` with the freeze/cross-session guardrails
-- **Release**: npm publishing is now STAGED by default — the workflow boots the packed tarball (`check:pack-boot`) and runs `npm stage publish` (bytes parked on the registry, not installable); the owner verifies the staged bytes and releases them with `npm stage approve` + 2FA, moving the human gate to after the proof (the structural fix for the #7065 broken-tarball class); `publish_mode=direct` remains as a documented emergency fallback
-- chore(release): v3.8.47 pre-flight — relocate #6943 orphan test to a collected path, restore no-explicit-any suppression match, testFrozen bump translator-openai-to-gemini (1541→1553), zizmor rebaseline 159→169
-- **Docs**: `QUALITY_GATES.md` now codifies the per-runner test retry policy (Playwright 1 CI retry with trace; Vitest per-test explicit quarantine only; node:test never) with target flake SLOs, and the release-level ratchet-drift rule (combination drift on the pure tip is the release captain's to fix once on the branch — never pushed onto contributor PRs, never rebaselined per-PR)
-- chore(quality): owner-approved ratchet rebaseline for the v3.8.49 merge campaign — complexity 2072→2130, cognitive-complexity 900→950 (the day's 17 merged PRs consumed the entire slack; wide margin chosen over per-PR extraction for the rest of the cycle)
-- **docs(readme):** fix stale counts — 18 routing strategies (adds the missing `pipeline` row), 94 MCP tools, 12-factor Auto-Combo scoring.
-- Rebaseline the cyclomatic-complexity ceiling (2059 → 2072) and cognitive-complexity ceiling (890 → 900) to absorb a cluster of clean contributor feature PRs whose per-PR +1/+2 own-growth collectively exceeded the tip's 3-unit slack. Owner-approved; structural shrink remains tracked in #3501.
-- **CI**: release-green validation is now continuous — every code push to `release/v*` (including the captain's direct sync-back pushes, the one previously ungated write path) triggers a `--quick` HARD-gate run with per-branch superseded-run cancellation, and the tracking issue names the offending push range; the deep `--with-build --full-ci` sweep now runs 3×/day instead of nightly-only (base-red MTTD: ≤24h → ~15min after the offending push)
-- **chore(ci):** fix two shared base-reds on the release tip that blocked the PR queue — register `cliproxyapi-model-mapping-dispatch.test.ts` in `stryker.conf.json` `tap.testFiles` (mutation-coverage gap left by #6903) and update `provider-models-route-codex.test.ts` to expect Codex client version `0.144.0` (stale assertion left by #6780's production bump).
-- **docs:** refresh `llm.txt` to the current project state (248 providers, 94 MCP tools / 30 scopes, 18 routing strategies, 12-factor Auto-Combo scoring, v3.8.47) and sync its 42 i18n mirrors; move the implemented design-system plan from the repo root to `docs/architecture/DESIGN_SYSTEM.md` rewritten as a reference doc.
-- Strengthen the `compareRouterEvalRuns` regression test to assert the actual AIQ and cost regression reasons instead of counting entries, clearing the weakened-assert (test-masking) gate on the release tip.
-- **Ops**: `scripts/ops/runner-janitor.sh` + `docs/ops/RUNNER_BOX.md` codify the self-hosted runner box hygiene that was manual discipline — 30min cron sweeping stale runner temp dirs, alerting at ≥85% disk, and enforcing the proven 4-runner ceiling on the 16 GB box (8-wide OOM-killed jobs twice on the v3.8.47 release day)
-- **chore(security):** scrub hardcoded live-instance credentials (API key + auth cookie + host URL) from the `tests/boundary/*.live.test.ts` files landed via #6786 — they now read `OMNIROUTE_TEST_BASE` / `OMNIROUTE_TEST_BEARER` / `OMNIROUTE_TEST_COOKIE` from the environment and stay gated behind `RUN_BOUNDARY_LIVE=1`.
-- **Tests**: the #6634 self-reference test now fetches `origin/main` on demand and skips cleanly when the ref is unreachable — it failed as a false positive on shallow/single-ref checkouts (GitHub-hosted runners)
-- Register 5 covering unit tests (account-fallback lockout eviction, cliproxyapi dedicated credential #7645, combo least-used account, combo recovery-hint, route-guard forge/jcode local-only) in `stryker.conf.json` `tap.testFiles` to clear the release base-red.
-- chore(quality): register microsoft-designer-web-6672 test in stryker tap.testFiles (unblocks Fast Quality Gates base-red)
-- **Release tooling**: `sync-next-cycle.mjs` now runs `validate-release-green --quick` on the merged tree BEFORE pushing the parallel-cycle sync-back — the one write path to the release branch that had no CI gate; a red merged tree stays local instead of turning the whole PR queue red (`--skip-green-gate` is the documented emergency hatch)
-- Rebaseline `testFrozen` for `tests/unit/providers-page-utils.test.ts` (1107 → 1294) after #7775 legitimately grew it with the Kimi provider pinning + supporter-card coverage; the merged PR did not update the baseline, leaving the `test-file-size` gate red on the release tip.
-- **chore(quality):** tighten the coverage ratchet to the CI's real numbers (branches 73→78.1, statements/lines 76.5→80.8, functions 82→86.44, plus 7 per-module floors). The gate had been asking for this in plain text; the values come from the merged-coverage run on `main`, not a local run (local measures ~68% vs CI's ~80% — the baseline's own note warns about that gap).
-- **chore(quality):** split `open-sse/services/tokenRefresh.ts` (2249 lines, frozen) into per-provider leaves — `open-sse/services/tokenRefresh/providers/{windsurf,codebuddyCn,cline,kimiCoding,gitlabDuo,claudeOAuth,google,codex,kiro,qoder,github,copilot}.ts` plus a `tokenRefresh/shared.ts` for the cross-provider OAuth-error classifier and form-body helper — pure move, zero behavior change; the file shrinks to ~989 lines and every previously-public export (`refreshCopilotToken`, `getAccessToken`, `extractOAuthErrorCode`, etc.) is re-exported unchanged so no importer needed to change. Idea originally proposed by @KooshaPari in #7338 against a much older base; redone here against the current tip.
-- chore(quality): re-pin the file-size ceilings touched by the v3.8.49 merge-train 1H (31 PRs) and register three covering tests that had drifted out of `stryker.conf.json` — the mutation gate was failing `Fast Quality Gates` on every new PR
-- chore(quality): re-pin the `chatCore.ts` file-size ceiling for the Responses multi-turn image compaction added in #8595
-- chore(quality): align the pack-artifact expected-path fixture with the Android/Termux cache module added in #8593, and re-pin the `chatCore.ts` ceiling grown by the merge-train 2 batch
-- chore(quality): re-pin the `apiKeys.ts` and `chatCore.ts` ceilings grown by the merge-train 3 batch, and register the Cloudflare-1010 regression test in `stryker.conf.json`
-- **CI**: Playwright E2E and both vitest suites now emit JUnit and upload to Trunk Flaky Tests (org `omniroute`) — advisory step, own-origin only, uploader action SHA-pinned (WS5.2/5.3 of the quality plan; node:test stays out of the first wave)
-- **CI**: the fast-path Vitest job (every PR) now also emits JUnit and uploads to Trunk Flaky Tests — the heavy-gate uploads alone (release PR only) would never accumulate flaky-detection volume
-- **CI**: TypeScript 7 (native compiler, GA 2026-07-08) now runs as an advisory SHADOW of the blocking `typecheck:core` gate on the fast path — same tsconfig, isolated `npx` (no dependency change; the Compiler API only lands in TS 7.1, so typescript-eslint/type-coverage/Stryker stay on 6.x). Local parity proven (0 errors on both, exit 0); promotion to the blocking gate after ~1 week of CI parity
-- **maintenance(quality):** clear v3.8.49 owner-PR-campaign base-reds on `release/v3.8.49` (accumulated because fast-gates PR→release skip the complexity/golden/file-size ratchets, surfaced only on re-sync): regenerate the `provider/translate-path` golden snapshot for the new providers; re-point the `#6772` connId-prefix test off the now-reserved `fta` alias (claimed by freetheai #7602 — built-in aliases shadow custom-node prefixes by design); bump the complexity baseline 2056→2058 for the new provider dispatch handlers. No behavior change.
-- **Release tooling**: new `scripts/release/verify-published.mjs <version>` — post-publish net that installs the published version from the public registry inside a clean `node:24-slim` container and boots it until `/api/monitoring/health` reports the expected version (validates the exact bytes users install, on a machine with no repo/devbox state); wired into the release Phase 4 monitoring playbook
-- **CI**: promote `test:vitest:ui` to a blocking gate — the suite is 870/870 green again after the WS6.1 triage (#7127), so `continue-on-error` is removed from the vitest job
-- chore(tests): fix all 70 failing `test:vitest:ui` tests across 30 files (was advisory/parked) — root causes were 15 node:test-authored `.tsx` files never collected by vitest, a missing `window.matchMedia` jsdom polyfill, stale assertions against a redesigned BuildTab wizard / CompressionHub Phase-2 UI, and one obsolete test for a retired Plans screen; suite is now 158/158 files, 870/870 tests green (promotion to blocking is a follow-up)
-
-
-
-
-
-
-### 🙌 Contributors
-
-Thanks to everyone whose work landed in v3.8.49:
-
-| Contributor | PRs / Issues |
-| --- | --- |
-| [@0x2f0](https://github.com/0x2f0) | #8679 |
-| [@0xheycat](https://github.com/0xheycat) | #8751 |
-| [@adevwithpurpose](https://github.com/adevwithpurpose) | #8123 |
-| [@adrianaryaputra](https://github.com/adrianaryaputra) | #7928 |
-| [@advane204f](https://github.com/advane204f) | direct commit / report |
-| [@Ajeesh25353646](https://github.com/Ajeesh25353646) | #7528 |
-| [@allanvb](https://github.com/allanvb) | #8471, #8759, #8814, #8862 |
-| [@alltomatos](https://github.com/alltomatos) | #6703, #6715, #6756, #6757, #6759, #6813, #6819, #6821, #7041, #7042, #7164, #7277, #7490, #7492, #7644 |
-| [@alvaretto](https://github.com/alvaretto) | #8077, #8161, #8170 |
-| [@amitgolan60-coder](https://github.com/amitgolan60-coder) | #8727 |
-| [@andrea-kingautomation](https://github.com/andrea-kingautomation) | #7678 |
-| [@andrewmunsell](https://github.com/andrewmunsell) | #6774, #6779, #6795 |
-| [@AndrianBalanescu](https://github.com/AndrianBalanescu) | #6828, #6829, #7794, #7804, #7810, #7813, #7816, #7891, #8050 |
-| [@anhdiepmmk](https://github.com/anhdiepmmk) | direct commit / report |
-| [@anndev-69](https://github.com/anndev-69) | direct commit / report |
-| [@apoapostolov](https://github.com/apoapostolov) | #8127 |
-| [@arpit-jaiswal-dev](https://github.com/arpit-jaiswal-dev) | #7881 |
-| [@artickc](https://github.com/artickc) | #6763, #6955, #7204, #7696, #7768, #7896, #7900, #7911, #7930, #7994, #8006, #8159, #8470, #8496, #8511, #8863 |
-| [@Arul-](https://github.com/Arul-) | #7878 |
-| [@asynx6](https://github.com/asynx6) | direct commit / report |
-| [@attid](https://github.com/attid) | #6984 |
-| [@backryun](https://github.com/backryun) | #6280, #6675, #6862, #7296, #7314, #7358, #7531, #7687, #7772, #7812, #7866, #7874, #7882, #7914, #8013, #8225, #8226, #8227, #8230, #8266, #8275, #8298, #8464, #8473, #8483, #8485, #8489, #8490, #8498, #8499, #8520, #8525, #8528, #8531, #8533, #8557, #8638, #8639, #8641, #8643, #8644, #8645, #8646, #8647, #8661, #8663, #8665, #8732, #8810, #8811, #8812, #8815, #8816, #8819, #8820, #8824 |
-| [@beingshafin](https://github.com/beingshafin) | direct commit / report |
-| [@brick30llc-ctrl](https://github.com/brick30llc-ctrl) | #6944 |
-| [@brunnolouzada](https://github.com/brunnolouzada) | #8581 |
-| [@c4usal](https://github.com/c4usal) | #7627, #8129 |
-| [@CahyokPutraDev99](https://github.com/CahyokPutraDev99) | direct commit / report |
-| [@Capslockb](https://github.com/Capslockb) | #7892 |
-| [@CarmeloCampos](https://github.com/CarmeloCampos) | direct commit / report |
-| [@Chewji9875](https://github.com/Chewji9875) | #7545 |
-| [@chirag127](https://github.com/chirag127) | #6022, #6593, #6643, #6644, #6646, #6650, #6769, #6771, #6804, #7079, #7520, #8143 |
-| [@chitholian](https://github.com/chitholian) | direct commit / report |
-| [@chy1211](https://github.com/chy1211) | direct commit / report |
-| [@CitrusIce](https://github.com/CitrusIce) | #6937, #6938 |
-| [@costaeder](https://github.com/costaeder) | #8628 |
-| [@Dan-ex-hub](https://github.com/Dan-ex-hub) | #7743 |
-| [@danscMax](https://github.com/danscMax) | #7359, #7511, #7517, #7648, #7656, #7672, #7689 |
-| [@dependabot](https://github.com/dependabot) | #7897, #7898, #8235 |
-| [@Dingding-leo](https://github.com/Dingding-leo) | #7988, #7989, #8162, #8165, #8167, #8283, #8286, #8287, #8633, #8636, #8642, #8651, #8652, #8667, #8691, #8715, #8730, #8731, #8762, #8763, #8764, #8795 |
-| [@DinonowDev](https://github.com/DinonowDev) | #8552, #8559, #8583, #8596, #8615, #8709, #8710, #8716, #8798, #8800, #8802 |
-| [@dionisius95](https://github.com/dionisius95) | direct commit / report |
-| [@DKotsyuba](https://github.com/DKotsyuba) | #7500 |
-| [@dongwook-chan](https://github.com/dongwook-chan) | #7574, #7582, #7704 |
-| [@Dragost](https://github.com/Dragost) | #8289 |
-| [@Duongkhanhtool](https://github.com/Duongkhanhtool) | direct commit / report |
-| [@dvirarad](https://github.com/dvirarad) | #8410 |
-| [@ekinnee](https://github.com/ekinnee) | #7601, #7613, #7614, #7662, #7779, #7927, #7932, #7980, #8735 |
-| [@enjoyer-hub](https://github.com/enjoyer-hub) | #6647, #7863 |
-| [@epsilonode](https://github.com/epsilonode) | #8724 |
-| [@evinjohnn](https://github.com/evinjohnn) | direct commit / report |
-| [@fajarbossit](https://github.com/fajarbossit) | direct commit / report |
-| [@felipeleite](https://github.com/felipeleite) | direct commit / report |
-| [@fenix007](https://github.com/fenix007) | #7171, #7399, #8306, #8561 |
-| [@FenjuFu](https://github.com/FenjuFu) | #7942 |
-| [@floze-the-genius](https://github.com/floze-the-genius) | #7707 |
-| [@fontvu](https://github.com/fontvu) | direct commit / report |
-| [@fuko2935](https://github.com/fuko2935) | #8726 |
-| [@fzrilsh](https://github.com/fzrilsh) | direct commit / report |
-| [@gitcommit90](https://github.com/gitcommit90) | #6986 |
-| [@glazec](https://github.com/glazec) | #8632 |
-| [@growab](https://github.com/growab) | #7062, #7300 |
-| [@guanbear](https://github.com/guanbear) | #7028 |
-| [@guhcostan](https://github.com/guhcostan) | #8433 |
-| [@hartmark](https://github.com/hartmark) | #8208, #8209, #8210, #8211, #8212, #8213, #8337, #8341, #8354, #8462 |
-| [@HassiyYT](https://github.com/HassiyYT) | #7864 |
-| [@heishen6](https://github.com/heishen6) | direct commit / report |
-| [@herjarsa](https://github.com/herjarsa) | #7612, #7625, #7633, #7869, #7871, #8476 |
-| [@HoneyTyagii](https://github.com/HoneyTyagii) | #8444 |
-| [@HouMinXi](https://github.com/HouMinXi) | #7035, #7129, #7290, #7398, #7408, #7973, #8290, #8312, #8842, #8845, #8860, #8865 |
-| [@hppsc1215](https://github.com/hppsc1215) | #7546, #8835 |
-| [@huohua-dev](https://github.com/huohua-dev) | #6794 |
-| [@hydraxman](https://github.com/hydraxman) | #7909 |
-| [@iamraydoan](https://github.com/iamraydoan) | #6798 |
-| [@ianriizky](https://github.com/ianriizky) | #6072, #6538 |
-| [@ikelvingo](https://github.com/ikelvingo) | #8355 |
-| [@insoln](https://github.com/insoln) | #7906, #7908, #8041, #8054, #8062 |
-| [@irvandikky](https://github.com/irvandikky) | #7695 |
-| [@isiahw1](https://github.com/isiahw1) | #7555 |
-| [@itiwant](https://github.com/itiwant) | direct commit / report |
-| [@janeza2](https://github.com/janeza2) | #6308 |
-| [@Jordannst](https://github.com/Jordannst) | direct commit / report |
-| [@JoshimOfficial](https://github.com/JoshimOfficial) | #8526 |
-| [@justdoGIT](https://github.com/justdoGIT) | #8695 |
-| [@JxnLexn](https://github.com/JxnLexn) | #6776, #6993, #7154, #7177, #7269, #7273, #7280, #7281, #7282, #7323, #7360, #7377, #7378, #7379, #7380, #7381, #7419, #7607, #7894, #7905, #7912, #8008, #8009, #8010 |
-| [@kamenkadmitry](https://github.com/kamenkadmitry) | #7350, #7425 |
-| [@kaon0388v1](https://github.com/kaon0388v1) | #7049 |
-| [@KaynXu](https://github.com/KaynXu) | #8284 |
-| [@KooshaPari](https://github.com/KooshaPari) | #6611, #6632, #6856, #7008, #7087, #7093, #7128, #7130, #7136, #7315, #7318, #7334, #7336 |
-| [@KunN-21](https://github.com/KunN-21) | direct commit / report |
-| [@leninejunior](https://github.com/leninejunior) | #8049 |
-| [@leszek3737](https://github.com/leszek3737) | #7782, #7807, #8343, #8543, #8823 |
-| [@like3213934360-lab](https://github.com/like3213934360-lab) | direct commit / report |
-| [@linhdmn](https://github.com/linhdmn) | #8439 |
-| [@Long-Feeds](https://github.com/Long-Feeds) | #8011 |
-| [@loulanyue](https://github.com/loulanyue) | #7540 |
-| [@lucasjustinudin](https://github.com/lucasjustinudin) | direct commit / report |
-| [@lunkerchen](https://github.com/lunkerchen) | #8024 |
-| [@makcimbx](https://github.com/makcimbx) | #7692, #8171, #8432 |
-| [@Mananz90](https://github.com/Mananz90) | #8723 |
-| [@marceli1404](https://github.com/marceli1404) | #8570 |
-| [@maxmad64bis](https://github.com/maxmad64bis) | #8660 |
-| [@megamen32](https://github.com/megamen32) | #7313 |
-| [@MichaelYcJo](https://github.com/MichaelYcJo) | #8224 |
-| [@mikeiagents](https://github.com/mikeiagents) | #8598 |
-| [@MikeTuev](https://github.com/MikeTuev) | #6586 |
-| [@mikolaj92](https://github.com/mikolaj92) | #6973 |
-| [@MisileLab](https://github.com/MisileLab) | #8566 |
-| [@MonteNegroX](https://github.com/MonteNegroX) | #8217 |
-| [@Moseyuh333](https://github.com/Moseyuh333) | #7781, #8264 |
-| [@MrFadiAi](https://github.com/MrFadiAi) | #7073 |
-| [@mrprohack](https://github.com/mrprohack) | direct commit / report |
-| [@MumuTW](https://github.com/MumuTW) | #8423, #8425, #8426, #8427, #8428, #8524, #8534, #8544, #8545, #8546, #8547, #8548, #8554, #8582, #8585, #8589, #8592, #8604, #8605, #8612, #8619, #8657, #8690, #8741, #8749 |
-| [@mustafa-phd](https://github.com/mustafa-phd) | #7686 |
-| [@NBN-N3](https://github.com/NBN-N3) | #8794 |
-| [@nguyenha935](https://github.com/nguyenha935) | #7493, #7547, #7552, #7553, #7629, #7935, #8031, #8098, #8233, #8565 |
-| [@nguyenphi37](https://github.com/nguyenphi37) | direct commit / report |
-| [@not-knope](https://github.com/not-knope) | #8206 |
-| [@nramabad](https://github.com/nramabad) | #7926 |
-| [@oyi77](https://github.com/oyi77) | #6917, #6918, #6919, #6920, #6921, #6923, #7032, #7045, #7046, #7066, #7070, #7178, #7719, #7744, #7787, #7893, #8219 |
-| [@Pitchfork-and-Torch](https://github.com/Pitchfork-and-Torch) | #6747, #6791 |
-| [@professional-ALFIE](https://github.com/professional-ALFIE) | #6877 |
-| [@Prudhvivuda](https://github.com/Prudhvivuda) | #8032, #8220, #8250, #8309, #8441, #8467, #8488, #8493, #8494, #8495, #8586, #8587, #8606, #8607, #8608, #8611, #8805, #8806 |
-| [@QRcode1337](https://github.com/QRcode1337) | #7034 |
-| [@quanturbo](https://github.com/quanturbo) | #6780 |
-| [@rafaeldrincon](https://github.com/rafaeldrincon) | #8866, #8867 |
-| [@rafaumeu](https://github.com/rafaumeu) | #6813, #6979, #6982, #6983, #6987, #6988, #7001, #7808, #7815, #8071, #8113, #8179, #8184, #8185, #8190, #8195, #8196, #8203 |
-| [@RaviTharuma](https://github.com/RaviTharuma) | #7852, #7853, #7855, #7862, #7885, #7972, #7978, #8021, #8022, #8023, #8025, #8027, #8030, #8101, #8102, #8124, #8252, #8292, #8296, #8301, #8302, #8303, #8304, #8308 |
-| [@RCrushMe](https://github.com/RCrushMe) | #8151, #8378 |
-| [@ricatix](https://github.com/ricatix) | direct commit / report |
-| [@ridho9](https://github.com/ridho9) | #8310 |
-| [@rinseaid](https://github.com/rinseaid) | #8721, #8729, #8821 |
-| [@rixzkiye](https://github.com/rixzkiye) | direct commit / report |
-| [@rqzbeh](https://github.com/rqzbeh) | #8514, #8515 |
-| [@rushsinging](https://github.com/rushsinging) | #7256 |
-| [@ryanngit](https://github.com/ryanngit) | direct commit / report |
-| [@samir-abis](https://github.com/samir-abis) | direct commit / report |
-| [@seanford](https://github.com/seanford) | #8194, #8218, #8232 |
-| [@SeaXen](https://github.com/SeaXen) | #7063, #7264, #7294 |
-| [@Securiteru](https://github.com/Securiteru) | #7683 |
-| [@SemonCat](https://github.com/SemonCat) | direct commit / report |
-| [@shixi-li](https://github.com/shixi-li) | #8569 |
-| [@SingCJ](https://github.com/SingCJ) | direct commit / report |
-| [@skutanjir](https://github.com/skutanjir) | #7865, #7939 |
-| [@spacesky-cell](https://github.com/spacesky-cell) | direct commit / report |
-| [@SteeleHu](https://github.com/SteeleHu) | #8747 |
-| [@sumanxg](https://github.com/sumanxg) | #8837, #8856 |
-| [@swingtempo](https://github.com/swingtempo) | #7790, #8349, #8766 |
-| [@Tasogarre](https://github.com/Tasogarre) | #7861, #8207 |
-| [@techsolutionmta](https://github.com/techsolutionmta) | direct commit / report |
-| [@tenshiak](https://github.com/tenshiak) | #7274, #7643 |
-| [@terrafirmbot-source](https://github.com/terrafirmbot-source) | #8685 |
-| [@thepigdestroyer](https://github.com/thepigdestroyer) | #7497 |
-| [@tianrking](https://github.com/tianrking) | #7353 |
-| [@tientien17](https://github.com/tientien17) | #7841, #7844, #7925 |
-| [@TitoTFP](https://github.com/TitoTFP) | #8838 |
-| [@tjengbudi](https://github.com/tjengbudi) | #4009 |
-| [@tmone](https://github.com/tmone) | #7806, #7933 |
-| [@TrackCrewGalore](https://github.com/TrackCrewGalore) | #6271, #8128 |
-| [@trfi](https://github.com/trfi) | direct commit / report |
-| [@TuyulSpam](https://github.com/TuyulSpam) | direct commit / report |
-| [@ViFigueiredo](https://github.com/ViFigueiredo) | #7301 |
-| [@vzts](https://github.com/vzts) | #7390 |
-| [@warelik](https://github.com/warelik) | direct commit / report |
-| [@way-art](https://github.com/way-art) | direct commit / report |
-| [@webmasterarbez](https://github.com/webmasterarbez) | #7504 |
-| [@wgordon17](https://github.com/wgordon17) | #8852 |
-| [@whale9820](https://github.com/whale9820) | direct commit / report |
-| [@Wibias](https://github.com/Wibias) | #7125 |
-| [@wilsonicdev](https://github.com/wilsonicdev) | direct commit / report |
-| [@Witroch4](https://github.com/Witroch4) | #6753, #6762, #6790, #7901, #7902 |
-| [@XCrag](https://github.com/XCrag) | direct commit / report |
-| [@xiaoyaner0201](https://github.com/xiaoyaner0201) | #8122, #8261, #8262 |
-| [@xier2012](https://github.com/xier2012) | #7036, #7050, #7052, #7053, #7056, #7059, #7060, #7061, #7166, #7299 |
-| [@xxue-z](https://github.com/xxue-z) | #7098 |
-| [@xz-dev](https://github.com/xz-dev) | #6323, #6330, #6714, #6727, #7004, #7012, #7027, #7673, #7700, #7747, #7776, #7843 |
-| [@yidecode](https://github.com/yidecode) | direct commit / report |
-| [@yinaoxiong](https://github.com/yinaoxiong) | #6805 |
-| [@diegosouzapw](https://github.com/diegosouzapw) | maintainer |
-
----
-
-## [3.8.48] — 2026-07-13
-
-> ⚠️ **Hotfix release.** The published npm package for 3.8.47 crashed on every boot ([#7065](https://github.com/diegosouzapw/OmniRoute/issues/7065)) and was deprecated — **3.8.48 is the first installable release of the v3.8.47 cycle**, so everything listed under [3.8.47] below ships here.
-
-### 🐛 Bug Fixes
-
-- **fix(build):** ship `dist/head-response-guard.cjs` in the npm tarball — the prepublish prune allowlist lacked it, so every `omniroute` boot of the published 3.8.47 crashed with `ERR_MODULE_NOT_FOUND` (3rd occurrence of this class after tls-options/3.8.41); now allowlisted, enforced by `check:pack-artifact`, and guarded by a closure test that derives every `server-ws.mjs` sibling import ([#7065](https://github.com/diegosouzapw/OmniRoute/issues/7065), [#7040](https://github.com/diegosouzapw/OmniRoute/issues/7040))
-- **fix(build):** Electron Windows packaging — the better-sqlite3 Electron-ABI rebuild now spawns `npx.cmd` through a shell (Node's CVE-2024-27980 hardening made the shell-less spawn fail with `status null` on Windows runners, breaking the v3.8.47 desktop build)
-- **fix(ci):** Sonar quality gate zeroed on new code — the coverage lcov now reaches the scanner at `coverage/lcov.info` (it read 0% on every scan), the async `isCloudEnabled()` gate in the Kiro auto-import route is awaited (cloud sync ran even when disabled), the dead `structuredClone` fallback in the reasoning-split clone is a real JSON fallback, the codex executor handles the async `reader.cancel()` rejection, deterministic `localeCompare` sorts, a path-traversal guard in `classify-pr-changes.mjs`, and the Docker better-sqlite3 rebuild uses npm's bundled node-gyp instead of `npx --yes`
-- **chore(ci):** the Sonar quality gate is informational (`sonar.qualitygate.wait=false`) while the org's SonarCloud plan cannot associate the tuned "OmniRoute way" gate (coverage ≥60 aligned with the repo floor)
-
----
-
-## [3.8.47] — TBD
-
-_Living section — bullets land here as PRs merge into `release/v3.8.47` (parallel-cycle model; cycle opened at the v3.8.46 release freeze). Finalized at the v3.8.47 release._
-
-### 📝 Maintenance
-
-- **chore(quality):** `validate-release-green --full-ci` reproduces the full `ci.yml` static gate set locally — the pre-flight now reads `ci.yml` itself and runs every `npm run check:*` from the `lint` / `quality-gate` / `quality-extended` / `docs-sync-strict` / `pr-test-policy` jobs (`--` ratchet flags preserved, `test-masking` against `GITHUB_BASE_REF=main`), skipping only the non-local `pr-evidence`/`codeql-ratchet`. Closes the gap where 11 static base-reds leaked to the v3.8.46 release PR in ~2h of layered CI. Also wired into `nightly-release-green` so a static base-red opens a tracking issue the night it lands. Regression guard: `tests/unit/validate-release-green.test.ts` (+5 `extractCiGates` cases).
-
----
-
-## [3.8.46] — 2026-07-07
-
-### ✨ New Features
-
-- **feat(sse):** **hide paid-only models from `auto/*` routing** when `hidePaidModels` is on ([#6512](https://github.com/diegosouzapw/OmniRoute/issues/6512)) — follow-up to #6328/#6495. PR #6495 hid paid-only models from the `GET /v1/models` listing, but `auto/*` combos (`auto/best-coding`, `auto/glm`, …) could still pick a paid-only backend into their candidate pool → a 402/403 at request time. `createVirtualAutoCombo` now filters the candidate pool through the new pure `open-sse/services/autoCombo/paidModelFilter.ts` (`filterPaidOnlyCandidates`), applying the same free-model predicate #6495 uses in `catalog.ts` (`providerHasFreeModels(provider) && isFreeModel(provider, {id})`) whenever `settings.hidePaidModels === true`. Applied before the category/tier/family narrowing, so it covers every `auto/*` combo; an all-paid pool degrades to the existing graceful empty-pool path. **Opt-in — default OFF leaves the pool unchanged** (identity). Regression guard: `tests/unit/autoCombo/paid-model-filter-6512.test.ts` (4, incl. the default-off identity guard).
-- **feat(sse):** **provider-family auto combos** — `auto/glm`, `auto/minimax`, `auto/mimo`, `auto/zai`, `auto/gemma`, `auto/llama`, `auto/gemini` ([#6453](https://github.com/diegosouzapw/OmniRoute/issues/6453)) — new routable ids that materialize an on-demand virtual combo spanning whatever installed backends currently expose that model family, degrading gracefully as backends rotate. A new pure `open-sse/services/autoCombo/modelFamily.ts` (`detectModelFamily`) classifies by model-id prefix for six families; `zai` is instead resolved by provider id (z.ai's hosted API serves the same `glm-*` model ids as every other GLM backend, so `auto/zai` means "route to my z.ai backend specifically" vs `auto/glm`'s "any connected GLM backend"). Reuses the existing `createVirtualAutoCombo` on-demand materialization path (no DB writes) and the `/v1/models` catalog advertising loop. Regression guard: `tests/unit/autoCombo/provider-family-combos.test.ts` (11).
-- **feat(proxy):** native **proxy-pool round-robin / egress IP rotation** ([#6365](https://github.com/diegosouzapw/OmniRoute/issues/6365)) — a scope (global / provider / account) can now hold **multiple** proxies as a pool with a rotation strategy, so outbound requests cycle their egress IP instead of pinning one proxy per scope. Migration `117_proxy_pool_rotation.sql` lifts the `UNIQUE(scope, scope_id)` constraint (rebuild via the canonical rename/copy/drop; existing single assignments become 1-element pools) and adds a `proxy_scope_rotation` companion table holding the per-scope strategy + a persisted monotonic round-robin cursor. Strategies: `round-robin` (default, monotonic cursor — never `Math.random`), `random`, and `sticky-per-N-min`. Resolution (`resolveProxyForScopeFromRegistry` / `resolveProxyForConnectionFromRegistry`) now fetches the alive, position-ordered candidate set (unchanged `PROXY_ALIVE_PREDICATE`) and applies the strategy; an empty / all-dead pool still returns `null` — the #6246 fail-closed guard is **untouched** (never falls through to direct egress). Backend + DB only; dashboard pool-builder UI is a follow-up. Regression guard: `tests/unit/proxy-pool-rotation-6365.test.ts` (8, incl. fail-closed + backward-compat).
-- **feat(providers):** end-to-end **tool/function calling on the native Gemini `/v1beta` endpoint** ([#6222](https://github.com/diegosouzapw/OmniRoute/issues/6222)) — both directions of the Gemini↔OpenAI conversion now preserve tool data (previously silently dropped). Request side: `convertGeminiToInternal` (extracted to its own testable module) maps `tools[].functionDeclarations` → OpenAI `tools`, prior `functionCall` parts → assistant `tool_calls`, and `functionResponse` parts → `tool`-role messages. Response side: `convertOpenAIResponseToGemini` emits `parts[].functionCall {name,args}` from `message.tool_calls`, and the streaming `openAIChunkToGeminiChunk` accumulates fragmented `tool_calls` deltas by index into complete `functionCall` parts. The non-Gemini client paths (Claude, OpenAI-Responses) already preserved tool calls — this closes the gap specific to the native Gemini surface. Regression guard: `tests/unit/v1beta-gemini-tool-calling-6222.test.ts` (6, incl. a streaming SSE round-trip).
-- **feat(providers):** copilot-m365-web **enterprise / work tier** support ([#6334](https://github.com/diegosouzapw/OmniRoute/issues/6334)) — mirrors the EDU-tier pattern (#6210): `M365ConnectionParams` gains an `agent` field, a new opt-in `M365_ENTERPRISE_OVERRIDES` preset (`agent=work`, `scenario=officeweb`, `licenseType=Premium`) applies via `providerSpecificData.tier="enterprise"` (alias `"work"`), and `agent` is also overridable directly via `providerSpecificData.agent`. `buildWsUrl` was hardcoding `agent="web"` (the one enterprise-distinguishing param with no override path), so a Premium work account handshook then returned an empty stream. The individual and EDU paths are untouched. Kilo's dup flag vs #6210 (EDU tier) was a false positive — different tier. Regression guard: `tests/unit/copilot-m365-enterprise-6334.test.ts` (7). End-to-end confirmation on a real Premium work account is a live-VPS validation follow-up (Hard Rule #18). (thanks @Forcerecon)
-- **feat(api):** standardized, provider-agnostic **`effort` + `thinking` request params** ([#6241](https://github.com/diegosouzapw/OmniRoute/issues/6241)) — a thin standardization layer over the existing mature per-provider reasoning plumbing (no provider mapper touched). `providerChatCompletionSchema` gains a canonical `effort` (reusing the shared `none/low/medium/high/xhigh` vocabulary — the UI tiers `extra`/`max` collapse onto `xhigh`) and a boolean `thinking`. A pure `normalizeReasoningRequest` (wired once in `src/sse/handlers/chat.ts`, before any reasoning field is read) folds them onto the fields the translators already consume (`reasoning_effort` / `reasoning.effort` / `thinking`), so they fan out to Anthropic / Gemini / xAI / Responses — an explicit client `reasoning_effort` / object-shaped `thinking` always wins (backward-compatible). `/models` additively exposes `supportsThinking` + `effort_tiers` so the frontend can render the toggles (UI component is a follow-up). Regression guard: `tests/unit/effort-thinking-standardization-6241.test.ts` (12). (thanks @Iammilansoni, @shabeer)
-- **feat(combo):** new **`pipeline` (sequential) combo strategy** ([#6297](https://github.com/diegosouzapw/OmniRoute/issues/6297)) — the 18th routing strategy runs targets **in order**, threading each step's output into the next step's input, with an optional per-step `prompt` (system instruction); only the final step's response is returned. Distinct from `fusion` (parallel fan-out + judge). Implemented as a self-contained `open-sse/services/pipeline.ts` (sibling to `fusion.ts`), dispatched from `combo.ts`; the step list reuses `combo.models` order and reads an optional `prompt` off each target (backward-compatible — ignored by every other strategy). Intermediate steps run non-streaming with tools stripped (complete prose to thread forward); the final step keeps the client's `stream` flag + tools. A failing/empty/unparseable intermediate step fails the whole pipeline explicitly via a sanitized error (never silently swallowed). Kilo's dup flag vs #563 was a false positive (that's model→chain selection; this is a sequential chain). Regression guard: `tests/unit/combo-pipeline-strategy.test.ts` (5). (thanks @ofekbetzalel)
-- **feat(ci):** `check:test-masking` now flags **inline-reimplemented prod conditions** ([#6348](https://github.com/diegosouzapw/OmniRoute/issues/6348)) — a new **report-only** subcheck (v2, 6A.10 family) catches the wrong-shape contract test: a test that recomputes the condition under test inline instead of importing/exercising the real function (the #6216 class, where `=== 500` → `>= 500` stayed green because the test re-implemented the branch). For each added/modified test file it warns when the file textually duplicates a ≥3-token conditional from a production file touched in the same PR **and** does not import the symbol/module owning it, via a pure, fixture-tested `findReimplementedConditions()` with an allowlist mirroring `assertReductionAllowlist`. Report-only for now (does not fail the gate) — to be promoted to blocking after a triage cycle. Regression guard: `tests/unit/check-test-masking.test.ts` (45).
-- **feat(sse):** per-connection routing override (native vs CLIProxyAPI) ([#6339](https://github.com/diegosouzapw/OmniRoute/issues/6339)) — the previously-dead `isCliproxyapiDeepModeEnabled` helper is now wired into `resolveExecutorWithProxy`: a single connection can opt itself into the CLIProxyAPI passthrough executor via `providerSpecificData.cliproxyapiMode="claude-native"`, with precedence **connection override > provider `upstream_proxy_config` mode > default**. `resolveExecutorWithProxy` now receives the resolved connection's `providerSpecificData` (threaded from `chatCore.ts`), so one connection can deep-route while the provider's other connections stay native — no DB schema change (the toggle rides in `providerSpecificData`). Also resolves the same-provider mixing ask in #6340. Regression guard: `tests/unit/chatcore-executor-proxy.test.ts` (9). (thanks @RaviTharuma)
-- **feat(dashboard):** "Add session cookie" modal now shows a prominent **"Open ‹host› →"** link to the provider's own site ([#6268](https://github.com/diegosouzapw/OmniRoute/issues/6268)) — every `-web` cookie-session provider (chatgpt-web, claude-web, gemini-web, kimi-web, lmarena, qwen-web, m365-copilot-web, …) renders a one-click external link (opening the provider's login/home page in a new tab) so operators no longer tab away to retype the URL mid-setup. The host resolves from a pure, unit-tested `resolveWebProviderHost()` (prefers `WEB_COOKIE_PROVIDERS[id].website`, falls back to the registry `baseUrl` origin); non-web providers render exactly as before. Kilo's dup flag vs #6265 (modal-too-small-on-1080p) was a false positive — distinct concern. Regression guard: `tests/unit/resolve-web-provider-host.test.ts` (5). (thanks @chirag127)
-- **feat(providers):** add **DigitalOcean** AI (serverless inference) as an OpenAI-compatible API-key provider ([#6373](https://github.com/diegosouzapw/OmniRoute/pull/6373)) — base `https://inference.do-ai.run/v1`, wired through the shared OpenAI-compatible registry with full model passthrough (`open-sse/config/providers/registry/digitalocean/`, `src/shared/constants/providers/apikey/inference-hosts.ts`). Regression guard: `tests/unit/digitalocean-provider.test.ts`. (thanks @newnol)
-- **feat(providers):** add **Huancheng Public API** (`hcnsec`) as an OpenAI-compatible regional provider ([#6410](https://github.com/diegosouzapw/OmniRoute/pull/6410)) — Xinjiang Huancheng Cybersecurity's public LLM platform (base `https://api.hcnsec.cn/v1`, free credits via daily check-ins), wired through the shared OpenAI-compatible registry with full model passthrough (`open-sse/config/providers/registry/hcnsec/`, `src/shared/constants/providers/apikey/regional.ts`). Regression guard: `tests/unit/hcnsec-provider.test.ts`. (thanks @UnrealAryan)
-- **feat(dashboard):** the web-session credential guide now shows an **"Open {host}" link** ([#6316](https://github.com/diegosouzapw/OmniRoute/pull/6316)) to the provider's sign-in site (derived from the provider `website` via `getProviderWebsiteHost`), so you can jump straight to the page where the cookie/session must be captured. Regression guard: `tests/unit/web-session-provider-link-6316.test.ts`. (thanks @jordansilly77-stack)
-- **feat(cerebras):** add the **Gemma 4 31B** model (`gemma-4-31b`) to the Cerebras registry + pricing table ([#6331](https://github.com/diegosouzapw/OmniRoute/pull/6331)). Regression guard extends `tests/unit/t28-model-catalog-updates.test.ts`. (thanks @backryun)
-- **feat(providers):** add **Yuanbao (web)** as a cookie-session provider ([#6196](https://github.com/diegosouzapw/OmniRoute/issues/6196)) — `yuanbao-web` (Tencent Yuanbao, `yuanbao.tencent.com`) with cookie-only auth (`hy_user`/`hy_token` + public agent id), SSE→OpenAI translation incl. `reasoning_content`, exposing DeepSeek V3/R1 + Hunyuan / Hunyuan-T1. Regression guard: `tests/unit/providers-yuanbao-web.test.ts`. `together-web` was **deferred** (no verifiable web-session endpoint — needs a captured request) and `huggingchat-web` **dropped** (the existing `huggingchat` already is a web-cookie provider). (thanks @chirag127)
-- **feat(providers):** route the built-in **agentrouter** through the dynamic Claude-Code wire image ([#6056](https://github.com/diegosouzapw/OmniRoute/issues/6056)) — a small static allow-set (`CC_WIRE_IMAGE_BUILTINS` in `open-sse/services/ccWireImageBuiltins.ts`), consulted by `isClaudeCodeCompatible` / `isClaudeCodeCompatibleProvider` / `applyFingerprint`, makes agentrouter adopt the CC wire-image headers + fingerprint **while guarding the CC baseUrl/auth branches** so it keeps its own registry `baseUrl` and `x-api-key` auth. Regression guard: `tests/unit/agentrouter-cc-wire-image.test.ts` (asserts the wire image is applied AND agentrouter's baseUrl/auth are preserved). Live WAF-acceptance against agentrouter.org is a VPS validation follow-up (Hard Rule #18).
-- **feat(providers):** **bulk-add API keys for Cloudflare Workers AI** ([#6174](https://github.com/diegosouzapw/OmniRoute/issues/6174)) — `cloudflare-ai` is removed from the bulk-add exclusion list and the bulk parser gains a 3-field `name|accountId|apiKey` mode; the bulk route now builds a **per-entry** `providerSpecificData` so each key carries its own `accountId` (fixing the previous shared-object reuse), and both the create + key-validation paths receive it. Regression guard: `tests/unit/bulk-api-key-parser-cloudflare.test.ts`. (thanks @muflifadla38)
-- **feat(dashboard):** routing/settings UX clarity ([#6147](https://github.com/diegosouzapw/OmniRoute/issues/6147)) — (1) weighted combos show the **effective routing share %** next to each weight when weights don't sum to 100 (`WeightTotalBar.tsx`); (2) the status widget's user-facing **"Cloud Sync" label is renamed** to "Remote Settings Sync" (`CloudSyncStatus.tsx`; internal ids/state untouched); (3) built-in providers gain an **opt-in advanced base-URL override** (`isBaseUrlOverrideEligibleProvider`, hidden behind an "Advanced" toggle, reusing the existing `providerSpecificData.baseUrl` persistence — not globally widened). Regression guard: `tests/unit/routing-settings-ux-6147.test.ts`.
-- **feat(combo):** add an option to **disable session stickiness**, per-combo or globally — round-robin / random combos can rotate to a different connection on every request instead of pinning a whole conversation to one connection by its first-message hash. Resolution precedence per-combo `config.disableSessionStickiness` → global `settings.disableSessionStickiness` → default `false` (preserves the #3825 prompt-cache/504 fix); gates **both** stickiness call sites in `open-sse/services/combo.ts`. Exposed as a global toggle (Combo Defaults) and a per-combo Inherit/on/off control. ([#6168](https://github.com/diegosouzapw/OmniRoute/issues/6168)) Regression guard: `tests/unit/combo-disable-session-stickiness.test.ts`. (thanks @RCrushMe)
-- **feat(docker):** add the `OMNIROUTE_NO_SUDO` env flag for root-less / user-namespaced deployments — the MITM cert-trust command path (`resolveSudoSpawn` in `src/mitm/systemCommands.ts`) now strips the leading `sudo` when the flag is truthy, in addition to the existing root / sudo-missing cases, so the Proxy Agent runs without `sudo` (the operator trusts the CA manually, e.g. via `NODE_EXTRA_CA_CERTS`). Argv-array `spawn` preserved — no shell interpolation (Hard Rule #13). ([#6122](https://github.com/diegosouzapw/OmniRoute/issues/6122)) Regression guard: `tests/unit/mitm-systemCommands-no-sudo.test.ts`. (thanks @powellnorma)
-- **feat(providers):** add **Requesty** as an OpenAI-compatible gateway provider (BYOK, base `https://router.requesty.ai/v1`, ~200 free requests/day) — wired through the shared OpenAI-compatible registry with full model passthrough (`open-sse/config/providers/registry/requesty/`, `src/shared/constants/providers/apikey/gateways.ts`). ([#6120](https://github.com/diegosouzapw/OmniRoute/issues/6120)) Regression guard: `tests/unit/requesty-provider.test.ts`. (thanks @chirag127)
-- **feat(dashboard):** add **configured-only / available-only filters** to the Free Provider Rankings page ([#6150](https://github.com/diegosouzapw/OmniRoute/issues/6150)) — hide providers you haven't configured, or whose connections are all rate-limited / out of quota, via server-side query params (`?configuredOnly` / `?availableOnly` on `GET /api/free-provider-rankings`) backed by a testable lib helper reusing the in-process connection state (no Redis). Both filters default off, so the default view is unchanged; this supersedes the earlier client-side "Configured Only" toggle (#6245) with an available-only dimension and unit-tested logic. Regression guard: `tests/unit/freeProviderRankings-filters.test.ts`.
-
-### 🔧 Bug Fixes
-
-- **fix(dashboard):** adding a second API key connection for the same provider no longer silently overwrites the first — the Add-API-key modal now derives a unique default connection name (`main`, then `main-2`, `main-3`, …) so the backend name-based upsert can't collide (#6499 — thanks @dilneiss).
-- **fix(compression):** the session-dedup engine now also deduplicates a large multi-line block repeated **within a single message** (intra-message dedup), not just across turns; the compression-preview API surfaces a `fallbackReason`, and the fusion panel reports how many models were rate-limited vs failed on total-panel failure (#6501 — thanks @chirag127).
-- **fix(compression):** a stacked-pipeline step naming an unregistered engine now surfaces a `validationErrors` entry instead of silently no-op'ing, so misconfigured pipelines are visible in the preview API (#6506 — thanks @chirag127).
-- **feat(usage):** add a **Codex reset-credit redemption** flow to the Provider Limits UI ([#6361](https://github.com/diegosouzapw/OmniRoute/pull/6361)) — a `useCodexResetCreditRedemption` hook + `/api/usage/codex-reset-credit` route + `codexResetCredits` lib let you redeem banked Codex reset credits from the quota card. Regression guard: `tests/unit/codex-reset-credits.test.ts`. (thanks @JxnLexn)
-- **feat(glm):** add **team-plan quota settings** for `glm-cn` connections ([#6351](https://github.com/diegosouzapw/OmniRoute/pull/6351)) — a dedicated `GlmTeamQuotaFields` form section (team quota id / limits) threaded through the Add/Edit connection modals, persisted via `providerSpecificData`, with the GLM usage service reading the team quota. Regression guards: `tests/unit/glm-team-quota.test.ts`, `provider-specific-data-schema.test.ts`. (thanks @hao3039032)
-- **feat(providers):** add **TinyFish** web-fetch/search support ([#6349](https://github.com/diegosouzapw/OmniRoute/pull/6349)) — a `tinyfish-fetch` executor + `/v1/web/fetch` route + MCP web-fetch tool, registered as a specialty-media provider with request-validation and a search-provider catalog entry. Regression guards: `tests/unit/executor-tinyfish-fetch.test.ts`, `web-fetch-handler.test.ts`, `mcp-web-fetch-tool.test.ts`, `provider-validation-tinyfish.test.ts`. (thanks @dtybnrj)
-- **fix(cli):** `omniroute launch-codex` now spawns `codex.cmd` through a shell on Windows (the npm `.cmd` shim is unresolvable by bare `spawn` → ENOENT), mirroring the qodercli Windows fix (#6263) ([#6312](https://github.com/diegosouzapw/OmniRoute/pull/6312)). Regression guard: `tests/unit/launch-codex-windows-spawn-6312.test.ts`. (thanks @swingtempo)
-- **fix(codex):** isolate the **Spark** quota from the shared Codex quota and stabilize the quota UI ordering / hydration so per-scope limits render consistently ([#6336](https://github.com/diegosouzapw/OmniRoute/pull/6336)). Regression guards: `tests/unit/codex-quota-selection-hydration.test.ts`, `provider-limits-ui.test.ts` + 3 more. (thanks @xz-dev)
-- **feat(api):** add a `hidePaidModels` setting that filters paid-only models out of the `/v1/models` catalog. Regression guard: `tests/unit/models-catalog-hide-paid.test.ts`. (thanks @chirag127)
-- **fix(api-manager):** the fallback model picker now preserves combos instead of dropping them when a primary model is unavailable ([#6443](https://github.com/diegosouzapw/OmniRoute/pull/6443)). Regression guard: `tests/unit/api-manager-page-static.test.ts`. (thanks @jmengit)
-- **fix(providers):** recoverable Antigravity / Cloud-Code (Gemini Code Assist) `403` responses ([#6452](https://github.com/diegosouzapw/OmniRoute/pull/6452)) are now classified as a retryable project-config error instead of a terminal account ban, so a fixable project/API-disabled 403 no longer forces a ~1-year cooldown / full OAuth reconnect. Regression guard: `tests/unit/errorclassifier-antigravity-403.test.ts`. (thanks @developerjillur)
-- **fix(mitm):** `sanitizeHeaders` now redacts `Set-Cookie` response headers so upstream session cookies never leak into logs / diagnostics ([#6451](https://github.com/diegosouzapw/OmniRoute/pull/6451)). Regression guard: `tests/unit/mitm-sanitize-headers.test.ts`. (thanks @developerjillur)
-- **fix(api):** `/api/compression/preview` now accepts `mode: "caveman"` and correctly handles stacked / zero-compression previews ([#6425](https://github.com/diegosouzapw/OmniRoute/issues/6425)). Regression guard: `tests/unit/api/compression-preview-caveman-and-stacked-6425.test.ts`. (thanks @chirag127)
-- **feat(providers):** add **Zed** hosted LLM aggregator as a native-app provider ([#6118](https://github.com/diegosouzapw/OmniRoute/pull/6118)) — OAuth sign-in via the Zed hosted flow, registered through the shared provider registry + executor. Regression guards: `tests/unit/zed-oauth-provider.test.ts`, `zed-import-utils.test.ts`, `zed-docker-detect.test.ts`, `mitm-handler-zed.test.ts`. VPS-validated via live operator login (Hard Rule #18).
-- **fix(oauth):** the Kiro SSO-cache auto-import now **preserves the IDC region** — cross-region Amazon Q / Kiro profiles imported from the SSO cache are no longer collapsed to the default region ([#6113](https://github.com/diegosouzapw/OmniRoute/pull/6113)). Regression guard: `tests/unit/kiro-auto-import-idc-2059.test.ts`. VPS-validated via live operator login (Hard Rule #18).
-- **fix(dashboard):** passthrough model aliases no longer collide when two namespaced model ids share a last segment (port from 9router#1850, [#6431](https://github.com/diegosouzapw/OmniRoute/pull/6431)). `enx/gpt-5.5` and `enx/codebuddy/gpt-5.5` both auto-generated the alias `gpt-5.5`, so the second model could never be added (the UI just alerted "alias already exists"). Aliases are now disambiguated deterministically — bare last segment when free, then parent-qualified (`codebuddy-gpt-5.5`), then a numeric suffix — while re-adding the exact same model id is still blocked. Regression guard: `tests/unit/passthrough-alias-1850.test.ts`. (thanks @arpicato)
-- **fix(translator):** preserve a Gemini `functionResponse` co-located with other parts (another `functionCall`, or trailing `text`) in the same content when translating **Gemini → OpenAI** ([#6376](https://github.com/diegosouzapw/OmniRoute/pull/6376)). `convertGeminiContent()` early-returned the tool message on the first `functionResponse` part, dropping any co-located parts; such contents are now pre-split (one tool message per `functionResponse`, emitted first, plus one message for the remaining parts). Regression guard: `tests/unit/gemini-to-openai-function-response.test.ts`. (thanks @warelik)
-- **fix(headroom):** detect a python interpreter managed by **mise / pyenv / asdf / conda** (port from 9router#2353, [#6382](https://github.com/diegosouzapw/OmniRoute/pull/6382)). Headroom's python probe (`src/lib/headroom/detect.ts`) searched a hardcoded `PATH`, but version managers expose their interpreters via shim dirs that only join `PATH` through interactive-shell activation — which the non-interactive server never runs, so a managed python (≥3.10) was invisible and Headroom reported it missing. The search path now prepends the well-known shim/bin dirs (`~/.local/share/mise/shims`, `~/.pyenv/shims`, `~/.asdf/shims`, `$CONDA_PREFIX/bin`, `~/.local/bin`, respecting `MISE_DATA_DIR`/`PYENV_ROOT`/`ASDF_DATA_DIR` when set), and a new `HEADROOM_PYTHON` env override lets operators point straight at their interpreter (mirroring `HEADROOM_URL`). Still shell-free (`execFileSync`). Regression guard: `tests/unit/headroom-detect.test.ts` (5). (thanks @loopyd)
-- **fix(executors):** strip the OpenAI-Codex/Claude-CLI `client_metadata` passthrough field for **NVIDIA** requests (port from 9router#1887, [#6411](https://github.com/diegosouzapw/OmniRoute/pull/6411)). NVIDIA's OpenAI-compatible wrapper rejects it with `400 Unsupported parameter`, the same class already handled for `cerebras`/`mistral`; `nvidia` (executor `default`) was missing from the strip allowlist so Codex/Claude-Code passthrough requests 400'd. Regression guard: `tests/unit/executor-default-strip-client-metadata.test.ts` (+nvidia case). (thanks @phidinhmanh)
-- **fix(translator):** strip the Claude-style `thinking` field for **NVIDIA `z-ai/glm-5.2`** (port from 9router#2023, [#6413](https://github.com/diegosouzapw/OmniRoute/pull/6413)). NVIDIA's OpenAI-compatible wrapper 400s on `thinking` (a Claude-format client routed here leaves a `thinking:{type:"adaptive"}`); the existing strip rule only dropped `reasoning`. Same class already handled for `minimax-m2.7`. Regression guard: `tests/unit/nvidia-minimax-thinking-strip.test.ts` (+glm-5.2 case). (thanks @phidinhmanh)
-- **fix(translator):** suppress the streamed `</think>` close marker for the **Antigravity IDE** client (port from 9router#1061, [#6415](https://github.com/diegosouzapw/OmniRoute/pull/6415)). On thinking-only turns Antigravity rendered a bare `</think>` as the sole visible content, tripping its loop-detection and wasting requests. Antigravity's UA (`vscode/<v> (Antigravity/<v>)`) is added to the marker-suppress allowlist (alongside OpenCode); Claude Code / Cursor still get the marker, and `x-omniroute-thinking-marker: on` force-restores it. Regression guard: `tests/unit/think-close-marker-suppress-5245.test.ts`. (thanks @abdofallah)
-- **fix(executors):** strip nested `reasoning_content` from messages for **Mistral** (port from 9router#1649, [#6417](https://github.com/diegosouzapw/OmniRoute/pull/6417)). Mistral's API returns `422 extra_forbidden` when an assistant message carries `reasoning_content` (replayed thinking from a prior turn, e.g. via the Codex `/responses` path); the generic top-level 400 field-downgrade retry never covered the nested per-message field. `DefaultExecutor` now strips it for provider `mistral` only, so DeepSeek (which requires replayed `reasoning_content`) is unaffected. Regression guard: `tests/unit/mistral-strip-reasoning-content-1649.test.ts`. (thanks @xxy9468615)
-- **fix(executors):** strip the `client_metadata` passthrough field on the **OpenCode** path (port from 9router#1442, [#6418](https://github.com/diegosouzapw/OmniRoute/pull/6418)). OpenCode upstreams (e.g. `kimi-k2.6` via opencode-go) reject it with `400 "Extra inputs are not permitted, field: 'client_metadata'"`; the DefaultExecutor strip only covered cerebras/mistral and `OpencodeExecutor` extends `BaseExecutor` directly, so nothing removed it there. Regression guard: `tests/unit/opencode-strip-client-metadata-1442.test.ts`. (thanks @yanpaing007)
-- **fix(executors):** inject the `reasoning_content` echo for the native **Moonshot Kimi** provider (port from 9router#1480, [#6419](https://github.com/diegosouzapw/OmniRoute/pull/6419)). Kimi (executor `default`) is a thinking-mode upstream that 400s with "reasoning_content must be passed back" when a prior assistant turn lacks it; the placeholder injection was only wired into the OpenCode meta-provider, so direct multi-turn Kimi conversations failed. Scoped to `kimi` (gateway-served models matching the thinking-model name pattern are unaffected). Regression guard: `tests/unit/kimi-native-reasoning-injected-1480.test.ts`. (thanks @2220258345)
-- **fix(executors):** recover from a strict gateway's `context_management: Extra inputs are not permitted` 400 (port from 9router#1468, [#6420](https://github.com/diegosouzapw/OmniRoute/pull/6420)). **Claude Code** always sends a top-level `context_management` field; strict anthropic-compatible gateways reject it. The dedicated context-editing 400-fallback only fired when OmniRoute's own `contextEditing` feature was enabled (default off), so a client-sent field passed through untouched and 400'd. `context_management` is now in the generic reactive field-strip list, so it's stripped-and-retried once regardless of the feature flag (with correct request re-signing for claude-compatible relays). Regression guard: `tests/unit/provider-field-strips.test.ts`. (thanks @ohahe52-dot)
-- **fix(network):** enable **RFC 8305 Happy Eyeballs** (`autoSelectFamily`) on the direct-egress undici dispatcher (port from 9router#1237, [#6423](https://github.com/diegosouzapw/OmniRoute/pull/6423)). When DNS returns both IPv6 (AAAA) and IPv4 (A) and the IPv6 route is broken (e.g. a NAT64 `64:ff9b::` prefix without routing), undici tried IPv6 first and hung until `ETIMEDOUT` (then a 502 + account lockout), even though `curl` reached the same host. The direct dispatcher now races both families and uses whichever connects first. Proxy paths pin family via `proxyTls` and are unaffected. Regression guard: `tests/unit/direct-dispatcher-pipelining-4580.test.ts`. (thanks @adentdk)
-- **fix(combo):** round-robin now advances the rotation pointer past the model that **actually served**, not the eagerly-scheduled one (port from 9router#948, [#6428](https://github.com/diegosouzapw/OmniRoute/pull/6428)). With `stickyLimit: 1` (true round-robin), when the scheduled model failed and a _different_ model served via fallback, the counter had already advanced +1 from the scheduled index — so the next request reused the fallback-served model, degrading round-robin into hot-spotting on whichever model was healthy. The pointer now advances to the served index + 1 (mirroring the sticky-limit>1 path). Session-stickiness (#3825) and distribution are preserved. Regression guard: `tests/unit/combo-rr-fallback-advance-948.test.ts`. (thanks @binsarjr)
-- **fix(sse):** a non-string `model` field is now rejected with a `400` before the resolver, instead of crashing downstream `.toLowerCase()`/`.split()` calls into an empty-body `500` that escapes the error sanitizer ([#6407](https://github.com/diegosouzapw/OmniRoute/issues/6407)). Regression guard: `tests/unit/chat-non-string-model-6407.test.ts`. (thanks @chirag127)
-- **fix(api):** unknown `/api/*` routes now return a JSON `404` (instead of the dashboard HTML shell) and scalar chat params (`model`/`temperature`/etc.) are validated **before** the provider lookup so malformed requests fail fast with a clear `400` ([#6424](https://github.com/diegosouzapw/OmniRoute/issues/6424), [#6412](https://github.com/diegosouzapw/OmniRoute/issues/6412)). Regression guards: `tests/unit/api/api-catchall-json-404.test.ts`, `tests/unit/chat-early-schema-validation-6412.test.ts`. (thanks @chirag127)
-- **fix(api):** `/v1/chat/completions` now rejects a non-JSON `Content-Type` with a `400` before parsing the body ([#6414](https://github.com/diegosouzapw/OmniRoute/issues/6414)). Regression guard: `tests/unit/v1-chat-completions-content-type-6414.test.ts`. (thanks @chirag127)
-- **fix(api):** the `X-OmniRoute-Compression` response header is now echoed on `/v1/chat/completions` and `/v1/completions` ([#6422](https://github.com/diegosouzapw/OmniRoute/issues/6422)). Regression guard: `tests/unit/compression-header-echo-6422.test.ts`. (thanks @chirag127)
-- **fix(api):** concurrent `GET /v1/models` requests are coalesced into a single catalog build ([#6408](https://github.com/diegosouzapw/OmniRoute/issues/6408)). Regression guard: `tests/unit/v1-models-concurrent-6408.test.ts`. (thanks @chirag127)
-- **fix(api):** `/v1/completions` now echoes the requested `body.model` in its JSON + streamed responses ([#6429](https://github.com/diegosouzapw/OmniRoute/pull/6429)). Regression guard: `tests/unit/completions-body-model-echo.test.ts`. (thanks @chirag127)
-- **fix(api):** env-var master keys now see the full `/v1/models` catalog ([#6406](https://github.com/diegosouzapw/OmniRoute/issues/6406)). Regression guard: `tests/unit/models-catalog-envkey-6406.test.ts`. (thanks @chirag127)
-- **fix(api):** non-streaming `/v1/completions` responses now echo `body.model` aligned with the `X-OmniRoute-Model` header ([#6426](https://github.com/diegosouzapw/OmniRoute/issues/6426)). Regression guard: `tests/unit/v1-completions-model-header-match-6426.test.ts`. (thanks @chirag127)
-- **fix(api):** unknown `/v1/*` routes now return a JSON `404 not_found` instead of the Next.js dashboard HTML shell ([#6405](https://github.com/diegosouzapw/OmniRoute/issues/6405)). Regression guard: `tests/unit/api/v1-catchall-json-404.test.ts`. (thanks @chirag127)
-- **fix(api):** the per-connection provider models route now degrades to the shipped catalog when a provider's `/models` endpoint answers with a redirect ([#6267](https://github.com/diegosouzapw/OmniRoute/issues/6267)) — a `qwen-web` import failed with a raw `Redirect blocked … (307)` 503. `safeOutboundFetch` throws `REDIRECT_BLOCKED` on the 307, `getSafeOutboundFetchErrorStatus` maps it to 503, and `buildDiscoveryErrorFallbackResponse` treated every 503 as a hard error — so the non-empty `getModelsByProviderId("qwen-web")` catalog was never surfaced. A models-endpoint redirect is not a fixable-config error (unlike `URL_GUARD_BLOCKED`/`INVALID_URL`, which stay hard errors), so it now falls back to the local/cached catalog before the 503 short-circuit. General fix — covers any config-driven provider that 307s. Regression guard: `tests/unit/provider-models-qwen-web-redirect-6267.test.ts`. (thanks @chirag127)
-- **fix(api):** the per-connection provider models route (MCP `list_models_catalog` + the dashboard import view) now merges USER-ADDED custom models into its response ([#6247](https://github.com/diegosouzapw/OmniRoute/issues/6247)) — custom models live in the `key_value` namespace `customModels`, which the live REST `/api/v1/models` already merges, but `src/app/api/providers/[id]/models/route.ts` never read `getCustomModels`, so custom models were dropped on both the discovery-success and local_catalog paths. They are now folded into the returned model list (deduped by id, stamped `owned_by: provider`), fixing MCP + the dashboard import view in one place. Regression guard: `tests/unit/provider-models-custom-merge-6247.test.ts`. (thanks @RCrushMe)
-
-- **fix(providers):** GitLab Duo tool-calling follow-up turns no longer fail upstream with `422 {"detail":"Validation error"}` (tokens 0/0, rejected pre-inference). The #6234 tool-result-feedback fix serialized the **entire** multi-turn conversation into GitLab's single-file `code_suggestions` (`small_file`) generation endpoint — folded history that turn-N sent as an oversized `current_file.content_above_cursor` **and** duplicated verbatim into `user_instruction`, tripping the AI-Gateway's `small_file` validation guard. The executor now **bounds** that prompt: it keeps system + latest user message + the most-recent tool round (dropping older turns), caps oversized tool results, and stops duplicating the full prompt into `user_instruction` (which now carries only the short latest user message) — while still feeding the most-recent tool result back so the agent continues (`open-sse/executors/gitlab.ts`, [#6220](https://github.com/diegosouzapw/OmniRoute/issues/6220)). The unit test covers the bounding logic; the upstream 422→200 clearing is VPS-only (Hard Rule #18). Regression guard: `tests/unit/gitlab-tool-exchange-bounded-6220.test.ts`.
-
-- **fix(i18n):** the provider-detail (`/dashboard/providers/[id]`) connection-status filter labels no longer render as `__MISSING__:All` / `__MISSING__:Active` / `__MISSING__:Error` / `__MISSING__:Banned` / `__MISSING__:CreditsExhausted` in non-English locales (notably pt-BR) ([#6290](https://github.com/diegosouzapw/OmniRoute/issues/6290)). Root cause was **not** the namespace mismatch the issue guessed — the `providers.filter*` keys resolve correctly in `en.json`; the debt lived in the locale mirrors (`src/i18n/messages/*.json`), where these five keys carried the `__MISSING__:` sync sentinel in ~15 locales and were absent entirely in ~26 others, so next-intl found the key and echoed the sentinel verbatim. All 40 non-English/-Chinese mirrors now ship real translations for the five `providers.filter*` labels. Regression guard: `tests/unit/i18n-provider-filter-keys-6290.test.ts`. (thanks @diegosouzapw)
-
-- **fix(providers):** the `copilot-m365-web` streaming executor now emits `debug`-level WebSocket diagnostics ([#6210](https://github.com/diegosouzapw/OmniRoute/issues/6210)) — the outbound WS URL (with the `access_token` **redacted** via `redactWsUrl()`), handshake success/failure, and each received SignalR frame's `type`/`target`. Previously the streaming path logged nothing, so an empty `content:null` response (the M365 Education / Starter tier symptom fixed in #6234) was undiagnosable even at `APP_LOG_LEVEL=debug`. The change is debug-level and side-effect-free — it does not alter streaming behavior or the frame parser, and the token never reaches the logs. Regression guard: `tests/unit/copilot-m365-web-logging-6210.test.ts` (thanks @qpeyba)
-
-- **fix(resilience):** a round-robin combo no longer returns `503 all upstream accounts are unavailable` when a compatibility-rejected target is actually healthy ([#6238](https://github.com/diegosouzapw/OmniRoute/issues/6238)). `filterTargetsByRequestCompatibility` drops request-incompatible targets (tool/vision/structured-output unsupported, or below the required context window) **before** any availability check runs, and its `compatible.length === 0` safety net only fired when _all_ targets were filtered — not when the kept targets later all turned out runtime-unavailable (circuit-open / cooldown / no credentials). So a combo could 503 while a compat-rejected-but-healthy provider sat unused. `handleRoundRobinCombo` now keeps the compat-rejected set and, when every compat-kept target was skipped without a single real attempt, probes those rejected targets as a **last-resort fallback tier** (via the new pure `open-sse/services/combo/comboCompatFallback.ts`) before crystallizing the 503. Regression guard: `tests/unit/combo-roundrobin-compat-fallback-6238.test.ts`. (thanks @ThongAccount)
-
-- **fix(startup):** best-effort self-heal for a corrupted Turbopack dev cache on Windows ([#6289](https://github.com/diegosouzapw/OmniRoute/issues/6289)). On Windows, `pnpm dev` can fail at startup when Turbopack `mmap`s a persistent-cache SST file and the OS refuses the mapping (`os error 1455` — "paging file too small"), which Turbopack surfaces as a misleading `Module not found: Can't resolve '@/shared/utils/machine'`. This is a **known upstream Turbopack cache-corruption bug — not our code**. The dev launcher (`scripts/dev/run-next.mjs`) now wraps `nextApp.prepare()` and, when it rejects with that signature (`isTurbopackCacheCorruption` in the new `scripts/dev/turbopackCacheHeal.mjs`), purges `.build/next/**/cache/turbopack` and retries **once** with a clear log. **Caveat — best-effort only:** the corruption often surfaces as a runtime overlay rather than a `prepare()` rejection, so this cannot always intercept it; the reliable remedy remains manually deleting the Turbopack cache dir. Regression guard: `tests/unit/turbopack-cache-heal-6289.test.ts`. (thanks @chirag127)
-
-- **fix(providers):** qodercli PAT auth no longer fails with `spawn qodercli ENOENT` on Windows ([#6263](https://github.com/diegosouzapw/OmniRoute/issues/6263)) — `spawnQoderCli` spawned the bare `qodercli` name with `shell:false` and an unenriched env, so the npm `.cmd` wrapper under `%APPDATA%\npm` (a user-PATH directory) was never resolved. It now resolves the absolute `.cmd`/`.exe` path through the existing `getCliRuntimeStatus("qoder")` resolver in `src/shared/services/cliRuntime.ts` (memoized), spawns with `shell` when the target is a `.cmd`/`.bat`, and uses the cliRuntime-enriched env (PATH + PATHEXT + APPDATA); the ENOENT error now lists the searched paths plus the `CLI_QODER_BIN` override. End-to-end spawn on a real Windows host is host-only (Hard Rule #18); the path-resolution logic is unit-tested. Regression guard: `tests/unit/qodercli-windows-resolve-6263.test.ts`. (thanks @chirag127)
-
-- **fix(sse):** the reasoning-token buffer no longer inflates **probe-sized `max_tokens`** ([#6274](https://github.com/diegosouzapw/OmniRoute/issues/6274)) — Claude Code's `/model` capability check sends `max_tokens: 1`, but for a thinking-capable model with a large output cap (e.g. `glm-5.2`) the #3587 headroom heuristic (`max(current + 1000, ceil(current * 1.5))`) rewrote it to `1001` and forwarded that upstream, wasting tokens on a request that was never a genuine reasoning budget. `resolveReasoningBufferedMaxTokens()` (`open-sse/services/reasoningTokenBuffer.ts`) now short-circuits and returns the caller's value verbatim when it is below the new `REASONING_BUFFER_MIN_TRIGGER` (256) threshold — a tiny explicit limit is a probe, not a reasoning request. Real budgets still receive the #3587 headroom unchanged, and the guard runs after the existing capability checks so unknown / non-reasoning models keep returning `null`. Regression guard: `tests/unit/reasoning-token-buffer-6274.test.ts`. (thanks @brightfiscalband)
-
-- **fix(cli):** `omniroute reset-password` now works as a real subcommand, and password resets over piped (non-TTY) stdin actually apply ([#6261](https://github.com/diegosouzapw/OmniRoute/issues/6261), [#6258](https://github.com/diegosouzapw/OmniRoute/issues/6258)). Two coupled defects: (1) **#6261** — `bin/omniroute.mjs` routed everything through Commander with only two pre-Commander bypasses (`--mcp`, `reset-encrypted-columns`), so `omniroute reset-password` was rejected as an unknown command; only the separate `omniroute-reset-password` bin worked, while the docs falsely advertised the subcommand (incl. a bogus "legacy alias still works"). A pre-Commander bypass mirroring `reset-encrypted-columns` now dynamically imports `bin/reset-password.mjs` (which self-executes) before Commander parses; the three doc lines were corrected. (2) **#6258** — `bin/reset-password.mjs` issued two sequential `rl.question` prompts; under piped stdin the second read never settled at EOF, so `main()` never reached `resetManagementPassword` and the reset was a silent no-op (both prompts printed, no success, password unchanged). The CLI now detects non-TTY stdin and reads it once (first line = password, second line = confirm if present, else reused), adds a `--password-stdin` flag (entire stdin is the password, no confirmation), and exits `0` explicitly so the success line always flushes; interactive TTY behavior is unchanged. Regression guard: `tests/unit/reset-password-cli-6261-6258.test.ts` (3). (thanks @chirag127)
-
-- **fix(db):** the mass-migration **safety abort** now tells the operator how to bypass it and stops flooding the log ([#6260](https://github.com/diegosouzapw/OmniRoute/issues/6260)) — after restoring a backup that wiped the migration tracking table, `runMigrations()` threw the abort on every downstream `ensureDbInitialized()`, re-logging the full banner 11+ times, and the message never mentioned the existing `OMNIROUTE_MAX_PENDING_MIGRATIONS` escape hatch. The abort text now appends a bypass hint (set `OMNIROUTE_MAX_PENDING_MIGRATIONS=0` in `server.env` / `DATA_DIR/.env`), and a new `MigrationSafetyAbortError` is memoized so repeated calls in the same process throw the same instance and emit a single concise line instead of the full cascade. Regression guard: `tests/unit/migration-safety-abort-6260.test.ts`. (thanks @chirag127)
-
-- **fix(auth):** importing a **distinct** Codex/ChatGPT OAuth `auth.json` is no longer falsely rejected as "already exists" when it belongs to a different user in the same workspace ([#6301](https://github.com/diegosouzapw/OmniRoute/issues/6301)). `findExistingCodexConnection` (in `src/lib/oauth/utils/codexAuthImport.ts`) deduped **only** on `providerSpecificData.workspaceId === accountId`, where `accountId` is the shared `chatgpt_account_id`/`tokens.account_id` — so two members of the same ChatGPT Team collapsed onto a single connection (409 `duplicate_account`). The id_token's `https://api.openai.com/auth` claim carries a per-user `chatgpt_user_id` alongside the workspace id (the device-flow path already persisted it as `chatgptUserId`, but the import path did not). Now `parseAndValidateCodexAuth` extracts `userId` (`chatgpt_user_id` → `user_id` → JWT `sub`) into `ParsedCodexAuth`, the create/update paths persist `chatgptUserId` in `providerSpecificData` (mirroring `codex.ts`), and dedup keys on `workspaceId` **AND** `chatgptUserId` — with a backward-compat fallback to legacy accountId-only matching when no stored connection for that workspace records a `chatgptUserId`, so genuinely-same accounts still dedup. Regression guard: `tests/unit/codex-auth-import-userid-dedup-6301.test.ts` (4). (thanks @anungma)
-
-- **fix(providers):** importing models for the **venice-web** provider no longer fails with a red "Provider venice-web does not support models listing" ([#6269](https://github.com/diegosouzapw/OmniRoute/issues/6269)). `venice-web` is a web-cookie provider with an executor but no upstream `/v1/models` endpoint and no registry `models`, so the models route fell through to the tail `400`. Mirroring the `jules`/`linkup-search`/`ollama-search` fix (#5569), it now ships a static local catalog entry in `src/lib/providers/staticModels.ts` — seeding the current Venice lineup (`venice-uncensored`, `llama-3.3-70b`, `qwen3-235b`, `qwen3-4b`, `deepseek-r1-671b`; Venice rotates its catalog, see docs.venice.ai/models/overview) — so the route returns `200` with `source:"local_catalog"`, `intentional:true`. Regression guard: `tests/unit/static-models-venice-web-6269.test.ts`. (thanks @chirag127)
-
-- **fix(api):** the specialty model catalogs (`/v1/embeddings`, `/v1/images`, `/v1/music`, `/v1/videos` model lists) are now derived from the **unified catalog filtered by a predicate** (`getSpecialtyModelsResponse`) instead of ad-hoc per-route logic, so they consistently respect active-credential visibility and stay in sync with the main catalog ([#6303](https://github.com/diegosouzapw/OmniRoute/pull/6303)). Regression guard: `tests/unit/specialty-model-catalog-routes.test.ts`. (thanks @makcimbx)
-- **fix(api):** the agent-bridge server route now resolves the MITM manager via a **dynamic `import("@/mitm/manager.runtime")`** so Turbopack does not statically pull the stub (or over-bundle the manager), and the agent-skills generator anchors its output base path with `path.join(process.cwd(), …)` so Turbopack's static analyzer stops tracing the whole project root ([#6329](https://github.com/diegosouzapw/OmniRoute/issues/6329), [#6366](https://github.com/diegosouzapw/OmniRoute/pull/6366)). Regression guard: `tests/unit/agent-bridge-server-route-dynamic-import.test.ts`. (thanks @Iammilansoni)
-- **fix(api):** internal probes (combo-test, cloud-sync verify) now pick a **management-scoped / allow-all API key** instead of naively grabbing `getApiKeys()[0]` — a restricted `self:usage` first row made the probe fail with "Model X is not allowed for this API key" even when the combo path was healthy (`pickApiKeyForInternalUse` in `src/lib/db/apiKeys.ts`). The API-manager model editor also falls back to `/api/models?all=true` when `/v1/models` is catalog-protected ([#6372](https://github.com/diegosouzapw/OmniRoute/pull/6372)). Regression guard: `tests/unit/pick-internal-api-key-6372.test.ts`. (thanks @jmengit)
-- **fix(live-ws):** the Live Dashboard WebSocket server now **rejects on bind failure** (e.g. `EADDRINUSE` when the API bridge already holds the port) instead of letting the error surface as an unhandled `error` event that crash-loops the process — the `error` listener is attached to `wss` (not `server`) and releases the EventBus subscription on a failed start ([#6324](https://github.com/diegosouzapw/OmniRoute/issues/6324)). Regression guard: `tests/unit/live-ws-eaddrinuse-6324.test.ts`. (thanks @vinayakkulkarni)
-- **fix(dashboard):** the Home provider-topology widget now trusts the live provider-metrics snapshot — it uses `topology.errorProvider` and live `activeRequests` directly instead of re-deriving state from a stale `lastErrorAt` or applying a frontend timeout filter, so the topology reflects real-time provider health ([#6322](https://github.com/diegosouzapw/OmniRoute/pull/6322)). Regression guard: `tests/unit/home-provider-topology-live-state.test.ts`. (thanks @xz-dev)
-- **fix(sse):** strip zero-width markers from streamed **tool-call arguments** — a follow-up to [#5857](https://github.com/diegosouzapw/OmniRoute/pull/5857). That PR removed injected zero-width joiners (U+200D) from streamed assistant text/reasoning but deliberately left tool-call argument JSON byte-exact. The request-side obfuscation (`open-sse/services/claudeCodeObfuscation.ts`) injects ZWJ into agent words — including the temp path inside the Bash tool description — and Claude models copy that verbatim into generated commands, which are delivered as tool-call arguments rather than assistant text. As a result the ZWJ survived and corrupted code blocks (e.g. a temp path rendered with an invisible joiner). Now `open-sse/handlers/responseSanitizer.ts` strips zero-width code points from tool-call argument strings at every emit site (OpenAI non-stream/stream chat `tool_calls` + legacy `function_call`, native Responses `function_call` items, the OpenAI→Responses conversion, and the native Responses streaming `response.function_call_arguments.delta/.done` events). Only zero-width code points are removed; JSON structure and all other bytes stay identical (no parse/restringify), so normal arguments remain byte-exact. Regression guard: 6 new cases in `tests/unit/response-sanitizer.test.ts` (suite 50/50).
-
-- **fix(nodejs):** the default app log path now resolves under `DATA_DIR` (`~/.omniroute/logs/application/app.log`) instead of `process.cwd()` ([#6197](https://github.com/diegosouzapw/OmniRoute/issues/6197)) — the globally-installed CLI runs from an arbitrary working directory, so anchoring the default to cwd made file logging silently write to (or no-op under) an unrelated directory, contradicting the documented `.env.example` default. `getAppLogFilePath()` now computes the default lazily via the pure `resolveDataDir()` resolver (honours a per-process `DATA_DIR`, no directory-creation side effect); an explicit `APP_LOG_FILE_PATH` still wins. Regression guard: `tests/unit/logenv-datadir-path-6197.test.ts` (3).
-
-- **fix(docker):** AgentBridge/`startMitm` no longer aborts in containers/headless when the Antigravity-default DNS step can't write `/etc/hosts` ([#6127](https://github.com/diegosouzapw/OmniRoute/issues/6127)), and the privileged command's stderr now reaches `app.log` instead of only a bare exit code hitting the toast ([#6198](https://github.com/diegosouzapw/OmniRoute/issues/6198)). The default DNS step (`addDNSEntry`) was called unguarded while cert install and the two sibling DNS steps were each best-effort — in the runtime Docker image (`USER node`, no `sudo`, read-only `/etc/hosts`) it threw `Command failed with code 1` out of `startMitmInternal` and killed the whole start, discarding the stderr. The three DNS steps are extracted into a best-effort `provisionDnsEntries()` where each failure is logged with the full `err` (stderr included, folded in by `systemCommands.ts`) and never aborts the start. Regression guard: `tests/unit/mitm-dns-graceful-degrade-6127.test.ts` (4).
-
-- **fix(providers):** copilot-m365-web now supports the M365 Education "Starter / OfficeWebIncludedCopilot" tier and no longer returns an empty `content:null` stream ([#6210](https://github.com/diegosouzapw/OmniRoute/issues/6210)). Two gaps: (1) `buildWsUrl()` hardcoded the individual-consumer scenario (`OfficeWebPaidConsumerCopilot`, `isEdu=false`) — the EDU tier is now opt-in via `providerSpecificData.tier="edu"`, emitting `scenario=OfficeWebIncludedCopilot`/`isEdu=true` (the individual path is unchanged); (2) the EDU/GPT-5.5 path streams deltas via `arguments[0].writeAtCursor` (incremental) instead of only `messages[].text` (accumulated snapshots), which the parser dropped — a new `accumulateBotContent()` folds both formats, with `type:2 item.result.message` as a last-resort fallback. Regression guard: `tests/unit/copilot-m365-edu-writeatcursor-6210.test.ts` (10). (thanks @qpeyba)
-
-- **fix(providers):** GitLab Duo executor now feeds tool results back into the prompt instead of looping ([#6220](https://github.com/diegosouzapw/OmniRoute/issues/6220)) — `buildPrompt()` branched only on `system`/`user` and took `userParts.at(-1)`, silently dropping the `assistant{tool_calls}` + `tool{result}` turns the client appended, so the reconstructed prompt was byte-identical to turn 1 and the model re-emitted the same `<tool>` call forever. When a tool exchange is present the full conversation is now serialized, folding each tool result back keyed by its `tool_call_id`; simple conversations keep the legacy shape. Complements the tool_call emission from [#6051](https://github.com/diegosouzapw/OmniRoute/issues/6051) (the `kilo-duplicate` label was a false positive — different, sequential defect). Regression guard: `tests/unit/gitlab-tool-result-feedback-6220.test.ts` (4).
-
-- **fix(providers):** opencode-go/opencode-zen can now synthesize the OpenCode CLI identity headers Cloudflare requires on VPS egress ([#5997](https://github.com/diegosouzapw/OmniRoute/issues/5997)) — on a datacenter VPS, `opencode.ai/zen/go/v1/chat/completions` 403s (HTML challenge) requests lacking CLI identity, while the reporter's control curl proved that `User-Agent: opencode-cli/1.0.0` + `x-opencode-client: cli` + `x-opencode-project: default` + fresh request/session UUIDs succeed. Opt-in via `OPENCODE_SYNTHESIZE_CLI_HEADERS=true` (values overridable via `OPENCODE_GO_USER_AGENT`/`OPENCODE_USER_AGENT`/`OPENCODE_CLIENT`/`OPENCODE_PROJECT`); it fills only headers the client did not already send. Kept **off by default** — the forward-only path is deliberate (fabricating a wrong value risks upstream rejection; a prior dedup regressed with `opencode/local`), so this replaces the fragile local header-injection shim without changing default behavior. Regression guard: `tests/unit/opencode-cli-headers-synthesis-5997.test.ts` (6). (thanks @aleksesipenko)
-- fix(resilience): sticky session affinity now evicts and fails over to another account when the pinned account is exhausted/unavailable (#6219)
-
-- fix(sse): Responses API passthrough now drops internal commentary-phase output before forwarding to clients (gated by RESPONSES_PASSTHROUGH_DROP_COMMENTARY, default on) (#6199)
-
-- **fix(sse):** tool-call function schemas with a root `type: null` are now coerced to `type: "object"` before dispatch ([#6359](https://github.com/diegosouzapw/OmniRoute/issues/6359)) — clients like the Codex app emit `parameters: { type: null, ... }` for some tools, which OpenAI-compatible upstreams reject with `400 Invalid schema for function '...': schema must be a JSON Schema of 'type: "object"', got 'type: null'`, failing the whole request. `toolSchemaSanitizer` already stripped the null; it now re-adds the mandatory root `"object"` type (and empty `properties`/open `additionalProperties` when absent). Combinator roots (`anyOf`/`oneOf`/`allOf`) and explicit root types are left untouched. Regression guard: 5 new cases in `tests/unit/tool-schema-sanitizer.test.mjs`.
-
-- **fix(docker):** AgentBridge no longer fails to start on npm/Electron/VPS installs with "MITM manager stub reached at runtime" ([#6344](https://github.com/diegosouzapw/OmniRoute/issues/6344)) — v3.8.45 flipped the production bundler default to Turbopack, but `next.config.mjs` aliased `@/mitm/manager` to its Docker-only degraded stub **unconditionally**. That was harmless while Docker (which sets the alias intentionally for #3390 graceful degradation) was the sole Turbopack consumer, but once every artifact built with Turbopack the stub shipped to all non-Docker users and `startMitm` threw on the first Agent-Bridge start. The alias is now opt-in via `OMNIROUTE_MITM_STUB=1` (set only by the Dockerfile) through the shared `scripts/build/mitm-stub-flag.mjs` helper; default builds bundle the real manager. Regression guard: `tests/unit/mitm-stub-alias-6344.test.mjs` (4).
-
-- **fix(proxy):** stop the v3.8.44 proxy regression that leaked the real IP and disabled healthy proxies ([#6246](https://github.com/diegosouzapw/OmniRoute/issues/6246)). Two coupled defects from the new health scheduler: (1) **IP leak** — when a proxy assigned to a connection was marked `inactive`, resolution fell through to a **direct** egress instead of blocking, exposing the operator's real IP; (2) **over-deactivation** — the sweep flipped a proxy to `inactive` on the **first** failed probe and counted our own 5s timeout / a probe-target `5xx` as the proxy's fault, so healthy paid proxies vanished from egress selection ("my proxies are not being used anymore"). Fix: the sweep decision is extracted into a pure, network-free `decideProxyHealthAction` (`src/lib/proxyHealth/decision.ts`) — by default the health check now **only counts/logs and never downgrades status** (a proxy is downgraded/removed only with `PROXY_AUTO_REMOVE=true`, after `PROXY_AUTO_REMOVE_AFTER` **consecutive** conclusive failures); probes are classified tri-state so an inconclusive result (our timeout, or a `5xx` from the probe target) never penalizes the proxy, and the probe timeout is raised 5s→15s. Separately, `safeResolveProxy` now **fails closed** via the existing policy: a connection whose assigned proxy is dead is blocked instead of leaking direct (`hasBlockingProxyAssignment`), honoring the explicit `proxy off` toggles and the `PROXY_FAIL_OPEN=true` opt-out. Existing proxies stuck `inactive` by the old behavior need a one-time manual re-activate (the operator owns proxy status). Regression guards: `tests/unit/proxy-health-decide-action-6246.test.ts`, `tests/unit/proxy-assigned-unavailable-6246.test.ts`.
-
-- **fix(proxy):** make "Test All" read-only and add bulk enable/disable ([#6246](https://github.com/diegosouzapw/OmniRoute/issues/6246)). Complements the core fail-closed / scheduler fix (#6296) with the two remaining reporter asks. (1) The **"Test All" button** (`POST /api/settings/proxies/auto-test`) used to flip a proxy to `inactive` on a failed reachability probe; since the egress selector excludes `inactive` proxies, a flaky probe (an unreachable `httpbin.org`, a proxy that blocks `HEAD`, or a slow paid proxy) silently disabled every proxy that failed — "Test All" is now **read-only by default** (only the operator sets a proxy active/inactive; opt back into the legacy test-and-set with `PROXY_HEALTH_AUTO_DEACTIVATE=true`). (2) Adds a **bulk enable/disable** proxies endpoint + toolbar action (`POST /api/settings/proxies/batch-activate`) so an operator can re-activate proxies in one click. Regression guard: `tests/unit/proxy-health-6246.test.ts`. (thanks @tenshiak)
-
-- **chatcore (tools): stop the default 128-tool cap from silently dropping opencode's `task`/MCP tools.** opencode (used as an MCP/agent host) sends a large tool list; when it exceeds the speculative `MAX_TOOLS_LIMIT` (128) default, `truncateToolList` did a blind `tools.slice(0, 128)`, dropping every tool past index 128 — including opencode's built-in `task` tool (subagent launch) and many MCP tools, so models routed through OmniRoute could no longer spawn subagents or reach part of their tools. The cap exists to avoid upstream `400`s for providers with real hard limits (e.g. grok-cli 200), so it is kept for those: detection of the opencode client (`isOpencodeClient` — any `x-opencode-*` header, or `opencode` in the user-agent) now only bypasses the **speculative 128 default**, never a known provider ceiling. Precedence is explicit — a proactive/detected provider limit always truncates (even for opencode); otherwise opencode forwards its full tool list; otherwise the unchanged 128 default applies to every other client. Refactors `getEffectiveToolLimit` into `getKnownToolLimit(provider) ?? DEFAULT_LIMIT` (byte-identical for existing callers) and fixes a cosmetic debug-log that reported the truncated count instead of the original. Regression guard: `tests/unit/tool-limit-detector.test.ts`.
-
-- **fix(mitm):** the macOS MITM-cert install check now matches the system keychain again. `security find-certificate -a -Z` prints the SHA-1 as a colon-less hex string, but the installed-check compared it against `getCertFingerprint()`'s colon-separated form, so the substring match never hit — the cert was reported as not-installed and re-prompted for the sudo install on every run. Fingerprints are now normalized (colons stripped, upper-cased) on both sides via the extracted `macCertOutputHasFingerprint` helper. Regression guard: `tests/unit/mitm-cert-mac-fingerprint.test.ts`. ([#6204](https://github.com/diegosouzapw/OmniRoute/pull/6204), closes [#6134](https://github.com/diegosouzapw/OmniRoute/issues/6134) — thanks @rianonehub)
-
-- **fix(api):** `/v1/messages/count_tokens` now counts `tool_use`, `tool_result` and `thinking` content blocks (and array-form `system` prompts) in the local-estimation path, instead of only `text`. Real agentic conversations keep ~95% of their tokens inside tool results; the previous estimate returned near-zero for them, which silently broke Claude Code's auto-compaction (context grew past the window with no compaction until the upstream API rejected the request). The real provider-side count path is unchanged. Regression guard: `tests/unit/messages-count-tokens-route.test.ts`. ([#6221](https://github.com/diegosouzapw/OmniRoute/pull/6221) — thanks @luweiCN)
-
-- **fix(antigravity):** strip a trailing assistant prefill turn for Vertex Claude models to avoid upstream 400s ([#6114](https://github.com/diegosouzapw/OmniRoute/pull/6114)). Regression guard: `tests/unit/antigravity-claude-prefill-strip.test.ts`. (thanks @anki1kr)
-
-- **fix(security):** the mutable cloud-agent routes (`/api/cloud/credentials/update`, `/api/cloud/models/alias`) now require management auth instead of being treated as public. They were classified as public API routes, so a request without management credentials could update stored cloud-agent credentials and model aliases. They are removed from the public-route set, classified as management routes in the authz pipeline, and gated by `requireManagementAuth`; cloud **read**/auth routes stay public. Regression guards: `tests/unit/cloud-write-auth.test.ts`, `tests/unit/authz/classify.test.ts`, `tests/unit/public-api-routes.test.ts`. ([#6233](https://github.com/diegosouzapw/OmniRoute/pull/6233) — thanks @vittoroliveira-dev)
-
-- **refactor(dashboard):** extract the onboarding-wizard "Open provider details" link target into a pure, unit-tested `buildProviderDetailsHref(connection)` helper. The wizard already routes by `connection.id` (the node UUID) rather than the provider category slug (#6144/#6145); this hardens that behavior behind a tested helper that guards a missing id/connection. Regression guard: `tests/unit/provider-onboarding-href.test.ts`. ([#6166](https://github.com/diegosouzapw/OmniRoute/pull/6166) — thanks @KooshaPari)
-
-- **fix(security):** the doubao synthetic device-id generator now derives its digits via an unbiased crypto-random draw (rejection sampling over `crypto.randomBytes()`) instead of a `% 10` reduction, closing a CodeQL `js/biased-cryptographic-random` finding.
-- **fix(agentSkills):** the GitHub-skills generator now resolves `outputDir` to an absolute path before writing, fixing a regression introduced by #6366 (relative-to-cwd base path) that could write generated skill files to the wrong directory.
-- **fix(security):** `/api/keys/{id}/devices` now checks the HTTP method before auth/validation, returning a `405` for non-GET/DELETE verbs instead of a misleading `401`/`500` (closes a `dast-smoke` QUERY-method finding).
-- **fix(quality):** clear the last 2 heavy quality-gate reds on the release tip (cycle pre-flight).
-- **fix(mitm):** the test suite and CI can never mutate the OS trust store — `OMNIROUTE_SKIP_SYSTEM_TRUST=1` is set globally for tests/CI so `installCert`/`uninstallCert`/`installTproxyCa` skip the privileged OS dispatch ([#6310](https://github.com/diegosouzapw/OmniRoute/pull/6310); full detail is under the [3.8.45] section below — this branch received it via the parallel-cycle sync-back).
-- **fix(api):** `POST /api/github-skills` now Zod-validates its request body; documented the new quality-gate env vars and pinned the merge-integrity GitHub Actions to a commit SHA.
-- **fix(skills):** generate the missing `omni-github-skills` registry entry and align the agent-skills catalog-count tests (follow-up to #6186).
-- **fix(quality):** clear the cycle's 11 net-new ESLint errors and make `validate-release-green` suppressions-aware.
-- **fix(security):** proxy-pool `random` rotation now selects via `crypto.randomInt` instead of `Math.random` — silences the post-release CodeQL `js/insecure-randomness` alerts (#698/#699) that flagged `Math.random` flowing into the selected proxy's credentials. Load-balancing selection is not a secret, but the crypto source is unbiased and clears the alert at the origin (#6365 follow-up).
-
-### 📝 Maintenance
-
-- **i18n(it):** add 118 missing Italian (`it`) translations (net-additive — no existing keys dropped, valid JSON), improving Italian UI coverage. ([#6212](https://github.com/diegosouzapw/OmniRoute/pull/6212) — thanks @serverless83)
-- **chore(providers):** remove deprecated **MiMo V2** model entries from the catalogs (xiaomi-mimo, opencode-go, zenmux-free, audio TTS) — the upstream V2 line is superseded by MiMo V2.5; drops `mimo-v2-tts`, `mimo-v2-pro`, `mimo-v2-omni`, `mimo-v2-flash`, `mimo-v2-flash-free` and realigns the provider-catalog tests. ([#6248](https://github.com/diegosouzapw/OmniRoute/pull/6248) — thanks @backryun)
-- **chore(release):** ~50 commits on this branch are v3.8.45 pre-flight/hardening fixes and CI-perf work that landed here via the parallel-cycle sync-back (`sync-next-cycle.mjs`, Hard Rule #21) **after** the `v3.8.45` git tag was cut, and are already fully documented under the **[3.8.45]** section below — listed here only so the per-cycle commit-coverage check (`npm run release:uncovered`) doesn't flag them as gaps. Provider/catalog/UX/backend fixes: #6041, #6078, #6108, #6135, #6148, #6149, #6154, #6158, #6161, #6162, #6163, #6164, #6165, #6170, #6177, #6178, #6181, #6186, #6187, #6191, #6193, #6194, #6195, #6200, #6205, #6208, #6209, #6211, #6213, #6223, #6224, #6225, #6226, #6227, #6228, #6229, #6230, #6235, #6291, #6292. CI/release-pipeline work: #6167, #6203, #6214, #6215, #6218, #6273, #6275, #6283, #6284, #6285, #6300, #6305.
-- **chore(release):** additional zero-ref release-cycle plumbing on this branch, kept out of `release:uncovered` on purpose (no `#N` in the commit subject to cite): opening the v3.8.46 cycle, opening/closing the v3.8.45 cycle, the finalized [3.8.45] CHANGELOG i18n sync-back to 42 mirrors, the v3.8.45 cognitive/cyclomatic and file-size drift rebaselines, ESLint stale-suppression pruning (4,273 → 4,233), and clearing test-masking/docs-all pre-flight reds for v3.8.45.
-
-### ⚡ Performance & Infrastructure
-
-- **perf(release-green):** the pre-flight validator (`scripts/quality/validate-release-green.mjs`) now runs its 4 slow suites (unit / vitest / integration / pack-artifact) **concurrently** via `Promise.all` — pre-flight wall time drops from ~the sum of the suites to ~the slowest one (~30min saved per round; Phase 0 was the nº1 bottleneck of the v3.8.45 release benchmark, 2h54 of 6h34 e2e). Guard: `tests/unit/validate-release-green.test.ts` ("runs the slow suites CONCURRENTLY"). ([#6319](https://github.com/diegosouzapw/OmniRoute/pull/6319))
-- **fix(ci):** `scripts/release/sync-next-cycle.mjs` — two defects found live in its first production run (v3.8.45 Phase 5): (1) the `git()` helper's default 1 MiB `maxBuffer` crashed with `ENOBUFS` on `git show origin/main:CHANGELOG.md` (the CHANGELOG alone is >1 MiB) — widened to 64 MiB; (2) the i18n resync only propagated the `[NEXT]` (TBD) section, leaving the just-shipped finalized section as "— TBD" in all 42 mirrors — it now also syncs `[prevVersion]` bounded by the heading below it (new exported pure helper `versionAfter`). Guards: +5 tests in `tests/unit/sync-next-cycle.test.ts` (8/8). ([#6327](https://github.com/diegosouzapw/OmniRoute/pull/6327))
-- **test(ci):** concurrency-sensitive flaky tests are **quarantined into a serial pass** (`tests/unit/serial/`, `--test-concurrency=1`, appended to every unit runner incl. sharded variants — the serial pass is sharded too so concurrent shard jobs never self-collide). Initial set: `glm-coding-plan-monthly-3580`, `quota-division-blocks`, `provider-health-autopilot`, `combo-health-autopilot` — the class behind the ~28min CI wedges/re-runs (two live 1h+ wedges cancelled during this PR's own validation). Discovery + TIA gates track the new glob; systemic root cause (async logger writing after teardown) tracked in [#6360](https://github.com/diegosouzapw/OmniRoute/issues/6360). Guard: `tests/unit/test-serial-quarantine.test.ts` (4). ([#6347](https://github.com/diegosouzapw/OmniRoute/pull/6347))
-
-### 🙌 Contributors
-
-Thanks to everyone whose work landed in v3.8.46:
-
-| Contributor                                                    | PRs / Issues           |
-| -------------------------------------------------------------- | ---------------------- |
-| [@2220258345](https://github.com/2220258345)                   | direct commit / report |
-| [@abdofallah](https://github.com/abdofallah)                   | direct commit / report |
-| [@adentdk](https://github.com/adentdk)                         | direct commit / report |
-| [@aleksesipenko](https://github.com/aleksesipenko)             | direct commit / report |
-| [@anki1kr](https://github.com/anki1kr)                         | direct commit / report |
-| [@anungma](https://github.com/anungma)                         | direct commit / report |
-| [@arpicato](https://github.com/arpicato)                       | direct commit / report |
-| [@backryun](https://github.com/backryun)                       | #6248                  |
-| [@binsarjr](https://github.com/binsarjr)                       | direct commit / report |
-| [@brightfiscalband](https://github.com/brightfiscalband)       | direct commit / report |
-| [@chirag127](https://github.com/chirag127)                     | #6501, #6506           |
-| [@developerjillur](https://github.com/developerjillur)         | direct commit / report |
-| [@dilneiss](https://github.com/dilneiss)                       | #6499                  |
-| [@dtybnrj](https://github.com/dtybnrj)                         | direct commit / report |
-| [@Forcerecon](https://github.com/Forcerecon)                   | direct commit / report |
-| [@hao3039032](https://github.com/hao3039032)                   | direct commit / report |
-| [@Iammilansoni](https://github.com/Iammilansoni)               | #6150, #6245           |
-| [@jmengit](https://github.com/jmengit)                         | direct commit / report |
-| [@jordansilly77-stack](https://github.com/jordansilly77-stack) | direct commit / report |
-| [@JxnLexn](https://github.com/JxnLexn)                         | direct commit / report |
-| [@KooshaPari](https://github.com/KooshaPari)                   | #6166                  |
-| [@loopyd](https://github.com/loopyd)                           | direct commit / report |
-| [@luweiCN](https://github.com/luweiCN)                         | #6221                  |
-| [@makcimbx](https://github.com/makcimbx)                       | direct commit / report |
-| [@muflifadla38](https://github.com/muflifadla38)               | direct commit / report |
-| [@newnol](https://github.com/newnol)                           | direct commit / report |
-| [@ofekbetzalel](https://github.com/ofekbetzalel)               | direct commit / report |
-| [@ohahe52-dot](https://github.com/ohahe52-dot)                 | direct commit / report |
-| [@phidinhmanh](https://github.com/phidinhmanh)                 | direct commit / report |
-| [@powellnorma](https://github.com/powellnorma)                 | direct commit / report |
-| [@qpeyba](https://github.com/qpeyba)                           | direct commit / report |
-| [@RaviTharuma](https://github.com/RaviTharuma)                 | direct commit / report |
-| [@RCrushMe](https://github.com/RCrushMe)                       | direct commit / report |
-| [@rianonehub](https://github.com/rianonehub)                   | #6134, #6204           |
-| [@serverless83](https://github.com/serverless83)               | #6212                  |
-| [@swingtempo](https://github.com/swingtempo)                   | direct commit / report |
-| [@tenshiak](https://github.com/tenshiak)                       | direct commit / report |
-| [@ThongAccount](https://github.com/ThongAccount)               | direct commit / report |
-| [@UnrealAryan](https://github.com/UnrealAryan)                 | direct commit / report |
-| [@vinayakkulkarni](https://github.com/vinayakkulkarni)         | direct commit / report |
-| [@vittoroliveira-dev](https://github.com/vittoroliveira-dev)   | #6233                  |
-| [@warelik](https://github.com/warelik)                         | direct commit / report |
-| [@xxy9468615](https://github.com/xxy9468615)                   | direct commit / report |
-| [@xz-dev](https://github.com/xz-dev)                           | direct commit / report |
-| [@yanpaing007](https://github.com/yanpaing007)                 | direct commit / report |
-| [@diegosouzapw](https://github.com/diegosouzapw)               | maintainer             |
-
----
-
-## [3.8.45] — 2026-07-06
-
-### ✨ New Features
-
-- **feat(providers):** add **Yuanbao (web)** as a cookie-session provider ([#6196](https://github.com/diegosouzapw/OmniRoute/issues/6196)) — `yuanbao-web` (Tencent Yuanbao, `yuanbao.tencent.com`) with cookie-only auth (`hy_user`/`hy_token` + public agent id), SSE→OpenAI translation incl. `reasoning_content`, exposing DeepSeek V3/R1 + Hunyuan / Hunyuan-T1. Regression guard: `tests/unit/providers-yuanbao-web.test.ts`. `together-web` was **deferred** (no verifiable web-session endpoint — needs a captured request) and `huggingchat-web` **dropped** (the existing `huggingchat` already is a web-cookie provider). (thanks @chirag127)
-- **feat(providers):** route the built-in **agentrouter** through the dynamic Claude-Code wire image ([#6056](https://github.com/diegosouzapw/OmniRoute/issues/6056)) — a small static allow-set (`CC_WIRE_IMAGE_BUILTINS` in `open-sse/services/ccWireImageBuiltins.ts`), consulted by `isClaudeCodeCompatible` / `isClaudeCodeCompatibleProvider` / `applyFingerprint`, makes agentrouter adopt the CC wire-image headers + fingerprint **while guarding the CC baseUrl/auth branches** so it keeps its own registry `baseUrl` and `x-api-key` auth. Regression guard: `tests/unit/agentrouter-cc-wire-image.test.ts` (asserts the wire image is applied AND agentrouter's baseUrl/auth are preserved). Live WAF-acceptance against agentrouter.org is a VPS validation follow-up (Hard Rule #18).
-- **feat(providers):** **bulk-add API keys for Cloudflare Workers AI** ([#6174](https://github.com/diegosouzapw/OmniRoute/issues/6174)) — `cloudflare-ai` is removed from the bulk-add exclusion list and the bulk parser gains a 3-field `name|accountId|apiKey` mode; the bulk route now builds a **per-entry** `providerSpecificData` so each key carries its own `accountId` (fixing the previous shared-object reuse), and both the create + key-validation paths receive it. Regression guard: `tests/unit/bulk-api-key-parser-cloudflare.test.ts`. (thanks @muflifadla38)
-- **feat(dashboard):** routing/settings UX clarity ([#6147](https://github.com/diegosouzapw/OmniRoute/issues/6147)) — (1) weighted combos show the **effective routing share %** next to each weight when weights don't sum to 100 (`WeightTotalBar.tsx`); (2) the status widget's user-facing **"Cloud Sync" label is renamed** to "Remote Settings Sync" (`CloudSyncStatus.tsx`; internal ids/state untouched); (3) built-in providers gain an **opt-in advanced base-URL override** (`isBaseUrlOverrideEligibleProvider`, hidden behind an "Advanced" toggle, reusing the existing `providerSpecificData.baseUrl` persistence — not globally widened). Regression guard: `tests/unit/routing-settings-ux-6147.test.ts`.
-- **feat(combo):** add an option to **disable session stickiness**, per-combo or globally — round-robin / random combos can rotate to a different connection on every request instead of pinning a whole conversation to one connection by its first-message hash. Resolution precedence per-combo `config.disableSessionStickiness` → global `settings.disableSessionStickiness` → default `false` (preserves the #3825 prompt-cache/504 fix); gates **both** stickiness call sites in `open-sse/services/combo.ts`. Exposed as a global toggle (Combo Defaults) and a per-combo Inherit/on/off control. ([#6168](https://github.com/diegosouzapw/OmniRoute/issues/6168)) Regression guard: `tests/unit/combo-disable-session-stickiness.test.ts`. (thanks @RCrushMe)
-- **feat(docker):** add the `OMNIROUTE_NO_SUDO` env flag for root-less / user-namespaced deployments — the MITM cert-trust command path (`resolveSudoSpawn` in `src/mitm/systemCommands.ts`) now strips the leading `sudo` when the flag is truthy, in addition to the existing root / sudo-missing cases, so the Proxy Agent runs without `sudo` (the operator trusts the CA manually, e.g. via `NODE_EXTRA_CA_CERTS`). Argv-array `spawn` preserved — no shell interpolation (Hard Rule #13). ([#6122](https://github.com/diegosouzapw/OmniRoute/issues/6122)) Regression guard: `tests/unit/mitm-systemCommands-no-sudo.test.ts`. (thanks @powellnorma)
-- **feat(providers):** add **Requesty** as an OpenAI-compatible gateway provider (BYOK, base `https://router.requesty.ai/v1`, ~200 free requests/day) — wired through the shared OpenAI-compatible registry with full model passthrough (`open-sse/config/providers/registry/requesty/`, `src/shared/constants/providers/apikey/gateways.ts`). ([#6120](https://github.com/diegosouzapw/OmniRoute/issues/6120)) Regression guard: `tests/unit/requesty-provider.test.ts`. (thanks @chirag127)
-- **feat(dashboard):** add **configured-only / available-only filters** to the Free Provider Rankings page ([#6150](https://github.com/diegosouzapw/OmniRoute/issues/6150)) — hide providers you haven't configured, or whose connections are all rate-limited / out of quota, via server-side query params (`?configuredOnly` / `?availableOnly` on `GET /api/free-provider-rankings`) backed by a testable lib helper reusing the in-process connection state (no Redis). Both filters default off, so the default view is unchanged; this supersedes the earlier client-side "Configured Only" toggle (#6245) with an available-only dimension and unit-tested logic. Regression guard: `tests/unit/freeProviderRankings-filters.test.ts`.
-- **feat(rankings):** add a **'Configured Only'** filter to the Free Provider Rankings page, so the table can be narrowed to just the providers you have configured connections for (with an empty-state hint when none are configured). New `en.json` keys and a pure filter helper covered by `tests/unit/free-provider-rankings-configured-filter.test.ts`. ([#6245](https://github.com/diegosouzapw/OmniRoute/pull/6245), closes [#6150](https://github.com/diegosouzapw/OmniRoute/issues/6150) — thanks @Iammilansoni)
-
-### 🔧 Bug Fixes
-
-- **fix(mitm):** the test suite and CI can never mutate the OS trust store again — `OMNIROUTE_SKIP_SYSTEM_TRUST=1` (set by the global test setup and all CI workflows) makes `installCert`/`uninstallCert`/`installTproxyCa` skip the privileged OS dispatch while preserving the #4546 environment-skip contract. Root cause of the self-hosted runner incident: a cert-flow integration test installed a 105-byte fake PEM into `/usr/local/share/ca-certificates`, breaking ALL system TLS on the VM. Regression guard: `tests/unit/system-trust-test-guard.test.ts`. ([#6310](https://github.com/diegosouzapw/OmniRoute/pull/6310))
-- **fix(security):** `/api/keys/{id}/devices` answers a clean method-first **405** for undocumented HTTP methods (e.g. the new `QUERY`) via a dedicated `http-method-guard` rule — the auth layer was answering 401 first, failing schemathesis's unsupported-methods check. Same pattern as the v3.8.44 TRACE fix. Regression guard: `tests/unit/dast-method-not-allowed.test.ts`.
-- **fix(combo):** the #6216 empty-stream failover is restricted to **truly empty bodies** (zero bytes — the Gemini HTTP-200-empty case), restoring the #3399/#3685 pass-through contracts for `[DONE]`-terminated empty streams and incomplete Claude lifecycles. New guard: `#5976 truly EMPTY streaming body → invalid for combo failover` (87/87 across both suites).
-- **fix(combo):** 5 streaming-path fixes — locked-stream 500, error-frame-only-if-no-content, Gemini `MALFORMED_RESPONSE`→content_filter failover, correlationId substring search, per-model-500 lockout skip + request-logger UI detail. Maintainer follow-up: `releaseQualityClone` cancels the abandoned quality-check tee branch (per-request memory) + regression test. ([#6216](https://github.com/diegosouzapw/OmniRoute/pull/6216) — thanks @hartmark)
-- **fix(skills):** generate the missing `omni-github-skills` registry entry (the #6186 catalog addition never ran the generator — 8 integration assertions split between old/new counts) and align the agent-skills catalog counts across integration + unit suites (43 = 23 API + 20 CLI; 44 with config).
-- **fix(a2a):** finish the #6186 catalog-count update — `listCapabilities` metadata reported `coverage.api.total: 22` (type literal + value) and `SkillCoverageSchema` pinned `z.literal(22)`, so the schema would REJECT the correct runtime value with 23 API skills. All three aligned to 23.
-- **fix(github-skills):** add a missing import, unit tests and a settings JSON-parse fix for the GitHub agent-skill discovery/import flow. ([#6186](https://github.com/diegosouzapw/OmniRoute/pull/6186) — thanks @Moseyuh333)
-- **fix(api):** `POST /api/github-skills` validates its body with a Zod schema (`validateBody`) instead of blind `request.json()` destructuring — a non-array `targets` would crash `.map`. Regression guard: `tests/unit/github-skills-route-validation.test.ts`.
-- **fix(docker):** add `id=` to the BuildKit cache mounts so strict builders (e.g. buildkitd with strict frontend parsing) accept the Dockerfile. ([#6291](https://github.com/diegosouzapw/OmniRoute/pull/6291) — thanks @karimalsalah)
-- **fix(oauth):** register `zed` in the OAuth `PROVIDERS` map (fixes "Unknown provider" on the Zed sign-in flow) ([#6078](https://github.com/diegosouzapw/OmniRoute/pull/6078) — thanks @anki1kr), and align `zed` in `OAUTH_PROVIDER_IDS` + the config enum after the merge.
-- **fix(doubao-web):** switch the Doubao web provider to the Dola global endpoint. ([#6235](https://github.com/diegosouzapw/OmniRoute/pull/6235) — thanks @backryun)
-- **fix(doctor):** resolve two false-positive WARNs in the doctor diagnostics ([#6163](https://github.com/diegosouzapw/OmniRoute/pull/6163), closes [#6162](https://github.com/diegosouzapw/OmniRoute/issues/6162) — thanks @arssnndr)
-- **fix(providers):** refresh the GitHub Copilot model catalog to the current upstream set. ([#6154](https://github.com/diegosouzapw/OmniRoute/pull/6154) — thanks @backryun)
-- **fix(providers):** correct the Kiro model catalog to real upstream ids — fabricated `claude-opus-4.7`/`claude-sonnet-4.6` entries removed, real `claude-sonnet-5`/`claude-sonnet-4.5`/`claude-haiku-4.5` kept. ([#6170](https://github.com/diegosouzapw/OmniRoute/pull/6170))
-- **feat(sse):** surface Kiro adaptive-thinking reasoning frames as `reasoning_content` in the OpenAI-shaped stream. ([#6213](https://github.com/diegosouzapw/OmniRoute/pull/6213) — thanks @VXNCXNX)
-- **fix(cli):** use `OMNIROUTE_SERVER_HOST` instead of the POSIX auto-set `HOSTNAME` for the bind address (fixes wrong bind on POSIX shells that export HOSTNAME). ([#6195](https://github.com/diegosouzapw/OmniRoute/pull/6195), closes [#6194](https://github.com/diegosouzapw/OmniRoute/issues/6194) — thanks @Theadd)
-- **feat(provider):** add Claude 5 Sonnet to the Claude Web provider catalog. ([#6209](https://github.com/diegosouzapw/OmniRoute/pull/6209), closes [#6200](https://github.com/diegosouzapw/OmniRoute/issues/6200) — thanks @Iammilansoni)
-- **fix(providers):** add `nvidia` to `PROVIDER_TOOL_LIMITS` (1536) to prevent silent tool-list truncation. ([#6177](https://github.com/diegosouzapw/OmniRoute/pull/6177) — thanks @LuisAlejandroVega)
-- **fix(translator):** strip the `reasoning` param for nvidia `z-ai/glm-5.2` (upstream 400s on it). ([#6181](https://github.com/diegosouzapw/OmniRoute/pull/6181) — thanks @kanztu)
-- **fix(dashboard):** providers page gains a data-timeout guard and the live-WS standalone wiring (no more indefinite spinner when the data fetch stalls). ([#6211](https://github.com/diegosouzapw/OmniRoute/pull/6211))
-- **fix(sse):** surface the ChatGPT-web image silent-drop as an accurate error instead of an empty success. ([#6208](https://github.com/diegosouzapw/OmniRoute/pull/6208))
-- **fix(cline):** force upstream streaming for Cline/ClinePass (streaming-only API) — non-stream client requests are served from the buffered SSE. ([#6165](https://github.com/diegosouzapw/OmniRoute/pull/6165))
-- **fix(dashboard):** remove the always-on Auto-Routing (combo) banner from the home page — it did not reflect live routing state and reappeared on every fresh browser. Replacement guard: `tests/unit/home-no-autorouting-banner.test.ts`. ([#6164](https://github.com/diegosouzapw/OmniRoute/pull/6164))
-- **fix(dashboard):** stop a model-test error from freezing the page (React #31 object-as-child toast) — errors go through `extractApiErrorMessage`. ([#6161](https://github.com/diegosouzapw/OmniRoute/pull/6161))
-- **fix(oauth):** extract the keychain-import-only guard to its own module, restoring the oauth file-size freeze. ([#6158](https://github.com/diegosouzapw/OmniRoute/pull/6158))
-
-- **fix(sse):** strip zero-width markers from streamed **tool-call arguments** — a follow-up to [#5857](https://github.com/diegosouzapw/OmniRoute/pull/5857). That PR removed injected zero-width joiners (U+200D) from streamed assistant text/reasoning but deliberately left tool-call argument JSON byte-exact. The request-side obfuscation (`open-sse/services/claudeCodeObfuscation.ts`) injects ZWJ into agent words — including the temp path inside the Bash tool description — and Claude models copy that verbatim into generated commands, which are delivered as tool-call arguments rather than assistant text. As a result the ZWJ survived and corrupted code blocks (e.g. a temp path rendered with an invisible joiner). Now `open-sse/handlers/responseSanitizer.ts` strips zero-width code points from tool-call argument strings at every emit site (OpenAI non-stream/stream chat `tool_calls` + legacy `function_call`, native Responses `function_call` items, the OpenAI→Responses conversion, and the native Responses streaming `response.function_call_arguments.delta/.done` events). Only zero-width code points are removed; JSON structure and all other bytes stay identical (no parse/restringify), so normal arguments remain byte-exact. Regression guard: 6 new cases in `tests/unit/response-sanitizer.test.ts` (suite 50/50).
-
-- **fix(nodejs):** the default app log path now resolves under `DATA_DIR` (`~/.omniroute/logs/application/app.log`) instead of `process.cwd()` ([#6197](https://github.com/diegosouzapw/OmniRoute/issues/6197)) — the globally-installed CLI runs from an arbitrary working directory, so anchoring the default to cwd made file logging silently write to (or no-op under) an unrelated directory, contradicting the documented `.env.example` default. `getAppLogFilePath()` now computes the default lazily via the pure `resolveDataDir()` resolver (honours a per-process `DATA_DIR`, no directory-creation side effect); an explicit `APP_LOG_FILE_PATH` still wins. Regression guard: `tests/unit/logenv-datadir-path-6197.test.ts` (3). (root cause independently diagnosed by @subhansh-dev in [#6298](https://github.com/diegosouzapw/OmniRoute/pull/6298) — thanks!)
-
-- **fix(docker):** AgentBridge/`startMitm` no longer aborts in containers/headless when the Antigravity-default DNS step can't write `/etc/hosts` ([#6127](https://github.com/diegosouzapw/OmniRoute/issues/6127)), and the privileged command's stderr now reaches `app.log` instead of only a bare exit code hitting the toast ([#6198](https://github.com/diegosouzapw/OmniRoute/issues/6198)). The default DNS step (`addDNSEntry`) was called unguarded while cert install and the two sibling DNS steps were each best-effort — in the runtime Docker image (`USER node`, no `sudo`, read-only `/etc/hosts`) it threw `Command failed with code 1` out of `startMitmInternal` and killed the whole start, discarding the stderr. The three DNS steps are extracted into a best-effort `provisionDnsEntries()` where each failure is logged with the full `err` (stderr included, folded in by `systemCommands.ts`) and never aborts the start. Regression guard: `tests/unit/mitm-dns-graceful-degrade-6127.test.ts` (4).
-
-- **fix(providers):** copilot-m365-web now supports the M365 Education "Starter / OfficeWebIncludedCopilot" tier and no longer returns an empty `content:null` stream ([#6210](https://github.com/diegosouzapw/OmniRoute/issues/6210)). Two gaps: (1) `buildWsUrl()` hardcoded the individual-consumer scenario (`OfficeWebPaidConsumerCopilot`, `isEdu=false`) — the EDU tier is now opt-in via `providerSpecificData.tier="edu"`, emitting `scenario=OfficeWebIncludedCopilot`/`isEdu=true` (the individual path is unchanged); (2) the EDU/GPT-5.5 path streams deltas via `arguments[0].writeAtCursor` (incremental) instead of only `messages[].text` (accumulated snapshots), which the parser dropped — a new `accumulateBotContent()` folds both formats, with `type:2 item.result.message` as a last-resort fallback. Regression guard: `tests/unit/copilot-m365-edu-writeatcursor-6210.test.ts` (10). (thanks @qpeyba)
-
-- **fix(providers):** GitLab Duo executor now feeds tool results back into the prompt instead of looping ([#6220](https://github.com/diegosouzapw/OmniRoute/issues/6220)) — `buildPrompt()` branched only on `system`/`user` and took `userParts.at(-1)`, silently dropping the `assistant{tool_calls}` + `tool{result}` turns the client appended, so the reconstructed prompt was byte-identical to turn 1 and the model re-emitted the same `<tool>` call forever. When a tool exchange is present the full conversation is now serialized, folding each tool result back keyed by its `tool_call_id`; simple conversations keep the legacy shape. Complements the tool_call emission from [#6051](https://github.com/diegosouzapw/OmniRoute/issues/6051) (the `kilo-duplicate` label was a false positive — different, sequential defect). Regression guard: `tests/unit/gitlab-tool-result-feedback-6220.test.ts` (4).
-
-- **fix(providers):** opencode-go/opencode-zen can now synthesize the OpenCode CLI identity headers Cloudflare requires on VPS egress ([#5997](https://github.com/diegosouzapw/OmniRoute/issues/5997)) — on a datacenter VPS, `opencode.ai/zen/go/v1/chat/completions` 403s (HTML challenge) requests lacking CLI identity, while the reporter's control curl proved that `User-Agent: opencode-cli/1.0.0` + `x-opencode-client: cli` + `x-opencode-project: default` + fresh request/session UUIDs succeed. Opt-in via `OPENCODE_SYNTHESIZE_CLI_HEADERS=true` (values overridable via `OPENCODE_GO_USER_AGENT`/`OPENCODE_USER_AGENT`/`OPENCODE_CLIENT`/`OPENCODE_PROJECT`); it fills only headers the client did not already send. Kept **off by default** — the forward-only path is deliberate (fabricating a wrong value risks upstream rejection; a prior dedup regressed with `opencode/local`), so this replaces the fragile local header-injection shim without changing default behavior. Regression guard: `tests/unit/opencode-cli-headers-synthesis-5997.test.ts` (6). (thanks @aleksesipenko)
-- fix(resilience): sticky session affinity now evicts and fails over to another account when the pinned account is exhausted/unavailable (#6219)
-
-- fix(sse): Responses API passthrough now drops internal commentary-phase output before forwarding to clients (gated by RESPONSES_PASSTHROUGH_DROP_COMMENTARY, default on) (#6199)
-
-- **fix(proxy):** stop the v3.8.44 proxy regression that leaked the real IP and disabled healthy proxies ([#6246](https://github.com/diegosouzapw/OmniRoute/issues/6246)). Two coupled defects from the new health scheduler: (1) **IP leak** — when a proxy assigned to a connection was marked `inactive`, resolution fell through to a **direct** egress instead of blocking, exposing the operator's real IP; (2) **over-deactivation** — the sweep flipped a proxy to `inactive` on the **first** failed probe and counted our own 5s timeout / a probe-target `5xx` as the proxy's fault, so healthy paid proxies vanished from egress selection ("my proxies are not being used anymore"). Fix: the sweep decision is extracted into a pure, network-free `decideProxyHealthAction` (`src/lib/proxyHealth/decision.ts`) — by default the health check now **only counts/logs and never downgrades status** (a proxy is downgraded/removed only with `PROXY_AUTO_REMOVE=true`, after `PROXY_AUTO_REMOVE_AFTER` **consecutive** conclusive failures); probes are classified tri-state so an inconclusive result (our timeout, or a `5xx` from the probe target) never penalizes the proxy, and the probe timeout is raised 5s→15s. Separately, `safeResolveProxy` now **fails closed** via the existing policy: a connection whose assigned proxy is dead is blocked instead of leaking direct (`hasBlockingProxyAssignment`), honoring the explicit `proxy off` toggles and the `PROXY_FAIL_OPEN=true` opt-out. Existing proxies stuck `inactive` by the old behavior need a one-time manual re-activate (the operator owns proxy status). Regression guards: `tests/unit/proxy-health-decide-action-6246.test.ts`, `tests/unit/proxy-assigned-unavailable-6246.test.ts`.
-
-- **fix(proxy):** make "Test All" read-only and add bulk enable/disable ([#6246](https://github.com/diegosouzapw/OmniRoute/issues/6246)). Complements the core fail-closed / scheduler fix (#6296) with the two remaining reporter asks. (1) The **"Test All" button** (`POST /api/settings/proxies/auto-test`) used to flip a proxy to `inactive` on a failed reachability probe; since the egress selector excludes `inactive` proxies, a flaky probe (an unreachable `httpbin.org`, a proxy that blocks `HEAD`, or a slow paid proxy) silently disabled every proxy that failed — "Test All" is now **read-only by default** (only the operator sets a proxy active/inactive; opt back into the legacy test-and-set with `PROXY_HEALTH_AUTO_DEACTIVATE=true`). (2) Adds a **bulk enable/disable** proxies endpoint + toolbar action (`POST /api/settings/proxies/batch-activate`) so an operator can re-activate proxies in one click. Regression guard: `tests/unit/proxy-health-6246.test.ts`. (thanks @tenshiak)
-
-- **chatcore (tools): stop the default 128-tool cap from silently dropping opencode's `task`/MCP tools.** opencode (used as an MCP/agent host) sends a large tool list; when it exceeds the speculative `MAX_TOOLS_LIMIT` (128) default, `truncateToolList` did a blind `tools.slice(0, 128)`, dropping every tool past index 128 — including opencode's built-in `task` tool (subagent launch) and many MCP tools, so models routed through OmniRoute could no longer spawn subagents or reach part of their tools. The cap exists to avoid upstream `400`s for providers with real hard limits (e.g. grok-cli 200), so it is kept for those: detection of the opencode client (`isOpencodeClient` — any `x-opencode-*` header, or `opencode` in the user-agent) now only bypasses the **speculative 128 default**, never a known provider ceiling. Precedence is explicit — a proactive/detected provider limit always truncates (even for opencode); otherwise opencode forwards its full tool list; otherwise the unchanged 128 default applies to every other client. Refactors `getEffectiveToolLimit` into `getKnownToolLimit(provider) ?? DEFAULT_LIMIT` (byte-identical for existing callers) and fixes a cosmetic debug-log that reported the truncated count instead of the original. Regression guard: `tests/unit/tool-limit-detector.test.ts`. ([#6193](https://github.com/diegosouzapw/OmniRoute/pull/6193) — thanks @DKotsyuba)
-
-- **fix(mitm):** the macOS MITM-cert install check now matches the system keychain again. `security find-certificate -a -Z` prints the SHA-1 as a colon-less hex string, but the installed-check compared it against `getCertFingerprint()`'s colon-separated form, so the substring match never hit — the cert was reported as not-installed and re-prompted for the sudo install on every run. Fingerprints are now normalized (colons stripped, upper-cased) on both sides via the extracted `macCertOutputHasFingerprint` helper. Regression guard: `tests/unit/mitm-cert-mac-fingerprint.test.ts`. ([#6204](https://github.com/diegosouzapw/OmniRoute/pull/6204), closes [#6134](https://github.com/diegosouzapw/OmniRoute/issues/6134) — thanks @rianonehub)
-
-- **fix(api):** `/v1/messages/count_tokens` now counts `tool_use`, `tool_result` and `thinking` content blocks (and array-form `system` prompts) in the local-estimation path, instead of only `text`. Real agentic conversations keep ~95% of their tokens inside tool results; the previous estimate returned near-zero for them, which silently broke Claude Code's auto-compaction (context grew past the window with no compaction until the upstream API rejected the request). The real provider-side count path is unchanged. Regression guard: `tests/unit/messages-count-tokens-route.test.ts`. ([#6221](https://github.com/diegosouzapw/OmniRoute/pull/6221) — thanks @luweiCN)
-
-- **fix(antigravity):** strip a trailing assistant prefill turn for Vertex Claude models to avoid upstream 400s ([#6114](https://github.com/diegosouzapw/OmniRoute/pull/6114)). Regression guard: `tests/unit/antigravity-claude-prefill-strip.test.ts`. (thanks @anki1kr)
-
-- **fix(security):** the mutable cloud-agent routes (`/api/cloud/credentials/update`, `/api/cloud/models/alias`) now require management auth instead of being treated as public. They were classified as public API routes, so a request without management credentials could update stored cloud-agent credentials and model aliases. They are removed from the public-route set, classified as management routes in the authz pipeline, and gated by `requireManagementAuth`; cloud **read**/auth routes stay public. Regression guards: `tests/unit/cloud-write-auth.test.ts`, `tests/unit/authz/classify.test.ts`, `tests/unit/public-api-routes.test.ts`. ([#6233](https://github.com/diegosouzapw/OmniRoute/pull/6233) — thanks @vittoroliveira-dev)
-
-- **refactor(dashboard):** extract the onboarding-wizard "Open provider details" link target into a pure, unit-tested `buildProviderDetailsHref(connection)` helper. The wizard already routes by `connection.id` (the node UUID) rather than the provider category slug (#6144/#6145); this hardens that behavior behind a tested helper that guards a missing id/connection. Regression guard: `tests/unit/provider-onboarding-href.test.ts`. ([#6166](https://github.com/diegosouzapw/OmniRoute/pull/6166) — thanks @KooshaPari)
-- **fix(api):** relay worker now binds the SSRF guard to a stable `const` name so minified standalone (Docker) builds resolve it ([#6149](https://github.com/diegosouzapw/OmniRoute/issues/6149)) — the Vercel/Deno relay generators embedded the shared `resolveRelayTarget` guard as a bare `${fn.toString()}` declaration while the worker body called the hardcoded literal name; SWC minification mangled the source function's name, so the deployed worker defined `<mangled>` but still called `resolveRelayTarget` → `ReferenceError`. Both templates now emit `const resolveRelayTarget = ${fn.toString()};` (the const name is a template literal, immune to minification). Regression guard: `tests/unit/relay-minified-fn-6149.test.ts` (4). (thanks @SeaXen)
-- **fix(providers):** refresh the stale NVIDIA NIM model registry — drop EOL `z-ai/glm-5.1`, add `z-ai/glm-5.2` and `nvidia/nemotron-3-ultra-550b-a55b` ([#6108](https://github.com/diegosouzapw/OmniRoute/issues/6108)). Regression guard: `tests/unit/nvidia-nim-registry-6108.test.ts`. (thanks @andrea-kingautomation)
-- **fix(backend):** GPT-family (codex) models now report a distinct `max_input_tokens` (272000) below their 400K `context_length` via an optional `maxInputTokens` on `RegistryModel`, so coding agents auto-compact correctly instead of overflowing the real input cap ([#6191](https://github.com/diegosouzapw/OmniRoute/issues/6191)). Regression guard: `tests/unit/gpt-max-input-tokens-6191.test.ts`. (thanks @luweiCN)
-- **fix(backend):** call logs now record a **reasoning source/char-count** (migration 116, `reasoning_source`/`reasoning_chars`) for models that emit `reasoning_content`/`<think>` but report zero reasoning tokens in usage, so `tokens_reasoning` no longer silently under-represents reasoning — cost math is unchanged (the priced `tokens_reasoning` stays usage-derived) ([#6187](https://github.com/diegosouzapw/OmniRoute/issues/6187)). Regression guard: `tests/unit/reasoning-token-source-6187.test.ts`. (thanks @andrea-kingautomation)
-- **fix(auth):** a stale/changed `STORAGE_ENCRYPTION_KEY` now surfaces as a clear **424 `storage_encryption_stale`** ("re-enter the API key") instead of a misleading "Auth failed: 401" — the connection's ciphertext failed to decrypt and was coerced to an empty Bearer, hiding the real cause ([#6148](https://github.com/diegosouzapw/OmniRoute/issues/6148)). Regression guard: `tests/unit/decrypt-stale-key-hint-6148.test.ts`. (thanks @chirag127)
-- **fix(backend):** memory injection now keeps the injected system message **first** for providers that require it (via a `PROVIDERS_SYSTEM_MUST_BE_FIRST` capability), instead of the cache-safe mid-array splice that made strict providers reject the request with a 400 ([#6135](https://github.com/diegosouzapw/OmniRoute/issues/6135)). Regression guard: `tests/unit/memory-system-first-6135.test.ts`.
-- **fix(services):** 9Router embed panel no longer 404s (optional catch-all route) and the supervisor probes the port before spawning to avoid raw EADDRINUSE ([#6205](https://github.com/diegosouzapw/OmniRoute/issues/6205)). Regression guards: `tests/unit/ninerouter-embed-port-6205.test.ts`, `tests/unit/services/ServiceSupervisor.test.ts`. (thanks @jonlwheat2-gif)
-- fix(mcp): forward the MCP request `extra` context through static tool loops so stdio callers keep their scope/identity ([#6178](https://github.com/diegosouzapw/OmniRoute/issues/6178))
-
-### ⚡ Performance & Infrastructure
-
-- **perf(test):** test-suite loader quick wins ([#6214](https://github.com/diegosouzapw/OmniRoute/pull/6214)) — the 19 test scripts switch `--import tsx` → `--import tsx/esm` (the repo is pure ESM; the unused CJS hook cost ~1.3s per test process × 2,462 processes — CI fast-path unit shards dropped 14.8→7.5 min, −49%), tsx bumped to ^4.23.0 (tsx#809 startup-regression fix), **37 orphan `.test.mjs` files (224 cases) recovered** into the canonical glob (they matched no runner and never ran in any CI job; `check:test-discovery` now scans `.mjs` too), and ci.yml/quality.yml unit jobs now call the canonical npm script `test:unit:ci:shard` (single source of truth — closes two silent drifts: missing `setupPolyfill` import in CI and `memory/`+`usage/` dirs absent from the fast-path glob). `tests/unit/dashboard/**` keeps the full tsx hook in its own invocation (`@lobehub/icons` es/ build internally `require()`s ESM-syntax files).
-- **ci:** heavy-pipeline dedup ([#6215](https://github.com/diegosouzapw/OmniRoute/pull/6215)) — the release-PR pipeline ran the unit suite 4× per sync (95 jobs, 208 machine-min; the v3.8.44 cycle fired 123 such runs, 88 cancelled). Now: Node 24/26 compat matrices move to a daily `nightly-compat.yml` (−28%/run; resolves the active release branch, opens a tracking issue on failure), coverage is collected inside the unit shards themselves via c8/`NODE_V8_COVERAGE` (−18%/run; the Coverage Shard ×8 matrix is gone — nodejs/node's own CI pattern), the ~40-job per-language i18n matrix becomes 1 job (the account has 20 concurrent-job slots total), and heavy jobs skip **draft** PRs — paired with `/generate-release` now opening the living release PR as draft (flipped ready at the new Phase 0a.0a), killing the per-merge churn for the whole cycle. Validated by a full `workflow_dispatch` of the new pipeline: 35 jobs, 0 failures, 23 min, merged coverage 80.16% (> ratchet baseline).
-- **feat(quality):** no-new-warnings per PR ([#6218](https://github.com/diegosouzapw/OmniRoute/pull/6218)) — native ESLint bulk suppressions (≥9.24) freeze the pre-existing debt (476 files / 4,273 violations in `config/quality/eslint-suppressions.json`); `npm run lint`, lint-staged (pre-commit) and a new fork-aware `lint-guard` job in quality.yml all run suppressions-aware, so a NEW warning goes red in the PR that introduces it instead of accruing invisibly (+41/+88 per cycle) and being blind-rebaselined at release. 3 warn rules promoted to error in `src/**` (`react-hooks/exhaustive-deps`, `@next/next/no-img-element`, `import/no-anonymous-default-export`); `collect-metrics` measures under the frozen baseline (ratchet metric = net-NEW debt; baseline tightened 4,279→0 in-PR per require-tighten); fork PRs run report-only (contributors are never blocked — the maintainer campaigns fix via co-authorship). Baseline stock shrinks via `--prune-suppressions` at release reconciliation.
-- **ci:** test jobs no longer wait on the Build gate ([#6275](https://github.com/diegosouzapw/OmniRoute/pull/6275)) — `test-unit`×8, `vitest`, `integration`×2 and `security` declared `needs: build` but never download the `next-build` artifact; they now start at minute 0 (`needs: changes`, same `if` as Build), cutting ~15–20 min of wall-clock per heavy run. `e2e`/`package-artifact`/`electron-smoke` keep `needs: build` (they consume the artifact for real).
-- **ci(build):** the ci.yml Build job compiles Next.js with **Turbopack** (`OMNIROUTE_USE_TURBOPACK=1`) ([#6273](https://github.com/diegosouzapw/OmniRoute/pull/6273)) — Build job 20 min → **6 min 59 s (~2.9×)** on ubuntu-latest; the webpack `actions/cache` step is removed. Validated end-to-end pre-merge via `gh workflow run ci.yml --ref <branch>`.
-- **feat(build):** **Turbopack becomes the default bundler** for `next build` and `next dev` ([#6283](https://github.com/diegosouzapw/OmniRoute/pull/6283)) — `build-next-isolated.mjs`, `run-next.mjs` and the playwright-runner default to Turbopack; `OMNIROUTE_USE_TURBOPACK=0` is the explicit webpack escape hatch. `nightly-compat.yml`/`npm-publish.yml` inherit the default. Regression guard: `tests/unit/build-bundler-default-turbopack.test.ts`.
-- **feat(docker):** the Docker image builds with Turbopack (`ENV OMNIROUTE_USE_TURBOPACK=1`) ([#6285](https://github.com/diegosouzapw/OmniRoute/pull/6285)) — the v3.8.27 ImportTracer panic ("unreachable: there must be a path to a root") does **not** reproduce on Next 16.2.9: amd64 (659 s) and arm64 (qemu) build clean, 0 panics, smoke health 200.
-- **ci:** opt-in **self-hosted VPS runners for the release window** ([#6284](https://github.com/diegosouzapw/OmniRoute/pull/6284)) — `scripts/vps/release-runner-up.sh`/`down.sh` manage the runner VM, and `build`/`test-unit`/`vitest` pick a dynamic `runs-on` gated by `vars.USE_VPS_RUNNER == 'true'` **and** own-origin (fork PRs never reach self-hosted runners). Wired into `/generate-release` (VM up at Phase 1, mandatory down at Phase 3).
-
-### 📝 Maintenance
-
-- **quality(release-green):** full pre-flight hardening for this release — the cycle's 11 net-new ESLint errors typed/fixed and `validate-release-green` made suppressions-aware with per-gate logs (`_artifacts/release-green/`) and a `--hermetic` mode; test-masking allowlist entries for the cycle's verified-legitimate assert reductions; stale ESLint suppressions pruned (4,273 → 4,233); the 7 net-new `as any` casts from #6292 typed; `githubSkillTools` MCP errors routed through `sanitizeErrorMessage()`; `combo-provider-cooldown-sibling` added to the Stryker tap set; executors/env docs count fixes.
-- **ci(quality):** merge-integrity fast-gates per PR — `check:changelog-integrity` (no base CHANGELOG bullet may vanish in the merge result — the auto-resolve "CHANGELOG-eat" pattern) and `check:agent-skills-sync` (generated SKILL.md ≡ catalog), blocking for own-origin branches and report-only for forks (Princípio Zero). ([#6300](https://github.com/diegosouzapw/OmniRoute/pull/6300))
-- **ci(vps):** hermetic `nightly-release-green` pre-flight on the dedicated `omni-release` self-hosted runner (dynamic `runs-on`, clean env); e2e/integration/electron stay on hosted runners (per-VM port collision + concurrent artifact-download limits documented in the PR). ([#6305](https://github.com/diegosouzapw/OmniRoute/pull/6305))
-- **chore(quality):** v3.8.45 cycle-close drift rebaselines — file-size (13 files grown by merged cycle PRs), cognitive 867→877, cyclomatic 2028→2035, kiro-translator test debt from #6213; all with dated justification keys.
-- **docs(architecture):** sync stale DB-layer counts (45+/55 → 95+/110+) in REPOSITORY_MAP, the db-schema diagram and llm.txt (+42 i18n mirrors). ([#6167](https://github.com/diegosouzapw/OmniRoute/pull/6167))
-- **chore(release):** parallel-cycle flow — `sync-next-cycle.mjs` + Hard Rule #21 semantics ([#6203](https://github.com/diegosouzapw/OmniRoute/pull/6203)); v3.8.45 development cycle opened.
-- **i18n(it):** add 118 missing Italian (`it`) translations (net-additive — no existing keys dropped, valid JSON), improving Italian UI coverage. ([#6212](https://github.com/diegosouzapw/OmniRoute/pull/6212) — thanks @serverless83)
-- **chore(providers):** remove deprecated **MiMo V2** model entries from the catalogs (xiaomi-mimo, opencode-go, zenmux-free, audio TTS) — the upstream V2 line is superseded by MiMo V2.5; drops `mimo-v2-tts`, `mimo-v2-pro`, `mimo-v2-omni`, `mimo-v2-flash`, `mimo-v2-flash-free` and realigns the provider-catalog tests. ([#6248](https://github.com/diegosouzapw/OmniRoute/pull/6248) — thanks @backryun)
-
-### 🙌 Contributors
-
-Thanks to everyone whose work landed in v3.8.45:
-
-| Contributor                                                        | PRs / Issues                        |
-| ------------------------------------------------------------------ | ----------------------------------- |
-| [@aleksesipenko](https://github.com/aleksesipenko)                 | direct commit / report              |
-| [@andrea-kingautomation](https://github.com/andrea-kingautomation) | direct commit / report              |
-| [@anki1kr](https://github.com/anki1kr)                             | #6078                               |
-| [@arssnndr](https://github.com/arssnndr)                           | #6162, #6163                        |
-| [@backryun](https://github.com/backryun)                           | #6154, #6235, #6248                 |
-| [@chirag127](https://github.com/chirag127)                         | direct commit / report              |
-| [@DKotsyuba](https://github.com/DKotsyuba)                         | #6193                               |
-| [@hartmark](https://github.com/hartmark)                           | #6216                               |
-| [@Iammilansoni](https://github.com/Iammilansoni)                   | #6150, #6200, #6209, #6245          |
-| [@jonlwheat2-gif](https://github.com/jonlwheat2-gif)               | direct commit / report              |
-| [@kanztu](https://github.com/kanztu)                               | #6181                               |
-| [@karimalsalah](https://github.com/karimalsalah)                   | #6291                               |
-| [@KooshaPari](https://github.com/KooshaPari)                       | #6166                               |
-| [@LuisAlejandroVega](https://github.com/LuisAlejandroVega)         | #6177                               |
-| [@luweiCN](https://github.com/luweiCN)                             | #6221                               |
-| [@Moseyuh333](https://github.com/Moseyuh333)                       | #6186                               |
-| [@muflifadla38](https://github.com/muflifadla38)                   | direct commit / report              |
-| [@powellnorma](https://github.com/powellnorma)                     | direct commit / report              |
-| [@qpeyba](https://github.com/qpeyba)                               | direct commit / report              |
-| [@RCrushMe](https://github.com/RCrushMe)                           | direct commit / report              |
-| [@rianonehub](https://github.com/rianonehub)                       | #6134, #6204                        |
-| [@SeaXen](https://github.com/SeaXen)                               | direct commit / report              |
-| [@serverless83](https://github.com/serverless83)                   | #6212                               |
-| [@subhansh-dev](https://github.com/subhansh-dev)                   | #6298 (diagnosis, landed via #6234) |
-| [@tenshiak](https://github.com/tenshiak)                           | direct commit / report              |
-| [@Theadd](https://github.com/Theadd)                               | #6194, #6195                        |
-| [@vittoroliveira-dev](https://github.com/vittoroliveira-dev)       | #6233                               |
-| [@VXNCXNX](https://github.com/VXNCXNX)                             | #6213                               |
-| [@diegosouzapw](https://github.com/diegosouzapw)                   | maintainer                          |
-
----
-
-## [3.8.44] — TBD
-
-### ✨ New Features
-
-- **feat(resilience):** throttle upstream quota fetches on the per-request preflight path ([#6009](https://github.com/diegosouzapw/OmniRoute/issues/6009)) — a new global min-interval gate (`open-sse/services/quotaFetchThrottle.ts`) spaces the actual network calls made by the Codex quota fetcher so that many accounts on one IP no longer fetch quota in the same second (which, per `router-for-me/CLIProxyAPI#2385`, can get a Codex OAuth token revoked). Complements the existing bulk-sync spacing (`PROVIDER_LIMITS_SYNC_SPACING_MS`) which already serialized the periodic provider-limits sync — this covers the concurrent combo/preflight path it didn't. Cache hits are never delayed; fail-open (only ever awaits a timer). Configurable via `OMNIROUTE_QUOTA_FETCH_MIN_INTERVAL_MS` (default 250ms, clamped 0..5000; `0` disables). Regression guard: `tests/unit/quota-fetch-throttle-6009.test.ts` (5). (thanks @powellnorma)
-- **feat(autoCombo):** add **per-request Auto-Combo controls** via two headers ([#6024](https://github.com/diegosouzapw/OmniRoute/issues/6024) / [#6025](https://github.com/diegosouzapw/OmniRoute/issues/6025) / [#6023](https://github.com/diegosouzapw/OmniRoute/issues/6023)) — `X-OmniRoute-Mode` steers an `auto` combo's scoring for a single request (friendly presets `fast`/`balanced`/`quality`/`cheap`/`reliable`/`offline` **or** a raw mode-pack name; `balanced` forces the default weights), and `X-OmniRoute-Budget` sets a hard per-request USD cost ceiling. Both override the combo's stored config only for the request that carries them; unknown/garbage values are ignored so the saved config is preserved. The resolvers are pure (`open-sse/services/autoCombo/requestControls.ts`) and feed the engine's existing `config.modePack` / `config.budgetCap` inputs — no engine changes. Regression guard: `tests/unit/auto-combo-request-controls-6024.test.ts` (5). (thanks @chirag127)
-- **feat(providers):** add the **Kenari** OpenAI-compatible gateway (BYOK). Regression guard: `tests/unit/kenari.test.ts`. (thanks @doedja)
-- **feat(models):** add `claude-sonnet-5` to the Antigravity model catalog (alias mapping in `antigravityModelAliases.ts`) ([#6103](https://github.com/diegosouzapw/OmniRoute/pull/6103)). Regression guard: `tests/unit/antigravity-model-aliases.test.ts`. (thanks @anki1kr)
-- **feat(api):** add `/v1/ocr` endpoint (Mistral OCR), an OCR provider category, and Mistral moderation support. ([#5950](https://github.com/diegosouzapw/OmniRoute/pull/5950)) (thanks @waguriagentic)
-- **Discovery tool (Phase 2):** add the `discoveryResults` DB module (CRUD over the `discovery_results` table, migration 074) and wire the opt-in provider-discovery service to persist and read findings through it (`persistDiscoveryResult`, `getDiscoveryResults`, `getDiscoveryResultById`, `markVerified`, `deleteDiscoveryResult`) with `(provider, method, endpoint)` upsert de-duplication. Adds the `/api/discovery/*` HTTP surface — `GET /results`, `GET|DELETE /results/:id`, `POST /scan`, `POST /verify/:id` — under **strict loopback-only** authorization (`/api/discovery/` is in `LOCAL_ONLY_API_PREFIXES` and is NOT manage-scope-bypassable, so the `scan` route's outbound probes can never be reached from a tunnel/remote origin). Adds a **dashboard UI tab** (Tools → Discovery, `/dashboard/discovery`) to run scans and review, verify, or delete findings. The service stays **opt-in / default-off**. ([#5939](https://github.com/diegosouzapw/OmniRoute/pull/5939))
-- **feat(api):** expose a read-only provider plugin manifest at `GET /api/v1/provider-plugin-manifest` for sidecar/relay discovery. ([#6001](https://github.com/diegosouzapw/OmniRoute/pull/6001)) (thanks @KooshaPari)
-- **feat(sidecar):** advertise the provider manifest URL to Bifrost/CLIProxyAPI via the `X-OmniRoute-Provider-Manifest-Url` header (`OMNIROUTE_PROVIDER_MANIFEST_URL`). ([#6007](https://github.com/diegosouzapw/OmniRoute/pull/6007)) (thanks @KooshaPari)
-- **feat(autoCombo):** add a latency/speed-optimized routing mode (shared `rankBySpeed` scoring core) plus the `omniroute_pick_fastest_model` MCP tool. ([#6011](https://github.com/diegosouzapw/OmniRoute/pull/6011)) (thanks @KooshaPari)
-- **feat(providers):** refresh The Old LLM (Free) model catalog ([#5181](https://github.com/diegosouzapw/OmniRoute/issues/5181)) — seed the current free `/api/chatgpt` tier (GPT-5/5.1/5.2/5.3/5.4, o3/o4-mini, Gemini 3 Pro / 2.5 Pro / 2.0 Flash / 1.5 Flash, Claude 4.6 Opus/Sonnet & 4.5 Haiku, GPT-4o, Grok 4, DeepSeek V3/R1, Sonar Pro) while keeping the legacy alias IDs for saved-preference compatibility. Also fixes a latent routing bug: `mapModel()` now passes known upstream IDs through unchanged, so Gemini/o-series/Grok/DeepSeek/Sonar models no longer silently collapse onto `GPT_5_4`. Regression guard: `tests/unit/theoldllm-model-refresh-5181.test.ts`. (thanks @WslzGmzs)
-- **feat(resilience):** surface Codex **banked reset credits** per connected account ([#5199](https://github.com/diegosouzapw/OmniRoute/issues/5199)) — the Codex quota parsers (`buildCodexUsageQuotas`, `parseCodexUsageResponse`) now additively read `rate_limit_reset_credits.available_count` (+ optional `rate_limit_reached_type`) from the `/wham/usage` payload OmniRoute already fetches, and the provider-limits dashboard renders a **"Banked Reset Credits"** row when a positive count is present. Display-only and **fail-open** — the field is eligibility-gated, so accounts without it are unaffected (parsers never throw on absent/garbage shapes); redemption (an unofficial mutating endpoint) is intentionally out of scope. Regression guard: `tests/unit/codex-banked-reset-credits-5199.test.ts` (8). (thanks @ofekbetzalel)
-- **feat(providers):** add sign-up geo-restriction notices for **SenseNova** and **StepFun** ([#5462](https://github.com/diegosouzapw/OmniRoute/issues/5462)) — the provider add-form now warns that SenseNova's console appears to require a Chinese (+86) phone number with no documented international path, and that StepFun's default endpoint is its China platform while a global StepFun Open Platform (`platform.stepfun.ai`, operated by Sparkling AI Pte. Ltd., Singapore) with email/Google/Discord login exists for international users. Informational `notice` only — neither provider is disabled. Regression guard: `tests/unit/regional-provider-cn-notices-5462.test.ts`. (thanks @chirag127)
-- **feat(usage):** add on-demand period-scoped usage-data reset (Settings → System Storage) with a purge API and time-window selector. ([#5831](https://github.com/diegosouzapw/OmniRoute/pull/5831))
-- **feat(claude-code):** add an opt-in auto-permission classifier compat mode (off/auto/always) for Claude Code, toggleable from the CLI Code settings. ([#5810](https://github.com/diegosouzapw/OmniRoute/pull/5810))
-- **feat(providers):** add optional client-identity header profiles for compatible nodes — preset User-Agent/fingerprint headers (e.g. matching a known CLI) merged into the existing customHeaders field. ([#5812](https://github.com/diegosouzapw/OmniRoute/pull/5812))
-- **feat(build):** add a backend-only fast build mode (`scripts/build/build-next-isolated.mjs` + `backendOnlyPages.mjs`) that skips compiling the dashboard frontend pages, cutting local/CI build time for backend-only changes. ([#6119](https://github.com/diegosouzapw/OmniRoute/pull/6119) — thanks @artickc)
-- **feat(minimax):** extract MiniMax M3's raw `<think>...</think>` leakage into `reasoning_content` on the 8 OpenAI-format provider tiers, leaving the Claude-format `minimax`/`minimax-cn` tiers untouched (they already report reasoning correctly). ([#6073](https://github.com/diegosouzapw/OmniRoute/pull/6073) — thanks @KooshaPari)
-- **feat(services):** promote **Bifrost** (`@maximhq/bifrost` — Go AI-gateway) from an env-only relay sidecar to a first-class embedded/supervised service, matching the existing cliproxy/9router model — installer, bootstrap `SERVICES[]` entry, migration 113 DB seed, 7 lifecycle API routes under `/api/services/bifrost/` (loopback-only), a dashboard tab, and relay auto-wiring that defaults `BIFROST_BASE_URL` to the supervised port when running. Implements item #2 of #5670; the broader RouterBackend contract (items #1, #3-#5) stays out of scope. ([#5817](https://github.com/diegosouzapw/OmniRoute/pull/5817), part of [#5670](https://github.com/diegosouzapw/OmniRoute/issues/5670))
-- **feat(services):** add **Mux** (`coder/mux` — local agent-orchestration daemon) as a fourth-tier embedded service on the existing `ServiceSupervisor` framework — npm-based installer, `bootstrap.ts` registration, migration 113 DB seed, 7 lifecycle API routes under `/api/services/mux/` (loopback-only, defense-in-depth bind to 127.0.0.1), and a dashboard tab reusing the shared service-management components. ([#6034](https://github.com/diegosouzapw/OmniRoute/pull/6034))
-- **feat(xai):** surface Grok/xAI usage on the quota dashboard via local `usageHistory` aggregation (`getXaiUsage`) — since xAI exposes no per-account quota API, this sums tokens routed to the connection from `usage_history` and reports them as a cumulative, uncapped quota, mirroring the existing Xiaomi MiMo self-track pattern. ([#5806](https://github.com/diegosouzapw/OmniRoute/pull/5806))
-- **feat(minimax):** extract MiniMax M3's raw `<think>...</think>` tags into a separate `reasoning_content` field on the 8 provider tiers that register M3 with `format:"openai"` (trae, huggingchat, bazaarlink, ollama-cloud, opencode, cline, opencode-zen, codebuddy-cn) — previously the thinking text leaked directly into `content`. Reuses the existing `extractThinkingFromContent` primitive, extending its allowlist with a minimax-m3-only pattern; the two direct minimax/minimax-cn tiers are untouched since they already surface reasoning natively over Anthropic's Messages format. (Inspired by 9router#2231.) ([#6050](https://github.com/diegosouzapw/OmniRoute/pull/6050) — thanks @KooshaPari)
-- **feat(i18n):** auto-detect the browser language on first visit — a pure `detectBrowserLocale()` matcher (exact match, `zh-HK`/`zh-MO` folded to `zh-TW`, language-prefix match, else `null`) plus a client-only `LocaleAutoDetect` component mounted once in the root layout. When no locale cookie is set yet, it reads `navigator.languages`, computes a match against the supported locales, and persists it via the same cookie/localStorage writer `LanguageSelector` already used (extracted to `shared/lib/persistLocale.ts`). (Inspired by 9router#1324.) ([#5979](https://github.com/diegosouzapw/OmniRoute/pull/5979))
-- **feat(cli-tools):** add **CodeWhale** — the actively-maintained successor to DeepSeek TUI (same author, renamed project) — as a dual dashboard entry alongside the existing "deepseek-tui" catalog entry, so existing DeepSeek TUI users keep a working card while new users are steered to CodeWhale. New `/api/cli-tools/codewhale-settings` route writes `~/.codewhale/config.toml` and keeps the legacy `~/.deepseek/config.toml` in sync. (Inspired by 9router#1761.) ([#5996](https://github.com/diegosouzapw/OmniRoute/pull/5996))
-- **feat(server):** support reverse-proxy `basePath` deployment via a new opt-in `OMNIROUTE_BASE_PATH` env var (empty by default), using Next.js's native `basePath` support so a deployment behind a reverse-proxy subpath (e.g. `https://host/omniroute/`) works without manual header stripping; the two hardcoded auth-redirect targets in `src/server/authz/pipeline.ts` now prefix with `request.nextUrl.basePath`. Default empty basePath is a no-op for existing root-path deployments. (Inspired by 9router#1810.) ([#5992](https://github.com/diegosouzapw/OmniRoute/pull/5992))
-- **feat(providers):** add **SumoPod** (`ai.sumopod.com`) and **X5Lab** (`api.x5lab.dev`) OpenAI-compatible BYOK aggregator gateways, wired via the default executor with bearer API-key auth; both use `passthroughModels` with a live `/v1/models` fetcher instead of a hardcoded catalog. Regression guard: `tests/unit/sumopod-x5lab-provider.test.ts`. (Inspired by 9router#1288.) ([#5963](https://github.com/diegosouzapw/OmniRoute/pull/5963))
-- **feat(providers):** add **Charm Hyper** (`hyper.charm.land`) as a new OpenAI-compatible, bearer-auth API-key gateway provider with a free tier (100 monthly Hypercredits); models resolve via passthrough (`modelsUrl` + live `/v1/models`) since the catalog isn't publicly documented. (Inspired by 9router#2006.) ([#5961](https://github.com/diegosouzapw/OmniRoute/pull/5961))
-- **feat(providers):** add **Nube.sh** (`ai.nube.sh`) as a new BYOK OpenAI-compatible gateway (LiteLLM proxy), Bearer/API-key auth. Its live model catalog is only reachable with a valid key, so no model IDs are hardcoded — it uses `passthroughModels` + `modelsUrl` for live enumeration. (Inspired by 9router#2294.) ([#5936](https://github.com/diegosouzapw/OmniRoute/pull/5936) — thanks @whale9820)
-- **feat(providers):** add **b.ai** (`api.b.ai`) as a new OpenAI-compatible BYOK provider, distinct from the existing thebai/theb.ai provider, using passthrough model discovery with no hardcoded model list. (Inspired by 9router#963.) ([#5969](https://github.com/diegosouzapw/OmniRoute/pull/5969))
-- **feat(providers):** add **Qiniu** (七牛云) AI inference gateway as a BYOK API-key provider — proxies many upstream models (DeepSeek V3/V4, Claude, Kimi, and more) behind a single key, shipping with an empty static seed and relying on `passthroughModels` + the live `/v1/models` catalog instead of a stale hardcoded model id. Regression guard: `tests/unit/qiniu-provider.test.ts`. (Inspired by 9router#911.) ([#5966](https://github.com/diegosouzapw/OmniRoute/pull/5966))
-- **feat(providers):** port **ModelScope** (Alibaba 魔搭) as a new API-key, OpenAI-compatible provider — verified against ModelScope's own docs that the real production domain is `api-inference.modelscope.cn` (`.cn`, not the upstream PR's `.ai`) and shipped `passthroughModels: true` with an empty seed + `modelsUrl` instead of the upstream PR's static 5-model snapshot, since the open-model catalog moves fast. (Ported from 9router#1764.) ([#5965](https://github.com/diegosouzapw/OmniRoute/pull/5965) — thanks @tn5052)
-- **feat(providers):** add **Augment (Auggie CLI)** as a new local, no-auth provider that spawns the user's local `auggie` CLI and pipes a flattened prompt via stdin, wrapping stdout as an OpenAI-compatible SSE stream or single JSON body. Auth is delegated to `auggie login` outside OmniRoute (synthetic `noAuth: true` connection, no DB row required); "Test Connection" spawns `auggie --version`. Hardened against the untrusted-input spawn sink: no `shell: true` on Windows (argv passed straight to the OS loader, no metacharacter interpretation), and `model` is validated against the registry allowlist before spawn (rejecting unknown or `-`-prefixed values) with a trailing `--` end-of-options marker. (Inspired by 9router#1200.) ([#5972](https://github.com/diegosouzapw/OmniRoute/pull/5972) — thanks @chamdanilukman)
-- **feat(providers):** add **NVIDIA NIM image generation** — a dedicated `nvidia-nim` image format/handler (separate host, `ai.api.nvidia.com/v1/genai/<model>`, native NIM body shape) for the 4 FLUX models (flux.1-dev, flux.1-schnell, flux.1-kontext-dev, flux.2-klein-4b), shaping each model's per-model request body (dimension/mode validation, required input image + aspect ratio, optional edit image) and normalizing the NIM response's varying shapes into the OpenAI `{created, data}` shape. (Inspired by 9router#1195.) ([#5971](https://github.com/diegosouzapw/OmniRoute/pull/5971))
-- **feat(oauth):** import a Codex connection from a raw ChatGPT access token — OmniRoute's only Codex import path previously required both `access_token` and `refresh_token`, leaving no path for a user with only a bare ChatGPT website access token. `createProviderConnection` gains an explicit `access_token` auth-type branch (intentionally never deduped), a new `POST /api/oauth/codex/import-token` route (Zod-validated), and `OAuthModal`'s manual-paste path now detects an `eyJ`-prefixed pasted token and posts it to the new endpoint, mirroring the existing grok-cli raw-token flow. The executor's `refreshCredentials()` already degrades safely to `null` without a refresh token, forcing re-auth on expiry. (Inspired by 9router#1290.) ([#5995](https://github.com/diegosouzapw/OmniRoute/pull/5995) — thanks @ryanngit)
-- **feat(dashboard):** add a tool-source diagnostics settings toggle — a new Settings → Advanced card lets operators flip the existing `logToolSources` flag from the UI instead of editing the DB row directly; `logToolSources` is added to the `.strict()` `/api/settings` Zod PATCH schema (previously rejected). (Inspired by 9router#1825.) ([#5978](https://github.com/diegosouzapw/OmniRoute/pull/5978) — thanks @DuyPrX)
-- **feat(dashboard):** collapse and sort provider quota rows by remaining percentage — the expanded quota list is sorted highest-remaining-first and collapsed to the first 3 rows by default, with a "Show N more"/"Show less" toggle when a connection reports more than 3 quotas, keeping at-risk quotas visible above a long list of healthy ones. Sort/slice logic extracted into pure, directly-unit-tested helpers (`sortQuotasByRemaining`, `getVisibleQuotas`). (Inspired by 9router#1919.) ([#5977](https://github.com/diegosouzapw/OmniRoute/pull/5977))
-- **feat(dashboard):** suggest HuggingFace Hub media models — a new `GET /api/v1/providers/suggested-models` route proxies the public HF Hub models search API (Zod-validated, no token exposed client-side) and `ImageExampleCard` merges the results into the model picker as a selectable chip row for the huggingface provider; also adds a dedicated `huggingface-image` format/handler for HF's raw-image-bytes response. (Inspired by 9router#1633.) ([#5990](https://github.com/diegosouzapw/OmniRoute/pull/5990))
-- **feat(cli-tools):** add a **Crush** entry to the dashboard CLI-Tools catalog plus a new `/api/cli-tools/crush-settings` route (GET/POST/DELETE) — OmniRoute already shipped a `crush` CLI setup command (`bin/cli/commands/setup-crush.mjs`) but the dashboard catalog had no matching entry; the new route writes to the same canonical `~/.config/crush/crush.json` path so the dashboard and CLI command agree. (Inspired by 9router#1233.) ([#5970](https://github.com/diegosouzapw/OmniRoute/pull/5970))
-- **feat(providers):** extend Vercel AI Gateway (`vercel-ai-gateway`/`vag`) beyond chat-only to support **embeddings and image generation** — the gateway's OpenAI-compatible `/v1` API also exposes `/embeddings` and `/images/generations`, so entries were added to `EMBEDDING_PROVIDERS` (`embeddingRegistry.ts`) and `IMAGE_PROVIDERS` (`imageRegistry.ts`) modeled on the existing `openai` entries. ([#5968](https://github.com/diegosouzapw/OmniRoute/pull/5968) — thanks @tantai-newnol)
-- **feat(api-keys):** add per-key **device/connection tracking** — a SHA-256 fingerprint of IP + User-Agent, with a 30-minute TTL and per-key/global caps, tracks distinct client devices seen with each API key (in-memory only, raw IP never stored). A new `GET /api/keys/[id]/devices` route exposes masked device details, and the API Keys dashboard tab gets a "Devices" count badge alongside the existing Sessions badge. This is a new granularity distinct from the existing `maxSessions` cap, which limits concurrent sticky-routing sessions rather than tracking device identity. ([#5998](https://github.com/diegosouzapw/OmniRoute/pull/5998) — thanks @mugni-rukita)
-- **feat(proxy):** add **Webshare** (`proxy.webshare.io`) as a fourth source in the free-proxy provider framework alongside 1proxy, Proxifly, and IPLocate. `WebshareProvider` paginates the account's `/api/v2/proxy/list/` endpoint, upserts proxies into the shared `free_proxies` table, and tombstones proxies the account no longer lists while never touching rows already promoted into the live proxy pool. Unlike the other sources, Webshare is a paid per-account list, gated on `FREE_PROXY_WEBSHARE_API_KEY`. ([#5993](https://github.com/diegosouzapw/OmniRoute/pull/5993) — thanks @ricatix)
-- **feat(antigravity):** support custom **Google Cloud project ID** settings from the connection edit modal (Antigravity family). ([#5905](https://github.com/diegosouzapw/OmniRoute/pull/5905) — thanks @nickwizard)
-- **feat(dashboard):** add a **wildcard-CORS runtime warning** banner (Settings → Authorization) when `CORS_ALLOW_ALL`/`*` origins are in effect, plus a new `docs/security/CORS.md` security guide covering the risk and safer alternatives. ([#5602](https://github.com/diegosouzapw/OmniRoute/issues/5602), [#5759](https://github.com/diegosouzapw/OmniRoute/pull/5759))
-- **feat(api):** add a `/v1/audio/translations` endpoint (Whisper-style audio translation), a new `audioTranslation` handler, and translation providers wired into `audioRegistry`. Regression guard: `tests/unit/audio-translations-route.test.ts` (8, incl. no-stack-leak). ([#5809](https://github.com/diegosouzapw/OmniRoute/pull/5809))
-- **feat(providers):** allow a **custom icon URL** for compatible provider nodes (migration 113 + `nodes.ts` + Zod schema + API routes + catalog + `ProviderIcon` UI). Regression guards: 14 backend + 5 frontend(vitest) + 24 page-utils tests. ([#5815](https://github.com/diegosouzapw/OmniRoute/pull/5815))
-- **feat(xai):** register a dedicated `XaiExecutor` with reasoning-effort suffix parsing. Regression guard: `tests/unit/executors/xai-executor.test.ts` (6). ([#5800](https://github.com/diegosouzapw/OmniRoute/pull/5800))
-- **feat(webfetch):** support **self-hosted FireCrawl** instances via `FIRECRAWL_BASE_URL`/`FIRECRAWL_TIMEOUT_MS`. Regression guard: `tests/unit/executors/firecrawl-fetch.test.ts` (4). ([#5793](https://github.com/diegosouzapw/OmniRoute/pull/5793))
-- **feat(providers):** add **ClinePass** as a first-class API-key (BYOK) provider — Cline's paid gateway (`cline-pass/*` models, plain Bearer key), distinct from the existing OAuth `cline` provider. Regression guard: 16 clinepass tests. ([#5942](https://github.com/diegosouzapw/OmniRoute/pull/5942) — thanks @adentdk)
-- **feat(relay):** gate **Bifrost auto-routing** by the provider plugin manifest — only manifest-eligible providers reach the sidecar; ineligible/unknown providers fall back to the existing TS routing path with explicit reasons. Regression guards: 4 provider-plugin-manifest + 11 relay-routing-backend tests. ([#5870](https://github.com/diegosouzapw/OmniRoute/pull/5870) — thanks @KooshaPari)
-- **feat(providers):** wire **Claude Sonnet 5** end-to-end across the model pipeline — registries, `modelSpecs`, pricing (×3), cost, Sonnet-family fallback, 1M-context, and static models. ([#5833](https://github.com/diegosouzapw/OmniRoute/pull/5833) — thanks @ggiak)
-
-### 🔧 Bug Fixes
-
-- **dashboard (`/dashboard/system/proxy` 500 on every render):** `ProxyRegistryManager` called `useProxyBatchOperations(load)` before the `const load = useCallback(...)` declaration in the component body, so every server render threw a TDZ `ReferenceError: Cannot access 'load' before initialization` and the whole proxy page 500'd (#5918 regression, caught by the release-PR e2e smoke — the PR→release fast-gates never render pages). The hook block now sits after the `load` declaration. Regression guard: `tests/unit/ui/ProxyRegistryManager-tdz-render.test.tsx` (SSR renderToString — the exact crash mode).
-
-- **server (TRACE/TRACK/CONNECT returned raw 500 on every route):** methods that undici/fetch cannot represent blew up inside Next's middleware adapter (`TypeError: 'TRACE' HTTP method is unsupported.`) as an unhandled 500 (caught by the release-PR dast-smoke Schemathesis negative tests on the new `/api/keys/{id}/devices` endpoint). The raw HTTP method guard now answers a clean 405 + `Allow` header for these methods on any path, before Next sees the request. Regression guard: `tests/unit/dast-method-not-allowed.test.ts` (new case).
-
-- **i18n (auto-detect refreshed every first visit):** `LocaleAutoDetect` (#5979) called `router.refresh()` on every cookie-less first visit — even when the detected browser locale was exactly the one the server had just rendered — re-navigating the page mid-interaction (flaky e2e "execution context destroyed" + a visible flash for every new visitor). It now refreshes only when the detected locale differs from the server-rendered `<html lang>`. Regression guard: `tests/unit/ui/LocaleAutoDetect-refresh.test.tsx`.
-
-- **models (`oc/` alias must reach the no-auth OpenCode provider):** restore the [#2901](https://github.com/diegosouzapw/OmniRoute/issues/2901) routing contract after the #5918 transitive-alias change made the registered no-auth `opencode` provider unreachable by any prefix (`oc/` chained through the manual `opencode` → `opencode-zen` slug override and misrouted its combo entries). `resolveProviderAlias` now stops the alias chain as soon as a hop lands on a registered provider id, while keeping #5918's transitivity across alias-only hops and its loop/depth guards. Regression guards: `tests/unit/combo-builder-opencode-prefix.test.ts`, `tests/unit/provider-alias-transitive-5918.test.ts`.
-
-- **providers (Auggie executor EPIPE crash):** a fast-exiting `auggie` CLI (e.g. binary present but immediately failing) delivered `EPIPE` **asynchronously** as an `'error'` event on the child's stdin stream — which a plain try/catch around `stdin.write()` cannot catch — crashing the request instead of surfacing the sanitized CLI error. Both spawn sites now attach a stdin `'error'` handler so the child's own exit/close handlers report the failure. Regression guard: `tests/unit/auggie-executor.test.ts` (deterministic 3/3 locally).
-
-- **dashboard (CoolingConnectionsPanel broke `next build`):** the cooling-connections panel from #6061 imported `Card` from a shadcn-style path that does not exist in this repo (`@/components/ui/card`) and pulled the server DB barrel (`@/lib/localDb`) into a client component — `next build` failed to compile on the release branch. The panel now renders with repo-native markup and reads `formatResetCountdown` from the new client-safe `src/shared/utils/formatting.ts`. Regression guards: `tests/unit/format-reset-countdown.test.ts`, `tests/unit/ui/CoolingConnectionsPanel.test.tsx`. ([#6155](https://github.com/diegosouzapw/OmniRoute/pull/6155))
-
-- **oauth (Zed "Unknown provider" crash):** adding **Zed** from the providers dashboard threw an unhandled `OAuth GET error: Unknown provider: zed` (500) ([#6041](https://github.com/diegosouzapw/OmniRoute/issues/6041)). Zed is a **keychain-import-only** provider — it's listed in the OAuth catalog so the UI shows it, but has no OAuth handler, so the generic `/api/oauth/[provider]/[action]` route hit `getProvider("zed")` and crashed. The route now recognizes keychain-import-only providers and returns a clear **400** pointing users at the **Import** button (for both GET and POST OAuth actions), instead of a 500. Regression guard: `tests/unit/oauth-keychain-import-only-6041.test.ts`. (thanks @imblowsnow)
-
-- **fix(providers):** disable the unsupported `thinking` param for `minimax-m2.7` on NVIDIA NIM (the upstream rejects it) ([#6102](https://github.com/diegosouzapw/OmniRoute/pull/6102)). Regression guard: `tests/unit/nvidia-minimax-thinking-strip.test.ts`. (thanks @anki1kr)
-
-- **fix(mitm):** add an in-process guard so concurrent MITM server starts no longer race — a second start while one is already in flight is short-circuited instead of double-binding the listener ([#6107](https://github.com/diegosouzapw/OmniRoute/pull/6107)). Regression guard: `tests/unit/mitm-start-guard.test.ts`. (thanks @anki1kr)
-
-- **translator (Responses → Chat Completions):** strip the Responses-API-only `truncation` field before forwarding a `/v1/responses` request to a non-OpenAI Chat Completions upstream ([#6109](https://github.com/diegosouzapw/OmniRoute/pull/6109)). Strict upstreams (e.g. NVIDIA NIM) rejected it with HTTP 400 `Unsupported parameter(s): truncation`, breaking Codex-style clients routed to those providers. `client_metadata`, `background`, and `safety_identifier` were already stripped — `truncation` was the remaining gap. Regression guard: `tests/unit/responses-strip-truncation-2311.test.ts`. (thanks @TuanNguyen0708)
-
-- **combo (prefer known context capacity over unknown):** when a combo filters out at least one target for exceeding a _known_ context limit, the router now prefers the remaining known-compatible targets over targets whose context metadata is simply unknown, instead of letting unknown-metadata targets be the only survivors. If no known-compatible context target remains, context-only candidates fall back to the normal strategy order. Regression guard: `tests/unit/combo-context-window-filter.test.ts`. ([#6088](https://github.com/diegosouzapw/OmniRoute/pull/6088) — thanks @Thinkscape)
-
-- **models (GLM-5.2 context normalization):** stop treating every hosted GLM-5.2 provider alias as the native 1M-context model. Native/bare GLM-5.2 and verified OpenCode / ZenMux routes keep their 1,000,000-token context, while hosted-provider aliases now respect the caps declared in their provider metadata instead of inheriting the native max. Regression guards: `tests/unit/model-capabilities-registry.test.ts`, `tests/unit/models-catalog-route.test.ts`. ([#6091](https://github.com/diegosouzapw/OmniRoute/pull/6091) — thanks @Thinkscape)
-
-- **providers (Gemini Web):** refresh the Gemini Web cookie handling and model catalog so live Gemini Web sessions keep authenticating and routing to current models. Regression guard: `tests/unit/gemini-web.test.ts`. ([#6095](https://github.com/diegosouzapw/OmniRoute/pull/6095) — thanks @backryun)
-
-- **providers (Perplexity Web):** refresh the Perplexity Web model catalog to the current set (GPT-5.4/5.5, Claude Sonnet 5.0 / Opus 4.8, GLM-5.2, Kimi K2.6, Nemotron 3 Ultra) and update the internal mode / `model_preference` mappings and thinking variants so requests resolve to live upstream models. Regression guard: `tests/unit/perplexity-web.test.ts`. ([#6106](https://github.com/diegosouzapw/OmniRoute/pull/6106) — thanks @backryun)
-
-- **dashboard ("Update now" → Internal Server Error):** clicking **Update now** on the dashboard home could crash the page with a blank "Internal Server Error" screen (`Minified React error #31`). The handler POSTs the loopback-only `/api/system/version` auto-update endpoint and, on a non-OK JSON response (e.g. a `403` when the dashboard is reached through a reverse proxy / non-loopback origin), passed the raw error envelope object `{ error: { code, message, correlation_id } }` straight to `notify.error()`, which rendered the object as a React child and threw #31. The update-error path now funnels the body through `extractApiErrorMessage()` (the same safe extractor added in #5340), so a readable string always reaches the toast. Regression guard: `tests/unit/ui/home-update-error-render-5991.test.ts`. ([#5991](https://github.com/diegosouzapw/OmniRoute/issues/5991))
-- **fix(onboarding):** route the provider-details link in the onboarding wizard by the node's stable id instead of the composite provider slug, which could point at the wrong provider details page for multi-account/fingerprint nodes. Regression guard: `tests/unit/onboarding-wizard-details-link-6145.test.ts`. ([#6145](https://github.com/diegosouzapw/OmniRoute/pull/6145) — thanks @chirag127)
-- **fix(cli):** give `setup-claude` a fallback profile generator mirroring `setup-codex`, so profile generation no longer silently no-ops when the primary generator path is unavailable. Regression guard: `tests/unit/cli/setup-claude.test.ts` (new cases). ([#6138](https://github.com/diegosouzapw/OmniRoute/pull/6138) — thanks @derhornspieler)
-- **fix(glm):** suppress a leaked `</think>` close marker in the GLM Anthropic transport, which was surfacing the raw reasoning-close tag in visible response content instead of being consumed as part of the thinking-block framing. Regression guard: `tests/unit/glm-think-close-marker-leak.test.ts`. ([#6133](https://github.com/diegosouzapw/OmniRoute/pull/6133) — thanks @dhaern)
-- **fix(provider-limits):** close a TOCTOU race in quota-recovery clearing by moving the check-then-clear to a CAS (compare-and-swap) primitive in `src/lib/db/providers.ts`, so two concurrent recovery paths can no longer both observe stale state and double-clear/re-lock a connection. Regression guard: `tests/unit/provider-limits-recovery.test.ts`. ([#6139](https://github.com/diegosouzapw/OmniRoute/pull/6139) — thanks @janeza2)
-- **fix(provider-limits):** clear transient rate-limit state (`rateLimitedUntil`, `lastError`, `backoffLevel`) as soon as quota recovers, instead of leaving stale rate-limit fields behind that could keep a now-healthy connection looking unavailable. Regression guard: `tests/unit/provider-limits-recovery.test.ts`. ([#6128](https://github.com/diegosouzapw/OmniRoute/pull/6128) — thanks @janeza2)
-- **combos (OpenCode/MiMo fingerprint accounts):** expand fingerprint-scoped OpenCode/MiMo accounts into their full per-fingerprint set in the combo builder, which previously showed only the first matching account entry and hid the rest from combo target selection. Regression guard: `tests/unit/combo-builder-fingerprint-expansion.test.ts`. ([#6092](https://github.com/diegosouzapw/OmniRoute/pull/6092), closes [#6087](https://github.com/diegosouzapw/OmniRoute/issues/6087) — thanks @anki1kr)
-- **fix(auth):** persist quota-preflight account lockouts until the reset window elapses, instead of losing the lockout on process restart and letting a still-quota-exhausted account be selected again immediately. Regression guards: `tests/unit/sse-auth.test.ts`, `tests/unit/opencode-quota-fetcher.test.ts`, `tests/unit/usage-service-hardening.test.ts`. ([#6090](https://github.com/diegosouzapw/OmniRoute/pull/6090) — thanks @Thinkscape)
-- **combo (fingerprint-based provider expansion):** expand fingerprint-based providers into per-fingerprint combo targets (`open-sse/services/combo/fingerprintExpansion.ts`) so a combo referencing a fingerprint-scoped provider fans out to every matching fingerprint account instead of collapsing onto one. Regression guards: `tests/unit/combo-fingerprint-expansion.test.ts`, `tests/integration/fingerprint-expansion.test.ts`. ([#6082](https://github.com/diegosouzapw/OmniRoute/pull/6082) — thanks @pizzav-xyz)
-- **fix (safety-net redirect `reqId` crash):** fix a `reqId` `ReferenceError` thrown inside the safety-net combo redirect path in `src/sse/handlers/chat.ts`, remove dead code in `src/domain/quotaCache.ts`, and rename the stray root `DESING.md` to `DESIGN.md`. Regression guard: `tests/unit/chat-safetynet-reqid-6097.test.ts`. ([#6097](https://github.com/diegosouzapw/OmniRoute/pull/6097) — thanks @fix2015)
-- **fix(compression):** send a patch-only body to `PUT /api/settings/compression` from `CompressionHub`, instead of round-tripping the full settings object and risking clobbering fields changed elsewhere between load and save. Regression guard: `tests/unit/ui/CompressionHub-patch-only.test.tsx`. ([#6077](https://github.com/diegosouzapw/OmniRoute/pull/6077), closes [#6039](https://github.com/diegosouzapw/OmniRoute/issues/6039) — thanks @anki1kr)
-- **fix(codex):** use `access_token.exp` instead of `id_token.exp` when computing `expiresAt` on Codex auth import, since the `id_token` can expire far sooner than the actual access token, causing imported connections to be treated as expired while still usable. Regression guard: `tests/unit/codex-auth-import-expiry.test.ts`. ([#6084](https://github.com/diegosouzapw/OmniRoute/pull/6084), closes [#6075](https://github.com/diegosouzapw/OmniRoute/issues/6075) — thanks @anki1kr)
-- **fix(security):** persist the IP allow/block-list configuration (it was resetting to Disabled and clearing configured IPs on every restart/update) and actually enforce it in the authz pipeline (`src/server/authz/pipeline.ts`), where it was previously validated but never applied. Regression guards: `tests/unit/ip-filter-persistence-6131.test.ts`, `tests/unit/authz/ip-filter-enforcement-6131.test.ts`, `tests/unit/ip-filter.test.ts`. (closes [#6131](https://github.com/diegosouzapw/OmniRoute/issues/6131), [#6132](https://github.com/diegosouzapw/OmniRoute/pull/6132))
-- **fix (Claude tool_result adjacency):** reattach an OpenAI-shaped `tool_result` to sit directly adjacent to its originating `tool_use` before translating to Claude's message format (`open-sse/translator/request/openai-to-claude/toolResultAdjacency.ts`), since Claude's API rejects/mishandles a tool result separated from its tool call by intervening messages. Regression guard: `tests/unit/translator-openai-to-claude.test.ts` (new cases). ([#6035](https://github.com/diegosouzapw/OmniRoute/pull/6035) — thanks @KooshaPari)
-- **fix(config):** externalize `ws`/`bufferutil`/`utf-8-validate` in `next.config.mjs` so the `copilot-m365-web` executor's WebSocket masking path works at runtime — chat requests through it were silently timing out because the bundler was inlining `ws` instead of leaving it as a real Node dependency. Regression guard: `tests/unit/next-config.test.ts`. ([#6130](https://github.com/diegosouzapw/OmniRoute/pull/6130), closes [#6062](https://github.com/diegosouzapw/OmniRoute/issues/6062) — thanks @anki1kr, whose #6098 fix it re-lands)
-- **fix(registry):** update grok-cli model context lengths to match the actual Grok CLI `/context` capacities — `grok-build` 128k→256k, `grok-composer-2.5-fast` 128k→200k — so context-aware routing stops filtering these models out for exceeding a stale, too-low limit. Registry-only. ([#5913](https://github.com/diegosouzapw/OmniRoute/pull/5913) — thanks @Chewji9875)
-- **fix(providers):** strip an orphan `tool_result` (one with no preceding `tool_use`) on the Antigravity MITM path before translating to OpenAI format, since an unpaired tool result upstream caused request failures. Regression guard: `tests/unit/antigravity-orphan-toolresult-6026.test.ts`. (closes [#6026](https://github.com/diegosouzapw/OmniRoute/issues/6026), [#6115](https://github.com/diegosouzapw/OmniRoute/pull/6115))
-- **fix(providers):** emulate OpenAI-style `tool_calls` in the GitLab Duo executor (new `open-sse/executors/gitlabResponses.ts`), since the executor previously didn't emulate tool-call semantics for Duo, breaking tool-using clients routed to GitLab Duo. Regression guard: `tests/unit/gitlab-duo-toolcalls-6051.test.ts`. (closes [#6051](https://github.com/diegosouzapw/OmniRoute/issues/6051), [#6111](https://github.com/diegosouzapw/OmniRoute/pull/6111))
-- **fix(429 / accountFallback):** persist the per-account 429 cooldown cascade across the request boundary and classify OpenCode's "Monthly usage limit. Resets in N days." message as a connection-scoped quota exhaustion with an N-day cooldown (instead of a ~5s transient retry), so an exhausted account stops being re-selected until its window resets. ([#6061](https://github.com/diegosouzapw/OmniRoute/pull/6061) — thanks @KooshaPari / @anki1kr, whose superseded #6086 carried the same day-parser approach)
-- **combo (sibling-model fallback on per-model-quota 500s):** when a combo held multiple models from the same provider (e.g. two Gemini models) and the first returned a server 500, the router retried the same locked model and surfaced a 429 "cooling down" instead of trying the sibling — `markConnectionLevelExhaustion` was wrongly tripped by a model-level 500 for per-model-quota providers (gemini, github, passthrough, compatible), and the retry loop didn't check `isModelLocked` before re-hitting the same model. Both gaps are fixed; the combo now falls through to the untried sibling model. Regression guard: `tests/unit/combo/combo-target-exhaustion.test.ts` (21 cases). ([#5976](https://github.com/diegosouzapw/OmniRoute/pull/5976) — thanks @hartmark)
-- **providers (Cline non-streaming envelope):** Cline can return OpenAI-compatible chat completions wrapped as `{ success, data: { choices, usage, ... } }`; the non-streaming path checked the top-level body for empty content before unwrapping, so a valid wrapped response could be misclassified as malformed/empty. The envelope is now unwrapped immediately after provider-envelope handling, before empty-content detection, usage extraction, and translation. Regression guard: `tests/unit/cline-response-envelope.test.ts`. ([#6046](https://github.com/diegosouzapw/OmniRoute/pull/6046) — thanks @KooshaPari)
-- **providers (kimi-web, qwen-web):** align the kimi-web model catalog and request-scenario selection with `www.kimi.com`'s live `GetAvailableModels` response, and stop aliasing `qwen3-coder-plus` on qwen-web now that it is present as its own model in the live Qwen web catalog. ([#5915](https://github.com/diegosouzapw/OmniRoute/pull/5915) — thanks @janeza2)
-- **translator (Antigravity/Gemini tool schemas):** strip `multipleOf` from function-declaration parameters before forwarding to Antigravity/Gemini — it is not part of the Gemini OpenAPI 3.0 schema subset accepted upstream and triggered a hard 400 ("Unknown name multipleOf"). Added to `GEMINI_UNSUPPORTED_SCHEMA_KEYS` so it is stripped at every schema level; `minimum`/`maximum` are unaffected since Gemini accepts them. (Ported from 9router#2309, reported by @abil0321.) ([#6052](https://github.com/diegosouzapw/OmniRoute/pull/6052))
-- **translator (Kiro system prompt leak):** Kiro/CodeWhisperer has no system role, so system messages were normalized into a bare user turn — the full Claude Code system prompt then appeared as raw user text, polluting model context. System-origin content is now wrapped in `<system-reminder>` tags before merging into the Kiro user message; real user turns are unaffected. (Ported from 9router#2306, reported by @VitzS7.) ([#6053](https://github.com/diegosouzapw/OmniRoute/pull/6053))
-- **fix(codex):** convert Chat Completions `json_schema` `response_format` → Responses API `text.format` on the Codex path, and preserve an existing `text.format` through verbosity normalization. Regression guards: 48 translator-openai-responses-req + 8 codex-verbosity tests. ([#5933](https://github.com/diegosouzapw/OmniRoute/pull/5933) — thanks @yusufrahadika)
-- **fix(thinking):** only inject the `redacted_thinking` replay block when `tool_use` is present and thinking is enabled, avoiding a fabricated replay block on plain (non-tool) turns. ([#5945](https://github.com/diegosouzapw/OmniRoute/issues/5945), [#5953](https://github.com/diegosouzapw/OmniRoute/pull/5953))
-- **fix(resilience):** honor active **codex session affinity** over per-request reset-aware re-scoring, so an in-flight session sticks to its pinned account instead of being re-scored away mid-conversation. New `src/sse/services/sessionAffinityPin.ts` module. Regression guard: `tests/unit/codex-session-affinity-reset-aware-5903.test.ts`. ([#5903](https://github.com/diegosouzapw/OmniRoute/issues/5903), [#5943](https://github.com/diegosouzapw/OmniRoute/pull/5943))
-- **fix(resilience):** compute per-window `is_exhausted` and honor the quota-exhaustion preflight for **priority combos**, so a combo no longer keeps routing to a target whose current window is already exhausted. New `open-sse/services/combo/quotaExhaustionCutoff.ts`. Regression guard: `tests/unit/combo-priority-quota-exhaustion-cutoff-5923.test.ts`. ([#5923](https://github.com/diegosouzapw/OmniRoute/issues/5923), [#5941](https://github.com/diegosouzapw/OmniRoute/pull/5941))
-- **fix(providers):** strip a `/v1` suffix from the base URL unconditionally in both models-discovery paths, avoiding a doubled `/v1/v1/models` fetch error (e.g. Api Airforce). Regression guard: `tests/unit/airforce-v1-double-prefix-5899.test.ts`. ([#5899](https://github.com/diegosouzapw/OmniRoute/issues/5899), [#5920](https://github.com/diegosouzapw/OmniRoute/pull/5920) — thanks @anki1kr)
-- **fix(api):** relax provider-scoped chat completion validation on `/api/providers/[provider]/chat/completions`. Regression guard: `tests/unit/provider-scoped-chat-completions-validation.test.ts`. ([#5907](https://github.com/diegosouzapw/OmniRoute/pull/5907) — thanks @nickwizard)
-- **fix(providers):** validate **v0 Platform** (Vercel) API keys via the `/chats` endpoint instead of a probe that rejected valid keys. Regression guard: `tests/unit/provider-validation-specialty.test.ts`. ([#5954](https://github.com/diegosouzapw/OmniRoute/pull/5954) — thanks @vittoroliveira-dev)
-- **fix(mcp):** auto-recover stale streamable HTTP MCP sessions on `initialize` instead of failing the reconnect. Regression guard: `tests/unit/mcp-session-sweep.test.ts`. ([#5957](https://github.com/diegosouzapw/OmniRoute/pull/5957) — thanks @Chewji9875)
-- **fix(translator):** enforce strict Anthropic content-block compliance when converting an antigravity → openai request. Regression guard: `tests/unit/translator-antigravity-to-openai.test.ts` (9). ([#5935](https://github.com/diegosouzapw/OmniRoute/pull/5935))
-- **fix(sse):** strip ANSI/VT100 escape codes from `gemini-cli` stream frames using a ReDoS-safe pattern. Regression guard: `tests/unit/gemini-cli-ansi-sanitization.test.ts` (5). ([#5934](https://github.com/diegosouzapw/OmniRoute/pull/5934) — thanks @anki1kr)
-- **fix(discovery):** resolve a doubled `/v1` discovery path and a `REDIRECT_BLOCKED` probe-loop abort in the model-discovery route. Regression guard: `tests/unit/provider-models-route.test.ts`. ([#5904](https://github.com/diegosouzapw/OmniRoute/pull/5904) — thanks @hamsa0x7)
-- **fix(providers): Perplexity Web now emits real `tool_calls` in streaming mode** — previously only non-streaming requests (`hasTools && !stream`) converted `<tool>{...}</tool>` text into OpenAI `tool_calls`; streaming requests (the default for agentic coding clients) got the raw `<tool>` text as plain `delta.content` and never emitted a `tool_calls` SSE delta. Now mirrors the `chatgpt-web` `toolMode` helpers (`buildToolModeResponse()`/`toolCompletionToSseStream()`, extended with a caller-supplied `idSeed` so tool-call ids stay provider-specific), buffering the completion and emitting a terminal SSE replay carrying `delta.tool_calls` + `finish_reason: tool_calls` regardless of the caller's stream flag. ([#5927](https://github.com/diegosouzapw/OmniRoute/issues/5927), [#5937](https://github.com/diegosouzapw/OmniRoute/pull/5937))
-- **providers (openai-family model inference no longer hijacks cataloged models):** `resolveModelByProviderInference()` had an unconditional `/^gpt-/i` heuristic that hijacked any model id starting with `gpt-`/`o1`/`o3` into provider `openai`, even when the id is cataloged under other providers — breaking bare (non-combo) requests for open-weight models like `gpt-oss-120b` (served by fireworks/cerebras/scaleway/byteplus/sambanova/heroku), which don't exist on openai's catalog, producing a 404 with no fallback. The heuristic is now gated on `providers.length === 0` so it only fires for genuinely uncataloged openai-family ids. Regression guard: `tests/unit/gptoss-provider-inference-5852.test.ts`. ([#5852](https://github.com/diegosouzapw/OmniRoute/issues/5852), [#5938](https://github.com/diegosouzapw/OmniRoute/pull/5938))
-- **fix(providers): deepseek-web reliability** — auto-refresh the session on `401`/`403`, refresh the v2.0.0 client headers, and fix the token-kind bulk import path. Regression guards: `tests/unit/deepseek-web-autorefresh-401-response.test.ts`, `tests/unit/bulk-web-session-import.test.ts`. ([#5988](https://github.com/diegosouzapw/OmniRoute/pull/5988) — thanks @backryun)
-- **fix(api):** guard the shared frontend API client (`handleResponse` in `src/shared/utils/api.ts`) against non-JSON error responses — it previously called `response.json()` unconditionally and read `data.error` directly, throwing an unrelated parse error (or `undefined`) instead of a useful message when an upstream/proxy returned a non-JSON error body. Now routes through `parseResponseBody`/`getErrorMessage` to build a safe message regardless of body shape. Regression guard: `tests/unit/shared-api-utils.test.ts`. ([#5973](https://github.com/diegosouzapw/OmniRoute/pull/5973))
-- **fix(embeddings):** forward the connection-level proxy configuration to embedding requests — `src/lib/embeddings/service.ts` previously ignored a connection's configured proxy when making embedding calls, so proxy-only network setups leaked embedding traffic outside the proxy. Regression guard: `tests/unit/embeddings-proxy-forwarding.test.ts`. ([#5975](https://github.com/diegosouzapw/OmniRoute/pull/5975))
-- **fix(resilience):** parse `Retry-After` from a 429's JSON body for cooldown calculation, not just the HTTP header — a new `retryAfterJson.ts` helper extracts a retry-after hint from common JSON error-body shapes and `accountFallback.ts`'s cooldown path now prefers it when the header is absent. Regression guard: `tests/unit/account-fallback-retry-after-json.test.ts`. (Includes #6013's retry-after-json extraction.) ([#5974](https://github.com/diegosouzapw/OmniRoute/pull/5974) — thanks @KooshaPari)
-
-### 📝 Maintenance
-
-- **release close (release-PR one-pass CI sweep):** restore Zod validation on the provider-scoped chat route with a `.passthrough()` schema that keeps #5907's relaxed semantics (t06 route-validation gate); point `/api/keys/{id}/devices`' 401 response at the management error envelope in `docs/openapi.yaml` (Schemathesis schema-conformance); rebaseline `i18nUiCoverage.pct` 77.5→76.8 (~1352 new en.json UI keys from the cycle await the async translation workflow — same shape as the v3.8.39 rebaseline); dismiss 2 CodeQL `js/incomplete-url-substring-sanitization` false positives on unit-test asserts (v3.8.35 precedent).
-
-- **release close (Phase 0 pre-flight):** align cycle-stale tests with merged behavior — provider count 166→167 (Kenari #6104), Linux-regenerated translate-path golden (+`kenari`), OpenCode quota scope `provider`→`connection` (#6061) — and absorb cycle ratchet drift (file-size caps for `oauth/[provider]/[action]/route.ts` 960, `providerLimits.ts` 998, `chat.ts` 1662, `auth.ts` 2426, with #6158 tracked to restore the oauth-route freeze). The test-masking gate gains a narrowly-scoped `_deletedWithReplacement` allowlist section (deletion is exempt ONLY when the declared replacement test file exists in HEAD — used for `targetExhaustion.test.ts` → `tests/unit/combo/combo-target-exhaustion.test.ts`, which has MORE coverage: 21 cases/52 asserts vs 13/37), plus 5 new gate unit tests and reduction-allowlist entries for the verified-legitimate #5958/#6088/#5816 assert migrations.
-
-- **test (deflake `setup-claude`):** `tests/unit/cli/setup-claude.test.ts` failed ~50% of runs with `Unable to deserialize cloned data due to invalid or unsupported version` at file teardown (all subtests passed), randomly reddening `Unit Tests fast-path (2/2)` / `Fast Quality Gates` across the PR→release queue. Root cause: `node --test` streams each file's report to the parent as V8-serialized frames on fd 1 (stdout), and the CLI helper under test (`syncClaudeProfilesFromModels`) prints progress via `console.log` — that stdout output interleaved with the serialized frames and corrupted the stream. The test now silences the stdout-writing `console` methods for the file's duration (no assertion inspects stdout), making it deterministic (15/15 green locally). ([#5959](https://github.com/diegosouzapw/OmniRoute/issues/5959)) ([#6021](https://github.com/diegosouzapw/OmniRoute/pull/6021))
-
-- **API validation:** add a `validatedJsonBody(request, schema)` helper in `src/shared/validation/helpers.ts` that fuses JSON body parsing and Zod validation into a single call, returning either the type-narrowed data or a ready-to-return 400 `NextResponse` with the standard error envelope. Salvaged from the closed refactor PR #5075 (Tier 1 portable helper) with a focused 6-case regression test. Co-authored-by: KooshaPari <KooshaPari@users.noreply.github.com>
-- **repo (Windows case-conflict cleanup):** remove the stale root `DESIGN.md`, which case-conflicted with `design.md` and broke checkouts/clones on case-insensitive Windows filesystems. ([#6140](https://github.com/diegosouzapw/OmniRoute/pull/6140) — thanks @backryun)
-- **i18n(zh-CN):** translate the CHANGELOG entries and section headings, adopting zh-CN as a fully translated locale alongside the existing supporting docs. ([#6043](https://github.com/diegosouzapw/OmniRoute/pull/6043) — thanks @studyzy)
-- **docs (env-doc-sync base-red):** document `BIFROST_PORT` in `.env.example` / `docs/reference/ENVIRONMENT.md` — the Bifrost embedded-service merge referenced `process.env.BIFROST_PORT` (default 8080) without documenting it, so `check:env-doc-sync` failed on the release tip and reddened Fast Quality Gates for every open PR→release. Docs-only (`8d7e3e28f`).
-- **test (CI-runner-independent translate-path golden):** normalize OS/arch-derived request headers (`X-Stainless-Os`/`X-Stainless-Arch`, `(OS;arch)` User-Agent segments, and Antigravity's `os.platform()`-derived platform substring) in the provider translate-path golden snapshot, so the test no longer depends on the OS/arch of the CI runner that generated it — a Mac-literal Antigravity UA was failing on Linux CI. Regression guard: `tests/unit/provider-translate-path-golden.test.ts`. ([#6076](https://github.com/diegosouzapw/OmniRoute/pull/6076) — thanks @KooshaPari)
-- **release-green base-reds (#5695 regex + file-size rebaseline):** `tests/unit/ui/quick-start-api-keys-link-5695.test.ts` now tolerates Prettier splitting a multi-line `<Link href=...>` so the `step1Desc` regex matches the `/dashboard/api-manager` link instead of skipping to `step2`'s single-line `/dashboard/providers` link (test was brittle, not the code). Also rebaselines 5 files that grew via already-merged release-tip PRs in `config/quality/file-size-baseline.json` (`ApiManagerPageClient` 3017→3058, `OAuthModal` 969→989, `cliRuntime` 1090→1100, `webProvidersA` 805→809, `deepseek-web.test` 1081→1092), with shrink tracked in #3501. ([#6093](https://github.com/diegosouzapw/OmniRoute/pull/6093))
-- **release close (LEDGER-4 base-red):** the `cline-pass` provider's `minimax-m3` registry entry was missing `supportsVision`, breaking the LEDGER-4 registry-consistency test (every `minimax-m3` entry must set `supportsVision` to match `lite.ts` — the model is multimodal). Flagged it to match every other `minimax-m3` entry (trae, bazaarlink, cline, ollama-cloud, ...). ([#6003](https://github.com/diegosouzapw/OmniRoute/pull/6003))
-- **release close (stryker `tap.testFiles` drift):** additional release-green cleanup clearing the `qoder` registry's `minimax-m3` `supportsVision` LEDGER-4 base-red and `stryker.conf.json`'s `tap.testFiles` drift. ([#6012](https://github.com/diegosouzapw/OmniRoute/pull/6012))
-- **install (pnpm 11+ support):** pnpm 11 introduced `ERR_PNPM_IGNORED_BUILDS` for native addon packages — without explicit `allowBuilds` approval, packages silently skip their build scripts and OmniRoute fails to start with missing native modules. Sets `allowBuilds=true` for all 13 native addon packages in `pnpm-workspace.yaml` (`@parcel/watcher`, `@swc/core`, `better-sqlite3`, `core-js`, `esbuild`, `keytar`, `koffi`, `libxmljs2`, `onnxruntime-node`, `protobufjs`, `sharp`, `tls-client-node`, `unrs-resolver`) and migrates `onlyBuiltDependencies` from the deprecated `package.json` field to a new `pnpm.json`. (commit 39349da18 — thanks @chirag127)
-- **refactor (Block J hot-path decomposition):** extract pure leaves with no behavior change from the executor, translator, combo, and SSE hot paths — orphaned executor tests moved to top-level so a runner collects them, and `handleComboChat`'s auto-strategy/target-timeout regions split into named helpers. ([#6063](https://github.com/diegosouzapw/OmniRoute/pull/6063), [#6049](https://github.com/diegosouzapw/OmniRoute/pull/6049), [#6036](https://github.com/diegosouzapw/OmniRoute/pull/6036), [#6030](https://github.com/diegosouzapw/OmniRoute/pull/6030), [#6020](https://github.com/diegosouzapw/OmniRoute/pull/6020), [#6018](https://github.com/diegosouzapw/OmniRoute/pull/6018), [#6017](https://github.com/diegosouzapw/OmniRoute/pull/6017), [#6016](https://github.com/diegosouzapw/OmniRoute/pull/6016), [#6015](https://github.com/diegosouzapw/OmniRoute/pull/6015), [#6014](https://github.com/diegosouzapw/OmniRoute/pull/6014), [#6008](https://github.com/diegosouzapw/OmniRoute/pull/6008), [#6006](https://github.com/diegosouzapw/OmniRoute/pull/6006), [#6000](https://github.com/diegosouzapw/OmniRoute/pull/6000), [#5999](https://github.com/diegosouzapw/OmniRoute/pull/5999), [#5994](https://github.com/diegosouzapw/OmniRoute/pull/5994), [#5967](https://github.com/diegosouzapw/OmniRoute/pull/5967), [#5962](https://github.com/diegosouzapw/OmniRoute/pull/5962), [#5960](https://github.com/diegosouzapw/OmniRoute/pull/5960), [#5947](https://github.com/diegosouzapw/OmniRoute/pull/5947), [#5949](https://github.com/diegosouzapw/OmniRoute/pull/5949), [#5940](https://github.com/diegosouzapw/OmniRoute/pull/5940), [#5932](https://github.com/diegosouzapw/OmniRoute/pull/5932))
-- **chore (quality/CI housekeeping):** rebaseline residual ESLint/cognitive-complexity/file-size drift accumulated over the v3.8.44 cycle, move orphaned executor tests to a top-level location so a runner actually collects them, harden the release pipeline with a test-masking pre-flight gate plus contributors/uncovered helpers, and make the `pr-evidence` FAIL output tell the author to push (a body edit alone does not re-run the gate). ([#5926](https://github.com/diegosouzapw/OmniRoute/pull/5926), [#5944](https://github.com/diegosouzapw/OmniRoute/pull/5944), [#5952](https://github.com/diegosouzapw/OmniRoute/pull/5952), [#6027](https://github.com/diegosouzapw/OmniRoute/pull/6027), [#5928](https://github.com/diegosouzapw/OmniRoute/pull/5928), plus a #5975-collateral test hardening pinning a seeded connection to direct egress in route-edge-coverage)
-- **docs (housekeeping):** normalize mixed-language documentation content, restore the OpenAPI coverage ratchet by documenting 9 newly-added routes, record Hard Rule #22 (cross-session safety — `git stash` + in-flight PR bans), and document the compression-engine's upstream sync policy for the RTK/Caveman engines. ([#6105](https://github.com/diegosouzapw/OmniRoute/pull/6105), [#5955](https://github.com/diegosouzapw/OmniRoute/pull/5955), [#5948](https://github.com/diegosouzapw/OmniRoute/pull/5948), plus docs-only commit 926b08aa8)
-
-### 🙌 Contributors
-
-Thanks to everyone whose work landed in v3.8.44:
-
-| Contributor                                                  | PRs / Issues                                                                                     |
-| ------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ |
-| [@adentdk](https://github.com/adentdk)                       | #5942                                                                                            |
-| [@anki1kr](https://github.com/anki1kr)                       | #5899, #5920, #5934, #6039, #6061, #6062, #6075, #6077, #6084, #6086, #6087, #6092, #6098, #6130 |
-| [@artickc](https://github.com/artickc)                       | #6119                                                                                            |
-| [@backryun](https://github.com/backryun)                     | #5988, #6095, #6106, #6140                                                                       |
-| [@chamdanilukman](https://github.com/chamdanilukman)         | #5972                                                                                            |
-| [@Chewji9875](https://github.com/Chewji9875)                 | #5913, #5957                                                                                     |
-| [@chirag127](https://github.com/chirag127)                   | #6145                                                                                            |
-| [@derhornspieler](https://github.com/derhornspieler)         | #6138                                                                                            |
-| [@dhaern](https://github.com/dhaern)                         | #6133                                                                                            |
-| [@doedja](https://github.com/doedja)                         | direct commit / report                                                                           |
-| [@DuyPrX](https://github.com/DuyPrX)                         | #5978                                                                                            |
-| [@fix2015](https://github.com/fix2015)                       | #6097                                                                                            |
-| [@ggiak](https://github.com/ggiak)                           | #5833                                                                                            |
-| [@hamsa0x7](https://github.com/hamsa0x7)                     | #5904                                                                                            |
-| [@hartmark](https://github.com/hartmark)                     | #5976                                                                                            |
-| [@imblowsnow](https://github.com/imblowsnow)                 | direct commit / report                                                                           |
-| [@janeza2](https://github.com/janeza2)                       | #5915, #6128, #6139                                                                              |
-| [@KooshaPari](https://github.com/KooshaPari)                 | #5870, #5974, #6035, #6046, #6050, #6061, #6073, #6076, #6086                                    |
-| [@mugni-rukita](https://github.com/mugni-rukita)             | #5998                                                                                            |
-| [@nickwizard](https://github.com/nickwizard)                 | #5905, #5907                                                                                     |
-| [@ofekbetzalel](https://github.com/ofekbetzalel)             | direct commit / report                                                                           |
-| [@pizzav-xyz](https://github.com/pizzav-xyz)                 | #6082                                                                                            |
-| [@powellnorma](https://github.com/powellnorma)               | direct commit / report                                                                           |
-| [@ricatix](https://github.com/ricatix)                       | #5993                                                                                            |
-| [@ryanngit](https://github.com/ryanngit)                     | #5995                                                                                            |
-| [@studyzy](https://github.com/studyzy)                       | #6043                                                                                            |
-| [@tantai-newnol](https://github.com/tantai-newnol)           | #5968                                                                                            |
-| [@Thinkscape](https://github.com/Thinkscape)                 | #6088, #6090, #6091                                                                              |
-| [@tn5052](https://github.com/tn5052)                         | #5965                                                                                            |
-| [@TuanNguyen0708](https://github.com/TuanNguyen0708)         | direct commit / report                                                                           |
-| [@vittoroliveira-dev](https://github.com/vittoroliveira-dev) | #5954                                                                                            |
-| [@waguriagentic](https://github.com/waguriagentic)           | direct commit / report                                                                           |
-| [@whale9820](https://github.com/whale9820)                   | #5936                                                                                            |
-| [@WslzGmzs](https://github.com/WslzGmzs)                     | direct commit / report                                                                           |
-| [@yusufrahadika](https://github.com/yusufrahadika)           | #5933                                                                                            |
-| [@diegosouzapw](https://github.com/diegosouzapw)             | maintainer                                                                                       |
-
----
-
-## [3.8.43] — 2026-07-02
-
-### ✨ New Features
-
-- **usage (quota percentages + provider USD drilldown):** `@@om-usage` and the HTTP usage endpoint now report personal API-key quotas as **remaining percentages** (USD amounts stay out of the command output), provider quota remaining is scaled by the configured quota cutoff so the protected reserve reads as 0% left, and the quota dashboard regains a **provider USD cost drilldown** (`/api/usage/provider-window-costs` + `ProviderUsdCostModal`, management-auth gated). Also honors **observed provider quota resets**: a same-`resetAt` reset (usage dropping back to the reset floor) is detected and preferred over stale recorded weekly events for provider USD windows and API-key USD quotas. New `src/lib/usage/providerWindowCosts.ts`. Regression guards: `tests/unit/provider-window-costs.test.ts`, `tests/unit/internal-usage-command.test.ts`, `tests/unit/api-key-usage-limits.test.ts`, `tests/unit/lib/quota-reset-events.test.ts`. Extracted from [#5863](https://github.com/diegosouzapw/OmniRoute/pull/5863) by [@Witroch4](https://github.com/Witroch4).
-
-- **dashboard (live WS behind reverse proxy):** the live dashboard WebSocket can now be fronted by a reverse proxy or Cloudflare Tunnel via `NEXT_PUBLIC_LIVE_WS_PUBLIC_URL` (e.g. `wss://ws.my-ai.com/live-ws`). The URL is honored both at build time (env inlined into the bundle) and at **runtime** for prebuilt Docker/npm images: the `/api/v1/ws?handshake=1` handshake now echoes a lazily-read `live.publicUrl` (only `ws://`/`wss://` values are accepted; anything else is rejected to `null`), and `useLiveDashboard` resolves the URL from that handshake before connecting, falling back to the previous `ws(s)://hostname:20129` default. Also documents `LIVE_WS_ALLOWED_HOSTS` and aligns the GitLab Duo OAuth scopes line in `.env.example` with the live config (`ai_features read_user`). Regression guard: `tests/unit/live-ws-public-url.test.ts` (5). ([#5877](https://github.com/diegosouzapw/OmniRoute/pull/5877) by [@ianriizky](https://github.com/ianriizky))
-
-- **providers (CLI profile auto-sync):** opt-in toggles to auto-regenerate CLI tool profiles after a provider model sync. When enabled, a model-catalog change (re)writes that tool's profile files from the live catalog — Codex (`~/.codex/*.config.toml`) and now **Claude Code** (`~/.claude/profiles/<name>/settings.json`, via an extracted `syncClaudeProfilesFromModels` + a new `claudeProfileAutoSync.ts` mirroring the Codex path). Both are **off by default** and never touch the active/default CLI config; they are backed by the `OMNIROUTE_AUTO_SYNC_CODEX_PROFILES` / `OMNIROUTE_AUTO_SYNC_CLAUDE_PROFILES` feature flags (DB/dashboard override > env > default "false") and additionally gated behind the existing `CLI_ALLOW_CONFIG_WRITES` write-guard. A **"CLI profile auto-sync"** card on the CLI Code dashboard toggles each (moved from the providers dashboard in [#5778](https://github.com/diegosouzapw/OmniRoute/pull/5778) — thanks [@rdself](https://github.com/rdself)). Regression guards: `tests/unit/claude-profile-auto-sync-gate.test.ts`, `tests/unit/codex-profile-auto-sync-gate.test.ts`, `tests/unit/cli/setup-claude.test.ts` (follow-up to #5737).
-
-- **cli (startup banner):** the `serve` startup banner now prints the running OmniRoute version (`v3.8.x`) beneath the ASCII logo, so the active version is visible at a glance without a separate `--version` call. Regression guard: `tests/unit/cli-serve-version-banner.test.ts`. Thanks [@chirag127](https://github.com/chirag127) ([#5752](https://github.com/diegosouzapw/OmniRoute/pull/5752)).
-
-- **analytics (subscription cost):** flat-rate providers now show **$0** in cost analytics instead of an inflated per-token estimate. Subscription / coding-plan providers (every cookie-web provider — ChatGPT Web, grok-web, … — plus the dedicated **Minimax Coding**, **Kimi Coding**, **GLM Coding**, **Alibaba Coding Plan**, and **Xiaomi MiMo** plans) bill a flat fee, not per token, yet still carry per-token pricing rows used for estimates — so the analytics dashboard over-reported their cost. A new flat-rate classifier (`src/lib/usage/flatRateProviders.ts`) is consulted by the analytics surfaces (analytics route, usage stats, usage analytics) via an opt-in `flatRateAsZero` cost option, so those providers read $0 while **budget / quota / routing keep estimating unchanged**. Deliberately NOT zeroed: `codex`/`cx` (OmniRoute actively tracks Codex token cost — Fast-tier multipliers, GPT-5.x pricing — and Codex can be a metered account), `byteplus` (metered ModelArk), `minimax-cn` (metered China API). Regression guard: `tests/unit/flat-rate-cost-5552.test.ts`. ([#5552](https://github.com/diegosouzapw/OmniRoute/issues/5552))
-
-- **mcp (RTK):** expose the RTK tool-output **learn/discover** workflow as two new MCP tools so an agent can grow the RTK filter catalog without leaving the protocol. `omniroute_rtk_discover` analyzes recently captured raw tool output (`discoverRepeatedNoise` / `suggestFilter`) and returns candidate noise patterns plus a suggested filter; `omniroute_rtk_learn` lists the captured command samples (`listRtkCommandSamples`) and resolves a command to its RTK filter id (`commandToId`). Both are read-only (scope `read:compression`), wrap the existing RTK discovery primitives (no new logic in the engine), and log to the MCP audit trail. Regression guard: `tests/unit/compression/rtk-mcp-tools.test.ts` (4). gaps v3.8.42 — T07.
-
-- **compression (LLM tier):** add an **opt-in, default-off LLM-tier compression engine** (`llm`) that condenses the prose of non-system messages via a pluggable chat-completion backend. It mirrors the `llmlingua` engine's contract but is **safe by construction**: the default backend is a **no-op pass-through** (the engine never mutates the payload until an operator both enables it _and_ wires a real backend via `setLlmCompressorBackend()`), it is **not** part of the default stacked pipeline, `enabled` defaults to `false`, fenced code blocks and `system` messages are never sent to the model, and every backend error **fails open** (the original segment/body is kept, never thrown). A `minTokens` floor skips small prompts. The real production backend is intentionally a VPS-validated follow-up (Hard Rule #18), exactly as the `llmlingua` worker backend is gated. New `open-sse/services/compression/engines/llm/index.ts`. Regression guard: `tests/unit/compression/llm-compressor-engine.test.ts` (8). gaps v3.8.42 — T05/C3.
-
-- **memory (typed decay):** add **opt-in typed memory decay** (TV6) so the conversational memory store stops accumulating stale `episodic` noise. Each injected memory now tracks an `access_count` + `last_accessed_at` (always-on, non-destructive telemetry; migration `111_memory_typed_decay`), and an **opt-in, default-off** sweep (`MEMORY_TYPED_DECAY_ENABLED`, default `false`) deletes memories that are past a **per-type TTL** and not immune. Only `episodic` decays by default (30d, env-tunable); `factual`/`procedural`/`semantic` are immune, and any memory accessed `>= 3` times earns access immunity (mirroring "guardrail/convention/decision never decay"). The decay clock re-bases on the last access, so used memories survive. Deletions reuse `deleteMemory` (SQLite + sqlite-vec + Qdrant stay in sync) and fail open; an optional periodic sweep is doubly opt-in (also needs `MEMORY_TYPED_DECAY_SWEEP_INTERVAL>0`). With the flag off nothing is ever deleted (Rule #20 spirit). New `src/lib/memory/typedDecay.ts`. Regression guard: `tests/unit/memory/typed-decay.test.ts` (15). gaps v3.8.42 — T10/TV6.
-
-- **dashboard (combos):** the named-combos editor now lets you **drag to reorder** the stacked-compression pipeline instead of only editing fixed-position steps. A new pure model (`src/shared/components/compression/compressionPipelineModel.ts`) owns add/remove/move/update with the engine→intensity invariant and a never-empty guarantee, and a `@dnd-kit/sortable` editor (`CompressionPipelineEditor.tsx`, matching the sidebar reorder pattern) replaces the inline list in `CompressionCombosPageClient`. Order persists through the existing combos endpoint. Regression guards: `tests/unit/compression-pipeline-model.test.ts` (11) + `tests/unit/ui/compression-pipeline-editor.test.tsx` (4). A dedicated `tests/e2e/compression-studio.spec.ts` (Tela A render + tab switch) closes the studios e2e gap the combo-live spec did not cover. gaps v3.8.42 — T06 + T03.
-
-- **compression (pipeline):** add an **opt-in, default-off per-engine circuit-breaker** to the stacked compression pipeline (T02). When an engine throws repeatedly **across requests**, its breaker opens and the stacked loops skip that engine (keeping the body verbatim for that step — fail-open) for a cooldown, then probe once (lazy half-open); success closes it, a failed probe re-opens it. This is distinct from the provider circuit-breaker (`src/shared/utils/circuitBreaker.ts`, provider-scoped + DB-persisted) — the new `pipelineEngineBreaker.ts` is engine-scoped, process-local, and adds zero DB/IO on the hot path. It composes with the existing per-request TV1 bail-out (which skips within a single request); the breaker adds cross-request memory. **Default off** (`COMPRESSION_PIPELINE_BREAKER_ENABLED=false`) → byte-identical to the pre-breaker pipeline (a throwing engine still propagates unless TV1 is separately enabled). Configurable per-call, per-`CompressionConfig`, or via env (`_THRESHOLD`/`_COOLDOWN_MS`). Regression guard: `tests/unit/compression/pipeline-circuit-breaker.test.ts` (9, incl. a throwing-engine integration); existing strategySelector/bail-out suites stay green. gaps v3.8.42 — T02 (2.2).
-
-- **compression (CCR):** the CCR retrieval-feedback (H8) is now **graduated** instead of a binary cliff. Previously a block retrieved `>= 3` times was flagged do-not-compress and everything below that stayed fully compressible. Now each prior retrieval raises a block's **effective `minChars` linearly** (`effectiveMinChars`), so frequently-retrieved content is compressed progressively less; the `>= 3` exclusion is preserved (as `Infinity`). The ramp is controlled by a `retrievalRampFactor` (default `2`, per-combo config or `COMPRESSION_CCR_RETRIEVAL_RAMP_FACTOR`); `1` reproduces the exact legacy binary behavior. Per-`(principal, hash)` isolation is unchanged. Regression guard: `tests/unit/compression/ccr-retrieval-ramp.test.ts` (12); existing CCR suites (51) stay green. gaps v3.8.42 — T08/H8.
-
-- **compression (cache-aware):** add an **opt-in, default-off usage-observed prefix freeze** (H5). The cache-aware guard previously preserved the system prompt only for providers a _static_ heuristic recognized as caching. It now also **learns** which system prompts actually recur: once a system prompt has been observed `>=` a threshold across requests, it is treated as a stable cacheable prefix and preserved from compression **even for providers the static check misses** — recovering prompt-cache hits that a prefix-compressing mode would otherwise bust. Content-addressed by a hash of the system prompt (OpenAI / Claude / Gemini shapes), in-memory + bounded, zero DB/IO; a "freeze" only _preserves_ the prefix, so it never mutates a payload. Default OFF (`COMPRESSION_PREFIX_FREEZE_ENABLED`, threshold `_THRESHOLD`); respects the `never` preserve-mode (never freezes). New `open-sse/services/compression/prefixFreeze.ts`, wired into `resolveCacheAwareConfig`. Regression guard: `tests/unit/compression/prefix-freeze.test.ts` (10); 44 existing cache-aware / preserve-mode tests stay green. gaps v3.8.42 — T08/H5.
-
-- **compression (read-lifecycle):** add a new **opt-in, default-off `read-lifecycle` engine** (H7) that collapses **stale/superseded file-Read tool results**. In agentic conversations the same file is Read repeatedly; an earlier Read becomes stale once the same path is **re-read** (superseded by a newer view) or **modified** by a later Write/Edit. The engine replaces those earlier Read results with a short stub — keeping only the current (last, un-superseded) Read intact — recovering the tokens the model no longer needs. Unlike `session-dedup` (identical-content) or `ccr` (reversible markers), this is semantic + **lossy**, so it is opt-in (`enabled` defaults `false`). Conservative by construction: matches only well-known Read/Write tool names, compares exact paths, collapses a Read only when a strictly-later invocation touches the same path, and **fail-opens** on any unexpected shape. Supports both the **Anthropic** (`tool_use`/`tool_result`) and **OpenAI** (`tool_calls` + `role:"tool"`) shapes. New `open-sse/services/compression/engines/readLifecycle/index.ts`. Regression guard: `tests/unit/compression/read-lifecycle.test.ts` (10). gaps v3.8.42 — T08/H7.
-
-- **observability (correlation IDs):** requests now carry a correlation id threaded through logs so a single request can be traced end-to-end across the pipeline. ([#5834](https://github.com/diegosouzapw/OmniRoute/pull/5834) — thanks @hartmark)
-
-- **cli (startup banner — boot time):** the `serve` ready banner now shows how long startup took, so slow-boot conditions are visible at a glance. ([#5799](https://github.com/diegosouzapw/OmniRoute/pull/5799) — thanks @ishatiwari21)
-
-- **api (quota-policy bypass scope):** add an **opt-in** API-key provider quota-policy bypass scope, so a designated key can be exempted from provider quota enforcement without disabling quotas globally. ([#5731](https://github.com/diegosouzapw/OmniRoute/pull/5731) — thanks @Witroch4)
-
-- **providers (Ollama local):** add a first-class **Ollama** local-provider card to the providers dashboard so the local LLM runtime can be configured like any other provider. ([#5712](https://github.com/diegosouzapw/OmniRoute/pull/5712) — thanks @diegosouzapw)
-
-- **codex (fallback profiles):** generate fallback CLI profiles for Codex-compatible models so compatible models get a usable profile automatically. ([#5701](https://github.com/diegosouzapw/OmniRoute/pull/5701) — thanks @skyzea1)
-
-- **api (response-body validation + failover):** add a **configurable response-body validation** step that can fail a target over to the next candidate when the upstream returns a structurally-invalid body (routing/#4985). ([#5684](https://github.com/diegosouzapw/OmniRoute/pull/5684) — thanks @diegosouzapw)
-
-- **providers (SenseNova):** complete the SenseNova free **Token Plan** — chat completions plus **Text-to-Image** (ported from 9router#2233). ([#5679](https://github.com/diegosouzapw/OmniRoute/pull/5679) — thanks @diegosouzapw)
-
-- **db (self-correcting context windows):** add **self-correcting model context-window overrides** so a model whose advertised context length is wrong is corrected automatically (models/#5004). ([#5667](https://github.com/diegosouzapw/OmniRoute/pull/5667) — thanks @diegosouzapw)
-
-- **routing (latency strategy):** optimize the latency routing strategy using observed per-target performance metrics for better candidate selection. ([#5629](https://github.com/diegosouzapw/OmniRoute/pull/5629) — thanks @KooshaPari)
-
-- **compression (preserveSystemPrompt mode):** add a `preserveSystemPrompt` mode enum (`always` | `whenNoCache` | `never`) with legacy back-compat, giving operators explicit control over when the system prompt is protected from compression (T05/C5). ([#5653](https://github.com/diegosouzapw/OmniRoute/pull/5653) — thanks @diegosouzapw)
-
-- **commandCode (vision):** add multimodal **image** support for Command Code vision models. ([#5557](https://github.com/diegosouzapw/OmniRoute/pull/5557) — thanks @Stazyu)
-
-- **compression (read-lifecycle engine):** T08/H7 (2.5) — an opt-in read-lifecycle engine that collapses superseded file reads so stale earlier reads of the same file are pruned from the context. ([#5754](https://github.com/diegosouzapw/OmniRoute/pull/5754) — thanks @diegosouzapw)
-
-- **compression (usage-observed prefix freeze):** T08/H5 (2.4) — opt-in prefix freeze driven by observed usage, keeping a stable cached prefix from being rewritten by downstream engines. ([#5744](https://github.com/diegosouzapw/OmniRoute/pull/5744) — thanks @diegosouzapw)
-
-- **compression (CCR retrieval-feedback ramp):** T08/H8 (2.3) — a graduated Context-Compression-Ratio retrieval-feedback ramp that tunes compression aggressiveness from retrieval signals. ([#5739](https://github.com/diegosouzapw/OmniRoute/pull/5739) — thanks @diegosouzapw)
-
-- **compression (per-engine circuit breaker):** T02 — an opt-in per-engine pipeline circuit-breaker that disables a misbehaving compression engine without failing the whole pipeline. ([#5735](https://github.com/diegosouzapw/OmniRoute/pull/5735) — thanks @diegosouzapw)
-
-- **compression (LLM-tier engine):** T05/C3 — an opt-in LLM-tier compression engine that uses a model pass for higher-ratio semantic compression. ([#5702](https://github.com/diegosouzapw/OmniRoute/pull/5702) — thanks @diegosouzapw)
-
-- **dashboard (compression pipeline editor):** T06/T03 — a drag-to-reorder compression pipeline editor plus a compression-studio e2e flow. ([#5727](https://github.com/diegosouzapw/OmniRoute/pull/5727) — thanks @diegosouzapw)
-
-- **memory (typed decay):** T10/TV6 — opt-in typed memory decay so aged, low-value memories fade on a per-type schedule. ([#5723](https://github.com/diegosouzapw/OmniRoute/pull/5723) — thanks @diegosouzapw)
-
-- **mcp (RTK tools):** T07 — expose the RTK learn/discover capabilities as first-class MCP tools. ([#5691](https://github.com/diegosouzapw/OmniRoute/pull/5691) — thanks @diegosouzapw)
-
-- **providers (CLI profile auto-sync):** opt-in CLI profile auto-sync toggles, including Claude Code auto-sync, so generated CLI profiles can track provider changes automatically. ([#5755](https://github.com/diegosouzapw/OmniRoute/pull/5755) — thanks @diegosouzapw)
-
-### 🔧 Bug Fixes
-
-- **fix(opencode):** stop fabricating `User-Agent: opencode/local` and `x-opencode-client: cli` headers when the client sends none — the executor-dedup refactor ([#5720](https://github.com/diegosouzapw/OmniRoute/pull/5720)) accidentally re-introduced header fabrication, violating the forward-only contract (inventing opencode-internal values risks upstream rejection). Restored to forward-only: those headers are emitted only when a real client source is present. Regression guard: `tests/unit/opencode-executor.test.ts`. (thanks @diegosouzapw)
-
-- **fix(executors):** `resolveEffectiveKey` returns `undefined` (not `""`) when no API key is present — a type-coercion cleanup ([#5798](https://github.com/diegosouzapw/OmniRoute/pull/5798)) changed `apiKey ?? ""` to satisfy the typechecker, silently mutating auth-key resolution semantics. Widened the return type to `string | undefined` and reverted the coercion so OAuth-only credentials resolve correctly. Regression guard: `tests/unit/refactor-buildHeaders-preamble.test.ts`. (thanks @diegosouzapw)
-
-- **fix(translator):** restore the terminal `message_delta` + `message_stop` on Responses→Claude streams — the doubled-tool-args dedup ([#5828](https://github.com/diegosouzapw/OmniRoute/pull/5828)) guarded the finish handler on the shared `state.finishReason`, which the openai-responses→openai leg sets first in the hub path, so the openai→claude leg dropped its terminal events and the stream ended after `content_block_delta`. The dedup now uses a dedicated `state.claudeFinishEmitted` flag. Regression guard: `tests/unit/claude-code-rendering-fixes.test.ts`. (thanks @diegosouzapw)
-
-- **fix(pricing):** add the Kiro `claude-sonnet-5` pricing row so the newly-catalogued model ([#5796](https://github.com/diegosouzapw/OmniRoute/pull/5796)) no longer reports `$0.00` usage. Regression guard: `tests/unit/catalog-updates-v3x.test.ts`. (thanks @diegosouzapw)
-
-- **fix(github):** keep Copilot access-token sessions active. GitHub Copilot device-flow accounts can hold a GitHub access token plus a short-lived Copilot token **without** a refresh token; the proactive health check treated that as terminal `no_refresh_token` and marked the connection expired minutes after login. The health check now keeps those sessions active, clears stale `no_refresh_token` state, and refreshes the Copilot sub-token when needed. Regression guard: `tests/unit/token-health-no-refresh-token-expired-5326.test.ts`. Extracted from [#5863](https://github.com/diegosouzapw/OmniRoute/pull/5863) by [@Witroch4](https://github.com/Witroch4).
-
-- **fix(kiro):** bound the Claude model-id dash→dot normalization to a 1–2 digit minor so date-suffixed ids (e.g. claude-opus-4-20250514) are no longer corrupted. (thanks @voravitl)
-
-- **fix(usage):** preserve (bounded) tool definitions in request logs even when the request body is truncated, so the request-details view can still show available tools. (thanks @noir017)
-
-- **fix(providers):** route OpenAI responses-only models to `/v1/responses` instead of 404ing on `/v1/chat/completions`. The curated `gpt-5.5-pro` / `gpt-5.4-pro` entries never worked (OpenAI only serves `*-pro` reasoning models via the Responses API), and "Test all models" surfaced the same 404s. The registry entries now carry `targetFormat: "openai-responses"` (reusing the existing per-model translation plumbing shared with `gh`/`codex`), `DefaultExecutor.buildUrl` swaps the `openai` endpoint to `/responses` in lockstep (honoring custom base URLs), and a `-pro` suffix heuristic covers dynamically-synced ids such as `o1-pro` / `gpt-5.2-pro` (same spirit as the gh executor's `/codex/i` routing, 9router#102). Legacy completions-only ids (e.g. `gpt-3.5-turbo-instruct`) are out of scope — they are not in the catalog and OmniRoute has no legacy `/v1/completions` upstream. Regression guard: `tests/unit/openai-responses-only-models-5842.test.ts` (8). Thanks [@maikokan](https://github.com/maikokan). ([#5842](https://github.com/diegosouzapw/OmniRoute/issues/5842))
-
-- **fix(image):** keep bare codex image aliases (e.g. `gpt-5.5`) resolving to the codex image pipeline even when a combo shares the same name. A chat combo named `gpt-5.5` used to shadow the bare image alias in `resolveImageRouteModel`, hijacking `/v1/images/*` requests to a chat target (regression path adjacent to [#5887](https://github.com/diegosouzapw/OmniRoute/issues/5887)); codex bare models are now reserved before bare-combo resolution, while non-codex aliases (e.g. `gpt-image-2`) remain user-shadowable (#3214/#3215 behavior preserved). Regression guard: `tests/unit/image-routes-combo-edits-3214-3215.test.ts` (9). ([#5902](https://github.com/diegosouzapw/OmniRoute/pull/5902) by [@KooshaPari](https://github.com/KooshaPari))
-
-- **fix(ci):** re-green the `release/v3.8.43` fast-gates queue — every PR→release was inheriting base-reds ([#5798](https://github.com/diegosouzapw/OmniRoute/issues/5798)). Five distinct blockers cleared: (1) stale `modelContextOverrides` entry in the `check:db-rules` intentionally-internal allowlist ([#5827](https://github.com/diegosouzapw/OmniRoute/pull/5827) allowlisted it while the [#5609](https://github.com/diegosouzapw/OmniRoute/issues/5609) fix re-exported it from `localDb.ts`; the re-export stays, the obsolete entry goes, classification guard re-pinned to 33); (2) `LIVE_WS_ALLOWED_HOSTS` / `NEXT_PUBLIC_LIVE_WS_PUBLIC_URL` documented in `docs/reference/ENVIRONMENT.md` (env/docs contract, from [#5877](https://github.com/diegosouzapw/OmniRoute/pull/5877)); (3) the Router Backends ADR's references to the not-yet-merged registry ([#5868](https://github.com/diegosouzapw/OmniRoute/pull/5868)) marked as landing-with-PR so `check:fabricated-docs --strict` passes; (4) `antigravity-429-quota-tdd` + `middleware-header-strip-5849` added to stryker `tap.testFiles` (`check:mutation-test-coverage`); (5) file-size / complexity / cognitive-complexity ratchets rebaselined with justification notes — all drift measured identical on the pristine tip and this PR (net-zero). Regression guard: `tests/unit/check-db-rules-classification.test.ts`. ([#5798](https://github.com/diegosouzapw/OmniRoute/issues/5798))
-
-- **providers (codex image auto-routing regression):** an unprefixed `gpt-5.5` request from a codex-only setup (no OpenAI connection) now correctly infers the `codex` provider again — the OpenAI static-catalog short-circuit in `resolveModelByProviderInference` was preempting the codex-preference block, so `gpt-5.5` (added to the OpenAI catalog) stopped auto-routing to Codex image generation. Users with an active OpenAI connection are unaffected (OpenAI stays default). Regression guard: `tests/unit/codex-gpt55-routing-5887.test.ts`. ([#5887](https://github.com/diegosouzapw/OmniRoute/issues/5887))
-
-- **api (proxy header hygiene):** upstream `x-middleware-*` control headers (emitted by providers hosted behind Next.js, e.g. synthetic.new) are now stripped from proxied responses instead of forwarded verbatim — forwarding `x-middleware-rewrite` made Next 16 throw `NextResponse.rewrite() was used in a app route handler` and return 500 despite a successful upstream call. Applies to both streaming and JSON paths. Regression guard: `tests/unit/middleware-header-strip-5849.test.ts`. ([#5849](https://github.com/diegosouzapw/OmniRoute/issues/5849))
-
-- **docs (pnpm global install):** replaced the unsupported `pnpm approve-builds -g` step with the install-time `pnpm add -g omniroute@latest --allow-build=better-sqlite3` flag across README + Setup Guide (and i18n mirrors), fixing native-build approval for pnpm v11 global installs. ([#5554](https://github.com/diegosouzapw/OmniRoute/issues/5554))
-
-- **dashboard (token badge):** the red "Token Expired" connection badge no longer flashes for OAuth refresh-capable providers (Antigravity/Gemini) whose access token merely lapsed but is auto-refreshed — it now shows only when the connection is terminally expired (`testStatus === "expired"`). Continuation of #5326. Regression guard: `tests/unit/ui/connection-row-token-badge-5836.test.tsx`. ([#5836](https://github.com/diegosouzapw/OmniRoute/issues/5836))
-
-- **db (auto backup toggle):** full pre-write SQLite backups now honor the persisted `backup.autoBackupEnabled` dashboard setting — previously only the `DISABLE_SQLITE_AUTO_BACKUP` env var was checked, so disabling auto-backup in the UI had no effect and ~70MB pre-write snapshots kept firing. Manual and pre-restore backups still always run. Regression guard: `tests/unit/db-backup-autobackup-setting-5871.test.ts`. ([#5871](https://github.com/diegosouzapw/OmniRoute/issues/5871))
-
-- **providers (auto/ routing for custom providers):** custom OpenAI-/Anthropic-compatible providers (dynamic `*-compatible-*` connection IDs) are no longer excluded from `auto/` routing — the Auto-Combo virtual factory previously skipped any connection whose provider was absent from the static registry. It now falls back to the connection's `defaultModel`. Regression guard: `tests/unit/auto-custom-provider-5873.test.ts`. ([#5873](https://github.com/diegosouzapw/OmniRoute/issues/5873))
-
-- **middleware (hook sandbox):** operator-authored pre-request hook code now runs inside a hardened Node `vm` sandbox (minimal context, no ambient globals/`process.env`, execution timeout, no `require`) instead of `new Function()` in the main process — closing the Hard Rule #3 / SonarCloud S1523 exposure. Regression guard: `tests/unit/middleware-hook-sandbox-5872.test.ts`. ([#5872](https://github.com/diegosouzapw/OmniRoute/issues/5872))
-
-- **mcp-server (auth forwarding):** the per-caller MCP identity forwarded via `withMcpHttpAuthContext` now wins over the static `OMNIROUTE_API_KEY` env fallback in the internal-fetch helpers (`apiFetch`, `omniRouteFetch`) — previously the env key was spread after the forwarded headers and clobbered the caller's `Authorization`. Regression guard: `open-sse/mcp-server/__tests__/httpAuthContext.test.ts`. ([#5819](https://github.com/diegosouzapw/OmniRoute/issues/5819))
-
-- **dashboard (Modal provider — two-field auth):** the Modal provider connection form now exposes **two fields — Token ID + Token Secret —** instead of a single API-key input, since Modal authenticates with `Authorization: Bearer <token-id>:<token-secret>`. The dashboard combines the two fields into the `id:secret` credential before saving (`combineModalCredential`, trims both parts), while a value pasted in the legacy single-field format keeps working verbatim (empty secret → passthrough), so existing saved connections need no migration; the key-help link points at Modal's token settings. Regression guard: `tests/unit/modal-credential-combine.test.ts` (5). ([#5881](https://github.com/diegosouzapw/OmniRoute/pull/5881), closes [#5446](https://github.com/diegosouzapw/OmniRoute/issues/5446)) Follow-up: the **Validation Model Id** field is now pre-filled for Modal with the same model the server-side validator probes (`Qwen/Qwen3-4B-Thinking-2507-FP8`, shared via `MODAL_DEFAULT_VALIDATION_MODEL_ID` in `src/shared/constants/modal.ts`), closing the last checklist item of #5446. Regression guard: `tests/unit/modal-validation-model-prefill.test.ts`.
-
-- **api (chat completions — early SSE keepalive gate):** the `/v1/chat/completions` route wrapped the response in the early-stream keepalive whenever `stream` was not explicitly `false`, so a client that omitted `stream` and asked for JSON (`Accept: application/json`) could receive premature SSE framing. The keepalive wrapper is now gated on an explicit `stream: true` in the body or an Accept header that forces SSE (`acceptHeaderForcesStream`); the parsed body is passed to the chat handler untouched, so the actual stream/JSON framing stays decided by `chatCore`/`resolveStreamFlag` — preserving OmniRoute's legacy streaming default when `stream` is omitted and the per-key `streamDefaultMode: "json"` opt-in. Regression guard: `tests/unit/chat-combo-live-test.test.ts` ("returns JSON without early SSE framing when stream is omitted and Accept is application/json"). ([#5866](https://github.com/diegosouzapw/OmniRoute/pull/5866) by [@rdself](https://github.com/rdself))
-
-- **fix(github):** drop a trailing assistant prefill before dispatching to GitHub Copilot chat to avoid 400 errors. (thanks @baslr)
-
-- **fix(oauth):** prevent cross-IdP account overwrites by disambiguating OAuth connections on `username` when present, not email alone. (thanks @KunN-21)
-
-- **fix(mitm):** best-effort revert privileged /etc/hosts entries on exit when a sudo password is cached, instead of always leaving orphaned state. (thanks @manhdzzz)
-
-- **providers (Kiro — Claude Sonnet 5):** the Kiro provider's model catalog was missing `claude-sonnet-5`, so the model could not be selected or routed even on accounts that already had access to it ("claude-sonnet-5 is not supported"). Added the model to the Kiro registry (`open-sse/config/providers/registry/kiro/index.ts`) as a 1M-context / 128K-output Claude model, mirroring the existing Claude entries; the registry `models[]` feeds both the model selector and the live CodeWhisperer `ListAvailableModels` fallback, so the model is now selectable and routable. Regression guard: `tests/unit/kiro-claude-sonnet-5-2267.test.ts`. (thanks [@openbioinfo](https://github.com/openbioinfo))
-
-- **settings (model aliases — self-heal after restart):** the Settings → Routing page showed "No exact-match aliases configured" after a server restart even though the aliases were persisted in the DB. Aliases are held in a module-local `_customAliases` map in `modelDeprecation.ts` that the boot path hydrates, but Next.js compiles the app-route module graph separately from the startup graph (the same webpack chunk-splitting class as #5312), so the `GET /api/settings/model-aliases` handler read a different, un-hydrated copy. The handler now self-heals: when its in-memory alias map is empty it reads `settings.modelAliases` from the DB (via the existing `getSettings()` db module — no raw SQL in the route) and repopulates the map, so the UI reflects the persisted aliases on the first GET after a restart. Follow-up: the root cause is now also fixed — the `_customAliases` store in `modelDeprecation.ts` is backed by `globalThis` (key `__omniroute_customAliases__`), so the startup and app-route module graphs share **one** store and the route reads the boot-hydrated aliases directly (the DB self-heal remains as a harmless fallback), mirroring the same `globalThis` singleton pattern already applied to `thinkingBudget.ts`/`backgroundTaskDetector.ts` (#5312). Regression guards: `tests/unit/model-aliases-settings-route-selfheal.test.ts` + `tests/unit/model-aliases-globalthis-5777.test.ts`. ([#5777](https://github.com/diegosouzapw/OmniRoute/pull/5777) — thanks [@jleonar2](https://github.com/jleonar2))
-
-- **providers (grok-cli token auto-refresh):** grok-cli OAuth tokens were never proactively refreshed before their real expiry. `mapTokens` hardcoded `expiresIn: 21600` (6 h) regardless of the token's actual lifetime, so the persisted `expiresAt` was always "now + 6 h" and the proactive `tokenHealthCheck` sweep (refresh when `expiresAt - now < 5 min`) fired 6 h after import instead of shortly before the token really expired. `mapTokens` now computes `expiresIn` from the authoritative `expires_at` field in `~/.grok/auth.json` (ISO → epoch-seconds) with a fallback to the JWT `exp` claim (payload-only decode, no signature trust); the hardcoded `21600` is kept only when neither is present. An already-expired token (real `expires_at`/`exp` in the past) is now clamped to a positive `expiresIn` via `Math.max(1, …)`, so the import route stores a near-future `expiresAt` and AutoCombo refreshes the connection instead of reading a past date and excluding it outright. Regression guards: 5 cases in `tests/unit/grok-cli-oauth.test.ts` (JWT `exp`, JSON `expires_at`, the `21600` fallback, and the two expired-token clamps). ([#5775](https://github.com/diegosouzapw/OmniRoute/pull/5775) — thanks [@Chewji9875](https://github.com/Chewji9875))
-
-- **compression (CCR retrieve via MCP HTTP):** the `omniroute_ccr_retrieve` MCP tool returned `"CCR block not found"` for blocks stored earlier in the **same** session when called over the MCP HTTP transports (SSE / Streamable HTTP), e.g. from OpenCode in a Docker deployment. Compression stores each block keyed by the API-key principal (`String(apiKeyInfo.id)`), but the tool resolved the caller via `extra.authInfo.clientId` — which the MCP SDK never populates for API-key auth — so it fell back to `"anonymous"` and the compound store-key never matched. The retrieve tool now resolves the caller's API-key id from the MCP HTTP auth context (`httpAuthContext`) using the **same** `getApiKeyMetadata` lookup used at storage time, so retrieval matches storage. Cross-tenant IDOR isolation is preserved: a different key resolves to a different id → miss; no key → the anonymous bucket only. Regression guard: `tests/unit/compression/ccr-mcp-principal-5649.test.ts` (extraction, distinct-principal isolation, fail-closed, end-to-end store→retrieve). ([#5649](https://github.com/diegosouzapw/OmniRoute/issues/5649))
-
-- **compression (context-editing telemetry):** streaming responses now record Context Editing savings. Anthropic surfaces `context_management.applied_edits[]` on the final `message_delta` snapshot of an SSE stream, but the streaming reconstruction (`buildStreamSummaryFromEvents` → Claude branch) dropped `context_management` entirely **and** no telemetry hook was wired into the streaming finalizer — so the delegated server-side context-clear savings (`cleared_input_tokens` / `cleared_tool_uses`) surfaced under engine `context-editing` in compression analytics **only for non-streaming responses**. The collector now preserves `context_management` from the final snapshot (last-writer-wins), and `onStreamComplete` mirrors the non-streaming `recordContextEditingTelemetryHook` (best-effort, Claude-only, HTTP 200 only). Purely additive telemetry — no payload mutation, no new env flag, no behavior change when the stream carries no `context_management`. Regression guard: `tests/unit/context-editing-streaming-telemetry.test.ts` (3). gaps v3.8.42 — T01 (5.1).
-
-- **proxy (relay test diagnostics):** the Proxy Pool "Test" button showed a bare "failed" with **nothing in the server logs** when a **relay** (Vercel / Deno / Cloudflare) _responded_ with a non-200 — e.g. a `401` from an auth-token mismatch after a `STORAGE_ENCRYPTION_KEY` rotation. The relay success-path response set `success: false` but carried no `error` field, so the dashboard had no reason to show and the server logged nothing. The test now returns an actionable `error` (the HTTP status, plus an auth/encryption-key hint on `401`/`403`) and logs the failure server-side; the SOCKS5/HTTP proxy path now logs its failures too. Shaping extracted to `buildRelayTestResult` with a regression guard (`tests/unit/proxy-relay-test-error-5716.test.ts`). Note: this surfaces _why_ a relay fails — it does not repair a genuinely broken/misconfigured relay. ([#5716](https://github.com/diegosouzapw/OmniRoute/issues/5716))
-
-- **fix(dashboard):** add error boundaries for the Combos and MITM Proxy pages so a render error shows a recoverable fallback instead of a blank page. (thanks @wahyuzero)
-
-- **providers (onboarding wizard — unsupported validation):** adding a provider whose credentials have **no live validator** (LMArena, PiAPI, …) failed silently in the Add-Provider wizard. The `/api/providers/validate` endpoint returns `HTTP 400 + { unsupported: true }` for these (#5565/#5567), but the wizard's `validateOnboardingApiKey` ran it through `expectOk`, which threw on the non-200 — so the flow jumped to the error step and the connection was **never created**. The wizard now treats `unsupported: true` as a non-blocking "can't verify" and proceeds to save, mirroring `AddApiKeyModal`. Regression guard added to `tests/unit/provider-onboarding-wizard.test.ts`. (related to [#5692](https://github.com/diegosouzapw/OmniRoute/issues/5692))
-
-- **dashboard (Quick Start step 1):** the Quick Start "Create API key" step told users to "Go to **Endpoint** → Registered Keys" and linked to `/dashboard/endpoint`, but API keys are created on the **API Manager** page (`/dashboard/api-manager`, sidebar "API Keys") — the Endpoint page has no "Registered Keys" section, so users followed the link and could not find where to create a key. Step 1 now reads "Go to **API Keys**" and links to `/dashboard/api-manager`. Regression guard: `tests/unit/ui/quick-start-api-keys-link-5695.test.ts`. ([#5695](https://github.com/diegosouzapw/OmniRoute/issues/5695))
-
-- **providers (DashScope/Alibaba setup link):** the "Get API key" link for the **Alibaba** and **Alibaba (China)** providers pointed at the bare API host (`dashscope-intl.aliyuncs.com` / `dashscope.aliyuncs.com`), which returns **404** in a browser — API hostnames have no homepage. Repointed to the consoles where keys are actually issued: `bailian.console.alibabacloud.com` (international) and `dashscope.console.aliyun.com` (China). Same class as #5572/#5574/#5576; regression guard added to `tests/unit/provider-setup-links-5572.test.ts`. ([#5665](https://github.com/diegosouzapw/OmniRoute/issues/5665))
-
-- **thinking / runtime-config (module-graph fix):** operator-configured proxy settings that are hydrated at **boot** but read **per-request** were silently ignored in production. Next.js compiles `instrumentation.ts` (boot hydration via `applyRuntimeSettings` / restore hooks) as a **separate webpack module graph** from the app-route / open-sse executors, so a module-local `let _config` singleton is **duplicated** — the boot copy is hydrated but the request path reads a different, un-hydrated copy. Live VPS validation proved the Thinking-Budget hydration ran to completion at boot yet `base.ts` still saw the `passthrough` default (this is why #5312 fix A stayed broken even after the boot-wiring fix). Fixed by backing the singletons with `globalThis` (the pattern `systemPrompt.ts` already uses for the Global System Prompt, #2470), so all module-graph copies share one instance: **`thinkingBudget.ts`** (the dashboard Thinking-Budget mode now reaches the executor), **`backgroundTaskDetector.ts`** (the opt-in background-model degradation now actually fires on requests), and **`systemTransforms.ts`** (operator pipeline overrides now reach the request path). `payloadRules.ts` was already safe (it lazily self-loads from the DB per request, #2986). Regression guards: `tests/unit/thinking-budget-globalthis-5312.test.ts` + `tests/unit/runtime-config-globalthis-5312.test.ts` (assert globalThis-backed sharing; a module-local `let` fails them). ([#5312](https://github.com/diegosouzapw/OmniRoute/issues/5312))
-
-- **thinking (Claude OAuth):** restore the proxy-level **Thinking-Budget** config on startup. The dashboard mode (`auto`/`custom`/`adaptive`) is persisted under `settings.thinkingBudget`, but the boot-time hydration (`hydrateThinkingBudgetConfig`) was only wired into `src/server-init.ts` — an **unused module that never runs in production** — so the operator's choice silently reverted to the `passthrough` default on every restart (#5312 fix A was non-functional, even though its direct unit test passed). The hydration now runs in the real boot path (`src/instrumentation-node.ts`), alongside the Global System Prompt restore. Surfaced by live Anthropic-OAuth validation on the VPS. Regression guard: `tests/unit/thinking-budget-boot-wiring-5312.test.ts` (asserts the production boot module calls the hydration, not just the function in isolation). ([#5312](https://github.com/diegosouzapw/OmniRoute/issues/5312))
-
-- **translator/chatcore (hardening):** re-apply two defensive review-fixes that were dropped in a branch rebuild before #5661 / #5662 landed. (1) `mergeConsecutiveSameRoleContents` (OpenAI→Gemini) now shallow-copies each entry and its `parts` array instead of pushing the input reference, so the consecutive-same-role merge never mutates the caller's objects. (2) `defaultClaudeToolType` (Claude tool defaults) now passes any non-object array entry (`null` / primitive) through unchanged instead of spreading it into a fabricated `{ type: "custom", … }` tool. No behavior change on real payloads (Gemini contents are freshly built; Claude tools are always objects); both properties are now locked by regression tests in `tests/unit/translator-gemini-consecutive-role-2191.test.ts` and `tests/unit/claude-tool-type-default-2195.test.ts`.
-
-- **providers (grok-cli):** truncate the tool list when it exceeds a provider's hard limit, so grok-cli (`cli-chat-proxy.grok.com`, max 200 tools) no longer rejects requests with `Maximum tools limit reached`. Adds a proactive `PROVIDER_TOOL_LIMITS` map (`grok-cli: 200`, consulted before the reactive cache), a corrected limit-parsing regex that captures the stated maximum (`200`) instead of the supplied count (`427`), and removes the broken `< MAX_TOOLS_LIMIT` truncation gate so truncation now fires whenever `tools.length` exceeds the effective limit. Regression guard: `tests/unit/tool-limit-detector.test.ts`. ([#5563](https://github.com/diegosouzapw/OmniRoute/pull/5563) — thanks @Chewji9875)
-
-- **resilience (antigravity):** record model lockout for Antigravity `429 rate_limit_exceeded` errors. Antigravity's `"Resource has been exhausted (e.g. check quota)."` text was matched by overly broad `QUOTA_PATTERNS` and misclassified as `QUOTA_EXHAUSTED`, so the combo retry path was skipped (`providerExhausted`) and the model was never cooled down. Classification now prefers the structured error code — `classifyErrorText(structuredError?.code || errorText)` — so a `rate_limit_exceeded` code is treated as a transient rate-limit (not quota), and the two broad patterns (`/resource.*exhaust/i`, `/check.*quota/i`) were replaced with Antigravity-specific ones (`individual quota reached`, `enable overages`). ([#5579](https://github.com/diegosouzapw/OmniRoute/pull/5579) — thanks @Chewji9875)
-
-- **providers (OpenAI-compatible):** Codex MCP / `tool_search` deferred discovery (and `apply_patch`) now works through a **Custom OpenAI-compatible provider**. When such a provider received a Responses-API-shaped request that carried MCP / `tool_search` tools, OmniRoute downgraded it to `/chat/completions`, which drops the deferred tool-discovery mechanism — so the MCP namespaces never surfaced to the model and `apply_patch` was mis-handled as a JSON tool. The executor now detects a Responses-shaped request (`input` / `previous_response_id` / `max_output_tokens` / `reasoning`) that carries `namespace` / `tool_search*` tools and routes it to the upstream `/responses` endpoint natively instead of downgrading (it can also be forced via `providerSpecificData._omnirouteForceResponsesUpstream`). This is a distinct code path from the official Codex OAuth backend (#3033 / #4539, which the earlier fix never touched). Regression guard: `tests/unit/executor-default-base.test.ts`. Thanks to @KooshaPari for the fix. ([#5483](https://github.com/diegosouzapw/OmniRoute/issues/5483))
-
-- **dashboard (routing):** selecting the **fusion** strategy on the Global Routing defaults tab now reveals fusion-specific config instead of only the generic resilience fields. Fusion's engine knobs — `judgeModel` (the model that synthesizes the panel answers) and `fusionTuning` (`minPanel` / `stragglerGraceMs` / `panelHardTimeoutMs`) — already existed in the schema and the per-combo editor, but the Global Routing tab never surfaced them, so picking "fusion" there was effectively a no-op. The fields are now shown (extracted into a new `FusionDefaultsFields` component). Voting / aggregation-mode / per-provider-weight are intentionally not shown — those don't exist in the fusion engine. Regression guard: `tests/unit/ui/combo-defaults-fusion-5598.test.tsx`. ([#5598](https://github.com/diegosouzapw/OmniRoute/issues/5598))
-
-- **dashboard (free proxy pool):** the free proxy pool "Sync All" no longer fails silently with `Total: 0`. Three fixes: (1) the **IPLocate** source fetched `…/protocols/<proto>.json` and parsed it as JSON, but the upstream list is plain text (`<proto>.txt`, one `ip:port` per line) — every protocol 404'd / failed to parse; it now fetches `.txt` and parses the line list. (2) The sync route **isolates each source** in its own try/catch, so one provider throwing (e.g. a TLS handshake failure) no longer aborts the whole sync — the working sources still populate the pool. (3) The UI now **surfaces the per-source errors** the route already returns, instead of discarding the response, so a partial/empty sync explains itself. Regression guards: `tests/unit/free-proxy-providers.test.ts`, `tests/unit/proxy-pool-sync-4878.test.ts`, `tests/unit/free-pool-tab.test.tsx`. ([#5595](https://github.com/diegosouzapw/OmniRoute/issues/5595))
-
-- **dashboard (memory engine):** the memory engine status page no longer mixes English and Portuguese. The embedding / vector-store / rerank **status detail strings** were hardcoded in Portuguese in the backend (`resolveEmbeddingSource`, `engineStatus`), e.g. `auto: nenhuma fonte de embedding disponível` and `sqlite-vec ativo, dim=…`, while the surrounding UI labels render from the English i18n bundle — so an English user saw a half-translated page. The backend detail strings are now English (`auto: no embedding source available`, `sqlite-vec active, dim=…`, etc.), matching the rest of the page. Regression guard: `tests/unit/memory-engine-status.test.ts`. ([#5596](https://github.com/diegosouzapw/OmniRoute/issues/5596))
-
-- **providers (cline):** stop falsely mapping valid **Cline** (OAuth) responses to `502 empty_choices` + account cooldown. `detectMalformedNonStream` only recognized `choices[].message.content` as a **string**, but some OpenAI-compatible upstreams — Cline via OAuth among them — return `content` as an **array of Anthropic-style text blocks** inside an OpenAI envelope. A non-empty response (recvBytes > 0) was therefore classified as `empty_choices` and turned into a 502 that also cooled the account down. The malformed-response detector now also treats a content array carrying at least one non-empty `text` block as real output. Regression guard: `tests/unit/diagnostics.test.ts`. ([#5559](https://github.com/diegosouzapw/OmniRoute/issues/5559))
-
-- **embedded services (Windows):** fix **CLIProxyAPI install failing instantly with `spawn unzip ENOENT`** on Windows. The binary extractor spawned `unzip`, which is not a Windows system command — it only ships inside Git for Windows' `usr/bin`, a directory Node's `spawn` PATH never sees, so even users with Git installed hit the error. On Windows the extractor now uses PowerShell's built-in `Expand-Archive` (via `execFileAsync`, no shell — paths pass as a single non-interpreted arg, with `''`-escaping + `-LiteralPath` as defense in depth); other platforms keep using `unzip`. This is distinct from #5379 (that was `npm.cmd` needing `shell: true`). Regression guard: `tests/unit/binary-manager-extract-zip-5590.test.ts`. ([#5590](https://github.com/diegosouzapw/OmniRoute/issues/5590))
-
-- **storage (daemon):** fix a Node.js **out-of-memory crash on startup** when `storage.sqlite` grows large (~170 MB+). The boot-time call-log cleanup (`cleanupExpiredLogs` → `rotateCallLogs`) ran two **unbounded `SELECT … FROM call_logs … .all()`** queries — `listReferencedArtifacts` (every artifact path) and `deleteCallLogsBefore` (every id before the retention cutoff). `node:sqlite`'s `StatementSync.all()` materializes the entire result set as JS objects at once, so on a large table the V8 heap blew up and the process crashed before binding (`FATAL ERROR: … heap out of memory`, native frame `node::sqlite::StatementSync::All`). Both queries now page through `call_logs` in bounded 5 000-row chunks (new `src/lib/usage/callLogsBoundedQueries.ts`), keeping peak memory flat regardless of table size — no more manual `--max-old-space-size` bump required. Regression guard: `tests/unit/call-log-oom-unbounded-5618.test.ts`. ([#5618](https://github.com/diegosouzapw/OmniRoute/issues/5618))
-
-- **dashboard (provider setup):** fix three provider setup links that pointed at 404 pages. **Ollama Cloud** / **ollama-search** linked to `ollama.com/settings/api-keys` → corrected to `ollama.com/settings/keys` (the page moved; Ollama Cloud is a real keyed service, so the field stays). **SearchAPI** linked to the bare `searchapi.io/docs` (404) → `searchapi.io/docs/google`. **You.com** linked to `you.com/docs/search/overview` (404) → `you.com/business/api/` (the developer portal). All three replacements were verified live. Regression guard: `tests/unit/provider-setup-links-5572.test.ts`. ([#5572](https://github.com/diegosouzapw/OmniRoute/issues/5572), [#5574](https://github.com/diegosouzapw/OmniRoute/issues/5574), [#5576](https://github.com/diegosouzapw/OmniRoute/issues/5576))
-
-- **providers (AI/ML API):** the model-import step now loads the **live** AI/ML API catalog (400+ models) instead of falling back to a stale 6-model seed. The registry had no `modelsUrl`, so the route silently used the bundled catalog with an "API unavailable — using local catalog" warning even when the key was valid. AI/ML API exposes its full catalog at the public, **auth-free** `https://api.aimlapi.com/models` endpoint (a bare array of `{ id, type, info }`, distinct from the OpenAI-compat `/v1/models`); it's now wired into the models route's discovery config, with the bundled catalog kept as the offline fallback. Regression guard: `tests/unit/provider-models-route.test.ts`. ([#5570](https://github.com/diegosouzapw/OmniRoute/issues/5570))
-
-- **providers (CablyAI):** mark **CablyAI** deprecated — `cablyai.com` no longer resolves (DNS `NXDOMAIN`, verified 2026-06-30); the domain is gone. The provider is removed from the models-route discovery config so the import step returns a clean error instead of an **unhandled 500 crash** (the dead-domain fetch threw with no local-catalog fallback), and the registry entry now carries `deprecated: true` / `riskNoticeVariant: "deprecated"` so the dashboard flags existing connections (same treatment as the shut-down `glhf`/`kluster.ai` gateways). Regression guard: `tests/unit/provider-models-route.test.ts`. ([#5568](https://github.com/diegosouzapw/OmniRoute/issues/5568))
-
-- **dashboard (provider add):** non-LLM search/agent providers no longer fail the model-import step with a red `Provider <id> does not support models listing`. **Jules** (Google Labs coding agent), **linkup-search** (Linkup web search), **ollama-search** (Ollama Cloud web search — distinct from the local Ollama LLM), and **searchapi-search** (SearchAPI SERP) have no `/v1/models` endpoint, so the import surfaced a failure for expected behavior. Each now ships a small static catalog of its selectable capability ids — Linkup's `fast`/`standard`/`deep` search depths, SearchAPI's `google`/`bing`/`youtube`/… engines, a single Jules/Ollama-web-search entry — so the import step returns a usable list (`source: local_catalog`) instead of an error. Regression guard: `tests/unit/provider-models-route.test.ts`. ([#5569](https://github.com/diegosouzapw/OmniRoute/issues/5569), [#5571](https://github.com/diegosouzapw/OmniRoute/issues/5571), [#5573](https://github.com/diegosouzapw/OmniRoute/issues/5573), [#5575](https://github.com/diegosouzapw/OmniRoute/issues/5575))
-
-- **dashboard (provider add):** providers without a live key/cookie validator (e.g. **LMArena (Free)**, **PiAPI**) can now be saved. The Add-connection modal treated the backend's `"Provider validation not supported"` response as a hard **Invalid** state and blocked Save entirely, leaving those providers impossible to add. The validate route now returns `unsupported: true` alongside the message, and the modal treats that as a non-blocking warning — the "Check" badge still shows "validation not supported" (informational), but Save persists the credential as-is. Regression guards: `tests/unit/ui/add-api-key-modal-unsupported-save-5565.test.tsx` (Save proceeds) and `tests/unit/providers-validate-route.test.ts` (wire-format). ([#5565](https://github.com/diegosouzapw/OmniRoute/issues/5565), [#5567](https://github.com/diegosouzapw/OmniRoute/issues/5567))
-
-- **providers (codex):** fix the **Codex Responses WebSocket** path (`/v1/responses`), which regressed in v3.8.40 with a client-visible `Invalid JSON body` and bypassed the configured proxy. (1) #5591 — PR #5237 bumped the impersonation TLS profile to `chrome_149`, but `wreq-js@2.3.1` only supports up to `chrome_147`; the unknown profile produced a degenerate fingerprint and ChatGPT rejected the upstream upgrade. The Codex WS path is reverted to the proven `chrome_142` (the v3.8.39 value), and the over-bumped `grok-web`/`claude-web` profiles (masked by their circuit-breaker but silently dropping TLS impersonation) are restored to `chrome_146`. A new regression guard asserts every configured `chrome_*` profile exists in the installed `wreq-js` typings (`tests/unit/tls-profiles-valid-5591.test.mjs`). (2) #5611 — the upstream `wreq-js.websocket()` connect ignored the Proxy Registry, so a no-direct-egress Docker container failed with a DNS error; the prepare route now resolves the Global/provider proxy and threads it through to the WS connect. Regression guard in `tests/unit/responses-ws-proxy.test.mjs`. ([#5591](https://github.com/diegosouzapw/OmniRoute/issues/5591), [#5611](https://github.com/diegosouzapw/OmniRoute/issues/5611))
-
-- **providers (GLM):** GLM **5.1 / 5.2** now keep the `system` role instead of having the system prompt folded into the first user turn. `roleNormalizer.ts` matched every `glm*` id with a blanket `startsWith("glm")` / `startsWith("glm-")` prefix, so the next-generation models — which z.ai documents as supporting the `system` role (GLM > 5.0) — were normalized as if they rejected it, degrading instruction-following. The matcher is now version-aware: it strips the system role only for bare `glm`, the 4.x family, and the 5.0 generation, and preserves it for `glm-5.1`/`glm-5.2` (and the Fireworks `glm-5p1` point alias). The ZenMux vendor-prefixed `z-ai/glm-*` compressed-history rule and the ERNIE rule are unchanged. Regression guards in `tests/unit/role-normalizer.test.ts`. ([#5610](https://github.com/diegosouzapw/OmniRoute/issues/5610))
-
-- **Security hardening follow-ups (v3.8.15):** the `auth_token` cookie now sets an explicit 30-day `maxAge` so sessions persist as intended (Seg3); the management bootstrap warns at boot when `INITIAL_PASSWORD` is left at the insecure `CHANGEME` default (Seg2); VS Code path-token endpoints (`/api/v1/vscode/raw/[token]`) emit a once-per-process security warning since the API key travels in the URL and can leak via logs/proxies (Seg4); the system version route resolves the real global install path via `npm root -g` instead of a hardcoded `/app` (Bug3); and auto-update mode detection segment-matches `node_modules` instead of substring-matching, eliminating false "global install" positives (Bug1).
-
-- **fix(cli):** rename the Node process title to `omniroute` so it shows correctly in ps/htop. (thanks @waguriagentic)
-
-- **dashboard (model picker):** guard against null model-alias values so opening Create Combo for a custom provider node no longer crashes. `ModelSelectModal`'s custom-provider branch filtered `modelAliases` entries with a raw `fullModel.startsWith(...)`, which threw a `TypeError` whenever an alias value was `null`/`undefined` (a stale/partial entry persisted to settings). The filter/map logic is extracted into a new `buildNodeAliasModels` helper (mirroring the sibling passthrough-alias guard, #485) that requires `typeof fullModel === "string"` before calling `.startsWith`. Regression guard: `tests/unit/model-select-null-alias-guard-2247.test.ts`. (thanks @wahyuzero)
-
-- **fix(translator):** strip orphaned tool results (results with no matching tool call) across request formats to avoid upstream 400s. (thanks @warelik)
-
-- **fix(kiro):** stop injecting a placeholder user turn on trailing tool-result turns so agentic loops aren't disrupted. (thanks @jetmiky)
-
-- **fix(translator):** prevent doubled tool arguments in OpenAI-to-Claude responses (duplicate finish_reason guard + string tool-input passthrough). (thanks @vishalrajv)
-
-- **codex (agent goal streams):** protect long-running agent goal streams so extended agent runs are no longer cut off prematurely. ([#5772](https://github.com/diegosouzapw/OmniRoute/pull/5772) — thanks @nguyenxvotanminh3)
-
-- **sse (zero-width markers):** strip zero-width markers from streamed responses, matching the non-streaming path so streamed output is byte-clean parity. ([#5857](https://github.com/diegosouzapw/OmniRoute/pull/5857) — thanks @DKotsyuba)
-
-- **usage (om-usage endpoint):** restore the `om-usage` HTTP endpoint. ([#5859](https://github.com/diegosouzapw/OmniRoute/pull/5859) — thanks @Witroch4)
-
-- **sse (stream readiness):** tune adaptive stream-readiness timeouts so slow-first-token upstreams are handled more reliably. ([#5767](https://github.com/diegosouzapw/OmniRoute/pull/5767) — thanks @nguyenxvotanminh3)
-
-- **security (provider node URL):** harden provider node URL validation. ([#5760](https://github.com/diegosouzapw/OmniRoute/pull/5760) — thanks @nguyenxvotanminh3)
-
-- **cli (Windows doctor):** correct `rootDir` resolution in `doctor.mjs` on Windows. ([#5845](https://github.com/diegosouzapw/OmniRoute/pull/5845) — thanks @arssnndr)
-
-- **providers (Antigravity):** fix a 429 hang on credit exhaustion and apply a precise reset-time model lockout instead of stalling — cleaned re-implementation of #5823. ([#5846](https://github.com/diegosouzapw/OmniRoute/pull/5846) — thanks @Chewji9875 / @diegosouzapw)
-
-- **providers (qwen-web):** unblock the validator and chat completion — the retired endpoint is replaced and the missing SPA version header is now sent. ([#5855](https://github.com/diegosouzapw/OmniRoute/pull/5855) — thanks @janeza2)
-
-- **providers (kimi-web):** migrate to the `www.kimi.com` Connect-RPC API after `kimi.moonshot.cn` was retired. ([#5858](https://github.com/diegosouzapw/OmniRoute/pull/5858) — thanks @janeza2)
-
-- **dashboard (CSRF):** unify the dashboard CSRF origin fallback so dynamic/public origins validate correctly. ([#5856](https://github.com/diegosouzapw/OmniRoute/pull/5856) — thanks @rdself)
-
-- **db (health check interval):** preserve `healthCheckInterval=0` across connection create/update instead of coercing it to a default. ([#5822](https://github.com/diegosouzapw/OmniRoute/pull/5822) — thanks @atomlong)
-
-- **sse (claude→codex streaming):** stop the reasoning-summary drop and duplicated deltas on claude→codex streaming — reasoning snapshots are now synthesized in TRANSLATE mode and the sequence-number watermark is tracked per-stream (#5786). ([#5832](https://github.com/diegosouzapw/OmniRoute/pull/5832) — thanks @diegosouzapw)
-
-- **deps (runtime):** add the missing runtime dependencies `@toon-format/toon` and `safe-regex` so the published package resolves them at runtime. ([#5771](https://github.com/diegosouzapw/OmniRoute/pull/5771) — thanks @chirag127)
-
-- **system (Windows auto-update):** route in-app auto-update `npm` calls through the win32 shell helper so updates run correctly on Windows (#5542). ([#5797](https://github.com/diegosouzapw/OmniRoute/pull/5797) — thanks @diegosouzapw)
-
-- **dashboard (validation badge):** show a neutral badge for unsupported validation and make OAuth error messages clickable links (#5442, #5486). ([#5795](https://github.com/diegosouzapw/OmniRoute/pull/5795) — thanks @diegosouzapw)
-
-- **providers (metadata):** correct stale/broken provider metadata (#5487, #5461, #5534, #5470). ([#5790](https://github.com/diegosouzapw/OmniRoute/pull/5790) — thanks @diegosouzapw)
-
-- **providers (local-catalog imports):** import intentional local-catalog-only providers instead of surfacing a 502 (#5460, #5465). ([#5787](https://github.com/diegosouzapw/OmniRoute/pull/5787) — thanks @diegosouzapw)
-
-- **proxyfetch (failover):** skip the failover retry for non-replayable request bodies so a consumed stream isn't re-sent empty. ([#5770](https://github.com/diegosouzapw/OmniRoute/pull/5770) — thanks @Ardem2025)
-
-- **batch (recovery):** persist batch item checkpoints during recovery so an interrupted batch resumes from where it left off. ([#5753](https://github.com/diegosouzapw/OmniRoute/pull/5753) — thanks @ag-linden)
-
-- **memory (Qdrant):** enabling Qdrant now activates it as the retrieval engine (the `auto` default never selected it) and adds inline guidance (#5597). ([#5741](https://github.com/diegosouzapw/OmniRoute/pull/5741) — thanks @diegosouzapw)
-
-- **chat (non-streaming aggregation):** harden non-streaming SSE aggregation against malformed upstream event sequences. ([#5746](https://github.com/diegosouzapw/OmniRoute/pull/5746) — thanks @rdself)
-
-- **sse (cooldown parsing):** the anti-thundering-herd guard now tolerates numeric-epoch cooldown values. ([#5747](https://github.com/diegosouzapw/OmniRoute/pull/5747) — thanks @diegosouzapw)
-
-- **api (body size):** raise the LLM API payload limit for the responses routes so larger requests aren't rejected. ([#5652](https://github.com/diegosouzapw/OmniRoute/pull/5652) — thanks @JxnLexn)
-
-- **providers (HuggingChat):** fix HuggingChat web-session routing (#5592). ([#5592](https://github.com/diegosouzapw/OmniRoute/pull/5592) — thanks @backryun)
-
-- **sse (heap pressure):** bound the chat hot-path heap — pressure-aware admission, response cap, and clone reductions — to avoid OOM under load (#5152). ([#5425](https://github.com/diegosouzapw/OmniRoute/pull/5425) — thanks @josevictorferreira)
-
-- **providers (M365 Copilot):** validate M365 Copilot web credentials. ([#5432](https://github.com/diegosouzapw/OmniRoute/pull/5432) — thanks @skyzea1)
-
-- **providers (chatgpt-web):** restore the dot-form Pro model ids. ([#5549](https://github.com/diegosouzapw/OmniRoute/pull/5549) — thanks @Thinkscape)
-
-- **security (error stacks):** avoid rendering error stacks in responses. ([#5624](https://github.com/diegosouzapw/OmniRoute/pull/5624) — thanks @KooshaPari)
-
-- **security (linkify):** restrict `linkifyText` hrefs to an explicit `http(s)` scheme allowlist. ([#948d2d7](https://github.com/diegosouzapw/OmniRoute/commit/948d2d7f2) — thanks @diegosouzapw)
-
-- **translator (doubled tool args):** prevent doubled tool-call arguments in the OpenAI→Claude translation path. ([#5828](https://github.com/diegosouzapw/OmniRoute/pull/5828) — thanks @diegosouzapw)
-
-- **translator (orphaned tool results):** strip orphaned tool-result turns across request formats so an upstream doesn't reject a tool result with no matching call. ([#5805](https://github.com/diegosouzapw/OmniRoute/pull/5805) — thanks @diegosouzapw)
-
-- **translator (Gemini/Claude hardening):** re-apply lost defensive hardening for the Gemini merge path and Claude tool defaults. ([#5706](https://github.com/diegosouzapw/OmniRoute/pull/5706) — thanks @diegosouzapw)
-
-- **kiro (tool-result turns):** stop injecting a placeholder user turn on tool-result turns, which corrupted otherwise-valid Kiro conversations. ([#5807](https://github.com/diegosouzapw/OmniRoute/pull/5807) — thanks @diegosouzapw)
-
-- **providers (Kiro catalog):** add `claude-sonnet-5` to the Kiro model catalog. ([#5796](https://github.com/diegosouzapw/OmniRoute/pull/5796) — thanks @diegosouzapw)
-
-- **oauth (connection disambiguation):** disambiguate OAuth connections on username so two different identity providers no longer overwrite each other. ([#5803](https://github.com/diegosouzapw/OmniRoute/pull/5803) — thanks @diegosouzapw)
-
-- **github (Copilot prefill):** drop the trailing assistant prefill for Copilot chat, which some Copilot models rejected. ([#5802](https://github.com/diegosouzapw/OmniRoute/pull/5802) — thanks @diegosouzapw)
-
-- **mitm (hosts cleanup):** clean up privileged `/etc/hosts` entries on exit when possible so a crashed/interrupted run doesn't leave stale redirects behind. ([#5808](https://github.com/diegosouzapw/OmniRoute/pull/5808) — thanks @diegosouzapw)
-
-- **dashboard (model picker):** guard null `modelAliases` values in the model picker so a connection with no aliases no longer throws. ([#5792](https://github.com/diegosouzapw/OmniRoute/pull/5792) — thanks @diegosouzapw)
-
-- **dashboard (error boundaries):** add error boundaries for the Combos and MITM Proxy pages so a render error no longer blanks the whole dashboard. ([#5788](https://github.com/diegosouzapw/OmniRoute/pull/5788) — thanks @diegosouzapw)
-
-- **cli (process title):** rename the running process title to `omniroute`. ([#5791](https://github.com/diegosouzapw/OmniRoute/pull/5791) — thanks @diegosouzapw)
-
-- **compression (context-editing telemetry):** record Context Editing telemetry on the streaming path, not just the non-streaming path. ([#5761](https://github.com/diegosouzapw/OmniRoute/pull/5761) — thanks @diegosouzapw)
-
-- **security (v3.8.15 hardening follow-ups):** land the Seg2/Seg3/Seg4/Bug3 hardening follow-ups from the v3.8.15 security review. ([#5512](https://github.com/diegosouzapw/OmniRoute/pull/5512) — thanks @diegosouzapw)
-
-### 📝 Maintenance
-
-- **docs (architecture):** add `docs/architecture/ROUTER_BACKENDS.md` — an ADR pinning down how the routing engines (`ts` native, `bifrost`, `cliproxy`, `9router`, VibeProxy-compatible) relate to each other along two orthogonal axes (lifecycle: in-process / supervised / external vs. relay selection backend), answering the architecture questions raised in [#5603](https://github.com/diegosouzapw/OmniRoute/issues/5603) (backend interface model, why CLIProxy spawns a process, feature-flag swapping, actionable route-contract errors). The typed router-backend registry the ADR describes lands separately via [#5868](https://github.com/diegosouzapw/OmniRoute/pull/5868). ([#5891](https://github.com/diegosouzapw/OmniRoute/pull/5891))
-
-- **tests (autoCombo):** stabilize the `getTaskFitnessWithSource identifies fitness_table as source for known models` unit test, which flaked whenever the models.dev capabilities DB was populated in CI: the fixture model `gpt-4o` is a real models.dev catalog id, so the fitness resolution chain returned `models_dev_tier` instead of the expected static `fitness_table` source. The fixture now uses `claude-sonnet` (a shortened alias absent from the models.dev catalog, matching the sibling resolution-chain test), which deterministically falls through to the static table — the exact `source` and score assertions are preserved (`0.95` = `FITNESS_TABLE.coding["claude-sonnet"]`). ([#5890](https://github.com/diegosouzapw/OmniRoute/pull/5890)) — thanks @KooshaPari
-
-- **oauth (dead-code removal):** delete the superseded legacy OAuth **service-class** hierarchy under `src/lib/oauth/services/`. The live OAuth flow runs through `src/lib/oauth/providers.ts` + `src/lib/oauth/providers/` (wired into the generic `oauth/[provider]/[action]` route); the old per-provider `class *Service extends OAuthService` implementations plus their barrel had **zero** production or test references. Removed `oauth.ts` (base class), `openai.ts`, `github.ts`, `claude.ts`, `codex.ts`, `antigravity.ts`, `qwen.ts`, `qoder.ts`, and the `index.ts` barrel (−1559 LOC). Kept the three still-live files that routes import **directly** by path: `kiro.ts` (Kiro import/exchange routes), `cursor.ts` (Cursor import route), and `codexImport.ts` (utility fns for the Codex bulk-import route). Proven safe by `typecheck:core` staying green (any live reference would fail the build) + a filesystem guard `tests/unit/oauth-legacy-services-removed.test.ts` pinning the removal against re-introduction. Salvage of the closed PR [#5039](https://github.com/diegosouzapw/OmniRoute/pull/5039). gaps v3.8.42 — T10 (5.7).
-
-- **refactor (god-file decomposition):** extracted pure leaf modules across db, sse, usage, api, memory, evals, models, resilience, and dashboard god-files (types/mappers/helpers/pure-transform leaves; behavior-preserving, test-guarded): db/providers, db/proxies, db/models, db/settings, usageAnalytics, migrationRunner ([#5714](https://github.com/diegosouzapw/OmniRoute/pull/5714), [#5717](https://github.com/diegosouzapw/OmniRoute/pull/5717), [#5705](https://github.com/diegosouzapw/OmniRoute/pull/5705), [#5709](https://github.com/diegosouzapw/OmniRoute/pull/5709), [#5722](https://github.com/diegosouzapw/OmniRoute/pull/5722), [#5721](https://github.com/diegosouzapw/OmniRoute/pull/5721)); sse openai-to-gemini / cursor-protobuf / rate-limit-headers / reasoning-tag ([#5824](https://github.com/diegosouzapw/OmniRoute/pull/5824), [#5794](https://github.com/diegosouzapw/OmniRoute/pull/5794), [#5736](https://github.com/diegosouzapw/OmniRoute/pull/5736), [#5734](https://github.com/diegosouzapw/OmniRoute/pull/5734)); usage families / callLogs / usageHistory / providerLimits ([#5782](https://github.com/diegosouzapw/OmniRoute/pull/5782), [#5725](https://github.com/diegosouzapw/OmniRoute/pull/5725), [#5728](https://github.com/diegosouzapw/OmniRoute/pull/5728), [#5730](https://github.com/diegosouzapw/OmniRoute/pull/5730)); api provider-models discovery / unified-catalog ([#5758](https://github.com/diegosouzapw/OmniRoute/pull/5758), [#5699](https://github.com/diegosouzapw/OmniRoute/pull/5699)); memory retrieval scoring ([#5733](https://github.com/diegosouzapw/OmniRoute/pull/5733)); evals golden-set suites ([#5740](https://github.com/diegosouzapw/OmniRoute/pull/5740)); modelsDevSync transform layer ([#5743](https://github.com/diegosouzapw/OmniRoute/pull/5743)); resilience settings split ([#5745](https://github.com/diegosouzapw/OmniRoute/pull/5745)); dashboard sidebarVisibility split ([#5683](https://github.com/diegosouzapw/OmniRoute/pull/5683)); executor shared-utility dedup + tests ([#5720](https://github.com/diegosouzapw/OmniRoute/pull/5720) — thanks @pizzav-xyz). — thanks @diegosouzapw
-
-- **chore (Bun script runner):** adopt Bun `1.3.10` as a locked, allow-listed **build/dev script runner** for a small set of validated TS gate/generator scripts (Node stays the published runtime): locked runtime dependency, CI script-checks + validated-scripts run under Bun, and a bun-safe pack validator. ([#5615](https://github.com/diegosouzapw/OmniRoute/pull/5615), [#5617](https://github.com/diegosouzapw/OmniRoute/pull/5617), [#5612](https://github.com/diegosouzapw/OmniRoute/pull/5612), [#5643](https://github.com/diegosouzapw/OmniRoute/pull/5643) — thanks @KooshaPari; docs [#5703](https://github.com/diegosouzapw/OmniRoute/pull/5703) — thanks @diegosouzapw)
-
-- **docs (sync & housekeeping):** i18n CHANGELOG mirror sync for the [3.8.43] section ([#5789](https://github.com/diegosouzapw/OmniRoute/pull/5789)); MCP tool count synced to 95 + routing-strategy count ([#5732](https://github.com/diegosouzapw/OmniRoute/pull/5732)); README faster/leaner install notes, refreshed metrics/badges, 17-strategy + Quota-Share listing, provider counts, and grammar fixes ([#5713](https://github.com/diegosouzapw/OmniRoute/pull/5713), [#5738](https://github.com/diegosouzapw/OmniRoute/pull/5738) — thanks @chirag127); security docs for banned-keyword/account-ban detection ([#5756](https://github.com/diegosouzapw/OmniRoute/pull/5756)) and the full LOCAL_ONLY route set + GHSA advisory + audit path ([#5748](https://github.com/diegosouzapw/OmniRoute/pull/5748)); relay backend-routing contract clarification ([#5621](https://github.com/diegosouzapw/OmniRoute/pull/5621) — thanks @KooshaPari); release-freeze scoped to `/generate-release` only ([#5839](https://github.com/diegosouzapw/OmniRoute/pull/5839)); `.editorconfig` repository standards ([#5879](https://github.com/diegosouzapw/OmniRoute/pull/5879) — thanks @shiva24082). — thanks @diegosouzapw
-
-- **test/ci (stabilization & ratchets):** guard the tsx/esm→esbuild boot transform ([#5773](https://github.com/diegosouzapw/OmniRoute/pull/5773)); align t3-web web-session metadata ([#5835](https://github.com/diegosouzapw/OmniRoute/pull/5835)); repoint the sidebar quota-share placement scan ([#5711](https://github.com/diegosouzapw/OmniRoute/pull/5711)); lightweight health probe for batch e2e ([#5651](https://github.com/diegosouzapw/OmniRoute/pull/5651) — thanks @KooshaPari); make release-green pre-flight gates visible + bounded ([#5644](https://github.com/diegosouzapw/OmniRoute/pull/5644)); stabilize nightly-mutation (tap.testFiles drift guard + anti-flake eps) ([#5682](https://github.com/diegosouzapw/OmniRoute/pull/5682)); close the QG v2 tail ([#5681](https://github.com/diegosouzapw/OmniRoute/pull/5681)); normalize check route paths on Windows ([#5613](https://github.com/diegosouzapw/OmniRoute/pull/5613) — thanks @KooshaPari); pass `sonar.projectVersion` to the SonarQube scan ([#5880](https://github.com/diegosouzapw/OmniRoute/pull/5880)); plus stryker `tap.testFiles` registration, compression-studio smoke re-anchoring, `rtk_discover` de-flake, and v3.8.43-cycle ratchet rebaselines (deadExports 225→227, complexity 1981→1982, cognitive-complexity 842→845, eslintWarnings 4121→4158→4199). — thanks @diegosouzapw
-
-- **refactor (oauth):** remove dead legacy OAuth service classes. ([#5838](https://github.com/diegosouzapw/OmniRoute/pull/5838) — thanks @diegosouzapw)
-
-### 🙌 Contributors
-
-Thanks to everyone whose work landed in v3.8.43:
-
-| Contributor                                                  | PRs / Issues                                                                                                         |
-| ------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------- |
-| [@ag-linden](https://github.com/ag-linden)                   | #5753                                                                                                                |
-| [@Ardem2025](https://github.com/Ardem2025)                   | #5770                                                                                                                |
-| [@arssnndr](https://github.com/arssnndr)                     | #5845                                                                                                                |
-| [@atomlong](https://github.com/atomlong)                     | #5822                                                                                                                |
-| [@backryun](https://github.com/backryun)                     | #5592                                                                                                                |
-| [@baslr](https://github.com/baslr)                           | direct commit / report                                                                                               |
-| [@Chewji9875](https://github.com/Chewji9875)                 | #5563, #5579, #5846                                                                                                  |
-| [@chirag127](https://github.com/chirag127)                   | #5738, #5771                                                                                                         |
-| [@DKotsyuba](https://github.com/DKotsyuba)                   | #5857                                                                                                                |
-| [@hartmark](https://github.com/hartmark)                     | #5834                                                                                                                |
-| [@ishatiwari21](https://github.com/ishatiwari21)             | #5799                                                                                                                |
-| [@janeza2](https://github.com/janeza2)                       | #5855, #5858                                                                                                         |
-| [@jetmiky](https://github.com/jetmiky)                       | direct commit / report                                                                                               |
-| [@josevictorferreira](https://github.com/josevictorferreira) | #5425                                                                                                                |
-| [@JxnLexn](https://github.com/JxnLexn)                       | #5652                                                                                                                |
-| [@KooshaPari](https://github.com/KooshaPari)                 | #5613, #5621, #5624, #5629, #5643, #5651, #5890                                                                      |
-| [@KunN-21](https://github.com/KunN-21)                       | direct commit / report                                                                                               |
-| [@manhdzzz](https://github.com/manhdzzz)                     | direct commit / report                                                                                               |
-| [@nguyenxvotanminh3](https://github.com/nguyenxvotanminh3)   | #5760, #5767, #5772                                                                                                  |
-| [@noir017](https://github.com/noir017)                       | direct commit / report                                                                                               |
-| [@pizzav-xyz](https://github.com/pizzav-xyz)                 | #5720                                                                                                                |
-| [@rdself](https://github.com/rdself)                         | #5746, #5856                                                                                                         |
-| [@shiva24082](https://github.com/shiva24082)                 | #5879                                                                                                                |
-| [@skyzea1](https://github.com/skyzea1)                       | #5432, #5701                                                                                                         |
-| [@Stazyu](https://github.com/Stazyu)                         | #5557                                                                                                                |
-| [@Thinkscape](https://github.com/Thinkscape)                 | #5549                                                                                                                |
-| [@vishalrajv](https://github.com/vishalrajv)                 | direct commit / report                                                                                               |
-| [@voravitl](https://github.com/voravitl)                     | direct commit / report                                                                                               |
-| [@waguriagentic](https://github.com/waguriagentic)           | direct commit / report                                                                                               |
-| [@wahyuzero](https://github.com/wahyuzero)                   | direct commit / report                                                                                               |
-| [@warelik](https://github.com/warelik)                       | direct commit / report                                                                                               |
-| [@Witroch4](https://github.com/Witroch4)                     | #5731, #5859, #5863                                                                                                  |
-| [@diegosouzapw](https://github.com/diegosouzapw)             | maintainer — cycle reconciliation, release-close base-red fixes, god-file decomposition, compression/memory features |
-
----
-
-## [3.8.42] — 2026-06-30
-
-### ✨ New Features
-
-- **compression (pipeline):** add an honest default-on **inflation guard** to the stacked compression pipeline (T02 / Headroom H1). If the fully-stacked engines produce a body that did not actually shrink — its token count is `>=` the original — the compressed body is discarded and the verbatim original request is sent upstream instead, with a `pipeline-inflation-guard` warning recorded in the compression stats. This is safe by construction (the only fallback is the unmodified original, always a valid payload) and complements the existing opt-in per-step TV1 bail-out, which governs step-to-step advancement rather than the final output. New `open-sse/services/compression/pipelineGuards.ts`; wired at the single `finalizeStackedResult` choke point shared by the sync and async stacked paths. Regression guards (incl. an inflating-engine integration test) in `tests/unit/compression-pipeline-inflation-guard.test.ts`.
-
-- **compression (caveman):** complete the German, French, and Japanese rule packs with the `dedup` (repeated-context collapsing) and `ultra` (abbreviation / terse) categories they were missing — these three languages previously shipped only `context`/`filler`/`structural`, while `en`/`es`/`id`/`pt-BR` had all five. So a de/fr/ja conversation compressed at higher intensities now collapses repeated boilerplate ("wie bereits besprochen" → "Siehe oben.", "comme mentionné précédemment" → "Voir ci-dessus.", "前述のとおり" → "（上記参照）") and abbreviates dense technical vocabulary (`Datenbank`→`DB`, `Authentifizierung`→`Auth`; `base de données`→`BD`, `authentification`→`auth`; `データベース`→`DB`, `アプリケーション`→`app`). Patterns mirror the existing `es` pack and stay ReDoS-safe (bounded literal alternations; the CJK pack uses no `\b` since Japanese has no word boundaries). Regression guard: `tests/unit/caveman-packs-de-fr-ja.test.ts` (packs load + validate + shrink a representative sample). gaps v3.8.42 — T05/C2.
-
-- **compression (caveman):** add a **Chinese (zh / wenyan 文言) input-side rule pack** — the counterpart of the existing output-side `terse-cjk` style. New `rules/zh/{dedup,filler,ultra}.json` collapse repeated context ("如前所述" → "见上。"), drop pleasantries/hedging ("请帮我…/谢谢/我觉得"), strip sentence-final modal particles ("吗/呢/吧"), and abbreviate dense technical terms ("数据库"→"DB", "应用程序"→"app"). Chinese is now auto-detected: `detectCompressionLanguage` distinguishes zh from ja by Han-without-kana (kana is Japanese-exclusive, so a Han-heavy Japanese sentence still resolves to `ja`), and `zh` is listed in `listSupportedCompressionLanguages`. Patterns are ReDoS-safe (bounded literal alternations, no `\b` since CJK has no word boundaries). Regression guard: `tests/unit/caveman-packs-zh-wenyan.test.ts` (packs load + validate + shrink; zh/ja/non-CJK detection). gaps v3.8.42 — T05/C6.
-
-- **compression (RTK):** add **Gradle** and **.NET CLI (`dotnet`)** to the RTK tool-output filter catalog. Tool output for `gradle`/`gradlew` and `dotnet build|test|restore|publish` is now recognized (both by command and by output content) and compressed: Gradle daemon/welcome banners and no-op `> Task … UP-TO-DATE/SKIPPED/FROM-CACHE` lines are dropped while `BUILD SUCCESSFUL/FAILED`, "What went wrong", and stack traces are preserved; the .NET build banner, copyright, and `Determining projects to restore`/`Restored …` chatter are dropped while `Build succeeded/FAILED`, `error CS####`/`warning CS####`, and test summaries are preserved. New builtin filters `engines/rtk/filters/{gradle,dotnet}.json` (with inline tests run by the catalog gate) plus `gradle`/`dotnet` entries in the command detector. Regression guard: `tests/unit/rtk-gradle-dotnet-filters.test.ts`. gaps v3.8.42 — T07/R9.
-
-### 🔧 Bug Fixes
-
-- **providers (chatgpt-web):** fix `502 ChatGPT sentinel failed: Digest method not supported` on the **Electron desktop app**, which made every `chatgpt-web/*` request fail. The sentinel proof-of-work hashed with native `createHash("sha3-512")`, but Electron's Node is built against **BoringSSL, which does not implement the SHA-3 family** (electron/electron#30530), so the digest threw at construction — the provider was unusable on the desktop build (works under plain Node/OpenSSL). The PoW now hashes through a new runtime-portable helper (`open-sse/utils/sha3-512.ts`) that prefers the native digest and transparently falls back to a dependency-free pure-JS Keccak-f[1600] when native SHA-3 is absent. The fallback is validated bit-for-bit against native `createHash("sha3-512")` (300 random inputs) and the published FIPS-202 known-answer vectors. Regression guards in `tests/unit/chatgpt-web-sha3-boringssl-5531.test.ts`. ([#5531](https://github.com/diegosouzapw/OmniRoute/issues/5531))
-
-- **providers (bytez):** fix Bytez key validation ("Provider validation endpoint not supported") and the chat base URL, verified live with a real key. Bytez **is** OpenAI-compatible at `…/models/v2/openai/v1`, but the registry stored the bare `…/models/v2` base, so the validation chat-probe hit `…/models/v2/chat/completions` → `404` → the misleading "endpoint not supported". Two parts: (1) the registry `baseUrl` now carries the full OpenAI-compat chat path (`…/models/v2/openai/v1/chat/completions`); (2) key validation no longer uses a chat probe — a Bytez account only serves models explicitly added to its catalog, so even valid keys 404 on any model id. A dedicated `validateBytezProvider` instead probes the **auth-only** `GET …/models/v2/list/tasks` endpoint (`200` ⇒ valid, `401/403` ⇒ invalid), which is independent of catalog provisioning. Regression guard: `tests/unit/bytez-validation-5422.test.ts`. ([#5422](https://github.com/diegosouzapw/OmniRoute/issues/5422))
-
-- **dashboard (provider add):** two provider-add UX fixes. (1) #5420 — the "Import Models" button now stays hidden for **tool-only providers** (web search / web fetch), not just `*-search` ids: `firecrawl` and `jina-reader` (declared `serviceKinds: ["webFetch"]`) previously showed an Import button that hit the `400 "does not support models listing"` route. A new capability check (`providerLacksModelListing` over the resolved serviceKinds) gates the section without ever hiding an LLM/media provider. (2) #5426 — Coze key validation no longer leaks the raw upstream envelope (`{code,msg,logId,from}`) into the UI; the Coze-shaped error becomes a friendly `Coze rejected the key: <msg> (code <n>)` message (scoped to `provider === "coze"` so no other provider is affected). Regression guards: `tests/unit/model-listing-capability-5420.test.ts`, `tests/unit/coze-validation-error-5426.test.ts`. ([#5420](https://github.com/diegosouzapw/OmniRoute/issues/5420), [#5426](https://github.com/diegosouzapw/OmniRoute/issues/5426))
-
-- **providers (friendliai, novita):** fix two provider registry endpoints that rejected valid keys (verified live with real keys). **FriendliAI** pointed at `…/dedicated/v1/chat/completions`, which `403 Forbidden`s a serverless `flp_*` token — switched to `…/serverless/v1/chat/completions` (+ a serverless `modelsUrl`). **Novita** pointed at the legacy `…/v3/…` base with a typo'd model id `ai-ai/llama-3.1-8b-instruct` (both `404`) — switched to the OpenAI-compatible `…/openai/v1/…` base + the valid `meta-llama/llama-3.1-8b-instruct` id. Regression guard: `tests/unit/provider-endpoints-friendliai-novita.test.ts`. ([#5430](https://github.com/diegosouzapw/OmniRoute/issues/5430), [#5455](https://github.com/diegosouzapw/OmniRoute/issues/5455))
-
-- **providers (muse-spark):** align the Muse Spark Web (Meta AI) cookie copy with the live cookie name. The default session cookie migrated from the retired `abra_sess` to `ecto_1_sess` (`META_AI_DEFAULT_COOKIE`), but the provider form hint and one 401 auth-failure message still told users to paste `abra_sess` — a cookie that no longer exists. Both strings now name `ecto_1_sess`. Regression guard: `tests/unit/muse-spark-cookie-copy-5449.test.ts`. ([#5449](https://github.com/diegosouzapw/OmniRoute/issues/5449))
-
-- **dashboard (provider add):** fix three rough edges in the Add-API-Key / model-import flow reported across the provider-catalog audit. (1) The **Validation Model** and **Account ID** form fields shipped untranslated i18n stub copy (`"Validation Model Id Label"`, `"Account Id Placeholder"`, …) that surfaced verbatim in the modal — replaced with real labels/placeholders/hints in `en.json`. (2) Model import **silently fell back to the cached/local catalog**: the route already returned a `warning` ("API unavailable — using local catalog"), but `useModelImportHandlers` only read `models`/`error` and dropped it, so the user got local models with no indication — the warning is now surfaced as an import log line (new pure helper `extractImportWarning`). (3) The required connection-**name** field defaulted to `""`, which let browser autofill inject garbage (e.g. `wiw`) — it now defaults to `"main"`. Regression guard: `tests/unit/provider-add-ux-i18n-import-warning.test.ts`. ([#5421](https://github.com/diegosouzapw/OmniRoute/issues/5421), [#5428](https://github.com/diegosouzapw/OmniRoute/issues/5428), [#5429](https://github.com/diegosouzapw/OmniRoute/issues/5429), [#5431](https://github.com/diegosouzapw/OmniRoute/issues/5431), [#5435](https://github.com/diegosouzapw/OmniRoute/issues/5435))
-
-- **services (installer):** fix `spawn EINVAL` when installing an embedded service (9Router / CLIProxy) on **Windows + Node.js 24+**. Node 24 stopped letting `child_process.execFile()` run `.cmd` batch files without a shell (nodejs/node#52554), and npm on Windows is `npm.cmd`, so `runNpm()` threw `EINVAL` the moment a user clicked **Install**. `runNpm` now enables `shell` on win32 only. To keep Hard Rule #13 intact under a shell — where the shell, not `execFile`, parses argv — the install `--prefix` (a `DATA_DIR` path that can legitimately contain spaces, e.g. `C:\Users\John Doe\.omniroute\…`) is now passed via the `npm_config_prefix` **environment variable** instead of an argv path, and the user-supplied install `version` is constrained to a dist-tag/semver shape (`SERVICE_VERSION_PATTERN`) at the route boundary so it can never carry shell metacharacters. With the prefix in the environment and the version validated, every remaining argv entry is a static flag. Regression guards: `tests/unit/services/installers/runNpm-shell-5379.test.ts` (+ existing `ninerouter.test.ts` aligned to npm's `npm_config_prefix` env). ([#5379](https://github.com/diegosouzapw/OmniRoute/issues/5379))
-
-- **cli (serve):** restore `dist/tls-options.mjs` to the npm tarball — the opt-in native HTTPS/TLS sidecar (#5361) was copied into the staged `dist/` by the build but then **pruned** by the prepublish allowlist step, so `omniroute serve` crashed on the published 3.8.41 with `ERR_MODULE_NOT_FOUND` (`dist/server-ws.mjs` imports `./tls-options.mjs`). Added `tls-options.mjs` to `APP_STAGING_ALLOWED_EXACT_PATHS` (survives the prune) and `dist/tls-options.mjs` to `PACK_ARTIFACT_REQUIRED_PATHS` (the `check:pack-artifact` gate now fails loudly if it ever vanishes again — same guard pattern as `webdav-handler.mjs`). Regression guards in `tests/unit/pack-artifact-policy.test.ts`. ([#5452](https://github.com/diegosouzapw/OmniRoute/issues/5452) — thanks @KooshaPari for the parallel fix [#5494](https://github.com/diegosouzapw/OmniRoute/pull/5494))
-
-- **dashboard:** fix the **Add Provider / onboarding wizard** button silently doing nothing. The `/dashboard/providers/new` route was a redirect stub (it bounced straight back to `/dashboard/providers`), so every "Add Provider" button and dashboard widget link opened nothing, and the fully-built `ProviderOnboardingWizard` component stayed orphaned (never rendered by any route). The route now renders the wizard directly; auth is enforced centrally by the `(dashboard)` layout, same as the sibling provider routes. Regression guard in `tests/unit/onboarding-wizard-route-5427.test.ts`. ([#5427](https://github.com/diegosouzapw/OmniRoute/issues/5427))
-
-- **db (import):** fix `EBUSY: resource busy or locked` when importing a database on **Windows**. The import route deleted the live `storage.sqlite` + WAL/`-shm`/`-journal` sidecars with a plain `fs.unlinkSync` immediately after `resetDbInstance()`, but Windows releases the SQLite file handle asynchronously after `close()` (mmap / antivirus), so the unlink raced and threw `EBUSY`. The route now deletes via `unlinkFileWithRetry` (EBUSY/EPERM backoff) — the same helper the restore path already uses. Regression guard in `tests/unit/db-import-ebusy-5406.test.ts`. ([#5406](https://github.com/diegosouzapw/OmniRoute/issues/5406), consolidated under [#5161](https://github.com/diegosouzapw/OmniRoute/issues/5161))
-
-- **build:** keep `ioredis` out of the client/CLI bundle — a dast-smoke regression revealed the module was being pulled into browser/Electron client-side chunks; adding it to the `SPAWN_CAPABLE_PREFIXES` leaf excludes it from client bundles while keeping it available on the server path. ([#5546](https://github.com/diegosouzapw/OmniRoute/pull/5546))
-
-- **providers (mimocode):** route per-account traffic through SOCKS5 proxy dispatchers — each mimocode account's requests are now dispatched via its configured SOCKS5 proxy rather than the default direct connection. ([#5521](https://github.com/diegosouzapw/OmniRoute/pull/5521) — thanks @pizzav-xyz)
-
-- **providers:** persist the **Configured** provider filter selection across page reloads — the filter was resetting to "All" on every navigation. ([#5510](https://github.com/diegosouzapw/OmniRoute/pull/5510) — thanks @KooshaPari)
-
-- **providers (chatgpt-web):** support **GPT-5.5 Pro** model handoff — adds the model mapping and handoff routing needed for the GPT-5.5 Pro tier. ([#5536](https://github.com/diegosouzapw/OmniRoute/pull/5536) — thanks @Thinkscape)
-
-- **dashboard:** keep onboarding schemas browser-safe — the schema module imported a server-side `db` reference that crashed the browser bundle; it is now imported only on the server path. ([#5525](https://github.com/diegosouzapw/OmniRoute/pull/5525) — thanks @KooshaPari)
-
-- **routing (bifrost):** add auto-fallback cooldown for bifrost targets — prevents rapid re-selection of a failing bifrost backend within the cooldown window, complementing the existing circuit-breaker mechanism. ([#5519](https://github.com/diegosouzapw/OmniRoute/pull/5519) — thanks @KooshaPari)
-
-- **providers (opencode-plugin):** bump the opencode plugin to **v0.2.0** and wire auto-publish on release so the plugin package tracks OmniRoute releases automatically. ([#5363](https://github.com/diegosouzapw/OmniRoute/pull/5363) — thanks @herjarsa)
-
-- **rate-limit:** normalize queue refresh settings — aligns the queue-refresh interval configuration across rate-limit strategies so stale queues are released on a consistent schedule. ([#5499](https://github.com/diegosouzapw/OmniRoute/pull/5499) — thanks @KooshaPari)
-
-- **fallback:** normalize provider error-rule header extraction — ensures fallback retry decisions correctly read all response headers regardless of casing, fixing cases where a provider's `Retry-After` or custom error header was silently dropped. ([#5473](https://github.com/diegosouzapw/OmniRoute/pull/5473) — thanks @KooshaPari)
-
-- **routing:** gate Claude adaptive-thinking defaults behind the feature flag — prevents the thinking budget from being injected into requests for models that do not support the extended-thinking parameter, avoiding upstream `400` errors on non-thinking Claude variants. ([#5480](https://github.com/diegosouzapw/OmniRoute/pull/5480) — thanks @KooshaPari)
-
-- **ci:** fix post-merge CI regressions introduced by the dead-code sweep — restores test imports and type references broken when the ratchet landed before downstream consumers were updated. ([#5467](https://github.com/diegosouzapw/OmniRoute/pull/5467) — thanks @KooshaPari)
-
-- **sse:** treat terminal stream cancels as complete — an aborted SSE stream was being left in a partial state, causing downstream consumers to wait indefinitely for a final event that would never arrive. ([#5491](https://github.com/diegosouzapw/OmniRoute/pull/5491) — thanks @JxnLexn)
-
-- **api:** fix framing of non-streaming JSON responses — `stream: false` chat-completions responses were returned without correct content-length framing, causing some clients to misparse the response body. ([#5416](https://github.com/diegosouzapw/OmniRoute/pull/5416) — thanks @rdself)
-
-- **dashboard (tests):** protect dynamic dashboard endpoint tests with CSRF validation — the test suite was exercising dashboard API routes without CSRF tokens, masking a coverage gap for those endpoints. ([#5405](https://github.com/diegosouzapw/OmniRoute/pull/5405) — thanks @rdself)
-
-- **providers:** remove the dead **Phind** provider (service shut down) and deduplicate the **HuggingChat** catalog listing that had accumulated a stale duplicate entry. ([#5530](https://github.com/diegosouzapw/OmniRoute/pull/5530) — thanks @backryun)
-
-- **providers (longcat):** correct the LongCat free tier — **LongCat-2.0** is now GA; the one-time 10M-token promo (KYC required) is correctly reflected in the catalog, replacing the stale legacy beta entry. ([#5508](https://github.com/diegosouzapw/OmniRoute/pull/5508) — thanks @backryun)
-
-### 📝 Maintenance
-
-- **dashboard (refactor):** consolidate the duplicate caveman on/off toggle from the compression settings tab onto the single-source panel (T11), eliminating the stale off-sync copy. ([#5524](https://github.com/diegosouzapw/OmniRoute/pull/5524))
-
-- **tests:** add quota guard for Claude-Code identity version lockstep (Phase 2) — asserts that the Claude-Code version reported in quota accounting stays in sync with the deployed version, preventing silent drift. ([#5514](https://github.com/diegosouzapw/OmniRoute/pull/5514))
-
-- **docs:** add relay backend strategy guide documenting supported relay backend types, selection criteria, and configuration patterns. ([#5547](https://github.com/diegosouzapw/OmniRoute/pull/5547))
-
-- **docs:** clarify bifrost relay backend environment variables — documents which env vars control bifrost's relay backend selection and failover behavior. ([#5520](https://github.com/diegosouzapw/OmniRoute/pull/5520) — thanks @KooshaPari)
-
-- **tests:** add relay routing fallback header behavior tests — regression guard asserting that fallback-triggered relay requests carry the correct forwarded headers through the routing layer. ([#5526](https://github.com/diegosouzapw/OmniRoute/pull/5526) — thanks @KooshaPari)
-
-- **ci:** add npm `fetch-retry` configuration and codify the release-freeze protocol (Hard Rule #21) — reduces transient npm registry fetch failures in CI and establishes the documented procedure for freezing releases. ([#5506](https://github.com/diegosouzapw/OmniRoute/pull/5506))
-
-- **deps:** bump 11 production dependencies to their latest compatible versions. ([#5414](https://github.com/diegosouzapw/OmniRoute/pull/5414))
-
-- **deps:** bump Electron from 42.4.1 to 42.5.1 in `/electron`. ([#5413](https://github.com/diegosouzapw/OmniRoute/pull/5413))
-
-- **deps:** bump the development dependency group with 9 updates. ([#5415](https://github.com/diegosouzapw/OmniRoute/pull/5415))
-
-- **maintenance (dead-code):** repo-wide sweep of unused exported symbols, types, and schemas — removes 35 no-longer-referenced exports across cloud-agent, a2a, SSE, memory, quota, skills, gamification, codex, qdrant, playground, provider catalog, and combo modules, reducing the exported API surface and eliminating stale misleading types. ([#5372](https://github.com/diegosouzapw/OmniRoute/pull/5372), [#5373](https://github.com/diegosouzapw/OmniRoute/pull/5373), [#5374](https://github.com/diegosouzapw/OmniRoute/pull/5374), [#5375](https://github.com/diegosouzapw/OmniRoute/pull/5375), [#5376](https://github.com/diegosouzapw/OmniRoute/pull/5376), [#5377](https://github.com/diegosouzapw/OmniRoute/pull/5377), [#5378](https://github.com/diegosouzapw/OmniRoute/pull/5378), [#5380](https://github.com/diegosouzapw/OmniRoute/pull/5380), [#5381](https://github.com/diegosouzapw/OmniRoute/pull/5381), [#5382](https://github.com/diegosouzapw/OmniRoute/pull/5382), [#5383](https://github.com/diegosouzapw/OmniRoute/pull/5383), [#5384](https://github.com/diegosouzapw/OmniRoute/pull/5384), [#5385](https://github.com/diegosouzapw/OmniRoute/pull/5385), [#5386](https://github.com/diegosouzapw/OmniRoute/pull/5386), [#5387](https://github.com/diegosouzapw/OmniRoute/pull/5387), [#5388](https://github.com/diegosouzapw/OmniRoute/pull/5388), [#5389](https://github.com/diegosouzapw/OmniRoute/pull/5389), [#5390](https://github.com/diegosouzapw/OmniRoute/pull/5390), [#5391](https://github.com/diegosouzapw/OmniRoute/pull/5391), [#5392](https://github.com/diegosouzapw/OmniRoute/pull/5392), [#5393](https://github.com/diegosouzapw/OmniRoute/pull/5393), [#5395](https://github.com/diegosouzapw/OmniRoute/pull/5395), [#5396](https://github.com/diegosouzapw/OmniRoute/pull/5396), [#5397](https://github.com/diegosouzapw/OmniRoute/pull/5397), [#5398](https://github.com/diegosouzapw/OmniRoute/pull/5398), [#5399](https://github.com/diegosouzapw/OmniRoute/pull/5399), [#5400](https://github.com/diegosouzapw/OmniRoute/pull/5400), [#5401](https://github.com/diegosouzapw/OmniRoute/pull/5401), [#5402](https://github.com/diegosouzapw/OmniRoute/pull/5402), [#5403](https://github.com/diegosouzapw/OmniRoute/pull/5403), [#5404](https://github.com/diegosouzapw/OmniRoute/pull/5404), [#5463](https://github.com/diegosouzapw/OmniRoute/pull/5463), [#5464](https://github.com/diegosouzapw/OmniRoute/pull/5464), [#5466](https://github.com/diegosouzapw/OmniRoute/pull/5466), [#5468](https://github.com/diegosouzapw/OmniRoute/pull/5468) — thanks @JxnLexn)
-
-- **maintenance (DRY):** DRY consolidation of shared helpers — extracts 17 duplicated utilities into single shared modules: vscode metadata helpers, proxy route handlers, auth zip extractors, combo-builder model options, vscode tokenized-request helpers, quota strategy ranking helpers, recharts donut card, provider-specific validation, batch response formatter, Redis runtime helpers, version-manager request parsing, media-generation route helpers, service install helpers, settings transform schemas, relay stream finalizer, machine-id fallback, and node SQLite adapter. ([#5471](https://github.com/diegosouzapw/OmniRoute/pull/5471), [#5472](https://github.com/diegosouzapw/OmniRoute/pull/5472), [#5475](https://github.com/diegosouzapw/OmniRoute/pull/5475), [#5477](https://github.com/diegosouzapw/OmniRoute/pull/5477), [#5479](https://github.com/diegosouzapw/OmniRoute/pull/5479), [#5482](https://github.com/diegosouzapw/OmniRoute/pull/5482), [#5484](https://github.com/diegosouzapw/OmniRoute/pull/5484), [#5485](https://github.com/diegosouzapw/OmniRoute/pull/5485), [#5488](https://github.com/diegosouzapw/OmniRoute/pull/5488), [#5490](https://github.com/diegosouzapw/OmniRoute/pull/5490), [#5492](https://github.com/diegosouzapw/OmniRoute/pull/5492), [#5493](https://github.com/diegosouzapw/OmniRoute/pull/5493), [#5495](https://github.com/diegosouzapw/OmniRoute/pull/5495), [#5496](https://github.com/diegosouzapw/OmniRoute/pull/5496), [#5497](https://github.com/diegosouzapw/OmniRoute/pull/5497), [#5498](https://github.com/diegosouzapw/OmniRoute/pull/5498), [#5500](https://github.com/diegosouzapw/OmniRoute/pull/5500) — thanks @JxnLexn)
-
----
-
-## [3.8.41] — 2026-06-29
-
-### ✨ New Features
-
-- **feat(relay): selectable relay backend (TS / Bifrost / `auto`)** — the OpenAI-compatible relay endpoint can now route its hot path through a native Bifrost sidecar without clients changing URLs. `OMNIROUTE_RELAY_BACKEND` / `RELAY_ROUTING_BACKEND` = `ts | bifrost | auto`: defaults to the existing TypeScript relay; `auto` selects Bifrost when `BIFROST_BASE_URL` is set (and `BIFROST_ENABLED` ≠ `0`) and falls back to TS automatically if the sidecar is unreachable; `bifrost` keeps strict failure behavior. Auth, per-IP/token rate limits, prompt-injection checks, and model allowlists still run in the Next relay route before dispatch (control plane stays in the app); responses carry `X-Routing-Backend` / `X-Routing-Fallback`. Regression guards: `tests/unit/api/v1/relay-routing-backend.test.ts`, `tests/unit/api/v1/bifrost-sidecar.test.ts`. ([#5315](https://github.com/diegosouzapw/OmniRoute/pull/5315), #5316 — thanks @KooshaPari)
-
-### 🔧 Bug Fixes
-
-- **translator (claude):** synthesize a minimal `user` turn when an OpenAI→Claude request carries **only** `system`/`developer` messages, so the request stops failing with `[400]: messages: at least one message is required`. `openaiToClaudeRequest` hoists every system/developer turn into Claude's top-level `system` field and filters them out of `messages`; an all-system input (OpenCode compaction / title-generation requests) left `messages: []`, which the Messages API rejects — surfacing in OpenCode as a mid-task `stream error` that drops the conversation. The guard fires only when `messages` would otherwise be empty (system instructions still drive the response), so non-empty requests are unaffected. ([#5342](https://github.com/diegosouzapw/OmniRoute/pull/5342) — thanks @wild-feather)
-- **providers (gemini):** drop retired Google AI Studio model ids and align the catalog to what the live GenAI API actually serves (verified 2026-06-29 against the official deprecations page). Removes long-retired `gemini-1.5-pro`/`gemini-1.5-flash`, the shut-down `gemini-2.0-flash`/`gemini-2.0-flash-lite`, and dead experimentals; renames `gemini-3.1-flash-lite-preview` → the GA `gemini-3.1-flash-lite`; swaps the retired `text-embedding-004` for the live `gemini-embedding-001`/`gemini-embedding-2`; and adds graceful `modelDeprecation` forwards so legacy/renamed ids redirect to the GA model instead of 404ing. Native AI-Studio-direct image/video/music registration is intentionally out of scope (needs real executor work; those models stay reachable via Antigravity/Vertex/aggregators). ([#5337](https://github.com/diegosouzapw/OmniRoute/pull/5337) — thanks @backryun)
-- **services (dashboard):** fix the embedded-services dashboard failures (#5298) — service supervisors are now lazily initialized from `/api/services/[name]/logs` so `cliproxy`/`9router` logs no longer 404 before bootstrap registers a supervisor; lifecycle buttons send JSON (empty install bodies default to `version: "latest"`, malformed JSON still returns `400 Invalid JSON body`); lifecycle and log-stream failures surface as actionable UI errors instead of silently showing no logs; Tailscale CGNAT `100.64.0.0/10` peers count as private-LAN local for local-only service access; a parent `/dashboard/context` → `/dashboard/context/settings` redirect stops RSC prefetch 404s; and `/api/v1/providers/{cliproxyapi,9router}/models` return synced embedded-service models instead of `invalid_provider`. ([#5299](https://github.com/diegosouzapw/OmniRoute/pull/5299), #5298 — thanks @KooshaPari)
-- **thinking (claude):** fix three independent defects in Claude adaptive-thinking on the OpenAI-compatible path (Cursor → Claude OAuth). **(A)** the dashboard Thinking-Budget setting was dropped on every restart — `setThinkingBudgetConfig` was never called at boot, so a saved `{mode:"adaptive"…}` silently reverted to passthrough; it's now hydrated from settings in `server-init`. **(B)** the Claude executor force-injected adaptive thinking _after_ translation, ignoring the operator's budget — it now honors `mode:"auto"` (strip) while keeping the default (passthrough) behavior byte-identical so native Claude Code is unaffected, and remaps an operator `thinking.type:"enabled"` to the `adaptive` shape Opus 4.7/4.8 require (`enabled` → 400). **(D)** on replay, signature-less `reasoning_content` was reconstructed as a `thinking` block carrying a fabricated signature → Anthropic `400 "Invalid signature in thinking block"`; it now emits a signature-less `redacted_thinking` block (real signatures are still preserved verbatim). Regression guards: `tests/unit/thinking-budget-hydration-5312.test.ts`, `base-thinking-budget-config-5312.test.ts`, `openai-to-claude-redacted-replay-5312.test.ts` (existing #5123/#4479/#2454 suites stay green). The `</think>` content-marker channel mismatch (RC-C, shared with #5245) is tracked as a follow-up pending a live Anthropic validation. ([#5312](https://github.com/diegosouzapw/OmniRoute/issues/5312) — thanks @vitalNohj)
-- **opencode (proxy pool):** the OpenCode Free per-account proxy modal now offers the global **Proxy Pool dropdown** (by-id reference) instead of forcing manual Host/Port/credentials on every account — Gap 1 of #5217. A **Saved / Custom** toggle: "Saved" picks a pre-saved proxy from `GET /api/settings/proxies` and stores `{fingerprint, proxyId}`, so updating that pool proxy applies to every account using it; "Custom" keeps the manual inputs (stored inline) as an escape hatch. Resolution happens server-side (`resolveAccountProxiesFromRegistry`) so the executor still receives a resolved proxy unchanged; existing inline entries keep working and an unknown/deleted `proxyId` degrades safely to direct. Regression guards: `tests/unit/noauth-proxy-resolution.test.ts`, `tests/unit/ui/noauth-account-card.test.tsx`. ([#5217](https://github.com/diegosouzapw/OmniRoute/issues/5217) Gap 1 — thanks @daniij)
-- **thinking (claude):** let reasoning_content-native clients (e.g. Cursor) opt out of the `</think>` close-marker so it no longer leaks an orphan `</think>` into visible `content` (RC-C of #5312, shared with #5245). The marker-suppression machinery already existed (UA allowlist, #5348) but Cursor's UA was deliberately excluded; this adds an explicit request header `x-omniroute-thinking-marker: off` (also `on`/`keep` to force-keep) that overrides the UA policy. With the header absent the behavior is byte-identical — Claude Code/Cursor-composer clients that scan `content` for the marker (#4633) still receive it. Regression guard: `tests/unit/think-close-marker-suppress-5245.test.ts` (#5123 case-b + #4479 stay green). ([#5312](https://github.com/diegosouzapw/OmniRoute/issues/5312), [#5245](https://github.com/diegosouzapw/OmniRoute/issues/5245) — thanks @vitalNohj, @wild-feather)
-- **cors:** browser/Electron clients (e.g. Wayland AI) can now use OmniRoute as an OpenAI-compatible provider out-of-the-box. The token-authenticated API surface (`/v1/*`, `/v1beta/*`) now returns a permissive `Access-Control-Allow-Origin` (echoes the request `Origin`, `*` when absent) by default — matching 9router and the OpenAI-compatible ecosystem — so a renderer `fetch` can read the response instead of failing CORS-blocked as "site not found" / empty catalog (while `curl`, which sends no preflight, worked). This is **safe**: those routes auth via `Authorization`/`x-api-key` headers browsers never auto-attach (no credentialed-session/CSRF exposure), and `Access-Control-Allow-Credentials` is never paired with the echo/wildcard. Cookie-authed **MANAGEMENT/dashboard routes stay exactly fail-closed**; `CORS_ALLOW_ALL`/`CORS_ALLOWED_ORIGINS` still take precedence. Regression guards: `tests/unit/cors/origins.test.ts`, `tests/unit/authz/pipeline.test.ts`. (Bug 2 of [#5242](https://github.com/diegosouzapw/OmniRoute/issues/5242) — thanks @jonlwheat2-gif)
-- **grok-web:** forward the Cloudflare clearance cookies and stop mislabeling IP-reputation blocks as a bad cookie. "Check cookie" returned `Invalid SSO cookie` even with a valid, complete browser session — but the cookie parser was never the problem (it robustly extracts `sso`/`sso-rw` from a full DevTools header). Two real gaps fixed: **(1)** `buildGrokCookieHeader` now forwards `cf_clearance` and `__cf_bm` when pasted (it dropped them before; AIClient2API forwards them too) — strictly additive, a bare `sso` blob still yields exactly `sso=…`; **(2)** when the user supplied a `cf_clearance`, a 401 / invalid-credentials-403 from grok.com is now surfaced as an IP-reputation/anti-bot block (cf_clearance is IP+TLS+UA-pinned and can't be replayed from a different machine) instead of the misleading "Invalid SSO cookie — re-paste". A bare cookie with no clearance still gets the re-paste hint. Regression guards in `web-cookie-auth.test.ts` + `provider-validation-specialty.test.ts`. ([#5350](https://github.com/diegosouzapw/OmniRoute/issues/5350) — thanks @SeaXen)
-- **cli (serve):** opt-in native **HTTPS/TLS** for `omniroute serve` — so strict-CSP Electron apps and browsers can reach OmniRoute over `https://` instead of plain `http://localhost`. Provide `--tls-cert <path> --tls-key <path>` (or `OMNIROUTE_TLS_CERT`/`OMNIROUTE_TLS_KEY`) and the standalone server terminates TLS on the same listener (no extra port/proxy); WebSocket upgrade (live dashboard + `/v1` streaming) works over `wss://` unchanged since `https.Server extends http.Server`. With no TLS flags the HTTP path is byte-identical to before; only one of cert/key, or an unreadable path, logs a warning and stays HTTP (never half-enables, never crashes). Auto-generated self-signed certs for localhost are a follow-up; for now provide an explicit cert/key (or front OmniRoute with a TLS terminator). Regression guard: `tests/unit/tls-options.test.ts`. (Bug 1C of [#5242](https://github.com/diegosouzapw/OmniRoute/issues/5242) — thanks @jonlwheat2-gif)
-- **opencode/observability:** make OpenCode Free account/proxy rotation visible and fix two real defects surfaced alongside it. **(1)** the per-request rotation selection log (`dispatch via account … through proxy …`) was `debug` (hidden at default `APP_LOG_LEVEL=info`) — promoted to `info` so the shuffle/cooldown lifecycle is auditable (token stays masked). **(2)** `[ProxyEgress]` reported `proxy=direct` even when an account proxy was applied, because the egress logger ran outside the executor's nested proxy context — the effective applied proxy is now captured (via an applied-proxy sink threaded through the proxy AsyncLocalStorage) and reflected in the egress log. **(3)** `[callLogs] too many SQL variables` — `deleteCallLogRowsByIds` deleted up to 5000 ids in one `IN (…)`, exceeding SQLite's ~999 bound-param cap and aborting log trimming/retention; ids are now chunked (≤500 per statement). Regression guards: `tests/unit/call-log-trim-sql-vars-5217.test.ts`, `apply-executor-proxy-info-5217.test.ts`, extended `opencode-proxy-rotation-4954.test.ts`. The Proxy Pool dropdown (by-id) UI (Gap 1) is a follow-up requiring browser validation. ([#5217](https://github.com/diegosouzapw/OmniRoute/issues/5217) — thanks @daniij)
-- **chatgpt-web:** wire tool/function calling into the `chatgpt-web` provider. It was the only web-session executor that never read `body.tools` — both response builders hardcoded `finish_reason:"stop"` and emitted only content, so tool calls were silently dropped (the model answered in prose). It now uses the shared `webTools` prompt-emulation shim (a `<tool>`-contract system message + `<tool>{…}</tool>` response parsing) exactly like its 9 sibling executors (qwen-web, perplexity-web, …) — it was simply omitted from the #3259 rollout. Tool mode buffers and emits `tool_calls` + `finish_reason:"tool_calls"` (gated off the image-gen path); plain chat is unchanged. Regression guard: `tests/unit/chatgpt-web-tools-5240.test.ts`. ([#5240](https://github.com/diegosouzapw/OmniRoute/issues/5240) — thanks @Rougler)
-- **oauth/dashboard:** fix the persistent/false Antigravity "Token Expired" badge (continuation of #3679/#3850). Two causes: **(1)** new OAuth connections never set `tokenExpiresAt` (only `expiresAt`), so the dashboard badge — which prefers `tokenExpiresAt || expiresAt` — fell back to the original grant clock and could flash a false "Token Expired" until the first background refresh. Creation now mirrors `expiresAt` into `tokenExpiresAt` across all 5 OAuth create paths (a shared `buildOAuthConnectionCreatePayload`), consistent with every refresh path which already writes both. **(2)** when a refresh-capable connection has no usable refresh token, the health-check sweep silently skipped it, leaving `testStatus="active"` forever while the cosmetic badge showed expired; it now surfaces a terminal `testStatus="expired"` ("needs re-auth"), tightly gated so it never clobbers non-refresh providers or already-terminal/cooldown states. Regression guards: `tests/unit/oauth-connection-tokenexpiresat-5326.test.ts`, `tests/unit/token-health-no-refresh-token-expired-5326.test.ts`. ([#5326](https://github.com/diegosouzapw/OmniRoute/issues/5326))
-- **routing:** auto-disable a depleted API key on upstream `402 "Insufficient account balance"` for API Key Round-Robin connections (multiple keys in one connection's `extraApiKeys`). The per-connection path already terminalized 402 (→ `credits_exhausted`), but the per-KEY health tracker (`recordKeyHealthStatus`) only recorded failures for `401`, so a 402-depleted key stayed in rotation and kept getting retried. Now a 402 marks the current key invalid immediately (terminal — balance won't recover mid-session) via a new `recordKeyTerminal`, so the rotator skips it and falls over to the next healthy key; the state persists across restarts. Also added `insufficient balance`/`insufficient_balance`/`insufficient account balance` to the credits-exhausted body signals so non-402 out-of-credit responses terminalize too. Regression guard: `tests/unit/key-health-402-disable-5239.test.ts`. ([#5239](https://github.com/diegosouzapw/OmniRoute/issues/5239) — thanks @muflifadla38)
-- **cli:** `omniroute serve` no longer discards a user-set `NODE_OPTIONS=--max-old-space-size=…`. It used to unconditionally overwrite `NODE_OPTIONS` (and pass an explicit `--max-old-space-size` CLI arg) with the calibrated default, so a user who exported `--max-old-space-size=8192` still ran at the old cap and OOM'd (#5238 reporter set 8192, crashed at ~505MB). Now it mirrors the Electron and standalone launchers: if `NODE_OPTIONS` already pins the heap, that value wins (and the duplicate CLI arg is suppressed); otherwise the calibrated `--max-old-space-size` is appended, preserving unrelated flags. Regression guard: `tests/unit/serve-node-options-preserve-5238.test.ts`. (Defect C of [#5238](https://github.com/diegosouzapw/OmniRoute/issues/5238); the `b.mask`/OOM-root parts are tracked separately.)
-- **dashboard:** restore the `{active}/{total} active` model-count badge in a provider's **Available Models** toolbar (provider detail page). It was dropped during the v3.8.13 god-file decomposition (#3327) — the `ModelVisibilityToolbar` still received `activeCount`/`totalCount` but they were orphaned as unused `_`-prefixed params and the rendering `<span>` was never carried over (the `modelsActiveCount` i18n key stayed). Re-wired the existing props to the existing key; zero data-layer or i18n change. Regression guard: `modelVisibilityToolbarActiveCount.test.tsx`. ([#5264](https://github.com/diegosouzapw/OmniRoute/issues/5264))
-- **rerank:** `/v1/rerank` no longer rejects SiliconFlow and DeepInfra Qwen3-Reranker models with `400 "Invalid rerank model"` even though `/v1/models` lists them. The model-ID parser was never the problem (it already splits on the first slash, so `siliconflow/Qwen/Qwen3-Reranker-8B` parses correctly) — `siliconflow` and `deepinfra` were just missing from the rerank provider registry. Added both: SiliconFlow as Cohere-compatible, DeepInfra via a new `deepinfra` adapter (model in the URL path `POST /v1/inference/<model>`, `{queries,documents}` request, positional `{scores}` response mapped to Cohere `results[]`). Regression guard: `tests/unit/rerank-providers-5332.test.ts`. ([#5332](https://github.com/diegosouzapw/OmniRoute/issues/5332) — thanks @maikokan)
-- **authz/dashboard:** stop rejecting every dashboard mutation with `403 INVALID_ORIGIN` when the dashboard is reached over a LAN IP / non-localhost host. The origin-pinning check (#5278) only accepted the configured `*_PUBLIC_BASE_URL` (typically `http://localhost:20128`) plus the internal `request.url` origin — which Next.js standalone reports as the bind host, not the real `Host`. So opening the dashboard at e.g. `http://192.168.0.15:20128` made the browser's same-origin `Origin` match no candidate, and **every** POST/PUT/DELETE (save API key, save provider, test connection) failed while GETs still worked. Two fixes: **(a)** the request `Host` (or a trusted `X-Forwarded-Host`) is now accepted as a valid mutation origin, gated by two independent checks — the token-stamped socket peer must be loopback/private-LAN **and** the Host itself must be a loopback/private-LAN IP literal, so a DNS-rebinding domain (which classifies as `remote`) can never become a trusted origin and the protocol is pinned to the actual connection; **(b)** the `INVALID_ORIGIN` response now carries an actionable message (set `OMNIROUTE_PUBLIC_BASE_URL`) and the dashboard surfaces API error `.message` via a shared `extractApiErrorMessage` helper instead of rendering the raw error object. Regression guards: `tests/unit/authz/public-origin.test.ts` (direct LAN/loopback + DNS-rebinding defense), `tests/unit/api-error-message-5340.test.ts`. ([#5340](https://github.com/diegosouzapw/OmniRoute/issues/5340))
-
-### 📝 Maintenance
-
-- **chore(dead-code):** repo-wide sweep of unused exported symbols and a matching dead-code baseline ratchet — trimmed unused exported helpers, validation/settings/encryption-config schemas, utility/domain/static-constant/formatting helpers, runtime test helpers, the request-timeout fetch wrapper, event-bus, semantic-cache (maintenance + expiry), correlation-middleware, MCP-scope, service-registry, build-profile, api-key-format, authz-class, models.dev-context, embedding-cache, provider-limits-scheduler, search-validator, webhook-example, agent-skills-repo-URL and command-code-auth-cleanup exports. Pure dead-code removal validated by `typecheck:core` (no remaining referencing site) — no behavior change. ([#5321](https://github.com/diegosouzapw/OmniRoute/pull/5321), [#5322](https://github.com/diegosouzapw/OmniRoute/pull/5322), [#5324](https://github.com/diegosouzapw/OmniRoute/pull/5324), [#5325](https://github.com/diegosouzapw/OmniRoute/pull/5325), [#5328](https://github.com/diegosouzapw/OmniRoute/pull/5328), [#5329](https://github.com/diegosouzapw/OmniRoute/pull/5329), [#5330](https://github.com/diegosouzapw/OmniRoute/pull/5330), [#5331](https://github.com/diegosouzapw/OmniRoute/pull/5331), [#5333](https://github.com/diegosouzapw/OmniRoute/pull/5333), [#5334](https://github.com/diegosouzapw/OmniRoute/pull/5334), [#5335](https://github.com/diegosouzapw/OmniRoute/pull/5335), [#5336](https://github.com/diegosouzapw/OmniRoute/pull/5336), [#5338](https://github.com/diegosouzapw/OmniRoute/pull/5338), [#5339](https://github.com/diegosouzapw/OmniRoute/pull/5339), [#5353](https://github.com/diegosouzapw/OmniRoute/pull/5353), [#5354](https://github.com/diegosouzapw/OmniRoute/pull/5354), [#5355](https://github.com/diegosouzapw/OmniRoute/pull/5355), [#5356](https://github.com/diegosouzapw/OmniRoute/pull/5356), [#5357](https://github.com/diegosouzapw/OmniRoute/pull/5357), [#5359](https://github.com/diegosouzapw/OmniRoute/pull/5359), [#5362](https://github.com/diegosouzapw/OmniRoute/pull/5362), [#5364](https://github.com/diegosouzapw/OmniRoute/pull/5364), [#5365](https://github.com/diegosouzapw/OmniRoute/pull/5365), [#5366](https://github.com/diegosouzapw/OmniRoute/pull/5366), [#5368](https://github.com/diegosouzapw/OmniRoute/pull/5368), [#5369](https://github.com/diegosouzapw/OmniRoute/pull/5369), [#5371](https://github.com/diegosouzapw/OmniRoute/pull/5371) — thanks @JxnLexn)
-
----
-
-## [3.8.40] — TBD
-
-_In development — bullets added per PR; finalized at release._
-
----
-
-## [3.8.39] — 2026-06-28
-
-### ✨ New Features
-
-- **feat(oauth): remote Antigravity login via local helper + paste-credentials** — Antigravity (and other Google "native/desktop" OAuth providers) use Google's `firstparty/nativeapp` consent, which only releases the auth code when the loopback redirect (`127.0.0.1:<port>`) is reachable from the approving browser. On a remote VPS install that loopback lives on the server, so the consent hangs forever and never emits a code — the "paste the callback URL" fallback has nothing to paste (a Google-side constraint, identical in upstream 9router). A new `omniroute login antigravity` CLI helper runs the OAuth on the user's **own** machine (where 127.0.0.1 works), exchanges the code, and prints a single-line `omniroute-cred-v1.…` credential blob; the dashboard's Antigravity Connect → Step 2 field now accepts that blob (alongside callback URLs) and persists the connection via a new `paste-credentials` action (server-side onboarding, provider-allowlisted, with the blob's embedded provider required to match the route). The SSH local-forward tunnel is documented as a zero-tooling alternative. See [`docs/guides/REMOTE-MODE.md`](docs/guides/REMOTE-MODE.md). ([#5203](https://github.com/diegosouzapw/OmniRoute/pull/5203))
-- **feat(agent-bridge): graceful cert-install fallback for containers / headless** — when the MITM root CA can't be installed into the system trust store automatically (Docker / headless / no sudo / read-only trust store), the Agent Bridge no longer hard-fails on start with a generic "Certificate install failed". It now starts in skip mode and the dashboard surfaces a platform-specific **manual-install guide** (plus a CA download link) so the operator can trust the certificate by hand. The trust-cert endpoints return a structured `{ skippable, manualGuide }` response (HTTP 200) for environment failures instead of a 500; an explicit user cancellation is still reported distinctly. ([#4546](https://github.com/diegosouzapw/OmniRoute/issues/4546) — thanks @phuchptty)
-- **feat(compression): CCR ranged/grep/stats retrieval (ReDoS-safe, backward-compat)** — extends the `omniroute_ccr_retrieve` MCP tool and `/api/compression/retrieve` endpoint with optional `range` (byte/line slice), `grep` (ReDoS-safe literal or bounded-pattern match against stored lines), and `stats` (byte/line/word counts) parameters so agents pull exactly the slice or summary they need instead of re-expanding the entire stored block. All parameters are optional — no parameters returns the full block byte-identical to the existing behavior; the CCR store written by ionizer/fuzzy/headroom is fully compatible. Sixth item of the compression roadmap. ([#5187](https://github.com/diegosouzapw/OmniRoute/pull/5187))
-- **feat(compression): TOON best-of-N candidate encoder + encoder A/B table** — adds `@toon-format/toon` as a candidate encoder in the headroom compression engine via a best-of-N scheme: both GCF and TOON run per prompt and the shorter result is kept, rather than hard-swapping encoders (GCF already encodes the headroom block and TOON is not a lossless universal win). An encoder A/B comparison table (GCF vs TOON vs JSON — bytes and cl100k tokens) is now surfaced in the compression studio. Fifth item of the compression feature-extraction roadmap (bench: [#5080](https://github.com/diegosouzapw/OmniRoute/pull/5080), gate: [#5127](https://github.com/diegosouzapw/OmniRoute/pull/5127), fuzzy/gate: [#5143](https://github.com/diegosouzapw/OmniRoute/pull/5143), ionizer: [#5148](https://github.com/diegosouzapw/OmniRoute/pull/5148)). ([#5163](https://github.com/diegosouzapw/OmniRoute/pull/5163))
-
-### 🔧 Bug Fixes
-
-- **fix(oauth): Antigravity refresh no longer nulls the stored refresh_token on an empty upstream response** — Google's OAuth token endpoint uses non-rotating refresh tokens: a refresh response normally OMITS `refresh_token` and occasionally returns it as an empty string. The Antigravity executor's `refreshCredentials` used `typeof tokens.refresh_token === "string" ? tokens.refresh_token : credentials.refreshToken`, and because `typeof "" === "string"` is true, an empty-string response overwrote the good token with `""` — nulling it on first refresh. The check now treats a non-string **or empty** value as absent and preserves the stored token, matching the canonical `refreshGoogleToken` (`tokens.refresh_token || refreshToken`) semantics. ([#3850](https://github.com/diegosouzapw/OmniRoute/issues/3850) — thanks @3xa228148)
-- **fix(api): LAN/Tailscale dashboard access — `ws:` CSP scheme, GET-exempt version route, surface combo field errors** — three failures when opening the dashboard from a non-loopback host: (1) CSP `connect-src` allowed the `ws:` scheme only for loopback origins, blocking the dashboard's `ws://<lan-host>:*` Live WebSocket from LAN/Tailscale clients; the bare `ws:` scheme is now permitted (symmetric with the bare `wss:` already allowed), kept declarative in `next.config.mjs` with no global middleware (the project has none by design); (2) `GET /api/system/version` was blocked by `LOCAL_ONLY_API_PREFIXES` for all methods despite only `POST` spawning child processes (git/npm/pm2) — a new `LOCAL_ONLY_API_GET_EXEMPTIONS` set exempts safe read methods for this path while keeping `POST`/`PUT`/`PATCH`/`DELETE` strictly loopback-only; (3) `COMBO_002` validation errors only surfaced the generic message — `firstField`/`firstMessage` are now extracted from the first Zod issue and included in the response body. ([#5083](https://github.com/diegosouzapw/OmniRoute/issues/5083) — thanks @KooshaPari for the diagnosis and original PR #5084)
-- **fix(sse): defer `</think>` close so it never leaks before `tool_calls` in Claude→OpenAI streaming** — when a Claude thinking block was followed by a tool_use block, the translator unconditionally emitted a `content: "</think>"` chunk at `content_block_stop`, injecting a spurious assistant text chunk immediately before the `tool_calls` delta and corrupting OpenAI-compatible clients (e.g. Kimi Coding). The close marker is now deferred: it is flushed at the first `text_delta` that follows the thinking block (preserving the #4633 / decolua/9router#454 behavior for Claude Code / Cursor) or at stream finish when no tool_calls were collected. Tool-use streams never get a `text_delta` after the thinking block, so `</think>` is never emitted into content before `tool_calls`. ([#5123](https://github.com/diegosouzapw/OmniRoute/issues/5123))
-- **fix(sse): normalize array user-message content in the Command Code executor to prevent upstream 400** — when a client sends a user turn whose `content` is an array of content parts (e.g. `[{type:"text",text:"…"}, …]`), the raw array was forwarded verbatim to the Command Code upstream, which requires `messages[N].content` for the `user` role to be a plain string — resulting in `expected string, received array` / HTTP 400 on DeepSeek V4-Pro and other Command Code models. The user branch of `convertMessages` now calls `normalizeContentText()` (already used by system, assistant, and tool branches) so multi-part user content is joined to a string before dispatch. Partially addresses ([#5166](https://github.com/diegosouzapw/OmniRoute/issues/5166)); the 0-output-token symptom on reasoning-only models is tracked separately.
-- **fix(mcp): return HTTP 404 (not 400) for an unknown/expired Streamable HTTP session id** — when an MCP session is terminated or idles out and the client reuses the stale `Mcp-Session-Id` header, the Streamable HTTP transport replied with HTTP 400. The MCP spec (2025-03-26 and 2025-11-25, Session Management) mandates HTTP 404 Not Found in that case, and spec-compliant clients only re-initialize a session on 404 — so the 400 was non-recoverable. The handler now returns 404 for a present-but-unknown session id, while a _missing_ session id on a non-initialize request correctly stays 400. ([#5169](https://github.com/diegosouzapw/OmniRoute/issues/5169) — thanks @czer323)
-- **fix(api): blocking "Auto (Zero-Config)" in Security settings now removes `auto/*` from `/v1/models`** — the built-in `auto/*` combo advertiser (#4164 / #4235) at the top of the models catalog ignored `settings.blockedProviders`, so checking **Auto (Zero-Config)** under Security → Blocked Providers had no effect and the model picker kept listing every `auto/*` entry. The injection loop now skips the entire `auto/*` block when the system provider `auto` (its id and alias are both `auto`) is blocked, consistent with how every other provider is filtered from the catalog. ([#5192](https://github.com/diegosouzapw/OmniRoute/issues/5192) — thanks @WslzGmzs)
-- **fix(cli): auto-calibrate the server V8 heap from physical RAM instead of a fixed 512MB default** — the server was spawned with a hard-coded `--max-old-space-size=512` (`omniroute serve`) or with no heap flag at all (Electron desktop, which then inherited the runtime's low ~512MB default), so RAM-rich machines still OOM-crashed under load (`FATAL ERROR: Ineffective mark-compacts near heap limit … ~500MB` at code=134) with many providers/accounts and large model catalogs (one report: 16GB RAM, 65 providers, ~100 accounts, ~2600 models). A new `calibrateHeapFallbackMb(os.totalmem())` helper derives the default heap as ~35% of physical RAM, clamped to `[512, 4096]`, and is wired into both `bin/cli/commands/serve.mjs` and `electron/main.js`. An explicit `OMNIROUTE_MEMORY_MB` (or a pre-set `--max-old-space-size`) still wins, so the #2939 override contract is unchanged. ([#5172](https://github.com/diegosouzapw/OmniRoute/issues/5172), [#5160](https://github.com/diegosouzapw/OmniRoute/issues/5160), [#5152](https://github.com/diegosouzapw/OmniRoute/issues/5152) — thanks @manchairwang, @Xyzjesus)
-
-- **fix(oauth): Antigravity login no longer hangs — fire-and-forget onboarding + bounded post-exchange** — the dashboard's Antigravity OAuth login spun indefinitely because `postExchange` awaited the `onboardUser` retry loop inline (up to 10 × 5 s per attempt, each fetch with no timeout), blocking the `/exchange` response forever. Matching the upstream 9router web flow: `onboardUser` now runs fire-and-forget in a background task; the `/exchange` endpoint is bounded by a 10 s hard timeout so it always returns; a progress endpoint lets the dashboard poll onboarding completion state. ([#5193](https://github.com/diegosouzapw/OmniRoute/pull/5193))
-- **fix(antigravity): retry Antigravity accounts by quota family before escalating the combo** — when one Antigravity account returns a quota or rate-limit `429` for a Gemini model (e.g. `gemini-3.5-flash-medium`), combo orchestration could prematurely advance to the next combo model instead of trying other eligible Antigravity accounts for the same quota family. Antigravity quota-family awareness is now added to the fallback path so a `429` on one account triggers a bounded same-model retry across other Antigravity accounts sharing that quota bucket before the combo degrades to a lower-tier model. ([#5180](https://github.com/diegosouzapw/OmniRoute/pull/5180) — thanks @Ardem2025)
-- **fix(translator): accept Claude Messages shape in the non-stream malformed-200 guard** — when a Claude client (e.g. Claude Code) is routed to a non-Claude provider, the translated non-streaming response body is in Claude Messages shape (`type: "message", content[]`) produced by `convertOpenAINonStreamingToClaude`. `detectMalformedNonStream` only recognized OpenAI `choices[].message` and Responses API `output[]`, so this shape fell through to `empty_choices` → 502. The guard now recognizes the Claude Messages shape: text, tool_use, and thinking blocks carrying a `signature` count as valid output, while a genuinely empty `content: []` is still flagged. ([#5156](https://github.com/diegosouzapw/OmniRoute/pull/5156) — thanks @NomenAK)
-- **fix(sse): resolve nameless deepseek-web `<tool>` blocks via parameter-schema match** — when `chat.deepseek.com` emits a `<tool>` block with no `<name>` child, no JSON body `name`/`type` key, and no tag suffix, every name-resolution path in `extractCall` returned `null` and the raw XML leaked to the client as plain text. A conservative schema-based fallback now compares the block's extracted parameter names against each declared tool's schema keys; if exactly one tool matches, its name is used. Zero or ambiguous (>1) matches still return `null` so no calls are misattributed. ([#5154](https://github.com/diegosouzapw/OmniRoute/issues/5154), [#5173](https://github.com/diegosouzapw/OmniRoute/pull/5173))
-- **fix(stream): normalize provider safety finish reasons to `content_filter`** — Gemini and Antigravity can return safety/prohibited terminal reasons (`SAFETY`, `RECITATION`, `BLOCKLIST`, `PROHIBITED_CONTENT`) that OpenAI-compatible downstream clients do not recognize. A shared finish-reason normalization helper now maps these to the standard `content_filter` value, applied in both the streaming and JSON collection paths for both providers. ([#5197](https://github.com/diegosouzapw/OmniRoute/pull/5197) — thanks @rdself)
-- **fix(responses): normalize non-array Responses API `input` before routing** — the OpenAI Responses API accepts `input` as a string, object, or list, but OmniRoute only handled list-shaped payloads; a string or object `input` was silently dropped on the Responses→Chat Completions path. The translator now normalizes `input` to a list before dispatch; the Codex-native Responses path also normalizes before forwarding (preventing upstream `400 Input must be a list`); and the prompt-injection and PII sanitizer extraction paths are guarded against object-valued `input` so security checks do not throw. ([#5204](https://github.com/diegosouzapw/OmniRoute/pull/5204) — thanks @wilsonicdev)
-- **fix(zenmux): normalize vendor-prefixed GLM system roles for Z.AI models** — ZenMux exposes Z.AI GLM via vendor-prefixed OpenAI-compatible IDs such as `z-ai/glm-5.2`. The existing GLM detection only matched bare `glm-*`/`glm` ids, so `zenmux/z-ai/glm-5.2` kept system messages in place; Z.AI rejects compressed histories ending with a system turn before `assistant(tool_calls) → tool` sequences. The fix extends GLM detection to cover `z-ai/glm-*` prefixes and routes them through the existing `normalizeSystemRole` path. ([#5158](https://github.com/diegosouzapw/OmniRoute/pull/5158) — thanks @Thinkscape)
-- **fix(xai): add OAuth connection test probe + normalize xAI reasoning effort aliases** — xAI rejects unsupported reasoning effort values (`max`, `xhigh`) with HTTP 400 after a provider update; the xAI translator now maps `max` and `xhigh` to `high` before forwarding. Additionally, xAI OAuth connections had no dashboard test configuration, so provider tests returned `"Provider test not supported"`; a dedicated OAuth test probe is now wired for xAI accounts with regression coverage for the effort normalization. ([#5157](https://github.com/diegosouzapw/OmniRoute/pull/5157) — thanks @nguyenxvotanminh3)
-- **fix(serve): honour `HOSTNAME` from `.env` instead of hardcoding `0.0.0.0`** — `bin/cli/commands/serve.mjs` spread `process.env` into the child-process environment but immediately overwrote `HOSTNAME` with a literal `"0.0.0.0"`, silently discarding any user-configured bind address even though `HOSTNAME` is documented in `.env.example` and `docs/reference/ENVIRONMENT.md`. `dist/server.js` already read `process.env.HOSTNAME` correctly; only the CLI wrapper was overriding it. The fix applies `process.env.HOSTNAME || "0.0.0.0"` so the env value takes effect. ([#5134](https://github.com/diegosouzapw/OmniRoute/issues/5134), [#5170](https://github.com/diegosouzapw/OmniRoute/pull/5170) — thanks @anki1kr / @Angelo90810)
-- **fix(cli): force `NODE_ENV` to match dev/start run mode in the custom Next server** — when `.env.example` ships `NODE_ENV=production`, starting `npm run dev` via `scripts/dev/run-next.mjs` forwarded that value to the programmatic `next()` entry, which — unlike the `next` CLI — does not normalize it to match the run mode. The resulting production flag caused PostCSS to skip Tailwind's CSS transform, surfacing as `Module parse failed: Unexpected character '@'` on `globals.css`. The custom server now explicitly forces `NODE_ENV=development` for the `dev` path and `NODE_ENV=production` for the `start` path regardless of `.env`. ([#5189](https://github.com/diegosouzapw/OmniRoute/pull/5189) — thanks @backryun)
-- **fix(cli): raise dev server Node heap limit to 8 GB to prevent OOM** — `npm run dev` crashed with `FATAL ERROR: Ineffective mark-compacts near heap limit — Allocation failed - JavaScript heap out of memory` while compiling heavy dashboard routes because `node scripts/dev/run-next.mjs` ran on V8's ~4 GB default with no `--max-old-space-size` flag. The `dev` npm script now passes `--max-old-space-size=8192` at invocation time (the only point where this flag can be set for that process). ([#5198](https://github.com/diegosouzapw/OmniRoute/pull/5198) — thanks @backryun)
-- **fix(cli): re-enable Turbopack as the default `npm run dev` bundler** — PR #4092 forced webpack because an earlier Turbopack 16.2.x panic (`internal error: entered unreachable code: there must be a path to a root` in `turbopack-core/module_graph`) blocked the OmniRoute module graph. That panic no longer reproduces on the pinned Next 16.2.9, so `OMNIROUTE_USE_TURBOPACK` is flipped from `0` to `1` in `.env.example`, aligning it with `docs/reference/ENVIRONMENT.md` which had already documented the default as `1`. ([#5206](https://github.com/diegosouzapw/OmniRoute/pull/5206) — thanks @backryun)
-- **fix(auth): allow synthetic no-auth fallback for mimocode** — mimocode connections without explicit credentials were blocked before reaching the executor. The auth layer now permits a synthetic no-auth fallback for the mimocode provider so credential-free access patterns work as intended. ([#5205](https://github.com/diegosouzapw/OmniRoute/pull/5205) — thanks @KooshaPari)
-- **fix(combo): reject empty Responses API `output: []` as a fail-over trigger** — a non-streaming Responses API body with `object: "response"` and `output: []` was accepted as a valid HTTP 200 by the combo response-quality validator, allowing a combo target to stop rather than fail over to the next leg. The non-stream validator now inspects Responses-API-shaped bodies before the generic `output` shortcut and rejects an empty `output: []` as `empty_choices`; structural non-empty output (e.g. `function_call`) remains valid. ([#5207](https://github.com/diegosouzapw/OmniRoute/pull/5207) — thanks @KooshaPari)
-- **fix(proxy): close cached dispatchers when clearing the proxy cache** — cached proxy and direct-retry dispatchers were not closed on cache clear, leaking open connection handles. The cache-clear path now calls `close()` on all evicted dispatchers; dispatcher cache and lifecycle helpers have been extracted from the oversized proxy-dispatcher module into a dedicated helper for reuse. ([#5202](https://github.com/diegosouzapw/OmniRoute/pull/5202) — thanks @KooshaPari)
-- **fix(proxy): coalesce concurrent fast-fail health probes per proxy URL** — under high concurrency each simultaneous request opened its own TCP health probe for the same proxy URL, creating a thundering-herd burst. Concurrent proxy fast-fail checks are now coalesced so only one TCP probe runs per proxy URL at a time; the completed-result health cache is preserved so subsequent same-URL checks return immediately. ([#5109](https://github.com/diegosouzapw/OmniRoute/issues/5109), [#5208](https://github.com/diegosouzapw/OmniRoute/pull/5208) — thanks @KooshaPari)
-- **fix(pwa): prefer cached navigation before showing the offline page** — the service worker was too eager to display `/offline` on transient navigation failures. It now caches successful navigation responses and consults the cached route or app shell before falling back to `/offline`; `/offline` remains the final fallback when no cached navigation or app shell exists. ([#5165](https://github.com/diegosouzapw/OmniRoute/issues/5165), [#5209](https://github.com/diegosouzapw/OmniRoute/pull/5209) — thanks @KooshaPari)
-- **fix(request-logger): never render a negative percentage in the compression badge** — when every prompt token was compressed (`totalIn = 0, compressed > 0`), the compression pill displayed `(-100%)` because the badge format hard-coded a leading `-` before the percentage value. The badge now omits the negative sign in this case, correctly representing the saving as a positive ratio. ([#5201](https://github.com/diegosouzapw/OmniRoute/pull/5201) — thanks @KooshaPari)
-- **fix(dashboard): use amber for home update-step warning icon** — the warning-state icon in the home update steps (`HomePageClient.tsx`) used `text-yellow-500` (Tailwind `#eab308`), which has poor contrast on light backgrounds (~1.9:1, below WCAG AA) and is inconsistent with the `amber` warning convention used by every sibling element in the same component. Switched to `text-amber-500` — a one-line `className` change with no behavior change. ([#5176](https://github.com/diegosouzapw/OmniRoute/pull/5176))
-
-### 📝 Maintenance
-
-- **test(combo): deterministic context-relay universal-handoff coverage** — covers the universal (provider-agnostic) session-handoff path in `context-relay` (`combo.ts:2099–2139`), which previously had only a definition-order assertion and a `TODO(phase-2)`. The test drives the real pipeline via session seams (`x-session-id` → `relayOptions.sessionId` → `maybeGenerateUniversalHandoff`) without live infrastructure. ([#5168](https://github.com/diegosouzapw/OmniRoute/pull/5168))
-- **test(combo): end-to-end quota-share DRR routing-decision coverage (matrix parity)** — adds the missing E2E test for the `quota-share` strategy, driving the real `handleChat` → chatCore → `selectQuotaShareTarget` → executor pipeline via in-process seams and asserting which connection is dispatched. The DRR selector already had 29 unit tests; this closes the E2E gap and brings quota-share to parity with the 17-strategy public matrix. ([#5179](https://github.com/diegosouzapw/OmniRoute/pull/5179))
-- **test(combo): deterministic context-relay codex quota-handoff coverage (closes last gap)** — covers the codex-specific handoff block of `context-relay` (`combo.ts:2143–2183`), which #5168 left documented-but-untested because it requires a `codex` connection. All seams (`fetchCodexQuota`, handoff generation, session relay) are mocked deterministically without live infra. ([#5195](https://github.com/diegosouzapw/OmniRoute/pull/5195))
-- **test(ci): wire antigravity-quota-family test under `test:vitest` (fix test-discovery orphan)** — `open-sse/services/__tests__/antigravity-quota-family.test.ts` (introduced by #5180) was not collected by any active runner, causing `check:test-discovery` to report a new orphan and gate every subsequent PR on the release branch. The file is now added to `vitest.mcp.config.ts` `include` and the corresponding orphan-allowlist entry is removed. ([#5196](https://github.com/diegosouzapw/OmniRoute/pull/5196))
-- **test(security): regression guard — PII redaction stays opt-in (default off) + Hard Rule #20** — adds a test asserting both `PII_REDACTION_ENABLED` and `PII_RESPONSE_SANITIZATION` feature-flag `defaultValue` fields are `"false"` and that data passes through all three application points (`piiMasker`, `piiSanitizer`, `streamingPiiTransform`) untouched when both flags are off, encoding Hard Rule #20 as a CI-enforced contract and fixing a misleading doc implication that PII masking was on by default. ([#5159](https://github.com/diegosouzapw/OmniRoute/pull/5159))
-- **docs(i18n): add Traditional Chinese (zh-TW) README + update zh-CN** — adds a new Traditional Chinese translation (`docs/i18n/zh-TW/README.md`) and updates the Simplified Chinese README to the current English baseline; the language index (`docs/i18n/README.md`) and root `README.md` badge row are updated accordingly. ([#5162](https://github.com/diegosouzapw/OmniRoute/pull/5162) — thanks @lunkerchen)
-- **docs(i18n): full sync of zh-TW and zh-CN README to canonical English v3.8.39** — brings both translations to full parity, adding the complete What's New section, compression real-token examples, and all sections updated in the v3.8.38/39 English README. ([#5171](https://github.com/diegosouzapw/OmniRoute/pull/5171) — thanks @lunkerchen)
-- **docs(combo): sync combo/routing-strategy docs to current state + document test coverage** — removes a stale ordinal from the Fusion bullet in `README.md`; adds a new **Testing & Coverage** section to `docs/routing/AUTO-COMBO.md` documenting the deterministic strategy matrix (`npm run test:combo:matrix`), quota-share DRR E2E coverage, and context-relay handoff tests delivered across the v3.8.39 cycle. ([#5185](https://github.com/diegosouzapw/OmniRoute/pull/5185))
-- **fix(docker):** copy the `open-sse` workspace manifest before `npm ci` so workspace-only deps install — the Dockerfile copied only the root `package*.json`, so `npm ci` skipped `safe-regex` and `@toon-format/toon` (declared in `open-sse/package.json`, not hoisted to root), breaking the multi-arch image build with `Module not found` during `npm run build`. (thanks @diegosouzapw)
-
----
-
-## [3.8.38] — 2026-06-27
-
-### ✨ New Features
-
-- **feat(sidebar): colored menu icons** — sidebar menu icons now render with a per-item accent color: curated colors for known items (`SIDEBAR_ICON_ACCENTS`) plus a deterministic hash-based fallback (`getSidebarIconAccent`) so every item gets a stable, distinct color across sessions. ([#3812](https://github.com/diegosouzapw/OmniRoute/pull/3812) — thanks @rafacpti23)
-- **feat(providers): add Factory (factory.ai) as a subscription gateway provider** — `factory` (Factory Droids' hosted gateway) is now a first-class routing provider on the OpenAI-compatible `https://api.factory.ai/v1` endpoint with Bearer apikey auth; the key is supplied from the Dashboard connection (not env). ([#5065](https://github.com/diegosouzapw/OmniRoute/pull/5065) — thanks @KooshaPari)
-- **feat(providers): add Grok Build (xAI) provider with OAuth import-token flow** — `grok-cli` (alias `gc`) routes through Grok's CLI chat proxy; users paste their `~/.grok/auth.json` (or the JWT), with automatic `refresh_token` rotation. The public xAI client_id is embedded via `resolvePublicCred("grok_id")` (Hard Rule #11), never a literal. ([#5020](https://github.com/diegosouzapw/OmniRoute/pull/5020) — thanks @fulorgnas)
-- **feat(dashboard): click-to-edit model alias in the provider page** — click an alias to edit it inline (Enter/blur saves, Escape cancels), instead of only being able to delete and re-add it. ([#5119](https://github.com/diegosouzapw/OmniRoute/pull/5119) — thanks @waguriagentic)
-- **feat(providers): add ZenMux Free (session-cookie free-tier) provider** — `zenmux-free` (alias `zmf`) with a dedicated executor translating ZenMux's Anthropic-style SSE to OpenAI format; ships 12 free-tier models (DeepSeek V3.2, GLM 4.7 Flash Free, etc.). ([#5105](https://github.com/diegosouzapw/OmniRoute/pull/5105) — thanks @mrnasil)
-- **feat(providers): allow local/private provider URLs by default (`Allow Local Provider URLs` flag)** — adding/validating an OpenAI-compatible provider on a loopback/LAN address (e.g. `http://127.0.0.1:3264/api`) was rejected by the SSRF guard with "Blocked private or local provider URL", even though OmniRoute is local-first. A new `OMNIROUTE_ALLOW_LOCAL_PROVIDER_URLS` feature flag (default **ON**, toggle in Settings → Feature Flags) now scopes the provider-validation guard to allow local/private hosts while still blocking cloud-metadata endpoints (169.254.169.254, metadata.google.internal). Disable it to restore strict public-only blocking. Webhook/remote-image SSRF defaults are unchanged. ([#5066](https://github.com/diegosouzapw/OmniRoute/issues/5066), thanks @daniij)
-- **feat(blackbox):** refresh provider model catalog with latest models. (thanks @ptkelanatechsolutions)
-- **kiro**: inline `<thinking>` stream splitter — when `<thinking_mode>enabled</thinking_mode>` is present, `assistantResponseEvent` content is now split into separate `delta.content` / `delta.reasoning_content` SSE chunks (new `open-sse/executors/kiroThinking.ts` module wired into `KiroExecutor.transformEventStreamToSSE`).
-- **feat(cursor):** parse Cursor Composer DeepSeek-style inline tool calls — Composer `cu/composer-2.5*` models embed tool invocations in their visible text using `<｜tool▁calls▁begin｜>…<｜tool▁calls▁end｜>` markers instead of structured protobuf frames; a new streaming parser (`composerToolCalls.ts`) intercepts these in both streaming and non-streaming paths, suppresses the markers from the client-visible content, and emits proper OpenAI `tool_calls` deltas so downstream clients handle them natively. (thanks @noestelar)
-- **feat(proxy):** support auth-less `host:port` batch import and surface proxy-test failures. (thanks @dimaslanjaka)
-- **feat(video): Alibaba DashScope video provider (`wan2.7-t2v`)** — adds the `alibaba` video provider (DashScope async task → poll → MP4) wired through the standard apikey credential path, so text-to-video requests can route to Alibaba's `wan2.7-t2v` model. (thanks @josevictorferreira)
-- **feat(cc): per-connection "summarized thinking display" toggle for Claude-Code-compatible providers** — exposes a connection-level toggle that drives the existing Copilot summarized-thinking marker, so operators can opt a CC-compatible connection into summarized reasoning display from the UI (schema + request defaults + provider modals, with i18n). (thanks @rdself)
-- **feat(compression): compression playground in the studio (Play + Compare tabs)** — `/dashboard/compression/studio` gains a synthetic playground: paste text → per-engine **lanes** (each deterministic engine run alone via `/api/compression/preview`) plus a **combined waterfall** ordered by `stackPriority`, and a free **A/B Compare** grid with on-demand, **USD-capped** fidelity verdicts (`/api/compression/compare` + `compare/verify`). The preview route now uses the real cl100k tokenizer, returns `engineBreakdown`, and accepts an ordered `pipeline[]`; new `compare` / `compare/verify` / `retrieve` routes; the live WS feed moved to `/dashboard/compression/live`. Management-only. ([#5080](https://github.com/diegosouzapw/OmniRoute/pull/5080))
-- **feat(dashboard): expose Fusion `judgeModel` + `fusionTuning` in the combo editor** — the Fusion strategy editor now surfaces the judge model (synthesizes the panel answers; defaults to the first panel model) plus the quorum-grace tuning fields (`minPanel`, `stragglerGraceMs`, `panelHardTimeoutMs`) that `open-sse/services/fusion.ts` already reads. Schema-validated + bounded; empty tuning is never persisted. ([#5074](https://github.com/diegosouzapw/OmniRoute/pull/5074))
-- **feat(compression): opt-in per-step fidelity gate for the stacked pipeline** — each compression step can now be guarded by a pure fidelity checker (4 invariants, fail-open) so a lossy engine that would degrade the prompt past a threshold is rejected and its lane skipped instead of silently shipping. Configurable via `fidelityGate` (advanced thresholds intentionally API-omitted), with a per-lane rejection breakdown surfaced in the studio playground toggle. ([#5143](https://github.com/diegosouzapw/OmniRoute/pull/5143))
-- **feat(compression): fuzzy near-duplicate dedup (session-dedup 2nd pass)** — the session-dedup engine gains a second fuzzy pass that collapses near-duplicate (not just byte-identical) segments, with a playground toggle to compare on/off. ([#5143](https://github.com/diegosouzapw/OmniRoute/pull/5143))
-- **feat(quota): opt-in Codex/Claude auto-ping keepalive** — an opt-in background keepalive can periodically ping Codex/Claude connections to keep their session/quota state warm, reducing cold-start failures on the first real request. ([#5102](https://github.com/diegosouzapw/OmniRoute/pull/5102))
-- **feat(ops): SRE playbooks + ops helper scripts** — salvaged from a closed stale PR; adds operator runbooks and ops helper scripts. ([#5138](https://github.com/diegosouzapw/OmniRoute/pull/5138) — thanks @KooshaPari / @diegosouzapw)
-- **feat(mcp): web-session robustness — cookie dedup + browser-pool observability** — the MCP web-session path now de-duplicates cookies when (re)hydrating a session (avoiding conflicting duplicate `Cookie` headers) and exposes browser-pool observability (pool size / in-use / acquisition metrics) for the headless web providers. ([#5121](https://github.com/diegosouzapw/OmniRoute/pull/5121), builds on [#3368](https://github.com/diegosouzapw/OmniRoute/issues/3368))
-- **feat(compression): Ionizer engine — lossy JSON-array sampling reversible via CCR** — a new compression engine that down-samples large JSON arrays to a representative subset and records a Compact Change Representation (CCR) so the omitted rows can be reconstructed, trading exactness for a large token reduction on tabular/array-heavy payloads. ([#5148](https://github.com/diegosouzapw/OmniRoute/pull/5148))
-
-### 🔧 Bug Fixes
-
-- **fix(proxy): make the SOCKS5 handshake timeout operator-tunable (`SOCKS_HANDSHAKE_TIMEOUT_MS`)** — under high concurrency against a single residential gateway host, the SOCKS5 connect handshake could exceed the hardcoded 10s even though the proxy was reachable, surfacing as a false `[Proxy Fast-Fail] Proxy unreachable` (the pool size is already tunable via `OMNIROUTE_PROXY_DISPATCHER_CONNECTIONS`). The handshake timeout now reads `SOCKS_HANDSHAKE_TIMEOUT_MS` (default unchanged at `10000`, capped at `120000`) so a concurrency-heavy deployment can raise it without a code change. Mitigation for #5109 (the full concurrency-100 collapse still needs the reporter's live load-test confirmation). ([#5109](https://github.com/diegosouzapw/OmniRoute/issues/5109))
-- **fix(api): resolve `GET /v1/models/{id}` case-insensitively** — clients that normalise the model id (e.g. OpenCode requesting `minimax/minimax-m3` for the canonical catalog entry `minimax/MiniMax-M3`) missed the single-model lookup, which is case-sensitive, and fell back to advertising `context_length: 0`. `findModelById` now prefers an exact-case match and falls back to a case-insensitive match, so the real entry (and its context window) is returned regardless of casing. ([#5082](https://github.com/diegosouzapw/OmniRoute/issues/5082))
-- **fix(services): embed WS proxy honours `LIVE_WS_HOST`; reject empty `messages` early** — two headless/Docker deployment fixes (#5110). The embed WebSocket proxy (`:20131`) only read `EMBED_WS_PROXY_HOST`, so behind a reverse proxy/tunnel it stayed bound to `127.0.0.1` even with `LIVE_WS_HOST=0.0.0.0` set and the Live dashboard showed "WebSocket disconnected"; it now falls back to `LIVE_WS_HOST` (default still loopback). Separately, a request with an explicitly empty `messages: []` array was forwarded upstream and bounced back as a confusing raw `400/502`; `handleChat` now rejects it up front with a clear `messages: at least one message is required` (Responses-API `input` requests are unaffected). ([#5110](https://github.com/diegosouzapw/OmniRoute/issues/5110))
-- **fix(proxy): repair one-click Deno & Cloudflare relay deployments** — the `/api/settings/proxy/test` endpoint only recognized the `vercel` relay type, so testing a deployed Deno or Cloudflare relay returned `proxy.type must be http, https, or socks5` and never reached the relay; it now routes all relay types through `isRelayType()`. On installs with `STORAGE_ENCRYPTION_KEY` the relay-auth token is read via `extractRelayAuth` (encrypted `relayAuthEnc` form), fixing the silent `401` that left `publicIp` null. The Cloudflare Worker upload now sends the script part as `application/javascript` (the API rejects `application/javascript+module`; ES-module semantics come from `main_module`), and the proxy-registry schema accepts the `deno`/`cloudflare` types + `deno-relay`/`cloudflare-relay` sources so editing a deployed relay no longer 400s. ([#5128](https://github.com/diegosouzapw/OmniRoute/issues/5128))
-- **fix(kiro): retire `claude-sonnet-4.5` from the Kiro catalog + pin the exact Kiro 400 error** — `claude-sonnet-4.5` left the Kiro free-tier lineup (current active models: Opus 4.8/4.7/4.6, Sonnet 4.6, Haiku 4.5), so it is removed from the Kiro registry entry and the free-model catalog. A regression test now pins Kiro's verbatim `[400] Invalid model. Please select a different model to continue.` to the `isModelUnavailableError` model-unavailable classification. A 400 on every model (including current ones) points to a server-side Kiro tier/region gate, not an OmniRoute catalog bug. ([#5140](https://github.com/diegosouzapw/OmniRoute/pull/5140), closes [#4484](https://github.com/diegosouzapw/OmniRoute/issues/4484))
-- **fix(dashboard): preserve every rendered field when loading/saving Resilience settings** — `ResilienceTab` renders `comboCooldownWait` and `quotaShareConcurrencyLimit`, but both the initial-load and save paths rewrote component state without those fields, so after a successful `/api/resilience` response the cards received `undefined` and the page fell back to the generic "failed to load" state. A shared `toResilienceResponse()` mapper now keeps all rendered fields, and `PATCH /api/resilience` returns `quotaShareConcurrencyLimit` to match GET and the UI contract. ([#5139](https://github.com/diegosouzapw/OmniRoute/pull/5139) — thanks @rdself)
-- **fix(quota): hydrate the in-memory quota cache from snapshots + scope auto-combo candidates** — after a restart the quota cache was empty, so a known-exhausted connection looked healthy until re-queried; `isAccountQuotaExhausted` now lazily hydrates from persisted `quota_snapshots`. Auto-combo candidate expansion is also scoped to the connections each combo target actually allows, instead of pulling in every connection for the provider. ([#5015](https://github.com/diegosouzapw/OmniRoute/pull/5015) — thanks @JxnLexn)
-- **fix(resilience): harden quota cutoff, Gemini audio MIME, and model-lockout cooldown** — stored quota hard-cutoff values are no longer coerced to `enabled=true` from arbitrary strings; Gemini audio input parts have their MIME type validated/normalized before forwarding; and model lockout now honours the configured `maxCooldownMs` ceiling. ([#5093](https://github.com/diegosouzapw/OmniRoute/pull/5093) — thanks @KooshaPari)
-- **fix(streaming): harden long OpenAI-compatible SSE streams** — a late pipeline-wind-down error can no longer overwrite an already-recorded successful stream (`streamCompletionRecorded` guard), client disconnects finalize as `499 client_disconnected` instead of poisoning provider/account failure state, JSON bodies that are actually SSE (wrong `application/json` content-type) are sniffed and re-streamed, and reasoning fields (`reasoning`/`reasoning_content` + OpenRouter/Gemini encrypted `reasoning_details`) are preserved through the JSON-as-SSE fallback. ([#5124](https://github.com/diegosouzapw/OmniRoute/pull/5124) — thanks @rdself)
-- **fix(usage): dedupe request-usage logging and debounce stats events** — `saveRequestUsage` now guards against duplicate inserts (natural key: timestamp + provider + model + connection + api-key + token counts), back-fills a missing `endpoint`, and only emits `usageRecorded` when a row was actually inserted; stats `update`/`pending` event bursts are collapsed into a single debounced notification to reduce churn. ([#4940](https://github.com/diegosouzapw/OmniRoute/pull/4940) — thanks @nguyenxvotanminh3)
-- **fix(sse): convert the native Gemini request body to OpenAI format in the Antigravity MITM handler** — `contents` / `systemInstruction` / `generationConfig` / `thinkingConfig` are now translated to OpenAI chat-completions format before forwarding to `/v1/chat/completions`, so thinking-capable models (e.g. `ag/claude-opus-4-6-thinking`) no longer fail with provider-side 400 "invalid argument" errors. ([#4845](https://github.com/diegosouzapw/OmniRoute/pull/4845) — thanks @anuragg-saxenaa)
-- **fix(db): translate the two pt-BR SQLite driver-fallback log lines to English** — `[DB] Pré-inicializando sql.js WASM…` and `[DB] Drivers síncronos indisponíveis…` were the only non-English server log strings, mixing languages in the logs. Now `[DB] Pre-initializing sql.js WASM (synchronous drivers unavailable)…` / `[DB] Synchronous drivers unavailable — falling back to sql.js (WASM)`, guarded by a test that scans the driver path for accented log strings. ([#5103](https://github.com/diegosouzapw/OmniRoute/issues/5103))
-- **fix(diagnostics): non-streaming Claude responses no longer false-502 as `empty_choices`** — the v3.8.37 malformed-200 detector (#4942) only understood OpenAI `choices` and Responses-API `output` shapes, so a `/v1/messages` response that stays in Claude shape (`{type:"message", content:[…]}`) fell through to `empty_choices` → 502 (cascading to "All models failed" in a combo). Most visibly, an extended-thinking turn whose buffered body is a single **empty thinking block with a valid `signature`** (Claude Code's non-streaming Bash classifier) 502'd on every call. `detectMalformedNonStream` now understands the Claude shape: text/tool_use blocks and thinking blocks carrying a signature count as valid output, while a genuinely empty `content:[]` is still flagged. ([#5108](https://github.com/diegosouzapw/OmniRoute/issues/5108), thanks @insoln)
-- **fix(combo): empty-content 502 now fails over within the same request instead of exhausting the provider** — a leg that answers HTTP 200 with no usable completion is rewritten to `502 "Provider returned empty content"`, but the combo exhaustion classifier treated that synthetic 502 as a connection-level failure (`#1731v2`) and marked the whole provider/connection exhausted, skipping every remaining **same-provider** leg in that request. The connection is actually healthy (it just returned an empty body), so empty-content 502s are now classified as model-level transient failures: the request advances to the next leg and the rest of that provider's legs stay eligible. Genuine gateway 502s still trip connection exhaustion. ([#5085](https://github.com/diegosouzapw/OmniRoute/issues/5085), thanks @andrea-kingautomation)
-- **fix(dashboard): surface the detailed credential-validation error instead of a bare "invalid" badge** — the inline "Check" in the Add-Connection modal discarded the `error` message returned by `/api/providers/validate` and showed only an `invalid` badge. For web providers (claude-web / chatgpt-web) the real cause is often an environment error the backend already reports (e.g. `TLS impersonation client failed to start: EACCES … mkdir tls-client-node/bin`), so users were left guessing. The modal now renders the full reason next to the badge. ([#5088](https://github.com/diegosouzapw/OmniRoute/issues/5088), thanks @tkhs101)
-- **fix(executors): strip `client_metadata` from forwarded body for Cerebras and Mistral** — Cerebras returns 400 (`wrong_api_format`) and Mistral returns 422 (`extra_forbidden`) when the passthrough body carries `client_metadata` (an OpenAI Codex / Claude CLI field with no equivalent on these upstreams). The default executor now drops it for these two providers before sending downstream; other providers (notably `openai`/`codex`) keep it. (thanks @saurabh321gupta)
-- **fix(codebuddy):** only send reasoning params when the client requests reasoning. (thanks @anki1kr)
-- **fix(sse):** keep streaming for forceStream providers when a JSON client requests it. Providers marked `forceStream:true` reject `stream:false` upstream (HTTP 400); `resolveStreamFlag` now guards against this so stream-only providers keep streaming even when the client sends `Accept: application/json` or `stream:false`. (thanks @anki1kr)
-- **fix(sse):** prevent non-JSON SSE lines and duplicate `[DONE]` from breaking clients. (thanks @qianze0628)
-- **fix(sse):** dedupe case-variant Anthropic headers in the executor `buildHeaders` path — Node/undici's `fetch` merges `anthropic-version` and `Anthropic-Version` into a single `"v, v"` value that the Anthropic API rejects, so both case variants are now collapsed to one canonical lowercase header (same for `anthropic-beta`). (thanks @Delcado19)
-- **oauth(kiro):** support Kiro IDC (organization) token import — when the `~/.aws/sso/cache` token carries a `clientIdHash`, auto-import now reads the linked client registration file to obtain `clientId`/`clientSecret`, probes the Kiro IDE `profile.json` for `profileArn` (ARN region normalized to `us-east-1` for the runtime gateway), and refreshes via the regional AWS OIDC endpoint instead of the social path; the import schema and modal forward these credentials so manual imports also work for IDC tokens. (thanks @enjoyer-hub)
-- **fix(translator):** preserve client `cache_control` breakpoints when routing Claude-format requests (e.g. Claude Code) to Alibaba DashScope's OpenAI-compatible providers (`alibaba` / `alibaba-cn`). The Claude→OpenAI translation previously stripped the markers from the system and message text blocks, so DashScope's explicit caching never engaged and every request was a cache miss. Cache hints now survive when preservation is requested for caching-capable OpenAI-format providers. (thanks @sacrtap)
-- **fix(tts):** resolve Gemini TTS models from catalog and add `gemini-3.1-flash-tts-preview` as the new default Vertex TTS model. (thanks @nguyenha935)
-- **fix(sse): don't cool down a healthy connection on a self-inflicted upstream timeout (504)** — when OmniRoute's own deadline elapses (surfaced as `TimeoutError`/`BodyTimeoutError` → 504), the connection is no longer disabled/failed-over, so a slow-but-healthy provider isn't penalised for our timeout. Genuine upstream 5xx/429 still trigger cooldown; antigravity keeps its own policy. (thanks @costaeder)
-- **fix(translator):** forward image `tool_result` blocks as `image_url` instead of stringifying base64. (thanks @alican532)
-- **fix(sse): robust Anthropic `/v1/messages` streaming — real ping keepalive + client-disconnect guard** — slow first tokens on reasoning models could trip strict clients' idle-read watchdog; the route now keeps the stream warm with a real `event: ping` (Anthropic clients ignore SSE comments) from the very first frame, and a client disconnect (AbortError / controller-closed) no longer counts as a provider failure (no failover/cooldown). (thanks @costaeder)
-- **fix: preserve model hidden flags (`isHidden`) across model sync** — `replaceCustomModels` pruned the compat-override list to the new custom-model ids, silently wiping the `isHidden` flag of eye-hidden SYNCED models on every periodic sync / import (all hidden models turned back on). The redundant cleanup is removed (per-model removal already handles its own compat cleanup), so eye-hidden models stay hidden across re-sync. ([#5086](https://github.com/diegosouzapw/OmniRoute/pull/5086) — thanks @herjarsa)
-- **fix(models): derive model-discovery config from the registry `modelsUrl`** — providers absent from the hardcoded `PROVIDER_MODELS_CONFIG` but carrying a registry `modelsUrl` (e.g. MiniMax) now get an auto-derived Bearer `/v1/models` discovery config, so "discover models" works instead of returning nothing. (thanks @herjarsa)
-- **fix(compression): resolve worker + rule/filter assets via runtime anchors (standalone bundle)** — the LLMLingua worker and the RTK rule/filter loaders relied on `fileURLToPath(import.meta.url)`, which the standalone bundle freezes to the build-machine path, so the worker never spawned and rule/filter packs failed to resolve. They now anchor on `process.cwd()`/`argv[1]` (with `pathToFileURL` for the worker URL). (thanks @fulorgnas)
-- **fix(api): sanitize error responses on seven management routes (Rule #12 hardening)** — `cli-tools/backups`, `cli-tools/guide-settings/[toolId]`, `logs/export`, `models/catalog`, `providers/test-batch`, `settings/import-json` and `usage/proxy-logs` no longer return raw `error.message`; they wrap caught errors in `sanitizeErrorMessage(...)`, and the routes are removed from the `check-error-helper` allowlist. (thanks @JxnLexn)
-- **fix(sse): keep `output_text`-only Responses bodies from being dropped/false-502'd** — some upstreams return a shorthand Responses body whose answer is only in `output_text` with an empty `output[]`. `sanitizeResponsesApiResponse` discarded the text, so the response then tripped the malformed-200 guard. The sanitizer now synthesizes an `output[]` message item from a non-empty `output_text` (complements the Claude-native fix in #5108; both stem from #4942).
-- **fix(executors): preserve a lone caller-supplied `Anthropic-Version` header casing** — the case-variant dedupe (#4846) unconditionally rewrote `Anthropic-Version`/`Anthropic-Beta` to lowercase even when only one variant was present, clobbering the caller's header. Dedupe now runs only when both case variants coexist (the actual undici-merge collision it was meant to fix).
-- **fix(responses):** default `text.format` to `{ type: "text" }` for openai-compatible **responses** providers — some Responses-compatible upstreams (e.g. LM Studio) reject a `text` object missing `text.format` with a 400 `missing_required_parameter`; the default executor now fills the Responses-API default before forwarding (guarded to `openai-compatible-*responses*`, never overwriting an existing format). (thanks @StevanusPangau)
-- **fix(translator): stop stripping client-provided `reasoning_content` for reasoning-replay providers** — the #4849 agentic-context strip (which drops `reasoning_content` from tool-call assistant turns to avoid O(n²) token growth) ran unconditionally, so replay providers (DeepSeek V4, Kimi K2, Qwen-Thinking, etc.) lost the client's reasoning and the reasoning-replay cache then overwrote it with a stale cached value (and such upstreams 400 without the original reasoning). The strip now skips reasoning-replay targets while non-reasoning providers keep the O(n²) protection. ([#5122](https://github.com/diegosouzapw/OmniRoute/pull/5122))
-- **fix(providers): add MiniMax M3 & Nemotron 3 Ultra to the Cline catalog** — the two models were missing from Cline's provider catalog and could not be selected; both are now registered. ([#5136](https://github.com/diegosouzapw/OmniRoute/pull/5136), closes [#3321](https://github.com/diegosouzapw/OmniRoute/issues/3321))
-- **fix(dashboard): key model-visibility toggle on the canonical `providerId`** — the per-model visibility toggle keyed off a display id, so toggling a model on one provider alias could mis-target another; it now keys on the canonical `providerId`. ([#5091](https://github.com/diegosouzapw/OmniRoute/pull/5091) — thanks @Theadd)
-- **fix(diagnostics): recognize the Claude API format in `detectMalformedNonStream`** — salvaged null-guard so a Claude-shaped non-streaming body is no longer misclassified. ([#5141](https://github.com/diegosouzapw/OmniRoute/pull/5141) — thanks @herjarsa / @diegosouzapw)
-- **fix(logging): track the final connection IDs in failover logs** — failover log lines now record the connection that actually served (or last failed) the request, instead of only the first attempt. ([#5016](https://github.com/diegosouzapw/OmniRoute/pull/5016) — thanks @JxnLexn)
-- **fix(sse): ignore disconnect races during in-band stream error handling** — a client disconnect that races with in-band upstream error handling no longer surfaces as a spurious provider failure. ([#5007](https://github.com/diegosouzapw/OmniRoute/pull/5007) — thanks @JxnLexn)
-- **fix(dashboard): surface the server error on `handleToggleCombo` failure** — a failed combo toggle now shows the backend error instead of silently no-op'ing. ([#5138](https://github.com/diegosouzapw/OmniRoute/pull/5138) — thanks @KooshaPari / @diegosouzapw)
-- **fix(quota): track provider quota reset windows + enrich the Codex playground** — observed quota reset windows are tracked and surfaced, and the Codex playground gains the enriched quota metadata. ([#5141](https://github.com/diegosouzapw/OmniRoute/pull/5141) — thanks @Witroch4 / @diegosouzapw)
-- **fix(sidebar): drop the orphan `settings` accent color** — removed a dangling accent-color entry that broke `typecheck:core`. ([#5142](https://github.com/diegosouzapw/OmniRoute/pull/5142))
-- **fix(sse): preserve non-stream reasoning fields for compatible clients** — non-streaming responses now keep the upstream reasoning fields (`reasoning` / `reasoning_content` and OpenRouter/Gemini `reasoning_details`) instead of stripping them in `responseSanitizer`, so clients that render reasoning on buffered responses no longer lose it. ([#5155](https://github.com/diegosouzapw/OmniRoute/pull/5155) — thanks @rdself)
-- **fix(i18n): add missing English UI labels** — fills in untranslated English strings that were surfacing as raw keys in the dashboard. ([#5153](https://github.com/diegosouzapw/OmniRoute/pull/5153) — thanks @rdself)
-
-### 🔒 Security
-
-- **fix(security): exact-host Anthropic `baseUrl` check** — the Anthropic base-URL guard used a substring match that a crafted host could partially satisfy; it now requires an exact host match (resolves CodeQL `js/incomplete-url-substring-sanitization` alert #674). ([#5130](https://github.com/diegosouzapw/OmniRoute/pull/5130))
-
-### 📝 Maintenance
-
-- **refactor(store): remove dead legacy store modules** — salvaged cleanup of unused legacy store code. ([#5138](https://github.com/diegosouzapw/OmniRoute/pull/5138) — thanks @JxnLexn / @diegosouzapw)
-- **test(combo): deterministic routing-decision matrix for all 17 strategies** — a deterministic E2E matrix pins the routing decision of every combo strategy. ([#5146](https://github.com/diegosouzapw/OmniRoute/pull/5146))
-- **chore:** baseline reconciliations (complexity / file-size / cognitive), golden-snapshot + apikey-count alignment for new providers, orphan-test relocation, release base-red repairs, CHANGELOG i18n mirror sync, and an `actions/cache` 5→6 bump. ([#5145](https://github.com/diegosouzapw/OmniRoute/pull/5145), [#5144](https://github.com/diegosouzapw/OmniRoute/pull/5144), [#5125](https://github.com/diegosouzapw/OmniRoute/pull/5125), [#5126](https://github.com/diegosouzapw/OmniRoute/pull/5126), [#5120](https://github.com/diegosouzapw/OmniRoute/pull/5120), [#5117](https://github.com/diegosouzapw/OmniRoute/pull/5117), [#5112](https://github.com/diegosouzapw/OmniRoute/pull/5112))
-- **test:** gated live smoke for combo strategies (in-process + VPS HTTP) and refreshed release expectations to match current code. ([#5151](https://github.com/diegosouzapw/OmniRoute/pull/5151), [#5150](https://github.com/diegosouzapw/OmniRoute/pull/5150) — thanks @KooshaPari / @diegosouzapw)
-
----
-
-## [3.8.37] — 2026-06-26
-
-### ✨ New Features
-
-- **feat(providers):** add DGrid AI gateway provider — OpenAI-compatible gateway at `api.dgrid.ai/v1` (alias `dgrid`, API-key auth, passthrough models). Free router tier (10 RPM / 100 RPD); a $5 lifetime top-up raises limits to 20 RPM / 1,000 RPD. ([#4931](https://github.com/diegosouzapw/OmniRoute/pull/4931) — thanks @dgridOP)
-
-- **feat(providers):** add Pioneer AI (Fastino Labs) provider — OpenAI-compatible chat completions at `api.pioneer.ai/v1`. Registered with alias `pn`, `X-API-Key` auth, and a catalog of 10 open-tier serverless models (Qwen3, Llama 3.1/3.2, Gemma 3, SmolLM3). Free $75 credits, no credit card required. Gated enterprise models (Claude/GPT/Gemini) require prior fine-tuning on the Pioneer platform and are intentionally excluded from the catalog. ([#4909](https://github.com/diegosouzapw/OmniRoute/pull/4909) — thanks @HikiNarou)
-
-- **feat(providers):** add xAI Grok inbound translators and a thinking patcher — Grok requests are now translated on the inbound path and reasoning is normalized so Grok modes behave consistently across clients. ([#4910](https://github.com/diegosouzapw/OmniRoute/pull/4910) — thanks @mugnimaestra)
-
-- **feat(oauth):** Codex bulk-import endpoint — `POST /api/oauth/codex/import` accepts multiple Codex OAuth credentials in one call for fast multi-account onboarding. ([#4914](https://github.com/diegosouzapw/OmniRoute/pull/4914) — thanks @beaaan)
-
-- **feat(embeddings):** add a `dimensions` override field to embedding combos so an embedding combo can pin the output vector size per target. ([#4913](https://github.com/diegosouzapw/OmniRoute/pull/4913) — thanks @wenzetan)
-
-- **feat(sse):** auto-promote successful combo model — a new opt-in `comboAutoPromoteEnabled` setting reorders a combo's persisted model list so that, when a combo model responds successfully, it is moved to position #1 for future requests. ([#4852](https://github.com/diegosouzapw/OmniRoute/pull/4852) — thanks @arssnndr)
-
-- **feat(sse):** add toggleable tool-source diagnostics — an opt-in switch surfaces where each tool definition originated when debugging tool-routing issues. ([#4856](https://github.com/diegosouzapw/OmniRoute/pull/4856) — thanks @DuyPrX)
-
-- **feat(headroom):** proxy lifecycle management + dashboard UI — start/stop/monitor a Headroom compression proxy from the dashboard, with Docker sidecar support. ([#4649](https://github.com/diegosouzapw/OmniRoute/pull/4649) — thanks @diegosouzapw / @carmelogunsroses)
-
-- **feat(sse):** `x-omniroute-strip-reasoning` request header to drop `reasoning_content` from upstream responses (opt-in, preserving reasoning-aware clients). ([#4678](https://github.com/diegosouzapw/OmniRoute/pull/4678) — thanks @anuragg-saxenaa / @diegosouzapw)
-
-- **feat(cli):** multi-model support for the Factory Droid CLI integration. ([#4682](https://github.com/diegosouzapw/OmniRoute/pull/4682) — thanks @anuragg-saxenaa / @diegosouzapw)
-
-- **feat(sse):** parse Gemini CLI 429 `retryDelay` from the structured `RetryInfo` payload so cooldowns honor the upstream-provided backoff. ([#4738](https://github.com/diegosouzapw/OmniRoute/pull/4738) — thanks @NoxzRCW)
-
-- **feat(sse):** add GPT-4 and GPT-4o mini to the GitHub Copilot provider catalog. ([#4798](https://github.com/diegosouzapw/OmniRoute/pull/4798), [#4797](https://github.com/diegosouzapw/OmniRoute/pull/4797) — thanks @decolua)
-
-- **feat(api):** add the `MiniMax-M3` pricing row (canonical + lowercase alias) so the new MiniMax default model gets accurate per-request cost accounting instead of falling back to a zero/default rate. ([#4814](https://github.com/diegosouzapw/OmniRoute/pull/4814) — thanks @octo-patch)
-
-### 🔧 Bug Fixes
-
-- **fix(sse):** dense, deterministic `response.output` ordering in `response.completed` — items are now sorted by their actual `output_index` (via a recorded-as-emitted accumulator + stable sort) instead of being rebuilt from unordered state dicts; `normalizeOutputIndex` replaces fragile `parseInt` calls for robust index coercion; superseded tool calls (replaced at the same index mid-stream) are excluded from the final output array. ([#4906](https://github.com/diegosouzapw/OmniRoute/pull/4906) — thanks @Marco9113)
-
-- **fix(sse):** normalize Codex custom/freeform tools (`apply_patch`, `type:"custom"` with no `parameters`) to a `{ input: string }` function schema instead of an empty schema — the empty schema made models invoke `apply_patch` with `{}`, breaking the Codex runtime which expects `{ input: string }`. Also maps `custom_tool_call` / `custom_tool_call_output` input items and streams `apply_patch` tool calls via `custom_tool_call_input.delta`/`.done` events. ([#4862](https://github.com/diegosouzapw/OmniRoute/pull/4862) — thanks @nstung463)
-
-- **fix(sse):** preserve the `required` array when translating Draft 2020-12 antigravity tool schemas (e.g. from OpenCode), stripping unsupported JSON Schema meta keywords while keeping mandatory arguments required so the model no longer calls tools without them. ([#4843](https://github.com/diegosouzapw/OmniRoute/pull/4843) — thanks @anuragg-saxenaa)
-
-- **fix(sse):** Kiro tool-schema sanitizer — strip unsupported JSON-Schema keywords (`anyOf`/`$ref`/`if`-`then`, etc.) and hash-truncate tool names >64 chars before dispatch, mapping the streamed tool-call name back for the client, so Kiro no longer rejects tool calls with `400 "Improperly formed request"`. ([#4847](https://github.com/diegosouzapw/OmniRoute/pull/4847) — thanks @smarthomeblack)
-
-- **fix(sse):** make the `anthropic-version` default-guard case-insensitive for `anthropic-compatible-*` providers, so a caller/operator-supplied `Anthropic-Version` (any casing) is no longer clobbered by a second lowercase `anthropic-version: 2023-06-01` header. ([#4823](https://github.com/diegosouzapw/OmniRoute/pull/4823) — thanks @zakirkun)
-
-- **fix(db):** validate HuggingFace API tokens via the `whoami-v2` endpoint as a pure auth probe so fine-grained Inference-Provider tokens (valid even when model/task endpoints reject them) are no longer falsely marked invalid; only 401/403 means an invalid key, other non-OK statuses surface as transient upstream errors. ([#4819](https://github.com/diegosouzapw/OmniRoute/pull/4819) — thanks @Delcado19)
-
-- **fix(sse):** reject the Anthropic-only `[1m]` context-1m suffix in `buildKiroPayload` before it reaches AWS Bedrock — Kiro is Bedrock-backed and cannot honor the beta, so a forwarded `kr/*[1m]` model id was malformed upstream; callers now get a clear error pointing them at a direct-Anthropic provider for 1M-context routing. ([#4816](https://github.com/diegosouzapw/OmniRoute/pull/4816) — thanks @Delcado19)
-
-- **fix(dashboard):** align the Engine Combos editor engines with the API schema — the named-combos pipeline dropdown offered four engines (`headroom`, `session-dedup`, `ccr`, `llmlingua`) that `PUT /api/context/combos/[id]` rejects, so selecting one made the save return 400 while the UI swallowed the error. The dropdown is now sourced from a single canonical engine map shared with `stackedPipelineStepSchema` (parity guarded by a unit test), and the editor surfaces save errors plus empty-name/empty-pipeline validation instead of failing quietly. ([#5062](https://github.com/diegosouzapw/OmniRoute/pull/5062) — closes #4955)
-
-- **fix(sse):** surface malformed HTTP-200 upstream responses instead of treating them as success, so combo fallback can trigger. ([#4942](https://github.com/diegosouzapw/OmniRoute/pull/4942) — thanks @haipham22)
-
-- **fix(antigravity):** retry transient upstream failures rather than failing the request outright. ([#4941](https://github.com/diegosouzapw/OmniRoute/pull/4941) — thanks @Jordannst)
-
-- **fix(sse):** exclude WS-bridge controller-closed errors from the provider circuit breaker so a client disconnect no longer trips the whole provider. ([#4870](https://github.com/diegosouzapw/OmniRoute/pull/4870) — closes #4602, thanks @huohua-dev)
-
-- **fix(sse):** resolve custom combos by id and case-insensitive name. ([#4869](https://github.com/diegosouzapw/OmniRoute/pull/4869) — closes #4446, thanks @herjarsa)
-
-- **fix(sse):** forward AI SDK image parts in the Responses translator. ([#4859](https://github.com/diegosouzapw/OmniRoute/pull/4859) — thanks @mugnimaestra)
-
-- **fix(sse):** emit valid concatenable Kiro `tool_calls.arguments` deltas. ([#4855](https://github.com/diegosouzapw/OmniRoute/pull/4855) — thanks @wahyuzero)
-
-- **fix(sse):** strip `temperature` for Claude models with extended thinking enabled (the upstream rejects it). ([#4853](https://github.com/diegosouzapw/OmniRoute/pull/4853) — thanks @noestelar)
-
-- **fix(sse):** unwrap the Qoder HTTP-200 SSE error envelope so combo fallback can trigger. ([#4850](https://github.com/diegosouzapw/OmniRoute/pull/4850) — thanks @vianlearns)
-
-- **fix(sse):** strip reasoning blobs from agentic context to prevent O(n²) token growth across multi-turn agent loops. ([#4849](https://github.com/diegosouzapw/OmniRoute/pull/4849) — thanks @GodrezJr2)
-
-- **fix(sse):** close the reasoning block before message content in the Responses stream so clients render reasoning and answer in the right order. ([#4848](https://github.com/diegosouzapw/OmniRoute/pull/4848) — thanks @kwanLeeFrmVi)
-
-- **fix(config):** sync the full SiliconFlow model list into the registry. ([#4844](https://github.com/diegosouzapw/OmniRoute/pull/4844) — thanks @letanphuc)
-
-- **fix(sse):** strip Composer `<｜final｜>` sentinel markers that leaked after Composer reasoning. ([#4842](https://github.com/diegosouzapw/OmniRoute/pull/4842) — thanks @noestelar)
-
-- **fix(build):** trace-include `sql.js`'s `sql-wasm.wasm` in the standalone bundle so SQLite-WASM works in the packaged build. ([#4839](https://github.com/diegosouzapw/OmniRoute/pull/4839) — thanks @Delcado19)
-
-- **fix(cli):** persist lazily-installed native runtime deps (`better-sqlite3`, `systray2`) to the shared runtime `package.json` with `--save-exact` instead of `--no-save`, so installing one no longer prunes the other as "extraneous" — fixing a "No SQLite driver available" failure after a `--tray` install. ([#4841](https://github.com/diegosouzapw/OmniRoute/pull/4841) — thanks @omartuhintvs)
-
-- **fix(sse):** resolve bare model names to a connection's `defaultModel` before upstream calls. ([#4825](https://github.com/diegosouzapw/OmniRoute/pull/4825) — thanks @anuragg-saxenaa)
-
-- **fix(api):** surface a Docker-localhost hint on provider-node validation connection errors. ([#4822](https://github.com/diegosouzapw/OmniRoute/pull/4822) — thanks @anuragg-saxenaa)
-
-- **fix(sse):** strip Gemini built-in tools when `functionDeclarations` are present in the Antigravity envelope (the two are mutually exclusive upstream). ([#4821](https://github.com/diegosouzapw/OmniRoute/pull/4821) — thanks @vanszs)
-
-- **fix(sse):** strip `X-Stainless-*` headers and normalize the SDK `User-Agent` for OpenAI-compatible endpoints. ([#4820](https://github.com/diegosouzapw/OmniRoute/pull/4820) — thanks @anuragg-saxenaa)
-
-- **fix(oauth):** allow a per-connection refresh lead-time override via `providerSpecificData.refreshLeadMs`. ([#4818](https://github.com/diegosouzapw/OmniRoute/pull/4818) — thanks @anuragg-saxenaa)
-
-- **fix(dashboard):** resolve passthrough model aliases by `providerId` in `ModelSelectModal`. ([#4815](https://github.com/diegosouzapw/OmniRoute/pull/4815) — thanks @anuragg-saxenaa)
-
-- **fix(sse):** strip `enumDescriptions` from Antigravity tool schemas. ([#4813](https://github.com/diegosouzapw/OmniRoute/pull/4813), [#4740](https://github.com/diegosouzapw/OmniRoute/pull/4740) — thanks @anuragg-saxenaa)
-
-- **fix(dashboard):** keep the desktop sidebar visible via an explicit CSS class. ([#4812](https://github.com/diegosouzapw/OmniRoute/pull/4812) — thanks @Delcado19)
-
-- **fix(sse):** filter nameless hosted tools when converting Responses API to Chat format. ([#4789](https://github.com/diegosouzapw/OmniRoute/pull/4789) — upstream, thanks Владимир Акимов)
-
-- **fix(sse):** stream-writer mock `abort()` now returns a Promise (test-stability fix). ([#4788](https://github.com/diegosouzapw/OmniRoute/pull/4788) — thanks @decolua)
-
-- **fix(sse):** use the WorkOS auth-token shape for Cline. ([#4787](https://github.com/diegosouzapw/OmniRoute/pull/4787) — thanks @apeltekci)
-
-- **fix(api):** fall back to the existing access token for any OAuth provider when a refresh fails. ([#4786](https://github.com/diegosouzapw/OmniRoute/pull/4786) — thanks @decolua)
-
-- **fix(sse):** read Antigravity usage from the `response.usageMetadata` envelope. ([#4785](https://github.com/diegosouzapw/OmniRoute/pull/4785) — thanks @decolua)
-
-- **fix(oauth):** verify Cursor installation on Linux before auto-import. ([#4770](https://github.com/diegosouzapw/OmniRoute/pull/4770) — upstream, thanks Ibrahim Ryan)
-
-- **fix(cli):** fall back to the default data dir when `DATA_DIR` is not writable. ([#4767](https://github.com/diegosouzapw/OmniRoute/pull/4767) — upstream, thanks Thiên Toán)
-
-- **fix(sse):** `json_schema` fallback for OpenAI-compatible providers that don't support structured outputs. ([#4766](https://github.com/diegosouzapw/OmniRoute/pull/4766) — thanks @mustafabozkaya)
-
-- **fix(cli):** verify launchd registration and skip self-SIGTERM in macOS autostart. ([#4765](https://github.com/diegosouzapw/OmniRoute/pull/4765) — thanks @ntdung6868)
-
-- **fix(sse):** finalize the `tool_calls` `finish_reason` on early stream end in the OpenAI Responses translator. ([#4764](https://github.com/diegosouzapw/OmniRoute/pull/4764) — thanks @decolua)
-
-- **fix(sse):** gate Kiro image attachments behind a Claude-capability check. ([#4763](https://github.com/diegosouzapw/OmniRoute/pull/4763) — thanks @decolua)
-
-- **fix(sse):** track Ollama streaming usage from raw NDJSON chunks. ([#4754](https://github.com/diegosouzapw/OmniRoute/pull/4754) — thanks @fresent)
-
-- **fix(sse):** include low-level cause details in `formatProviderError`. ([#4741](https://github.com/diegosouzapw/OmniRoute/pull/4741) — thanks @decolua)
-
-- **fix(executors):** `anthropic-compatible-*` gateways now get a `Bearer` token alongside `x-api-key`. ([#4729](https://github.com/diegosouzapw/OmniRoute/pull/4729) — thanks @hodtien)
-
-- **fix(translator):** strip the `x-anthropic-billing-header` in the claude-to-openai path. ([#4728](https://github.com/diegosouzapw/OmniRoute/pull/4728) — thanks @weimaozhen)
-
-- **fix(translator):** preserve `reasoning_effort` for non-Copilot Responses clients. ([#4688](https://github.com/diegosouzapw/OmniRoute/pull/4688) — thanks @ryanngit / @diegosouzapw)
-
-- **fix(codex):** treat an OAuth 401 as an unrecoverable refresh failure (stop retrying a dead token). ([#4686](https://github.com/diegosouzapw/OmniRoute/pull/4686) — thanks @sacwooky / @diegosouzapw)
-
-- **fix(translator):** coerce tool descriptions to strings in OpenAI normalization. ([#4675](https://github.com/diegosouzapw/OmniRoute/pull/4675) — thanks @East-rayyy / @diegosouzapw)
-
-- **fix(dashboard):** stop double-masking an already-masked API key in the list view (E2E 3/9 regression). ([#4671](https://github.com/diegosouzapw/OmniRoute/pull/4671) — thanks @diegosouzapw)
-
-- **fix(combo):** flatten Anthropic tool messages + tool history to prevent an upstream 503. ([#4648](https://github.com/diegosouzapw/OmniRoute/pull/4648) — thanks @warelik / @diegosouzapw)
-
-- **fix(providers):** require a Default Model in the compatible-provider API-key setup flow. ([#4641](https://github.com/diegosouzapw/OmniRoute/pull/4641) — thanks @arden1601)
-
-### 🔒 Security
-
-- **fix(auth):** only trust forwarding headers (`X-Forwarded-For` / `X-Real-IP`) from loopback TCP peers, so a non-loopback client can't spoof its origin to bypass local-only route guards. ([#4689](https://github.com/diegosouzapw/OmniRoute/pull/4689) — thanks @Jordannst / @diegosouzapw)
-
-- **fix(sse):** redact the API key from the AUTH debug log in the chat handler. ([#4858](https://github.com/diegosouzapw/OmniRoute/pull/4858) — thanks @sacwooky)
-
-- **fix(oauth):** classify `/api/oauth/cursor/auto-import` as a local-only route in the route guard, so the loopback-enforced process-spawning endpoint can't be reached through a tunneled/leaked JWT (Hard Rule #17). ([#5070](https://github.com/diegosouzapw/OmniRoute/pull/5070) — thanks @diegosouzapw)
-
-### 📝 Maintenance
-
-- **chore(ci):** harden the release flow — decouple the Quality Ratchet from coverage-shard flakes (`if: !cancelled()` + `--allow-missing`), add fast-path drift gates (`check:complexity`, `check:cognitive-complexity`, `check:pack-policy`, `check:build-scope`), and raise the default build heap to 8 GB. ([#5054](https://github.com/diegosouzapw/OmniRoute/pull/5054) — thanks @diegosouzapw)
-
-- **docs(routing):** sync the combo strategy docs for Fusion (17 strategies). ([#5067](https://github.com/diegosouzapw/OmniRoute/pull/5067) — thanks @diegosouzapw)
-
-- **test(sse):** golden-lock the `provider.ts` translate-path across all providers. ([#4734](https://github.com/diegosouzapw/OmniRoute/pull/4734) — thanks @diegosouzapw / @decolua)
-
-- **docs(env):** document `HEADROOM_URL` in `.env.example` + `ENVIRONMENT.md`. (thanks @diegosouzapw)
-
-- **chore(quality):** rebaseline the file-size ratchet across the rc17 PR-batch levas (leva2/leva3/leva4) to absorb cycle drift. (thanks @diegosouzapw)
-
----
-
-## [3.8.36] — 2026-06-25
-
-### ✨ New Features
-
-**Quota-Share system**
-
-- **feat(quota):** introduce a dedicated `quota-share` combo strategy (Fase 3 #9) — Deficit Round Robin scheduling with per-model in-flight gating (P2C), automatic DB migration that promotes existing `qtSd/*` combos, and per-policy gating so invalid allocations cannot bleed `allow` to unintended connections. ([#4939](https://github.com/diegosouzapw/OmniRoute/pull/4939), [#4901](https://github.com/diegosouzapw/OmniRoute/pull/4901))
-- **feat(quota):** multi-window usage buckets, per-(key,model) caps, and session stickiness — connections now track consumption across 5 h, 7 d, and per-model windows; `quota_allocation_model_caps` enforces per-key/model limits; session stickiness preserves prompt-cache integrity across turns. ([#4928](https://github.com/diegosouzapw/OmniRoute/pull/4928), [#4927](https://github.com/diegosouzapw/OmniRoute/pull/4927), [#4929](https://github.com/diegosouzapw/OmniRoute/pull/4929))
-- **feat(quota):** headroom strategy + proactive saturation — new `headroom` combo strategy selects connections by available quota margin; universal proactive saturation via upstream token-usage response headers; real Claude quota saturation sourced from `/api/oauth/usage`. ([#4908](https://github.com/diegosouzapw/OmniRoute/pull/4908), [#4907](https://github.com/diegosouzapw/OmniRoute/pull/4907), [#4885](https://github.com/diegosouzapw/OmniRoute/pull/4885))
-- **feat(quota):** concurrency control + cooldown-wait (Fase 2.1) — `max_concurrent` is enforced at dispatch time; quota-share combos queue concurrent requests with a short cooldown-wait and re-dispatch on slot availability (Variant A); a cron heal proactively restores connections after their window resets. ([#4965](https://github.com/diegosouzapw/OmniRoute/pull/4965), [#4970](https://github.com/diegosouzapw/OmniRoute/pull/4970), [#4967](https://github.com/diegosouzapw/OmniRoute/pull/4967), [#4900](https://github.com/diegosouzapw/OmniRoute/pull/4900))
-
-**Combo routing**
-
-- **feat(combo):** task-aware routing strategy — routes requests to the best-fit connection based on task-type metadata, enabling per-task provider specialization within a combo. ([#4945](https://github.com/diegosouzapw/OmniRoute/pull/4945))
-- **feat(combo):** Fusion strategy (16th strategy) — fan out to a configurable panel of models in parallel, then synthesize results through a judge model. ([#4652](https://github.com/diegosouzapw/OmniRoute/pull/4652))
-- **feat(combos):** add an editable per-combo `description` field. The routing-combo form now has a Description input, persisted in the combo `data` blob via `/api/combos` (POST/PUT) and round-tripped through GET — no new DB column. ([#5005](https://github.com/diegosouzapw/OmniRoute/issues/5005))
-- **feat(routing):** honor `X-Route-Model` request header to override `body.model`, enabling per-request model switching without modifying the request body. ([#4863](https://github.com/diegosouzapw/OmniRoute/pull/4863) — thanks @costaeder)
-
-**Providers & models**
-
-- **feat(providers):** update volcengine-ark model list, adding DeepSeek-V4-Flash and DeepSeek-V4-Pro. ([#4905](https://github.com/diegosouzapw/OmniRoute/pull/4905) — thanks @kenlin8827)
-- **feat(provider):** add CodeBuddy CN (`copilot.tencent.com`) — full OAuth + executor + model catalog stack. ([#4664](https://github.com/diegosouzapw/OmniRoute/pull/4664))
-- **feat(opencode-go):** advertise `glm-5.2` and `kimi-k2.7-code` to align with official Go endpoints. ([#4711](https://github.com/diegosouzapw/OmniRoute/pull/4711))
-- **feat(sse):** add Google Flow video-generation provider. ([#4769](https://github.com/diegosouzapw/OmniRoute/pull/4769))
-- **feat(api/v1):** include alias-backed models in the `/v1/models` listing. ([#4630](https://github.com/diegosouzapw/OmniRoute/pull/4630))
-
-**Proxy pool**
-
-- **feat(proxy-pool):** Cloudflare Workers proxy deployer + pool integration — deploy Cloudflare Workers relays directly from the dashboard and register them in the proxy pool. ([#4640](https://github.com/diegosouzapw/OmniRoute/pull/4640))
-- **feat(proxy-pool):** Deno Deploy relays + group action buttons — deploy Deno Deploy relay workers and manage proxy groups with new bulk-action controls. ([#4643](https://github.com/diegosouzapw/OmniRoute/pull/4643))
-
-**Compression & infrastructure**
-
-- **feat(compression):** Kiro/CodeWhisperer tool-result compression engine — dedicated compressor for Kiro/CodeWhisperer tool outputs integrated into the streaming pipeline. ([#4635](https://github.com/diegosouzapw/OmniRoute/pull/4635))
-- **feat(endpoint):** per-endpoint custom system prompt injection. A toggle + text field in the Endpoint settings card lets users inject a custom system prompt into every model request, applied via the existing system-prompt engine. Stored in settings DB. ([#5022](https://github.com/diegosouzapw/OmniRoute/pull/5022) — thanks @whale9820)
-- **feat(live-ws):** allow non-loopback clients via `LIVE_WS_ALLOWED_HOSTS` env var, enabling multi-host setups to access the live WebSocket API. ([#4877](https://github.com/diegosouzapw/OmniRoute/pull/4877) — thanks @KooshaPari)
-- **feat(db):** track API endpoint dimension on `usage_history` for per-endpoint cost and usage analytics. ([#4676](https://github.com/diegosouzapw/OmniRoute/pull/4676))
-
----
-
-### 🔧 Bug Fixes
-
-**Translator**
-
-- **fix(translator):** regroup parallel tool results to be adjacent to their originating assistant turn, fixing tool-message ordering for providers that require strict interleaving. ([#4882](https://github.com/diegosouzapw/OmniRoute/pull/4882))
-- **fix(translator):** preserve literal empty-string tool arguments in OpenAI-to-Claude streaming — they were previously dropped, causing tool calls to arrive with missing parameters. ([#4959](https://github.com/diegosouzapw/OmniRoute/pull/4959))
-- **fix(translator):** normalize tools to Anthropic-native shape for non-Anthropic providers, ensuring tool definitions pass validation regardless of the format at the call site. ([#4650](https://github.com/diegosouzapw/OmniRoute/pull/4650))
-- **fix(translator):** provider thinking compatibility — correct thinking-block serialization for DeepSeek and Gemini providers. ([#4946](https://github.com/diegosouzapw/OmniRoute/pull/4946))
-- **fix(translator):** emit `</think>` close marker for Anthropic thinking blocks, fixing truncated reasoning output in streamed responses. ([#4633](https://github.com/diegosouzapw/OmniRoute/pull/4633))
-- **fix(translator):** normalize `developer` role to `system` for OpenAI-format providers. ([#4625](https://github.com/diegosouzapw/OmniRoute/pull/4625))
-- **fix(translator):** strip top-level `client_metadata` on the OpenAI passthrough path (port from 9router#1157). ([#4624](https://github.com/diegosouzapw/OmniRoute/pull/4624))
-- **fix(translator):** replay `reasoning_content` on plain Xiaomi MiMo turns (port from 9router#1321). ([#4639](https://github.com/diegosouzapw/OmniRoute/pull/4639))
-
-**Copilot / GitHub executor**
-
-- **fix(copilot):** never route Gemini/Claude model variants to the `/responses` endpoint — these models require the chat-completions path only. ([#4627](https://github.com/diegosouzapw/OmniRoute/pull/4627))
-- **fix(github):** route Copilot Codex models to `/responses` (port from 9router#102). ([#4626](https://github.com/diegosouzapw/OmniRoute/pull/4626))
-- **fix(copilot,antigravity):** cap `maxOutputTokens` at 16384 to stop "Invalid Argument" 400 errors on high-token requests. ([#4636](https://github.com/diegosouzapw/OmniRoute/pull/4636))
-- **fix(codex):** drop non-standard `codex.*` streaming events that break `responses.stream` consumers. ([#4715](https://github.com/diegosouzapw/OmniRoute/pull/4715) — thanks @jeffer1312)
-
-**Claude / Anthropic**
-
-- **fix(claude):** omit `adaptive_thinking` and `output_config.effort` for Haiku model variants, which reject those parameters. ([#4661](https://github.com/diegosouzapw/OmniRoute/pull/4661))
-- **fix(claude):** skip `mcp__` tool-name cloaking and guard against missing `connectionId` to prevent crashes on Claude-native MCP tool calls. ([#4861](https://github.com/diegosouzapw/OmniRoute/pull/4861) — thanks @costaeder)
-- **fix(claude-oauth):** respect `429` backoff headers on the Claude OAuth usage endpoint to reduce polling spam during quota checks. ([#4655](https://github.com/diegosouzapw/OmniRoute/pull/4655))
-
-**Routing & SSE**
-
-- **fix(sse):** fail over on `400` responses that carry rate-limit text in the body, not just on canonical `429` status codes. ([#4986](https://github.com/diegosouzapw/OmniRoute/pull/4986))
-- **fix(sse):** honor per-account proxy and fingerprint-rotation settings in the opencode executor. ([#4989](https://github.com/diegosouzapw/OmniRoute/pull/4989))
-- **fix(sse):** soft-penalize exhausted providers in auto-combo scoring instead of hard-excluding them, improving fallback resilience. ([#4990](https://github.com/diegosouzapw/OmniRoute/pull/4990))
-- **fix(sse):** drop the CCP pin when the pinned provider is durably unhealthy, with anti-flap logic to prevent oscillation. ([#4864](https://github.com/diegosouzapw/OmniRoute/pull/4864) — thanks @costaeder)
-- **fix(combo):** fetch models dynamically from custom provider endpoints instead of relying on a static list. ([#4860](https://github.com/diegosouzapw/OmniRoute/pull/4860))
-- **fix(combo):** propagate the selected connection ID to fallback error responses so model lockout applies to the correct connection rather than the wrong fallback target. ([#4809](https://github.com/diegosouzapw/OmniRoute/pull/4809) — thanks @Chewji9875)
-- **fix(sse):** skip third-party tool-name cloaking for Anthropic-native server tools to prevent naming conflicts. ([#4808](https://github.com/diegosouzapw/OmniRoute/pull/4808) — thanks @NomenAK)
-
-**Quota**
-
-- **fix(quota):** quota-exclusive `qtSd/*` connections now appear in `/v1/models` listings; EPSILON-threshold check no longer falsely blocks under-budget allocations. ([#4830](https://github.com/diegosouzapw/OmniRoute/pull/4830))
-- **fix(quota):** migration 107 correctly activates the `quota-share` strategy on existing `qtSd/*` combos. ([#4962](https://github.com/diegosouzapw/OmniRoute/pull/4962))
-
-**API / responses**
-
-- **fix(api):** parse the `/v1/responses` request body once instead of 3–4 times on the hot path, reducing per-request overhead. ([#4958](https://github.com/diegosouzapw/OmniRoute/pull/4958))
-- **fix(api):** evict stale in-memory rate-limit windows to stop a slow heap leak on long-running instances. ([#4957](https://github.com/diegosouzapw/OmniRoute/pull/4957))
-- **fix(api):** require authentication on the compression `run-telemetry` endpoint; document `OMNIROUTE_EVAL_CREDENTIALS` env var. ([#4796](https://github.com/diegosouzapw/OmniRoute/pull/4796))
-- **fix(api):** stop `GET /api/system/env/repair` returning HTTP `500` on packaged installs (it broke the onboarding wizard). `createRequire(import.meta.url)` ran at module top-level; once webpack bundles the route into the standalone build, `import.meta.url` is frozen to the build-machine path and `createRequire` throws during evaluation, so the whole route failed to load. `createRequire` is now resolved lazily inside the guarded `better-sqlite3` block, root-dir resolution falls back to `process.cwd()`, and the route passes an explicit `rootDir`. ([#5028](https://github.com/diegosouzapw/OmniRoute/pull/5028))
-
-**Dashboard**
-
-- **fix(dashboard):** show custom provider given-name instead of internal id across dashboard pages — cache, combo health, compression analytics, cost overview, health/autopilot, provider stats, route explainability, provider utilization, runtime. Adds shared `resolveProviderName` resolver and `useProviderNodeMap` hook. (#4603)
-- **fix(dashboard):** on OAuth providers (e.g. GLM Coding), "Test all models" with auto-hide-failed now switches the model list to the "visible" filter after the run, so just-hidden failed models actually disappear on-screen — parity with the passthrough-provider path (#3610). Previously they were hidden in the DB but stayed visible under the "All" filter, so it looked like nothing was hidden. (#4887)
-- **fix(dashboard):** restore the home-page provider topology card that was hidden by a default state change in #4596. ([#4963](https://github.com/diegosouzapw/OmniRoute/pull/4963))
-- **fix(dashboard):** proxy-pool success gating, sync-timestamp persistence, and opt-in Redis backend. ([#4988](https://github.com/diegosouzapw/OmniRoute/pull/4988))
-- **fix(dashboard):** show custom vision models in the LLM selector dropdown. ([#4653](https://github.com/diegosouzapw/OmniRoute/pull/4653))
-
-**Providers**
-
-- **fix(pollinations):** stop forcing `jsonMode` on every request. Pollinations treats `jsonMode=true` as "the model MUST return JSON" and rejects (HTTP 400 "messages must contain the word 'json'") any normal chat request whose messages don't mention "json", so all non-JSON chat was broken. `jsonMode` is now only enabled when the caller actually requests JSON output (`response_format.type` of `json_object` or `json_schema`). (#3981)
-- **fix(antigravity):** default `safetySettings` to all-OFF for parity with the native Gemini paths. The Antigravity (Google Cloud Code) request builder set `safetySettings: undefined`, which `JSON.stringify` drops — so no safety settings reached Google and its server-side defaults false-flagged benign technical prompts as `prohibited_content` (HTTP 200 + blocked body, which combo failover treats as terminal). Now honors a caller-supplied value and otherwise defaults to `DEFAULT_SAFETY_SETTINGS`, matching the claude-to-gemini / openai-to-gemini paths. (#5003)
-- **fix(antigravity):** exclude the standard Gemini rate-limit message from quota-exhaustion keyword matching to prevent false-positive saturation flags. ([#4810](https://github.com/diegosouzapw/OmniRoute/pull/4810) — thanks @Chewji9875)
-- **fix(chatgpt-web):** map the advertised `gpt-5.5`, `gpt-5.5-pro`, `gpt-5.4-pro` and `gpt-5.2-pro` catalog ids to their dash-form ChatGPT backend slugs. They were missing from `MODEL_MAP`, so the executor sent the dot-form id verbatim, which the ChatGPT backend silently ignored and served the default Plus model instead of the requested one. Adds a drift guard asserting no advertised dot-form id reaches the backend verbatim. (#4665)
-- **fix(gemini):** preserve the `pattern` field in the Antigravity tool schema sanitizer to avoid stripping valid regex constraints from tool definitions. ([#4651](https://github.com/diegosouzapw/OmniRoute/pull/4651))
-- **fix(opencode):** preserve DeepSeek reasoning content in streamed responses. ([#4631](https://github.com/diegosouzapw/OmniRoute/pull/4631))
-- **fix(perplexity):** validate API keys via the `/v1/models` endpoint instead of issuing a full chat request. ([#4654](https://github.com/diegosouzapw/OmniRoute/pull/4654))
-- **fix(qoder):** exchange PAT for `jt-*` job token before initiating Cosy chat, fixing auth failures after the Qoder credential format change. ([#4884](https://github.com/diegosouzapw/OmniRoute/pull/4884))
-- **fix(executors):** strip parameters unsupported by the target provider/model to prevent `400 Invalid parameter` errors on strict endpoints. ([#4658](https://github.com/diegosouzapw/OmniRoute/pull/4658))
-- **fix(executors):** preserve literal `reasoning_effort: "max"` for Ollama Cloud instead of normalizing to `xhigh`. Ollama Cloud accepts `high|medium|low|max|none` and rejects `xhigh` (`invalid reasoning value: 'xhigh'`); OpenRouter DeepSeek `max→xhigh` normalization is unaffected. ([#4993](https://github.com/diegosouzapw/OmniRoute/pull/4993) — thanks @Thinkscape)
-- **fix(headroom):** translate openai-responses input through OpenAI for external compression. `adaptBodyForCompression` now serialises `function_call_output` items whose `output` field is a JSON object (not a string) so compression engines can process the content — previously those items were excluded from compression because `hasTextContent()` returned false for object values. ([#5023](https://github.com/diegosouzapw/OmniRoute/pull/5023) — thanks @anki1kr)
-- **fix(proxy):** fan out direct dispatcher streams to all registered proxy endpoints. ([#4803](https://github.com/diegosouzapw/OmniRoute/pull/4803) — thanks @makcimbx)
-
-**Compression**
-
-- **fix(compression):** eliminate ReDoS in the `math_inline` preservation regex — the previous pattern could catastrophically backtrack on untrusted input. ([#4838](https://github.com/diegosouzapw/OmniRoute/pull/4838))
-- **fix(compression):** stop RTK over-truncating file-read tool results — RTK now respects the full content length for file-read outputs. ([#4987](https://github.com/diegosouzapw/OmniRoute/pull/4987))
-
-**Build / CLI / infrastructure**
-
-- **fix(build):** drop `@omniroute/open-sse` from `optimizePackageImports` to fix the Next.js build OOM crash. ([#4968](https://github.com/diegosouzapw/OmniRoute/pull/4968))
-- **fix(cli):** SIGKILL the systray child PID before closing the IPC channel to prevent macOS NSStatusItem orphan processes. ([#4732](https://github.com/diegosouzapw/OmniRoute/pull/4732))
-- **fix(cli):** bump `better-sqlite3` runtime pin to 12.10.1 for Node 26 compatibility. ([#4685](https://github.com/diegosouzapw/OmniRoute/pull/4685))
-- **fix(cli):** harden the systray2 tray runtime (port from 9router#1080). ([#4628](https://github.com/diegosouzapw/OmniRoute/pull/4628))
-- **fix(cli-tools):** tolerate JSONC (comments and trailing commas) in tool settings files. ([#4659](https://github.com/diegosouzapw/OmniRoute/pull/4659))
-- **fix(install):** make the `transformers` dependency optional so CUDA-host installs that lack Python bindings succeed. ([#4807](https://github.com/diegosouzapw/OmniRoute/pull/4807) — thanks @megamen32)
-- **fix(db):** correct storage tuning settings to prevent WAL runaway on high-write workloads. ([#4834](https://github.com/diegosouzapw/OmniRoute/pull/4834) — thanks @rdself)
-- **fix(image):** prevent compatible nodes from shadowing provider aliases in the image routing table. ([#4656](https://github.com/diegosouzapw/OmniRoute/pull/4656))
-
-**Plugin**
-
-- **fix(plugin):** opencode `auth.json` dual-key fallback for the auto-prefix migration. The config hook now looks up both the prefixed (`opencode-omniroute`) and bare (`omniroute`) keys, so users who authenticated before the `opencode-` prefix landed no longer need to re-auth. ([#5027](https://github.com/diegosouzapw/OmniRoute/pull/5027) — thanks @herjarsa)
-
----
-
-### 🔒 Security
-
-- **fix(security):** block SSRF allowlist bypass via `x-relay-path` header manipulation on Deno/Vercel relays. ([#4899](https://github.com/diegosouzapw/OmniRoute/pull/4899))
-- **fix(security):** pin image-fetch DNS resolution to prevent SSRF DNS-rebinding attacks (GHSA-cmhj-wh2f-9cgx). ([#4634](https://github.com/diegosouzapw/OmniRoute/pull/4634))
-- **fix(security):** do not trust the loopback socket as local-only when the server is behind a reverse proxy, closing a potential auth bypass path. ([#4632](https://github.com/diegosouzapw/OmniRoute/pull/4632))
-- **fix(security):** validate the Kiro region parameter to prevent SSRF via crafted region strings (GHSA-6mwv-4mrm-5p3m). ([#4629](https://github.com/diegosouzapw/OmniRoute/pull/4629))
-- **fix(copilot):** replace `execSync` shell interpolation with `execFile` in the `runOmniRouteCli` tool to prevent command injection. The user-supplied command is now split into an argv array and passed to `execFile` (no shell), so shell metacharacters are treated as literal text; error output is routed through `sanitizeErrorMessage()`. ([#5024](https://github.com/diegosouzapw/OmniRoute/pull/5024) — thanks @hamsa0x7)
-
----
-
-### 📝 Maintenance
-
-**God-file decomposition (continued, #3501)**
-
-- **refactor(chatCore):** extracted 12 focused helpers from `chatCore.ts` covering the streaming pipeline (`assembleStreamingPipeline`), cache-store logic (`storeStreamingSemanticCacheResponse`, `storeSemanticCacheResponse`), response headers (`assembleStreamingResponseHeaders`, `buildNonStreamingResponseHeaders`), JSON→SSE bridge (`maybeConvertJsonBodyToSse`), guardrail context (`buildPostCallGuardrailContext`), usage buffer (`applyClientUsageBuffer`), plugin hook (`runPluginOnRequestHook`), analytics (`writeCompressionAnalytics`, `emitOutputStyleTelemetry`), and compression predicates/settings (`resolveCompressionSettings`, et al.). ([#4811](https://github.com/diegosouzapw/OmniRoute/pull/4811)–[#4837](https://github.com/diegosouzapw/OmniRoute/pull/4837))
-- **refactor(sse/db/api):** continued decomposition of `services/usage.ts` (extracted quota-core, scalar/format helpers, Antigravity/GLM/MiniMax usage families), `db/core.ts` (schema-column reconciliation, snake↔camel column-mapping), `db/apiKeys.ts` (row-parsers, model-permission matching), and `validation.ts` (URL/headers/transport leaf layer, web-cookie/Meta-AI validators, enterprise-cloud + probe, audio/speech/apikey, search/embedding/rerank, and OpenAI/Anthropic format validators). ([#4921](https://github.com/diegosouzapw/OmniRoute/pull/4921)–[#4956](https://github.com/diegosouzapw/OmniRoute/pull/4956))
-- **refactor(pricing/providers):** decomposed `pricing.ts` into shared tiers + partitioned `DEFAULT_PRICING` modules, and split the `providers.ts` catalog into semantic data modules organized by provider family. ([#4917](https://github.com/diegosouzapw/OmniRoute/pull/4917), [#4918](https://github.com/diegosouzapw/OmniRoute/pull/4918))
-- **refactor(open-sse):** extract `safeParseJSON` utility and dedup `tryParseJSON` call sites; extract and dedup the fallback `tool_call` ID generation helper. ([#4735](https://github.com/diegosouzapw/OmniRoute/pull/4735), [#4736](https://github.com/diegosouzapw/OmniRoute/pull/4736))
-
-**Quality & CI**
-
-- **chore(quality):** release base-red reconciliation + ratchet rebaselines — file-size, env-doc, and catalog baseline updates across multiple gates. ([#4630](https://github.com/diegosouzapw/OmniRoute/pull/4630), [#4879](https://github.com/diegosouzapw/OmniRoute/pull/4879), [#4886](https://github.com/diegosouzapw/OmniRoute/pull/4886), [#4915](https://github.com/diegosouzapw/OmniRoute/pull/4915), [#4961](https://github.com/diegosouzapw/OmniRoute/pull/4961), [#4973](https://github.com/diegosouzapw/OmniRoute/pull/4973))
-- **ci(quality):** shift heavy validation gates to the PR→release merge fast-path to accelerate the release cycle. ([#4857](https://github.com/diegosouzapw/OmniRoute/pull/4857))
-- **fix(ci):** include `coverage/lcov.info` in the coverage-report artifact so SonarQube can consume it. ([#4670](https://github.com/diegosouzapw/OmniRoute/pull/4670))
-- **fix(test):** validate Anthropic-compatible connections via `POST /v1/messages` for accurate connectivity testing. ([#4657](https://github.com/diegosouzapw/OmniRoute/pull/4657))
-
-**Docs**
-
-- **docs(resilience):** document Quota-Share Concurrency Control — `max_concurrent` enforcement, serialization behavior, and cooldown-wait semantics. ([#4980](https://github.com/diegosouzapw/OmniRoute/pull/4980))
-- **docs(perf):** add per-endpoint p50/p95/p99 latency and cost budgets reference. ([#4867](https://github.com/diegosouzapw/OmniRoute/pull/4867) — thanks @KooshaPari)
-- **docs(ops):** add canonical incident response runbook. ([#4868](https://github.com/diegosouzapw/OmniRoute/pull/4868) — thanks @KooshaPari)
-- **docs(ops):** document the release-green family — `green-prs`, `check:release-green`, `babysit`, and nightly gate workflows. ([#4679](https://github.com/diegosouzapw/OmniRoute/pull/4679))
-- **docs(agentbridge):** document Electron `NODE_EXTRA_CA_CERTS`, real model IDs, and identity caveat for agent bridge integrations. ([#4718](https://github.com/diegosouzapw/OmniRoute/pull/4718))
-- **docs:** clarify Kiro provides ~50 credits/month per account, not unlimited. ([#4690](https://github.com/diegosouzapw/OmniRoute/pull/4690))
-
-**Misc**
-
-- **chore(claude,codex):** bump pinned CLI identities — Claude `2.1.158 → 2.1.187`, Codex `0.132.0 → 0.142.0`. ([#4883](https://github.com/diegosouzapw/OmniRoute/pull/4883))
-- **chore(dashboard):** rename Qoder display label from "Qoder AI" to "Qoder". ([#4733](https://github.com/diegosouzapw/OmniRoute/pull/4733))
-
----
-
-## [3.8.35] — 2026-06-23
-
-### ✨ New Features
-
-- **Adaptive context compression (Phase 4)**: a four-layer compression upgrade landed across stacked PRs — an **Output Styles** registry (`terse-prose` / `less-code` / `terse-cjk`) ([#4694](https://github.com/diegosouzapw/OmniRoute/pull/4694) — thanks @diegosouzapw), an opt-in **SLM `ultra` tier** (two-tier LLMLingua with heuristic fallback) ([#4707](https://github.com/diegosouzapw/OmniRoute/pull/4707) — thanks @diegosouzapw), a **context-budget adaptive dial** (reserve-output ladder + floor) ([#4716](https://github.com/diegosouzapw/OmniRoute/pull/4716) — thanks @diegosouzapw), and an **offline evaluation harness** (PII-gated corpus, self-test judge, gold-grader, real-pipeline runner behind a `ModelClient` seam) ([#4720](https://github.com/diegosouzapw/OmniRoute/pull/4720) — thanks @diegosouzapw). All four layers share a single `CompressionRunTelemetry` contract.
-- **Redoc-rendered API docs**: a consolidated OpenAPI spec now lives at `docs/openapi.yaml` and is served as interactive Redoc documentation at `/api/docs`. ([#4781](https://github.com/diegosouzapw/OmniRoute/pull/4781) — thanks @KooshaPari / @diegosouzapw)
-
-### 🔧 Bug Fixes
-
-- **db-backups**: make the database-import size cap configurable via `OMNIROUTE_DB_IMPORT_MAX_MB` (default 100 MB, 4 GB ceiling) so backups larger than 100 MB can be restored; error message now points to the env var and to VACUUM ([#4757](https://github.com/diegosouzapw/OmniRoute/pull/4757) — closes #4719, thanks @diegosouzapw).
-- **Onboarding**: add the missing `onboarding.tiers` step-title translation so the setup wizard no longer crashes with `MISSING_MESSAGE: onboarding.tiers` ([#4755](https://github.com/diegosouzapw/OmniRoute/pull/4755) — closes #4698, thanks @diegosouzapw).
-- **deepseek-web**: fold `role:"tool"` results into the single-prompt transcript (`messagesToPrompt`) so tool outputs reach the model instead of being silently dropped when a follow-up turn omits the `tools[]` array ([#4756](https://github.com/diegosouzapw/OmniRoute/pull/4756) — closes #4712, thanks @diegosouzapw).
-- **Dashboard**: remove the dead, unconditional `useLiveRequests()` call from `HomePageClient.tsx` — it crashed the `/home` page in production builds with `ReferenceError: useLiveRequests is not defined` (#4759, #4745) and opened the live-dashboard WebSocket even when Provider Topology was hidden (#4596). The live feed remains owned by the settings-gated `HomeProviderTopologySection` ([#4761](https://github.com/diegosouzapw/OmniRoute/pull/4761) — thanks @diegosouzapw).
-- **Providers dashboard**: dedupe provider nodes by id when adding a compatible provider (`upsertProviderNodeById`) so the same provider can no longer appear twice and no-op adds don't invalidate the compatible-provider memo ([#4768](https://github.com/diegosouzapw/OmniRoute/pull/4768) — closes #4746, thanks @diegosouzapw).
-- **Storage VACUUM**: the scheduled VACUUM job now follows the Storage page settings (`scheduledVacuum` / `vacuumHour`) as the single source of truth; the legacy env-flag control path was removed ([#4726](https://github.com/diegosouzapw/OmniRoute/pull/4726) — thanks @rdself).
-- **Tiers**: no-auth providers are now counted as free, and the free-tier filter returns an empty set instead of falling through to every provider ([#4753](https://github.com/diegosouzapw/OmniRoute/pull/4753) — thanks @megamen32 / @diegosouzapw).
-- **Combos**: auto-promote `zeroLatencyOptimizationsEnabled` so legacy configs (pre-3.8.33 `fallbackCompressionMode="lite"`) round-trip cleanly on the first GUI edit ([#4774](https://github.com/diegosouzapw/OmniRoute/pull/4774) — thanks @KooshaPari / @diegosouzapw).
-
-### 📝 Maintenance
-
-- **chatCore (#3501)**: continued the incremental decomposition of `executeProviderRequest` and the streaming/non-streaming hooks into pure leaf modules — top-level helpers + 6 pure leaves ([#4571](https://github.com/diegosouzapw/OmniRoute/pull/4571)), `resolveExecutorWithProxy` + `getExecutionCredentials` ([#4646](https://github.com/diegosouzapw/OmniRoute/pull/4646)), Claude message transforms ([#4708](https://github.com/diegosouzapw/OmniRoute/pull/4708)), `persistAttemptLogs` ([#4717](https://github.com/diegosouzapw/OmniRoute/pull/4717)), `stageTrace` + `compressionUsageReceipt` ([#4721](https://github.com/diegosouzapw/OmniRoute/pull/4721)), `prepareUpstreamBody` ([#4730](https://github.com/diegosouzapw/OmniRoute/pull/4730)), parse + non-streaming usage-stats ([#4762](https://github.com/diegosouzapw/OmniRoute/pull/4762)), `recordContextEditingTelemetryHook` ([#4779](https://github.com/diegosouzapw/OmniRoute/pull/4779)), `scheduleQuotaShareConsumption` ([#4780](https://github.com/diegosouzapw/OmniRoute/pull/4780)), `emitRequestGamificationEvent` ([#4776](https://github.com/diegosouzapw/OmniRoute/pull/4776)), `runPluginOnResponseHook` ([#4782](https://github.com/diegosouzapw/OmniRoute/pull/4782)), `scheduleStreamingQuotaShareConsumption` ([#4784](https://github.com/diegosouzapw/OmniRoute/pull/4784)), `recordCompressionCacheStats` ([#4792](https://github.com/diegosouzapw/OmniRoute/pull/4792)), `writeCavemanOutputAnalytics` ([#4794](https://github.com/diegosouzapw/OmniRoute/pull/4794)), `recordStreamingUsageStats` ([#4791](https://github.com/diegosouzapw/OmniRoute/pull/4791)), and `recordStreamingCost` ([#4790](https://github.com/diegosouzapw/OmniRoute/pull/4790)). (thanks @diegosouzapw)
-- **Quality**: expand `check:release-green` to reproduce the full release-PR gate set locally ([#4758](https://github.com/diegosouzapw/OmniRoute/pull/4758) — thanks @diegosouzapw).
-- **db**: re-export `compressionRunTelemetry` from `localDb` to satisfy the db-rules gate ([#4775](https://github.com/diegosouzapw/OmniRoute/pull/4775) — thanks @diegosouzapw).
-- **Security docs**: add a canonical STRIDE-based threat model ([#4783](https://github.com/diegosouzapw/OmniRoute/pull/4783) — thanks @KooshaPari).
-- **Tests**: add a smoke test for the home-client dashboard ([#4793](https://github.com/diegosouzapw/OmniRoute/pull/4793) — thanks @JxnLexn).
-- **Docs**: credit **ponytail** and **OmniCompress** in the README inspiring-projects list and restore the `check:env-doc-sync` release-green by exempting the harness-only `OMNIROUTE_EVAL_CREDENTIALS` var ([#4799](https://github.com/diegosouzapw/OmniRoute/pull/4799) — thanks @diegosouzapw); declare the Phase 4 compression layers in the README + GUIDE ([#4801](https://github.com/diegosouzapw/OmniRoute/pull/4801) — thanks @diegosouzapw).
-- **Quality**: trim `combo-config.test.ts` comments back under the file-size cap (follow-up to #4774) ([#4800](https://github.com/diegosouzapw/OmniRoute/pull/4800) — thanks @diegosouzapw).
-
----
-
-## [3.8.34] — 2026-06-23
-
-### ✨ New Features
-
-- **feat(executors): Microsoft 365 Copilot pure framing + connection helpers** — adds the request/response framing and connection helpers to support `m365.cloud.microsoft/chat` for individual M365 plans. ([#4696](https://github.com/diegosouzapw/OmniRoute/pull/4696) — thanks @skyzea1 / @diegosouzapw)
-- **feat(compression): per-request `x-omniroute-compression` header (Phase 3)** — a request header now overrides the compression plan with the highest precedence (`request-header > routing > profile > auto-trigger > Default > off`), accepting `off` / `default` / `engine:<id>` / `<combo>`. The response echoes `X-OmniRoute-Compression: <mode>; source=<source>`. ([#4645](https://github.com/diegosouzapw/OmniRoute/pull/4645) — thanks @diegosouzapw)
-- **feat(audio): MiniMax T2A v2 TTS dispatch in `audioSpeech`** — adds MiniMax text-to-speech dispatch (port of upstream #1043). ([#4553](https://github.com/diegosouzapw/OmniRoute/pull/4553) — thanks @diegosouzapw)
-- **feat(opencode): OpenCode Go DeepSeek reasoning variants** — registers the Go DeepSeek reasoning model variants. ([#4647](https://github.com/diegosouzapw/OmniRoute/pull/4647) — thanks @DevEstacion)
-- **feat(quota): quota scraping for OpenCode Go and Ollama Cloud** — surfaces quota windows for the OpenCode Go and Ollama Cloud providers. ([#4642](https://github.com/diegosouzapw/OmniRoute/pull/4642) — thanks @JxnLexn)
-- **feat(settings): expose stream recovery feature flags** — surfaces the stream-recovery toggles in settings. ([#4586](https://github.com/diegosouzapw/OmniRoute/pull/4586) — thanks @rdself)
-- **feat(providers): optional model ID for custom API-key validation** — custom API-key connection tests can now specify the model ID used to validate the key. ([#4555](https://github.com/diegosouzapw/OmniRoute/pull/4555) — thanks @diegosouzapw)
-
-### 🐛 Fixed
-
-- **fix(db): scheduled cleanup actually runs + queries target the real tables (DB-bloat / OOM)** — `runAutoCleanup` was never scheduled, so retention cleanup never executed and tables (`compression_analytics`, `usage_history`, …) grew unbounded into multi-GB SQLite files driving high RSS. Worse, several cleanup queries referenced wrong table/column names (`call_logs.created_at`→`timestamp`, `compression_analytics.created_at`→`timestamp`, `mcp_audit_log`→`mcp_tool_audit`, `a2a_events`→`a2a_task_events`, `memory_entries`→`memories`), so even a manual run silently no-op'd or errored. Fixed the five queries to match the real schema, added `cleanupProxyLogs`, and wired a `startCleanupScheduler` (startup + every 6h, VACUUM after deletes) into `server-init` alongside the existing budget-reset and reasoning-cache jobs. ([#4691](https://github.com/diegosouzapw/OmniRoute/pull/4691), extracted from [#4428](https://github.com/diegosouzapw/OmniRoute/pull/4428) — thanks @oyi77 / @diegosouzapw)
-- **fix(routing): include all noAuth models in auto-combos + add reka-flash + best-free template** — noAuth provider models are no longer skipped when building auto-combos, `reka-flash` is registered, and a `best-free` combo template is added. ([#4621](https://github.com/diegosouzapw/OmniRoute/pull/4621) — thanks @oyi77)
-- **fix: noAuth provider validation + Kimi executor routing** — corrects noAuth provider membership checks and removes a mis-routed Kimi alias. (closes #4620) ([#4699](https://github.com/diegosouzapw/OmniRoute/pull/4699) — thanks @oyi77)
-- **fix(executors): Firecrawl `web_fetch` 500 with `include_metadata=true`** — fixes a crash when Firecrawl web_fetch is invoked with metadata extraction enabled. ([#4692](https://github.com/diegosouzapw/OmniRoute/pull/4692) — thanks @ponkcore)
-- **fix(proxy): apply `pipelining:0` + connections cap to the direct dispatcher** — same-provider concurrent requests no longer serialize behind a long/streaming request on the direct path. ([#4684](https://github.com/diegosouzapw/OmniRoute/pull/4684) — thanks @jeffer1312 / @diegosouzapw)
-- **fix(telemetry): back off live-WS event forwarding when the sidecar is unreachable** — stops repeatedly attempting to connect to `LIVE_WS_PORT` when live monitoring is not configured. ([#4687](https://github.com/diegosouzapw/OmniRoute/pull/4687) — thanks @FikFikk / @diegosouzapw)
-- **fix(api): serve `GET /v1/models/{model}` as JSON, not the HTML dashboard** — the per-model endpoint (IDs with slashes via a catch-all route) now returns JSON, unbreaking Claude Code. ([#4677](https://github.com/diegosouzapw/OmniRoute/pull/4677) — thanks @papajo / @diegosouzapw)
-- **fix(executors): robust deepseek-web tool-call parsing and agentic context retention** — hardens DeepSeek-web tool-call parsing and preserves agentic context across turns. ([#4644](https://github.com/diegosouzapw/OmniRoute/pull/4644) — thanks @BugsBag)
-- **fix(cli): authenticate `omniroute logs` and honor the active context** — the `logs` command now authenticates and respects the active context. ([#4638](https://github.com/diegosouzapw/OmniRoute/pull/4638) — thanks @Rahulsharma0810)
-- **fix(stream): estimate input tokens when upstream reports `prompt_tokens=0`** — input token usage is estimated when the upstream omits it. ([#4615](https://github.com/diegosouzapw/OmniRoute/pull/4615) — thanks @adivekar-utexas)
-- **fix(plugin): auto-prefix providerId with `opencode-` for OpenCode 1.17.8+ native gate** — adapts provider IDs to the OpenCode 1.17.8+ native provider gate. ([#4527](https://github.com/diegosouzapw/OmniRoute/pull/4527) — thanks @herjarsa)
-- **fix(catalog): shorten no-thinking gateway prefix to `no-think/`** — renames the no-thinking gateway prefix. ([#4525](https://github.com/diegosouzapw/OmniRoute/pull/4525) — thanks @Rahulsharma0810)
-- **fix(models): unknown max output limits no longer default to 8192** — models without synced/registry/static `maxOutputTokens` resolve the limit as unknown instead of a generic 8192 cap; clamping/injection only happens when a real cap is known. ([#4584](https://github.com/diegosouzapw/OmniRoute/pull/4584) — thanks @rdself)
-- **fix(resilience): respect upstream retry-hint toggle** — honors the configured toggle for upstream retry hints. ([#4585](https://github.com/diegosouzapw/OmniRoute/pull/4585) — thanks @rdself)
-- **fix(providers): show revealed connection API keys** — fixes revealing stored connection API keys in the UI. ([#4583](https://github.com/diegosouzapw/OmniRoute/pull/4583) — thanks @rdself)
-- **fix(logs): make active-request stale sweep configurable** — exposes the stale-request sweep interval as a setting. ([#4599](https://github.com/diegosouzapw/OmniRoute/pull/4599) — thanks @rdself)
-- **fix(resilience): retain provider cooldowns for the configured max window** — cooldowns persist for the configured maximum window. ([#4588](https://github.com/diegosouzapw/OmniRoute/pull/4588) — thanks @KooshaPari)
-- **fix(resilience): reject invalid provider cooldown bounds** — validates cooldown bound configuration. ([#4589](https://github.com/diegosouzapw/OmniRoute/pull/4589) — thanks @KooshaPari)
-- **fix(combo): preserve production combo metrics on shadow eviction** — shadow eviction no longer drops production combo metrics. ([#4590](https://github.com/diegosouzapw/OmniRoute/pull/4590) — thanks @KooshaPari)
-- **fix(combo): exclude exhausted connections from auto scoring** — exhausted connections are no longer scored as auto-combo candidates. ([#4592](https://github.com/diegosouzapw/OmniRoute/pull/4592) — thanks @KooshaPari)
-- **fix(relay): apply IP rate limit to the Bifrost sidecar** — extends IP rate limiting to the Bifrost relay sidecar. ([#4593](https://github.com/diegosouzapw/OmniRoute/pull/4593) — thanks @KooshaPari)
-- **fix(bifrost): finalize SSE relay usage after stream** — finalizes relay usage accounting once the SSE stream completes. ([#4612](https://github.com/diegosouzapw/OmniRoute/pull/4612) — thanks @KooshaPari)
-- **fix(quota): expose Bailian quota windows** — surfaces Bailian provider quota windows. ([#4610](https://github.com/diegosouzapw/OmniRoute/pull/4610) — thanks @KooshaPari)
-- **fix(dashboard): gate home topology live-WS networking behind widget visibility** — the home dashboard no longer starts topology polling / live sockets when topology is hidden. ([#4618](https://github.com/diegosouzapw/OmniRoute/pull/4618), [#4606](https://github.com/diegosouzapw/OmniRoute/pull/4606) — thanks @KooshaPari)
-- **fix(dashboard): isolate the quota widget refresh clock** — the quota widget refresh no longer drives unrelated re-renders. ([#4611](https://github.com/diegosouzapw/OmniRoute/pull/4611) — thanks @KooshaPari)
-- **fix(dashboard): memoize compatible provider groups** — avoids recomputing compatible provider groups on every render. ([#4613](https://github.com/diegosouzapw/OmniRoute/pull/4613) — thanks @KooshaPari)
-- **fix(cli): align `omniroute` data dir and env loading with the runtime** — the CLI's data-dir/env loading no longer drifts from the server runtime configuration. ([#4619](https://github.com/diegosouzapw/OmniRoute/pull/4619), [#4607](https://github.com/diegosouzapw/OmniRoute/pull/4607) — thanks @KooshaPari)
-- **fix(api/settings): prevent cached `/api/settings` responses** — disables caching on the settings endpoint (port from 9router#951). ([#4566](https://github.com/diegosouzapw/OmniRoute/pull/4566) — thanks @diegosouzapw)
-- **fix(executors): strip temperature for the GitHub Copilot gpt-5.4 family** — removes the unsupported `temperature` param for Copilot gpt-5.4 models (port from 9router#612). ([#4564](https://github.com/diegosouzapw/OmniRoute/pull/4564) — thanks @diegosouzapw)
-- **fix(dashboard): keep play_arrow spinning on provider "Test All" buttons** — fixes the spinner state on the provider test buttons (port from 9router#715). ([#4563](https://github.com/diegosouzapw/OmniRoute/pull/4563) — thanks @diegosouzapw)
-- **fix(dashboard): surface manual config CTA when Open Claw CLI auto-detect fails** — shows a manual-config call-to-action on the Open Claw CLI card when auto-detection fails. ([#4562](https://github.com/diegosouzapw/OmniRoute/pull/4562) — thanks @diegosouzapw)
-- **fix(oauth): update Qwen OAuth URLs from `chat.qwen.ai` to `qwen.ai`** — refreshes the Qwen OAuth endpoints (port of decolua/9router#683). ([#4561](https://github.com/diegosouzapw/OmniRoute/pull/4561) — thanks @diegosouzapw)
-
-### 📝 Maintenance
-
-- **refactor(imageGeneration): extract 8 provider families to co-located files** — splits the image-generation module into eight co-located per-provider files with no behavioral change. ([#4609](https://github.com/diegosouzapw/OmniRoute/pull/4609) — thanks @KooshaPari)
-- **deps: bump production + development groups; migrate js-yaml to v5 (ESM)** — dependency bumps plus a `js-yaml` v4→v5 migration to the ESM-only namespace import. ([#4697](https://github.com/diegosouzapw/OmniRoute/pull/4697) — thanks @diegosouzapw)
-- **chore(quality): release-green pre-flight validator + nightly signal** — new `npm run check:release-green` (`scripts/quality/validate-release-green.mjs`) reproduces the release-equivalent validation (full unit + vitest + ratchets + typecheck + lint, optional `--with-build` package-artifact) against the current working tree and classifies each red as **HARD** (real defect) vs **DRIFT** (ratchet, rebaselined at release) — purely diagnostic, never blocking contributors. A new `nightly-release-green` workflow runs it on the active release branch and opens/updates a tracking issue on hard failures. Closes the gap where the full gate (`ci.yml`) only ran on the release PR, so reds accrued silently on `release/**` and surfaced in layers at release time. ([#4622](https://github.com/diegosouzapw/OmniRoute/pull/4622) — thanks @diegosouzapw)
-- **chore(quality): reconcile file-size baseline for #4644 (`deepseek-web.ts` 1117→1125)** — rebaselines the file-size gate after the deepseek-web hardening. ([#4695](https://github.com/diegosouzapw/OmniRoute/pull/4695) — thanks @diegosouzapw)
-
----
-
-## [3.8.33] — TBD
-
-_See English CHANGELOG for v3.8.33 details._
-
-## [3.8.32] — TBD
-
-_See English CHANGELOG for v3.8.32 details._
-
----
-
-## [3.8.31] — 2026-06-20
-
-### ✨ New Features
-
-- **perf(dashboard): combos UI leaf-split, Next.js config tuning, 1-click Redis & Bifrost sidecar** — delivers four of the five performance/UX tracks from the #3932 thread: the combos dashboard page is split into focused leaf components (smaller bundles, faster reloads), `next.config` is tuned for the standalone build, Redis can be provisioned in one click, and a Bifrost sidecar option is wired in. (The fifth track — chatLogHelpers extraction — was already covered upstream and dropped.) ([#4381](https://github.com/diegosouzapw/OmniRoute/pull/4381) — thanks @KooshaPari)
-
-### 🐛 Fixed
-
-- **fix(embeddings): NVIDIA NIM asymmetric embedding models inject the required `input_type`** — NVIDIA NIM asymmetric embedders (e.g. `nvidia/nv-embedqa-e5-v5`) reject requests without an `input_type` parameter with `400 "'input_type' parameter is required"`, but OmniRoute only forwarded `input_type` when the client supplied it — so callers (and OpenAI-style SDKs that don't emit the field) got a hard failure. The embedding registry now carries a model-level default (`input_type: "query"`) for the asymmetric NVIDIA model, and the embeddings handler injects a model's default params into the upstream body **only** when the client didn't already send them — a client-supplied `input_type` (e.g. `"passage"`) is respected unchanged, and symmetric models that carry no default are unaffected. ([#4341](https://github.com/diegosouzapw/OmniRoute/pull/4341) — thanks @hydraromania)
-- **fix(api): migrate the deprecated Codex `[features].codex_hooks` flag to `[features].hooks`** — Codex renamed the `codex_hooks` feature flag to `hooks`; recent Codex CLI versions ignore the old key and print a deprecation notice. When OmniRoute rewrites an existing `~/.codex/config.toml` (configuring/resetting the Codex provider) it now carries the user's intent forward by renaming `[features].codex_hooks` → `[features].hooks` (preserving its value, never clobbering an already-present `hooks`) and dropping the deprecated key. No-op when the flag is absent. ([#4342](https://github.com/diegosouzapw/OmniRoute/pull/4342) — thanks @Bian-Sh)
-- **fix(translator): same-format response path no longer leaks a `data: null` SSE event** — the streaming response translator's same-format fast path returned `[chunk]` unconditionally, so the end-of-stream null/flush signal (`chunk === null`) propagated as a literal `[null]`. Downstream this surfaced as an empty `data: null` SSE event between chunks and crashed strict clients (e.g. Factory Droid BYOK on `/v1/responses`). The fast path now drops the null flush (returns `[]`) while still passing real chunks through unchanged. ([#4344](https://github.com/diegosouzapw/OmniRoute/pull/4344) — thanks @thaitryhand)
-- **fix(translator): strip client-only assistant echo fields on the OpenAI target path (Mistral 422)** — strict OpenAI-compatible upstreams (e.g. `mistral/codestral-latest`) reject client-only assistant "echo" fields sent back as input history with `422 extra_forbidden` (the report hit `messages[].assistant.reasoning_content` via Codex `/responses`). Only `reasoning_content` was being stripped on the OpenAI target path; the sibling echo fields `reasoning`, `refusal`, `annotations` and `cache_control` leaked through and tripped the 422. They are now all dropped on the non-reasoner OpenAI target path. `audio` is deliberately preserved (OpenAI audio models reference a prior assistant audio response by id on multi-turn; Mistral never emits audio, so nothing is lost there). ([#4350](https://github.com/diegosouzapw/OmniRoute/pull/4350) — thanks @xxy9468615)
-- **fix(translator): accept AI SDK-style `{ type: "image", image: "data:…" }` content parts** — several OpenAI-input translators only recognized images shaped as `image_url.url` (or an object with `.source`/`.url`), so an AI SDK-style part where `image` is a bare data-URL **string** was silently dropped before reaching a vision provider (OpenCode is one affected client; the gap is generic). The OpenAI→Claude, OpenAI→Kiro and OpenAI→Gemini/Antigravity translators now parse a string `image` data URL into each provider's native image shape (Claude `{source:{type:"base64"}}`, Kiro `images[].source.bytes`, Gemini `inlineData`). ([#4345](https://github.com/diegosouzapw/OmniRoute/pull/4345) — thanks @mugnimaestra)
-- **fix(translator): Gemini accepts HTTP/HTTPS image URLs instead of silently dropping them** — the OpenAI→Gemini request helper (`convertOpenAIContentToParts`) discarded remote `image_url` parts (emitting only a `console.warn`) because Gemini's `inlineData` needs base64 and the synchronous helper can't fetch+encode upstream. It now uses Gemini's native `fileData: { fileUri }` part for HTTP/HTTPS URLs (the model fetches the asset itself), so vision requests carrying a URL — not a `data:` URI — reach Gemini intact. ([#4373](https://github.com/diegosouzapw/OmniRoute/pull/4373) — ported from 9router#344, thanks @diegosouzapw)
-- **fix(executors): strip `stream_options` for qwen non-streaming / thinking Claude-Code requests** — Claude-Code-compatible providers force the executor-level `stream` flag on while the outgoing body keeps the caller's original `stream: false`, so `DefaultExecutor.transformRequest` injected `stream_options: { include_usage: true }` onto a body that still said `stream: false`, and qwen rejected it with `400 "'stream_options' only set this when you set stream: true"`. The executor now strips `stream_options` whenever the body's effective `stream` is false. ([#4374](https://github.com/diegosouzapw/OmniRoute/pull/4374) — ported from 9router#663, thanks @anuragg-saxenaa / @diegosouzapw)
-- **fix(executors): don't inject `thinking` when `tool_choice` forces a tool (native Claude)** — the Claude-Code wire-image emulation injects `thinking: { type: "adaptive" }` for non-Haiku Claude models, but Anthropic rejects `thinking` when `tool_choice` forces a specific tool (`{type:"any"|"tool"}`) with `400 "Thinking may not be enabled when tool_choice forces tool use."`. Any Opus/Sonnet call that pins a tool (e.g. Claude Code's `message_user`, or agent harnesses that force a tool) hit a hard 400; the injection is now suppressed when `tool_choice` forces a tool. ([#4389](https://github.com/diegosouzapw/OmniRoute/pull/4389) — thanks @NomenAK)
-- **fix(codex): request reasoning summaries on Codex Responses requests** — Codex/OpenAI Responses can return reasoning-token accounting and empty reasoning items unless visible reasoning summaries are requested, so Codex CLI / pi.dev paths missed visible thinking text. OmniRoute now requests `reasoning.summary: "auto"` (and includes `reasoning.encrypted_content`) when reasoning is enabled — preserving an explicit client `reasoning.summary` and existing `include` entries, and skipping it for `reasoning.effort: "none"`. ([#4359](https://github.com/diegosouzapw/OmniRoute/pull/4359) — thanks @xz-dev)
-- **fix(sse): default the combo per-target timeout to 120s for fast failover** — a combo's per-target timeout inherited the full `FETCH_TIMEOUT_MS` (600s default) when the combo didn't set `targetTimeoutMs`, so a single hung/slow target (e.g. an openai-compatible upstream returning 524/504) could stall the **whole** combo for up to 10 minutes before failing over. A new `DEFAULT_COMBO_TARGET_TIMEOUT_MS = 120_000` is used as the default-when-unset in `resolveComboTargetTimeoutMs` (backward-compatible 3rd arg, wired in `phaseComboSetup`); an explicit ceiling/opt-out is preserved. ([#4365](https://github.com/diegosouzapw/OmniRoute/pull/4365) — thanks @diegosouzapw)
-- **fix(cli): Tailscale login honors `TAILSCALE_AUTHKEY` for non-interactive sign-in** — `startTailscaleLogin` built `tailscale up` without ever reading `process.env.TAILSCALE_AUTHKEY`, so on a pre-authenticated / headless daemon the login waited for an interactive auth URL and timed out (~15s). When `TAILSCALE_AUTHKEY` is set it is now passed via `--auth-key=` (as a spawn argv element — no shell interpolation) so the daemon authenticates non-interactively; when unset, behavior is unchanged. ([#4343](https://github.com/diegosouzapw/OmniRoute/pull/4343) — thanks @ipeterpetrus)
-- **fix(dashboard): OAuth modal shows the real error on a non-JSON server response** — the OAuth connect/reauth modal called `await res.json()` unconditionally, so when a build/OAuth endpoint returned a plain-text error (e.g. a `500 Internal Server Error` page) the modal threw `Unexpected token 'I'…` and hid the real failure. Two shared helpers (`parseResponseBody` / `getErrorMessage` in `src/shared/utils/api.ts`) now read the body safely (JSON when it is JSON, raw text otherwise) and surface a clean message either way; all modal fetch sites use them. ([#4351](https://github.com/diegosouzapw/OmniRoute/pull/4351) — thanks @DNNYF)
-- **fix(dashboard): a disabled connection's last error is now visible** — the provider card's error badge counts a disabled connection (`isActive === false`) that has an error (its effective status is still error/expired/unavailable), but the connection row hid the `lastError` text for disabled rows — so the operator saw the error count without being able to see what failed. The row now shows the error text whenever there is one, regardless of the active toggle. ([#4352](https://github.com/diegosouzapw/OmniRoute/pull/4352) — thanks @ntdung6868)
-- **fix(providers): the "Test Connection One-by-One" OAuth probe can no longer hang the queue forever** — the OAuth connection-test path called bare `fetch(url, { method, headers })` with no `AbortController`/signal/timeout, so when a provider's probe endpoint accepted the socket but never responded, the awaited fetch never settled and the one-by-one test queue stalled indefinitely (the API-key path was already bounded via `validateProviderApiKey`'s `timeoutMs`). Both the initial probe and the post-refresh retry are now bounded with `AbortSignal.timeout(30s)` — matching the API-key path's 30s budget — and a timed-out probe resolves as a failure with a clear `Test timed out after 30s` message in the same shape as every other test error. ([#4347](https://github.com/diegosouzapw/OmniRoute/pull/4347) — thanks @ntdung6868)
-- **fix(providers): a deactivated account is labeled distinctly from a revoked token** — a Codex connection whose OAuth refresh is fully healthy but whose ChatGPT account has been deactivated by the provider gets a `401` from the upstream API. The connection test labeled that the same as a bad credential (`Token invalid or revoked` → `upstream_auth_error`), so the operator couldn't tell a deactivated account from a revoked token. The test now reads the `401`/`403` body and, when it indicates account deactivation, classifies it as `account_deactivated` — which the dashboard already renders as "Account Deactivated". A plain auth `401` is unchanged. ([#4353](https://github.com/diegosouzapw/OmniRoute/pull/4353) — thanks @ntdung6868)
-- **fix(db): cascade-delete orphaned model aliases when a provider is removed** — deleting a custom provider removed its connections and node but left behind the imported model-alias rows (stored as `key=<alias>`, `value="<providerId>/<model>"`). Those stale aliases then blocked re-importing the same provider — the import dedup treated them as "already exists", so no new models appeared. A new `deleteModelAliasesForProvider(providerId)` DB helper drops every alias whose stored value begins with `<providerId>/` (leaving other providers and user-defined settings aliases untouched), and the provider-node DELETE handler now calls it after removing the connections and node, so a fresh import is unblocked. ([#4348](https://github.com/diegosouzapw/OmniRoute/pull/4348) — thanks @nguyenvanhuy0612)
-- **fix(api): persist `max_input_tokens` / `max_output_tokens` when adding a custom model** — `POST /api/provider-models` silently dropped the per-model token limits set in the "add custom model" form: the handler destructured the rest of the body but never read `max_input_tokens` / `max_output_tokens`, and `addCustomModel()` had no parameter for them, so the values were thrown away on write. The DB layer (`inputTokenLimit` / `outputTokenLimit`) and the `/v1/models` catalog already round-trip these fields — only the write path was missing. The validation schema now accepts the two optional limits, the handler forwards them, and `addCustomModel()` persists them so a custom model's context/output window survives into the catalog. ([#4349](https://github.com/diegosouzapw/OmniRoute/pull/4349) — thanks @codename-zen)
-- **fix(plugin): the OpenCode static-catalog plugin prefixes combo/raw model keys with the provider id** — OpenCode's static-catalog reader misdetected the `omniroute` provider: combo keys emitted as `combo/MASTER` were parsed as provider `combo` ("No credentials for provider: omniroute"), while a bare-`MASTER` form was misread as a model with no resolvable provider, and mixed `omniroute/MASTER` + bare-raw keys were rejected by OpenCode's schema. The plugin now emits every combo and raw model key prefixed with the `omniroute` provider id, emits the provider id explicitly, and drops the legacy `combo/` prefix — so the static-catalog reader detects the provider and the auth loader returns the right credentials (the catalog-fetch timeout was also raised so a cold-start server doesn't publish an empty stub). ([#4384](https://github.com/diegosouzapw/OmniRoute/pull/4384) — thanks @herjarsa)
-
-### 🔒 Security
-
-- **fix(security): scope the OAuth callback `postMessage` to a trusted-origin allowlist** — the OAuth callback at `/callback` previously posted `{ code, state, … }` to `window.opener.postMessage(…, "*")` whenever the opener was cross-origin, so a hostile page that opened the well-known redirect URI in a popup could receive the OAuth code/state and complete the flow as the user. The wildcard fallback is replaced with iteration over a fixed allowlist (same-origin + Codex's `localhost:1455` / `127.0.0.1:1455` loopback helper); the browser silently drops `postMessage` to any opener whose origin isn't listed. ([#4372](https://github.com/diegosouzapw/OmniRoute/pull/4372) — ported from 9router#998, thanks @aeonframework / @diegosouzapw)
-- **fix(mitm): exact host membership in the MITM hosts test (CodeQL false positive)** — `tests/unit/mitm-tool-hosts.test.ts` checked host membership with `Array.includes(host)`, which CodeQL's `js/incomplete-url-substring-sanitization` heuristic misreads as a `String.includes()` URL-substring sanitization test (HIGH false positive). Switched to `.some((h) => h === host)` — identical semantics, no flagged pattern. ([#4386](https://github.com/diegosouzapw/OmniRoute/pull/4386))
-
-### 📝 Maintenance
-
-- **docs: one-time feature-documentation catch-up (v3.8.20 → v3.8.30)** — reconciled the docs with every user-facing feature shipped since v3.8.20: a new README **✨ What's New** section; new guides for [CLI integrations](docs/guides/CLI-INTEGRATIONS.md), [MITM TPROXY transparent decrypt](docs/security/MITM-TPROXY-DECRYPT.md) and [delegated Anthropic Context Editing](docs/compression/CONTEXT_EDITING.md); refreshed AUTO-COMBO (`auto/<category>:<tier>` + Arena-ELO), API_REFERENCE (`x-omniroute-no-memory`), MEMORY (int8 quantization, off-by-default), RESILIENCE (model-lockout success-decay), RTK, AGENTBRIDGE, TRAFFIC_INSPECTOR, GUARDRAILS, CLOUD_AGENT, ENVIRONMENT; regenerated PROVIDER_REFERENCE (231 providers) and synced the provider count in README/CLAUDE/AGENTS. Going forward this runs every release (generate-release step 6b). ([#4391](https://github.com/diegosouzapw/OmniRoute/pull/4391))
-- **refactor(chatCore): extract the `checkHeapPressureGuard` leaf (god-file decomposition start)** — first increment of decomposing `chatCore.ts` (~5127 LOC, the hottest path — every chat request flows through `handleChatCore`). The V8 heap-pressure guard at the top of `handleChatCore` (rejects with 503 when `heapUsed` exceeds the shed threshold) is moved to a self-contained, co-located `utils/heapPressure.ts::checkHeapPressureGuard(...)` with no behavior change. ([#4371](https://github.com/diegosouzapw/OmniRoute/pull/4371) — thanks @diegosouzapw)
-- **refactor(combo): de-dup the exhausted-target skip predicate across both dispatchers** — the byte-identical `#1731`/`#1731v2` pre-check (skip a target already exhausted on the provider/connection within a request) lived in both combo dispatchers; extracted to a shared `combo/comboPredicates.ts` helper. ([#4362](https://github.com/diegosouzapw/OmniRoute/pull/4362) — thanks @diegosouzapw)
-- **refactor(combo): de-dup the upstream-error exhaustion classification across both dispatchers** — both dispatchers ran a near-identical post-error block classifying the upstream error and updating the exhaustion Sets (`#1731` provider exhausted / `#1731v2` connection error / transient rate-limited); extracted to a shared `combo/targetExhaustion.ts::applyComboTargetExhaustion(...)`. ([#4366](https://github.com/diegosouzapw/OmniRoute/pull/4366) — thanks @diegosouzapw)
-- **chore(cli): localize CLI / scraping copy and stabilize fetch, memory & coverage handling** — localizes CLI and scraping UX copy plus the Adapta onboarding tutorial (and corrects the CLI Code page title), makes fetch retries honor the start timeout, tightens SSE/response typing, respects configured memory token limits during search, and reduces CI coverage-merge memory by merging V8 data incrementally. ([#4383](https://github.com/diegosouzapw/OmniRoute/pull/4383) — thanks @JxnLexn)
-- **test(combo): reset circuit breakers between stream-readiness cases (restore green)** — a stream-readiness fallback case failed on the release branch since the cycle-open tip due to test isolation: earlier combo-dispatch cases in the same file deliberately fail `glm` (tripping the module-level provider circuit breaker), and that OPEN state leaked into the next test so `combo.ts` skipped the model. The test now resets the circuit breakers between cases. ([#4396](https://github.com/diegosouzapw/OmniRoute/pull/4396) — thanks @diegosouzapw)
-- **chore(quality): reconcile the complexity ratchet baseline (1896 → 1900)** — absorbs the small complexity-metric increase from the v3.8.31 `/review-prs` merge batch into `quality-baseline.json` so the ratchet reflects the shipped code (no production change). ([#4410](https://github.com/diegosouzapw/OmniRoute/pull/4410) — thanks @diegosouzapw)
-- **test/gate: reconcile release-time drift surfaced by the full CI gate** — three already-merged changes left the release branch's full-CI gate red (the per-PR fast gates don't run it): the Gemini `convertOpenAIContentToParts` tests were realigned to the [#4373](https://github.com/diegosouzapw/OmniRoute/pull/4373) HTTP/HTTPS-URL `fileData` pass-through (they still asserted the old warn-and-drop behavior), the `t11` any-budget for `open-sse/executors/base.ts` was raised to 2 with a justification ([#4389](https://github.com/diegosouzapw/OmniRoute/pull/4389) compares `tool_choice` against the string literal `"any"`, not a TS `any` type), and the [#4384](https://github.com/diegosouzapw/OmniRoute/pull/4384) opencode-plugin combos test's net-assert reduction (dropping the obsolete `combo/` namespace) was allowlisted. No production behavior change. (thanks @diegosouzapw)
-
----
-
-## [3.8.30] — 2026-06-20
-
-### ✨ New Features
-
-- **feat(dashboard): category (media serviceKind) filter on the providers page** — `/dashboard/providers` gains a media-category filter row (Image / Video / Music / Text→Speech / Speech→Text / Embedding) that composes with the existing search, free-only and "show configured only" filters. Membership is derived from the backend media registries (a provider that serves a kind is surfaced even if it never declared `serviceKinds`), keeping the UI in lockstep with the backend. ([#4240](https://github.com/diegosouzapw/OmniRoute/issues/4240))
-- **feat(combo): per-step account allowlist — scope a round-robin/weighted step to a subset of a provider's connections** — a combo model step can now carry a first-class account allowlist so a round-robin (or weighted) strategy is scoped to a chosen subset of a provider's connections (e.g. only `foo1`+`foo2` out of `foo1..foo4`) without hand-pinning one step per account. Empty = the whole active pool (unchanged). When a step both has an allowlist and is tag-routed, the two intersect (most-restrictive wins); a single pinned account still takes precedence. The combo builder's Precision step editor gains an optional "Restrict to accounts" picker. ([#3266](https://github.com/diegosouzapw/OmniRoute/issues/3266))
-- **feat(providers): add OpenAdapter, dit.ai and TokenRouter as OpenAI-compatible providers** — three community-requested OpenAI-compatible aggregators now register as standard named OpenAI-style providers with live `/v1/models` discovery (the zenmux pattern), falling back to a seeded catalog when the upstream list is unavailable: **OpenAdapter** (`https://api.openadapter.in/v1`, free tier, 70+ open-source models — [#4239](https://github.com/diegosouzapw/OmniRoute/issues/4239)), **dit.ai** (`https://api.dit.ai/v1`, dynamic-pricing router/gateway — [#4155](https://github.com/diegosouzapw/OmniRoute/issues/4155)), and **TokenRouter** (`https://api.tokenrouter.com/v1`, free MiniMax model — [#3841](https://github.com/diegosouzapw/OmniRoute/issues/3841), thanks @FerLuisxd). No custom executor/translator — default OpenAI passthrough.
-- **feat(api): `x-omniroute-no-memory` request header — per-request opt-out of memory/skills injection** — clients that manage their own context (e.g. their own RAG/memory) can send `x-omniroute-no-memory: true` (mirrors the existing `x-omniroute-no-cache` convention) to skip the gateway injecting up to `memorySettings.maxTokens` (~2k) tokens of memory **and** skills context into that chat request — avoiding the token/cost inflation it otherwise adds on every call. Absent the header, behavior is unchanged. (PRD-2026-06-19-no-memory-header)
-- **feat(dashboard): MITM tool card lists the exact hosts-file entries to add manually** — the CLI-tools MITM card's "How it works" section now lists the full set of `127.0.0.1 <host>` lines for the selected tool (sourced from the canonical MITM target registry) instead of a single example domain. Users on locked-down machines — where the automatic, sudo-gated hosts-file edit isn't available — can now copy every required entry by hand. (thanks @mrcyclo)
-- **feat(cli): `omniroute launch-codex` + `setup-codex` — run/configure the Codex CLI against OmniRoute** — a launcher and setup command that point the Codex CLI at an OmniRoute endpoint (remote-mode aware). ([#4270](https://github.com/diegosouzapw/OmniRoute/pull/4270))
-- **feat(cli): Claude Code launcher + setup — remote mode + profiles** — `omniroute launch`/`setup` for Claude Code with remote-mode support and named connection profiles. ([#4274](https://github.com/diegosouzapw/OmniRoute/pull/4274))
-- **feat(cli): OpenCode setup — OpenAI-compatible provider + remote-aware plugin** — `setup-opencode` registers OmniRoute as an OpenAI-compatible provider for OpenCode and installs a remote-aware plugin. ([#4277](https://github.com/diegosouzapw/OmniRoute/pull/4277))
-- **feat(cli): one-command setup for popular AI coding tools** — new `setup-*` commands that configure each tool to talk to OmniRoute: **Cline** ([#4280](https://github.com/diegosouzapw/OmniRoute/pull/4280)), **Kilo Code** ([#4284](https://github.com/diegosouzapw/OmniRoute/pull/4284)), **Continue** ([#4289](https://github.com/diegosouzapw/OmniRoute/pull/4289)), **Cursor** ([#4291](https://github.com/diegosouzapw/OmniRoute/pull/4291)), **Roo Code** ([#4292](https://github.com/diegosouzapw/OmniRoute/pull/4292)), **Crush** ([#4298](https://github.com/diegosouzapw/OmniRoute/pull/4298)), **Goose** ([#4300](https://github.com/diegosouzapw/OmniRoute/pull/4300)), **Qwen Code** ([#4301](https://github.com/diegosouzapw/OmniRoute/pull/4301)), **Aider** ([#4302](https://github.com/diegosouzapw/OmniRoute/pull/4302)) and the **Gemini CLI** (native `/v1beta`) ([#4303](https://github.com/diegosouzapw/OmniRoute/pull/4303)).
-- **feat(providers): provider model sweep — live discovery, refreshed catalogs, dead-provider cleanup** — a broad sweep that enables live `/v1/models` discovery for more OpenAI-style providers (the zenmux pattern), refreshes the seeded catalogs with current models, and marks dead providers `deprecated`. ([#4324](https://github.com/diegosouzapw/OmniRoute/pull/4324))
-- **feat(mitm): translate Antigravity cloudcode end-to-end (Gap B)** — the MITM decrypt path now translates Antigravity `cloudcode` traffic end-to-end. ([#4299](https://github.com/diegosouzapw/OmniRoute/pull/4299))
-- **feat(keys): per-key USD usage quota controls** — an API key can now carry a USD spend quota that caps its usage once the threshold is reached. ([#4327](https://github.com/diegosouzapw/OmniRoute/pull/4327) — thanks @Witroch4)
-
-### 🔧 Changed
-
-- **change(memory): memory is now OFF by default** — `DEFAULT_MEMORY_SETTINGS.enabled` now defaults to `false`. Enabling memory injects up to ~2,000 tokens of retrieved context into **every** chat request (and that context is billed), which was a surprising default for new installs and for clients with their own context. Memory is now an explicit opt-in: installs that already enabled it keep it on; installs that never configured it default to off. The Settings → Memory panel now shows a token-cost warning when memory is enabled. (PRD-2026-06-19-no-memory-header)
-
-### 🐛 Fixed
-
-- **fix(translator): Gemini accepts HTTP/HTTPS image URLs (no longer silently dropped)** — OpenAI-style `image_url` parts whose URL was `http://…` or `https://…` reached `convertOpenAIContentToParts` (the OpenAI→Gemini request helper) and were dropped with only a `console.warn`, because Gemini's `inlineData` requires base64 and the helper is synchronous (it cannot fetch + encode). Gemini's `Part` schema, however, natively accepts `fileData: { fileUri }` for remote URIs — the model fetches the asset itself. The helper now emits a `fileData` part (`mimeType: "image/*"`, inferred upstream on fetch) instead of dropping, so vision requests that pass a URL — not a data: URI — now reach Gemini intact. `data:` URIs still go through `inlineData` unchanged; unsupported schemes (e.g. `ftp:`) are still skipped. (thanks @East-rayyy)
-- **fix(security): OAuth callback page no longer relays `code`/`state` to a wildcard `postMessage` target** — the OAuth callback at `/callback` posted `{ code, state, ... }` to `window.opener.postMessage(..., "*")` whenever the opener was cross-origin (a fallback for the legitimate remote-dashboard + local-loopback callback scenario). A hostile page that opened the callback URL in a popup against the well-known redirect URI would therefore receive the OAuth code+state and could complete the OAuth flow as the user. The wildcard fallback is replaced with an iteration over a fixed allowlist of trusted target origins (same-origin + Codex's loopback helper at `localhost:1455` / `127.0.0.1:1455`); the browser silently drops the message for any opener whose origin is not in the list. Methods 2 (`BroadcastChannel`) and 3 (`localStorage`) — already in the page — still cover same-origin parents when the opener was severed by COOP. (thanks @aeonframework)
-- **fix(compliance): startup cleanup honors the dashboard data-retention setting instead of always trimming to 7 days** — on every restart, `cleanupExpiredLogs()` (run at startup) read retention only from the `CALL_LOG_RETENTION_DAYS` / `APP_LOG_RETENTION_DAYS` env vars, which default to **7 days** when unset, and trimmed `usage_history` (the Usage Analysis data) before the dashboard-based `runAutoCleanup()` — which respects the configured retention — ever ran. So a dashboard "Data Retention" of 90 days was silently overridden and the Usage Analysis page only ever showed the last 7 days after a restart. Retention now follows the precedence **explicit env var → dashboard DB setting → 7-day default**, per table (`usage_history`→`usageHistory`, `call_logs`/`proxy_logs`/`request_detail_logs`→`callLogs`, `mcp_tool_audit`→`mcpAudit`); an operator who sets the env var still wins, and non-DB deployments still fall back to it. ([#4354](https://github.com/diegosouzapw/OmniRoute/issues/4354) — thanks @akbardwi)
-- **fix(providers): bailian-coding-plan static fallback catalog matches the registry (10 models)** — the provider-model sweep (#4324) added four current Model Studio coding-plan models (`qwen3.7-plus`, `qwen3-coder-plus`, `qwen3-coder-next`, `glm-4.7`) to the `bailian-coding-plan` registry entry but missed the static fallback mirror in `staticModels.ts`, which still listed only the older six. The static catalog (served when live discovery is unavailable) therefore diverged from the registry, and the existing static↔registry parity test went red on the release branch (only surfacing when test-impact analysis happened to select it). The static mirror now carries all ten models in registry order, restoring parity. ([#4324](https://github.com/diegosouzapw/OmniRoute/pull/4324))
-- **fix(executors): ArenaLLM accepts LMArena's split Supabase SSR auth cookie** — LMArena migrated to `@supabase/ssr` chunked auth cookies: the single `arena-auth-prod-v1` cookie is now empty and the real session is split across `arena-auth-prod-v1.0`, `arena-auth-prod-v1.1`, … (ascending). A user who pasted the (now-empty) single cookie therefore sent an empty session and upstream rejected it as "invalid cookie". The LMArena executor now reconstructs the single cookie from its chunks — reading `.0`, `.1`, … in ascending numeric order until one is missing and concatenating their raw values (`@supabase/ssr`'s `combineChunks` rule: plain `join("")`, no base64-decode, no JSON-parse, the `base64-` prefix kept verbatim) — while preserving the rest of the pasted jar. A non-empty single cookie is still forwarded unchanged (back-compat). The credential UX now instructs pasting the **full Cookie header** and tracks the `.0`/`.1` storage keys. ([#4271](https://github.com/diegosouzapw/OmniRoute/issues/4271) — thanks @caussao)
-- **fix(compression): preserve the cacheable prefix for automatic-cache providers** — OpenAI / Codex (and Azure-OpenAI) use _automatic_ prefix caching: the upstream caches the longest matching prefix of a request (system prompt + earliest messages) **without** any explicit `cache_control` markers in the body. The cache-aware compression guard only protected that prefix when the request carried explicit `cache_control`, so for automatic-cache providers the guard was skipped — and with compression enabled and `preserveSystemPrompt: false` (or a prefix-compressing mode like `aggressive`/`ultra`) it rewrote the system prompt / earliest messages, guaranteeing a cache miss and **higher** token spend through OmniRoute than going direct. The guard now treats a caching provider as sufficient on its own (`isCachingProvider` alone, independent of `cache_control`) to skip the system prompt and downgrade prefix-compressing modes, and OpenAI/Codex/Azure are now recognized as caching providers. Compression is still off by default — this only affects operators who enabled it with prefix preservation turned off. ([#3955](https://github.com/diegosouzapw/OmniRoute/issues/3955))
-- **fix(executors): DuckDuckGo AI Chat uses duckduckgo.com (fixes 400)** — the DuckDuckGo AI Chat executor fetched status/chat and set `Origin`/`Referer` against `https://duck.ai` while still sending `Sec-Fetch-Site: same-origin`, so the request's same-origin triplet (host + Origin + Referer) was inconsistent and the backend rejected it with HTTP 400. All current DDG reverse-engineering references — and the provider registry's own `baseUrl` — use `https://duckduckgo.com`; the executor now uses it consistently for the status URL, chat URL, `Origin`, and `Referer` (the same-origin header is now coherent). The `x-fe-version` scrape regex also required a 40-hex tail but the real served token has a 20-hex tail (e.g. `serp_20250401_100419_ET-19d438eb199b2bf7c300`), so it silently fell back to a hardcoded default; the pattern is relaxed to a bounded `{20,40}` tail (still ReDoS-safe). This addresses the DuckDuckGo half of the report; the separate Chipotle/`chipotle` upstream breakage is tracked independently. ([#4037](https://github.com/diegosouzapw/OmniRoute/issues/4037) — thanks @daniij)
-- **fix(security): bound the prompt-injection scan to the first 16 KB (hot-path perf)** — the prompt-injection guard joined every message/system string into one buffer and ran several regexes over the **whole** thing on every chat request, with no size cap — so a 300 KB body (pasted code, RAG context) meant O(body) CPU scanning on the hot path, a self-inflicted latency/GC source under concurrency. Both detection call sites (`detectInjection` in `inputSanitizer.ts` and the custom-pattern scan in `promptInjection.ts`) now slice the joined text to the first **16 KB** (`MAX_INJECTION_SCAN_BYTES`) before the regex loop. Injection directives sit near the top of a prompt, so the generous cap preserves real detection while scanning only a bounded prefix; the existing 10 MB body-size cap (which protects ingestion) is unchanged. ([#3932](https://github.com/diegosouzapw/OmniRoute/issues/3932) — thanks @KooshaPari)
-- **fix(sse): retry direct-connection socket failures on a fresh socket (fewer `502` bursts)** — the default direct-connection undici dispatcher pools keep-alive sockets for up to 4 s, but some edges (e.g. `nvidia`, `opencode-zen`) silently close idle keep-alive sockets within that window, so the next request reusing a pooled socket fails with `UND_ERR_SOCKET` ("other side closed") — in bursts. `proxyFetch` already retried once on such transient errors, but the retry reused the **same** pooled dispatcher and could grab another stale socket, then fell through to native fetch (which also pools) → the job sat in the rate-limit queue until the 30 s timeout → `502` + circuit-breaker open. The retry now uses a dedicated **no-keep-alive / no-pipelining** dispatcher so it opens a brand-new socket that can't be a dead pooled one; the first attempt still uses the pooled dispatcher (healthy keep-alive reuse is preserved). Complements the v3.8.29 diagnostics (`describeFetchCause`, #4281). ([#4252](https://github.com/diegosouzapw/OmniRoute/issues/4252) — thanks @klimadev)
-- **fix(sse): combo now stops at the first body-specific 400 instead of trying every target** — the `#2101` guard that detects a body-specific 400 (context overflow / malformed / model-access-denied, e.g. "model is not supported when using Codex with a ChatGPT account") logged "stopping combo" but executed a bare `break`, which only exited the inner retry loop; `executeTarget` then returned `null` and the outer target loop treated that as "this target produced nothing" and advanced to the next model. A combo of N targets that all reject the same request body therefore marched through all N (the report shows a 143-model Codex combo iterating every target), wasting upstream calls and per-attempt work. The guard now surfaces the 400 via the `{ ok, response }` contract (mirroring the 499 client-disconnect path) so the combo resolves and stops immediately. ([#4279](https://github.com/diegosouzapw/OmniRoute/issues/4279))
-- **fix(sse): non-streaming combo over a Responses-API target no longer returns empty content** — a Responses-API target (codex/`cx`) streams from upstream even on `stream:false`, and its terminal `response.completed` snapshot can carry a non-empty `output` that lacks the assistant message item (e.g. only a `reasoning` item) while the streamed `output_text` deltas had reconstructed the full message. The SSE→JSON aggregator preferred the terminal `output` wholesale, dropping the reconstructed text → HTTP 200 with empty content (hit notably via n8n, which defaults to `stream:false`). The aggregator now falls back to the reconstructed delta output when the terminal output has no message item but the reconstruction does; the terminal snapshot still wins whenever it already carries the message. ([#3948](https://github.com/diegosouzapw/OmniRoute/issues/3948))
-- **fix(executors): preserve tool-name casing on native Claude OAuth (`read` no longer leaks back as `Read`)** — native Claude OAuth traffic runs through an anti-fingerprint tool-name cloak that renames a tool literally named `read` to `Read` on the wire and records the reverse alias on a non-enumerable `_toolNameMap`, which the response side uses to restore the client's original casing. Since v3.8.27 the executor returned a JSON-round-tripped copy of the body as `transformedBody`, and that round-trip dropped the non-enumerable map — so the restore saw an empty map and the cloaked `Read` streamed verbatim to the client, corrupting the tool name. The executor now re-attaches the cloak map onto the serialized body (mirroring the Antigravity executor), so tool-name casing round-trips correctly. ([#4307](https://github.com/diegosouzapw/OmniRoute/issues/4307) — thanks @dev-cj)
-- **fix(api): cache-HIT `X-OmniRoute-Response-Cost` now reports the incremental cost (≈0), not the original** — on a semantic-cache HIT the gateway serves the stored response **without** an upstream call, but `X-OmniRoute-Response-Cost` was reporting the original call's full cost (recomputed from the cached `usage`). A consumer summing `response-cost` for billing was therefore charging for responses that cost ≈$0 to serve (and stale entries could inflate it). Cache hits now bill `X-OmniRoute-Response-Cost: 0.0000000000` (the real incremental cost), and the avoided cost is surfaced in a new **`X-OmniRoute-Cost-Saved`** header for cache analytics — mirroring the existing `tokens_saved` concept. The MISS path is unchanged. (PRD-2026-06-19-cache-hit-cost-reporting)
-- **fix(models): imported vision-capable models keep their vision capability** — after importing a provider key, vision-capable models (e.g. OpenRouter models whose `architecture` declares image input, and other synced providers) were listed as text-only in `/v1/models` and the dashboard — even though image requests actually worked. Synced model records never captured the vision flag, and the catalog's OpenRouter live-enrichment (which derives vision from `architecture.input_modalities`) is skipped once a provider has synced models. Discovery now captures `supportsVision` at sync time (from `architecture.input_modalities`, the string `architecture.modality`, or a top-level `input_modalities`), mirroring the existing `supportsThinking` capture, and the catalog surfaces `capabilities.vision` for synced models. ([#4264](https://github.com/diegosouzapw/OmniRoute/issues/4264) — thanks @FerLuisxd)
-- **fix(providers): Cloudflare Workers AI model discovery shows model names, not UUIDs** — importing a Cloudflare Workers AI key listed models with internal UUID identifiers (e.g. `429b9e8b-d99e-…`) instead of their usable slugs (`@cf/meta/llama-3.1-8b-instruct`). Cloudflare's `/ai/models/search` returns `{ id: "<uuid>", name: "@cf/…" }`, and discovery was passing the raw objects through — so the UUID `id` became the callable model id. The `cloudflare-ai` discovery now maps each result's `name` → id, surfacing the real `@cf/…` model ids. ([#4259](https://github.com/diegosouzapw/OmniRoute/issues/4259) — thanks @FerLuisxd)
-- **fix(translator): clamp Responses API `call_id` to 64 characters** — the OpenAI Responses API rejects `call_id` values longer than 64 characters with a 400. Long upstream tool-call ids (some clients emit ids well over the limit) are now clamped deterministically on both the `function_call` item and its matching `function_call_output`, so the pair stays matched through the orphaned-output filter and the request is accepted. (thanks @anuragg-saxenaa, @ngapngap)
-- **fix(oauth): GitHub Copilot token refresh now sends the public client_id** — the `github` provider config never carried a `clientId`, so GitHub OAuth `refresh_token` exchanges either omitted `client_id` or sent the literal string `undefined` (and a bogus `client_secret=undefined`), which GitHub rejects — leaving a Copilot connection stuck once its short-lived token expired and the long-lived refresh path was needed. The provider now resolves its public device-flow `client_id` from the embedded public credential and omits `client_secret` entirely (GitHub's Copilot app is a public client with no secret). (thanks @baslr)
-- **fix(translator): a tool property named `pattern` survives Gemini/Antigravity schema sanitization** — the Gemini schema sanitizer strips JSON-Schema constraint keywords Gemini rejects (`pattern`, `minLength`, …) at every nesting level, but it also deleted any tool **property** literally _named_ one of those keywords. glob/grep tools declare a property called `pattern`, so on `ag/*` (Antigravity) backends that argument (and its `required` entry) was silently dropped, breaking the tools. Keyword stripping is now position-aware: it only removes constraint keywords at the schema-node level and never against the user-defined names inside a `properties` map. A genuine string-level `pattern` _constraint_ is still stripped. (thanks @youthanh)
-- **fix(translator): MCP `namespace` tools flatten to individual functions on the Responses→Chat path** — when a Codex CLI client routes a Responses-API request to a non-Codex backend (e.g. `kr/claude-opus-4.7`), each MCP server is declared as a `namespace` tool (`{ type:"namespace", name, tools:[…] }`). The Responses→Chat translator had no `namespace` branch, so the whole group collapsed into a single empty-schema function named `mcp__<server>__` and every MCP call returned `unsupported call: mcp__<server>__`, breaking all MCP-based workflows (context7, codegraph, custom MCPs) for that combination. The translator now expands a namespace into one Chat function per sub-tool (preserving each sub-tool's name and parameters); an empty namespace yields no tools instead of a broken placeholder. The native Codex passthrough path was already correct. (thanks @V13t4nh)
-- **fix(cli): the active remote-context credential wins over an ambient `OMNIROUTE_API_KEY`** — when a remote context is selected, its scoped access token now takes precedence over an `OMNIROUTE_API_KEY` present in the environment, so the connected remote is targeted as expected. ([#4364](https://github.com/diegosouzapw/OmniRoute/pull/4364))
-- **fix(cli): wire the `contexts` command into the CLI program** — the `omniroute contexts` command (list/switch saved remote contexts) was implemented but never registered, so it was unreachable; it is now wired into the CLI program. ([#4369](https://github.com/diegosouzapw/OmniRoute/pull/4369))
-- **fix(mitm): mask bare `Bearer <token>` header values in the Traffic Inspector** — the inspector now redacts bare `Authorization: Bearer …` values so tokens don't leak into captured traffic. ([#4358](https://github.com/diegosouzapw/OmniRoute/pull/4358))
-- **fix(pricing): price the `gpt-5.x-pro` OpenAI models + align the opencode-go discovery test** — adds pricing for the gpt-5.x-pro models so cost telemetry reports a real cost instead of zero. ([#4355](https://github.com/diegosouzapw/OmniRoute/pull/4355))
-- **fix(sse): release the reader and cancel the stream on abort/error (no more Undici pool socket leak)** — on abort or a mid-stream error the response reader is released and the stream cancelled, preventing leaked pooled sockets that degraded later requests. ([#4309](https://github.com/diegosouzapw/OmniRoute/pull/4309) — thanks @Ardem2025)
-- **fix(kiro): emit an early role-only start chunk to release the stream-readiness gate** — Kiro streams now send an initial role-only chunk so the stream-readiness gate releases promptly instead of stalling. ([#4311](https://github.com/diegosouzapw/OmniRoute/pull/4311) — thanks @artickc)
-- **fix(dashboard): the proxy modal stops pre-filling new scopes with an unrelated proxy** — adding a new scope assignment no longer inherits a previously-selected proxy's configuration. ([#4312](https://github.com/diegosouzapw/OmniRoute/pull/4312))
-- **fix(open-sse): inner-ai stops silently rerouting unmatched models to `models[0]`** — an unmatched model id is no longer silently served by the first available model; the lookup now returns null and the request is handled explicitly. ([#4310](https://github.com/diegosouzapw/OmniRoute/pull/4310))
-- **fix(pollinations): handle auth-required premium models (claude, gemini, midjourney)** — premium Pollinations models that require authentication are now handled correctly instead of failing. ([#4266](https://github.com/diegosouzapw/OmniRoute/pull/4266) — thanks @oyi77)
-- **fix(codex): isolate the Spark quota scope** — Codex Spark usage is tracked under its own quota scope so it no longer bleeds into other Codex quotas. ([#4293](https://github.com/diegosouzapw/OmniRoute/pull/4293) — thanks @xz-dev)
-- **fix(dashboard): improve the API "try it" functionality** — fixes the request path used by the dashboard's API "try it" panel. ([#4296](https://github.com/diegosouzapw/OmniRoute/pull/4296) — thanks @edrickrenan)
-- **fix: polyfill `crypto.randomUUID` for non-secure contexts** — restores UUID generation when the dashboard is served over a non-secure (plain-HTTP) origin where `crypto.randomUUID` is unavailable. ([#4287](https://github.com/diegosouzapw/OmniRoute/pull/4287) — thanks @pizzav-xyz)
-- **fix(proxy): allow concurrent proxy dispatcher streams** — the proxy dispatcher no longer serializes streams, so concurrent requests through a proxied connection run in parallel. ([#4288](https://github.com/diegosouzapw/OmniRoute/pull/4288) — thanks @wilsonicdev)
-- **fix(build): co-locate llmlingua SLM optionals into `dist/node_modules` (postinstall)** — the optional llmlingua SLM packages are co-located into the standalone build so the compression worker can actually spawn in production. ([#4286](https://github.com/diegosouzapw/OmniRoute/pull/4286))
-- **fix(mitm): surface AgentBridge traffic in the Traffic Inspector (D4 ingest)** — AgentBridge requests now appear in the Traffic Inspector. ([#4285](https://github.com/diegosouzapw/OmniRoute/pull/4285))
-- **fix(sse): surface undici `err.cause` on dispatcher failure** — dispatcher failures now flatten the cause chain (and `AggregateError`s) into the error detail for diagnosability. ([#4281](https://github.com/diegosouzapw/OmniRoute/pull/4281))
-- **fix(cli): harden `launch`/`launch-codex` with free-claude-code patterns** — the launchers adopt the hardened launch patterns ported from free-claude-code. ([#4278](https://github.com/diegosouzapw/OmniRoute/pull/4278))
-- **fix(compression): end-to-end audit — fixes across the whole compression flow** — a sweep of the compression pipeline fixing ultra/aggressive/lossless edge cases, accessibility-anchor handling, language detection, and mode decoupling. ([#4323](https://github.com/diegosouzapw/OmniRoute/pull/4323))
-
-### 🧪 Tests
-
-- **test: align two tests left red by merged PRs** — re-aligns the db-rules classification count (#4335) and the LMArena split-cookie metadata test (#4271) after concurrent merges. ([#4346](https://github.com/diegosouzapw/OmniRoute/pull/4346))
-- **test(ci): reconcile the release/v3.8.30 baseline + test drift** — reconciles quality baselines and drifted tests accumulated on the release branch. ([#4276](https://github.com/diegosouzapw/OmniRoute/pull/4276))
-
-### 📝 Maintenance
-
-- **refactor(combo): `ComboContext` + extract `phaseComboSetup` (god-file split, phase 1)** — begins decomposing the combo god-file by extracting combo setup into a context object, without touching dispatch/semaphore logic. ([#4326](https://github.com/diegosouzapw/OmniRoute/pull/4326))
-- **feat(quality): cap test-file size — anti-reinflation Layer 1** — freezes the existing god-tests and caps new test files at 800 lines to stop re-inflation. ([#4273](https://github.com/diegosouzapw/OmniRoute/pull/4273))
-- **feat(quality): seed per-module mutationScore floors + a blocking aggregation ratchet (T3)** — adds per-module mutation-score floors with a blocking aggregate gate. ([#4305](https://github.com/diegosouzapw/OmniRoute/pull/4305))
-- **feat(quality): make the a11y gate real (`@axe-core/playwright` in nightly)** — wires the previously-phantom accessibility gate into the nightly run with real baselines. ([#4321](https://github.com/diegosouzapw/OmniRoute/pull/4321))
-- **feat(quality): unblock R1 — test-redundancy measurement via `disableBail`** — enables the test-redundancy measurement that was previously blocked by fail-fast. ([#4322](https://github.com/diegosouzapw/OmniRoute/pull/4322))
-- **fix(quality): the complexity gate now covers `bin/` + `electron/`, and tracked-artifacts runs in pre-commit** — extends the complexity gate's scope and moves the tracked-artifacts check into the pre-commit hook. ([#4318](https://github.com/diegosouzapw/OmniRoute/pull/4318))
-- **fix(quality): restore release/v3.8.30 green — 3 latent reds from concurrent merges** — fixes three latent test reds surfaced by concurrent merges into the release branch. ([#4335](https://github.com/diegosouzapw/OmniRoute/pull/4335))
-- **fix(combo): keep `phaseComboSetup` under the complexity ceiling** — extracts a helper so the new combo setup phase stays under the complexity gate. ([#4338](https://github.com/diegosouzapw/OmniRoute/pull/4338))
-- **ci(mutation): split over-budget batches by range/pair so every batch fits the job cap** — re-splits the mutation batches so each fits the CI job budget. ([#4272](https://github.com/diegosouzapw/OmniRoute/pull/4272))
-- **chore(ci): align the electron audit gate to the root advisory policy** — the electron-workspace audit gate now follows the same advisory policy as the root. ([#4275](https://github.com/diegosouzapw/OmniRoute/pull/4275))
-- **chore(quality): reconcile the complexity/quality baselines across concurrent-merge drift** — rolls up the cycle's baseline reconciliations driven by concurrent merges into the release branch. ([#4330](https://github.com/diegosouzapw/OmniRoute/pull/4330), [#4336](https://github.com/diegosouzapw/OmniRoute/pull/4336), [#4370](https://github.com/diegosouzapw/OmniRoute/pull/4370))
-- **docs: ban AI-generation footers in commits/PRs/CHANGELOG (Hard Rule #16)** — codifies the prohibition on AI-generation footers and bot co-author trailers. ([#4328](https://github.com/diegosouzapw/OmniRoute/pull/4328))
-- **docs(design): add the OmniRoute design system and visual identity specification** — adds the design-system / visual-identity specification document. (thanks @diegosouzapw)
-
-### 🔒 Security
-
-- **fix(sse): harden the DuckDuckGo lite scraper sanitization (CodeQL)** — closes four HIGH CodeQL alerts in the no-key web-search scraper: `decodeEntities` now resolves `&amp;` **last** so an already-escaped entity (e.g. `&amp;lt;`) survives as literal text instead of being double-unescaped (`js/double-escaping`); `stripTags` decodes entities first, then strips tags in a loop to a fixpoint and drops any trailing unclosed `<…`, so entity-encoded markup like `&lt;script&gt;` can never reach the LLM/client as a live tag (`js/incomplete-multi-character-sanitization`); and the host checks in the search tests use `new URL().hostname` equality instead of substring `.includes` (`js/incomplete-url-substring-sanitization`). ([#4356](https://github.com/diegosouzapw/OmniRoute/pull/4356))
-
-### 🔧 Dependencies
-
-- **fix(deps): bump undici to 7.28.0 and dompurify to 3.4.11 (security)** — addresses the undici SOCKS5-TLS / cache advisories and the dompurify advisory. ([#4306](https://github.com/diegosouzapw/OmniRoute/pull/4306))
-- **chore(deps): bump actions/checkout from 4 to 7** — CI checkout-action update. ([#4297](https://github.com/diegosouzapw/OmniRoute/pull/4297))
-- **fix(executors): strip `stream_options` for qwen non-streaming / thinking-mode Claude Code requests** — Claude-Code-compatible providers force the executor-level `stream` flag on via `upstreamStream = stream || isClaudeCodeCompatible` (`open-sse/handlers/chatCore.ts`), but the outgoing body keeps the caller's original `stream: false`. The shared `stream && targetFormat === "openai"` branch in `DefaultExecutor.transformRequest` then injected `stream_options: { include_usage: true }` onto a body that still said `stream: false`, and qwen upstream rejected it with `400 "'stream_options' only set this when you set stream: true"`. Same rejection when the body carries `thinking` / `enable_thinking`. The qwen branch now skips the injection (and strips any client-sent `stream_options`) when the body explicitly says `stream: false` or requests thinking, leaving regular qwen streaming requests with the usage injection intact. (thanks @anuragg-saxenaa)
-
----
-
-## [3.8.29] — 2026-06-19
-
-### ✨ New Features
-
-- **feat(cloud-agent): Cursor Cloud Agent via the official API-key REST API (no IDE-OAuth ban risk)** — adds a `cursor-cloud` cloud agent that drives Cursor's Background / Cloud Agents through the official REST API (`api.cursor.com`) authenticated with a user or service-account API key — the safer, first-party alternative to re-using the Cursor IDE's OAuth session (the existing `cursor` provider, which carries a ban-risk warning). Implemented as a plain REST adapter mirroring the Devin/Jules agents (`createTask`/`getStatus`/`sendMessage`/`listSources`), so it does **not** pull in the `@cursor/sdk` package and its per-platform native binaries (Cursor's SDK is itself a thin wrapper over this REST API). Cursor's UPPERCASE status enums (`CREATING`/`RUNNING`/`FINISHED`/`ERROR`) are mapped explicitly to the shared `CloudAgentStatus`, and `baseUrl` is overridable per-credential. Credentials are stored encrypted via the existing `cloud_agent_credentials` table; no schema change. ([#4227](https://github.com/diegosouzapw/OmniRoute/issues/4227) — thanks @MRDGH2821)
-- **feat(routing): OpenRouter-style `auto/<category>:<tier>` combos** — auto-routing now understands suffixed combos that separate the _category_ (what kind of route) from the _tier_ (how to optimize): `auto/coding:fast`, `auto/coding:cheap` (alias `:floor`), `auto/coding:free`, `auto/coding:pro`, `auto/coding:reliable`, plus the new category roots `auto/reasoning`, `auto/vision`, `auto/multimodal`. The **tier** picks the scoring weights — `:fast` → ship-fast, `:cheap`/`:floor` → cost-saver, `:reliable` → a new reliability-first pack (circuit-breaker health + latency stability) — while `:free`/`:pro` filter the candidate pool by model tier (`classifyTier`: free-tier vs. premium models). The **category** filters the pool by capability (`vision`/`multimodal` → vision-capable models, `reasoning` → reasoning/thinking models). Any valid `auto/<category>:<tier>` resolves on demand; a curated set is advertised in `/v1/models` and the dashboard. Filtering is fail-open — if a constraint matches no connected models the full pool is used so routing never breaks. All composition lives in the new `open-sse/services/autoCombo/suffixComposition.ts`; the core combo scorer (`combo.ts`) is untouched. Second slice of #4235 (premium account-tier weighting is a later follow-up). ([#4235](https://github.com/diegosouzapw/OmniRoute/issues/4235) — thanks @MRDGH2821)
-- **feat(routing): advertise the `auto/cheap`, `auto/offline`, `auto/smart` combos (catalog ↔ README sync)** — the README lists `auto/cheap` (cheapest-per-token first), `auto/offline` (most quota/rate-limit headroom first) and `auto/smart` (quality-first + 10% exploration), and they already resolved at request time via `parseAutoPrefix` → `createVirtualAutoCombo`. But they were missing from `AUTO_TEMPLATE_VARIANTS`, so `/v1/models` and the dashboard combos list (which iterate that catalog) never showed them — the catalog drifted from the docs (visible in the issue's screenshots). Added the three entries so they're advertised everywhere alongside the other built-in `auto/*` combos. First slice of #4235 (OpenRouter-style `auto/<category>:<tier>` suffixes + new categories follow). ([#4235](https://github.com/diegosouzapw/OmniRoute/issues/4235) — thanks @MRDGH2821)
-- **feat(cli): remote mode — drive a remote OmniRoute with scoped access tokens** — a new CLI mode that connects to a remote OmniRoute instance using scoped access tokens, so a local CLI can drive a server you don't own a session on. ([#4256](https://github.com/diegosouzapw/OmniRoute/pull/4256))
-- **feat(api): cost-telemetry parity — `X-OmniRoute-*` headers on every endpoint + a non-token cost engine** — every endpoint now emits the `X-OmniRoute-*` cost/usage headers, backed by a cost engine that also prices non-token (media/request-based) usage. ([#4247](https://github.com/diegosouzapw/OmniRoute/pull/4247))
-- **feat(api): register Kimi K2.7 Code models (`kimi-k2.7-code` + `-highspeed`)** — the new Moonshot thinking-only coding models are registered (fixed sampling; `temperature`/`top_p` marked unsupported). ([#4183](https://github.com/diegosouzapw/OmniRoute/pull/4183))
-- **feat(catalog): add `kimi-k2.7-code` to the kmca catalog + qwen-web models discovery** — surfaces the new Kimi coding model in the kmca catalog and wires qwen-web into model discovery. ([#4185](https://github.com/diegosouzapw/OmniRoute/pull/4185))
-- **feat(api): expand the `zai` provider catalog with GLM-5.2 / GLM-4.7** — adds the real GLM-5.2, GLM-4.7 and GLM-4.7-flash model ids to the Anthropic-direct `zai` provider. ([#4201](https://github.com/diegosouzapw/OmniRoute/pull/4201))
-- **feat(api): no-thinking gateway model IDs (FCC port, Fase 8.1)** — gateway model id variants that force thinking off, ported from free-claude-code. ([#4145](https://github.com/diegosouzapw/OmniRoute/pull/4145))
-- **feat(sse): mid-stream continuation for truncated streams (FCC port, Task 4.4)** — when a stream is cut short, OmniRoute can transparently continue it, ported from free-claude-code. ([#4147](https://github.com/diegosouzapw/OmniRoute/pull/4147))
-- **feat(sse): per-provider sliding-window rate-limit fallback (FCC port, Fase 8.2)** — a per-provider sliding-window rate limiter as a fallback path, ported from free-claude-code. ([#4146](https://github.com/diegosouzapw/OmniRoute/pull/4146))
-- **feat(sse): transparent stream recovery (FCC port, Fase 4, opt-in)** — opt-in transparent recovery of interrupted upstream streams, ported from free-claude-code. ([#4131](https://github.com/diegosouzapw/OmniRoute/pull/4131))
-- **feat(search): free DuckDuckGo web search as a last-resort provider (FCC port, Fase 6)** — adds a no-key DuckDuckGo web-search provider used as a last resort, ported from free-claude-code. ([#4136](https://github.com/diegosouzapw/OmniRoute/pull/4136))
-- **feat(logging): credential-redaction safety net in the pino logger (FCC port, Fase 8.3)** — a logger-level redaction pass that scrubs credentials from log output, ported from free-claude-code. ([#4140](https://github.com/diegosouzapw/OmniRoute/pull/4140))
-- **feat(memory): opt-in Qdrant scalar int8 quantization (F4.4 Q1)** — opt-in int8 scalar quantization for Qdrant-backed memory vectors. ([#4187](https://github.com/diegosouzapw/OmniRoute/pull/4187))
-- **feat(memory): opt-in sqlite-vec int8 vector quantization (F4.4 Q2)** — opt-in int8 quantization for the sqlite-vec memory backend. ([#4190](https://github.com/diegosouzapw/OmniRoute/pull/4190))
-- **feat(deploy): keep optional deps on `update` (`--include=optional`)** — the in-place update path now passes `--include=optional` so native/optional packages aren't dropped on update. ([#4260](https://github.com/diegosouzapw/OmniRoute/pull/4260))
-- **feat(dashboard): unified visual identity — grid, primitives, tables, form controls (design phases 1-4)** — a sweeping design pass aligning the dashboard with the site: grid wallpaper, button/card/input primitives, theme-aware tables and form controls. ([#4122](https://github.com/diegosouzapw/OmniRoute/pull/4122))
-- **feat(dashboard): grid wallpaper on all standalone screens + fluid 4K layout** — the identity grid now backs every standalone screen and the layout scales fluidly to 4K. ([#4158](https://github.com/diegosouzapw/OmniRoute/pull/4158))
-- **feat(dashboard): make the identity grid visible + unify the focus ring on accent** — design follow-up making the grid actually visible and standardizing focus rings on the accent color. ([#4141](https://github.com/diegosouzapw/OmniRoute/pull/4141))
-- **feat(dashboard): import only free models + free-model list controls** — the model-import page can import just the free models, with controls to manage the free-model list. ([#4176](https://github.com/diegosouzapw/OmniRoute/pull/4176) — thanks @felipesartori)
-- **feat(dashboard): compact grid layout for no-auth provider accounts** — a denser grid layout for provider accounts when auth is disabled. ([#4137](https://github.com/diegosouzapw/OmniRoute/pull/4137) — thanks @felipesartori)
-- **feat(dashboard): derive media `serviceKinds` from the registries (surface MiniMax + the media catalog)** — `/media-providers/[kind]` now derives its service kinds from the registries instead of a hand-maintained list, surfacing ~48 previously-invisible media providers (incl. MiniMax TTS/video/music). ([#4212](https://github.com/diegosouzapw/OmniRoute/pull/4212))
-- **feat(traffic-inspector): live (in-flight) request filter (Gap 5)** — the Traffic Inspector can filter to in-flight requests as they happen. ([#4130](https://github.com/diegosouzapw/OmniRoute/pull/4130))
-- **feat(agent-bridge): maintenance & diagnostics dashboard controls** — adds maintenance and diagnostics controls for the Agent Bridge to the dashboard. ([#4127](https://github.com/diegosouzapw/OmniRoute/pull/4127))
-- **feat(mitm): TPROXY IP_TRANSPARENT native addon + conditional loader (Epic A)** — a native `IP_TRANSPARENT` addon with a conditional loader, the foundation for TPROXY capture. ([#4148](https://github.com/diegosouzapw/OmniRoute/pull/4148))
-- **feat(mitm): Fase 3 Epic A spike — TPROXY command builder** — a transactional builder for the iptables/TPROXY command set. ([#4139](https://github.com/diegosouzapw/OmniRoute/pull/4139))
-- **feat(mitm): TPROXY setup layer — transactional apply/revert (Epic A)** — applies and reverts the TPROXY routing setup transactionally. ([#4144](https://github.com/diegosouzapw/OmniRoute/pull/4144))
-- **feat(mitm): add `setSocketMark` to the TPROXY addon (anti-loop primitive)** — exposes `setSocketMark` so OmniRoute's own egress can be marked and skipped (anti-loop). ([#4160](https://github.com/diegosouzapw/OmniRoute/pull/4160))
-- **feat(mitm): TPROXY capture-mode listener + `connectMarked` (Epic A)** — the capture-mode listener plus a marked-connect primitive. ([#4169](https://github.com/diegosouzapw/OmniRoute/pull/4169))
-- **feat(mitm): dynamic per-SNI cert authority for TPROXY (TLS decrypt 1/N)** — a per-SNI on-the-fly certificate authority, the first slice of TLS decrypt. ([#4173](https://github.com/diegosouzapw/OmniRoute/pull/4173))
-- **feat(mitm): TLS-terminating capture for TPROXY (decrypt 2/N)** — terminates TLS to capture decrypted traffic. ([#4179](https://github.com/diegosouzapw/OmniRoute/pull/4179))
-- **feat(mitm): wire the TLS decrypt engine into TPROXY capture mode (decrypt 3/N)** — connects the decrypt engine to the capture-mode pipeline. ([#4200](https://github.com/diegosouzapw/OmniRoute/pull/4200))
-- **feat(mitm): TPROXY capture-mode manager (decrypt 4a/N)** — a manager coordinating the TPROXY capture lifecycle. ([#4208](https://github.com/diegosouzapw/OmniRoute/pull/4208))
-- **feat(mitm): local-only route + trust-store installer for TPROXY decrypt (4b/N)** — a loopback-only management route plus a CA trust-store installer for the decrypt CA. ([#4211](https://github.com/diegosouzapw/OmniRoute/pull/4211))
-- **feat(dashboard): TPROXY decrypt capture toggle in the Traffic Inspector (4c/N)** — a UI toggle to enable/disable decrypted capture. ([#4216](https://github.com/diegosouzapw/OmniRoute/pull/4216))
-- **feat(compression): replace the headroom tabular encoder with a vendored GCF** — swaps the tabular encoder for a vendored GCF implementation. ([#4167](https://github.com/diegosouzapw/OmniRoute/pull/4167) — thanks @blackwell-systems)
-- **feat(compression): live per-engine streaming via `compression.step` (F3.3)** — streams per-engine compression progress through a `compression.step` event. ([#4217](https://github.com/diegosouzapw/OmniRoute/pull/4217))
-- **feat(compression): show an engine node for single-engine runs in the studio** — the Compression Studio now renders an engine node even when only one engine runs. ([#4210](https://github.com/diegosouzapw/OmniRoute/pull/4210))
-- **feat(compression): expose the WaterfallInspector via a Canvas/Waterfall toggle** — adds a Canvas/Waterfall view toggle that surfaces the WaterfallInspector. ([#4238](https://github.com/diegosouzapw/OmniRoute/pull/4238))
-- **feat(compression): make `mcpAccessibility` config reachable via a settings sub-route** — exposes the `mcpAccessibility` config under a dedicated settings sub-route. ([#4237](https://github.com/diegosouzapw/OmniRoute/pull/4237))
-- **feat(compression): runnable A/B benchmark CLI (F2.4)** — a CLI to run A/B compression benchmarks. ([#4220](https://github.com/diegosouzapw/OmniRoute/pull/4220))
-- **feat(compression): add a transcript loader to the replay harness** — the replay harness can now load real transcripts. ([#4246](https://github.com/diegosouzapw/OmniRoute/pull/4246))
-- **feat(compression): wire MCP tool-cardinality reduction (F4.3, opt-in)** — opt-in reduction of MCP tool-set cardinality to shrink prompts. ([#4221](https://github.com/diegosouzapw/OmniRoute/pull/4221))
-- **feat(compression): wire RTK comment-stripping config + honor `preserveDocstrings`** — RTK comment-stripping is now configurable and honors a `preserveDocstrings` flag. ([#4242](https://github.com/diegosouzapw/OmniRoute/pull/4242))
-- **feat(compression): honor the per-filter RTK `deduplicate` flag** — RTK filters now respect a per-filter `deduplicate` flag. ([#4231](https://github.com/diegosouzapw/OmniRoute/pull/4231))
-- **feat(compression): honor the registry `enabled` flag in the stacked loop** — the stacked compression loop now skips engines disabled in the registry. ([#4244](https://github.com/diegosouzapw/OmniRoute/pull/4244))
-- **feat(compression): persist RTK grouping config (unlock R5 `enableGrouping`)** — persists the RTK grouping configuration, unlocking the R5 `enableGrouping` rule. ([#4207](https://github.com/diegosouzapw/OmniRoute/pull/4207))
-- **feat(compression): wire ultra's `modelPath`/`slmFallbackToAggressive` to the LLMLingua SLM tier** — connects the ultra tier's small-language-model knobs to the LLMLingua SLM path. ([#4257](https://github.com/diegosouzapw/OmniRoute/pull/4257))
-- **feat(quality): Onda 2 mutation-gate tooling — radiography classifier (T1) + `mutationScore` ratchet (T3)** — new mutation-testing tooling: a survivor-radiography classifier and a `mutationScore` ratchet. ([#4234](https://github.com/diegosouzapw/OmniRoute/pull/4234))
-- **feat(ci): wire the F2.4 compression budget-gate ratchet** — adds a CI ratchet that gates compression budget regressions. ([#4232](https://github.com/diegosouzapw/OmniRoute/pull/4232))
-
-### 🐛 Fixed
-
-- **fix(providers): qwen-web model discovery now lists the live catalog instead of nothing** — the `qwen-web` cookie provider had no entry in `PROVIDER_MODELS_CONFIG`, so its model-discovery page returned an empty/stale local catalog (the OAuth fallback at the top of the route only fires for `provider === "qwen"`, leaving `qwen-web` to fall through to the no-config branch). Added a `qwen-web` entry that fetches the **public** `https://chat.qwen.ai/api/v2/models` endpoint (no auth header) and parses the `{ data: { data: [{ id, name, owned_by }] } }` shape (with a flatter `{ data: [] }` fallback). This is Problem #3 of #3931 (diagnosed by @thezukiru); Problem #1 — validator bare-token false-positive — shipped earlier in #3958, and Problem #2 — empty stream from Qwen WAF bot-detection on the streaming endpoint — remains a separate upstream/stealth concern. ([#3931](https://github.com/diegosouzapw/OmniRoute/issues/3931) — thanks @thezukiru)
-- **fix(providers): ZenMux model discovery now lists the live catalog (incl. the free models) instead of the stale 9-entry hardcoded list** — adding a ZenMux key validated fine, but the connection then showed `API unavailable — using local catalog` and was missing the free models ZenMux advertises (`z-ai/glm-5.2-free`, `moonshotai/kimi-k2.7-code-free`). Root cause: `zenmux` carries a correct `modelsUrl` in the registry, but — like `llm7`/`byteplus` before #3976 — it was not classified by any live-fetch branch of the model-import route (not `openai-compatible-*`, not self-hosted, not in `NAMED_OPENAI_STYLE_PROVIDERS`), so the route never probed the upstream `/models` and fell through to the registry's hardcoded `models[]`. Added `zenmux` to `NAMED_OPENAI_STYLE_PROVIDERS`, so the route probes `https://zenmux.ai/api/v1/models` (the `/chat/completions`-stripped `<baseUrl>/models` candidate) and serves the live list, falling back to the local catalog only when the upstream fetch fails — import never breaks. ([#4202](https://github.com/diegosouzapw/OmniRoute/issues/4202) — thanks @mikmaneggahommie)
-- **fix(providers): Vercel AI Gateway "import models" now loads the live catalog instead of nothing** — adding a Vercel AI Gateway key worked, but clicking **import** on the models page loaded nothing usable (manually adding the same models worked). Same class as #4202 (zenmux) / #3976 (llm7/byteplus): `vercel-ai-gateway` carries a real `baseUrl` (`https://ai-gateway.vercel.sh/v1/chat/completions`, format `openai`) in the registry, but was not classified by any live-fetch branch of the model-import route (not `openai-compatible-*`, not self-hosted, not in `NAMED_OPENAI_STYLE_PROVIDERS`), so the route never probed the upstream `/models` and fell through to the registry's tiny 5-entry hardcoded `models[]`. Added `vercel-ai-gateway` to `NAMED_OPENAI_STYLE_PROVIDERS`, so the route probes `https://ai-gateway.vercel.sh/v1/models` (the `/chat/completions`-stripped `<baseUrl>/models` candidate) and serves the live list, falling back to the local catalog only when the upstream fetch fails — import never breaks. ([#4249](https://github.com/diegosouzapw/OmniRoute/issues/4249) — thanks @FerLuisxd)
-- **fix(sse): clear error when the request queue drops a job (no more fake-upstream "This job timed out after Nms")** — under concurrent load, requests that exceed the per-connection rate-limit queue budget (`resilienceSettings.requestQueue.maxWaitMs`) were dropped by Bottleneck with its raw `This job timed out after <maxWaitMs> ms.` message. That string is indistinguishable from an upstream gateway timeout, so the 502 body and call-log `last_error` looked like a provider outage across unrelated providers (TI:0\|TO:0) — an operator spent ~3h misdiagnosing local queue saturation as upstream failures. `withRateLimit` now rewrites that specific Bottleneck error into a clear, OmniRoute-owned message that names the knob (`requestQueue.maxWaitMs`, tunable in Settings → Resilience), explicitly disclaims an upstream timeout, preserves the original as `cause`, and tags `code: "RATE_LIMIT_QUEUE_TIMEOUT"`. Behavior is unchanged — the job is still dropped so combo falls back to the next target. ([#4165](https://github.com/diegosouzapw/OmniRoute/issues/4165) — thanks @KooshaPari)
-- **fix(api): advertise the built-in `auto/*` combos in `/v1/models`** — OmniRoute ships a zero-setup `auto/*` catalog (`auto/best-coding`, `auto/pro-reasoning`, …, 16 variants) that the dashboard advertises and that resolve on demand, but the `/v1/models` listing only emitted persisted DB combos + provider models. Clients that build their model picker from `/v1/models` (e.g. Hermes Agent) never saw any `auto/*` option. The catalog now emits every `AUTO_TEMPLATE_VARIANTS` id (as `owned_by: "combo"`) at the top of the list, deduped against persisted combos. (Showing each `auto/*`'s dynamically-selected members is a separate enhancement.) ([#4164](https://github.com/diegosouzapw/OmniRoute/issues/4164) — thanks @MRDGH2821)
-- **fix(sse): restore MCP / third-party tool names on the native Claude path (MCP dispatch broken in Claude Code)** — since 3.8.27, every MCP tool call routed through OmniRoute to a native Claude OAuth provider failed client-side with `Error: No such tool available: <PascalCaseName>`: tool schemas arrived fine but the streamed `tool_use.name` reached Claude Code in its cloaked form (e.g. `McpN8nMcpSearchWorkflows` instead of the registered `mcp__n8n-mcp__search_workflows`). The native-Claude tool-name cloak stashes its per-request alias→original map as a **non-enumerable** `_toolNameMap` on the request body; the request-inspector capture added in 3.8.27 rebuilds the captured body from its serialized form (`JSON.parse(JSON.stringify(...))`), which drops non-enumerable properties, so `finalBody._toolNameMap` was empty and the response-side un-cloak silently fell back to the static built-in map — never restoring dynamic MCP / snake_case names. Built-in tools (Bash/Read/…) were unaffected (static map); cross-format paths were unaffected (they attach the map enumerably). The provider-request capture now re-attaches the per-request map (kept non-enumerable, so it still never re-serializes upstream) when the captured copy lost it, restoring MCP tool dispatch. ([#4091](https://github.com/diegosouzapw/OmniRoute/issues/4091) — thanks @pedrotecinf, @NakHalal)
-- **fix(dashboard): Logs auto-refresh self-heals in embedded/proxied hosts that pin or mis-fire visibility** — a follow-up to #4054: the Request Logger still froze auto-refresh on some hosts (reported on 3.8.28 Docker, works on 3.8.24). #4054 made the initial visibility fail-open, but the pause is event-driven — a host that fires a one-shot `visibilitychange` → hidden and then keeps reporting `"hidden"` (or recovers without firing the event again) left the cached visibility flag stuck `false`, so the interval ticked but never polled (only the manual Refresh button worked). The poll tick now also re-checks the **live** `document.visibilityState`, and a **window `focus`** listener re-arms polling (a focused window is a reliable signal the page is actively viewed). A genuinely backgrounded browser tab still pauses (it reports `"hidden"` and never receives focus), preserving the #3109 network-saturation optimization. ([#4133](https://github.com/diegosouzapw/OmniRoute/issues/4133) — thanks @tjengbudi)
-- **fix(capabilities): unify vision model-id detection into one shared source** — three code paths kept independent, drifting vision-model lists, so the same model id could get up to three different verdicts. Two concrete bugs: lite compression's gate was missing pixtral / llava / qwen-vl / glm-4v / kimi-vl / mistral-medium-3, so it **stripped images for those real vision models and blinded them** (same class as #4071 / #4012); and the `/v1/models` list was too broad, flagging text models (`gemma`, bare `kimi` like `kimi-k2`) as vision. All three (`modelCapabilities` routing fallback, `/v1/models` listing, lite image-strip gate) now delegate to a single conservative source `src/shared/constants/visionModels.ts`, which also restores `glm-4v` / `gemini-3` coverage and keeps the #3328 MiniMax M3 carve-out. ([#4072](https://github.com/diegosouzapw/OmniRoute/issues/4072) — thanks @diego-anselmo)
-- **fix(sse): surface mid-stream Gemini errors instead of returning a truncated 200** — when an upstream Gemini SSE stream emitted some partial content and then a JSON error object (`{"error":{"code":503,"message":"…high demand…","status":"UNAVAILABLE"}}`) instead of a `candidates` payload, OmniRoute silently dropped it: the gemini→openai translator's no-candidate branch only handled `promptFeedback` (content-filter) and returned `null` for anything else, so the stream simply ended and the client got HTTP 200 with a truncated body and `finish_reason: "stop"` — masking the failure and skipping combo fallback. `geminiToOpenAIResponse` now detects an `error` object (optionally wrapped in `response`), records it as `state.upstreamError` (preserving the real status — 503/`UNAVAILABLE`, or 429 for `RESOURCE_EXHAUSTED`), and lets `stream.ts` error the stream out through the existing `onFailure`/`buildErrorBody`/`controller.error` path — the same mechanism the openai-responses translator already uses. ([#4177](https://github.com/diegosouzapw/OmniRoute/issues/4177) — thanks @hartmark)
-- **fix(capabilities): resolve models.dev-synced vision metadata for Mistral `-latest` aliases** — root cause behind the #4071 heuristic: `getResolvedModelCapabilities("mistral/pixtral-12b-latest").supportsVision` resolved `null` (vision came only from the #4071 model-id heuristic, with `attachment` still `null`) even though models.dev exposes the model as multimodal. Confirmed against the live models.dev API: it catalogs Pixtral 12B under the **short** id `pixtral-12b` (with `attachment: true`, `modalities.input: ["text","image"]`), while requests use the Mistral API alias `pixtral-12b-latest`. The synced lookup tried the exact / raw / static-spec-canonical ids — all of which miss the short form — so it fell through to the heuristic. `getSyncedCapabilityForResolved` now adds a last-resort fallback that retries with a trailing `-latest` stripped, so synced metadata (`attachment` / image modalities) wins for these aliases; models whose `-latest` id is stored verbatim (e.g. `pixtral-large-latest`) keep resolving directly. Note: the models.dev sync is currently manual-only (Settings → models.dev) with no scheduled refresh, so a fresh instance still relies on the #4071 heuristic until that sync runs — a periodic-refresh cadence is left as a separate follow-up. ([#4073](https://github.com/diegosouzapw/OmniRoute/issues/4073) — thanks @diego-anselmo)
-- **fix(sse): map Xiaomi MiMo reasoning control to its native `thinking:{type}` shape** — MiMo (`api.xiaomimimo.com`) controls chain-of-thought **only** via top-level `thinking:{type:"enabled"|"disabled"}` and does not understand OpenAI's `reasoning_effort`/`reasoning`, while its request validator is strict (`400 Param Incorrect`). OmniRoute's OpenAI path carried reasoning intent as `reasoning_effort`, and the claude→openai translator can leave a Claude-shaped `thinking:{type, budget_tokens}` — so the client's on/off choice was silently dropped and `budget_tokens`/`reasoning_effort` rode along as extra params the validator can reject. New `open-sse/services/mimoThinking.ts::normalizeMimoThinking` (wired in `chatCore` for `provider==="xiaomi-mimo"`) reduces any thinking object to just `{type}` (`disabled` stays; `enabled`/`adaptive`/other → `enabled`) and drops `reasoning_effort`/`reasoning`. It deliberately does **not** synthesize thinking from a bare `reasoning_effort` — `mimo-v2-omni` is non-thinking, so that could turn a silently-ignored param into a hard error. ([#4224](https://github.com/diegosouzapw/OmniRoute/pull/4224))
-- **fix(capabilities): Xiaomi MiMo `*-pro` chat models are text-only (no vision)** — only `mimo-v2.5` and `mimo-v2-omni` accept images per Xiaomi's docs; `mimo-v2.5-pro`/`mimo-v2-pro` are text-only, but `modelSpecs` marked them vision-capable and models.dev mislabels them ([hermes-agent#18884](https://github.com/NousResearch/hermes-agent/issues/18884)). Since `resolveVisionCapability` lets a synced `attachment:true` win first, an image request could be routed to a blind model (the #4071 failure mode). Corrected the specs **and** added a hard override in `resolveVisionCapability` (checked before the synced branch, anchored so `mimo-v2.5-pro` never matches the multimodal `mimo-v2.5`) that beats the wrong synced attachment. Also registered the missing native `mimo-v2-pro` chat model and the missing `mimo-v2-tts` speech model. ([#4224](https://github.com/diegosouzapw/OmniRoute/pull/4224))
-- **fix(sse): Claude Opus 4.7+/Fable 5 use adaptive thinking only (no more manual-budget 400s)** — Opus 4.7 and later (Opus 4.7/4.8, Fable 5) removed manual extended thinking: `thinking.type:"enabled"` or **any** `thinking.budget_tokens` now returns `400` ("Any request that tries to set a fixed thinking budget gets a 400" — Anthropic migration guide). Reasoning is adaptive-only, steered by `output_config.effort`. OmniRoute's OpenAI→Claude translator mapped `reasoning_effort` low/medium/high to a manual `thinking:{type:"enabled", budget_tokens}`, so those requests hard-400'd on the most-used provider (and a Claude-native passthrough client sending the legacy shape did too). A new `adaptiveThinkingOnly` model flag now drives two fixes: the translator maps `reasoning_effort` of **every** level to `{type:"adaptive"}` + `output_config.effort` (preserving the requested level, never a budget) for these models, and a `normalizeClaudeAdaptiveThinking` catch-all at the existing post-translation thinking-normalization chokepoint collapses any residual manual thinking (passthrough legacy shape, per-model defaults) to `{type:"adaptive"}`, keyed on the resolved upstream model so it covers every routing mode. Pre-4.7 models (Opus 4.6/4.5, Sonnet, Haiku) keep manual budgets unchanged. ([#4230](https://github.com/diegosouzapw/OmniRoute/pull/4230))
-- **fix(providers): strip non-default temperature/top_p/top_k for Claude Opus 4.7+/Fable 5 (fixed sampling → no 400)** — Opus 4.7 and later reject non-default `temperature`/`top_p`/`top_k` with a `400` (sampling is fixed; reasoning moved to `output_config.effort`). The translator forwarded client-supplied `temperature`/`top_p` unconditionally and the Claude registry models carried no `unsupportedParams`, so a plain OpenAI-format request with `temperature: 0.7` to `claude-opus-4-8` hard-400'd. Added `unsupportedParams: ["temperature","top_p","top_k"]` to the Opus 4.7+/Fable 5 ids in both the `claude` (dashed `claude-opus-4-8`) and `anthropic` (dotted `claude-opus-4.7`) registries, so they're stripped at the existing `getUnsupportedParams` dispatch chokepoint. Pre-4.7 Claude models still accept sampling params. ([#4230](https://github.com/diegosouzapw/OmniRoute/pull/4230))
-- **fix(providers): conditionally strip temperature/top_p for GPT-5 reasoning on the `openai` Chat Completions path (no 400 when an effort is active)** — GPT-5 reasoning models reject non-default `temperature`/`top_p` with a `400` whenever a reasoning effort is active, yet accept them again under `reasoning_effort:"none"` (the GPT-5.1+ default, i.e. non-reasoning mode). On the `openai` provider only `o3` carried `REASONING_UNSUPPORTED`; `gpt-5.5`/`gpt-5.4`/`gpt-5.4-mini`/`gpt-5.4-nano` carried no sampling guard, so a `temperature` + active-effort request hard-400'd. A static `unsupportedParams` list can't express the `none`-mode carve-out (it would over-strip the legitimate case), so the new `gpt5SamplingGuard` drops `temperature`/`top_p` only when the resolved effort is active — wired at the existing `getUnsupportedParams` chokepoint and scoped to the `openai` Chat Completions surface (the `codex` Responses path is already covered by the CodexExecutor allowlist; other providers are untouched). ([#4245](https://github.com/diegosouzapw/OmniRoute/pull/4245))
-- **fix(codex): stop silently dropping GPT-5 output verbosity (`verbosity` / `text.verbosity`)** — the GPT-5 series added an output-verbosity control: `verbosity` (low/medium/high) on Chat Completions, nested as `text.verbosity` on the Responses API. The CodexExecutor gates translated requests through an allowlist that had no `text` entry, so for the `codex` provider the hint was dropped before reaching upstream (the `openai` Chat path already forwarded it). `normalizeCodexVerbosity` now folds whichever shape arrived into a single validated `text:{verbosity}` before the allowlist (which now permits `text`), and the OpenAI Chat↔Responses request translators map `verbosity` across formats so the hint survives a format crossing for non-codex Responses backends too. Invalid/absent verbosity collapses to no `text` (status quo). ([#4245](https://github.com/diegosouzapw/OmniRoute/pull/4245))
-- **fix(sse): map `reasoning_effort` to DeepSeek V4's native `{high, max}` vocabulary** — DeepSeek V4 only understands `high`/`max` reasoning levels, so other `reasoning_effort` values are mapped onto its native vocabulary instead of being rejected. ([#4219](https://github.com/diegosouzapw/OmniRoute/pull/4219))
-- **fix(glm): default `max_tokens` and an extended timeout for GLM-5.2+ thinking** — GLM-5.2+ thinking responses are slow and need headroom, so OmniRoute now sets a sensible default `max_tokens` and a longer timeout for them. ([#4255](https://github.com/diegosouzapw/OmniRoute/pull/4255) — thanks @dhaern)
-- **fix(antigravity): default `includeThoughts` for modern Gemini models** — modern Gemini models on the Antigravity path now default to including thoughts so reasoning isn't silently dropped. ([#4180](https://github.com/diegosouzapw/OmniRoute/pull/4180) — thanks @dhaern)
-- **fix(provider-registry): add correct `contextLength` to theoldllm models** — fills in accurate context-window sizes for theoldllm's models. ([#4184](https://github.com/diegosouzapw/OmniRoute/pull/4184) — thanks @herjarsa)
-- **fix(models): expose combo model token limits** — `/v1/models` now reports token limits for combo models. ([#4189](https://github.com/diegosouzapw/OmniRoute/pull/4189) — thanks @megamen32)
-- **fix(combo): keep the passthrough quota fallback scoped** — prevents the passthrough quota fallback from leaking across unrelated targets. ([#4194](https://github.com/diegosouzapw/OmniRoute/pull/4194) — thanks @Svetznaniy33)
-- **fix(combo): opt proactive-fallback compression into the TV1 bail-out (no silent target drop)** — proactive-fallback compression now participates in the TV1 bail-out so a target is never silently dropped. ([#4228](https://github.com/diegosouzapw/OmniRoute/pull/4228))
-- **fix(compression): show engine preview output** — the Compression Studio preview now renders the engine's output. ([#4128](https://github.com/diegosouzapw/OmniRoute/pull/4128) — thanks @megamen32)
-- **fix(compression): harden engines against I/O failures and misconfig (F5.3)** — compression engines degrade gracefully on I/O errors and bad configuration instead of throwing. ([#4198](https://github.com/diegosouzapw/OmniRoute/pull/4198))
-- **fix(compression): harden RTK raw-output redaction + ReDoS guard for custom filters (F5.3)** — broadens RTK raw-output redaction and adds a ReDoS guard for user-supplied filter patterns. ([#4203](https://github.com/diegosouzapw/OmniRoute/pull/4203))
-- **fix(compression): bound `mcpAccessibility` `maxTextChars` on the live read path** — the live read path now clamps `maxTextChars` so a small value can't make tools disappear. ([#4206](https://github.com/diegosouzapw/OmniRoute/pull/4206))
-- **fix(dashboard): data tables paint an opaque surface so the grid doesn't bleed through** — data tables now render on an opaque surface, fixing the grid wallpaper showing through. ([#4233](https://github.com/diegosouzapw/OmniRoute/pull/4233))
-- **fix(dashboard): make the provider card hover visible (was ~1% opacity)** — the provider-card hover state was effectively invisible; it now has a visible surface. ([#4214](https://github.com/diegosouzapw/OmniRoute/pull/4214))
-- **fix(vscode): sanitize implicit editor context** — redacts sensitive filenames/keywords from the implicit VS Code editor context before it's sent upstream. ([#4124](https://github.com/diegosouzapw/OmniRoute/pull/4124) — thanks @zhiru)
-- **fix(build): raise the Node heap for the local `next build` to stop OOM/stall** — bumps the build-time heap so the local production build no longer OOMs or stalls. ([#4171](https://github.com/diegosouzapw/OmniRoute/pull/4171))
-- **fix(mitm): TPROXY OUTPUT-based recipe for local traffic (validated e2e on VPS)** — switches the TPROXY rules to an OUTPUT-chain recipe so locally-originated traffic is captured; validated end-to-end on the VPS. ([#4156](https://github.com/diegosouzapw/OmniRoute/pull/4156))
-- **fix(mitm): forward anti-loop — put the bypass-marked socket on the Agent (decrypt 4d)** — places the bypass-marked socket on the HTTP Agent so OmniRoute's own forwarded traffic never re-enters the capture loop; VPS-validated. ([#4229](https://github.com/diegosouzapw/OmniRoute/pull/4229))
-- **fix(free-tiers): retire dead-tier `hasFree`, round the headline to ~1.6B, regenerate the per-provider table** — drops dead free tiers from the headline math and regenerates the per-provider free-tier table. ([#4142](https://github.com/diegosouzapw/OmniRoute/pull/4142))
-- **fix(free-tiers): retire 4 re-verified-dead free tiers, flag iflytek/sparkdesk ToS, clarify monsterapi one-time** — removes four confirmed-dead free tiers and annotates ToS/one-time caveats. ([#4152](https://github.com/diegosouzapw/OmniRoute/pull/4152))
-
-### 🧪 Tests
-
-- **test(sse): guard the Antigravity `_toolNameMap` cloak map through the request-capture round-trip** — follow-up to #4091: the generic capture fix in `createPreparedRequestLogger().body()` (#4153) re-attaches the non-enumerable `_toolNameMap` that the request-inspector drops when it rebuilds the upstream body via `JSON.parse(JSON.stringify(...))`, but the only regression test covered the native-Claude OAuth cloak (PascalCase aliases). The Antigravity cloak differs — `cloakAntigravityToolPayload` suffixes custom tools with `_ide` (`workspace_read` → `workspace_read_ide`), leaves native tools untouched, and returns the reverse map separately — so a refactor of `providerRequestLogging.ts` or the executor could silently re-break Antigravity tool dispatch without tripping the Claude test. Adds a dedicated regression test driving the real `cloakAntigravityToolPayload` through the capture round-trip and asserting the `_ide` reverse map survives, stays non-enumerable (never re-serializes upstream), and that all-native traffic produces no spurious map (verified failing with the #4153 re-attach removed). No production change. ([#4181](https://github.com/diegosouzapw/OmniRoute/issues/4181) — thanks @hertznsk)
-- **test(chatcore): dedicated unit tests for 6 leaves + wire into stryker mutate (QG v2 Fase 9 T5 Fase 3)** — adds focused unit tests for 6 chatCore leaf helpers and enrolls them in mutation testing. ([#4218](https://github.com/diegosouzapw/OmniRoute/pull/4218))
-- **test(chatcore): telemetry / memory-skills / semantic-cache tests + wire 2 into stryker (QG v2 Fase 9 T5 Fase 3)** — new tests for the telemetry, memory-skills and semantic-cache leaves, two of which are added to the mutation set. ([#4222](https://github.com/diegosouzapw/OmniRoute/pull/4222))
-- **test+ci(chatcore): semanticCache HIT-path fixture (15/15 mutate) + 350min budget headroom** — closes the semantic-cache HIT path to a full 15/15 mutation score and gives the nightly auth/accountFallback batches more budget headroom. ([#4225](https://github.com/diegosouzapw/OmniRoute/pull/4225))
-- **test(compression): close F5.1 coverage gaps (replay reducer, live accumulator, StatusDot)** — fills the remaining F5.1 compression coverage gaps. ([#4192](https://github.com/diegosouzapw/OmniRoute/pull/4192))
-- **test(db,sse): de-flake db-backup + chatcore streaming timing assertions** — stabilizes two timing-sensitive tests (fire-and-forget backup completion + a streaming race). ([#4132](https://github.com/diegosouzapw/OmniRoute/pull/4132))
-- **test: align stale integration tests surfaced post-v3.8.28 on main** — realigns integration tests that drifted after the v3.8.28 merge. ([#4129](https://github.com/diegosouzapw/OmniRoute/pull/4129))
-
-### 📝 Maintenance
-
-- **refactor(sse): split chatCore.ts pure helpers into chatCore/ modules (−561 LOC)** — extracts pure helpers out of the chatCore god-file into dedicated modules (Onda 3). ([#4159](https://github.com/diegosouzapw/OmniRoute/pull/4159))
-- **refactor(chatcore): extract passthrough/header/telemetry helpers (QG v2 Fase 9 T5 C2-C3-C5)** — further chatCore decomposition. ([#4188](https://github.com/diegosouzapw/OmniRoute/pull/4188))
-- **refactor(chatcore): extract combo/proxy context cache + semaphore helpers (QG v2 Fase 9 T5 C6-C7)** — continues the chatCore split. ([#4193](https://github.com/diegosouzapw/OmniRoute/pull/4193))
-- **refactor(combo): god-file split pilot — types + validateQuality + predicates (QG v2 Fase 9 T5 D1-D3)** — first slice of the combo.ts decomposition. ([#4162](https://github.com/diegosouzapw/OmniRoute/pull/4162))
-- **refactor(combo): god-file split part 2 — shadow + sorters + structure (QG v2 Fase 9 T5 D4-D6)** — continues the combo.ts split. ([#4175](https://github.com/diegosouzapw/OmniRoute/pull/4175))
-- **refactor(combo): god-file split part 3 — auto strategy (QG v2 Fase 9 T5 D8)** — extracts the auto strategy from combo.ts. ([#4186](https://github.com/diegosouzapw/OmniRoute/pull/4186))
-- **refactor(combo): extract round-robin sticky state to `combo/rrState.ts` (D7a)** — moves round-robin sticky state into its own module. ([#4196](https://github.com/diegosouzapw/OmniRoute/pull/4196))
-- **refactor(combo): extract the reset-aware quota block to `combo/quotaStrategies.ts` (D7b)** — moves the reset-aware quota strategies into their own module. ([#4204](https://github.com/diegosouzapw/OmniRoute/pull/4204))
-- **refactor(compression): remove vestigial SLM seam + dead deprecated alias** — drops dead compression code. ([#4253](https://github.com/diegosouzapw/OmniRoute/pull/4253))
-- **chore(compression): remove vestigial reconstructCcr/SessionDedup round-trip helpers** — removes unused round-trip helpers. ([#4226](https://github.com/diegosouzapw/OmniRoute/pull/4226))
-- **chore(compression): remove dead exports + fix stale llmlingua docs** — prunes dead exports and corrects stale LLMLingua docs. ([#4223](https://github.com/diegosouzapw/OmniRoute/pull/4223))
-- **chore(build): build + ship the TPROXY native addon in the standalone (prebuilds 4e)** — bundles the native TPROXY addon prebuilds into the standalone build. ([#4236](https://github.com/diegosouzapw/OmniRoute/pull/4236))
-- **chore(ci): add quota + 6 covered chatCore leaves to stryker mutate (QG v2 Fase 9 T5 Fase 3 follow-up)** — enrolls more covered leaves into mutation testing. ([#4209](https://github.com/diegosouzapw/OmniRoute/pull/4209))
-- **chore(ci): re-add 8 combo split leaves to stryker mutate + expand nightly batch-matrix 3→5 (QG v2 Fase 9 T5 Fase 3)** — restores mutation coverage for the split combo leaves and widens the nightly matrix. ([#4205](https://github.com/diegosouzapw/OmniRoute/pull/4205))
-- **chore(quality): close v3.8.28 cycle gate drift (re-baseline + nightly-mutation scope)** — reconciles quality-gate baselines after the v3.8.28 cycle. ([#4135](https://github.com/diegosouzapw/OmniRoute/pull/4135))
-- **ci(mutation): split nightly into 3 parallel batches to fit the 180min budget (QG v2 Fase 9 T0)** — parallelizes the nightly mutation run. ([#4150](https://github.com/diegosouzapw/OmniRoute/pull/4150))
-- **ci(mutation): restore cold-seed timeout headroom (a/b lost in #4225 squash) + extend to c/d/g/h** — restores and extends per-batch cold-seed timeouts. ([#4258](https://github.com/diegosouzapw/OmniRoute/pull/4258))
-- **ci(docs): harden the fabricated-docs checker + enforce `--strict` (QG v2 Fase 9 T9)** — tightens the anti-hallucination docs checker. ([#4149](https://github.com/diegosouzapw/OmniRoute/pull/4149))
-- **ci: derive the oasdiff base-ref from the package version + flag the mutation-toolchain regression** — fixes the OpenAPI-diff base-ref and surfaces a mutation-toolchain regression. ([#4134](https://github.com/diegosouzapw/OmniRoute/pull/4134))
-- **docs(ci): correct the mutation-gate note (no regression — `stryker -c` is `--concurrency`); record Task 12 GO** — corrects a misread of the stryker flag and records the spike GO. ([#4138](https://github.com/diegosouzapw/OmniRoute/pull/4138))
-- **docs(api): document the `/api/v1/ws` chat WebSocket endpoint in openapi.yaml** — adds the WebSocket chat endpoint to the OpenAPI spec. ([#4215](https://github.com/diegosouzapw/OmniRoute/pull/4215))
-- **docs(readme): expand Acknowledgments into a themed, star-counted credits hall** — reworks the README acknowledgments section. ([#4195](https://github.com/diegosouzapw/OmniRoute/pull/4195))
-- **style(dashboard): shrink the identity grid cell 46px → 32px (~30% smaller)** — tightens the identity grid density. ([#4143](https://github.com/diegosouzapw/OmniRoute/pull/4143))
-
-### 🔧 Dependencies
-
-- **deps: bump the production group with 5 updates** — routine production-dependency bumps. ([#4121](https://github.com/diegosouzapw/OmniRoute/pull/4121))
-- **chore(deps): bump github/codeql-action from 3 to 4** — CI action update. ([#4120](https://github.com/diegosouzapw/OmniRoute/pull/4120))
-- **chore(deps): bump actions/setup-python from 5 to 6** — CI action update. ([#4119](https://github.com/diegosouzapw/OmniRoute/pull/4119))
-
----
-
-## [3.8.28] — 2026-06-17
-
-### ✨ New Features
-
-- **feat(providers): add OrcaRouter (OpenAI-compatible routing gateway)** — OrcaRouter is now registered as an API-key provider. Its adaptive router is exposed as `orcarouter/auto` (smart routing across 150+ upstream models), alongside a curated flagship set (GPT-5.5, Gemini 3.5 Flash, Claude Opus 4.8, Grok 4.3, DeepSeek V4 Pro, MiniMax M2.7, Qwen3.7 Max). `passthroughModels` is enabled so any OrcaRouter model id works. OpenAI-compatible endpoint (`https://api.orcarouter.ai/v1`), Bearer (`sk-orca-…`) auth — no custom executor or translator required. ([#4070](https://github.com/diegosouzapw/OmniRoute/pull/4070) — thanks @jinhaosong-source)
-- **feat(providers): add Wafer AI (Anthropic-compatible, Bearer auth)** — Wafer AI is now a built-in provider speaking the Anthropic Messages format with Bearer authentication, registered with its model catalog so it works out of the box. ([#4098](https://github.com/diegosouzapw/OmniRoute/pull/4098) — thanks @diegosouzapw)
-- **feat(cli): `omniroute launch` — zero-config Claude Code launcher** — a new CLI subcommand that boots OmniRoute (if not already running) and launches Claude Code pre-wired to it, with no manual env/settings editing. ([#4097](https://github.com/diegosouzapw/OmniRoute/pull/4097) — thanks @diegosouzapw)
-- **feat(api): exact offline token counting for the `count_tokens` fallback via tiktoken** — the local `count_tokens` fallback now uses a real tiktoken (BPE) tokenizer for exact offline counts instead of a heuristic estimate, so token budgeting is accurate even when no upstream count endpoint is reachable. ([#4087](https://github.com/diegosouzapw/OmniRoute/pull/4087) — thanks @diegosouzapw)
-- **feat(sse): Claude Code quota-probe bypass + command meta-request helpers** — ported from free-claude-code: OmniRoute now recognizes Claude Code's quota-probe and command meta-requests and serves them locally instead of burning an upstream call, reducing wasted quota during CLI sessions. ([#4083](https://github.com/diegosouzapw/OmniRoute/pull/4083) — thanks @diegosouzapw)
-- **feat(sse): generic 400 field-downgrade retry + Groq field stripping** — when an upstream rejects a request with `400` because of an unsupported field, OmniRoute now strips the offending field and retries (a generic downgrade path), with Groq-specific field stripping wired in. Aligned with the existing `context_management` retry handling. ([#4096](https://github.com/diegosouzapw/OmniRoute/pull/4096) — thanks @diegosouzapw)
-- **feat(sse): delegated Anthropic Context Editing — relay coverage + 400-fallback** — extends the Claude server-side Context Editing delegation (#4021) with broader relay coverage and a `400`-fallback so a request the upstream rejects for the context-management beta degrades gracefully instead of failing. ([#4065](https://github.com/diegosouzapw/OmniRoute/pull/4065) — thanks @diegosouzapw)
-- **feat(compression): record per-engine Context Editing telemetry** — the compression pipeline now records a `context-editing` engine entry so the dashboard attributes server-side Context Editing savings alongside the local compression engines. ([#4062](https://github.com/diegosouzapw/OmniRoute/pull/4062) — thanks @diegosouzapw)
-- **feat(compression): RTK learn/discover (sample source + API + UI)** — the rule-based RTK compression engine gains a learn/discover workflow: sample a source, surface candidate rules through a new API, and review/apply them in the dashboard. ([#4088](https://github.com/diegosouzapw/OmniRoute/pull/4088) — thanks @diegosouzapw)
-- **feat(dashboard): 2026-06-17 free-tier refresh — honest catalog, uncapped + boost tiers, Layout A budget table** — the free-tier page was refreshed with an honest, deep-researched catalog (pooled/realistic figures rather than inflated 24/7 RPM math), new `recurring-uncapped` and boost tiers, new providers, and a KPI + budget table (Layout A). ([#4089](https://github.com/diegosouzapw/OmniRoute/pull/4089) — thanks @diegosouzapw)
-- **feat(dashboard): Combo Studio connection-cooldown badge (U1b Slice 2)** — the Combo Live cascade now surfaces each connection's cooldown state as a badge, complementing the circuit-breaker badge shipped in 3.8.27. ([#4068](https://github.com/diegosouzapw/OmniRoute/pull/4068) — thanks @diegosouzapw)
-- **feat(mitm): attribute intercepted requests to the originating process (Gap 1)** — the Traffic Inspector now resolves each intercepted connection back to the originating local process (via `/proc`), so captured traffic can be attributed to the app that produced it. (ProxyBridge-inspired hardening.) ([#4085](https://github.com/diegosouzapw/OmniRoute/pull/4085) — thanks @diegosouzapw)
-- **feat(mitm): capture-pipeline self-test route (Gap 12)** — a diagnostic route that exercises the MITM capture pipeline end-to-end so operators can confirm interception is working without crafting a real upstream call. ([#4093](https://github.com/diegosouzapw/OmniRoute/pull/4093) — thanks @diegosouzapw)
-- **feat(mitm): loop-guard self-check + verbosity control in `server.cjs` (Gaps 14+15)** — the MITM proxy gains a self-referential loop guard (so it never proxies its own traffic into an infinite loop) and a `MITM_VERBOSE` routing-decision log level. ([#4101](https://github.com/diegosouzapw/OmniRoute/pull/4101) — thanks @diegosouzapw)
-- **feat(agent-bridge): portable JSON import/export of config (Gap 4)** — the Agent Bridge / MITM configuration can now be exported to and imported from a portable JSON file, so a working setup can be backed up or moved between machines. ([#4094](https://github.com/diegosouzapw/OmniRoute/pull/4094) — thanks @diegosouzapw)
-
-### 🐛 Fixed
-
-- **fix(ws): start the LiveWS sidecar with `cwd` at the package root (global/systemd installs)** — the standalone LiveWS launcher (`scripts/start-ws-server.mjs`) re-spawns itself with `node --import tsx <self>` but did not set `cwd`. When the WebSocket sidecar was launched from outside the package directory — a global npm/homebrew install, or a `systemd`/`launchd` unit started from `$HOME` — Node could not resolve the `tsx` package (`ERR_MODULE_NOT_FOUND: Cannot find package 'tsx'`), and even from the package directory `tsx` could not resolve the tsconfig `@/*` path aliases (e.g. `@/types/databaseSettings`), so the sidecar never booted. The spawn now pins `cwd` to the package root (the directory above `scripts/`, where `package.json` + `tsconfig.json` live), which resolves both `tsx` discovery and the `@/*` aliases regardless of launch directory. ([#4055](https://github.com/diegosouzapw/OmniRoute/issues/4055) — thanks @Rahulsharma0810)
-- **fix(dashboard): Logs page auto-refresh now works in embedded/proxied dashboards** — the Request Logger gated each auto-refresh tick on a static `document.visibilityState === "visible"` read. Hosts that report a permanent non-`"visible"` state without ever firing a `visibilitychange` event (Docker dashboard wrappers, embedded webviews) froze auto-refresh entirely — only the manual Refresh button worked, a regression from 3.8.24's unconditional polling. The pause is now event-driven and fail-open: polling starts enabled and only pauses after a real `visibilitychange` → hidden transition (still preserving the backgrounded-tab optimization for normal browser tabs). ([#4054](https://github.com/diegosouzapw/OmniRoute/issues/4054) — thanks @tjengbudi)
-- **fix(docker): raise the build-stage Node heap to stop the production-build OOM** — the Docker `builder` stage ran `npm run build` with V8's default heap ceiling (~2 GB). After #4052 forced the heavier webpack engine (Turbopack panics on this Next.js version), the production optimization pass exceeded that ceiling and the build died with `FATAL ERROR: … JavaScript heap out of memory` at `[builder] npm run build`. The builder stage now sets `NODE_OPTIONS=--max-old-space-size` (default 4096 MB, overridable via `--build-arg OMNIROUTE_BUILD_MEMORY_MB=…`) before the build; the value propagates to the spawned `next build`. Build-only — the runtime heap (`OMNIROUTE_MEMORY_MB` on the runner stage) is unchanged. ([#4076](https://github.com/diegosouzapw/OmniRoute/issues/4076) — thanks @kamenkadmitry)
-- **fix(dashboard): "Update Available" banner reappears reliably across Docker/npm/desktop installs** — the home-page banner is gated on `GET /api/system/version`'s `updateAvailable`, which derived the latest version ONLY from `npm info omniroute version --json` via the `npm` CLI binary. When that binary is absent from the runtime PATH (Docker/desktop/locked-down installs) or the registry is unreachable, the call returned `null` → `updateAvailable=false` → the banner silently never rendered even when a newer release existed. The route now resolves the latest version through `resolveLatestVersion()`: the fast `npm` CLI path first, then an npm-binary-free fallback over the registry HTTP API (`registry.npmjs.org/omniroute/latest`), and a logged warning instead of silent degradation when both fail. Version comparison was also hardened to tolerate `v`-prefixed and pre-release version strings. ([#4100](https://github.com/diegosouzapw/OmniRoute/issues/4100))
-- **fix(sse): route image requests only to confirmed-vision combo targets** — a combo could route an image-bearing request to a member that doesn't actually support vision. Routing now requires `supportsVision === true` (plus a model-id heuristic) before sending images to a target, so multimodal requests land only on members that can handle them. ([#4071](https://github.com/diegosouzapw/OmniRoute/pull/4071) — thanks @diego-anselmo)
-- **fix(security): injection guard respects the `INJECTION_GUARD_MODE` DB feature flag** — the prompt-injection guard ignored the database feature-flag, so operators couldn't change its mode at runtime; it now reads the flag and honors the configured mode. ([#4077](https://github.com/diegosouzapw/OmniRoute/pull/4077) — thanks @zhiru)
-- **fix(ws): proxy LAN `/live-ws` upgrades and warn on an unset `JWT_SECRET`** — WebSocket upgrade requests arriving over the LAN proxy path were not forwarded to the LiveWS sidecar; they are now proxied correctly, and the server logs a clear warning when `JWT_SECRET` is unset. ([#4079](https://github.com/diegosouzapw/OmniRoute/pull/4079) — thanks @Rahulsharma0810)
-- **fix(dev): force webpack in the custom dev server (Turbopack 16.2.x panics)** — the custom dev server now forces the webpack engine because Turbopack panics on this Next.js version, so `npm run dev` boots reliably. ([#4092](https://github.com/diegosouzapw/OmniRoute/pull/4092) — thanks @chirag127)
-- **fix(auto): resolve built-in `auto/*` catalog combos** — referencing a built-in `auto/*` combo returned a premature `400` because the catalog entry wasn't resolved; the built-in auto catalog is now resolved before validation so those combos work. ([#4058](https://github.com/diegosouzapw/OmniRoute/pull/4058) — thanks @megamen32)
-- **fix(sse): friendly 413 message for ChatGPT-web payload-too-large** — an oversized ChatGPT-web payload returned an opaque error; it now returns a clear `413` with a human-readable message. ([#4080](https://github.com/diegosouzapw/OmniRoute/pull/4080) — thanks @diegosouzapw)
-- **fix(ws): warm the SSE auth import on LiveWS startup; relocate the boot test to integration** — the LiveWS sidecar now pre-imports the SSE auth module at startup to avoid a first-request stall, and its boot test was moved to the integration suite. ([#4063](https://github.com/diegosouzapw/OmniRoute/pull/4063) — thanks @diegosouzapw)
-- **fix(mitm): crash-safe system-state teardown + socket timeouts (ProxyBridge-inspired hardening)** — the MITM proxy could leave the host's system proxy settings applied if it crashed mid-teardown, and long-lived tunnels could leak as half-open sockets. Teardown is now crash-safe (system state is always restored) and proxied sockets get an idle timeout (`MITM_IDLE_TIMEOUT_MS`, default 60s). ([#4084](https://github.com/diegosouzapw/OmniRoute/pull/4084) — thanks @diegosouzapw)
-- **fix(responses): clear the `/v1/responses` keep-alive timer on cancel/abort** — a cancelled or aborted `/v1/responses` stream left its keep-alive timer running, leaking a timer and burning CPU; the timer is now cleared on cancel/abort. ([#4105](https://github.com/diegosouzapw/OmniRoute/pull/4105) — thanks @artickc)
-- **fix(usage): reap orphaned pending-request details (unbounded memory leak)** — pending-request detail entries whose request never completed accumulated without bound; they are now reaped, closing a slow memory leak. ([#4107](https://github.com/diegosouzapw/OmniRoute/pull/4107) — thanks @artickc)
-- **fix(auth): prune expired entries from the login brute-force guard map (unbounded growth)** — the login brute-force guard map grew without bound because expired entries were never removed; expired entries are now pruned. ([#4111](https://github.com/diegosouzapw/OmniRoute/pull/4111) — thanks @artickc)
-- **fix(logger): hard-cap the error-dedup map to bound memory under unique-message bursts** — a burst of unique error messages could grow the dedup map without limit; it is now hard-capped. ([#4113](https://github.com/diegosouzapw/OmniRoute/pull/4113) — thanks @artickc)
-- **fix(circuit-breaker): enforce `MAX_REGISTRY_SIZE` (declared but never applied)** — the circuit-breaker registry declared a maximum size that was never enforced, so it could grow unbounded; the cap is now applied. ([#4114](https://github.com/diegosouzapw/OmniRoute/pull/4114) — thanks @artickc)
-- **fix(webhook): clear the abort timer in `finally` to avoid dangling timers on fetch error** — a webhook dispatch that threw before clearing its abort timer left the timer dangling; it is now cleared in a `finally` block. ([#4115](https://github.com/diegosouzapw/OmniRoute/pull/4115) — thanks @artickc)
-- **fix(combo): detach the per-target listener from the shared hedge abort signal** — combo hedging attached a per-target listener to a shared abort signal without detaching it, leaking listeners across requests; the listener is now detached. ([#4116](https://github.com/diegosouzapw/OmniRoute/pull/4116) — thanks @artickc)
-- **fix(timers): unref background interval timers so they don't block clean shutdown** — long-lived background interval timers kept the event loop alive and blocked a clean process exit; they are now `unref`'d. ([#4117](https://github.com/diegosouzapw/OmniRoute/pull/4117) — thanks @artickc)
-
-### ⚡ Performance
-
-- **perf(registry): precompute the model→provider index in `parseModelFromRegistry`** — model→provider lookups now use a precomputed index instead of scanning the registry on every call. ([#4110](https://github.com/diegosouzapw/OmniRoute/pull/4110) — thanks @artickc)
-- **perf(obfuscation): cache per-word regexes instead of recompiling every request** — the obfuscation pass now caches its per-word regexes rather than recompiling them on each request. ([#4109](https://github.com/diegosouzapw/OmniRoute/pull/4109) — thanks @artickc)
-- **perf(stream): use `structuredClone` instead of a JSON round-trip for per-chunk reasoning split** — the per-chunk reasoning split now clones with `structuredClone` rather than `JSON.parse(JSON.stringify(...))`. ([#4108](https://github.com/diegosouzapw/OmniRoute/pull/4108) — thanks @artickc)
-- **perf(gemini): cache the reasoning close-tag regex instead of recompiling per token** — the Gemini reasoning close-tag regex is now compiled once and reused instead of per token. ([#4106](https://github.com/diegosouzapw/OmniRoute/pull/4106) — thanks @artickc)
-
-### 📝 Maintenance
-
-- **ci(quality): flip the TIA impacted-unit-tests gate from advisory to blocking (Fase 9)** — the test-impact-analysis gate that runs the unit tests impacted by a diff is now blocking on PRs. ([#4069](https://github.com/diegosouzapw/OmniRoute/pull/4069) — thanks @diegosouzapw)
-- **ci(quality): dedup the doubly-run `check:docs-sync` + record the validated ROI backlog (Fase 9)** — `check:docs-sync` was running twice in CI; the duplicate was removed and the validated quality-gate ROI backlog recorded. ([#4099](https://github.com/diegosouzapw/OmniRoute/pull/4099) — thanks @diegosouzapw)
-- **docs(quality-gates): reconcile the gate inventory with `ci.yml` + add the ROI rationalization backlog** — the quality-gate inventory doc was reconciled against the actual CI jobs and a rationalization backlog added. ([#4095](https://github.com/diegosouzapw/OmniRoute/pull/4095) — thanks @diegosouzapw)
-- **test(infra): isolate `DATA_DIR` per test process; raise Stryker concurrency 1→4** — test processes now get an isolated `DATA_DIR` (no shared-DB cross-talk) and the mutation runner's concurrency was raised. ([#4078](https://github.com/diegosouzapw/OmniRoute/pull/4078) — thanks @diegosouzapw)
-- **test(dashboard): smoke e2e for the Combo Live Studio page** — adds a Playwright smoke test covering the Combo Live Studio page. ([#4075](https://github.com/diegosouzapw/OmniRoute/pull/4075) — thanks @diegosouzapw)
-- **docs(compression): document LLMLingua optional deps + on-demand install** — documents the optional LLMLingua dependencies and how they are installed on demand. ([#4061](https://github.com/diegosouzapw/OmniRoute/pull/4061) — thanks @diegosouzapw)
-- **chore(deps): freeze `@huggingface/transformers` in dependabot (hard-pin)** — the transformers dependency is hard-pinned and frozen in dependabot to protect the VPS-validated LLMLingua + memory-embeddings stack from a breaking major bump. ([#4066](https://github.com/diegosouzapw/OmniRoute/pull/4066) — thanks @diegosouzapw)
-- **chore(docs): update the Discord invite link to a non-expiring one** — replaces the expiring Discord invite with a permanent link. ([#4067](https://github.com/diegosouzapw/OmniRoute/pull/4067) — thanks @diegosouzapw)
-- **chore(docs): document the new MITM env vars + reconcile the env-doc contract** — documents `MITM_IDLE_TIMEOUT_MS` and `MITM_VERBOSE` in `.env.example` + `ENVIRONMENT.md`, allowlists the framework-internal `TURBOPACK` and the Claude Code `ANTHROPIC_AUTH_TOKEN`, and relocates/prunes stale provider/guide docs. (thanks @diegosouzapw)
-
-### 🔧 Dependencies
-
-- **deps: bump the development group with 10 updates** — routine dependabot dev-dependency bumps. ([#4051](https://github.com/diegosouzapw/OmniRoute/pull/4051))
-- **deps(electron): bump electron 42.4.0 → 42.4.1** — ([#4049](https://github.com/diegosouzapw/OmniRoute/pull/4049))
-- **ci(deps): bump `actions/setup-node` 4 → 6** — ([#4048](https://github.com/diegosouzapw/OmniRoute/pull/4048))
-- **ci(deps): bump `actions/cache` 4.3.0 → 5.0.5** — ([#4047](https://github.com/diegosouzapw/OmniRoute/pull/4047))
-- **ci(deps): bump `actions/github-script` 7 → 9** — ([#4046](https://github.com/diegosouzapw/OmniRoute/pull/4046))
-- **ci(deps): bump `ossf/scorecard-action` 2.4.0 → 2.4.3** — ([#4045](https://github.com/diegosouzapw/OmniRoute/pull/4045))
-- **ci(deps): bump `actions/upload-artifact` 4 → 7** — ([#4044](https://github.com/diegosouzapw/OmniRoute/pull/4044))
-
----
-
-## [3.8.27] — 2026-06-17
-
-### ✨ New Features
-
-- **feat(combos): advertise combo capabilities (multimodal / reasoning / caching) on the import surfaces** — importing a combo package into a client (LobeHub / OpenCode / VS Code, via `/v1/combos` and the VS Code combo catalog) no longer requires manually enabling multimodal/image-input, reasoning, and caching afterwards. `projectCombo` now attaches a registry-derived `capabilities` block, gated conservatively: `multimodal`/`reasoning` are advertised only when **every** concrete model step proves the capability (an unprovable nested combo-ref drops them, since the strategy may route to any member), and `caching` reflects the combo's explicit Context-Cache-Protection setting (no surprise prompt-cache cost). The public `/v1/combos` default projection (#2300) is unchanged unless the caller opts in. ([#3979](https://github.com/diegosouzapw/OmniRoute/issues/3979) — thanks @xenstar)
-- **feat(sse): delegated Anthropic Context Editing for Claude (`clear_tool_uses`)** — Claude requests can now offload context trimming to Anthropic's server-side context-management API (beta `context-management-2025-06-27`, `clear_tool_uses_20250919`), pruning stale tool-use turns upstream instead of locally. Claude-only by nature (the edit runs server-side); multi-provider context trimming remains the job of the local compression engines. ([#4021](https://github.com/diegosouzapw/OmniRoute/pull/4021) — thanks @diegosouzapw)
-- **feat(sse): real LLMLingua-2 ONNX compression engine (stable)** — the LLMLingua-2 prompt-compression engine is now a real local ONNX model (TinyBERT default, transformers.js + tfjs), promoted to stable after VPS validation, replacing the previous placeholder. ([#4014](https://github.com/diegosouzapw/OmniRoute/pull/4014) — thanks @diegosouzapw)
-- **feat(compression): capture per-engine analytics + Lite schema fix** — the compression pipeline now persists a per-engine breakdown for historical analytics so the dashboard can attribute savings to each engine in a stacked pipeline, and a Lite-schema mismatch was corrected. ([#4018](https://github.com/diegosouzapw/OmniRoute/pull/4018) — thanks @diegosouzapw)
-- **feat(dashboard): real circuit-breaker state in the Combo Live cascade (U1b)** — the Combo Live cascade view now surfaces each provider's real circuit-breaker state (CLOSED / OPEN / HALF_OPEN) as a badge, read live from `/api/monitoring/health`, instead of inferring health from request outcomes. ([#4029](https://github.com/diegosouzapw/OmniRoute/pull/4029) — thanks @diegosouzapw)
-- **feat(openai): honor a custom base URL in model discovery + complete openai/codex pricing** — OpenAI-format providers configured with a custom base URL now have that URL honored during model discovery (not just inference), and the openai/codex pricing table was completed. Discovery is routed through the SSRF-guarded outbound fetch. ([#4005](https://github.com/diegosouzapw/OmniRoute/pull/4005) — thanks @artickc)
-- **feat(observability): capture actual upstream provider requests** — the request inspector now records the exact payload sent to the upstream provider (post-translation), so you can see what OmniRoute actually dispatched rather than only the client's original request. ([#3941](https://github.com/diegosouzapw/OmniRoute/pull/3941) — thanks @rdself)
-- **feat(providers): provider auth visibility controls** — adds controls to show/hide provider auth details in the dashboard so credentials can be revealed only when needed. ([#3953](https://github.com/diegosouzapw/OmniRoute/pull/3953) — thanks @rdself)
-- **feat(providers): model search filter on the provider dashboard** — the provider dashboard gains a search filter to quickly narrow a provider's model list. ([#3950](https://github.com/diegosouzapw/OmniRoute/pull/3950) — thanks @felipesartori)
-- **feat(compression): Indonesian caveman rules + language pack** — adds an Indonesian "caveman" rule set and language pack to the rule-based compression engine. ([#3975](https://github.com/diegosouzapw/OmniRoute/pull/3975) — thanks @Veier04)
-- **feat(dashboard): sidebar group separator toggles** — the dashboard sidebar can now toggle group separators for a cleaner navigation layout. ([#3971](https://github.com/diegosouzapw/OmniRoute/pull/3971) — thanks @rdself)
-- **feat(api): local `@@om-usage` command for cached per-key usage** — API clients can send a message that is exactly `@@om-usage` to retrieve cached Claude-style usage data locally, without forwarding the prompt to an upstream provider. Gated by a new per-key allowance flag. ([#4034](https://github.com/diegosouzapw/OmniRoute/pull/4034) — thanks @Witroch4)
-
-### 🐛 Fixed
-
-- **fix(opencode): forward the OpenCode session id to the upstream regardless of how the user named the provider** — the `OpencodeExecutor` forwarded the `x-opencode-session/request/project/client` headers, but the OpenCode CLI only emits those when the configured `providerID` **starts with** `"opencode"`. A user who adds OmniRoute as a custom provider (e.g. `"omniroute"`) makes the CLI send `x-session-affinity` / `X-Session-Id` instead (both carry the same session id), which the executor never read — so the session-metadata forwarding was effectively dead code for the realistic provider-naming case. The opencode-family executor now falls back to `x-session-affinity` / `X-Session-Id` and maps it onto `x-opencode-session` when the client didn't send the header directly, so session continuity to the `opencode.ai` upstream works for any provider name (a direct `x-opencode-session` still wins). Scoped to this executor only — the generic `DefaultExecutor` intentionally does **not** do this, to avoid leaking the client session id to arbitrary third-party upstreams. ([#4022](https://github.com/diegosouzapw/OmniRoute/issues/4022) — thanks @pizzav-xyz)
-- **fix(guardrails): Vision Bridge no longer drops the image when the describe call fails (Nvidia NIM "Image unavailable")** — the Vision Bridge is enabled by default and engages for any model whose vision capability OmniRoute can't prove from the registry (`supportsVision !== true`, which includes uncatalogued models that resolve to `null`). When the per-image describe call failed (e.g. no vision model configured), it replaced the image with the literal text `[Image N]: (unavailable)` and dropped the original `image_url` — so a genuinely vision-capable upstream (Nvidia NIM) received text only and answered "Image unavailable. Cannot provide description without visual data." A describe failure is no longer destructive: `replaceImageParts` now receives `null` for failed images and **preserves the original image part** so the upstream can still see it (successful describes still replace the image with the text description; `meta.descriptions` observability is unchanged). ([#4012](https://github.com/diegosouzapw/OmniRoute/issues/4012) — thanks @daniij)
-- **fix(kiro): preserve `finish_reason: "tool_calls"` on the Kiro streaming path** — streaming tool-call requests through the Kiro (Responses API) provider had their terminal `finish_reason` reported as `"stop"` instead of `"tool_calls"`, so agent clients (Hermes) treated the tool-call turn as a finished turn, never ran the tool, and the next request failed with HTTP 400 on the incomplete tool state. `convertKiroToOpenAI`'s terminal `messageStopEvent`/`done` branch hardcoded `finish_reason: "stop"` regardless of whether the stream had emitted `toolUseEvent`s. The translator now records `state.sawToolUse` when a tool-use chunk is emitted and reports `finish_reason: "tool_calls"` on the terminal chunk (and in `state.finishReason`) whenever the stream produced tool calls. The non-streaming path was already correct. ([#3980](https://github.com/diegosouzapw/OmniRoute/issues/3980) — thanks @lordavadon2)
-- **fix(resilience): respect connection cooldown stored as a numeric epoch** — the router kept dispatching to connections still inside their rate-limit cooldown because `rate_limited_until` (a `TEXT` column) was persisted as a raw epoch number, which SQLite coerced to a string like `"1781696905131.0"` that `new Date(...)` parsed as `NaN`, so the cooling connection was never skipped. The cooldown read predicates now normalize numeric-epoch strings via a shared `cooldownUntilMs()` helper; ISO behavior is unchanged. ([#3995](https://github.com/diegosouzapw/OmniRoute/pull/3995) — thanks @diegosouzapw)
-- **fix(providers): fetch the live `/models` catalog for LLM7 and BytePlus** — importing an LLM7 or BytePlus key surfaced only a small, outdated hardcoded list because neither provider was classified by any live-fetch branch of the model-import route. Both are now in `NAMED_OPENAI_STYLE_PROVIDERS`, so the route probes `<baseUrl>/models` with the key and serves the live catalog, falling back to the local catalog only when the upstream fetch fails. ([#3996](https://github.com/diegosouzapw/OmniRoute/pull/3996) — thanks @FerLuisxd / @diegosouzapw)
-- **fix(dashboard): logs auto-refresh reads live visibility, not a stale mount ref** — the Logs page never auto-refreshed when the tab loaded in the background because the auto-refresh interval gated each tick on a visibility ref seeded once at mount; the tick now reads the live `document.visibilityState`, so polling self-heals as soon as the tab is visible while still pausing when genuinely hidden. ([#3997](https://github.com/diegosouzapw/OmniRoute/pull/3997) — thanks @tjengbudi / @diegosouzapw)
-- **fix(combo): shuffle the strict-random fallback remainder to spread load** — with the `strict-random` strategy a persistently-failing model was retried on essentially every request because only the deck-selected slot 0 was shuffled while the fallback remainder stayed in fixed priority order; the remainder is now shuffled too, so fallback load (and recovery from a failing target) spreads evenly across healthy peers. ([#3998](https://github.com/diegosouzapw/OmniRoute/pull/3998) — thanks @KeNJiKunG / @diegosouzapw)
-- **fix(claude): forward the client `tool-search-tool-2025-10-19` anthropic-beta on the Claude OAuth path** — with deferred tools active, Claude Code negotiates the `tool-search-tool-2025-10-19` beta, but OmniRoute dropped it on both Claude code paths, so the claude.ai backend rejected every deferred-tool request with `400 Tool reference not found`. A new allowlist-merge (`mergeClientAnthropicBeta`) now unions the client's negotiated beta into the outbound set on both paths, appending only allowlisted client betas (preserving the #3415 fix). ([#3999](https://github.com/diegosouzapw/OmniRoute/pull/3999) — thanks @huohua-dev / @diegosouzapw)
-- **fix(executor): strip `stream_options` on non-streaming requests (NVIDIA NIM 400)** — clients that send `stream_options: { include_usage: true }` regardless of `stream` (e.g. the OpenAI Python SDK) had it passed through untouched on non-streaming calls, and NVIDIA NIM rejected it with `400 "Stream options can only be defined when stream=True"`. `DefaultExecutor.transformRequest` now strips `stream_options` whenever `stream` is false; the streaming injection path is unchanged. ([#4000](https://github.com/diegosouzapw/OmniRoute/pull/4000) — thanks @andrea-kingautomation / @daniij / @diegosouzapw)
-- **fix(sse): guard model-less registry entries in `getUnsupportedParams` (mimocode)** — a registry entry without a model map (mimocode) threw when computing unsupported params; the lookup now guards the model-less case so request validation no longer crashes. ([#4015](https://github.com/diegosouzapw/OmniRoute/pull/4015) — thanks @diegosouzapw)
-- **fix(perplexity-web): parse the schematized `diff_block` stream so answers aren't empty** — Perplexity web streamed its answer as RFC-6902 `diff_block` patches that OmniRoute didn't apply during the `PENDING` phase, so responses came back empty; the parser now applies the patches and materializes the text only on `COMPLETED`. ([#4001](https://github.com/diegosouzapw/OmniRoute/pull/4001) — thanks @artickc)
-- **fix(default-executor): honor a custom `providerSpecificData.baseUrl` for OpenAI-format providers** — OpenAI-format providers configured with a custom base URL had it ignored on the inference path; the default executor now honors `providerSpecificData.baseUrl` so requests reach the configured endpoint. ([#4002](https://github.com/diegosouzapw/OmniRoute/pull/4002) — thanks @artickc)
-- **fix(live-ws): bridge LiveWS sidecar events to the dashboard** — events emitted by the LiveWS sidecar were not reaching the dashboard; they are now bridged so live websocket activity is visible. (A cookie-auth regression in the sidecar's auth-token parsing was also corrected.) ([#4004](https://github.com/diegosouzapw/OmniRoute/pull/4004) — thanks @megamen32)
-- **fix(qwen-web): cookie validation false-positive — check the response body for a user object** — Qwen web cookie validation reported a valid cookie as invalid; it now inspects the response body for the `user` object instead of relying on the status code alone. ([#3958](https://github.com/diegosouzapw/OmniRoute/pull/3958) — thanks @thezukiru)
-- **fix(vision-bridge): force the bridge for tokenrouter deepseek models** — tokenrouter DeepSeek models are now forced through the Vision Bridge so image inputs are handled correctly. ([#3946](https://github.com/diegosouzapw/OmniRoute/pull/3946) — thanks @WormAlien)
-- **fix(api): return 400 (not 500) for malformed JSON on `/api/auth/login`** — a malformed JSON body on the login endpoint returned an opaque 500; it now returns a proper 400. ([#4031](https://github.com/diegosouzapw/OmniRoute/pull/4031) — thanks @rdself)
-- **fix(dashboard): Playground Compare tab loading + HTTP method guard** — the Playground Compare tab failed to load; the loading path was fixed and an HTTP method guard added. ([#4024](https://github.com/diegosouzapw/OmniRoute/pull/4024) — thanks @rdself)
-- **fix(proxy): gate the control-plane proxy direct fallback behind a feature flag (fail-closed)** — the direct-connection fallback for control-plane ops when a pinned proxy is unreachable is now gated behind a feature flag and fails closed, so a pinned proxy is never silently bypassed unless explicitly allowed. ([#3963](https://github.com/diegosouzapw/OmniRoute/pull/3963) — thanks @rdself)
-- **fix(db): persist backup retention days** — the backup retention-days setting was not persisted across restarts; it is now stored durably. ([#3970](https://github.com/diegosouzapw/OmniRoute/pull/3970) — thanks @rdself)
-- **fix(dashboard): refine the provider quota card display** — the provider quota card layout was refined for clearer quota/usage presentation. ([#3969](https://github.com/diegosouzapw/OmniRoute/pull/3969) — thanks @rdself)
-- **fix(dashboard): refine compression settings, storage labels, and sidebar grouping** — polishes the compression-settings UI, clarifies storage labels, and tidies the sidebar grouping. ([#4033](https://github.com/diegosouzapw/OmniRoute/pull/4033) — thanks @rdself)
-
-### 🔒 Security & Hardening
-
-- **fix(security): eliminate a polynomial ReDoS in the combo `<omniModel>` tag regex** — `comboAgentMiddleware`'s cache-tag pattern wrapped the tag in an unbounded newline run (`(?:\n|\r)*`), making `.test()` / `.replace()` run in O(n²) on inputs with many newlines (CodeQL `js/polynomial-redos`). The detection pattern now matches only the core `<omniModel>…</omniModel>` and the global strip pattern bounds the surrounding newline runs, keeping it linear; detection / extraction / multi-tag stripping behavior is unchanged. ([#3982](https://github.com/diegosouzapw/OmniRoute/pull/3982) — thanks @diegosouzapw)
-- **ci(security): harden workflows — artipacked `persist-credentials`, cache-poisoning, SC2086** — GitHub Actions workflows were hardened against the artipacked `persist-credentials` leak and cache-poisoning, and shell-quoting (`SC2086`) issues were fixed. ([#3965](https://github.com/diegosouzapw/OmniRoute/pull/3965) — thanks @diegosouzapw)
-- **ci(quality): flip require-tighten + osv + Trivy to blocking (cycle-end)** — the per-module require-tighten check and the OSV / Trivy scanners moved from advisory to blocking for the v3.8.27 cycle close, so new dependency or coverage regressions fail CI. ([#3984](https://github.com/diegosouzapw/OmniRoute/pull/3984) — thanks @diegosouzapw)
-- **chore(deps): dependabot security bumps + drop unused gray-matter** — applies a batch of Dependabot security bumps and removes the unused `gray-matter` dependency from the tree. ([#4036](https://github.com/diegosouzapw/OmniRoute/pull/4036) — thanks @diegosouzapw)
-- **chore(deps): automated dependency bumps** — Dependabot upgraded the production dependency group (13 updates), `vite`, `form-data`, and the `npm_and_yarn` group. ([#3915](https://github.com/diegosouzapw/OmniRoute/pull/3915), [#3942](https://github.com/diegosouzapw/OmniRoute/pull/3942), [#3943](https://github.com/diegosouzapw/OmniRoute/pull/3943), [#3944](https://github.com/diegosouzapw/OmniRoute/pull/3944) — thanks @dependabot)
-
-### 🧹 Internal / Quality / Docs
-
-- **feat(ci): Quality Gate v2 — Onda 0 + Onda 1** — first two waves of the Quality Gate v2 program: gate flips, test-impact analysis (TIA), SAST, DAST-smoke, and mutation-testing infrastructure. ([#4016](https://github.com/diegosouzapw/OmniRoute/pull/4016) — thanks @diegosouzapw)
-- **refactor: modularize the provider registry into individual provider plugins** — `providerRegistry.ts` was split into individual per-provider plugin modules (non-stacked). A forward-fix restored the `byteplus` + `mimocode` modules dropped by the move. ([#3993](https://github.com/diegosouzapw/OmniRoute/pull/3993) — thanks @oyi77 / @diegosouzapw)
-- **refactor: modularize schemas (non-stacked)** — the request/response schema definitions were split into individual modules to reduce file size and improve maintainability. ([#3988](https://github.com/diegosouzapw/OmniRoute/pull/3988) — thanks @oyi77)
-- **fix: restore unit regressions dropped by the lossy schema/registry modularizations** — the schema/registry modularizations (#3988, #3993) silently dropped internal logic covered by unit tests; this PR restores the regressed units. ([#4030](https://github.com/diegosouzapw/OmniRoute/pull/4030) — thanks @diegosouzapw)
-- **refactor(dashboard): settings UI layout + API Keys naming** — the settings UI layout was reorganized and the "API Keys" naming clarified. ([#4020](https://github.com/diegosouzapw/OmniRoute/pull/4020) — thanks @rdself)
-- **大量UI显示和i18n优化 (dashboard UI display + i18n improvements)** — a batch of dashboard UI-display refinements and i18n string improvements. ([#3973](https://github.com/diegosouzapw/OmniRoute/pull/3973) — thanks @rdself)
-- **fix(ci): scope TIA to `node:test` unit files only** — test-impact analysis was matching files the `node:test` runner doesn't execute, producing 99 false failures; the TIA glob now mirrors the `test:unit` glob exactly. ([#4035](https://github.com/diegosouzapw/OmniRoute/pull/4035) — thanks @diegosouzapw)
-- **fix(ci): electron-release publish-npm needs `contents: write`** — the reusable npm-publish job invoked by the electron release lacked `contents: write`, causing a v3.8.26 `startup_failure`; the permission was granted. ([#3966](https://github.com/diegosouzapw/OmniRoute/pull/3966) — thanks @diegosouzapw)
-- **test(opencode-plugin): ESM default-export test (drop the stale CJS bundle test)** — replaces the stale CJS bundle test with an ESM default-export test, following up the #3883 ESM-only migration. ([#3967](https://github.com/diegosouzapw/OmniRoute/pull/3967) — thanks @diegosouzapw)
-- **fix(ci): Fix promptfoo security-assertion parsing** — the promptfoo (DAST/security eval) assertion parser was corrected so security assertions are read reliably. ([#4032](https://github.com/diegosouzapw/OmniRoute/pull/4032) — thanks @rdself)
-- **docs(troubleshooting): note that the MITM proxy cannot intercept Windows-host apps under WSL** — documents that the MITM proxy running inside WSL cannot intercept traffic from apps on the Windows host. ([#4003](https://github.com/diegosouzapw/OmniRoute/pull/4003) — thanks @diegosouzapw)
-- **chore(quality): maintenance roll-up** — assorted quality-gate hygiene that does not change runtime behavior: re-baseline `validation.ts` for the #3958 qwen body-check, allowlist the `socks` dependency declared by #4004, ignore jscpd major bumps (the v5 Rust rewrite breaks the pinned duplication gate), untrack an accidentally-committed root `node_modules` symlink (and gitignore it), rehome the #3972 logs auto-refresh test so a runner collects it, and open the v3.8.27 development cycle. (thanks @diegosouzapw)
-
----
-
-## [3.8.26] — 2026-06-15
-
-### ✨ New Features
-
-- **feat(media): Vertex AI (Google) speech, transcription, music & video generation** — Vertex AI's Google media models are now routable through dynamic discovery: speech synthesis, audio transcription, music generation, and video generation. ([#3929](https://github.com/diegosouzapw/OmniRoute/pull/3929) — thanks @artickc)
-- **feat(glm): add GLM-5.2 with effort-tier routing (high/max)** — GLM-5.2 is registered with high/max effort-tier routing. ([#3885](https://github.com/diegosouzapw/OmniRoute/pull/3885) — thanks @dhaern)
-- **feat(combo): add a sticky round-robin target limit** — round-robin combos can cap how many targets stay "sticky" within a session (`stickyRoundRobinLimit`), balancing stickiness against spread. ([#3846](https://github.com/diegosouzapw/OmniRoute/pull/3846) — thanks @adivekar-utexas)
-- **feat(openrouter): connection presets** — OpenRouter connections support reusable presets (provider routing / sort / quantization preferences), selectable when adding a connection. ([#3878](https://github.com/diegosouzapw/OmniRoute/pull/3878) — thanks @rdself)
-
-### 🐛 Fixed
-
-- **fix(compression/memory): stop memory + compression from poisoning the upstream prompt cache** — with compression and/or memory enabled, requests to caching providers (Anthropic-family) missed the prompt cache on every turn, multiplying cost. Two root causes: (1) memory injection prepended the retrieved memories — which **vary per user query** — at index 0 of the message array, shifting the entire cacheable prefix every turn; memory is now inserted just before the last user message when the request carries `cache_control` breakpoints, keeping the cacheable prefix (system prompt + prior turns) byte-stable. (2) the cache-aware `skipSystemPrompt` flag computed by `getCacheAwareStrategy()` was dropped by `selectCompressionStrategy()` (which can only return a mode), so the system prompt could still be compressed under caching; a new `resolveCacheAwareConfig()` now forces `preserveSystemPrompt` on for caching requests. ([#3936](https://github.com/diegosouzapw/OmniRoute/pull/3936), closes [#3890](https://github.com/diegosouzapw/OmniRoute/issues/3890) — thanks @xenstar / @diegosouzapw)
-- **fix(providers): register BytePlus ModelArk so its API key can be added** — adding a BytePlus (`ark-…`) key reported "invalid". `byteplus` was present in the provider catalog (`APIKEY_PROVIDERS`) but **never registered in the routing registry**, so key validation fell through to `{ unsupported: true }` → HTTP 400 → the UI rendered every key as invalid (and the provider was unusable for inference). Added a registry entry modeled on the existing Volcengine Ark provider: OpenAI-compatible format, base `https://ark.ap-southeast.bytepluses.com/api/v3` (region `ap-southeast-1`), `Authorization: Bearer` auth, seeded with the catalog's advertised models (Seed 2.0, Kimi K2 Thinking, GLM 4.7, GPT-OSS-120B). ([#3935](https://github.com/diegosouzapw/OmniRoute/pull/3935), closes [#3877](https://github.com/diegosouzapw/OmniRoute/issues/3877) — thanks @nikohd12 / @diegosouzapw)
-- **fix(providers): Nous Research key validation no longer fails on a stale probe model** — adding a valid Nous Research API key reported "invalid" even though the same key worked via the portal's copy-shell `curl`. The validation probe sent `model: "nousresearch/hermes-4-70b"`, which Nous does not serve, so the API returned `400` and the validator (which only treated `200`/`429` as success) reported the key invalid. The probe now uses the real `Hermes-4-70B` slug, and any non-auth 4xx (`400`/`404`/`422`) is treated as a valid key (the request shape was wrong, not the credentials) — mirroring the longcat/nvidia validators so a future model rename can't re-break key validation. ([#3934](https://github.com/diegosouzapw/OmniRoute/pull/3934), closes [#3881](https://github.com/diegosouzapw/OmniRoute/issues/3881) — thanks @FerLuisxd / @diegosouzapw)
-- **fix(stream): persist mid-stream upstream failures** — when an upstream stream fails partway through, the partial response and incremental usage are now finalized and persisted instead of lost; extracts a shared `streamFailureFinalization` path and merges incremental Claude usage (follow-up to #3879). ([#3937](https://github.com/diegosouzapw/OmniRoute/pull/3937) — thanks @rdself)
-- **fix(perplexity-web): update the request payload to schema v2.18 (HTTP 400)** — Perplexity web requests started returning HTTP 400; the request payload was updated to Perplexity's v2.18 schema. ([#3938](https://github.com/diegosouzapw/OmniRoute/pull/3938) — thanks @artickc)
-- **fix(stream): keep the in-flight request payload in sync** — the pending-by-id request record is now updated in place (`Object.assign`) so the in-flight payload stays consistent with what was dispatched (coexists with #3937). ([#3940](https://github.com/diegosouzapw/OmniRoute/pull/3940) — thanks @rdself)
-- **fix: stabilize reasoning streams and request logs** — reasoning-token streaming and the request-log capture path were stabilized to avoid dropped/duplicated reasoning frames and inconsistent log entries. ([#3879](https://github.com/diegosouzapw/OmniRoute/pull/3879) — thanks @rdself)
-- **fix(opencode-plugin): include nested combo-refs in the LCD context window** — the OpenCode plugin now follows nested combo references when computing the least-common-denominator context window, so a combo nested inside another no longer reports an inflated window. ([#3910](https://github.com/diegosouzapw/OmniRoute/pull/3910) — thanks @herjarsa)
-- **fix(models): correct the failed-model auto-hide defaults** — the defaults governing when a failed model is auto-hidden were corrected, and auto-hide is now opt-in so models are no longer dropped unexpectedly. ([#3930](https://github.com/diegosouzapw/OmniRoute/pull/3930) — thanks @rdself)
-- **fix(openrouter): show the preset field when editing a connection** — the connection-preset field appeared only when creating a connection, not when editing one; it now appears in both (follow-up to #3878). ([#3921](https://github.com/diegosouzapw/OmniRoute/pull/3921) — thanks @rdself)
-- **fix(sse): announce the assistant role on the first delta (Responses→Chat)** — the first SSE delta of a Responses-API→Chat-Completions stream now carries `role: "assistant"`, which strict OpenAI-compatible clients expect before content deltas. ([#3911](https://github.com/diegosouzapw/OmniRoute/pull/3911) — thanks @diego-anselmo)
-- **fix(vertex): add the generative-language scope so SA-JSON model discovery works** — Vertex service-account (SA-JSON) model discovery failed without the `generative-language` OAuth scope; the scope is now requested. ([#3922](https://github.com/diegosouzapw/OmniRoute/pull/3922) — thanks @artickc)
-- **fix(proxy): direct-connection fallback for control-plane ops when a pinned proxy is unreachable** — control-plane operations (validation, discovery) now fall back to a direct connection when a connection's pinned proxy is unreachable, instead of failing outright. ([#3906](https://github.com/diegosouzapw/OmniRoute/pull/3906) — thanks @zhiru)
-- **fix(providers): prevent zombie-socket hangs for zai/glm and tighten the default keepAlive** — zai/glm could hang on dead keep-alive sockets; the default keepAlive was tightened to evict zombie sockets. ([#3907](https://github.com/diegosouzapw/OmniRoute/pull/3907) — thanks @insoln)
-- **fix(setup): remove the stale CJS bundle check from setup-open-code** — the OpenCode setup helper no longer checks for a CJS bundle that the now ESM-only plugin no longer ships. ([#3908](https://github.com/diegosouzapw/OmniRoute/pull/3908) — thanks @herjarsa)
-- **fix(opencode-plugin): drop the CJS bundle to fix the OpenCode plugin loader** — the plugin is now ESM-only, fixing the OpenCode loader which failed on the dual CJS/ESM build. ([#3883](https://github.com/diegosouzapw/OmniRoute/pull/3883) — thanks @herjarsa)
-- **fix(mcp): fall back to `node:sqlite` when the better-sqlite3 binding is missing** — the MCP server now falls back to Node's built-in `node:sqlite` when the native better-sqlite3 binding is unavailable, instead of crashing. ([#3887](https://github.com/diegosouzapw/OmniRoute/pull/3887) — thanks @megamen32)
-- **fix(models): correct the generate-models alias lookup** — alias resolution during model generation was corrected so aliased model ids resolve to their canonical entry. ([#3870](https://github.com/diegosouzapw/OmniRoute/pull/3870) — thanks @YunyunZhai)
-- **fix(combo): guard the candidate pool against an empty array** — combo candidate-pool selection no longer throws when the pool resolves to an empty array. ([#3871](https://github.com/diegosouzapw/OmniRoute/pull/3871) — thanks @YunyunZhai)
-
-### 🔒 Security & Hardening
-
-- **fix(security): bump form-data + vite (2 HIGH), harden workflow template-injection & allowlist guarded `workflow_run`** — two HIGH Dependabot advisories (`form-data`, `vite`) were upgraded; GitHub Actions workflows were hardened against `${{ }}` template-injection (untrusted values now passed via `env:`); and the guarded `workflow_run` trigger was allowlisted. ([#3949](https://github.com/diegosouzapw/OmniRoute/pull/3949) — thanks @diegosouzapw)
-
-### 🧹 Internal / Quality / Docs
-
-- **fix(ci): grant `contents: write` to the npm publish job for SBOM attach** — the v3.8.25 TokenPermissions hardening set the npm-publish `publish` job to `contents: read`, but its "Attach SBOM to GitHub Release" step (`gh release upload`) needs `contents: write` and failed with HTTP 403 on the v3.8.25 release (npm / GitHub Packages / opencode-plugin / Docker / Electron all published fine; only the SBOM attach broke — the v3.8.25 SBOM was attached manually). ([#3874](https://github.com/diegosouzapw/OmniRoute/pull/3874) — thanks @diegosouzapw)
-- **ci(quality): make zizmor / gitleaks / osv scanners functional + freeze advisory baselines** — the supply-chain scanners are now actually executed (correct install + invocation) with frozen advisory baselines so new findings surface as diffs. ([#3947](https://github.com/diegosouzapw/OmniRoute/pull/3947) — thanks @diegosouzapw)
-- **ci(quality): fix scanner install + size-limit preset, promote `codeqlAlerts` to blocking** — corrected the scanner install and the size-limit preset, and promoted the `codeqlAlerts` ratchet from advisory to blocking. ([#3945](https://github.com/diegosouzapw/OmniRoute/pull/3945) — thanks @diegosouzapw)
-- **ci(quality): wire Stryker mutation testing as an advisory nightly** — Stryker mutation testing runs nightly (advisory) — Quality Gates Fase 7 · Task 11. ([#3898](https://github.com/diegosouzapw/OmniRoute/pull/3898) — thanks @diegosouzapw)
-- **ci(quality): freeze per-module coverage floors + wire require-tighten (advisory)** — per-module coverage floors are frozen with an advisory "require-tighten" check that flags modules drifting below their floor. ([#3901](https://github.com/diegosouzapw/OmniRoute/pull/3901) — thanks @diegosouzapw)
-- **ci(quality): enforce the stale-allowlist check on `check-known-symbols`** — stale allowlist entries (suppressing a symbol that no longer exists) now fail the gate — Fase 6A.3 follow-up. ([#3899](https://github.com/diegosouzapw/OmniRoute/pull/3899) — thanks @diegosouzapw)
-- **test(ci): de-flake pipeline-payloads via per-test re-seed + honest reset** — the pipeline-payloads suite now re-seeds per test and performs an honest cache reset, eliminating a cross-test ordering flake. ([#3893](https://github.com/diegosouzapw/OmniRoute/pull/3893) — thanks @diegosouzapw)
-- **fix(ci): drop the `secrets`-in-job-`if` from nightly-llm-security** — referencing `secrets` in a job-level `if` caused a `startup_failure` on push; the gating was moved so the workflow starts cleanly. ([#3892](https://github.com/diegosouzapw/OmniRoute/pull/3892) — thanks @diegosouzapw)
-- **test: reconcile the runtime-timeouts keepAlive baseline to 4000 after the #3907 source revert** — the keepAlive assertion was realigned to the source value (4000) after #3907's source-side revert. ([#3933](https://github.com/diegosouzapw/OmniRoute/pull/3933) — thanks @diegosouzapw)
-- **chore(repo): nest quality-gate state under `config/quality`, declutter the repo root** — baselines / allowlists / metrics moved under `config/quality/`, trimming the tracked root file count. ([#3896](https://github.com/diegosouzapw/OmniRoute/pull/3896) — thanks @diegosouzapw)
-- **docs: refresh the provider count to 226 + regenerate `PROVIDER_REFERENCE.md`** — the README advertised a stale `177 providers`; the canonical generator (`scripts/docs/gen-provider-reference.ts`) now reports **226 unique provider IDs**, so the README badges/anchors and the generated provider reference were brought in sync. Also adds a documentation audit/sync report. (thanks @diegosouzapw)
-- **docs: sync all documentation to v3.8.24 + count-guard & wiki/prose CI** — a full documentation sync with a strict provider/locale count-guard plus Vale / markdownlint prose CI. ([#3804](https://github.com/diegosouzapw/OmniRoute/pull/3804) — thanks @diegosouzapw)
-- **docs: regenerate stale counts to canonical values** — 226 providers / 87 MCP tools / 15 strategies / 42 locales. ([#3904](https://github.com/diegosouzapw/OmniRoute/pull/3904) — thanks @diegosouzapw)
-- **docs(quality): correct the stale gate count + add an opt-in agent-lsp scaffold** — ([#3902](https://github.com/diegosouzapw/OmniRoute/pull/3902) — thanks @diegosouzapw)
-- **docs(mcp): correct the MCP tool-inventory diagram source + text to 87 tools** — ([#3909](https://github.com/diegosouzapw/OmniRoute/pull/3909) — thanks @diegosouzapw)
-- **docs: update the compression section to the 9-engine multi-layer stack** — ([#3894](https://github.com/diegosouzapw/OmniRoute/pull/3894) — thanks @diegosouzapw)
-- **ci(docs): automate GitHub wiki sync (add missing pages + cover counts)** — ([#3900](https://github.com/diegosouzapw/OmniRoute/pull/3900) — thanks @diegosouzapw)
-- **docs: require a dedicated git worktree + branch per development task (Hard Rule #19)** — codifies the worktree-isolation rule after the shared-checkout incidents. ([#3939](https://github.com/diegosouzapw/OmniRoute/pull/3939) — thanks @diegosouzapw)
-- **fix(docs): add MDX frontmatter to `DOCUMENTATION_AUDIT_REPORT` so the fumadocs build passes** — the audit report lacked the `title:` frontmatter MDX pages require. (thanks @diegosouzapw)
-
----
-
-## [3.8.25] — 2026-06-14
-
-### ✨ New Features
-
-- **feat(compression): pluggable compression engines + async pipeline + Compression Studios** — a new prompt-compression subsystem with selectable engines (Lite / Aggressive / Ultra), an asynchronous compression pipeline wired into the chat core, and "Compression Studios" tooling for inspecting and tuning compression. ([#3848](https://github.com/diegosouzapw/OmniRoute/pull/3848))
-- **feat(compression-ui): unified compression configuration UI** — a Compression Hub with per-engine pages (Lite / Aggressive / Ultra), a combos editor, a dedicated sidebar entry, and live-WS default-on. ([#3860](https://github.com/diegosouzapw/OmniRoute/pull/3860))
-- **feat(security): prompt-injection guard across every LLM route + red-team suite** — the prompt-injection guard now runs on all LLM routes (chat, responses, embeddings, images, audio, rerank, search, moderations, videos, music) with a shared input sanitizer and a promptfoo-based red-team suite (Quality Gates Fase 8 · Bloco D). ([#3857](https://github.com/diegosouzapw/OmniRoute/pull/3857))
-- **feat(kiro): live per-account model discovery** — Kiro now discovers each account/tier's entitled models via CodeWhisperer `ListAvailableModels` (region-matched, with a static-catalog fallback). ([#3836](https://github.com/diegosouzapw/OmniRoute/pull/3836) — thanks @artickc)
-- **feat(gemini/vertex): surface Veo video models in dynamic discovery** — Veo video models (`predictLongRunning`) now appear in Gemini/Vertex dynamic model discovery. ([#3839](https://github.com/diegosouzapw/OmniRoute/pull/3839) — thanks @artickc)
-- **feat(mimocode): per-account proxy for multi-account round-robin** — each mimocode account can route through its own proxy (resolved per account by fingerprint via `runWithProxyContext`), with a "Distribute proxies" UI helper. ([#3837](https://github.com/diegosouzapw/OmniRoute/pull/3837) — thanks @pizzav-xyz)
-- **feat(intelligence): expose Arena ELO sync as a feature flag** — the LM Arena ELO leaderboard sync is now toggleable (`ARENA_ELO_SYNC_ENABLED`, DB-override + env fallback). ([#3821](https://github.com/diegosouzapw/OmniRoute/pull/3821) — thanks @rdself)
-
-### 🐛 Fixed
-
-- **test(oauth): prove refresh_token preservation for the real gemini-cli / antigravity dispatch** — the #3679/#3766 regression test used a synthetic provider that routes through the generic `tokenUrl` path, so the fix was never proven for the actual Google-family providers, which dispatch through `refreshGoogleToken()` against the hardcoded `OAUTH_ENDPOINTS.google.token`. Added a test that drives `checkConnection` through the real `gemini-cli`/`antigravity` path (redirecting the Google token endpoint to a local server returning `invalid_grant`) and asserts the `refresh_token` is preserved (not nulled) — confirming these connections are not spuriously destroyed on a failed refresh. ([#3850](https://github.com/diegosouzapw/OmniRoute/issues/3850) — thanks @3xa228148)
-- **fix(oauth): clear setup message for GitLab Duo instead of "Internal server error"** — adding a GitLab Duo connection without a registered OAuth client returned an opaque `Internal server error` at the Add Connection step. `buildAuthUrl` **threw** when `GITLAB_DUO_OAUTH_CLIENT_ID` was missing, and the route swallowed it into a generic 500. It now returns `null` (mirroring the Qoder provider) and the authorize route surfaces an actionable message: register an OAuth app at `https://gitlab.com/-/profile/applications` with redirect URI `http://localhost:20128/callback` and scopes `ai_features read_user`, then set `GITLAB_DUO_OAUTH_CLIENT_ID`. ([#3861](https://github.com/diegosouzapw/OmniRoute/issues/3861) — thanks @sidinsearch)
-- **fix(db): persist the "Keep latest backups" retention setting** — changing the backup-retention count in Settings → Database backup retention had no effect: it always snapped back to 20 on refresh (and editing `.env` post-start was ignored too, since `process.env` isn't reloaded). `getDbBackupMaxFiles()` only read the `DB_BACKUP_MAX_FILES` env var — there was no setter and no persisted value. The value now round-trips through a dedicated `key_value` store (`getDbBackupMaxFiles` precedence: env override → persisted UI value → default 20), and the "Clean old backups" action persists the chosen count. Existing installs keep the historical default of 20 until explicitly changed. ([#3834](https://github.com/diegosouzapw/OmniRoute/issues/3834) — thanks @netstratego)
-- **fix(sse): clamp Gemini thinking budget to the model's real cap (`reasoning_effort`/`effort=high` 400)** — translating OpenAI `reasoning_effort=high` (and Claude-Code `output_config.effort=high`) to a Gemini target sent a hardcoded `thinkingBudget: 32768`, which exceeds Flash-tier Gemini's real max of 24576 → upstream HTTP 400 (the `thinkingLevel=high` path already used 24576 and worked on the same model). `gemini-2.5-flash` now declares its real `thinkingBudgetCap` (24576) so the existing `capThinkingBudget()` chokepoint actually clamps, and the Claude→Gemini `output_config.effort` path — which previously sent the raw value with no cap at all — now routes through the same clamp (pro-tier, real cap 32768, is left untouched). ([#3842](https://github.com/diegosouzapw/OmniRoute/issues/3842) — thanks @andrea-kingautomation)
-- **fix(intelligence): run pricing + models.dev sync from the live startup path** — like the Arena ELO sync (v3.8.24), the external **pricing sync** (`PRICING_SYNC_ENABLED`) and the **models.dev capability sync** (Settings → AI toggle) were only initialized from `server-init.ts`, which the Next standalone runtime never executes — and models.dev had no caller at all. Their toggles were inert in production. Both are now initialized from `instrumentation-node.ts` (self-gated, opt-in preserved, non-blocking, never fatal). (thanks @diegosouzapw)
-- **test(proxy): guard the per-connection 'direct' bypass over a global proxy + clearer label** — the per-connection "Proxy Off" toggle (`proxyEnabled: false`) already overrides a configured **global** proxy (`resolveProxyForConnection` short-circuits to `level: "direct"` before the global step). Added an explicit regression test proving the bypass beats a global assignment (and round-trips on re-enable), and relabeled the UI to "Direct (bypass proxy)" so operators recognize it. Closes the verification gap in [#2996](https://github.com/diegosouzapw/OmniRoute/issues/2996). (thanks @diegosouzapw)
-- **feat(connections): per-connection "disable cooldown" opt-out** — a connection can now opt out of the transient cooldown (`providerSpecificData.disableCooling`, with a toggle in the Edit Connection modal). When set, a recoverable failure still records the error/backoff but does **not** take the connection out of rotation, so it stays eligible for selection — useful for a primary key you never want parked on a blip. Terminal states (banned / expired / credits_exhausted) still apply. ([#2997](https://github.com/diegosouzapw/OmniRoute/issues/2997) — thanks @diegosouzapw)
-- **fix(combo): restore sessionless combo stickiness + reasoning-aware readiness (504 / TPS regression after v3.8.14)** — #3399 (v3.8.16) replaced the `<omniModel>`-tag combo pinning with a server-side context-cache pin gated on a client `sessionId`. Clients that send no session id (most OpenAI-compatible tools) lost combo stickiness, so combos re-ran strategy selection every turn → upstream prompt-cache misses → cold high-reasoning starts (~78s) → intermittent `[504] Upstream request did not return response headers` + TPS collapse (only on combos). The pin now falls back to a stable per-conversation fingerprint (`extractSessionAffinityKey(body)`) when no session id is present — **only when `context_cache_protection` is on**, so #3399's anti-leak behaviour is preserved. Separately, the stream-readiness window now grants the +30s reasoning budget **unconditionally** for high-reasoning Codex GPT-5.x (small high-reasoning prompts were 504-ing at the 80s base regardless of stickiness). ([#3825](https://github.com/diegosouzapw/OmniRoute/issues/3825) — thanks @bypanghu)
-- **test(combo): cover the `skipProviderBreaker` consumer gate** — the producer was tested but the consumer (whether a failed combo target trips the whole-provider circuit breaker) was not; the breaker decision is now an exported pure predicate (`shouldRecordProviderBreakerFailure`, behaviour-identical) with direct tests asserting a `connection_cooldown` 503 does not trip the breaker while a plain 503 does. Closes another deferred test gap from [#2743](https://github.com/diegosouzapw/OmniRoute/issues/2743). (thanks @diegosouzapw)
-- **fix(providers): surface the real Devin error + correct the Windsurf auth instructions** — Devin chat returned a generic 502 "Invalid SSE response for non-streaming request" that swallowed the real cause (e.g. "Devin CLI not found"): an error-only SSE chunk (no `choices`) is now propagated with its sanitized message. The Windsurf "Visit windsurf.com/show-auth-token" instruction (the bare URL shows no token without an IDE-supplied `?state=`) now directs users to the `Windsurf: Provide Auth Token` command-palette flow. ([#3324](https://github.com/diegosouzapw/OmniRoute/issues/3324) — thanks @mikmaneggahommie)
-- **fix(grok-web): clearer 403 message for anti-bot / IP-reputation blocks** — a Grok Web subscription validating from a flagged datacenter/VPS IP got a 403 that read like an invalid cookie, sending users to chase a cookie that was actually fine. A non-auth 403 (Cloudflare challenge / anti-bot body) now returns a message stating the cookie is likely OK and the block is IP-reputation-based — retry from a residential IP or configure a proxy (auth-shaped 403s keep the re-paste guidance). ([#3474](https://github.com/diegosouzapw/OmniRoute/issues/3474) — thanks @friedtofu1608)
-- **fix(db): make the mass-pending-migrations safety threshold env-overridable** — restoring a backup DB from an older version could trip "Detected N pending migrations … threshold is 50" with no way to override the hardcoded `50`. The threshold is now configurable via `OMNIROUTE_MAX_PENDING_MIGRATIONS` (resolved at startup; `0` disables the check). ([#3416](https://github.com/diegosouzapw/OmniRoute/issues/3416) — thanks @samuraiIT)
-- **test(proxy): cover the Vercel-relay `proxyFetch` path** — net-new tests for `buildVercelRelayHeaders` and the `vercel`-type relay short-circuit (`x-relay-target`/`-path`/`-auth`, TCP-skip, missing-auth fail-closed), closing one of the deferred test gaps tracked in [#2743](https://github.com/diegosouzapw/OmniRoute/issues/2743). (thanks @diegosouzapw)
-- **fix(cli): surface `omniroute runtime repair` in the native-module error messages** — after a Node major upgrade, `better-sqlite3`'s prebuilt binary mismatches the ABI and the service can crash-loop; the error only mentioned `npm rebuild better-sqlite3` (which fails for global / no-toolchain installs). The startup + SQLite error hints now also point to the existing self-heal command `omniroute runtime repair` (rebuilds into a user-writable runtime), and a top-level `omniroute repair` alias was added. ([#3476](https://github.com/diegosouzapw/OmniRoute/issues/3476) — thanks @Rahulsharma0810)
-- **fix(antigravity): per-request Pro-family upstream-id fallback chain (`gemini-3.1-pro-high` 400)** — Antigravity silently renamed the Gemini 3.1 Pro-high upstream id, so `gemini-3.1-pro-high` started returning HTTP 400 (while `-low` still worked) and the live id can't be determined statically (competitor proxies disagree). The executor now retries alternative ids on a 400 (`gemini-3.1-pro-high` → `gemini-pro-agent` → `gemini-3-pro-high`, analogous for pro-low), bounded and only on a 400, with zero extra cost on the happy path; the 1:1 tier-passthrough invariant is preserved (the chain is request-time, not a static alias remap). ([#3786](https://github.com/diegosouzapw/OmniRoute/issues/3786) — thanks @aliaksandrsen)
-- **fix(sse): retry once on an early stream close (`STREAM_EARLY_EOF`) for single-model requests** — flaky OpenAI-compatible upstreams (e.g. NVIDIA NIM with minimax-m3 / qwen3.5 / glm-5.1) intermittently send HTTP 200 then close the SSE with zero useful frames, surfacing as a 502 "Stream ended before producing useful content". Only Antigravity got an early-close retry; every other provider returned the 502 immediately on the non-combo single-model path. A bounded one-retry (early-close only — not readiness-timeout — and without marking the account unavailable) now generalizes it. (The separate qwen-web validation SSRF part of the same report was already fixed in v3.8.24, [#3767](https://github.com/diegosouzapw/OmniRoute/pull/3767).) ([#3758](https://github.com/diegosouzapw/OmniRoute/issues/3758) — thanks @Svatosalav)
-- **fix(models): preserve eye-hidden models across auto-sync / import** — hiding models via the visibility (eye) toggle to keep only a combo's models was undone on every model import or auto-sync, which re-showed all of them. The sync re-import treated "hidden" identically to "deleted" and dropped both; a distinct `isDeleted` marker now separates the trash/delete path (still dropped on re-import, #3199) from the eye toggle (preserved as listed-but-hidden), and eye-hidden models are no longer re-aliased into the routable catalog on sync. ([#3782](https://github.com/diegosouzapw/OmniRoute/issues/3782) — thanks @xenstar)
-- **fix(providers): correct the lmarena cookie hint (`session` → `arena-auth-prod-v1`)** — the lmarena credential hint asked for a cookie named `session`, but lmarena.ai's real auth cookie is `arena-auth-prod-v1`, so users who pasted only `session=…` hit validation failures. The credential name, placeholder and storage keys now use the correct name (the legacy `session` key is retained for back-compat with already-saved credentials). ([#3810](https://github.com/diegosouzapw/OmniRoute/issues/3810) — thanks @xspylol)
-- **fix(reasoning): normalize OpenAI-compatible `max` effort to `xhigh` by default** — OpenAI-compatible providers do not accept literal `max`, but some upstreams (for example DeepSeek through OpenRouter) support `xhigh`; `max` now maps to `xhigh` unless the target model explicitly opts out of `xhigh`, with Claude alias variants still honoring the canonical Claude opt-out list. ([#3826](https://github.com/diegosouzapw/OmniRoute/pull/3826) — thanks @rdself)
-- **fix(combo): return the replay response on the round-robin streaming path** — a round-robin combo with a streaming target returned a body already locked by the readiness peek, surfacing as a 500 "ReadableStream is locked"; the round-robin path now returns the replay clone like the priority path does. ([#3811](https://github.com/diegosouzapw/OmniRoute/pull/3811) — thanks @0xtbug)
-- **fix(claude): strip the reasoning-effort suffix from Claude model ids** — Claude ids carrying an effort suffix (`…-low` … `…-max`) 404'd upstream and tripped the circuit breaker into a misleading "rate-limited" state; the suffix is now stripped before dispatch. ([#3807](https://github.com/diegosouzapw/OmniRoute/pull/3807) — thanks @zhiru)
-- **fix(sse): flush routed SSE chunks promptly (ping/zombie readiness filter)** — combo stream-readiness now filters ping/zombie frames so routed SSE chunks stream out without waiting on the readiness window. ([#3759](https://github.com/diegosouzapw/OmniRoute/pull/3759) — thanks @rdself)
-- **fix(models): don't auto-hide transient (rate-limited / timeout) failures on Test All** — a parallel Test All across many models could rate-limit an account and auto-hide every model that 429'd / timed out (dropping them from `/v1/models`); transient failures now surface an error state but stay visible. ([#3849](https://github.com/diegosouzapw/OmniRoute/pull/3849) — thanks @lukmanc405)
-- **fix(quota): surface OpenCode Go's missing quota-API as a latched diagnostic** — OpenCode Go keys whose quota endpoints return 404/401 no longer hammer the dead endpoints; the gap is latched with a clear message and an `OMNIROUTE_OPENCODE_GO_QUOTA_URL` override hint. ([#3838](https://github.com/diegosouzapw/OmniRoute/pull/3838) — thanks @adivekar-utexas)
-- **fix(pricing): add the missing Kiro model pricing rows** — Kiro models the registry serves (e.g. `claude-sonnet-4.6`) had no pricing row and reported $0.00; the rows were added. ([#3835](https://github.com/diegosouzapw/OmniRoute/pull/3835) — thanks @artickc)
-- **fix(ui): render country flags via flagcdn SVGs for Windows compatibility** — Windows doesn't render regional-indicator flag emoji; flags now use flagcdn SVGs with an emoji fallback. ([#3814](https://github.com/diegosouzapw/OmniRoute/pull/3814) — thanks @rafacpti23)
-- **fix(ui): expand the request log table with a vertical resize handle** — the request log table now shows ~10 rows and can be resized vertically. ([#3820](https://github.com/diegosouzapw/OmniRoute/pull/3820) — thanks @rafacpti23)
-- **fix(i18n): translate the missing `embeddedServices` keys across 37 locales** — the `embeddedServices` strings showed `__MISSING__` in 37 locales; they are now translated. ([#3819](https://github.com/diegosouzapw/OmniRoute/pull/3819) — thanks @rafacpti23)
-
-### 🔒 Security & Hardening
-
-- **fix(security): CCR cross-tenant IDOR — per-principal scope store + bounded memory** — the compression CCR scope store was shared across principals, allowing cross-tenant reads; it is now scoped per-principal with bounded memory. ([#3859](https://github.com/diegosouzapw/OmniRoute/pull/3859))
-- **feat(supply-chain): build provenance, SBOM, Trivy scan & OpenSSF Scorecard (advisory)** — added npm build provenance, a CycloneDX SBOM, Trivy image scanning, and an OpenSSF Scorecard workflow (Quality Gates Fase 8 · Bloco A, advisory). ([#3824](https://github.com/diegosouzapw/OmniRoute/pull/3824))
-
-### 🧹 Internal / Quality / Docs
-
-- **Consolidate the email-privacy control into Settings → Appearance** — the per-page email-privacy toggles were replaced by a single global switch. ([#3822](https://github.com/diegosouzapw/OmniRoute/pull/3822) — thanks @rdself)
-- **docs(ui): clarify the routing-settings copy (strategy sync + sticky limit)** — ([#3843](https://github.com/diegosouzapw/OmniRoute/pull/3843) — thanks @adivekar-utexas)
-- **Quality Gates — Fase 7 & 8** — promoted the dead-code / cognitive-complexity / type-coverage ratchets to blocking, installed advisory CI scanners (gitleaks / osv / actionlint / zizmor), and added property + golden + SSE-correctness tests and a runtime-resilience (chaos / heap-growth / k6 soak) suite. ([#3809](https://github.com/diegosouzapw/OmniRoute/pull/3809), [#3858](https://github.com/diegosouzapw/OmniRoute/pull/3858), [#3808](https://github.com/diegosouzapw/OmniRoute/pull/3808), [#3854](https://github.com/diegosouzapw/OmniRoute/pull/3854))
-- **fix(docs): add MDX frontmatter to `SUPPLY_CHAIN.md`** — the new security doc lacked the `title:` frontmatter that MDX pages require, which broke the production Build + Docker Hub publish; the frontmatter was added. ([#3864](https://github.com/diegosouzapw/OmniRoute/pull/3864))
-- **chore(deps): bump `aquasecurity/trivy-action` 0.28.0 → 0.36.0** ([#3862](https://github.com/diegosouzapw/OmniRoute/pull/3862))
-- **chore(quality): reconcile the file-size ratchet baseline for Prettier-inflated v3.8.25 fixes + `chat.ts` growth** — the per-file size baseline was re-frozen to absorb the formatting/line-count growth from this cycle's chat-core and combo fixes (manual edits, never an automatic upward ratchet). ([#3823](https://github.com/diegosouzapw/OmniRoute/pull/3823), [#3833](https://github.com/diegosouzapw/OmniRoute/pull/3833) — thanks @diegosouzapw)
-- **test(suite): green the unit suite at release time — align stale tests to this cycle's intended behavior + de-flake two new suites** — release-gate housekeeping: updated tests that lagged behind intended behavior changes (OpenCode Go latched quota message #3838, the email-privacy control consolidated into Settings #3822, SOCKS5 default-on proxy-type message, the `[id]` provider-detail strangler-fig decomposition #3501, Vertex Express-mode keys, Antigravity discovery using a current user-callable model id) and the same-provider 503 fall-through resilience test; de-flaked the compression benchmark reproducibility test (sequential passes) and the ServiceSupervisor crash test (poll instead of fixed sleep). No production code changed. Also documented `OMNIROUTE_MAX_PENDING_MIGRATIONS` (#3416) in `.env.example` + `ENVIRONMENT.md`. (thanks @diegosouzapw)
-
----
-
-## [3.8.24] — TBD
-
-_See English CHANGELOG for v3.8.24 details._
-
----
-
-## [3.8.22] — TBD
-
-_See English CHANGELOG for v3.8.22 details._
-
----
-
-## [3.8.21] — 2026-06-11
-
-_See [English CHANGELOG](/CHANGELOG.md) for v3.8.21 details._
-
----
-
-## [3.8.20] — Unreleased
-
-_Development cycle in progress._
-
----
-
-## [3.8.19] — Unreleased
-
-_Development cycle in progress._
-
----
-
-## [3.8.18] — Unreleased
-
-_Development cycle in progress._
-
----
-
-## [3.8.17] — Unreleased
-
-_Development cycle in progress._
-
----
-
-## [3.8.16] — Unreleased
-
-_Development cycle in progress._
-
----
-
-## [3.8.15] — Unreleased
-
-_Development cycle in progress._
-
----
-
-## [3.8.14] — Unreleased
-
-_Development cycle in progress._
-
----
-
-## [3.8.13] — Unreleased
-
-_Development cycle in progress._
-
----
-
-## [3.8.12] — Unreleased
-
-_Development cycle in progress._
-
----
-
-## [3.8.11] — Unreleased
-
-_Development cycle in progress._
-
----
-
-## [3.8.10] — Unreleased
-
----
-
-## [3.8.9] — Unreleased
-
----
-
-## [3.8.8] — 2026-06-01
-
-### Added
-
-- **Plugins framework** (`src/lib/plugins/`, `/api/plugins/*`, `/dashboard/plugins`) — hooks + registry unification, plugin SDK (`definePlugin`), worker-thread sandbox, per-plugin hook rate limiting, SHA-256 integrity verification, semver-gated upgrade, and execution analytics. Plugin routes are loopback-only (`isLocalOnlyPath`) and `child_process` exec is opt-in via `OMNIROUTE_PLUGINS_ALLOW_EXEC`. (#2913 / #3041 — thanks @oyi77)
-- **Plugin system: response-hook wiring + startup load + example plugin** — wires the plugin `onResponse` hook into the chat success path, loads active plugins on server startup so they survive restarts (`pluginManager.loadAll()` in `server-init`), and ships a `welcome-banner` example plugin (`examples/plugins/`) plus a comprehensive plugin test suite. (#3045 — thanks @oyi77)
-- **API key option: disable non-published models** — a per-key flag restricting the key to discovered, public models (combos / `auto/*` / `qtSd/*` routing still allowed). (#3017 — thanks @androw)
-- **SessionPool — modular & provider-agnostic** (`open-sse/services/sessionPool/`) — pooled
-  cookie/session manager with round-robin fingerprint rotation (distinct fingerprint per pooled
-  session), per-session cooldown/backoff, and a provider-agnostic `webExecutorWrapper`. Adds pool
-  support for DuckDuckGo Web and LLM7 providers and an MCP `poolTools` toolset. (#2954 / #2978 — thanks @oyi77)
-- **AgentBridge** (`/dashboard/tools/agent-bridge`) — MITM proxy consolidating 9 IDE agents
-  (Antigravity, Kiro, GitHub Copilot, OpenAI Codex, Cursor IDE, Zed Industries, Claude Code,
-  Open Code, Trae stub) with server card, per-agent setup wizard, model mapping table,
-  bypass list, upstream CA cert support, and redirect from legacy `/dashboard/system/mitm-proxy`.
-  See `docs/frameworks/AGENTBRIDGE.md`. (#2858 — thanks @diegosouzapw)
-- **Traffic Inspector** (`/dashboard/tools/traffic-inspector`) — LLM-aware HTTPS debugger with
-  4 capture modes (AgentBridge hook, Custom Hosts DNS, HTTP_PROXY :8080, System-wide proxy),
-  DevTools split UI, 7 detail tabs (Conversation, Headers, Request, Response, Timing, LLM Details,
-  Stats), resizable panels, session recording (.har/.jsonl export), SSE stream merger,
-  conversation normalizer (multi-provider), system-prompt fingerprint colorization, and annotations.
-  See `docs/frameworks/TRAFFIC_INSPECTOR.md`.
-- **MITM handler base + 9 agent handlers** (`src/mitm/handlers/`) — `MitmHandlerBase` abstract
-  class with `hookBufferStart`/`hookBufferUpdate` for Traffic Inspector integration; concrete
-  handlers for all 9 agents.
-- **MITM targets registry** (`src/mitm/targets/`) — declarative `MitmTarget` shape per agent;
-  emits `DATA_DIR/mitm/targets.json` for dynamic `server.cjs` resolution.
-- **Traffic Inspector core** (`src/mitm/inspector/`) — `TrafficBuffer` in-memory ring,
-  `kindDetector`, `sseMerger` (MIT port from chouzz/llm-interceptor), `conversationNormalizer`
-  (MIT port), `contextKey` fingerprinting, `httpProxyServer`, `systemProxyConfig`.
-- **AgentBridge passthrough + bypass** (`src/mitm/passthrough.ts`) — TCP tunnel for
-  non-mapped hosts; bypass list with default sensitive-host patterns + user-defined patterns.
-- **Upstream CA cert** (`src/mitm/upstreamTrust.ts`) — `AGENTBRIDGE_UPSTREAM_CA_CERT` for
-  corporate TLS environments.
-- **Secret masking** (`src/mitm/maskSecrets.ts`) — sk-/Bearer/generic token masking before
-  any log or Traffic Inspector broadcast.
-- **DB migrations 073–075** — `agent_bridge_state`, `agent_bridge_mappings`,
-  `agent_bridge_bypass`, `inspector_custom_hosts`, `inspector_sessions`,
-  `inspector_session_requests`.
-- **~28 API routes** under `/api/tools/agent-bridge/` (12 routes) and
-  `/api/tools/traffic-inspector/` (16+ routes). All LOCAL_ONLY + SPAWN_CAPABLE.
-- **i18n** PT-BR + EN for all new keys in `agentBridge.*` and `trafficInspector.*` namespaces;
-  all other locales fall back to EN automatically.
-- **E2E smoke tests** — `tests/e2e/agent-bridge.spec.ts`,
-  `tests/e2e/traffic-inspector.spec.ts`, `tests/e2e/agent-bridge-traffic-cross.spec.ts`
-  (skip-gated on CI by `RUN_AGENT_BRIDGE_E2E` / `RUN_TRAFFIC_INSPECTOR_E2E` / `RUN_CROSS_E2E`).
-- **Documentation** — `docs/frameworks/AGENTBRIDGE.md` and `docs/frameworks/TRAFFIC_INSPECTOR.md`;
-  `docs/architecture/REPOSITORY_MAP.md` updated; `docs/reference/openapi.yaml` updated with
-  ~28 new routes and 20+ new schemas.
-- **i18n:** translate Ukrainian (uk-UA) menu and UI strings, plus complete uk-UA UI coverage (#2981 / #2988 — thanks @Lion-killer)
-- **providers:** add SiliconFlow endpoint selector (#2975 — thanks @xz-dev)
-- **oauth:** add Trae SOLO provider (work/code modes) (#2964 — thanks @S0yora)
-- **providers:** add Qwen Web (chat.qwen.ai) web-cookie provider (#2947 — thanks @oyi77)
-- **Quota Share Engine — multi-provider quota pools** — Monitoring/Costs reorg plus a Quota Share Engine: group selector, grouped pool cards, exclusive-quota API keys (`allowedQuotas`), `quotaShared-*` routing models via combos, a 3-step pool wizard (legacy Plans page retired), endpoint + key preview, and full pool editing. Adds quota-pool DB migrations. (#2859 / #3022 / #3032 — thanks @diegosouzapw)
-- **Dashboard page redesigns (Nav Restructure)** — agent-skills + omni-skills with a dynamic 42-skill catalog and MCP/A2A discovery (#2827); CLI Code's + CLI Agents + ACP Agents pages (#2839); translator friendly redesign, 5 tabs → 2 (#2847); functional `/batch` + `/batch/files` redesign (#2849); Playground Studio + Search Tools Studio (#2869); memory engine redesign — sqlite-vec + hybrid RRF + Studio UI (#2873). (thanks @diegosouzapw)
-- **notion:** add Notion as an MCP context source — 6 tools (`notion_search`, `notion_list_databases`, `notion_get_database`, `notion_query_database`, `notion_read`, `notion_append_blocks`) scoped under `read:notion` / `write:notion`, with dashboard "Context Sources" tab, settings API, and token persistence in `key_value` table (#2959)
-
-### Changed
-
-- Sidebar Tools group: added `agent-bridge` and `traffic-inspector` items after `cloud-agents`.
-- `/api/tools/agent-bridge/` and `/api/tools/traffic-inspector/` added to `LOCAL_ONLY_API_PREFIXES`
-  and `SPAWN_CAPABLE_PREFIXES` in `src/server/authz/routeGuard.ts`.
-- `.env.example`: documented 9 new env vars (`AGENTBRIDGE_UPSTREAM_CA_CERT`,
-  `INSPECTOR_BUFFER_SIZE`, `INSPECTOR_HTTP_PROXY_PORT`, `INSPECTOR_HTTP_PROXY_AUTOSTART`,
-  `INSPECTOR_TLS_INTERCEPT`, `INSPECTOR_SYSTEM_PROXY_GUARD_MINUTES`, `INSPECTOR_MAX_BODY_KB`,
-  `INSPECTOR_MASK_SECRETS`, `INSPECTOR_LLM_HOSTS_EXTRA`, `INSPECTOR_INTERNAL_INGEST_TOKEN`).
-
-### Fixed
-
-- **codex/providers:** `POST /api/providers/[id]/refresh` (the manual/auto "refresh
-  token" endpoint) no longer rotates rotating-refresh providers (Codex/OpenAI share
-  one Auth0 `client_id`). This was the last unguarded proactive-refresh entry point:
-  when the dashboard auto-refreshed every expiring connection on a page load (or an
-  old cached frontend bulk-called it), each Codex account's single-use refresh_token
-  was rotated, and Auth0 revoked the whole token family (`openai/codex#9648`) — every
-  account but the last died with `[403] <!DOCTYPE`. The endpoint now skips proactive
-  rotation for rotating providers and defers to the reactive, serialized 401 path
-  (same guard as `refreshAndUpdateCredentials` and the connection-test route).
-- **codex/quota:** opening the Quota / Providers dashboard no longer disconnects
-  Codex multi-account setups. The quota-sync path
-  (`refreshAndUpdateCredentials`) proactively refreshed every connection — for
-  rotating-refresh providers (Codex/OpenAI share one Auth0 `client_id`) it
-  refreshed siblings concurrently, so Auth0 revoked the whole token family
-  (`openai/codex#9648`) and every account but the last died with
-  `[403] <!DOCTYPE html>`. The quota path now skips proactive refresh for
-  rotating providers (`rotationGroupFor`) and reuses the current access*token,
-  deferring genuine expiry to the reactive, serialized 401 path. Defense in
-  depth: `serializeRefresh` now leaves a settle gap between two \_queued* sibling
-  refreshes (default 2000 ms, tunable via `CODEX_REFRESH_SPACING_MS`, `"0"` to
-  opt out) while releasing a lone refresh immediately, so the reactive path adds
-  no latency.
-- **payload-rules:** saved payload rules now survive a server restart. When no
-  in-memory override is set (fresh process before the boot hook ran, or a
-  separate module instance in the standalone build), `getPayloadRulesConfig`
-  now reads the DB-persisted rules (the source of truth) before the file config,
-  instead of silently returning the empty file default. (#2986)
-- **models/custom:** custom models can now carry a per-model `targetFormat`
-  override (e.g. an opencode-go custom model that must use the Anthropic Messages
-  shape). Previously custom models always routed as OpenAI-compatible because
-  `targetFormat` was neither persisted nor consulted at routing time. Threaded
-  through `addCustomModel`/`replaceCustomModels`/`updateCustomModel`, the API
-  schema/route, `getModelInfo`, and chatCore's targetFormat resolution. (#2905)
-- **providers/pollinations:** route to `gen.pollinations.ai/v1` instead of the
-  retired `text.pollinations.ai` host, which now returns `404 "legacy API"` for
-  all models. The gen gateway is the current OpenAI-compatible endpoint. (#2987)
-- **executors/codex:** drop the CLI-injected `image_generation` hosted tool for
-  free-plan Codex accounts (`workspacePlanType === "free"`), which can't run it
-  server-side and would otherwise get an upstream 400. Paid plans keep it.
-  (mirrors CLIProxyAPI's free-plan guard; spun off from the #2980 analysis)
-- **dashboard:** custom providers (`openai-compatible-*` / `anthropic-compatible-*`)
-  now show their user-given node name instead of the raw UUID id across the
-  active-requests panel, proxy logger, and home-page provider topology. The
-  display-label resolver was extracted into a shared util reused by all surfaces
-  (previously only the request-log viewer resolved it). (#2968)
-- **docker:** the standalone launcher (Docker `CMD`) now honors
-  `OMNIROUTE_MEMORY_MB` (default 512, clamped [64, 16384]) and overrides the
-  image `NODE_OPTIONS` fallback, fixing random OOM crashes under load / with
-  large SQLite DBs. Previously only `omniroute serve` honored the knob. (#2939)
-- **docker:** add a `web` compose profile (`omniroute-web`, target `runner-web`,
-  image `omniroute:web`) so web-cookie providers (gemini-web, claude-web,
-  claude-turnstile) work out of the box — the default `base` image ships without
-  Chromium/Playwright, which made those providers fail with
-  "Executable doesn't exist at .../ms-playwright/chromium...". (#2832)
-- **routing/codex:** fix two gpt-5.5 Codex defects (#2877). (A) For a Codex-only
-  account, a bare `gpt-5.5` Responses request was rerouted to codex with the
-  model hardcoded to `gpt-5.5-medium` (`chatHelpers.ts`); the executor read that
-  `-medium` suffix as an explicit `modelEffort` that (per #2331) overrode a
-  client `reasoning.effort=xhigh`, silently demoting it — now it keeps the bare
-  `gpt-5.5` id so the client effort wins. (B) `gpt-5.5-xhigh`/`-high`/`-low`
-  misrouted to `openai` (→ "No credentials" for codex-only users); the suffixed
-  variants are now in `CODEX_PREFERRED_UNPREFIXED_MODELS` so they infer codex.
-- **sse/chatCore:** remove a duplicate `const settings` declaration in
-  `handleChatCore` (introduced alongside the per-key stream-default-mode
-  feature). The same-scope redeclaration made esbuild/tsx fail with
-  "The symbol 'settings' has already been declared", which turned every unit
-  test that imports chatCore red and broke the production build. The earlier
-  consolidated `settings` const is now reused.
-- **db/migrations:** resolve a `077` migration version collision
-  (`077_api_key_stream_default_mode.sql` vs `077_quota_pools.sql`) that made
-  `getMigrationFiles()` throw and blocked `getDbInstance()` at startup (app would
-  not boot; every DB-touching test was red). Renumbered the dependency-free,
-  idempotent `quota_pools` migration to `085`, kept the non-idempotent
-  `api_key_stream_default_mode` `ALTER` at `077`, added a retroactive
-  `isSchemaAlreadyApplied` guard (case `085`), and a regression test enforcing
-  unique migration prefixes.
-- **routing/reasoning-replay:** OpenCode `big-pickle` (provider `opencode`/`oc`
-  and `opencode-zen`) now declares the interleaved `reasoning_content` contract
-  via a new `RegistryModel.interleavedField` field, so follow-up/tool-use turns
-  replay reasoning_content. Previously `big-pickle` matched no replay pattern and
-  failed with `[400] The reasoning_content in the thinking mode must be passed
-back to the API` (its DeepSeek-thinking upstream is not detectable from the
-  model id, and `requiresReasoningReplay` does not consume `supportsReasoning`).
-  `getResolvedModelCapabilities` now surfaces the registry `interleavedField`. (#2900)
-- **providers/github-copilot:** built-in GitHub Copilot Claude Opus and Gemini
-  models (`claude-opus-4.7`, `claude-opus-4-5-20251101`, `gemini-3.1-pro-preview`,
-  `gemini-3-flash-preview`) no longer carry `targetFormat: "openai-responses"`, so
-  they route through `chat/completions` (the provider default, like the working
-  `claude-opus-4.6`) instead of the Responses API, which Copilot does not serve for
-  non-OpenAI models (returned `[400]`). Native OpenAI `gpt-*` models keep the
-  Responses API. (#2911)
-- **translator/responses:** Codex Desktop injects an `image_generation` hosted
-  tool into every Responses API request (even text-only ones), which OmniRoute
-  rejected with `[400] image_generation tool type is not supported`. It is now
-  treated like `tool_search`: allowed past the tool-type validator and dropped
-  silently from the tools array before forwarding to Chat Completions. (#2950)
-- **combo/builder:** no-auth OpenCode Free combo entries now use the `oc/` routing
-  alias instead of the `opencode/` prefix. `parseModel("opencode/<model>")`
-  resolves to the `opencode-zen` api-key tier (via a manual `ALIAS_TO_PROVIDER_ID`
-  override), so combos built with the bare provider id misrouted away from the
-  no-auth `opencode` provider; `oc/<model>` resolves correctly. (#2901)
-- **resilience/providers:** a route-restriction `403` (e.g. Fireworks Fire Pass
-  `fpk_*` keys returning "…not authorized for this route." on `/models`, while
-  chat still works) no longer marks the connection unavailable. Provider
-  validation falls through to the chat probe for such 403s instead of returning
-  "Invalid API key", and `checkFallbackError` short-circuits them to no cooldown.
-  Genuine auth failures (401 / generic 403) still fail fast. (#2929)
-- **auth/opencode-zen:** the OpenCode Zen free model now works in the Playground
-  and combos without an API key. `opencode-zen` serves the public, signup-free
-  endpoint (`https://opencode.ai/zen/v1`); when no api-key connection is
-  configured, credential resolution now falls back to anonymous (no-auth) access
-  instead of failing with "No credentials for provider: opencode-zen". A
-  configured, active key is still used when present. (#2962)
-- **translator/responses:** fixed an upstream `[400] Messages with role 'tool'
-must be a response to a preceding message with 'tool_calls'` when a Codex
-  client sent a `function_call` with an empty/missing `call_id`. The orphaned
-  `function_call_output` previously slipped past the orphan filter. Now
-  empty-`call_id` function calls are skipped (no dangling assistant tool_call)
-  and any tool result without a matching tool_call id is dropped. (#2893)
-- **deps:** remove the `proxifly` npm dependency (#3000 — thanks @terence71-glitch)
-- **proxy:** use connection proxy for OAuth refresh (#3012 — thanks @terence71-glitch)
-- **usage:** export pure helper functions for unit testing (#3015 — thanks @oyi77)
-- **docs/docker:** align memory default docs to 1024MB (#3006 — thanks @terence71-glitch)
-- **providers:** fix DuckDuckGo missing API key & update OpenCode free model list (#3008 — thanks @NekoMonci12)
-- **claude:** bump Claude Code identity to 2.1.158 and sync beta flags (#3010 — thanks @Tentoxa)
-- **test:** increase DB and usage utils coverage to >60% (#3018 — thanks @oyi77)
-- **oom:** resolve memory leak in Bottleneck limiter caches and provider registry (#2965 — thanks @soyelmismo)
-- **proxy:** show registry provider proxies in dashboard after Custom proxy flow moved them into the proxy registry (#2963 — thanks @terence71-glitch)
-- **routing:** add agy to executor map so it uses AntigravityExecutor (#2957 — thanks @ReqX)
-- **skills:** avoid Claude assistant tool_result blocks (#2956 — thanks @terence71-glitch)
-- **perf:** CPU leak from Bottleneck limiter accumulation + per-request optimizations (#2951 — thanks @soyelmismo)
-- **combo:** combo credential resolution ignores target.providerId — prefer combo target's providerId over model-inferred provider (#2946 — thanks @oyi77)
-- **dashboard:** v3.8.8 screen fixes — agent-bridge SSR + audit/logs/memory/playground (#2944)
-- **claude:** sanitize tool schemas + cloak third-party tool names on native Claude OAuth (#2943 — thanks @NomenAK)
-- **auth:** prevent Codex multi-account refresh_token family revocation (#2941)
-- **combo:** fix combo vision passthrough and Codex tool history repair (#2940 — thanks @charithharshana)
-- **claude:** map WebSearch to Responses web_search (#2938 — thanks @makcimbx)
-- **claude:** strip empty Read pages tool input (#2937 — thanks @makcimbx)
-- **dashboard:** improve self-service provider quota visibility (#2931 — thanks @guanbear)
-- **antigravity:** avoid visible signatureless tool history (#2927 — thanks @dhaern)
-- **sse/web-search:** bypass the web-search fallback on a Claude → Claude passthrough so native Claude requests aren't rewritten (#2960 — thanks @terence71-glitch)
-- **oom:** prevent per-request memory accumulation (~256MB heap growth) (#2973 — thanks @soyelmismo)
-- **perf/proxy:** parallelize provider proxy overlay lookups (#2984 — thanks @terence71-glitch)
-- **privacy/PII:** resolve the PII feature flag correctly and fix PII response sanitization in streaming SSE requests (#3021 — thanks @dangeReis)
-- **electron:** improve macOS window chrome (#3029 — thanks @bobbyunknown)
-- **i18n:** fix missing API key scope translations (#3031 — thanks @guanbear)
-- **stream/responses:** drop a leaked chat bootstrap chunk for Responses-API clients (#3035 — thanks @CitrusIce)
-- **docker:** warn-only on the `/app/data` permission check instead of `exit 1`, so a non-writable bind mount no longer kills the container at boot (#3036 — thanks @wussh)
-- **mcp:** resolve streamable-HTTP transport readiness reporting an offline status (#3037 — thanks @Chewji9875)
-- **dashboard:** use a lightweight ping endpoint for the MaintenanceBanner (fixes #3040) (#3043 — thanks @herjarsa)
-- **test:** resolve pre-existing test failures — env sync, PII, quota, sidebar (#3039 — thanks @oyi77)
-- **docs/mcp:** regenerate the mcp-tools diagram for 43 tools and fix the tool count (#3028 — thanks @diegosouzapw)
-- **mcp:** move `enforceScopes` guard before `MCP_TOOL_MAP` lookup, add inline `scopes` parameter to `withScopeEnforcement()`, and declare scopes on all 24 dynamic tool definitions (memory, skills, plugins, gamification, compression) to fix scope enforcement for dynamic MCP tool groups (#2958)
-
----
-
-## [3.8.7] — 2026-05-29
-
-### ✨ New Features
-
-- **api (self-service):** add `GET /api/v1/me/status` so a delegated API key can view its own usage (USD used, budget percent, token totals) and optional shared Codex account quota, backed by migration `075_api_key_self_service_usage_scopes` (#2908 — thanks @guanbear).
-- **analytics:** roll up usage logs to `daily_usage_summary` before raw log cleanup, and query a SQL `UNION` of raw and rolled-up data to prevent analytics history data loss (#2904 — thanks @unitythemaker).
-- **perf (RAM):** reduce server memory footprint by capping 11 in-memory caches, limiting SQLite page cache, lazy-loading provider registries via Proxy, and optimizing Next.js startup database probes (#2903 — thanks @soyelmismo).
-
-### 🔧 Bug Fixes
-
-- **token-accounting:** prefer `prompt_tokens` over compatibility `input_tokens` for Anthropic Claude streams to avoid double-counting cached tokens (#2904 — thanks @unitythemaker).
-
-- **agy:** add the **Antigravity CLI (`agy`)** as a standalone OAuth provider next to `gemini-cli`/`antigravity`. It reuses the antigravity inference backend (identical Google client, `daily-cloudcode-pa.googleapis.com`) but ships its own model catalog — notably the Claude models the backend exposes (`claude-opus-4-6-thinking`, `claude-sonnet-4-6`) — its own account pool, and connection methods: import the `agy` CLI token file (paste/upload), auto-detect a local CLI login (`~/.gemini/antigravity-cli/antigravity-oauth-token`), browser OAuth, and bulk/ZIP import. New routes: `POST /api/providers/agy-auth/{import,import-bulk,zip-extract,apply-local}`.
-
-### Breaking Changes
-
-- **proxy-logs:** `GET /api/usage/proxy-logs` now returns `clientIp` instead of `publicIp` for each log entry. External consumers reading `log.publicIp` must update to `log.clientIp`. The underlying SQLite column (`public_ip`) is unchanged, so callers that query the database directly are unaffected (#2880 — thanks @rdself).
-
-### Known Inconsistency
-
-- **log-export:** `GET /api/logs/export?type=proxy-logs` returns raw SQLite rows whose IP field is still named `public_ip` (the historical column name). This differs from the `clientIp` field exposed by `GET /api/usage/proxy-logs`. The two endpoints are intentionally inconsistent for now and will be aligned in a future migration (#2880).
-
-### ✨ New Features
-
-- **usage:** add per-API-key token limits scoped to model/provider/global with two-tier inline enforcement and in-memory cache accelerator (#2888 — thanks @mugnimaestra).
-- **providers:** audit web cookie providers, fix 4 missing registry entries, and add DuckDuckGo AI Chat provider (#2862 — thanks @oyi77).
-- **compression:** expand pt-BR pack with 34 new rules inspired by the troglodita project (#2818 — thanks @leninejunior).
-
-### 🔧 Bug Fixes
-
-- **oauth:** hotfix Windsurf login — drop dead PKCE flow, promote import-token, and resolve SQLite bind type errors (#2884 — thanks @yunaamelia).
-- **models:** prune stale synced available models for inactive connections and dynamically map Antigravity MITM aliases loop-safely (#2886 — thanks @herjarsa).
-- **antigravity:** harden signatureless tool history replay by making text representation inert (#2878 — thanks @dhaern).
-- **i18n:** complete 144 missing Portuguese (pt-BR) locale keys and synchronize them with English (#2870 — thanks @alltomatos).
-- **opencode-go:** add OpenCode Go provider limits quota fetcher to retrieve Z.AI quota windows (#2861 — thanks @RajvardhanPatil07).
-- **reasoning:** gate reasoning trace replay injection on model interleaved capability metadata (#2843 — thanks @nickwizard).
-- **audio:** construct multipart body manually for transcription form-data to prevent dropped boundary headers under Next.js fetch (#2842 — thanks @soyelmismo).
-- **gemini-cli:** prefer real Google Cloud project IDs over default-project during model synchronization (#2841 — thanks @nickwizard).
-- **mcp:** redirect console.log and console.warn startup messages to stderr in stdio MCP mode to prevent JSON-RPC parsing failures (#2840 — thanks @disonjer).
-- **antigravity:** normalize unescaped tool calls and classify resource exhaustion 429 errors as lockout cooldowns (#2828 — thanks @Ardem2025).
-- **sse:** repair RTK engine defaults to resolve consecutive-line deduplication and direct compression calls (#2825 — thanks @leninejunior).
-- **fix(usage):** add opencode-go / opencode / opencode-zen quota fetcher so the provider limits page surfaces $12/5h, $30/wk, $60/mo windows alongside other quota-aware providers ([#2852](https://github.com/diegosouzapw/OmniRoute/issues/2852) — thanks @apoapostolov)
-
----
-
-## [3.8.6] — 2026-05-27
-
-### 🧹 Chores
-
-- **gitignore:** ignore `.claude/settings.local.json` so per-user Claude Code permissions never get committed by accident
-- **release:** version bump and metadata sync (package.json, package-lock.json, electron, open-sse, openapi.yaml)
-
-> v3.8.6 is a maintenance/scaffolding patch. All feature and bug-fix work from the post-v3.8.5 cycle (44 commits — community PRs #2777, #2782–#2787, #2789, #2790, plus internal hotfixes) was already integrated into v3.8.5 and is documented under that section.
-
----
-
-## [3.8.5] — 2026-05-26
-
-### 🔒 Security
-
-- **authz:** redirect `/home` and `/home/:path*` to `/login` when unauthenticated (#2712)
-
-### 🔧 Bug Fixes
-
-- **mcp:** break callLogs ↔ compliance ESM cycle that deadlocks the bundled MCP server on Node.js 24 (#2650)
-- **deepseek:** guard PoW solver Web Worker handler under Node strict mode (#2724)
-- **combos:** include no-auth providers in the combo builder picker (#2737)
-- **translator:** allow the `web_search` server-tool family in the Responses API translator (#2695)
-- **oauth:** register the missing `trae` provider with `import_token` flow (#2658)
-- **model:** merge settings-based aliases with the legacy DB alias namespace (#2618, #2208)
-- **kiro:** clipboard fallback for HTTP / non-secure contexts (#2689)
-- **cli:** raise `omniroute serve` ready timeout to 60s with TCP fallback for Windows cold start (#2460)
-
----
-
-## [Unreleased]
-
----
-
-## [3.8.23] — TBD
-
----
-
-### ✨ New Features
-
-### 🔧 Bug Fixes
-
----
-
-## [3.8.4] — 2026-05-25
-
-### Added
-
-- Embedded services (work in progress — 9Router, CLIProxyAPI; see T-15 for full entry).
-
----
-
-## [3.8.3] — 2026-05-24
-
-### ✨ New Features
-
-- **feat(combos):** universal context handoff for cross-model conversation continuity — structured XML summary system (`<context_handoff>`) that preserves conversation continuity and handles state transfer when combo routing switches models. ([#2653](https://github.com/diegosouzapw/OmniRoute/pull/2653) — thanks @herjarsa)
-- **feat(docs):** migrate `/docs` to Fumadocs MDX with nested routes — replaces the custom docs engine with Fumadocs, adding `[...slug]` catch-all routing, search API at `/docs/api/search`, `source.config.ts` content configuration, and `meta.json` navigation files across 8 doc sections (`architecture/`, `compression/`, `frameworks/`, `guides/`, `ops/`, `reference/`, `routing/`, `security/`). Includes 50+ URL redirects for backward compatibility via `next.config.mjs`. ([#2614](https://github.com/diegosouzapw/OmniRoute/pull/2614) — thanks @ovehbe)
-- **feat(dashboard):** add search and filters to `/dashboard/api-manager` — filter bar with search by name/key, active-only toggle (persisted to localStorage), status filter (active/disabled/banned/expired), type filter (standard/manage/restricted), filter count badges, and empty state with "Clear Filters" button. ([#2628](https://github.com/diegosouzapw/OmniRoute/pull/2628) / [#2641](https://github.com/diegosouzapw/OmniRoute/pull/2641) — thanks @diegosouzapw)
-- **feat(dashboard):** free-tier grouping with symbolic link in `/dashboard/providers` — groups and displays all free-tier providers from all categories dynamically using `hasFree: true` properties without removing them from their native lists. Displays category dot and amber dot with localizable tooltips, dedupes search results by provider ID, and corrects free tier count statistics. ([#2632](https://github.com/diegosouzapw/OmniRoute/pull/2632) — thanks @diegosouzapw)
-- **feat(dashboard):** risk notice modal for sensitive providers — show a soft, informative warning modal when connecting to session-based or OAuth providers (like Claude, Cursor, Copilot) for the first time. Adds `subscriptionRisk` properties to 20 providers, localizable templates, and stores acknowledgment in localStorage. ([#2633](https://github.com/diegosouzapw/OmniRoute/pull/2633) / [#2638](https://github.com/diegosouzapw/OmniRoute/pull/2638) — thanks @diegosouzapw)
-- **feat(dashboard):** refactor free-tier provider dashboard layout — cleans up visual clutter, reorganizes categories, hides redundant banners, and integrates free-tier categories nicely into the primary provider interface. ([#2640](https://github.com/diegosouzapw/OmniRoute/pull/2640) — thanks @diegosouzapw)
-- **feat(dashboard):** mini-playground inline (Phase 4) — integrated interactive mini-playground capabilities to provider details pages, including support for specialized example cards (Embedding, Image, LLM Chat, Music, STT, TTS, Video, Web Fetch, Web Search), unified API key loading hooks, model listing hooks, and curl command builder. ([#2648](https://github.com/diegosouzapw/OmniRoute/pull/2648) — thanks @diegosouzapw)
-- **feat(webfetch):** category support with dedicated media providers page and executors for Firecrawl, Jina Reader, and Tavily. ([#2645](https://github.com/diegosouzapw/OmniRoute/pull/2645) — thanks @diegosouzapw)
-- **feat(adapta):** integrate Adapta Org (`adapta-web`) provider with automatic Clerk authentication refresh and custom onboarding tutorial modal. ([#2643](https://github.com/diegosouzapw/OmniRoute/pull/2643) — thanks @df4p)
-- **feat(i18n):** complete translations for Simplified Chinese — translates 1220 missing keys bringing UI coverage to 98.8% with 0 placeholders. ([#2655](https://github.com/diegosouzapw/OmniRoute/pull/2655) — thanks @L-aros)
-
-### 🔧 Bug Fixes
-
-- **fix(settings):** Require Login modal Cancel button text and dismissal — modal now renders localized cancel label via the `common` namespace and closes correctly without modifying settings when cancelled. ([#2649](https://github.com/diegosouzapw/OmniRoute/pull/2649) — thanks @Chewji9875)
-- **fix(deepseek-web):** re-apply SSE parser, prompt format, and error handling fixes — handles all 3 DeepSeek SSE stream formats (initial fragments, APPEND operations, bare string tokens), uses non-greedy regex for markdown image stripping, simplifies prompt to single-turn, checks `json.code` before token extraction, and uses `accessToken` fallback for session cache eviction on auth errors. ([#2616](https://github.com/diegosouzapw/OmniRoute/pull/2616) — thanks @ovehbe)
-- **fix(deepseek-web):** SSE thinking/search routing and session lifecycle — properly routes thinking vs content fragments based on `thinking_enabled` flag, handles search results with citation indices, appends search result footnotes, refactors `transformSSE()` and `collectSSEContent()` with shared helpers. ([#2624](https://github.com/diegosouzapw/OmniRoute/pull/2624) — thanks @ovehbe)
-- **fix(codex):** use allowlist to strip non-Responses-API fields in non-passthrough path — strips residual Chat Completions fields (`stream_options`, `service_tier`, `store`, `metadata`) from the request body when routing through the non-passthrough (translation) code path, preventing GPT-5.5 from receiving invalid parameters. ([#2615](https://github.com/diegosouzapw/OmniRoute/pull/2615) — thanks @diegosouzapw)
-- **fix(catalog):** skip static PROVIDER_MODELS when synced models exist — prevents stale/duplicate model entries in `/v1/models` for auto-synced providers. ([#2625](https://github.com/diegosouzapw/OmniRoute/pull/2625) — thanks @herjarsa)
-- **fix(qoder):** Cosy auth fallback for PAT tokens + vision support for qwen3-vl-plus — when a PAT token gets 401, falls back to Cosy auth against `api1.qoder.sh`; adds `supportsVision: true` to qwen3-vl-plus. ([#2629](https://github.com/diegosouzapw/OmniRoute/pull/2629) — thanks @herjarsa)
-- **fix(cli):** register tsx loader and add opencode config subcommand — registers `tsx/esm` at CLI startup so dynamic `.ts` imports resolve; adds `omniroute config opencode` convenience alias. ([#2631](https://github.com/diegosouzapw/OmniRoute/pull/2631) — thanks @amogus22877769)
-- **fix(claude):** improve Pi and OpenCode compatibility — adds Pi Coding Agent anchors to system transform removal, stores `_toolNameMap` as non-enumerable, strips `context_management` when thinking is disabled. ([#2621](https://github.com/diegosouzapw/OmniRoute/pull/2621) — thanks @unitythemaker)
-- **fix(passthrough):** restore semantic passthrough system-role-only extraction — reverts full `normalizeClaudeUpstreamMessages()` to lighter `extractSystemRoleMessages()` in CC semantic passthrough paths, preventing document/tool chain corruption. ([#2620](https://github.com/diegosouzapw/OmniRoute/pull/2620) — thanks @Tentoxa)
-- **fix(kiro):** stabilize conversationId across prompt compression — captures pre-compression body and uses the original first user message as seed for UUID v5, keeping Kiro's AWS conversation context stable. ([#2630](https://github.com/diegosouzapw/OmniRoute/pull/2630) — thanks @HALDRO)
-- **fix(t3-chat-web):** close implementation gaps for t3.chat TanStack Start, tracking of stream_options, and retry configurations — parses TSS Turbo Stream Serialization from `_serverFn/*`, tracks request `combo_strategy` via database migration `062_usage_history_combo_strategy.sql`, and makes batch retry backoffs custom-configurable via environment variables. ([#2634](https://github.com/diegosouzapw/OmniRoute/pull/2634) — thanks @oyi77)
-- **fix(reasoning):** extend empty `reasoning_content` injection to prevent tool call loops in Kimi K2 and replay models — injects empty `reasoning_content` field to Kimi models during tool-calling sequences to bypass loop issues. ([#2639](https://github.com/diegosouzapw/OmniRoute/pull/2639) — thanks @herjarsa)
-- **fix(cli):** Linux autostart via systemd user service on headless VPS — adds auto-generating systemd user service unit for headless setups on Linux, updating tray configs and system variables allowlist (`LOGNAME` and `XDG_CURRENT_DESKTOP`). ([#2635](https://github.com/diegosouzapw/OmniRoute/pull/2635) — thanks @janeza2)
-- **fix(combo):** preserve `<omniModel>` tag in SSE stream output for combos when using `context_cache_protection` to ensure correct context pinning round-trips. ([#2646](https://github.com/diegosouzapw/OmniRoute/pull/2646) — thanks @herjarsa)
-- **fix(rtk):** prevent false positives in RTK compression by skipping content-based filter matching for non-shell tool results (e.g. read_file, grep_search). ([#2642](https://github.com/diegosouzapw/OmniRoute/pull/2642) — thanks @HALDRO)
-- **fix(translator):** enable Claude extended thinking for Copilot Responses-API requests — handles reasoning budget and translations for Copilot. ([#2647](https://github.com/diegosouzapw/OmniRoute/pull/2647) — thanks @ivan-mezentsev)
-- **fix(tests):** remove duplicate assertion in schema coercion & fix(cli): ignore system vars in env check. (thanks @diegosouzapw)
-
-### 📝 Maintenance
-
-- **chore(config):** ignore additional agent workflow command files (`.agents/commands/`). (thanks @diegosouzapw)
-- **chore(config):** ignore `memory-bank` and Cursor agent rules from tracking. (thanks @ovehbe)
-
----
-
-## [3.8.2] — 2026-05-22
-
-### ✨ New Features
-
-- **feat(@omniroute/opencode-plugin):** upstream-provider suffix in model display name — appends provider label to enriched names (e.g. `Claude Opus 4.7 · Claude` vs `Claude Opus 4.7 · Kiro`) so the OC TUI model picker can differentiate same-id models routed through different upstream connections. Default-on, opt-out via `features.providerTag: false`. ([#2602](https://github.com/diegosouzapw/OmniRoute/pull/2602) — thanks @mrmm)
-- **feat(@omniroute/opencode-plugin):** provider-tag becomes a prefix + traffic-light compression emoji — provider label now prepends (`Claude - Claude Opus 4.7`) for better TUI column grouping, with smart abbreviation for long labels (`GitHub Models` → `GHM`). Compression pipelines render intensity as emoji (🟢🟡🟠🔴). ([#2604](https://github.com/diegosouzapw/OmniRoute/pull/2604) — thanks @mrmm)
-- **feat(providers):** add 7 free-tier providers (Wave 1) — Arcee AI, InclusionAI, Krutrim, Liquid AI, MonsterAPI, Nomic, and Poolside now available as new API-key providers with provider icons, model specs, and full routing support. ([#2479](https://github.com/diegosouzapw/OmniRoute/pull/2479) — thanks @oyi77)
-- **feat(providers):** add Astraflow provider support with global + China endpoints — new provider with dual-region base URLs for global and mainland China access. ([#2486](https://github.com/diegosouzapw/OmniRoute/pull/2486) — thanks @ucloudnb666)
-- **feat(providers):** add `claude-web` provider — cookie-based Claude Web chat access without OAuth. ([#2476](https://github.com/diegosouzapw/OmniRoute/pull/2476) — thanks @oyi77)
-- **feat(providers):** add 14 free-tier providers (Wave 1b) — 360AI, Baichuan, Baidu, ByteDance/Doubao, IDEO, Kuaishou/Kling, Kunlun/Skywork, SenseTime/SenseNova, Stepfun, Tencent HunYuan, Zhipu GLM, Replicate, RunPod, and Modal with provider icons, model specs, and routing support. ([#2488](https://github.com/diegosouzapw/OmniRoute/pull/2488) — thanks @oyi77)
-- **feat(hermes):** add rich multi-role Hermes Agent CLI support — 7 configurable roles (default, delegation, vision, compression, web_extract, skills_hub, approval), per-role model selection with YAML config generation, dashboard card with preview, and home widget integration. ([#2526](https://github.com/diegosouzapw/OmniRoute/pull/2526) — thanks @apoapostolov)
-- **feat(cloud-agents):** cloud agents UX overhaul — tabs (tasks/agents/settings), status filters, Material icons, duration formatting, cloud agent credentials and health API endpoints, memory stats endpoint. ([#2516](https://github.com/diegosouzapw/OmniRoute/pull/2516) — thanks @oyi77)
-- **feat(authz):** manage-scope API keys may reach `/api/mcp/*` from non-loopback — Route Guard Tiers system (LOCAL_ONLY / ALWAYS_PROTECTED / MANAGEMENT), narrow carve-out for remote MCP access gated by `manage` scope; `/api/cli-tools/runtime/*` stays strict-loopback. Includes dashboard AuthzSection, inventory API, and comprehensive docs. ([#2473](https://github.com/diegosouzapw/OmniRoute/pull/2473) — thanks @mrmm)
-- **feat(home):** home page customization for experienced users — pin Provider Quota to home, toggle Quick Start and Provider Topology visibility via Appearance settings. ([#2531](https://github.com/diegosouzapw/OmniRoute/pull/2531) — thanks @apoapostolov)
-- **feat(home):** automatic refresh of Provider Quota — configurable interval (60s–600s) with toggle in Appearance settings; auto-refreshes pinned quota on the home page. ([#2532](https://github.com/diegosouzapw/OmniRoute/pull/2532) — thanks @apoapostolov)
-- **feat(@omniroute/opencode-plugin):** OmniRoute OpenCode plugin — live models fetched from OmniRoute API, combo-aware model listing, Gemini request sanitization, multi-instance support, auth flow integration, and 10 test files. ([#2529](https://github.com/diegosouzapw/OmniRoute/pull/2529) — thanks @mrmm)
-- **feat(executors):** forward OpenCode client headers to upstream providers — OpenCode-specific headers are now forwarded through the executor pipeline for improved compatibility. ([#2538](https://github.com/diegosouzapw/OmniRoute/pull/2538) — thanks @kang-heewon)
-- **feat(fireworks):** add new models with `modelIdPrefix` support — generic registry field that stores short model IDs and prepends the full path prefix before upstream API calls. Adds 6 new Fireworks models, `modelsUrl` for dynamic sync, and Qwen3 reranker. ([#2560](https://github.com/diegosouzapw/OmniRoute/pull/2560) — thanks @HALDRO)
-- **feat(@omniroute/opencode-plugin):** readable + filterable + offline-resilient model picker — `usableOnly` filter (only show providers with healthy connections), `diskCache` for offline hydration, `Combo:` prefix labeling, and compression metadata tags in combo display names. ([#2572](https://github.com/diegosouzapw/OmniRoute/pull/2572) — thanks @mrmm)
-- **feat(smart-pipeline):** multi-stage pipeline for auto combo routing — rule-based + intent-classifier + domain-specific stages with configurable pipeline router, accuracy benchmarks, and comprehensive tests. ([#2551](https://github.com/diegosouzapw/OmniRoute/pull/2551) — thanks @oyi77)
-- **feat(ops):** skip DB health check on startup via `OMNIROUTE_SKIP_DB_HEALTHCHECK=1` — replaces slow `integrity_check` (7+ min on large WAL) with `quick_check`, and adds env var to skip entirely. ([#2554](https://github.com/diegosouzapw/OmniRoute/pull/2554) — thanks @soyelmismo)
-- **refactor(dashboard):** Provider Quota grouped layout with vertical rail — restructures the page to a 2-column per-provider layout (left rail with icon/name/status, right content with dynamic per-provider columns), new `providerColumns.ts` / `ProviderGroup.tsx` / `AccountRow.tsx` components, env chip-filter row, bulk-refresh per group, and inline expanded panels. ([#2528](https://github.com/diegosouzapw/OmniRoute/pull/2528) — thanks @Gi99lin)
-- **feat(providers):** add 26 free-tier providers missing from registry — Novita, Avian, Chutes, Kluster, Targon, Nineteen, Celery, Ditto, Atoma, and more. ([#2590](https://github.com/diegosouzapw/OmniRoute/pull/2590) — thanks @oyi77)
-- **feat(providers):** add api-airforce free provider with 55 models. ([#2587](https://github.com/diegosouzapw/OmniRoute/pull/2587) — thanks @oyi77)
-- **feat(dashboard):** configurable sidebar — presets, drag-and-drop ordering, smart-grouping, and new Settings → Sidebar page. ([#2581](https://github.com/diegosouzapw/OmniRoute/pull/2581) — thanks @Gi99lin)
-
-### 🔧 Bug Fixes
-
-- **fix(validation):** stop appending a second `/models` when the Gemini base URL already ends in `/models` — Google AI Studio connections using the default base URL were validating against `.../v1beta/models/models` and failing with `404` for every connection. ([#2545](https://github.com/diegosouzapw/OmniRoute/issues/2545))
-- **fix(cloudflare-ai):** flatten OpenAI content-part arrays to plain strings for the Workers AI (`cf/`) executor — Workers AI's `/ai/v1/chat/completions` rejects `content: [{type:"text",...}]` with HTTP 400, so requests with array content now have their text parts joined into a string. ([#2539](https://github.com/diegosouzapw/OmniRoute/issues/2539))
-- **fix(i18n):** replace leftover Portuguese strings in the English source with English on the Quota dashboards — the quota-share Beta notice (`betaConfigSaved*`) and the Provider Quota row's `Edit cutoffs` / `Refresh now` fallbacks were showing Portuguese. ([#2540](https://github.com/diegosouzapw/OmniRoute/issues/2540))
-
-- **fix(proxy):** honor the legacy per-provider/global proxy config in `resolveProxyForProvider` — the Claude OAuth token exchange and token refresh only consulted the new proxy registry, so a proxy configured the legacy way (`/api/settings/proxy?level=provider`) was ignored and the exchange went out directly from the host, tripping Anthropic's IP `rate_limit_error` on VPS deployments. It now falls back to the legacy config, mirroring `resolveProxyForConnection`. ([#2456](https://github.com/diegosouzapw/OmniRoute/issues/2456))
-- **fix(antigravity):** auto-discover a missing Cloud Code `projectId` via `loadCodeAssist` before failing — a freshly re-added Antigravity account whose stored `projectId` was empty (OAuth-time discovery returned nothing) now recovers the project on the first request instead of returning `422 Missing Google projectId`, mirroring the `gemini-cli` bootstrap. ([#2334](https://github.com/diegosouzapw/OmniRoute/issues/2334), [#2541](https://github.com/diegosouzapw/OmniRoute/issues/2541))
-- **fix(stream):** keep the `/v1/responses` SSE connection warm for strict clients — emit an early keepalive while the upstream produces its first token and lower the heartbeat cadence to 4s, so Codex CLI's `reqwest` client (≈5s idle-read timeout) no longer drops the stream "before completion" on slow/reasoning models. `curl` was unaffected because it has no idle timeout. ([#2544](https://github.com/diegosouzapw/OmniRoute/issues/2544))
-- **fix(electron):** wait longer for the server on first launch and reload once it responds — long post-upgrade DB migrations could exceed the 30s readiness probe, leaving the desktop app stuck on the "Server starting" screen even though the backend was healthy. The probe now targets the auth-exempt health endpoint with a generous timeout and reloads the window once the server comes up. ([#2460](https://github.com/diegosouzapw/OmniRoute/issues/2460))
-
-- **fix(cli):** mark `bin/omniroute.mjs` as executable (mode 755) so the globally-installed CLI runs directly without a manual `chmod +x`. ([#2469](https://github.com/diegosouzapw/OmniRoute/issues/2469) — thanks @disonjer)
-- **fix(settings):** restore the Global System Prompt into the in-memory config on server startup and after JSON/SQLite import — it was only loaded by the PUT endpoint, so the toggle/prompt silently reverted to defaults after any restart or import. ([#2470](https://github.com/diegosouzapw/OmniRoute/issues/2470) — thanks @disonjer)
-- **fix(settings):** append the Global System Prompt **after** existing system content instead of prepending it, so provider/agent instructions (Kiro, OpenCode, Hermes, …) injected into the system message no longer override the user's global prompt via recency bias. ([#2468](https://github.com/diegosouzapw/OmniRoute/issues/2468) — thanks @disonjer)
-- **fix(kiro):** refresh imported social tokens (`authMethod === "imported"`) via the Kiro social-auth endpoint instead of AWS SSO OIDC — imported tokens carry a registered `clientId`/`clientSecret` but a social-issued refresh token the OIDC client cannot refresh, so auto-refresh was failing with "provider returned no new token". ([#2467](https://github.com/diegosouzapw/OmniRoute/issues/2467) — thanks @disonjer)
-- **fix(antigravity):** resolve the Cloud Code `projectId` from `providerSpecificData` as a fallback (and preserve it across token refresh) so the Gemini `/v1beta` streaming path stops returning a spurious `422 Missing Google projectId` for connections that store the project there. ([#2480](https://github.com/diegosouzapw/OmniRoute/issues/2480))
-- **fix(api):** `GET /v1beta/models` now lists only models whose provider has an active/validated connection, matching the OpenAI-format `/v1/models` behavior, instead of returning the entire catalog. ([#2483](https://github.com/diegosouzapw/OmniRoute/issues/2483))
-
-- **fix(cli):** persist `STORAGE_ENCRYPTION_KEY` into `DATA_DIR` (not only `~/.omniroute`) and refuse to auto-generate a fresh key when a `storage.sqlite` already exists — a new key cannot decrypt previously-encrypted credentials, so silently regenerating it locked users out of their database. The CLI now mirrors the server `bootstrapEnv` guard. (reported by Daniel Nach; original key persistence by @Chewji9875 — follow-up to [#1622](https://github.com/diegosouzapw/OmniRoute/issues/1622))
-- **fix(gemini):** preserve and re-attach the `thoughtSignature` on Gemini thinking-model tool calls — thread the signature namespace through the `FORMATS.GEMINI` and `FORMATS.GEMINI_CLI` request translators so the cached signature (keyed by connection + tool-call id) is found on the follow-up turn. Fixes `[400]: Function call is missing a thought_signature in functionCall parts` on agentic Gemini tool use. ([#2504](https://github.com/diegosouzapw/OmniRoute/issues/2504))
-- **fix(translator):** accept PDFs sent in the Responses-API `input_file` shape on the Gemini path, and the Gemini-style `document` shape on the Responses/Codex path — content parts are now normalized across `input_file` / `file` / `document` so a PDF reaches the model regardless of which field name the client used. ([#2515](https://github.com/diegosouzapw/OmniRoute/issues/2515))
-- **fix(stream):** count `thinking` arrays and `reasoning_details` as useful stream output — a reasoning-only response (e.g. Mistral/StepFun with a low `max_tokens`) was misclassified as "Stream ended before producing useful content" and turned into a spurious 502; it is now recognized as valid output. ([#2520](https://github.com/diegosouzapw/OmniRoute/issues/2520))
-- **fix(claude):** extract system/developer role messages in Claude Code semantic passthrough paths — moves `role:"system"` / `role:"developer"` messages from the `messages[]` array to the top-level `system` parameter before sending to Anthropic, which rejects them inside messages. Fixes memory injection context being silently dropped. ([#2497](https://github.com/diegosouzapw/OmniRoute/pull/2497) — thanks @unitythemaker)
-- **fix(vision-bridge):** auto-route non-standard provider models through OmniRoute self-loop — vision-bridge now detects when a model doesn't natively support vision and automatically re-routes the image through OmniRoute's own endpoint for format translation. ([#2487](https://github.com/diegosouzapw/OmniRoute/pull/2487) — thanks @herjarsa)
-- **fix(mitm):** add IPv6 DNS redirect, modular antigravity target, improved logging — MITM DNS handler now correctly redirects IPv6 (AAAA) queries alongside IPv4, adds a dedicated `antigravity.ts` target module, and enhances DNS/TLS logging for debugging. ([#2514](https://github.com/diegosouzapw/OmniRoute/pull/2514) — thanks @herjarsa)
-- **fix(usage):** improve Claude and MiniMax plan label detection — better tier name resolution for Claude OAuth usage (tier/plan/subscription_type/org fields) and new MiniMax plan label inference from quota totals. ([#2498](https://github.com/diegosouzapw/OmniRoute/pull/2498) — thanks @Gi99lin)
-- **fix(codex):** fan out image `n` requests in parallel — when Codex requests `n > 1` images, the image-generation handler now dispatches them concurrently instead of sequentially, significantly reducing total latency. ([#2499](https://github.com/diegosouzapw/OmniRoute/pull/2499) — thanks @nmime)
-- **fix(embeddings):** strip stale `Content-Encoding` headers from upstream response — prevents clients from receiving gzip-encoded responses with `identity` encoding declared, which caused silent data corruption. ([#2477](https://github.com/diegosouzapw/OmniRoute/pull/2477) — thanks @lordavadon2)
-- **fix(model):** return clear error instead of silent OpenAI default for unrecognized models — previously, an unrecognized model silently fell back to OpenAI; now returns a 404 with a descriptive message listing known providers. ([#2492](https://github.com/diegosouzapw/OmniRoute/pull/2492) — thanks @herjarsa)
-- **fix(dark-mode):** correct background token on Compression Override select — the combo compression override `<select>` was using a hard-coded white background that was invisible in dark mode. ([#2513](https://github.com/diegosouzapw/OmniRoute/pull/2513) — thanks @apoapostolov)
-- **fix(antigravity):** align subscription tier detection with Antigravity Manager — `extractCodeAssistSubscriptionTier` now parses the correct nested field from the `loadCodeAssist` response, and a new `extractCodeAssistOnboardTierId` fallback handles the onboarding flow. Subscription info is cached per access-token with 5-min TTL. ([#2496](https://github.com/diegosouzapw/OmniRoute/pull/2496) — thanks @Gi99lin)
-- **fix(opencode-zen):** add `opencode` provider alias and sync model list with live API — `opencode-zen` and `opencode-go` are now also reachable via the shorter `opencode` alias, and the default model list is kept in sync with the live `/v1/models` catalog. ([#2508](https://github.com/diegosouzapw/OmniRoute/pull/2508) — thanks @herjarsa)
-- **fix(combo):** clarify log message when combo target is skipped due to unavailable credentials — previously logged a misleading "provider not found" message; now says "skipped: credentials unavailable". ([#2494](https://github.com/diegosouzapw/OmniRoute/pull/2494) — thanks @herjarsa)
-- **fix(security):** replace `Math.random` with `crypto.randomUUID` in `generateTaskId`/`ActivityId` and fix URL hostname check in test — eliminates weak PRNG usage flagged by CodeQL. ([#2489](https://github.com/diegosouzapw/OmniRoute/pull/2489))
-- **fix(electron):** downgrade to Electron 41.x for better-sqlite3 V8 compatibility — Electron 42.x shipped a V8 version that broke `better-sqlite3` native bindings at runtime; pinning to 41.x restores stability.
-- **fix(@omniroute/opencode-provider):** include `limit.context` in model entries for OpenCode context window detection — OpenCode reads `limit.context` to determine usable context length for compaction and overflow detection.
-- **fix(providers):** make `gitlawb/gitlawb-gmi` model entry optional — prevents provider initialization failure when the model is not available in the catalog. ([#2476](https://github.com/diegosouzapw/OmniRoute/pull/2476) — thanks @oyi77)
-- **fix(translator):** inject `omniroute_web_search` in the Responses-API flat tool shape (`{ type, name }`) when the target provider speaks the Responses API — previously it was always emitted in the Chat Completions nested shape, so Codex/relay upstreams rejected the request. ([#2390](https://github.com/diegosouzapw/OmniRoute/issues/2390))
-- **fix(kiro):** serialize non-string `role:"tool"` message content before sending to CodeWhisperer — structured/array tool output was collapsing to `content:[{ text: "" }]`, which Kiro rejects with `400 Improperly formed request`. ([#2446](https://github.com/diegosouzapw/OmniRoute/issues/2446))
-- **fix(claude):** gate the heavy-agent beta headers (`context-1m`, `effort`, `advanced-tool-use`) on Opus/Sonnet only — Haiku with OAuth was receiving `context-1m` and rejecting it with 400. Also sanitizes historical `thinking` block signatures in passthrough. ([#2454](https://github.com/diegosouzapw/OmniRoute/issues/2454) — thanks @havockdev)
-- **fix(perplexity-web):** route requests through a Firefox-148 TLS-impersonating client so Perplexity's Cloudflare edge stops rejecting VPS/datacenter IPs with a 403 challenge. ([#2459](https://github.com/diegosouzapw/OmniRoute/issues/2459) — thanks @havockdev)
-- **fix(validation):** guard `apiKey`/`modelsUrl` against non-string values before calling `.startsWith()` / `.trim()` in the provider connection-test path. ([#2463](https://github.com/diegosouzapw/OmniRoute/issues/2463))
-- **fix(cost):** prevent double-billing of `cache_creation_input_tokens` — `prompt_tokens` from token extractors already includes both `cache_read` and `cache_creation`, so `nonCachedInput` now subtracts both cache types to avoid pricing cache at the full input rate. ([#2522](https://github.com/diegosouzapw/OmniRoute/pull/2522) — thanks @herjarsa)
-- **fix(handler):** always normalize system role messages in Claude passthrough paths — `normalizeClaudeUpstreamMessages()` is now called unconditionally in both `compatibleBridge` and pure passthrough, ensuring `role:"system"` messages are always extracted to the top-level `system` parameter. ([#2519](https://github.com/diegosouzapw/OmniRoute/pull/2519) — thanks @herjarsa)
-- **fix(handler):** capture Gemini `thought_signature` in non-streaming response path — the non-streaming translator now captures `thoughtSignature` from Gemini thinking model parts and persists them so follow-up turns can resolve them correctly. ([#2518](https://github.com/diegosouzapw/OmniRoute/pull/2518) — thanks @herjarsa)
-- **fix(kiro):** replace broken social OAuth with device flow — rewrites Kiro's Google/GitHub social login from the broken PKCE `kiro://` custom protocol to AWS Cognito device flow, which works correctly in web/proxy environments. ([#2524](https://github.com/diegosouzapw/OmniRoute/pull/2524) — thanks @disonjer)
-- **fix(providers):** resolve `opencode/` → `opencode-zen` slug mismatch + add 40+ new models — `opencode` is now a proper alias for `opencode-zen` in executor, model resolver, and provider registry; adds GPT 5.x, Claude 4.x, Gemini 3.x, Grok, Kimi, and other models with tests. ([#2517](https://github.com/diegosouzapw/OmniRoute/pull/2517) — thanks @herjarsa)
-- **fix(antigravity):** fail over stalled Antigravity sessions — new `ANTIGRAVITY_PRE_RESPONSE_TIMEOUT_CODE` shared constant for pre-response timeout detection, automatic failover to next account when session stalls before headers arrive. Node.js engine range relaxed to `>=20.20.2`. ([#2464](https://github.com/diegosouzapw/OmniRoute/pull/2464) — thanks @dhaern)
-- **fix(deepseek-web):** fix SSE parser, prompt format, and error handling — handles all 3 DeepSeek SSE stream formats (initial fragments, APPEND operations, bare string tokens), simplifies prompt to single-turn to prevent chat marker leakage, and checks `json.code` before token extraction. ([#2502](https://github.com/diegosouzapw/OmniRoute/pull/2502) — thanks @ovehbe)
-- **fix(codex):** accept `auth.json` without `auth_mode` field on import — Codex CLI no longer writes `auth_mode`; import now accepts both formats as long as required tokens are present. Semantic cache read now requires explicit `temperature: 0`. ([#2536](https://github.com/diegosouzapw/OmniRoute/pull/2536) — thanks @janeza2)
-- **fix(freetheai):** add `/chat/completions` to baseUrl to resolve 404 errors. ([#2557](https://github.com/diegosouzapw/OmniRoute/pull/2557) — thanks @lordavadon2)
-- **fix(qoder):** route PAT tokens to Qoder native API instead of DashScope — detects `pt-` prefixed tokens and routes to `api.qoder.com` with proper User-Agent header. ([#2559](https://github.com/diegosouzapw/OmniRoute/pull/2559) — thanks @herjarsa)
-- **fix(perf):** cache compiled RegExp in RTK compression hot path — eliminates thousands of redundant `new RegExp()` instantiations per second. ([#2553](https://github.com/diegosouzapw/OmniRoute/pull/2553) — thanks @soyelmismo)
-- **fix(reasoning-cache):** auto-start periodic cleanup on module load — the `server-init.ts` job was never imported (dead code), causing the `reasoning_cache` table to grow indefinitely. Now runs 30-min cleanup cycles automatically. ([#2552](https://github.com/diegosouzapw/OmniRoute/pull/2552) — thanks @soyelmismo)
-- **fix(claude):** omit `context-1m` beta for Sonnet — restrict to Opus-only to avoid long-context credit gate errors. Add `afk-mode-2026-01-31`, replace `redact-thinking` with `thinking-token-count-2026-05-13`. ([#2568](https://github.com/diegosouzapw/OmniRoute/pull/2568) — thanks @unitythemaker)
-- **fix(codex):** relax `auth_mode` check in frontend import preview — accept `undefined`/`null`/`"chatgpt"` instead of requiring `"chatgpt"` strictly, matching the backend fix in #2536. ([#2567](https://github.com/diegosouzapw/OmniRoute/pull/2567) — thanks @janeza2)
-- **fix(kimi):** declare vision capability for Kimi K2.6 in all 4 layers — `providerRegistry`, `modelSpecs`, `catalog.ts` keyword list, and Playground `VISION_MODELS`; previously the model silently rejected image uploads. ([#2573](https://github.com/diegosouzapw/OmniRoute/pull/2573) — thanks @herjarsa)
-- **fix(dashboard):** paginate request-log viewer beyond 300 rows — `getCallLogs` now accepts `offset` with parameterized SQL (eliminates string-interpolated `LIMIT`); `RequestLoggerV2` grows its window via "Load more" + IntersectionObserver infinite scroll, resetting on filter change. ([#2576](https://github.com/diegosouzapw/OmniRoute/pull/2576))
-- **fix(cli):** use `/api/monitoring/health` for server readiness check — `waitForServer()` was polling the auth-protected `/api/health` (401), causing `omniroute serve` to hang indefinitely. ([#2578](https://github.com/diegosouzapw/OmniRoute/pull/2578) — thanks @amogus22877769)
-- **fix(combo):** detect invalid model errors via structured error codes + regex fallback — when a combo target rejects a model (e.g. free account vs Pro), the router now recognizes `model_not_found` / `deployment_not_found` codes and 6 regex patterns, and falls through to the next target instead of stopping the loop. ([#2534](https://github.com/diegosouzapw/OmniRoute/pull/2534) — thanks @HALDRO)
-- **fix(security):** post-review hardening batch — `spawnSync` arg-array replaces `execSync` string-template (command injection), CSP `unsafe-eval` gated on `!app.isPackaged`, `requireManagementAuth` guard on budget/bulk and resilience/reset endpoints, error messages sanitized in gemini-web/claude-web/copilot-web/oauth/agents catch blocks, circuit breaker persists `lastFailureKind`, and combo resets `exhaustedProviders` per set-retry iteration. ([#2435](https://github.com/diegosouzapw/OmniRoute/pull/2435))
-- **fix(@omniroute/opencode-plugin):** honor `geminiSanitization` and `fetchInterceptor` feature flags — both were applied unconditionally; now each fetch layer is gated by its flag (default ON), and disabling both falls back to plain SDK fetch. ([#2546](https://github.com/diegosouzapw/OmniRoute/pull/2546))
-- **fix(#2575):** check DB feature flag override in `arePrivateProviderUrlsAllowed()` — supports runtime toggle without restart. ([#2595](https://github.com/diegosouzapw/OmniRoute/pull/2595) — thanks @herjarsa)
-- **fix(mimo):** add `supportsVision` flag to MiMo-V2.5, V2.5-Pro, and V2-Omni — previously image uploads were silently rejected. ([#2592](https://github.com/diegosouzapw/OmniRoute/pull/2592) — thanks @herjarsa)
-- **fix(ops):** propagate `OMNIROUTE_SKIP_DB_HEALTHCHECK` env var to periodic DB health check scheduler — companion fix to #2554. ([#2591](https://github.com/diegosouzapw/OmniRoute/pull/2591) — thanks @soyelmismo)
-- **fix(github):** remove incorrect `openai-responses` targetFormat from GitHub Copilot's Haiku/Sonnet models. ([#2583](https://github.com/diegosouzapw/OmniRoute/pull/2583) — thanks @oyi77)
-- **fix(copilot):** stabilize responses configuration — removes 865 lines of unstable config, simplifies handler. ([#2579](https://github.com/diegosouzapw/OmniRoute/pull/2579) — thanks @ivan-mezentsev)
-- **fix(#2544):** add SSE heartbeat keepalive to Responses API transform stream — prevents Codex CLI 0.130.0 from disconnecting during long thinking/reasoning phases. ([#2599](https://github.com/diegosouzapw/OmniRoute/pull/2599) — thanks @herjarsa)
-- **fix(memory):** extract system role messages in semantic passthrough path to prevent 400 on memory injection — system messages were being passed as-is to providers that reject mixed roles. ([#2474](https://github.com/diegosouzapw/OmniRoute/pull/2474) — thanks @Tentoxa)
-- **fix(@omniroute/opencode-provider):** include `limit.context` in model entries for OpenCode context window detection — previously OpenCode couldn't determine model context size. ([#2482](https://github.com/diegosouzapw/OmniRoute/pull/2482) — thanks @herjarsa)
-- **fix(mimo):** add `supportsVision` flag to Kimi K2.6 in providerRegistry + comprehensive vision tests for MiMo V2.5/V2.5-Pro/V2-Omni. ([#2600](https://github.com/diegosouzapw/OmniRoute/pull/2600) — thanks @herjarsa)
-- **fix(proxy):** prefer scoped proxies over registry global fallback — legacy provider-specific proxy was being shadowed by a registry-global fallback across both storage backends. Resolution now follows strict specificity: account → provider → combo → global. ([#2606](https://github.com/diegosouzapw/OmniRoute/pull/2606) — thanks @terence71-glitch)
-- **fix(@omniroute/opencode-plugin):** canonical-twin dedup + alias-fallback enrichment — `/v1/models` returned the same model under both alias (`cc/claude-opus-4-7`) and canonical (`claude/claude-opus-4-7`) names; now drops ~75 canonical duplicates and rescues ~88 raw-id rows with proper provider prefix via alias-index fallback. Also emits `cost`, `release_date`, `modalities` fields in static catalog and raises provider label threshold to 12 chars (preserves `AssemblyAI`, `Antigravity` verbatim). ([#2607](https://github.com/diegosouzapw/OmniRoute/pull/2607) — thanks @mrmm)
-- **fix(registry):** populate empty models arrays for HuggingFace (6 models) and HackClub (3 models) + fix Snowflake placeholder baseUrl to `{account}` template pattern. ([#2611](https://github.com/diegosouzapw/OmniRoute/pull/2611) — thanks @oyi77)
-
-### 🌐 Internationalization
-
-- **i18n(zh-CN):** translate 830 missing UI strings — replaces all `__MISSING__:` placeholders with proper Chinese translations. ([#2523](https://github.com/diegosouzapw/OmniRoute/pull/2523) — thanks @InkshadeWoods)
-- **i18n(dashboard):** add missing dashboard keys and fix EN fallbacks — hundreds of hardcoded English strings across cache, caveman, costs, skills, memory, and evals pages replaced with `t()` calls. ([#2500](https://github.com/diegosouzapw/OmniRoute/pull/2500) — thanks @Gi99lin)
-- **i18n(pt-BR):** complete and fix Brazilian Portuguese translation — comprehensive overhaul of pt-BR locale with ~3000 lines of quality translations, filling all missing keys and correcting existing entries. ([#2543](https://github.com/diegosouzapw/OmniRoute/pull/2543) — thanks @alltomatos)
-- **i18n(ru):** comprehensive Russian translation update — ~2000 lines of corrected and filled translations. ([#2550](https://github.com/diegosouzapw/OmniRoute/pull/2550) — thanks @AgentAlexAI)
-- **i18n(all):** comprehensive localization and UI refactoring — 42 locale files synchronized with missing keys, cloud-agents page i18n rewrite, and consistent `t()` usage across 21 dashboard components. ([#2580](https://github.com/diegosouzapw/OmniRoute/pull/2580) — thanks @alltomatos)
-- **i18n(all):** translate freeTier provider strings across 41 locales — replaces `__MISSING__:Free Tier Providers` placeholders with proper translations in both `common` and `providers` namespaces. ([#2609](https://github.com/diegosouzapw/OmniRoute/pull/2609) — thanks @leninejunior)
-- **i18n(pt-BR):** eliminate all 1270 remaining `__MISSING__` markers — completes pt-BR translation across 41 namespaces to true 100% coverage. ([#2610](https://github.com/diegosouzapw/OmniRoute/pull/2610) — thanks @leninejunior)
-
-### 📝 Maintenance
-
-- **chore:** remove Akamai VPS deploy from release workflow and skills.
-- **chore(deps):** bump `actions/setup-node` from v4 to v6 + `randomBytes` security fix for cloud agent task IDs. ([#2589](https://github.com/diegosouzapw/OmniRoute/pull/2589))
-- **chore(deps):** bump `actions/upload-artifact` from v4 to v7. ([#2588](https://github.com/diegosouzapw/OmniRoute/pull/2588))
-- **chore:** ignore `.claude/worktrees` from git tracking.
-- **chore(ci):** auto-lock release branch on version publish — new CI workflow applies `lock_branch` protection when a GitHub Release is published. ([#2542](https://github.com/diegosouzapw/OmniRoute/pull/2542))
-- **docs:** redesign README — marketing-first layout with accurate provider counts. ([#2490](https://github.com/diegosouzapw/OmniRoute/pull/2490))
-
----
-
-## [3.8.1] — 2026-05-21
-
-### ✨ New Features
-
-- **feat(settings):** Feature Flags Settings Page (Card Grid + DB overrides) — fully implements the feature flags UI dashboard using Variant A (Card Grid) with Glassmorphism, complete with global `GET/PUT/DELETE` API routes, Zod validation, debounced search, category filters, and full 30+ locale i18n support. Resolves priority hierarchy to DB > ENV > Defaults. ([#2457](https://github.com/diegosouzapw/OmniRoute/pull/2457))
-- **feat(db):** multi-driver SQLite abstraction layer — new `SqliteAdapter` interface with 3 concrete adapters (`betterSqliteAdapter`, `nodeSqliteAdapter`, `sqljsAdapter`) and a `driverFactory` that cascades `better-sqlite3` → `node:sqlite` → `sql.js (WASM)`. Enables OmniRoute to run on any JavaScript runtime (Node.js, Bun, Deno, Cloudflare Workers) without native binary dependencies. `better-sqlite3` moved to `optionalDependencies`. ([#2447](https://github.com/diegosouzapw/OmniRoute/pull/2447))
-- **feat(settings):** Claude Fast Mode toggle in Settings › AI — opt-in toggle that forwards `X-CPA-Force-Fast-Mode` header so a paired CLIProxyAPI build can reach Anthropic Fast Mode (`speed:"fast"`). Model-gated to Opus models matching Anthropic's binary KT() check. ([#2449](https://github.com/diegosouzapw/OmniRoute/pull/2449) — thanks @NomenAK)
-- **feat(settings):** Codex Fast Tier — tier dropdown (`default`/`priority`/`flex`) + per-model gate preventing 400 errors from OpenAI when the tier toggle was on for non-Fast-eligible models. ([#2451](https://github.com/diegosouzapw/OmniRoute/pull/2451) — thanks @NomenAK)
-- **feat:** align Antigravity 2.0.1 support — updated client profile, upstream headers, and model aliases. ([#2443](https://github.com/diegosouzapw/OmniRoute/pull/2443) — thanks @dhaern)
-- **feat:** enhance `extractBearer` to support `x-api-key` for Anthropic API style auth. ([#2436](https://github.com/diegosouzapw/OmniRoute/pull/2436) — thanks @thedtvn)
-- **feat(memory):** wire `createMemory` to `upsertSemanticMemoryPoint` (Qdrant). ([#2439](https://github.com/diegosouzapw/OmniRoute/pull/2439) — thanks @NomenAK)
-
-### 🔧 Bug Fixes & Refactors
-
-- **fix(deepseek-web):** rewrite auth to userToken Bearer + WASM PoW solver. ([#2452](https://github.com/diegosouzapw/OmniRoute/pull/2452) — thanks @ovehbe)
-- **chore:** update node dependencies and runtime support. ([#2453](https://github.com/diegosouzapw/OmniRoute/pull/2453) — thanks @backryun)
-- **fix(translator):** fix 3 Kiro `tool_result` defects causing 400 on follow-up turns — missing `tool_use_id` mapping, orphan result blocks, and conversation ID collision on assistant-first turns. ([#2447](https://github.com/diegosouzapw/OmniRoute/pull/2447))
-- **fix(translator):** treat `developer` role as system in OpenAI → Claude translation — `openAIToClaude` now extracts `developer`-role messages into `systemParts` (same as `system`) and filters them from the non-system message list, preventing identity context injected via the Responses API `developer` role from silently becoming an assistant turn when routing to a Claude-format provider. ([#2407](https://github.com/diegosouzapw/OmniRoute/issues/2407))
-- **fix(antigravity):** deduplicate `removeHeaderCaseInsensitive` — export canonical implementation from `antigravityClientProfile.ts` and remove the local copy in `antigravity.ts`; export `AntigravityCredentialsLike` type for cross-module use. (#2433 — thanks @Gi99lin)
-- **refactor(docs):** enhance frontmatter handling in DocPage — gray-matter Date object parsing bug fix. ([#2448](https://github.com/diegosouzapw/OmniRoute/pull/2448) — thanks @ovehbe)
-- **fix(jules):** Jules API parity and cloud-agent provider registration. ([#2438](https://github.com/diegosouzapw/OmniRoute/pull/2438))
-- **fix(i18n):** harden diff key extraction tag sanitization in `extract-keys-from-diff.mjs`.
-- **chore(i18n):** refresh fr/es/de locales + add missing `settings.update` key. ([#2437](https://github.com/diegosouzapw/OmniRoute/pull/2437))
-- **fix(dashboard):** allow bracketed combo names — align dashboard combo-name validator regex with the shared/server schema updated in PR #2354; names like `Claude [1m]` are now accepted in the create/edit form. ([#2458](https://github.com/diegosouzapw/OmniRoute/pull/2458) — thanks @congvc-dev)
-- **docs(agentrouter):** recommend native provider as the simple path — guide now prefers the built-in AgentRouter provider instead of manual OpenAI-compatible configuration. ([#2429](https://github.com/diegosouzapw/OmniRoute/pull/2429) — thanks @leninejunior)
-- **feat(settings):** surface Codex Fast Tier toggle in Settings › AI — companion UI toggle for the Codex Fast Tier feature. ([#2440](https://github.com/diegosouzapw/OmniRoute/pull/2440) — thanks @NomenAK)
-
-### 🔒 Security Fixes
-
-- **fix(security):** replace `execSync` string-template with `spawnSync` arg-array in `plugin.mjs` — eliminates shell command injection via malicious plugin names.
-- **fix(security):** gate Electron CSP `unsafe-eval` on `!app.isPackaged` instead of URL substring match — was leaking `unsafe-eval` into production builds; merged duplicate `connect-src` directives.
-- **fix(api):** add `requireManagementAuth` to `/api/usage/budget/bulk` and `/api/resilience/reset` — both endpoints exposed spend data and circuit-breaker controls without auth.
-- **fix(security):** route catch-block error messages through `sanitizeErrorMessage()` in `gemini-web`, `claude-web`, `copilot-web` executors, `oauth` route, and cloud-agent task routes — prevents stack traces and internal paths leaking into HTTP responses.
-- **fix(codex):** `refreshCredentials` returns `null` (not error-object) on token refresh failure — prevents base executor from spreading `{error}` onto active credentials.
-- **fix(tokenRefresh):** safe `unknown`-error access in `catch` block (`error instanceof Error ? error.message : String(error)`).
-- **fix(combo):** reset `exhaustedProviders` set at start of each set-retry iteration — providers excluded in a failing pass now get a second chance on retry.
-- **fix(circuitBreaker):** persist and restore `lastFailureKind` via the `options` JSON column — kind-based cooldown overrides (`cooldownByKind`) now survive server restarts.
-
----
-
-## [3.8.0] — 2026-05-06
-
-### 🚀 Post-release hotfixes e contribuições (2026-05-06 → 2026-05-20)
-
-#### 2026-05-20
-
-- **feat(batch):** implement 10 feature requests harvested from issues — T3 Chat Web executor (cookie-based), per-request exhausted-provider tracking (#1731) to skip quota-drained providers mid-combo, Zed Docker detection, API key rotator health dashboard, Kiro multi-account isolation, context-window model filtering, cost blending in combos, combo config tests, provider validation branches, and postinstall support scripts. ([#2414](https://github.com/diegosouzapw/OmniRoute/pull/2414))
-- **feat(combos):** add `falloverBeforeRetry` strategy — combo routing now falls over to the next target before retrying the same model, eliminating the tail-latency spike from exhausting all per-model retries on a failing endpoint. Also wraps the retry loop in a `setTry` outer loop for per-target retry coordination. ([#2417](https://github.com/diegosouzapw/OmniRoute/pull/2417) — thanks @hartmark)
-- **fix(gamification):** resolve 6 implementation gaps — missing `SELECT` in `checkActionCountBadges` SQL (was silently skipping 8 badges), federation leaderboard auth enforcement, pagination `offset` parameter no longer silently discarded, admin anomaly view now computes real z-scores, `addXp` correctly calculates initial level from XP amount, and barrel `index.ts` for clean module exports. 72-test suite covering all fixes. ([#2421](https://github.com/diegosouzapw/OmniRoute/pull/2421) — thanks @oyi77)
-- **docs:** add AgentRouter provider setup guide — step-by-step instructions for connecting OmniRoute to AgentRouter.org's Claude-compatible relay endpoint, covering API key configuration and wire-image headers. ([#2422](https://github.com/diegosouzapw/OmniRoute/pull/2422) — thanks @leninejunior)
-- **fix(claude):** drop orphan `tool_result` blocks left behind when `fixToolAdjacency` strips a dangling `tool_use` — resolves HTTP 400 "unexpected tool_use_id in tool_result blocks" from the Anthropic API on truncated histories. `fixToolPairs` now re-runs after every `fixToolAdjacency` pass across all three call sites (`contextManager.ts`, `base.ts`, `claudeCodeCompatible.ts`). (discussion [#2410](https://github.com/diegosouzapw/OmniRoute/discussions/2410))
-- **fix(playground):** guard against `null`/non-string model IDs in Playground dropdowns — `typeof m?.id !== "string"` check prevents a silent crash in the provider discovery loop and `filteredModels` computation that was leaving all Playground dropdowns empty when `/v1/models` returned entries with `id: null`; adds deduplication via `Set` to eliminate duplicate React key warnings.
-- **fix(mitm):** point MITM runtime manager re-export to the compiled `.js` entrypoint — fixes module resolution after build when the `.ts` source is no longer present.
-- **fix(storage):** persist `STORAGE_ENCRYPTION_KEY` across upgrades (closes #1622) — ensures that SQLite encryption keys are preserved during version upgrades. ([#2428](https://github.com/diegosouzapw/OmniRoute/pull/2428) — thanks @Chewji9875)
-- **fix(auth):** auto-reset credential `apiKeyHealth` status on successful connection test. ([#2427](https://github.com/diegosouzapw/OmniRoute/pull/2427) — thanks @clousky2020)
-- **fix(mitm):** drop `.js` extension on `manager.runtime` re-export to fix webpack packaging issue. ([#2425](https://github.com/diegosouzapw/OmniRoute/pull/2425) — thanks @NomenAK)
-- **fix(image):** support Antigravity image generation and add Gemini 3.5 Flash support. ([#2423](https://github.com/diegosouzapw/OmniRoute/pull/2423) — thanks @backryun)
-
-#### 2026-05-19
-
-- **chore(i18n):** comprehensive dashboard i18n coverage — 6 rounds of parallel refactoring replacing hardcoded English/Portuguese text with `t()` calls across 57+ dashboard pages; 420+ new keys added to `en.json` covering `settings`, `playground`, `analytics`, `apiManager`, `providers`, `skills`, `memory`, `agents`, and 15 other namespaces (coverage: ~88%, up from ~20%).
-- **fix(offline):** avoid SSR/CSR hydration mismatch on the offline status page — switches from a `useState` lazy initializer (which accessed `navigator.onLine` on the server) to `useSyncExternalStore` with a distinct `false` server snapshot, eliminating the React hydration warning.
-- **fix(cli-tools):** guard `modelId` type before calling `.indexOf()` — prevents a `TypeError` when a model entry without a string `id` reaches the comparison logic in CLI Tools.
-- **fix(providers):** add missing `isLocalProvider` import and update changelog.
-- **fix(resilience):** add API Key health tracking with automatic rotation and UI toast alerts. ([#2412](https://github.com/diegosouzapw/OmniRoute/pull/2412) — thanks @clousky2020)
-- **feat(providers):** support Gemini API keys for Gemini CLI executor. ([#2408](https://github.com/diegosouzapw/OmniRoute/pull/2408) — thanks @benzntech)
-- **feat(gamification):** implement Gamification & Leaderboard System with non-blocking event-driven updates. ([#2405](https://github.com/diegosouzapw/OmniRoute/pull/2405) — thanks @oyi77)
-- **fix(providers):** Kilo Code provider no longer blocks on a missing local `kilocode` CLI binary — the provider uses OAuth device flow + direct HTTPS to `api.kilo.ai` and never required the CLI at runtime; the connection test was hard-failing with "Local CLI runtime is not installed" even when the OAuth token was valid. CLI Tools integration (`/api/cli-tools/kilo-settings`) keeps its own runtime check. ([#2404](https://github.com/diegosouzapw/OmniRoute/issues/2404) — thanks @Flexible78)
-- **fix(db):** `bun add -g omniroute` (and other runtimes that skip postinstall) no longer surfaces a generic 500 — `isNativeSqliteLoadError` now also detects "Could not locate the bindings file" / `MODULE_NOT_FOUND`, so the user gets the friendly rebuild guide instead. ([#2358](https://github.com/diegosouzapw/OmniRoute/issues/2358) — thanks @yamansin)
-- **fix(kiro):** enable Google OAuth login option in the Kiro auth modal — surfaces the Google SSO button alongside the existing identity providers. ([#2392](https://github.com/diegosouzapw/OmniRoute/pull/2392) — thanks @congvc-dev)
-- **fix(security):** drop hashing layer in `sessionPoolKey` after switching to a non-cryptographic key derivation strategy that clears CodeQL alert #247. ([#2396](https://github.com/diegosouzapw/OmniRoute/pull/2396))
-- **feat(providers):** Gemini Web cookie-based provider — proxies google.com chat through a session cookie, allowing free Gemini access without API keys. ([#2380](https://github.com/diegosouzapw/OmniRoute/pull/2380) — thanks @oyi77)
-- **model:** add Composer 2.5 to the Cursor provider catalog. ([#2381](https://github.com/diegosouzapw/OmniRoute/pull/2381) — thanks @backryun)
-- **fix:** `tool_use` without adjacent `tool_result` causes Claude 400 — adjacency guard now also applies inside `compressContext`. ([#2383](https://github.com/diegosouzapw/OmniRoute/pull/2383) — thanks @oyi77)
-- **build(deps):** bump `electron` from 42.0.1 to 42.1.0 in `/electron`. ([#2397](https://github.com/diegosouzapw/OmniRoute/pull/2397))
-- **build(deps):** production group bumps — 4 updates. ([#2398](https://github.com/diegosouzapw/OmniRoute/pull/2398))
-- **build(deps):** development group bumps — 4 updates. ([#2399](https://github.com/diegosouzapw/OmniRoute/pull/2399))
-- **chore:** sync `release/v3.8.0` with `main` (CodeQL hotfixes + Dependabot bumps) via merge commit.
-
-#### 2026-05-18
-
-- **fix(security):** resolve CodeQL alerts #243/#244/#245 — incomplete URL substring sanitization and weak crypto signal hardening. ([#2391](https://github.com/diegosouzapw/OmniRoute/pull/2391))
-- **fix(security):** switch `sessionPoolKey` derivation to HMAC-SHA256 to clear CodeQL alert #246 (insecure hash for sensitive data). ([#2394](https://github.com/diegosouzapw/OmniRoute/pull/2394))
-- **docs(readme):** restore the 9router acknowledgment that was inadvertently dropped during the v3.8.0 README rework. ([#2393](https://github.com/diegosouzapw/OmniRoute/pull/2393))
-- **refactor(dashboard):** comprehensive nav, providers, endpoint, runtime, quota, pricing, budget redesign + quota sharing preview (sidebar restructure → 12 collapsible sections, 22 new routes). ([#2384](https://github.com/diegosouzapw/OmniRoute/pull/2384))
-- **fix(dashboard):** PR #2384 follow-up review fixes — Runtime quota i18n, Budget projection logic, QuotaShare i18n externalization, Provider Limits semantic markup, bulk endpoint usage. ([#2389](https://github.com/diegosouzapw/OmniRoute/pull/2389))
-- **feat(content):** add Haiper, Leonardo, Ideogram, Suno, and Udio as content/media providers. ([#2377](https://github.com/diegosouzapw/OmniRoute/pull/2377) — thanks @oyi77)
-- **feat(@omniroute/opencode-provider):** expand config helpers, add MCP entry, live model fetch, and combo builder. ([#2375](https://github.com/diegosouzapw/OmniRoute/pull/2375) — thanks @mrmm)
-- **fix(claude-oauth):** enable system-transforms pipeline for the native Claude executor (closes 400 billing-gate). ([#2370](https://github.com/diegosouzapw/OmniRoute/pull/2370) — thanks @thepigdestroyer)
-- **feat(content):** extend providers with video, audio, TTS, music capabilities — Pollinations, MiniMax, Together, Replicate across Audio TTS and Transcription registries. ([#2369](https://github.com/diegosouzapw/OmniRoute/pull/2369) — thanks @oyi77)
-- **feat(providers):** add Veo AI Free as a web-wrapper provider for generating video, image, and TTS without an API key. ([#2366](https://github.com/diegosouzapw/OmniRoute/pull/2366) — thanks @oyi77)
-- **feat(providers):** add Replicate as a free provider for OpenAI-compatible inference with community models. ([#2364](https://github.com/diegosouzapw/OmniRoute/pull/2364) — thanks @oyi77)
-- **fix(claude):** avoided redundant deep cloning of Claude Code messages during semantic passthrough preparation, improving memory/CPU efficiency for large histories. ([#2362](https://github.com/diegosouzapw/OmniRoute/pull/2362) — thanks @terence71-glitch)
-- **fix(providers):** register `llm7` in the executor registry and route Cohere via OpenAI-compatible layer. ([#2361](https://github.com/diegosouzapw/OmniRoute/pull/2361), [#2360](https://github.com/diegosouzapw/OmniRoute/pull/2360))
-- **fix(rate-limiter):** Redis is now opt-in — when `REDIS_URL` is unset, the rate limiter falls back to the in-memory store instead of spamming `ECONNREFUSED`. ([#2357](https://github.com/diegosouzapw/OmniRoute/pull/2357))
-- **fix(streaming):** emit protocol-aware stream errors — `createDisconnectAwareStream()` now emits native Responses API or Claude API SSE error blocks based on the client protocol. ([#2355](https://github.com/diegosouzapw/OmniRoute/pull/2355) — thanks @dhaern)
-- **fix(combos):** allow bracketed combo names (e.g. `Claude [1m]`) by updating validation schemas. ([#2354](https://github.com/diegosouzapw/OmniRoute/pull/2354) — thanks @congvc-dev)
-- **fix(claude-code):** semantic passthrough — preserve Claude Code `messages[]` structure for native Claude OAuth and relay routes. ([#2351](https://github.com/diegosouzapw/OmniRoute/pull/2351) — thanks @terence71-glitch)
-- **fix(usage):** extract flat `cached_tokens` and `reasoning_tokens` from OpenAI-compatible usage objects. ([#2350](https://github.com/diegosouzapw/OmniRoute/pull/2350) — thanks @TF0rd)
-- **fix(translator):** DeepSeek tool-call response lookup reads cached reasoning before falling back to empty string. ([#2349](https://github.com/diegosouzapw/OmniRoute/pull/2349) — thanks @herjarsa)
-- **fix(ui/tooltip):** render in portal + clamp to viewport so tooltips aren't clipped in modal dialogs. ([#2352](https://github.com/diegosouzapw/OmniRoute/pull/2352) — thanks @slider23)
-- **fix(auto-routing):** replace bare `getSettings()` with `getCachedSettings` to stop 500 on `auto/*` requests. ([#2346](https://github.com/diegosouzapw/OmniRoute/pull/2346))
-- **fix(docker):** ship Dashboard Docs markdown in the container image. ([#2348](https://github.com/diegosouzapw/OmniRoute/pull/2348))
-- **fix(combo/validator):** treat upstream responses carrying a non-empty `reasoning_content` as valid output. ([#2341](https://github.com/diegosouzapw/OmniRoute/pull/2341))
-- **fix(account-fallback):** classify Anthropic `Usage Limit Reached` as `QUOTA_EXHAUSTED` with a 1h cooldown. ([#2321](https://github.com/diegosouzapw/OmniRoute/pull/2321))
-- **feat(providers):** add GitHub Models as a free provider — GPT-5, o-series, DeepSeek-R1, Llama 4, Grok 3. ([#2344](https://github.com/diegosouzapw/OmniRoute/pull/2344) — thanks @oyi77)
-- **feat(providers):** add Hackclub AI as a free provider — 30+ models, no credit card required. ([#2339](https://github.com/diegosouzapw/OmniRoute/pull/2339) — thanks @oyi77)
-- **feat(providers):** add Microsoft Copilot Web executor — WebSocket-based provider. ([#2340](https://github.com/diegosouzapw/OmniRoute/pull/2340) — thanks @oyi77)
-- **feat(routing):** LKGP stores last known good account `connectionId` alongside provider. ([#2338](https://github.com/diegosouzapw/OmniRoute/pull/2338) — thanks @oyi77)
-- **feat(dashboard):** add Claude Code auth import/export UI + i18n (three-PR series: libs, API routes, dashboard UI).
-- **feat(dashboard):** add Gemini CLI auth import/export UI + i18n (three-PR series: libs, API routes, dashboard UI).
-- **fix(routing):** implement embedding combos, local provider validation bypass, and resolve migration collisions.
-- **fix(build):** import Monaco ESM API to fix webpack `nls.messages-loader` error.
-- **fix(ui):** v3.8.0 polish — connections border, sticky tabs, EN translations, save toasts, auto-combo catalog. ([#2305](https://github.com/diegosouzapw/OmniRoute/pull/2305) — thanks @mrmm)
-- **fix(auth+build):** Bearer manage scope on management routes + lazy-load deepseek PoW solver. ([#2308](https://github.com/diegosouzapw/OmniRoute/pull/2308) — thanks @mrmm)
-- **fix(claude):** guard orphan tool_use/tool_result pairs before upstream send. ([#2312](https://github.com/diegosouzapw/OmniRoute/pull/2312) — thanks @mrmm)
-- **fix(ui):** remove count from batch removal button. ([#2309](https://github.com/diegosouzapw/OmniRoute/pull/2309) — thanks @hartmark)
-- **fix:** remove implicit API key request caps — removes default 1K/5K/20K rate caps. ([#2289](https://github.com/diegosouzapw/OmniRoute/pull/2289) — thanks @josephvoxone)
-- **fix(sse):** strip stale `Content-Encoding`, `Content-Length`, and `Transfer-Encoding` headers on non-streaming forward. ([#2264](https://github.com/diegosouzapw/OmniRoute/pull/2264) — thanks @gleber)
-- **chore(providers):** refresh provider model metadata and ordering. ([#2318](https://github.com/diegosouzapw/OmniRoute/pull/2318) — thanks @backryun)
-- **chore(providers):** consolidate Alibaba provider entries. ([#2319](https://github.com/diegosouzapw/OmniRoute/pull/2319) — thanks @backryun)
-- **fix(streaming):** harden stream readiness detection. ([#2317](https://github.com/diegosouzapw/OmniRoute/pull/2317) — thanks @dhaern)
-- **fix(v1/messages):** default to non-streaming when `stream` field is absent for Anthropic format. ([#2326](https://github.com/diegosouzapw/OmniRoute/pull/2326) — thanks @thepigdestroyer)
-- **fix(claude):** `fitThinkingToMaxTokens` caps thinking budget to model's output ceiling. ([#2327](https://github.com/diegosouzapw/OmniRoute/pull/2327) — thanks @thepigdestroyer)
-- **fix(codex):** Codex reasoning priority resolves `modelEffort` before `explicitReasoning`. ([#2335](https://github.com/diegosouzapw/OmniRoute/pull/2335) — thanks @terence71-glitch)
-- **fix(providers):** providers page no longer deadlocks when no providers are configured. ([#2329](https://github.com/diegosouzapw/OmniRoute/pull/2329) — thanks @slider23)
-- **chore(providers):** update HuggingFace to use the new `/v1/` router endpoint. ([#2322](https://github.com/diegosouzapw/OmniRoute/pull/2322) — thanks @backryun)
-- **fix(security):** resolve CodeQL ReDoS + URL sanitization alerts.
-- **fix(auth):** stop retrying unrecoverable token refresh failures and include connection id in token health check credentials.
-- **fix(auth):** return synthetic credentials for noAuth free providers and show no-auth card in dashboard instead of OAuth modal.
-- **fix(endpoint):** replace nested `<button>` with `<div role=button>` in tunnel toggle rows to fix hydration warnings.
-- **fix(migrations):** resolve version collision at migration slot 056 and add batch deletion API. ([#2294](https://github.com/diegosouzapw/OmniRoute/pull/2294) — thanks @hartmark)
-- **feat(batch):** global rate-limit header cache with 60s TTL + 24h retry window. ([#2299](https://github.com/diegosouzapw/OmniRoute/pull/2299) — thanks @hartmark)
-- **feat(cc-bridge):** config-driven per-provider system-block transform DSL. ([#2286](https://github.com/diegosouzapw/OmniRoute/pull/2286), closes #2260 — thanks @mrmm)
-- **feat(deepseek-web):** full DeepSeek web API executor with Keccak PoW solver. ([#2295](https://github.com/diegosouzapw/OmniRoute/pull/2295) — thanks @oyi77)
-- **feat(i18n):** add Azerbaijani (az / 🇦🇿) language support — new locale in `config/i18n.json`, 42 total supported languages.
-- **build(deps):** bump `actions/checkout` from 4 to 6 in CI workflows. ([#2288](https://github.com/diegosouzapw/OmniRoute/pull/2288))
-
-#### 2026-05-17
-
-- **fix(codex):** bulk import Codex `auth.json` — multi-file upload, paste-from-clipboard, and ZIP archive support. ([#2343](https://github.com/diegosouzapw/OmniRoute/pull/2343))
-- **feat(codex):** import single Codex `auth.json` as an OAuth connection (one-click migration from Codex Desktop). ([#2336](https://github.com/diegosouzapw/OmniRoute/pull/2336))
-- **feat(codex-auth):** rename `export` action + gate "Apply Local" behind a confirmation modal to prevent accidental local config overwrite. ([#2332](https://github.com/diegosouzapw/OmniRoute/pull/2332))
-- **fix(providers):** providers page empty-state — missing i18n keys and "Add Provider" CTA so first-time users can add a provider. ([#2333](https://github.com/diegosouzapw/OmniRoute/pull/2333), [#2337](https://github.com/diegosouzapw/OmniRoute/pull/2337))
-- **fix(providers):** Fix Providers empty state blocking first provider setup. (thanks @slider23)
-- **feat(providers):** bulk add API keys with Single/Bulk tabs.
-- **feat(ui):** comprehensive dashboard UX rework including simple/advanced modes for RTK/Caveman, human-readable error badges, InfoTooltip/PresetSlider shared components, sidebar subtitles, and provider category filters. ([#2315](https://github.com/diegosouzapw/OmniRoute/pull/2315), [#2316](https://github.com/diegosouzapw/OmniRoute/pull/2316) — thanks @oyi77)
-- **feat(provider):** add Gitlawb Opengateway provider (xiaomi-mimo + gmi-cloud) with hasFree flag support. ([#2314](https://github.com/diegosouzapw/OmniRoute/pull/2314) — thanks @oyi77)
-- **feat(i18n):** add simple/advanced mode keys and missing provider filter keys (`allProviders`, `audioProviders`, `showFreeOnly`).
-
-#### 2026-05-16
-
-- **feat(deepseek-web):** full DeepSeek web API executor with PoW solver — also landed via PR #2295. (thanks @oyi77)
-- **feat(batch):** global rate-limit header cache with 60s TTL — also via #2299.
-- **feat(cc-bridge):** config-driven per-provider system-block transform DSL — also via #2286.
-- **feat(dashboard):** provider summary card, free test button, sidebar order, i18n fix.
-- **feat(dashboard):** A2A audit page, stats bar on MCP audit, sidebar deduplication.
-- **feat(skills):** add 5 CLI skill manifests + AgentSkills / OmniSkills dashboard pages. ([#2284](https://github.com/diegosouzapw/OmniRoute/pull/2284))
-- **fix(translator):** map `developer` → `system` by default for non-OpenAI-family providers. ([#2281](https://github.com/diegosouzapw/OmniRoute/pull/2281))
-- **fix(api/combos):** add API-key-safe `GET /v1/combos` endpoint. ([#2300](https://github.com/diegosouzapw/OmniRoute/pull/2300))
-- **fix(embeddings/registry):** add DeepInfra to the embedding provider registry. ([#2298](https://github.com/diegosouzapw/OmniRoute/pull/2298))
-- **fix(opencode-zen):** flag `qwen3.6-plus` and `qwen3.6-plus-free` with `targetFormat: "claude"`. ([#2292](https://github.com/diegosouzapw/OmniRoute/pull/2292))
-- **fix(settings):** default `debugMode` to `true` on fresh installations.
-- **fix(sse):** remove dead-code flag leak in `claudeCodeToolRemapper`. ([#2290](https://github.com/diegosouzapw/OmniRoute/pull/2290) — thanks @thepigdestroyer)
-- **fix(sse):** strip stale `Content-Encoding`, `Content-Length`, `Transfer-Encoding` from upstream responses. ([#2291](https://github.com/diegosouzapw/OmniRoute/pull/2291) — thanks @thepigdestroyer)
-- **fix(migrations):** resolve version collisions and add schema repair for quota thresholds.
-
-#### 2026-05-15
-
-- **feat(cli):** CLI v4 — Commander.js architecture, 50+ commands, interactive TUI, full i18n (42 locales), plugin system (Fases 0–9). ([#2280](https://github.com/diegosouzapw/OmniRoute/pull/2280))
-- **feat(skills):** publish 3 operational SKILL.md manifests + AI Skills dashboard entry. ([#2276](https://github.com/diegosouzapw/OmniRoute/pull/2276))
-- **feat(termux):** Android/Termux headless support — auto-detect Android platform for headless mode. ([#2273](https://github.com/diegosouzapw/OmniRoute/pull/2273) — thanks @t-way666)
-- **feat(limits):** per-window quota cutoffs across all providers with usage data. ([#2267](https://github.com/diegosouzapw/OmniRoute/pull/2267) — thanks @payne0420)
-- **feat(api-keys):** configurable default rate limits via `DEFAULT_RATE_LIMIT_PER_DAY` env var. ([#2266](https://github.com/diegosouzapw/OmniRoute/pull/2266) — thanks @gleber)
-- **feat(authz):** `managementPolicy` accepts API keys with `manage` scope. ([#2265](https://github.com/diegosouzapw/OmniRoute/pull/2265) — thanks @gleber)
-- **feat(mcp):** MCP accessibility-tree smart filter engine — collapses ≥30 repeated sibling lines, 60-80% token savings.
-- **feat(auth):** CLI machine-ID HMAC-SHA256 token for zero-friction local auth without JWT/password.
-- **feat(security):** route protection tiers — 5 tiers: public/read-only/protected/always/local-only.
-- **feat(compression):** Caveman `SHARED_BOUNDARIES` — all 6 languages × 3 intensities embed boundary clause.
-- **feat(runtime):** dynamic SQLite 5-step fallback chain — bundled → runtime-installed → lazy-install → node:sqlite → sql.js.
-- **feat(cli):** standalone system tray with PowerShell fallback on Windows (`omniroute --tray`).
-- **fix(providers/command-code):** send required `skills` and `stream` payload fields. ([#2271](https://github.com/diegosouzapw/OmniRoute/pull/2271) — thanks @ddarkr)
-- **chore:** ignore `.playwright-mcp/` generated artifacts. ([#2269](https://github.com/diegosouzapw/OmniRoute/pull/2269) — thanks @backryun)
-- **chore:** tidy up deprecated models from Windsurf provider registry. ([#2279](https://github.com/diegosouzapw/OmniRoute/pull/2279) — thanks @backryun)
-- **chore(deps):** node dependency updates. ([#2259](https://github.com/diegosouzapw/OmniRoute/pull/2259) — thanks @backryun)
-- **build(deps):** bump `mermaid` from 11.14.0 to 11.15.0. ([#2178](https://github.com/diegosouzapw/OmniRoute/pull/2178))
-
-#### 2026-05-08 a 2026-05-14
-
-- **feat(guardrails/vision-bridge):** add `VISION_BRIDGE_BASE_URL` + `VISION_BRIDGE_API_KEY` env overrides for non-Anthropic vision-bridge routing. ([#2232](https://github.com/diegosouzapw/OmniRoute/pull/2232))
-- **feat(claude-web):** implement session-based Claude Web executor with auto-refresh authentication. ([#2283](https://github.com/diegosouzapw/OmniRoute/pull/2283) — thanks @oyi77)
-- **refactor(@omniroute/opencode-provider):** complete rewrite of the npm helper — tsup build (CJS + ESM + `.d.ts`), schema-correct output, `baseURL` deduplication, input validation, 13 unit tests. Versioned as `0.1.0`.
-- **BREAKING:** dropped Node 20.x support. Minimum Node version is now 22.22.2 (or 24.0.0+).
-- **fix(auth):** accept `x-api-key` header in `extractApiKey` so Anthropic-native clients hit the same per-key policy enforcement. ([#2225](https://github.com/diegosouzapw/OmniRoute/pull/2225))
-- **fix(translator/claude-to-openai):** stop including `cache_creation_input_tokens` in `prompt_tokens`. ([#2215](https://github.com/diegosouzapw/OmniRoute/pull/2215))
-- **fix(kiro):** harden OpenAI-to-Kiro translator for API compliance. ([#2251](https://github.com/diegosouzapw/OmniRoute/pull/2251) — thanks @8mbe)
-- **fix(models):** sync managed model aliases with provider model visibility. ([#2250](https://github.com/diegosouzapw/OmniRoute/pull/2250) — thanks @InkshadeWoods)
-- **fix(models/cleanup):** align managed model cleanup for imported models. ([#2261](https://github.com/diegosouzapw/OmniRoute/pull/2261) — thanks @InkshadeWoods)
-- **fix(executor/claude-code):** store tool-name round-trip metadata in non-enumerable `_toolNameMap`. ([#2254](https://github.com/diegosouzapw/OmniRoute/pull/2254) — thanks @Rikonorus)
-- **fix(streaming):** strip upstream `Content-Encoding`, `Content-Length`, `Transfer-Encoding` headers from SSE responses. ([#2253](https://github.com/diegosouzapw/OmniRoute/pull/2253) — thanks @Rikonorus)
-- **fix(security):** remediate CodeQL vulnerabilities (ReDoS, cryptographic bias, stack trace exposure, weak password hashing). ([#216](https://github.com/diegosouzapw/OmniRoute/issues/216), [#215](https://github.com/diegosouzapw/OmniRoute/issues/215), [#211](https://github.com/diegosouzapw/OmniRoute/issues/211), [#208](https://github.com/diegosouzapw/OmniRoute/issues/208), [#206](https://github.com/diegosouzapw/OmniRoute/issues/206), [#210](https://github.com/diegosouzapw/OmniRoute/issues/210))
-- **fix(providers/blackbox-web):** add `BLACKBOX_WEB_VALIDATED_TOKEN` env override and 403 token-error disambiguation. ([#2252](https://github.com/diegosouzapw/OmniRoute/pull/2252))
-- **fix(auth):** `REQUIRE_API_KEY=false` invalid Bearer no longer 401s the whole request. ([#2257](https://github.com/diegosouzapw/OmniRoute/pull/2257))
-- **feat(resilience):** add model cooldowns dashboard card with real-time list, individual/bulk re-enable, and auto-refresh.
-- **feat(resilience):** `useUpstream429BreakerHints` toggle. ([#2133](https://github.com/diegosouzapw/OmniRoute/pull/2133) — thanks @eleata)
-- **feat(auto):** zero-config auto-routing with `auto/` prefix — dynamic virtual combo from connected providers with 6 variant profiles. ([#2131](https://github.com/diegosouzapw/OmniRoute/pull/2131) — thanks @oyi77)
-- **feat(kiro):** headless auth via kiro-cli SQLite, image support, tool overflow handling, model list sync. ([#2129](https://github.com/diegosouzapw/OmniRoute/pull/2129) — thanks @christlau)
-- **feat(cursor):** surface Cursor Pro plan usage on provider-limits dashboard. ([#2128](https://github.com/diegosouzapw/OmniRoute/pull/2128) — thanks @payne0420)
-- **feat(mitm):** dynamic Linux certificate path detection for multi-distro MITM cert trust. ([#2134](https://github.com/diegosouzapw/OmniRoute/pull/2134) — thanks @flyingmongoose)
-- **feat(1proxy):** add dedicated settings tab with proxy rotation support. ([#2135](https://github.com/diegosouzapw/OmniRoute/pull/2135) — thanks @oyi77)
-- **feat(responses):** degrade `background: true` to synchronous execution with a warning. ([#2164](https://github.com/diegosouzapw/OmniRoute/pull/2164) — thanks @Yosee11)
-- **feat(api):** aggregate combo model metadata in catalog endpoint. ([#2166](https://github.com/diegosouzapw/OmniRoute/pull/2166) — thanks @faisalill)
-- **feat(oauth):** complete Windsurf and Devin CLI OAuth + API-token flows. ([#2168](https://github.com/diegosouzapw/OmniRoute/pull/2168) — thanks @Zhaba1337228)
-- **feat(antigravity):** support custom Google Cloud project ID. ([#2227](https://github.com/diegosouzapw/OmniRoute/pull/2227) — thanks @nickwizard)
-- **feat(cli):** CLI Integration Suite — 5 new management commands, 3 API endpoints, config generators for 6 tools. ([#2240](https://github.com/diegosouzapw/OmniRoute/pull/2240) — thanks @oyi77)
-- **fix(sanitizer):** preserve `reasoning_content` on assistant messages with `tool_calls`. ([#2140](https://github.com/diegosouzapw/OmniRoute/pull/2140) — thanks @DavyMassoneto)
-- **fix(catalog):** ensure individual models expose `context_length` via `getTokenLimit()` fallback chain. ([#2136](https://github.com/diegosouzapw/OmniRoute/pull/2136) — thanks @herjarsa)
-- **fix(docker):** remove docs directory from `.dockerignore`. ([#2137](https://github.com/diegosouzapw/OmniRoute/pull/2137), [#2120](https://github.com/diegosouzapw/OmniRoute/pull/2120) — thanks @hartmark)
-- **fix(providers):** restore cloud agent provider exports and logger import. ([#2138](https://github.com/diegosouzapw/OmniRoute/pull/2138) — thanks @backryun)
-- **fix(providers):** remove duplicate `CLOUD_AGENT_PROVIDERS` declaration. ([#2141](https://github.com/diegosouzapw/OmniRoute/pull/2141) — thanks @backryun)
-- **fix(translator):** preserve `body.system` in openai→claude when Claude Code sends native format. ([#2130](https://github.com/diegosouzapw/OmniRoute/pull/2130))
-- **fix(authz):** classify `/dashboard/onboarding` as PUBLIC to unblock setup wizard. ([#2127](https://github.com/diegosouzapw/OmniRoute/pull/2127))
-- **fix(i18n):** complete Simplified Chinese translations. ([#2115](https://github.com/diegosouzapw/OmniRoute/pull/2115) — thanks @boa-z)
-- **fix(sse):** classify hour quota errors as QUOTA_EXHAUSTED. ([#2119](https://github.com/diegosouzapw/OmniRoute/pull/2119) — thanks @clousky2020)
-- **fix(sse):** fix CC-compatible streaming bridge. ([#2118](https://github.com/diegosouzapw/OmniRoute/pull/2118) — thanks @rdself)
-- **fix(cliproxyapi):** detect Anthropic-shaped request bodies and route to `/v1/messages`. ([#2165](https://github.com/diegosouzapw/OmniRoute/pull/2165) — thanks @Brkic-Nikola)
-- **fix(claudeHelper):** preserve latest assistant thinking blocks verbatim. ([#2224](https://github.com/diegosouzapw/OmniRoute/pull/2224) — thanks @NomenAK)
-- **fix(deepseek):** preserve `reasoning_content` through full pipeline for DeepSeek V4 models. ([#2231](https://github.com/diegosouzapw/OmniRoute/pull/2231) — thanks @kang-heewon)
-- **fix(chatcore):** stop leaking provider credentials in response headers.
-- **fix(export):** exclude telemetry/usage-history tables from JSON config backups by default. ([#2125](https://github.com/diegosouzapw/OmniRoute/pull/2125))
-- **build(deps):** regenerate `package-lock.json` to match `http-proxy-middleware` 4.x bump. ([#2228](https://github.com/diegosouzapw/OmniRoute/pull/2228) — thanks @NomenAK)
-
-#### 2026-05-06 a 2026-05-07 (lançamento inicial v3.8.0)
-
-- **feat(zed):** Zed IDE Docker support — when OmniRoute runs in Docker and Zed is on the host, the Import flow now returns a 422 with `zedDockerEnvironment: true` and the dashboard auto-expands a Manual Token Import panel (new `POST /api/providers/zed/manual-import` endpoint with Zod validation). Includes Docker detection utility (`/.dockerenv` + cgroup heuristics) and a setup guide at [`docs/providers/ZED-DOCKER.md`](docs/providers/ZED-DOCKER.md). ([#2306])
-- **feat(workflow):** `/implement-features` gains pre-flight triage script (`scripts/features/feature-triage.mjs`) classifying open feature requests into 8 buckets — fresh issues (<14d) stay dormant to give the community time to react, engagement override (≥5 👍 or ≥3 unique non-bot commenters) absorbs early, already-delivered detection via merged PRs + CHANGELOG + git log closes issues with version + PR reference, stale `need_details/` (>30d) is closed politely, aged `defer/` (>90d) is re-evaluated, and externally-closed issues clean up `_ideia/` automatically. Idea files now carry a YAML frontmatter snapshot enabling incremental comment re-sync. 53 unit tests cover the new logic.
-- **feat(providers):** add GitHub Models as a free provider — GPT-5, o-series, DeepSeek-R1, Llama 4, Grok 3 with GitHub PAT auth and dynamic model fetch from `api.github.com`. ([#2344](https://github.com/diegosouzapw/OmniRoute/pull/2344) — thanks @oyi77)
-- **feat(providers):** add Hackclub AI as a free provider — 30+ models, no credit card required, optional API key auth with passthrough model support. ([#2339](https://github.com/diegosouzapw/OmniRoute/pull/2339) — thanks @oyi77)
-- **feat(providers):** add Microsoft Copilot Web executor — WebSocket-based provider translating OpenAI chat completions to Copilot's proprietary event protocol with per-token session pool isolation. ([#2340](https://github.com/diegosouzapw/OmniRoute/pull/2340) — thanks @oyi77)
-- **feat(routing):** LKGP stores last known good account `connectionId` alongside provider — combo routing now prioritizes the exact connection that last succeeded, with graceful provider-level fallback for old records. ([#2338](https://github.com/diegosouzapw/OmniRoute/pull/2338) — thanks @oyi77)
-- **feat(i18n):** add Azerbaijani (az / 🇦🇿) language support — new locale in `config/i18n.json` (source of truth), `src/i18n/messages/az.json` (UI strings), `docs/i18n/az/` (full documentation set), README language bar, docs i18n index, and both translation pipeline scripts (`generate-multilang.mjs`, `i18n_autotranslate.py`). Total supported languages: **42**.
-- **feat(limits):** per-window quota cutoffs across all providers with usage data — operators can set per-quota-window thresholds (e.g. `session=95%, weekly=80%`) with cascading resolver (connection → provider default → global 98%) and zero-latency gate when nothing is configured. New migration 056, new `GET /api/providers/quota-windows` endpoint, and Dashboard › Limits cutoff modal. ([#2267](https://github.com/diegosouzapw/OmniRoute/pull/2267) — thanks @payne0420)
-- **feat(api-keys):** configurable default rate limits via `DEFAULT_RATE_LIMIT_PER_DAY` env var — replaces hardcoded 1000/day fallback with Zod-validated configuration while preserving secure defaults for existing deployments. ([#2266](https://github.com/diegosouzapw/OmniRoute/pull/2266) — thanks @gleber)
-- **feat(authz):** `managementPolicy` accepts API keys with `manage` scope — enables headless/programmatic management (provisioning providers, setting rate limits) without a browser session. ([#2265](https://github.com/diegosouzapw/OmniRoute/pull/2265) — thanks @gleber)
-- **feat(termux):** Android/Termux headless support — auto-detect Android platform for headless mode (no browser open), move `wreq-js` and `tls-client-node` to `optionalDependencies` for ARM compatibility, lazy-load WS proxy with graceful 503 when unavailable, set `GYP_DEFINES` for `better-sqlite3` ARM build, extended build timeout to 600s. ([#2273](https://github.com/diegosouzapw/OmniRoute/pull/2273) — thanks @t-way666)
-- **feat(deepseek-web):** full DeepSeek web API executor with Keccak PoW solver (`DeepSeekHashV1`), SSE streaming, and auto-refresh session management via `ds_session_id`. ([#2295](https://github.com/diegosouzapw/OmniRoute/pull/2295) — thanks @oyi77)
-- **feat(cc-bridge):** config-driven per-provider system-block transform DSL — operators can now configure system prompt transformations per-provider via Dashboard settings UI. ([#2286](https://github.com/diegosouzapw/OmniRoute/pull/2286), closes #2260 — thanks @mrmm)
-- **feat(batch):** global rate-limit header cache with 60s TTL + 24h time-based retry window — shares rate-limit throttle state across sequential batches and uses time-based retry limits for robust large-batch processing. ([#2299](https://github.com/diegosouzapw/OmniRoute/pull/2299) — thanks @hartmark)
-- **feat(providers):** improve Cohere provider support, expanding models and accurately updating OpenAI context limits. ([#2313](https://github.com/diegosouzapw/OmniRoute/pull/2313) — thanks @backryun)
-- **feat(claude-web):** implement session-based Claude Web executor with auto-refresh authentication — enables direct Claude Web API access without an API key. ([#2283](https://github.com/diegosouzapw/OmniRoute/pull/2283) — thanks @oyi77)
-- **feat(skills):** add 5 CLI skill manifests + AgentSkills / OmniSkills dashboard pages — enables external AI agents to discover and invoke OmniRoute capabilities. ([#2284](https://github.com/diegosouzapw/OmniRoute/pull/2284))
-- **feat(providers):** add llama.cpp as local provider — `llama-cpp` (alias `llamacpp`) added to `LOCAL_PROVIDERS` and `SELF_HOSTED_CHAT_PROVIDER_IDS`; default base URL `http://127.0.0.1:8080/v1`; no API key required; uses the default OpenAI-compatible executor ([#1980](https://github.com/diegosouzapw/OmniRoute/issues/1980))
-- **feat(providers):** bulk add API keys with Single/Bulk tabs.
-- **feat(provider):** add Gitlawb Opengateway provider (xiaomi-mimo + gmi-cloud) with hasFree flag support. ([#2314](https://github.com/diegosouzapw/OmniRoute/pull/2314) — thanks @oyi77)
-- **feat(ui):** comprehensive dashboard UX rework including simple/advanced modes for RTK/Caveman, human-readable error badges, InfoTooltip/PresetSlider shared components, sidebar subtitles, and provider category filters. ([#2315](https://github.com/diegosouzapw/OmniRoute/pull/2315), [#2316](https://github.com/diegosouzapw/OmniRoute/pull/2316) — thanks @dhaern, @oyi77)
-- **feat(i18n):** add simple/advanced mode keys and missing provider filter keys (`allProviders`, `audioProviders`, `showFreeOnly`).
-- **feat(cli):** full i18n support — 42 locales, `--lang` flag, `config lang get/set/list` commands for CLI language selection. ([#2285](https://github.com/diegosouzapw/OmniRoute/pull/2285))
-- **feat(claude-code):** semantic passthrough for Claude Code `/v1/messages` payloads — preserves client `messages[]` structure (document blocks, tool_use/tool_result chains, cache_control, unknown content types) for native Claude OAuth and `anthropic-compatible-cc-*` relay routes, skipping broad normalization that could rewrite valid Claude Code semantics. ([#2351](https://github.com/diegosouzapw/OmniRoute/pull/2351) — thanks @terence71-glitch)
-
-### Changed
-
-- **CLI**: Refactored architecture to use Commander.js as framework. Monolith `bin/cli-commands.mjs` (2853 lines) removed — commands now live individually in `bin/cli/commands/`. No breaking changes in normal usage; all previously listed subcommands continue working.
-
-### Removed
-
-- `bin/cli-commands.mjs` — replaced by modular structure in `bin/cli/commands/`.
-- `bin/cli/index.mjs` — replaced by `bin/cli/program.mjs` + `bin/cli/commands/registry.mjs`.
-- `bin/cli/args.mjs` — replaced by Commander.js native parsing support.
-
-- **refactor(@omniroute/opencode-provider):** complete rewrite of the npm helper. The `1.0.0` artifact was non-functional — `index.js` re-exported from `.ts` (unrunnable at install time) and the emitted shape didn't match the OpenCode `https://opencode.ai/config.json` schema. The new release ships a real `tsup` build (CJS + ESM + `.d.ts`), schema-correct output (`npm: "@ai-sdk/openai-compatible"`, with `models` catalog), `baseURL` deduplication (no more `/v1/v1`), input validation, 13 unit tests, and full documentation in [`docs/frameworks/OPENCODE.md`](docs/frameworks/OPENCODE.md). Versioned as `0.1.0` to signal the pre-1.0 reset.
-- **chore(npm):** [`@omniroute/opencode-provider@0.1.0`](https://www.npmjs.com/package/@omniroute/opencode-provider) published to npmjs.com under the new `@omniroute` org. Install with `npm install --save-dev @omniroute/opencode-provider`.
-- **BREAKING**: dropped Node 20.x support. Minimum Node version is now 22.22.2 (or 24.0.0+). Required because http-proxy-middleware 4.x requires `node >=22.15.0`. Users on Node 20 must upgrade — see [`package.json` engines field](package.json) and the README Node badge.
-
-### Security
-
-- **fix(oauth/windsurf):** Windsurf Firebase token refresh now reads `WINDSURF_CONFIG.firebaseApiKey` instead of `process.env.WINDSURF_FIREBASE_API_KEY` directly.
-- **fix(kiro/translator):** assistant-first conversations no longer collide on a single `conversationId`.
-- **fix(utils/publicCreds):** `decodePublicCred()` no longer silently mangles raw credential overrides that don't match `RAW_VALUE_PATTERN`.
-- **fix(auth/extractApiKey):** `x-api-key` fallback now only triggers when the request also carries an `anthropic-version` header.
-- **fix(providers/qoder):** the OAuth+PAT disambiguation message now actually surfaces.
-- **fix(authz/clientApi):** when `REQUIRE_API_KEY=false`, an invalid Bearer no longer 401s the whole request — falls through to anonymous (matching the "no auth required" semantics of the flag) with a single warning log carrying the masked key id. Fixes the surprise 401s that hit CLI integrations (Codex Desktop auto-config, Hermes Agent) that ship a stale Bearer in their saved config. (#2257)
-
-### Fixed
-
-- **fix(providers/llm7):** add `llm7` to the executor registry (`open-sse/config/providerRegistry.ts`). The provider was advertised in the dashboard catalog but missing from the executor table, so every connection test failed with a credential error. Now routes through the standard OpenAI-compatible `https://api.llm7.io/v1/chat/completions` endpoint with optional bearer auth. (#2361)
-- **fix(providers/cohere):** switch the Cohere upstream from `https://api.cohere.com/v2/chat` (native shape) to `https://api.cohere.com/compatibility/v1/chat/completions` (OpenAI-compatible). The native endpoint returned `{ message: { content: [...] } }` which the combo test validator could not read, surfacing as `Provider returned HTTP 200 but no text content.` (#2360)
-- **fix(combo/dispatch):** add defensive `typeof target.modelStr === "string"` guards around the LKGP fallback findIndex and the combo test target builder. Combo entries whose `modelStr` failed to resolve at routing time (regression after #2338 added per-account LKGP) used to crash the request with `TypeError: e.startsWith is not a function`; we now surface a clean error instead. (#2359)
-- **fix(rate-limiter):** Redis is now opt-in. When `REDIS_URL` is unset, the rate limiter and API-key auth cache fall back silently to the in-memory store instead of spamming `connect ECONNREFUSED 127.0.0.1:6379` for every request. Connection-error logging is also deduped so docker logs no longer flood under sustained outage. Single-instance deployments work out of the box; multi-instance deployments continue to use Redis when `REDIS_URL` is provided. (#2357)
-- **fix(auto-routing):** stop the `ReferenceError: getSettings is not defined` 500 that every `auto` / `auto/*` request raised. `src/sse/handlers/chat.ts` called the bare `getSettings` symbol without importing it; replaced with the already-imported `getCachedSettings` (same shape, plus the auto-routing hot path benefits from the cache). (#2346)
-- **fix(combo/validator):** treat upstream responses carrying a non-empty `reasoning_content` (or `reasoning`) field as valid output, even when `content` is null. Reasoning models like `moonshotai/Kimi-K2.5-TEE`, `zai-org/GLM-5-TEE`, and the QwQ family put their answer in `reasoning_content` only — the quality validator was rejecting them with `502: empty content` and triggering unnecessary combo fallbacks. (#2341)
-- **fix(docker):** the Dashboard Docs viewer now actually has documents to show. `.dockerignore` was hiding every file under `docs/` except `openapi.yaml`, so the in-product `/docs/*` viewer threw `ENOENT: no such file or directory, open '/app/docs/...'` for every page. We now ship the ~5 MB English markdown tree and still exclude the ~45 MB of translations/screenshots/raster diagrams that were the original optimization target. (#2348)
-- **fix(account-fallback):** Anthropic OAuth (Claude Code Pro/Team) 429 responses carrying phrases like `Usage Limit Reached`, `Claude Pro usage limit reached`, or `you've reached your usage limit` are now classified as `QUOTA_EXHAUSTED` with a 1h cooldown instead of `RATE_LIMIT_EXCEEDED` with a ~5s transient backoff. Previously every Claude Pro account cascaded into a tight retry loop until the 5h subscription window genuinely reset. Also honors absolute ISO timestamps embedded in the error body (`Try again at 2026-05-17T10:00:00Z`) so the cooldown matches the upstream's stated recovery time. (#2321)
-- **fix(ui/tooltip):** the shared `<Tooltip>` component now renders into a React portal anchored to `document.body` by default, so tooltips in modal dialogs (combo editor, etc.) are no longer clipped by `overflow:hidden` ancestors. Adds an optional `multiline` prop that swaps the legacy `whitespace-nowrap` clamp for `max-w-xs whitespace-normal break-words` when the label is long. Coordinates are clamped to the viewport so triggers near the right edge don't bleed off-screen. (#2352)
-- **fix(claude):** avoided redundant deep cloning of Claude Code messages during semantic passthrough preparation, improving memory/CPU efficiency for large histories. ([#2362](https://github.com/diegosouzapw/OmniRoute/pull/2362) — thanks @terence71-glitch)
-- **fix(streaming):** emit protocol-aware stream errors — `createDisconnectAwareStream()` now emits native Responses API (`response.failed`) or Claude API (`event: error`) SSE error blocks based on the client protocol instead of falling back to raw Chat Completions chunks, resolving upstream client parse failures on mid-stream disconnects. ([#2355](https://github.com/diegosouzapw/OmniRoute/pull/2355) — thanks @dhaern)
-- **fix(combos):** allow bracketed combo names (e.g. `Claude [1m]`) by updating validation schemas and pinning exact combo lookup behavior before model suffix parsing. ([#2354](https://github.com/diegosouzapw/OmniRoute/pull/2354) — thanks @congvc-dev)
-- **fix(v1/messages):** `POST /v1/messages` now defaults to non-streaming when the `stream` field is absent and the Anthropic source format is detected — prevents `STREAM_EARLY_EOF` errors from Anthropic SDK clients that omit the field per spec. ([#2326](https://github.com/diegosouzapw/OmniRoute/pull/2326) — thanks @thepigdestroyer)
-- **fix(claude):** `fitThinkingToMaxTokens` caps thinking budget to the model's output ceiling — eliminates HTTP 400 from Anthropic when `max_tokens + budget` exceeds model limits (e.g. Opus 4.7's 128K ceiling). ([#2327](https://github.com/diegosouzapw/OmniRoute/pull/2327) — thanks @thepigdestroyer)
-- **fix(codex):** Codex reasoning priority now resolves `modelEffort` before `explicitReasoning` — aligns with expected precedence and fixes suffix alias mismatches. ([#2335](https://github.com/diegosouzapw/OmniRoute/pull/2335) — thanks @terence71-glitch)
-- **fix(translator):** DeepSeek tool-call response lookup reads cached reasoning before falling back to empty string — preserves reasoning content in multi-turn tool-call flows. ([#2349](https://github.com/diegosouzapw/OmniRoute/pull/2349) — thanks @herjarsa)
-- **fix(providers):** providers page no longer deadlocks when no providers are configured — setup hint is shown instead of an empty filtered list, allowing the first provider to be added. ([#2329](https://github.com/diegosouzapw/OmniRoute/pull/2329) — thanks @slider23)
-- **fix(usage):** extract flat `cached_tokens` and `reasoning_tokens` from OpenAI-compatible usage objects — providers like Xiaomi MiMo that return these as top-level fields instead of nesting in `prompt_tokens_details`/`completion_tokens_details` now properly surface in call logs and dashboard. ([#2350](https://github.com/diegosouzapw/OmniRoute/pull/2350) — thanks @TF0rd)
-- **chore(providers):** update HuggingFace to use the new `/v1/` router endpoint with dynamic model list (`router.huggingface.co/v1/`), removing the stale static model list. ([#2322](https://github.com/diegosouzapw/OmniRoute/pull/2322) — thanks @backryun)
-- **fix(security):** resolve CodeQL ReDoS + URL sanitization alerts.
-- **fix(auth):** stop retrying unrecoverable token refresh failures and include connection id in token health check credentials.
-- **fix(auth):** return synthetic credentials for noAuth free providers and show no-auth card in dashboard instead of OAuth modal.
-- **fix(endpoint):** replace nested `<button>` with `<div role=button>` in tunnel toggle rows to fix hydration warnings.
-- **fix(claude):** guard orphan tool_use/tool_result pairs before upstream send, resolving a critical Anthropic 400 error on truncated histories. ([#2312](https://github.com/diegosouzapw/OmniRoute/pull/2312) — thanks @mrmm)
-- **fix(ui):** remove count from batch removal button for cleaner interface. ([#2309](https://github.com/diegosouzapw/OmniRoute/pull/2309) — thanks @hartmark)
-- **fix(sse):** strip stale `Content-Encoding`, `Content-Length`, and `Transfer-Encoding` headers on non-streaming forward — fixes JSON truncation on gzipped Gemini responses where clients honoring `Content-Length` read only the compressed byte count of the decompressed payload, causing `"Unterminated string in JSON"` parse failures. RFC 7230 §6.1 compliant. ([#2264](https://github.com/diegosouzapw/OmniRoute/pull/2264) — thanks @gleber)
-- **fix(executor/claude-code):** store tool-name round-trip metadata in non-enumerable `_toolNameMap` so it survives in-memory but is stripped by `JSON.stringify()` — prevents internal OmniRoute metadata from leaking to upstream providers. ([#2254](https://github.com/diegosouzapw/OmniRoute/pull/2254) — thanks @Rikonorus)
-- **fix(streaming):** strip upstream `Content-Encoding`, `Content-Length`, and `Transfer-Encoding` headers from SSE responses — prevents client-side decompression corruption when the proxy serves plain-text event streams through nginx/caddy. ([#2253](https://github.com/diegosouzapw/OmniRoute/pull/2253) — thanks @Rikonorus)
-- **fix(kiro):** harden OpenAI-to-Kiro translator for API compliance: recursively strip `additionalProperties` and empty `required: []` from tool schemas; merge consecutive assistant messages; prepend synthetic user for assistant-first conversations; convert orphaned tool results to inline text; enforce `origin: "AI_EDITOR"` on all history user messages; deterministic `uuidv5` session caching. Closes #2213. ([#2251](https://github.com/diegosouzapw/OmniRoute/pull/2251) — thanks @8mbe)
-- **fix(models):** sync managed model aliases with provider model visibility — remove aliases when models are hidden/deleted, skip alias creation for hidden models during sync, restore aliases when unhidden, cross-connection safety guard prevents pruning aliases still valid from another connection. ([#2250](https://github.com/diegosouzapw/OmniRoute/pull/2250) — thanks @InkshadeWoods)
-- **fix(models/cleanup):** align managed model cleanup for imported models — provider-level "Delete All" now also removes synced available model storage; delete-alias button only shown for alias-source rows; compatible models section uses proper 3-way source-aware delete logic. ([#2261](https://github.com/diegosouzapw/OmniRoute/pull/2261) — thanks @InkshadeWoods)
-- **fix(auth):** accept `x-api-key` header in `extractApiKey` so Anthropic-native clients (Claude Code, `@anthropic-ai/sdk`) hit the same per-key policy enforcement as Bearer clients. Previously these requests were treated as anonymous, bypassing model/budget/rate-limit policies and showing up as `NULL` in `usage_history.api_key_id` (~50% of traffic invisible in Costs/Analytics). `Authorization: Bearer` still wins when both are present (back-compat). (#2225)
-- **fix(translator/claude-to-openai):** stop including `cache_creation_input_tokens` in `prompt_tokens`. Anthropic pads short prompts up to a 1024-token minimum on cache creation, so a 2-token `"hi"` could be reported as ~2008 `prompt_tokens` and inflate downstream billing (Sub2API/NewAPI/OneAPI) ~250x. `prompt_tokens` now matches the dashboard "Total In" (`input + cache_read`); `cache_creation_tokens` is exposed separately in `prompt_tokens_details.cache_creation_tokens` for auditing. (#2215)
-- **fix(ui/claude-extra-usage):** clarify the toggle-success notification text to spell out the toggle→effect relationship ("Claude extra-usage blocking enabled/disabled" instead of the ambiguous "blocked/allowed"). (#2157)
-- **fix(providers/qoder):** disambiguate the "Local CLI runtime is not installed" error when a user pastes a Personal Access Token but the connection is in OAuth/CLI-flavored mode. The test route now surfaces a single actionable message ("switch this connection to API Key auth") instead of cascading CLI + 401 errors. (#2247)
-- **fix(dashboard/api-manager):** route custom OpenAI-/Anthropic-compatible provider IDs through `getProviderDisplayName` so the model grouping label shows `Compatible (openai)` instead of leaking the raw synthetic `openai-compatible-chat-<uuid>` value. (#2021)
-- **fix(providers/blackbox-web):** add `BLACKBOX_WEB_VALIDATED_TOKEN` env override and 403 token-error disambiguation. Blackbox `/api/chat` started rejecting requests whose `validated` field didn't match the frontend `tk` token, even with a valid cookie + active subscription. Operators with the real token can now set the env var; otherwise the previous random-UUID fallback still ships, and a 403 with a token-specific body now surfaces a one-line "set BLACKBOX_WEB_VALIDATED_TOKEN" hint instead of the generic "cookie expired" message. (#2252)
-- **fix(guardrails/vision-bridge):** add `VISION_BRIDGE_BASE_URL` + `VISION_BRIDGE_API_KEY` env overrides so non-Anthropic vision-bridge calls can be routed through OmniRoute's own `/v1` self-loop, Google's Gemini OpenAI-compat endpoint, OpenRouter, or any other OpenAI-compatible URL — instead of being hardcoded to `https://api.openai.com/v1` (which failed with 401 for users without an OpenAI key, even when they configured `visionBridgeModel: "google/gemini-2.0-flash"`). Anthropic models keep their dedicated path. (#2232)
-- **docs(security):** document the ToS-violation hot spot of `ANTIGRAVITY_CREDITS=always` in `STEALTH_GUIDE.md`, including why it draws Google abuse detection more aggressively than free-tier-only usage and the recommended posture (`=retry`, Auto-Combo spread, per-connection RPM caps). (#2246)
-- **fix(translator/developer-role):** convert OpenAI `developer` role → `system` by default for non-OpenAI-family providers. Codex/Responses API clients hitting DeepSeek (and other OpenAI-compatible gateways: MiniMax, Mimo, GLM, Fireworks, Together, etc.) were getting `400: unknown variant 'developer'` because the previous default preserved `developer` for any `targetFormat=openai` upstream. New default: preserve only for `openai`/`azure-openai`/`azure`/`github` (and any id containing `"openai"`); convert everywhere else. Operators can still force preservation per-model via the dashboard "Compatibility → preserveOpenAIDeveloperRole = true" toggle. (#2281)
-- **fix(api/combos):** add API-key-safe `GET /v1/combos` endpoint that mirrors the `/v1/models` auth model. Previously `/api/combos` was management-gated, blocking read-only integrations (e.g. `opencode-omniroute-auth` plugin) that need to enrich combo capabilities from a normal Bearer API key. The new endpoint projects only public metadata (name, strategy, model ids, providerId, description) — internal routing details like `connectionId`, weights, and labels are stripped. `/api/combos` (management) is unchanged. (#2300)
-- **fix(embeddings/registry):** add DeepInfra to the embedding provider registry. Custom embedding models on the DeepInfra provider (e.g. `Qwen/Qwen3-Embedding-8B`, `BAAI/bge-large-en-v1.5`) were failing with `Unknown embedding provider: deepinfra` because the registry only included Nebius/OpenAI/Together/Fireworks/NVIDIA/etc. Now ships 8 popular DeepInfra embedding models out of the box and routes through `https://api.deepinfra.com/v1/openai/embeddings`. (#2298)
-- **fix(opencode-zen):** flag `qwen3.6-plus` and `qwen3.6-plus-free` with `targetFormat: "claude"`. The opencode-zen upstream returns Claude-format SSE bodies (`type: "message_start"`, no `choices` array) for these Qwen3.6 models even when the request hits the OpenAI-compatible `/chat/completions` endpoint, causing client-side Zod failures (`expected "choices" (array), received undefined`). Routing them through the Claude `/messages` endpoint + translator fixes the format mismatch. (#2292)
-- **fix(settings):** default `debugMode` to `true` on fresh installations — the Debug sidebar section (Translator, Playground, Search Tools) was hidden on new installs because `debugMode` was not in the settings defaults object, making `data?.debugMode === true` evaluate to `false`. The toggle in System & Storage appeared active but had no effect until manually set. Now all sidebar sections are visible out of the box.
-- **fix(providers/command-code):** send required `skills` and `stream` payload fields — Command Code upstream wrapper now includes `skills: ""` and forces `params.stream: true` to align with upstream API requirements. Validation probe defaults to `deepseek/deepseek-v4-flash`. ([#2271](https://github.com/diegosouzapw/OmniRoute/pull/2271) — thanks @ddarkr)
-- **fix(sse):** strip stale `Content-Encoding`, `Content-Length`, and `Transfer-Encoding` from upstream responses — prevents JSON truncation and `ZlibError` on gzipped provider responses forwarded through the proxy. ([#2291](https://github.com/diegosouzapw/OmniRoute/pull/2291) — thanks @thepigdestroyer)
-- **fix(sse):** remove dead-code flag leak in `claudeCodeToolRemapper` — eliminates a stale boolean flag that could cause incorrect tool remapping behavior on subsequent requests. ([#2290](https://github.com/diegosouzapw/OmniRoute/pull/2290) — thanks @thepigdestroyer)
-- **fix(ui):** v3.8.0 polish — connections border, sticky tabs, EN translations, save toasts, auto-combo catalog. ([#2305](https://github.com/diegosouzapw/OmniRoute/pull/2305) — thanks @mrmm)
-- **fix:** remove implicit API key request caps — removes the default daily/weekly/monthly rate caps (1K/5K/20K) that silently applied 429s to API keys without explicit limits configured, causing unexpected throttling for operators who hadn't set custom rate policies. ([#2289](https://github.com/diegosouzapw/OmniRoute/pull/2289) — thanks @josephvoxone)
-- **fix(auth+build):** Bearer manage scope on management routes + lazy-load deepseek PoW solver — unblocks MCP remote usage and Docker Next.js standalone builds. ([#2308](https://github.com/diegosouzapw/OmniRoute/pull/2308) — thanks @mrmm)
-- **fix(migrations):** resolve version collision at migration slot 056 by renaming the quota thresholds migration to 057, and add batch deletion API with bulk cleanup support and batch/file management UI. ([#2294](https://github.com/diegosouzapw/OmniRoute/pull/2294) — thanks @hartmark)
-- **chore:** ignore `.playwright-mcp/` generated artifacts (CSP error logs, accessibility tree snapshots) — removes tracked test artifacts and adds the directory to `.gitignore`. ([#2269](https://github.com/diegosouzapw/OmniRoute/pull/2269) — thanks @backryun)
-- **chore:** tidy up deprecated models from Windsurf provider registry. ([#2279](https://github.com/diegosouzapw/OmniRoute/pull/2279) — thanks @backryun)
-- **build(deps):** bump `actions/checkout` from 4 to 6 in CI workflows. ([#2288](https://github.com/diegosouzapw/OmniRoute/pull/2288))
-- **build(deps):** regenerate `package-lock.json` to match `http-proxy-middleware` 4.x bump. ([#2228](https://github.com/diegosouzapw/OmniRoute/pull/2228) — thanks @NomenAK)
-- **fix(streaming):** harden stream readiness detection — recognize OpenAI Responses API lifecycle events (`response.created`, `response.in_progress`, `response.output_item.added`) and Chat Completions start chunks as readiness signals; switch GLM from idle timeout to readiness timeout; compact Provider Limits cutoff UI with i18n fallback labels; fix DeepSeek PoW dynamic import warning; static locale for docs prerender. ([#2317](https://github.com/diegosouzapw/OmniRoute/pull/2317) — thanks @dhaern)
-- **chore(providers):** refresh provider model metadata, sort dashboard entries by display name, fix docs generator relative links and frontmatter. ([#2318](https://github.com/diegosouzapw/OmniRoute/pull/2318) — thanks @backryun)
-- **chore(providers):** consolidate Alibaba provider entries — merge `alicode`/`alicode-intl` into shared `ALIBABA_DASHSCOPE_MODELS` array, update 42 i18n llm.txt files. ([#2319](https://github.com/diegosouzapw/OmniRoute/pull/2319) — thanks @backryun)
-- **chore:** narrow `.claude/` gitignore to runtime files only and untrack `scheduled_tasks.lock`.
-- **Docs:** 270 broken internal markdown links repaired.
-
-### 🏆 v3.8.0 Hall of Fame — extended credits (post-release)
-
-The following contributions landed after the initial v3.8.0 cut and supplement the 55+ community hall of fame below. Updated tallies:
-
-| Contributor                                              | New PRs in this cycle                                                | Full v3.8.0 PR list                                                                                                  |
-| :------------------------------------------------------- | :------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------- |
-| [@oyi77](https://github.com/oyi77)                       | #2338, #2339, #2340, #2344, #2364, #2366, #2369, #2377, #2380, #2383 | (+ already listed: #2010, #2014, #2041, #2052, #2061, #2074, #2091, #2094, #2096, #2131, #2135, #2240, #2283, #2295) |
-| [@backryun](https://github.com/backryun)                 | #2269, #2279, #2313, #2318, #2319, #2381                             | (+ already listed: #1992, #2033, #2088, #2123, #2138, #2141, #2150, #2177)                                           |
-| [@thepigdestroyer](https://github.com/thepigdestroyer)   | #2326, #2327, #2370                                                  | (+ already listed: #2290, #2291)                                                                                     |
-| [@mrmm](https://github.com/mrmm)                         | #2375, #2286 _(closes #2260)_, #2305, #2308, #2312                   | (consolidates the row)                                                                                               |
-| [@dhaern](https://github.com/dhaern)                     | #2315, #2316, #2317, #2355                                           | (+ already listed: #2028, #2039, #2087, #2090)                                                                       |
-| [@hartmark](https://github.com/hartmark)                 | #2294, #2299, #2309                                                  | (+ already listed: #2045, #2137)                                                                                     |
-| [@gleber](https://github.com/gleber)                     | #2264, #2265, #2266                                                  | (+ already listed: #2103)                                                                                            |
-| [@herjarsa](https://github.com/herjarsa)                 | #2349                                                                | (+ already listed: #2030, #2136, #2152)                                                                              |
-| [@congvc-dev](https://github.com/congvc-dev)             | #2354, #2392                                                         | (+ already listed: #2004)                                                                                            |
-| [@terence71-glitch](https://github.com/terence71-glitch) | #2335, #2351, #2362                                                  | (new contributor — 3 PRs)                                                                                            |
-| [@TF0rd](https://github.com/TF0rd)                       | #2350                                                                | (new contributor — 1 PR)                                                                                             |
-| [@slider23](https://github.com/slider23)                 | #2329, #2352                                                         | (new contributor — 2 PRs)                                                                                            |
-| [@t-way666](https://github.com/t-way666)                 | #2273                                                                | (new contributor — 1 PR)                                                                                             |
-| [@payne0420](https://github.com/payne0420)               | #2267                                                                | (+ already listed: #2082, #2128)                                                                                     |
-| [@Rikonorus](https://github.com/Rikonorus)               | #2253, #2254                                                         | (new contributor — 2 PRs)                                                                                            |
-| [@8mbe](https://github.com/8mbe)                         | #2251                                                                | (new contributor — 1 PR)                                                                                             |
-| [@InkshadeWoods](https://github.com/InkshadeWoods)       | #2250, #2261                                                         | (+ already listed: #2202)                                                                                            |
-| [@clousky2020](https://github.com/clousky2020)           | #2412                                                                | (+ already listed: 15 PRs)                                                                                           |
-| [@benzntech](https://github.com/benzntech)               | #2408                                                                | (+ already listed: 8 PRs)                                                                                            |
-
-Thanks also to **@app/dependabot** for keeping our dependency tree current via #2178, #2228, #2288, #2397, #2398, #2399.
-
----
-
-### Detalhes completos — features do release (2026-05-15)
-
-- **feat(providers):** expanded capabilities for Pollinations, MiniMax, Together, and Replicate across Video, Audio TTS, and Transcription registries. ([#2369](https://github.com/diegosouzapw/OmniRoute/pull/2369) — thanks @oyi77)
-- **feat(providers):** added Veo AI Free as a web-wrapper provider for generating video, image, and TTS without an API key. ([#2366](https://github.com/diegosouzapw/OmniRoute/pull/2366) — thanks @oyi77)
-- **feat(providers):** added Replicate as a free provider for OpenAI-compatible inference with community models. ([#2364](https://github.com/diegosouzapw/OmniRoute/pull/2364) — thanks @oyi77)
-- `feat(mcp): MCP accessibility-tree smart filter engine` — collapses ≥30 repeated sibling lines, preserves `[ref=eXX]` anchors, 60-80% savings on browser snapshot outputs (Task 1)
-- `docs(skills): publish 10 SKILL.md manifests for external AI agents` — zero-friction onboarding for Claude Desktop, ChatGPT, Cursor, Cline (Task 2)
-- `feat(cli): standalone system tray with PowerShell fallback on Windows` — no Electron required; `omniroute --tray`; autostart via LaunchAgent/.desktop/registry (Task 3)
-- `feat(auth): CLI machine-ID HMAC-SHA256 token` — zero-friction local auth without JWT/password; loopback-only; constant-time compare (Task 4)
-- `feat(security): route protection tiers` — 5 tiers: public/read-only/protected/always/local-only; spawn-capable routes enforce loopback even with valid JWT (Task 5)
-- `feat(compression): Caveman SHARED_BOUNDARIES` — all 6 languages × 3 intensities embed boundary clause; `alreadyApplied` check order fixed (Task 6)
-- `feat(runtime): dynamic SQLite 5-step fallback chain` — bundled → runtime-installed → lazy-install → node:sqlite → sql.js; magic-byte validation (ELF/Mach-O/PE) (Task 7)
-- `docs/ux: tier 1/2/3 marketing, onboarding tour, dashboard widget` — README tier diagram, `docs/marketing/TIERS.md`, TierTour onboarding step, Tier Coverage widget (Task 8)
-- `docs(comparison): OMNIROUTE_VS_ALTERNATIVES.md` — objective comparison vs LiteLLM, OpenRouter, Portkey
-
-### Changed
-
-- `getDbInstance()` requires prior `ensureDbInitialized()` call — server startup awaits it automatically (see release notes for migration)
-- Caveman prompts embed `SHARED_BOUNDARIES` verbatim (LITE/FULL/ULTRA × 6 languages)
-- README "Why OmniRoute?" enhanced with 3-tier ASCII diagram and comparison table
-- Onboarding wizard gains "How It Works" tier tour step (after Welcome, before Security)
-- Home dashboard shows "Tier coverage" widget (configured + active counts per tier)
-
-### Security
-
-- Hard Rule #15: spawn-capable routes must call `assertRouteAllowed(req)` (CLAUDE.md)
-- CLI token rejected on non-loopback hosts even when the HMAC is correct
-- `always`-protected routes (shutdown, db export) reject CLI tokens unconditionally
-
-### Documentation
-
-- `docs/security/CLI_TOKEN.md`
-- `docs/security/ROUTE_GUARD_TIERS.md`
-- `docs/ops/SQLITE_RUNTIME.md`
-- `docs/marketing/TIERS.md`
-- `docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md`
-- `docs/releases/v3.8.0.md`
-
----
-
-### Dependencies
-
-- **chore(deps):** node dependency updates — bump multiple runtime and dev dependencies to latest patch/minor versions. ([#2259](https://github.com/diegosouzapw/OmniRoute/pull/2259) — thanks @backryun)
-
-### Detalhes completos — features e fixes do lançamento (2026-05-06 a 2026-05-14)
-
-#### ✨ New Features
-
-- **feat(providers):** add Command Code provider (#2199 — thanks @ddarkr)
-- **feat(providers):** add ModelScope provider-specific 429 handling and retry logic (#2202 — thanks @InkshadeWoods)
-- **feat(providers):** update Gemini CLI provider models catalog (#2196 — thanks @nickwizard)
-- **feat(antigravity):** integrate Antigravity provider with dynamic `maxOutputTokens` calculation, identity fingerprinting overhaul, and Cloud Code envelope payload sanitization (#2055, #2063)
-- **feat(gemini-cli):** add custom projectId support for Gemini CLI transport (UI, DB, executor) (#1991)
-- **feat(providers):** add KIE media provider support with dynamic polling, text models, and expanded video models catalog (#2009 — thanks @wauputr4)
-- **feat(providers):** add Z.AI provider support with GLM quota handling and new quota labels — thanks @JxnLexn
-- **feat(providers):** add 9 new free AI providers — LLM7, Lepton, Kluster, UncloseAI, BazaarLink, Completions, Enally, FreeTheAi (#2096 — thanks @oyi77)
-- **feat(providers):** batch delete provider connections via checkbox multi-select (#2094 — thanks @oyi77)
-- **feat(cursor):** full OpenAI parity — tool calls, streaming, and session management (#2082 — thanks @payne0420)
-- **feat(cursor):** surface Cursor Pro plan usage on provider-limits dashboard (#2128 — thanks @payne0420)
-- **feat(cli):** comprehensive CLI enhancement suite with 20+ new commands including `omniroute providers`, `omniroute combos`, `omniroute doctor` (#2074 — thanks @oyi77)
-- **feat(cli):** add modular CLI setup and provider management commands (#2046 — thanks @wauputr4)
-- **feat(mcp):** add DeepSeek quota and limit monitoring feature (#2089 — thanks @HoaPham98)
-- **feat(circuit-breaker):** classify 429 errors and apply per-kind cooldowns (#2116 — thanks @eleata)
-- **feat(multi):** manifest-aware tier routing — W1-W4 complete (#2014 — thanks @oyi77)
-- **feat(combos):** add reset-aware routing strategy for quota-based providers — thanks @JxnLexn
-- **feat(combo):** add context_length input field to combo edit form (#2047 — thanks @ddarkr)
-- **feat(combo):** add `fallbackDelayMs` to combo configuration and related settings — thanks @JxnLexn
-- **feat(chat):** dynamic tool limit detection with proactive truncation (#2061 — thanks @oyi77)
-- **feat(chat):** add `STREAM_READINESS_TIMEOUT_MS` and integrate into chat handling — thanks @JxnLexn
-- **feat(chat):** enhance error handling for semaphore capacity with fallback logic — thanks @JxnLexn
-- **feat(sse):** refresh Claude OAuth wire image to claude-cli/2.1.131 (#2011 — thanks @Tentoxa)
-- **feat(github):** add `targetFormat: openai-responses` to all GitHub models (#2122 — thanks @abhinavjnu)
-- **feat(api):** allow configuration via API calls — open management routes to Bearer keys with manage scope (#2103 — thanks @gleber)
-- **feat(api):** update API bridge proxy timeout to 600,000ms (#2019 — thanks @JxnLexn)
-- **feat(api):** aggregate combo model metadata in catalog endpoint — `buildComboCatalogMetadata()` inlines contextLength, strategy, and target count for combo entries (#2166 — thanks @faisalill)
-- **feat(usage):** add service tier breakdown, codex fast service tier analytics, and account for fast tier — thanks @JxnLexn
-- **feat(qdrant):** embedding model discovery (#2086 — thanks @rafacpti23)
-- **feat(auth):** per-session sticky routing for Codex (#1887)
-- **feat(oauth):** complete Windsurf and Devin CLI OAuth + API-token flows — WindsurfExecutor (gRPC-web/protobuf), DevinCliExecutor (ACP JSON-RPC 2.0 over stdio), model alias map, OAuth provider config (#2168 — thanks @Zhaba1337228)
-- **feat(inworld):** enhance Inworld TTS support (#2123 — thanks @backryun)
-- **feat(kiro):** headless auth via kiro-cli SQLite, image support, tool overflow handling, and model list sync (#2129 — thanks @christlau)
-- **feat(auto):** zero-config auto-routing with `auto/` prefix — dynamic virtual combo from connected providers with 6 variant profiles (coding, fast, cheap, offline, smart, lkgp), analytics tab, and settings UI (#2131 — thanks @oyi77)
-- **feat(resilience):** add model cooldowns dashboard card with real-time list, individual/bulk re-enable, and auto-refresh (#2146 — thanks @rafacpti23)
-- **feat(resilience):** `useUpstream429BreakerHints` toggle — per-provider default policy for upstream 429 hint trust at the circuit-breaker cooldown layer with tri-state PATCH semantics (#2133 — thanks @eleata)
-- **feat(search):** add Ollama Search as a web search provider with registry integration and validation (#2176 — thanks @andrewmunsell)
-- **feat(search):** add Z.AI Coding Plan Search via MCP protocol integration (#2238 — thanks @andrewmunsell)
-- **feat(debug):** configurable chat log truncation limits via environment variables (`CHAT_LOG_TEXT_LIMIT`, `CHAT_LOG_ARRAY_TAIL_ITEMS`, `CHAT_LOG_MAX_DEPTH`, `CHAT_LOG_MAX_OBJECT_KEYS`) and `CHAT_DEBUG_FILE` mode for untruncated JSON payloads (#2156 — thanks @bypanghu)
-- **feat(responses):** degrade `background: true` to synchronous execution with a warning instead of throwing `unsupportedFeature` (#2164 — thanks @Yosee11)
-- **feat(mitm):** dynamic Linux certificate path detection for multi-distro MITM cert trust (Debian, Arch/CachyOS, Fedora/RHEL, openSUSE) with NSS browser database injection (#2134 — thanks @flyingmongoose)
-- **feat(1proxy):** add dedicated settings tab with proxy rotation support (#2135 — thanks @oyi77)
-- **feat(antigravity):** support custom Google Cloud project ID for Antigravity provider (#2227 — thanks @nickwizard)
-- **feat(cli):** CLI Integration Suite — 5 new management commands (`config`, `status`, `logs`, `update`, `provider`), 3 API endpoints, config generators for 6 tools (Claude, Cline, Codex, Continue, KiloCode, OpenCode), zero-config `auto/` routing, and `@omniroute/opencode-provider` npm package (#2240 — thanks @oyi77)
-
-### 🐛 Bug Fixes
-
-- **fix(pricing):** make `getPricingForModel` fully case-insensitive to ensure custom prices correctly reflect in new incoming requests cost calculations
-- **fix(gemini):** prevent `functionDeclarations` from being dropped by the sanitizer when `googleSearch` tool is present (#2077)
-- **fix(pollinations):** add `jsonMode: true` flag in the request transformation to enforce correct JSON structure from Pollinations API (#2109)
-- **fix(docker):** update Dockerfile to copy `/docs` directory during build ensuring API catalog availability at runtime (#2083)
-- **fix(docker):** include OpenAPI spec in runtime image (#2007 — thanks @tatsster)
-- **fix(providers):** strip OpenAI-specific fields in Kiro translator to prevent 400 errors (#2037)
-- **fix(kiro):** normalize tool-use payloads to prevent 400 errors from agents (#2104 — thanks @rilham97)
-- **fix(kiro):** merge adjacent user history turns after role normalization (#2105 — thanks @Gioxaa)
-- **fix(ui):** resolve text contrast issues for zero-config warning banner in light mode (#2050)
-- **fix(core):** inject global system prompt correctly into downstream chat completions pipeline (#2080)
-- **fix(core):** restore Claude Code adaptive thinking defaults and resolve audio transcription CORS regression
-- **fix(routing):** add missing v1beta rewrites to next.config to resolve 404 on Gemini models endpoint (#2102)
-- **fix(routing):** fix bare GPT-5.5 routing for Codex-only installations (#2054 — thanks @guanbear)
-- **fix(routing):** add fuzzy auto-combo routing for `auto/*` model prefix (#2010 — thanks @oyi77)
-- **fix(cache):** optimize cache_control preservation logic and explicitly align tool schema with upstream Claude Code expectations
-- **fix(db):** preserve legacy SQLite database path on Windows to prevent data loss (#1973)
-- **fix(db):** reduce hot-path persistence overhead (#2039 — thanks @dhaern)
-- **fix(db):** resolve migration conflict by renumbering overlapping migration entries (#2041 — thanks @oyi77)
-- **fix(settings):** resolve model alias persistence double stringification preventing UI updates (#2018)
-- **fix(routing):** dynamically filter bare model auto-resolution by active provider connections to prevent dead-routing (#2029)
-- **fix(embeddings):** add Google Gemini embeddings compatibility via OpenAI-compatible endpoint mapping (#2006)
-- **fix(sse):** prevent Claude OAuth multi-account correlation via metadata.user_id (#2053 — thanks @Tentoxa)
-- **fix(sse):** prevent Claude Code identity cloak overrides and fix fallback resilience (#2053 — thanks @Tentoxa)
-- **fix(sse):** classify hour quota errors as QUOTA_EXHAUSTED (#2119 — thanks @clousky2020)
-- **fix(sse):** fix CC-compatible streaming bridge (#2118 — thanks @rdself)
-- **fix(antigravity):** sanitize Claude Cloud Code payloads (#2090 — thanks @dhaern)
-- **fix(antigravity):** add duplex half for streaming bodies — thanks @Gi99lin
-- **fix(antigravity):** align identity protocol and behavior with official AM — thanks @Gi99lin
-- **fix(chatgpt-web):** plumb proxy through to native tls-client (#2022, #2023 — thanks @xssdem)
-- **fix(codex):** expose native model IDs in catalog (#2012 — thanks @Tr0sT)
-- **fix(glm):** add dedicated coding transport (#2087 — thanks @dhaern)
-- **fix(compression):** support Responses input and expand Spanish compression rules (#2028 — thanks @dhaern)
-- **fix(catalog):** auto-calculate combo context_length from target model limits (#2030 — thanks @herjarsa)
-- **fix(api):** fix usage analytics and API key identity (#2008, #2092 — thanks @AveryanAlex, @yoviarpauzi)
-- **fix(api-key):** allow Unicode letters in API key name validation (#1996 — thanks @rodrigogbbr-stack)
-- **fix(auth):** allow bootstrap without password (#2048 — thanks @tces1)
-- **fix(proxy):** clean up proxy page redundancy and fix 1proxy sync empty body error (#2052 — thanks @oyi77)
-- **fix(dashboard):** resolve Unknown plan display in Provider Limits — thanks @congvc-dev
-- **fix(usage):** add extensible CURRENCY_SYMBOLS mapping for deepseek currencies
-- **fix(runtime):** harden timer handling and model pricing fallback
-- **fix(i18n):** complete Simplified Chinese translations (#2115 — thanks @boa-z)
-- **fix(mitm):** add Linux cert install and skip sudo password when root (#1999 — thanks @NekoMonci12)
-- **fix(mitm):** prevent stub from loading at runtime via bypass module — thanks @NekoMonci12
-- **fix:** remove Anthropic-Beta header from non-Anthropic providers to fix identity contamination (#1989)
-- **fix(cli):** resolve .env loading failure for global npm installations
-- **fix(authz):** classify `/dashboard/onboarding` as PUBLIC to unblock setup wizard (#2127)
-- **fix(chatcore):** stop leaking provider credentials in response headers
-- **fix(analytics):** precise SQL matching for `auto/` prefix models
-- **fix(export):** exclude telemetry/usage-history tables from JSON config backups by default to prevent unbounded file growth (#2125)
-- **fix(translator):** preserve `body.system` in openai→claude translator when Claude Code sends native Anthropic system array through /chat/completions — fixes v3.7.9 regression where system prompt was silently dropped, triggering Anthropic 429 (#2130)
-- **fix(sanitizer):** preserve `reasoning_content` on assistant messages with `tool_calls` or `function_call` — fixes Kimi and other thinking-enabled providers returning 400 errors when reasoning_content was incorrectly stripped (#2140 — thanks @DavyMassoneto)
-- **fix(catalog):** ensure individual (non-combo) models expose `context_length` via `getTokenLimit()` fallback chain — prevents OpenCode and other clients from falling back to conservative ~4000 token limit (#2136 — thanks @herjarsa)
-- **fix(docker):** remove docs directory from `.dockerignore` so API catalog documentation is available at runtime inside containers (#2137, #2120 — thanks @hartmark)
-- **fix(types):** systematic `any` type elimination across 8 core files — `antigravity.ts`, `accountFallback.ts`, `usage.ts`, `geminiHelper.ts`, `error.ts`, `apiKeys.ts`, `settings.ts`, `logger.ts` (#2137 — thanks @hartmark)
-- **fix(providers):** restore cloud agent provider exports and logger import (#2138 — thanks @backryun)
-- **fix(providers):** remove duplicate `CLOUD_AGENT_PROVIDERS` declaration, move Kiro dash→dot Claude model aliases to `PROVIDER_MODEL_ALIASES`, and trim deprecated Kiro registry entries (#2141 — thanks @backryun)
-- **fix:** Follow OpenAI specification, handle throttling in batch and fix UI (#2045)
-- **fix(cliproxyapi):** probe `/v1/models` for health when CPA 6.x has no `/health` endpoint (#2189 — thanks @Brkic-Nikola)
-- **fix(cliproxyapi):** detect Anthropic-shaped request bodies and route to `/v1/messages`, strip Capy extras, and round-trip `mcp_*` tool name rewrites to `Mcp_*` (#2165 — thanks @Brkic-Nikola)
-- **fix(cliproxyapi):** detect Anthropic shape on minimal Capy bodies (#2192 — thanks @Brkic-Nikola)
-- **fix(stream):** skip `[DONE]` terminator for Claude SSE clients (#2190 — thanks @Brkic-Nikola)
-- **fix(claudeHelper):** emit `data` field on `redacted_thinking`, drop bogus signature (#2191 — thanks @Brkic-Nikola)
-- **fix(modelSpecs):** cap thinking budget for Claude Opus 4.6 / 4.7 / Sonnet 4.6 (#2197 — thanks @Brkic-Nikola)
-- **fix(reasoning-cache):** include xiaomi-mimo in replay provider/model detection (#2198 — thanks @Brkic-Nikola)
-- **fix(kiro):** synthesize minimal tools schema when `body.tools` is omitted but message history contains `tool_calls`, preventing 400 errors from Claude Code and OpenCode (#2149 — thanks @Gioxaa)
-- **fix(kiro):** avoid treating high-traffic 429s as quota exhaustion — use `classify429FromError` to prevent premature account deactivation (#2153 — thanks @Gioxaa)
-- **fix(responses):** propagate `include` array (e.g. `reasoning.encrypted_content`) during Chat→Responses API translation, fixing broken thinking panel in Codex/OpenCode (#2154 — thanks @Gioxaa)
-- **fix(responses):** emit reasoning summary as `delta.reasoning_content` (flat) instead of `delta.reasoning.summary` (nested) for Chat Completions client compatibility (#2159 — thanks @Gioxaa)
-- **fix(cloudflare):** add state file write serialization lock to prevent race conditions in `cloudflaredTunnel.ts` (#2156 — thanks @bypanghu)
-- **fix(providers):** allow optional-key providers to pass connection test (#2169 — thanks @andrewmunsell)
-- **fix(providers):** correct pollinations requests and provider dashboard state
-- **fix(providers):** fix Azure AI Foundry provider connection handling (#2236 — thanks @one-vs)
-- **fix(providers/command-code):** fix validation request format for Command Code API (#2243 — thanks @ddarkr)
-- **fix(antigravity):** strip `generationConfig.thinkingConfig` for Claude models routed through Antigravity to prevent upstream errors (#2217 — thanks @NomenAK)
-- **fix(antigravity):** bootstrap project via `loadCodeAssist` + `fetchAvailableModels` fallback for robust startup (#2219 — thanks @NomenAK)
-- **fix(rateLimit):** never `.stop()` during runtime reset, evict cache instead to prevent stale rate-limit state (#2218 — thanks @NomenAK)
-- **fix(ModelSync):** shared loopback readiness gate + IPv4 force to prevent model sync failures on dual-stack hosts (#2221 — thanks @NomenAK)
-- **fix(proxyFetch):** retry once on undici dispatcher failure before native fallback (#2222 — thanks @NomenAK)
-- **fix(model):** local aliases override cross-proxy provider inference to prevent incorrect model resolution (#2223 — thanks @NomenAK)
-- **fix(claudeHelper):** preserve latest assistant thinking blocks verbatim to prevent Anthropic HTTP 400 errors (#2224 — thanks @NomenAK)
-- **fix(deepseek):** preserve `reasoning_content` through full pipeline for DeepSeek V4 models — prevents reasoning context loss on multi-turn conversations (#2231 — thanks @kang-heewon)
-- **fix(sse-heartbeat):** shape-aware keepalives keep streams alive through stricter proxies (#2233 — thanks @NomenAK)
-- **fix(translator):** coerce `submit_pr_review` `functionalChanges`/`findings` to arrays to prevent upstream schema errors (#2242 — thanks @NomenAK)
-- **fix(api):** validate model cooldown delete payload
-- **fix(ci):** run coverage gate serially, align resilience and thinking checks, align cloud code thinking and model catalog tests
-
-### 🔒 Security
-
-- **fix(security):** remediate CodeQL vulnerabilities (ReDoS, cryptographic bias, stack trace exposure, and weak password hashing) (#216, #215, #211, #208, #206, #210)
-- **fix(security):** sanitize error messages in API routes to prevent stack trace exposure (CodeQL js/stack-trace-exposure) (#2209)
-- **fix(security):** remediate regex validation backtracking path in core compression cleanup (#1990)
-- **fix(core):** harden input handling and stabilization for prompt compression edge cases
-
-### 📝 Documentation
-
-- **docs:** add competitive marketing tables and SEO/AEO optimizations to README (#2091)
-- **docs:** refresh providers, model catalogs, and docs for v3.8.0 (#2088)
-- **docs:** update Claude MD and update GLM-CN max context to 200k (#2027)
-- **docs(env):** add `GITLAB_DUO_OAUTH_CLIENT_ID` to `.env.example` (#2031)
-- **docs:** add Brazilian WhatsApp group link to README (#2201 — thanks @rafacpti23)
-
-### 🔧 Improvements
-
-- **refactor(executor):** `sanitizeReasoningEffortForProvider()` hook in `BaseExecutor.execute()` — downgrades `xhigh`→`high` for unsupporting providers, strips effort for mistral/devstral and github claude models (#2162 — thanks @hachimed)
-- **refactor(translator):** remove redundant provider guard from Claude thinking placeholder injection — applies to all `targetFormat === FORMATS.CLAUDE` bodies (#2161 — thanks @JohnDoe-oss)
-- **refactor(catalog):** remove 11 `.ts` extension imports, eliminate all `as any` casts, add `CustomModelEntry` interface and `ComboModelStep` type predicate, normalize alias resolution with `resolveCanonicalProviderId()` (#2152 — thanks @herjarsa)
-- **feat(resilience):** `useUpstream429BreakerHints` tri-state PATCH field — `true`/`false` persists, `null` resets to undefined (omitted from JSON) (#2146 tests — thanks @rafacpti23)
-
-### 🧹 Chores & Maintenance
-
-- **chore(providers):** prune redundant local provider icon assets in favor of `@lobehub/icons` web fonts (#1992)
-- **chore(providers):** remove deprecated models (#2033)
-- **chore(providers):** improve BazaarLink and Completions.me support (#2177 — thanks @backryun)
-- **chore(registry):** refresh `contextLength` and `maxOutputTokens` for claude, kiro, github, kimi-coding, xiaomi-mimo, codex/gpt-5.5 models (#2163 — thanks @brucevoin)
-- **chore(models):** tidy up Alibaba Coding Plan base URL, reorganize Cursor model list by family, fix `gpt-4o` model ID, update OpenCode Zen model (#2150 — thanks @backryun)
-- **chore(deps):** resolve npm audit moderate vulnerability (hono)
-- **chore(deps):** move `gray-matter` from devDependencies to dependencies (runtime requirement) (#2156 — thanks @bypanghu)
-- **deps:** bump `fast-uri` from 3.1.0 to 3.1.2 (#2078)
-- **deps:** bump `hono` from 4.12.14 to 4.12.18 (#2065, #2079)
-- **deps:** bump the development group with 6 updates (#2184)
-- **deps:** bump `electron-builder` from 26.9.1 to 26.10.0 (#2183)
-- **ci:** update build-fork workflow to build from main branch (#2055)
-- **ci:** skip SonarCloud scan on main pushes to optimize CI time
-- **test:** stabilize cooldown abort coverage case in integration testing
-- **build(deps):** regenerate `package-lock.json` to match `http-proxy-middleware` 4.x bump (#2228 — thanks @NomenAK)
-- **fix(requestLogger):** exempt tools field from array truncation for full debug visibility (#2234 — thanks @NomenAK)
-
-### 🏆 v3.8.0 Community Contributors
-
-Thank you to all **55+ community contributors** who made v3.8.0 possible! 🎉
-
-| Contributor                                                | PRs | Contributions                                                                                    |
-| :--------------------------------------------------------- | :-: | :----------------------------------------------------------------------------------------------- |
-| [@NomenAK](https://github.com/NomenAK)                     | 12  | #2217, #2218, #2219, #2221, #2222, #2223, #2224, #2228, #2233, #2234, #2242, #2192               |
-| [@oyi77](https://github.com/oyi77)                         | 14  | #2010, #2014, #2041, #2052, #2061, #2074, #2091, #2094, #2096, #2131, #2135, #2240, #2283, #2295 |
-| [@backryun](https://github.com/backryun)                   |  9  | #1992, #2033, #2088, #2123, #2138, #2141, #2150, #2177, #2279                                    |
-| [@Brkic-Nikola](https://github.com/Brkic-Nikola)           |  6  | #2165, #2189, #2190, #2191, #2192, #2197                                                         |
-| [@Gioxaa](https://github.com/Gioxaa)                       |  5  | #2105, #2149, #2153, #2154, #2159                                                                |
-| [@dhaern](https://github.com/dhaern)                       |  4  | #2028, #2039, #2087, #2090                                                                       |
-| [@andrewmunsell](https://github.com/andrewmunsell)         |  3  | #2169, #2176, #2238                                                                              |
-| [@ddarkr](https://github.com/ddarkr)                       |  4  | #2047, #2199, #2243, #2271                                                                       |
-| [@nickwizard](https://github.com/nickwizard)               |  3  | #1991, #2196, #2227                                                                              |
-| [@herjarsa](https://github.com/herjarsa)                   |  3  | #2030, #2136, #2152                                                                              |
-| [@rafacpti23](https://github.com/rafacpti23)               |  3  | #2086, #2146, #2201                                                                              |
-| [@Tentoxa](https://github.com/Tentoxa)                     |  2  | #2011, #2053                                                                                     |
-| [@wauputr4](https://github.com/wauputr4)                   |  2  | #2009, #2046                                                                                     |
-| [@hartmark](https://github.com/hartmark)                   |  4  | #2045, #2137, #2294, #2299                                                                       |
-| [@payne0420](https://github.com/payne0420)                 |  2  | #2082, #2128                                                                                     |
-| [@bypanghu](https://github.com/bypanghu)                   |  2  | #2027, #2156                                                                                     |
-| [@eleata](https://github.com/eleata)                       |  2  | #2116, #2133                                                                                     |
-| [@Tr0sT](https://github.com/Tr0sT)                         |  1  | #2012                                                                                            |
-| [@AveryanAlex](https://github.com/AveryanAlex)             |  1  | #2008                                                                                            |
-| [@rodrigogbbr-stack](https://github.com/rodrigogbbr-stack) |  1  | #1996                                                                                            |
-| [@NekoMonci12](https://github.com/NekoMonci12)             |  1  | #1999                                                                                            |
-| [@congvc-dev](https://github.com/congvc-dev)               |  1  | #2004                                                                                            |
-| [@tatsster](https://github.com/tatsster)                   |  1  | #2007                                                                                            |
-| [@xssdem](https://github.com/xssdem)                       |  1  | #2023                                                                                            |
-| [@wucm667](https://github.com/wucm667)                     |  1  | #2031                                                                                            |
-| [@tces1](https://github.com/tces1)                         |  1  | #2048                                                                                            |
-| [@guanbear](https://github.com/guanbear)                   |  1  | #2054                                                                                            |
-| [@Gi99lin](https://github.com/Gi99lin)                     |  1  | #2055                                                                                            |
-| [@ivan-mezentsev](https://github.com/ivan-mezentsev)       |  1  | #2063                                                                                            |
-| [@JxnLexn](https://github.com/JxnLexn)                     |  1  | #2019                                                                                            |
-| [@yoviarpauzi](https://github.com/yoviarpauzi)             |  1  | #2092                                                                                            |
-| [@gleber](https://github.com/gleber)                       |  1  | #2103                                                                                            |
-| [@rilham97](https://github.com/rilham97)                   |  1  | #2104                                                                                            |
-| [@boa-z](https://github.com/boa-z)                         |  1  | #2115                                                                                            |
-| [@rdself](https://github.com/rdself)                       |  1  | #2118                                                                                            |
-| [@clousky2020](https://github.com/clousky2020)             |  1  | #2119                                                                                            |
-| [@abhinavjnu](https://github.com/abhinavjnu)               |  1  | #2122                                                                                            |
-| [@HoaPham98](https://github.com/HoaPham98)                 |  1  | #2089                                                                                            |
-| [@christlau](https://github.com/christlau)                 |  1  | #2129                                                                                            |
-| [@flyingmongoose](https://github.com/flyingmongoose)       |  1  | #2134                                                                                            |
-| [@05dunski](https://github.com/05dunski)                   |  1  | #1978 (cherry-picked)                                                                            |
-| [@DavyMassoneto](https://github.com/DavyMassoneto)         |  1  | #2140                                                                                            |
-| [@Zhaba1337228](https://github.com/Zhaba1337228)           |  1  | #2168                                                                                            |
-| [@faisalill](https://github.com/faisalill)                 |  1  | #2166                                                                                            |
-| [@Yosee11](https://github.com/Yosee11)                     |  1  | #2164                                                                                            |
-| [@hachimed](https://github.com/hachimed)                   |  1  | #2162                                                                                            |
-| [@JohnDoe-oss](https://github.com/JohnDoe-oss)             |  1  | #2161                                                                                            |
-| [@brucevoin](https://github.com/brucevoin)                 |  1  | #2163                                                                                            |
-| [@InkshadeWoods](https://github.com/InkshadeWoods)         |  1  | #2202                                                                                            |
-| [@kang-heewon](https://github.com/kang-heewon)             |  1  | #2231                                                                                            |
-| [@one-vs](https://github.com/one-vs)                       |  1  | #2236                                                                                            |
-| [@thepigdestroyer](https://github.com/thepigdestroyer)     |  2  | #2290, #2291                                                                                     |
-| [@josephvoxone](https://github.com/josephvoxone)           |  1  | #2289                                                                                            |
-| [@mrmm](https://github.com/mrmm)                           |  3  | #2286, #2305, #2308                                                                              |
-
-## [3.7.9] — 2026-05-03
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-
-- **feat(compression):** major upgrade to Caveman and RTK compression pipelines (#1876, #1889):
-  - Add RTK tool-output compression, stacked Caveman + RTK pipelines, compression combo assignments, dashboard context pages, MCP management tools, and language-aware Caveman rule packs.
-  - Expand RTK parity with a 39-filter catalog, RTK-style JSON DSL stages, inline verify/benchmark coverage, trust-gated custom filters, expanded command detection, and redacted raw-output recovery.
-  - Expose rule intensities, track USD savings, unify config validation, and persist MCP savings.
-  - Expand Caveman parity and MCP metadata compression.
-- **feat(provider):** update Jina AI model catalog to support Embeddings and Rerank natively (#1874 — thanks @backryun)
-- **feat(provider):** add NanoGPT image generation provider (#1899 — thanks @Aculeasis)
-- **feat(ui):** move proxy configuration to dedicated System → Proxy page (#1907 — thanks @oyi77)
-- **feat(ui):** add K/M/B/T cost shortener utility (#1902 — thanks @oyi77)
-- **feat(providers):** implement bulk paste for extra API keys (#1916 — thanks @0xtbug)
-- **feat(analytics):** usage history API key backfill + dark mode pricing (#1896 — thanks @Gi99lin)
-- **feat(logs):** show RTK and Caveman compression token savings accurately in request log UI (#1923 — thanks @emdash)
-- **feat(routing):** auto-skip exhausted quota accounts (Issue #1952)
-- **feat(docs):** docs site overhaul (#1976 — thanks @oyi77)
-- **feat(db):** consolidate all database settings into SystemStorageTab (closes #1935) (#1947 — thanks @oyi77)
-- **feat(sse):** codex 429 mid-task failover with account rotation (#1888 — thanks @smartenok-ops)
-- **feat(auto-assessment):** add auto-assessment engine for combo self-healing (#1918 — thanks @oyi77)
-- **feat(usage):** DeepSeek V4 native cache token extraction (#1930 — thanks @smartenok-ops)
-- **feat(cost):** enhance cost formatting and add Codex GPT-5.5 pricing support (#1944 — thanks @JxnLexn)
-
-### 🐛 Bug Fixes
-
-- **fix(auth):** implement session affinity sticky routing logic
-- **fix(dashboard):** derive display base URL from origin instead of hardcoding localhost (#1960 — thanks @jeanfbrito)
-- **fix(proxy):** use credentials.connectionId instead of non-existent credentials.id for image proxy resolution (#1929 — thanks @Aculeasis)
-- **fix(routing):** codex bare-name disambiguation + family-native fallback (#1933 — thanks @smartenok-ops)
-- **fix(infrastructure):** move wreq-js to optionalDependencies and add Node 25/26 to secure runtime policy (#1924)
-- **fix(providers):** resolve ChatGPT Web authentication failure by aligning TLS fingerprint User-Agent strings (#1925)
-- **fix(mitm):** support root user for MITM sudo handling (#1948 — thanks @NekoMonci12)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941, #1945)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-- **fix(mcp):** reclassify MCP endpoints to ensure API key authentication works even when dashboard auth is enabled (#1970)
-- **fix(providers):** allow local OpenAI-compatible endpoints (like Ollama) to be added without an API key (fixes #1893)
-- **fix(providers):** bypass AgentRouter unauthorized_client_error by spoofing Claude CLI headers via Anthropic endpoints (fixes #1921)
-- **fix(copilot):** emit compatible reasoning text deltas (#1919 — thanks @ivan-mezentsev)
-- **fix(api-manager):** show validation errors inline in modals, not behind (#1920 — thanks @andrewmunsell)
-- **fix(compression):** align seeded standard savings combo with stacked default, preserve stacked defaults, and secure metadata routes.
-- **fix(gemini-cli):** separate Cloud Code transport from Antigravity (#1869 — thanks @dhaern)
-- **fix(codex):** map prompt field to input array for Cursor compatibility (fixes #1872)
-- **fix(core):** align stream parameter default to false per strict OpenAI spec (fixes #1873)
-- **fix(ui):** restore Next.js CSP `unsafe-eval` in production `script-src` to fix unresponsive Onboarding button (fixes #1883)
-- **fix(proxy):** globally strip `prompt_cache_retention` in `BaseExecutor` to prevent upstream 400 errors from strict endpoints like droid/gemini-2-pro (fixes #1884)
-- **fix(ui):** include `isOpen` dependency in `EditConnectionModal` state sync to ensure `maxConcurrent` is properly hydrated when reopening the modal (fixes #1859)
-- **fix(security):** remediate 4 polynomial-redos CodeQL alerts in compression regexes by bounding repetitions and removing overlapping quantifiers
-- **fix(codex):** flatten Chat Completions tool format to Codex Responses format in `normalizeCodexTools` — prevents `Missing required parameter: tools[0].name` upstream errors (#1914 — thanks @tranduykhanh030)
-- **fix(proxy):** add proxy-aware execution context to image generation route — proxy settings are now correctly applied for image providers behind restricted networks (#1904 — thanks @Aculeasis)
-- **fix(translator):** inject `properties: {}` into zero-argument MCP tool schemas during Anthropic→OpenAI translation — prevents 400 errors from OpenAI strict schema validation (#1898 — thanks @bryceIT)
-- **fix(codex):** sanitize raw responses input (#1895 — thanks @dhaern)
-- **fix(combos):** align strategy contracts (#1892 — thanks @dhaern)
-- **fix(combos):** fix combo provider breaker profile handling (#1891 — thanks @rdself)
-- **fix(migrations):** duplicate-column no-op fix (#1886 — thanks @smartenok-ops)
-- **fix(auth):** per-connection OAuth refresh mutex (#1885 — thanks @smartenok-ops)
-- **fix(auth):** require dashboard management auth for compression preview
-
-### 🔄 Updates
-
-- **chore(provider):** Add reka models list (#1956 — thanks @backryun)
-- **chore(model):** Update new models, Delete Deprecated models (#1949 — thanks @backryun)
-
-### 📝 Documentation
-
-- **docs(compression):** document RTK+Caveman stacked savings ranges
-
-### 🏆 Release Attribution & Retroactive Credits
-
-- **@payne0420** (PR #1828 / #1839) — Implementation of the **Rate Limit Watchdog** and environment overrides. (This feature was manually backported to v3.7.8, causing the automatic GitHub Release notes to omit the author's credit).
-
----
-
-## [3.7.8] — 2026-05-01
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** add Grok 4.3 and Xiaomi Mimo TTS provider (#1837)
-- **feat(core):** implement Rate Limit Watchdog with environment override capability to detect and reset stalled queues (#1839)
-- **feat(providers):** add muse-spark-web provider with multiple models and reasoning support (#1843)
-- **feat(1proxy):** integrate 1proxy free proxy marketplace with dashboard management and new MCP tools (closes #1788) (#1847)
-
-### 🐛 Bug Fixes
-
-- **fix(codex):** sanitize Responses replay state to prevent internal assistant commentary from leaking (#1868 — thanks @dhaern)
-- **fix(cli):** add capture-backed Gemini CLI fingerprint (#1866)
-- **fix(ui):** hide combo compression controls when the global setting is disabled (#1840)
-- **fix(db):** tolerate missing request_detail_logs table for legacy deployments (#1848)
-- **fix(core):** remove unneeded \`store\` payload parameter for providers lacking support (closes #1841)
-- **fix(core):** ensure safeOutboundFetch and A2A routers return 503 Service Unavailable when security guardrails are triggered
-- **fix(usage):** correct Unix seconds vs milliseconds parsing logic for Kiro AI quota reset (closes #1849)
-- **fix(ui):** apply robust NaN handling, ensure 24h consistency, and fix missing hour slots in Compression Analytics (closes #1844)
-- **fix(ui):** implement short number formatting for token consumption metrics on cache pages to prevent overflow (closes #1842)
-- **fix(combo):** stabilize provider routing at 500+ connections by bounding semaphore queues and adjusting circuit breaker tracking (closes #1846) (#1854)
-- **fix(maritalk):** update Maritalk model list, use Authorization Key header, and align with latest API endpoints (#1856)
-- **fix(grok-web):** stabilize tool calling (bash, readFile, webSearch) and response parsing by mapping native Grok intents to standard OpenAI payloads (#1857)
-- **fix(providers):** correctly map and expose the Upstage embedding and chat model catalogs (#1855)
-- **fix(executor):** apply proper urlSuffix and custom authHeaders for unknown registry-based providers in DefaultExecutor (closes #1846) (#1861)
-
-### 🛠️ Maintenance
-
-- **fix(workflow):** build docker images on version tags (#1838)
-
----
-
-## [3.7.7] — 2026-04-30
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **Prompt Compression Pipeline:** Implemented a multi-phase prompt compression engine including `lite` (whitespace/duplication collapse), `aggressive` (summarization, tool compression), and `ultra` modes (heuristic pruning and SLM stub) (#1633, #1738, #1739, #1741)
-- **Compression Dashboard & Analytics:** Added a compression settings UI, real-time log viewer, pipeline statistics tracking, and interactive playground preview (#1756)
-- **Compression Caching & MCP:** Added caching-aware strategy adjustments to the compression pipeline, alongside new MCP tools for status and configuration (#1758)
-- **Analytics Custom Filters:** Added custom date range selection, API key filtering, and NULL key analytics backfilling to the Costs Dashboard (#1830)
-
-### 🐛 Bug Fixes
-
-- **Combo Routing:** Fixed an issue where Gemini `-preview` models were incorrectly normalized to their canonical names, causing 404 errors during combo routing (#1834)
-- **Codex Native Passthrough:** Added support for Cursor 5.5 sending `messages` arrays to the `responses/compact` endpoint, preventing upstream rejections with empty requests (#1832)
-- **Rate-limit Watchdog:** Implemented a new rate-limit watchdog with environment override capabilities and Stage Tracing to prevent and diagnose silent wedges (#1828)
-- **Encryption Resiliency:** Prevent sending encrypted tokens to providers by returning null on decryption failure (#763d353)
-- **i18n & Locales:** Fixed OpenCode baseUrl locale placeholders and added compression keys across 32 languages
-- **Startup Stability:** Hardened resilience integration server startup logic (#9aa89b17)
-
-### 🛠️ Maintenance
-
-- **Tests & Docs:** Expanded the test suite with 61 unit/integration tests for the compression pipeline and updated `AGENTS.md`
-- **Workflow:** Fixed the changelog extraction logic to accurately capture GitHub release descriptions
-
----
-
-## [3.7.6] — 2026-04-30
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(api-keys):** add rename support in the permissions modal — editable key name field with validation (#1796)
-- **feat(chatgpt-web):** support `thinking_effort` parameter (Standard/Extended) for thinking-capable models (#1821)
-- **feat(dashboard):** implement remaining v3.7.6 dashboard features — Costs overview, Translator pipeline, and Endpoint tabs improvements
-- **feat(tools):** inject fallback tool names to prevent upstream 400 errors on providers that require tool names (#1775)
-- **feat(db):** auto-restore probe-failed database on startup to prevent data loss after failed upgrades (#1810)
-- **feat(analytics):** add cost-based usage insights and activity streaks in the analytics dashboard
-
-### 🔒 Security
-
-- **fix(security):** resolve ReDoS vulnerability in Codex executor regex patterns (#1797, #1789)
-
-### 🐛 Bug Fixes
-
-- **fix(stability):** resolve codex input validation, enable combo circuit breaker, and fix broken unit tests (#1804, #1805)
-- **fix(stability):** safely cast inputs to strings before calling `.trim()` to avoid crashes on numeric fields in proxy modal (#1825)
-- **fix(stability):** clear active requests and recover providers after connection failures (#1824)
-- **fix(xiaomi-mimo):** update models to V2.5, fix Token Plan validation and default region (#1823)
-- **fix(codex):** omit compact client metadata to prevent upstream rejections (#1822)
-- **fix(dashboard):** fix endpoint visibility, A2A status display, and API catalog consistency (#1806)
-- **fix(analytics):** use pure SQL aggregations — no history rows loaded into memory (#1802)
-- **fix(dashboard):** correct `loadPresets` ReferenceError in CostOverviewTab
-- **fix(mitm):** enforce transparent interception on port 443 only
-
-### 🧹 Chores
-
-- **chore(workflow):** mandate implementation plan generation in `/resolve-issues` workflow before coding
-- **chore(release):** expand contributor credits to 155 PRs across full project history
-
-### 🏆 Community Contributors Acknowledgment
-
-We identified that **155 community PRs** across the entire project history (from inception through v3.7.5) were manually integrated into release branches but closed instead of properly merged through GitHub, preventing contributors from receiving merge credit on their profiles. We sincerely apologize for this oversight and have since updated our workflows to ensure this never happens again.
-
-**The following contributors had their code and ideas integrated across multiple releases without proper merge credit. Thank you for your invaluable contributions to OmniRoute:**
-
-| Contributor                                                  | PRs (Total) | All Contributions                                                                                                                                                                   |
-| :----------------------------------------------------------- | :---------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| [@rdself](https://github.com/rdself)                         |     28      | #542, #705, #717, #737, #738, #841, #851, #853, #875, #880, #888, #891, #903, #904, #974, #1069, #1089, #1196, #1267, #1272, #1299, #1300, #1356, #1357, #1441, #1443, #1549, #1742 |
-| [@oyi77](https://github.com/oyi77)                           |     27      | #644, #672, #700, #850, #859, #862, #868, #874, #881, #883, #908, #926, #931, #983, #990, #1019, #1020, #1021, #1103, #1281, #1286, #1363, #1368, #1377, #1411, #1689, #1717        |
-| [@clousky2020](https://github.com/clousky2020)               |     15      | #1244, #1323, #1365, #1366, #1408, #1442, #1484, #1595, #1598, #1599, #1611, #1618, #1620, #1621, #1644                                                                             |
-| [@benzntech](https://github.com/benzntech)                   |      8      | #158, #1264, #1435, #1436, #1437, #1440, #1444, #1677                                                                                                                               |
-| [@kang-heewon](https://github.com/kang-heewon)               |      5      | #530, #854, #884, #1235, #1574                                                                                                                                                      |
-| [@herjarsa](https://github.com/herjarsa)                     |      4      | #1472, #1474, #1477, #1480                                                                                                                                                          |
-| [@backryun](https://github.com/backryun)                     |      4      | #1358, #1609, #1627, #1722                                                                                                                                                          |
-| [@tombii](https://github.com/tombii)                         |      4      | #708, #856, #900, #1013                                                                                                                                                             |
-| [@christopher-s](https://github.com/christopher-s)           |      3      | #868, #885, #992                                                                                                                                                                    |
-| [@zen0bit](https://github.com/zen0bit)                       |      3      | #561, #650, #912                                                                                                                                                                    |
-| [@k0valik](https://github.com/k0valik)                       |      3      | #554, #587, #596                                                                                                                                                                    |
-| [@zhangqiang8vip](https://github.com/zhangqiang8vip)         |      2      | #470, #575                                                                                                                                                                          |
-| [@wlfonseca](https://github.com/wlfonseca)                   |      2      | #997, #1016                                                                                                                                                                         |
-| [@RaviTharuma](https://github.com/RaviTharuma)               |      2      | #1188, #1277                                                                                                                                                                        |
-| [@prakersh](https://github.com/prakersh)                     |      2      | #419, #480                                                                                                                                                                          |
-| [@payne0420](https://github.com/payne0420)                   |      2      | #1593, #1670                                                                                                                                                                        |
-| [@only4copilot](https://github.com/only4copilot)             |      2      | #855, #1039                                                                                                                                                                         |
-| [@jay77721](https://github.com/jay77721)                     |      2      | #581, #582                                                                                                                                                                          |
-| [@hijak](https://github.com/hijak)                           |      2      | #295, #578                                                                                                                                                                          |
-| [@hartmark](https://github.com/hartmark)                     |      2      | #1494, #1500                                                                                                                                                                        |
-| [@defhouse](https://github.com/defhouse)                     |      2      | #906, #946                                                                                                                                                                          |
-| [@xiaoge1688](https://github.com/xiaoge1688)                 |      1      | #1304                                                                                                                                                                               |
-| [@xandr0s](https://github.com/xandr0s)                       |      1      | #1376                                                                                                                                                                               |
-| [@willbnu](https://github.com/willbnu)                       |      1      | #882                                                                                                                                                                                |
-| [@slewis3600](https://github.com/slewis3600)                 |      1      | #1624                                                                                                                                                                               |
-| [@sergey-v9](https://github.com/sergey-v9)                   |      1      | #594                                                                                                                                                                                |
-| [@razllivan](https://github.com/razllivan)                   |      1      | #987                                                                                                                                                                                |
-| [@nmime](https://github.com/nmime)                           |      1      | #1271                                                                                                                                                                               |
-| [@Moutia-Ben-Yahia](https://github.com/Moutia-Ben-Yahia)     |      1      | #1663                                                                                                                                                                               |
-| [@Mind-Dragon](https://github.com/Mind-Dragon)               |      1      | #467                                                                                                                                                                                |
-| [@mercs2910](https://github.com/mercs2910)                   |      1      | #1001                                                                                                                                                                               |
-| [@MAINER4IK](https://github.com/MAINER4IK)                   |      1      | #196                                                                                                                                                                                |
-| [@luandiasrj](https://github.com/luandiasrj)                 |      1      | #996                                                                                                                                                                                |
-| [@knopki](https://github.com/knopki)                         |      1      | #1434                                                                                                                                                                               |
-| [@kfiramar](https://github.com/kfiramar)                     |      1      | #389                                                                                                                                                                                |
-| [@ken2190](https://github.com/ken2190)                       |      1      | #166                                                                                                                                                                                |
-| [@keith8496](https://github.com/keith8496)                   |      1      | #569                                                                                                                                                                                |
-| [@jonesfernandess](https://github.com/jonesfernandess)       |      1      | #1118                                                                                                                                                                               |
-| [@JasonLandbridge](https://github.com/JasonLandbridge)       |      1      | #1626                                                                                                                                                                               |
-| [@i1hwan](https://github.com/i1hwan)                         |      1      | #1386                                                                                                                                                                               |
-| [@Gorchakov-Pressure](https://github.com/Gorchakov-Pressure) |      1      | #754                                                                                                                                                                                |
-| [@foxy1402](https://github.com/foxy1402)                     |      1      | #934                                                                                                                                                                                |
-| [@dt418](https://github.com/dt418)                           |      1      | #896                                                                                                                                                                                |
-| [@dhaern](https://github.com/dhaern)                         |      1      | #1647                                                                                                                                                                               |
-| [@DavyMassoneto](https://github.com/DavyMassoneto)           |      1      | #211                                                                                                                                                                                |
-| [@dail45](https://github.com/dail45)                         |      1      | #1413                                                                                                                                                                               |
-| [@congvc-dev](https://github.com/congvc-dev)                 |      1      | #1569                                                                                                                                                                               |
-| [@be0hhh](https://github.com/be0hhh)                         |      1      | #1581                                                                                                                                                                               |
-| [@andruwa13](https://github.com/andruwa13)                   |      1      | #1457                                                                                                                                                                               |
-| [@AndrewDragonIV](https://github.com/AndrewDragonIV)         |      1      | #898                                                                                                                                                                                |
-| [@AndersonFirmino](https://github.com/AndersonFirmino)       |      1      | #362                                                                                                                                                                                |
-| [@alexsvdk](https://github.com/alexsvdk)                     |      1      | #1280                                                                                                                                                                               |
-| [@abhinavjnu](https://github.com/abhinavjnu)                 |      1      | #550                                                                                                                                                                                |
-
----
-
-## [3.7.5] — 2026-04-29
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(tunnels):** integrate native ngrok tunnel support with dashboard UI parity (#1753)
-
-### 🐛 Bug Fixes
-
-- **fix(dashboard):** add manual 'Clear All' button to terminate stalled long-running requests in Active Requests panel (#1799)
-- **fix(schema):** remove empty string values from optional tool parameters to prevent upstream validation errors (#1674)
-- **fix(providers):** ensure proper streaming cleanup and semaphore release to prevent stalls with nanoGPT (#1781)
-- **fix(db):** wrap quota_snapshots access in try/catch to gracefully handle pending database migrations (#1784)
-- **feat(providers):** add support for glm-cn (BigModel) provider (#1770)
-- **fix(grok-web):** fix Grok validator and cookie parsing (#1793)
-- **fix(antigravity):** scrub internal OmniRoute headers (#1794)
-- **fix(chatgpt-web):** restore validator + expand model catalog to ChatGPT Plus tier (#1792)
-- **fix(codex):** stabilize Copilot responses replay state (#1791)
-- **fix(antigravity):** cap Claude bridge output tokens (#1785)
-- **fix(schema):** strip `default` properties from tool-call JSON schemas during egress to prevent injection errors (#1782)
-- **fix(db):** add `quota_snapshots` table to core DB schema initialization to prevent startup failures on fresh installs
-- **fix(models):** apply blocked providers filter to non-chat catalog models (image, embedding, audio, etc.) (#1752)
-- **fix(antigravity):** stabilize streaming payload parsing and deduplicate usage/model metadata refreshes (#1748)
-- **fix(antigravity):** normalize Gemini bridge payloads — sanitize tool names, cap output tokens, and fix thinking budget (#1769)
-- **fix(sse):** propagate AbortSignal to pre-fetch semaphore and rate-limit awaits to prevent memory leaks (#1771)
-- **fix(models):** fix model sync import handling — separate synced models from custom models to prevent data loss (#1755)
-- **fix(codex):** improve VS Code Copilot /responses reasoning and tool follow-ups (#1750)
-- **fix(memory):** resolve build issues and implement memory UPSERT logic to prevent duplicate entries (#1763)
-- **fix(kiro):** support organization IDC OAuth with regional endpoints and refresh (#1754)
-- **fix(combo):** include 429 in provider circuit breaker to stop infinite retry loops on exhausted quotas (#1767)
-- **fix(claude):** respect client-set thinking/effort params — only inject adaptive thinking and high effort when the client hasn't explicitly set them, preventing forced quota drain on Claude Max accounts (#1761)
-- **fix(blackbox-web):** correct cookie name and populate session/subscription fields (#1776)
-- **fix(codex):** align client identity metadata (#1778)
-- **fix(claude):** fix support for claude-cli using Gemini provider (#1779)
-- **test(reasoning-cache):** isolate DB state using mkdtempSync to prevent 401 middleware errors
-
-### 🛠️ Maintenance
-
-- **chore(docs):** add MseeP.ai security assessment badge to README (#1727)
-- **chore(xiaomi):** update Xiaomi provider model list (#1759)
-- **chore(db):** move DB health endpoint to management API (#1757)
-- **chore(ui):** speed up endpoint initial render with background task loading (#1760)
-- **chore(workflows):** add strict PR contributor credit policy to prevent future merge credit loss
-
----
-
-## [3.7.4] — 2026-04-28
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(ui):** add endpoint tunnel visibility settings (#1743)
-- **feat(cli):** refresh CLI fingerprint provider profiles (#1746)
-- **feat(proxy):** implement bulk proxy import via pipe-delimited parser with update-or-create (upsert) logic and real-time preview table
-- **feat(pwa):** add fullscreen installable PWA with manifest, service worker, and cross-platform app icons (#1728)
-
-### 🔒 Security
-
-- **security:** replace insecure `Math.random` with `crypto.getRandomValues` for fallback UUID generation to resolve CodeQL CWE-338 finding (#182)
-
-### 🐛 Bug Fixes
-
-- **fix(cc-compatible):** fix CC-compatible relay format and UI copy (#1742)
-- **fix(codex):** normalize max reasoning effort for Codex routing (#1744)
-- **fix(claude-code):** fix Claude Code gateway config helper (#1745)
-- **fix(db):** reconcile legacy `create_reasoning_cache` migration tracking to prevent version shadowing on `032` and resolve startup warnings (#1734)
-- **fix(db):** intercept `007` migration to use idempotent `IF NOT EXISTS` logic via `PRAGMA table_info`, preventing syntax crashes on fresh installs (#1733)
-- **fix(cc-compatible):** preserve Claude Code system skeleton to prevent request rejection by strict compatible upstream providers (#1740)
-
-- **fix(providers):** add API key validation for image-only providers and fix Stability AI requests to use `multipart/form-data` instead of JSON (#1726)
-- **fix(codex):** preserve `previous_response_id` and `conversation_id` fields when input array is empty to prevent schema validation errors (#1729)
-- **fix(searxng):** bypass UI validation block when `apiKeyOptional` is true and fix typing errors in provider dashboard to allow saving search providers without credentials (#1721)
-- **fix(proxy):** disable HTTP keep-alive and pipelining in Undici proxy dispatcher to prevent "Socket hang up" rotation failures
-- **stream:** correctly identify `thought` and `error` blocks in Antigravity/Gemini SSE streams to prevent premature 502 timeouts (#1725, #1705)
-
-### 🛠️ Maintenance
-
-- **workflow:** add phase 4 release monitoring instructions to `/generate-release` workflow
-- **test:** fix typescript compilation errors in unit tests to keep CI typecheck pipeline fully green
-- **test:** update responses store expectations for empty input arrays
-
----
-
-## [3.7.3] — 2026-04-28
-
-### 🐛 Bug Fixes
-
-- **fix(claude):** strip existing billing headers from system array before injecting to prevent Anthropic prompt cache misses — stacked `x-anthropic-billing-header` blocks invalidated prefix matching, causing ~100% cache_create instead of cache_read (#1712)
-- **fix(claude):** strip `output_config.format` for non-Anthropic Claude-compatible providers during passthrough — third-party Claude endpoints (MiniMax, DeepSeek via aggregators) reject structured output fields with 400 errors (#1719)
-- **fix(combo):** set terminal error state on response quality validation failure — prevents misleading `ALL_ACCOUNTS_INACTIVE` 503 when the real issue is response quality validation (#1707, #1710)
-- **fix(combo):** treat combo fallback as target-level orchestration — all non-ok responses (including generic 400s) now fall through to the next target instead of being terminal; removes complex bad-request allowlist regex (#1713)
-- **fix(codex):** restore namespace MCP tools and hosted-tool whitelist — regression from #1581 that silently dropped all MCP tool groups and Responses-API hosted tools (#1715)
-- **fix(codex):** add neutral instructions for bare chat requests — Codex Responses backend rejects requests without `instructions`, making Codex unusable for normal chat (#1709)
-- **fix(proxy):** wrap proxy assignment queries in try-catch for missing `proxy_assignments` table — Electron installs where migration 004 hasn't run no longer crash with `no such table` error (#1706)
-- **fix(migration):** improve Windows file URL path resolution in migration runner — adds direct URL path extraction and `process.cwd()` fallback for CI-built bundles with leaked build-time paths (#1704)
-- **fix(ui):** fix light mode active request payload modal — add missing `--color-card` theme token, use opaque `bg-surface` instead of translucent `bg-card/70`, add backdrop blur (#1714)
-
-### 🔄 Updates
-
-- **chore(image-models):** refresh image generation model registry — replace stale FLUX aliases with FLUX Kontext / FLUX.2 mappings, remove deprecated FLUX Redux/Depth/Canny variants (#1722)
-
----
-
-## [3.7.2] — 2026-04-28
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(authz):** introduce centralized proxy-based authz pipeline and lifecycle policy (#1632)
-- **feat(logs):** configure call log pipeline artifacts (#1650)
-- **feat(network):** add guarded remote image fetch utility
-- **feat(codex):** enable native Codex websocket responses on beta-gated models (#1658)
-- **feat(muse-spark-web):** continue the same meta.ai conversation across turns (#1673)
-
-### 🐛 Bug Fixes
-
-- **fix(responses):** sanitize empty string placeholders from tool-call optional arguments in stream delta accumulation to avoid breaking strict clients (#1674)
-- **fix(codex):** prevent unexpected protocol leakage and fabricated instructions on bare chat completion requests without tools (#1686)
-- **fix(executors):** truncate tools array to 128 items max in GitHub Copilot and OpenCode executors to mitigate 400 Bad Request errors from upstream (#1687)
-- **fix:** add body-read timeout to prevent stuck pending requests (#1680)
-- **fix(rate-limit):** replace unsupported Bottleneck `maxWait` option with job-level `expiration` to prevent indefinite queue stalls (#1694)
-- **fix(sse):** sanitize OpenAI tool schemas for strict upstream validators — strips null from enum arrays, normalizes tuple items, filters invalid required keys (#1692)
-- **fix(stream):** fail zombie SSE streams before accepting response — returns 504 instead of hanging indefinitely, enables combo fallback (#1693)
-- **fix(combo):** complete context truncation hotfix — cache getCombos() with 10s TTL, pass allCombosData to resolveComboTargets() for nested combo resolution, consolidate duplicated context overflow regex patterns (#1685)
-- **fix(codex):** raise default quota threshold from 90% to 99% to avoid premature account blocking when usable quota remains (#1697)
-- **fix(memory):** use `user` role for GLM/ZAI/Qianfan providers — providers with strict role constraints (no `system` role) now correctly receive memory context as a `user` message instead of a `system` message, preventing 422 validation errors (#1701)
-- **fix(oauth):** target specific connection by ID on re-auth token exchange — prevents duplicate account creation when re-authenticating an existing OAuth connection (#1702 — thanks @namhhitvn)
-- **feat(email-privacy):** integrate email visibility toggle in RequestLoggerV2 — log detail modal now respects global email privacy state, hiding email addresses by default (#1700 — thanks @namhhitvn)
-- **fix(combo):** trigger fallback on Anthropic `Invalid signature in thinking block` errors instead of returning 400 directly (#1696)
-- **fix:** combo retry loop stops immediately on client disconnect (499) (#1681)
-- **fix(search):** support optional bearer auth for SearXNG (#1683)
-- **fix(vision):** respect native GPT vision support — prevents VisionBridge from intercepting models that already handle images natively (#1678)
-- **fix(qwen):** use `security.auth` format instead of `modelProviders` for Qwen Code config generation (#1677)
-- **fix(codex):** remove stale websocket transport lookup that caused fallback errors (#1676)
-- **fix(chatgpt-web):** bound tls-client native deadlocks so requests never hang forever (#1664)
-- **fix(codex):** default gpt-5.5 to HTTP transport instead of WebSocket (#1660)
-- **fix(codex):** [urgent] fix gpt-5.5 websocket transport and model labels (#1656)
-- **fix(grokweb):** update Request and Response Specifications (#1655)
-- **fix(blackbox-web):** set isPremium flag to true to enable premium model access (#1661)
-- **fix(core):** avoid OpenAI stream options for Anthropic-compatible providers (#1654)
-- **fix(electron):** resolve MCP server start failure on Windows (#1662)
-- **fix(electron):** make Windows smoke test non-blocking (continue-on-error), pre-create userData dir for Windows + stream logs in CI, and add --no-sandbox and sandbox env for CI smoke tests
-- **fix(codex):** fix `getWreqWebsocket` ReferenceError causing 502 on all Codex requests (#1652, #1653)
-- **fix(codex):** default `store` to `false` — Codex OAuth backend rejects `store=true` (#1635)
-- **fix(db):** add post-migration guards for missing `batches` table and `combos.sort_order` column on DB upgrades (#1648, #1657)
-- **fix(db):** renumber duplicate migration `032` to prevent collision
-- **fix(perplexity-web):** update API version and user-agent to match upstream requirements (#1666)
-- **fix(docker):** copy SQLite migration files and explicitly trace in standalone build (#1665)
-- **fix(muse-spark-web):** update to Meta's Ecto-era persisted query — fixes 502 `Unknown type "RewriteOptionsInput"` after Meta retired the Abra mutation (#1668)
-- **fix(dev):** enable Turbopack by default and repair Codex CORS headers (#1669)
-- **fix(authz):** restore `REQUIRE_API_KEY` support in clientApi policy
-- **fix(auth):** align fallback API key format with test setup
-
-### 🛠️ Maintenance
-
-- **build(prepublish):** make Next.js build bundler configurable (webpack/turbopack)
-- **ci:** align sonar analysis scope
-- **ci:** stabilize release branch checks
-- **ci:** remove expired advanced security scans job
-
-### 🧪 Tests
-
-- **test:** fix TypeScript configuration errors in plan3-p0.test.ts
-- **test:** fix implicit any types across test suites
-- **test:** disable type checking in flaky unit tests
-- **test:** fix failing tests due to recent refactors
-- **fix(tests):** align integration tests with authz pipeline refactor
-- **fix(tests):** align test assertions with v3.7.2 source code changes
-- **fix(tests):** CORS test now checks object body instead of entire file
-- **fix(e2e):** fix E2E flakiness and implicit any type errors
-
----
-
-## [3.7.1] — 2026-04-26
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Add GPT-5.5 support to the Codex provider — includes 1.05M context window, tool calling, vision, and reasoning capabilities with proper pricing entries across `cx` and `openai` providers. Refactors `splitCodexReasoningSuffix()` into a shared helper for cleaner effort-level parsing (#1617 — thanks @Zhaba1337228).
-- **feat(cli):** Add `omniroute reset-encrypted-columns` recovery command — nulls encrypted credential columns (`api_key`, `access_token`, `refresh_token`, `id_token`) in `provider_connections` while preserving provider metadata, giving users affected by #1622 a clean recovery path without losing configurations.
-- **feat(i18n):** Expand locale coverage with nine new language packs (Bengali, Farsi, Gujarati, Indonesian, Marathi, Swahili, Tamil, Telugu, Urdu), bringing total language support from 32 to 41 locales.
-
-### 🐛 Bug Fixes
-
-- **fix(rate-limit):** Add per-model rate limiting for GitHub Copilot provider — a 429 on one model (e.g. `gpt-5.1-codex-max`) no longer locks the entire connection, matching the existing Gemini per-model quota pattern (#1624 — thanks @slewis3600).
-- **fix(cli-tools):** Preserve existing OpenCode configuration (MCP servers, custom providers, comments) when saving OmniRoute settings — uses `jsonc-parser` for tree-preserving edits instead of destructive JSON roundtrip. Fix API key clipboard copy to use raw keys instead of masked placeholders. Add theme-aware OpenCode light/dark SVG logos (#1626 — thanks @JasonLandbridge).
-- **fix(cli-tools):** Fix OpenCode guide step 3 `{{baseUrl}}` double-brace placeholder to use ICU-style `{baseUrl}` across all 41 locales, restoring next-intl interpolation (#1626).
-- **fix(codex):** Make `wreq-js` native module import lazy and optional to prevent server crash on startup when the platform-specific binary is missing — affects pnpm installs, Docker Alpine, macOS ARM, and Windows (#1612, #1613, #1616).
-- **fix(i18n):** Add 14 missing translation keys (`logs.runningRequests`, `logs.model`, `logs.provider`, `logs.account`, `logs.elapsed`, `logs.count`, `logs.payloads`, etc.) for the Active Requests panel across all locales. Replace 83 placeholder values in usage/evals namespace. Add 5 missing health namespace keys for rate limit status.
-- **fix(encryption):** Prevent `STORAGE_ENCRYPTION_KEY` from being silently regenerated during `npm install -g` upgrades, which made all previously-encrypted provider credentials permanently unrecoverable due to AES-GCM auth-tag mismatch (#1622).
-- **fix(startup):** Add decrypt-probe diagnostic at server bootstrap — if `STORAGE_ENCRYPTION_KEY` doesn't match encrypted credentials in the database, a prominent warning is logged directing users to restore the key or use the new recovery command.
-- **fix(cli-tools):** Allow `null` API key values in `cliModelConfigSchema` to prevent 400 Bad Request errors when saving cloud-based CLI tool configurations. Fix error handling across all 10 ToolCard components to safely extract messages from structured error objects, preventing React Error #31 crashes.
-- **fix(docker):** Set `NPM_CONFIG_LEGACY_PEER_DEPS=true` in the Docker builder layer before `npm ci` and remove duplicate `postinstallSupport.mjs` COPY instruction — fixes container image build failures introduced in v3.7.0 (#1630 — thanks @rdself).
-- **fix(antigravity):** Hide deprecated Gemini-routed Claude 4.5 models from public catalogs and model lists. Legacy `gemini-claude-*` aliases now silently resolve to current Claude 4.6 equivalents. Replace dynamic reverse-alias generation with an explicit allowlist for predictable model visibility (#1631 — thanks @backryun).
-- **fix(types):** Add explicit type annotations to sync-env test helpers and dynamic import casts to satisfy `typecheck:noimplicit:core` CI gate.
-- **fix(reasoning):** Implement Reasoning Replay Cache — hybrid memory/SQLite persistence for `reasoning_content` in multi-turn tool-calling flows. Automatically captures reasoning from DeepSeek V4, Kimi K2, Qwen-Thinking, and GLM models and re-injects it on follow-up turns to prevent HTTP 400 errors from strict reasoning-content validation. Includes dashboard telemetry tab, REST API, and 21 unit tests (#1628 — thanks @JasonLandbridge).
-- **fix(postinstall):** Extend postinstall native module repair to cover `wreq-js` — detects missing platform-specific `.node` binaries inside `app/node_modules/wreq-js/rust/` and copies them from the root install. Fixes global `pnpm` installs on macOS arm64 where the standalone app directory only contained Linux binaries (#1634 — thanks @MarcosT96).
-- **fix(migration):** Prevent compat-renamed migration slots from shadowing new migrations at the same version number. After rewriting `028_provider_connection_max_concurrent` → `029`, the runner now verifies the old version slot is clear, ensuring `028_create_files_and_batches` runs on v3.6.x → v3.7.x upgrades. Adds `batches` table as a physical schema sentinel for upgrade recovery (#1637 — thanks @V8-Software).
-- **fix(registry):** Route GitHub Copilot GPT 5.4/5.5 models through the Responses API (`targetFormat: "openai-responses"`). Fixes `gpt-5.4-mini` and `gpt-5.4` being rejected on `/chat/completions` by GitHub (#1641 — thanks @dhaern).
-- **fix(usage):** Correct MiniMax token plan quota display — the newer `/v1/token_plan/remains` endpoint reports used counts, not remaining counts. Rounds floating-point percentage artifacts in Provider Limits UI (#1642 — thanks @CruxExperts).
-- **fix(codex):** Lazy-load `wreq-js` WebSocket transport via `createRequire` instead of top-level import. Server boots cleanly when native module is unavailable and returns 503 only when Codex WebSocket is actually requested. Fixes #1612 (#1640 — thanks @dendyadinirwana).
-- **fix(electron):** Package Electron runtime dependencies into `resources/app/node_modules/` via separate `extraResources` FileSet. Adds cross-platform packaged app smoke test script and CI integration to prevent future regressions. Closes #1636 (#1639 — thanks @prateek).
-- **feat(account-fallback):** Add model-level daily quota lockout. When a provider returns 429 with `quota_exhausted`, cooldown is set to tomorrow 00:00 instead of exponential backoff. Detects daily quota patterns via `isDailyQuotaExhausted()` in chat handler (#1644 — thanks @clousky2020).
-- **fix(codex):** Use per-conversation `session_id`/`conversation_id` from client body as `prompt_cache_key` instead of account-wide `workspaceId`. The official Codex CLI uses `conversation_id` (a unique UUID per session); using the shared `workspaceId` capped cache hit-rate at ~49%. Includes 10 unit tests (#1643).
-- **fix(claude):** Stabilize billing header fingerprint to prevent Anthropic prompt-cache prefix invalidation. The fingerprint was derived from the first user message text, which changes every turn, mutating `system[]` and forcing ~100% `cache_create`. Now uses a stable per-day hash, preserving ~96% `cache_read` hit rate (#1638).
-- **fix(transport):** Harden GitHub and Kiro streaming — thread `clientHeaders` through `BaseExecutor.buildHeaders()` to eliminate mutable singleton state race condition on concurrent requests. Remove redundant `[DONE]` stripping TransformStream from GitHub executor. Add defensive `parseToolInput()` for malformed Kiro tool call arguments. Hoist `TextEncoder`/`TextDecoder` to module singletons and use zero-copy `subarray()` (#1645 — thanks @dhaern).
-- **fix(transport):** Prevent memory bloat and database exhaustion from large, fragmented streaming responses. Implemented `ByteQueue` in `kiro.ts` for zero-copy binary accumulation, refactored `antigravity.ts` for incremental SSE parsing, and enforced a strict 512KB tiered truncation limit (`MAX_CALL_LOG_ARTIFACT_BYTES`) on stream request logs and call artifacts (#1647).
-- **chore(ci):** Update build environment dependencies — bump Node to `24.15.0`, `actions/checkout@v6`, `docker/build-push-action@v7`, pin `actions/setup-python` to major tag (#1646 — thanks @backryun).
-
-### 📝 Documentation
-
-- **docs(env):** Add `OMNIROUTE_ALLOW_PRIVATE_PROVIDER_URLS` to `.env.example` with documentation for LM Studio and other local provider use cases (#1623).
-
----
-
-## [3.7.0] — 2026-04-26
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-- **feat(providers):** Add CrofAI as a built-in API-key provider with quota/usage monitoring wired into the dashboard Limits page (#1604, #1606).
-- **feat(skills):** Add workspace-scoped built-in skills (`file_read`, `file_write`, `http_request`, `eval_code`, `execute_command`) with real sandbox execution via Docker, replacing stub responses. Browser skills now fail explicitly when runtime is not configured.
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **feat(provider):** add ChatGPT Web (Plus/Pro) session provider (#1593)
-- **feat(provider):** add Baidu Qianfan chat provider (#1582)
-- **feat(codex):** support GPT-5.5 responses websocket (#1573)
-- **feat(sse):** Codex CLI image_generation + DALL-E-style image route (#1544)
-- **feat(dashboard):** Complete the reconciled v3.7.0 dashboard task set: MCP cache tools and count, video endpoint visibility, provider taxonomy, upstream proxy visibility, provider count badges, costs overview, eval suite management, Custom CLI builder, ACP-focused Agents copy, Translator stream transformer, logs convergence, learned rate-limit health cards, docs expansion, and active request payload inspection.
-- **feat(mcp):** Register `omniroute_cache_stats` and `omniroute_cache_flush` across MCP schemas, server registration, handlers, docs, and tests.
-- **feat(providers):** Complete the v3.7.0 provider onboarding wave with self-hosted/local providers (`lm-studio`, `vllm`, `lemonade`, `llamafile`, `triton`, `docker-model-runner`, `xinference`, `oobabooga`), OpenAI-compatible gateways (`glhf`, `cablyai`, `thebai`, `fenayai`, `empower`, `poe`), enterprise providers (`datarobot`, `azure-openai`, `azure-ai`, `bedrock`, `watsonx`, `oci`, `sap`), specialty providers (`clarifai`, `modal`, `reka`, `nous-research`, `nlpcloud`, `petals`, `vertex-partner`), `amazon-q`, GitLab/GitLab Duo, and Chutes.ai.
-- **feat(providers):** Add Cloudflare Workers AI integration and UI support for robust backend execution.
-- **feat(telemetry):** Implement proactive public IP capture from client headers (`x-forwarded-for`, `x-real-ip`, etc.) within `safeLogEvents` for accurate database observability.
-- **feat(audio):** Add AWS Polly as an audio speech provider with SigV4 request signing, static engine catalog, provider validation, managed-provider UI coverage, and sanitization for AWS secret/session fields.
-- **feat(search):** Add You.com search provider support with dashboard discovery, validation, livecrawl option handling, and search handler normalization.
-- **feat(video):** Add RunwayML task-based video generation support, task polling, provider catalog metadata, validation, and dashboard/model-list coverage.
-- **feat(providers):** Add search functionality to the providers dashboard with i18n support. (#1511 — thanks @th-ch)
-- **feat(providers):** Register 6 new models in the opencode-go provider catalog. (#1510 — thanks @kang-heewon)
-- **feat(providers):** Add ModelScope provider (Chinese AI marketplace) with Kimi K2.5, GLM-5, and Step-3.5-Flash integration. (#1430 — thanks @clousky2020)
-- **feat(providers):** Add LM Studio as an OpenAI-compatible local provider for self-hosted model inference.
-- **feat(providers):** Add Grok 4.3 thinking model support for xAI web executor requests.
-- **feat(core):** Implement provider-level Circuit Breaker to prevent cascading failures across connections, enforcing a 10-minute cooldown after 5 consecutive transient failures. (#1430)
-- **feat(core):** Add daily quota exhaustion lock to detect "quota exceeded" signals and lock the specific model until midnight. (#1430)
-- **feat(core):** Auto-inject `stream_options.include_usage = true` for OpenAI format streams to guarantee token usage is reported correctly during streaming. (#1423)
-- **feat(core):** Add OpenAI Batch Processing API support — submit, monitor, and manage batch jobs through the proxy with full lifecycle tracking.
-- **feat(vision-bridge):** Add automatic image description fallback for non-vision models via `VisionBridgeGuardrail` (priority 5). Intercepts image-bearing requests to non-vision models, extracts descriptions via a configurable vision model (default: gpt-4o-mini), and replaces images with text before forwarding. Fails open on any error. (#1476)
-- **feat(dashboard):** Introduce real-time model status badges with countdown timers in the provider detail and combo panel interfaces. (#1430)
-- **feat(dashboard):** Add Batch/File management data grid with full i18n translations for batch processing workflows. (#1479)
-- **feat(usage):** MiniMax + MiniMax-CN quota tracking in provider limits dashboard. (#1516)
-- **feat(providers):** Fix OpenRouter remote discovery and unify managed model sync. (#1521)
-- **feat(providers):** Implement provider and account-level concurrency cap enforcement (`maxConcurrent`) using robust semaphore mechanisms. (#1524)
-- **feat(core):** Implement Hermes CLI config generation and message content stripping. (#1475)
-- **feat(combos):** Add expert combo configuration mode for advanced routing controls. (#1547)
-- **feat(providers):** Register Codex auto review and expand icon coverage.
-- **feat(tunnels):** Add Tailscale tunnel management routes and runtime helpers for install, login, daemon start, enable/disable, and health checks.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(chatgpt-web):** Fix empty-file race in `tlsFetchStreaming` where `waitForFile` accepted zero-byte files, silently degrading streaming requests to buffered mode. Replaced with `waitForContent` requiring `file.size > 0` with early exit on request settlement. (#1597 — thanks @trader-payne)
-- **fix(chatgpt-web):** Fix stale NextAuth session-token cookies surviving rotation shape changes (unchunked↔chunked). `mergeRefreshedCookie` now drops all session-token family members via `SESSION_TOKEN_FAMILY_RE` before appending the refreshed set, preventing auth failures from dual cookie submission. (#1597 — thanks @trader-payne)
-- **fix(codex):** WebSocket memory retention and weekly limit handling (#1581)
-- **fix(providers):** Default models list logic (#1577)
-- **fix(ui):** Dashboard endpoint URL hydration respects `NEXT_PUBLIC_BASE_URL` when behind a reverse proxy (#1579)
-- **fix(providers):** Restore strict PascalCase header masquerading for Claude Code to resolve HTTP 429 upstream errors (#1556)
-- **fix(sse):** make Responses passthrough robust for size-sensitive clients (#1580)
-- **fix(codex):** update client version for gpt-5.5 (#1578)
-- **fix(vision-bridge):** force GPT-family image fallback (#1571)
-- **fix(claude):** skip adaptive thinking defaults for unsupported models (#1563)
-- **fix(claude):** preserve tool_result adjacency in native and CC-compatible paths (#1555)
-- **fix(reasoning):** Preserve OpenAI Chat Completions `reasoning_effort` through assistant-prefill requests and label OpenAI request protocols explicitly as `OpenAI-Chat` or `OpenAI-Responses`. (#1550)
-- **fix(codex):** Fix Codex auto-review model routing so review traffic resolves to the intended configured model. (#1551)
-- **fix(resilience):** Route HTTP 429 cooldowns through runtime settings so cooldown behavior follows the configured resilience profile. (#1548)
-- **fix(providers):** Normalize Anthropic header keys to lowercase in the provider registry to avoid duplicate or case-variant upstream headers. (#1527)
-- **fix(providers):** Preserve audio, embedding, rerank, image, video, and OpenAI-compatible alias metadata when `/v1/models` merges static and discovered catalogs.
-- **fix(providers):** Discover Azure OpenAI deployments from resource endpoints using `api-key` auth and configurable API versions.
-- **fix(providers):** Keep local OpenAI-style providers authless when no API key is configured, including the Lemonade Server default endpoint.
-- **fix(translator):** Preserve Antigravity default system instructions and caller-provided system prompts as separate Gemini `systemInstruction` parts instead of concatenating them.
-- **fix(security):** Sanitize provider-specific AWS secrets and session tokens from provider management API responses.
-- **fix(release):** Resolve combo prefixing, Electron packaging, CLI auth, and release-branch integration regressions. (#1471, #1492, #1496, #1497, #1486)
-- **fix(providers):** Resolve 400 errors for GLM and Antigravity Claude adapter during request translation by scoping prompt caching to compatible Anthropic endpoints and flattening system instructions. (#1514, #1520, #1522)
-- **fix(core):** Strip `reasoning_content` from OpenAI format messages for non-reasoning models to prevent upstream HTTP 400 validation errors. (#1505)
-- **fix(sse):** Map Claude `output_config/thinking` to OpenAI `reasoning_effort` for proper Antigravity tool translation. (#1528)
-- **fix(combo):** Fallback to next model on all-accounts-rate-limited (HTTP 503/429) to maintain high availability. (#1523)
-- **fix(api):** Harden batch and file endpoints for auth and recovery to prevent schema state collisions.
-- **fix(ui):** Add missing UI wiring for "Add Memory" and "Import" buttons on the `/dashboard/memory` page. (#1506)
-- **fix(ui):** Prevent Dark Mode FOUC (Flash of Unstyled Content) by injecting a synchronous theme initialization script into the root `layout.tsx`.
-- **fix(ui):** Fix mobile layout text overflow in provider and combo cards, and enable touch-friendly reordering arrows across all combo strategies.
-- **fix(core):** Add periodic runtime log rotation checks to prevent disk exhaustion in long-running instances. (#1504 — thanks @ether-btc)
-- **fix(build):** Resolve missing `process` module in webpack client build for pino-abstract-transport. (#1509 — thanks @hartmark)
-- **fix(ui):** Add dark mode support for native dropdown `<option>` elements on Linux/Windows, resolving invisible text in settings and combo builders (#1488)
-- **fix(batch):** Add batch item dispatching to specific handlers based on URL to support embeddings and other modalities (#1495 — thanks @hartmark)
-- **fix(dashboard):** Correct TOML round-trip corruption in Codex config serializer by dequoting keys and preserving array/boolean structures properly. (#1438 — thanks @benzntech)
-- **fix(security):** Resolve CodeQL alert 164 (ReDoS in extraction) and 163 (incomplete URL sanitization). (#163, #164)
-- **fix(providers):** Add optional chaining to connection object before accessing `providerSpecificData`, preventing runtime errors when the connection is null/undefined.
-- **fix(codex):** Preserve namespace MCP tools forwarded to Codex Responses API, preventing tool name stripping during translation. (#1483)
-- **fix(codex):** Deduplicate case-variant `anthropic-version` header in Claude Code patch to prevent duplicate header injection. (#1481)
-- **fix(fallback):** Use shared `CircuitBreaker` instead of undefined constants, fixing runtime errors in provider failure handling. (#1485)
-- **fix(fallback):** Merge new provider failure threshold fields (`providerFailureThreshold`, `providerFailureWindowMs`, `providerCooldownMs`) into resilience profiles.
-- **fix(fallback):** Remove 429 from `PROVIDER_FAILURE_ERROR_CODES` — rate limits are already handled by model-level and account-level locks; including them in the provider-wide circuit breaker caused premature cooldown.
-- **fix(sse):** Enable tool calling for GPT OSS and DeepSeek Reasoner models. (#1455)
-- **fix(encryption):** Return null on decryption failure to prevent sending encrypted tokens to providers. (#1462)
-- **fix(combo):** Resolve cross-provider thinking 400 errors and HTTP clipboard issues during combo routing. (#1444)
-- **fix(core):** Resolve skills, memory, and encryption system issues affecting startup and runtime stability. (#1456)
-- **fix(core):** Fix model ID parsing for providers with slashes in model names — use `indexOf`/`substring` instead of `split` to handle models like `modelscope/moonshotai/Kimi-K2.5`.
-- **fix(core):** Fix reference counting in `ModelStatusContext` — changed `registeredModels` from `Set` to `Map<string, number>` to prevent polling stop when one component unmounts while others still track the same model.
-- **fix(security):** Prompt injection guard failures now return an explicit 500 response instead of silently passing through (fail-closed policy).
-- **fix(security):** Encryption now derives new keys from a secret-based salt while falling back to the legacy static-salt key during decryption, preserving existing stored credentials.
-- **fix(combo):** Resolve context truncation bug in combo routing to prevent incomplete execution states. (#1517)
-- **fix(compression):** Implement bidirectional tool_pair cleaning for anthropic inputs (fixes #1592).
-- **fix:** Resolve v3.7.0 stabilization issues including dashboard navigation routing, ProxyRegistryManager component layout, and models API response merging (#1566, #1560, #1559).
-- **fix(cli):** Preserve TOML integer/boolean types in Codex config round-trip to prevent `tui.model_availability_nux` validation errors.
-- **fix(tailscale):** Support sudo auth prompts and live daemon socket detection for non-root tunnel management.
-- **fix(dashboard):** Stabilize usage tab loading and refresh behavior to prevent empty state flashes.
-- **fix(i18n):** Translate 519 untranslated pt-BR keys and add missing Windsurf/Cline/Kimi docs keys.
-- **fix(i18n):** Add missing dashboard message keys across all 30 locales.
-- **fix(cli):** Align OpenCode config preview and add multi-model selection (#1602).
-- **fix(security):** Harden management API auth and OpenAPI try-proxy endpoint.
-- **fix(security):** Resolve vulnerability scan findings for auth-guarded routes.
-
-### ♻️ Refactoring
-
-- **refactor(fallback):** Make provider failure thresholds configurable via `PROVIDER_PROFILES` instead of hardcoded constants, supporting different failure tolerance per provider type. (#1449)
-- **refactor(resilience):** Unify resilience controls across the codebase for consistent circuit breaker and fallback behavior. (#1449)
-- **refactor(core):** Implement shared path utilities, add custom date formatting, improve type safety, and unify database imports across modules.
-- **refactor(security):** Harden backup archive creation by switching to `execFileSync`, validate ACP agent IDs, expand shared CORS handling.
-- **refactor(release):** Remove obsolete agent workflow playbooks and the stale compiled `src/lib/dataPaths.js` artifact. (#1541)
-
-### 🧪 Tests
-
-- **test(providers):** Add targeted coverage for AWS Polly SigV4 speech/validation, Azure OpenAI deployment discovery, Lemonade local discovery, provider dashboard taxonomy, managed provider catalog behavior, and merged `/v1/models` alias metadata.
-- **test(catalog):** Add v3.7.0 catalog coverage for Pollinations text models, Perplexity Sonar via Puter, and NVIDIA free-model alias resolution.
-- **test(vision-bridge):** Add 51 unit tests covering all VisionBridge spec scenarios (VB-S01 through VB-S10), including helper functions for `callVisionModel`, `extractImageParts`, `replaceImageParts`, and `resolveImageAsDataUri`.
-- **test(batch-api):** Isolate batch API unit tests with temp `DATA_DIR` to prevent schema state collisions.
-- **test(settings-api):** Add test harness with `createSettingsApiHarness` function for proper temp directory setup and storage reset between tests.
-- **test(security):** Update prompt injection test for fail-closed policy alignment.
-- **test(core):** Restore local test fixes for encryption and resilience modules.
-- **test(next):** Align transpile package expectations for the Next.js standalone build.
-- **test(ci):** Fix CI-only test failures from environment differences — clear `INITIAL_PASSWORD` and `JWT_SECRET` in integration tests, handle `XDG_CONFIG_HOME` for guide-settings tests.
-
-### 📚 Documentation
-
-- **docs:** Update the root changelog with all release-branch changes through 2026-04-24, including PRs #1544, #1555, #1551, #1550, #1548, #1547, #1541, #1538, #1536, and #1527.
-- **docs:** Fix broken README and localized documentation links. (#1536)
-- **docs:** Add dashboard docs coverage for current API endpoints, management APIs, ACP, MCP tools, provider onboarding, and v3.7.0 task reconciliation.
-- **docs:** Add Arch Linux AUR install notes for community package support. (#1478)
-- **docs(i18n):** Improve Ukrainian (uk-UA) translation quality — full Ukrainian translation for README, SECURITY, A2A-SERVER, API_REFERENCE, AUTO-COMBO, and USER_GUIDE documents. Fix mixed Latin/Cyrillic typos, translate model table entries, and standardize section headers.
-
-### 🛠️ Maintenance
-
-- **chore:** Add `.tmp/` to `.gitignore` to keep local build/test artifacts out of release diffs. (#1538)
-- **chore(release):** Clarify release version parity and changelog segregation rules for generated release workflows.
-
-### 📦 Dependencies
-
-- **deps:** Bump the development group with 4 updates. (#1464)
-- **deps:** Bump the production group with 4 updates. (#1463)
-- **deps:** Update `@lobehub/icons` to `5.5.4`, add explicit `react-is@19.2.5` for Recharts, pin npm installs to skip unused peer auto-installs, and override Electron's transitive `@xmldom/xmldom` to `0.9.10` so audit findings stay closed.
-
----
-
-## [3.6.9] — 2026-04-19
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Mark Qwen OAuth provider as deprecated following the upstream free tier shutdown on 2026-04-15. Adds deprecation warning to CLI tool UI and rewrites `saveQwenConfig` to inject OmniRoute as a multi-provider (openai, anthropic, gemini) via `.qwen/settings.json` and `.qwen/.env` (#1437)
-- **feat(cc-compatible):** Align Claude Code-compatible request shape with the official Claude CLI protocol, including proper system skeleton and request normalization (#1411)
-- **feat(skills):** Provider-aware marketplace UX with scored AUTO injection and memory pipeline hardening. Skills now show relevance scores and can automatically inject context into requests (#1411)
-- **feat(claude-code):** Update Claude Code obfuscation to version 2.1.114, centralize hardcoded version strings, and use standard logger (#1403)
-- **feat(cli-tools):** Add direct configuration file generation and override support for Qwen Code local settings (#1394)
-- **feat(providers):** Derive Claude CLI model defaults dynamically from provider registry to stay current with upstream API changes (#1393)
-- **feat(core):** Implement persistent API key, backup pruning, and GPU optimization (#1350, #1367, #1369)
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(cli-tools):** Prevent masked API keys (`sk-31c4****8600`) from being written to CLI tool config files. The dashboard UI now passes `key.id` to the backend, which resolves the unmasked key from the database via a new `resolveApiKey()` helper. Fixes auth failures across all CLI tools (Claude, Codex, Cline, Kilo, Droid, OpenClaw, Antigravity) (#1435)
-- **fix(cc-compatible):** Trim the default Claude Code-compatible system prompt skeleton from a multi-paragraph instruction set down to a single identifier line, reducing redundant token usage since Claude Code already injects its own extensive system context (#1433)
-- **fix(security):** Resolve SSRF environment static evaluation bug where the outbound URL guard could be bypassed via computed expressions (#1427)
-- **fix(auth):** Reload fresh token state and unify expiry persistence to prevent stale credentials from causing cascading auth failures
-- **fix(core):** Stabilization fixes for token refresh, usage translation, and testing infrastructure
-- **fix(api):** Stop sending unsupported parameters to Gemini and Codex upstream APIs, preventing 400 Bad Request errors
-- **fix(skills):** Optimize AUTO scoring algorithm and include Responses API input context for more accurate skill relevance matching (#1418)
-- **fix(responses):** Preserve reasoning content when translating Chat Completions format to Responses API format, preventing loss of chain-of-thought data (#1414)
-- **fix(cc-compatible):** Add Claude CLI system skeleton for OpenAI-format inputs to ensure consistent behavior when CC-compatible providers receive OpenAI-style payloads
-- **fix(providers):** Add `ref` to `GEMINI_UNSUPPORTED_SCHEMA_KEYS` to fix 400 errors from Gemini CLI when tool schemas contain JSON Schema `$ref` fields
-- **fix(codex):** Prevent proactive token refresh from consuming valid tokens and strip the unsupported `background` parameter from upstream requests
-- **fix(providers):** Fix `usage.prompt_tokens` under-reporting when translating Claude caching responses to OpenAI format (#1426)
-- **fix(core):** Fix token refresh resilience for Codex providers. Unrecoverable OAuth refresh errors (`token_expired` and `invalid_token`) now correctly mark the connection as invalid to prompt user re-authentication, rather than silently failing (#1415)
-- **fix(providers):** Fix Gemini tool calling by removing the unsupported `additionalProperties` schema field, resolving 400 errors during complex tool invocations (#1421)
-- **fix(providers):** Remove arbitrary user thought signature injection in Gemini responses to comply with updated API constraints (#1410)
-- **fix(providers):** Fix Gemini API part count mismatch for streaming responses (#1412)
-- **fix(codex):** Respect `openaiStoreEnabled` setting during native passthrough for Responses API to prevent unsupported upstream arguments (#1432)
-- **fix(ui):** Makes dropdown text visible in dark mode within the Combo Builder modal (#1409)
-- **fix(chatcore):** Apply proactive compression before provider translation to prevent token limit errors in combo routes (#1406)
-- **fix(claude-code):** Scope thinking stripping to executor boundaries to prevent issues with normal API requests (#1401)
-- **fix(claude-code):** Scope obfuscation logic to CLI clients only and fix associated test assertions
-- **fix(mitm):** Resolve MITM not working when connecting Antigravity (#1399)
-- **fix(security):** Resolve CodeQL password hash alert and fix TruffleHog CI failure (#161)
-- **fix(combo):** Fallback to the next model when all provider accounts return a 503 rate-limited signal instead of aborting the routing sequence (#1398)
-- **fix(codex):** Strip server-generated IDs from response items in input to prevent 404 lookup errors in multi-turn Codex Conversations (#1397)
-- **fix(codex):** Optimize Chat Completions paths by converting `system` to `developer` roles instead of hoisting them into instructions, enabling prompt caching for system messages on GPT-5 models (#1400)
-- **fix(providers):** Resolve Claude passthrough corruption (#1359), Kimi-k2 reasoning header rejections (#1360), thinking parameter leaks (#1361), and Ollama proxy redirect drops (#1381)
-- **fix(core):** Proxy lookup in key validation respects the new ProxyRegistry environments, and proxy contexts correctly inherit downwards during token refresh preventing expiration loops (#1384, #1390)
-- **fix(providers):** Treat upstream legacy validation HTTP 5xx responses as a valid bypass for Qoder PAT tokens to prevent false negative invalidation (#1391)
-- **fix(electron):** Resolve type error in Header electronAPI properties
-- **fix(security):** Resolve CodeQL security alerts including safe prototype bindings (#151, #152, #154, #155-159)
-- **fix(tsc):** Silence `baseUrl` deprecation warnings for TypeScript 5.5+ configurations
-
-### 🧪 Tests
-
-- **test(core):** Resolve typescript strictness complaints and fix combo-routing-engine test regression
-- **test(core):** Resolve remaining strict type errors across all unit test files
-- **test(providers):** Fix provider service assertion for anthropic-compatible header format
-- **test(codex):** Align codex passthrough assertions with explicit store retention policy
-- **test(codex):** Fix store assertion for codex responses
-- **test(cli):** Resolve strict null checks in Qoder unit tests
-
-### 🛠️ Maintenance
-
-- **chore:** Sync infrastructure with docker postinstall components and secondary CodeQL analysis rules
-- **chore:** Enforce contributor credit rule in review-prs workflow
-- **chore:** Fix TS errors and update review-prs workflow for improved automation
-- **ci:** Allow manual CI dispatch for release branches
-- **ci:** Shard long-running test suites and relax timeouts for stability
-- **ci:** Restore release v3.6.9 build pipeline and fix flaky tests
-- **docs:** Update generate-release workflow to use full changelog for PR body
-- **docs:** Enforce PR merge instead of manual close in workflows
-
----
-
-## [3.6.8] — 2026-04-17
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **feat(providers):** Support `xhigh` reasoning tier exclusively on Claude models that expose it (#1356)
-- **feat(providers):** Add CC Compatible connection-level 1M context toggle (#1357)
-- **feat(core):** Add full support for Node.js 24 LTS (Krypton) environments with continuous integration coverage (#1340)
-- **feat(dashboard):** Display Antigravity credit balance in dashboard Limits & Quotas (#1338)
-- **feat(i18n):** Add internationalization support for combo features and dashboard components; sync translations across 31 keys (#1318)
-- **feat(providers):** Add Claude Opus 4.7 to Claude Code OAuth models natively with extended context and caching (#1347)
-- **feat(core):** Add stopSequences support and expand tool definitions to include Google Search capabilities
-- **feat(auth):** Enforce dashboard session authentication on all management API routes, preventing unauthenticated access to configuration endpoints
-- **feat(runtime):** Add hot-reloadable guardrails and model diagnostics for real-time rule evaluation without restarts
-- **feat(core):** Add payload rules, tag-based routing, and scheduled budget systems for fine-grained request governance
-- **feat(providers):** Expose Antigravity preview model aliases and Gemini CLI onboarding flow for first-time setup
-- **feat(antigravity):** Add client model aliases and thoughtSignature bypass modes for Antigravity OAuth connections
-- **feat(providers):** Expand image provider registry with extended model support including SD3.5, FLUX, and DALL-E 3 HD configurations
-- **feat(combos):** Add new routing strategies and full i18n support for agent features section across 31 languages
-
-### 🔒 Security
-
-- **security:** Resolve 18 GitHub CodeQL scan alerts including ReDoS, incomplete sanitization, and bad HTML filtering regexp patterns
-- **fix(auth):** Seal privilege escalation vector by enforcing JWT session checking exclusively on `/api/keys` management endpoints (#1353)
-- **fix(providers):** Resolve Codex token refresh race condition via mutex `getAccessToken` preventing `refresh_token_reused` Auth0 revocations
-
-### 🔧 Maintenance & Architecture
-
-- **refactor(core):** Split CLI runner and decouple migration engine for extensibility (#1358)
-- **refactor(audit):** Rewire audit dashboard from dead in-memory `configAudit` store to live SQLite `audit_log` table — 331+ hidden compliance entries now visible in `/dashboard/audit`
-- **build(deps):** Bump `softprops/action-gh-release` from v2 to v3
-- **ci:** Bump GitHub Actions CI node-version to Node.js 24 natively
-- **fix(types):** Resolve TypeScript compilation errors in `claudeCodeCompatible.ts` (type predicates, `cache_control` index access) and `proxyFetch.ts` (`signal` nullability)
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(context):** Scale reserved context tokens dynamically using a 15% sliding window for smaller models
-- **test(core):** Replace unit test with integration test for proactive context compression to align with isolated runner rules (#1378)
-- **fix(services):** Pass origin provider to refreshWithRetry to avoid tripping the generic "unknown" circuit breaker (fixes Codex accounts erroneously disabling)
-- **fix(db):** Prevent native module ABI load crashes from assuming database corruption and skipping databases
-- **fix(db):** Increase mass-migration threshold from 5 to 50 pending migrations to protect legacy users upgrading node
-- **fix(db):** Prevent migration runner safety aborts from triggering on fresh `DATA_DIR` installations by detecting new databases (#1328)
-- **fix(mcp):** Checkpoint and close MCP audit SQLite database safely on process signals and shutdown (#1348)
-- **fix(mcp):** Fully decouple MCP audit SQLite connection caching via globalThis to fix unhandled teardown in standalone Next.js chunks (#1349)
-- **fix(cli):** Avoid creating app router directory during postinstall initialization on non-built source trees (#1351)
-- **fix(codex):** Correctly translate `system` role to `developer` in input array to unlock GPT-5 automatic prompt caching (#1346)
-- **fix(core):** Pass client headers to executor in chatCore (#1335)
-- **fix(providers):** Separate test batch calls and ignore unknown connections
-- **fix(providers):** Add grok-web SSO cookie validation handler (#1334)
-- **fix(db):** Preserve key_value settings (dashboard passwords, saved aliases) across DB heuristic recreation cycles (#1333)
-- **fix(routing):** Allow combo fallback to cascade context overflow 400 errors instead of immediate aborts (#1331)
-- **fix(core):** Resolve thinking leaks, consecutive roles, and missing thoughtSignatures for Antigravity translator (#1316)
-- **fix(translator):** Only apply thoughtSignature to the first `functionCall` part in Gemini parallel tool calls, preventing duplicate signatures
-- **fix(providers):** Default to batch testing execution blocks for web, search, and audio modalities to prevent connection timeouts
-- **fix(cli):** Resolve Node 22 TS entrypoint incompatibility by using esbuild compilation (#1315)
-- **fix(chat):** Preserve max_output_tokens for Responses API targets in chatCore sanitization (#1313)
-- **fix(api):** API Manager usage stats showing 0 for all registered keys (#1310)
-- **fix(api):** Support image-only models in catalog and allow authless search providers to bypass validation requirements
-- **fix(routes):** Require prompts for media generation requests (`/images`, `/videos`, `/music`), returning 400 on missing payloads
-- **fix(dashboard):** Auto-scroll ActivityHeatmap to show current date (#1309)
-- **fix(dashboard):** Restore horizontal layout with `w-max` wrapper in heatmap components
-- **fix(i18n):** Update `nodeIncompatibleHint` to recommend Node 24 LTS across all 31 languages
-- **fix(i18n):** Add Chinese i18n support to remaining dashboard components (`Loading.tsx`, `DataTable`, etc.)
-- **fix(requestLogger):** Add missing `cacheSource` and `tps` columns to i18n log detail views
-
-## [3.6.6] — 2026-04-15
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **feat(storage):** Add database backup cleanup controls, UI management, and customizable retention period env vars (#1304)
-- **feat(providers):** Add Freepik Pikaso image generation provider with support for cookie/subscription-based auth modes (#1277)
-- **feat(providers): Add Perplexity Web (Session) Provider** — Routes through Perplexity's internal SSE API using a session cookie, giving native proxy access without separate API costs to GPT-5.4, Claude Opus, Gemini 3.1 Pro, and Nemotron via preferences mapping (#1289)
-- **feat(api): Sync Tokens & V1 WebSocket Bridge** — Dedicated sync token storage, issuance, revocation, and bundle download routes backed by stable config bundle versioning with ETag support. Exposes `/v1/ws` WebSocket upgrade route and a custom Next.js server bridge (`scripts/v1-ws-bridge.mjs`) so OpenAI-compatible WebSocket traffic can be proxied through the gateway. Compliance auditing expanded with structured metadata, pagination, request context, auth/provider credential events, and SSRF-blocked validation logging. New migrations: `024_create_sync_tokens.sql`. New modules: `syncTokens.ts`, `src/lib/sync/bundle.ts`, `src/lib/sync/tokens.ts`, `src/lib/ws/handshake.ts`, `src/lib/apiBridgeServer.ts`, `src/lib/compliance/providerAudit.ts`.
-- **feat(models): GLM Thinking Preset & Hybrid Token Counting** — GLM Thinking (`glmt`) registered as a first-class provider preset with shared GLM model metadata, pricing, per-connection usage sync, dashboard support, and `maxTokens: 65536 / thinkingBudgetTokens: 24576` request defaults with 900s extended timeout. Provider-side `/messages/count_tokens` endpoint used when a Claude-compatible upstream supports it; gracefully falls back to estimation on missing models, missing credentials, or upstream failures. Startup seeding of default model aliases (`src/lib/modelAliasSeed.ts`) normalizes common cross-proxy model dialects so canonical slash-based model IDs are not misrouted. New file `open-sse/config/glmProvider.ts`.
-- **feat(core): Hardened Outbound Provider Calls & Cooldown Retries** — Guarded outbound fetch helpers (`src/shared/network/safeOutboundFetch.ts`, `src/shared/network/outboundUrlGuard.ts`) blocking private/local URLs with configurable retry, timeout normalisation, and route-level status propagation for provider validation and model discovery. Cooldown-aware chat retries (`src/sse/services/cooldownAwareRetry.ts`) with configurable `requestRetry` and `maxRetryIntervalSec` settings and model-scoped cooldown responses. Improved rate-limit learning from headers and error bodies so short upstream lockouts can recover automatically. Runtime environment validation (`src/lib/env/runtimeEnv.ts`) checks env at startup. Pollinations now requires an API key. Antigravity and Codex header handling aligned via `open-sse/config/antigravityUpstream.ts` and `open-sse/config/codexClient.ts`. Gemini tool names restored in translated responses; synthetic Claude text block injected when upstream SSE completes empty.
-- **feat(logs):** Add TPS (Tokens Per Second) metric to log details modal metadata grid (#1182)
-- **feat(memory+skills):** Full-featured Memory & Skills systems with FTS5 SQLite search, dynamic UI pagination, backend observability, and extensive test coverage (#1228)
-- **feat(bailian-quota):** Add Alibaba Coding Plan quota monitoring, multi-window quota extraction, and UI credential validation (#1235)
-- **feat(storage): Call Log Storage Refactor** — Extracted heavy request/response JSON payloads from the core SQLite database (`storage.sqlite`) into filesystem artifacts stored within `DATA_DIR/call_logs`. This massively reduces WAL bloat and eliminates `SQLITE_FULL` crashes on high-traffic nodes (#1307).
-- **feat(providers): Add Grok Web (Subscription) Provider** — Routes through the xAI web interface for subscription users via cookie session mapping (#1295).
-- **feat(api): Advanced Media Support** — Extends OpenAI generic proxy layer to natively support `image`, `embeddings`, `audio-transcriptions`, and `audio-speech` workflows (#1297).
-- **feat(cli-tools): Qwen Code CLI Integration** — Full integration for Qwen Code local execution mapping, model resolution, and dynamic API key fetching (#1266, #1263).
-- **feat(oauth):** Supports `cursor-agent` CLI as a native Cursor credential source alongside the standard configuration (#1258).
-- **feat(models):** Custom and imported models now merge correctly into filter lists for all available global providers (#1191).
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(providers):** match correct endpoint api.xiaomimimo.com for Xiaomi MiMo (#1303)
-- **fix(core):** strip provider alias routing prefix from payload for custom endpoints to fix Azure OpenAI 400 errors (#1261)
-- **fix(core):** ProxyFetch Undici dispatcher automatically bypasses LAN/local addresses, preventing fetch failures on internal OpenRouter requests (#1254)
-- **fix(core):** Gemini thought stream signature detection upgraded to use native part.thought boolean, preventing reasoning text leaks (#1298)
-- **deps:** bump hono from 4.12.12 to 4.12.14 to resolve CVE SSR HTML injection vulnerability (#1306, #59)
-- **deps:** update dompurify to 3.4.0 in frontend overrides mitigating XSS HTML Injection (CVE-XYZ / Dependabot #60)
-- **test:** Disable SQLite automatic backups during continuous integration (CI) tests to resolve E2E timeout issues limiting runner scaling (#24481475058)
-- **feat(core): Proactive Context Compression** — `chatCore` now proactively compresses oversized message contexts before hitting upstream providers to dramatically reduce `context_length_exceeded` errors. Employs binary-search message pruning with structural integrity guarantees tracking explicit `tool_use` boundaries ensuring truncated tool inputs drop paired outputs appropriately (#1292, #1293)
-
-- **fix(cli):** Resolve codex routing config parsing by strictly quoting section keys array, enforcing responses wire_api with fallback, and standardizing select-model button positioning mirroring Claude UI
-- **fix(providers):** Correct Lobehub provider icons rendering by removing unsupported local references ensuring local SVG/PNG fallback mechanism invokes natively
-- **fix(db):** Implement Database migration tracking safety abort safeguards (pre-migration backups via `VACUUM INTO` and mass renumbering warnings) to protect existing database structures on startup upgrades (#1281)
-- **fix(dashboard):** Cleaned up target codex `config.toml` structure preventing recursive section rendering by enforcing quotes on section dot paths and mapping correct UI `OMNIROUTE_API_KEY` names.
-- **fix(mcp):** Add dedicated explicit timeout constraint overrides for search handlers (#1280)
-- **fix(crypto):** Add validation guard to encryption layer to surface clear UI errors when cryptographic environment variables are missing, replacing raw Node.js TypeErrors. Legacy env vars `OMNIROUTE_CRYPT_KEY` and `OMNIROUTE_API_KEY_BASE64` now also accepted as fallbacks (#1165)
-- **fix(providers):** Update Pollinations provider definition to require API keys and specify their new limited pollen/hour free tier (#1177)
-- **Streaming `\n\n` Artifact Fix (#1211):** Changed `<omniModel>` tag-stripping regex from `?` to `*` quantifier across `combo.ts`, `comboAgentMiddleware.ts`, and `contextHandoff.ts` to greedily strip all accumulated JSON-escaped newline sequences surrounding the tag. This prevents literal `\n\n` prefix artifacts from appearing in consumer streaming responses
-- **E2E Combo Test Locator:** Fixed Playwright strict-mode violation in `combo-unification.spec.ts` by replacing ambiguous `getByRole` locator with a compound filter locator for the "All" strategy tab
-- **fix(cc-compatible):** Trim beta flags and preserve cache passthrough for third-party HTTP proxy compatibility (#1230)
-- **fix(providers):** Update Xiaomi MiMo endpoints to the live token-plan, migrating away from dead API URLs (#1238)
-- **fix:** Forward client `x-initiator` header to GitHub Copilot upstream to accurately distinguish agent vs user turns (#1227)
-- **fix:** Resolve backlog bugs including streaming edge cases, unhandled rejections, and quota parse failures (#1206, #1220, #1231, #1175, #1187, #1218, #1202)
-- **fix(tests):** Resolve memory migration and skills route pagination bugs arising from PR overlaps
-- **fix(i18n):** Add missing Chinese i18n support to dashboard components (`DataTable`, `EmptyState`, etc), update `en.json/zh-CN.json` routing keys, and natively resolve JSX defaults via `next-intl` (#1274)
-
-### 🔧 Internal Improvements
-
-- **Compliance Audit Expansion:** `src/lib/compliance/index.ts` expanded with structured metadata, pagination support, request context enrichment, and new `providerAudit.ts` module logging auth and provider credential events, SSRF-blocked validation attempts, and provider CRUD operations
-- **Config Sync Bundle:** `src/lib/sync/bundle.ts` exports `buildConfigBundle()` generating a versioned JSON snapshot of settings, provider connections, nodes, model aliases, combos, and API keys (passwords redacted) with ETag support for bandwidth-efficient polling
-- **Codex Client Constants:** Centralized `CODEX_CLIENT_VERSION`, `CODEX_USER_AGENT_PLATFORM`, and pattern-validated env overrides (`CODEX_CLIENT_VERSION`, `CODEX_USER_AGENT`) in `open-sse/config/codexClient.ts`
-- **Antigravity Upstream Constants:** `open-sse/config/antigravityUpstream.ts` consolidates all Antigravity base URLs and model/fetchAvailableModels discovery path builders
-- **Model Alias Seed:** `src/lib/modelAliasSeed.ts` seeds 30+ cross-proxy model dialect aliases (e.g. `openai/gpt-5` → `gpt-5`, `anthropic/claude-opus-4-6` → `cc/claude-opus-4-6`) at startup via idempotent `upsert`
-- **Test Coverage:** 15+ new unit test suites covering sync routes, WebSocket bridge, compliance index, GLM provider config, cooldown-aware retry, safe outbound fetch, stream utilities, Codex executor, provider validation branches, model cross-proxy compatibility, and model alias seeding
-- **TypeScript Migration:** Finalized migration of remaining JS tests (`proxy-load` and `testFromFile`) to TypeScript ES modules, ensuring a fully synchronized TS stack.
-- **Reliability & Resilience:** Added exponential backoff to `models.dev` auto-sync to combat transient network failures, raised interval floor to 1 hour, and added LKGP debug logging for enhanced observability during routing. (#1286)
-
----
-
-## [3.6.5] — 2026-04-13
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Antigravity AI Credits Fallback:** Automatically retries with `GOOGLE_ONE_AI` credit injection when free-tier quota is exhausted. Per-account credit balance (5-hour TTL) is cached from SSE `remainingCredits` and exposed as a numeric badge in the Provider Usage dashboard (#1190 — thanks @sFaxsy)
-- **Claude Code Native Parity:** Full header/body signing parity with the Claude Code 2.1.87 OAuth client — CCH xxHash64 body signing with singleton WASM initialization promise (fixing race conditions), dynamic per-request fingerprint, bidirectional TitleCase ↔ lowercase tool name remapping (14 tools), API constraint enforcement (`temperature=1` for thinking, max 4 `cache_control` blocks, auto-inject ephemeral on last user message), and optional ZWJ obfuscation. Wired into `BaseExecutor` for automatic CCH signing on all `anthropic-compatible-cc-*` providers and into `chatCore` for synchronous parity pipeline steps (#1188 — thanks @RaviTharuma)
-- **Per-Connection Codex Defaults:** Codex Fast Service Tier and Reasoning Effort settings are now per-connection instead of a single global toggle. Existing connections are migrated automatically on startup via an idempotent backfill migration (#1176 — thanks @rdself)
-- **Cursor Usage Dashboard:** New `getCursorUsage()` fetches quotas from Cursor's `/api/usage`, `/api/auth/me`, and `/api/subscription` endpoints. Displays standard requests, on-demand usage, and per-plan limits (Free/Pro/Business/Team). Client version bumped to `3.1.0` and `x-cursor-user-agent` header added for parity
-- **Database Health Check System:** Automated periodic SQLite integrity monitoring via `runDbHealthCheck()` — detects orphan quota/domain rows, broken combo references, stale snapshots, and invalid JSON state. Runs every 6 hours (configurable via `OMNIROUTE_DB_HEALTHCHECK_INTERVAL_MS`), with auto-repair and pre-repair backup. Exposed as **MCP tool #18** (`omniroute_db_health_check`) with Zod schemas and `autoRepair` option. Dashboard panel in Health page with status card, issue count, repaired count, and one-click repair button
-- **OpenAI Responses API Store Opt-In:** Per-connection `openaiStoreEnabled` flag controls whether the `store` field is preserved or forced to `false` on Codex Responses API requests. When enabled, `previous_response_id`, `prompt_cache_key`, `session_id`, and `conversation_id` fields are round-tripped through the Chat Completions → Responses translation, enabling multi-turn context caching on supported providers
-- **Email Privacy Toggle (Combos Page):** Global email visibility toggle (`EmailPrivacyToggle`) added to the Combos page header with responsive layout, tooltip guidance, and per-connection label masking via `pickDisplayValue()`. All combo builder options, provider connection lists, and quota screens now respect the global privacy state from `emailPrivacyStore`
-- **skills.sh Integration:** Added `skills.sh` as an external skill provider. Users can now search, browse, and install agent skills directly from a new "skills.sh" tab in the Skills dashboard. Includes backend API resolvers, frontend implementation with search/install states, and a dedicated unit test suite (#1223 — thanks @RaviTharuma)
-- **Stabilization Settings:** Added persistence support for `lkgpEnabled` and `backgroundDegradation` settings, integrated into `instrumentation-node.ts` for improved lifecycle awareness (#1212)
-- **xxhash-wasm dependency:** Added `xxhash-wasm@^1.1.0` for CCH signing (xxHash64 with seed `0x6E52736AC806831E`)
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Codex `stream: false` via Combo (ALL_ACCOUNTS_INACTIVE):** Fixed a critical bug where Codex combos returned `ALL_ACCOUNTS_INACTIVE` or empty content when the client sent `stream: false`. Root cause was triple: (1) `CodexExecutor.transformRequest()` mutated `body.stream` in-place to `true`, contaminating the combo's quality check which skipped validation thinking it was streaming; (2) the non-stream SSE parser used the wrong format (Chat Completions instead of Responses API) for Codex SSE output; (3) combo quality validation read the mutated `body.stream` instead of the client's original intent. Fixed by: cloning the body via `structuredClone()` in CodexExecutor, detecting Codex/Responses SSE format in the non-stream fallback path (with auto-translation back to Chat Completions), and capturing `clientRequestedStream` before the combo loop
-- **Gemini CLI Tool Schema Rejection:** Fixed 400 Bad Request errors from the Google API by strictly filtering non-standard vendor extensions (starting with `x-`) and `deprecated` fields from tool parameter schemas (#1206)
-- **SOCKS5 Proxy Interop (Node.js 22):** Resolved `invalid onRequestStart method` crashes caused by `undici` version mismatches between dispatchers and the built-in fetch. Hardened `proxyFetch.ts` to strictly use the library's fetch implementation for custom dispatchers (#1219)
-- **Search Cache Coalescing with TTL=0:** Fixed a bug where providers configured with `cacheTTLMs: 0` (caching explicitly disabled) still had concurrent requests coalesced and returned `{ cached: true }`. Now each call gets its own independent upstream fetch (#1178 — thanks @sjhddh)
-- **Antigravity Credit Cache Alignment (PR #1190):** Reconciled `accountId` derivation between `AntigravityExecutor.collectStreamToResponse` and `getAntigravityUsage` to use consistent cache keys (`email || sub || "unknown"`). Previously, SSE-parsed credit balances could be written under a different key than the one read by the usage dashboard, causing stale/missing credit badges
-- **Non-streaming reasoning_content Duplication:** Fixed clients rendering duplicated reasoning panels when both `reasoning_content` and visible `content` were present in non-streaming responses. `responseSanitizer` now strips `reasoning_content` from messages that already have visible text content, preserving it only for reasoning-only messages
-- **Streaming Regression Fix:** Hardened the `sanitize` TransformStream in the combo engine to strip both literal and JSON-escaped newline sequences, eliminating leading `\n\n` prefixes in assistant responses (#1211)
-- **Gemini Empty Choice Fix:** Ensured initial assistant deltas always include an empty `content: ""` string to satisfy strict OpenAI client requirements and prevent empty choice responses in tools (#1209)
-- **Gemini Tools Sanitizer Deduplication:** Extracted shared tool conversion logic into `buildGeminiTools()` helper (`geminiToolsSanitizer.ts`), eliminating duplicate implementations between `openai-to-gemini.ts` and `claude-to-gemini.ts`. The new helper correctly handles `web_search` / `web_search_preview` tool types by emitting `googleSearch` tools with priority over function declarations
-- **Qwen/Qoder Thinking+Tool_Choice Conflict:** Added `sanitizeQwenThinkingToolChoice()` to both `DefaultExecutor` (for Qwen provider) and `QoderExecutor` to prevent provider-side 400 errors when clients send `tool_choice` alongside thinking/reasoning parameters that are mutually exclusive upstream
-- **API Key Deletion Orphan Cleanup:** Deleting an API key now also removes associated `domain_budgets` and `domain_cost_history` rows, preventing orphan data accumulation
-- **CC-compatible test assertion:** Fixed pre-existing test that expected no `cache_control` on system blocks — the billing header system block now carries `cache_control: { type: "ephemeral" }` per PR #1188 design
-- **Codex Combo Smoke Test False Positives:** Fixed combo tests incorrectly reporting `ERROR` for valid Codex streaming responses when `response.output` is empty but text deltas were emitted. The summary now falls back to accumulated delta text (#1176 — thanks @rdself)
-- **Electron Builder Version Mismatch:** Fixed Electron desktop startup failures on Windows packaged builds caused by native modules (`better-sqlite3`) being under `app.asar.unpacked` while helpers were in `app/node_modules`. `resolveServerNodePath()` now merges both locations with deduplication and existence checks (#1172 — thanks @backryun)
-
-### 🔧 Internal Improvements
-
-- **SSE Parser: Responses API Non-Stream Conversion:** Added full `parseSSEToResponsesOutput()` implementation in `sseParser.ts` (255+ lines) — reconstructs complete Responses API objects from SSE event streams, handling `response.output_text.delta/done`, `response.reasoning_summary_text.delta/done`, `response.function_call_arguments.delta/done`, and terminal events. Used by the new chatCore non-stream fallback path for Codex
-- **Cursor Executor Version Sync:** Updated Cursor client User-Agent to `3.1.0` and centralized version constants (`CURSOR_CLIENT_VERSION`, `CURSOR_USER_AGENT`) for consistent fingerprinting across executor, usage fetcher, and OAuth flows
-- **Responses API Translator Parity:** `convertResponsesApiFormat()` now accepts credentials and passes them through to the translator, enabling store-aware field propagation. Round-trip preservation of `previous_response_id`, `prompt_cache_key`, `session_id`, and `conversation_id` fields
-- **Provider Schema Validation:** Added `openaiStoreEnabled` boolean validation to `providerSpecificData` Zod schema
-- **Combo Error Response Normalization:** Empty combo targets now return 404 (`comboModelNotFoundResponse`) instead of generic 503, improving client-side error differentiation
-- **Dependency Updates:** Bumps `typescript-eslint` to `8.58.2` (dev), `axios` to `1.15.0` (prod), and `next` to `16.2.2` (prod) (#1224, #1225)
-
-### ⚠️ Breaking Changes
-
-- **`DELETE /api/settings/codex-service-tier` removed:** This endpoint no longer exists. Codex Service Tier configuration has moved to per-connection `providerSpecificData.requestDefaults`. Existing connections are migrated automatically on first startup after upgrade. Any external scripts or integrations that call this endpoint should be updated — use `PUT /api/providers/:id` with `providerSpecificData.requestDefaults.serviceTier` instead (#1176).
-- **CCH signing on CC-compatible providers:** All requests to `anthropic-compatible-cc-*` providers now include an xxHash64 integrity token (`cch=...`) in the billing header. Providers that do not validate CCH will ignore it (no behavioral change), but any custom middleware inspecting the billing header should expect a 5-character hex token instead of the `00000` placeholder
-
----
-
-## [3.6.4] — 2026-04-12
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Combo Builder v2 (Wizard UI):** Completely redesigned the combo creation/editing interface as a multi-stage wizard with stages: Basics → Steps → Strategy → Review. The builder fetches provider, model, and connection metadata via a new `GET /api/combos/builder/options` endpoint, enabling precise provider/model/account selection with duplicate detection and automatic next-connection suggestion. Heavy UI components (`ModelSelectModal`, `ProxyConfigModal`, `ModelRoutingSection`) are now lazily loaded via `next/dynamic` for faster initial page render
-- **Combo Step Architecture (Schema v2):** Introduced a structured step model (`ComboModelStep`, `ComboRefStep`) replacing the legacy flat string/object combo entries. Steps carry explicit `id`, `kind`, `providerId`, `connectionId`, `weight`, and `label` fields, enabling pinned-account routing, cross-combo references, and per-step metrics. All combo CRUD operations normalize entries through the new `src/lib/combos/steps.ts` module. Zod schemas updated with `comboModelStepInputSchema` and `comboRefStepInputSchema` unions
-- **Composite Tiers System:** Added tiered model routing via `config.compositeTiers` — each tier maps a named stage to a specific combo step with optional fallback chains. Includes comprehensive validation (`src/lib/combos/compositeTiers.ts`) ensuring step existence, preventing circular fallback, and validating default tier references. Zod schema enforcement blocks composite tiers on global defaults (concrete combos only)
-- **Model Capabilities Registry:** Created `src/lib/modelCapabilities.ts` providing `getResolvedModelCapabilities()` — a unified resolver that merges static specs, provider registry data, and live-synced capabilities into a single `ResolvedModelCapabilities` object covering tool calling, reasoning, vision, context window, thinking budget, modalities, and model lifecycle metadata
-- **Observability Module:** Extracted health and telemetry payload construction into `src/lib/monitoring/observability.ts` with `buildHealthPayload()`, `buildTelemetryPayload()`, and `buildSessionsSummary()` builders. The health endpoint now returns session activity, quota monitor status, and per-provider breakdowns alongside existing system metrics
-- **Session & Quota Monitor Dashboard:** Added live Session Activity and Quota Monitors panels to the Health dashboard, showing active session counts, sticky-bound sessions, per-API-key breakdowns, and top session details alongside quota monitor alerting/exhausted/error status with per-provider drill-down
-- **Combo Health Per-Target Analytics:** The combo-health API now resolves per-target metrics using the new `resolveNestedComboTargets()` function, providing step-level success rates, latency, and historical usage breakdowns per execution key — enabling per-account, per-connection health visibility
-- **Auto-Combo → Combos Unification:** Merged the separate `/dashboard/auto-combo` page into the main `/dashboard/combos` page. Auto/LKGP combos are now managed alongside all other combos with a new strategy filter tabs system (All / Intelligent / Deterministic). The old auto-combo route redirects to `/dashboard/combos?filter=intelligent`. Removed the `auto-combo` sidebar entry, consolidating navigation into the single `Combos` item
-- **Intelligent Routing Panel (`IntelligentComboPanel`):** New inline panel (371 lines) within the combos page that shows real-time provider scores, 6-factor scoring breakdown (quota, health, cost, latency, task fitness, stability), mode pack selector, incident mode status, and excluded providers for `auto`/`lkgp` combos — replacing the former standalone auto-combo dashboard
-- **Builder Intelligent Step (`BuilderIntelligentStep`):** New conditional wizard step (280 lines) that appears in the Builder v2 flow only when `strategy=auto` or `strategy=lkgp` is selected. Exposes candidate pool selection, mode pack presets, router sub-strategy selector, exploration rate slider, budget cap, and collapsible advanced scoring weights configuration
-- **Intelligent Routing Module (`intelligentRouting.ts`):** Extracted strategy categorization and filtering logic into a dedicated shared module (210 lines) with `getStrategyCategory()`, `isIntelligentStrategy()`, `filterCombosByStrategyCategory()`, `normalizeIntelligentRoutingFilter()`, and `normalizeIntelligentRoutingConfig()` utility functions
-- **LKGP Standalone Strategy:** Implemented `lkgp` (Last Known Good Provider) as a fully functional standalone combo strategy. Previously, `lkgp` as a combo strategy silently fell through to `priority` ordering — the LKGP lookup only ran inside the `auto` engine. Now `strategy: "lkgp"` correctly queries the LKGP state, moves the last successful provider to the top of the target list, and saves the LKGP state after each successful request. Falls back to priority ordering when no LKGP state exists
-- **Unified Routing Rules & Model Aliases:** Consolidated the routing rules and model alias management controls into the Settings page, reducing fragmentation across the dashboard
-
-### ⚡ Performance
-
-- **Middleware Lazy Loading:** Refactored `src/proxy.ts` to lazy-import `apiAuth`, `db/settings`, and `modelSyncScheduler` modules, reducing middleware cold-start overhead. Added inline `isPublicApiRoute()` to avoid loading the full auth module for public routes
-- **E2E Auth Bypass:** Added `NEXT_PUBLIC_OMNIROUTE_E2E_MODE` environment flag to bypass authentication gates for dashboard and management API routes during Playwright E2E test runs
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **P2C Credential Selection:** Implemented Power-of-Two-Choices (P2C) connection scoring in `src/sse/services/auth.ts` with quota headroom awareness, error/recency penalties, and forced/excluded connection support. The new `getProviderCredentialsWithQuotaPreflight()` function integrates quota preflight checks directly into credential selection, eliminating the separate Codex-only preflight path
-- **Fixed-Account Combo Steps:** Combo steps with explicit `connectionId` now correctly bypass provider-level model cooldowns and circuit breakers, preventing a single account failure from blocking pinned-connection routing for the same model
-- **Combo Metrics Per-Target Tracking:** Extended `comboMetrics.ts` to track `byTarget` metrics keyed by execution path, recording per-step `provider`, `providerId`, `connectionId`, and `label` alongside existing per-model aggregates
-- **Call Logs Schema Expansion:** Added `requested_model`, `request_type`, `tokens_cache_read`, `tokens_cache_creation`, `tokens_reasoning`, `combo_step_id`, and `combo_execution_key` columns to `call_logs` with auto-migration. Added composite index `idx_cl_combo_target` for efficient per-target historical queries
-- **Quota Monitor Enrichment:** Expanded `quotaMonitor.ts` with full lifecycle state tracking (`status`, `startedAt`, `lastPolledAt`, `consecutiveFailures`, `totalPolls`, `totalAlerts`), ISO-formatted snapshots via `getQuotaMonitorSnapshots()`, and sorted summary via `getQuotaMonitorSummary()`
-- **Codex Quota Fetcher Hardening:** Improved `codexQuotaFetcher.ts` with safer connection registration and quota fetch error handling
-- **LKGP Save Refactored to Async/Await:** Replaced fire-and-forget `.then()` chain for LKGP persistence after successful combo routing with proper `async/await` + `try/catch`, preventing unhandled promise rejections and ensuring LKGP state is reliably saved before the response is returned
-- **Duplicate `auto` in Combo Strategy Schema:** Removed duplicate `"auto"` entry from `comboStrategySchema` (was listed on both line 104 and 108). Harmless to Zod runtime but cleaned up to avoid confusion. Schema now has exactly 13 unique strategy values
-- **Legacy Combo Refs Normalization:** Fixed combo step normalization to preserve legacy string combo references during CRUD operations, preventing data loss when editing combos created before the v2 step architecture
-
-### 🔒 Security
-
-- **Auth Bypass on Backup Routes (Critical):** Added `isAuthenticated` guards to `/api/db-backups/exportAll` (full database export) and `/api/db-backups` (list, create, and restore backups) — both were previously accessible without authentication
-- **Auth Guard on Translator Save:** Added `isAuthenticated` guard to `/api/translator/save` for defense-in-depth consistency
-- **API Key Secret Hardening:** Removed the hardcoded `"omniroute-default-insecure-api-key-secret"` fallback from `apiKey.ts` — the function now fails fast if `API_KEY_SECRET` is unset, relying on the startup validator to auto-generate it
-- **NPM Tarball Leak Fix:** Added `app/.env*` to `.npmignore` to prevent the working `.env` file from being shipped inside the npm tarball distribution
-- **Electron Builder CVE Fix:** Bumped `electron-builder` to 26.8.1 to resolve `tar` CVEs in the desktop build pipeline
-
-### 🔧 Maintenance & Infrastructure
-
-- **DB Migration 021:** Added `combo_call_log_targets` migration for `combo_step_id` and `combo_execution_key` columns in call_logs
-- **Combo CRUD Normalization:** `db/combos.ts` now normalizes all stored combo entries through the step normalization pipeline on read, ensuring consistent step IDs and kind annotations regardless of when the combo was created
-- **Playwright Config:** Updated Playwright configuration and `run-next-playwright.mjs` script for improved E2E test orchestration
-- **Build Script:** Updated `build-next-isolated.mjs` with additional reliability improvements
-- **Auto-Combo UI Cleanup:** Deleted `AutoComboModal.tsx` (161 lines), replaced `auto-combo/page.tsx` (478→5 lines) with a server-side redirect to `/dashboard/combos?filter=intelligent`
-- **Sidebar Consolidation:** Removed `"auto-combo"` from `HIDEABLE_SIDEBAR_ITEM_IDS` and `PRIMARY_SIDEBAR_ITEMS` — `normalizeHiddenSidebarItems()` silently discards any stale `"auto-combo"` entries in user settings
-- **Schema Cleanup:** Removed obsolete `createAutoComboSchema` from `schemas.ts`. Exported `comboStrategySchema` for direct use in test and filter modules
-- **A2A Agent Card Update:** Renamed skill ID from `auto-combo` to `intelligent-routing` with updated description referencing the unified combos dashboard
-- **Builder Draft Refactor:** Extended `builderDraft.ts` with dynamic stage list generation via `getComboBuilderStages()` and `isIntelligentBuilderStrategy()`. Stage navigation (`getNextComboBuilderStage`, `getPreviousComboBuilderStage`, `canAccessComboBuilderStage`) now accepts options to conditionally include/skip the `intelligent` wizard step
-- **i18n Consolidation:** Removed the standalone `"autoCombo"` i18n block (22 keys) from all 30 language files. Migrated keys into the `"combos"` block with new additions for filter tabs, intelligent panel, and builder step labels
-
-### 🧪 Tests
-
-- **16 New Test Suites:** Added comprehensive test coverage including:
-  - `combo-builder-draft.test.mjs` (186 lines) — Builder draft step construction and validation
-  - `combo-builder-options-route.test.mjs` (228 lines) — Builder options API endpoint
-  - `combo-health-route.test.mjs` (266 lines) — Combo health analytics with per-target metrics
-  - `combo-routes-composite-tiers.test.mjs` (157 lines) — Composite tiers API integration
-  - `composite-tiers-validation.test.mjs` (131 lines) — Composite tier validation rules
-  - `db-combos-crud.test.mjs` — Combo CRUD with step normalization
-  - `db-core-init.test.mjs` (129 lines) — DB initialization and column migrations
-  - `model-capabilities-registry.test.mjs` (105 lines) — Model capabilities resolution
-  - `observability-payloads.test.mjs` (165 lines) — Health/telemetry payload construction
-  - `openapi-spec-route.test.mjs` — OpenAPI spec generation
-  - `proxy-e2e-mode.test.mjs` (74 lines) — E2E mode auth bypass
-  - `quota-monitor.test.mjs` — Quota monitor lifecycle state
-  - `run-next-playwright.test.mjs` (119 lines) — Playwright runner script
-  - `sse-auth.test.mjs` (154 lines) — P2C credential selection and quota preflight
-  - `telemetry-summary-route.test.mjs` (35 lines) — Telemetry summary endpoint
-  - Plus updates to 12 existing test files for compatibility with new step architecture
-- **Auto-Combo Unification Tests:**
-  - `autocombo-unification.test.mjs` (156 lines) — Strategy categorization, schema deduplication, sidebar cleanup, and routing strategies metadata validation
-  - `combo-unification.spec.ts` (189 lines) — Playwright E2E tests for filter tabs, intelligent panel rendering, redirect from old route, sidebar entry removal, and Builder v2 intelligent step flow
-  - 3 new LKGP standalone tests in `combo-routing-engine.test.mjs` — Validates LKGP provider prioritization, fallback to priority when no state exists, and LKGP state persistence after successful requests
-  - Updated `combo-builder-draft.test.mjs` with intelligent stage navigation tests
-  - Updated `sidebar-visibility.test.mjs` to reflect `auto-combo` removal
-
----
-
-## [3.6.3] — 2026-04-11
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **OpenAI-Compatible Loose Validation:** Empty API keys can now be naturally submitted and saved for any `openai-compatible-*` providers (e.g. Pollinations, localized routes) directly in the UI instead of blocking save actions (#1152)
-- **Cloudflare Configuration:** Updated the provider schema and UI integration for Cloudflare AI to officially expose and support the backend `accountId` field securely without overrides (#1150)
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Vertex JSON Validation Crash:** Prevented `invalid character in header` crashes inside the `/validate` endpoint by creating a native authentication parser that correctly handles Google Identity Service Account JSON flows prior to pinging endpoints (#1153)
-- **Extraneous Payload Rejection:** Globally prevented upstream `400 Bad Request` execution crashes by stripping the non-standard `prompt_cache_retention` attribute forcibly attached by Cursor/Cline IDE engines when targeting strict OpenAI/Anthropic routes (#1154)
-- **Reasoning Content Drop:** Prevented pure reasoning packets, common in advanced fallback models like DeepSeek, from being aborted mid-stream by explicitly adjusting the `Empty Content (502)` circuit breakers to acknowledge `reasoning_content` states as valid (#1155)
-- **Desktop Windows Build Crash:** Fixed `better_sqlite3.node is not a valid Win32 application` preventing OmniRoute Desktop from launching on Windows by properly removing the ABI-mismatched sqlite cache from Next.js standalone and falling back to the cross-compiled Electron equivalent during packager build steps (#1163)
-- **Login Visual Security:** Removed the raw fallback hash dump that artificially rendered underneath the login modal in Docker instances missing `OMNIROUTE_API_KEY_BASE64` flags (#1148)
-
-### 🔧 Maintenance & Dependencies
-
-- **Dependabot Updates:** Safely bumped GitHub Actions `docker/build-push-action` to v7 and `actions/download-artifact` to v8
-- **Electron Updates:** Upgraded desktop wrapper core to Electron `41.2.0` and `electron-builder` to `26.8.1`, incorporating essential V8/Chromium security patches
-- **NPM Package Groups:** Updated `production` and `development` NPM groups to securely handle minor audit warnings and keep toolchains modern
-- **CI/CD Reliability:** Fixed persistent `Snyk` token-absence failures on automated pull requests by appropriately bypassing on dependabot actions
-
-## [3.6.2] — 2026-04-11
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **33 New API Key Providers:** Massive provider expansion adding DeepInfra, Vercel AI Gateway, Lambda AI, SambaNova, nScale, OVHcloud AI, Baseten, PublicAI, Moonshot AI, Meta Llama API, v0 (Vercel), Morph, Featherless AI, FriendliAI, LlamaGate, Galadriel, Weights & Biases Inference, Volcengine, AI21 Labs, Venice.ai, Codestral, Upstage, Maritalk, Xiaomi MiMo, Inference.net, NanoGPT, Predibase, Bytez, Heroku AI, Databricks, Snowflake Cortex, and GigaChat (Sber). OmniRoute now supports **100+ providers** (4 Free + 8 OAuth + 91 API Key + Custom compatible)
-- **Global Email Privacy Toggle:** Added a persistent eye-icon toggle button across all dashboard pages (Providers, Usage Limits, Playground) that reveals or hides masked email addresses. Toggle state is stored in localStorage and synced globally via Zustand store
-- **Documentation Refresh:** Updated README, ARCHITECTURE, FEATURES, AGENTS.md, and API_REFERENCE for v3.6.2 with accurate provider counts (100+), new executor list, and system API documentation
-- **Uninstall Guide:** Created comprehensive `docs/guides/UNINSTALL.md` covering clean uninstallation for all deployment methods (npm, Docker, Electron, source)
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **PDF Attachments:** Unlocked deep string object parsing (`geminiHelper`) ensuring Gemini translation successfully passes complex PDF payloads from OpenAI-compatible streams without dropping them silently (#993)
-- **SkillsMP Engine:** Corrected object extraction path mappings inside the API router to fix UI marketplace rendering under Docker/Standalone Node isolated deployments (#988)
-
----
-
-## [3.6.1] — 2026-04-10
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **OAuth Env Repair Action:** Added a "Repair env" button to the OAuth Providers dashboard that detects and restores missing OAuth client IDs from `.env.example` — with timestamped backup and append-only safety. Includes full 33-language i18n support and sanitized API responses (#1116, by @yart)
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **i18n: Missing Provider Keys:** Added missing `filterModels`, `modelsActive`, `showModel`, `hideModel` keys across all 32 locale files, fixing runtime `MISSING_MESSAGE` errors in the providers UI. Also cleaned up duplicate keys in `en.json` (#1111, by @rilham97)
-- **GPT-5.4 Routing:** Added missing `targetFormat: "openai-responses"` to `gpt-5.4` and `gpt-5.4-mini` models in both the Codex and GitHub Copilot providers, fixing `[400]: model not accessible via /chat/completions` errors (#1114, by @ask33r)
-
----
-
-## [3.6.0] — 2026-04-10
-
-### ✨ New Features & Analytics
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Combo Smoke Test:** Raised the default token budget to 2048 to prevent truncation of thinking models during preflight checks, and fully randomized the arithmetic probe prompt to bypass deterministic caching from upstream relays (#1105)
-
-### 🐛 Bug Fixes & Compliance
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **DB Bloat / Row Limits:** Added `CALL_LOGS_TABLE_MAX_ROWS` and `PROXY_LOGS_TABLE_MAX_ROWS` (default: 100,000) to the backend DB compliance cleaner to prevent runaway SQLite growth. Limits are enforced automatically on the TTL cycle (#1104, fixes #1101)
-- **HTML Error Handling:** The router now correctly identifies unexpected HTML responses (e.g. `<!DOCTYPE html>`) sent by upstream providers (like Azure/Copilot) instead of throwing obscure `Unexpected token '<'` JSON parse errors, bubbling up a clean 502 Bad Gateway (#1104, fixes #1066)
-- **Android/Termux SQLite Native Support:** `better-sqlite3` is now correctly built from source with cross-compilation flags in ARM64 local Termux deployments without failing on missing prebuilt binaries (#1107)
-
----
-
-## [3.5.9] — 2026-04-09
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Persistent Combo Ordering:** Drag combo cards by handle to reorder them in the dashboard; order is persisted to SQLite via a new `sort_order` column and `POST /api/combos/reorder` endpoint. Includes DB migration `020_combo_sort_order.sql` and JSON import preservation (#1095)
-- **Sidebar Group Reorder:** Moved "Logs" before "Health" in the System section and "Limits & Quotas" after "Cache" in the Primary section for a more logical navigation flow (#1095)
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Stream Failure Surfacing:** Upstream `response.failed` events (e.g. Codex rate-limit errors) are now properly surfaced as non-200 errors instead of being silently swallowed as empty 200 OK streams. Rate-limit failures return HTTP 429 (#1098, closes #1093)
-- **Upstream Model Preservation:** The Responses-to-OpenAI stream translator now preserves the actual upstream model (e.g. `gpt-5.4`) instead of hardcoding a `gpt-4` fallback (#1098, closes #1094)
-- **Docker EXDEV Fix:** `build-next-isolated.mjs` now falls back from `fs.rename()` to `cp/rm` when Docker buildx raises `EXDEV` (cross-device link), unblocking the Docker image publish workflow (#1097)
-- **macOS CLI Path Resolution:** `cliRuntime.ts` resolves symlink parents with `fs.realpath()` to handle macOS `/var` → `/private/var` chains, preventing false `symlink_escape` rejections (#1097)
-- **Request Log Token Layout:** Split token badges into separate Input (Total In, Cache Read, Cache Write) and Output (Total Out, Reasoning) groups for clearer readability; renamed "Time" label to "Completed Time" (#1096)
-
----
-
-## [3.5.8] — 2026-04-09
-
-### ✨ New Features & Analytics
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Analytics Layout Redesign:** Replaced flat metrics with a responsive `CompactStatGrid`, grouping data visually across sections (#1089)
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Build Core:** Force Turbopack cleanup via Prepbulish script to prevent Next.js 16 app/ routing conflicts on runtime.
-- **Provider Quarantine:** Introduces model/provider circuit-breakers with adaptive TTL exponential backoff for recurring upstream errors (#1090)
-- **Oauth Keep-Alive:** Safely protects authenticated active accounts against spontaneous dropping from router due to transient token refresh failures (#1085)
-
-### 🔒 Security & Maintenance
-
-- **Dependabot:** bumped axios from 1.14.0 to 1.15.0 addressing SSRF flags (#1088)
-
----
-
-## [3.5.7] — 2026-04-09
-
-### 🐛 Bug Fixes & Security
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Turbopack Standalone Chunks:** Fixed a critical bug in `scripts/prepublish.mjs` where Turbopack chunks missing from the `.next/standalone` trace resulted in a `500 ChunkLoadError` (e.g., `_not-found` page crash) during production deployments via NPM or Docker. Standalone chunks are now explicitly copied and correctly stripped of Turbopack hashes.
-
----
-
-## [3.5.6] — 2026-04-09
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Email Privacy Masking:** OAuth account emails are now masked in the provider dashboard (e.g. `di*****@g****.com`) to prevent accidental exposure when sharing screenshots. Full address visible on hover via `title` attribute (#1025).
-- **OpenRouter & GitHub in Embedding/Image Registries:** OpenRouter (3 embedding models, 4 image models) and GitHub Models (2 embedding models via Azure inference) are now first-class entries in the provider registries, enabling their use for `/v1/embeddings` and `/v1/images/generations` (#960).
-- **Model Visibility Toggle & Search Filter:** The provider page model list now includes a real-time search/filter bar and a per-model visibility toggle (👁 icon). Hidden models are grayed out and excluded from the `/v1/models` catalog. An active-count badge (`N/M active`) shows at a glance how many models are enabled (#750).
-- **Chinese Localization (zh-CN):** Added missing translations for Context Relay, Memory, LKGP, and Models.dev sync features, while standardizing terminology across the application (#1079).
-- **Environment Auto-Sync:** Added `sync-env.mjs` to auto-generate and append `.env` from `.env.example` during installation, automatically generating cryptographic secrets on first run.
-- **Source Mode Dashboard Update:** Fixed real-time Source (git-checkout) updating in the dashboard, enabling secure, real-time update pipelines for non-NPM installations.
-
-### 🐛 Bug Fixes & Security
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Hardcoded Secret Cleanup:** Removed 12 hardcoded OAuth credential fallbacks from the source code, forcing secure reliance on environment variables and resolving static analysis security alerts.
-- **Next.js Security Patch:** Bumped `next` from 16.2.2 to 16.2.3 to resolve critical RSC deserialization RCE vulnerability (SNYK-JS-NEXT-15954202).
-- **Memory/Cache UI Crash:** Added null-safety guards (`?? 0`) to `.toLocaleString()` calls in Memory and Cache dashboard pages, preventing `TypeError` crashes when database tables are empty or contain null numeric values (#1083).
-- **WebSearch tool_choice Translation:** Fixed OpenAI-to-Claude translator dropping `tool_choice` objects with `type: "function"` as-is, which Claude rejects. Now properly maps all OpenAI `tool_choice` variants (`function`, `required`, `none`) to Claude-compatible format (`tool`, `any`, `auto`), fixing "Did 0 searches" in Claude Code WebSearch (#1072).
-- **Provider Validation baseUrl Override:** Added `baseUrl` passthrough from frontend validation requests to the backend validation endpoint. Chinese-site users of Alibaba Coding Plan (bailian-coding-plan) can now validate API keys against their custom Base URL instead of always hitting the international endpoint (#1078).
-- **Minimax Auth Header:** Switched Minimax provider from `x-api-key` to `Authorization: Bearer` header format, matching the current API spec (#1076).
-- **Native Fetch Fallback:** Added graceful fallback to native `fetch` when the `undici` dispatcher fails, improving resilience in environments where undici is unavailable (#1054).
-- **EPIPE Flood Fix:** Added circuit-breaker logic to prevent EPIPE errors from creating a feedback loop that fills logs at GB/s (#1006).
-- **Qoder PAT Validation:** Improved Qoder Personal Access Token validation with actionable error messages that guide users to the correct token format (#966).
-- **CI/CD Pipeline:** Fixed `check:docs-sync` failure by syncing OpenAPI version to 3.5.6 and finalizing CHANGELOG release heading. Commented out `DATA_DIR` in `.env.example` to prevent E2E test failures in CI runners lacking root permissions.
-
-### 🌍 i18n
-
-- **Auto Language Generation (CI):** Added CI pipeline to auto-generate missing language files and strings via `feat(CI,i18n)` workflow, covering 30+ locales (#1071).
-
----
-
-## [3.5.5] — 2026-04-08
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Node.js 24 Compatibility Warning:** Added a proactive version incompatibility warning on the login page to guide users to the stable Node.js 22 LTS, preventing native sqlite binding crashes.
-- **Context Relay Combo Strategy:** Added the new `context-relay` combo strategy with priority-style routing, structured handoff summary generation once quota usage reaches the warning threshold, and handoff injection after the next real account switch.
-- **Global Context Relay Defaults:** Added global Settings defaults plus combo-level configuration for `handoffThreshold`, `handoffModel`, and `handoffProviders`, so new or unconfigured combos can inherit the feature consistently.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Proxy Connection Healthchecks:** Applied proxy resolution per connection in the sweeping loop (`tokenHealthCheck.ts`) and global provider validation sweeps, resolving Node 22 bypass and improving proxy stability (#1051, #1056, #1061).
-- **Security Vulnerability Remediation:** Resolved multiple CodeQL scanning alerts including SSRF in model sync, insecure randomness in web crypto (`generateSessionId`), and incomplete URL sanitization.
-- **Context Relay Typing & Synchronization:** Reverted out-of-scope test breakages and resolved `handoffProvider` and response `input` extraction payload typing.
-- **Legacy OpenAI-Compatible Responses Routing:** Fixed legacy/imported OpenAI-compatible providers (for example `openai-compatible-sp-openai`) incorrectly routing Chat Completions traffic to `/chat/completions` when the real provider node was configured as `apiType: "responses"`. OmniRoute now treats `providerSpecificData.apiType` as authoritative across routing, executors, and translator tools, avoiding false empty-content failures during combo/provider smoke tests (#1069).
-- **Gemini PDF Attachment Integration:** Fixed payload generation and format for parsing `inline_data` and generic base64 sources for deep Gemini PDF routing (#993, #1021).
-- **Vercel AI SDK Fallbacks:** Mapped `max_output_tokens` to `max_tokens` for strict OpenAI-compatible providers, resolving errors from standard AI agents and frameworks (#994).
-- **External Auth & UI Reliability:** Handled null `state` failures in Cline OAuth exchange (#1016), added 3rd-party 400 error patterns to combo fallback (#1024), and resolved desktop sidebar layout and popover overflows (#1039, #1001).
-- **Context Relay In-Flight Deduplication:** Prevented duplicate handoff generation for the same session/combo while an earlier summary request is still in flight.
-- **Context Relay Provider Gating:** Aligned runtime behavior with configuration so explicit `handoffProviders` exclusions, including an empty array, now disable handoff generation as expected.
-
-### 🛠️ Maintenance & Dependabot
-
-- **Updated Sub-dependencies:** Bumped `hono` to `4.12.12` and `@hono/node-server` to `1.19.13` to patch critical security gaps (#1063, #1064, #1067, #1068).
-
-### 📚 Documentation
-
-- **Documentation Synchronization:** Updated system documentation (README, Architecture, Features, Tools, Troubleshooting) and synced `i18n` configurations to match the v3.5.5 context relay patterns and proxy troubleshooting steps.
-- **Context Relay Delivery Notes:** Documented the current architecture, runtime flow, and Codex-focused scope in the feature docs, changelog, and agent guidance.
-
----
-
-## [3.5.4] — 2026-04-07
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Detailed Token Tracking:** Added granular token breakdown columns (cache read, cache write, reasoning) to call logs with proper null vs zero distinction. Includes DB migration 018 and 5-label UI display per provider capability (#1017 — thanks @rdself).
-- **Legacy JSON Config Import/Export:** Restored JSON-based settings export and import for migration from legacy configurations. Security-hardened with Zero-Trust redaction of passwords and `requireLogin` fields, and automatic pre-import database backups (#1012 — thanks @luandiasrj).
-- **Non-Stream Aliases:** Added API support for explicit non-streaming aliases (`non_stream`, `disable_stream`, `disable_streaming`, `streaming=false`), normalized at the boundary before provider translation (#1036 — thanks @wlfonseca).
-- **Russian Dashboard Localization:** Comprehensive Russian translation for the dashboard UI, including fixes for 2 Ukrainian locale keys (#1003 — thanks @mercs2910).
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Anthropic Streaming Input Undercount:** Fixed a critical bug where Anthropic streaming `prompt_tokens` only reported non-cached tokens (e.g., `in=3` when actual total was 113,616). Cache tokens are now summed into prompt_tokens during streaming (#1017).
-- **Built-in Responses API Tool Types:** Preserved built-in Responses API tools (`web_search`, `file_search`, `computer`, `code_interpreter`, `image_generation`) from being silently stripped by the empty-name tool filter — these tools carry no `.name` field (#1014 — thanks @rdself).
-- **Cursor/Codex Responses Compatibility:** Fixed empty output in Cursor when using Codex models by hoisting system input items to `instructions`, sanitizing invalid tool names, and detecting Responses-format payloads on chat/completions endpoint (#1002 — thanks @mercs2910).
-- **OAuth Token Expiry Display:** Fixed OAuth connections showing "expired" badge even with valid tokens by reading `tokenExpiresAt` (updated on refresh) instead of `expiresAt` (original grant timestamp) (#1032 — thanks @tombii).
-- **Codex Fast-Tier Copy:** Corrected dashboard settings copy from `service_tier=fast` to `service_tier=priority`, matching the actual Codex wire format (#1045 — thanks @kfiramar).
-- **macOS Desktop App Startup:** Stabilized packaged macOS app launch by excluding desktop artifacts from the standalone bundle and improving launch path detection (#1004 — thanks @mercs2910).
-- **macOS Sidebar Layout:** Fixed macOS traffic light overlap, sidebar spacing, and button overflow in the Electron desktop app (#1001 — thanks @mercs2910).
-
-### ⚡ Performance
-
-- **Analytics Page Load:** Dramatically reduced analytics page load times (30s→1-2s for 50K entries) via date-filtered DB queries, parallel `Promise.all()` cost calculations, and merged 6 COUNT queries into a single CASE WHEN aggregate (#1038 — thanks @oyi77).
-
-### 🔒 Security & Dependencies
-
-- **Node Base Image:** Upgraded Docker base from `22-bookworm-slim` to `22.22.2-trixie-slim` (#1011 — Snyk).
-- **Production Dependencies:** Bumped 5 production dependencies (#1044 — Dependabot).
-- **Vite:** Bumped from 8.0.3 to 8.0.5 (#1031 — Dependabot).
-- **Development Dependencies:** Bumped 4 development dependencies (#1030 — Dependabot).
-
-### 🧪 Tests
-
-- **Token Accounting Tests:** Added 18 new unit tests covering detailed token breakdown, null vs zero semantics, per-provider token extraction, and Anthropic streaming input fix (#1017).
-- **Built-in Tool Tests:** Added 3 new test cases for built-in Responses API tool type preservation (#1014).
-- **ChatCore Sanitization:** Updated sanitization tests to accommodate Responses format detection (PR #1002) and built-in tool preservation (PR #1014).
-
-### 🛠️ Maintenance
-
-- **PR Workflow:** Updated `/review-prs` workflow to merge PRs into the release branch (`release/vX.Y.Z`) instead of directly into `main`, ensuring proper pre-release staging.
-
-### Coverage
-
-- **2537 tests, 2532 passing** — Statement coverage: 91.95%, Branch coverage: 78.79%, Function coverage: 93.19%
-
-## [3.5.3] - 2026-04-07
-
-### Security
-
-- **Vulnerabilities:** Fully remediated 12 High-Severity CodeQL vulnerabilities by migrating from Math.random to `crypto.randomUUID()`, wrapping SSE injection points with aggressive backslash escaping, sanitizing trailing HTTP fragments, and enforcing rigid SSRF HTTP verification schemes across internal routes.
-- **Dependencies:** Upgraded Next.js to `^16.2.2` and Vite to `>=8.0.5` resolving critical DoS, arbitrary file reads and CSRF vectors in the build/server environments.
-
-### Fixed
-
-- **E2E Stability:** Eliminated extreme CI unreliability and transient test timeouts (Playwright) by propagating internal standalone `_next/static` assets properly and refactoring deep UI interactions inside defensive `expect().toPass()` loops.
-- **Middleware:** Resolved infinite redirect loop on dashboard for fresh instances when requireLogin is disabled.
-- **Core Fallbacks:** Preserved primary failure contexts and enhanced Edge-case error handling pipelines across chat and fallback loops.
-- **Proxy/Hooks:** Optimized local git hooks, normalized token coverage endpoints into `/coverage`, and guarded GLM region lookups.
-
-### 🛠️ Maintenance
-
-- **CI/CD Stabilization:** Prevented random GitHub Runner freezes by decoupling sharded processes, adjusting test concurrencies, unref-ing active connections on server teardown, and strictly capping job timeout durations.
-
-### Documentation
-
-- **I18n Engine:** Synchronized and pushed deep Machine Translation updates across all 32 natively-supported languages (682 translation nodes aligned).
-
-### Coverage
-
-- **Testing:** Consolidated the workspace test coverage framework hitting 92.1% statement line coverage, with new rigid unit-tests matching API key policies and tool scopes.
-
----
-
-## [3.5.2] — 2026-04-05
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Qoder API Native Integration:** Completely refactored the Qoder Executor to bypass the legacy COSY AES/RSA encryption algorithm, routing directly into the native DashScope OpenAi-compatible URL. Eliminates complex dependencies on Node `crypto` modules while improving stream fidelity.
-- **Resilience Engine Overhaul:** Integrated context overflow graceful fallbacks, proactive OAuth token detection, and empty-content emission prevention (#990).
-- **Context-Optimized Routing Strategy:** Added new intelligent routing capability to natively maximize context windows in automated combo deployments (#990).
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Responses API Stream Corruption:** Fixed deep-cloning corruption where Anthropic/OpenAI translation boundaries stripped `response.` specific SSE prefixes from streaming boundaries (#992).
-- **Claude Cache Passthrough Alignment:** Aligned CC-Compatible cache markers consistently with upstream Client Pass-Through mode preserving prompt caching.
-- **Turbopack Memory Leak:** Pinned Next.js to strict `16.0.10` preventing memory leaks and build staleness from recent upstream Turbopack hashed module regressions (#987).
-
----
-
-## [3.5.1] — 2026-04-04
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Models.dev Integration:** Integrated models.dev as the authoritative runtime source for model pricing, capabilities, and specifications, overriding hardcoded prices. Includes a settings UI to manage sync intervals, translation strings for all 30 languages, and robust test coverage.
-- **Provider Native Capabilities:** Added support for declaring and checking native API features (e.g. `systemInstructions_supported`) preventing failures by sanitizing invalid roles. Currently configured for Gemini Base and Antigravity OAuth providers.
-- **API Provider Advanced Settings:** Added per-connection custom `User-Agent` overrides for API-key provider connections. The override is stored in `providerSpecificData.customUserAgent` and now applies to validation probes and upstream execution requests.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Qwen OAuth Reliability:** Resolved a series of OAuth integration issues including a 400 Bad Request blocker on expired tokens, fallback generation for parsing OIDC `access_token` properties when `id_token` is omitted, model catalog discovery errors, and strict filtering of `X-Dashscope-*` headers to avoid 400 rejection from OpenAI-compatible endpoints.
-
-## [3.5.0] — 2026-04-03
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Auto-Combo & Routing:** Completed native CRUD lifecycle integration for the advanced Auto-Combo engine (#955).
-- **Core Operations:** Fixed missing translations for new native Auto-Combos options (#955).
-- **Security Validation:** Disabled SQLite auto-backup tasks natively during unit test CI execution to explicitly resolve Node 22 Event Loop hanging memory leaks (#956).
-- **Ecosystem Proxies:** Completed explicit integration mapping model synchronization schedulers, OAuth cycles, and Token Check refreshes safely through OmniRoute's native system upstream proxies (#953).
-- **MCP Extensibility:** Added and successfully registered the new `omniroute_web_search` MCP framework tool out of beta into production schemas (#951).
-- **Tokens Buffer Logic:** Added runtime configuration limits extending configurable input/output token buffers for precise Usage Tracking metrics (#959).
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **CodeQL Remediation:** Fully resolved and secured critical string indexing operations preventing Server-Side Request Forgery (SSRF) arrays indexing heuristics alongside polynomial algorithmic backtracking (ReDoS) inside deep proxy dispatcher modules.
-- **Crypto Hashes:** Replaced weak unverified legacy OAuth 1.0 hashes with robust HMAC-SHA-256 standard validation primitives ensuring tight access controls.
-- **API Boundary Protection:** Correctly verified and mapped structural route protections enforcing strict `isAuthenticated()` middleware logic covering newer dynamic endpoints targeting settings manipulation and native skills loading.
-- **CLI Ecosystem Compat:** Resolved broken native runtime parser bindings crashing `where` environment detectors strictly over `.cmd/.exe` edge cases gracefully for external plugins (#969).
-- **Cache Architecture:** Refactored exact Analytics and System Settings dashboard parameters layout structure caching to maintain stable re-hydration persistence cycles resolving visual unaligned state flashes (#952).
-- **Claude Caching Standards:** Normalized and accurately strictly preserved critical ephemeral block markers `ephemeral` caching TTL orders for downstream nodes enforcing standard compatible CC requests mapping cleanly without dropped metrics (#948).
-- **Internal Aliases Auth:** Simplified internal runtime mappings normalizing Codex credential payload lookups inside global translation parameters resolving 401 unauthenticated drops (#958).
-
-### 🛠️ Maintenance
-
-- **UI Discoverability:** Correctly adjusted layout categorizations explicitly separating free tier providers logic improving UX sorting flows inside the general API registry pages (#950).
-- **Deployment Topology:** Unified Docker deployment artifacts ensuring the root `fly.toml` matches expected cloud instance parameters out-of-the-box natively handling automated deployments scaling properly.
-- **Development Tooling:** Decoupled `LKGP` runtime parameters into explicit DB layer abstraction caching utilities ensuring strict test isolation coverage for core caching layers safely.
-
----
-
-## [3.4.9] — 2026-04-03
-
-### Features & Refactoring
-
-- **Dashboard Auto-Combo Panel:** Completely refactored the `/dashboard/auto-combo` UI to seamlessly integrate with native Dashboard Cards and standardized visual padding/headers. Added dynamic visual progress bars mapping model selection weight mechanisms.
-- **Settings Routing Sync:** Fully exposed advanced routing `priority` and `weighted` schema targets internally inside global settings fallback lists.
-
-### Bug Fixes
-
-- **Memory & Skills Locale Nodes:** Resolved empty rendering tags for Memory and Skills options directly inside global settings views by wiring all `settings.*` mapping values internally into `en.json` (also mapped implicitly for cross-translation tools).
-
-### Internal Integrations
-
-- Integrated PR #946 — fix: preserve Claude Code compatibility in responses conversion
-- Integrated PR #944 — fix(gemini): preserve thought signatures across antigravity tool calls
-- Integrated PR #943 — fix: restore GitHub Copilot body
-- Integrated PR #942 — Fix cc-compatible cache markers
-- Integrated PR #941 — refactor(auth): improve NVIDIA alias lookup + add LKGP error logging
-- Integrated PR #939 — Restore Claude OAuth localhost callback handling
-- _(Note: PR #934 was omitted from 3.4.9 cycle to prevent core conflict regressions)_
-
----
-
-## [3.4.8] — 2026-04-03
-
-### Security
-
-- Fully remediated all outstanding Github Advanced Security (CodeQL) findings and Dependabot alerts.
-- Fixed insecure randomness vulnerabilities by migrating from `Math.random` to `crypto.randomUUID()`.
-- Secured shell commands in automated scripts from string injection.
-- Migrated vulnerable catastrophic backtracking RegEx parsing patterns in chat/translation pipelines.
-- Enhanced output sanitization controls inside React UI components and Server Sent Events (SSE) tag injection.
-
----
-
-## [3.4.7] — 2026-04-03
-
-### Features
-
-- Added `Cryptography` node to Monitoring and MCP health checks (#798)
-- Hardened model-catalog route permissions mapping (`/models`) (#781)
-
-### Bug Fixes
-
-- Fixed Claude OAuth token refreshes failing to preserve cache contexts (#937)
-- Fixed CC-Compatible provider errors rendering cached models unreachable (#937)
-- Fixed GitHub Executor errors related to invalid context arrays (#937)
-- Fixed NPM-installed CLI tools healthcheck failures on Windows (#935)
-- Fixed payload translation dropping valid content due to invalid API fields (#927)
-- Fixed runtime crash in Node 25 regarding API key execution (#867)
-- Fixed MCP standalone module-resolution (`ERR_MODULE_NOT_FOUND`) via `esbuild` (#936)
-- Fixed NVIDIA NIM routing credential resolution alias mismatch (#931)
-
-### Security
-
-- Added safe strict input boundary protection against raw `shell: true` remote-code execution injections.
-
----
-
-## [3.4.6] - 2026-04-02
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Providers:** Registered new image, video, and audio generation providers from the community-requested list (#926).
-- **Dashboard UI:** Added standalone sidebar navigation for the new Memory and Skills modules (#926).
-- **i18n:** Added translation strings and layout mappings across 30 languages for the Memory and Skills namespaces.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Resilience:** Prevented the proxy Circuit Breaker from becoming stuck in an OPEN state indefinitely by handling direct transitions to CLOSED state inside fallback combo paths (#930).
-- **Protocol Translation:** Patched the streaming transformer to sanitize response blocks based on the expected _source_ protocol rather than the provider _target_ protocol, fixing Anthropics models wrapped in OpenAI payloads crashing Claude Code (#929).
-- **API Specs & Gemini:** Fixed `thought_signature` parsing in `openai-to-gemini` and `claude-to-gemini` translators, preventing HTTP 400 errors across all Gemini 3 API tool-calls.
-- **Providers:** Cleaned up non-OpenAI-compatible endpoints preventing valid upstream connections (#926).
-- **Cache Trends:** Fixed an invalid property mapping data mismatch causing Cache Trends UI charts to crash, and extracted redundant cache metric widgets (#926).
-
----
-
-## [3.4.5] - 2026-04-02
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **CLIProxyAPI Ecosystem Integration:** Added the `cliproxyapi` executor with built-in module-level caching and proxy routing. Introduced a comprehensive Version Manager service to automatically test health, download binaries from GitHub, spawn isolated background processes, and cleanly manage the lifecycle of external CLI tools directly through the UI. Includes DB tables for proxy configuration to enable automatic SSRF-gated cross-routing of external OpenAI requests via the local CLI tool layer (#914, #915, #916).
-- **Qoder PAT Support:** Integrated Personal Access Tokens (PAT) support directly via the local `qodercli` transport instead of legacy remote `.cn` browser configurations (#913).
-- **Gemini 3.1 Pro Preview (GitHub):** Added `gemini-3.1-pro-preview` canonical explicit model support natively into the GitHub Copilot provider while preserving older routing aliases (#924).
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **GitHub Copilot Token Stability:** Repaired the Copilot token refresh loop where stale tokens weren't deep-merged into DB, and removed `reasoning_text` fields that were fatally breaking downstream Anthropic block conversions for multi-turn chats (#923).
-- **Global Timeout Matrix:** Centralized and parameterized request timeouts explicitly from `REQUEST_TIMEOUT_MS` to prevent hidden (~300s) default fetch buffers prematurely cutting off long-lived SSE streaming responses from heavy reasoning models (#918).
-- **Cloudflare Quick Tunnels State:** Fixed a severe state inconsistency where restarted OmniRoute instances erroneously showed destroyed tunnels as active, and defaulted cloudflared tunneling to `HTTP/2` to eliminate UDP receive buffer log spam (#925).
-- **i18n Translation Overhaul (Czech & Hindi):** Fixed Hindi code from DEPRECATED `in.json` to canonical `hi.json`, overhauled Czech text mappings, extracted `untranslatable-keys.json` to fix CI/CD false-positive validations, and generated comprehensive `I18N.md` docs to guide translators (#912).
-- **Tokens Provider Recovery:** Fixed Qwen losing specific `resourceUrl` endpoints after automatic health-check token refreshes because of missing DB deep merges (#917).
-- **CC Compatible UX & Streaming:** Unified the Add CC/OpenAI/Anthropic compatible actions around the Anthropic UI treatment, forced CC-compatible upstream requests to use SSE while still returning streaming or non-streaming responses based on the client request, removed CC model-list configuration/import support in favor of an explicit unsupported-model-listing error, and made CC-compatible Available Models mirror the OAuth Claude Code registry list (#921).
-
----
-
-## [3.4.4] - 2026-04-02
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Responses API Token Reporting:** Emit `response.completed` with correct `input_tokens`/`output_tokens` fields for Codex CLI clients, fixing token usage display (#909 — thanks @christopher-s).
-- **SQLite WAL Checkpoint on Shutdown:** Flush WAL changes into the primary database file during graceful shutdown/restart, preventing data loss on Docker container stops (#905 — thanks @rdself).
-- **Graceful Shutdown Signal:** Changed `/api/restart` and `/api/shutdown` routes from `process.exit(0)` to `process.kill(SIGTERM)`, ensuring the shutdown handler runs before exit.
-- **Docker Stop Grace Period:** Added `stop_grace_period: 40s` to Docker Compose files and `--stop-timeout 40` to Docker run examples.
-
-### 🛠️ Maintenance
-
-- Closed 5 resolved/not-a-bug issues (#872, #814, #816, #890, #877).
-- Triaged 6 issues with needs-info requests (#892, #887, #886, #865, #895, #870).
-- Responded to CLI detection tracking issue (#863) with contributor guidance.
-
----
-
-## [3.4.3] - 2026-04-02
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Antigravity Memory & Skills:** Completed remote memory and skills injection for the Antigravity provider at the proxy network level.
-- **Claude Code Compatibility:** Built a natively hidden compatibility bridge for Claude Code, passing tools and formatting through cleanly.
-- **Web Search MCP:** Added the `omniroute_web_search` tool with the `execute:search` scope.
-- **Cache Components:** Implemented dynamic cache components utilizing TDD.
-- **UI & Customization:** Added custom favicon support, appearance tabs, wired whitelabeling to the sidebar, and added Windsurf guide steps across all 33 languages.
-- **Log Retention:** Unified request log retention and artifacts natively.
-- **Model Enhancements:** Added explicit `contextLength` for all opencode-zen models.
-- **i18n & translations:** Integrated 33 language translations natively, including placeholder CI validations and Chinese documentation updates (#873, #869).
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Qwen OAuth Mapping:** Reverted `id_token` reliance to `access_token` and enabled dynamic `resource_url` API endpoint injection for proper regional routing (#900).
-- **Model Sync Engine:** Stored the strict internal Provider ID in `getCustomModels()` sync routines instead of the UI Channel Alias format, preventing SQLite catalog insertion failures (#903).
-- **Claude Code & Codex:** Standardized non-streaming blank responses to Anthropic-formatted `(empty response)` to prevent CLI proxy crashes (#866).
-- **CC Compatible Routing:** Resolved duplicate `/v1` endpoint collision during path concatenation for generic Claude Code gateways (#904).
-- **Antigravity Dashboards:** Blocked unlimited quota models from falsely registering as exhausted `100% Usage` limit states in the Provider Usage UI (#857).
-- **Claude Image Passthrough:** Fixed Claude models missing image block passthroughs (#898).
-- **Gemini CLI Routing:** Resolved 403 authorization lockouts and content accumulation issues by refreshing the project ID via `loadCodeAssist` (#868).
-- **Antigravity Stability:** Corrected model access lists, enforced 404 lockouts, fixed 429 cascades locking out standard connections, and capped `gemini-3.1-pro` output tokens (#885).
-- **Provider Sync Cadence:** Repaired the provider limits synchronization cadence via the internal scheduler (#888).
-- **Dashboard Optimization:** Resolved `/dashboard/limits` UI freezing when processing 70+ accounts via chunk parallelization (#784).
-- **SSRF Hardening:** Enforced strict SSRF IP range filtering and blocked the `::1` loopback interface.
-- **MIME Types:** Standardized `mime_type` to snake_case to match Gemini API specifications.
-- **CI Stabilization:** Fixed failing analytics/settings Playwright selectors and request assertions so GitHub Actions E2E runs pass reliably across localized UIs and switch-based controls.
-- **Deterministic Tests:** Removed date-sensitive quota fixtures from Copilot usage tests and aligned idempotency/model catalog tests with the merged runtime behavior.
-- **MCP Type Hardening:** Removed zero-budget explicit `any` regressions from the MCP server tool registration path.
-- **Model Sync Engine:** Bypassed destructive `replace` overrides when the provider's auto-sync yields an empty model list, maintaining stability for dynamic catalogs (#899).
-
-### 🛠️ Maintenance
-
-- **Pipeline Logging:** Refined pipeline logging artifacts and enforce retention caps (#880).
-- **AGENTS.md Overhaul:** Condensed from 297→153 lines. Added build/test/style guidelines, code workflows (Prettier, TypeScript, ESLint), and trimmed verbose tables (#882).
-- **Release Branch Integration:** Consolidated the active feature branches into `release/v3.4.2` on top of current `main` and validated the branch with lint, unit, coverage, build, and CI-mode E2E runs.
-- **Testing:** Added vitest configuration for component testing and Playwright specs for settings toggles.
-- **Doc Updates:** Expanded root readmes, translated chinese documents natively, and cleaned up obsolete files.
-
-## [3.4.1] - 2026-03-31
-
-> [!WARNING]
-> **BREAKING CHANGE: request logging, retention, and logging environment variables have been redesigned.**
-> On the first startup after upgrading, OmniRoute archives legacy request logs from `DATA_DIR/logs/`, legacy `DATA_DIR/call_logs/`, and `DATA_DIR/log.txt` into `DATA_DIR/log_archives/*.zip`, then removes the deprecated layout and switches to the new unified artifact format under `DATA_DIR/call_logs/`.
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **.ENV Migration Utility:** Included `scripts/migrate-env.mjs` to seamlessly migrate `<v3.3` configurations to `v3.4.x` strict security validation constraints (FASE-01), repairing startup crashes caused by short `JWT_SECRET` instances.
-- **Kiro AI Cache Optimization:** Implemented deterministic `conversationId` generation (uuidv5) to enable AWS Builder ID Prompt Caching properly across invocations (#814).
-- **Dashboard UI Restoration & Consolidation:** Resolved sidebar logic omitting the Debug section, and cleared Nextjs routing warnings by moving standalone `/dashboard/mcp` and `/dashboard/a2a` pages explicitly into embedded Endpoint Proxy UI components.
-- **Unified Request Log Artifacts:** Request logging now stores one SQLite index row plus one JSON artifact per request under `DATA_DIR/call_logs/`, with optional pipeline capture embedded in the same file.
-- **Language:** Improved the Chinese translation (#855)
-- **Opencode-Zen Models:** Added 4 free models to opencode-zen registry (#854)
-- **Tests:** Added unit and E2E tests for settings toggles and bug fixes (#850)
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **429 Quota Parsing:** Parsed long quota reset times from error bodies to honor correct backoffs and prevent rate-limited account bans (#859)
-- **Prompt Caching:** Preserved client `cache_control` headers for all Claude-protocol providers (like Minimax, GLM, and Bailian), correctly recognizing caching support (#856)
-- **Model Sync Logs:** Reduced log spam by recording `sync-models` only when the channel actually modifies the list (#853)
-- **Provider Quota & Token Parsing:** Switched Antigravity limits to use `retrieveUserQuota` natively and correctly mapped Claude token refresh payloads to URL-encoded forms (#862)
-- **Rate-Limiting Stability:** Universalized the 429 Retry-After parsing architecture to cap provider-induced cooldowns at 24 hours max (#862)
-- **Dashboard Limit Rendering:** Re-architected `/dashboard/limits` quota mapping to render immediately inside chunks, fixing a major UI freezing delay on accounts exceeding 70 active connections (#784)
-- **QWEN OAuth Authorization:** Mapped the OIDC `id_token` as the primary API Bearer token for Dashscope requests, fixing immediate 401 Unauthorized errors after connecting accounts or refreshing tokens (#864)
-- **ZAI API Stability:** Hardened Server-Sent Events compiler to gracefully fallback to empty strings when DeepSeek providers stream mathematically null content during reasoning phases (#871)
-- **Claude Code/Codex Translations:** Protected non-streaming payload conversions against empty responses from upstream Codex tools, avoiding catastrophic TypeErrors (#866)
-- **NVIDIA NIM Rendering:** Conditionally stripped identical provider prefixes dynamically pushed by audio models, eliminating duplicate `nim/nim` tag structures throwing 404 on the Media Playground (#872)
-
-### ⚠️ Breaking Changes
-
-- **Request Log Layout:** Removed the old multi-file `DATA_DIR/logs/` request log sessions and the `DATA_DIR/log.txt` summary file. New requests are written as single JSON artifacts in `DATA_DIR/call_logs/YYYY-MM-DD/`.
-- **Logging Environment Variables:** Replaced `LOG_*`, `ENABLE_REQUEST_LOGS`, `CALL_LOGS_MAX`, `CALL_LOG_PAYLOAD_MODE`, and `PROXY_LOG_MAX_ENTRIES` with the new `APP_LOG_*` and `CALL_LOG_RETENTION_DAYS` configuration model.
-- **Pipeline Toggle Setting:** Replaced the legacy `detailed_logs_enabled` setting with `call_log_pipeline_enabled`. New pipeline details are embedded inside the request artifact instead of being stored as separate `request_detail_logs` records.
-
-### 🛠️ Maintenance
-
-- **Legacy Request Log Upgrade Backup:** Upgrades now archive old `data/logs/`, legacy `data/call_logs/`, and `data/log.txt` layouts into `DATA_DIR/log_archives/*.zip` before removing the deprecated structure.
-- **Streaming Usage Persistence:** Streaming requests now write a single `usage_history` row on completion instead of emitting a duplicate in-progress usage row with empty status metadata.
-- **Logging Follow-up Cleanup:** Pipeline logs no longer capture `SOURCE REQUEST`, request artifact entries now honor `CALL_LOG_MAX_ENTRIES`, and application log archives now honor `APP_LOG_MAX_FILES`.
-
----
-
-## [3.4.0] - 2026-03-31
-
-### 🚀 Features
-
-- **Subscription Utilization Analytics:** Added quota snapshot time-series tracking, Provider Utilization and Combo Health tabs with recharts visualizations, and corresponding API endpoints (#847)
-- **SQLite Backup Control:** New `OMNIROUTE_DISABLE_AUTO_BACKUP` env flag to disable automatic SQLite backups (#846)
-- **Model Registry Update:** Injected `gpt-5.4-mini` into the Codex provider's array of models (#756)
-- **Provider Limit Tracking:** Track and display when provider rate limits were last refreshed per account (#843)
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Qwen Auth Routing:** Re-routed Qwen OAuth completions from the DashScope API to the Web Inference API (`chat.qwen.ai`), resolving authorization failures (#844, #807, #832)
-- **Qwen Auto-Retry Loop:** Added targeted 429 Quota Exceeded backoff handling inside `chatCore` protecting burst requests
-- **Codex OAuth Fallback:** Modern browser popup blocking no longer traps the user; it automatically falls back to manual URL entry (#808)
-- **Claude Token Refresh:** Anthropic's strict `application/json` boundaries are now respected during token generation instead of encoded URLs (#836)
-- **Codex Messages Schema:** Stripped purist `messages` injects from native passthrough requests to avoid structural rejections from the ChatGPT upstream (#806)
-- **CLI Detection Size Limit:** Safely bumped the Node binary scanning upper bound from 100MB to 350MB, allowing heavy standalone tools like Claude Code (229MB) and OpenCode (153MB) to be correctly detected by the VPS runtime (#809)
-- **CLI Runtime Environment:** Restored ability for CLI configurations to respect user override paths (`CLI_{PROVIDER}_BIN`) bypassing strict path-bound discovery rules
-- **Nvidia Header Conflicts:** Removed `prompt_cache_key` properties from upstream headers when calling non-Anthropic providers (#848)
-- **Codex Fast Tier Toggle:** Restored Codex service tier toggle contrast in light mode (#842)
-- **Test Infrastructure:** Updated `t28-model-catalog-updates` test that incorrectly expected the outdated DashScope endpoint for the Qwen native registry
-
----
-
-## [3.3.9] - 2026-03-31
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Custom Provider Rotation:** Integrated `getRotatingApiKey` internally inside DefaultExecutor, ensuring `extraApiKeys` rotation triggers correctly for custom and compatible upstream providers (#815)
-
----
-
-## [3.3.8] - 2026-03-30
-
-### 🚀 Features
-
-- **Models API Filtering:** Endpoint `/v1/models` now dynamically filters its list based on the permissions tied to the `Authorization: Bearer <token>` when restricted access is on (#781)
-- **Qoder Integration:** Native integration for Qoder AI natively replacing the legacy iFlow platform mappings (#660)
-- **Prompt Cache Tracking:** Added tracking capabilities and frontend visualization (Stats card) for semantic and prompt caching in the Dashboard UI
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Cache Dashboard Sizing:** Improved the UI layout sizes and context headers for the advanced cache pages (#835)
-- **Debug Sidebar Visibility:** Fixed an issue where the debug toggle wouldn't correctly show/hide sidebar debug details (#834)
-- **Gemini Model Prefixing:** Modified the namespace fallback to properly route via `gemini-cli/` instead of `gc/` to respect upstream specs (#831)
-- **OpenRouter Sync:** Improved compatibility synchronization to automatically ingest the available models catalog correctly from OpenRouter (#830)
-- **Streaming Payloads Mapping:** Reserialization of reasoning fields natively resolves conflict alias paths when output is streaming to edge devices
-
----
-
-## [3.3.7] - 2026-03-30
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **OpenCode Config:** Restructured generated `opencode.json` to use the `@ai-sdk/openai-compatible` record-based schema with `options` and `models` as object maps instead of flat arrays, fixing config validation failures (#816)
-- **i18n Missing Keys:** Added missing `cloudflaredUrlNotice` translation key across all 30 language files to prevent `MISSING_MESSAGE` console errors in the Endpoint page (#823)
-
----
-
-## [3.3.6] - 2026-03-30
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Token Accounting:** Included prompt cache tokens safely in historical usage inputs calculations for correct quota deductions (PR #822)
-- **Combo Test Probes:** Fixed combo testing logic false negatives by resolving parsing for reasoning-only responses and enabled massive parallelization via Promise.all (PR #828)
-- **Docker Quick Tunnels:** Embedded required ca-certificates inside the base runtime container to resolve Cloudflared TLS startup failures, and surfaced stdout network errors replacing generic exit codes (PR #829)
-
----
-
-## [3.3.5] - 2026-03-30
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Gemini Quota Tracking:** Added real-time Gemini CLI quota tracking via the `retrieveUserQuota` API (PR #825)
-- **Cache Dashboard:** Enhanced the Cache Dashboard to display prompt cache metrics, 24h trends, and estimated cost savings (PR #824)
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **User Experience:** Removed invasive auto-opening OAuth modal loops on barren provider detailed pages (PR #820)
-- **Dependency Updates:** Bumped and locked down dependencies for development and production trees including Next.js 16.2.1, Recharts, and TailwindCSS 4.2.2 (PR #826, #827)
-
----
-
-## [3.3.4] - 2026-03-30
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **A2A Workflows:** Added deterministic FSM orchestrator for multi-step agent workflows.
-- **Graceful Degradation:** Added a new multi-layer fallback framework to preserve core functionality during partial system outages.
-- **Config Audit:** Added an audit trail with diff detection to track changes and enable configuration rollbacks.
-- **Provider Health:** Added provider expiration tracking with proactive UI alerts for expiring API keys.
-- **Adaptive Routing:** Added an adaptive volume and complexity detector to override routing strategies dynamically based on load.
-- **Provider Diversity:** Implemented provider diversity scoring via Shannon entropy to improve load distribution.
-- **Auto-Disable Bounds:** Added an Auto-Disable Banned Accounts setting toggle to the Resilience dashboard.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Codex & Claude Compatibility:** Fixed UI fallbacks, patched Codex non-streaming integration issues, and resolved CLI runtime detection on Windows.
-- **Release Automation:** Expanded permissions required for the Electron App build in GitHub Actions.
-- **Cloudflare Runtime:** Addressed correct runtime isolation exit codes for Cloudflared tunnel components.
-
-### 🧪 Tests
-
-- **Test Suite Updates:** Expanded test coverage for volume detectors, provider diversity, configuration audit, and FSM.
-
----
-
-## [3.3.3] - 2026-03-29
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **CI/CD Reliability:** Patched GitHub Actions to stable dependency versions (`actions/checkout@v4`, `actions/upload-artifact@v4`) to mitigate unannounced builder environment deprecations.
-- **Image Fallbacks:** Replaced arbitrary fallback chains in `ProviderIcon.tsx` with explicit asset validation to prevent UI loading `<Image>` components for files that don't exist, eliminating `404` errors in dashboard console logs (#745).
-- **Admin Updater:** Dynamic source-installation detection for the dashboard Updater. Safely disables the `Update Now` button when OmniRoute is built locally rather than through npm, prompting for `git pull` (#743).
-- **Update ERESOLVE Error:** Injected `package.json` overrides for `react`/`react-dom` and enabled `--legacy-peer-deps` within the internal automatic updater scripts to resolve breaking dependency tree conflicts with `@lobehub/ui`.
-
----
-
-## [3.3.2] - 2026-03-29
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Cloudflare Tunnels:** Cloudflare Quick Tunnel integration with dashboard controls (PR #772).
-- **Diagnostics:** Semantic cache bypass for combo live tests (PR #773).
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Streaming Stability:** Apply `FETCH_TIMEOUT_MS` to streaming requests' initial `fetch()` call to prevent 300s Node.js TCP timeout causing silent task failures (#769).
-- **i18n:** Add missing `windsurf` and `copilot` entries to `toolDescriptions` across all 33 locale files (#748).
-- **GLM Coding Audit:** Complete provider audit fixing ReDoS vulnerabilities, context window sizing (128k/16k), and model registry syncing (PR #778).
-
----
-
-## [3.3.1] - 2026-03-29
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **OpenAI Codex:** Fallback processing fix for `type: "text"` elements carrying null or empty datasets that caused 400 rejection (#742).
-- **Opencode:** Update schema alignment to singular `provider` to match official spec (#774).
-- **Gemini CLI:** Inject missing end-user quota headers preventing 403 authorization lockouts (#775).
-- **DB Recovery:** Refactor multipart payload imports into raw binary buffered arrays to bypass reverse proxy max body limits (#770).
-
----
-
-## [3.3.0] - 2026-03-29
-
-### ✨ Enhancements & Refactoring
-
-- **Release Stabilization** — Finalized v3.2.9 release (combo diagnostics, quality gates, Gemini tool fix) and created missing git tag. Consolidated all staged changes into a single atomic release commit.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Auto-Update Test** — Fixed `buildDockerComposeUpdateScript` test assertion to match unexpanded shell variable references (`$TARGET_TAG`, `${TARGET_TAG#v}`) in the generated deploy script, aligning with the refactored template from v3.2.8.
-- **Circuit Breaker Test** — Hardened `combo-circuit-breaker.test.mjs` by injecting `maxRetries: 0` to prevent retry inflation from skewing failure count assertions during breaker state transitions.
-
----
-
-## [3.2.9] - 2026-03-29
-
-### ✨ Enhancements & Refactoring
-
-- **Combo Diagnostics** — Introduced a live test bypass flag (`forceLiveComboTest`) allowing administrators to execute real upstream health checks that bypass all local circuit-breaker and cooldown state mechanisms, enabling precise diagnostics during rolling outages (PR #759)
-- **Quality Gates** — Added automated response quality validation for combos and officially integrated `claude-4.6` model support into the core routing schemas (PR #762)
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Tool Definition Validation** — Repaired Gemini API integration by normalizing enum types inside tool definitions, preventing upstream HTTP 400 parameter errors (PR #760)
-
----
-
-## [3.2.8] - 2026-03-29
-
-### ✨ Enhancements & Refactoring
-
-- **Docker Auto-Update UI** — Integrated a detached background update process for Docker Compose deployments. The Dashboard UI now seamlessly tracks update lifecycle events combining JSON REST responses with SSE streaming progress overlays for robust cross-environment reliability.
-- **Cache Analytics** — Repaired zero-metrics visualization mapping by migrating Semantic Cache telemetry logs directly into the centralized tracking SQLite module.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Authentication Logic** — Fixed a bug where saving dashboard settings or adding models failed with a 401 Unauthorized error when `requireLogin` was disabled. API endpoints now correctly evaluate the global authentication toggle. Resolved global redirection by reactivating `src/middleware.ts`.
-- **CLI Tool Detection (Windows)** — Prevented fatal initialization exceptions during CLI environment detection by catching `cross-spawn` ENOENT errors correctly. Adds explicit detection paths for `\AppData\Local\droid\droid.exe`.
-- **Codex Native Passthrough** — Normalized model translation parameters preventing context poisoning in proxy pass-through mode, enforcing generic `store: false` constraints explicitly for all Codex-originated requests.
-- **SSE Token Reporting** — Normalized provider tool-call chunk `finish_reason` detection, fixing 0% Usage analytics for stream-only responses missing strict `<DONE>` indicators.
-- **DeepSeek <think> Tags** — Implemented an explicit `<think>` extraction mapping inside `responsesHandler.ts`, ensuring DeepSeek reasoning streams map equivalently to native Anthropic `<thinking>` structures.
-
----
-
-## [3.2.7] - 2026-03-29
-
-### Fixed
-
-- **Seamless UI Updates**: The "Update Now" feature on the Dashboard now provides live, transparent feedback using Server-Sent Events (SSE). It performs package installation, native module rebuilds (better-sqlite3), and PM2 restarts reliably while showing real-time loaders instead of silently hanging.
-
----
-
-## [3.2.6] — 2026-03-29
-
-### ✨ Enhancements & Refactoring
-
-- **API Key Reveal (#740)** — Added a scoped API key copy flow in the Api Manager, protected by the `ALLOW_API_KEY_REVEAL` environment variable.
-- **Sidebar Visibility Controls (#739)** — Admins can now hide any sidebar navigation link via the Appearance settings to reduce visual clutter.
-- **Strict Combo Testing (#735)** — Hardened the combo health check endpoint to require live text responses from models instead of just soft reachability signals.
-- **Streamed Detailed Logs (#734)** — Switched detailed request logging for SSE streams to reconstruct the final payload, saving immense amounts of SQLite database size and significantly cleaning up the UI.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **OpenCode Go MiniMax Auth (#733)** — Corrected the authentication header logic for `minimax` models on OpenCode Go to use `x-api-key` instead of standard bearer tokens across the `/messages` protocol.
-
----
-
-## [3.2.5] — 2026-03-29
-
-### ✨ Enhancements & Refactoring
-
-- **Void Linux Deployment Support (#732)** — Integrated `xbps-src` packaging template and instructions to natively compile and install OmniRoute with `better-sqlite3` bindings via cross-compilation target.
-
-## [3.2.4] — 2026-03-29
-
-### ✨ Enhancements & Refactoring
-
-- **Qoder AI Migration (#660)** — Completely migrated the legacy `iFlow` core provider onto `Qoder AI` maintaining stable API routing capabilities.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Gemini Tools HTTP 400 Payload Invalid Argument (#731)** — Prevented `thoughtSignature` array injections inside standard Gemini `functionCall` sequences blocking agentic routing flows.
-
----
-
-## [3.2.3] — 2026-03-29
-
-### ✨ Enhancements & Refactoring
-
-- **Provider Limits Quota UI (#728)** — Normalized quota limit logic and data labeling inside the Limits interface.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Core Routing Schemas & Leaks** — Expanded `comboStrategySchema` to natively support `fill-first` and `p2c` strategies to unblock complex combo editing natively.
-- **Thinking Tags Extraction (CLI)** — Restructured CLI token responses sanitizer RegEx capturing model reasoning structures inside streams avoiding broken `<thinking>` extractions breaking response text output format.
-- **Strict Format Enforcements** — Hardened pipeline sanitization execution making it universally apply to translation mode targets.
-
----
-
-## [3.2.2] — 2026-03-29
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Four-Stage Request Log Pipeline (#705)** — Refactored log persistence to save comprehensive payloads at four distinct pipeline stages: Client Request, Translated Provider Request, Provider Response, and Translated Client Response. Introduced `streamPayloadCollector` for robust SSE stream truncation and payload serialization.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Mobile UI Fixes (#659)** — Prevented table components on the dashboard from breaking the layout on narrow viewports by adding proper horizontal scrolling and overflow containment to `DashboardLayout`.
-- **Claude Prompt Cache Fixes (#708)** — Ensured `cache_control` blocks in Claude-to-Claude fallback loops are faithfully preserved and passed safely back to Anthropic models.
-- **Gemini Tool Definitions (#725)** — Fixed schema translation errors when declaring simple `object` parameter types for Gemini function calling.
-
-## [3.2.1] — 2026-03-29
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Global Fallback Provider (#689)** — When all combo models are exhausted (502/503), OmniRoute now attempts a configurable global fallback model before returning the error. Set `globalFallbackModel` in settings to enable.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Fix #721** — Fixed context pinning bypass during tool-call responses. Non-streaming tagging used wrong JSON path (`json.messages` → `json.choices[0].message`). Streaming injection now triggers on `finish_reason` chunks for tool-call-only streams. `injectModelTag()` now appends synthetic pin messages for non-string content.
-- **Fix #709** — Confirmed already fixed (v3.1.9) — `system-info.mjs` creates directories recursively. Closed.
-- **Fix #707** — Confirmed already fixed (v3.1.9) — empty tool name sanitization in `chatCore.ts`. Closed.
-
-### 🧪 Tests
-
-- Added 6 unit tests for context pinning with tool-call responses (null content, array content, roundtrip, re-injection)
-
-## [3.2.0] — 2026-03-28
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Cache Management UI** — Added a dedicated semantic caching dashboard at \`/dashboard/cache\` with targeted API invalidation and 31-language i18n support (PR #701 by @oyi77)
-- **GLM Quota Tracking** — Added real-time usage and session quota tracking for the GLM Coding (Z.AI) provider (PR #698 by @christopher-s)
-- **Detailed Log Payloads** — Wired full four-stage pipeline payload capturing (original, translated, provider-response, streamed-deltas) directly into the UI (PR #705 by @rdself)
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Fix #708** — Prevented token bleeding for Claude Code users routing through OmniRoute by correctly preserving native \`cache_control\` headers during Claude-to-Claude passthrough (PR #708 by @tombii)
-- **Fix #719** — Setup internal auth boundaries for \`ModelSyncScheduler\` to prevent unauthenticated daemon failures on startup (PR #719 by @rdself)
-- **Fix #718** — Rebuilt badge rendering in Provider Limits UI preventing bad quota boundaries overlap (PR #718 by @rdself)
-- **Fix #704** — Fixed Combo Fallbacks breaking on HTTP 400 content-policy errors preventing model-rotation dead-routing (PR #704 by @rdself)
-
-### 🔒 Security & Dependencies
-
-- Bumped \`path-to-regexp\` to \`8.4.0\` resolving dependabot vulnerabilities (PR #715)
-
-## [3.1.10] — 2026-03-28
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Fix #706** — Fixed icon fallback rendering caused by Tailwind V4 `font-sans` override by applying `!important` to `.material-symbols-outlined`.
-- **Fix #703** — Fixed GitHub Copilot broken streams by enabling `responses` to `openai` format translation for any custom models leveraging `apiFormat: "responses"`.
-- **Fix #702** — Replaced flat-rate usage tracking with accurate DB pricing calculations for both streaming and non-streaming responses.
-- **Fix #716** — Cleaned up Claude tool-call translation state, correctly parsing streaming arguments and preventing OpenAI `tool_calls` chunks from repeating the `id` field.
-
-## [3.1.9] — 2026-03-28
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Schema Coercion** — Auto-coerce string-encoded numeric JSON Schema constraints (e.g. `"minimum": "1"`) to proper types, preventing 400 errors from Cursor, Cline, and other clients sending malformed tool schemas.
-- **Tool Description Sanitization** — Ensure tool descriptions are always strings; converts `null`, `undefined`, or numeric descriptions to empty strings before sending to providers.
-- **Clear All Models Button** — Added i18n translations for the "Clear All Models" provider action across all 30 languages.
-- **Codex Auth Export** — Added Codex `auth.json` export and apply-local buttons for seamless CLI integration.
-- **Windsurf BYOK Notes** — Added official limitation warnings to the Windsurf CLI tool card documenting BYOK constraints.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Fix #709** — `system-info.mjs` no longer crashes when the output directory doesn't exist (added `mkdirSync` with recursive flag).
-- **Fix #710** — A2A `TaskManager` singleton now uses `globalThis` to prevent state leakage across Next.js API route recompilations in dev mode. E2E test suite updated to handle 401 gracefully.
-- **Fix #711** — Added provider-specific `max_tokens` cap enforcement for upstream requests.
-- **Fix #605 / #592** — Strip `proxy_` prefix from tool names in non-streaming Claude responses; fixed LongCat validation URL.
-- **Call Logs Max Cap** — Upgraded `getMaxCallLogs()` with caching layer, env var support (`CALL_LOGS_MAX`), and DB settings integration.
-
-### 🧪 Tests
-
-- Test suite expanded from 964 → 1027 tests (63 new tests)
-- Added `schema-coercion.test.mjs` — 9 tests for numeric field coercion and tool description sanitization
-- Added `t40-opencode-cli-tools-integration.test.mjs` — OpenCode/Windsurf CLI integration tests
-- Enhanced feature-tests branch with comprehensive coverage tooling
-
-### 📁 New Files
-
-| File                                                     | Purpose                                                     |
-| -------------------------------------------------------- | ----------------------------------------------------------- |
-| `open-sse/translator/helpers/schemaCoercion.ts`          | Schema coercion and tool description sanitization utilities |
-| `tests/unit/schema-coercion.test.mjs`                    | Unit tests for schema coercion                              |
-| `tests/unit/t40-opencode-cli-tools-integration.test.mjs` | CLI tool integration tests                                  |
-| `COVERAGE_PLAN.md`                                       | Test coverage planning document                             |
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Claude Prompt Caching Passthrough** — Fixed cache_control markers being stripped in Claude passthrough mode (Claude → OmniRoute → Claude), which caused Claude Code users to deplete their Anthropic API quota 5-10x faster than direct connections. OmniRoute now preserves client's cache_control markers when sourceFormat and targetFormat are both Claude, ensuring prompt caching works correctly and dramatically reducing token consumption.
-
-## [3.1.8] - 2026-03-27
-
-### 🐛 Bug Fixes & Features
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Platform Core:** Implemented global state handling for Hidden Models & Combos preventing them from cluttering the catalog or leaking into connected MCP agents (#681).
-- **Stability:** Patched streaming crashes related to the native Antigravity provider integration failing due to unhandled undefined state arrays (#684).
-- **Localization Sync:** Deployed a fully overhauled `i18n` synchronizer detecting missing nested JSON properties and retro-fitting 30 locales sequentially (#685).## [3.1.7] - 2026-03-27
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Streaming Stability:** Fixed `hasValuableContent` returning `undefined` for empty chunks in SSE streams (#676).
-- **Tool Calling:** Fixed an issue in `sseParser.ts` where non-streaming Claude responses with multiple tool calls dropped the `id` of subsequent tool calls due to incorrect index-based deduplication (#671).
-
----
-
-## [3.1.6] — 2026-03-27
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Claude Native Tool Name Restoration** — Tool names like `TodoWrite` are no longer prefixed with `proxy_` in Claude passthrough responses (both streaming and non-streaming). Includes unit test coverage (PR #663 by @coobabm)
-- **Clear All Models Alias Cleanup** — "Clear All Models" button now also removes associated model aliases, preventing ghost models in the UI (PR #664 by @rdself)
-
----
-
-## [3.1.5] — 2026-03-27
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Backoff Auto-Decay** — Rate-limited accounts now auto-recover when their cooldown window expires, fixing a deadlock where high `backoffLevel` permanently deprioritized accounts (PR #657 by @brendandebeasi)
-
-### 🌍 i18n
-
-- **Chinese translation overhaul** — Comprehensive rewrite of `zh-CN.json` with improved accuracy (PR #658 by @only4copilot)
-
----
-
-## [3.1.4] — 2026-03-27
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Streaming Override Fix** — Explicit `stream: true` in request body now takes priority over `Accept: application/json` header. Clients sending both will correctly receive SSE streaming responses (#656)
-
-### 🌍 i18n
-
-- **Czech string improvements** — Refined terminology across `cs.json` (PR #655 by @zen0bit)
-
----
-
-## [3.1.3] — 2026-03-26
-
-### 🌍 i18n & Community
-
-- **~70 missing translation keys** added to `en.json` and 12 languages (PR #652 by @zen0bit)
-- **Czech documentation updated** — CLI-TOOLS, API_REFERENCE, VM_DEPLOYMENT guides (PR #652)
-- **Translation validation scripts** — `check_translations.py` and `validate_translation.py` for CI/QA (PR #651 by @zen0bit)
-
----
-
-## [3.1.2] — 2026-03-26
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Critical: Tool Calling Regression** — Fixed `proxy_Bash` errors by disabling the `proxy_` tool name prefix in the Claude passthrough path. Tools like `Bash`, `Read`, `Write` were being renamed to `proxy_Bash`, `proxy_Read`, etc., causing Claude to reject them (#618)
-- **Kiro Account Ban Documentation** — Documented as upstream AWS anti-fraud false positive, not an OmniRoute issue (#649)
-
-### 🧪 Tests
-
-- **936 tests, 0 failures**
-
----
-
-## [3.1.1] — 2026-03-26
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Vision Capability Metadata**: Added `capabilities.vision`, `input_modalities`, and `output_modalities` to `/v1/models` entries for vision-capable models (PR #646)
-- **Gemini 3.1 Models**: Added `gemini-3.1-pro-preview` and `gemini-3.1-flash-lite-preview` to the Antigravity provider (#645)
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Ollama Cloud 401 Error**: Fixed incorrect API base URL — changed from `api.ollama.com` to official `ollama.com/v1/chat/completions` (#643)
-- **Expired Token Retry**: Added bounded retry with exponential backoff (5→10→20 min) for expired OAuth connections instead of permanently skipping them (PR #647)
-
-### 🧪 Tests
-
-- **936 tests, 0 failures**
-
----
-
-## [3.1.0] — 2026-03-26
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **GitHub Issue Templates**: Added standardized bug report, feature request, and config/proxy issue templates (#641)
-- **Clear All Models**: Added a "Clear All Models" button to the provider detail page with i18n support in 29 languages (#634)
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Locale Conflict (`in.json`)**: Renamed the Hindi locale file from `in.json` (Indonesian ISO code) to `hi.json` to fix translation conflicts in Weblate (#642)
-- **Codex Empty Tool Names**: Moved tool name sanitization before the native Codex passthrough, fixing 400 errors from upstream providers when tools had empty names (#637)
-- **Streaming Newline Artifacts**: Added `collapseExcessiveNewlines` to the response sanitizer, collapsing runs of 3+ consecutive newlines from thinking models into a standard double newline (#638)
-- **Claude Reasoning Effort**: Converted OpenAI `reasoning_effort` param to Claude's native `thinking` budget block across all request paths, including automatic `max_tokens` adjustment (#627)
-- **Qwen Token Refresh**: Implemented proactive pre-expiry OAuth token refreshes (5-minute buffer) to prevent requests from failing when using short-lived tokens (#631)
-
-### 🧪 Tests
-
-- **936 tests, 0 failures** (+10 tests since 3.0.9)
-
----
-
-## [3.0.9] — 2026-03-26
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **NaN tokens in Claude Code / client responses (#617):**
-  - `sanitizeUsage()` now cross-maps `input_tokens`→`prompt_tokens` and `output_tokens`→`completion_tokens` before the whitelist filter, fixing responses showing NaN/0 token counts when providers return Claude-style usage field names
-
-### 🔒 Security
-
-- Updated `yaml` package to fix stack overflow vulnerability (GHSA-48c2-rrv3-qjmp)
-
-### 📋 Issue Triage
-
-- Closed #613 (Codestral — resolved with Custom Provider workaround)
-- Commented on #615 (OpenCode dual-endpoint — workaround provided, tracked as feature request)
-- Commented on #618 (tool call visibility — requesting v3.0.9 test)
-- Commented on #627 (effort level — already supported)
-
----
-
-## [3.0.8] — 2026-03-25
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Translation Failures for OpenAI-format Providers in Claude CLI (#632):**
-  - Handle `reasoning_details[]` array format from StepFun/OpenRouter — converts to `reasoning_content`
-  - Handle `reasoning` field alias from some providers → normalized to `reasoning_content`
-  - Cross-map usage field names: `input_tokens`↔`prompt_tokens`, `output_tokens`↔`completion_tokens` in `filterUsageForFormat`
-  - Fix `extractUsage` to accept both `input_tokens`/`output_tokens` and `prompt_tokens`/`completion_tokens` as valid usage fields
-  - Applied to both streaming (`sanitizeStreamingChunk`, `openai-to-claude.ts` translator) and non-streaming (`sanitizeMessage`) paths
-
----
-
-## [3.0.7] — 2026-03-25
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Antigravity Token Refresh:** Fixed `client_secret is missing` error for npm-installed users — the `clientSecretDefault` was empty in providerRegistry, causing Google to reject token refresh requests (#588)
-- **OpenCode Zen Models:** Added `modelsUrl` to the OpenCode Zen registry entry so "Import from /models" works correctly (#612)
-- **Streaming Artifacts:** Fixed excessive newlines left in responses after thinking-tag signature stripping (#626)
-- **Proxy Fallback:** Added automatic retry without proxy when SOCKS5 relay fails
-- **Proxy Test:** Test endpoint now resolves real credentials from DB via proxyId
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Playground Account/Key Selector:** Persistent, always-visible dropdown to select specific provider accounts/keys for testing — fetches all connections at startup and filters by selected provider
-- **CLI Tools Dynamic Models:** Model selection now dynamically fetches from `/v1/models` API — providers like Kiro now show their full model catalog
-- **Antigravity Model List:** Updated with Claude Sonnet 4.5, Claude Sonnet 4, GPT 5, GPT 5 Mini; enabled `passthroughModels` for dynamic model access (#628)
-
-### 🔧 Maintenance
-
-- Merged PR #625 — Provider Limits light mode background fix
-
----
-
-## [3.0.6] — 2026-03-25
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Limits/Proxy:** Fixed Codex limit fetching for accounts behind SOCKS5 proxies — token refresh now runs inside proxy context
-- **CI:** Fixed integration test `v1/models` assertion failure in CI environments without provider connections
-- **Settings:** Proxy test button now shows success/failure results immediately (previously hidden behind health data)
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Playground:** Added Account selector dropdown — test specific connections individually when a provider has multiple accounts
-
-### 🔧 Maintenance
-
-- Merged PR #623 — LongCat API base URL path correction
-
----
-
-## [3.0.5] — 2026-03-25
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Limits UI:** Added tag grouping feature to the connections dashboard to improve visual organization for accounts with custom tags.
-
----
-
-## [3.0.4] — 2026-03-25
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Streaming:** Fixed `TextDecoder` state corruption inside combo `sanitize` TransformStream which caused SSE garbled output matching multibyte characters (PR #614)
-- **Providers UI:** Safely render HTML tags inside provider connection error tooltips using `dangerouslySetInnerHTML`
-- **Proxy Settings:** Added missing `username` and `password` payload body properties allowing authenticated proxies to be successfully verified from the Dashboard.
-- **Provider API:** Bound soft exception returns to `getCodexUsage` preventing API HTTP 500 failures when token fetch fails
-
----
-
-## [3.0.3] — 2026-03-25
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Auto-Sync Models:** Added a UI toggle and `sync-models` endpoint to automatically synchronise model lists per provider using a scheduled interval scheduler (PR #597)
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Timeouts:** Elevated default proxies `FETCH_TIMEOUT_MS` and `STREAM_IDLE_TIMEOUT_MS` to 10 minutes to properly support deep reasoning models (like o1) without aborting requests (Fixes #609)
-- **CLI Tool Detection:** Improved cross-platform detection handling NVM paths, Windows `PATHEXT` (preventing `.cmd` wrappers issue), and custom NPM prefixes (PR #598)
-- **Streaming Logs:** Implemented `tool_calls` delta accumulation in streaming response logs so function calls are tracked and persisted accurately in DB (PR #603)
-- **Model Catalog:** Removed auth exemption, properly hiding `comfyui` and `sdwebui` models when no provider is explicitly configured (PR #599)
-
-### 🌐 Translations
-
-- **cs:** Improved Czech translation strings across the app (PR #601)
-
-## [3.0.2] — 2026-03-25
-
-### 🚀 Enhancements & Features
-
-#### feat(ui): Connection Tag Grouping
-
-- Added a Tag/Group field to `EditConnectionModal` (stored in `providerSpecificData.tag`) without requiring DB schema migrations.
-- Connections in the provider view now dynamically group by tag with visual dividers.
-- Untagged connections appear first without a header, followed by tagged groups in alphabetical order.
-- The tag grouping automatically applies to the Codex/Copilot/Antigravity Limits section since toggles exist inside connection rows.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-#### fix(ui): Proxy Management UI Stabilization
-
-- **Missing badges on connection cards:** Fixed by using `resolveProxyForConnection()` rather than static mapping.
-- **Test Connection disabled in saved mode:** Enabled the Test button by resolving proxy config from the saved list.
-- **Config Modal freezing:** Added `onClose()` calls after save/clear to prevent the UI from freezing.
-- **Double usage counting:** `ProxyRegistryManager` now loads usage eagerly on mount with deduplication by `scope` + `scopeId`. Usage counts were replaced with a Test button displaying IP/latency inline.
-
-#### fix(translator): `function_call` prefix stripping
-
-- Repaired an incomplete fix from PR #607 where only `tool_use` blocks stripped Claude's `proxy_` tool prefix. Now, clients using the OpenAI Responses API format will also correctly receive tool tools without the `proxy_` prefix.
-
----
-
-## [3.0.1] — 2026-03-25
-
-### 🔧 Hotfix Patch — Critical Bug Fixes
-
-Three critical regressions reported by users after the v3.0.0 launch have been resolved.
-
-#### fix(translator): strip `proxy_` prefix in non-streaming Claude responses (#605)
-
-The `proxy_` prefix added by Claude OAuth was only stripped from **streaming** responses. In **non-streaming** mode, `translateNonStreamingResponse` had no access to the `toolNameMap`, causing clients to receive mangled tool names like `proxy_read_file` instead of `read_file`.
-
-**Fix:** Added optional `toolNameMap` parameter to `translateNonStreamingResponse` and applied prefix stripping in the Claude `tool_use` block handler. `chatCore.ts` now passes the map through.
-
-#### fix(validation): add LongCat specialty validator to skip /models probe (#592)
-
-LongCat AI does not expose `GET /v1/models`. The generic `validateOpenAICompatibleProvider` validator fell through to a chat-completions fallback only if `validationModelId` was set, which LongCat doesn't configure. This caused provider validation to fail with a misleading error on add/save.
-
-**Fix:** Added `longcat` to the specialty validators map, probing `/chat/completions` directly and treating any non-auth response as a pass.
-
-#### fix(translator): normalize object tool schemas for Anthropic (#595)
-
-MCP tools (e.g. `pencil`, `computer_use`) forward tool definitions with `{type:"object"}` but without a `properties` field. Anthropic's API rejects these with: `object schema missing properties`.
-
-**Fix:** In `openai-to-claude.ts`, inject `properties: {}` as a safe default when `type` is `"object"` and `properties` is absent.
-
----
-
-### 🔀 Community PRs Merged (2)
-
-| PR       | Author  | Summary                                                                    |
-| -------- | ------- | -------------------------------------------------------------------------- |
-| **#589** | @flobo3 | docs(i18n): fix Russian translation for Playground and Testbed             |
-| **#591** | @rdself | fix(ui): improve Provider Limits light mode contrast and plan tier display |
-
----
-
-### ✅ Issues Resolved
-
-`#592` `#595` `#605`
-
----
-
-### 🧪 Tests
-
-- **926 tests, 0 failures** (unchanged from v3.0.0)
-
----
-
-## [3.0.0] — 2026-03-24
-
-### 🎉 OmniRoute v3.0.0 — The Free AI Gateway, Now with 67+ Providers
-
-> **The biggest release ever.** From 36 providers in v2.9.5 to **67+ providers** in v3.0.0 — with MCP Server, A2A Protocol, auto-combo engine, Provider Icons, Registered Keys API, 926 tests, and contributions from **12 community members** across **10 merged PRs**.
->
-> Consolidated from v3.0.0-rc.1 through rc.17 (17 release candidates over 3 days of intense development).
-
----
-
-### 🆕 New Providers (+31 since v2.9.5)
-
-| Provider                      | Alias           | Tier        | Notes                                                                       |
-| ----------------------------- | --------------- | ----------- | --------------------------------------------------------------------------- |
-| **OpenCode Zen**              | `opencode-zen`  | Free        | 3 models via `opencode.ai/zen/v1` (PR #530 by @kang-heewon)                 |
-| **OpenCode Go**               | `opencode-go`   | Paid        | 4 models via `opencode.ai/zen/go/v1` (PR #530 by @kang-heewon)              |
-| **LongCat AI**                | `lc`            | Free        | 50M tokens/day (Flash-Lite) + 500K/day (Chat/Thinking) during public beta   |
-| **Pollinations AI**           | `pol`           | Free        | No API key needed — GPT-5, Claude, Gemini, DeepSeek V3, Llama 4 (1 req/15s) |
-| **Cloudflare Workers AI**     | `cf`            | Free        | 10K Neurons/day — ~150 LLM responses or 500s Whisper audio, edge inference  |
-| **Scaleway AI**               | `scw`           | Free        | 1M free tokens for new accounts — EU/GDPR compliant (Paris)                 |
-| **AI/ML API**                 | `aiml`          | Free        | $0.025/day free credits — 200+ models via single endpoint                   |
-| **Puter AI**                  | `pu`            | Free        | 500+ models (GPT-5, Claude Opus 4, Gemini 3 Pro, Grok 4, DeepSeek V3)       |
-| **Alibaba Cloud (DashScope)** | `ali`           | Paid        | International + China endpoints via `alicode`/`alicode-intl`                |
-| **Alibaba Coding Plan**       | `bcp`           | Paid        | Alibaba Model Studio with Anthropic-compatible API                          |
-| **Kimi Coding (API Key)**     | `kmca`          | Paid        | Dedicated API-key-based Kimi access (separate from OAuth)                   |
-| **MiniMax Coding**            | `minimax`       | Paid        | International endpoint                                                      |
-| **MiniMax (China)**           | `minimax-cn`    | Paid        | China-specific endpoint                                                     |
-| **Z.AI (GLM-5)**              | `zai`           | Paid        | Zhipu AI next-gen GLM models                                                |
-| **Vertex AI**                 | `vertex`        | Paid        | Google Cloud — Service Account JSON or OAuth access_token                   |
-| **Ollama Cloud**              | `ollamacloud`   | Paid        | Ollama's hosted API service                                                 |
-| **Synthetic**                 | `synthetic`     | Paid        | Passthrough models gateway                                                  |
-| **Kilo Gateway**              | `kg`            | Paid        | Passthrough models gateway                                                  |
-| **Perplexity Search**         | `pplx-search`   | Paid        | Dedicated search-grounded endpoint                                          |
-| **Serper Search**             | `serper-search` | Paid        | Web search API integration                                                  |
-| **Brave Search**              | `brave-search`  | Paid        | Brave Search API integration                                                |
-| **Exa Search**                | `exa-search`    | Paid        | Neural search API integration                                               |
-| **Tavily Search**             | `tavily-search` | Paid        | AI search API integration                                                   |
-| **NanoBanana**                | `nb`            | Paid        | Image generation API                                                        |
-| **ElevenLabs**                | `el`            | Paid        | Text-to-speech voice synthesis                                              |
-| **Cartesia**                  | `cartesia`      | Paid        | Ultra-fast TTS voice synthesis                                              |
-| **PlayHT**                    | `playht`        | Paid        | Voice cloning and TTS                                                       |
-| **Inworld**                   | `inworld`       | Paid        | AI character voice chat                                                     |
-| **SD WebUI**                  | `sdwebui`       | Self-hosted | Stable Diffusion local image generation                                     |
-| **ComfyUI**                   | `comfyui`       | Self-hosted | ComfyUI local workflow node-based generation                                |
-| **GLM Coding**                | `glm`           | Paid        | BigModel/Zhipu coding-specific endpoint                                     |
-
-**Total: 67+ providers** (4 Free, 8 OAuth, 55 API Key) + unlimited OpenAI/Anthropic-Compatible custom providers.
-
----
-
-### ✨ Major Features
-
-#### 🔑 Registered Keys Provisioning API (#464)
-
-Auto-generate and issue OmniRoute API keys programmatically with per-provider and per-account quota enforcement.
-
-| Endpoint                        | Method       | Description                                      |
-| ------------------------------- | ------------ | ------------------------------------------------ |
-| `/api/v1/registered-keys`       | `POST`       | Issue a new key — raw key returned **once only** |
-| `/api/v1/registered-keys`       | `GET`        | List registered keys (masked)                    |
-| `/api/v1/registered-keys/{id}`  | `GET/DELETE` | Get metadata / Revoke                            |
-| `/api/v1/quotas/check`          | `GET`        | Pre-validate quota before issuing                |
-| `/api/v1/providers/{id}/limits` | `GET/PUT`    | Configure per-provider issuance limits           |
-| `/api/v1/accounts/{id}/limits`  | `GET/PUT`    | Configure per-account issuance limits            |
-| `/api/v1/issues/report`         | `POST`       | Report quota events to GitHub Issues             |
-
-**Security:** Keys stored as SHA-256 hashes. Raw key shown once on creation, never retrievable again.
-
-#### 🎨 Provider Icons via @lobehub/icons (#529)
-
-130+ provider logos using `@lobehub/icons` React components (SVG). Fallback chain: **Lobehub SVG → existing PNG → generic icon**. Applied across Dashboard, Providers, and Agents pages with standardized `ProviderIcon` component.
-
-#### 🔄 Model Auto-Sync Scheduler (#488)
-
-Auto-refreshes model lists for connected providers every **24 hours**. Runs on server startup. Configurable via `MODEL_SYNC_INTERVAL_HOURS`.
-
-#### 🔀 Per-Model Combo Routing (#563)
-
-Map model name patterns (glob) to specific combos for automatic routing:
-
-- `claude-sonnet*` → code-combo, `gpt-4o*` → openai-combo, `gemini-*` → google-combo
-- New `model_combo_mappings` table with glob-to-regex matching
-- Dashboard UI section: "Model Routing Rules" with inline add/edit/toggle/delete
-
-#### 🧭 API Endpoints Dashboard
-
-Interactive catalog, webhooks management, OpenAPI viewer — all in one tabbed page at `/dashboard/endpoint`.
-
-#### 🔍 Web Search Providers
-
-5 new search provider integrations: **Perplexity Search**, **Serper**, **Brave Search**, **Exa**, **Tavily** — enabling grounded AI responses with real-time web data.
-
-#### 📊 Search Analytics
-
-New tab in `/dashboard/analytics` — provider breakdown, cache hit rate, cost tracking. API: `GET /api/v1/search/analytics`.
-
-#### 🛡️ Per-API-Key Rate Limits (#452)
-
-`max_requests_per_day` and `max_requests_per_minute` columns with in-memory sliding-window enforcement returning HTTP 429.
-
-#### 🎵 Media Playground
-
-Full media generation playground at `/dashboard/media`: Image Generation, Video, Music, Audio Transcription (2GB upload limit), and Text-to-Speech.
-
----
-
-### 🔒 Security & CI/CD
-
-- **CodeQL remediation** — Fixed 10+ alerts: 6 polynomial-redos, 1 insecure-randomness (`Math.random()` → `crypto.randomUUID()`), 1 shell-command-injection
-- **Route validation** — Zod schemas + `validateBody()` on **176/176 API routes** — CI enforced
-- **CVE fix** — dompurify XSS vulnerability (GHSA-v2wj-7wpq-c8vv) resolved via npm overrides
-- **Flatted** — Bumped 3.3.3 → 3.4.2 (CWE-1321 prototype pollution)
-- **Docker** — Upgraded `docker/setup-buildx-action` v3 → v4
-
----
-
-### 🐛 Bug Fixes (40+)
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-#### OAuth & Auth
-
-- **#537** — Gemini CLI OAuth: clear actionable error when `GEMINI_OAUTH_CLIENT_SECRET` missing in Docker
-- **#549** — CLI settings routes now resolve real API key from `keyId` (not masked strings)
-- **#574** — Login no longer freezes after skipping wizard password setup
-- **#506** — Cross-platform `machineId` rewritten (Windows REG.exe → macOS ioreg → Linux → hostname fallback)
-
-#### Providers & Routing
-
-- **#536** — LongCat AI: fixed `baseUrl` and `authHeader`
-- **#535** — Pinned model override: `body.model` correctly set to `pinnedModel`
-- **#570** — Unprefixed Claude models now resolve to Anthropic provider
-- **#585** — `<omniModel>` internal tags no longer leak to clients in SSE streaming
-- **#493** — Custom provider model naming no longer mangled by prefix stripping
-- **#490** — Streaming + context cache protection via `TransformStream` injection
-- **#511** — `<omniModel>` tag injected into first content chunk (not after `[DONE]`)
-
-#### CLI & Tools
-
-- **#527** — Claude Code + Codex loop: `tool_result` blocks now converted to text
-- **#524** — OpenCode config saved correctly (XDG_CONFIG_HOME, TOML format)
-- **#522** — API Manager: removed misleading "Copy masked key" button
-- **#546** — `--version` returning `unknown` on Windows (PR by @k0valik)
-- **#544** — Secure CLI tool detection via known installation paths (PR by @k0valik)
-- **#510** — Windows MSYS2/Git-Bash paths normalized automatically
-- **#492** — CLI detects `mise`/`nvm`-managed Node when `app/server.js` missing
-
-#### Streaming & SSE
-
-- **PR #587** — Revert `resolveDataDir` import in responsesTransformer for Cloudflare Workers compat (@k0valik)
-- **PR #495** — Bottleneck 429 infinite wait: drop waiting jobs on rate limit (@xandr0s)
-- **#483** — Stop trailing `data: null` after `[DONE]` signal
-- **#473** — Zombie SSE streams: timeout reduced 300s → 120s for faster fallback
-
-#### Media & Transcription
-
-- **Transcription** — Deepgram `video/mp4` → `audio/mp4` MIME mapping, auto language detection, punctuation
-- **TTS** — `[object Object]` error display fixed for ElevenLabs-style nested errors
-- **Upload limits** — Media transcription increased to 2GB (nginx `client_max_body_size 2g` + `maxDuration=300`)
-
----
-
-### 🔧 Infrastructure & Improvements
-
-#### Sub2api Gap Analysis (T01–T15 + T23–T42)
-
-- **T01** — `requested_model` column in call logs (migration 009)
-- **T02** — Strip empty text blocks from nested `tool_result.content`
-- **T03** — Parse `x-codex-5h-*` / `x-codex-7d-*` quota headers
-- **T04** — `X-Session-Id` header for external sticky routing
-- **T05** — Rate-limit DB persistence with dedicated API
-- **T06** — Account deactivated → permanent block (1-year cooldown)
-- **T07** — X-Forwarded-For IP validation (`extractClientIp()`)
-- **T08** — Per-API-key session limits with sliding-window enforcement
-- **T09** — Codex vs Spark rate-limit scopes (separate pools)
-- **T10** — Credits exhausted → distinct 1h cooldown fallback
-- **T11** — `max` reasoning effort → 131072 budget tokens
-- **T12** — MiniMax M2.7 pricing entries
-- **T13** — Stale quota display fix (reset window awareness)
-- **T14** — Proxy fast-fail TCP check (≤2s, cached 30s)
-- **T15** — Array content normalization for Anthropic
-- **T23** — Intelligent quota reset fallback (header extraction)
-- **T24** — `503` cooldown + `406` mapping
-- **T25** — Provider validation fallback
-- **T29** — Vertex AI Service Account JWT auth
-- **T33** — Thinking level to budget conversion
-- **T36** — `403` vs `429` error classification
-- **T38** — Centralized model specifications (`modelSpecs.ts`)
-- **T39** — Endpoint fallback for `fetchAvailableModels`
-- **T41** — Background task auto-redirect to flash models
-- **T42** — Image generation aspect ratio mapping
-
-#### Other Improvements
-
-- **Per-model upstream custom headers** — via configuration UI (PR #575 by @zhangqiang8vip)
-- **Model context length** — configurable in model metadata (PR #578 by @hijak)
-- **Model prefix stripping** — option to remove provider prefix from model names (PR #582 by @jay77721)
-- **Gemini CLI deprecation** — marked deprecated with Google OAuth restriction warning
-- **YAML parser** — replaced custom parser with `js-yaml` for correct OpenAPI spec parsing
-- **ZWS v5** — HMR leak fix (485 DB connections → 1, memory 2.4GB → 195MB)
-- **Log export** — New JSON export button on dashboard with time range dropdown
-- **Update notification banner** — dashboard homepage shows when new versions are available
-
----
-
-### 🌐 i18n & Documentation
-
-- **30 languages** at 100% parity — 2,788 missing keys synced
-- **Czech** — Full translation: 22 docs, 2,606 UI strings (PR by @zen0bit)
-- **Chinese (zh-CN)** — Complete retranslation (PR by @only4copilot)
-- **VM Deployment Guide** — Translated to English as source document
-- **API Reference** — Added `/v1/embeddings` and `/v1/audio/speech` endpoints
-- **Provider count** — Updated from 36+/40+/44+ to **67+** across README and all 30 i18n READMEs
-
----
-
-### 🔀 Community PRs Merged (10)
-
-| PR       | Author          | Summary                                                              |
-| -------- | --------------- | -------------------------------------------------------------------- |
-| **#587** | @k0valik        | fix(sse): revert resolveDataDir import for Cloudflare Workers compat |
-| **#582** | @jay77721       | feat(proxy): model name prefix stripping option                      |
-| **#581** | @jay77721       | fix(npm): link electron-release to npm-publish workflow              |
-| **#578** | @hijak          | feat: configurable context length in model metadata                  |
-| **#575** | @zhangqiang8vip | feat: per-model upstream headers, compat PATCH, chat alignment       |
-| **#562** | @coobabm        | fix: MCP session management, Claude passthrough, detectFormat        |
-| **#561** | @zen0bit        | fix(i18n): Czech translation corrections                             |
-| **#555** | @k0valik        | fix(sse): centralized `resolveDataDir()` for path resolution         |
-| **#546** | @k0valik        | fix(cli): `--version` returning `unknown` on Windows                 |
-| **#544** | @k0valik        | fix(cli): secure CLI tool detection via installation paths           |
-| **#542** | @rdself         | fix(ui): light mode contrast CSS theme variables                     |
-| **#530** | @kang-heewon    | feat: OpenCode Zen + Go providers with `OpencodeExecutor`            |
-| **#512** | @zhangqiang8vip | feat: per-protocol model compatibility (`compatByProtocol`)          |
-| **#497** | @zhangqiang8vip | fix: dev-mode HMR resource leaks (ZWS v5)                            |
-| **#495** | @xandr0s        | fix: Bottleneck 429 infinite wait (drop waiting jobs)                |
-| **#494** | @zhangqiang8vip | feat: MiniMax developer→system role fix                              |
-| **#480** | @prakersh       | fix: stream flush usage extraction                                   |
-| **#479** | @prakersh       | feat: Codex 5.3/5.4 and Anthropic pricing entries                    |
-| **#475** | @only4copilot   | feat(i18n): improved Chinese translation                             |
-
-**Thank you to all contributors!** 🙏
-
----
-
-### 📋 Issues Resolved (50+)
-
-`#452` `#458` `#462` `#464` `#466` `#473` `#474` `#481` `#483` `#487` `#488` `#489` `#490` `#491` `#492` `#493` `#506` `#508` `#509` `#510` `#511` `#513` `#520` `#521` `#522` `#524` `#525` `#527` `#529` `#531` `#532` `#535` `#536` `#537` `#541` `#546` `#549` `#563` `#570` `#574` `#585`
-
----
-
-### 🧪 Tests
-
-- **926 tests, 0 failures** (up from 821 in v2.9.5)
-- +105 new tests covering: model-combo mappings, registered keys, OpencodeExecutor, Bailian provider, route validation, error classification, aspect ratio mapping, and more
-
----
-
-### 📦 Database Migrations
-
-| Migration | Description                                                           |
-| --------- | --------------------------------------------------------------------- |
-| **008**   | `registered_keys`, `provider_key_limits`, `account_key_limits` tables |
-| **009**   | `requested_model` column in `call_logs`                               |
-| **010**   | `model_combo_mappings` table for per-model combo routing              |
-
----
-
-### ⬆️ Upgrading from v2.9.5
-
-```bash
-# npm
-npm install -g omniroute@3.0.0
-
-# Docker
-docker pull diegosouzapw/omniroute:3.0.0
-
-# Migrations run automatically on first startup
-```
-
-> **Breaking changes:** None. All existing configurations, combos, and API keys are preserved.
-> Database migrations 008-010 run automatically on startup.
-
----
-
-## [3.0.0-rc.17] — 2026-03-24
-
-### 🔒 Security & CI/CD
-
-- **CodeQL remediation** — Fixed 10+ alerts:
-  - 6 polynomial-redos in `provider.ts` / `chatCore.ts` (replaced `(?:^|/)` alternation patterns with segment-based matching)
-  - 1 insecure-randomness in `acp/manager.ts` (`Math.random()` → `crypto.randomUUID()`)
-  - 1 shell-command-injection in `prepublish.mjs` (`JSON.stringify()` path escaping)
-- **Route validation** — Added Zod schemas + `validateBody()` to 5 routes missing validation:
-  - `model-combo-mappings` (POST, PUT), `webhooks` (POST, PUT), `openapi/try` (POST)
-  - CI `check:route-validation:t06` now passes: **176/176 routes validated**
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **#585** — `<omniModel>` internal tags no longer leak to clients in SSE responses. Added outbound sanitization `TransformStream` in `combo.ts`
-
-### ⚙️ Infrastructure
-
-- **Docker** — Upgraded `docker/setup-buildx-action` from v3 → v4 (Node.js 20 deprecation fix)
-- **CI cleanup** — Deleted 150+ failed/cancelled workflow runs
-
-### 🧪 Tests
-
-- Test suite: **926 tests, 0 failures** (+3 new)
-
----
-
-## [3.0.0-rc.16] — 2026-03-24
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- Increased media transcription limits
-- Added Model Context Length to registry metadata
-- Added per-model upstream custom headers via configuration UI
-- Fixed multiple bugs, Zod valiadation for patches, and resolved various community issues.
-
-## [3.0.0-rc.15] — 2026-03-24
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **#563** — Per-model Combo Routing: map model name patterns (glob) to specific combos for automatic routing
-  - New `model_combo_mappings` table (migration 010) with pattern, combo_id, priority, enabled
-  - `resolveComboForModel()` DB function with glob-to-regex matching (case-insensitive, `*` and `?` wildcards)
-  - `getComboForModel()` in `model.ts`: augments `getCombo()` with model-pattern fallback
-  - `chat.ts`: routing decision now checks model-combo mappings before single-model handling
-  - API: `GET/POST /api/model-combo-mappings`, `GET/PUT/DELETE /api/model-combo-mappings/:id`
-  - Dashboard: "Model Routing Rules" section added to Combos page with inline add/edit/toggle/delete
-  - Examples: `claude-sonnet*` → code-combo, `gpt-4o*` → openai-combo, `gemini-*` → google-combo
-
-### 🌐 i18n
-
-- **Full i18n Sync**: 2,788 missing keys added across 30 language files — all languages now at 100% parity with `en.json`
-- **Agents page i18n**: OpenCode Integration section fully internationalized (title, description, scanning, download labels)
-- **6 new keys** added to `agents` namespace for OpenCode section
-
-### 🎨 UI/UX
-
-- **Provider Icons**: 16 missing provider icons added (3 copied, 2 downloaded, 11 SVG created)
-- **SVG fallback**: `ProviderIcon` component updated with 4-tier strategy: Lobehub → PNG → SVG → Generic icon
-- **Agents fingerprinting**: Synced with CLI tools — added droid, openclaw, copilot, opencode to fingerprint list (14 total)
-
-### 🔒 Security
-
-- **CVE fix**: Resolved dompurify XSS vulnerability (GHSA-v2wj-7wpq-c8vv) via npm overrides forcing `dompurify@^3.3.2`
-- `npm audit` now reports **0 vulnerabilities**
-
-### 🧪 Tests
-
-- Test suite: **923 tests, 0 failures** (+15 new model-combo mapping tests)
-
----
-
-## [3.0.0-rc.14] — 2026-03-23
-
-### 🔀 Community PRs Merged
-
-| PR       | Author   | Summary                                                                                      |
-| -------- | -------- | -------------------------------------------------------------------------------------------- |
-| **#562** | @coobabm | fix(ux): MCP session management, Claude passthrough normalization, OAuth modal, detectFormat |
-| **#561** | @zen0bit | fix(i18n): Czech translation corrections — HTTP method names and documentation updates       |
-
-### 🧪 Tests
-
-- Test suite: **908 tests, 0 failures**
-
----
-
-## [3.0.0-rc.13] — 2026-03-23
-
-### 🔧 Bug Fixes
-
-- **config:** resolve real API key from `keyId` in CLI settings routes (`codex-settings`, `droid-settings`, `kilo-settings`) to prevent writing masked strings (#549)
-
----
-
-## [3.0.0-rc.12] — 2026-03-23
-
-### 🔀 Community PRs Merged
-
-| PR       | Author   | Summary                                                                                                                                                       |
-| -------- | -------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **#546** | @k0valik | fix(cli): `--version` returning `unknown` on Windows — use `JSON.parse(readFileSync)` instead of ESM import                                                   |
-| **#555** | @k0valik | fix(sse): centralized `resolveDataDir()` for path resolution in credentials, autoCombo, responses logger, and request logger                                  |
-| **#544** | @k0valik | fix(cli): secure CLI tool detection via known installation paths (8 tools) with symlink validation, file-type checks, size bounds, minimal env in healthcheck |
-| **#542** | @rdself  | fix(ui): improve light mode contrast — add missing CSS theme variables (`bg-primary`, `bg-subtle`, `text-primary`) and fix dark-only colors in log detail     |
-
-### 🔧 Bug Fixes
-
-- **TDZ fix in `cliRuntime.ts`** — `validateEnvPath` was used before initialization at module startup by `getExpectedParentPaths()`. Reordered declarations to fix `ReferenceError`.
-- **Build fixes** — Added `pino` and `pino-pretty` to `serverExternalPackages` to prevent Turbopack from breaking Pino's internal worker loading.
-
-### 🧪 Tests
-
-- Test suite: **905 tests, 0 failures**
-
----
-
-## [3.0.0-rc.10] — 2026-03-23
-
-### 🔧 Bug Fixes
-
-- **#509 / #508** — Electron build regression: downgraded Next.js from `16.1.x` to `16.0.10` to eliminate Turbopack module-hashing instability that caused blank screens in the Electron desktop bundle.
-- **Unit test fixes** — Corrected two stale test assertions (`nanobanana-image-handler` aspect ratio/resolution, `thinking-budget` Gemini `thinkingConfig` field mapping) that had drifted after recent implementation changes.
-- **#541** — Responded to user feedback about installation complexity; no code changes required.
-
----
-
-## [3.0.0-rc.9] — 2026-03-23
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **T29** — Vertex AI SA JSON Executor: implemented using the `jose` library to handle JWT/Service Account auth, along with configurable regions in the UI and automatic partner model URL building.
-- **T42** — Image generation aspect ratio mapping: created `sizeMapper` logic for generic OpenAI formats (`size`), added native `imagen3` handling, and updated NanoBanana endpoints to utilize mapped aspect ratios automatically.
-- **T38** — Centralized model specifications: `modelSpecs.ts` created for limits and parameters per model.
-
-### 🔧 Improvements
-
-- **T40** — OpenCode CLI tools integration: native `opencode-zen` and `opencode-go` integration completed in earlier PR.
-
----
-
-## [3.0.0-rc.8] — 2026-03-23
-
-### 🔧 Bug Fixes & Improvements (Fallback, Quota & Budget)
-
-- **T24** — `503` cooldown await fix + `406` mapping: mapped `406 Not Acceptable` to `503 Service Unavailable` with proper cooldown intervals.
-- **T25** — Provider validation fallback: graceful fallback to standard validation models when a specific `validationModelId` is not present.
-- **T36** — `403` vs `429` provider handling refinement: extracted into `errorClassifier.ts` to properly segregate hard permissions failures (`403`) from rate limits (`429`).
-- **T39** — Endpoint Fallback for `fetchAvailableModels`: implemented a tri-tier mechanism (`/models` -> `/v1/models` -> local generic catalog) + `list_models_catalog` MCP tool updates to reflect `source` and `warning`.
-- **T33** — Thinking level to budget conversion: translates qualitative thinking levels into precise budget allocations.
-- **T41** — Background task auto redirect: routes heavy background evaluation tasks to flash/efficient models automatically.
-- **T23** — Intelligent quota reset fallback: accurately extracts `x-ratelimit-reset` / `retry-after` header values or maps static cooldowns.
-
----
-
-## [3.0.0-rc.7] — 2026-03-23 _(What's New vs v2.9.5 — will be released as v3.0.0)_
-
-> **Upgrade from v2.9.5:** 16 issues resolved · 2 community PRs merged · 2 new providers · 7 new API endpoints · 3 new features · DB migration 008+009 · 832 tests passing · 15 sub2api gap improvements (T01–T15 complete).
-
-### 🆕 New Providers
-
-| Provider         | Alias          | Tier | Notes                                                          |
-| ---------------- | -------------- | ---- | -------------------------------------------------------------- |
-| **OpenCode Zen** | `opencode-zen` | Free | 3 models via `opencode.ai/zen/v1` (PR #530 by @kang-heewon)    |
-| **OpenCode Go**  | `opencode-go`  | Paid | 4 models via `opencode.ai/zen/go/v1` (PR #530 by @kang-heewon) |
-
-Both providers use the new `OpencodeExecutor` with multi-format routing (`/chat/completions`, `/messages`, `/responses`, `/models/{model}:generateContent`).
-
----
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-#### 🔑 Registered Keys Provisioning API (#464)
-
-Auto-generate and issue OmniRoute API keys programmatically with per-provider and per-account quota enforcement.
-
-| Endpoint                              | Method    | Description                                      |
-| ------------------------------------- | --------- | ------------------------------------------------ |
-| `/api/v1/registered-keys`             | `POST`    | Issue a new key — raw key returned **once only** |
-| `/api/v1/registered-keys`             | `GET`     | List registered keys (masked)                    |
-| `/api/v1/registered-keys/{id}`        | `GET`     | Get key metadata                                 |
-| `/api/v1/registered-keys/{id}`        | `DELETE`  | Revoke a key                                     |
-| `/api/v1/registered-keys/{id}/revoke` | `POST`    | Revoke (for clients without DELETE support)      |
-| `/api/v1/quotas/check`                | `GET`     | Pre-validate quota before issuing                |
-| `/api/v1/providers/{id}/limits`       | `GET/PUT` | Configure per-provider issuance limits           |
-| `/api/v1/accounts/{id}/limits`        | `GET/PUT` | Configure per-account issuance limits            |
-| `/api/v1/issues/report`               | `POST`    | Report quota events to GitHub Issues             |
-
-**DB — Migration 008:** Three new tables: `registered_keys`, `provider_key_limits`, `account_key_limits`.
-**Security:** Keys stored as SHA-256 hashes. Raw key shown once on creation, never retrievable again.
-**Quota types:** `maxActiveKeys`, `dailyIssueLimit`, `hourlyIssueLimit` per provider and per account.
-**Idempotency:** `idempotency_key` field prevents duplicate issuance. Returns `409 IDEMPOTENCY_CONFLICT` if key was already used.
-**Budget per key:** `dailyBudget` / `hourlyBudget` — limits how many requests a key can route per window.
-**GitHub reporting:** Optional. Set `GITHUB_ISSUES_REPO` + `GITHUB_ISSUES_TOKEN` to auto-create GitHub issues on quota exceeded or issuance failures.
-
-#### 🎨 Provider Icons — @lobehub/icons (#529)
-
-All provider icons in the dashboard now use `@lobehub/icons` React components (130+ providers with SVG).
-Fallback chain: **Lobehub SVG → existing `/providers/{id}.png` → generic icon**. Uses a proper React `ErrorBoundary` pattern.
-
-#### 🔄 Model Auto-Sync Scheduler (#488)
-
-OmniRoute now automatically refreshes model lists for connected providers every **24 hours**.
-
-- Runs on server startup via the existing `/api/sync/initialize` hook
-- Configurable via `MODEL_SYNC_INTERVAL_HOURS` environment variable
-- Covers 16 major providers
-- Records last sync time in the settings database
-
----
-
-### 🔧 Bug Fixes
-
-#### OAuth & Auth
-
-- **#537 — Gemini CLI OAuth:** Clear actionable error when `GEMINI_OAUTH_CLIENT_SECRET` is missing in Docker/self-hosted deployments. Previously showed cryptic `client_secret is missing` from Google. Now provides specific `docker-compose.yml` and `~/.omniroute/.env` instructions.
-
-#### Providers & Routing
-
-- **#536 — LongCat AI:** Fixed `baseUrl` (`api.longcat.chat/openai`) and `authHeader` (`Authorization: Bearer`).
-- **#535 — Pinned model override:** `body.model` is now correctly set to `pinnedModel` when context-cache protection is active.
-- **#532 — OpenCode Go key validation:** Now uses the `zen/v1` test endpoint (`testKeyBaseUrl`) — same key works for both tiers.
-
-#### CLI & Tools
-
-- **#527 — Claude Code + Codex loop:** `tool_result` blocks are now converted to text instead of dropped, stopping infinite tool-result loops.
-- **#524 — OpenCode config save:** Added `saveOpenCodeConfig()` handler (XDG_CONFIG_HOME aware, writes TOML).
-- **#521 — Login stuck:** Login no longer freezes after skipping password setup — redirects correctly to onboarding.
-- **#522 — API Manager:** Removed misleading "Copy masked key" button (replaced with a lock icon tooltip).
-- **#532 — OpenCode Go config:** Guide settings handler now handles `opencode` toolId.
-
-#### Developer Experience
-
-- **#489 — Antigravity:** Missing `googleProjectId` returns a structured 422 error with reconnect guidance instead of a cryptic crash.
-- **#510 — Windows paths:** MSYS2/Git-Bash paths (`/c/Program Files/...`) are now normalized to `C:\Program Files\...` automatically.
-- **#492 — CLI startup:** `omniroute` CLI now detects `mise`/`nvm`-managed Node when `app/server.js` is missing and shows targeted fix instructions.
-
----
-
-### 📖 Documentation Updates
-
-- **#513** — Docker password reset: `INITIAL_PASSWORD` env var workaround documented
-- **#520** — pnpm: `pnpm approve-builds better-sqlite3` step documented
-
----
-
-### ✅ Issues Resolved in v3.0.0
-
-`#464` `#488` `#489` `#492` `#510` `#513` `#520` `#521` `#522` `#524` `#527` `#529` `#532` `#535` `#536` `#537`
-
----
-
-### 🔀 Community PRs Merged
-
-| PR       | Author       | Summary                                                                |
-| -------- | ------------ | ---------------------------------------------------------------------- |
-| **#530** | @kang-heewon | OpenCode Zen + Go providers with `OpencodeExecutor` and improved tests |
-
----
-
-## [3.0.0-rc.7] - 2026-03-23
-
-### 🔧 Improvements (sub2api Gap Analysis — T05, T08, T09, T13, T14)
-
-- **T05** — Rate-limit DB persistence: `setConnectionRateLimitUntil()`, `isConnectionRateLimited()`, `getRateLimitedConnections()` in `providers.ts`. The existing `rate_limited_until` column is now exposed as a dedicated API — OAuth token refresh must NOT touch this field to prevent rate-limit loops.
-- **T08** — Per-API-key session limit: `max_sessions INTEGER DEFAULT 0` added to `api_keys` via auto-migration. `sessionManager.ts` gains `registerKeySession()`, `unregisterKeySession()`, `checkSessionLimit()`, and `getActiveSessionCountForKey()`. Callers in `chatCore.js` can enforce the limit and decrement on `req.close`.
-- **T09** — Codex vs Spark rate-limit scopes: `getCodexModelScope()` and `getCodexRateLimitKey()` in `codex.ts`. Standard models (`gpt-5.x-codex`, `codex-mini`) get scope `"codex"`; spark models (`codex-spark*`) get scope `"spark"`. Rate-limit keys should be `${accountId}:${scope}` so exhausting one pool doesn't block the other.
-- **T13** — Stale quota display fix: `getEffectiveQuotaUsage(used, resetAt)` returns `0` when the reset window has passed; `formatResetCountdown(resetAt)` returns a human-readable countdown string (e.g. `"2h 35m"`). Both exported from `providers.ts` + `localDb.ts` for dashboard consumption.
-- **T14** — Proxy fast-fail: new `src/lib/proxyHealth.ts` with `isProxyReachable(proxyUrl, timeoutMs=2000)` (TCP check, ≤2s instead of 30s timeout), `getCachedProxyHealth()`, `invalidateProxyHealth()`, and `getAllProxyHealthStatuses()`. Results cached 30s by default; configurable via `PROXY_FAST_FAIL_TIMEOUT_MS` / `PROXY_HEALTH_CACHE_TTL_MS`.
-
-### 🧪 Tests
-
-- Test suite: **832 tests, 0 failures**
-
----
-
-## [3.0.0-rc.6] - 2026-03-23
-
-### 🔧 Bug Fixes & Improvements (sub2api Gap Analysis — T01–T15)
-
-- **T01** — `requested_model` column in `call_logs` (migration 009): track which model the client originally requested vs the actual routed model. Enables fallback rate analytics.
-- **T02** — Strip empty text blocks from nested `tool_result.content`: prevents Anthropic 400 errors (`text content blocks must be non-empty`) when Claude Code chains tool results.
-- **T03** — Parse `x-codex-5h-*` / `x-codex-7d-*` headers: `parseCodexQuotaHeaders()` + `getCodexResetTime()` extract Codex quota windows for precise cooldown scheduling instead of generic 5-min fallback.
-- **T04** — `X-Session-Id` header for external sticky routing: `extractExternalSessionId()` in `sessionManager.ts` reads `x-session-id` / `x-omniroute-session` headers with `ext:` prefix to avoid collision with internal SHA-256 session IDs. Nginx-compatible (hyphenated header).
-- **T06** — Account deactivated → permanent block: `isAccountDeactivated()` in `accountFallback.ts` detects 401 deactivation signals and applies a 1-year cooldown to prevent retrying permanently dead accounts.
-- **T07** — X-Forwarded-For IP validation: new `src/lib/ipUtils.ts` with `extractClientIp()` and `getClientIpFromRequest()` — skips `unknown`/non-IP entries in `X-Forwarded-For` chains (Nginx/proxy-forwarded requests).
-- **T10** — Credits exhausted → distinct fallback: `isCreditsExhausted()` in `accountFallback.ts` returns 1h cooldown with `creditsExhausted` flag, distinct from generic 429 rate limiting.
-- **T11** — `max` reasoning effort → 131072 budget tokens: `EFFORT_BUDGETS` and `THINKING_LEVEL_MAP` updated; reverse mapping now returns `"max"` for full-budget responses. Unit test updated.
-- **T12** — MiniMax M2.7 pricing entries added: `minimax-m2.7`, `MiniMax-M2.7`, `minimax-m2.7-highspeed` added to pricing table (sub2api PR #1120). M2.5/GLM-4.7/GLM-5/Kimi pricing already existed.
-- **T15** — Array content normalization: `normalizeContentToString()` helper in `openai-to-claude.ts` correctly collapses array-formatted system/tool messages to string before sending to Anthropic.
-
-### 🧪 Tests
-
-- Test suite: **832 tests, 0 failures** (unchanged from rc.5)
-
----
-
-## [3.0.0-rc.5] - 2026-03-22
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **#464** — Registered Keys Provisioning API: auto-issue API keys with per-provider & per-account quota enforcement
-  - `POST /api/v1/registered-keys` — issue keys with idempotency support
-  - `GET /api/v1/registered-keys` — list (masked) registered keys
-  - `GET /api/v1/registered-keys/{id}` — get key metadata
-  - `DELETE /api/v1/registered-keys/{id}` / `POST ../{id}/revoke` — revoke keys
-  - `GET /api/v1/quotas/check` — pre-validate before issuing
-  - `PUT /api/v1/providers/{id}/limits` — set provider issuance limits
-  - `PUT /api/v1/accounts/{id}/limits` — set account issuance limits
-  - `POST /api/v1/issues/report` — optional GitHub issue reporting
-  - DB migration 008: `registered_keys`, `provider_key_limits`, `account_key_limits` tables
-
----
-
-## [3.0.0-rc.4] - 2026-03-22
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **#530 (PR)** — OpenCode Zen and OpenCode Go providers added (by @kang-heewon)
-  - New `OpencodeExecutor` with multi-format routing (`/chat/completions`, `/messages`, `/responses`)
-  - 7 models across both tiers
-
----
-
-## [3.0.0-rc.3] - 2026-03-22
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **#529** — Provider icons now use [@lobehub/icons](https://github.com/lobehub/lobe-icons) with graceful PNG fallback and a `ProviderIcon` component (130+ providers supported)
-- **#488** — Auto-update model lists every 24h via `modelSyncScheduler` (configurable via `MODEL_SYNC_INTERVAL_HOURS`)
-
-### 🔧 Bug Fixes
-
-- **#537** — Gemini CLI OAuth: now shows clear actionable error when `GEMINI_OAUTH_CLIENT_SECRET` is missing in Docker/self-hosted deployments
-
----
-
-## [3.0.0-rc.2] - 2026-03-22
-
-### 🔧 Bug Fixes
-
-- **#536** — LongCat AI key validation: fixed baseUrl (`api.longcat.chat/openai`) and authHeader (`Authorization: Bearer`)
-- **#535** — Pinned model override: `body.model` is now set to `pinnedModel` when context-cache protection detects a pinned model
-- **#524** — OpenCode config now saved correctly: added `saveOpenCodeConfig()` handler (XDG_CONFIG_HOME aware, writes TOML)
-
----
-
-## [3.0.0-rc.1] - 2026-03-22
-
-### 🔧 Bug Fixes
-
-- **#521** — Login no longer gets stuck after skipping password setup (redirects to onboarding)
-- **#522** — API Manager: Removed misleading "Copy masked key" button (replaced with lock icon tooltip)
-- **#527** — Claude Code + Codex superpowers loop: `tool_result` blocks now converted to text instead of dropped
-- **#532** — OpenCode GO API key validation now uses the correct `zen/v1` endpoint (`testKeyBaseUrl`)
-- **#489** — Antigravity: missing `googleProjectId` returns structured 422 error with reconnect guidance
-- **#510** — Windows: MSYS2/Git-Bash paths (`/c/Program Files/...`) are now normalized to `C:\Program Files\...`
-- **#492** — `omniroute` CLI now detects `mise`/`nvm` when `app/server.js` is missing and shows targeted fix
-
-### 📖 Documentation
-
-- **#513** — Docker password reset: `INITIAL_PASSWORD` env var workaround documented
-- **#520** — pnpm: `pnpm approve-builds better-sqlite3` documented
-
-### ✅ Closed Issues
-
-#489, #492, #510, #513, #520, #521, #522, #525, #527, #532
-
----
-
-## [2.9.5] — 2026-03-22
-
-> Sprint: New OpenCode providers, embedding credentials fix, CLI masked key bug, CACHE_TAG_PATTERN fix.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **CLI tools save masked API key to config files** — `claude-settings`, `cline-settings`, and `openclaw-settings` POST routes now accept a `keyId` param and resolve the real API key from DB before writing to disk. `ClaudeToolCard` updated to send `keyId` instead of the masked display string. Fixes #523, #526.
-- **Custom embedding providers: `No credentials` error** — `/v1/embeddings` now tracks `credentialsProviderId` separately from the routing prefix, so credentials are fetched from the matching provider node ID rather than the public prefix string. Fixes a regression where `google/gemini-embedding-001` and similar custom-provider models would always fail with a credentials error. Fixes #532-related. (PR #528 by @jacob2826)
-- **Context cache protection regex misses `
-` prefix** — `CACHE_TAG_PATTERN` in `comboAgentMiddleware.ts` updated to match both literal `
-` (backslash-n) and actual newline U+000A that `combo.ts` streaming injects around the `<omniModel>` tag after fix #515. Fixes #531.
-
-### ✨ New Providers
-
-- **OpenCode Zen** — Free tier gateway at `opencode.ai/zen/v1` with 3 models: `minimax-m2.5-free`, `big-pickle`, `gpt-5-nano`
-- **OpenCode Go** — Subscription service at `opencode.ai/zen/go/v1` with 4 models: `glm-5`, `kimi-k2.5`, `minimax-m2.7` (Claude format), `minimax-m2.5` (Claude format)
-- Both providers use the new `OpencodeExecutor` which routes dynamically to `/chat/completions`, `/messages`, `/responses`, or `/models/{model}:generateContent` based on the requested model. (PR #530 by @kang-heewon)
-
----
-
-## [2.9.4] — 2026-03-21
-
-> Sprint: Bug fixes — preserve Codex prompt cache key, fix tagContent JSON escaping, sync expired token status to DB.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(translator)**: Preserve `prompt_cache_key` in Responses API → Chat Completions translation (#517)
-  — The field is a cache-affinity signal used by Codex; stripping it was preventing prompt cache hits.
-  Fixed in `openai-responses.ts` and `responsesApiHelper.ts`.
-
-- **fix(combo)**: Escape `
-` in `tagContent` so injected JSON string is valid (#515)
-  — Template literal newlines (U+000A) are not allowed unescaped inside JSON string values.
-  Replaced with `\n` literal sequences in `open-sse/services/combo.ts`.
-
-- **fix(usage)**: Sync expired token status back to DB on live auth failure (#491)
-  — When the Limits & Quotas live check returns 401/403, the connection `testStatus` is now updated
-  to `"expired"` in the database so the Providers page reflects the same degraded state.
-  Fixed in `src/app/api/usage/[connectionId]/route.ts`.
-
----
-
-## [2.9.3] — 2026-03-21
-
-> Sprint: Add 5 new free AI providers — LongCat, Pollinations, Cloudflare AI, Scaleway, AI/ML API.
-
-### ✨ New Providers
-
-- **feat(providers/longcat)**: Add LongCat AI (`lc/`) — 50M tokens/day free (Flash-Lite) + 500K/day (Chat/Thinking) during public beta. OpenAI-compatible, standard Bearer auth.
-- **feat(providers/pollinations)**: Add Pollinations AI (`pol/`) — no API key required. Proxies GPT-5, Claude, Gemini, DeepSeek V3, Llama 4 (1 req/15s free). Custom executor handles optional auth.
-- **feat(providers/cloudflare-ai)**: Add Cloudflare Workers AI (`cf/`) — 10K Neurons/day free (~150 LLM responses or 500s Whisper audio). 50+ models on global edge. Custom executor builds dynamic URL with `accountId` from credentials.
-- **feat(providers/scaleway)**: Add Scaleway Generative APIs (`scw/`) — 1M free tokens for new accounts. EU/GDPR compliant (Paris). Qwen3 235B, Llama 3.1 70B, Mistral Small 3.2.
-- **feat(providers/aimlapi)**: Add AI/ML API (`aiml/`) — $0.025/day free credit, 200+ models (GPT-4o, Claude, Gemini, Llama) via single aggregator endpoint.
-
-### 🔄 Provider Updates
-
-- **feat(providers/together)**: Add `hasFree: true` + 3 permanently free model IDs: `Llama-3.3-70B-Instruct-Turbo-Free`, `Llama-Vision-Free`, `DeepSeek-R1-Distill-Llama-70B-Free`
-- **feat(providers/gemini)**: Add `hasFree: true` + `freeNote` (1,500 req/day, no credit card needed, aistudio.google.com)
-- **chore(providers/gemini)**: Rename display name to `Gemini (Google AI Studio)` for clarity
-
-### ⚙️ Infrastructure
-
-- **feat(executors/pollinations)**: New `PollinationsExecutor` — omits `Authorization` header when no API key provided
-- **feat(executors/cloudflare-ai)**: New `CloudflareAIExecutor` — dynamic URL construction requires `accountId` in provider credentials
-- **feat(executors)**: Register `pollinations`, `pol`, `cloudflare-ai`, `cf` executor mappings
-
-### 📝 Documentation
-
-- **docs(readme)**: Expanded free combo stack to 11 providers ($0 forever)
-- **docs(readme)**: Added 4 new free provider sections (LongCat, Pollinations, Cloudflare AI, Scaleway) with model tables
-- **docs(readme)**: Updated pricing table with 4 new free tier rows
-- **docs(i18n/pt-BR)**: Updated pricing table + added LongCat/Pollinations/Cloudflare AI/Scaleway sections in Portuguese
-- **docs(new-features/ai)**: 10 task spec files + master implementation plan in `docs/new-features/ai/`
-
-### 🧪 Tests
-
-- Test suite: **821 tests, 0 failures** (unchanged)
-
----
-
-## [2.9.2] — 2026-03-21
-
-> Sprint: Fix media transcription (Deepgram/HuggingFace Content-Type, language detection) and TTS error display.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(transcription)**: Deepgram and HuggingFace audio transcription now correctly map `video/mp4` → `audio/mp4` and other media MIME types via new `resolveAudioContentType()` helper. Previously, uploading `.mp4` files consistently returned "No speech detected" because Deepgram was receiving `Content-Type: video/mp4`.
-- **fix(transcription)**: Added `detect_language=true` to Deepgram requests — auto-detects audio language (Portuguese, Spanish, etc.) instead of defaulting to English. Fixes non-English transcriptions returning empty or garbage results.
-- **fix(transcription)**: Added `punctuate=true` to Deepgram requests for higher-quality transcription output with correct punctuation.
-- **fix(tts)**: `[object Object]` error display in Text-to-Speech responses fixed in both `audioSpeech.ts` and `audioTranscription.ts`. The `upstreamErrorResponse()` function now correctly extracts nested string messages from providers like ElevenLabs that return `{ error: { message: "...", status_code: 401 } }` instead of a flat error string.
-
-### 🧪 Tests
-
-- Test suite: **821 tests, 0 failures** (unchanged)
-
-### Triaged Issues
-
-- **#508** — Tool call format regression: requested proxy logs and provider chain info (`needs-info`)
-- **#510** — Windows CLI healthcheck path: requested shell/Node version info (`needs-info`)
-- **#485** — Kiro MCP tool calls: closed as external Kiro issue (not OmniRoute)
-- **#442** — Baseten /models endpoint: closed (documented manual workaround)
-- **#464** — Key provisioning API: acknowledged as roadmap item
-
----
-
-## [2.9.1] — 2026-03-21
-
-> Sprint: Fix SSE omniModel data loss, merge per-protocol model compatibility.
-
-### Bug Fixes
-
-- **#511** — Critical: `<omniModel>` tag was sent after `finish_reason:stop` in SSE streams, causing data loss. Tag is now injected into the first non-empty content chunk, guaranteeing delivery before SDKs close the connection.
-
-### Merged PRs
-
-- **PR #512** (@zhangqiang8vip): Per-protocol model compatibility — `normalizeToolCallId` and `preserveOpenAIDeveloperRole` can now be configured per client protocol (OpenAI, Claude, Responses API). New `compatByProtocol` field in model config with Zod validation.
-
-### Triaged Issues
-
-- **#510** — Windows CLI healthcheck_failed: requested PATH/version info
-- **#509** — Turbopack Electron regression: upstream Next.js bug, documented workarounds
-- **#508** — macOS black screen: suggested `--disable-gpu` workaround
-
----
-
-## [2.9.0] — 2026-03-20
-
-> Sprint: Cross-platform machineId fix, per-API-key rate limits, streaming context cache, Alibaba DashScope, search analytics, ZWS v5, and 8 issues closed.
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **feat(search)**: Search Analytics tab in `/dashboard/analytics` — provider breakdown, cache hit rate, cost tracking. New API: `GET /api/v1/search/analytics` (#feat/search-provider-routing)
-- **feat(provider)**: Alibaba Cloud DashScope added with custom endpoint path validation — configurable `chatPath` and `modelsPath` per node (#feat/custom-endpoint-paths)
-- **feat(api)**: Per-API-key request-count limits — `max_requests_per_day` and `max_requests_per_minute` columns with in-memory sliding-window enforcement returning HTTP 429 (#452)
-- **feat(dev)**: ZWS v5 — HMR leak fix (485 DB connections → 1), memory 2.4GB → 195MB, `globalThis` singletons, Edge Runtime warning fix (@zhangqiang8vip)
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(#506)**: Cross-platform `machineId` — `getMachineIdRaw()` rewritten with try/catch waterfall (Windows REG.exe → macOS ioreg → Linux file read → hostname → `os.hostname()`). Eliminates `process.platform` branching that Next.js bundler dead-code-eliminated, fixing `'head' is not recognized` on Windows. Also fixes #466.
-- **fix(#493)**: Custom provider model naming — removed incorrect prefix stripping in `DefaultExecutor.transformRequest()` that mangled org-scoped model IDs like `zai-org/GLM-5-FP8`.
-- **fix(#490)**: Streaming + context cache protection — `TransformStream` intercepts SSE to inject `<omniModel>` tag before `[DONE]` marker, enabling context cache protection for streaming responses.
-- **fix(#458)**: Combo schema validation — `system_message`, `tool_filter_regex`, `context_cache_protection` fields now pass Zod validation on save.
-- **fix(#487)**: KIRO MITM card cleanup — removed ZWS_README, generified `AntigravityToolCard` to use dynamic tool metadata.
-
-### 🧪 Tests
-
-- Added Anthropic-format tools filter unit tests (PR #397) — 8 regression tests for `tool.name` without `.function` wrapper
-- Test suite: **821 tests, 0 failures** (up from 813)
-
-### 📋 Issues Closed (8)
-
-- **#506** — Windows machineId `head` not recognized (fixed)
-- **#493** — Custom provider model naming (fixed)
-- **#490** — Streaming context cache (fixed)
-- **#452** — Per-API-key request limits (implemented)
-- **#466** — Windows login failure (same root cause as #506)
-- **#504** — MITM inactive (expected behavior)
-- **#462** — Gemini CLI PSA (resolved)
-- **#434** — Electron app crash (duplicate of #402)
-
-## [2.8.9] — 2026-03-20
-
-> Sprint: Merge community PRs, fix KIRO MITM card, dependency updates.
-
-### Merged PRs
-
-- **PR #498** (@Sajid11194): Fix Windows machine ID crash (`undefined\REG.exe`). Replaces `node-machine-id` with native OS registry queries. **Closes #486.**
-- **PR #497** (@zhangqiang8vip): Fix dev-mode HMR resource leaks — 485 leaked DB connections → 1, memory 2.4GB → 195MB. `globalThis` singletons, Edge Runtime warning fix, Windows test stability. (+1168/-338 across 22 files)
-- **PRs #499-503** (Dependabot): GitHub Actions updates — `docker/build-push-action@7`, `actions/checkout@6`, `peter-evans/dockerhub-description@5`, `docker/setup-qemu-action@4`, `docker/login-action@4`.
-
-### Bug Fixes
-
-- **#505** — KIRO MITM card now displays tool-specific instructions (`api.anthropic.com`) instead of Antigravity-specific text.
-- **#504** — Responded with UX clarification (MITM "Inactive" is expected behavior when proxy is not running).
-
----
-
-## [2.8.8] — 2026-03-20
-
-> Sprint: Fix OAuth batch test crash, add "Test All" button to individual provider pages.
-
-### Bug Fixes
-
-- **OAuth batch test crash** (ERR_CONNECTION_REFUSED): Replaced sequential for-loop with 5-connection concurrency limit + 30s per-connection timeout via `Promise.race()` + `Promise.allSettled()`. Prevents server crash when testing large OAuth provider groups (~30+ connections).
-
-### Features
-
-- **"Test All" button on provider pages**: Individual provider pages (e.g., `/providers/codex`) now show a "Test All" button in the Connections header when there are 2+ connections. Uses `POST /api/providers/test-batch` with `{mode: "provider", providerId}`. Results displayed in a modal with pass/fail summary and per-connection diagnosis.
-
----
-
-## [2.8.7] — 2026-03-20
-
-> Sprint: Merge PR #495 (Bottleneck 429 drop), fix #496 (custom embedding providers), triage features.
-
-### Bug Fixes
-
-- **Bottleneck 429 infinite wait** (PR #495 by @xandr0s): On 429, `limiter.stop({ dropWaitingJobs: true })` immediately fails all queued requests so upstream callers can trigger fallback. Limiter is deleted from Map so next request creates a fresh instance.
-- **Custom embedding models unresolvable** (#496): `POST /v1/embeddings` now resolves custom embedding models from ALL provider_nodes (not just localhost). Enables models like `google/gemini-embedding-001` added via dashboard.
-
-### Issues Responded
-
-- **#452** — Per-API-key request-count limits (acknowledged, on roadmap)
-- **#464** — Auto-issue API keys with provider/account limits (needs more detail)
-- **#488** — Auto-update model lists (acknowledged, on roadmap)
-- **#496** — Custom embedding provider resolution (fixed)
-
----
-
-## [2.8.6] — 2026-03-20
-
-> Sprint: Merge PR #494 (MiniMax role fix), fix KIRO MITM dashboard, triage 8 issues.
-
-### Features
-
-- **MiniMax developer→system role fix** (PR #494 by @zhangqiang8vip): Per-model `preserveDeveloperRole` toggle. Adds "Compatibility" UI in providers page. Fixes 422 "role param error" for MiniMax and similar gateways.
-- **roleNormalizer**: `normalizeDeveloperRole()` now accepts `preserveDeveloperRole` parameter with tri-state behavior (undefined=keep, true=keep, false=convert).
-- **DB**: New `getModelPreserveOpenAIDeveloperRole()` and `mergeModelCompatOverride()` in `models.ts`.
-
-### Bug Fixes
-
-- **KIRO MITM dashboard** (#481/#487): `CLIToolsPageClient` now routes any `configType: "mitm"` tool to `AntigravityToolCard` (MITM Start/Stop controls). Previously only Antigravity was hardcoded.
-- **AntigravityToolCard generic**: Uses `tool.image`, `tool.description`, `tool.id` instead of hardcoded Antigravity values. Guards against missing `defaultModels`.
-
-### Cleanup
-
-- Removed `ZWS_README_V2.md` (development-only docs from PR #494).
-
-### Issues Triaged (8)
-
-- **#487** — Closed (KIRO MITM fixed in this release)
-- **#486** — needs-info (Windows REG.exe PATH issue)
-- **#489** — needs-info (Antigravity projectId missing, OAuth reconnect needed)
-- **#492** — needs-info (missing app/server.js on mise-managed Node)
-- **#490** — Acknowledged (streaming + context cache blocking, fix planned)
-- **#491** — Acknowledged (Codex auth state inconsistency)
-- **#493** — Acknowledged (Modal provider model name prefix, workaround provided)
-- **#488** — Feature request backlog (auto-update model lists)
-
----
-
-## [2.8.5] — 2026-03-19
-
-> Sprint: Fix zombie SSE streams, context cache first-turn, KIRO MITM, and triage 5 external issues.
-
-### Bug Fixes
-
-- **Zombie SSE Streams** (#473): Reduce `STREAM_IDLE_TIMEOUT_MS` from 300s → 120s for faster combo fallback when providers hang mid-stream. Configurable via env var.
-- **Context Cache Tag** (#474): Fix `injectModelTag()` to handle first-turn requests (no assistant messages) — context cache protection now works from the very first response.
-- **KIRO MITM** (#481): Change KIRO `configType` from `guide` → `mitm` so the dashboard renders MITM Start/Stop controls.
-- **E2E Test** (CI): Fix `providers-bailian-coding-plan.spec.ts` — dismiss pre-existing modal overlay before clicking Add API Key button.
-
-### Closed Issues
-
-- #473 — Zombie SSE streams bypass combo fallback
-- #474 — Context cache `<omniModel>` tag missing on first turn
-- #481 — MITM for KIRO not activatable from dashboard
-- #468 — Gemini CLI remote server (superseded by #462 deprecation)
-- #438 — Claude unable to write files (external CLI issue)
-- #439 — AppImage doesn't work (documented libfuse2 workaround)
-- #402 — ARM64 DMG "damaged" (documented xattr -cr workaround)
-- #460 — CLI not runnable on Windows (documented PATH fix)
-
----
-
-## [2.8.4] — 2026-03-19
-
-> Sprint: Gemini CLI deprecation, VM guide i18n fix, dependabot security fix, provider schema expansion.
-
-### Features
-
-- **Gemini CLI Deprecation** (#462): Mark `gemini-cli` provider as deprecated with warning — Google restricts third-party OAuth usage from March 2026
-- **Provider Schema** (#462): Expand Zod validation with `deprecated`, `deprecationReason`, `hasFree`, `freeNote`, `authHint`, `apiHint` optional fields
-
-### Bug Fixes
-
-- **VM Guide i18n** (#471): Add `VM_DEPLOYMENT_GUIDE.md` to i18n translation pipeline, regenerate all 30 locale translations from English source (were stuck in Portuguese)
-
-### Security
-
-- **deps**: Bump `flatted` 3.3.3 → 3.4.2 — fixes CWE-1321 prototype pollution (#484, @dependabot)
-
-### Closed Issues
-
-- #472 — Model Aliases regression (fixed in v2.8.2)
-- #471 — VM guide translations broken
-- #483 — Trailing `data: null` after `[DONE]` (fixed in v2.8.3)
-
-### Merged PRs
-
-- #484 — deps: bump flatted from 3.3.3 to 3.4.2 (@dependabot)
-
----
-
-## [2.8.3] — 2026-03-19
-
-> Sprint: Czech i18n, SSE protocol fix, VM guide translation.
-
-### Features
-
-- **Czech Language** (#482): Full Czech (cs) i18n — 22 docs, 2606 UI strings, language switcher updates (@zen0bit)
-- **VM Deployment Guide**: Translated from Portuguese to English as the source document (@zen0bit)
-
-### Bug Fixes
-
-- **SSE Protocol** (#483): Stop sending trailing `data: null` after `[DONE]` signal — fixes `AI_TypeValidationError` in strict AI SDK clients (Zod-based validators)
-
-### Merged PRs
-
-- #482 — Add Czech language + Fix VM_DEPLOYMENT_GUIDE.md English source (@zen0bit)
-
----
-
-## [2.8.2] — 2026-03-19
-
-> Sprint: 2 merged PRs, model aliases routing fix, log export, and issue triage.
-
-### Features
-
-- **Log Export**: New Export button on `/dashboard/logs` with time range dropdown (1h, 6h, 12h, 24h). Downloads JSON of request/proxy/call logs via `/api/logs/export` API (#user-request)
-
-### Bug Fixes
-
-- **Model Aliases Routing** (#472): Settings → Model Aliases now correctly affect provider routing, not just format detection. Previously `resolveModelAlias()` output was only used for `getModelTargetFormat()` but the original model ID was sent to the provider
-- **Stream Flush Usage** (#480): Usage data from the last SSE event in the buffer is now correctly extracted during stream flush (merged from @prakersh)
-
-### Merged PRs
-
-- #480 — Extract usage from remaining buffer in flush handler (@prakersh)
-- #479 — Add missing Codex 5.3/5.4 and Anthropic model ID pricing entries (@prakersh)
-
----
-
-## [2.8.1] — 2026-03-19
-
-> Sprint: Five community PRs — streaming call log fixes, Kiro compatibility, cache token analytics, Chinese translation, and configurable tool call IDs.
-
-### ✨ Features
-
-- **feat(logs)**: Call log response content now correctly accumulated from raw provider chunks (OpenAI/Claude/Gemini) before translation, fixing empty response payloads in streaming mode (#470, @zhangqiang8vip)
-- **feat(providers)**: Per-model configurable 9-char tool call ID normalization (Mistral-style) — only models with the option enabled get truncated IDs (#470)
-- **feat(api)**: Key PATCH API expanded to support `allowedConnections`, `name`, `autoResolve`, `isActive`, and `accessSchedule` fields (#470)
-- **feat(dashboard)**: Response-first layout in request log detail UI (#470)
-- **feat(i18n)**: Improved Chinese (zh-CN) translation — complete retranslation (#475, @only4copilot)
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(kiro)**: Strip injected `model` field from request body — Kiro API rejects unknown top-level fields (#478, @prakersh)
-- **fix(usage)**: Include cache read + cache creation tokens in usage history input totals for accurate analytics (#477, @prakersh)
-- **fix(callLogs)**: Support Claude format usage fields (`input_tokens`/`output_tokens`) alongside OpenAI format, include all cache token variants (#476, @prakersh)
-
----
-
-## [2.8.0] — 2026-03-19
-
-> Sprint: Bailian Coding Plan provider with editable base URLs, plus community contributions for Alibaba Cloud and Kimi Coding.
-
-### ✨ Features
-
-- **feat(providers)**: Added Bailian Coding Plan (`bailian-coding-plan`) — Alibaba Model Studio with Anthropic-compatible API. Static catalog of 8 models including Qwen3.5 Plus, Qwen3 Coder, MiniMax M2.5, GLM 5, and Kimi K2.5. Includes custom auth validation (400=valid, 401/403=invalid) (#467, @Mind-Dragon)
-- **feat(admin)**: Editable default URL in Provider Admin create/edit flows — users can configure custom base URLs per connection. Persisted in `providerSpecificData.baseUrl` with Zod schema validation rejecting non-http(s) schemes (#467)
-
-### 🧪 Tests
-
-- Added 30+ unit tests and 2 e2e scenarios for Bailian Coding Plan provider covering auth validation, schema hardening, route-level behavior, and cross-layer integration
-
----
-
-## [2.7.10] — 2026-03-19
-
-> Sprint: Two new community-contributed providers (Alibaba Cloud Coding, Kimi Coding API-key) and Docker pino fix.
-
-### ✨ Features
-
-- **feat(providers)**: Added Alibaba Cloud Coding Plan support with two OpenAI-compatible endpoints — `alicode` (China) and `alicode-intl` (International), each with 8 models (#465, @dtk1985)
-- **feat(providers)**: Added dedicated `kimi-coding-apikey` provider path — API-key-based Kimi Coding access is no longer forced through OAuth-only `kimi-coding` route. Includes registry, constants, models API, config, and validation test (#463, @Mind-Dragon)
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(docker)**: Added missing `split2` dependency to Docker image — `pino-abstract-transport` requires it at runtime but it was not being copied into the standalone container, causing `Cannot find module 'split2'` crashes (#459)
-
----
-
-## [2.7.9] — 2026-03-18
-
-> Sprint: Codex responses subpath passthrough natively supported, Windows MITM crash fixed, and Combos agent schemas adjusted.
-
-### ✨ Features
-
-- **feat(codex)**: Native responses subpath passthrough for Codex — natively routes `POST /v1/responses/compact` to Codex upstream, maintaining Claude Code compatibility without stripping the `/compact` suffix (#457)
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(combos)**: Zod schemas (`updateComboSchema` and `createComboSchema`) now include `system_message`, `tool_filter_regex`, and `context_cache_protection`. Fixes bug where agent-specific settings created via the dashboard were silently discarded by the backend validation layer (#458)
-- **fix(mitm)**: Kiro MITM profile crash on Windows fixed — `node-machine-id` failed due to missing `REG.exe` env, and the fallback threw a fatal `crypto is not defined` error. Fallback now safely and correctly imports crypto (#456)
-
----
-
-## [2.7.8] — 2026-03-18
-
-> Sprint: Budget save bug + combo agent features UI + omniModel tag security fix.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(budget)**: "Save Limits" no longer returns 422 — `warningThreshold` is now correctly sent as fraction (0–1) instead of percentage (0–100) (#451)
-- **fix(combos)**: `<omniModel>` internal cache tag is now stripped before forwarding requests to providers, preventing cache session breaks (#454)
-
-### ✨ Features
-
-- **feat(combos)**: Agent Features section added to combo create/edit modal — expose `system_message` override, `tool_filter_regex`, and `context_cache_protection` directly from the dashboard (#454)
-
----
-
-## [2.7.7] — 2026-03-18
-
-> Sprint: Docker pino crash, Codex CLI responses worker fix, package-lock sync.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(docker)**: `pino-abstract-transport` and `pino-pretty` now explicitly copied in Docker runner stage — Next.js standalone trace misses these peer deps, causing `Cannot find module pino-abstract-transport` crash on startup (#449)
-- **fix(responses)**: Remove `initTranslators()` from `/v1/responses` route — was crashing Next.js worker with `the worker has exited` uncaughtException on Codex CLI requests (#450)
-
-### 🔧 Maintenance
-
-- **chore(deps)**: `package-lock.json` now committed on every version bump to ensure Docker `npm ci` uses exact dependency versions
-
----
-
-## [2.7.5] — 2026-03-18
-
-> Sprint: UX improvements and Windows CLI healthcheck fix.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(ux)**: Show default password hint on login page — new users now see `"Default password: 123456"` below the password input (#437)
-- **fix(cli)**: Claude CLI and other npm-installed tools now correctly detected as runnable on Windows — spawn uses `shell:true` to resolve `.cmd` wrappers via PATHEXT (#447)
-
----
-
-## [2.7.4] — 2026-03-18
-
-> Sprint: Search Tools dashboard, i18n fixes, Copilot limits, Serper validation fix.
-
-### 🚀 Features
-
-- **feat(search)**: Add Search Playground (10th endpoint), Search Tools page with Compare Providers/Rerank Pipeline/Search History, local rerank routing, auth guards on search API (#443 by @Regis-RCR)
-  - New route: `/dashboard/search-tools`
-  - Sidebar entry under Debug section
-  - `GET /api/search/providers` and `GET /api/search/stats` with auth guards
-  - Local provider_nodes routing for `/v1/rerank`
-  - 30+ i18n keys in search namespace
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(search)**: Fix Brave news normalizer (was returning 0 results), enforce max_results truncation post-normalization, fix Endpoints page fetch URL (#443 by @Regis-RCR)
-- **fix(analytics)**: Localize analytics day/date labels — replace hardcoded Portuguese strings with `Intl.DateTimeFormat(locale)` (#444 by @hijak)
-- **fix(copilot)**: Correct GitHub Copilot account type display, filter misleading unlimited quota rows from limits dashboard (#445 by @hijak)
-- **fix(providers)**: Stop rejecting valid Serper API keys — treat non-4xx responses as valid authentication (#446 by @hijak)
-
----
-
-## [2.7.3] — 2026-03-18
-
-> Sprint: Codex direct API quota fallback fix.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(codex)**: Block weekly-exhausted accounts in direct API fallback (#440)
-  - `resolveQuotaWindow()` prefix matching: `"weekly"` now matches `"weekly (7d)"` cache keys
-  - `applyCodexWindowPolicy()` enforces `useWeekly`/`use5h` toggles correctly
-  - 4 new regression tests (766 total)
-
----
-
-## [2.7.2] — 2026-03-18
-
-> Sprint: Light mode UI contrast fixes.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(logs)**: Fix light mode contrast in request logs filter buttons and combo badge (#378)
-  - Error/Success/Combo filter buttons now readable in light mode
-  - Combo row badge uses stronger violet in light mode
-
----
-
-## [2.7.1] — 2026-03-17
-
-> Sprint: Unified web search routing (POST /v1/search) with 5 providers + Next.js 16.1.7 security fixes (6 CVEs).
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **feat(search)**: Unified web search routing — `POST /v1/search` with 5 providers (Serper, Brave, Perplexity, Exa, Tavily)
-  - Auto-failover across providers, 6,500+ free searches/month
-  - In-memory cache with request coalescing (configurable TTL)
-  - Dashboard: Search Analytics tab in `/dashboard/analytics` with provider breakdown, cache hit rate, cost tracking
-  - New API: `GET /api/v1/search/analytics` for search request statistics
-  - DB migration: `request_type` column on `call_logs` for non-chat request tracking
-  - Zod validation (`v1SearchSchema`), auth-gated, cost recorded via `recordCost()`
-
-### 🔒 Security
-
-- **deps**: Next.js 16.1.6 → 16.1.7 — fixes 6 CVEs:
-  - **Critical**: CVE-2026-29057 (HTTP request smuggling via http-proxy)
-  - **High**: CVE-2026-27977, CVE-2026-27978 (WebSocket + Server Actions)
-  - **Medium**: CVE-2026-27979, CVE-2026-27980, CVE-2026-jcc7
-
-### 📁 New Files
-
-| File                                                             | Purpose                                    |
-| ---------------------------------------------------------------- | ------------------------------------------ |
-| `open-sse/handlers/search.ts`                                    | Search handler with 5-provider routing     |
-| `open-sse/config/searchRegistry.ts`                              | Provider registry (auth, cost, quota, TTL) |
-| `open-sse/services/searchCache.ts`                               | In-memory cache with request coalescing    |
-| `src/app/api/v1/search/route.ts`                                 | Next.js route (POST + GET)                 |
-| `src/app/api/v1/search/analytics/route.ts`                       | Search stats API                           |
-| `src/app/(dashboard)/dashboard/analytics/SearchAnalyticsTab.tsx` | Analytics dashboard tab                    |
-| `src/lib/db/migrations/007_search_request_type.sql`              | DB migration                               |
-| `tests/unit/search-registry.test.mjs`                            | 277 lines of unit tests                    |
-
----
-
-## [2.7.0] — 2026-03-17
-
-> Sprint: ClawRouter-inspired features — toolCalling flag, multilingual intent detection, benchmark-driven fallback, request deduplication, pluggable RouterStrategy, Grok-4 Fast + GLM-5 + MiniMax M2.5 + Kimi K2.5 pricing.
-
-### ✨ New Models & Pricing
-
-- **feat(pricing)**: xAI Grok-4 Fast — `$0.20/$0.50 per 1M tokens`, 1143ms p50 latency, tool calling supported
-- **feat(pricing)**: xAI Grok-4 (standard) — `$0.20/$1.50 per 1M tokens`, reasoning flagship
-- **feat(pricing)**: GLM-5 via Z.AI — `$0.5/1M`, 128K output context
-- **feat(pricing)**: MiniMax M2.5 — `$0.30/1M input`, reasoning + agentic tasks
-- **feat(pricing)**: DeepSeek V3.2 — updated pricing `$0.27/$1.10 per 1M`
-- **feat(pricing)**: Kimi K2.5 via Moonshot API — direct Moonshot API access
-- **feat(providers)**: Z.AI provider added (`zai` alias) — GLM-5 family with 128K output
-
-### 🧠 Routing Intelligence
-
-- **feat(registry)**: `toolCalling` flag per model in provider registry — combos can now prefer/require tool-calling capable models
-- **feat(scoring)**: Multilingual intent detection for AutoCombo scoring — PT/ZH/ES/AR script/language patterns influence model selection per request context
-- **feat(fallback)**: Benchmark-driven fallback chains — real latency data (p50 from `comboMetrics`) used to re-order fallback priority dynamically
-- **feat(dedup)**: Request deduplication via content-hash — 5-second idempotency window prevents duplicate provider calls from retrying clients
-- **feat(router)**: Pluggable `RouterStrategy` interface in `autoCombo/routerStrategy.ts` — custom routing logic can be injected without modifying core
-
-### 🔧 MCP Server Improvements
-
-- **feat(mcp)**: 2 new advanced tool schemas: `omniroute_get_provider_metrics` (p50/p95/p99 per provider) and `omniroute_explain_route` (routing decision explanation)
-- **feat(mcp)**: MCP tool auth scopes updated — `metrics:read` scope added for provider metrics tools
-- **feat(mcp)**: `omniroute_best_combo_for_task` now accepts `languageHint` parameter for multilingual routing
-
-### 📊 Observability
-
-- **feat(metrics)**: `comboMetrics.ts` extended with real-time latency percentile tracking per provider/account
-- **feat(health)**: Health API (`/api/monitoring/health`) now returns per-provider `p50Latency` and `errorRate` fields
-- **feat(usage)**: Usage history migration for per-model latency tracking
-
-### 🗄️ DB Migrations
-
-- **feat(migrations)**: New column `latency_p50` in `combo_metrics` table — zero-breaking, safe for existing users
-
-### 🐛 Bug Fixes / Closures
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **close(#411)**: better-sqlite3 hashed module resolution on Windows — fixed in v2.6.10 (f02c5b5)
-- **close(#409)**: GitHub Copilot chat completions fail with Claude models when files attached — fixed in v2.6.9 (838f1d6)
-- **close(#405)**: Duplicate of #411 — resolved
-
-## [2.6.10] — 2026-03-17
-
-> Windows fix: better-sqlite3 prebuilt download without node-gyp/Python/MSVC (#426).
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(install/#426)**: On Windows, `npm install -g omniroute` used to fail with `better_sqlite3.node is not a valid Win32 application` because the bundled native binary was compiled for Linux. Adds **Strategy 1.5** to `scripts/postinstall.mjs`: uses `@mapbox/node-pre-gyp install --fallback-to-build=false` (bundled within `better-sqlite3`) to download the correct prebuilt binary for the current OS/arch without requiring any build tools (no node-gyp, no Python, no MSVC). Falls back to `npm rebuild` only if the download fails. Adds platform-specific error messages with clear manual fix instructions.
-
----
-
-## [2.6.9] — 2026-03-17
-
-> CI fixes (t11 any-budget), bug fix #409 (file attachments via Copilot+Claude), release workflow correction.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(ci)**: Remove word "any" from comments in `openai-responses.ts` and `chatCore.ts` that were failing the t11 `any` budget check (false positive from regex counting comments)
-- **fix(chatCore)**: Normalize unsupported content part types before forwarding to providers (#409 — Cursor sends `{type:"file"}` when `.md` files are attached; Copilot and other OpenAI-compat providers reject with "type has to be either 'image_url' or 'text'"; fix converts `file`/`document` blocks to `text` and drops unknown types)
-
-### 🔧 Workflow
-
-- **chore(generate-release)**: Add ATOMIC COMMIT RULE — version bump (`npm version patch`) MUST happen before committing feature files to ensure tag always points to a commit containing all version changes together
-
----
-
-## [2.6.8] — 2026-03-17
-
-> Sprint: Combo as Agent (system prompt + tool filter), Context Caching Protection, Auto-Update, Detailed Logs, MITM Kiro IDE.
-
-### 🗄️ DB Migrations (zero-breaking — safe for existing users)
-
-- **005_combo_agent_fields.sql**: `ALTER TABLE combos ADD COLUMN system_message TEXT DEFAULT NULL`, `tool_filter_regex TEXT DEFAULT NULL`, `context_cache_protection INTEGER DEFAULT 0`
-- **006_detailed_request_logs.sql**: New `request_detail_logs` table with 500-entry ring-buffer trigger, opt-in via settings toggle
-
-### ✨ Features
-
-- **feat(combo)**: System Message Override per Combo (#399 — `system_message` field replaces or injects system prompt before forwarding to provider)
-- **feat(combo)**: Tool Filter Regex per Combo (#399 — `tool_filter_regex` keeps only tools matching pattern; supports OpenAI + Anthropic formats)
-- **feat(combo)**: Context Caching Protection (#401 — `context_cache_protection` tags responses with `<omniModel>provider/model</omniModel>` and pins model for session continuity)
-- **feat(settings)**: Auto-Update via Settings (#320 — `GET /api/system/version` + `POST /api/system/update` — checks npm registry and updates in background with pm2 restart)
-- **feat(logs)**: Detailed Request Logs (#378 — captures full pipeline bodies at 4 stages: client request, translated request, provider response, client response — opt-in toggle, 64KB trim, 500-entry ring-buffer)
-- **feat(mitm)**: MITM Kiro IDE profile (#336 — `src/mitm/targets/kiro.ts` targets api.anthropic.com, reuses existing MITM infrastructure)
-
----
-
-## [2.6.7] — 2026-03-17
-
-> Sprint: SSE improvements, local provider_nodes extensions, proxy registry, Claude passthrough fixes.
-
-### ✨ Features
-
-- **feat(health)**: Background health check for local `provider_nodes` with exponential backoff (30s→300s) and `Promise.allSettled` to avoid blocking (#423, @Regis-RCR)
-- **feat(embeddings)**: Route `/v1/embeddings` to local `provider_nodes` — `buildDynamicEmbeddingProvider()` with hostname validation (#422, @Regis-RCR)
-- **feat(audio)**: Route TTS/STT to local `provider_nodes` — `buildDynamicAudioProvider()` with SSRF protection (#416, @Regis-RCR)
-- **feat(proxy)**: Proxy registry, management APIs, and quota-limit generalization (#429, @Regis-RCR)
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(sse)**: Strip Claude-specific fields (`metadata`, `anthropic_version`) when target is OpenAI-compat (#421, @prakersh)
-- **fix(sse)**: Extract Claude SSE usage (`input_tokens`, `output_tokens`, cache tokens) in passthrough stream mode (#420, @prakersh)
-- **fix(sse)**: Generate fallback `call_id` for tool calls with missing/empty IDs (#419, @prakersh)
-- **fix(sse)**: Claude-to-Claude passthrough — forward body completely untouched, no re-translation (#418, @prakersh)
-- **fix(sse)**: Filter orphaned `tool_result` items after Claude Code context compaction to avoid 400 errors (#417, @prakersh)
-- **fix(sse)**: Skip empty-name tool calls in Responses API translator to prevent `placeholder_tool` infinite loops (#415, @prakersh)
-- **fix(sse)**: Strip empty text content blocks before translation (#427, @prakersh)
-- **fix(api)**: Add `refreshable: true` to Claude OAuth test config (#428, @prakersh)
-
-### 📦 Dependencies
-
-- Bump `vitest`, `@vitest/*` and related devDependencies (#414, @dependabot)
-
----
-
-## [2.6.6] — 2026-03-17
-
-> Hotfix: Turbopack/Docker compatibility — remove `node:` protocol from all `src/` imports.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(build)**: Removed `node:` protocol prefix from `import` statements in 17 files under `src/`. The `node:fs`, `node:path`, `node:url`, `node:os` etc. imports caused `Ecmascript file had an error` on Turbopack builds (Next.js 15 Docker) and on upgrades from older npm global installs. Affected files: `migrationRunner.ts`, `core.ts`, `backup.ts`, `prompts.ts`, `dataPaths.ts`, and 12 others in `src/app/api/` and `src/lib/`.
-- **chore(workflow)**: Updated `generate-release.md` to make Docker Hub sync and dual-VPS deploy **mandatory** steps in every release.
-
----
-
-## [2.6.5] — 2026-03-17
-
-> Sprint: reasoning model param filtering, local provider 404 fix, Kilo Gateway provider, dependency bumps.
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **feat(api)**: Added **Kilo Gateway** (`api.kilo.ai`) as a new API Key provider (alias `kg`) — 335+ models, 6 free models, 3 auto-routing models (`kilo-auto/frontier`, `kilo-auto/balanced`, `kilo-auto/free`). Passthrough models supported via `/api/gateway/models` endpoint. (PR #408 by @Regis-RCR)
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(sse)**: Strip unsupported parameters for reasoning models (o1, o1-mini, o1-pro, o3, o3-mini). Models in the `o1`/`o3` family reject `temperature`, `top_p`, `frequency_penalty`, `presence_penalty`, `logprobs`, `top_logprobs`, and `n` with HTTP 400. Parameters are now stripped at the `chatCore` layer before forwarding. Uses a declarative `unsupportedParams` field per model and a precomputed O(1) Map for lookup. (PR #412 by @Regis-RCR)
-- **fix(sse)**: Local provider 404 now results in a **model-only lockout (5 seconds)** instead of a connection-level lockout (2 minutes). When a local inference backend (Ollama, LM Studio, oMLX) returns 404 for an unknown model, the connection remains active and other models continue working immediately. Also fixes a pre-existing bug where `model` was not passed to `markAccountUnavailable()`. Local providers detected via hostname (`localhost`, `127.0.0.1`, `::1`, extensible via `LOCAL_HOSTNAMES` env var). (PR #410 by @Regis-RCR)
-
-### 📦 Dependencies
-
-- `better-sqlite3` 12.6.2 → 12.8.0
-- `undici` 7.24.2 → 7.24.4
-- `https-proxy-agent` 7 → 8
-- `agent-base` 7 → 8
-
----
-
-## [2.6.4] — 2026-03-17
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(providers)**: Removed non-existent model names across 5 providers:
-  - **gemini / gemini-cli**: removed `gemini-3.1-pro/flash` and `gemini-3-*-preview` (don't exist in Google API v1beta); replaced with `gemini-2.5-pro`, `gemini-2.5-flash`, `gemini-2.0-flash`, `gemini-1.5-pro/flash`
-  - **antigravity**: removed `gemini-3.1-pro-high/low` and `gemini-3-flash` (invalid internal aliases); replaced with real 2.x models
-  - **github (Copilot)**: removed `gemini-3-flash-preview` and `gemini-3-pro-preview`; replaced with `gemini-2.5-flash`
-  - **nvidia**: corrected `nvidia/llama-3.3-70b-instruct` → `meta/llama-3.3-70b-instruct` (NVIDIA NIM uses `meta/` namespace for Meta models); added `nvidia/llama-3.1-70b-instruct` and `nvidia/llama-3.1-405b-instruct`
-- **fix(db/combo)**: Updated `free-stack` combo on remote DB: removed `qw/qwen3-coder-plus` (expired refresh token), corrected `nvidia/llama-3.3-70b-instruct` → `nvidia/meta/llama-3.3-70b-instruct`, corrected `gemini/gemini-3.1-flash` → `gemini/gemini-2.5-flash`, added `if/deepseek-v3.2`
-
----
-
-## [2.6.3] — 2026-03-16
-
-> Sprint: zod/pino hash-strip baked into build pipeline, Synthetic provider added, VPS PM2 path corrected.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(build)**: Turbopack hash-strip now runs at **compile time** for ALL packages — not just `better-sqlite3`. Step 5.6 in `prepublish.mjs` walks every `.js` in `app/.next/server/` and strips the 16-char hex suffix from any hashed `require()`. Fixes `zod-dcb22c...`, `pino-...`, etc. MODULE_NOT_FOUND on global npm installs. Closes #398
-- **fix(deploy)**: PM2 on both VPS was pointing to stale git-clone directories. Reconfigured to `app/server.js` in the npm global package. Updated `/deploy-vps` workflow to use `npm pack + scp` (npm registry rejects 299MB packages).
-
-### ✨ Features
-
-- **feat(provider)**: Synthetic ([synthetic.new](https://synthetic.new)) — privacy-focused OpenAI-compatible inference. `passthroughModels: true` for dynamic HuggingFace model catalog. Initial models: Kimi K2.5, MiniMax M2.5, GLM 4.7, DeepSeek V3.2. (PR #404 by @Regis-RCR)
-
-### 📋 Issues Closed
-
-- **close #398**: npm hash regression — fixed by compile-time hash-strip in prepublish
-- **triage #324**: Bug screenshot without steps — requested reproduction details
-
----
-
-## [2.6.2] — 2026-03-16
-
-> Sprint: module hashing fully fixed, 2 PRs merged (Anthropic tools filter + custom endpoint paths), Alibaba Cloud DashScope provider added, 3 stale issues closed.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(build)**: Extended webpack `externals` hash-strip to cover ALL `serverExternalPackages`, not just `better-sqlite3`. Next.js 16 Turbopack hashes `zod`, `pino`, and every other server-external package into names like `zod-dcb22c6336e0bc69` that don't exist in `node_modules` at runtime. A HASH_PATTERN regex catch-all now strips the 16-char suffix and falls back to the base package name. Also added `NEXT_PRIVATE_BUILD_WORKER=0` in `prepublish.mjs` to reinforce webpack mode, plus a post-build scan that reports any remaining hashed refs. (#396, #398, PR #403)
-- **fix(chat)**: Anthropic-format tool names (`tool.name` without `.function` wrapper) were silently dropped by the empty-name filter introduced in #346. LiteLLM proxies requests with `anthropic/` prefix in Anthropic Messages API format, causing all tools to be filtered and Anthropic to return `400: tool_choice.any may only be specified while providing tools`. Fixed by falling back to `tool.name` when `tool.function.name` is absent. Added 8 regression unit tests. (PR #397)
-
-### ✨ Features
-
-- **feat(api)**: Custom endpoint paths for OpenAI-compatible provider nodes — configure `chatPath` and `modelsPath` per node (e.g. `/v4/chat/completions`) in the provider connection UI. Includes a DB migration (`003_provider_node_custom_paths.sql`) and URL path sanitization (no `..` traversal, must start with `/`). (PR #400)
-- **feat(provider)**: Alibaba Cloud DashScope added as OpenAI-compatible provider. International endpoint: `dashscope-intl.aliyuncs.com/compatible-mode/v1`. 12 models: `qwen-max`, `qwen-plus`, `qwen-turbo`, `qwen3-coder-plus/flash`, `qwq-plus`, `qwq-32b`, `qwen3-32b`, `qwen3-235b-a22b`. Auth: Bearer API key.
-
-### 📋 Issues Closed
-
-- **close #323**: Cline connection error `[object Object]` — fixed in v2.3.7; instructed user to upgrade from v2.2.9
-- **close #337**: Kiro credit tracking — implemented in v2.5.5 (#381); pointed user to Dashboard → Usage
-- **triage #402**: ARM64 macOS DMG damaged — requested macOS version, exact error, and advised `xattr -d com.apple.quarantine` workaround
-
----
-
-## [2.6.1] — 2026-03-15
-
-> Critical startup fix: v2.6.0 global npm installs crashed with a 500 error due to a Turbopack/webpack module-name hashing bug in the Next.js 16 instrumentation hook.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(build)**: Force `better-sqlite3` to always be required by its exact package name in the webpack server bundle. Next.js 16 compiled the instrumentation hook into a separate chunk and emitted `require('better-sqlite3-<hash>')` — a hashed module name that doesn't exist in `node_modules` — even though the package was listed in `serverExternalPackages`. Added an explicit `externals` function to the server webpack config so the bundler always emits `require('better-sqlite3')`, resolving the startup `500 Internal Server Error` on clean global installs. (#394, PR #395)
-
-### 🔧 CI
-
-- **ci**: Added `workflow_dispatch` to `npm-publish.yml` with version sync safeguard for manual triggers (#392)
-- **ci**: Added `workflow_dispatch` to `docker-publish.yml`, updated GitHub Actions to latest versions (#392)
-
----
-
-## [2.6.0] - 2026-03-15
-
-> Issue resolution sprint: 4 bugs fixed, logs UX improved, Kiro credit tracking added.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(media)**: ComfyUI and SD WebUI no longer appear in the Media page provider list when unconfigured — fetches `/api/providers` on mount and hides local providers with no connections (#390)
-- **fix(auth)**: Round-robin no longer re-selects rate-limited accounts immediately after cooldown — `backoffLevel` is now used as primary sort key in the LRU rotation (#340)
-- **fix(oauth)**: Qoder (and other providers that redirect to their own UI) no longer leave the OAuth modal stuck at "Waiting for Authorization" — popup-closed detector auto-transitions to manual URL input mode (#344)
-- **fix(logs)**: Request log table is now readable in light mode — status badges, token counts, and combo tags use adaptive `dark:` color classes (#378)
-
-### ✨ Features
-
-- **feat(kiro)**: Kiro credit tracking added to usage fetcher — queries `getUserCredits` from AWS CodeWhisperer endpoint (#337)
-
-### 🛠 Chores
-
-- **chore(tests)**: Aligned `test:plan3`, `test:fixes`, `test:security` to use same `tsx/esm` loader as `npm test` — eliminates module resolution false negatives in targeted runs (PR #386)
-
----
-
-## [2.5.9] - 2026-03-15
-
-> Codex native passthrough fix + route body validation hardening.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(codex)**: Preserve native Responses API passthrough for Codex clients — avoids unnecessary translation mutations (PR #387)
-- **fix(api)**: Validate request bodies on pricing/sync and task-routing routes — prevents crashes from malformed inputs (PR #388)
-- **fix(auth)**: JWT secrets persist across restarts via `src/lib/db/secrets.ts` — eliminates 401 errors after pm2 restart (PR #388)
-
----
-
-## [2.5.8] - 2026-03-15
-
-> Build fix: restore VPS connectivity broken by v2.5.7 incomplete publish.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(build)**: `scripts/prepublish.mjs` still used deprecated `--webpack` flag causing Next.js standalone build to fail silently — npm publish completed without `app/server.js`, breaking VPS deployment
-
----
-
-## [2.5.7] - 2026-03-15
-
-> Media playground error handling fixes.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(media)**: Transcription "API Key Required" false positive when audio contains no speech (music, silence) — now shows "No speech detected" instead
-- **fix(media)**: `upstreamErrorResponse` in `audioTranscription.ts` and `audioSpeech.ts` now returns proper JSON (`{error:{message}}`), enabling correct 401/403 credential error detection in the MediaPageClient
-- **fix(media)**: `parseApiError` now handles Deepgram's `err_msg` field and detects `"api key"` in error messages for accurate credential error classification
-
----
-
-## [2.5.6] - 2026-03-15
-
-> Critical security/auth fixes: Antigravity OAuth broken + JWT sessions lost after restart.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(oauth) #384**: Antigravity Google OAuth now correctly sends `client_secret` to the token endpoint. The fallback for `ANTIGRAVITY_OAUTH_CLIENT_SECRET` was an empty string, which is falsy — so `client_secret` was never included in the request, causing `"client_secret is missing"` errors for all users without a custom env var. Closes #383.
-- **fix(auth) #385**: `JWT_SECRET` is now persisted to SQLite (`namespace='secrets'`) on first generation and reloaded on subsequent starts. Previously, a new random secret was generated each process startup, invalidating all existing cookies/sessions after any restart or upgrade. Affects both `JWT_SECRET` and `API_KEY_SECRET`. Closes #382.
-
----
-
-## [2.5.5] - 2026-03-15
-
-> Model list dedup fix, Electron standalone build hardening, and Kiro credit tracking.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(models) #380**: `GET /api/models` now includes provider aliases when building the active-provider filter — models for `claude` (alias `cc`) and `github` (alias `gh`) were always shown regardless of whether a connection was configured, because `PROVIDER_MODELS` keys are aliases but DB connections are stored under provider IDs. Fixed by expanding each active provider ID to also include its alias via `PROVIDER_ID_TO_ALIAS`. Closes #353.
-- **fix(electron) #379**: New `scripts/prepare-electron-standalone.mjs` stages a dedicated `/.next/electron-standalone` bundle before Electron packaging. Aborts with a clear error if `node_modules` is a symlink (electron-builder would ship a runtime dependency on the build machine). Cross-platform path sanitization via `path.basename`. By @kfiramar.
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **feat(kiro) #381**: Kiro credit balance tracking — usage endpoint now returns credit data for Kiro accounts by calling `codewhisperer.us-east-1.amazonaws.com/getUserCredits` (same endpoint Kiro IDE uses internally). Returns remaining credits, total allowance, renewal date, and subscription tier. Closes #337.
-
-## [2.5.4] - 2026-03-15
-
-> Logger startup fix, login bootstrap security fix, and dev HMR reliability improvement. CI infrastructure hardened.
-
-### 🐛 Bug Fixes (PRs #374, #375, #376 by @kfiramar)
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(logger) #376**: Restore pino transport logger path — `formatters.level` combined with `transport.targets` is rejected by pino. Transport-backed configs now strip the level formatter via `getTransportCompatibleConfig()`. Also corrects numeric level mapping in `/api/logs/console`: `30→info, 40→warn, 50→error` (was shifted by one).
-- **fix(login) #375**: Login page now bootstraps from the public `/api/settings/require-login` endpoint instead of the protected `/api/settings`. In password-protected setups, the pre-auth page was receiving a 401 and falling back to safe defaults unnecessarily. The public route now returns all bootstrap metadata (`requireLogin`, `hasPassword`, `setupComplete`) with a conservative 200 fallback on error.
-- **fix(dev) #374**: Add `localhost` and `127.0.0.1` to `allowedDevOrigins` in `next.config.mjs` — HMR websocket was blocked when accessing the app via loopback address, producing repeated cross-origin warnings.
-
-### 🔧 CI & Infrastructure
-
-- **ESLint OOM fix**: `eslint.config.mjs` now ignores `vscode-extension/**`, `electron/**`, `docs/**`, `app/.next/**`, and `clipr/**` — ESLint was crashing with a JS heap OOM by scanning VS Code binary blobs and compiled chunks.
-- **Unit test fix**: Removed stale `ALTER TABLE provider_connections ADD COLUMN "group"` from 2 test files — column is now part of the base schema (added in #373), causing `SQLITE_ERROR: duplicate column name` on every CI run.
-- **Pre-commit hook**: Added `npm run test:unit` to `.husky/pre-commit` — unit tests now block broken commits before they reach CI.
-
-## [2.5.3] - 2026-03-14
-
-> Critical bugfixes: DB schema migration, startup env loading, provider error state clearing, and i18n tooltip fix. Code quality improvements on top of each PR.
-
-### 🐛 Bug Fixes (PRs #369, #371, #372, #373 by @kfiramar)
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix(db) #373**: Add `provider_connections.group` column to base schema + backfill migration for existing databases — column was used in all queries but missing from schema definition
-- **fix(i18n) #371**: Replace non-existent `t("deleteConnection")` key with existing `providers.delete` key — fixes `MISSING_MESSAGE: providers.deleteConnection` runtime error on provider detail page
-- **fix(auth) #372**: Clear stale error metadata (`errorCode`, `lastErrorType`, `lastErrorSource`) from provider accounts after genuine recovery — previously, recovered accounts kept appearing as failed
-- **fix(startup) #369**: Unify env loading across `npm run start`, `run-standalone.mjs`, and Electron to respect `DATA_DIR/.env → ~/.omniroute/.env → ./.env` priority — prevents generating a new `STORAGE_ENCRYPTION_KEY` over an existing encrypted database
-
-### 🔧 Code Quality
-
-- Documented `result.success` vs `response?.ok` patterns in `auth.ts` (both intentional, now explained)
-- Normalized `overridePath?.trim()` in `electron/main.js` to match `bootstrap-env.mjs`
-- Added `preferredEnv` merge order comment in Electron startup
-
-> Codex account quota policy with auto-rotation, fast tier toggle, gpt-5.4 model, and analytics label fix.
-
-### ✨ New Features (PRs #366, #367, #368)
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Codex Quota Policy (PR #366)**: Per-account 5h/weekly quota window toggles in Provider dashboard. Accounts are automatically skipped when enabled windows reach 90% threshold and re-admitted after `resetAt`. Includes `quotaCache.ts` with side-effect free status getter.
-- **Codex Fast Tier Toggle (PR #367)**: Dashboard → Settings → Codex Service Tier. Default-off toggle injects `service_tier: "flex"` only for Codex requests, reducing cost ~80%. Full stack: UI tab + API endpoint + executor + translator + startup restore.
-- **gpt-5.4 Model (PR #368)**: Adds `cx/gpt-5.4` and `codex/gpt-5.4` to the Codex model registry. Regression test included.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix #356**: Analytics charts (Top Provider, By Account, Provider Breakdown) now display human-readable provider names/labels instead of raw internal IDs for OpenAI-compatible providers.
-
-> Major release: strict-random routing strategy, API key access controls, connection groups, external pricing sync, and critical bug fixes for thinking models, combo testing, and tool name validation.
-
-### ✨ New Features (PRs #363 & #365)
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Strict-Random Routing Strategy**: Fisher-Yates shuffle deck with anti-repeat guarantee and mutex serialization for concurrent requests. Independent decks per combo and per provider.
-- **API Key Access Controls**: `allowedConnections` (restrict which connections a key can use), `is_active` (enable/disable key with 403), `accessSchedule` (time-based access control), `autoResolve` toggle, rename keys via PATCH.
-- **Connection Groups**: Group provider connections by environment. Accordion view in Limits page with localStorage persistence and smart auto-switch.
-- **External Pricing Sync (LiteLLM)**: 3-tier pricing resolution (user overrides → synced → defaults). Opt-in via `PRICING_SYNC_ENABLED=true`. MCP tool `omniroute_sync_pricing`. 23 new tests.
-- **i18n**: 30 languages updated with strict-random strategy, API key management strings. pt-BR fully translated.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **fix #355**: Stream idle timeout increased from 60s to 300s — prevents aborting extended-thinking models (claude-opus-4-6, o3, etc.) during long reasoning phases. Configurable via `STREAM_IDLE_TIMEOUT_MS`.
-- **fix #350**: Combo test now bypasses `REQUIRE_API_KEY=true` using internal header, and uses OpenAI-compatible format universally. Timeout extended from 15s to 20s.
-- **fix #346**: Tools with empty `function.name` (forwarded by Claude Code) are now filtered before upstream providers receive them, preventing "Invalid input[N].name: empty string" errors.
-
-### 🗑️ Closed Issues
-
-- **#341**: Debug section removed — replacement is `/dashboard/logs` and `/dashboard/health`.
-
-> API Key Round-Robin support for multi-key provider setups, and confirmation of wildcard routing and quota window rolling already in place.
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **API Key Round-Robin (T07)**: Provider connections can now hold multiple API keys (Edit Connection → Extra API Keys). Requests rotate round-robin between primary + extra keys via `providerSpecificData.extraApiKeys[]`. Keys are held in-memory indexed per connection — no DB schema changes required.
-
-### 📝 Already Implemented (confirmed in audit)
-
-- **Wildcard Model Routing (T13)**: `wildcardRouter.ts` with glob-style wildcard matching (`gpt*`, `claude-?-sonnet`, etc.) is already integrated into `model.ts` with specificity ranking.
-- **Quota Window Rolling (T08)**: `accountFallback.ts:isModelLocked()` already auto-advances the window — if `Date.now() > entry.until`, lock is deleted immediately (no stale blocking).
-
-> UI polish, routing strategy additions, and graceful error handling for usage limits.
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Fill-First & P2C Routing Strategies**: Added `fill-first` (drain quota before moving on) and `p2c` (Power-of-Two-Choices low-latency selection) to combo strategy picker, with full guidance panels and color-coded badges.
-- **Free Stack Preset Models**: Creating a combo with the Free Stack template now auto-fills 7 best-in-class free provider models (Gemini CLI, Kiro, Qoder×2, Qwen, NVIDIA NIM, Groq). Users just activate the providers and get a $0/month combo out-of-the-box.
-- **Wider Combo Modal**: Create/Edit combo modal now uses `max-w-4xl` for comfortable editing of large combos.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Limits page HTTP 500 for Codex & GitHub**: `getCodexUsage()` and `getGitHubUsage()` now return a user-friendly message when the provider returns 401/403 (expired token), instead of throwing and causing a 500 error on the Limits page.
-- **MaintenanceBanner false-positive**: Banner no longer shows "Server is unreachable" spuriously on page load. Fixed by calling `checkHealth()` immediately on mount and removing stale `show`-state closure.
-- **Provider icon tooltips**: Edit (pencil) and delete icon buttons in the provider connection row now have native HTML tooltips — all 6 action icons are now self-documented.
-
-> Multiple improvements from community issue analysis, new provider support, bug fixes for token tracking, model routing, and streaming reliability.
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Task-Aware Smart Routing (T05)**: Automatic model selection based on request content type — coding → deepseek-chat, analysis → gemini-2.5-pro, vision → gpt-4o, summarization → gemini-2.5-flash. Configurable via Settings. New `GET/PUT/POST /api/settings/task-routing` API.
-- **HuggingFace Provider**: Added HuggingFace Router as an OpenAI-compatible provider with Llama 3.1 70B/8B, Qwen 2.5 72B, Mistral 7B, Phi-3.5 Mini.
-- **Vertex AI Provider**: Added Vertex AI (Google Cloud) provider with Gemini 2.5 Pro/Flash, Gemma 2 27B, Claude via Vertex.
-- **Playground File Uploads**: Audio upload for transcription, image upload for vision models (auto-detect by model name), inline image rendering for image generation results.
-- **Model Select Visual Feedback**: Already-added models in combo picker now show ✓ green badge — prevents duplicate confusion.
-- **Qwen Compatibility (PR #352)**: Updated User-Agent and CLI fingerprint settings for Qwen provider compatibility.
-- **Round-Robin State Management (PR #349)**: Enhanced round-robin logic to handle excluded accounts and maintain rotation state correctly.
-- **Clipboard UX (PR #360)**: Hardened clipboard operations with fallback for non-secure contexts; Claude tool normalization improvements.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Fix #302 — OpenAI SDK stream=False drops tool_calls**: T01 Accept header negotiation no longer forces streaming when `body.stream` is explicitly `false`. Was causing tool_calls to be silently dropped when using the OpenAI Python SDK in non-streaming mode.
-- **Fix #73 — Claude Haiku routed to OpenAI without provider prefix**: `claude-*` models sent without a provider prefix now correctly route to the `antigravity` (Anthropic) provider. Added `gemini-*`/`gemma-*` → `gemini` heuristic as well.
-- **Fix #74 — Token counts always 0 for Antigravity/Claude streaming**: The `message_start` SSE event which carries `input_tokens` was not being parsed by `extractUsage()`, causing all input token counts to drop. Input/output token tracking now works correctly for streaming responses.
-- **Fix #180 — Model import duplicates with no feedback**: `ModelSelectModal` now shows ✓ green highlight for models already in the combo, making it obvious they're already added.
-- **Media page generation errors**: Image results now render as `<img>` tags instead of raw JSON. Transcription results shown as readable text. Credential errors show an amber banner instead of silent failure.
-- **Token refresh button on provider page**: Manual token refresh UI added for OAuth providers.
-
-### 🔧 Improvements
-
-- **Provider Registry**: HuggingFace and Vertex AI added to `providerRegistry.ts` and `providers.ts` (frontend).
-- **Read Cache**: New `src/lib/db/readCache.ts` for efficient DB read caching.
-- **Quota Cache**: Improved quota cache with TTL-based eviction.
-
-### 📦 Dependencies
-
-- `dompurify` → 3.3.3 (PR #347)
-- `undici` → 7.24.2 (PR #348, #361)
-- `docker/setup-qemu-action` → v4 (PR #342)
-- `docker/setup-buildx-action` → v4 (PR #343)
-
-### 📁 New Files
-
-| File                                          | Purpose                                 |
-| --------------------------------------------- | --------------------------------------- |
-| `open-sse/services/taskAwareRouter.ts`        | Task-aware routing logic (7 task types) |
-| `src/app/api/settings/task-routing/route.ts`  | Task routing config API                 |
-| `src/app/api/providers/[id]/refresh/route.ts` | Manual OAuth token refresh              |
-| `src/lib/db/readCache.ts`                     | Efficient DB read cache                 |
-| `src/shared/utils/clipboard.ts`               | Hardened clipboard with fallback        |
-
-## [2.4.1] - 2026-03-13
-
-### 🐛 Fix
-
-- **Combos modal: Free Stack visible and prominent** — Free Stack template was hidden (4th in 3-column grid). Fixed: moved to position 1, switched to 2x2 grid so all 4 templates are visible, green border + FREE badge highlight.
-
-## [2.4.0] - 2026-03-13
-
-> **Major release** — Free Stack ecosystem, transcription playground overhaul, 44+ providers, comprehensive free tier documentation, and UI improvements across the board.
-
-### ✨ Features
-
-- **Combos: Free Stack template** — New 4th template "Free Stack ($0)" using round-robin across Kiro + Qoder + Qwen + Gemini CLI. Suggests the pre-built zero-cost combo on first use.
-- **Media/Transcription: Deepgram as default** — Deepgram (Nova 3, $200 free) is now the default transcription provider. AssemblyAI ($50 free) and Groq Whisper (free forever) shown with free credit badges.
-- **README: "Start Free" section** — New early-README 5-step table showing how to set up zero-cost AI in minutes.
-- **README: Free Transcription Combo** — New section with Deepgram/AssemblyAI/Groq combo suggestion and per-provider free credit details.
-- **providers.ts: hasFree flag** — NVIDIA NIM, Cerebras, and Groq marked with hasFree badge and freeNote for the providers UI.
-- **i18n: templateFreeStack keys** — Free Stack combo template translated and synced to all 30 languages.
-
-## [2.3.16] - 2026-03-13
-
-### 📖 Documentation
-
-- **README: 44+ Providers** — Updated all 3 occurrences of "36+ providers" to "44+" reflecting the actual codebase count (44 providers in providers.ts)
-- **README: New Section "🆓 Free Models — What You Actually Get"** — Added 7-provider table with per-model rate limits for: Kiro (Claude unlimited via AWS Builder ID), Qoder (5 models unlimited), Qwen (4 models unlimited), Gemini CLI (180K/mo), NVIDIA NIM (~40 RPM dev-forever), Cerebras (1M tok/day / 60K TPM), Groq (30 RPM / 14.4K RPD). Includes the \/usr/bin/bash Ultimate Free Stack combo recommendation.
-- **README: Pricing Table Updated** — Added Cerebras to API KEY tier, fixed NVIDIA from "1000 credits" to "dev-forever free", updated Qoder/Qwen model counts and names
-- **README: Qoder 8→5 models** (named: kimi-k2-thinking, qwen3-coder-plus, deepseek-r1, minimax-m2, kimi-k2)
-- **README: Qwen 3→4 models** (named: qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next, vision-model)
-
-## [2.3.15] - 2026-03-13
-
-### ✨ Features
-
-- **Auto-Combo Dashboard (Tier Priority)**: Added `🏷️ Tier` as the 7th scoring factor label in the `/dashboard/auto-combo` factor breakdown display — all 7 Auto-Combo scoring factors are now visible.
-- **i18n — autoCombo section**: Added 20 new translation keys for the Auto-Combo dashboard (`title`, `status`, `modePack`, `providerScores`, `factorTierPriority`, etc.) to all 30 language files.
-
-## [2.3.14] - 2026-03-13
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Qoder OAuth (#339)**: Restored the valid default `clientSecret` — was previously an empty string, causing "Bad client credentials" on every connect attempt. The public credential is now the default fallback (overridable via `QODER_OAUTH_CLIENT_SECRET` env var).
-- **MITM server not found (#335)**: `prepublish.mjs` now compiles `src/mitm/*.ts` to JavaScript using `tsc` before copying to the npm bundle. Previously only raw `.ts` files were copied — meaning `server.js` never existed in npm/Volta global installs.
-- **GeminiCLI missing projectId (#338)**: Instead of throwing a hard 500 error when `projectId` is missing from stored credentials (e.g. after Docker restart), OmniRoute now logs a warning and attempts the request — returning a meaningful provider-side error instead of an OmniRoute crash.
-- **Electron version mismatch (#323)**: Synced `electron/package.json` version to `2.3.13` (was `2.0.13`) so the desktop binary version matches the npm package.
-
-### ✨ New Models (#334)
-
-- **Kiro**: `claude-sonnet-4`, `claude-opus-4.6`, `deepseek-v3.2`, `minimax-m2.1`, `qwen3-coder-next`, `auto`
-- **Codex**: `gpt5.4`
-
-### 🔧 Improvements
-
-- **Tier Scoring (API + Validation)**: Added `tierPriority` (weight `0.05`) to the `ScoringWeights` Zod schema and the `combos/auto` API route — the 7th scoring factor is now fully accepted by the REST API and validated on input. `stability` weight adjusted from `0.10` to `0.05` to keep total sum = `1.0`.
-
-### ✨ New Features
-
-- **feat(docs):** integrate multi-page documentation into OmniRoute dashboard (#1969)
-- **feat(settings):** add request body limit setting (#1968)
-- **feat(auth):** add Gemini CLI OAuth client secret default (#1974)
-- **feat(models):** expose models.dev context windows in /v1/models (#1972)
-- **fix(db):** resolve legacy encryption fallback causing re-encryption loops (#1941)
-- **fix(auth):** fix Codex assistant final_answer response sanitization (#1965)
-
-- **feat(providers):** Implement Image Generation and Editing capabilities for ChatGPT Web, including in-band chat image generation and caching (#1606).
-- **feat(ui):** Integrate OpenCode Zen/Go API tool logo SVG and polish API key copy-to-clipboard interactions (#1607).
-
-- **feat(providers):** Integrate AgentRouter as a new OpenAI-compatible passthrough provider with $200 free credits via sign-up (Issue #1572).
-- **feat(ui):** Implement on-demand per-model testing in the provider dashboard, allowing single-token diagnostic checks without triggering rate-limits (Issue #1532).
-
-- **Tiered Quota Scoring (Auto-Combo)**: Added `tierPriority` as a 7th scoring factor — accounts with Ultra/Pro tiers are now preferred over Free tiers when other factors are equal. New optional fields `accountTier` and `quotaResetIntervalSecs` on `ProviderCandidate`. All 4 mode packs updated (`ship-fast`, `cost-saver`, `quality-first`, `offline-friendly`).
-- **Intra-Family Model Fallback (T5)**: When a model is unavailable (404/400/403), OmniRoute now automatically falls back to sibling models from the same family before returning an error (`modelFamilyFallback.ts`).
-- **Configurable API Bridge Timeout**: `API_BRIDGE_PROXY_TIMEOUT_MS` env var lets operators tune the proxy timeout (default 30s). Fixes 504 errors on slow upstream responses. (#332)
-- **Star History**: Replaced star-history.com widget with starchart.cc (`?variant=adaptive`) in all 30 READMEs — adapts to light/dark theme, real-time updates.
-
-### 🐛 Bug Fixes
-
-- **fix(mitm):** Compile MITM utilities as NodeNext ESM during prepublish, copy the CommonJS MITM server into the standalone artifact, and resolve MITM data paths without relying on Next.js aliases in packaged runtime.
-- **fix(build):** Move the local `.tmp/wine32` Wine prefix out of the isolated Next.js build path so Windows Electron packaging artifacts cannot trigger `EACCES` scans during Node 24 builds.
-- **fix(build):** Copy the `wreq-js` native runtime directory into the isolated Next.js standalone output so packaged Playwright/E2E starts can load the instrumentation hook on Linux.
-- **fix(api):** Validate the Codex Responses websocket bridge and `/v1/batches` JSON payloads with Zod before use, keeping `request.json()` route validation green and returning explicit 400 responses for invalid bodies.
-- **fix(providers):** Add explicit typing to provider alias and category helpers so the strict `typecheck:noimplicit:core` CI gate passes.
-- **fix(ui):** Keep the upstream proxy provider detail page labeled with a fallback "Managed via Upstream Proxy Settings" management surface when translations are unavailable.
-- **fix(electron):** Harden the production desktop CSP by removing `unsafe-eval` outside development and adding object, base URI, form action, frame ancestor, and worker restrictions.
-- **fix(cli):** Replace shell-interpolated setup and privileged command execution paths with argument-based `spawn`/`execFile` helpers for database setup, Tailscale sudo commands, MITM DNS edits, and certificate install/uninstall flows.
-- **fix(ui):** Keep provider icons resilient by using direct `@lobehub/icons` components first, then local PNG/SVG fallbacks, avoiding the `@lobehub/ui` peer runtime in the dashboard.
-
-- **Auth — First-time password**: `INITIAL_PASSWORD` env var is now accepted when setting the first dashboard password. Uses `timingSafeEqual` for constant-time comparison, preventing timing attacks. (#333)
-- **README Truncation**: Fixed a missing `</details>` closing tag in the Troubleshooting section that caused GitHub to stop rendering everything below it (Tech Stack, Docs, Roadmap, Contributors).
-- **pnpm install**: Removed redundant `@swc/helpers` override from `package.json` that conflicted with the direct dependency, causing `EOVERRIDE` errors on pnpm. Added `pnpm.onlyBuiltDependencies` config.
-- **CLI Path Injection (T12)**: Added `isSafePath()` validator in `cliRuntime.ts` to block path traversal and shell metacharacters in `CLI_*_BIN` env vars.
-- **CI**: Regenerated `package-lock.json` after override removal to fix `npm ci` failures on GitHub Actions.
-
-### 🔧 Improvements
-
-- **Response Format (T1)**: `response_format` (json_schema/json_object) now injected as a system prompt for Claude, enabling structured output compatibility.
-- **429 Retry (T2)**: Intra-URL retry for 429 responses (2× attempts with 2s delay) before falling back to next URL.
-- **Gemini CLI Headers (T3)**: Added `User-Agent` and `X-Goog-Api-Client` fingerprint headers for Gemini CLI compatibility.
-- **Pricing Catalog (T9)**: Added `deepseek-3.1`, `deepseek-3.2`, and `qwen3-coder-next` pricing entries.
-
-### 📁 New Files
-
-| File                                       | Purpose                                                  |
-| ------------------------------------------ | -------------------------------------------------------- |
-| `open-sse/services/modelFamilyFallback.ts` | Model family definitions and intra-family fallback logic |
-
-### Fixed
-
-- **KiloCode**: kilocode healthcheck timeout already fixed in v2.3.11
-- **OpenCode**: Add opencode to cliRuntime registry with 15s healthcheck timeout
-- **OpenClaw / Cursor**: Increase healthcheck timeout to 15s for slow-start variants
-- **VPS**: Install droid and openclaw npm packages; activate CLI_EXTRA_PATHS for kiro-cli
-- **cliRuntime**: Add opencode tool registration and increase timeout for continue
-
-## [2.3.11] - 2026-03-12
-
-### Fixed
-
-- **KiloCode healthcheck**: Increase `healthcheckTimeoutMs` from 4000ms to 15000ms — kilocode renders an ASCII logo banner on startup causing false `healthcheck_failed` on slow/cold-start environments
-
-## [2.3.10] - 2026-03-12
-
-### Fixed
-
-- **Lint**: Fix `check:any-budget:t11` failure — replace `as any` with `as Record<string, unknown>` in OAuthModal.tsx (3 occurrences)
-
-### Docs
-
-- **CLI-TOOLS.md**: Complete guide for all 11 CLI tools (claude, codex, gemini, opencode, cline, kilocode, continue, kiro-cli, cursor, droid, openclaw)
-- **i18n**: CLI-TOOLS.md synced to 30 languages with translated title + intro
-
-## [2.3.8] - 2026-03-12
-
-## [2.3.9] - 2026-03-12
-
-### Added
-
-- **/v1/completions**: New legacy OpenAI completions endpoint — accepts both `prompt` string and `messages` array, normalizes to chat format automatically
-- **EndpointPage**: Now shows all 3 OpenAI-compatible endpoint types: Chat Completions, Responses API, and Legacy Completions
-- **i18n**: Added `completionsLegacy/completionsLegacyDesc` to 30 language files
-
-### Fixed
-
-- **OAuthModal**: Fix `[object Object]` displayed on all OAuth connection errors — properly extract `.message` from error response objects in all 3 `throw new Error(data.error)` calls (exchange, device-code, authorize)
-- Affects Cline, Codex, GitHub, Qwen, Kiro, and all other OAuth providers
-
-## [2.3.7] - 2026-03-12
-
-### Fixed
-
-- **Cline OAuth**: Add `decodeURIComponent` before base64 decode so URL-encoded auth codes from the callback URL are parsed correctly, fixing "invalid or expired authorization code" errors on remote (LAN IP) setups
-- **Cline OAuth**: `mapTokens` now populates `name = firstName + lastName || email` so Cline accounts show real user names instead of "Account #ID"
-- **OAuth account names**: All OAuth exchange flows (exchange, poll, poll-callback) now normalize `name = email` when name is missing, so every OAuth account shows its email as the display label in the Providers dashboard
-- **OAuth account names**: Removed sequential "Account N" fallback in `db/providers.ts` — accounts with no email/name now use a stable ID-based label via `getAccountDisplayName()` instead of a sequential number that changes when accounts are deleted
-
-## [2.3.6] - 2026-03-12
-
-### Fixed
-
-- **Provider test batch**: Fixed Zod schema to accept `providerId: null` (frontend sends null for non-provider modes); was incorrectly returning "Invalid request" for all batch tests
-- **Provider test modal**: Fixed `[object Object]` display by normalizing API error objects to strings before rendering in `setTestResults` and `ProviderTestResultsView`
-- **i18n**: Added missing keys `cliTools.toolDescriptions.opencode`, `cliTools.toolDescriptions.kiro`, `cliTools.guides.opencode`, `cliTools.guides.kiro` to `en.json`
-- **i18n**: Synchronized 1111 missing keys across all 29 non-English language files using English values as fallbacks
-
-## [2.3.5] - 2026-03-11
-
-### Fixed
-
-- **@swc/helpers**: Added permanent `postinstall` fix to copy `@swc/helpers` into the standalone app's `node_modules` — prevents MODULE_NOT_FOUND crash on global npm installs
-
-## [2.3.4] - 2026-03-10
-
-### Added
-
-- Multiple provider integrations and dashboard improvements
diff --git a/docs/i18n/in/CLAUDE.md b/docs/i18n/in/CLAUDE.md
deleted file mode 100644
index 3d01829ac0..0000000000
--- a/docs/i18n/in/CLAUDE.md
+++ /dev/null
@@ -1,412 +0,0 @@
-# CLAUDE.md (Bahasa Indonesia (Alt))
-
-🌐 **Languages:** 🇺🇸 [English](../../../CLAUDE.md) · 🇸🇦 [ar](../ar/CLAUDE.md) · 🇦🇿 [az](../az/CLAUDE.md) · 🇧🇬 [bg](../bg/CLAUDE.md) · 🇧🇩 [bn](../bn/CLAUDE.md) · 🇨🇿 [cs](../cs/CLAUDE.md) · 🇩🇰 [da](../da/CLAUDE.md) · 🇩🇪 [de](../de/CLAUDE.md) · 🇪🇸 [es](../es/CLAUDE.md) · 🇮🇷 [fa](../fa/CLAUDE.md) · 🇫🇮 [fi](../fi/CLAUDE.md) · 🇫🇷 [fr](../fr/CLAUDE.md) · 🇮🇳 [gu](../gu/CLAUDE.md) · 🇮🇱 [he](../he/CLAUDE.md) · 🇮🇳 [hi](../hi/CLAUDE.md) · 🇭🇺 [hu](../hu/CLAUDE.md) · 🇮🇩 [id](../id/CLAUDE.md) · 🇮🇹 [it](../it/CLAUDE.md) · 🇯🇵 [ja](../ja/CLAUDE.md) · 🇰🇷 [ko](../ko/CLAUDE.md) · 🇮🇳 [mr](../mr/CLAUDE.md) · 🇲🇾 [ms](../ms/CLAUDE.md) · 🇳🇱 [nl](../nl/CLAUDE.md) · 🇳🇴 [no](../no/CLAUDE.md) · 🇵🇭 [phi](../phi/CLAUDE.md) · 🇵🇱 [pl](../pl/CLAUDE.md) · 🇵🇹 [pt](../pt/CLAUDE.md) · 🇧🇷 [pt-BR](../pt-BR/CLAUDE.md) · 🇷🇴 [ro](../ro/CLAUDE.md) · 🇷🇺 [ru](../ru/CLAUDE.md) · 🇸🇰 [sk](../sk/CLAUDE.md) · 🇸🇪 [sv](../sv/CLAUDE.md) · 🇰🇪 [sw](../sw/CLAUDE.md) · 🇮🇳 [ta](../ta/CLAUDE.md) · 🇮🇳 [te](../te/CLAUDE.md) · 🇹🇭 [th](../th/CLAUDE.md) · 🇹🇷 [tr](../tr/CLAUDE.md) · 🇺🇦 [uk-UA](../uk-UA/CLAUDE.md) · 🇵🇰 [ur](../ur/CLAUDE.md) · 🇻🇳 [vi](../vi/CLAUDE.md) · 🇨🇳 [zh-CN](../zh-CN/CLAUDE.md)
-
----
-
-File ini memberikan panduan untuk Claude Code (claude.ai/code) saat bekerja dengan kode di repositori ini.
-
-## Memulai dengan Cepat
-
-```bash
-npm install                    # Instal deps (secara otomatis menghasilkan .env dari .env.example)
-npm run dev                    # Server dev di http://localhost:20128
-npm run build                  # Build produksi (Next.js 16 standalone)
-npm run lint                   # ESLint (0 kesalahan yang diharapkan; peringatan sudah ada sebelumnya)
-npm run typecheck:core         # Pemeriksaan TypeScript (harus bersih)
-npm run typecheck:noimplicit:core  # Pemeriksaan ketat (tidak ada implicit any)
-npm run test:coverage          # Unit tests + coverage gate (75/75/75/70 — pernyataan/garis/fungsi/cabang)
-npm run check                  # lint + test digabungkan
-npm run check:cycles           # Deteksi ketergantungan melingkar
-```
-
-### Menjalankan Tes
-
-```bash
-# File tes tunggal (penguji native Node.js — sebagian besar tes)
-node --import tsx/esm --test tests/unit/your-file.test.ts
-
-# Vitest (server MCP, autoCombo, cache)
-npm run test:vitest
-
-# Semua suite
-npm run test:all
-```
-
-Untuk matriks tes lengkap, lihat `CONTRIBUTING.md` → "Menjalankan Tes". Untuk arsitektur mendalam, lihat `AGENTS.md`.
-
----
-
-## Proyek Sekilas
-
-**OmniRoute** — proxy/router AI terpadu. Satu endpoint, 329 penyedia LLM, auto-fallback.
-
-| Lapisan       | Lokasi                  | Tujuan                                                                    |
-| ------------- | ----------------------- | ------------------------------------------------------------------------- |
-| API Routes    | `src/app/api/v1/`       | Next.js App Router — titik masuk                                          |
-| Handlers      | `open-sse/handlers/`    | Pemrosesan permintaan (chat, embeddings, dll)                             |
-| Executors     | `open-sse/executors/`   | Pengiriman HTTP spesifik penyedia                                         |
-| Translators   | `open-sse/translator/`  | Konversi format (OpenAI↔Claude↔Gemini)                                    |
-| Transformer   | `open-sse/transformer/` | API Respons ↔ Penyelesaian Chat                                           |
-| Services      | `open-sse/services/`    | Routing combo, batas kecepatan, caching, dll                              |
-| Database      | `src/lib/db/`           | 110 top-level SQLite domain modules, 130 migrations                       |
-| Domain/Policy | `src/domain/`           | Mesin kebijakan, aturan biaya, logika fallback                            |
-| MCP Server    | `open-sse/mcp-server/`  | 107 unique tools, 3 transports (stdio / SSE / Streamable HTTP), 32 scopes |
-| A2A Server    | `src/lib/a2a/`          | Protokol agen JSON-RPC 2.0                                                |
-| Skills        | `src/lib/skills/`       | Kerangka keterampilan yang dapat diperluas                                |
-| Memory        | `src/lib/memory/`       | Memori percakapan yang persisten                                          |
-
-Monorepo: `src/` (aplikasi Next.js 16), `open-sse/` (workspace mesin streaming), `electron/` (aplikasi desktop), `tests/`, `bin/` (titik masuk CLI).
-
----
-
-## Jalur Permintaan
-
-```
-Klien → /v1/chat/completions (rute Next.js)
-  → CORS → validasi Zod → otentikasi? → pemeriksaan kebijakan → penjaga injeksi prompt
-  → handleChatCore() [open-sse/handlers/chatCore.ts]
-    → pemeriksaan cache → batasan laju → pengalihan combo?
-      → resolveComboTargets() → handleSingleModel() per target
-    → translateRequest() → getExecutor() → executor.execute()
-      → fetch() upstream → coba lagi dengan backoff
-    → terjemahan respons → aliran SSE atau JSON
-    → Jika API Respons: responsesTransformer.ts TransformStream
-```
-
-Rute API mengikuti pola yang konsisten: `Rute → CORS preflight → validasi body Zod → Otentikasi opsional (extractApiKey/isValidApiKey) → penegakan kebijakan kunci API → Delegasi Handler (open-sse)`. Tidak ada middleware global Next.js — intersepsi bersifat spesifik rute.
-
-**Combo routing** (`open-sse/services/combo.ts`): 19 public strategies (priority, weighted, fill-first, round-robin, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline). Each target calls `handleSingleModel()`, which wraps `handleChatCore()` with per-target error handling and circuit-breaker checks. See `docs/routing/AUTO-COMBO.md` for the 13-factor Auto-Combo scoring and `docs/architecture/RESILIENCE_GUIDE.md` for the 3 resilience layers.
-
----
-
-## Status Runtime Ketahanan
-
-OmniRoute memiliki tiga mekanisme kegagalan sementara yang terkait tetapi berbeda. Jaga agar ruang lingkup mereka terpisah saat melakukan debugging perilaku pengalihan. Lihat diagram
-[3-lapisan ketahanan](./docs/diagrams/exported/resilience-3layers.svg)
-(sumber: [docs/diagrams/resilience-3layers.mmd](./docs/diagrams/resilience-3layers.mmd))
-untuk peta sekilas.
-
-### Pemutus Sirkuit Penyedia
-
-**Ruang Lingkup**: seluruh penyedia, misalnya `glm`, `openai`, `anthropic`.
-
-**Tujuan**: menghentikan pengiriman lalu lintas ke penyedia yang terus-menerus gagal di tingkat upstream/layanan, sehingga satu penyedia yang tidak sehat tidak memperlambat setiap permintaan.
-
-**Implementasi**:
-
-- Kelas inti: `src/shared/utils/circuitBreaker.ts`
-- Pemasangan gerbang/chat eksekusi: `src/sse/handlers/chatHelpers.ts`, `src/sse/handlers/chat.ts`
-- API status runtime: `src/app/api/monitoring/health/route.ts`
-- Pembungkus bersama: `open-sse/services/accountFallback.ts`
-- Tabel status yang dipersistenkan: `domain_circuit_breakers`
-
-**Status**:
-
-- `CLOSED`: lalu lintas normal diizinkan.
-- `OPEN`: penyedia diblokir sementara; pemanggil mendapatkan respons pemutus-sirkuit-penyedia-terbuka
-  atau pengalihan combo melewati target lain.
-- `HALF_OPEN`: waktu reset telah berlalu; izinkan permintaan probe. Keberhasilan menutup
-  pemutus, kegagalan membukanya lagi.
-
-**Defaults** (`open-sse/config/constants.ts`):
-
-- Penyedia OAuth: ambang `3`, waktu reset `60s`.
-- Penyedia kunci API: ambang `5`, waktu reset `30s`.
-- Penyedia lokal: ambang `2`, waktu reset `15s`.
-
-Hanya status kegagalan tingkat penyedia yang harus memicu pemutus penyedia:
-
-```ts
-(408, 500, 502, 503, 504);
-```
-
-Jangan memicu pemutus seluruh-penyedia untuk kesalahan akun/kunci/model normal seperti kebanyakan
-kasus `401`, `403`, atau `429`. Itu biasanya termasuk dalam cooldown koneksi atau penguncian model. Penyedia kunci API generik `403` harus dapat dipulihkan kecuali diklasifikasikan
-sebagai kesalahan penyedia/akun terminal.
-
-Pemutus menggunakan pemulihan malas, bukan timer latar belakang. Ketika `OPEN` kedaluwarsa, pembacaan seperti `getStatus()`, `canExecute()`, dan `getRetryAfterMs()` menyegarkan status menjadi
-`HALF_OPEN`, sehingga dasbor dan pembangun kandidat combo tidak terus mengecualikan penyedia yang kedaluwarsa selamanya.
-
-### Cooldown Koneksi
-
-**Ruang Lingkup**: satu koneksi/akun/kunci penyedia.
-
-**Tujuan**: sementara melewatkan satu kunci/akun yang buruk sambil memungkinkan koneksi lain untuk
-penyedia yang sama terus melayani permintaan.
-
-**Implementasi**:
-
-- Jalur tulis/perbarui: `src/sse/services/auth.ts::markAccountUnavailable()`
-- Pemilihan/filtering akun: `src/sse/services/auth.ts::getProviderCredentials...`
-- Perhitungan cooldown: `open-sse/services/accountFallback.ts::checkFallbackError()`
-- Pengaturan: `src/lib/resilience/settings.ts`
-
-Bidang penting pada koneksi penyedia:
-
-```ts
-rateLimitedUntil;
-testStatus: "unavailable";
-lastError;
-lastErrorType;
-errorCode;
-backoffLevel;
-```
-
-Selama pemilihan akun, koneksi dilewatkan sementara:
-
-```ts
-new Date(rateLimitedUntil).getTime() > Date.now();
-```
-
-Cooldown juga malas: ketika `rateLimitedUntil` berada di masa lalu, koneksi menjadi
-layak lagi. Pada penggunaan yang berhasil, `clearAccountError()` menghapus `testStatus`,
-`rateLimitedUntil`, bidang kesalahan, dan `backoffLevel`.
-
-Perilaku default cooldown koneksi:
-
-- Cooldown dasar OAuth: `5s`.
-- Cooldown dasar kunci API: `3s`.
-- Kunci API `429` harus lebih memilih petunjuk coba lagi upstream (`Retry-After`, header reset, atau
-  teks reset yang dapat diuraikan) jika tersedia.
-- Kegagalan yang dapat dipulihkan berulang menggunakan backoff eksponensial:
-
-```ts
-baseCooldownMs * 2 ** failureIndex;
-```
-
-Penjaga anti-thundering-herd mencegah kegagalan bersamaan pada koneksi yang sama dari
-berulang kali memperpanjang cooldown atau menggandakan `backoffLevel`.
-
-Status terminal bukanlah cooldown. `banned`, `expired`, dan `credits_exhausted` dimaksudkan untuk tetap tidak tersedia sampai kredensial/pengaturan berubah atau operator meresetnya. Jangan menimpa status terminal dengan status cooldown sementara.
-
-### Penguncian Model
-
-**Ruang Lingkup**: penyedia + koneksi + model.
-
-**Tujuan**: menghindari menonaktifkan seluruh koneksi ketika hanya satu model yang tidak tersedia atau
-terbatas kuota untuk koneksi tersebut.
-
-Contoh:
-
-- Penyedia kuota per-model yang mengembalikan `429`.
-- Penyedia lokal yang mengembalikan `404` untuk satu model yang hilang.
-- Kegagalan izin mode/model spesifik penyedia seperti mode Grok yang dipilih.
-
-Penguncian model berada di `open-sse/services/accountFallback.ts` dan memungkinkan koneksi yang sama
-terus melayani model lain.
-
-### Panduan Debugging
-
-- Jika semua kunci untuk penyedia dilewatkan, periksa status pemutus penyedia dan setiap
-  koneksi `rateLimitedUntil`/`testStatus`.
-- Jika penyedia tampak secara permanen dikecualikan setelah jendela reset, periksa apakah kode
-  membaca `state` mentah alih-alih menggunakan `getStatus()`/`canExecute()`.
-- Jika satu kunci penyedia gagal tetapi yang lain seharusnya berfungsi, lebih baik memilih cooldown koneksi daripada
-  pemutus penyedia.
-- Jika hanya satu model yang gagal, lebih baik memilih penguncian model daripada cooldown koneksi.
-- Jika sebuah status seharusnya pulih sendiri, itu harus memiliki cap waktu/reset timeout di masa depan dan jalur
-  baca yang menyegarkan status yang kedaluwarsa. Status permanen memerlukan perubahan kredensial
-  atau konfigurasi manual.
-
-## Konvensi Kunci
-
-### Gaya Kode
-
-- **2 spasi**, titik koma, tanda kutip ganda, lebar 100 karakter, koma trailing es5 (ditegakkan oleh lint-staged melalui Prettier)
-- **Impor**: eksternal → internal (`@/`, `@omniroute/open-sse`) → relatif
-- **Penamaan**: file=camelCase/kebab, komponen=PascalCase, konstanta=UPPER_SNAKE
-- **ESLint**: `no-eval`, `no-implied-eval`, `no-new-func` = kesalahan di mana saja; `no-explicit-any` = peringatan di `open-sse/` dan `tests/`
-- **TypeScript**: `strict: false`, target ES2022, modul esnext, resolusi bundler. Utamakan tipe eksplisit.
-
-### Basis Data
-
-- **Selalu** melalui modul domain `src/lib/db/` — **jangan pernah** menulis SQL mentah di rute atau pengendali
-- **Jangan pernah** menambahkan logika ke `src/lib/localDb.ts` (hanya lapisan re-ekspor)
-- **Jangan pernah** barrel-import dari `localDb.ts` — impor modul `db/` tertentu sebagai gantinya
-- Singleton DB: `getDbInstance()` dari `src/lib/db/core.ts` (jurnal WAL)
-- Migrasi: `src/lib/db/migrations/` — file SQL versi, idempotent, dijalankan dalam transaksi
-
-### Penanganan Kesalahan
-
-- coba/tangkap dengan tipe kesalahan tertentu, log dengan konteks pino
-- Jangan pernah menelan kesalahan dalam aliran SSE — gunakan sinyal abort untuk pembersihan
-- Kembalikan kode status HTTP yang tepat (4xx/5xx)
-
-### Keamanan
-
-- **Jangan pernah** menggunakan `eval()`, `new Function()`, atau eval implisit
-- Validasi semua input dengan skema Zod
-- Enkripsi kredensial saat tidak aktif (AES-256-GCM)
-- Daftar penolakan header upstream: `src/shared/constants/upstreamHeaders.ts` — jaga sanitasi, skema Zod, dan pengujian unit tetap selaras saat mengedit
-- **Kredensial upstream publik** (Gemini/Antigravity/Windsurf-style OAuth client_id/secret + kunci Web Firebase yang diekstrak dari CLI publik): **HARUS** disematkan melalui `resolvePublicCred()` dari `open-sse/utils/publicCreds.ts` — **jangan pernah** sebagai literal string. Lihat `docs/security/PUBLIC_CREDS.md` untuk pola yang wajib.
-- **Respon kesalahan** (HTTP / SSE / eksekutor / pengendali MCP): **HARUS** diarahkan melalui `buildErrorBody()` atau `sanitizeErrorMessage()` dari `open-sse/utils/error.ts` — **jangan pernah** menempatkan `err.stack` atau `err.message` mentah dalam tubuh respon. Lihat `docs/security/ERROR_SANITIZATION.md`.
-- **Perintah shell yang dibangun dari variabel**: saat memanggil `exec()`/`spawn()` dengan skrip yang memerlukan nilai runtime, kirimkan melalui opsi `env` (secara otomatis di-escape shell) — **jangan pernah** melakukan interpolasi string jalur yang tidak tepercaya/eksternal ke dalam tubuh skrip. Referensi: `src/mitm/cert/install.ts::updateNssDatabases`.
-- **Perpustakaan aman secara default** ([tldrsec/awesome-secure-defaults](https://github.com/tldrsec/awesome-secure-defaults)): utamakan Helmet.js, DOMPurify, ssrf-req-filter, safe-regex, Google Tink daripada implementasi kustom kapan pun menambahkan permukaan yang sensitif terhadap keamanan yang baru.
-
----
-
-## Skenario Modifikasi Umum
-
-### Menambahkan Penyedia Baru
-
-1. Daftarkan di `src/shared/constants/providers.ts` (divalidasi Zod saat dimuat)
-2. Tambahkan eksekutor di `open-sse/executors/` jika logika kustom diperlukan (perluas `BaseExecutor`)
-3. Tambahkan penerjemah di `open-sse/translator/` jika format bukan OpenAI
-4. Tambahkan konfigurasi OAuth di `src/lib/oauth/constants/oauth.ts` jika berbasis OAuth — jika CLI upstream mengirimkan client_id/secret publik, sematkan melalui `resolvePublicCred()` (lihat `docs/security/PUBLIC_CREDS.md`), **jangan pernah** sebagai literal
-5. Daftarkan model di `open-sse/config/providerRegistry.ts`
-6. Tulis pengujian di `tests/unit/` (termasuk pernyataan bentuk publicCreds jika Anda menambahkan default yang disematkan baru)
-
-### Menambahkan Rute API Baru
-
-1. Buat direktori di bawah `src/app/api/v1/your-route/`
-2. Buat `route.ts` dengan pengendali `GET`/`POST`
-3. Ikuti pola: CORS → validasi tubuh Zod → otentikasi opsional → delegasi pengendali
-4. Pengendali ditempatkan di `open-sse/handlers/` (impor dari sana, bukan inline)
-5. Respon kesalahan menggunakan `buildErrorBody()` / `errorResponse()` dari `open-sse/utils/error.ts` (otomatis disanitasi — jangan pernah menempatkan `err.stack` atau `err.message` mentah dalam tubuh). Lihat `docs/security/ERROR_SANITIZATION.md`.
-6. Tambahkan pengujian — termasuk setidaknya satu pernyataan bahwa respon kesalahan tidak membocorkan jejak tumpukan (`!body.error.message.includes("at /")`)
-
-### Menambahkan Modul DB Baru
-
-1. Buat `src/lib/db/yourModule.ts` — impor `getDbInstance` dari `./core.ts`
-2. Ekspor fungsi CRUD untuk tabel domain Anda
-3. Tambahkan migrasi di `src/lib/db/migrations/` jika tabel baru diperlukan
-4. Re-ekspor dari `src/lib/localDb.ts` (tambahkan ke daftar re-ekspor saja)
-5. Tulis pengujian
-
-### Menambahkan Alat MCP Baru
-
-1. Tambahkan definisi alat di `open-sse/mcp-server/tools/` dengan skema input Zod + pengendali asinkron
-2. Daftarkan dalam set alat (terhubung oleh `createMcpServer()`)
-3. Tetapkan ke lingkup yang sesuai
-4. Tulis pengujian (panggilan alat dicatat ke tabel `mcp_audit`)
-
-### Menambahkan Keterampilan A2A Baru
-
-1. Buat keterampilan di `src/lib/a2a/skills/` (5 sudah ada: smart-routing, quota-management, provider-discovery, cost-analysis, health-report)
-2. Keterampilan menerima konteks tugas (pesan, metadata) → mengembalikan hasil terstruktur
-3. Daftarkan di `A2A_SKILL_HANDLERS` di `src/lib/a2a/taskExecution.ts`
-4. Ekspos di `src/app/.well-known/agent.json/route.ts` (Kartu Agen)
-5. Tulis pengujian di `tests/unit/`
-6. Dokumentasikan di tabel keterampilan `docs/frameworks/A2A-SERVER.md`
-
-### Menambahkan Agen Cloud Baru
-
-1. Buat kelas agen di `src/lib/cloudAgent/agents/` yang memperluas `CloudAgentBase` (3 sudah ada: codex-cloud, devin, jules)
-2. Implementasikan `createTask`, `getStatus`, `approvePlan`, `sendMessage`, `listSources`
-3. Daftarkan di `src/lib/cloudAgent/registry.ts`
-4. Tambahkan penanganan OAuth/kredensial jika diperlukan (`src/lib/oauth/providers/`)
-5. Pengujian + dokumentasikan di `docs/frameworks/CLOUD_AGENT.md`
-
-### Menambahkan Guardrail / Eval / Keterampilan / Acara Webhook Baru
-
-- Guardrail: `src/lib/guardrails/` → dokumen: `docs/security/GUARDRAILS.md`
-- Suite Eval: `src/lib/evals/` → dokumen: `docs/frameworks/EVALS.md`
-- Keterampilan (sandbox): `src/lib/skills/` → dokumen: `docs/frameworks/SKILLS.md`
-- Acara Webhook: `src/lib/webhookDispatcher.ts` → dokumen: `docs/frameworks/WEBHOOKS.md`
-
-## Dokumentasi Referensi
-
-Untuk setiap perubahan yang tidak sepele, baca pendalaman yang sesuai terlebih dahulu:
-
-| Area                                    | Dok                                                               |
-| --------------------------------------- | ----------------------------------------------------------------- |
-| Navigasi repo                           | `docs/architecture/REPOSITORY_MAP.md`                             |
-| Arsitektur                              | `docs/architecture/ARCHITECTURE.md`                               |
-| Referensi teknik                        | `docs/architecture/CODEBASE_DOCUMENTATION.md`                     |
-| Auto-Combo (13-factor scoring, 19 public strategies) | `docs/routing/AUTO-COMBO.md` |
-| Ketahanan (3 mekanisme)                 | `docs/architecture/RESILIENCE_GUIDE.md`                           |
-| Pemutaran penalaran                     | `docs/routing/REASONING_REPLAY.md`                                |
-| Kerangka keterampilan                   | `docs/frameworks/SKILLS.md`                                       |
-| Sistem memori (FTS5 + Qdrant)           | `docs/frameworks/MEMORY.md`                                       |
-| Agen cloud                              | `docs/frameworks/CLOUD_AGENT.md`                                  |
-| Pembatas (PII / injeksi / visi)         | `docs/security/GUARDRAILS.md`                                     |
-| Kredensial publik hulu (Gemini/dll.)    | `docs/security/PUBLIC_CREDS.md`                                   |
-| Sanitasi pesan kesalahan                | `docs/security/ERROR_SANITIZATION.md`                             |
-| Evaluasi                                | `docs/frameworks/EVALS.md`                                        |
-| Kepatuhan / audit                       | `docs/security/COMPLIANCE.md`                                     |
-| Webhook                                 | `docs/frameworks/WEBHOOKS.md`                                     |
-| Jalur otorisasi                         | `docs/architecture/AUTHZ_GUIDE.md`                                |
-| Stealth (TLS / sidik jari)              | `docs/security/STEALTH_GUIDE.md`                                  |
-| Protokol agen (A2A / ACP / Cloud)       | `docs/frameworks/AGENT_PROTOCOLS_GUIDE.md`                        |
-| Server MCP                              | `docs/frameworks/MCP-SERVER.md`                                   |
-| Server A2A                              | `docs/frameworks/A2A-SERVER.md`                                   |
-| Referensi API + OpenAPI                 | `docs/reference/API_REFERENCE.md` + `docs/reference/openapi.yaml` |
-| Katalog penyedia (auto-dihasilkan)      | `docs/reference/PROVIDER_REFERENCE.md`                            |
-| Alur rilis                              | `docs/ops/RELEASE_CHECKLIST.md`                                   |
-
----
-
-## Pengujian
-
-| Apa                     | Perintah                                                               |
-| ----------------------- | ---------------------------------------------------------------------- |
-| Uji unit                | `npm run test:unit`                                                    |
-| File tunggal            | `node --import tsx/esm --test tests/unit/file.test.ts`                 |
-| Vitest (MCP, autoCombo) | `npm run test:vitest`                                                  |
-| E2E (Playwright)        | `npm run test:e2e`                                                     |
-| Protokol E2E (MCP+A2A)  | `npm run test:protocols:e2e`                                           |
-| Ekosistem               | `npm run test:ecosystem`                                               |
-| Gerbang cakupan         | `npm run test:coverage` (75/75/75/70 — pernyataan/garis/fungsi/cabang) |
-| Laporan cakupan         | `npm run coverage:report`                                              |
-
-**Aturan PR**: Jika Anda mengubah kode produksi di `src/`, `open-sse/`, `electron/`, atau `bin/`, Anda harus menyertakan atau memperbarui pengujian dalam PR yang sama.
-
-**Preferensi lapisan pengujian**: unit pertama → integrasi (multi-modul atau status DB) → e2e (UI/workflow saja). Kodekan reproduksi bug sebagai pengujian otomatis sebelum atau bersamaan dengan perbaikan.
-
-**Kebijakan cakupan Copilot**: Ketika PR mengubah kode produksi dan cakupan di bawah 75% (pernyataan/garis/fungsi) atau 70% (cabang), jangan hanya melaporkan — tambahkan atau perbarui pengujian, jalankan kembali gerbang cakupan, lalu minta konfirmasi. Sertakan perintah yang dijalankan, file pengujian yang diubah, dan hasil cakupan akhir dalam laporan PR.
-
----
-
-## Alur Kerja Git
-
-```bash
-# Jangan pernah melakukan commit langsung ke main
-git checkout -b feat/your-feature
-git commit -m "feat: deskripsikan perubahan Anda"
-git push -u origin feat/your-feature
-```
-
-**Awalan cabang**: `feat/`, `fix/`, `refactor/`, `docs/`, `test/`, `chore/`
-
-**Format commit** (Conventional Commits): `feat(db): tambahkan circuit breaker` — lingkup: `db`, `sse`, `oauth`, `dashboard`, `api`, `cli`, `docker`, `ci`, `mcp`, `a2a`, `memory`, `skills`
-
-**Hook Husky**:
-
-- **pre-commit**: lint-staged + `check-docs-sync` + `check:any-budget:t11`
-- **pre-push**: `npm run test:unit`
-
----
-
-## Lingkungan
-
-- **Runtime**: Node.js ≥20.20.2 <21 |
-  | ≥22.22.2 <23 |
-  | ≥24 <25, ES Modules
-- **TypeScript**: 5.9+, target ES2022, module esnext, resolution bundler
-- **Alias jalur**: `@/*` → `src/`, `@omniroute/open-sse` → `open-sse/`, `@omniroute/open-sse/*` → `open-sse/*`
-- **Port default**: 20128 (API + dashboard di port yang sama)
-- **Direktori data**: variabel lingkungan `DATA_DIR`, default ke `~/.omniroute/`
-- **Variabel lingkungan kunci**: `PORT`, `JWT_SECRET`, `API_KEY_SECRET`, `INITIAL_PASSWORD`, `REQUIRE_API_KEY`, `APP_LOG_LEVEL`
-- Setup: `cp .env.example .env` lalu buat `JWT_SECRET` (`openssl rand -base64 48`) dan `API_KEY_SECRET` (`openssl rand -hex 32`)
-
----
-
-## Aturan Keras
-
-1. Jangan pernah melakukan commit rahasia atau kredensial
-2. Jangan pernah menambahkan logika ke `localDb.ts`
-3. Jangan pernah menggunakan `eval()` / `new Function()` / eval implisit
-4. Jangan pernah melakukan commit langsung ke `main`
-5. Jangan pernah menulis SQL mentah di rute — gunakan modul `src/lib/db/`
-6. Jangan pernah menelan kesalahan secara diam-diam di aliran SSE
-7. Selalu validasi input dengan skema Zod
-8. Selalu sertakan pengujian saat mengubah kode produksi
-9. Cakupan harus tetap ≥75% (pernyataan, garis, fungsi) / ≥70% (cabang). Saat ini terukur: ~82%.
-10. Jangan pernah melewati hook Husky (`--no-verify`, `--no-gpg-sign`) tanpa persetujuan operator yang eksplisit.
-11. Jangan pernah menyematkan client_id/secret OAuth upstream publik atau kunci Web Firebase sebagai literal string — selalu melalui `resolvePublicCred()` (`open-sse/utils/publicCreds.ts`). Lihat `docs/security/PUBLIC_CREDS.md`.
-12. Jangan pernah mengembalikan `err.stack` / `err.message` mentah dalam respons HTTP / SSE / executor — selalu rute melalui `buildErrorBody()` atau `sanitizeErrorMessage()` (`open-sse/utils/error.ts`). Lihat `docs/security/ERROR_SANITIZATION.md`.
-13. Jangan pernah melakukan interpolasi string jalur eksternal atau nilai runtime ke dalam skrip shell yang diteruskan ke `exec()`/`spawn()` — lewati melalui opsi `env` sebagai gantinya. Referensi: `src/mitm/cert/install.ts::updateNssDatabases`.
-14. Jangan pernah mengabaikan peringatan CodeQL / Secret-Scanning tanpa (a) terlebih dahulu memeriksa dokumen pola di atas untuk melihat apakah pembantu berlaku, dan (b) mencatat justifikasi teknis dalam komentar pengabaian. Preseden: `js/stack-trace-exposure` yang muncul di callsites yang sudah rute melalui `sanitizeErrorMessage()` adalah batasan CodeQL yang dikenal (pembersih kustom tidak dikenali) — abaikan sebagai `false positive` yang merujuk pada `docs/security/ERROR_SANITIZATION.md`.
-15. Jangan pernah mengekspos rute yang memunculkan proses anak (`/api/mcp/`, `/api/cli-tools/runtime/`) tanpa klasifikasi `isLocalOnlyPath()` di `src/server/authz/routeGuard.ts`. Penegakan loopback terjadi tanpa syarat sebelum pemeriksaan otentikasi — JWT yang bocor melalui terowongan tidak dapat memicu pemunculan proses. Lihat `docs/security/ROUTE_GUARD_TIERS.md`.
-16. Jangan pernah menyertakan trailer `Co-Authored-By` yang memberi kredit kepada asisten AI, LLM, atau akun otomatisasi (mis. nama yang mengandung "Claude", "GPT", "Copilot", "Bot"; email di `anthropic.com` / `openai.com` / alamat `noreply.github.com` milik bot). Trailer semacam itu mengarahkan atribusi commit ke akun bot di GitHub, menyembunyikan penulis sebenarnya (`diegosouzapw`) dalam riwayat PR. Kolaborator manusia — termasuk penulis PR upstream dan pelapor issue yang di-port ke OmniRoute — DAPAT dan HARUS dikreditkan dengan trailer standar `Co-authored-by: Name <email>`; alur kerja upstream-port (`/port-upstream-features`, `/port-upstream-issues`) bergantung pada ini.
diff --git a/docs/i18n/in/CODE_OF_CONDUCT.md b/docs/i18n/in/CODE_OF_CONDUCT.md
deleted file mode 100644
index 9f2e884560..0000000000
--- a/docs/i18n/in/CODE_OF_CONDUCT.md
+++ /dev/null
@@ -1,132 +0,0 @@
-# Contributor Covenant Code of Conduct (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../CODE_OF_CONDUCT.md) · 🇪🇸 [es](../es/CODE_OF_CONDUCT.md) · 🇫🇷 [fr](../fr/CODE_OF_CONDUCT.md) · 🇩🇪 [de](../de/CODE_OF_CONDUCT.md) · 🇮🇹 [it](../it/CODE_OF_CONDUCT.md) · 🇷🇺 [ru](../ru/CODE_OF_CONDUCT.md) · 🇨🇳 [zh-CN](../zh-CN/CODE_OF_CONDUCT.md) · 🇯🇵 [ja](../ja/CODE_OF_CONDUCT.md) · 🇰🇷 [ko](../ko/CODE_OF_CONDUCT.md) · 🇸🇦 [ar](../ar/CODE_OF_CONDUCT.md) · 🇮🇳 [hi](../hi/CODE_OF_CONDUCT.md) · 🇮🇳 [in](../in/CODE_OF_CONDUCT.md) · 🇹🇭 [th](../th/CODE_OF_CONDUCT.md) · 🇻🇳 [vi](../vi/CODE_OF_CONDUCT.md) · 🇮🇩 [id](../id/CODE_OF_CONDUCT.md) · 🇲🇾 [ms](../ms/CODE_OF_CONDUCT.md) · 🇳🇱 [nl](../nl/CODE_OF_CONDUCT.md) · 🇵🇱 [pl](../pl/CODE_OF_CONDUCT.md) · 🇸🇪 [sv](../sv/CODE_OF_CONDUCT.md) · 🇳🇴 [no](../no/CODE_OF_CONDUCT.md) · 🇩🇰 [da](../da/CODE_OF_CONDUCT.md) · 🇫🇮 [fi](../fi/CODE_OF_CONDUCT.md) · 🇵🇹 [pt](../pt/CODE_OF_CONDUCT.md) · 🇷🇴 [ro](../ro/CODE_OF_CONDUCT.md) · 🇭🇺 [hu](../hu/CODE_OF_CONDUCT.md) · 🇧🇬 [bg](../bg/CODE_OF_CONDUCT.md) · 🇸🇰 [sk](../sk/CODE_OF_CONDUCT.md) · 🇺🇦 [uk-UA](../uk-UA/CODE_OF_CONDUCT.md) · 🇮🇱 [he](../he/CODE_OF_CONDUCT.md) · 🇵🇭 [phi](../phi/CODE_OF_CONDUCT.md) · 🇧🇷 [pt-BR](../pt-BR/CODE_OF_CONDUCT.md) · 🇨🇿 [cs](../cs/CODE_OF_CONDUCT.md) · 🇹🇷 [tr](../tr/CODE_OF_CONDUCT.md)
-
----
-
-## Our Pledge
-
-We as members, contributors, and leaders pledge to make participation in our
-community a harassment-free experience for everyone, regardless of age, body
-size, visible or invisible disability, ethnicity, sex characteristics, gender
-identity and expression, level of experience, education, socio-economic status,
-nationality, personal appearance, race, religion, or sexual identity
-and orientation.
-
-We pledge to act and interact in ways that contribute to an open, welcoming,
-diverse, inclusive, and healthy community.
-
-## Our Standards
-
-Examples of behavior that contributes to a positive environment for our
-community include:
-
-- Demonstrating empathy and kindness toward other people
-- Being respectful of differing opinions, viewpoints, and experiences
-- Giving and gracefully accepting constructive feedback
-- Accepting responsibility and apologizing to those affected by our mistakes,
-  and learning from the experience
-- Focusing on what is best not just for us as individuals, but for the
-  overall community
-
-Examples of unacceptable behavior include:
-
-- The use of sexualized language or imagery, and sexual attention or
-  advances of any kind
-- Trolling, insulting or derogatory comments, and personal or political attacks
-- Public or private harassment
-- Publishing others' private information, such as a physical or email
-  address, without their explicit permission
-- Other conduct which could reasonably be considered inappropriate in a
-  professional setting
-
-## Enforcement Responsibilities
-
-Community leaders are responsible for clarifying and enforcing our standards of
-acceptable behavior and will take appropriate and fair corrective action in
-response to any behavior that they deem inappropriate, threatening, offensive,
-or harmful.
-
-Community leaders have the right and responsibility to remove, edit, or reject
-comments, commits, code, wiki edits, issues, and other contributions that are
-not aligned to this Code of Conduct, and will communicate reasons for moderation
-decisions when appropriate.
-
-## Scope
-
-This Code of Conduct applies within all community spaces, and also applies when
-an individual is officially representing the community in public spaces.
-Examples of representing our community include using an official e-mail address,
-posting via an official social media account, or acting as an appointed
-representative at an online or offline event.
-
-## Enforcement
-
-Instances of abusive, harassing, or otherwise unacceptable behavior may be
-reported to the community leaders responsible for enforcement at
-.
-All complaints will be reviewed and investigated promptly and fairly.
-
-All community leaders are obligated to respect the privacy and security of the
-reporter of any incident.
-
-## Enforcement Guidelines
-
-Community leaders will follow these Community Impact Guidelines in determining
-the consequences for any action they deem in violation of this Code of Conduct:
-
-### 1. Correction
-
-**Community Impact**: Use of inappropriate language or other behavior deemed
-unprofessional or unwelcome in the community.
-
-**Consequence**: A private, written warning from community leaders, providing
-clarity around the nature of the violation and an explanation of why the
-behavior was inappropriate. A public apology may be requested.
-
-### 2. Warning
-
-**Community Impact**: A violation through a single incident or series
-of actions.
-
-**Consequence**: A warning with consequences for continued behavior. No
-interaction with the people involved, including unsolicited interaction with
-those enforcing the Code of Conduct, for a specified period of time. This
-includes avoiding interactions in community spaces as well as external channels
-like social media. Violating these terms may lead to a temporary or
-permanent ban.
-
-### 3. Temporary Ban
-
-**Community Impact**: A serious violation of community standards, including
-sustained inappropriate behavior.
-
-**Consequence**: A temporary ban from any sort of interaction or public
-communication with the community for a specified period of time. No public or
-private interaction with the people involved, including unsolicited interaction
-with those enforcing the Code of Conduct, is allowed during this period.
-Violating these terms may lead to a permanent ban.
-
-### 4. Permanent Ban
-
-**Community Impact**: Demonstrating a pattern of violation of community
-standards, including sustained inappropriate behavior, harassment of an
-individual, or aggression toward or disparagement of classes of individuals.
-
-**Consequence**: A permanent ban from any sort of public interaction within
-the community.
-
-## Attribution
-
-This Code of Conduct is adapted from the [Contributor Covenant][homepage],
-version 2.0, available at
-https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
-
-Community Impact Guidelines were inspired by [Mozilla's code of conduct
-enforcement ladder](https://github.com/mozilla/diversity).
-
-[homepage]: https://www.contributor-covenant.org
-
-For answers to common questions about this code of conduct, see the FAQ at
-https://www.contributor-covenant.org/faq. Translations are available at
-https://www.contributor-covenant.org/translations.
diff --git a/docs/i18n/in/CONTRIBUTING.md b/docs/i18n/in/CONTRIBUTING.md
deleted file mode 100644
index 2332c6bec2..0000000000
--- a/docs/i18n/in/CONTRIBUTING.md
+++ /dev/null
@@ -1,311 +0,0 @@
-# Contributing to OmniRoute (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../CONTRIBUTING.md) · 🇪🇸 [es](../es/CONTRIBUTING.md) · 🇫🇷 [fr](../fr/CONTRIBUTING.md) · 🇩🇪 [de](../de/CONTRIBUTING.md) · 🇮🇹 [it](../it/CONTRIBUTING.md) · 🇷🇺 [ru](../ru/CONTRIBUTING.md) · 🇨🇳 [zh-CN](../zh-CN/CONTRIBUTING.md) · 🇯🇵 [ja](../ja/CONTRIBUTING.md) · 🇰🇷 [ko](../ko/CONTRIBUTING.md) · 🇸🇦 [ar](../ar/CONTRIBUTING.md) · 🇮🇳 [hi](../hi/CONTRIBUTING.md) · 🇮🇳 [in](../in/CONTRIBUTING.md) · 🇹🇭 [th](../th/CONTRIBUTING.md) · 🇻🇳 [vi](../vi/CONTRIBUTING.md) · 🇮🇩 [id](../id/CONTRIBUTING.md) · 🇲🇾 [ms](../ms/CONTRIBUTING.md) · 🇳🇱 [nl](../nl/CONTRIBUTING.md) · 🇵🇱 [pl](../pl/CONTRIBUTING.md) · 🇸🇪 [sv](../sv/CONTRIBUTING.md) · 🇳🇴 [no](../no/CONTRIBUTING.md) · 🇩🇰 [da](../da/CONTRIBUTING.md) · 🇫🇮 [fi](../fi/CONTRIBUTING.md) · 🇵🇹 [pt](../pt/CONTRIBUTING.md) · 🇷🇴 [ro](../ro/CONTRIBUTING.md) · 🇭🇺 [hu](../hu/CONTRIBUTING.md) · 🇧🇬 [bg](../bg/CONTRIBUTING.md) · 🇸🇰 [sk](../sk/CONTRIBUTING.md) · 🇺🇦 [uk-UA](../uk-UA/CONTRIBUTING.md) · 🇮🇱 [he](../he/CONTRIBUTING.md) · 🇵🇭 [phi](../phi/CONTRIBUTING.md) · 🇧🇷 [pt-BR](../pt-BR/CONTRIBUTING.md) · 🇨🇿 [cs](../cs/CONTRIBUTING.md) · 🇹🇷 [tr](../tr/CONTRIBUTING.md)
-
----
-
-Thank you for your interest in contributing! This guide covers everything you need to get started.
-
----
-
-## Development Setup
-
-### Prerequisites
-
-- **Node.js** >= 18 < 24 (recommended: 22 LTS)
-- **npm** 10+
-- **Git**
-
-### Clone & Install
-
-```bash
-git clone https://github.com/diegosouzapw/OmniRoute.git
-cd OmniRoute
-npm install
-```
-
-### Environment Variables
-
-```bash
-# Create your .env from the template
-cp .env.example .env
-
-# Generate required secrets
-echo "JWT_SECRET=$(openssl rand -base64 48)" >> .env
-echo "API_KEY_SECRET=$(openssl rand -hex 32)" >> .env
-```
-
-Key variables for development:
-
-| Variable               | Development Default      | Description           |
-| ---------------------- | ------------------------ | --------------------- |
-| `PORT`                 | `20128`                  | Server port           |
-| `NEXT_PUBLIC_BASE_URL` | `http://localhost:20128` | Base URL for frontend |
-| `JWT_SECRET`           | (generate above)         | JWT signing secret    |
-| `INITIAL_PASSWORD`     | `CHANGEME`               | First login password  |
-| `APP_LOG_LEVEL`        | `info`                   | Log verbosity level   |
-
-### Dashboard Settings
-
-The dashboard provides UI toggles for features that can also be configured via environment variables:
-
-| Setting Location    | Toggle             | Description                    |
-| ------------------- | ------------------ | ------------------------------ |
-| Settings → Advanced | Debug Mode         | Enable debug request logs (UI) |
-| Settings → General  | Sidebar Visibility | Show/hide sidebar sections     |
-
-These settings are stored in the database and persist across restarts, overriding env var defaults when set.
-
-### Running Locally
-
-```bash
-# Development mode (hot reload)
-npm run dev
-
-# Production build
-npm run build
-npm run start
-
-# Common port configuration
-PORT=20128 NEXT_PUBLIC_BASE_URL=http://localhost:20128 npm run dev
-```
-
-Default URLs:
-
-- **Dashboard**: `http://localhost:20128/dashboard`
-- **API**: `http://localhost:20128/v1`
-
----
-
-## Git Workflow
-
-> ⚠️ **NEVER commit directly to `main`.** Always use feature branches.
-
-```bash
-git checkout -b feat/your-feature-name
-# ... make changes ...
-git commit -m "feat: describe your change"
-git push -u origin feat/your-feature-name
-# Open a Pull Request on GitHub
-```
-
-### Branch Naming
-
-| Prefix      | Purpose                   |
-| ----------- | ------------------------- |
-| `feat/`     | New features              |
-| `fix/`      | Bug fixes                 |
-| `refactor/` | Code restructuring        |
-| `docs/`     | Documentation changes     |
-| `test/`     | Test additions/fixes      |
-| `chore/`    | Tooling, CI, dependencies |
-
-### Commit Messages
-
-Follow [Conventional Commits](https://www.conventionalcommits.org/):
-
-```
-feat: add circuit breaker for provider calls
-fix: resolve JWT secret validation edge case
-docs: update SECURITY.md with PII protection
-test: add observability unit tests
-refactor(db): consolidate rate limit tables
-```
-
-Scopes: `db`, `sse`, `oauth`, `dashboard`, `api`, `cli`, `docker`, `ci`, `mcp`, `a2a`, `memory`, `skills`.
-
----
-
-## Running Tests
-
-```bash
-# All tests (unit + vitest + ecosystem + e2e)
-npm run test:all
-
-# Single test file (Node.js native test runner — most tests use this)
-node --import tsx/esm --test tests/unit/your-file.test.ts
-
-# Vitest (MCP server, autoCombo, cache)
-npm run test:vitest
-
-# E2E tests (requires Playwright)
-npm run test:e2e
-
-# Protocol clients E2E (MCP transports, A2A)
-npm run test:protocols:e2e
-
-# Ecosystem compatibility tests
-npm run test:ecosystem
-
-# Coverage (60% min statements/lines/functions/branches)
-npm run test:coverage
-npm run coverage:report
-
-# Lint + format check
-npm run lint
-npm run check
-```
-
-Coverage notes:
-
-- `npm run test:coverage` measures source coverage for the main unit test suite, excludes `tests/**`, and includes `open-sse/**`
-- Pull requests must keep the overall coverage gate at **60% or higher** for statements, lines, functions, and branches
-- If a PR changes production code in `src/`, `open-sse/`, `electron/`, or `bin/`, it must add or update automated tests in the same PR
-- `npm run coverage:report` prints the detailed file-by-file report from the latest coverage run
-- `npm run test:coverage:legacy` preserves the older metric for historical comparison
-- See `docs/ops/COVERAGE_PLAN.md` for the phased coverage improvement roadmap
-
-### Pull Request Requirements
-
-Before opening or merging a PR:
-
-- Run `npm run test:unit`
-- Run `npm run test:coverage`
-- Ensure the coverage gate stays at **60%+** for all metrics
-- Include the changed or added test files in the PR description when production code changed
-- Check the SonarQube result on the PR when the project secrets are configured in CI
-
-Current test status: **122 unit test files** covering:
-
-- Provider translators and format conversion
-- Rate limiting, circuit breaker, and resilience
-- Semantic cache, idempotency, progress tracking
-- Database operations and schema (21 DB modules)
-- OAuth flows and authentication
-- API endpoint validation (Zod v4)
-- MCP server tools and scope enforcement
-- Memory and Skills systems
-
----
-
-## Code Style
-
-- **ESLint** — Run `npm run lint` before committing
-- **Prettier** — Auto-formatted via `lint-staged` on commit (2 spaces, semicolons, double quotes, 100 char width, es5 trailing commas)
-- **TypeScript** — All `src/` code uses `.ts`/`.tsx`; `open-sse/` uses `.ts`/`.js`; document with TSDoc (`@param`, `@returns`, `@throws`)
-- **No `eval()`** — ESLint enforces `no-eval`, `no-implied-eval`, `no-new-func`
-- **Zod validation** — Use Zod v4 schemas for all API input validation
-- **Naming**: Files = camelCase/kebab-case, components = PascalCase, constants = UPPER_SNAKE
-
----
-
-## Project Structure
-
-```
-src/                        # TypeScript (.ts / .tsx)
-├── app/                    # Next.js 16 App Router
-│   ├── (dashboard)/        # Dashboard pages (23 sections)
-│   ├── api/                # API routes (51 directories)
-│   └── login/              # Auth pages (.tsx)
-├── domain/                 # Policy engine (policyEngine, comboResolver, costRules, etc.)
-├── lib/                    # Core business logic (.ts)
-│   ├── a2a/                # Agent-to-Agent v0.3 protocol server
-│   ├── acp/                # Agent Communication Protocol registry
-│   ├── compliance/         # Compliance policy engine
-│   ├── db/                 # SQLite database layer (110 top-level modules + 130 migrations)
-│   ├── memory/             # Persistent conversational memory
-│   ├── oauth/              # OAuth providers, services, and utilities
-│   ├── skills/             # Extensible skill framework
-│   ├── usage/              # Usage tracking and cost calculation
-│   └── localDb.ts          # Re-export layer only — never add logic here
-├── middleware/              # Request middleware (promptInjectionGuard)
-├── mitm/                   # MITM proxy (cert, DNS, target routing)
-├── shared/
-│   ├── components/         # React components (.tsx)
-│   ├── constants/          # Provider definitions (329), MCP scopes, routing strategies
-│   ├── utils/              # Circuit breaker, sanitizer, auth helpers
-│   └── validation/         # Zod v4 schemas
-└── sse/                    # SSE proxy pipeline
-
-open-sse/                   # @omniroute/open-sse workspace
-├── executors/              # 89 executor implementation modules
-├── handlers/               # 11 request handlers (chat, responses, embeddings, images, etc.)
-├── mcp-server/             # MCP server (107 tools, 3 transports, 32 scopes)
-├── services/               # 178 top-level services (combo, autoCombo, rateLimitManager, etc.)
-├── translator/             # Format translators (OpenAI ↔ Claude ↔ Gemini ↔ Responses ↔ Ollama)
-├── transformer/            # Responses API transformer
-└── utils/                  # 22 utility modules (stream, TLS, proxy, logging)
-
-electron/                   # Electron desktop app (cross-platform)
-
-tests/
-├── unit/                   # Node.js test runner (122 test files)
-├── integration/            # Integration tests
-├── e2e/                    # Playwright tests
-├── security/               # Security tests
-├── translator/             # Translator-specific tests
-└── load/                   # Load tests
-
-docs/                       # Documentation
-├── ARCHITECTURE.md         # System architecture
-├── API_REFERENCE.md        # All endpoints
-├── USER_GUIDE.md           # Provider setup, CLI integration
-├── TROUBLESHOOTING.md      # Common issues
-├── MCP-SERVER.md           # MCP server (107 tools)
-├── A2A-SERVER.md           # A2A agent protocol
-├── AUTO-COMBO.md           # Auto-combo engine
-├── CLI-TOOLS.md            # CLI tools integration
-├── COVERAGE_PLAN.md        # Test coverage improvement plan
-├── openapi.yaml            # OpenAPI specification
-└── adr/                    # Architecture Decision Records
-```
-
----
-
-## Adding a New Provider
-
-### Step 1: Register Provider Constants
-
-Add to `src/shared/constants/providers.ts` — Zod-validated at module load.
-
-### Step 2: Add Executor (if custom logic needed)
-
-Create executor in `open-sse/executors/your-provider.ts` extending the base executor.
-
-### Step 3: Add Translator (if non-OpenAI format)
-
-Create request/response translators in `open-sse/translator/`.
-
-### Step 4: Add OAuth Config (if OAuth-based)
-
-Add OAuth credentials in `src/lib/oauth/constants/oauth.ts` and service in `src/lib/oauth/services/`.
-
-### Step 5: Register Models
-
-Add model definitions in `open-sse/config/providerRegistry.ts`.
-
-### Step 6: Add Tests
-
-Write unit tests in `tests/unit/` covering at minimum:
-
-- Provider registration
-- Request/response translation
-- Error handling
-
----
-
-## Pull Request Checklist
-
-- [ ] Tests pass (`npm test`)
-- [ ] Linting passes (`npm run lint`)
-- [ ] Build succeeds (`npm run build`)
-- [ ] TypeScript types added for new public functions and interfaces
-- [ ] No hardcoded secrets or fallback values
-- [ ] All inputs validated with Zod schemas
-- [ ] CHANGELOG updated (if user-facing change)
-- [ ] Documentation updated (if applicable)
-
----
-
-## Releasing
-
-Releases are managed via the `/generate-release` workflow. When a new GitHub Release is created, the package is **automatically published to npm** via GitHub Actions.
-
----
-
-## Getting Help
-
-- **Architecture**: See [`docs/architecture/ARCHITECTURE.md`](docs/architecture/ARCHITECTURE.md)
-- **API Reference**: See [`docs/reference/API_REFERENCE.md`](docs/reference/API_REFERENCE.md)
-- **Issues**: [github.com/diegosouzapw/OmniRoute/issues](https://github.com/diegosouzapw/OmniRoute/issues)
-- **ADRs**: See `docs/adr/` for architectural decision records
diff --git a/docs/i18n/in/GEMINI.md b/docs/i18n/in/GEMINI.md
deleted file mode 100644
index 67b8eec3e4..0000000000
--- a/docs/i18n/in/GEMINI.md
+++ /dev/null
@@ -1,19 +0,0 @@
-# Security and Cleanliness Rules for AI Assistants (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../GEMINI.md) · 🇪🇸 [es](../es/GEMINI.md) · 🇫🇷 [fr](../fr/GEMINI.md) · 🇩🇪 [de](../de/GEMINI.md) · 🇮🇹 [it](../it/GEMINI.md) · 🇷🇺 [ru](../ru/GEMINI.md) · 🇨🇳 [zh-CN](../zh-CN/GEMINI.md) · 🇯🇵 [ja](../ja/GEMINI.md) · 🇰🇷 [ko](../ko/GEMINI.md) · 🇸🇦 [ar](../ar/GEMINI.md) · 🇮🇳 [hi](../hi/GEMINI.md) · 🇮🇳 [in](../in/GEMINI.md) · 🇹🇭 [th](../th/GEMINI.md) · 🇻🇳 [vi](../vi/GEMINI.md) · 🇮🇩 [id](../id/GEMINI.md) · 🇲🇾 [ms](../ms/GEMINI.md) · 🇳🇱 [nl](../nl/GEMINI.md) · 🇵🇱 [pl](../pl/GEMINI.md) · 🇸🇪 [sv](../sv/GEMINI.md) · 🇳🇴 [no](../no/GEMINI.md) · 🇩🇰 [da](../da/GEMINI.md) · 🇫🇮 [fi](../fi/GEMINI.md) · 🇵🇹 [pt](../pt/GEMINI.md) · 🇷🇴 [ro](../ro/GEMINI.md) · 🇭🇺 [hu](../hu/GEMINI.md) · 🇧🇬 [bg](../bg/GEMINI.md) · 🇸🇰 [sk](../sk/GEMINI.md) · 🇺🇦 [uk-UA](../uk-UA/GEMINI.md) · 🇮🇱 [he](../he/GEMINI.md) · 🇵🇭 [phi](../phi/GEMINI.md) · 🇧🇷 [pt-BR](../pt-BR/GEMINI.md) · 🇨🇿 [cs](../cs/GEMINI.md) · 🇹🇷 [tr](../tr/GEMINI.md)
-
----
-
-## 1. File Placement & Organization
-
-- **Test Files**: ALL unit tests, integration tests, ecosystem tests, or Vitest files MUST strictly be placed within the `tests/` directory (e.g., `tests/unit/`, `tests/integration/`). NEVER create test files in the project root (`/`).
-- **Scripts and Utilities**: ALL maintenance, debugging, generation, or experimental scripts (`.cjs`, `.mjs`, `.js`, `.ts`) MUST be placed strictly inside the `scripts/` directory or `scripts/scratch/` for temporary one-offs. NEVER dump loose scripts in the project root (`/`).
-
-**The Project Root MUST ONLY CONTAIN:**
-
-- Configuration files (`vitest.config.ts`, `next.config.mjs`, `eslint.config.mjs`, etc.)
-- Dependency files (`package.json`, `package-lock.json`)
-- Documentation files (`README.md`, `CHANGELOG.md`, `AGENTS.md`)
-- CI/CD files and ignore definitions (`.gitignore`, `.dockerignore`)
-
-When creating _any_ validation tests or one-off logic scripts, default to using `scripts/scratch/` or the `tests/unit/` directories according to your goals. Do not pollute the `/` root context.
diff --git a/docs/i18n/in/README.md b/docs/i18n/in/README.md
deleted file mode 100644
index 4adff969bd..0000000000
--- a/docs/i18n/in/README.md
+++ /dev/null
@@ -1,2195 +0,0 @@
-# 🚀 OmniRoute — The Free AI Gateway (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../README.md) · 🇪🇸 [es](../es/README.md) · 🇫🇷 [fr](../fr/README.md) · 🇩🇪 [de](../de/README.md) · 🇮🇹 [it](../it/README.md) · 🇷🇺 [ru](../ru/README.md) · 🇨🇳 [zh-CN](../zh-CN/README.md) · 🇯🇵 [ja](../ja/README.md) · 🇰🇷 [ko](../ko/README.md) · 🇸🇦 [ar](../ar/README.md) · 🇮🇳 [hi](../hi/README.md) · 🇮🇳 [in](../in/README.md) · 🇹🇭 [th](../th/README.md) · 🇻🇳 [vi](../vi/README.md) · 🇮🇩 [id](../id/README.md) · 🇲🇾 [ms](../ms/README.md) · 🇳🇱 [nl](../nl/README.md) · 🇵🇱 [pl](../pl/README.md) · 🇸🇪 [sv](../sv/README.md) · 🇳🇴 [no](../no/README.md) · 🇩🇰 [da](../da/README.md) · 🇫🇮 [fi](../fi/README.md) · 🇵🇹 [pt](../pt/README.md) · 🇷🇴 [ro](../ro/README.md) · 🇭🇺 [hu](../hu/README.md) · 🇧🇬 [bg](../bg/README.md) · 🇸🇰 [sk](../sk/README.md) · 🇺🇦 [uk-UA](../uk-UA/README.md) · 🇮🇱 [he](../he/README.md) · 🇵🇭 [phi](../phi/README.md) · 🇧🇷 [pt-BR](../pt-BR/README.md) · 🇨🇿 [cs](../cs/README.md) · 🇹🇷 [tr](../tr/README.md)
-
----
-
-### Keep coding through provider limits. Smart routing to free-access and low-cost AI models with automatic fallback.
-
-_Your universal API proxy — one endpoint, 329 provider catalog entries, resilient fallback subject to upstream availability. Includes **MCP Server (107 tools, 32 scopes)**, **A2A Protocol**, **Memory/Skills Systems** & **Electron Desktop App**._
-
-**Chat Completions • Embeddings • Image Generation • Video • Music • Audio • Reranking • **Web Search** • MCP Server • A2A Protocol • 100% TypeScript**
-
----
-
-<div align="center">
-
-[![npm version](https://img.shields.io/npm/v/omniroute?color=cb3837&logo=npm)](https://www.npmjs.com/package/omniroute)
-[![Docker Hub](https://img.shields.io/docker/v/diegosouzapw/omniroute?label=Docker%20Hub&logo=docker&color=2496ED)](https://hub.docker.com/r/diegosouzapw/omniroute)
-
-![NPM Downloads](https://img.shields.io/npm/dw/omniroute?label=npm%20down%20week&color=red)
-![NPM Downloads](https://img.shields.io/npm/dm/omniroute?label=npm%20down%20month&color=red)
-
-![NPM Downloads](https://img.shields.io/npm/d18m/omniroute?label=npm%20down%20year&color=red)
-![Docker Pulls](https://img.shields.io/docker/pulls/diegosouzapw/omniroute)
-![GitHub Downloads (all assets, all releases)](https://img.shields.io/github/downloads/diegosouzapw/omniroute/total?style=flat&label=eletron%20donwloads&color=blue)
-
-[![stars](https://custom-icon-badges.demolab.com/github/stars/diegosouzapw/OmniRoute?logo=star&style=flat)](https://github.com/diegosouzapw/OmniRoute/stargazers)
-[![open issues](https://custom-icon-badges.demolab.com/github/issues-raw/diegosouzapw/OmniRoute?logo=issue)](https://github.com/diegosouzapw/OmniRoute/issues)
-[![license](https://custom-icon-badges.demolab.com/github/license/diegosouzapw/OmniRoute?logo=law)](https://github.com/diegosouzapw/OmniRoute/blob/main/LICENSE)
-[![last commit](https://custom-icon-badges.demolab.com/github/last-commit/diegosouzapw/OmniRoute?logo=history&logoColor=white)](https://github.com/diegosouzapw/OmniRoute/commits/main)
-[![total contributions](https://custom-icon-badges.demolab.com/badge/dynamic/json?logo=graph&logoColor=fff&color=blue&label=total%20contributions&query=%24.totalContributions&url=https%3A%2F%2Fstreak-stats.demolab.com%2F%3Fuser%3Ddiegosouzapw%26type%3Djson)](https://github.com/diegosouzapw)
-[![code size](https://custom-icon-badges.demolab.com/github/languages/code-size/diegosouzapw/OmniRoute?logo=file-code&logoColor=white)](https://github.com/diegosouzapw/OmniRoute)
-[![pr closed](https://custom-icon-badges.demolab.com/github/issues-pr-closed/diegosouzapw/OmniRoute?color=purple&logo=git-pull-request&logoColor=white)](https://github.com/diegosouzapw/OmniRoute/pulls?q=is%3Apr+is%3Aclosed)
-[![tag](https://custom-icon-badges.demolab.com/github/v/tag/diegosouzapw/OmniRoute?logo=tag&logoColor=white)](https://github.com/diegosouzapw/OmniRoute/tags)
-[![github streak](https://custom-icon-badges.demolab.com/badge/dynamic/json?logo=fire&logoColor=fff&color=orange&label=github%20streak&query=%24.currentStreak.length&suffix=%20days&url=https%3A%2F%2Fstreak-stats.demolab.com%2F%3Fuser%3Ddiegosouzapw%26type%3Djson)](https://github.com/diegosouzapw)
-[![followers](https://custom-icon-badges.demolab.com/github/followers/diegosouzapw?logo=person-add)](https://github.com/diegosouzapw?tab=followers)
-[![fork](https://custom-icon-badges.demolab.com/github/forks/diegosouzapw/OmniRoute?logo=fork)](https://github.com/diegosouzapw/OmniRoute/network/members)
-[![watch](https://custom-icon-badges.demolab.com/github/watchers/diegosouzapw/OmniRoute?logo=eye)](https://github.com/diegosouzapw/OmniRoute/watchers)
-
-[![License](https://img.shields.io/github/license/diegosouzapw/OmniRoute)](https://github.com/diegosouzapw/OmniRoute/blob/main/LICENSE)
-[![Website](https://img.shields.io/badge/Website-omniroute.online-blue?logo=google-chrome&logoColor=white)](https://omniroute.online)
-[![WhatsApp](https://img.shields.io/badge/WhatsApp-Community-25D366?logo=whatsapp&logoColor=white)](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t)
-
-[🌐 Website](https://omniroute.online) • [🚀 Quick Start](#-quick-start) • [💡 Features](#-key-features) • [📖 Docs](#-documentation) • [💰 Pricing](#-pricing-at-a-glance) • [💬 WhatsApp](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t)
-
-</div>
-
-🌐 **Available in:** 🇺🇸 [English](README.md) | 🇧🇷 [Português (Brasil)](docs/i18n/pt-BR/README.md) | 🇪🇸 [Español](docs/i18n/es/README.md) | 🇫🇷 [Français](docs/i18n/fr/README.md) | 🇮🇹 [Italiano](docs/i18n/it/README.md) | 🇷🇺 [Русский](docs/i18n/ru/README.md) | 🇨🇳 [中文 (简体)](docs/i18n/zh-CN/README.md) | 🇩🇪 [Deutsch](docs/i18n/de/README.md) | 🇮🇳 [हिन्दी](docs/i18n/in/README.md) | 🇹🇭 [ไทย](docs/i18n/th/README.md) | 🇺🇦 [Українська](docs/i18n/uk-UA/README.md) | 🇸🇦 [العربية](docs/i18n/ar/README.md) | 🇯🇵 [日本語](docs/i18n/ja/README.md) | 🇻🇳 [Tiếng Việt](docs/i18n/vi/README.md) | 🇧🇬 [Български](docs/i18n/bg/README.md) | 🇩🇰 [Dansk](docs/i18n/da/README.md) | 🇫🇮 [Suomi](docs/i18n/fi/README.md) | 🇮🇱 [עברית](docs/i18n/he/README.md) | 🇭🇺 [Magyar](docs/i18n/hu/README.md) | 🇮🇩 [Bahasa Indonesia](docs/i18n/id/README.md) | 🇰🇷 [한국어](docs/i18n/ko/README.md) | 🇲🇾 [Bahasa Melayu](docs/i18n/ms/README.md) | 🇳🇱 [Nederlands](docs/i18n/nl/README.md) | 🇳🇴 [Norsk](docs/i18n/no/README.md) | 🇵🇹 [Português (Portugal)](docs/i18n/pt/README.md) | 🇷🇴 [Română](docs/i18n/ro/README.md) | 🇵🇱 [Polski](docs/i18n/pl/README.md) | 🇸🇰 [Slovenčina](docs/i18n/sk/README.md) | 🇸🇪 [Svenska](docs/i18n/sv/README.md) | 🇵🇭 [Filipino](docs/i18n/phi/README.md) | 🇨🇿 [Čeština](docs/i18n/cs/README.md)
-
----
-
-## 🖼️ Main Dashboard
-
-<div align="center">
-  <img src="./docs/screenshots/MainOmniRoute.png" alt="OmniRoute Dashboard" width="800"/>
-</div>
-
----
-
-## 📸 Dashboard Preview
-
-<details>
-<summary><b>Click to see dashboard screenshots</b></summary>
-
-| Page           | Screenshot                                        |
-| -------------- | ------------------------------------------------- |
-| **Providers**  | ![Providers](docs/screenshots/01-providers.png)   |
-| **Combos**     | ![Combos](docs/screenshots/02-combos.png)         |
-| **Analytics**  | ![Analytics](docs/screenshots/03-analytics.png)   |
-| **Health**     | ![Health](docs/screenshots/04-health.png)         |
-| **Translator** | ![Translator](docs/screenshots/05-translator.png) |
-| **Settings**   | ![Settings](docs/screenshots/06-settings.png)     |
-| **CLI Tools**  | ![CLI Tools](docs/screenshots/07-cli-tools.png)   |
-| **Usage Logs** | ![Usage](docs/screenshots/08-usage.png)           |
-| **Endpoints**  | ![Endpoints](docs/screenshots/09-endpoint.png)    |
-
-</details>
-
----
-
-### 🤖 Free AI Provider for your favorite coding agents
-
-_Connect any AI-powered IDE or CLI tool through OmniRoute — free-access AI gateway; provider limits and terms apply._
-
-  <table>
-    <tr>
-      <td align="center" width="110">
-        <a href="https://github.com/openclaw/openclaw">
-          <img src="./public/providers/openclaw.png" alt="OpenClaw" width="48"/><br/>
-          <b>OpenClaw</b>
-        </a><br/>
-        <sub>⭐ 205K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/HKUDS/nanobot">
-          <img src="../../../public/providers/cli-generic.svg" alt="NanoBot" width="48"/><br/>
-          <b>NanoBot</b>
-        </a><br/>
-        <sub>⭐ 20.9K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/sipeed/picoclaw">
-          <img src="./public/providers/picoclaw.svg" alt="PicoClaw" width="48"/><br/>
-          <b>PicoClaw</b>
-        </a><br/>
-        <sub>⭐ 14.6K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/zeroclaw-labs/zeroclaw">
-          <img src="../../../public/providers/cli-generic.svg" alt="ZeroClaw" width="48"/><br/>
-          <b>ZeroClaw</b>
-        </a><br/>
-        <sub>⭐ 9.9K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/nearai/ironclaw">
-          <img src="../../../public/providers/cli-generic.svg" alt="IronClaw" width="48"/><br/>
-          <b>IronClaw</b>
-        </a><br/>
-        <sub>⭐ 2.1K</sub>
-      </td>
-    </tr>
-    <tr>
-      <td align="center" width="110">
-        <a href="https://github.com/anomalyco/opencode">
-          <img src="../../../public/providers/cli-generic.svg" alt="OpenCode" width="48"/><br/>
-          <b>OpenCode</b>
-        </a><br/>
-        <sub>⭐ 106K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/openai/codex">
-          <img src="./public/providers/codex.svg" alt="Codex CLI" width="48"/><br/>
-          <b>Codex CLI</b>
-        </a><br/>
-        <sub>⭐ 60.8K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/anthropics/claude-code">
-          <img src="./public/providers/claude.svg" alt="Claude Code" width="48"/><br/>
-          <b>Claude Code</b>
-        </a><br/>
-        <sub>⭐ 67.3K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/Kilo-Org/kilocode">
-          <img src="../../../public/providers/cli-generic.svg" alt="Kilo Code" width="48"/><br/>
-          <b>Kilo Code</b>
-        </a><br/>
-        <sub>⭐ 15.5K</sub>
-      </td>
-    </tr>
-  </table>
-
-<sub>📡 All agents connect via <code>http://localhost:20128/v1</code> or <code>http://cloud.omniroute.online/v1</code> — one config; model access and quotas depend on providers</sub>
-
----
-
-## 🤔 Why OmniRoute?
-
-**Stop wasting money and hitting limits:**
-
-- <img src="https://img.shields.io/badge/✗-e74c3c?style=flat-square" height="16"/> Subscription quota expires unused every month
-- <img src="https://img.shields.io/badge/✗-e74c3c?style=flat-square" height="16"/> Rate limits stop you mid-coding
-- <img src="https://img.shields.io/badge/✗-e74c3c?style=flat-square" height="16"/> Expensive APIs ($20-50/month per provider)
-- <img src="https://img.shields.io/badge/✗-e74c3c?style=flat-square" height="16"/> Manual switching between providers
-
-**OmniRoute solves this:**
-
-- ✅ **Maximize subscriptions** - Track quota, use every bit before reset
-- ✅ **Auto fallback** - Subscription → API Key → Cheap → Free; availability depends on eligible upstream routes
-- ✅ **Multi-account** - Round-robin between accounts per provider
-
----
-
-## 📧 Support
-
-> 💬 **Join our community!** [WhatsApp Group](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t) — Get help, share tips, and stay updated.
-
-- **Website**: [omniroute.online](https://omniroute.online)
-- **GitHub**: [github.com/diegosouzapw/OmniRoute](https://github.com/diegosouzapw/OmniRoute)
-- **Issues**: [github.com/diegosouzapw/OmniRoute/issues](https://github.com/diegosouzapw/OmniRoute/issues)
-- **WhatsApp**: [Community Group](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t)
-- **Contributing**: See [CONTRIBUTING.md](CONTRIBUTING.md), open a PR, or pick a `good first issue`
-
-### 🐛 Reporting a Bug?
-
-When opening an issue, please run the system-info command and attach the generated file:
-
-```bash
-npm run system-info
-```
-
-This generates a `system-info.txt` with your Node.js version, OmniRoute version, OS details, installed CLI tools (qoder, gemini, claude, codex, antigravity, droid, etc.), Docker/PM2 status, and system packages — everything we need to reproduce your issue quickly. Attach the file directly to your GitHub issue.
-
----
-
-## 🔄 How It Works
-
-```
-┌─────────────┐
-│  Your CLI   │  (Claude Code, Codex, OpenClaw, Cursor, Cline...)
-│   Tool      │
-└──────┬──────┘
-       │ http://localhost:20128/v1
-       ↓
-┌─────────────────────────────────────────┐
-│           OmniRoute (Smart Router)        │
-│  • Format translation (OpenAI ↔ Claude) │
-│  • Quota tracking + Embeddings + Images │
-│  • Auto token refresh                   │
-└──────┬──────────────────────────────────┘
-       │
-       ├─→ [Tier 1: SUBSCRIPTION] Claude Code, Codex
-       │   ↓ quota exhausted
-       ├─→ [Tier 2: API KEY] DeepSeek, Groq, xAI, Mistral, NVIDIA NIM, etc.
-       │   ↓ budget limit
-       ├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
-       │   ↓ budget limit
-       └─→ [Tier 4: FREE] Qoder, Kiro (provider limits apply)
-
-Result: broader fallback coverage and cost control; availability is not guaranteed
-```
-
----
-
-## 🎯 What OmniRoute Solves — 30 Real Pain Points & Use Cases
-
-> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to protocol operations and enterprise observability.
-
-<details>
-<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
-
-Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
-
-**How OmniRoute solves it:**
-
-- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
-- **Provider Limits Tracking** — Cached quota snapshots refresh on a server-side schedule (default `PROVIDER_LIMITS_SYNC_INTERVAL_MINUTES=70`) with manual refresh available in the UI
-- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
-- **Custom Combos** — Customizable fallback chains with 13 balancing strategies (priority, weighted, fill-first, round-robin, P2C, random, least-used, cost-optimized, strict-random, auto, lkgp, context-optimized, **context-relay**)
-- **Structured Combo Builder** — Build combos step-by-step with explicit provider + model + account selection, including repeated providers and fixed-account targets
-- **Quota-Aware P2C** — Power-of-two account selection now factors quota headroom, backoff, recent errors, and consecutive use
-- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
-
-</details>
-
-<details>
-<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
-
-OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
-
-**How OmniRoute solves it:**
-
-- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 329 provider catalog entries
-- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
-- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
-- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
-- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
-- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
-- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
-
-</details>
-
-<details>
-<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
-
-Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
-
-**How OmniRoute solves it:**
-
-- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
-- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
-- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
-- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
-- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
-- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
-- **🔏 CLI Fingerprint Matching** — Reorders headers and body fields to match native CLI binary signatures, drastically reducing account flagging risk. The proxy IP is preserved — you get both stealth **and** IP masking simultaneously
-
-</details>
-
-<details>
-<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
-
-Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
-
-**How OmniRoute solves it:**
-
-- **Ollama Cloud** — Cloud-hosted Ollama models at `api.ollama.com` with free "Light usage" tier; use `ollamacloud/<model>` prefix
-- **Free-Only Combos** — Chain `if/kimi-k2-thinking → kr/qwen3-coder-next` can use currently listed $0 access; limits and availability apply
-- **NVIDIA NIM Free Access** — ~40 RPM free access as currently listed; provider terms and model availability apply at build.nvidia.com (transitioning from credits to pure rate limits)
-- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
-
-</details>
-
-<details>
-<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
-
-When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
-
-**How OmniRoute solves it:**
-
-- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
-- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
-- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
-- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
-- **Rate Limiter** — Per-IP rate limiting with configurable windows
-- **IP Filtering** — Allowlist/blocklist for access control
-- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
-- **AES-256-GCM Encryption** — Credentials encrypted at rest
-
-</details>
-
-<details>
-<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
-
-AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
-
-**How OmniRoute solves it:**
-
-- **Settings-Driven Lock Hierarchy** — Provider profiles control default account/model lockouts, global model quarantine, and provider circuit breakers from one control surface, while explicit upstream `Retry-After` windows still take priority
-- **Exponential Backoff** — Progressive retry delays for both account/model lockouts and higher-level quarantine
-- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
-- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
-- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
-- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
-
-</details>
-
-<details>
-<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
-
-**How OmniRoute solves it:**
-
-- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
-- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
-- **Onboarding Wizard** — Guided 4-step setup for first-time users
-- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 329 provider catalog entries
-
-</details>
-
-<details>
-<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
-
-Claude Code, Codex, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
-
-**How OmniRoute solves it:**
-
-- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
-- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Copilot, Kiro, Qoder
-- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
-- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
-- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
-- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
-
-</details>
-
-<details>
-<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
-
-Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
-
-**How OmniRoute solves it:**
-
-- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
-- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
-- **Per-Model Pricing Configuration** — Configurable prices per model
-- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
-- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
-
-</details>
-
-<details>
-<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
-
-When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
-
-**How OmniRoute solves it:**
-
-- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
-- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
-- **SQLite Summary Logs** — Request and proxy log indexes stay queryable across restarts without loading large payload blobs into SQLite
-- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
-- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
-- **File-Based Detail Artifacts** — App logs rotate by size, retention days, and archive count; detailed request/response payloads live in `DATA_DIR/call_logs/` and rotate independently of SQLite summaries
-- **System Info Report** — `npm run system-info` generates `system-info.txt` with your full environment (Node version, OmniRoute version, OS, CLI tools, Docker/PM2 status). Attach it when reporting issues for instant triage.
-
-</details>
-
-<details>
-<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
-
-Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
-
-**How OmniRoute solves it:**
-
-- **npm global install** — `npm install -g omniroute && omniroute` — done
-- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
-- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
-- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
-- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
-- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
-- **DB Backups** — Automatic backup, restore, export and import of all settings, with `DISABLE_SQLITE_AUTO_BACKUP` for externally managed backups
-
-</details>
-
-<details>
-<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
-
-Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
-
-**How OmniRoute solves it:**
-
-- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
-- **RTL Support** — Right-to-left support for Arabic and Hebrew
-- **Multi-Language READMEs** — 30 complete documentation translations
-- **Language Selector** — Globe icon in header for real-time switching
-
-</details>
-
-<details>
-<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
-
-AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
-
-**How OmniRoute solves it:**
-
-- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
-- **Image Generation** — `/v1/images/generations` with 10 providers and 20+ models (OpenAI, xAI, Together, Fireworks, Nebius, Hyperbolic, NanoBanana, Antigravity, SD WebUI, ComfyUI)
-- **Text-to-Video** — `/v1/videos/generations` — ComfyUI (AnimateDiff, SVD) and SD WebUI
-- **Text-to-Music** — `/v1/music/generations` — ComfyUI (Stable Audio Open, MusicGen)
-- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper + Nvidia NIM, HuggingFace, Qwen3
-- **Text-to-Speech** — `/v1/audio/speech` — ElevenLabs, Nvidia NIM, HuggingFace, Coqui, Tortoise, Qwen3, **Inworld**, **Cartesia**, **PlayHT**, + existing providers
-- **Moderations** — `/v1/moderations` — Content safety checks
-- **Reranking** — `/v1/rerank` — Document relevance reranking
-- **Responses API** — Full `/v1/responses` support for Codex
-
-</details>
-
-<details>
-<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
-
-Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
-
-**How OmniRoute solves it:**
-
-- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
-- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
-- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
-- **Chat Tester** — Full round-trip with visual response rendering
-- **Live Monitor** — Real-time stream of all requests flowing through the proxy
-
-</details>
-
-<details>
-<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
-
-As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
-
-**How OmniRoute solves it:**
-
-- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
-- **Request Idempotency** — 5s deduplication window for identical requests
-- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
-- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
-- **API Key Validation Cache** — 3-tier cache for production performance
-- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
-
-</details>
-
-<details>
-<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
-
-Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
-
-**How OmniRoute solves it:**
-
-- **System Prompt Injection** — Global prompt applied to all requests
-- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
-- **9 Routing Strategies** — Global strategies that determine how requests are distributed
-- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
-- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
-- **Manual Combo Ordering** — Drag combo cards by handle and persist the order in SQLite
-- **Provider Toggle** — Enable/disable all connections for a provider with one click
-- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
-
-</details>
-
-<details>
-<summary><b>🧰 17. "I need MCP tools as first-class product capabilities"</b></summary>
-
-Many AI gateways expose MCP only as a hidden implementation detail. Teams need a visible, manageable operation layer.
-
-**How OmniRoute solves it:**
-
-- MCP appears in the dashboard navigation and endpoint protocol tab
-- Dedicated MCP management page with process, tools, scopes, and audit
-- Built-in quick-start for `omniroute --mcp` and client onboarding
-
-</details>
-
-<details>
-<summary><b>🧠 18. "I need A2A orchestration with sync + stream task paths"</b></summary>
-
-Agent workflows need both direct replies and long-running streamed execution with lifecycle control.
-
-**How OmniRoute solves it:**
-
-- A2A JSON-RPC endpoint (`POST /a2a`) with `message/send` and `message/stream`
-- SSE streaming with terminal state propagation
-- Task lifecycle APIs for `tasks/get` and `tasks/cancel`
-
-</details>
-
-<details>
-<summary><b>🛰️ 19. "I need real MCP process health, not guessed status"</b></summary>
-
-Operational teams need to know if MCP is actually alive, not just whether an API is reachable.
-
-**How OmniRoute solves it:**
-
-- Runtime heartbeat file with PID, timestamps, transport, tool count, and scope mode
-- MCP status API combining heartbeat + recent activity
-- UI status cards for process/uptime/heartbeat freshness
-
-</details>
-
-<details>
-<summary><b>📋 20. "I need auditable MCP tool execution"</b></summary>
-
-When tools mutate config or trigger ops actions, teams need forensic traceability.
-
-**How OmniRoute solves it:**
-
-- SQLite-backed audit logging for MCP tool calls
-- Filters by tool, success/failure, API key, and pagination
-- Dashboard audit table + stats endpoints for automation
-
-</details>
-
-<details>
-<summary><b>🔐 21. "I need scoped MCP permissions per integration"</b></summary>
-
-Different clients should have least-privilege access to tool categories.
-
-**How OmniRoute solves it:**
-
-- 32 granular MCP scopes for controlled tool access
-- Scope enforcement and visibility in MCP management UI
-- Safe default posture for operational tooling
-
-</details>
-
-<details>
-<summary><b>⚙️ 22. "I need operational controls without redeploying"</b></summary>
-
-Teams need quick runtime changes during incidents or cost events.
-
-**How OmniRoute solves it:**
-
-- Switch combo activation directly from MCP dashboard
-- Apply resilience profiles from pre-defined policy packs
-- Reset circuit breaker state from the same operations panel
-
-</details>
-
-<details>
-<summary><b>🔄 23. "I need live A2A task lifecycle visibility and cancellation"</b></summary>
-
-Without lifecycle visibility, task incidents become hard to triage.
-
-**How OmniRoute solves it:**
-
-- Task listing/filtering by state/skill with pagination
-- Drill-down on task metadata, events, and artifacts
-- Task cancellation endpoint and UI action with confirmation
-
-</details>
-
-<details>
-<summary><b>🌊 24. "I need active stream metrics for A2A load"</b></summary>
-
-Streaming workflows require operational insight into concurrency and live connections.
-
-**How OmniRoute solves it:**
-
-- Active stream counters integrated into A2A status
-- Last task timestamp and per-state counts
-- A2A dashboard cards for real-time ops monitoring
-
-</details>
-
-<details>
-<summary><b>🪪 25. "I need standard agent discovery for clients"</b></summary>
-
-External clients and orchestrators need machine-readable metadata for onboarding.
-
-**How OmniRoute solves it:**
-
-- Agent Card exposed at `/.well-known/agent.json`
-- Capabilities and skills shown in management UI
-- A2A status API includes discovery metadata for automation
-
-</details>
-
-<details>
-<summary><b>🧭 26. "I need protocol discoverability in the product UX"</b></summary>
-
-If users cannot discover protocol surfaces, adoption and support quality drop.
-
-**How OmniRoute solves it:**
-
-- Consolidated **Endpoints** page with tabs for Proxy, MCP, A2A, and API Endpoints
-- Inline service status toggles (Online/Offline) for MCP and A2A
-- Links from overview to dedicated management tabs
-
-</details>
-
-<details>
-<summary><b>🧪 27. "I need end-to-end protocol validation with real clients"</b></summary>
-
-Mock tests are not enough to validate protocol compatibility before release.
-
-**How OmniRoute solves it:**
-
-- E2E suite that boots app and uses real MCP SDK client transport
-- A2A client tests for discovery, send, stream, get, and cancel flows
-- Cross-check assertions against MCP audit and A2A tasks APIs
-
-</details>
-
-<details>
-<summary><b>📡 28. "I need unified observability across all interfaces"</b></summary>
-
-Splitting observability by protocol creates blind spots and longer MTTR.
-
-**How OmniRoute solves it:**
-
-- Unified dashboards/logs/analytics in one product
-- Health + audit + request telemetry across OpenAI, MCP, and A2A layers
-- Operational APIs for status and automation
-
-</details>
-
-<details>
-<summary><b>💼 29. "I need one runtime for proxy + tools + agent orchestration"</b></summary>
-
-Running many separate services increases operational cost and failure modes.
-
-**How OmniRoute solves it:**
-
-- OpenAI-compatible proxy, MCP server, and A2A server in one stack
-- Shared auth, resilience, data store, and observability
-- Consistent policy model across all interaction surfaces
-
-</details>
-
-<details>
-<summary><b>🚀 30. "I need to ship agentic workflows without glue-code sprawl"</b></summary>
-
-Teams lose velocity when stitching multiple ad-hoc services and scripts.
-
-**How OmniRoute solves it:**
-
-- Unified endpoint strategy for clients and agents
-- Built-in protocol management UIs and smoke validation paths
-- Production-ready foundations (security, logging, resilience, backup)
-
-</details>
-
-<details>
-<summary><b>📚 31. "My long sessions crash with 'context_length_exceeded' limits"</b></summary>
-
-During deep debugging, long histories with tool results quickly exceed provider token windows, causing failed requests and orphaned context.
-
-**How OmniRoute solves it:**
-
-- **Proactive Context Compression** — Evaluates token budgets before the request hits upstream and proactively prunes old conversation history with a smart binary-search mechanism.
-- **Structural Integrity Guards** — Automatically tracks explicit `tool_use` definitions and ensures that if a tool input is truncated, its corresponding `tool_result` is also safely removed, preventing API validation errors.
-- **Multi-Layer Dropping** — Progressively drops system messages, regular messages, and finally enforces strict length limits without breaking conversational logic.
-
-</details>
-
-### Example Playbooks (Integrated Use Cases)
-
-**Playbook A: Maximize paid subscription + cheap backup**
-
-```txt
-Combo: "maximize-claude"
-  1. cc/claude-opus-4-7
-  2. glm/glm-4.7
-  3. if/kimi-k2-thinking
-
-Monthly cost: $20 + small backup spend
-Outcome: higher quality, near-zero interruption
-```
-
-**Playbook B: Zero-cost coding stack**
-
-```txt
-Combo: "free-access"
-  1. if/kimi-k2-thinking       (no published token cap; limits apply)
-  2. kr/qwen3-coder-next
-
-Monthly cost: $0
-Outcome: broader free-access fallback; upstream availability is not guaranteed
-```
-
-**Playbook C: 24/7 always-on fallback chain**
-
-```txt
-Combo: "multi-layer-fallback"
-  1. cc/claude-opus-4-7
-  2. cx/gpt-5.2-codex
-  3. glm/glm-4.7
-  4. minimax/MiniMax-M2.1
-  5. if/kimi-k2-thinking
-
-Outcome: deep fallback depth for deadline-critical workloads
-```
-
-**Playbook D: Agent ops with MCP + A2A**
-
-```txt
-1) Start MCP transport (`omniroute --mcp`) for tool-driven operations
-2) Run A2A tasks via `message/send` and `message/stream`
-3) Observe via /dashboard/endpoint (MCP and A2A tabs)
-4) Toggle services via inline status controls
-```
-
----
-
-## 🆓 Start Free — Zero Configuration Cost
-
-> Setup AI coding in minutes at **$0/month**. Connect these free accounts and use the built-in **Free Stack** combo.
-
-| Step | Action                                             | Providers Unlocked                                                                 |
-| ---- | -------------------------------------------------- | ---------------------------------------------------------------------------------- |
-| 1    | Connect **Kiro** (AWS Builder ID OAuth)            | Claude Sonnet 4.5, Haiku 4.5 — provider/account limits apply                       |
-| 2    | Connect **Qoder** (Google OAuth)                   | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1... — provider/account limits apply |
-| 3    | `/dashboard/combos` → **Free Stack ($0)** template | Round-robin all free providers automatically                       |
-
-**Point any IDE/CLI to:** `http://localhost:20128/v1` · API Key: `any-string` · Done.
-
-> **Optional extra coverage (current terms apply):** Groq, NVIDIA NIM, Cerebras, LongCat and Cloudflare Workers AI can provide free access or signup credits where currently listed. Quotas, models, accounts, regions and provider terms can change; see [`FREE_TIERS.md`](../../reference/FREE_TIERS.md).
-
-## त्वरित प्रारंभ
-
-### 1) Install and run
-
-```bash
-npm install -g omniroute
-omniroute
-```
-
-> **pnpm users:** Pass `--allow-build` at install time to enable native build scripts required by `better-sqlite3` and `@swc/core` (the `approve-builds -g` command is not supported for global installs on pnpm v11):
->
-> ```bash
-> pnpm add -g omniroute@latest --allow-build=better-sqlite3 --allow-build=@swc/core
-> omniroute
-> ```
-
-Dashboard opens at `http://localhost:20128` and API base URL is `http://localhost:20128/v1`.
-
-| Command                 | Description                                                 |
-| ----------------------- | ----------------------------------------------------------- |
-| `omniroute`             | Start server (`PORT=20128`, API and dashboard on same port) |
-| `omniroute --port 3000` | Set canonical/API port to 3000                              |
-| `omniroute --mcp`       | Start MCP server (stdio transport)                          |
-| `omniroute --no-open`   | Don't auto-open browser                                     |
-| `omniroute --help`      | Show help                                                   |
-
-Optional split-port mode:
-
-```bash
-PORT=20128 DASHBOARD_PORT=20129 omniroute
-# API:       http://localhost:20128/v1
-# Dashboard: http://localhost:20129
-```
-
-### 2) Uninstalling
-
-When you no longer need OmniRoute, we provide two quick scripts for a clean removal:
-
-| Command                  | Action                                                                              |
-| ------------------------ | ----------------------------------------------------------------------------------- |
-| `npm run uninstall`      | Removes the system app but **keeps your DB and configurations** in `~/.omniroute`.  |
-| `npm run uninstall:full` | Removes the app AND permanently **erases all configurations, keys, and databases**. |
-
-> Note: To run these commands, navigate to the OmniRoute project folder (if you cloned it) and run them. Alternatively, if globally installed, you can simply run `npm uninstall -g omniroute`.
-
-### Long-Running Streaming Timeouts
-
-For most deployments, you only need:
-
-| Variable                 | Default                       | Purpose                                                                                                                                      |
-| ------------------------ | ----------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------- |
-| `REQUEST_TIMEOUT_MS`     | `600000`                      | Shared baseline for upstream response-start timeout, hidden Undici timeouts, TLS fingerprint requests, and API bridge request/proxy timeouts |
-| `STREAM_IDLE_TIMEOUT_MS` | inherits `REQUEST_TIMEOUT_MS` | Maximum gap between streaming chunks before OmniRoute aborts the SSE stream                                                                  |
-
-Backward compatibility is preserved: existing `FETCH_TIMEOUT_MS`, `API_BRIDGE_PROXY_TIMEOUT_MS`, and other per-layer timeout vars still work and override the shared baseline.
-
-For Claude Code-compatible upstreams (`anthropic-compatible-cc-*`), OmniRoute also derives the outbound `X-Stainless-Timeout` header from the resolved fetch timeout so provider-side read timeouts stay aligned with your env configuration.
-
-For third-party Claude Code-compatible reverse proxies, OmniRoute keeps the default
-`anthropic-beta` set conservative and, when `Client Cache Control` is left on `Auto`,
-only forwards client-provided `cache_control` markers. If the request does not include
-`cache_control`, OmniRoute does not inject bridge-owned markers.
-
-Advanced overrides are available if you need finer control:
-
-| Variable                                 | Default                                    | Purpose                                                              |
-| ---------------------------------------- | ------------------------------------------ | -------------------------------------------------------------------- |
-| `FETCH_TIMEOUT_MS`                       | inherits `REQUEST_TIMEOUT_MS`              | Upstream response-start timeout used until response headers arrive   |
-| `FETCH_HEADERS_TIMEOUT_MS`               | inherits `FETCH_TIMEOUT_MS`                | Undici time limit for receiving upstream response headers            |
-| `FETCH_BODY_TIMEOUT_MS`                  | inherits `FETCH_TIMEOUT_MS`                | Undici time limit between upstream body chunks (`0` disables it)     |
-| `FETCH_CONNECT_TIMEOUT_MS`               | `30000`                                    | Undici TCP connect timeout                                           |
-| `FETCH_KEEPALIVE_TIMEOUT_MS`             | `4000`                                     | Undici idle keep-alive socket timeout                                |
-| `TLS_CLIENT_TIMEOUT_MS`                  | inherits `FETCH_TIMEOUT_MS`                | Timeout for TLS fingerprint requests made through `wreq-js`          |
-| `API_BRIDGE_PROXY_TIMEOUT_MS`            | inherits `REQUEST_TIMEOUT_MS` or `600000`  | Timeout for `/v1` proxy forwarding from API port to dashboard port   |
-| `API_BRIDGE_SERVER_REQUEST_TIMEOUT_MS`   | `max(API_BRIDGE_PROXY_TIMEOUT_MS, 300000)` | Incoming request timeout on the API bridge server                    |
-| `API_BRIDGE_SERVER_HEADERS_TIMEOUT_MS`   | `60000`                                    | Incoming header timeout on the API bridge server                     |
-| `API_BRIDGE_SERVER_KEEPALIVE_TIMEOUT_MS` | `5000`                                     | Keep-alive timeout on the API bridge server                          |
-| `API_BRIDGE_SERVER_SOCKET_TIMEOUT_MS`    | `0`                                        | Socket inactivity timeout on the API bridge server (`0` disables it) |
-
-For streaming requests, `FETCH_TIMEOUT_MS` only covers connection setup / waiting for the first upstream response. Once the stream is active, OmniRoute will only abort on an actual stall (`STREAM_IDLE_TIMEOUT_MS`) or Undici body inactivity (`FETCH_BODY_TIMEOUT_MS`).
-
-If you run OmniRoute behind Nginx, Caddy, Cloudflare, or another reverse proxy, make sure the proxy
-timeouts are also higher than your OmniRoute stream/fetch timeouts.
-
-### 2) Connect providers and create your API key
-
-1. Open Dashboard → `Providers` and connect at least one provider (OAuth or API key).
-2. Open Dashboard → `Endpoints` and create an API key.
-3. (Optional) Open Dashboard → `Combos` and set your fallback chain.
-
-### 3) Point your coding tool to OmniRoute
-
-```txt
-Base URL: http://localhost:20128/v1
-API Key:  [copy from Endpoint page]
-Model:    if/kimi-k2-thinking (or any provider/model prefix)
-```
-
-### 4) Enable and validate protocols (v2.0)
-
-**MCP (for tool-driven operations):**
-
-```bash
-omniroute --mcp
-```
-
-Then connect your MCP client over `stdio` and test tools like:
-
-- `omniroute_get_health`
-- `omniroute_list_combos`
-
-**A2A (for agent-to-agent workflows):**
-
-```bash
-curl http://localhost:20128/.well-known/agent.json
-```
-
-```bash
-curl -X POST http://localhost:20128/a2a \
-  -H 'content-type: application/json' \
-  -d '{"jsonrpc":"2.0","id":"quickstart","method":"message/send","params":{"skill":"quota-management","messages":[{"role":"user","content":"Give me a short quota summary."}]}}'
-```
-
-### 5) Validate everything end-to-end (recommended)
-
-```bash
-npm run test:protocols:e2e
-```
-
-This suite validates real MCP and A2A client flows against a running app.
-
-### Alternative: run from source
-
-```bash
-cp .env.example .env
-npm install
-PORT=20128 DASHBOARD_PORT=20129 NEXT_PUBLIC_BASE_URL=http://localhost:20129 npm run dev
-```
-
-<details>
-<summary><b>Void Linux (`xbps-src` template)</b></summary>
-
-For Void Linux users, you can build a native package using `xbps-src`. Save this block as `srcpkgs/omniroute/template`:
-
-```bash
-# Template file for 'omniroute'
-pkgname=omniroute
-version=3.4.1
-revision=1
-hostmakedepends="nodejs python3 make"
-depends="openssl"
-short_desc="Universal AI gateway with smart routing for multiple LLM providers"
-maintainer="zenobit <zenobit@disroot.org>"
-license="MIT"
-homepage="https://github.com/diegosouzapw/OmniRoute"
-distfiles="https://github.com/diegosouzapw/OmniRoute/archive/refs/tags/v${version}.tar.gz"
-checksum=009400afee90a9f32599d8fe734145cfd84098140b7287990183dde45ae2245b
-system_accounts="_omniroute"
-omniroute_homedir="/var/lib/omniroute"
-export NODE_ENV=production
-export npm_config_engine_strict=false
-export npm_config_loglevel=error
-export npm_config_fund=false
-export npm_config_audit=false
-
-do_build() {
-	# Determine target CPU arch for node-gyp
-	local _gyp_arch
-	case "$XBPS_TARGET_MACHINE" in
-		aarch64*) _gyp_arch=arm64 ;;
-		armv7*|armv6*) _gyp_arch=arm ;;
-		i686*) _gyp_arch=ia32 ;;
-		*) _gyp_arch=x64 ;;
-	esac
-
-	# 1) Install all deps – skip scripts (no network in do_build, native modules
-	#    compiled separately below; better-sqlite3 is serverExternalPackage so
-	#    Next.js does not execute it during next build)
-	NODE_ENV=development npm ci --ignore-scripts
-
-	# 2) Build the Next.js standalone bundle
-	npm run build
-
-	# 3) Copy static assets into standalone
-	cp -r .next/static .next/standalone/.next/static
-	[ -d public ] && cp -r public .next/standalone/public || true
-
-	# 4) Compile better-sqlite3 native binding for the target architecture.
-	#    Use node-gyp directly so CC/CXX from xbps-src cross-toolchain are used
-	#    without npm altering them.
-	local _node_gyp=/usr/lib/node_modules/npm/node_modules/node-gyp/bin/node-gyp.js
-	(cd node_modules/better-sqlite3 && node "$_node_gyp" rebuild --arch="$_gyp_arch")
-
-	# 5) Place the compiled binding into the standalone bundle
-	local _bs3_release=.next/standalone/node_modules/better-sqlite3/build/Release
-	mkdir -p "$_bs3_release"
-	cp node_modules/better-sqlite3/build/Release/better_sqlite3.node "$_bs3_release/"
-
-	# 6) Remove arch-specific sharp bundles – upstream sets images.unoptimized=true
-	#    so sharp is not used at runtime; x64 .so files would break aarch64 strip
-	rm -rf .next/standalone/node_modules/@img
-
-	# 7) Copy pino runtime deps omitted by Next.js static analysis:
-	#    pino-abstract-transport – required by pino's worker thread
-	#    split2 – dep of pino-abstract-transport
-	#    process-warning – dep of pino itself
-	for _mod in pino-abstract-transport split2 process-warning; do
-		cp -r "node_modules/$_mod" .next/standalone/node_modules/
-	done
-}
-
-do_check() {
-	npm run test:unit
-}
-
-do_install() {
-	vmkdir usr/lib/omniroute/.next
-
-	vcopy .next/standalone/. usr/lib/omniroute/.next/standalone
-
-	# Prevent removal of empty Next.js app router dirs by the post-install hook
-	for _d in \
-		.next/standalone/.next/server/app/dashboard \
-		.next/standalone/.next/server/app/dashboard/settings \
-		.next/standalone/.next/server/app/dashboard/providers; do
-		touch "${DESTDIR}/usr/lib/omniroute/${_d}/.keep"
-	done
-
-	cat > "${WRKDIR}/omniroute" <<'EOF'
-#!/bin/sh
-export PORT="${PORT:-20128}"
-export DATA_DIR="${DATA_DIR:-${XDG_DATA_HOME:-${HOME}/.local/share}/omniroute}"
-export APP_LOG_TO_FILE="${APP_LOG_TO_FILE:-false}"
-mkdir -p "${DATA_DIR}"
-exec node /usr/lib/omniroute/.next/standalone/server.js "$@"
-EOF
-	vbin "${WRKDIR}/omniroute"
-}
-
-post_install() {
-	vlicense LICENSE
-}
-```
-
-</details>
-
----
-
-## 🐳 Docker
-
-OmniRoute is available as a public Docker image on [Docker Hub](https://hub.docker.com/r/diegosouzapw/omniroute).
-
-**Quick run:**
-
-```bash
-docker run -d \
-  --name omniroute \
-  --restart unless-stopped \
-  --stop-timeout 40 \
-  -p 20128:20128 \
-  -v omniroute-data:/app/data \
-  diegosouzapw/omniroute:latest
-```
-
-**With environment file:**
-
-```bash
-# Copy and edit .env first
-cp .env.example .env
-
-docker run -d \
-  --name omniroute \
-  --restart unless-stopped \
-  --stop-timeout 40 \
-  --env-file .env \
-  -p 20128:20128 \
-  -v omniroute-data:/app/data \
-  diegosouzapw/omniroute:latest
-```
-
-**Using Docker Compose:**
-
-```bash
-# Base profile (no CLI tools)
-docker compose --profile base up -d
-
-# CLI profile (Claude Code, Codex, OpenClaw built-in)
-docker compose --profile cli up -d
-```
-
-Dashboard support for Docker deployments now includes a one-click **Cloudflare Quick Tunnel** on `Dashboard → Endpoints`. The first enable downloads `cloudflared` only when needed, starts a temporary tunnel to your current `/v1` endpoint, and shows the generated `https://*.trycloudflare.com/v1` URL directly below your normal public URL.
-
-Notes:
-
-- Quick Tunnel URLs are temporary and change after every restart.
-- Quick Tunnels are not auto-restored after an OmniRoute or container restart. Re-enable them from the dashboard when needed.
-- Managed install currently supports Linux, macOS, and Windows on `x64` / `arm64`.
-- Managed Quick Tunnels default to HTTP/2 transport to avoid noisy QUIC UDP buffer warnings in constrained container environments. Set `CLOUDFLARED_PROTOCOL=quic` or `auto` if you want a different transport.
-- Docker images bundle system CA roots and pass them to managed `cloudflared`, which avoids TLS trust failures when the tunnel bootstraps inside the container.
-- SQLite runs in WAL mode. `docker stop` should be allowed to finish so OmniRoute can checkpoint the latest changes back into `storage.sqlite`.
-- The bundled Compose files already set a 40s stop grace period. If you run the image directly, keep `--stop-timeout 40` (or similar) so manual stops do not cut off shutdown cleanup.
-- Set `CLOUDFLARED_BIN=/absolute/path/to/cloudflared` if you want OmniRoute to use an existing binary instead of downloading one.
-
-**Using Docker Compose with Caddy (HTTPS Auto-TLS):**
-
-OmniRoute can be securely exposed using Caddy's automatic SSL provisioning. Ensure your domain's DNS A record points to your server's IP.
-
-```yaml
-services:
-  omniroute:
-    image: diegosouzapw/omniroute:latest
-    container_name: omniroute
-    restart: unless-stopped
-    volumes:
-      - omniroute-data:/app/data
-    environment:
-      - PORT=20128
-      - NEXT_PUBLIC_BASE_URL=https://your-domain.com
-
-  caddy:
-    image: caddy:latest
-    container_name: caddy
-    restart: unless-stopped
-    ports:
-      - "80:80"
-      - "443:443"
-    command: caddy reverse-proxy --from https://your-domain.com --to http://omniroute:20128
-
-volumes:
-  omniroute-data:
-```
-
-| Image                    | Tag      | Size   | Description           |
-| ------------------------ | -------- | ------ | --------------------- |
-| `diegosouzapw/omniroute` | `latest` | ~250MB | Latest stable release |
-| `diegosouzapw/omniroute` | `3.6.2`  | ~250MB | Current version       |
-
----
-
-## 🖥️ Desktop App — Offline & Always-On
-
-> 🆕 **NEW!** OmniRoute is now available as a **native desktop application** for Windows, macOS, and Linux.
-
-Run OmniRoute as a standalone desktop app — no terminal, no browser, no internet required for local models. The Electron-based app includes:
-
-- 🖥️ **Native Window** — Dedicated app window with system tray integration
-- 🔄 **Auto-Start** — Launch OmniRoute on system login
-- 🔔 **Native Notifications** — Get alerts for quota exhaustion or provider issues
-- ⚡ **One-Click Install** — NSIS (Windows), DMG (macOS), AppImage (Linux)
-- 🌐 **Offline Mode** — Works fully offline with bundled server
-
-### त्वरित प्रारंभ
-
-```bash
-# Development mode
-npm run electron:dev
-
-# Build for your platform
-npm run electron:build         # Current platform
-npm run electron:build:win     # Windows (.exe)
-npm run electron:build:mac     # macOS (.dmg) — x64 & arm64
-npm run electron:build:linux   # Linux (.AppImage)
-```
-
-### System Tray
-
-When minimized, OmniRoute lives in your system tray with quick actions:
-
-- Open dashboard
-- Change server port
-- Quit application
-
-📖 Full documentation: [`electron/README.md`](electron/README.md)
-
----
-
-## 💰 Pricing at a Glance
-
-| Tier                | Provider                    | Cost                                  | Quota Reset           | Best For                           |
-| ------------------- | --------------------------- | ------------------------------------- | --------------------- | ---------------------------------- |
-| **💳 SUBSCRIPTION** | Claude Code (Pro)           | $20/mo                                | 5h + weekly           | Already subscribed                 |
-|                     | Codex (Plus/Pro)            | $20-200/mo                            | 5h + weekly           | OpenAI users                       |
-|                     | GitHub Copilot              | $10-19/mo                             | Monthly               | GitHub users                       |
-| **🔑 API KEY**      | NVIDIA NIM                  | **FREE ACCESS** (current terms apply) | ~40 RPM               | 70+ open models                    |
-|                     | Cerebras                    | **FREE** (1M tok/day)                 | 60K TPM / 30 RPM      | World's fastest                    |
-|                     | Groq                        | **FREE** (30 RPM)                     | 14.4K RPD             | Ultra-fast Llama/Gemma             |
-|                     | DeepSeek V3.2               | $0.27/$1.10 per 1M                    | None                  | Best price/quality reasoning       |
-|                     | xAI Grok-4 Fast             | **$0.20/$0.50 per 1M** 🆕             | None                  | Fastest + tool calling, ultralow   |
-|                     | xAI Grok-4 (standard)       | $0.20/$1.50 per 1M 🆕                 | None                  | Reasoning flagship from xAI        |
-|                     | Mistral                     | Free trial + paid                     | Rate limited          | European AI                        |
-|                     | OpenRouter                  | Pay-per-use                           | None                  | 100+ models aggr.                  |
-| **💰 CHEAP**        | GLM-5 (via Z.AI) 🆕         | $0.5/1M                               | Daily 10AM            | 128K output, newest flagship       |
-|                     | GLM-4.7                     | $0.6/1M                               | Daily 10AM            | Budget backup                      |
-|                     | MiniMax M2.5 🆕             | $0.3/1M input                         | 5-hour rolling        | Reasoning + agentic tasks          |
-|                     | MiniMax M2.1                | $0.2/1M                               | 5-hour rolling        | Cheapest option                    |
-|                     | Kimi K2.5 (Moonshot API) 🆕 | Pay-per-use                           | None                  | Direct Moonshot API access         |
-|                     | Kimi K2                     | $9/mo flat                            | 10M tokens/mo         | Predictable cost                   |
-| **🆓 FREE ACCESS**  | Qoder                       | **$0**                                | Limits apply          | Selected models; terms apply       |
-|                     | Kiro                        | **$0**                                | Credit/account limits | Claude access; current terms apply |
-|                     | LongCat signup credit       | **$0** (10M one-time; KYC)            | One-time              | Signup grant; not recurring        |
-|                     | Pollinations AI 🆕          | **$0** (no key needed)                | 1 req/15s             | GPT-5, Claude, DeepSeek, Llama 4   |
-|                     | Cloudflare Workers AI 🆕    | **$0** (10K Neurons/day)              | ~150 resp/day         | 50+ models, global edge            |
-|                     | Scaleway AI 🆕              | **$0** (1M tokens total)              | Rate limited          | EU/GDPR, Qwen3 235B, Llama 70B     |
-
-> 🆕 **New models added (Mar 2026):** Grok-4 Fast family at $0.20/$0.50/M (benchmarked at 1143ms — 30% faster than Gemini 2.5 Flash), GLM-5 via Z.AI with 128K output, MiniMax M2.5 reasoning, DeepSeek V3.2 updated pricing, Kimi K2.5 via Moonshot direct API.
-
-**💡 $0 Combo Stack — The Complete Free Setup:**
-
-```
-# 🆓 Free-access examples — provider limits and terms apply
-Kiro (kr/)             → Claude access — account/credit limits apply
-Qoder (if/)            → selected models — no published token cap; rate/account limits apply
-LongCat (lc/)          → LongCat-2.0 — 10M one-time signup credit; KYC required
-Pollinations (pol/)    → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
-Gemini (gemini/)       → selected free-tier models — current API quotas apply
-Cloudflare AI (cf/)    → Llama 70B, Gemma 3, Mistral — 10K Neurons/day
-Scaleway (scw/)        → Qwen3 235B, Llama 70B — 1M free tokens (EU)
-Groq (groq/)           → selected models — current per-model rate limits apply
-NVIDIA NIM (nvidia/)   → selected models — current rate limits apply
-Cerebras (cerebras/)   → Llama/Qwen world-fastest — 1M tok/day
-```
-
-**Current $0 access where listed; availability is not guaranteed.** A combo can try the next eligible route when a quota or upstream fails.
-
----
-
----
-
-## 🆓 Free Models — What You Actually Get
-
-> The entries below summarize access that was listed as free when audited. Provider quotas, card/account/KYC requirements, models, regions and terms can change. A combo broadens fallback coverage but does not guarantee uninterrupted $0 access.
-
-### 🔵 CLAUDE MODELS (via Kiro — AWS Builder ID)
-
-| Model               | Prefix | Limit                  | Rate Limit                                 |
-| ------------------- | ------ | ---------------------- | ------------------------------------------ |
-| `claude-sonnet-4.5` | `kr/`  | No published token cap | Provider/account limits may apply          |
-| `claude-haiku-4.5`  | `kr/`  | No published token cap | Provider/account limits may apply          |
-| `claude-opus-4.6`   | `kr/`  | No published token cap | Latest Opus; provider/account limits apply |
-
-### 🟢 QODER MODELS (Free PAT via qodercli)
-
-| Model              | Prefix | Limit                  | Rate Limit                        |
-| ------------------ | ------ | ---------------------- | --------------------------------- |
-| `kimi-k2-thinking` | `if/`  | No published token cap | Provider/account limits may apply |
-| `qwen3-coder-plus` | `if/`  | No published token cap | Provider/account limits may apply |
-| `deepseek-r1`      | `if/`  | No published token cap | Provider/account limits may apply |
-| `minimax-m2.1`     | `if/`  | No published token cap | Provider/account limits may apply |
-| `kimi-k2`          | `if/`  | No published token cap | Provider/account limits may apply |
-
-> Recommended connection method: **Personal Access Token + `qodercli`**. Browser OAuth is
-> experimental and disabled by default unless `QODER_OAUTH_*` environment variables are configured.
-
-
-### ⚫ NVIDIA NIM (Free API Key — build.nvidia.com)
-
-| Tier       | Daily Limit  | Rate Limit  | Notes                                                  |
-| ---------- | ------------ | ----------- | ------------------------------------------------------ |
-| Free (Dev) | No token cap | **~40 RPM** | 70+ models; transitioning to pure rate limits mid-2025 |
-
-Popular free models: `moonshotai/kimi-k2.5` (Kimi K2.5), `z-ai/glm4.7` (GLM 4.7), `deepseek-ai/deepseek-v3.2` (DeepSeek V3.2), `nvidia/llama-3.3-70b-instruct`, `deepseek/deepseek-r1`
-
-### ⚪ CEREBRAS (Free API Key — inference.cerebras.ai)
-
-| Tier | Daily Limit       | Rate Limit       | Notes                                       |
-| ---- | ----------------- | ---------------- | ------------------------------------------- |
-| Free | **1M tokens/day** | 60K TPM / 30 RPM | World's fastest LLM inference; resets daily |
-
-Available free: `llama-3.3-70b`, `llama-3.1-8b`, `deepseek-r1-distill-llama-70b`
-
-### 🔴 GROQ (Free API Key — console.groq.com)
-
-| Tier | Daily Limit   | Rate Limit       | Notes                                     |
-| ---- | ------------- | ---------------- | ----------------------------------------- |
-| Free | **14.4K RPD** | 30 RPM per model | No credit card; 429 on limit, not charged |
-
-Available free: `llama-3.3-70b-versatile`, `gemma2-9b-it`, `mixtral-8x7b`, `whisper-large-v3`
-
-### 🔴 LONGCAT AI (Signup credit — KYC required)
-
-| Model         | Prefix | Current catalog grant   | Notes                                               |
-| ------------- | ------ | ----------------------- | --------------------------------------------------- |
-| `LongCat-2.0` | `lc/`  | **10M tokens one-time** | Signup grant; not a recurring monthly or daily pool |
-
-> Provider terms, eligibility and model availability can change. See [`FREE_TIERS.md`](../../reference/FREE_TIERS.md) for the audited catalog entry.
-
-### 🟢 POLLINATIONS AI (No API Key Required) 🆕
-
-| Model      | Prefix | Rate Limit | Provider Behind    |
-| ---------- | ------ | ---------- | ------------------ |
-| `openai`   | `pol/` | 1 req/15s  | GPT-5              |
-| `claude`   | `pol/` | 1 req/15s  | Anthropic Claude   |
-| `gemini`   | `pol/` | 1 req/15s  | Google Gemini      |
-| `deepseek` | `pol/` | 1 req/15s  | DeepSeek V3        |
-| `llama`    | `pol/` | 1 req/15s  | Meta Llama 4 Scout |
-| `mistral`  | `pol/` | 1 req/15s  | Mistral AI         |
-
-> ✨ **Zero friction:** No signup, no API key. Add the Pollinations provider with an empty key field and it works immediately.
-
-### 🟠 CLOUDFLARE WORKERS AI (Free API Key — cloudflare.com) 🆕
-
-| Tier | Daily Neurons | Equivalent Usage                        | Notes                   |
-| ---- | ------------- | --------------------------------------- | ----------------------- |
-| Free | **10,000**    | ~150 LLM resp / 500s audio / 15K embeds | Global edge, 50+ models |
-
-Popular free models: `@cf/meta/llama-3.3-70b-instruct`, `@cf/google/gemma-3-12b-it`, `@cf/openai/whisper-large-v3-turbo` (free audio!), `@cf/qwen/qwen2.5-coder-15b-instruct`
-
-> Requires API Token + Account ID from [dash.cloudflare.com](https://dash.cloudflare.com). Store Account ID in provider settings.
-
-### 🟣 SCALEWAY AI (1M Free Tokens — scaleway.com) 🆕
-
-| Tier | Free Quota    | Location     | Notes                               |
-| ---- | ------------- | ------------ | ----------------------------------- |
-| Free | **1M tokens** | 🇫🇷 Paris, EU | No credit card needed within limits |
-
-Available free: `qwen3-235b-a22b-instruct-2507` (Qwen3 235B!), `llama-3.1-70b-instruct`, `mistral-small-3.2-24b-instruct-2506`, `deepseek-v3-0324`
-
-> EU/GDPR compliant. Get API key at [console.scaleway.com](https://console.scaleway.com).
-
-> **💡 Free-access examples (provider limits and terms apply):**
->
-> ```
-> Kiro (kr/)             → Claude access — account/credit limits apply
-> Qoder (if/)            → selected models — no published token cap; limits apply
-> LongCat (lc/)          → LongCat-2.0 — 10M one-time signup credit; KYC required
-> Pollinations (pol/)    → GPT-5, Claude, DeepSeek, Llama 4 — no key needed
-> Gemini (gemini/)       → selected free-tier models — current quotas apply
-> Cloudflare AI (cf/)    → 50+ models — 10K Neurons/day
-> Scaleway (scw/)        → Qwen3 235B, Llama 70B — 1M free tokens (EU)
-> Groq (groq/)           → selected models — current per-model rate limits apply
-> NVIDIA NIM (nvidia/)   → selected models — current rate limits apply
-> Cerebras (cerebras/)   → Llama/Qwen world-fastest — 1M tok/day
-> ```
-
-## 🎙️ Free Transcription Combo
-
-> Transcription access depends on each upstream allowance — Deepgram and AssemblyAI signup credits can lead, with Groq Whisper as a rate-limited fallback.
-
-| Provider          | Free Credits                | Best Model                                   | Rate Limit                               |
-| ----------------- | --------------------------- | -------------------------------------------- | ---------------------------------------- |
-| 🟢 **Deepgram**   | **$200 free** (signup)      | `nova-3` — best accuracy, 30+ languages      | No RPM limit on free credits             |
-| 🔵 **AssemblyAI** | **$50 free** (signup)       | `universal-3-pro` — chapters, sentiment, PII | No RPM limit on free credits             |
-| 🔴 **Groq**       | **Free tier; limits apply** | `whisper-large-v3` — OpenAI Whisper          | Current model-specific rate limits apply |
-
-**Suggested combo in `/dashboard/combos`:**
-
-```
-Name: free-transcription
-Strategy: Priority
-Nodes:
-  [1] deepgram/nova-3          → uses $200 free first
-  [2] assemblyai/universal-3-pro → fallback when Deepgram credits run out
-  [3] groq/whisper-large-v3    → free access; rate limits apply
-```
-
-Then in `/dashboard/media` → **Transcription** tab: upload any audio or video file → select your combo endpoint → get transcription in supported formats.
-
-## 💡 Key Features
-
-OmniRoute v3.6 is built as an operational platform, not just a relay proxy.
-
-### 🆕 New — v3.6.x Highlights (Apr 2026)
-
-| Feature                            | What It Does                                                                                                                                      |
-| ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
-| 🌐 **V1 WebSocket Bridge**         | OpenAI-compatible WebSocket traffic upgraded and proxied via `/v1/ws` — full streaming over WS with session auth (API key or session cookie)      |
-| 🔑 **Sync Tokens & Config Bundle** | Issue/revoke sync tokens for config sync endpoints. Config bundles versioned with ETag for bandwidth-efficient polling                            |
-| 🧠 **GLM Thinking (glmt) Preset**  | GLM Thinking registered first-class: 65 536 max tokens, 24 576 thinking budget, 900s timeout, usage sync & pricing — Claude-compatible API        |
-| 🔢 **Hybrid Token Counting**       | Uses provider-side `/messages/count_tokens` when available; falls back to estimation — accurate usage tracking without guessing                   |
-| 🌱 **Model Alias Auto-Seed**       | 30+ cross-proxy dialect aliases normalised at startup — no more routing mismatches                                                                |
-| 🛡️ **Safe Outbound Fetch**         | All provider validation and model discovery go through a guarded fetch layer blocking private/local URLs with retry, timeout, and SSRF protection |
-| 🔄 **Cooldown-Aware Retries**      | Chat requests auto-retry on model-scoped cooldowns with configurable `requestRetry` and `maxRetryIntervalSec`                                     |
-| 🔍 **Runtime Env Validation**      | Startup validates all env vars with Zod schemas — clear errors for missing secrets, invalid URLs, or wrong types                                  |
-| 📋 **Compliance Audit Expansion**  | Structured audit logs with pagination, request context, auth events, provider CRUD events, and SSRF-blocked validation logging                    |
-| 🔐 **TPS Log Metric**              | Log details modal shows Tokens Per Second (TPS) — quick performance at-a-glance for every request                                                 |
-| 🗑️ **Uninstall / Full Uninstall**  | `npm run uninstall` keeps data, `npm run uninstall:full` removes everything — clean removal for all install methods                               |
-| 🔧 **OAuth Env Repair**            | One-click "Repair env" action for OAuth providers restores missing env vars and fixes broken auth state                                           |
-| 🔒 **Graceful Electron Shutdown**  | Electron `before-quit` shuts down Next.js gracefully, preventing SQLite WAL database locks on desktop close                                       |
-| 👁️ **Model Visibility Toggle**     | Per-model visibility toggle (👁 icon) with search filter and active-count badge (`N/M active`) on provider pages                                   |
-| 📧 **Email Privacy Masking**       | OAuth account emails masked (`di*****@g****.com`), full address visible on hover                                                                  |
-| 🔗 **Context Relay Strategy**      | Combo strategy preserving session continuity via structured handoff summaries when accounts rotate mid-conversation                               |
-| 🛡️ **Proxy Hardening**             | Token health check, API key validation, and undici dispatcher all honor proxy config                                                              |
-| ⚠️ **Node.js 24 Login Warning**    | Login page proactively detects incompatible Node.js versions and shows a clear warning banner                                                     |
-| 📎 **Gemini PDF Attachments**      | PDF attachments correctly routed to Gemini via `inline_data` and generic base64 detection                                                         |
-| 🔒 **CodeQL Security Hardening**   | Resolved SSRF, insecure randomness, polynomial ReDoS, and incomplete URL sanitization alerts                                                      |
-
-### 🆕 New — ClawRouter-Inspired Improvements (Mar 2026)
-
-| Feature                              | What It Does                                                                                |
-| ------------------------------------ | ------------------------------------------------------------------------------------------- |
-| ⚡ **Grok-4 Fast Family**            | xAI models at $0.20/$0.50/M — benchmarked 1143ms (30% faster than Gemini 2.5 Flash)         |
-| 🧠 **GLM-5 via Z.AI**                | 128K output context, $0.5/1M — newest flagship from the GLM family                          |
-| 🔮 **MiniMax M2.5**                  | Reasoning + agentic tasks at $0.30/1M — significant upgrade from M2.1                       |
-| 🎯 **toolCalling Flag per Model**    | Per-model `toolCalling: true/false` in registry — AutoCombo skips non-tool-capable models   |
-| 🌍 **Multilingual Intent Detection** | PT/ZH/ES/AR keywords in AutoCombo scoring — better model selection for non-English content  |
-| 📊 **Benchmark-Driven Fallbacks**    | Real p95 latency from live requests feeds combo scoring — AutoCombo learns from actual data |
-| 🔁 **Request Deduplication**         | Content-hash based dedup window — multi-agent safe, prevents duplicate charges              |
-| 🔌 **Pluggable RouterStrategy**      | Extensible `RouterStrategy` interface — add custom routing logic as plugins                 |
-
-### 🚀 Previous v2.0.9+ — Playground, CLI Fingerprints & ACP
-
-| Feature                                 | What It Does                                                                                                                                                                                                                            |
-| --------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| 🎮 **Model Playground**                 | Dashboard page to test any model directly — provider/model/endpoint selectors, Monaco Editor, streaming, abort, timing                                                                                                                  |
-| 🔏 **CLI Fingerprint Matching**         | Per-provider header/body ordering to match native CLI signatures — toggle per provider in Settings > Security. **Your proxy IP is preserved**                                                                                           |
-| 🤖 **ACP Agents Dashboard**             | Debug › Agents page — grid of 14 agents with install status, version, custom agent form for any CLI tool. **OpenCode** users get a "Download opencode.json" button that auto-generates a ready-to-use config with all available models. |
-| 🔧 **Custom Model `apiFormat` Routing** | Custom models with `apiFormat: "responses"` now correctly route to the Responses API translator                                                                                                                                         |
-| 🏢 **Codex Workspace Isolation**        | Multiple Codex workspaces per email — OAuth correctly separates connections by workspace ID                                                                                                                                             |
-| 🔄 **Electron Auto-Update**             | Desktop app checks for updates + auto-install on restart                                                                                                                                                                                |
-
-### 🤖 Agent & Protocol Operations (v2.0)
-
-| Feature                               | What It Does                                                                                                                                                                                              |
-| ------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| 🔧 **MCP Server (107 tools)**         | IDE/agent tools via 3 transports: stdio, SSE (`/api/mcp/sse`), Streamable HTTP (`/api/mcp/stream`). 107 unique tools across the registered tool families; enabled skills may add dynamic tools at runtime |
-| 🤝 **A2A Server (JSON-RPC + SSE)**    | Agent-to-agent task execution with sync and streaming flows                                                                                                                                               |
-| 🧭 **Consolidated Endpoints Page**    | Tabbed management page with Endpoint Proxy, MCP, A2A, and API Endpoints tabs                                                                                                                              |
-| 🎚️ **Service Enable/Disable Toggles** | ON/OFF switches for MCP and A2A with settings persistence (default: OFF)                                                                                                                                  |
-| 🛰️ **MCP Runtime Heartbeat**          | Real process status (pid, uptime, heartbeat age, transport, scope mode)                                                                                                                                   |
-| 📋 **MCP Audit Trail**                | Filterable audit logs with success/failure and key attribution                                                                                                                                            |
-| 🔐 **MCP Scope Enforcement**          | 32 granular scope permissions for controlled tool access                                                                                                                                                  |
-| 📡 **A2A Task Lifecycle Management**  | List/filter tasks, inspect events/artifacts, cancel running tasks                                                                                                                                         |
-| 📋 **Agent Card Discovery**           | `/.well-known/agent.json` for client auto-discovery                                                                                                                                                       |
-| 🧪 **Protocol E2E Test Harness**      | Real MCP SDK + A2A client flows in `test:protocols:e2e`                                                                                                                                                   |
-| ⚙️ **Operational Controls**           | Switch combo, apply resilience profiles, reset breakers from one control surface                                                                                                                          |
-
-### 🧠 Routing & Intelligence
-
-| Feature                            | What It Does                                                             |
-| ---------------------------------- | ------------------------------------------------------------------------ |
-| 🎯 **Smart 4-Tier Fallback**       | Auto-route: Subscription → API Key → Cheap → Free                        |
-| 📊 **Real-Time Quota Tracking**    | Live token count + reset countdown per provider                          |
-| 🔄 **Format Translation**          | OpenAI ↔ Claude ↔ Gemini ↔ Responses with schema-safe conversions        |
-| 👥 **Multi-Account Support**       | Multiple accounts per provider with intelligent selection                |
-| 🔄 **Auto Token Refresh**          | OAuth tokens refresh automatically with retry                            |
-| 🎨 **Custom Combos**               | 13 balancing strategies + fallback chain control                         |
-| 🔗 **Context Relay**               | Session continuity handoffs when account rotation happens mid-session    |
-| 🌐 **Wildcard Router**             | `provider/*` dynamic routing                                             |
-| 🧠 **Thinking Budget Controls**    | Passthrough, auto, custom, and adaptive reasoning limits                 |
-| 🔀 **Model Aliases**               | Built-in + custom model aliasing and migration safety                    |
-| ⚡ **Background Degradation**      | Route low-priority background tasks to cheaper models                    |
-| 🧪 **Task-Aware Smart Routing**    | Auto-select model by content type (coding/vision/analysis/summarization) |
-| 🔄 **A2A Agent Workflows**         | Deterministic FSM orchestrator for stateful multi-step agent executions  |
-| 🔀 **Adaptive Routing**            | Dynamic strategy override based on token volume and prompt complexity    |
-| 🎲 **Provider Diversity**          | Shannon entropy scoring balancing auto-combo traffic distribution        |
-| 💬 **System Prompt Injection**     | Global behavior controls applied consistently                            |
-| 📄 **Responses API Compatibility** | Full `/v1/responses` support for Codex and advanced agentic workflows    |
-
-### 🎵 Multi-Modal APIs
-
-| Feature                    | What It Does                                                                                                                                                               |
-| -------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| 🖼️ **Image Generation**    | `/v1/images/generations` with cloud and local backends                                                                                                                     |
-| 📐 **Embeddings**          | `/v1/embeddings` for search and RAG pipelines                                                                                                                              |
-| 🎤 **Audio Transcription** | `/v1/audio/transcriptions` — 7 providers (Deepgram Nova 3, AssemblyAI, Groq Whisper, HuggingFace, ElevenLabs, OpenAI, Azure), auto-language detection, MP4/MP3/WAV support |
-| 🔊 **Text-to-Speech**      | `/v1/audio/speech` — 10 providers (ElevenLabs, OpenAI, Deepgram, Cartesia, PlayHT, HuggingFace, Nvidia NIM, Inworld, Coqui, Tortoise) with correct error messages          |
-| 🎬 **Video Generation**    | `/v1/videos/generations` (ComfyUI + SD WebUI workflows)                                                                                                                    |
-| 🎵 **Music Generation**    | `/v1/music/generations` (ComfyUI workflows)                                                                                                                                |
-| 🛡️ **Moderations**         | `/v1/moderations` safety checks                                                                                                                                            |
-| 🔀 **Reranking**           | `/v1/rerank` for relevance scoring                                                                                                                                         |
-| 🔍 **Web Search** 🆕       | `/v1/search` — 5 providers (Serper, Brave, Perplexity, Exa, Tavily), 6,500+ free/month, auto-failover, cache                                                               |
-
-### 🛡️ Resilience, Security & Governance
-
-| Feature                             | What It Does                                                                            |
-| ----------------------------------- | --------------------------------------------------------------------------------------- |
-| 🔌 **Circuit Breakers**             | Per-provider and per-model trip/recover with 10-minute cooldowns                        |
-| 🔒 **Daily Quota Lock** 🆕          | Detects exhaustion signals and locks routing for the specific model until midnight      |
-| 🎯 **Endpoint-Aware Models**        | Custom models declare supported endpoints + API format                                  |
-| 🛡️ **Anti-Thundering Herd**         | Mutex + semaphore protections on retry/rate events                                      |
-| 🧠 **Semantic + Signature Cache**   | Cost/latency reduction with two cache layers                                            |
-| ⚡ **Request Idempotency**          | Duplicate protection window                                                             |
-| 🔒 **TLS Fingerprint Spoofing**     | Browser-like TLS fingerprint — **reduces bot detection and account flagging**           |
-| 🔏 **CLI Fingerprint Matching**     | Matches native CLI request signatures — **reduces ban risk while preserving proxy IP**  |
-| 🌐 **IP Filtering**                 | Allowlist/blocklist control for exposed deployments                                     |
-| 📊 **Editable Rate Limits**         | Configurable global/provider-level limits with persistence                              |
-| 📉 **Graceful Degradation**         | Multi-layer capability fallbacks protecting core gateway operations                     |
-| 📜 **Config Audit Trail**           | Diff-based change tracking preventing operational drift with simple rollbacks           |
-| ⏳ **Provider Health Sync**         | Proactive token expiration monitoring triggering alerts before authorization failures   |
-| 🚪 **Auto-Disable Banned Accounts** | Operational circuit breaker sealing permanently blocked token accounts automatically    |
-| 🔑 **API Key Management + Scoping** | Secure key issuance/rotation and model/provider controls                                |
-| 👁️ **Scoped API Key Reveal** 🆕     | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL`                                  |
-| 🛡️ **Protected `/models`**          | Optional auth gating and provider hiding for model catalog                              |
-| 🛡️ **Safe Outbound Fetch** 🆕       | Guarded fetch for provider calls — blocks private/local URLs, retries, SSRF protection  |
-| 🔄 **Cooldown-Aware Retries** 🆕    | Auto-retry chat on model cooldowns; configurable `requestRetry` / `maxRetryIntervalSec` |
-| 🔍 **Runtime Env Validation** 🆕    | Zod-based env schema validation at startup with actionable error messages               |
-| 📋 **Compliance Audit v2** 🆕       | Pagination, request context, auth events, provider CRUD, and SSRF-blocked logging       |
-
-### 📊 Observability & Analytics
-
-| Feature                          | What It Does                                          |
-| -------------------------------- | ----------------------------------------------------- |
-| 📝 **Request + Proxy Logging**   | Full request/response and proxy logging               |
-| 📉 **Streamed Detailed Logs**    | Reconstructs SSE payload streams cleanly into the UI  |
-| 🏷️ **Real-Time Model Badges** 🆕 | Live model status and daily quota countdown timers    |
-| 📋 **Unified Logs Dashboard**    | Request, proxy, audit, and console views in one page  |
-| 🔍 **Request Telemetry**         | p50/p95/p99 latency and request tracing               |
-| 🏥 **Health Dashboard**          | Uptime, breaker states, lockouts, cache stats         |
-| 💰 **Cost Tracking**             | Budget controls and per-model pricing visibility      |
-| 📈 **Analytics Visualizations**  | Model/provider usage insights and trend views         |
-| 🧪 **Evaluation Framework**      | Golden set testing with configurable match strategies |
-| 📡 **Live Diagnostics** 🆕       | Semantic cache bypass for accurate combo live testing |
-| 🔐 **TPS Log Metric** 🆕         | Tokens Per Second badge in log details modal          |
-
-### ☁️ Deployment & Platform
-
-| Feature                        | What It Does                                                          |
-| ------------------------------ | --------------------------------------------------------------------- |
-| 🌐 **Deploy Anywhere**         | Localhost, VPS, Docker, Cloud environments                            |
-| 🚇 **Cloudflare Tunnel** 🆕    | One-click Quick Tunnel integration from the dashboard                 |
-| 🔑 **API Key Model Filtering** | Native /v1/models response filtered via assigned Bearer context roles |
-| ⚡ **Smart Cache Bypass**      | Configurable TTL heuristics and forced refetch controls               |
-| 🔄 **Backup/Restore**          | Export/import and disaster recovery flows                             |
-| 🧙 **Onboarding Wizard**       | First-run guided setup                                                |
-| 🔧 **CLI Tools Dashboard**     | One-click setup for popular coding tools                              |
-| 🎮 **Model Playground**        | Test any provider/model/endpoint from the dashboard                   |
-| 🔏 **CLI Fingerprint Toggle**  | Per-provider fingerprint matching in Settings > Security              |
-| 🌐 **i18n (30 languages)**     | Full dashboard + docs language support with RTL coverage              |
-| 🧹 **Clear All Models**        | One-click model list clearing in provider details                     |
-| 👁️ **Sidebar Controls** 🆕     | Hide components and integrations from Appearance Settings             |
-| 📋 **Issue Templates**         | Standardized GitHub templates for bugs and features                   |
-| 📂 **Custom Data Directory**   | `DATA_DIR` override for storage location                              |
-| 🌐 **V1 WebSocket Bridge** 🆕  | OpenAI-compatible WebSocket traffic proxied via `/v1/ws`              |
-| 🔑 **Sync Tokens & Bundle** 🆕 | Config sync tokens + versioned bundle endpoint with ETag support      |
-
-### Feature Deep Dive
-
-#### Smart fallback with practical cost control
-
-```txt
-Combo: "my-coding-stack"
-  1. cc/claude-opus-4-7
-  2. nvidia/llama-3.3-70b
-  3. glm/glm-4.7
-  4. if/kimi-k2-thinking
-```
-
-When quota, rate, or health fails, OmniRoute automatically moves to the next candidate without manual switching.
-
-#### Protocol management that is visible and operable
-
-- MCP + A2A are discoverable in UI and docs (not hidden)
-- Protocol status APIs expose live operational data (`/api/mcp/*`, `/api/a2a/*`)
-- Dashboards include actions for day-2 ops (combo toggles, breaker resets, task cancellation)
-
-#### Translator + validation workflow
-
-The Translator area includes:
-
-- **Playground**: request transformation checks
-- **Chat Tester**: full request/response round-trip
-- **Test Bench**: multiple cases in one run
-- **Live Monitor**: real-time traffic view
-
-Plus protocol validation with real clients via `npm run test:protocols:e2e`.
-
-> 📖 **[MCP Server README](open-sse/mcp-server/README.md)** — Tool reference, IDE configs, and client examples
->
-> 📖 **[A2A Server README](src/lib/a2a/README.md)** — Skills, JSON-RPC methods, streaming, and task lifecycle
-
-## 🧪 Evaluations (Evals)
-
-OmniRoute includes a built-in evaluation framework to test LLM response quality against a golden set. Access it via **Analytics → Evals** in the dashboard.
-
-### Built-in Golden Set
-
-The pre-loaded "OmniRoute Golden Set" contains test cases for:
-
-- Greetings, math, geography, code generation
-- JSON format compliance, translation, markdown generation
-- Safety refusal (harmful content), counting, boolean logic
-
-### Evaluation Strategies
-
-| Strategy   | Description                                      | Example                          |
-| ---------- | ------------------------------------------------ | -------------------------------- |
-| `exact`    | Output must match exactly                        | `"4"`                            |
-| `contains` | Output must contain substring (case-insensitive) | `"Paris"`                        |
-| `regex`    | Output must match regex pattern                  | `"1.*2.*3"`                      |
-| `custom`   | Custom JS function returns true/false            | `(output) => output.length > 10` |
-
----
-
-## 📖 Setup Guide
-
-### Protocol Setup (MCP + A2A)
-
-<details>
-<summary><b>🧩 MCP Setup (Model Context Protocol)</b></summary>
-
-Start MCP transport in stdio mode:
-
-```bash
-omniroute --mcp
-```
-
-Recommended validation flow:
-
-1. Connect your MCP client over stdio.
-2. Run `omniroute_get_health`.
-3. Run `omniroute_list_combos`.
-4. Open `/dashboard/mcp` to confirm heartbeat, activity, and audit.
-
-Useful APIs for automation:
-
-- `GET /api/mcp/status`
-- `GET /api/mcp/tools`
-- `GET /api/mcp/audit`
-- `GET /api/mcp/audit/stats`
-
-</details>
-
-<details>
-<summary><b>🤝 A2A Setup (Agent2Agent)</b></summary>
-
-Discover the agent:
-
-```bash
-curl http://localhost:20128/.well-known/agent.json
-```
-
-Send a task:
-
-```bash
-curl -X POST http://localhost:20128/a2a \
-  -H 'content-type: application/json' \
-  -d '{"jsonrpc":"2.0","id":"setup-a2a","method":"message/send","params":{"skill":"quota-management","messages":[{"role":"user","content":"Summarize quota status."}]}}'
-```
-
-Manage lifecycle:
-
-- `GET /api/a2a/status`
-- `GET /api/a2a/tasks`
-- `GET /api/a2a/tasks/:id`
-- `POST /api/a2a/tasks/:id/cancel`
-
-Operational UI:
-
-- `/dashboard/a2a` for task/state/stream observability and smoke actions
-
-</details>
-
-<details>
-<summary><b>🧪 End-to-end protocol validation</b></summary>
-
-Validate both protocols with real clients:
-
-```bash
-npm run test:protocols:e2e
-```
-
-This verifies:
-
-- MCP SDK client connect/list/call
-- A2A discovery/send/stream/get/cancel
-- Cross-check data in MCP audit and A2A task management APIs
-
-</details>
-
-<details>
-<summary><b>💳 Subscription Providers</b></summary>
-
-### Claude Code (Pro/Max)
-
-```bash
-Dashboard → Providers → Connect Claude Code
-→ OAuth login → Auto token refresh
-→ 5-hour + weekly quota tracking
-
-Models:
-  cc/claude-opus-4-7
-  cc/claude-sonnet-4-5-20250929
-  cc/claude-haiku-4-5-20251001
-```
-
-**Pro Tip:** Use Opus for complex tasks, Sonnet for speed. OmniRoute tracks quota per model!
-
-### OpenAI Codex (Plus/Pro)
-
-```bash
-Dashboard → Providers → Connect Codex
-→ OAuth login (port 1455)
-→ 5-hour + weekly reset
-
-Models:
-  cx/gpt-5.2-codex
-  cx/gpt-5.1-codex-max
-```
-
-#### Codex Account Limit Management (5h + Weekly)
-
-Each Codex account now has policy toggles in `Dashboard -> Providers`:
-
-- `5h` (ON/OFF): enforce the 5-hour window threshold policy.
-- `Weekly` (ON/OFF): enforce the weekly window threshold policy.
-- Threshold behavior: when an enabled window reaches >=90% usage, that account is skipped.
-- Rotation behavior: OmniRoute routes to the next eligible Codex account automatically.
-- Reset behavior: when the provider `resetAt` time passes, the account becomes eligible again automatically.
-
-Scenarios:
-
-- `5h ON` + `Weekly ON`: account is skipped when either window reaches threshold.
-- `5h OFF` + `Weekly ON`: only weekly usage can block the account.
-- `5h ON` + `Weekly OFF`: only 5-hour usage can block the account.
-- `resetAt` passed: account re-enters rotation automatically (no manual re-enable).
-
-### GitHub Copilot
-
-```bash
-Dashboard → Providers → Connect GitHub
-→ OAuth via GitHub
-→ Monthly reset (1st of month)
-
-Models:
-  gh/gpt-5
-  gh/claude-4.5-sonnet
-  gh/gemini-3.1-pro-preview
-```
-
-</details>
-
-<details>
-<summary><b>🔑 API Key Providers</b></summary>
-
-### NVIDIA NIM (FREE developer access — 70+ models)
-
-1. Sign up: [build.nvidia.com](https://build.nvidia.com)
-2. Get free API key (1000 inference credits included)
-3. Dashboard → Add Provider → NVIDIA NIM:
-   - API Key: `nvapi-your-key`
-
-**Models:** `nvidia/llama-3.3-70b-instruct`, `nvidia/mistral-7b-instruct`, and 50+ more
-
-**Pro Tip:** OpenAI-compatible API — works seamlessly with OmniRoute's format translation!
-
-### DeepSeek
-
-1. Sign up: [platform.deepseek.com](https://platform.deepseek.com)
-2. Get API key
-3. Dashboard → Add Provider → DeepSeek
-
-**Models:** `deepseek/deepseek-chat`, `deepseek/deepseek-coder`
-
-### Groq (Free Tier Available!)
-
-1. Sign up: [console.groq.com](https://console.groq.com)
-2. Get API key (free tier included)
-3. Dashboard → Add Provider → Groq
-
-**Models:** `groq/llama-3.3-70b`, `groq/mixtral-8x7b`
-
-**Pro Tip:** Ultra-fast inference — best for real-time coding!
-
-### OpenRouter (100+ Models)
-
-1. Sign up: [openrouter.ai](https://openrouter.ai)
-2. Get API key
-3. Dashboard → Add Provider → OpenRouter
-
-**Models:** Access 100+ models from all major providers through a single API key.
-
-**Dashboard behavior:** OpenRouter models are managed from **Available Models**. Manual add, import, and auto-sync all update the same list.
-
-</details>
-
-<details>
-<summary><b>💰 Cheap Providers (Backup)</b></summary>
-
-### GLM-4.7 (Daily reset, $0.6/1M)
-
-1. Sign up: [Zhipu AI](https://open.bigmodel.cn/)
-2. Get API key from Coding Plan
-3. Dashboard → Add API Key:
-   - Provider: `glm`
-   - API Key: `your-key`
-
-**Use:** `glm/glm-4.7`
-
-**Pro Tip:** Coding Plan offers 3× quota at 1/7 cost! Reset daily 10:00 AM.
-
-### MiniMax M2.1 (5h reset, $0.20/1M)
-
-1. Sign up: [MiniMax](https://www.minimax.io/)
-2. Get API key
-3. Dashboard → Add API Key
-
-**Use:** `minimax/MiniMax-M2.1`
-
-**Pro Tip:** Cheapest option for long context (1M tokens)!
-
-### Kimi K2 ($9/month flat)
-
-1. Subscribe: [Moonshot AI](https://platform.moonshot.ai/)
-2. Get API key
-3. Dashboard → Add API Key
-
-**Use:** `kimi/kimi-latest`
-
-**Pro Tip:** Fixed $9/month for 10M tokens = $0.90/1M effective cost!
-
-</details>
-
-<details>
-<summary><b>🆓 FREE Providers (Emergency Backup)</b></summary>
-
-### Qoder (5 FREE models via OAuth)
-
-```bash
-Dashboard → Connect Qoder
-→ Qoder OAuth login
-→ Access is subject to current provider limits
-
-Models:
-  if/kimi-k2-thinking
-  if/qwen3-coder-plus
-  if/glm-4.7
-  if/minimax-m2
-  if/deepseek-r1
-```
-
-
-### Kiro (Claude FREE)
-
-```bash
-Dashboard → Connect Kiro
-→ AWS Builder ID or Google/GitHub
-→ Access is subject to current provider limits
-
-Models:
-  kr/claude-sonnet-4.5
-  kr/claude-haiku-4.5
-```
-
-</details>
-
-<details>
-<summary><b>🎨 Create Combos</b></summary>
-
-### Example 1: Maximize Subscription → Cheap Backup
-
-```
-Dashboard → Combos → Create New
-
-Name: premium-coding
-Models:
-  1. cc/claude-opus-4-7 (Subscription primary)
-  2. glm/glm-4.7 (Cheap backup, $0.6/1M)
-  3. minimax/MiniMax-M2.1 (Cheapest fallback, $0.20/1M)
-
-Use in CLI: premium-coding
-```
-
-### Example 2: Free-Only (Zero Cost)
-
-```
-Name: free-combo
-Models:
-  1. if/kimi-k2-thinking (no published token cap; provider limits may apply)
-  2. kr/qwen3-coder-next
-
-Cost: currently listed as $0; terms and availability may change
-```
-
-</details>
-
-<details>
-<summary><b>🔧 CLI Integration</b></summary>
-
-### Cursor IDE
-
-```
-Settings → Models → Advanced:
-  OpenAI API Base URL: http://localhost:20128/v1
-  OpenAI API Key: [from OmniRoute dashboard]
-  Model: cc/claude-opus-4-7
-```
-
-### Claude Code
-
-Use the **CLI Tools** page in the dashboard for one-click configuration, or edit `~/.claude/settings.json` manually.
-
-### Codex CLI
-
-```bash
-export OPENAI_BASE_URL="http://localhost:20128"
-export OPENAI_API_KEY="your-omniroute-api-key"
-
-codex "your prompt"
-```
-
-### OpenClaw
-
-**Option 1 — Dashboard (recommended):**
-
-```
-Dashboard → CLI Tools → OpenClaw → Select Model → Apply
-```
-
-**Option 2 — Manual:** Edit `~/.openclaw/openclaw.json`:
-
-```json
-{
-  "models": {
-    "providers": {
-      "omniroute": {
-        "baseUrl": "http://127.0.0.1:20128/v1",
-        "apiKey": "sk_omniroute",
-        "api": "openai-completions"
-      }
-    }
-  }
-}
-```
-
-> **Note:** OpenClaw only works with local OmniRoute. Use `127.0.0.1` instead of `localhost` to avoid IPv6 resolution issues.
-
-### Cline / Continue / RooCode
-
-```
-Settings → API Configuration:
-  Provider: OpenAI Compatible
-  Base URL: http://localhost:20128/v1
-  API Key: [from OmniRoute dashboard]
-  Model: if/kimi-k2-thinking
-```
-
-### OpenCode
-
-**Step 1:** Add OmniRoute as a custom provider:
-
-```bash
-opencode
-/connect
-# Select "Other" → Enter ID: "omniroute" → Enter your OmniRoute API key
-```
-
-**Step 2:** Create/edit `opencode.json` in your project root:
-
-```json
-{
-  "$schema": "https://opencode.ai/config.json",
-  "provider": {
-    "omniroute": {
-      "npm": "@ai-sdk/openai-compatible",
-      "name": "OmniRoute",
-      "options": {
-        "baseURL": "http://localhost:20128/v1"
-      },
-      "models": {
-        "cc/claude-sonnet-4-20250514": { "name": "Claude Sonnet 4" },
-        "gg/gemini-2.5-pro": { "name": "Gemini 2.5 Pro" },
-        "if/kimi-k2-thinking": { "name": "Kimi K2 (Free)" }
-      }
-    }
-  }
-}
-```
-
-**Step 3:** Select the model in OpenCode:
-
-```bash
-/models
-# Select any OmniRoute model from the list
-```
-
-> **Tip:** Add any model available in your OmniRoute `/v1/models` endpoint to the `models` section. Use the format `provider/model-id` from your OmniRoute dashboard.
-
-</details>
-
----
-
-## समस्या निवारण
-
-<details>
-<summary><b>Click to expand troubleshooting guide</b></summary>
-
-**"Language model did not provide messages"**
-
-- Provider quota exhausted → Check dashboard quota tracker
-- Solution: Use combo fallback or switch to cheaper tier
-
-**Rate limiting**
-
-- Subscription quota out → Fallback to GLM/MiniMax
-- Add combo: `cc/claude-opus-4-7 → glm/glm-4.7 → if/kimi-k2-thinking`
-
-**OAuth token expired**
-
-- Auto-refreshed by OmniRoute
-- If issues persist: Dashboard → Provider → Reconnect
-
-**High costs**
-
-- Check usage stats in Dashboard → Costs
-- Switch primary model to GLM/MiniMax
-
-**Dashboard/API ports are wrong**
-
-- `PORT` is the canonical base port (and API port by default)
-- `API_PORT` overrides only OpenAI-compatible API listener
-- `DASHBOARD_PORT` overrides only dashboard/Next.js listener
-- Set `NEXT_PUBLIC_BASE_URL` to your dashboard/public URL (for OAuth callbacks)
-
-**Cloud sync errors**
-
-- Verify `BASE_URL` points to your running instance
-- Verify `CLOUD_URL` points to your expected cloud endpoint
-- Keep `NEXT_PUBLIC_*` values aligned with server-side values
-
-**First login not working**
-
-- Check `INITIAL_PASSWORD` in `.env`
-- If unset, fallback password is `123456`
-
-**No request logs**
-
-- `call_logs` in SQLite stores summary metadata for the Request Logs table and analytics views
-- Detailed request/response payloads are written to `DATA_DIR/call_logs/` as one JSON artifact per request
-- Enable pipeline capture from Dashboard → Logs → Request Logs if you need detailed per-stage payloads
-- `Export Logs` reads the artifact files on demand, while `Export All` includes the `call_logs/` directory alongside `storage.sqlite`
-- Set `APP_LOG_TO_FILE=true` if you also want application console logs in `logs/application/app.log`
-- Adjust `APP_LOG_MAX_FILE_SIZE`, `APP_LOG_RETENTION_DAYS`, `APP_LOG_MAX_FILES`, and `CALL_LOG_MAX_ENTRIES` as needed
-
-**Connection test shows "Invalid" for OpenAI-compatible providers**
-
-- Many providers don't expose a `/models` endpoint
-- OmniRoute v1.0.6+ includes fallback validation via chat completions
-- Ensure base URL includes `/v1` suffix
-
-### 🔐 OAuth on a Remote Server
-
-<a name="oauth-on-a-remote-server"></a>
-<a name="oauth-em-servidor-remoto"></a>
-
-> **⚠️ Important for users running OmniRoute on a VPS, Docker, or any remote server**
-
-The OAuth credentials bundled in OmniRoute are registered **for `localhost` only**. When you access OmniRoute on a remote server (e.g. `https://omniroute.myserver.com`), Google rejects the authentication with:
-
-```
-Error 400: redirect_uri_mismatch
-```
-
-#### Solution: Configure your own OAuth credentials
-
-You need to create an **OAuth 2.0 Client ID** in Google Cloud Console with your server's URI.
-
-#### Step-by-step
-
-**1. Open Google Cloud Console**
-
-Go to: [https://console.cloud.google.com/apis/credentials](https://console.cloud.google.com/apis/credentials)
-
-**2. Create a new OAuth 2.0 Client ID**
-
-- Click **"+ Create Credentials"** → **"OAuth client ID"**
-- Application type: **"Web application"**
-- Name: anything you like (e.g. `OmniRoute Remote`)
-
-**3. Add Authorized Redirect URIs**
-
-In the **"Authorized redirect URIs"** field, add:
-
-```
-https://your-server.com/callback
-```
-
-> Replace `your-server.com` with your server's domain or IP (include the port if needed, e.g. `http://45.33.32.156:20128/callback`).
-
-**4. Save and copy the credentials**
-
-After creating, Google will show the **Client ID** and **Client Secret**.
-
-**5. Set environment variables**
-
-In your `.env` (or Docker environment variables):
-
-```bash
-# For Antigravity:
-ANTIGRAVITY_OAUTH_CLIENT_ID=your-client-id.apps.googleusercontent.com
-ANTIGRAVITY_OAUTH_CLIENT_SECRET=GOCSPX-your-secret
-
-GEMINI_OAUTH_CLIENT_ID=your-client-id.apps.googleusercontent.com
-GEMINI_OAUTH_CLIENT_SECRET=GOCSPX-your-secret
-```
-
-**6. Restart OmniRoute**
-
-```bash
-# npm:
-npm run dev
-
-# Docker:
-docker restart omniroute
-```
-
-**7. Try connecting again**
-
-Google will now redirect correctly to `https://your-server.com/callback`.
-
----
-
-#### Temporary workaround (without custom credentials)
-
-If you don't want to set up your own credentials right now, you can still use the **manual URL flow**:
-
-1. OmniRoute opens the Google authorization URL
-2. After authorizing, Google tries to redirect to `localhost` (which fails on the remote server)
-3. **Copy the full URL** from your browser's address bar (even if the page doesn't load)
-4. Paste that URL into the field shown in the OmniRoute connection modal
-5. Click **"Connect"**
-
-> This works because the authorization code in the URL is valid regardless of whether the redirect page loaded.
-
----
-
-## 🛠️ Tech Stack
-
-<details>
-<summary><b>Click to expand tech stack details</b></summary>
-
-- **Runtime**: Node.js 18–22 LTS (⚠️ Node.js 24+ is **not supported** — `better-sqlite3` native binaries are incompatible)
-- **Language**: TypeScript 5.9 — **100% TypeScript** across `src/` and `open-sse/` (zero `any` in core modules since v2.0)
-- **Framework**: Next.js 16 + React 19 + Tailwind CSS 4
-- **Database**: better-sqlite3 (SQLite) + LowDB (JSON legacy) — domain state, proxy logs, MCP audit, routing decisions, memory, skills
-- **Schemas**: Zod (MCP tool I/O validation, API contracts)
-- **Protocols**: MCP (stdio/HTTP) + A2A v0.3 (JSON-RPC 2.0 + SSE)
-- **Streaming**: Server-Sent Events (SSE)
-- **Auth**: OAuth 2.0 (PKCE) + JWT + API Keys + MCP Scoped Authorization
-- **Testing**: Node.js test runner + Vitest (900+ tests including unit, integration, E2E)
-- **CI/CD**: GitHub Actions (auto npm publish + Docker Hub on release)
-- **Website**: [omniroute.online](https://omniroute.online)
-- **Package**: [npmjs.com/package/omniroute](https://www.npmjs.com/package/omniroute)
-- **Docker**: [hub.docker.com/r/diegosouzapw/omniroute](https://hub.docker.com/r/diegosouzapw/omniroute)
-- **Resilience**: Circuit breaker, exponential backoff, anti-thundering herd, TLS spoofing, auto-combo self-healing
-
-</details>
-
----
-
-## दस्तावेज़
-
-| Document                                                              | Description                                         |
-| --------------------------------------------------------------------- | --------------------------------------------------- |
-| [User Guide](docs/guides/USER_GUIDE.md)                               | Providers, combos, CLI integration, deployment      |
-| [API Reference](docs/reference/API_REFERENCE.md)                      | All endpoints with examples                         |
-| [MCP Server](open-sse/mcp-server/README.md)                           | 107 MCP tools, IDE configs, Python/TS/Go clients    |
-| [A2A Server](src/lib/a2a/README.md)                                   | JSON-RPC 2.0 protocol, skills, streaming, task mgmt |
-| [Auto-Combo Engine](docs/routing/AUTO-COMBO.md)                       | 13-factor scoring, mode packs, self-healing         |
-| [Context Relay](docs/features/context-relay.md)                       | Session handoff strategy for account rotation       |
-| [Troubleshooting](docs/guides/TROUBLESHOOTING.md)                     | Common problems and solutions                       |
-| [Architecture](docs/architecture/ARCHITECTURE.md)                     | System architecture and internals                   |
-| [Codebase Documentation](docs/architecture/CODEBASE_DOCUMENTATION.md) | Beginner-friendly codebase walkthrough              |
-| [Uninstall Guide](docs/guides/UNINSTALL.md)                           | Clean removal for all install methods               |
-| [Environment Config](docs/reference/ENVIRONMENT.md)                   | Complete `.env` variables and references            |
-| [Contributing](CONTRIBUTING.md)                                       | Development setup and guidelines                    |
-| [OpenAPI Spec](docs/reference/openapi.yaml)                           | OpenAPI 3.0 specification                           |
-| [Security Policy](SECURITY.md)                                        | Vulnerability reporting and security practices      |
-| [VM Deployment](docs/ops/VM_DEPLOYMENT_GUIDE.md)                      | Complete guide: VM + nginx + Cloudflare setup       |
-| [Features Gallery](docs/guides/FEATURES.md)                           | Visual dashboard tour with screenshots              |
-| [Release Checklist](docs/ops/RELEASE_CHECKLIST.md)                    | Pre-release validation steps                        |
-
----
-
-## 🗺️ Roadmap
-
-OmniRoute has **218+ features planned** across multiple development phases. Here are the key areas:
-
-| Category                      | Planned Features | Highlights                                                                                            |
-| ----------------------------- | ---------------- | ----------------------------------------------------------------------------------------------------- |
-| 🧠 **Routing & Intelligence** | 25+              | Lowest-latency routing, tag-based routing, quota preflight, quota-aware P2C, step-based combo routing |
-| 🔒 **Security & Compliance**  | 20+              | SSRF hardening, credential cloaking, rate-limit per endpoint, management key scoping                  |
-| 📊 **Observability**          | 15+              | OpenTelemetry integration, real-time quota monitoring, combo target health, cost tracking per model   |
-| 🔄 **Provider Integrations**  | 20+              | Dynamic model registry, provider cooldowns, multi-account Codex, Copilot quota parsing                |
-| ⚡ **Performance**            | 15+              | Dual cache layer, prompt cache, response cache, streaming keepalive, batch API                        |
-| 🌐 **Ecosystem**              | 10+              | WebSocket API, config hot-reload, distributed config store, commercial mode                           |
-
-### 🔜 Coming Soon
-
-- 🔗 **OpenCode Integration** — Native provider support for the OpenCode AI coding IDE
-- 🔗 **TRAE Integration** — Full support for the TRAE AI development framework
-- 📦 **Batch API** — Asynchronous batch processing for bulk requests
-- 🎯 **Tag-Based Routing** — Route requests based on custom tags and metadata
-- 💰 **Lowest-Cost Strategy** — Automatically select the cheapest available provider
-
-> 📝 Full feature specifications available in [`docs/new-features/`](docs/new-features/) (217 detailed specs)
-
----
-
-## 👥 Contributors
-
-[![Contributors](https://contrib.rocks/image?repo=diegosouzapw/OmniRoute&max=100&columns=20&anon=1)](https://github.com/diegosouzapw/OmniRoute/graphs/contributors)
-
-### How to Contribute
-
-1. Fork the repository
-2. Create your feature branch (`git checkout -b feature/amazing-feature`)
-3. Commit your changes (`git commit -m 'Add amazing feature'`)
-4. Push to the branch (`git push origin feature/amazing-feature`)
-5. Open a Pull Request
-
-See [CONTRIBUTING.md](CONTRIBUTING.md) for detailed guidelines.
-
-### Releasing a New Version
-
-```bash
-# Create a release — npm publish happens automatically
-gh release create v2.0.0 --title "v2.0.0" --generate-notes
-```
-
----
-
-## 📊 Star History
-
-<a href="https://www.star-history.com/?repos=diegosouzapw%2Fomniroute&type=date&legend=top-left">
- <picture>
-   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/chart?repos=diegosouzapw/omniroute&type=date&theme=dark&legend=top-left" />
-   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/chart?repos=diegosouzapw/omniroute&type=date&legend=top-left" />
-   <img alt="Star History Chart" src="https://api.star-history.com/chart?repos=diegosouzapw/omniroute&type=date&legend=top-left" />
- </picture>
-</a>
-
-## 🌍 StarMapper
-
-<a href="https://starmapper.bruniaux.com/diegosouzapw/omniroute">
-  <picture>
-    <source media="(prefers-color-scheme: dark)" srcset="https://starmapper.bruniaux.com/api/map-image/diegosouzapw/omniroute?theme=dark" />
-    <source media="(prefers-color-scheme: light)" srcset="https://starmapper.bruniaux.com/api/map-image/diegosouzapw/omniroute?theme=light" />
-    <img alt="StarMapper" src="https://starmapper.bruniaux.com/api/map-image/diegosouzapw/omniroute" />
-  </picture>
-</a>
-
-## 🙏 Acknowledgments
-
-Special thanks to **[CLIProxyAPI](https://github.com/router-for-me/CLIProxyAPI)** — the original Go implementation that inspired this JavaScript port.
-
----
-
-## लाइसेंस
-
-MIT License - see [LICENSE](LICENSE) for details.
-
----
-
-<div align="center">
-  <sub>Built with ❤️ for developers who code 24/7</sub>
-  <br/>
-  <sub><a href="https://omniroute.online">omniroute.online</a></sub>
-</div>
-<!-- GitHub Discussions enabled for community Q&A -->
diff --git a/docs/i18n/in/SECURITY.md b/docs/i18n/in/SECURITY.md
deleted file mode 100644
index 5103197ee3..0000000000
--- a/docs/i18n/in/SECURITY.md
+++ /dev/null
@@ -1,179 +0,0 @@
-# Security Policy (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../SECURITY.md) · 🇪🇸 [es](../es/SECURITY.md) · 🇫🇷 [fr](../fr/SECURITY.md) · 🇩🇪 [de](../de/SECURITY.md) · 🇮🇹 [it](../it/SECURITY.md) · 🇷🇺 [ru](../ru/SECURITY.md) · 🇨🇳 [zh-CN](../zh-CN/SECURITY.md) · 🇯🇵 [ja](../ja/SECURITY.md) · 🇰🇷 [ko](../ko/SECURITY.md) · 🇸🇦 [ar](../ar/SECURITY.md) · 🇮🇳 [hi](../hi/SECURITY.md) · 🇮🇳 [in](../in/SECURITY.md) · 🇹🇭 [th](../th/SECURITY.md) · 🇻🇳 [vi](../vi/SECURITY.md) · 🇮🇩 [id](../id/SECURITY.md) · 🇲🇾 [ms](../ms/SECURITY.md) · 🇳🇱 [nl](../nl/SECURITY.md) · 🇵🇱 [pl](../pl/SECURITY.md) · 🇸🇪 [sv](../sv/SECURITY.md) · 🇳🇴 [no](../no/SECURITY.md) · 🇩🇰 [da](../da/SECURITY.md) · 🇫🇮 [fi](../fi/SECURITY.md) · 🇵🇹 [pt](../pt/SECURITY.md) · 🇷🇴 [ro](../ro/SECURITY.md) · 🇭🇺 [hu](../hu/SECURITY.md) · 🇧🇬 [bg](../bg/SECURITY.md) · 🇸🇰 [sk](../sk/SECURITY.md) · 🇺🇦 [uk-UA](../uk-UA/SECURITY.md) · 🇮🇱 [he](../he/SECURITY.md) · 🇵🇭 [phi](../phi/SECURITY.md) · 🇧🇷 [pt-BR](../pt-BR/SECURITY.md) · 🇨🇿 [cs](../cs/SECURITY.md) · 🇹🇷 [tr](../tr/SECURITY.md)
-
----
-
-## Reporting Vulnerabilities
-
-If you discover a security vulnerability in OmniRoute, please report it responsibly:
-
-1. **DO NOT** open a public GitHub issue
-2. Use [GitHub Security Advisories](https://github.com/diegosouzapw/OmniRoute/security/advisories/new)
-3. Include: description, reproduction steps, and potential impact
-
-## Response Timeline
-
-| Stage               | Target                      |
-| ------------------- | --------------------------- |
-| Acknowledgment      | 48 hours                    |
-| Triage & Assessment | 5 business days             |
-| Patch Release       | 14 business days (critical) |
-
-## Supported Versions
-
-| Version | Support Status |
-| ------- | -------------- |
-| 3.6.x   | ✅ Active      |
-| 3.5.x   | ✅ Security    |
-| < 3.5.0 | ❌ Unsupported |
-
----
-
-## Security Architecture
-
-OmniRoute implements a multi-layered security model:
-
-```
-Request → CORS → API Key Auth → Prompt Injection Guard → Input Sanitizer → Rate Limiter → Circuit Breaker → Provider
-```
-
-### 🔐 Authentication & Authorization
-
-| Feature              | Implementation                                             |
-| -------------------- | ---------------------------------------------------------- |
-| **Dashboard Login**  | Password-based auth with JWT tokens (HttpOnly cookies)     |
-| **API Key Auth**     | HMAC-signed keys with CRC validation                       |
-| **OAuth 2.0 + PKCE** | Secure provider auth (Claude, Codex, Gemini, Cursor, etc.) |
-| **Token Refresh**    | Automatic OAuth token refresh before expiry                |
-| **Secure Cookies**   | `AUTH_COOKIE_SECURE=true` for HTTPS environments           |
-| **MCP Scopes**       | 32 granular scopes for MCP tool access control             |
-
-### 🛡️ Encryption at Rest
-
-All sensitive data stored in SQLite is encrypted using **AES-256-GCM** with scrypt key derivation:
-
-- API keys, access tokens, refresh tokens, and ID tokens
-- Versioned format: `enc:v1:<iv>:<ciphertext>:<authTag>`
-- Passthrough mode (plaintext) when `STORAGE_ENCRYPTION_KEY` is not set
-
-```bash
-# Generate encryption key:
-STORAGE_ENCRYPTION_KEY=$(openssl rand -hex 32)
-```
-
-### 🧠 Prompt Injection Guard
-
-Middleware that detects and blocks prompt injection attacks in LLM requests:
-
-| Pattern Type        | Severity | Example                                        |
-| ------------------- | -------- | ---------------------------------------------- |
-| System Override     | High     | "ignore all previous instructions"             |
-| Role Hijack         | High     | "you are now DAN, you can do anything"         |
-| Delimiter Injection | Medium   | Encoded separators to break context boundaries |
-| DAN/Jailbreak       | High     | Known jailbreak prompt patterns                |
-| Instruction Leak    | Medium   | "show me your system prompt"                   |
-
-Configure via dashboard (Settings → Security) or `.env`:
-
-```env
-INPUT_SANITIZER_ENABLED=true
-INPUT_SANITIZER_MODE=block    # warn | block | redact
-```
-
-### 🔒 PII Redaction
-
-Automatic detection and optional redaction of personally identifiable information:
-
-| PII Type      | Pattern               | Replacement        |
-| ------------- | --------------------- | ------------------ |
-| Email         | `user@domain.com`     | `[EMAIL_REDACTED]` |
-| CPF (Brazil)  | `123.456.789-00`      | `[CPF_REDACTED]`   |
-| CNPJ (Brazil) | `12.345.678/0001-00`  | `[CNPJ_REDACTED]`  |
-| Credit Card   | `4111-1111-1111-1111` | `[CC_REDACTED]`    |
-| Phone         | `+55 11 99999-9999`   | `[PHONE_REDACTED]` |
-| SSN (US)      | `123-45-6789`         | `[SSN_REDACTED]`   |
-
-```env
-PII_REDACTION_ENABLED=true
-```
-
-### 🌐 Network Security
-
-| Feature                  | Description                                                      |
-| ------------------------ | ---------------------------------------------------------------- |
-| **CORS**                 | Configurable origin control (`CORS_ORIGIN` env var, default `*`) |
-| **IP Filtering**         | Allowlist/blocklist IP ranges in dashboard                       |
-| **Rate Limiting**        | Per-provider rate limits with automatic backoff                  |
-| **Anti-Thundering Herd** | Mutex + per-connection locking prevents cascading 502s           |
-| **TLS Fingerprint**      | Browser-like TLS fingerprint spoofing to reduce bot detection    |
-| **CLI Fingerprint**      | Per-provider header/body ordering to match native CLI signatures |
-
-### 🔌 Resilience & Availability
-
-| Feature                 | Description                                                        |
-| ----------------------- | ------------------------------------------------------------------ |
-| **Circuit Breaker**     | 3-state (Closed → Open → Half-Open) per provider, SQLite-persisted |
-| **Request Idempotency** | 5-second dedup window for duplicate requests                       |
-| **Exponential Backoff** | Automatic retry with increasing delays                             |
-| **Health Dashboard**    | Real-time provider health monitoring                               |
-
-### 📋 Compliance
-
-| Feature            | Description                                                 |
-| ------------------ | ----------------------------------------------------------- |
-| **Log Retention**  | Automatic cleanup after `CALL_LOG_RETENTION_DAYS`           |
-| **No-Log Opt-out** | Per API key `noLog` flag disables request logging           |
-| **Audit Log**      | Administrative actions tracked in `audit_log` table         |
-| **MCP Audit**      | SQLite-backed audit logging for all MCP tool calls          |
-| **Zod Validation** | All API inputs validated with Zod v4 schemas at module load |
-
----
-
-## Required Environment Variables
-
-All secrets must be set before starting the server. The server will **fail fast** if they are missing or weak.
-
-```bash
-# REQUIRED — server will not start without these:
-JWT_SECRET=$(openssl rand -base64 48)     # min 32 chars
-API_KEY_SECRET=$(openssl rand -hex 32)    # min 16 chars
-
-# RECOMMENDED — enables encryption at rest:
-STORAGE_ENCRYPTION_KEY=$(openssl rand -hex 32)
-```
-
-The server actively rejects known-weak values like `changeme`, `secret`, or `password`.
-
----
-
-## Docker Security
-
-- Use non-root user in production
-- Mount secrets as read-only volumes
-- Never copy `.env` files into Docker images
-- Use `.dockerignore` to exclude sensitive files
-- Set `AUTH_COOKIE_SECURE=true` when behind HTTPS
-
-```bash
-docker run -d \
-  --name omniroute \
-  --restart unless-stopped \
-  --read-only \
-  -p 20128:20128 \
-  -v omniroute-data:/app/data \
-  -e JWT_SECRET="$(openssl rand -base64 48)" \
-  -e API_KEY_SECRET="$(openssl rand -hex 32)" \
-  -e STORAGE_ENCRYPTION_KEY="$(openssl rand -hex 32)" \
-  diegosouzapw/omniroute:latest
-```
-
----
-
-## Dependencies
-
-- Run `npm audit` regularly
-- Keep dependencies updated
-- The project uses `husky` + `lint-staged` for pre-commit checks
-- CI pipeline runs ESLint security rules on every push
-- Provider constants validated at module load via Zod (`src/shared/validation/providerSchema.ts`)
diff --git a/docs/i18n/in/docs/architecture/ARCHITECTURE.md b/docs/i18n/in/docs/architecture/ARCHITECTURE.md
deleted file mode 100644
index 78322e2ec7..0000000000
--- a/docs/i18n/in/docs/architecture/ARCHITECTURE.md
+++ /dev/null
@@ -1,889 +0,0 @@
-# OmniRoute Architecture (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../../docs/ARCHITECTURE.md) · 🇪🇸 [es](../../es/docs/ARCHITECTURE.md) · 🇫🇷 [fr](../../fr/docs/ARCHITECTURE.md) · 🇩🇪 [de](../../de/docs/ARCHITECTURE.md) · 🇮🇹 [it](../../it/docs/ARCHITECTURE.md) · 🇷🇺 [ru](../../ru/docs/ARCHITECTURE.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/ARCHITECTURE.md) · 🇯🇵 [ja](../../ja/docs/ARCHITECTURE.md) · 🇰🇷 [ko](../../ko/docs/ARCHITECTURE.md) · 🇸🇦 [ar](../../ar/docs/ARCHITECTURE.md) · 🇮🇳 [hi](../../hi/docs/ARCHITECTURE.md) · 🇮🇳 [in](../../in/docs/ARCHITECTURE.md) · 🇹🇭 [th](../../th/docs/ARCHITECTURE.md) · 🇻🇳 [vi](../../vi/docs/ARCHITECTURE.md) · 🇮🇩 [id](../../id/docs/ARCHITECTURE.md) · 🇲🇾 [ms](../../ms/docs/ARCHITECTURE.md) · 🇳🇱 [nl](../../nl/docs/ARCHITECTURE.md) · 🇵🇱 [pl](../../pl/docs/ARCHITECTURE.md) · 🇸🇪 [sv](../../sv/docs/ARCHITECTURE.md) · 🇳🇴 [no](../../no/docs/ARCHITECTURE.md) · 🇩🇰 [da](../../da/docs/ARCHITECTURE.md) · 🇫🇮 [fi](../../fi/docs/ARCHITECTURE.md) · 🇵🇹 [pt](../../pt/docs/ARCHITECTURE.md) · 🇷🇴 [ro](../../ro/docs/ARCHITECTURE.md) · 🇭🇺 [hu](../../hu/docs/ARCHITECTURE.md) · 🇧🇬 [bg](../../bg/docs/ARCHITECTURE.md) · 🇸🇰 [sk](../../sk/docs/ARCHITECTURE.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/ARCHITECTURE.md) · 🇮🇱 [he](../../he/docs/ARCHITECTURE.md) · 🇵🇭 [phi](../../phi/docs/ARCHITECTURE.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/ARCHITECTURE.md) · 🇨🇿 [cs](../../cs/docs/ARCHITECTURE.md) · 🇹🇷 [tr](../../tr/docs/ARCHITECTURE.md)
-
----
-
-_Last updated: 2026-04-15_
-
-## Executive Summary
-
-OmniRoute is a local AI routing gateway and dashboard built on Next.js.
-It provides a single OpenAI-compatible endpoint (`/v1/*`) and routes traffic across multiple upstream providers with translation, fallback, token refresh, and usage tracking.
-
-Core capabilities:
-
-- OpenAI-compatible API surface for CLI/tools (329 provider catalog entries, 89 executor implementation modules)
-- Request/response translation across provider formats
-- Model combo fallback (multi-model sequence)
-- Structured combo steps (`provider + model + connection`) with runtime ordering by `compositeTiers`
-- Account-level fallback (multi-account per provider)
-- Quota preflight and quota-aware P2C account selection in the main chat path
-- OAuth + API-key provider connection management (23 OAuth catalog entries backed by 21 provider modules)
-- Embedding generation via `/v1/embeddings` (6 providers, 9 models)
-- Image generation via `/v1/images/generations` (10+ providers, 20+ models)
-- Audio transcription via `/v1/audio/transcriptions` (7 providers)
-- Text-to-speech via `/v1/audio/speech` (10 providers)
-- Video generation via `/v1/videos/generations` (ComfyUI + SD WebUI)
-- Music generation via `/v1/music/generations` (ComfyUI)
-- Web search via `/v1/search` (12 providers)
-- Moderations via `/v1/moderations`
-- Reranking via `/v1/rerank`
-- Think tag parsing (`<think>...</think>`) for reasoning models
-- Response sanitization for strict OpenAI SDK compatibility
-- Role normalization (developer→system, system→user) for cross-provider compatibility
-- Structured output conversion (json_schema → Gemini responseSchema)
-- Local persistence for providers, keys, aliases, combos, settings, pricing (110 top-level DB modules)
-- Usage/cost tracking and request logging
-- Optional cloud sync for multi-device/state sync
-- IP allowlist/blocklist for API access control
-- Thinking budget management (passthrough/auto/custom/adaptive)
-- Global system prompt injection
-- Session tracking and fingerprinting
-- Per-account enhanced rate limiting with provider-specific profiles
-- Circuit breaker pattern for provider resilience
-- Anti-thundering herd protection with mutex locking
-- Signature-based request deduplication cache
-- Domain layer: model availability, cost rules, fallback policy, lockout policy
-- Context Relay: session handoff summaries for account rotation continuity
-- Domain state persistence (SQLite write-through cache for fallbacks, budgets, lockouts, circuit breakers)
-- Policy engine for centralized request evaluation (lockout → budget → fallback)
-- Request telemetry with p50/p95/p99 latency aggregation
-- Combo target telemetry and historical combo target health via `combo_execution_key` / `combo_step_id`
-- Correlation ID (X-Request-Id) for end-to-end tracing
-- Compliance audit logging with opt-out per API key
-- Eval framework for LLM quality assurance
-- Resilience UI dashboard with real-time circuit breaker status
-- MCP Server (107 unique tools, 32 scopes) with 3 transports (stdio/SSE/Streamable HTTP)
-- A2A Server (JSON-RPC 2.0 + SSE) with skills and task lifecycle
-- Memory system (extraction, injection, retrieval, summarization)
-- Skills system (registry, executor, sandbox, built-in skills)
-- MITM proxy with certificate management and DNS handling
-- Prompt injection guard middleware
-- ACP (Agent Communication Protocol) registry
-- Modular OAuth providers (21 implementation modules under `src/lib/oauth/providers/`)
-- Uninstall/full-uninstall scripts
-- OAuth environment repair action
-- WebSocket bridge for OpenAI-compatible WS clients (`/v1/ws`)
-- Sync token management (issue/revoke, ETag-versioned config bundle download)
-- GLM Thinking (`glmt`) first-class provider preset
-- Hybrid token counting (provider-side `/messages/count_tokens` with estimation fallback)
-- Model alias auto-seeding (30+ cross-proxy dialect normalizations at startup)
-- Safe outbound fetch with SSRF guard, private URL blocking, and configurable retry
-- Cooldown-aware chat retries with configurable `requestRetry` and `maxRetryIntervalSec`
-- Runtime environment validation with Zod at startup
-- Compliance audit v2 with pagination, provider CRUD events, and SSRF-blocked validation logging
-
-Primary runtime model:
-
-- Next.js app routes under `src/app/api/*` implement both dashboard APIs and compatibility APIs
-- A shared SSE/routing core in `src/sse/*` + `open-sse/*` handles provider execution, translation, streaming, fallback, and usage
-
-## Scope and Boundaries
-
-### In Scope
-
-- Local gateway runtime
-- Dashboard management APIs
-- Provider authentication and token refresh
-- Request translation and SSE streaming
-- Local state + usage persistence
-- Optional cloud sync orchestration
-
-### Out of Scope
-
-- Cloud service implementation behind `NEXT_PUBLIC_CLOUD_URL`
-- Provider SLA/control plane outside local process
-- External CLI binaries themselves (Claude CLI, Codex CLI, etc.)
-
-## Dashboard Surface (Current)
-
-Main pages under `src/app/(dashboard)/dashboard/`:
-
-- `/dashboard` — quick start + provider overview
-- `/dashboard/endpoint` — endpoint proxy + MCP + A2A + API endpoint tabs
-- `/dashboard/providers` — provider connections and credentials
-- `/dashboard/combos` — combo strategies, templates, step-based builder, model routing rules, manual persisted ordering
-- `/dashboard/costs` — cost aggregation and pricing visibility
-- `/dashboard/analytics` — usage analytics, evaluations, combo target health
-- `/dashboard/limits` — quota/rate controls
-- `/dashboard/cli-tools` — CLI onboarding, runtime detection, config generation
-- `/dashboard/agents` — detected ACP agents + custom agent registration
-- `/dashboard/media` — image/video/music playground
-- `/dashboard/search-tools` — search provider testing and history
-- `/dashboard/health` — uptime, circuit breakers, rate limits, quota-monitored sessions
-- `/dashboard/logs` — request/proxy/audit/console logs
-- `/dashboard/settings` — system settings tabs (general, routing, combo defaults, etc.)
-- `/dashboard/api-manager` — API key lifecycle and model permissions
-
-## High-Level System Context
-
-```mermaid
-flowchart LR
-    subgraph Clients[Developer Clients]
-        C1[Claude Code]
-        C2[Codex CLI]
-        C3[OpenClaw / Droid / Cline / Continue / Roo]
-        C4[Custom OpenAI-compatible clients]
-        BROWSER[Browser Dashboard]
-    end
-
-    subgraph Router[OmniRoute Local Process]
-        API[V1 Compatibility API\n/v1/*]
-        DASH[Dashboard + Management API\n/api/*]
-        CORE[SSE + Translation Core\nopen-sse + src/sse]
-        DB[(storage.sqlite)]
-        UDB[(usage tables + log artifacts)]
-    end
-
-    subgraph Upstreams[Upstream Providers]
-        P1[OAuth Providers\nClaude/Codex/Gemini/Qwen/Qoder/GitHub/Kiro/Cursor/Antigravity]
-        P2[API Key Providers\nOpenAI/Anthropic/OpenRouter/GLM/Kimi/MiniMax\nDeepSeek/Groq/xAI/Mistral/Perplexity\nTogether/Fireworks/Cerebras/Cohere/NVIDIA]
-        P3[Compatible Nodes\nOpenAI-compatible / Anthropic-compatible]
-    end
-
-    subgraph Cloud[Optional Cloud Sync]
-        CLOUD[Cloud Sync Endpoint\nNEXT_PUBLIC_CLOUD_URL]
-    end
-
-    C1 --> API
-    C2 --> API
-    C3 --> API
-    C4 --> API
-    BROWSER --> DASH
-
-    API --> CORE
-    DASH --> DB
-    CORE --> DB
-    CORE --> UDB
-
-    CORE --> P1
-    CORE --> P2
-    CORE --> P3
-
-    DASH --> CLOUD
-```
-
-## Core Runtime Components
-
-## 1) API and Routing Layer (Next.js App Routes)
-
-Main directories:
-
-- `src/app/api/v1/*` and `src/app/api/v1beta/*` for compatibility APIs
-- `src/app/api/*` for management/configuration APIs
-- Next rewrites in `next.config.mjs` map `/v1/*` to `/api/v1/*`
-
-Important compatibility routes:
-
-- `src/app/api/v1/chat/completions/route.ts`
-- `src/app/api/v1/messages/route.ts`
-- `src/app/api/v1/responses/route.ts`
-- `src/app/api/v1/models/route.ts` — includes custom models with `custom: true`
-- `src/app/api/v1/embeddings/route.ts` — embedding generation (6 providers)
-- `src/app/api/v1/images/generations/route.ts` — image generation (4+ providers incl. Antigravity/Nebius)
-- `src/app/api/v1/messages/count_tokens/route.ts`
-- `src/app/api/v1/providers/[provider]/chat/completions/route.ts` — dedicated per-provider chat
-- `src/app/api/v1/providers/[provider]/embeddings/route.ts` — dedicated per-provider embeddings
-- `src/app/api/v1/providers/[provider]/images/generations/route.ts` — dedicated per-provider images
-- `src/app/api/v1beta/models/route.ts`
-- `src/app/api/v1beta/models/[...path]/route.ts`
-
-Management domains:
-
-- Auth/settings: `src/app/api/auth/*`, `src/app/api/settings/*`
-- Providers/connections: `src/app/api/providers*`
-- Provider nodes: `src/app/api/provider-nodes*`
-- Custom models: `src/app/api/provider-models` (GET/POST/DELETE)
-- Model catalog: `src/app/api/models/route.ts` (GET)
-- Proxy config: `src/app/api/settings/proxy` (GET/PUT/DELETE) + `src/app/api/settings/proxy/test` (POST)
-- OAuth: `src/app/api/oauth/*`
-- Keys/aliases/combos/pricing: `src/app/api/keys*`, `src/app/api/models/alias`, `src/app/api/combos*`, `src/app/api/pricing`
-- Usage: `src/app/api/usage/*`
-- Sync/cloud: `src/app/api/sync/*`, `src/app/api/cloud/*`
-- CLI tooling helpers: `src/app/api/cli-tools/*`
-- IP filter: `src/app/api/settings/ip-filter` (GET/PUT)
-- Thinking budget: `src/app/api/settings/thinking-budget` (GET/PUT)
-- System prompt: `src/app/api/settings/system-prompt` (GET/PUT)
-- Sessions: `src/app/api/sessions` (GET)
-- Rate limits: `src/app/api/rate-limits` (GET)
-- Resilience: `src/app/api/resilience` (GET/PATCH) — provider profiles, circuit breaker, rate limit state
-- Resilience reset: `src/app/api/resilience/reset` (POST) — reset breakers + cooldowns
-- Cache stats: `src/app/api/cache/stats` (GET/DELETE)
-- Model availability: `src/app/api/models/availability` (GET/POST)
-- Telemetry: `src/app/api/telemetry/summary` (GET)
-- Budget: `src/app/api/usage/budget` (GET/POST)
-- Fallback chains: `src/app/api/fallback/chains` (GET/POST/DELETE)
-- Compliance audit: `src/app/api/compliance/audit-log` (GET, with pagination + structured metadata)
-- Evals: `src/app/api/evals` (GET/POST), `src/app/api/evals/[suiteId]` (GET)
-- Policies: `src/app/api/policies` (GET/POST)
-- Sync tokens: `src/app/api/sync/tokens` (GET/POST), `src/app/api/sync/tokens/[id]` (GET/DELETE)
-- Config bundle: `src/app/api/sync/bundle` (GET, ETag-versioned snapshot of settings/providers/combos/keys)
-- WebSocket: `src/app/api/v1/ws/route.ts` — Upgrade handler for OpenAI-compatible WS clients
-
-## 2) SSE + Translation Core
-
-Main flow modules:
-
-- Entry: `src/sse/handlers/chat.ts`
-- Core orchestration: `open-sse/handlers/chatCore.ts`
-- Provider execution adapters: `open-sse/executors/*`
-- Format detection/provider config: `open-sse/services/provider.ts`
-- Model parse/resolve: `src/sse/services/model.ts`, `open-sse/services/model.ts`
-- Account fallback logic: `open-sse/services/accountFallback.ts`
-- Translation registry: `open-sse/translator/index.ts`
-- Stream transformations: `open-sse/utils/stream.ts`, `open-sse/utils/streamHandler.ts`
-- Usage extraction/normalization: `open-sse/utils/usageTracking.ts`
-- Think tag parser: `open-sse/utils/thinkTagParser.ts`
-- Embedding handler: `open-sse/handlers/embeddings.ts`
-- Embedding provider registry: `open-sse/config/embeddingRegistry.ts`
-- Image generation handler: `open-sse/handlers/imageGeneration.ts`
-- Image provider registry: `open-sse/config/imageRegistry.ts`
-- Response sanitization: `open-sse/handlers/responseSanitizer.ts`
-- Role normalization: `open-sse/services/roleNormalizer.ts`
-
-Services (business logic):
-
-- Account selection/scoring: `open-sse/services/accountSelector.ts`
-- Context lifecycle management: `open-sse/services/contextManager.ts`
-- IP filter enforcement: `open-sse/services/ipFilter.ts`
-- Session tracking: `open-sse/services/sessionManager.ts`
-- Request deduplication: `open-sse/services/signatureCache.ts`
-- System prompt injection: `open-sse/services/systemPrompt.ts`
-- Thinking budget management: `open-sse/services/thinkingBudget.ts`
-- Wildcard model routing: `open-sse/services/wildcardRouter.ts`
-- Rate limit management: `open-sse/services/rateLimitManager.ts`
-- Circuit breaker: `open-sse/services/circuitBreaker.ts`
-- Context handoff: `open-sse/services/contextHandoff.ts` — handoff summary generation and injection for context-relay strategy
-- Codex quota fetcher: `open-sse/services/codexQuotaFetcher.ts` — fetches Codex quota for context-relay handoff decisions
-- Cooldown-aware retry: `src/sse/services/cooldownAwareRetry.ts` — per-model cooldown retries with configurable `requestRetry` / `maxRetryIntervalSec`
-- Safe outbound fetch: `src/shared/network/safeOutboundFetch.ts` — guarded provider/model fetch with SSRF guard, private-URL blocking, retry, and timeout
-- Outbound URL guard: `src/shared/network/outboundUrlGuard.ts` — validates provider URLs against private/localhost CIDR ranges
-- Provider request defaults: `open-sse/services/providerRequestDefaults.ts` — provider-level `maxTokens`, `temperature`, `thinkingBudgetTokens` defaults
-- GLM provider constants: `open-sse/config/glmProvider.ts` — shared GLM models, quota URLs, GLMT timeout/defaults
-- Antigravity upstream: `open-sse/config/antigravityUpstream.ts` — base URL and discovery path constants
-- Codex client constants: `open-sse/config/codexClient.ts` — versioned user-agent and client-version values
-- Model alias seed: `src/lib/modelAliasSeed.ts` — seeds 30+ cross-proxy dialect aliases at startup
-
-Domain layer modules:
-
-- Model availability: `src/lib/domain/modelAvailability.ts`
-- Cost rules/budgets: `src/lib/domain/costRules.ts`
-- Fallback policy: `src/lib/domain/fallbackPolicy.ts`
-- Combo resolver: `src/lib/domain/comboResolver.ts`
-- Lockout policy: `src/lib/domain/lockoutPolicy.ts`
-- Policy engine: `src/domain/policyEngine.ts` — centralized lockout → budget → fallback evaluation
-- Error codes catalog: `src/lib/domain/errorCodes.ts`
-- Request ID: `src/lib/domain/requestId.ts`
-- Fetch timeout: `src/lib/domain/fetchTimeout.ts`
-- Request telemetry: `src/lib/domain/requestTelemetry.ts`
-- Compliance/audit: `src/lib/domain/compliance/index.ts`
-- Eval runner: `src/lib/domain/evalRunner.ts`
-- Domain state persistence: `src/lib/db/domainState.ts` — SQLite CRUD for fallback chains, budgets, cost history, lockout state, circuit breakers
-
-OAuth provider modules (21 implementation modules under `src/lib/oauth/providers/`):
-
-- Registry index: `src/lib/oauth/providers/index.ts`
-- Individual providers: `claude.ts`, `codex.ts`, `gemini.ts`, `antigravity.ts`, `qoder.ts`, `qwen.ts`, `kimi-coding.ts`, `github.ts`, `kiro.ts`, `cursor.ts`, `kilocode.ts`, `cline.ts`
-- Thin wrapper: `src/lib/oauth/providers.ts` — re-exports from individual modules
-
-## 3) Persistence Layer
-
-Primary state DB (SQLite):
-
-- Core infra: `src/lib/db/core.ts` (better-sqlite3, migrations, WAL)
-- Re-export facade: `src/lib/localDb.ts` (thin compatibility layer for callers)
-- file: `${DATA_DIR}/storage.sqlite` (or `$XDG_CONFIG_HOME/omniroute/storage.sqlite` when set, else `~/.omniroute/storage.sqlite`)
-- entities (tables + KV namespaces): providerConnections, providerNodes, modelAliases, combos, apiKeys, settings, pricing, **customModels**, **proxyConfig**, **ipFilter**, **thinkingBudget**, **systemPrompt**
-
-Usage persistence:
-
-- facade: `src/lib/usageDb.ts` (decomposed modules in `src/lib/usage/*`)
-- SQLite tables in `storage.sqlite`: `usage_history`, `call_logs`, `proxy_logs`
-- optional file artifacts remain for compatibility/debug (`${DATA_DIR}/log.txt`, `${DATA_DIR}/call_logs/`, `<repo>/logs/...`)
-- legacy JSON files are migrated to SQLite by startup migrations when present
-
-Domain State DB (SQLite):
-
-- `src/lib/db/domainState.ts` — CRUD operations for domain state
-- Tables (created in `src/lib/db/core.ts`): `domain_fallback_chains`, `domain_budgets`, `domain_cost_history`, `domain_lockout_state`, `domain_circuit_breakers`
-- Write-through cache pattern: in-memory Maps are authoritative at runtime; mutations are written synchronously to SQLite; state is restored from DB on cold start
-
-## 4) Auth + Security Surfaces
-
-- Dashboard cookie auth: `src/proxy.ts`, `src/app/api/auth/login/route.ts`
-- API key generation/verification: `src/shared/utils/apiKey.ts`
-- Provider secrets persisted in `providerConnections` entries
-- Outbound proxy support via `open-sse/utils/proxyFetch.ts` (env vars) and `open-sse/utils/networkProxy.ts` (configurable per-provider or global)
-- SSRF / outbound URL guard: `src/shared/network/outboundUrlGuard.ts` — blocks private/loopback/link-local ranges for all provider calls
-- Runtime env validation: `src/lib/env/runtimeEnv.ts` — Zod schema for all environment variables, surfaced as startup errors/warnings
-- Sync tokens: `src/lib/db/syncTokens.ts` — scoped tokens for config bundle download endpoints; backed by `sync_tokens` SQLite table (migration `024_create_sync_tokens.sql`)
-- WebSocket handshake auth: `src/lib/ws/handshake.ts` — validates WS upgrade requests via API key or session cookie
-
-## 5) Cloud Sync
-
-- Scheduler init: `src/lib/initCloudSync.ts`, `src/shared/services/initializeCloudSync.ts`, `src/shared/services/modelSyncScheduler.ts`
-- Periodic task: `src/shared/services/cloudSyncScheduler.ts`
-- Periodic task: `src/shared/services/modelSyncScheduler.ts`
-- Control route: `src/app/api/sync/cloud/route.ts`
-
-## Request Lifecycle (`/v1/chat/completions`)
-
-```mermaid
-sequenceDiagram
-    autonumber
-    participant Client as CLI/SDK Client
-    participant Route as /api/v1/chat/completions
-    participant Chat as src/sse/handlers/chat
-    participant Core as open-sse/handlers/chatCore
-    participant Model as Model Resolver
-    participant Auth as Credential Selector
-    participant Exec as Provider Executor
-    participant Prov as Upstream Provider
-    participant Stream as Stream Translator
-    participant Usage as usageDb
-
-    Client->>Route: POST /v1/chat/completions
-    Route->>Chat: handleChat(request)
-    Chat->>Model: parse/resolve model or combo
-
-    alt Combo model
-        Chat->>Chat: iterate combo models (handleComboChat)
-    end
-
-    Chat->>Auth: getProviderCredentials(provider)
-    Auth-->>Chat: active account + tokens/api key
-
-    Chat->>Core: handleChatCore(body, modelInfo, credentials)
-    Core->>Core: detect source format
-    Core->>Core: translate request to target format
-    Core->>Exec: execute(provider, transformedBody)
-    Exec->>Prov: upstream API call
-    Prov-->>Exec: SSE/JSON response
-    Exec-->>Core: response + metadata
-
-    alt 401/403
-        Core->>Exec: refreshCredentials()
-        Exec-->>Core: updated tokens
-        Core->>Exec: retry request
-    end
-
-    Core->>Stream: translate/normalize stream to client format
-    Stream-->>Client: SSE chunks / JSON response
-
-    Stream->>Usage: extract usage + persist history/log
-```
-
-## Combo + Account Fallback Flow
-
-```mermaid
-flowchart TD
-    A[Incoming model string] --> B{Is combo name?}
-    B -- Yes --> C[Load combo models sequence]
-    B -- No --> D[Single model path]
-
-    C --> E[Try model N]
-    E --> F[Resolve provider/model]
-    D --> F
-
-    F --> G[Select account credentials]
-    G --> H{Credentials available?}
-    H -- No --> I[Return provider unavailable]
-    H -- Yes --> J[Execute request]
-
-    J --> K{Success?}
-    K -- Yes --> L[Return response]
-    K -- No --> M{Fallback-eligible error?}
-
-    M -- No --> N[Return error]
-    M -- Yes --> O[Mark account unavailable cooldown]
-    O --> P{Another account for provider?}
-    P -- Yes --> G
-    P -- No --> Q{In combo with next model?}
-    Q -- Yes --> E
-    Q -- No --> R[Return all unavailable]
-```
-
-Fallback decisions are driven by `open-sse/services/accountFallback.ts` using status codes and error-message heuristics. Combo routing adds one extra guard: provider-scoped 400s such as upstream content-block and role-validation failures are treated as model-local failures so later combo targets can still run.
-
-## OAuth Onboarding and Token Refresh Lifecycle
-
-```mermaid
-sequenceDiagram
-    autonumber
-    participant UI as Dashboard UI
-    participant OAuth as /api/oauth/[provider]/[action]
-    participant ProvAuth as Provider Auth Server
-    participant DB as localDb
-    participant Test as /api/providers/[id]/test
-    participant Exec as Provider Executor
-
-    UI->>OAuth: GET authorize or device-code
-    OAuth->>ProvAuth: create auth/device flow
-    ProvAuth-->>OAuth: auth URL or device code payload
-    OAuth-->>UI: flow data
-
-    UI->>OAuth: POST exchange or poll
-    OAuth->>ProvAuth: token exchange/poll
-    ProvAuth-->>OAuth: access/refresh tokens
-    OAuth->>DB: createProviderConnection(oauth data)
-    OAuth-->>UI: success + connection id
-
-    UI->>Test: POST /api/providers/[id]/test
-    Test->>Exec: validate credentials / optional refresh
-    Exec-->>Test: valid or refreshed token info
-    Test->>DB: update status/tokens/errors
-    Test-->>UI: validation result
-```
-
-Refresh during live traffic is executed inside `open-sse/handlers/chatCore.ts` via executor `refreshCredentials()`.
-
-## Cloud Sync Lifecycle (Enable / Sync / Disable)
-
-```mermaid
-sequenceDiagram
-    autonumber
-    participant UI as Endpoint Page UI
-    participant Sync as /api/sync/cloud
-    participant DB as localDb
-    participant Cloud as External Cloud Sync
-    participant Claude as ~/.claude/settings.json
-
-    UI->>Sync: POST action=enable
-    Sync->>DB: set cloudEnabled=true
-    Sync->>DB: ensure API key exists
-    Sync->>Cloud: POST /sync/{machineId} (providers/aliases/combos/keys)
-    Cloud-->>Sync: sync result
-    Sync->>Cloud: GET /{machineId}/v1/verify
-    Sync-->>UI: enabled + verification status
-
-    UI->>Sync: POST action=sync
-    Sync->>Cloud: POST /sync/{machineId}
-    Cloud-->>Sync: remote data
-    Sync->>DB: update newer local tokens/status
-    Sync-->>UI: synced
-
-    UI->>Sync: POST action=disable
-    Sync->>DB: set cloudEnabled=false
-    Sync->>Cloud: DELETE /sync/{machineId}
-    Sync->>Claude: switch ANTHROPIC_BASE_URL back to local (if needed)
-    Sync-->>UI: disabled
-```
-
-Periodic sync is triggered by `CloudSyncScheduler` when cloud is enabled.
-
-## Data Model and Storage Map
-
-```mermaid
-erDiagram
-    SETTINGS ||--o{ PROVIDER_CONNECTION : controls
-    PROVIDER_NODE ||--o{ PROVIDER_CONNECTION : backs_compatible_provider
-    PROVIDER_CONNECTION ||--o{ USAGE_ENTRY : emits_usage
-
-    SETTINGS {
-      boolean cloudEnabled
-      number stickyRoundRobinLimit
-      boolean requireLogin
-      string password_hash
-      string fallbackStrategy
-      json rateLimitDefaults
-      json providerProfiles
-    }
-
-    PROVIDER_CONNECTION {
-      string id
-      string provider
-      string authType
-      string name
-      number priority
-      boolean isActive
-      string apiKey
-      string accessToken
-      string refreshToken
-      string expiresAt
-      string testStatus
-      string lastError
-      string rateLimitedUntil
-      json providerSpecificData
-    }
-
-    PROVIDER_NODE {
-      string id
-      string type
-      string name
-      string prefix
-      string apiType
-      string baseUrl
-    }
-
-    MODEL_ALIAS {
-      string alias
-      string targetModel
-    }
-
-    COMBO {
-      string id
-      string name
-      string[] models
-    }
-
-    API_KEY {
-      string id
-      string name
-      string key
-      string machineId
-    }
-
-    USAGE_ENTRY {
-      string provider
-      string model
-      number prompt_tokens
-      number completion_tokens
-      string connectionId
-      string timestamp
-    }
-
-    CUSTOM_MODEL {
-      string id
-      string name
-      string providerId
-    }
-
-    PROXY_CONFIG {
-      string global
-      json providers
-    }
-
-    IP_FILTER {
-      string mode
-      string[] allowlist
-      string[] blocklist
-    }
-
-    THINKING_BUDGET {
-      string mode
-      number customBudget
-      string effortLevel
-    }
-
-    SYSTEM_PROMPT {
-      boolean enabled
-      string prompt
-      string position
-    }
-```
-
-Physical storage files:
-
-- primary runtime DB: `${DATA_DIR}/storage.sqlite`
-- request log lines: `${DATA_DIR}/log.txt` (compat/debug artifact)
-- structured call payload archives: `${DATA_DIR}/call_logs/`
-- optional translator/request debug sessions: `<repo>/logs/...`
-
-## Deployment Topology
-
-```mermaid
-flowchart LR
-    subgraph LocalHost[Developer Host]
-        CLI[CLI Tools]
-        Browser[Dashboard Browser]
-    end
-
-    subgraph ContainerOrProcess[OmniRoute Runtime]
-        Next[Next.js Server\nPORT=20128]
-        Core[SSE Core + Executors]
-        MainDB[(storage.sqlite)]
-        UsageDB[(usage tables + log artifacts)]
-    end
-
-    subgraph External[External Services]
-        Providers[AI Providers]
-        SyncCloud[Cloud Sync Service]
-    end
-
-    CLI --> Next
-    Browser --> Next
-    Next --> Core
-    Next --> MainDB
-    Core --> MainDB
-    Core --> UsageDB
-    Core --> Providers
-    Next --> SyncCloud
-```
-
-## Module Mapping (Decision-Critical)
-
-### Route and API Modules
-
-- `src/app/api/v1/*`, `src/app/api/v1beta/*`: compatibility APIs
-- `src/app/api/v1/providers/[provider]/*`: dedicated per-provider routes (chat, embeddings, images)
-- `src/app/api/providers*`: provider CRUD, validation, testing
-- `src/app/api/provider-nodes*`: custom compatible node management
-- `src/app/api/provider-models`: custom model management (CRUD)
-- `src/app/api/models/route.ts`: model catalog API (aliases + custom models)
-- `src/app/api/oauth/*`: OAuth/device-code flows
-- `src/app/api/keys*`: local API key lifecycle
-- `src/app/api/models/alias`: alias management
-- `src/app/api/combos*`: fallback combo management
-- `src/app/api/pricing`: pricing overrides for cost calculation
-- `src/app/api/settings/proxy`: proxy configuration (GET/PUT/DELETE)
-- `src/app/api/settings/proxy/test`: outbound proxy connectivity test (POST)
-- `src/app/api/usage/*`: usage and logs APIs
-- `src/app/api/sync/*` + `src/app/api/cloud/*`: cloud sync and cloud-facing helpers
-- `src/app/api/cli-tools/*`: local CLI config writers/checkers
-- `src/app/api/settings/ip-filter`: IP allowlist/blocklist (GET/PUT)
-- `src/app/api/settings/thinking-budget`: thinking token budget config (GET/PUT)
-- `src/app/api/settings/system-prompt`: global system prompt (GET/PUT)
-- `src/app/api/sessions`: active session listing (GET)
-- `src/app/api/rate-limits`: per-account rate limit status (GET)
-- `src/app/api/sync/tokens`: sync token CRUD (GET/POST)
-- `src/app/api/sync/tokens/[id]`: sync token get/delete (GET/DELETE)
-- `src/app/api/sync/bundle`: config bundle download (GET, ETag versioning)
-- `src/app/api/v1/ws`: WebSocket upgrade handler for OpenAI-compatible WS clients
-
-### Routing and Execution Core
-
-- `src/sse/handlers/chat.ts`: request parse, combo handling, account selection loop
-- `open-sse/handlers/chatCore.ts`: translation, executor dispatch, retry/refresh handling, stream setup
-- `open-sse/executors/*`: provider-specific network and format behavior
-
-### Translation Registry and Format Converters
-
-- `open-sse/translator/index.ts`: translator registry and orchestration
-- Request translators: `open-sse/translator/request/*`
-- Response translators: `open-sse/translator/response/*`
-- Format constants: `open-sse/translator/formats.ts`
-
-### Persistence
-
-- `src/lib/db/*`: persistent config/state and domain persistence on SQLite
-- `src/lib/localDb.ts`: compatibility re-export for DB modules
-- `src/lib/usageDb.ts`: usage history/call logs facade on top of SQLite tables
-
-## Provider Executor Coverage (Strategy Pattern)
-
-Each provider has a specialized executor extending `BaseExecutor` (in `open-sse/executors/base.ts`), which provides URL building, header construction, retry with exponential backoff, credential refresh hooks, and the `execute()` orchestration method.
-
-| Executor               | Provider(s)                                                                                                                                                 | Special Handling                                                     |
-| ---------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------- |
-| `DefaultExecutor`      | OpenAI, Claude, Gemini, Qwen, OpenRouter, GLM, Kimi, MiniMax, DeepSeek, Groq, xAI, Mistral, Perplexity, Together, Fireworks, Cerebras, Cohere, NVIDIA, etc. | Dynamic URL/header config per provider                               |
-| `AntigravityExecutor`  | Google Antigravity                                                                                                                                          | Custom project/session IDs, Retry-After parsing                      |
-| `CliProxyApiExecutor`  | CLIProxyAPI-compatible providers                                                                                                                            | Custom auth and protocol handling                                    |
-| `CloudflareAiExecutor` | Cloudflare Workers AI                                                                                                                                       | Account ID injection, Neurons-based usage tracking                   |
-| `CodexExecutor`        | OpenAI Codex                                                                                                                                                | Injects system instructions, forces reasoning effort                 |
-| `CursorExecutor`       | Cursor IDE                                                                                                                                                  | ConnectRPC protocol, Protobuf encoding, request signing via checksum |
-| `GithubExecutor`       | GitHub Copilot                                                                                                                                              | Copilot token refresh, VSCode-mimicking headers                      |
-| `KiroExecutor`         | AWS CodeWhisperer/Kiro                                                                                                                                      | AWS EventStream binary format → SSE conversion                       |
-| `OpenCodeExecutor`     | OpenCode                                                                                                                                                    | AI SDK compatible provider setup                                     |
-| `PollinationsExecutor` | Pollinations AI                                                                                                                                             | No API key required, rate-limited requests                           |
-| `QoderExecutor`        | Qoder AI                                                                                                                                                    | PAT and OAuth support, multi-model free tier                         |
-| `VertexExecutor`       | Google Vertex AI                                                                                                                                            | Service account auth, region-based endpoints                         |
-
-All other providers (including custom compatible nodes) use the `DefaultExecutor`.
-
-## Provider Compatibility Matrix
-
-| Provider         | Format           | Auth                  | Stream           | Non-Stream | Token Refresh | Usage API          |
-| ---------------- | ---------------- | --------------------- | ---------------- | ---------- | ------------- | ------------------ |
-| Claude           | claude           | API Key / OAuth       | ✅               | ✅         | ✅            | ⚠️ Admin only      |
-| Gemini           | gemini           | API Key / OAuth       | ✅               | ✅         | ✅            | ⚠️ Cloud Console   |
-| Antigravity      | antigravity      | OAuth                 | ✅               | ✅         | ✅            | ✅ Full quota API  |
-| OpenAI           | openai           | API Key               | ✅               | ✅         | ❌            | ❌                 |
-| Codex            | openai-responses | OAuth                 | ✅ forced        | ❌         | ✅            | ✅ Rate limits     |
-| GitHub Copilot   | openai           | OAuth + Copilot Token | ✅               | ✅         | ✅            | ✅ Quota snapshots |
-| Cursor           | cursor           | Custom checksum       | ✅               | ✅         | ❌            | ❌                 |
-| Kiro             | kiro             | AWS SSO OIDC          | ✅ (EventStream) | ❌         | ✅            | ✅ Usage limits    |
-| Qwen             | openai           | OAuth                 | ✅               | ✅         | ✅            | ⚠️ Per request     |
-| Qoder            | openai           | OAuth / PAT           | ✅               | ✅         | ✅            | ⚠️ Per request     |
-| Kilo Code        | openai           | OAuth                 | ✅               | ✅         | ✅            | ❌                 |
-| Cline            | openai           | OAuth                 | ✅               | ✅         | ✅            | ❌                 |
-| Kimi Coding      | openai           | OAuth                 | ✅               | ✅         | ✅            | ❌                 |
-| OpenRouter       | openai           | API Key               | ✅               | ✅         | ❌            | ❌                 |
-| GLM/Kimi/MiniMax | claude           | API Key               | ✅               | ✅         | ❌            | ❌                 |
-| DeepSeek         | openai           | API Key               | ✅               | ✅         | ❌            | ❌                 |
-| Groq             | openai           | API Key               | ✅               | ✅         | ❌            | ❌                 |
-| xAI (Grok)       | openai           | API Key               | ✅               | ✅         | ❌            | ❌                 |
-| Mistral          | openai           | API Key               | ✅               | ✅         | ❌            | ❌                 |
-| Perplexity       | openai           | API Key               | ✅               | ✅         | ❌            | ❌                 |
-| Together AI      | openai           | API Key               | ✅               | ✅         | ❌            | ❌                 |
-| Fireworks AI     | openai           | API Key               | ✅               | ✅         | ❌            | ❌                 |
-| Cerebras         | openai           | API Key               | ✅               | ✅         | ❌            | ❌                 |
-| Cohere           | openai           | API Key               | ✅               | ✅         | ❌            | ❌                 |
-| NVIDIA NIM       | openai           | API Key               | ✅               | ✅         | ❌            | ❌                 |
-| Cloudflare AI    | openai           | API Token + Acct ID   | ✅               | ✅         | ❌            | ❌                 |
-| Pollinations     | openai           | None (no key)         | ✅               | ✅         | ❌            | ❌                 |
-| Scaleway AI      | openai           | API Key               | ✅               | ✅         | ❌            | ❌                 |
-| LongCat          | openai           | API Key               | ✅               | ✅         | ❌            | ❌                 |
-| Ollama Cloud     | openai           | API Key (optional)    | ✅               | ✅         | ❌            | ❌                 |
-| HuggingFace      | openai           | API Key               | ✅               | ✅         | ❌            | ❌                 |
-| Nebius           | openai           | API Key               | ✅               | ✅         | ❌            | ❌                 |
-| SiliconFlow      | openai           | API Key               | ✅               | ✅         | ❌            | ❌                 |
-| Hyperbolic       | openai           | API Key               | ✅               | ✅         | ❌            | ❌                 |
-| Vertex AI        | gemini           | Service Account       | ✅               | ✅         | ✅            | ⚠️ Cloud Console   |
-
-## Format Translation Coverage
-
-Detected source formats include:
-
-- `openai`
-- `openai-responses`
-- `claude`
-- `gemini`
-
-Target formats include:
-
-- OpenAI chat/Responses
-- Claude
-- Gemini/Antigravity envelope
-- Kiro
-- Cursor
-
-Translations use **OpenAI as the hub format** — all conversions go through OpenAI as intermediate:
-
-```
-Source Format → OpenAI (hub) → Target Format
-```
-
-Translations are selected dynamically based on source payload shape and provider target format.
-
-Additional processing layers in the translation pipeline:
-
-- **Response sanitization** — Strips non-standard fields from OpenAI-format responses (both streaming and non-streaming) to ensure strict SDK compliance
-- **Role normalization** — Converts `developer` → `system` for non-OpenAI targets; merges `system` → `user` for models that reject the system role (GLM, ERNIE)
-- **Think tag extraction** — Parses `<think>...</think>` blocks from content into `reasoning_content` field
-- **Structured output** — Converts OpenAI `response_format.json_schema` to Gemini's `responseMimeType` + `responseSchema`
-
-## Supported API Endpoints
-
-| Endpoint                                           | Format             | Handler                                                             |
-| -------------------------------------------------- | ------------------ | ------------------------------------------------------------------- |
-| `POST /v1/chat/completions`                        | OpenAI Chat        | `src/sse/handlers/chat.ts`                                          |
-| `POST /v1/messages`                                | Claude Messages    | Same handler (auto-detected)                                        |
-| `POST /v1/responses`                               | OpenAI Responses   | `open-sse/handlers/responsesHandler.ts`                             |
-| `POST /v1/embeddings`                              | OpenAI Embeddings  | `open-sse/handlers/embeddings.ts`                                   |
-| `GET /v1/embeddings`                               | Model listing      | API route                                                           |
-| `POST /v1/images/generations`                      | OpenAI Images      | `open-sse/handlers/imageGeneration.ts`                              |
-| `GET /v1/images/generations`                       | Model listing      | API route                                                           |
-| `POST /v1/providers/{provider}/chat/completions`   | OpenAI Chat        | Dedicated per-provider with model validation                        |
-| `POST /v1/providers/{provider}/embeddings`         | OpenAI Embeddings  | Dedicated per-provider with model validation                        |
-| `POST /v1/providers/{provider}/images/generations` | OpenAI Images      | Dedicated per-provider with model validation                        |
-| `POST /v1/messages/count_tokens`                   | Claude Token Count | API route                                                           |
-| `GET /v1/models`                                   | OpenAI Models list | API route (chat + embedding + image + custom models)                |
-| `GET /api/models/catalog`                          | Catalog            | All models grouped by provider + type                               |
-| `POST /v1beta/models/*:streamGenerateContent`      | Gemini native      | API route                                                           |
-| `GET/PUT/DELETE /api/settings/proxy`               | Proxy Config       | Network proxy configuration                                         |
-| `POST /api/settings/proxy/test`                    | Proxy Connectivity | Proxy health/connectivity test endpoint                             |
-| `GET/POST/DELETE /api/provider-models`             | Provider Models    | Provider model metadata backing custom and managed available models |
-
-## Bypass Handler
-
-The bypass handler (`open-sse/utils/bypassHandler.ts`) intercepts known "throwaway" requests from Claude CLI — warmup pings, title extractions, and token counts — and returns a **fake response** without consuming upstream provider tokens. This is triggered only when `User-Agent` contains `claude-cli`.
-
-## Request Logging and Artifacts
-
-The older file-based request logger (`open-sse/utils/requestLogger.ts`) is retained only for
-legacy compatibility. The current runtime contract uses:
-
-- `APP_LOG_TO_FILE=true` for application and audit logs written under `<repo>/logs/`
-- SQLite-backed call log records in `call_logs`
-- `${DATA_DIR}/call_logs/YYYY-MM-DD/...` artifacts when the call log pipeline is enabled
-
-## Failure Modes and Resilience
-
-## 1) Account/Provider Availability
-
-- provider account cooldown on transient/rate/auth errors
-- account fallback before failing request
-- combo model fallback when current model/provider path is exhausted
-
-## 2) Token Expiry
-
-- pre-check and refresh with retry for refreshable providers
-- 401/403 retry after refresh attempt in core path
-
-## 3) Stream Safety
-
-- disconnect-aware stream controller
-- translation stream with end-of-stream flush and `[DONE]` handling
-- usage estimation fallback when provider usage metadata is missing
-
-## 4) Cloud Sync Degradation
-
-- sync errors are surfaced but local runtime continues
-- scheduler has retry-capable logic, but periodic execution currently calls single-attempt sync by default
-
-## 5) Data Integrity
-
-- SQLite schema migrations and auto-upgrade hooks at startup
-- legacy JSON → SQLite migration compatibility path
-
-## 6) SSRF / Outbound URL Guard
-
-- `src/shared/network/outboundUrlGuard.ts` blocks all private/loopback/link-local target URLs before they reach provider executors
-- Provider model discovery and validation routes use `src/shared/network/safeOutboundFetch.ts` which applies the guard before every outbound request
-- Guard errors surface as `URL_GUARD_BLOCKED` with HTTP 422 and are logged to the compliance audit trail via `providerAudit.ts`
-
-## Observability and Operational Signals
-
-Runtime visibility sources:
-
-- console logs from `src/sse/utils/logger.ts`
-- per-request usage aggregates in SQLite (`usage_history`, `call_logs`, `proxy_logs`)
-- four-stage detailed payload captures in SQLite (`request_detail_logs`) when `settings.detailed_logs_enabled=true`
-- textual request status log in `log.txt` (optional/compat)
-- optional application log files under `logs/` when `APP_LOG_TO_FILE=true`
-- optional request artifacts under `${DATA_DIR}/call_logs/` when the call log pipeline is enabled
-- dashboard usage endpoints (`/api/usage/*`) for UI consumption
-
-Detailed request payload capture stores up to four JSON payload stages per routed call:
-
-- raw request received from the client
-- translated request actually sent upstream
-- provider response reconstructed as JSON; streamed responses are compacted to the final summary plus stream metadata
-- final client response returned by OmniRoute; streamed responses are stored in the same compact summary form
-
-## Security-Sensitive Boundaries
-
-- JWT secret (`JWT_SECRET`) secures dashboard session cookie verification/signing
-- Initial password bootstrap (`INITIAL_PASSWORD`) should be explicitly configured for first-run provisioning
-- API key HMAC secret (`API_KEY_SECRET`) secures generated local API key format
-- Provider secrets (API keys/tokens) are persisted in local DB and should be protected at filesystem level
-- Cloud sync endpoints rely on API key auth + machine id semantics
-
-## Environment and Runtime Matrix
-
-Environment variables actively used by code:
-
-- App/auth: `JWT_SECRET`, `INITIAL_PASSWORD`
-- Storage: `DATA_DIR`
-- Compatible node behavior: `ALLOW_MULTI_CONNECTIONS_PER_COMPAT_NODE`
-- Optional storage base override (Linux/macOS when `DATA_DIR` unset): `XDG_CONFIG_HOME`
-- Security hashing: `API_KEY_SECRET`, `MACHINE_ID_SALT`
-- Logging: `APP_LOG_TO_FILE`, `APP_LOG_RETENTION_DAYS`, `CALL_LOG_RETENTION_DAYS`
-- Sync/cloud URLing: `NEXT_PUBLIC_BASE_URL`, `NEXT_PUBLIC_CLOUD_URL`
-- Outbound proxy: `HTTP_PROXY`, `HTTPS_PROXY`, `ALL_PROXY`, `NO_PROXY` and lowercase variants
-- SOCKS5 feature flags: `ENABLE_SOCKS5_PROXY`, `NEXT_PUBLIC_ENABLE_SOCKS5_PROXY`
-- Platform/runtime helpers (not app-specific config): `APPDATA`, `NODE_ENV`, `PORT`, `HOSTNAME`
-
-## Known Architectural Notes
-
-1. `usageDb` and `localDb` share the same base directory policy (`DATA_DIR` -> `XDG_CONFIG_HOME/omniroute` -> `~/.omniroute`) with legacy file migration.
-2. `/api/v1/route.ts` delegates to the same unified catalog builder used by `/api/v1/models` (`src/app/api/v1/models/catalog.ts`) to avoid semantic drift.
-3. Request logger writes full headers/body when enabled; treat log directory as sensitive.
-4. Cloud behavior depends on correct `NEXT_PUBLIC_BASE_URL` and cloud endpoint reachability.
-5. The `open-sse/` directory is published as the `@omniroute/open-sse` **npm workspace package**. Source code imports it via `@omniroute/open-sse/...` (resolved by Next.js `transpilePackages`). File paths in this document still use the directory name `open-sse/` for consistency.
-6. Charts in the dashboard use **Recharts** (SVG-based) for accessible, interactive analytics visualizations (model usage bar charts, provider breakdown tables with success rates).
-7. E2E tests use **Playwright** (`tests/e2e/`), run via `npm run test:e2e`. Unit tests use **Node.js test runner** (`tests/unit/`), run via `npm run test:unit`. Source code under `src/` is **TypeScript** (`.ts`/`.tsx`); the `open-sse/` workspace remains JavaScript (`.js`).
-8. Settings page is organized into 5 tabs: Security, Routing (6 global strategies: fill-first, round-robin, p2c, random, least-used, cost-optimized), Resilience (editable rate limits, circuit breaker, policies, **Context Relay** handoff config), AI (thinking budget, system prompt, prompt cache), Advanced (proxy).
-9. **Context Relay** strategy (`context-relay`) is split across two layers: `combo.ts` decides if a handoff should be generated, `chat.ts` injects the handoff after account resolution. Handoff data lives in `context_handoffs` SQLite table. This split is intentional because only `chat.ts` knows whether the actual account changed.
-10. **Proxy enforcement** is now comprehensive: `tokenHealthCheck.ts` resolves proxy per connection, `/api/providers/validate` uses `runWithProxyContext`, and `proxyFetch.ts` uses `undici.fetch()` to maintain dispatcher compatibility on Node 22.
-11. **Node.js runtime policy detection**: `/api/settings/require-login` returns `nodeVersion` and `nodeCompatible` fields. The login page renders a warning banner when the runtime falls outside the supported secure Node.js lines.
-
-## Operational Verification Checklist
-
-- Build from source: `npm run build`
-- Build Docker image: `docker build -t omniroute .`
-- Start service and verify:
-- `GET /api/settings`
-- `GET /api/v1/models`
-- CLI target base URL should be `http://<host>:20128/v1` when `PORT=20128`
diff --git a/docs/i18n/in/docs/architecture/CODEBASE_DOCUMENTATION.md b/docs/i18n/in/docs/architecture/CODEBASE_DOCUMENTATION.md
deleted file mode 100644
index cb2b6d60ea..0000000000
--- a/docs/i18n/in/docs/architecture/CODEBASE_DOCUMENTATION.md
+++ /dev/null
@@ -1,587 +0,0 @@
-# omniroute — Codebase Documentation (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../../docs/CODEBASE_DOCUMENTATION.md) · 🇪🇸 [es](../../es/docs/CODEBASE_DOCUMENTATION.md) · 🇫🇷 [fr](../../fr/docs/CODEBASE_DOCUMENTATION.md) · 🇩🇪 [de](../../de/docs/CODEBASE_DOCUMENTATION.md) · 🇮🇹 [it](../../it/docs/CODEBASE_DOCUMENTATION.md) · 🇷🇺 [ru](../../ru/docs/CODEBASE_DOCUMENTATION.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/CODEBASE_DOCUMENTATION.md) · 🇯🇵 [ja](../../ja/docs/CODEBASE_DOCUMENTATION.md) · 🇰🇷 [ko](../../ko/docs/CODEBASE_DOCUMENTATION.md) · 🇸🇦 [ar](../../ar/docs/CODEBASE_DOCUMENTATION.md) · 🇮🇳 [hi](../../hi/docs/CODEBASE_DOCUMENTATION.md) · 🇮🇳 [in](../../in/docs/CODEBASE_DOCUMENTATION.md) · 🇹🇭 [th](../../th/docs/CODEBASE_DOCUMENTATION.md) · 🇻🇳 [vi](../../vi/docs/CODEBASE_DOCUMENTATION.md) · 🇮🇩 [id](../../id/docs/CODEBASE_DOCUMENTATION.md) · 🇲🇾 [ms](../../ms/docs/CODEBASE_DOCUMENTATION.md) · 🇳🇱 [nl](../../nl/docs/CODEBASE_DOCUMENTATION.md) · 🇵🇱 [pl](../../pl/docs/CODEBASE_DOCUMENTATION.md) · 🇸🇪 [sv](../../sv/docs/CODEBASE_DOCUMENTATION.md) · 🇳🇴 [no](../../no/docs/CODEBASE_DOCUMENTATION.md) · 🇩🇰 [da](../../da/docs/CODEBASE_DOCUMENTATION.md) · 🇫🇮 [fi](../../fi/docs/CODEBASE_DOCUMENTATION.md) · 🇵🇹 [pt](../../pt/docs/CODEBASE_DOCUMENTATION.md) · 🇷🇴 [ro](../../ro/docs/CODEBASE_DOCUMENTATION.md) · 🇭🇺 [hu](../../hu/docs/CODEBASE_DOCUMENTATION.md) · 🇧🇬 [bg](../../bg/docs/CODEBASE_DOCUMENTATION.md) · 🇸🇰 [sk](../../sk/docs/CODEBASE_DOCUMENTATION.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/CODEBASE_DOCUMENTATION.md) · 🇮🇱 [he](../../he/docs/CODEBASE_DOCUMENTATION.md) · 🇵🇭 [phi](../../phi/docs/CODEBASE_DOCUMENTATION.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/CODEBASE_DOCUMENTATION.md) · 🇨🇿 [cs](../../cs/docs/CODEBASE_DOCUMENTATION.md) · 🇹🇷 [tr](../../tr/docs/CODEBASE_DOCUMENTATION.md)
-
----
-
-> A comprehensive, beginner-friendly guide to the **omniroute** multi-provider AI proxy router.
-
----
-
-## 1. What Is omniroute?
-
-omniroute is a **proxy router** that sits between AI clients (Claude CLI, Codex, Cursor IDE, etc.) and AI providers (Anthropic, Google, OpenAI, AWS, GitHub, etc.). It solves one big problem:
-
-> **Different AI clients speak different "languages" (API formats), and different AI providers expect different "languages" too.** omniroute translates between them automatically.
-
-Think of it like a universal translator at the United Nations — any delegate can speak any language, and the translator converts it for any other delegate.
-
----
-
-## 2. Architecture Overview
-
-```mermaid
-graph LR
-    subgraph Clients
-        A[Claude CLI]
-        B[Codex]
-        C[Cursor IDE]
-        D[OpenAI-compatible]
-    end
-
-    subgraph omniroute
-        E[Handler Layer]
-        F[Translator Layer]
-        G[Executor Layer]
-        H[Services Layer]
-    end
-
-    subgraph Providers
-        I[Anthropic Claude]
-        J[Google Gemini]
-        K[OpenAI / Codex]
-        L[GitHub Copilot]
-        M[AWS Kiro]
-        N[Antigravity]
-        O[Cursor API]
-    end
-
-    A --> E
-    B --> E
-    C --> E
-    D --> E
-    E --> F
-    F --> G
-    G --> I
-    G --> J
-    G --> K
-    G --> L
-    G --> M
-    G --> N
-    G --> O
-    H -.-> E
-    H -.-> G
-```
-
-### Core Principle: Hub-and-Spoke Translation
-
-All format translation passes through **OpenAI format as the hub**:
-
-```
-Client Format → [OpenAI Hub] → Provider Format    (request)
-Provider Format → [OpenAI Hub] → Client Format    (response)
-```
-
-This means you only need **N translators** (one per format) instead of **N²** (every pair).
-
----
-
-## 3. Project Structure
-
-```
-omniroute/
-├── open-sse/                  ← Core proxy library (portable, framework-agnostic)
-│   ├── index.js               ← Main entry point, exports everything
-│   ├── config/                ← Configuration & constants
-│   ├── executors/             ← Provider-specific request execution
-│   ├── handlers/              ← Request handling orchestration
-│   ├── services/              ← Business logic (auth, models, fallback, usage)
-│   ├── translator/            ← Format translation engine
-│   │   ├── request/           ← Request translators (8 files)
-│   │   ├── response/          ← Response translators (7 files)
-│   │   └── helpers/           ← Shared translation utilities (6 files)
-│   └── utils/                 ← Utility functions
-├── src/                       ← Application layer (Express/Worker runtime)
-│   ├── app/                   ← Web UI, API routes, middleware
-│   ├── lib/                   ← Database, auth, and shared library code
-│   ├── mitm/                  ← Man-in-the-middle proxy utilities
-│   ├── models/                ← Database models
-│   ├── shared/                ← Shared utilities (wrappers around open-sse)
-│   ├── sse/                   ← SSE endpoint handlers
-│   └── store/                 ← State management
-├── data/                      ← Runtime data (credentials, logs)
-│   └── provider-credentials.json   (external credentials override, gitignored)
-└── tester/                    ← Test utilities
-```
-
----
-
-## 4. Module-by-Module Breakdown
-
-### 4.1 Config (`open-sse/config/`)
-
-The **single source of truth** for all provider configuration.
-
-| File                          | Purpose                                                                                                                                                                                                                   |
-| ----------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `constants.ts`                | `PROVIDERS` object with base URLs, OAuth credentials (defaults), headers, and default system prompts for every provider. Also defines `HTTP_STATUS`, `ERROR_TYPES`, `COOLDOWN_MS`, `BACKOFF_CONFIG`, and `SKIP_PATTERNS`. |
-| `credentialLoader.ts`         | Loads external credentials from `data/provider-credentials.json` and merges them over the hardcoded defaults in `PROVIDERS`. Keeps secrets out of source control while maintaining backwards compatibility.               |
-| `providerModels.ts`           | Central model registry: maps provider aliases → model IDs. Functions like `getModels()`, `getProviderByAlias()`.                                                                                                          |
-| `codexInstructions.ts`        | System instructions injected into Codex requests (editing constraints, sandbox rules, approval policies).                                                                                                                 |
-| `defaultThinkingSignature.ts` | Default "thinking" signatures for Claude and Gemini models.                                                                                                                                                               |
-| `ollamaModels.ts`             | Schema definition for local Ollama models (name, size, family, quantization).                                                                                                                                             |
-
-#### Credential Loading Flow
-
-```mermaid
-flowchart TD
-    A["App starts"] --> B["constants.ts defines PROVIDERS\nwith hardcoded defaults"]
-    B --> C{"data/provider-credentials.json\nexists?"}
-    C -->|Yes| D["credentialLoader reads JSON"]
-    C -->|No| E["Use hardcoded defaults"]
-    D --> F{"For each provider in JSON"}
-    F --> G{"Provider exists\nin PROVIDERS?"}
-    G -->|No| H["Log warning, skip"]
-    G -->|Yes| I{"Value is object?"}
-    I -->|No| J["Log warning, skip"]
-    I -->|Yes| K["Merge clientId, clientSecret,\ntokenUrl, authUrl, refreshUrl"]
-    K --> F
-    H --> F
-    J --> F
-    F -->|Done| L["PROVIDERS ready with\nmerged credentials"]
-    E --> L
-```
-
----
-
-### 4.2 Executors (`open-sse/executors/`)
-
-Executors encapsulate **provider-specific logic** using the **Strategy Pattern**. Each executor overrides base methods as needed.
-
-```mermaid
-classDiagram
-    class BaseExecutor {
-        +buildUrl(model, stream, options)
-        +buildHeaders(credentials, stream, body)
-        +transformRequest(body, model, stream, credentials)
-        +execute(url, options)
-        +shouldRetry(status, error)
-        +refreshCredentials(credentials, log)
-    }
-
-    class DefaultExecutor {
-        +refreshCredentials()
-    }
-
-    class AntigravityExecutor {
-        +buildUrl()
-        +buildHeaders()
-        +transformRequest()
-        +shouldRetry()
-        +refreshCredentials()
-    }
-
-    class CursorExecutor {
-        +buildUrl()
-        +buildHeaders()
-        +transformRequest()
-        +parseResponse()
-        +generateChecksum()
-    }
-
-    class KiroExecutor {
-        +buildUrl()
-        +buildHeaders()
-        +transformRequest()
-        +parseEventStream()
-        +refreshCredentials()
-    }
-
-    BaseExecutor <|-- DefaultExecutor
-    BaseExecutor <|-- AntigravityExecutor
-    BaseExecutor <|-- CursorExecutor
-    BaseExecutor <|-- KiroExecutor
-    BaseExecutor <|-- CodexExecutor
-    BaseExecutor <|-- GithubExecutor
-```
-
-| Executor         | Provider                                   | Key Specializations                                                                                                 |
-| ---------------- | ------------------------------------------ | ------------------------------------------------------------------------------------------------------------------- |
-| `base.ts`        | —                                          | Abstract base: URL building, headers, retry logic, credential refresh                                               |
-| `default.ts`     | Claude, Gemini, OpenAI, GLM, Kimi, MiniMax | Generic OAuth token refresh for standard providers                                                                  |
-| `antigravity.ts` | Google Cloud Code                          | Project/session ID generation, multi-URL fallback, custom retry parsing from error messages ("reset after 2h7m23s") |
-| `cursor.ts`      | Cursor IDE                                 | **Most complex**: SHA-256 checksum auth, Protobuf request encoding, binary EventStream → SSE response parsing       |
-| `codex.ts`       | OpenAI Codex                               | Injects system instructions, manages thinking levels, removes unsupported parameters                                |
-| `github.ts`      | GitHub Copilot                             | Dual token system (GitHub OAuth + Copilot token), VSCode header mimicking                                           |
-| `kiro.ts`        | AWS CodeWhisperer                          | AWS EventStream binary parsing, AMZN event frames, token estimation                                                 |
-| `index.ts`       | —                                          | Factory: maps provider name → executor class, with default fallback                                                 |
-
----
-
-### 4.3 Handlers (`open-sse/handlers/`)
-
-The **orchestration layer** — coordinates translation, execution, streaming, and error handling.
-
-| File                  | Purpose                                                                                                                                                                                                                |
-| --------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `chatCore.ts`         | **Central orchestrator** (~600 lines). Handles the complete request lifecycle: format detection → translation → executor dispatch → streaming/non-streaming response → token refresh → error handling → usage logging. |
-| `responsesHandler.ts` | Adapter for OpenAI's Responses API: converts Responses format → Chat Completions → sends to `chatCore` → converts SSE back to Responses format.                                                                        |
-| `embeddings.ts`       | Embedding generation handler: resolves embedding model → provider, dispatches to provider API, returns OpenAI-compatible embedding response. Supports 6+ providers.                                                    |
-| `imageGeneration.ts`  | Image generation handler: resolves image model → provider, supports OpenAI-compatible, Gemini-image (Antigravity), and fallback (Nebius) modes. Returns base64 or URL images.                                          |
-
-#### Request Lifecycle (chatCore.ts)
-
-```mermaid
-sequenceDiagram
-    participant Client
-    participant chatCore
-    participant Translator
-    participant Executor
-    participant Provider
-
-    Client->>chatCore: Request (any format)
-    chatCore->>chatCore: Detect source format
-    chatCore->>chatCore: Check bypass patterns
-    chatCore->>chatCore: Resolve model & provider
-    chatCore->>Translator: Translate request (source → OpenAI → target)
-    chatCore->>Executor: Get executor for provider
-    Executor->>Executor: Build URL, headers, transform request
-    Executor->>Executor: Refresh credentials if needed
-    Executor->>Provider: HTTP fetch (streaming or non-streaming)
-
-    alt Streaming
-        Provider-->>chatCore: SSE stream
-        chatCore->>chatCore: Pipe through SSE transform stream
-        Note over chatCore: Transform stream translates<br/>each chunk: target → OpenAI → source
-        chatCore-->>Client: Translated SSE stream
-    else Non-streaming
-        Provider-->>chatCore: JSON response
-        chatCore->>Translator: Translate response
-        chatCore-->>Client: Translated JSON
-    end
-
-    alt Error (401, 429, 500...)
-        chatCore->>Executor: Retry with credential refresh
-        chatCore->>chatCore: Account fallback logic
-    end
-```
-
----
-
-### 4.4 Services (`open-sse/services/`)
-
-Business logic that supports the handlers and executors.
-
-| File                 | Purpose                                                                                                                                                                                                                                                                                                                                |
-| -------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `provider.ts`        | **Format detection** (`detectFormat`): analyzes request body structure to identify Claude/OpenAI/Gemini/Antigravity/Responses formats (includes `max_tokens` heuristic for Claude). Also: URL building, header building, thinking config normalization. Supports `openai-compatible-*` and `anthropic-compatible-*` dynamic providers. |
-| `model.ts`           | Model string parsing (`claude/model-name` → `{provider: "claude", model: "model-name"}`), alias resolution with collision detection, input sanitization (rejects path traversal/control chars), and model info resolution with async alias getter support.                                                                             |
-| `accountFallback.ts` | Rate-limit handling: exponential backoff (1s → 2s → 4s → max 2min), account cooldown management, error classification (which errors trigger fallback vs. not).                                                                                                                                                                         |
-| `tokenRefresh.ts`    | OAuth token refresh for **every provider**: Google (Gemini, Antigravity), Claude, Codex, Qwen, Qoder, GitHub (OAuth + Copilot dual-token), Kiro (AWS SSO OIDC + Social Auth). Includes in-flight promise deduplication cache and retry with exponential backoff.                                                                       |
-| `combo.ts`           | **Combo models**: chains of fallback models. If model A fails with a fallback-eligible error, try model B, then C, etc. Returns actual upstream status codes.                                                                                                                                                                          |
-| `usage.ts`           | Fetches quota/usage data from provider APIs (GitHub Copilot quotas, Antigravity model quotas, Codex rate limits, Kiro usage breakdowns, Claude settings).                                                                                                                                                                              |
-| `accountSelector.ts` | Smart account selection with scoring algorithm: considers priority, health status, round-robin position, and cooldown state to pick the optimal account for each request.                                                                                                                                                              |
-| `contextManager.ts`  | Request context lifecycle management: creates and tracks per-request context objects with metadata (request ID, timestamps, provider info) for debugging and logging.                                                                                                                                                                  |
-| `ipFilter.ts`        | IP-based access control: supports allowlist and blocklist modes. Validates client IP against configured rules before processing API requests.                                                                                                                                                                                          |
-| `sessionManager.ts`  | Session tracking with client fingerprinting: tracks active sessions using hashed client identifiers, monitors request counts, and provides session metrics.                                                                                                                                                                            |
-| `signatureCache.ts`  | Request signature-based deduplication cache: prevents duplicate requests by caching recent request signatures and returning cached responses for identical requests within a time window.                                                                                                                                              |
-| `systemPrompt.ts`    | Global system prompt injection: prepends or appends a configurable system prompt to all requests, with per-provider compatibility handling.                                                                                                                                                                                            |
-| `thinkingBudget.ts`  | Reasoning token budget management: supports passthrough, auto (strip thinking config), custom (fixed budget), and adaptive (complexity-scaled) modes for controlling thinking/reasoning tokens.                                                                                                                                        |
-| `wildcardRouter.ts`  | Wildcard model pattern routing: resolves wildcard patterns (e.g., `*/claude-*`) to concrete provider/model pairs based on availability and priority.                                                                                                                                                                                   |
-
-#### Token Refresh Deduplication
-
-```mermaid
-sequenceDiagram
-    participant R1 as Request 1
-    participant R2 as Request 2
-    participant Cache as refreshPromiseCache
-    participant OAuth as OAuth Provider
-
-    R1->>Cache: getAccessToken("gemini", token)
-    Cache->>Cache: No in-flight promise
-    Cache->>OAuth: Start refresh
-    R2->>Cache: getAccessToken("gemini", token)
-    Cache->>Cache: Found in-flight promise
-    Cache-->>R2: Return existing promise
-    OAuth-->>Cache: New access token
-    Cache-->>R1: New access token
-    Cache-->>R2: Same access token (shared)
-    Cache->>Cache: Delete cache entry
-```
-
-#### Account Fallback State Machine
-
-```mermaid
-stateDiagram-v2
-    [*] --> Active
-    Active --> Error: Request fails (401/429/500)
-    Error --> Cooldown: Apply backoff
-    Cooldown --> Active: Cooldown expires
-    Active --> Active: Request succeeds (reset backoff)
-
-    state Error {
-        [*] --> ClassifyError
-        ClassifyError --> ShouldFallback: Rate limit / Auth / Transient
-        ClassifyError --> NoFallback: 400 Bad Request
-    }
-
-    state Cooldown {
-        [*] --> ExponentialBackoff
-        ExponentialBackoff: Level 0 = 1s
-        ExponentialBackoff: Level 1 = 2s
-        ExponentialBackoff: Level 2 = 4s
-        ExponentialBackoff: Max = 2min
-    }
-```
-
-#### Combo Model Chain
-
-```mermaid
-flowchart LR
-    A["Request with\ncombo model"] --> B["Model A"]
-    B -->|"2xx Success"| C["Return response"]
-    B -->|"429/401/500"| D{"Fallback\neligible?"}
-    D -->|Yes| E["Model B"]
-    D -->|No| F["Return error"]
-    E -->|"2xx Success"| C
-    E -->|"429/401/500"| G{"Fallback\neligible?"}
-    G -->|Yes| H["Model C"]
-    G -->|No| F
-    H -->|"2xx Success"| C
-    H -->|"Fail"| I["All failed →\nReturn last status"]
-```
-
----
-
-### 4.5 Translator (`open-sse/translator/`)
-
-The **format translation engine** using a self-registering plugin system.
-
-#### आर्किटेक्चर
-
-```mermaid
-graph TD
-    subgraph "Request Translation"
-        A["Claude → OpenAI"]
-        B["Gemini → OpenAI"]
-        C["Antigravity → OpenAI"]
-        D["OpenAI Responses → OpenAI"]
-        E["OpenAI → Claude"]
-        F["OpenAI → Gemini"]
-        G["OpenAI → Kiro"]
-        H["OpenAI → Cursor"]
-    end
-
-    subgraph "Response Translation"
-        I["Claude → OpenAI"]
-        J["Gemini → OpenAI"]
-        K["Kiro → OpenAI"]
-        L["Cursor → OpenAI"]
-        M["OpenAI → Claude"]
-        N["OpenAI → Antigravity"]
-        O["OpenAI → Responses"]
-    end
-```
-
-| Directory    | Files         | Description                                                                                                                                                                                                                                                      |
-| ------------ | ------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `request/`   | 8 translators | Convert request bodies between formats. Each file self-registers via `register(from, to, fn)` on import.                                                                                                                                                         |
-| `response/`  | 7 translators | Convert streaming response chunks between formats. Handles SSE event types, thinking blocks, tool calls.                                                                                                                                                         |
-| `helpers/`   | 6 helpers     | Shared utilities: `claudeHelper` (system prompt extraction, thinking config), `geminiHelper` (parts/contents mapping), `openaiHelper` (format filtering), `toolCallHelper` (ID generation, missing response injection), `maxTokensHelper`, `responsesApiHelper`. |
-| `index.ts`   | —             | Translation engine: `translateRequest()`, `translateResponse()`, state management, registry.                                                                                                                                                                     |
-| `formats.ts` | —             | Format constants: `OPENAI`, `CLAUDE`, `GEMINI`, `ANTIGRAVITY`, `KIRO`, `CURSOR`, `OPENAI_RESPONSES`.                                                                                                                                                             |
-
-#### Key Design: Self-Registering Plugins
-
-```javascript
-// Each translator file calls register() on import:
-import { register } from "../index.js";
-register("claude", "openai", translateClaudeToOpenAI);
-
-// The index.js imports all translator files, triggering registration:
-import "./request/claude-to-openai.js"; // ← self-registers
-```
-
----
-
-### 4.6 Utils (`open-sse/utils/`)
-
-| File               | Purpose                                                                                                                                                                                                                                                                              |
-| ------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| `error.ts`         | Error response building (OpenAI-compatible format), upstream error parsing, Antigravity retry-time extraction from error messages, SSE error streaming.                                                                                                                              |
-| `stream.ts`        | **SSE Transform Stream** — the core streaming pipeline. Two modes: `TRANSLATE` (full format translation) and `PASSTHROUGH` (normalize + extract usage). Handles chunk buffering, usage estimation, content length tracking. Per-stream encoder/decoder instances avoid shared state. |
-| `streamHelpers.ts` | Low-level SSE utilities: `parseSSELine` (whitespace-tolerant), `hasValuableContent` (filters empty chunks for OpenAI/Claude/Gemini), `fixInvalidId`, `formatSSE` (format-aware SSE serialization with `perf_metrics` cleanup).                                                       |
-| `usageTracking.ts` | Token usage extraction from any format (Claude/OpenAI/Gemini/Responses), estimation with separate tool/message char-per-token ratios, buffer addition (2000 tokens safety margin), format-specific field filtering, console logging with ANSI colors.                                |
-| `requestLogger.ts` | Legacy file-based request logging helper kept for compatibility. Current deployments should prefer `APP_LOG_TO_FILE` for application logs and the call log pipeline for persisted request artifacts.                                                                                 |
-| `bypassHandler.ts` | Intercepts specific patterns from Claude CLI (title extraction, warmup, count) and returns fake responses without calling any provider. Supports both streaming and non-streaming. Intentionally limited to Claude CLI scope.                                                        |
-| `networkProxy.ts`  | Resolves outbound proxy URL for a given provider with precedence: provider-specific config → global config → environment variables (`HTTPS_PROXY`/`HTTP_PROXY`/`ALL_PROXY`). Supports `NO_PROXY` exclusions. Caches config for 30s.                                                  |
-
-#### SSE Streaming Pipeline
-
-```mermaid
-flowchart TD
-    A["Provider SSE stream"] --> B["TextDecoder\n(per-stream instance)"]
-    B --> C["Buffer lines\n(split on newline)"]
-    C --> D["parseSSELine()\n(trim whitespace, parse JSON)"]
-    D --> E{"Mode?"}
-    E -->|TRANSLATE| F["translateResponse()\ntarget → OpenAI → source"]
-    E -->|PASSTHROUGH| G["fixInvalidId()\nnormalize chunk"]
-    F --> H["hasValuableContent()\nfilter empty chunks"]
-    G --> H
-    H -->|"Has content"| I["extractUsage()\ntrack token counts"]
-    H -->|"Empty"| J["Skip chunk"]
-    I --> K["formatSSE()\nserialize + clean perf_metrics"]
-    K --> L["TextEncoder\n(per-stream instance)"]
-    L --> M["Enqueue to\nclient stream"]
-
-    style A fill:#f9f,stroke:#333
-    style M fill:#9f9,stroke:#333
-```
-
-#### Request Logger Session Structure
-
-```
-logs/
-└── claude_gemini_claude-sonnet_20260208_143045/
-    ├── 1_req_client.json      ← Raw client request
-    ├── 2_req_source.json      ← After initial conversion
-    ├── 3_req_openai.json      ← OpenAI intermediate format
-    ├── 4_req_target.json      ← Final target format
-    ├── 5_res_provider.txt     ← Provider SSE chunks (streaming)
-    ├── 5_res_provider.json    ← Provider response (non-streaming)
-    ├── 6_res_openai.txt       ← OpenAI intermediate chunks
-    ├── 7_res_client.txt       ← Client-facing SSE chunks
-    └── 6_error.json           ← Error details (if any)
-```
-
----
-
-### 4.7 Application Layer (`src/`)
-
-| Directory     | Purpose                                                                |
-| ------------- | ---------------------------------------------------------------------- |
-| `src/app/`    | Web UI, API routes, Express middleware, OAuth callback handlers        |
-| `src/lib/`    | Database access (`localDb.ts`, `usageDb.ts`), authentication, shared   |
-| `src/mitm/`   | Man-in-the-middle proxy utilities for intercepting provider traffic    |
-| `src/models/` | Database model definitions                                             |
-| `src/shared/` | Wrappers around open-sse functions (provider, stream, error, etc.)     |
-| `src/sse/`    | SSE endpoint handlers that wire the open-sse library to Express routes |
-| `src/store/`  | Application state management                                           |
-
-#### Notable API Routes
-
-| Route                                         | Methods         | Purpose                                                                               |
-| --------------------------------------------- | --------------- | ------------------------------------------------------------------------------------- |
-| `/api/provider-models`                        | GET/POST/DELETE | CRUD for custom models per provider                                                   |
-| `/api/models/catalog`                         | GET             | Aggregated catalog of all models (chat, embedding, image, custom) grouped by provider |
-| `/api/settings/proxy`                         | GET/PUT/DELETE  | Hierarchical outbound proxy configuration (`global/providers/combos/keys`)            |
-| `/api/settings/proxy/test`                    | POST            | Validates proxy connectivity and returns public IP/latency                            |
-| `/v1/providers/[provider]/chat/completions`   | POST            | Dedicated per-provider chat completions with model validation                         |
-| `/v1/providers/[provider]/embeddings`         | POST            | Dedicated per-provider embeddings with model validation                               |
-| `/v1/providers/[provider]/images/generations` | POST            | Dedicated per-provider image generation with model validation                         |
-| `/api/settings/ip-filter`                     | GET/PUT         | IP allowlist/blocklist management                                                     |
-| `/api/settings/thinking-budget`               | GET/PUT         | Reasoning token budget configuration (passthrough/auto/custom/adaptive)               |
-| `/api/settings/system-prompt`                 | GET/PUT         | Global system prompt injection for all requests                                       |
-| `/api/sessions`                               | GET             | Active session tracking and metrics                                                   |
-| `/api/rate-limits`                            | GET             | Per-account rate limit status                                                         |
-
----
-
-## 5. Key Design Patterns
-
-### 5.1 Hub-and-Spoke Translation
-
-All formats translate through **OpenAI format as the hub**. Adding a new provider only requires writing **one pair** of translators (to/from OpenAI), not N pairs.
-
-### 5.2 Executor Strategy Pattern
-
-Each provider has a dedicated executor class inheriting from `BaseExecutor`. The factory in `executors/index.ts` selects the right one at runtime.
-
-### 5.3 Self-Registering Plugin System
-
-Translator modules register themselves on import via `register()`. Adding a new translator is just creating a file and importing it.
-
-### 5.4 Account Fallback with Exponential Backoff
-
-When a provider returns 429/401/500, the system can switch to the next account, applying exponential cooldowns (1s → 2s → 4s → max 2min).
-
-### 5.5 Combo Model Chains
-
-A "combo" groups multiple `provider/model` strings. If the first fails, fallback to the next automatically.
-
-### 5.6 Stateful Streaming Translation
-
-Response translation maintains state across SSE chunks (thinking block tracking, tool call accumulation, content block indexing) via the `initState()` mechanism.
-
-### 5.7 Usage Safety Buffer
-
-A 2000-token buffer is added to reported usage to prevent clients from hitting context window limits due to overhead from system prompts and format translation.
-
----
-
-## 6. Supported Formats
-
-| Format                  | Direction       | Identifier         |
-| ----------------------- | --------------- | ------------------ |
-| OpenAI Chat Completions | source + target | `openai`           |
-| OpenAI Responses API    | source + target | `openai-responses` |
-| Anthropic Claude        | source + target | `claude`           |
-| Google Gemini           | source + target | `gemini`           |
-| Antigravity             | source + target | `antigravity`      |
-| AWS Kiro                | target only     | `kiro`             |
-| Cursor                  | target only     | `cursor`           |
-
----
-
-## 7. Supported Providers
-
-| Provider                 | Auth Method            | Executor    | Key Notes                                     |
-| ------------------------ | ---------------------- | ----------- | --------------------------------------------- |
-| Anthropic Claude         | API key or OAuth       | Default     | Uses `x-api-key` header                       |
-| Google Gemini            | API key or OAuth       | Default     | Uses `x-goog-api-key` header                  |
-| Antigravity              | OAuth                  | Antigravity | Multi-URL fallback, custom retry parsing      |
-| OpenAI                   | API key                | Default     | Standard Bearer auth                          |
-| Codex                    | OAuth                  | Codex       | Injects system instructions, manages thinking |
-| GitHub Copilot           | OAuth + Copilot token  | Github      | Dual token, VSCode header mimicking           |
-| Kiro (AWS)               | AWS SSO OIDC or Social | Kiro        | Binary EventStream parsing                    |
-| Cursor IDE               | Checksum auth          | Cursor      | Protobuf encoding, SHA-256 checksums          |
-| Qwen                     | OAuth                  | Default     | Standard auth                                 |
-| Qoder                    | OAuth (Basic + Bearer) | Default     | Dual auth header                              |
-| OpenRouter               | API key                | Default     | Standard Bearer auth                          |
-| GLM, Kimi, MiniMax       | API key                | Default     | Claude-compatible, use `x-api-key`            |
-| `openai-compatible-*`    | API key                | Default     | Dynamic: any OpenAI-compatible endpoint       |
-| `anthropic-compatible-*` | API key                | Default     | Dynamic: any Claude-compatible endpoint       |
-
----
-
-## 8. Data Flow Summary
-
-### Streaming Request
-
-```mermaid
-flowchart LR
-    A["Client"] --> B["detectFormat()"]
-    B --> C["translateRequest()\nsource → OpenAI → target"]
-    C --> D["Executor\nbuildUrl + buildHeaders"]
-    D --> E["fetch(providerURL)"]
-    E --> F["createSSEStream()\nTRANSLATE mode"]
-    F --> G["parseSSELine()"]
-    G --> H["translateResponse()\ntarget → OpenAI → source"]
-    H --> I["extractUsage()\n+ addBuffer"]
-    I --> J["formatSSE()"]
-    J --> K["Client receives\ntranslated SSE"]
-    K --> L["logUsage()\nsaveRequestUsage()"]
-```
-
-### Non-Streaming Request
-
-```mermaid
-flowchart LR
-    A["Client"] --> B["detectFormat()"]
-    B --> C["translateRequest()\nsource → OpenAI → target"]
-    C --> D["Executor.execute()"]
-    D --> E["translateResponse()\ntarget → OpenAI → source"]
-    E --> F["Return JSON\nresponse"]
-```
-
-### Bypass Flow (Claude CLI)
-
-```mermaid
-flowchart LR
-    A["Claude CLI request"] --> B{"Match bypass\npattern?"}
-    B -->|"Title/Warmup/Count"| C["Generate fake\nOpenAI response"]
-    B -->|"No match"| D["Normal flow"]
-    C --> E["Translate to\nsource format"]
-    E --> F["Return without\ncalling provider"]
-```
diff --git a/docs/i18n/in/docs/cloudflare-zero-trust-guide.md b/docs/i18n/in/docs/cloudflare-zero-trust-guide.md
deleted file mode 100644
index 4b1ffc0eb0..0000000000
--- a/docs/i18n/in/docs/cloudflare-zero-trust-guide.md
+++ /dev/null
@@ -1,106 +0,0 @@
-# Guia Completo: Cloudflare Tunnel & Zero Trust (Split-Port) (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../../docs/cloudflare-zero-trust-guide.md) · 🇪🇸 [es](../../es/docs/cloudflare-zero-trust-guide.md) · 🇫🇷 [fr](../../fr/docs/cloudflare-zero-trust-guide.md) · 🇩🇪 [de](../../de/docs/cloudflare-zero-trust-guide.md) · 🇮🇹 [it](../../it/docs/cloudflare-zero-trust-guide.md) · 🇷🇺 [ru](../../ru/docs/cloudflare-zero-trust-guide.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/cloudflare-zero-trust-guide.md) · 🇯🇵 [ja](../../ja/docs/cloudflare-zero-trust-guide.md) · 🇰🇷 [ko](../../ko/docs/cloudflare-zero-trust-guide.md) · 🇸🇦 [ar](../../ar/docs/cloudflare-zero-trust-guide.md) · 🇮🇳 [hi](../../hi/docs/cloudflare-zero-trust-guide.md) · 🇮🇳 [in](../../in/docs/cloudflare-zero-trust-guide.md) · 🇹🇭 [th](../../th/docs/cloudflare-zero-trust-guide.md) · 🇻🇳 [vi](../../vi/docs/cloudflare-zero-trust-guide.md) · 🇮🇩 [id](../../id/docs/cloudflare-zero-trust-guide.md) · 🇲🇾 [ms](../../ms/docs/cloudflare-zero-trust-guide.md) · 🇳🇱 [nl](../../nl/docs/cloudflare-zero-trust-guide.md) · 🇵🇱 [pl](../../pl/docs/cloudflare-zero-trust-guide.md) · 🇸🇪 [sv](../../sv/docs/cloudflare-zero-trust-guide.md) · 🇳🇴 [no](../../no/docs/cloudflare-zero-trust-guide.md) · 🇩🇰 [da](../../da/docs/cloudflare-zero-trust-guide.md) · 🇫🇮 [fi](../../fi/docs/cloudflare-zero-trust-guide.md) · 🇵🇹 [pt](../../pt/docs/cloudflare-zero-trust-guide.md) · 🇷🇴 [ro](../../ro/docs/cloudflare-zero-trust-guide.md) · 🇭🇺 [hu](../../hu/docs/cloudflare-zero-trust-guide.md) · 🇧🇬 [bg](../../bg/docs/cloudflare-zero-trust-guide.md) · 🇸🇰 [sk](../../sk/docs/cloudflare-zero-trust-guide.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/cloudflare-zero-trust-guide.md) · 🇮🇱 [he](../../he/docs/cloudflare-zero-trust-guide.md) · 🇵🇭 [phi](../../phi/docs/cloudflare-zero-trust-guide.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/cloudflare-zero-trust-guide.md) · 🇨🇿 [cs](../../cs/docs/cloudflare-zero-trust-guide.md) · 🇹🇷 [tr](../../tr/docs/cloudflare-zero-trust-guide.md)
-
----
-
-Este guia documenta o padrão ouro de infraestrutura de rede para proteger o **OmniRoute** e expor sua aplicação de forma segura para a internet, **sem abrir nenhuma porta (Zero Inbound)**.
-
-## O que foi feito na sua VM?
-
-Nós ativamos o OmniRoute em modo **Split-Port** através do PM2:
-
-- **Porta \`20128\`:** Roda **apenas a API** `/v1`.
-- **Porta \`20129\`:** Roda **apenas o Dashboard** Administrativo visual.
-
-Além disso, o serviço interno exige \`REQUIRE_API_KEY=true\`, o que significa que nenhum agente pode consumir os endpoints da API sem enviar um "Bearer Token" legítimo gerado na aba API Keys do Painel.
-
-Isso nos permite criar duas regras completamente independentes na rede. É aqui que entra o **Cloudflare Tunnel (cloudflared)**.
-
----
-
-## 1. Como Criar o Túnel na Cloudflare
-
-O utilitário \`cloudflared\` já está instalado na sua máquina. Siga os passos na nuvem:
-
-1. Acesse seu painel **Cloudflare Zero Trust** (One.dash.cloudflare.com).
-2. No menu à esquerda, vá em **Networks > Tunnels**.
-3. Clique em **Add a Tunnel**, escolha **Cloudflared** e dê o nome \`OmniRoute-VM\`.
-4. Ele vai gerar um comando na tela chamado "Install and run a connector". **Você só precisa copiar o Token (a string longa após `--token`)**.
-5. Logue via SSH na sua máquina virtual (ou Terminal do Proxmox) e execute:
-   \`\`\`bash
-   # Inicia e amarra o túnel permanentemente à sua conta
-   cloudflared service install SEU_TOKEN_GIGANTE_AQUI
-   \`\`\`
-
----
-
-## 2. Configurando o Roteamento (Public Hostnames)
-
-Ainda na tela do Tunnel recém-criado, vá para a aba **Public Hostnames** e adicione as **duas** rotas, aproveitando a separação que fizemos:
-
-### Rota 1: API Segura (Limitada)
-
-- **Subdomain:** \`api\`
-- **Domain:** \`seuglobal.com.br\` (escolha seu domínio real)
-- **Service Type:** \`HTTP\`
-- **URL:** \`127.0.0.1:20128\` _(Porta interna da API)_
-
-### Rota 2: Painel Zero Trust (Fechado)
-
-- **Subdomain:** \`omniroute\` ou \`painel\`
-- **Domain:** \`seuglobal.com.br\`
-- **Service Type:** \`HTTP\`
-- **URL:** \`127.0.0.1:20129\` _(Porta interna do App/Visual)_
-
-Neste momento, a conectividade "Física" está resolvida. Agora vamos blindar de verdade.
-
----
-
-## 3. Blindando o Painel com Zero Trust (Access)
-
-Nenhuma senha local protege melhor o seu painel do que remover totalmente o acesso a ele da internet aberta.
-
-1. No painel Zero Trust, vá em **Access > Applications > Add an application**.
-2. Selecione **Self-hosted**.
-3. Em **Application name**, coloque \`Painel OmniRoute\`.
-4. Em **Application domain**, coloque \`omniroute.seuglobal.com.br\` (O mesmo que você fez na "Rota 2").
-5. Clique em **Next**.
-6. Em **Rule action**, escolha \`Allow\`. Em nome da Rule coloque \`Admin Apenas\`.
-7. Em **Include**, no seletor de "Selector" escolha \`Emails\` e digite o seu email, por exemplo \`admin@spgeo.com.br\`.
-8. Salve (`Add application`).
-
-> **O que isso fez:** Se você tentar abrir \`omniroute.seuglobal.com.br\`, não cai mais na sua aplicação OmniRoute! Cai numa tela elegante da Cloudflare pedindo para digitar seu email. Somente se você (ou o email que você botou) for digitado lá, ele recebe no Outlook/Gmail um código de 6 dígitos temporário que libera o túnel até a porta \`20129\`.
-
----
-
-## 4. Limitando e Protegendo a API com Rate Limit (WAF)
-
-O Dashboard do Zero Trust não se aplica à rota da API (\`api.seuglobal.com.br\`), porque é um acesso programático via ferramentas automatizadas (agentes) sem navegador. Para ele, usaremos o Firewall principal (WAF) da Cloudflare.
-
-1. Acesse o **Painel Normal** da Cloudflare (dash.cloudflare.com) e entre no seu Domínio.
-2. No menu esquerdo, vá em **Security > WAF > Rate limiting rules**.
-3. Clique em **Create rule**.
-4. **Name:** \`Anti-Abuso OmniRoute API\`
-5. **If incoming requests match...**
-   - Escolha em Field: \`Hostname\`
-   - Operator: \`equals\`
-   - Value: \`api.seuglobal.com.br\`
-6. Em **With the same characteristics:** Mantenha \`IP\`.
-7. Nos limites (Limit):
-   - **When requests exceed:** \`50\`
-   - **Period:** \`1 minute\`
-8. No final, em **Action**: \`Block\` (Bloquear) e decida se o bloqueio dura por 1 minuto ou 1 hora.
-9. **Deploy**.
-
-> **O que isso fez:** Ninguém pode mandar mais de 50 requisições num período de 60 segundos na sua URL de API. Como você roda vários agentes e os consumos por trás já batem rate limit e já rastreiam tokens, isso é apenas uma medida na Borda da Internet (Edge Layer) que protege sua Instância On-Premises de cair por estresse térmico antes mesmo do tráfego descer pelo túnel.
-
----
-
-## Finalização
-
-1. A sua VM **não possui nenhuma porta exposta** em `/etc/ufw`.
-2. O OmniRoute só conversa HTTPS saindo (\`cloudflared\`) e não recebendo TCP direto do mundo.
-3. Seus requets pro OpenAI são ofuscados porque configuramos eles globalmente pra passar em um Proxy SOCKS5 (A nuvem não liga pro SOCKS5 porque ela vem Inbound).
-4. Seu painel web tem 2-Factor com Email.
-5. Sua API está ratelimitada na borda pela Cloudflare e só trafega Bearer Tokens.
diff --git a/docs/i18n/in/docs/features/context-relay.md b/docs/i18n/in/docs/features/context-relay.md
deleted file mode 100644
index d07c29df31..0000000000
--- a/docs/i18n/in/docs/features/context-relay.md
+++ /dev/null
@@ -1,130 +0,0 @@
-# Context Relay (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../../../docs/features/context-relay.md) · 🇪🇸 [es](../../../es/docs/features/context-relay.md) · 🇫🇷 [fr](../../../fr/docs/features/context-relay.md) · 🇩🇪 [de](../../../de/docs/features/context-relay.md) · 🇮🇹 [it](../../../it/docs/features/context-relay.md) · 🇷🇺 [ru](../../../ru/docs/features/context-relay.md) · 🇨🇳 [zh-CN](../../../zh-CN/docs/features/context-relay.md) · 🇯🇵 [ja](../../../ja/docs/features/context-relay.md) · 🇰🇷 [ko](../../../ko/docs/features/context-relay.md) · 🇸🇦 [ar](../../../ar/docs/features/context-relay.md) · 🇮🇳 [hi](../../../hi/docs/features/context-relay.md) · 🇮🇳 [in](../../../in/docs/features/context-relay.md) · 🇹🇭 [th](../../../th/docs/features/context-relay.md) · 🇻🇳 [vi](../../../vi/docs/features/context-relay.md) · 🇮🇩 [id](../../../id/docs/features/context-relay.md) · 🇲🇾 [ms](../../../ms/docs/features/context-relay.md) · 🇳🇱 [nl](../../../nl/docs/features/context-relay.md) · 🇵🇱 [pl](../../../pl/docs/features/context-relay.md) · 🇸🇪 [sv](../../../sv/docs/features/context-relay.md) · 🇳🇴 [no](../../../no/docs/features/context-relay.md) · 🇩🇰 [da](../../../da/docs/features/context-relay.md) · 🇫🇮 [fi](../../../fi/docs/features/context-relay.md) · 🇵🇹 [pt](../../../pt/docs/features/context-relay.md) · 🇷🇴 [ro](../../../ro/docs/features/context-relay.md) · 🇭🇺 [hu](../../../hu/docs/features/context-relay.md) · 🇧🇬 [bg](../../../bg/docs/features/context-relay.md) · 🇸🇰 [sk](../../../sk/docs/features/context-relay.md) · 🇺🇦 [uk-UA](../../../uk-UA/docs/features/context-relay.md) · 🇮🇱 [he](../../../he/docs/features/context-relay.md) · 🇵🇭 [phi](../../../phi/docs/features/context-relay.md) · 🇧🇷 [pt-BR](../../../pt-BR/docs/features/context-relay.md) · 🇨🇿 [cs](../../../cs/docs/features/context-relay.md) · 🇹🇷 [tr](../../../tr/docs/features/context-relay.md)
-
----
-
-`context-relay` is a combo strategy that keeps session continuity when the active account
-rotates before the conversation is finished.
-
-The current runtime behaves like priority routing for model selection, then adds a
-handoff layer on top:
-
-- before the active account is exhausted, OmniRoute generates a compact structured summary
-- after authentication selects a different account for the same session, OmniRoute injects
-  that summary as a system message into the next request
-- once the handoff is consumed successfully, it is removed from storage
-
-## When To Use It
-
-Use `context-relay` when all of the following are true:
-
-- the combo is expected to rotate between multiple accounts of the same provider
-- losing short-term conversational continuity would hurt task quality
-- the provider exposes enough quota information to predict an approaching account limit
-
-This is most useful for long-running coding or research sessions that may outlive a single
-account window.
-
-## Runtime Flow
-
-The current behavior is intentionally split across two runtime layers.
-
-### 0% to 84% quota used
-
-No handoff is generated. Requests behave like normal priority routing.
-
-### 85% to 94% quota used
-
-If the active provider is enabled in `handoffProviders`, OmniRoute generates a structured
-handoff summary in the background before the account is fully exhausted.
-
-Important details:
-
-- the default warning threshold is `0.85`
-- the hard stop for generation is `0.95`
-- only one in-flight handoff generation is allowed per `sessionId + comboName`
-- if an active handoff already exists for that session/combo, no duplicate summary is generated
-
-### 95% or more quota used
-
-No new handoff is generated. At this point the system is already in or near exhaustion and
-the runtime avoids scheduling another summary request.
-
-### After account rotation
-
-When the next request for the same session resolves to a different authenticated account,
-OmniRoute prepends the stored handoff as a system message. Injection happens only after the
-real account switch is known.
-
-## Handoff Payload
-
-The persisted handoff payload is stored in `context_handoffs` and includes:
-
-- `sessionId`
-- `comboName`
-- `fromAccount`
-- `summary`
-- `keyDecisions`
-- `taskProgress`
-- `activeEntities`
-- `messageCount`
-- `model`
-- `warningThresholdPct`
-- `generatedAt`
-- `expiresAt`
-
-The summary model is instructed to return a JSON object with this structure:
-
-```json
-{
-  "summary": "Dense summary of what matters for continuity",
-  "keyDecisions": ["Decision 1", "Decision 2"],
-  "taskProgress": "What is done, what is pending, and the next step",
-  "activeEntities": ["fileA.ts", "feature X", "provider Y"]
-}
-```
-
-At injection time, OmniRoute converts that payload into a `<context_handoff>` system
-message so the next account can continue with the correct local context.
-
-## कॉन्फ़िगरेशन
-
-`context-relay` supports these config fields:
-
-- `handoffThreshold`: warning threshold for summary generation, default `0.85`
-- `handoffModel`: optional model override used only for summary generation
-- `handoffProviders`: allowlist of providers allowed to trigger handoff generation
-
-Global defaults can be configured in Settings, and combo-specific values can override them
-in the Combos page.
-
-## Architectural Note
-
-The current implementation does not use a standalone `handleContextRelayCombo` handler.
-
-Instead:
-
-- `open-sse/services/combo.ts` decides whether a successful turn should generate a handoff
-- `src/sse/handlers/chat.ts` injects the handoff only after authentication resolves the
-  actual account used for the request
-
-This split is intentional in the current codebase because the combo loop alone does not know
-whether the request stayed on the same account or actually switched accounts.
-
-## Limitations
-
-- Effective runtime support is currently centered on `codex` quota rotation.
-- `handoffProviders` is already modeled as a config surface, but real handoff generation
-  still depends on provider-specific quota plumbing.
-- The summary is intentionally compact and recent-history based; it is not a full transcript
-  replay mechanism.
-- Handoffs are scoped by `sessionId + comboName` and expire automatically.
-- If the session does not switch accounts, the stored handoff is not injected.
-
-## Recommended Usage Pattern
-
-- use multiple accounts from the same provider
-- keep stable `sessionId` values across the session
-- set `handoffThreshold` early enough to leave room for the background summary request
-- treat the feature as continuity assistance, not as a replacement for persistent memory
diff --git a/docs/i18n/in/docs/frameworks/A2A-SERVER.md b/docs/i18n/in/docs/frameworks/A2A-SERVER.md
deleted file mode 100644
index 8010e88b8f..0000000000
--- a/docs/i18n/in/docs/frameworks/A2A-SERVER.md
+++ /dev/null
@@ -1,200 +0,0 @@
-# OmniRoute A2A Server Documentation (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../../docs/A2A-SERVER.md) · 🇪🇸 [es](../../es/docs/A2A-SERVER.md) · 🇫🇷 [fr](../../fr/docs/A2A-SERVER.md) · 🇩🇪 [de](../../de/docs/A2A-SERVER.md) · 🇮🇹 [it](../../it/docs/A2A-SERVER.md) · 🇷🇺 [ru](../../ru/docs/A2A-SERVER.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/A2A-SERVER.md) · 🇯🇵 [ja](../../ja/docs/A2A-SERVER.md) · 🇰🇷 [ko](../../ko/docs/A2A-SERVER.md) · 🇸🇦 [ar](../../ar/docs/A2A-SERVER.md) · 🇮🇳 [hi](../../hi/docs/A2A-SERVER.md) · 🇮🇳 [in](../../in/docs/A2A-SERVER.md) · 🇹🇭 [th](../../th/docs/A2A-SERVER.md) · 🇻🇳 [vi](../../vi/docs/A2A-SERVER.md) · 🇮🇩 [id](../../id/docs/A2A-SERVER.md) · 🇲🇾 [ms](../../ms/docs/A2A-SERVER.md) · 🇳🇱 [nl](../../nl/docs/A2A-SERVER.md) · 🇵🇱 [pl](../../pl/docs/A2A-SERVER.md) · 🇸🇪 [sv](../../sv/docs/A2A-SERVER.md) · 🇳🇴 [no](../../no/docs/A2A-SERVER.md) · 🇩🇰 [da](../../da/docs/A2A-SERVER.md) · 🇫🇮 [fi](../../fi/docs/A2A-SERVER.md) · 🇵🇹 [pt](../../pt/docs/A2A-SERVER.md) · 🇷🇴 [ro](../../ro/docs/A2A-SERVER.md) · 🇭🇺 [hu](../../hu/docs/A2A-SERVER.md) · 🇧🇬 [bg](../../bg/docs/A2A-SERVER.md) · 🇸🇰 [sk](../../sk/docs/A2A-SERVER.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/A2A-SERVER.md) · 🇮🇱 [he](../../he/docs/A2A-SERVER.md) · 🇵🇭 [phi](../../phi/docs/A2A-SERVER.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/A2A-SERVER.md) · 🇨🇿 [cs](../../cs/docs/A2A-SERVER.md) · 🇹🇷 [tr](../../tr/docs/A2A-SERVER.md)
-
----
-
-> Agent-to-Agent Protocol v0.3 — OmniRoute as an intelligent routing agent
-
-## Agent Discovery
-
-```bash
-curl http://localhost:20128/.well-known/agent.json
-```
-
-Returns the Agent Card describing OmniRoute's capabilities, skills, and authentication requirements.
-
----
-
-## Authentication
-
-All `/a2a` requests require an API key via the `Authorization` header:
-
-```
-Authorization: Bearer YOUR_OMNIROUTE_API_KEY
-```
-
-If no API key is configured on the server, authentication is bypassed.
-
----
-
-## JSON-RPC 2.0 Methods
-
-### `message/send` — Synchronous Execution
-
-Sends a message to a skill and waits for the complete response.
-
-```bash
-curl -X POST http://localhost:20128/a2a \
-  -H "Content-Type: application/json" \
-  -H "Authorization: Bearer YOUR_KEY" \
-  -d '{
-    "jsonrpc": "2.0",
-    "id": "1",
-    "method": "message/send",
-    "params": {
-      "skill": "smart-routing",
-      "messages": [{"role": "user", "content": "Write a hello world in Python"}],
-      "metadata": {"model": "auto", "combo": "fast-coding"}
-    }
-  }'
-```
-
-**Response:**
-
-```json
-{
-  "jsonrpc": "2.0",
-  "id": "1",
-  "result": {
-    "task": { "id": "uuid", "state": "completed" },
-    "artifacts": [{ "type": "text", "content": "..." }],
-    "metadata": {
-      "routing_explanation": "Selected claude-sonnet via provider \"anthropic\" (latency: 1200ms, cost: $0.003)",
-      "cost_envelope": { "estimated": 0.005, "actual": 0.003, "currency": "USD" },
-      "resilience_trace": [
-        { "event": "primary_selected", "provider": "anthropic", "timestamp": "..." }
-      ],
-      "policy_verdict": { "allowed": true, "reason": "within budget and quota limits" }
-    }
-  }
-}
-```
-
-### `message/stream` — SSE Streaming
-
-Same as `message/send` but returns Server-Sent Events for real-time streaming.
-
-```bash
-curl -N -X POST http://localhost:20128/a2a \
-  -H "Content-Type: application/json" \
-  -H "Authorization: Bearer YOUR_KEY" \
-  -d '{
-    "jsonrpc": "2.0",
-    "id": "1",
-    "method": "message/stream",
-    "params": {
-      "skill": "smart-routing",
-      "messages": [{"role": "user", "content": "Explain quantum computing"}]
-    }
-  }'
-```
-
-**SSE Events:**
-
-```
-data: {"jsonrpc":"2.0","method":"message/stream","params":{"task":{"id":"...","state":"working"},"chunk":{"type":"text","content":"..."}}}
-
-: heartbeat 2026-03-03T17:00:00Z
-
-data: {"jsonrpc":"2.0","method":"message/stream","params":{"task":{"id":"...","state":"completed"},"metadata":{...}}}
-```
-
-### `tasks/get` — Query Task Status
-
-```bash
-curl -X POST http://localhost:20128/a2a \
-  -H "Content-Type: application/json" \
-  -H "Authorization: Bearer YOUR_KEY" \
-  -d '{"jsonrpc":"2.0","id":"2","method":"tasks/get","params":{"taskId":"TASK_UUID"}}'
-```
-
-### `tasks/cancel` — Cancel a Task
-
-```bash
-curl -X POST http://localhost:20128/a2a \
-  -H "Content-Type: application/json" \
-  -H "Authorization: Bearer YOUR_KEY" \
-  -d '{"jsonrpc":"2.0","id":"3","method":"tasks/cancel","params":{"taskId":"TASK_UUID"}}'
-```
-
----
-
-## Available Skills
-
-| Skill              | Description                                                                                                                     |
-| :----------------- | :------------------------------------------------------------------------------------------------------------------------------ |
-| `smart-routing`    | Routes prompts through OmniRoute's intelligent pipeline. Returns response with routing explanation, cost, and resilience trace. |
-| `quota-management` | Answers natural-language queries about provider quotas, suggests free combos, and provides quota rankings.                      |
-
----
-
-## Task Lifecycle
-
-```
-submitted → working → completed
-                    → failed
-                    → cancelled
-```
-
-- Tasks expire after 5 minutes (configurable)
-- Terminal states: `completed`, `failed`, `cancelled`
-- Event log tracks every state transition
-
----
-
-## Error Codes
-
-| Code   | Meaning                        |
-| :----- | :----------------------------- |
-| -32700 | Parse error (invalid JSON)     |
-| -32600 | Invalid request / Unauthorized |
-| -32601 | Method or skill not found      |
-| -32602 | Invalid params                 |
-| -32603 | Internal error                 |
-
----
-
-## Integration Examples
-
-### Python (requests)
-
-```python
-import requests
-
-resp = requests.post("http://localhost:20128/a2a", json={
-    "jsonrpc": "2.0", "id": "1",
-    "method": "message/send",
-    "params": {
-        "skill": "smart-routing",
-        "messages": [{"role": "user", "content": "Hello"}]
-    }
-}, headers={"Authorization": "Bearer YOUR_KEY"})
-
-result = resp.json()["result"]
-print(result["artifacts"][0]["content"])
-print(result["metadata"]["routing_explanation"])
-```
-
-### TypeScript (fetch)
-
-```typescript
-const resp = await fetch("http://localhost:20128/a2a", {
-  method: "POST",
-  headers: {
-    "Content-Type": "application/json",
-    Authorization: "Bearer YOUR_KEY",
-  },
-  body: JSON.stringify({
-    jsonrpc: "2.0",
-    id: "1",
-    method: "message/send",
-    params: {
-      skill: "smart-routing",
-      messages: [{ role: "user", content: "Hello" }],
-    },
-  }),
-});
-const { result } = await resp.json();
-console.log(result.metadata.routing_explanation);
-```
diff --git a/docs/i18n/in/docs/frameworks/MCP-SERVER.md b/docs/i18n/in/docs/frameworks/MCP-SERVER.md
deleted file mode 100644
index 4cdeece934..0000000000
--- a/docs/i18n/in/docs/frameworks/MCP-SERVER.md
+++ /dev/null
@@ -1,87 +0,0 @@
-# OmniRoute MCP Server Documentation (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../../docs/MCP-SERVER.md) · 🇪🇸 [es](../../es/docs/MCP-SERVER.md) · 🇫🇷 [fr](../../fr/docs/MCP-SERVER.md) · 🇩🇪 [de](../../de/docs/MCP-SERVER.md) · 🇮🇹 [it](../../it/docs/MCP-SERVER.md) · 🇷🇺 [ru](../../ru/docs/MCP-SERVER.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/MCP-SERVER.md) · 🇯🇵 [ja](../../ja/docs/MCP-SERVER.md) · 🇰🇷 [ko](../../ko/docs/MCP-SERVER.md) · 🇸🇦 [ar](../../ar/docs/MCP-SERVER.md) · 🇮🇳 [hi](../../hi/docs/MCP-SERVER.md) · 🇮🇳 [in](../../in/docs/MCP-SERVER.md) · 🇹🇭 [th](../../th/docs/MCP-SERVER.md) · 🇻🇳 [vi](../../vi/docs/MCP-SERVER.md) · 🇮🇩 [id](../../id/docs/MCP-SERVER.md) · 🇲🇾 [ms](../../ms/docs/MCP-SERVER.md) · 🇳🇱 [nl](../../nl/docs/MCP-SERVER.md) · 🇵🇱 [pl](../../pl/docs/MCP-SERVER.md) · 🇸🇪 [sv](../../sv/docs/MCP-SERVER.md) · 🇳🇴 [no](../../no/docs/MCP-SERVER.md) · 🇩🇰 [da](../../da/docs/MCP-SERVER.md) · 🇫🇮 [fi](../../fi/docs/MCP-SERVER.md) · 🇵🇹 [pt](../../pt/docs/MCP-SERVER.md) · 🇷🇴 [ro](../../ro/docs/MCP-SERVER.md) · 🇭🇺 [hu](../../hu/docs/MCP-SERVER.md) · 🇧🇬 [bg](../../bg/docs/MCP-SERVER.md) · 🇸🇰 [sk](../../sk/docs/MCP-SERVER.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/MCP-SERVER.md) · 🇮🇱 [he](../../he/docs/MCP-SERVER.md) · 🇵🇭 [phi](../../phi/docs/MCP-SERVER.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/MCP-SERVER.md) · 🇨🇿 [cs](../../cs/docs/MCP-SERVER.md) · 🇹🇷 [tr](../../tr/docs/MCP-SERVER.md)
-
----
-
-> Model Context Protocol server with 16 intelligent tools
-
-## स्थापित करें
-
-OmniRoute MCP is built-in. Start it with:
-
-```bash
-omniroute --mcp
-```
-
-Or via the open-sse transport:
-
-```bash
-# HTTP streamable transport (port 20130)
-omniroute --dev  # MCP auto-starts on /mcp endpoint
-```
-
-## IDE Configuration
-
-See [IDE Configs](integrations/ide-configs.md) for Antigravity, Cursor, Copilot, and Claude Desktop setup.
-
----
-
-## Essential Tools (8)
-
-| Tool                            | Description                              |
-| :------------------------------ | :--------------------------------------- |
-| `omniroute_get_health`          | Gateway health, circuit breakers, uptime |
-| `omniroute_list_combos`         | All configured combos with models        |
-| `omniroute_get_combo_metrics`   | Performance metrics for a specific combo |
-| `omniroute_switch_combo`        | Switch active combo by ID/name           |
-| `omniroute_check_quota`         | Quota status per provider or all         |
-| `omniroute_route_request`       | Send a chat completion through OmniRoute |
-| `omniroute_cost_report`         | Cost analytics for a time period         |
-| `omniroute_list_models_catalog` | Full model catalog with capabilities     |
-
-## Advanced Tools (8)
-
-| Tool                               | Description                                                 |
-| :--------------------------------- | :---------------------------------------------------------- |
-| `omniroute_simulate_route`         | Dry-run routing simulation with fallback tree               |
-| `omniroute_set_budget_guard`       | Session budget with degrade/block/alert actions             |
-| `omniroute_set_resilience_profile` | Apply conservative/balanced/aggressive preset               |
-| `omniroute_test_combo`             | Live-test all models in a combo via a real upstream request |
-| `omniroute_get_provider_metrics`   | Detailed metrics for one provider                           |
-| `omniroute_best_combo_for_task`    | Task-fitness recommendation with alternatives               |
-| `omniroute_explain_route`          | Explain a past routing decision                             |
-| `omniroute_get_session_snapshot`   | Full session state: costs, tokens, errors                   |
-
-## Authentication
-
-MCP tools are authenticated via API key scopes. Each tool requires specific scopes:
-
-| Scope          | Tools                                            |
-| :------------- | :----------------------------------------------- |
-| `read:health`  | get_health, get_provider_metrics                 |
-| `read:combos`  | list_combos, get_combo_metrics                   |
-| `write:combos` | switch_combo                                     |
-| `read:quota`   | check_quota                                      |
-| `write:route`  | route_request, simulate_route, test_combo        |
-| `read:usage`   | cost_report, get_session_snapshot, explain_route |
-| `write:config` | set_budget_guard, set_resilience_profile         |
-| `read:models`  | list_models_catalog, best_combo_for_task         |
-
-## Audit Logging
-
-Every tool call is logged to `mcp_tool_audit` with:
-
-- Tool name, arguments, result
-- Duration (ms), success/failure
-- API key hash, timestamp
-
-## Files
-
-| File                                         | Purpose                                     |
-| :------------------------------------------- | :------------------------------------------ |
-| `open-sse/mcp-server/server.ts`              | MCP server creation + 16 tool registrations |
-| `open-sse/mcp-server/transport.ts`           | Stdio + HTTP transport                      |
-| `open-sse/mcp-server/auth.ts`                | API key + scope validation                  |
-| `open-sse/mcp-server/audit.ts`               | Tool call audit logging                     |
-| `open-sse/mcp-server/tools/advancedTools.ts` | 8 advanced tool handlers                    |
diff --git a/docs/i18n/in/docs/guides/CLI-INTEGRATIONS.md b/docs/i18n/in/docs/guides/CLI-INTEGRATIONS.md
deleted file mode 100644
index 0652dffb4e..0000000000
--- a/docs/i18n/in/docs/guides/CLI-INTEGRATIONS.md
+++ /dev/null
@@ -1,315 +0,0 @@
-# CLI-INTEGRATIONS (Bahasa Indonesia (Alt))
-
-🌐 **Languages:** 🇺🇸 [English](../../../../guides/CLI-INTEGRATIONS.md) · 🇸🇦 [ar](../../../ar/docs/guides/CLI-INTEGRATIONS.md) · 🇦🇿 [az](../../../az/docs/guides/CLI-INTEGRATIONS.md) · 🇧🇬 [bg](../../../bg/docs/guides/CLI-INTEGRATIONS.md) · 🇧🇩 [bn](../../../bn/docs/guides/CLI-INTEGRATIONS.md) · 🇨🇿 [cs](../../../cs/docs/guides/CLI-INTEGRATIONS.md) · 🇩🇰 [da](../../../da/docs/guides/CLI-INTEGRATIONS.md) · 🇩🇪 [de](../../../de/docs/guides/CLI-INTEGRATIONS.md) · 🇪🇸 [es](../../../es/docs/guides/CLI-INTEGRATIONS.md) · 🇮🇷 [fa](../../../fa/docs/guides/CLI-INTEGRATIONS.md) · 🇫🇮 [fi](../../../fi/docs/guides/CLI-INTEGRATIONS.md) · 🇫🇷 [fr](../../../fr/docs/guides/CLI-INTEGRATIONS.md) · 🇮🇳 [gu](../../../gu/docs/guides/CLI-INTEGRATIONS.md) · 🇮🇱 [he](../../../he/docs/guides/CLI-INTEGRATIONS.md) · 🇮🇳 [hi](../../../hi/docs/guides/CLI-INTEGRATIONS.md) · 🇭🇺 [hu](../../../hu/docs/guides/CLI-INTEGRATIONS.md) · 🇮🇩 [id](../../../id/docs/guides/CLI-INTEGRATIONS.md) · 🇮🇹 [it](../../../it/docs/guides/CLI-INTEGRATIONS.md) · 🇯🇵 [ja](../../../ja/docs/guides/CLI-INTEGRATIONS.md) · 🇰🇷 [ko](../../../ko/docs/guides/CLI-INTEGRATIONS.md) · 🇮🇳 [mr](../../../mr/docs/guides/CLI-INTEGRATIONS.md) · 🇲🇾 [ms](../../../ms/docs/guides/CLI-INTEGRATIONS.md) · 🇳🇱 [nl](../../../nl/docs/guides/CLI-INTEGRATIONS.md) · 🇳🇴 [no](../../../no/docs/guides/CLI-INTEGRATIONS.md) · 🇵🇭 [phi](../../../phi/docs/guides/CLI-INTEGRATIONS.md) · 🇵🇱 [pl](../../../pl/docs/guides/CLI-INTEGRATIONS.md) · 🇵🇹 [pt](../../../pt/docs/guides/CLI-INTEGRATIONS.md) · 🇧🇷 [pt-BR](../../../pt-BR/docs/guides/CLI-INTEGRATIONS.md) · 🇷🇴 [ro](../../../ro/docs/guides/CLI-INTEGRATIONS.md) · 🇷🇺 [ru](../../../ru/docs/guides/CLI-INTEGRATIONS.md) · 🇸🇰 [sk](../../../sk/docs/guides/CLI-INTEGRATIONS.md) · 🇸🇪 [sv](../../../sv/docs/guides/CLI-INTEGRATIONS.md) · 🇰🇪 [sw](../../../sw/docs/guides/CLI-INTEGRATIONS.md) · 🇮🇳 [ta](../../../ta/docs/guides/CLI-INTEGRATIONS.md) · 🇮🇳 [te](../../../te/docs/guides/CLI-INTEGRATIONS.md) · 🇹🇭 [th](../../../th/docs/guides/CLI-INTEGRATIONS.md) · 🇹🇷 [tr](../../../tr/docs/guides/CLI-INTEGRATIONS.md) · 🇺🇦 [uk-UA](../../../uk-UA/docs/guides/CLI-INTEGRATIONS.md) · 🇵🇰 [ur](../../../ur/docs/guides/CLI-INTEGRATIONS.md) · 🇻🇳 [vi](../../../vi/docs/guides/CLI-INTEGRATIONS.md) · 🇨🇳 [zh-CN](../../../zh-CN/docs/guides/CLI-INTEGRATIONS.md) · 🇹🇼 [zh-TW](../../../zh-TW/docs/guides/CLI-INTEGRATIONS.md)
-
----
-
----
-
-title: "Integrasi CLI — arahkan CLI pengkodean ke OmniRoute"
-version: 3.8.50
-lastUpdated: 2026-08-18
----
-
-# Integrasi CLI
-
-OmniRoute menyediakan serangkaian perintah `setup-*` yang mengonfigurasi CLI pengkodean
-(Codex, Claude Code, OpenCode, Cline, …) untuk menggunakan OmniRoute sebagai backend-nya — sehingga
-alat tersebut berkomunikasi dengan **satu** endpoint dan OmniRoute mengarahkan ke penyedia yang tepat dengan
-fallback otomatis. Setiap perintah membaca katalog model **langsung** dari OmniRoute yang sedang berjalan
-(lokal atau jarak jauh) dan menulis file konfigurasi alat itu sendiri di **mesin Anda**. Kunci API dirujuk oleh variabel lingkungan di mana pun alat tersebut mendukungnya. Perintah yang mempertahankan file lingkungan lokal alat dicatat di bawah.
-
-Ada juga peluncur generik — `omniroute run <target>` — yang memunculkan
-`claude`, `codex`, `aider`, `goose`, `opencode`, `qwen` atau `gemini` dengan
-lingkungan yang tepat disuntikkan, tanpa menulis konfigurasi sama sekali. Target dan aliasnya berasal dari manifest kanonik `bin/cli/cli-manifest.mjs`
-(`claude-code|cc|anthropic`, `codex-cli|openai-codex|openai`, `goose-cli`,
-`open-code`, `qwen-code`, `gemini-cli`), dan `omniroute completion` menawarkan
-kata target yang sama yang berasal dari manifest. Peluncur per-alat yang lama —
-`omniroute launch` (Claude Code) dan `omniroute launch-codex` (Codex) — tetap
-tersedia.
-
-Onboarding penyedia tersedia dari konteks lokal/remote yang sama. Perintah
-API-first di bawah ini menjaga autentikasi manajemen terpisah dari kredensial penyedia
-dan tidak pernah mencetak kredensial dalam output terstruktur:
-
-```bash
-omniroute providers add glm --credential-env GLM_API_KEY --name work
-omniroute providers import ./providers.json --dry-run --json
-omniroute providers auth openai
-omniroute providers edit <connection-id> --default-model glm/glm-5.2
-omniroute providers remove <connection-id> --yes
-```
-
-Untuk skrip, lebih baik menggunakan `--credential-stdin` atau `--credential-env`; `--credential`
-dipertahankan untuk penggunaan lokal yang terkontrol. `providers remove` memerlukan `--yes` pada terminal
-non-interaktif, dan kelima perintah menghormati konteks aktif atau opsi global `--base-url`/`--api-key`.
-
-Untuk pengaturan dasar satu kali yang ditulis tangan dari dua integrasi terkaya, lihat
-penjelasan mendalam per-alat:
-
-- [Konfigurasi Claude Code](./CLAUDE-CODE-CONFIGURATION.md)
-- [Konfigurasi CLI Codex](./CODEX-CLI-CONFIGURATION.md)
-- [Mode Jarak Jauh](./REMOTE-MODE.md) — mengendalikan OmniRoute jarak jauh (VPS / Tailnet) dari laptop Anda
-- [VS Code Copilot Chat](./VSCODE-COPILOT.md) — ekstensi OmniCopilot; ini juga dapat menjalankan
-  perintah `setup-*` ini untuk Anda dari dalam editor
-
----
-
-## Tabel Master
-
-Setiap perintah menghormati **konteks aktif** (diatur dengan `omniroute connect`, lihat
-[Mode Jarak Jauh](./REMOTE-MODE.md)) atau bendera eksplisit `--remote <url> --api-key <key>`.
-"Local vs remote" di bawah ini berarti: tanpa bendera, itu menargetkan `http://localhost:20128`;
-dengan `--remote` (atau konteks jarak jauh yang aktif) itu mengambil katalog dari server tersebut dan menulis konfigurasi secara lokal.
-
-| Perintah                   | Alat                                | Apa yang ditulis                                                                                                                                                             | Bendera kunci                                                                                                                              | Local vs remote |
-| -------------------------- | ----------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ | --------------- |
-| `omniroute setup-codex`    | OpenAI Codex CLI                    | `~/.codex/<name>.config.toml` — satu profil per model teks yang kompatibel (`codex --profile <name>`)                                                                        | `--remote` `--api-key` `--only` `--dry-run` `--port` `--codex-home`                                                                        | Keduanya        |
-| `omniroute setup-claude`   | Claude Code                         | `~/.claude/profiles/<name>/settings.json` — satu profil per model yang cocok (`CLAUDE_CONFIG_DIR`)                                                                           | `--remote` `--api-key` `--only` `--dry-run` `--port` `--claude-home`                                                                       | Keduanya        |
-| `omniroute setup-opencode` | OpenCode (kompatibel dengan openai) | `~/.config/opencode/opencode.json` — penyedia `omniroute` dengan setiap model katalog (`opencode -m omniroute/<model>`)                                                      | `--remote` `--api-key` `--only` `--model` `--dry-run` `--port`                                                                             | Keduanya        |
-| `omniroute setup-cline`    | Cline                               | `~/.cline/data/{globalState,secrets}.json` (mode CLI) + mencetak pengaturan ekstensi VS Code                                                                                 | `--remote` `--api-key` `--model` `--yes` `--dry-run` `--port` `--cline-dir`                                                                | Keduanya        |
-| `omniroute setup-kilo`     | Kilo Code                           | `~/.local/share/kilo/auth.json` (CLI) + menggabungkan `kilocode.*` ke dalam `settings.json` VS Code jika ada                                                                 | `--remote` `--api-key` `--model` `--yes` `--dry-run` `--port` `--auth-path` `--vscode-settings`                                            | Keduanya        |
-| `omniroute setup-continue` | Continue / `cn` CLI                 | `~/.continue/config.yaml` — model `provider: openai`, kunci melalui `${{ secrets.OMNIROUTE_API_KEY }}`                                                                       | `--remote` `--api-key` `--only` `--dry-run` `--port` `--config-path`                                                                       | Keduanya        |
-| `omniroute setup-cursor`   | Cursor                              | Tidak ada — mencetak langkah-langkah dalam aplikasi (konfigurasi Cursor tidak terlihat)                                                                                      | `--remote` `--api-key` `--only` `--port`                                                                                                   | Keduanya        |
-| `omniroute setup-roo`      | Roo Code                            | `~/.omniroute/roo-settings.json` (dokumen impor) + mengatur `roo-cline.autoImportSettingsPath` jika ada `settings.json` VS Code                                              | `--remote` `--api-key` `--model` `--yes` `--dry-run` `--port` `--import-path` `--vscode-settings`                                          | Keduanya        |
-| `omniroute setup-crush`    | Crush                               | `~/.config/crush/crush.json` — penyedia `openai-compat`, kunci melalui `$OMNIROUTE_API_KEY`                                                                                  | `--remote` `--api-key` `--only` `--dry-run` `--port` `--config-path`                                                                       | Keduanya        |
-| `omniroute setup-goose`    | Goose                               | `~/.config/goose/config.yaml` (`GOOSE_PROVIDER`/`OPENAI_HOST`/`GOOSE_MODEL`) + mencetak resep env                                                                            | `--remote` `--api-key` `--model` `--yes` `--dry-run` `--port` `--config-path`                                                              | Keduanya        |
-| `omniroute setup-aider`    | Aider                               | `~/.aider.conf.yml` (`openai-api-base` + `model: openai/<id>`) + mencetak resep env                                                                                          | `--remote` `--api-key` `--model` `--yes` `--dry-run` `--port` `--config-path`                                                              | Keduanya        |
-| `omniroute setup-qwen`     | Qwen Code                           | `~/.qwen/settings.json` — array `modelProviders.openai` V4 + `OMNIROUTE_API_KEY` di `~/.qwen/.env`                                                                           | `--remote` `--api-key` `--model` `--yes` `--dry-run` `--port` `--config-path` `--env-path`                                                 | Keduanya        |
-| `omniroute run <target>`   | Peluncuran runtime (generik)        | Tidak ada — memunculkan `claude`/`codex`/`aider`/`goose`/`opencode`/`qwen`/`gemini` dengan env dan argumen yang tepat; Qwen dan Gemini menggunakan home terisolasi sementara | `--remote` `--base-url` `--context` `--provider` `--model` `--api-key` `--api-key-env` `--dry-run` `--json` `--port` `--profile` `--token` | Keduanya        |
-| `omniroute launch`         | Claude Code                         | Tidak ada — memunculkan `claude` dengan `ANTHROPIC_BASE_URL`/`ANTHROPIC_AUTH_TOKEN` disuntikkan                                                                              | `--remote` `--api-key` `--token` `--profile` `--port`                                                                                      | Keduanya        |
-| `omniroute launch-codex`   | OpenAI Codex CLI                    | Tidak ada — memunculkan `codex` dengan penyedia `omniroute` disuntikkan melalui bendera `-c`                                                                                 | `--remote` `--api-key` `--profile` (`-p`) `--port`                                                                                         | Keduanya        |
-
-Catatan tentang bendera (diverifikasi dalam sumber perintah):
-
-- `--remote <url>` — mengambil katalog dari OmniRoute jarak jauh (mengganti `--port`
-  dan konteks aktif). `--api-key <key>` menyediakan kredensial untuk server tersebut
-  (default ke variabel lingkungan `OMNIROUTE_API_KEY`, atau token konteks aktif).
-- `--only <patterns>` — substring yang dipisahkan koma; hanya menyimpan ID model yang cocok
-  (misalnya `--only glm,kimi`). Tersedia pada `setup-codex`, `setup-claude`,
-  `setup-opencode`, `setup-continue`, `setup-cursor`, `setup-crush`.
-- `--dry-run` — mencetak persis apa yang akan ditulis tanpa menyentuh
-  sistem file. Tersedia pada setiap perintah `setup-*` **kecuali** `setup-cursor`
-  (yang tidak pernah menulis file).
-- `--model <id>` — diperlukan (atau dipilih secara interaktif) untuk alat yang tidak memiliki
-  penemuan model otomatis: Cline, Kilo, Roo, Goose, Qwen, Aider. Alat-alat tersebut
-  juga menerima `--yes` untuk penggunaan non-interaktif (yang kemudian memerlukan `--model`).
-  `setup-opencode` mengambil `--model` untuk mengatur model tingkat atas default.
-- `--model <id>` pada `omniroute run` mengikuti pengkabelan per-target manifest
-  (`bin/cli/cli-manifest.mjs`): **aider** menerima `--model openai/<id>` dan
-  **opencode** `--model omniroute/<id>` (awalan hanya ditambahkan ketika id
-  tidak sudah membawanya); **qwen** dan **gemini** menerima id secara verbatim;
-  **claude** mendapatkannya melalui `ANTHROPIC_MODEL`, **goose** melalui `GOOSE_MODEL`, dan
-  **codex** melalui argumen `-c model_providers.omniroute.*`. **Qwen adalah satu-satunya target run
-  yang secara keras memerlukan `--model`** — `omniroute run qwen` tanpa itu keluar
-  `2` dengan kesalahan eksplisit.
-- `--port <port>` — port OmniRoute lokal (default `20128`, diabaikan saat `--remote`
-  diatur). Tersedia pada semua `setup-*` dan kedua peluncur.
-- Kode keluar `omniroute run`: kode keluar CLI anak disebarkan
-  secara verbatim; `2` = argumen tidak valid (target tidak didukung, `--model` yang diperlukan hilang, penjaga kontainer); `127` = biner target tidak ada di `PATH`;
-  `130`/`143`/`129` ketika peluncuran diakhiri oleh `SIGINT`/`SIGTERM`/`SIGHUP`;
-  `1` = kegagalan peluncuran runtime lainnya.
-- Kedua peluncur (`launch`, `launch-codex`) menerima `--profile <name>` untuk memilih
-  profil yang ditulis oleh `setup-claude` / `setup-codex`, ditambah argumen pass-through untuk
-  biner `claude` / `codex` yang mendasarinya.
-
-Pemilih interaktif juga dibagikan oleh resep pengaturan:
-
-```bash
-# Pilih dari katalog model lokal atau jarak jauh yang aktif dan konfigurasikan target.
-omniroute configure claude
-omniroute configure opencode --provider glm
-omniroute configure qwen --model qwen/qwen3.8-max-preview --yes
-```
-
-`configure` saat ini mendelegasikan ke resep yang diuji untuk `codex`, `claude`,
-`opencode`, `qwen`, `aider`, `goose`, `cline`, `continue`, dan `kilo`. Entri katalog yang hanya untuk IDE,
-MITM, dan hanya panduan tetap sebagai alur `setup-*`/manual yang eksplisit dan
-tidak disajikan sebagai target yang dapat diluncurkan.
-
-> `setup-opencode` adalah integrasi OpenCode **ringan yang kompatibel dengan openai**.
-> Ada juga integrasi plugin yang lebih kaya — `omniroute setup opencode` — yang
-> menginstal `@omniroute/opencode-plugin`. Mereka adalah perintah yang berbeda; tabel
-> di atas mendokumentasikan `setup-opencode`.
-
----
-
-## Penggunaan Lokal
-
-Dengan OmniRoute berjalan di `localhost:20128`, cukup jalankan perintah setup untuk alat Anda. Katalog diambil dari server lokal.
-
-```bash
-# Codex: tulis profil per model yang cocok ke ~/.codex/
-omniroute setup-codex
-codex --profile glm52            # gunakan profil yang dihasilkan
-
-# Claude Code: tulis profil per-model, lalu luncurkan satu
-omniroute setup-claude
-omniroute launch --profile glm52
-
-# OpenCode: tulis penyedia yang kompatibel dengan openai dengan semua model katalog
-omniroute setup-opencode
-export OMNIROUTE_API_KEY=sk-...  # dirujuk melalui {env:OMNIROUTE_API_KEY}, tidak pernah di disk
-opencode -m omniroute/glm/glm-5.2 "..."
-
-# Alat tanpa penemuan otomatis memerlukan model eksplisit:
-omniroute setup-aider --model glm/glm-5.2
-omniroute setup-qwen --model qwen/qwen3.8-max-preview
-
-# Prabaca tanpa menulis apa pun:
-omniroute setup-continue --dry-run
-```
-
-Luncurkan tanpa menulis konfigurasi sama sekali (hanya injeksi-env):
-
-```bash
-omniroute launch                 # Claude Code → OmniRoute lokal
-omniroute launch-codex           # Codex CLI → OmniRoute lokal
-omniroute launch-codex --profile glm52
-omniroute run claude --model openai/gpt-5.4
-omniroute run codex --model openai/gpt-5.4 --dry-run --json
-omniroute run aider --model glm/glm-5.2 -- --message "reply OK"
-omniroute run goose --model glm/glm-5.2
-omniroute run opencode --model glm/glm-5.2 -- run "reply OK"
-omniroute run qwen --model glm/glm-5.2 -- -p "reply OK"
-omniroute run gemini --model glm/glm-5.2 -- --skip-trust -p "reply OK"
-
-# Jalur perintah eksplisit: teruskan apa pun yang datang setelah --
-omniroute run claude -- --print-system-prompt "review this diff"
-```
-
----
-
-## Penggunaan Jarak Jauh
-
-Arahkan perintah setup apa pun ke OmniRoute jarak jauh dengan `--remote` + `--api-key`. Katalog diambil dari jarak jauh; konfigurasi ditulis di mesin lokal Anda.
-
-```bash
-# OpenCode terhadap VPS jarak jauh, simpan hanya model glm/kimi
-omniroute setup-opencode --remote http://192.168.0.15:20128 --api-key oma_live_xxx \
-  --only glm,kimi
-opencode -m omniroute/glm/glm-5.2 "..."   # ekspor OMNIROUTE_API_KEY terlebih dahulu
-
-# Profil Codex dari katalog jarak jauh
-omniroute setup-codex --remote http://192.168.0.15:20128 --api-key oma_live_xxx
-
-# Luncurkan CLI langsung terhadap jarak jauh
-omniroute launch       --remote http://192.168.0.15:20128 --api-key oma_live_xxx
-omniroute launch-codex --remote http://192.168.0.15:20128 --api-key oma_live_xxx
-```
-
-Alih-alih melewatkan `--remote`/`--api-key` setiap kali, masuk sekali dan biarkan **konteks aktif** menyediakannya secara otomatis:
-
-```bash
-omniroute connect 192.168.0.15        # menciptakan token terikat, menyimpan konteks
-omniroute setup-codex                 # ← sekarang menggunakan katalog jarak jauh
-omniroute setup-opencode              # ← sama
-omniroute launch                      # ← Claude Code terhadap jarak jauh
-```
-
-Lihat [Mode Jarak Jauh](./REMOTE-MODE.md) untuk konteks, ruang lingkup, dan manajemen token.
-
----
-
-## Konvensi URL Dasar (alat yang menginginkan `/v1`)
-
-OmniRoute mengekspos permukaan OpenAI di `/v1`, permukaan Anthropic di root, dan permukaan Gemini asli di `/v1beta`. Setiap integrasi terhubung ke bentuk yang diharapkan alatnya (diverifikasi di sumber perintah):
-
-| Integrasi                                                                  | URL Dasar yang ditulis | `/v1`?                                             |
-| -------------------------------------------------------------------------- | ---------------------- | -------------------------------------------------- |
-| `setup-cline` (`openAiBaseUrl`)                                            | root                   | Tidak — Cline menambahkan `/v1/chat/completions`   |
-| `setup-goose` (`OPENAI_HOST`)                                              | root                   | Tidak — Goose menambahkan jalur                    |
-| `setup-aider` (`OPENAI_API_BASE`)                                          | root                   | Tidak — LiteLLM menambahkan `/v1/chat/completions` |
-| `setup-kilo`, `setup-roo`, `setup-continue`, `setup-crush`, `setup-cursor` | dengan `/v1`           | Ya                                                 |
-| `setup-claude` (`ANTHROPIC_BASE_URL`), `launch`                            | root                   | Tidak — Claude Code menambahkan `/v1/messages`     |
-| `setup-codex`, `launch-codex` (`model_providers.omniroute.base_url`)       | dengan `/v1`           | Ya                                                 |
-| `setup-qwen` (`modelProviders.openai[].baseUrl`)                           | dengan `/v1`           | Ya                                                 |
-| `run gemini` (`GOOGLE_GEMINI_BASE_URL`)                                    | root                   | Tidak — SDK menambahkan `/v1beta/models/…`         |
-
----
-
-## Menjaga dependensi native saat pembaruan: `--include=optional`
-
-Saat Anda memperbarui dengan `omniroute update` (setelah mengonfirmasi, atau dengan `--apply`),
-OmniRoute menjalankan instalasi dengan `--include=optional` yang sudah terintegrasi:
-
-```bash
-npm install -g omniroute@latest --include=optional
-```
-
-Ini **bukan** sebuah flag yang Anda berikan ke `omniroute update` — ini selalu diterapkan oleh
-updater. Ini menjamin bahwa `optionalDependencies` (`better-sqlite3`, `keytar`,
-`tls-client`, tumpukan LLMLingua SLM) tetap ada setelah pembaruan meskipun konfigurasi npm Anda
-memiliki `omit=optional` yang akan menghapus driver SQLite native dan binding OS-keyring secara diam-diam. Untuk melihat perintah yang tepat tanpa menerapkannya:
-
-```bash
-omniroute update --dry-run
-# [DRY RUN] Akan menjalankan: npm install -g omniroute@latest --include=optional
-```
-
-Flag `omniroute update` lainnya (terverifikasi dalam sumber): `--check` (keluar 1 jika
-ketinggalan), `--apply` (instal tanpa meminta), `--changelog`, `--no-backup`,
-`--yes`.
-
----
-
-## Google Gemini CLI melalui `omniroute run gemini`
-
-Kontrak diverifikasi terhadap `@google/gemini-cli` 0.50.0: CLI menghormati
-`GOOGLE_GEMINI_BASE_URL` dan mengeluarkan `POST /v1beta/models/<model>:generateContent`
-(dan `:streamGenerateContent?alt=sse`) terhadapnya — persis seperti permukaan Gemini native OmniRoute (`/v1beta`). `omniroute run gemini` menghubungkan itu secara otomatis:
-
-- `GOOGLE_GEMINI_BASE_URL` → URL dasar OmniRoute yang aktif (root, tanpa `/v1`);
-- `GEMINI_API_KEY` → kredensial OmniRoute yang terpecahkan (opsi/env/konteks);
-- **`GEMINI_CLI_HOME` sementara yang terisolasi** yang `.gemini/settings.json`
-  memilih otentikasi `gemini-api-key`, sehingga sesi OAuth Google yang disimpan (Code Assist)
-  tidak pernah menimpa peluncuran yang diarahkan oleh OmniRoute — dihapus setelah keluar;
-- **kebersihan env**: lingkungan anak dibersihkan dari `GOOGLE_API_KEY`,
-  `GOOGLE_GENAI_USE_VERTEXAI` dan `GOOGLE_GENAI_USE_GCA` (yang akan mengalihkan
-  otentikasi ke Vertex/Code Assist), dan `GEMINI_DEFAULT_AUTH_TYPE=gemini-api-key` diatur sebagai
-  cadangan — target `run` lainnya mendapatkan perlakuan yang sama untuk variabel yang bertentangan;
-- injeksi `--model <id>` dari `--provider`/`--model`.
-
-```bash
-omniroute run gemini --model glm/glm-5.2 -- --skip-trust -p "hello"
-```
-
-Pengaman kepercayaan workspace Gemini masih berlaku dalam mode headless — berikan
-`--skip-trust` (atau percayakan direktori secara interaktif) sendiri; peluncur
-dengan sengaja tidak melewatinya. Peluncur ini berbeda dari **registrasi ACP**
-(`src/lib/acp/registry.ts`, `gemini --acp`), yang tetap menjadi
-integrasi protokol agen untuk `/dashboard/acp-agents`.
-
----
-
-## Pembersihan asap nyata (opt-in)
-
-Regresi rencana peluncuran deterministik berjalan di CI (`tests/unit/cli/run-command.test.ts`,
-`tests/unit/cli/run-execution.test.ts`). Untuk memvalidasi biner REAL terhadap server
-OmniRoute yang REAL, ada harness opt-in di
-`tests/integration/upstream-cli-smoke.int.test.ts`. Ini tidak pernah berjalan secara otomatis
-(setiap sub-tes dilewati kecuali `RUN_CLI_SMOKE=1`), meneruskan kredensial melalui variabel-env
-NAMA (tidak pernah melalui nilai), menyensor string berbentuk kunci dari output yang tercatat,
-melewati target yang biner-nya tidak terinstal, dan mengklasifikasikan kegagalan sebagai
-otentikasi / upstream / konfigurasi alih-alih boolean kosong:
-
-```bash
-RUN_CLI_SMOKE=1 \
-OMNIROUTE_SMOKE_BASE_URL="http://localhost:20128" \
-OMNIROUTE_SMOKE_MODEL="<provider/model>" \
-OMNIROUTE_SMOKE_API_KEY_ENV="OMNIROUTE_API_KEY" \
-node --import tsx/esm --test tests/integration/upstream-cli-smoke.int.test.ts
-```
-
-Opsional: `OMNIROUTE_SMOKE_TARGETS="codex,opencode,qwen"` membatasi pembersihan;
-`OMNIROUTE_SMOKE_TIMEOUT_MS` menggantikan batas waktu 120 detik per-target.
-
----
-
-## Lihat juga
-
-- [Konfigurasi Kode Claude](./CLAUDE-CODE-CONFIGURATION.md) — panduan lebih dalam tentang Kode Claude
-- [Konfigurasi CLI Codex](./CODEX-CLI-CONFIGURATION.md) — pengaturan dasar `[model_providers.omniroute]` sekali saja
-- [Mode Jarak Jauh](./REMOTE-MODE.md) — konteks, token akses terbatas, mengendalikan server jarak jauh
-- [Referensi Alat CLI](../reference/CLI-TOOLS.md) — katalog lengkap alat yang didukung + halaman dasbor
-- [Panduan Pengaturan](./SETUP_GUIDE.md) — metode instalasi dan onboarding saat pertama kali menjalankan
diff --git a/docs/i18n/in/docs/guides/FEATURES.md b/docs/i18n/in/docs/guides/FEATURES.md
deleted file mode 100644
index 20ebfe2359..0000000000
--- a/docs/i18n/in/docs/guides/FEATURES.md
+++ /dev/null
@@ -1,269 +0,0 @@
-# OmniRoute — Dashboard Features Gallery (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../../docs/FEATURES.md) · 🇪🇸 [es](../../es/docs/FEATURES.md) · 🇫🇷 [fr](../../fr/docs/FEATURES.md) · 🇩🇪 [de](../../de/docs/FEATURES.md) · 🇮🇹 [it](../../it/docs/FEATURES.md) · 🇷🇺 [ru](../../ru/docs/FEATURES.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/FEATURES.md) · 🇯🇵 [ja](../../ja/docs/FEATURES.md) · 🇰🇷 [ko](../../ko/docs/FEATURES.md) · 🇸🇦 [ar](../../ar/docs/FEATURES.md) · 🇮🇳 [hi](../../hi/docs/FEATURES.md) · 🇮🇳 [in](../../in/docs/FEATURES.md) · 🇹🇭 [th](../../th/docs/FEATURES.md) · 🇻🇳 [vi](../../vi/docs/FEATURES.md) · 🇮🇩 [id](../../id/docs/FEATURES.md) · 🇲🇾 [ms](../../ms/docs/FEATURES.md) · 🇳🇱 [nl](../../nl/docs/FEATURES.md) · 🇵🇱 [pl](../../pl/docs/FEATURES.md) · 🇸🇪 [sv](../../sv/docs/FEATURES.md) · 🇳🇴 [no](../../no/docs/FEATURES.md) · 🇩🇰 [da](../../da/docs/FEATURES.md) · 🇫🇮 [fi](../../fi/docs/FEATURES.md) · 🇵🇹 [pt](../../pt/docs/FEATURES.md) · 🇷🇴 [ro](../../ro/docs/FEATURES.md) · 🇭🇺 [hu](../../hu/docs/FEATURES.md) · 🇧🇬 [bg](../../bg/docs/FEATURES.md) · 🇸🇰 [sk](../../sk/docs/FEATURES.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/FEATURES.md) · 🇮🇱 [he](../../he/docs/FEATURES.md) · 🇵🇭 [phi](../../phi/docs/FEATURES.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/FEATURES.md) · 🇨🇿 [cs](../../cs/docs/FEATURES.md) · 🇹🇷 [tr](../../tr/docs/FEATURES.md)
-
----
-
-Visual guide to every section of the OmniRoute dashboard.
-
----
-
-## 🔌 Providers
-
-
-![Providers Dashboard](screenshots/01-providers.png)
-
----
-
-## 🎨 Combos
-
-Create model routing combos with 13 strategies: priority, weighted, round-robin, random, least-used, cost-optimized, strict-random, auto, fill-first, p2c, lkgp, context-optimized, and **context-relay**. Each combo chains multiple models with automatic fallback and includes quick templates and readiness checks.
-
-Recent combo improvements:
-
-- **Structured combo builder** — create each step by selecting provider, model, and exact account/connection
-- **Repeated provider support** — reuse the same provider many times in one combo as long as the `(provider, model, connection)` tuple is unique
-- **Combo target health** — analytics and health surfaces now distinguish individual combo targets/steps instead of collapsing everything into model strings
-- **Composite tier ordering** — `defaultTier -> fallbackTier` now influences runtime execution/fallback order for top-level combo steps
-
-![Combos Dashboard](screenshots/02-combos.png)
-
----
-
-## 📊 Analytics
-
-Comprehensive usage analytics with token consumption, cost estimates, activity heatmaps, weekly distribution charts, and per-provider breakdowns.
-
-![Analytics Dashboard](screenshots/03-analytics.png)
-
----
-
-## 🏥 System Health
-
-Real-time monitoring: uptime, memory, version, latency percentiles (p50/p95/p99), cache statistics, provider circuit breaker states, active quota-monitored sessions, and combo target health.
-
-![Health Dashboard](screenshots/04-health.png)
-
----
-
-## 🔧 Translator Playground
-
-Four modes for debugging API translations: **Playground** (format converter), **Chat Tester** (live requests), **Test Bench** (batch tests), and **Live Monitor** (real-time stream).
-
-![Translator Playground](screenshots/05-translator.png)
-
----
-
-## 🎮 Model Playground _(v2.0.9+)_
-
-Test any model directly from the dashboard. Select provider, model, and endpoint, write prompts with Monaco Editor, stream responses in real-time, abort mid-stream, and view timing metrics.
-
----
-
-## 🎨 Themes _(v2.0.5+)_
-
-Customizable color themes for the entire dashboard. Choose from 7 preset colors (Coral, Blue, Red, Green, Violet, Orange, Cyan) or create a custom theme by picking any hex color. Supports light, dark, and system mode.
-
----
-
-## ⚙️ Settings
-
-Comprehensive settings panel with tabs:
-
-- **General** — System storage, backup management (export/import database)
-- **Appearance** — Theme selector (dark/light/system), color theme presets and custom colors, health log visibility, sidebar item visibility controls
-- **Security** — API endpoint protection, custom provider blocking, IP filtering, session info
-- **Routing** — Model aliases, background task degradation
-- **Resilience** — Rate limit persistence, circuit breaker tuning, auto-disable banned accounts, provider expiration monitoring, **Context Relay** handoff threshold and summary model configuration
-- **Advanced** — Configuration overrides, configuration audit trail, fallback degradation mode
-
-![Settings Dashboard](screenshots/06-settings.png)
-
----
-
-## 🔧 CLI Tools
-
-One-click configuration for AI coding tools: Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline, Continue, Cursor, and Factory Droid. Features automated config apply/reset, connection profiles, and model mapping.
-
-![CLI Tools Dashboard](screenshots/07-cli-tools.png)
-
----
-
-## 🤖 CLI Agents _(v2.0.11+)_
-
-Dashboard for discovering and managing CLI agents. Shows a grid of 17 built-in agents (Codex, Claude, Goose, OpenClaw, Aider, OpenCode, Cline, Qwen Code, ForgeCode, Amazon Q, Open Interpreter, Cursor CLI, Warp, **Windsurf**, **Devin CLI**, **Kimi Coding**, **Command Code**) with:
-
-- **Installation status** — Installed / Not Found with version detection
-- **Protocol badges** — stdio, HTTP, etc.
-- **Custom agents** — Register any CLI tool via form (name, binary, version command, spawn args)
-- **CLI Fingerprint Matching** — Per-provider toggle to match native CLI request signatures, reducing ban risk while preserving proxy IP
-
----
-
-## 🔗 Context Relay _(v3.5.5+)_
-
-A combo strategy that preserves session continuity when account rotation happens mid-conversation. Before the active account is exhausted, OmniRoute generates a structured handoff summary in the background. After the next request resolves to a different account, the summary is injected as a system message so the new account continues with full context.
-
-Configurable via combo-level or global settings:
-
-- **Handoff Threshold** — Quota usage percentage that triggers summary generation (default 85%)
-- **Max Messages For Summary** — How much recent history to condense
-- **Summary Model** — Optional override model for generating the handoff summary
-
-Currently supports Codex account rotation. See [Context Relay documentation](features/context-relay.md).
-
----
-
-## 🛡️ Proxy Hardening _(v3.5.5+)_
-
-Comprehensive proxy configuration enforcement across the entire request pipeline:
-
-- **Token Health Check** — Background OAuth refresh now resolves proxy config per connection, preventing failures in proxy-required environments
-- **API Key Validation** — Provider key validation (`POST /api/providers/validate`) routes through `runWithProxyContext`, honoring provider-level and global proxy settings
-- **undici Dispatcher Fix** — Proxy dispatchers use undici's own fetch implementation instead of Node's built-in fetch, resolving `invalid onRequestStart method` errors on Node.js 22
-- **Node.js Version Detection** — Login page proactively detects incompatible Node.js versions (24+) and displays a warning banner with instructions to use Node 22 LTS
-
----
-
-## 📧 Email Privacy Masking _(v3.5.6+)_
-
-OAuth account emails are now masked in the provider dashboard (e.g. `di*****@g****.com`) to prevent accidental exposure when sharing screenshots or recording demos. The full email address remains accessible via hover tooltip (`title` attribute).
-
----
-
-## 👁️ Model Visibility Toggle _(v3.5.6+)_
-
-The provider page model list now includes:
-
-- **Real-time search/filter bar** — Quickly find specific models
-- **Per-model visibility toggle** (👁 icon) — Hidden models are grayed out and excluded from the `/v1/models` catalog
-- **Active-count badge** (`N/M active`) — Shows at a glance how many models are enabled vs total
-
----
-
-## 🔧 OAuth Env Repair _(v3.6.1+)_
-
-One-click "Repair env" action for OAuth providers that restores missing environment variables and fixes broken auth state. Accessible from `Dashboard → Providers → [OAuth Provider] → Repair env`. Automatically detects and repairs:
-
-- Missing OAuth client credentials
-- Corrupted env file entries
-- Backup path sanitization
-
----
-
-## 🗑️ Uninstall / Full Uninstall _(v3.6.2+)_
-
-Clean removal scripts for all installation methods:
-
-| Command                  | Action                                                                              |
-| ------------------------ | ----------------------------------------------------------------------------------- |
-| `npm run uninstall`      | Removes the system app but **keeps your DB and configurations** in `~/.omniroute`.  |
-| `npm run uninstall:full` | Removes the app AND permanently **erases all configurations, keys, and databases**. |
-
----
-
-## 🖼️ Media _(v2.0.3+)_
-
-Generate images, videos, and music from the dashboard. Supports OpenAI, xAI, Together, Hyperbolic, SD WebUI, ComfyUI, AnimateDiff, Stable Audio Open, and MusicGen.
-
----
-
-## 📝 Request Logs
-
-Real-time request logging with filtering by provider, model, account, and API key. Shows status codes, token usage, latency, and response details.
-
-![Usage Logs](screenshots/08-usage.png)
-
----
-
-## 🌐 API Endpoint
-
-Your unified API endpoint with capability breakdown: Chat Completions, Responses API, Embeddings, Image Generation, Reranking, Audio Transcription, Text-to-Speech, Moderations, and registered API keys. Cloudflare Quick Tunnel integration and cloud proxy support for remote access.
-
-![Endpoint Dashboard](screenshots/09-endpoint.png)
-
----
-
-## 🔑 API Key Management
-
-Create, scope, and revoke API keys. Each key can be restricted to specific models/providers with full access or read-only permissions. Visual key management with usage tracking.
-
----
-
-## 📋 Audit Log
-
-Administrative action tracking with filtering by action type, actor, target, IP address, and timestamp. Full security event history.
-
----
-
-## 🖥️ Desktop Application
-
-Native Electron desktop app for Windows, macOS, and Linux. Run OmniRoute as a standalone application with system tray integration, offline support, auto-update, and one-click install.
-
-Key features:
-
-- Server readiness polling (no blank screen on cold start)
-- System tray with port management
-- Content Security Policy
-- Single-instance lock
-- Auto-update on restart
-- Platform-conditional UI (macOS traffic lights, Windows/Linux default titlebar)
-- Hardened Electron build packaging — symlinked `node_modules` in the standalone bundle is detected and rejected before packaging, preventing runtime dependency on the build machine (v2.5.5+)
-- **Graceful shutdown** — Electron `before-quit` shuts down Next.js cleanly, preventing SQLite WAL database locks (v3.6.2+)
-
-📖 See [`electron/README.md`](../electron/README.md) for full documentation.
-
----
-
-## 🌐 V1 WebSocket Bridge _(v3.6.6+)_
-
-OmniRoute now supports **OpenAI-compatible WebSocket clients** via the `/v1/ws` upgrade endpoint. The custom `scripts/v1-ws-bridge.mjs` server wraps Next.js and upgrades WS connections to full bidirectional streaming sessions. Authentication uses the same API key or session cookie as HTTP requests.
-
-Key behaviours:
-
-- WS upgrade validated by `src/lib/ws/handshake.ts` before the connection is established
-- Streams terminated cleanly on session close or upstream error
-- Works alongside the existing HTTP+SSE streaming path simultaneously
-
----
-
-## 🔑 Sync Tokens & Config Bundle _(v3.6.6+)_
-
-Multi-device and external operator access is now possible via **scoped sync tokens**:
-
-- **`POST /api/sync/tokens`** — Issue a new sync token (scoped, with optional expiry)
-- **`DELETE /api/sync/tokens/:id`** — Revoke a token
-- **`GET /api/sync/bundle`** — Download a versioned, ETag-keyed JSON snapshot of all non-sensitive settings (passwords redacted)
-
-The config bundle is built by `src/lib/sync/bundle.ts`. Consumers compare the `ETag` response header to detect changes without re-downloading the full payload.
-
----
-
-## 🧠 GLM Thinking Preset _(v3.6.6+)_
-
-**GLM Thinking (`glmt`)** is now a registered first-class provider: 65 536 max output tokens, 24 576 thinking budget, 900 s default timeout, Claude-compatible API format, and shared usage sync with the GLM family.
-
-**Hybrid token counting** also lands in v3.6.6: when a Claude-compatible provider exposes `/messages/count_tokens`, OmniRoute calls it before large requests with graceful estimation fallback.
-
----
-
-## 🛡️ Safe Outbound Fetch & SSRF Guard _(v3.6.6+)_
-
-All provider validation and model discovery calls now go through a two-layer outbound guard:
-
-1. **URL guard** (`src/shared/network/outboundUrlGuard.ts`) — Blocks private/loopback/link-local IP ranges before the socket is opened.
-2. **Safe fetch wrapper** (`src/shared/network/safeOutboundFetch.ts`) — Applies the URL guard, normalises timeouts, and retries transient errors with exponential backoff.
-
-Guard violations surface as HTTP 422 (`URL_GUARD_BLOCKED`) and are written to the compliance audit log via `providerAudit.ts`.
-
----
-
-## 🔄 Cooldown-Aware Retries _(v3.6.6+)_
-
-Chat requests now **automatically retry** when an upstream provider returns a model-scoped cooldown. Configurable via `REQUEST_RETRY` (default: 2) and `MAX_RETRY_INTERVAL_SEC` (default: 30 s). Rate-limit header learning improved across `x-ratelimit-reset-requests`, `x-ratelimit-reset-tokens`, and `Retry-After` — per-model cooldown state is visible in the Resilience dashboard.
-
----
-
-## 📋 Compliance Audit v2 _(v3.6.6+)_
-
-The audit log has been expanded with cursor-based pagination, request context enrichment (request ID, user agent, IP), structured auth events, provider CRUD events with diff context, and SSRF-blocked validation logging. New events emitted by `src/lib/compliance/providerAudit.ts`.
diff --git a/docs/i18n/in/docs/guides/I18N.md b/docs/i18n/in/docs/guides/I18N.md
deleted file mode 100644
index 909472adf2..0000000000
--- a/docs/i18n/in/docs/guides/I18N.md
+++ /dev/null
@@ -1,445 +0,0 @@
-# i18n — Internationalization Guide (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../../docs/I18N.md) · 🇪🇸 [es](../../es/docs/I18N.md) · 🇫🇷 [fr](../../fr/docs/I18N.md) · 🇩🇪 [de](../../de/docs/I18N.md) · 🇮🇹 [it](../../it/docs/I18N.md) · 🇷🇺 [ru](../../ru/docs/I18N.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/I18N.md) · 🇯🇵 [ja](../../ja/docs/I18N.md) · 🇰🇷 [ko](../../ko/docs/I18N.md) · 🇸🇦 [ar](../../ar/docs/I18N.md) · 🇮🇳 [hi](../../hi/docs/I18N.md) · 🇮🇳 [in](../../in/docs/I18N.md) · 🇹🇭 [th](../../th/docs/I18N.md) · 🇻🇳 [vi](../../vi/docs/I18N.md) · 🇮🇩 [id](../../id/docs/I18N.md) · 🇲🇾 [ms](../../ms/docs/I18N.md) · 🇳🇱 [nl](../../nl/docs/I18N.md) · 🇵🇱 [pl](../../pl/docs/I18N.md) · 🇸🇪 [sv](../../sv/docs/I18N.md) · 🇳🇴 [no](../../no/docs/I18N.md) · 🇩🇰 [da](../../da/docs/I18N.md) · 🇫🇮 [fi](../../fi/docs/I18N.md) · 🇵🇹 [pt](../../pt/docs/I18N.md) · 🇷🇴 [ro](../../ro/docs/I18N.md) · 🇭🇺 [hu](../../hu/docs/I18N.md) · 🇧🇬 [bg](../../bg/docs/I18N.md) · 🇸🇰 [sk](../../sk/docs/I18N.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/I18N.md) · 🇮🇱 [he](../../he/docs/I18N.md) · 🇵🇭 [phi](../../phi/docs/I18N.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/I18N.md) · 🇨🇿 [cs](../../cs/docs/I18N.md) · 🇹🇷 [tr](../../tr/docs/I18N.md)
-
----
-
-OmniRoute supports **30 languages** with full dashboard UI translation, translated documentation, and RTL support for Arabic and Hebrew.
-
-## Quick Reference
-
-| Task                   | Command                                                                                 |
-| ---------------------- | --------------------------------------------------------------------------------------- |
-| Generate translations  | `node scripts/i18n/generate-multilang.mjs messages`                                     |
-| Translate docs (LLM)   | `python3 scripts/i18n_autotranslate.py --api-url <url> --api-key <key> --model <model>` |
-| Validate a locale      | `python3 scripts/validate_translation.py quick -l cs`                                   |
-| Check code keys        | `python3 scripts/check_translations.py`                                                 |
-| Generate QA report     | `node scripts/i18n/generate-qa-checklist.mjs`                                           |
-| Visual QA (Playwright) | `node scripts/i18n/run-visual-qa.mjs`                                                   |
-
-## आर्किटेक्चर
-
-![Incremental hash-based i18n pipeline](./diagrams/exported/i18n-flow.svg)
-
-> Source: [diagrams/i18n-flow.mmd](./diagrams/i18n-flow.mmd)
-
-### Source of Truth
-
-- **UI strings**: `src/i18n/messages/en.json` (English source, ~2800 keys)
-- **Locale files**: `src/i18n/messages/{locale}.json` (30 translations)
-- **Framework**: `next-intl` with cookie-based locale resolution
-- **Config**: `src/i18n/config.ts` — defines all 30 locales, language names, flags
-
-### Runtime Flow
-
-1. User selects language → `NEXT_LOCALE` cookie set
-2. `src/i18n/request.ts` resolves locale: cookie → `Accept-Language` header → fallback `en`
-3. Dynamic import loads `messages/{locale}.json`
-4. Components use `useTranslations("namespace")` and `t("key")`
-
-### Supported Locales
-
-| Code    | Language             | RTL | Google Translate Code |
-| ------- | -------------------- | --- | --------------------- |
-| `ar`    | العربية              | Yes | `ar`                  |
-| `bg`    | Български            | No  | `bg`                  |
-| `cs`    | Čeština              | No  | `cs`                  |
-| `da`    | Dansk                | No  | `da`                  |
-| `de`    | Deutsch              | No  | `de`                  |
-| `es`    | Español              | No  | `es`                  |
-| `fi`    | Suomi                | No  | `fi`                  |
-| `fr`    | Français             | No  | `fr`                  |
-| `he`    | עברית                | Yes | `iw`                  |
-| `hi`    | हिन्दी               | No  | `hi`                  |
-| `hu`    | Magyar               | No  | `hu`                  |
-| `id`    | Bahasa Indonesia     | No  | `id`                  |
-| `it`    | Italiano             | No  | `it`                  |
-| `ja`    | 日本語               | No  | `ja`                  |
-| `ko`    | 한국어               | No  | `ko`                  |
-| `ms`    | Bahasa Melayu        | No  | `ms`                  |
-| `nl`    | Nederlands           | No  | `nl`                  |
-| `no`    | Norsk                | No  | `no`                  |
-| `phi`   | Filipino             | No  | `tl`                  |
-| `pl`    | Polski               | No  | `pl`                  |
-| `pt`    | Português (Portugal) | No  | `pt`                  |
-| `pt-BR` | Português (Brasil)   | No  | `pt`                  |
-| `ro`    | Română               | No  | `ro`                  |
-| `ru`    | Русский              | No  | `ru`                  |
-| `sk`    | Slovenčina           | No  | `sk`                  |
-| `sv`    | Svenska              | No  | `sv`                  |
-| `th`    | ไทย                  | No  | `th`                  |
-| `tr`    | Türkçe               | No  | `tr`                  |
-| `uk-UA` | Українська           | No  | `uk`                  |
-| `vi`    | Tiếng Việt           | No  | `vi`                  |
-| `zh-CN` | 中文 (简体)          | No  | `zh-CN`               |
-
-## Adding a New Language
-
-### 1. Register the Locale
-
-Edit `src/i18n/config.ts`:
-
-```ts
-// Add to LOCALES array
-"xx",
-// Add to LANGUAGES array
-{ code: "xx", label: "XX", name: "Language Name", flag: "🏳️" },
-```
-
-### 2. Add to Generator
-
-Edit `scripts/i18n/generate-multilang.mjs` — add entry to `LOCALE_SPECS`:
-
-```js
-{
-  code: "xx",
-  googleTl: "xx",
-  label: "XX",
-  flag: "🏳️",
-  languageName: "Language Name",
-  readmeName: "Language Name",
-  docsName: "Language Name",
-},
-```
-
-### 3. Generate Initial Translation
-
-```bash
-node scripts/i18n/generate-multilang.mjs messages
-```
-
-This creates `src/i18n/messages/xx.json` auto-translated from `en.json` via Google Translate.
-
-### 4. Review & Fix Auto-Translations
-
-Auto-translations are a starting point. Review manually for:
-
-- Technical accuracy
-- Context-appropriate terminology
-- Proper handling of placeholders (`{count}`, `{value}`, etc.)
-
-### 5. Validate
-
-```bash
-python3 scripts/validate_translation.py quick -l xx
-python3 scripts/validate_translation.py diff common -l xx
-```
-
-### 6. Generate Translated Documentation
-
-```bash
-node scripts/i18n/generate-multilang.mjs docs
-```
-
-## Auto-Translation Pipeline
-
-### generate-multilang.mjs (Google Translate)
-
-**Primary auto-translation engine** — uses Google Translate free API to generate translations for UI strings, READMEs, and documentation.
-
-```bash
-node scripts/i18n/generate-multilang.mjs [messages|readme|docs|all]
-```
-
-| Mode       | What it does                                                                  |
-| ---------- | ----------------------------------------------------------------------------- |
-| `messages` | Translates missing keys in `src/i18n/messages/{locale}.json` from `en.json`   |
-| `readme`   | Translates `README.md` into all locales as `README.{code}.md` in project root |
-| `docs`     | Translates `DOC_SOURCE_FILES` into `docs/i18n/{locale}/{docName}`             |
-| `all`      | Runs all three modes                                                          |
-
-**Features:**
-
-- **Text protection**: Masks code blocks (` ``` `), inline code (`` ` ``), markdown links/images (`[text](url)`), HTML tags, tables, and ICU placeholders (`{count}`, `{value}`, `{total}`, etc.) before translation, then restores them
-- **Chunked batching**: Joins multiple strings with `__OMNIROUTE_I18N_SEPARATOR__` delimiters to minimize API calls (max 1800 chars per request)
-- **In-memory cache**: Avoids redundant API calls for repeated strings within a session
-- **Retry logic**: Exponential backoff (up to 5 attempts with 300ms × attempt delay) for 429/5xx errors
-- **Timeout**: 20 seconds per request
-- **Skip existing**: If target file already exists, it is NOT overwritten
-
-**Important behaviors:**
-
-- `docs/i18n/README.md` is **regenerated** each run — it's an auto-generated index of all docs
-- Root `README.{code}.md` files are only created if they don't exist (skips locales in `EXISTING_README_CODES`)
-- Language bars (`🌐 **Languages:** ...`) are automatically inserted/updated in all translated docs
-
-### i18n_autotranslate.py (LLM-based)
-
-**Secondary translator** — uses any OpenAI-compatible LLM API (including OmniRoute itself) to translate existing `docs/i18n/` markdown files. Best for polishing or re-translating docs with better quality than Google Translate.
-
-```bash
-python3 scripts/i18n_autotranslate.py \
-  --api-url http://localhost:20128/v1 \
-  --api-key sk-your-key \
-  --model gpt-4o
-```
-
-**Features:**
-
-- Scans `docs/i18n/` markdown files for English paragraphs
-- Skips code blocks, tables, and already-translated content
-- Sends paragraphs to LLM with technical translation system prompt
-- Supports all 30 languages
-
-## Validation & QA
-
-### validate_translation.py
-
-**Translation validator** — compares any locale JSON against `en.json` and reports issues.
-
-```bash
-# Quick check (counts only)
-python3 scripts/validate_translation.py quick -l cs
-# Output:
-# Missing: 0
-# Untranslated: 0
-# Ignored (UNTRANSLATABLE_KEYS): 236
-
-# Detailed diff by category
-python3 scripts/validate_translation.py diff common -l cs
-python3 scripts/validate_translation.py diff settings -l cs
-
-# Export to CSV
-python3 scripts/validate_translation.py csv -l cs > report.csv
-
-# Export to Markdown
-python3 scripts/validate_translation.py md -l cs > report.md
-
-# Full report (default)
-python3 scripts/validate_translation.py -l cs
-```
-
-**Detects:**
-
-- **Missing keys** — keys in `en.json` but not in locale file
-- **Extra keys** — keys in locale file but not in `en.json`
-- **Untranslated keys** — keys where locale value equals English source (excluding allowlist)
-- **Placeholder mismatches** — ICU placeholders that don't match between source and translation
-
-**Exit codes:**
-| Code | Meaning |
-|------|---------|
-| 0 | OK |
-| 1 | Generic error |
-| 2 | Missing strings (hard error) |
-| 3 | Untranslated warning (soft) |
-
-**Environment:** Set `TRANSLATION_LANG=cs` or use `-l cs` flag.
-
-### check_translations.py
-
-**Code-to-JSON key checker** — scans `src/**/*.tsx` and `src/**/*.ts` for `useTranslations()` calls and verifies all referenced keys exist in `en.json`.
-
-```bash
-# Basic check
-python3 scripts/check_translations.py
-
-# Verbose output
-python3 scripts/check_translations.py --verbose
-
-# Auto-fix (adds missing keys to en.json)
-python3 scripts/check_translations.py --fix
-```
-
-### generate-qa-checklist.mjs
-
-**Static analysis QA** — scans Next.js page files for i18n risk metrics and generates a Markdown report.
-
-```bash
-node scripts/i18n/generate-qa-checklist.mjs
-```
-
-**Checks:**
-
-- Fixed-width class usage (overflow risk)
-- Directional left/right classes (RTL risk)
-- Clipping-prone patterns
-- Locale parity (missing/extra keys vs `en.json`)
-- README language selector bars in priority locales (`es`, `fr`, `de`, `ja`, `ar`)
-
-**Output:** `docs/reports/i18n-qa-checklist-{date}.md`
-
-### run-visual-qa.mjs
-
-**Visual QA via Playwright** — takes screenshots of all dashboard routes in multiple locales and viewports, then evaluates page health.
-
-```bash
-# Default: es, fr, de, ja, ar on localhost:20128
-node scripts/i18n/run-visual-qa.mjs
-
-# Custom base URL and locales
-QA_BASE_URL=http://staging.example.com QA_LOCALES=de,fr node scripts/i18n/run-visual-qa.mjs
-
-# Custom routes
-QA_ROUTES=/dashboard/settings,/dashboard/providers node scripts/i18n/run-visual-qa.mjs
-```
-
-**Detects:**
-
-- Text overflow
-- Element clipping
-- RTL layout mismatches
-
-**Output:** `docs/reports/i18n-visual-qa-{date}.md` + JSON report
-
-## Managing Untranslatable Keys
-
-### untranslatable-keys.json
-
-**File:** `scripts/i18n/untranslatable-keys.json`
-
-Allowlist of keys that should remain identical to English source. Used by `validate_translation.py` to avoid false-positive "untranslated" warnings.
-
-```json
-{
-  "description": "Keys that should remain untranslated...",
-  "keys": [
-    "common.model",
-    "common.oauth",
-    "health.cpu",
-    ...
-  ]
-}
-```
-
-**What belongs here:**
-
-- Brand/product names: `landing.brandName`, `common.social-github`
-- Technical terms/acronyms: `health.cpu`, `mcpDashboard.pid`, `settings.ai`
-- ICU/format strings: `apiManager.modelsCount`, `health.millisecondsShort`
-- Placeholder values: `providers.openaiBaseUrlPlaceholder`, `cliTools.baseUrlPlaceholder`
-- Protocol names: `common.http`, `common.oauth`, `providers.oauth2Label`
-- Navigation sections: `sidebar.primarySection`, `sidebar.cliSection`
-
-**To add a key:** Edit the `keys` array in `scripts/i18n/untranslatable-keys.json` and re-run validation.
-
-## CI Integration
-
-### GitHub Actions (`.github/workflows/ci.yml`)
-
-The CI pipeline validates all locales on every push and PR:
-
-1. **`i18n-matrix` job** — dynamically discovers all locale files (excluding `en.json`)
-2. **`i18n` job** — runs `validate_translation.py quick -l '<lang>'` for each locale in parallel
-3. **`ci-summary` job** — aggregates results into a dashboard summary
-
-```yaml
-# i18n-matrix: discovers languages
-LANGS=$(ls src/i18n/messages/*.json | xargs -n1 basename | sed 's/.json$//' | grep -v '^en$')
-
-# i18n: validates each language
-python3 scripts/validate_translation.py quick -l '${{ matrix.lang }}'
-```
-
-**Dashboard output:**
-
-```
-## 🌍 Translations
-| Metric | Value |
-|--------|------|
-| Languages checked | 30 |
-| Total untranslated | 0 |
-
-✅ All translations complete
-```
-
-## File Structure
-
-```
-src/i18n/
-├── config.ts                    # Locale definitions (30 locales, RTL config)
-├── request.ts                   # Runtime locale resolution
-└── messages/
-    ├── en.json                  # Source of truth (~2800 keys)
-    ├── cs.json                  # Czech translation
-    ├── de.json                  # German translation
-    └── ...                      # 30 locale files total
-
-scripts/
-├── i18n/
-│   ├── generate-multilang.mjs   # Auto-translation engine (Google Translate, 888 lines)
-│   ├── generate-qa-checklist.mjs # Static analysis QA
-│   ├── run-visual-qa.mjs        # Playwright visual QA
-│   └── untranslatable-keys.json # Allowlist for validation (236 keys)
-├── validate_translation.py      # Translation validator
-├── check_translations.py        # Code-to-JSON key checker
-└── i18n_autotranslate.py        # LLM-based doc translator
-
-.github/workflows/
-└── ci.yml                       # i18n validation in CI matrix
-
-docs/
-├── I18N.md                      # This file — i18n toolchain documentation
-├── i18n/
-│   ├── README.md                # Auto-generated language index
-│   ├── cs/                      # Czech docs
-│   │   └── docs/
-│   │       ├── I18N.md          # Czech translation of this file
-│   │       └── ...
-│   ├── de/                      # German docs
-│   └── ...                      # 30 locale directories
-└── reports/
-    ├── i18n-qa-checklist-*.md   # Static analysis reports
-    └── i18n-visual-qa-*.md      # Visual QA reports
-```
-
-## Best Practices
-
-### When Editing Translations
-
-1. **Always edit `en.json` first** — it's the source of truth
-2. **Run `generate-multilang.mjs messages`** to propagate new keys to all locales
-3. **Review auto-translations** — Google Translate is a starting point, not final
-4. **Validate before committing** — `python3 scripts/validate_translation.py quick -l <lang>`
-5. **Update `untranslatable-keys.json`** if a key should remain in English
-
-### Placeholder Safety
-
-- ICU placeholders (`{count}`, `{value}`, `{total}`, `{seconds}`) must be preserved exactly
-- Plural formats (`{count, plural, one {# model} other {# models}}`) must maintain structure
-- The validator detects placeholder mismatches automatically
-
-### Adding New Translation Keys in Code
-
-```tsx
-// Use namespaced keys
-const t = useTranslations("settings");
-t("cacheSettings"); // maps to settings.cacheSettings in JSON
-
-// Run check_translations.py to verify keys exist
-python3 scripts/check_translations.py --verbose
-```
-
-### RTL Considerations
-
-- Arabic (`ar`) and Hebrew (`he`) are RTL locales
-- Avoid hardcoded `left`/`right` CSS — use `start`/`end` logical properties
-- Visual QA catches RTL layout mismatches via `run-visual-qa.mjs`
-
-## Known Issues & History
-
-### `in.json` → `hi.json` Fix
-
-The generator originally used `code: "in"` (deprecated Google Translate code) for Hindi instead of the correct ISO 639-1 `hi`. This created an orphaned `in.json` duplicate of `hi.json`. Fixed by changing `code: "in"` to `code: "hi"` in `generate-multilang.mjs` and removing the orphaned file.
-
-### `docs/i18n/README.md` Is Auto-Generated
-
-The `docs/i18n/README.md` file is completely regenerated by `generate-multilang.mjs docs`. Any manual edits will be lost. Use `docs/guides/I18N.md` (this file) for hand-written documentation that should persist.
-
-### External Untranslatable Keys List
-
-The `untranslatable-keys.json` allowlist was moved from an inline Python set in `validate_translation.py` to an external JSON file for easier maintenance. The validator loads it at runtime.
-
-### `generate-multilang.mjs` Hindi Code Fix
-
-The generator originally used `code: "in"` (deprecated Google Translate code) for Hindi instead of the correct ISO 639-1 `hi`. This was introduced in upstream commit `952b0b22c` by `diegosouzapw`. Fixed by changing `code: "in"` to `code: "hi"` in the `LOCALE_SPECS` array and removing the orphaned `in.json` file.
-
-### `validate_translation.py` Ignored Count Output
-
-The `quick` check now displays the count of ignored keys from `untranslatable-keys.json`:
-
-```
-Missing: 0
-Untranslated: 0
-Ignored (UNTRANSLATABLE_KEYS): 236
-```
diff --git a/docs/i18n/in/docs/guides/TROUBLESHOOTING.md b/docs/i18n/in/docs/guides/TROUBLESHOOTING.md
deleted file mode 100644
index 7269a1151a..0000000000
--- a/docs/i18n/in/docs/guides/TROUBLESHOOTING.md
+++ /dev/null
@@ -1,340 +0,0 @@
-# Troubleshooting (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../../docs/TROUBLESHOOTING.md) · 🇪🇸 [es](../../es/docs/TROUBLESHOOTING.md) · 🇫🇷 [fr](../../fr/docs/TROUBLESHOOTING.md) · 🇩🇪 [de](../../de/docs/TROUBLESHOOTING.md) · 🇮🇹 [it](../../it/docs/TROUBLESHOOTING.md) · 🇷🇺 [ru](../../ru/docs/TROUBLESHOOTING.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/TROUBLESHOOTING.md) · 🇯🇵 [ja](../../ja/docs/TROUBLESHOOTING.md) · 🇰🇷 [ko](../../ko/docs/TROUBLESHOOTING.md) · 🇸🇦 [ar](../../ar/docs/TROUBLESHOOTING.md) · 🇮🇳 [hi](../../hi/docs/TROUBLESHOOTING.md) · 🇮🇳 [in](../../in/docs/TROUBLESHOOTING.md) · 🇹🇭 [th](../../th/docs/TROUBLESHOOTING.md) · 🇻🇳 [vi](../../vi/docs/TROUBLESHOOTING.md) · 🇮🇩 [id](../../id/docs/TROUBLESHOOTING.md) · 🇲🇾 [ms](../../ms/docs/TROUBLESHOOTING.md) · 🇳🇱 [nl](../../nl/docs/TROUBLESHOOTING.md) · 🇵🇱 [pl](../../pl/docs/TROUBLESHOOTING.md) · 🇸🇪 [sv](../../sv/docs/TROUBLESHOOTING.md) · 🇳🇴 [no](../../no/docs/TROUBLESHOOTING.md) · 🇩🇰 [da](../../da/docs/TROUBLESHOOTING.md) · 🇫🇮 [fi](../../fi/docs/TROUBLESHOOTING.md) · 🇵🇹 [pt](../../pt/docs/TROUBLESHOOTING.md) · 🇷🇴 [ro](../../ro/docs/TROUBLESHOOTING.md) · 🇭🇺 [hu](../../hu/docs/TROUBLESHOOTING.md) · 🇧🇬 [bg](../../bg/docs/TROUBLESHOOTING.md) · 🇸🇰 [sk](../../sk/docs/TROUBLESHOOTING.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/TROUBLESHOOTING.md) · 🇮🇱 [he](../../he/docs/TROUBLESHOOTING.md) · 🇵🇭 [phi](../../phi/docs/TROUBLESHOOTING.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/TROUBLESHOOTING.md) · 🇨🇿 [cs](../../cs/docs/TROUBLESHOOTING.md) · 🇹🇷 [tr](../../tr/docs/TROUBLESHOOTING.md)
-
----
-
-Common problems and solutions for OmniRoute.
-
----
-
-## Quick Fixes
-
-| Problem                                             | Solution                                                                                                                                                 |
-| --------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| First login not working                             | Set `INITIAL_PASSWORD` in `.env` (no hardcoded default)                                                                                                  |
-| Dashboard opens on wrong port                       | Set `PORT=20128` and `NEXT_PUBLIC_BASE_URL=http://localhost:20128`                                                                                       |
-| No logs written to disk                             | Set `APP_LOG_TO_FILE=true` and verify call log capture is enabled                                                                                        |
-| EACCES: permission denied                           | Set `DATA_DIR=/path/to/writable/dir` to override `~/.omniroute`                                                                                          |
-| Routing strategy not saving                         | Update to v1.4.11+ (Zod schema fix for settings persistence)                                                                                             |
-| Login crash / blank page                            | Check Node.js version — see [Node.js Compatibility](#nodejs-compatibility) below                                                                         |
-| `dlopen` / `slice is not valid mach-o file` (macOS) | Run `cd $(npm root -g)/omniroute/app && npm rebuild better-sqlite3 && omniroute` — see [macOS native module rebuild](#macos-native-module-rebuild) below |
-| Proxy "fetch failed"                                | Ensure proxy config is set at the correct level — see [Proxy Issues](#proxy-issues) below                                                                |
-
----
-
-## Node.js Compatibility
-
-<a name="nodejs-compatibility"></a>
-
-### Login page crashes or shows "Module self-registration" error
-
-**Cause:** You are running a Node.js version outside OmniRoute's approved secure runtime floor. The most common case is running an older Node 20, 22, or 24 patch level that falls below the patched security floor OmniRoute requires.
-
-**Symptoms:**
-
-- Login page shows a blank screen or a server error
-- Console shows `Error: Module did not self-register` or similar native binding errors
-- The login page shows an **orange warning banner** with your Node version if the runtime is outside the supported secure policy
-
-**Fix:**
-
-1. Install a supported Node.js LTS release (recommended: Node.js 24.x):
-   ```bash
-   nvm install 24
-   nvm use 24
-   ```
-2. Verify your version: `node --version` should show `v24.0.0` or newer on the 24.x LTS line
-3. Reinstall OmniRoute: `npm install -g omniroute`
-4. Restart: `omniroute`
-
-> **Supported secure versions:** `>=20.20.2 <21`, `>=22.22.2 <23`, or `>=24.0.0 <25`. Node.js 24.x LTS (Krypton) is fully supported.
-
-### macOS: `dlopen` / "slice is not valid mach-o file"
-
-<a name="macos-native-module-rebuild"></a>
-
-**Cause:** After a global `npm install -g omniroute`, the `better-sqlite3` native binary inside the package may have been compiled for a different architecture or Node.js ABI than what is running locally. This is common on macOS (both Apple Silicon and Intel) when the pre-built binary does not match your environment.
-
-**Symptoms:**
-
-- Server fails immediately on startup with a `dlopen` error
-- Error contains `slice is not valid mach-o file`
-- Full example:
-
-```
-dlopen(/Users/<user>/.nvm/versions/node/v24.14.1/lib/node_modules/omniroute/app/node_modules/better-sqlite3/build/Release/better_sqlite3.node, 0x0001): tried: '...' (slice is not valid mach-o file)
-```
-
-**Fix — rebuild for your local environment (no Node.js downgrade required):**
-
-```bash
-cd $(npm root -g)/omniroute/app
-npm rebuild better-sqlite3
-omniroute
-```
-
-> **Note:** This recompiles the native binding against your local Node.js version and CPU architecture, resolving the binary mismatch. The officially supported range is **`>=20.20.2 <21`, `>=22.22.2 <23`, or `>=24.0.0 <25`** (`engines` field in `package.json`). Node.js 24.x LTS (Krypton) is fully supported with `better-sqlite3` v12.x.
-
----
-
-## Proxy Issues
-
-<a name="proxy-issues"></a>
-
-### Provider validation shows "fetch failed"
-
-**Cause:** The API key validation endpoint (`POST /api/providers/validate`) was previously bypassing proxy configuration, causing failures in environments that require proxy routing.
-
-**Fix (v3.5.5+):** This is now fixed. Provider validation routes through `runWithProxyContext`, honoring provider-level and global proxy settings automatically.
-
-### Token health check fails with "fetch failed"
-
-**Cause:** Background OAuth token refresh was not resolving proxy configuration per connection.
-
-**Fix (v3.5.5+):** The token health check scheduler now resolves proxy config per connection before attempting refresh. Update to v3.5.5+.
-
-### SOCKS5 proxy returns "invalid onRequestStart method"
-
-**Cause:** On Node.js 22, the undici@8 dispatcher is incompatible with Node's built-in `fetch()` implementation.
-
-**Fix (v3.5.5+):** OmniRoute now uses undici's own `fetch()` function when a proxy dispatcher is active, ensuring consistent behavior. Update to v3.5.5+.
-
----
-
-## Provider Issues
-
-### "Language model did not provide messages"
-
-**Cause:** Provider quota exhausted.
-
-**Fix:**
-
-1. Check dashboard quota tracker
-2. Use a combo with fallback tiers
-3. Switch to cheaper/free tier
-
-### Rate Limiting
-
-**Cause:** Subscription quota exhausted.
-
-**Fix:**
-
-- Add fallback: `cc/claude-opus-4-6 → glm/glm-4.7 → if/kimi-k2-thinking`
-- Use GLM/MiniMax as cheap backup
-
-### OAuth Token Expired
-
-OmniRoute auto-refreshes tokens. If issues persist:
-
-1. Dashboard → Provider → Reconnect
-2. Delete and re-add the provider connection
-
----
-
-## Cloud Issues
-
-### Cloud Sync Errors
-
-1. Verify `BASE_URL` points to your running instance (e.g., `http://localhost:20128`)
-2. Verify `CLOUD_URL` points to your cloud endpoint (e.g., `https://omniroute.dev`)
-3. Keep `NEXT_PUBLIC_*` values aligned with server-side values
-
-### Cloud `stream=false` Returns 500
-
-**Symptom:** `Unexpected token 'd'...` on cloud endpoint for non-streaming calls.
-
-**Cause:** Upstream returns SSE payload while client expects JSON.
-
-**Workaround:** Use `stream=true` for cloud direct calls. Local runtime includes SSE→JSON fallback.
-
-### Cloud Says Connected but "Invalid API key"
-
-1. Create a fresh key from local dashboard (`/api/keys`)
-2. Run cloud sync: Enable Cloud → Sync Now
-3. Old/non-synced keys can still return `401` on cloud
-
----
-
-## Docker Issues
-
-### CLI Tool Shows Not Installed
-
-1. Check runtime fields: `curl http://localhost:20128/api/cli-tools/runtime/codex | jq`
-2. For portable mode: use image target `runner-cli` (bundled CLIs)
-3. For host mount mode: set `CLI_EXTRA_PATHS` and mount host bin directory as read-only
-4. If `installed=true` and `runnable=false`: binary was found but failed healthcheck
-
-### Quick Runtime Validation
-
-```bash
-curl -s http://localhost:20128/api/cli-tools/codex-settings | jq '{installed,runnable,commandPath,runtimeMode,reason}'
-curl -s http://localhost:20128/api/cli-tools/claude-settings | jq '{installed,runnable,commandPath,runtimeMode,reason}'
-curl -s http://localhost:20128/api/cli-tools/openclaw-settings | jq '{installed,runnable,commandPath,runtimeMode,reason}'
-```
-
----
-
-## Cost Issues
-
-### High Costs
-
-1. Check usage stats in Dashboard → Usage
-2. Switch primary model to GLM/MiniMax
-3. Set cost budgets per API key: Dashboard → API Keys → Budget
-
----
-
-## Debugging
-
-### Enable Log Files
-
-Set `APP_LOG_TO_FILE=true` in your `.env` file. Application logs are written under `logs/`.
-Request artifacts are stored under `${DATA_DIR}/call_logs/` when the call log pipeline is
-enabled in settings.
-
-### Check Provider Health
-
-```bash
-# Health dashboard
-http://localhost:20128/dashboard/health
-
-# API health check
-curl http://localhost:20128/api/monitoring/health
-```
-
-### Runtime Storage
-
-- Main state: `${DATA_DIR}/storage.sqlite` (providers, combos, aliases, keys, settings)
-- Usage: SQLite tables in `storage.sqlite` (`usage_history`, `call_logs`, `proxy_logs`) + optional `${DATA_DIR}/call_logs/`
-- Application logs: `<repo>/logs/...` (when `APP_LOG_TO_FILE=true`)
-- Call log artifacts: `${DATA_DIR}/call_logs/YYYY-MM-DD/...` when the call log pipeline is enabled
-
----
-
-## Circuit Breaker Issues
-
-### Provider stuck in OPEN state
-
-When a provider's circuit breaker is OPEN, requests are blocked until the cooldown expires.
-
-**Fix:**
-
-1. Go to **Dashboard → Settings → Resilience**
-2. Check the circuit breaker card for the affected provider
-3. Click **Reset All** to clear all breakers, or wait for the cooldown to expire
-4. Verify the provider is actually available before resetting
-
-### Provider keeps tripping the circuit breaker
-
-If a provider repeatedly enters OPEN state:
-
-1. Check **Dashboard → Health → Provider Health** for the failure pattern
-2. Go to **Settings → Resilience → Provider Profiles** and increase the failure threshold
-3. Check if the provider has changed API limits or requires re-authentication
-4. Review latency telemetry — high latency may cause timeout-based failures
-
----
-
-## Audio Transcription Issues
-
-### "Unsupported model" error
-
-- Ensure you're using the correct prefix: `deepgram/nova-3` or `assemblyai/best`
-- Verify the provider is connected in **Dashboard → Providers**
-
-### Transcription returns empty or fails
-
-- Check supported audio formats: `mp3`, `wav`, `m4a`, `flac`, `ogg`, `webm`
-- Verify file size is within provider limits (typically < 25MB)
-- Check provider API key validity in the provider card
-
----
-
-## Translator Debugging
-
-Use **Dashboard → Translator** to debug format translation issues:
-
-| Mode             | When to Use                                                                                  |
-| ---------------- | -------------------------------------------------------------------------------------------- |
-| **Playground**   | Compare input/output formats side by side — paste a failing request to see how it translates |
-| **Chat Tester**  | Send live messages and inspect the full request/response payload including headers           |
-| **Test Bench**   | Run batch tests across format combinations to find which translations are broken             |
-| **Live Monitor** | Watch real-time request flow to catch intermittent translation issues                        |
-
-### Common format issues
-
-- **Thinking tags not appearing** — Check if the target provider supports thinking and the thinking budget setting
-- **Tool calls dropping** — Some format translations may strip unsupported fields; verify in Playground mode
-- **System prompt missing** — Claude and Gemini handle system prompts differently; check translation output
-- **SDK returns raw string instead of object** — Fixed in v1.1.0: response sanitizer now strips non-standard fields (`x_groq`, `usage_breakdown`, etc.) that cause OpenAI SDK Pydantic validation failures
-- **GLM/ERNIE rejects `system` role** — Fixed in v1.1.0: role normalizer automatically merges system messages into user messages for incompatible models
-- **`developer` role not recognized** — Fixed in v1.1.0: automatically converted to `system` for non-OpenAI providers
-- **`json_schema` not working with Gemini** — Fixed in v1.1.0: `response_format` is now converted to Gemini's `responseMimeType` + `responseSchema`
-
----
-
-## Resilience Settings
-
-### Auto rate-limit not triggering
-
-- Auto rate-limit only applies to API key providers (not OAuth/subscription)
-- Verify **Settings → Resilience → Provider Profiles** has auto-rate-limit enabled
-- Check if the provider returns `429` status codes or `Retry-After` headers
-
-### Tuning exponential backoff
-
-Provider profiles support these settings:
-
-- **Base delay** — Initial wait time after first failure (default: 1s)
-- **Max delay** — Maximum wait time cap (default: 30s)
-- **Multiplier** — How much to increase delay per consecutive failure (default: 2x)
-
-### Anti-thundering herd
-
-When many concurrent requests hit a rate-limited provider, OmniRoute uses mutex + auto rate-limiting to serialize requests and prevent cascading failures. This is automatic for API key providers.
-
----
-
-## Optional RAG / LLM failure taxonomy (16 problems)
-
-Some OmniRoute users place the gateway in front of RAG or agent stacks. In those setups it is common to see a strange pattern: OmniRoute looks healthy (providers up, routing profiles ok, no rate limit alerts) but the final answer is still wrong.
-
-In practice these incidents usually come from the downstream RAG pipeline, not from the gateway itself.
-
-If you want a shared vocabulary to describe those failures you can use the WFGY ProblemMap, an external MIT license text resource that defines sixteen recurring RAG / LLM failure patterns. At a high level it covers:
-
-- retrieval drift and broken context boundaries
-- empty or stale indexes and vector stores
-- embedding versus semantic mismatch
-- prompt assembly and context window issues
-- logic collapse and overconfident answers
-- long chain and agent coordination failures
-- multi agent memory and role drift
-- deployment and bootstrap ordering problems
-
-The idea is simple:
-
-1. When you investigate a bad response, capture:
-   - user task and request
-   - route or provider combo in OmniRoute
-   - any RAG context used downstream (retrieved documents, tool calls, etc)
-2. Map the incident to one or two WFGY ProblemMap numbers (`No.1` … `No.16`).
-3. Store the number in your own dashboard, runbook, or incident tracker next to the OmniRoute logs.
-4. Use the corresponding WFGY page to decide whether you need to change your RAG stack, retriever, or routing strategy.
-
-Full text and concrete recipes live here (MIT license, text only):
-
-[WFGY ProblemMap README](https://github.com/onestardao/WFGY/blob/main/ProblemMap/README.md)
-
-You can ignore this section if you do not run RAG or agent pipelines behind OmniRoute.
-
----
-
-## Still Stuck?
-
-- **GitHub Issues**: [github.com/diegosouzapw/OmniRoute/issues](https://github.com/diegosouzapw/OmniRoute/issues)
-- **Architecture**: See [`docs/architecture/ARCHITECTURE.md`](ARCHITECTURE.md) for internal details
-- **API Reference**: See [`docs/reference/API_REFERENCE.md`](API_REFERENCE.md) for all endpoints
-- **Health Dashboard**: Check **Dashboard → Health** for real-time system status
-- **Translator**: Use **Dashboard → Translator** to debug format issues
diff --git a/docs/i18n/in/docs/guides/UNINSTALL.md b/docs/i18n/in/docs/guides/UNINSTALL.md
deleted file mode 100644
index ec3c43c0ed..0000000000
--- a/docs/i18n/in/docs/guides/UNINSTALL.md
+++ /dev/null
@@ -1,157 +0,0 @@
-# OmniRoute — Uninstall Guide (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../../docs/UNINSTALL.md) · 🇪🇸 [es](../../es/docs/UNINSTALL.md) · 🇫🇷 [fr](../../fr/docs/UNINSTALL.md) · 🇩🇪 [de](../../de/docs/UNINSTALL.md) · 🇮🇹 [it](../../it/docs/UNINSTALL.md) · 🇷🇺 [ru](../../ru/docs/UNINSTALL.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/UNINSTALL.md) · 🇯🇵 [ja](../../ja/docs/UNINSTALL.md) · 🇰🇷 [ko](../../ko/docs/UNINSTALL.md) · 🇸🇦 [ar](../../ar/docs/UNINSTALL.md) · 🇮🇳 [hi](../../hi/docs/UNINSTALL.md) · 🇮🇳 [in](../../in/docs/UNINSTALL.md) · 🇹🇭 [th](../../th/docs/UNINSTALL.md) · 🇻🇳 [vi](../../vi/docs/UNINSTALL.md) · 🇮🇩 [id](../../id/docs/UNINSTALL.md) · 🇲🇾 [ms](../../ms/docs/UNINSTALL.md) · 🇳🇱 [nl](../../nl/docs/UNINSTALL.md) · 🇵🇱 [pl](../../pl/docs/UNINSTALL.md) · 🇸🇪 [sv](../../sv/docs/UNINSTALL.md) · 🇳🇴 [no](../../no/docs/UNINSTALL.md) · 🇩🇰 [da](../../da/docs/UNINSTALL.md) · 🇫🇮 [fi](../../fi/docs/UNINSTALL.md) · 🇵🇹 [pt](../../pt/docs/UNINSTALL.md) · 🇷🇴 [ro](../../ro/docs/UNINSTALL.md) · 🇭🇺 [hu](../../hu/docs/UNINSTALL.md) · 🇧🇬 [bg](../../bg/docs/UNINSTALL.md) · 🇸🇰 [sk](../../sk/docs/UNINSTALL.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/UNINSTALL.md) · 🇮🇱 [he](../../he/docs/UNINSTALL.md) · 🇵🇭 [phi](../../phi/docs/UNINSTALL.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/UNINSTALL.md) · 🇨🇿 [cs](../../cs/docs/UNINSTALL.md) · 🇹🇷 [tr](../../tr/docs/UNINSTALL.md)
-
----
-
-This guide covers how to cleanly remove OmniRoute from your system.
-
----
-
-## Quick Uninstall (v3.6.2+)
-
-OmniRoute provides two built-in scripts for clean removal:
-
-### Keep Your Data
-
-```bash
-npm run uninstall
-```
-
-This removes the OmniRoute application but **preserves** your database, configurations, API keys, and provider settings in `~/.omniroute/`. Use this if you plan to reinstall later and want to keep your setup.
-
-### Full Removal
-
-```bash
-npm run uninstall:full
-```
-
-This removes the application **and permanently erases** all data:
-
-- Database (`storage.sqlite`)
-- Provider configurations and API keys
-- Backup files
-- Log files
-- All files in the `~/.omniroute/` directory
-
-> ⚠️ **Warning:** `npm run uninstall:full` is irreversible. All your provider connections, combos, API keys, and usage history will be permanently deleted.
-
----
-
-## Manual Uninstall
-
-### NPM Global Install
-
-```bash
-# Remove the global package
-npm uninstall -g omniroute
-
-# (Optional) Remove data directory
-rm -rf ~/.omniroute
-```
-
-### pnpm Global Install
-
-```bash
-pnpm uninstall -g omniroute
-rm -rf ~/.omniroute
-```
-
-### Docker
-
-```bash
-# Stop and remove the container
-docker stop omniroute
-docker rm omniroute
-
-# Remove the volume (deletes all data)
-docker volume rm omniroute-data
-
-# (Optional) Remove the image
-docker rmi diegosouzapw/omniroute:latest
-```
-
-### Docker Compose
-
-```bash
-# Stop and remove containers
-docker compose down
-
-# Also remove volumes (deletes all data)
-docker compose down -v
-```
-
-### Electron Desktop App
-
-**Windows:**
-
-- Open `Settings → Apps → OmniRoute → Uninstall`
-- Or run the NSIS uninstaller from the install directory
-
-**macOS:**
-
-- Drag `OmniRoute.app` from `/Applications` to Trash
-- Remove data: `rm -rf ~/Library/Application Support/omniroute`
-
-**Linux:**
-
-- Remove the AppImage file
-- Remove data: `rm -rf ~/.omniroute`
-
-### Source Install (git clone)
-
-```bash
-# Remove the cloned directory
-rm -rf /path/to/omniroute
-
-# (Optional) Remove data directory
-rm -rf ~/.omniroute
-```
-
----
-
-## Data Directories
-
-OmniRoute stores data in the following locations by default:
-
-| Platform      | Default Path                  | Override                  |
-| ------------- | ----------------------------- | ------------------------- |
-| Linux         | `~/.omniroute/`               | `DATA_DIR` env var        |
-| macOS         | `~/.omniroute/`               | `DATA_DIR` env var        |
-| Windows       | `%APPDATA%/omniroute/`        | `DATA_DIR` env var        |
-| Docker        | `/app/data/` (mounted volume) | `DATA_DIR` env var        |
-| XDG-compliant | `$XDG_CONFIG_HOME/omniroute/` | `XDG_CONFIG_HOME` env var |
-
-### Files in the data directory
-
-| File/Directory       | Description                                       |
-| -------------------- | ------------------------------------------------- |
-| `storage.sqlite`     | Main database (providers, combos, settings, keys) |
-| `storage.sqlite-wal` | SQLite write-ahead log (temporary)                |
-| `storage.sqlite-shm` | SQLite shared memory (temporary)                  |
-| `call_logs/`         | Request payload archives                          |
-| `backups/`           | Automatic database backups                        |
-| `log.txt`            | Legacy request log (optional)                     |
-
----
-
-## Verify Complete Removal
-
-After uninstalling, verify there are no remaining files:
-
-```bash
-# Check for global npm package
-npm list -g omniroute 2>/dev/null
-
-# Check for data directory
-ls -la ~/.omniroute/ 2>/dev/null
-
-# Check for running processes
-pgrep -f omniroute
-```
-
-If any process is still running, stop it:
-
-```bash
-pkill -f omniroute
-```
diff --git a/docs/i18n/in/docs/guides/USER_GUIDE.md b/docs/i18n/in/docs/guides/USER_GUIDE.md
deleted file mode 100644
index 31126e65dc..0000000000
--- a/docs/i18n/in/docs/guides/USER_GUIDE.md
+++ /dev/null
@@ -1,937 +0,0 @@
-# User Guide (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../../docs/USER_GUIDE.md) · 🇪🇸 [es](../../es/docs/USER_GUIDE.md) · 🇫🇷 [fr](../../fr/docs/USER_GUIDE.md) · 🇩🇪 [de](../../de/docs/USER_GUIDE.md) · 🇮🇹 [it](../../it/docs/USER_GUIDE.md) · 🇷🇺 [ru](../../ru/docs/USER_GUIDE.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/USER_GUIDE.md) · 🇯🇵 [ja](../../ja/docs/USER_GUIDE.md) · 🇰🇷 [ko](../../ko/docs/USER_GUIDE.md) · 🇸🇦 [ar](../../ar/docs/USER_GUIDE.md) · 🇮🇳 [hi](../../hi/docs/USER_GUIDE.md) · 🇮🇳 [in](../../in/docs/USER_GUIDE.md) · 🇹🇭 [th](../../th/docs/USER_GUIDE.md) · 🇻🇳 [vi](../../vi/docs/USER_GUIDE.md) · 🇮🇩 [id](../../id/docs/USER_GUIDE.md) · 🇲🇾 [ms](../../ms/docs/USER_GUIDE.md) · 🇳🇱 [nl](../../nl/docs/USER_GUIDE.md) · 🇵🇱 [pl](../../pl/docs/USER_GUIDE.md) · 🇸🇪 [sv](../../sv/docs/USER_GUIDE.md) · 🇳🇴 [no](../../no/docs/USER_GUIDE.md) · 🇩🇰 [da](../../da/docs/USER_GUIDE.md) · 🇫🇮 [fi](../../fi/docs/USER_GUIDE.md) · 🇵🇹 [pt](../../pt/docs/USER_GUIDE.md) · 🇷🇴 [ro](../../ro/docs/USER_GUIDE.md) · 🇭🇺 [hu](../../hu/docs/USER_GUIDE.md) · 🇧🇬 [bg](../../bg/docs/USER_GUIDE.md) · 🇸🇰 [sk](../../sk/docs/USER_GUIDE.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/USER_GUIDE.md) · 🇮🇱 [he](../../he/docs/USER_GUIDE.md) · 🇵🇭 [phi](../../phi/docs/USER_GUIDE.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/USER_GUIDE.md) · 🇨🇿 [cs](../../cs/docs/USER_GUIDE.md) · 🇹🇷 [tr](../../tr/docs/USER_GUIDE.md)
-
----
-
-Complete guide for configuring providers, creating combos, integrating CLI tools, and deploying OmniRoute.
-
----
-
-## Table of Contents
-
-- [Pricing at a Glance](#-pricing-at-a-glance)
-- [Use Cases](#-use-cases)
-- [Provider Setup](#-provider-setup)
-- [CLI Integration](#-cli-integration)
-- [Deployment](#-deployment)
-- [Available Models](#-available-models)
-- [Advanced Features](#-advanced-features)
-
----
-
-## 💰 Pricing at a Glance
-
-| Tier                | Provider          | Cost        | Quota Reset    | Best For             |
-| ------------------- | ----------------- | ----------- | -------------- | -------------------- |
-| **💳 SUBSCRIPTION** | Claude Code (Pro) | $20/mo      | 5h + weekly    | Already subscribed   |
-|                     | Codex (Plus/Pro)  | $20-200/mo  | 5h + weekly    | OpenAI users         |
-|                     | GitHub Copilot    | $10-19/mo   | Monthly        | GitHub users         |
-| **🔑 API KEY**      | DeepSeek          | Pay per use | None           | Cheap reasoning      |
-|                     | Groq              | Pay per use | None           | Ultra-fast inference |
-|                     | xAI (Grok)        | Pay per use | None           | Grok 4 reasoning     |
-|                     | Mistral           | Pay per use | None           | EU-hosted models     |
-|                     | Perplexity        | Pay per use | None           | Search-augmented     |
-|                     | Together AI       | Pay per use | None           | Open-source models   |
-|                     | Fireworks AI      | Pay per use | None           | Fast FLUX images     |
-|                     | Cerebras          | Pay per use | None           | Wafer-scale speed    |
-|                     | Cohere            | Pay per use | None           | Command R+ RAG       |
-|                     | NVIDIA NIM        | Pay per use | None           | Enterprise models    |
-| **💰 CHEAP**        | GLM-4.7           | $0.6/1M     | Daily 10AM     | Budget backup        |
-|                     | MiniMax M2.1      | $0.2/1M     | 5-hour rolling | Cheapest option      |
-|                     | Kimi K2           | $9/mo flat  | 10M tokens/mo  | Predictable cost     |
-| **🆓 FREE**         | Qoder             | $0          | Provider limits apply | Verify current catalog        |
-|                     | Kiro              | $0          | Provider limits apply | Claude free          |
-
----
-
-## 🎯 Use Cases
-
-### Case 1: "I have Claude Pro subscription"
-
-**Problem:** Quota expires unused, rate limits during heavy coding
-
-```
-Combo: "maximize-claude"
-  1. cc/claude-opus-4-7        (use subscription fully)
-  2. glm/glm-4.7               (cheap backup when quota out)
-  3. if/kimi-k2-thinking       (free emergency fallback)
-
-Monthly cost: $20 (subscription) + ~$5 (backup) = $25 total
-vs. $20 + hitting limits = frustration
-```
-
-### Case 2: "I want zero cost"
-
-**Problem:** Can't afford subscriptions, need reliable AI coding
-
-```
-Combo: "free-tier-fallback"
-  1. if/kimi-k2-thinking       (no published token cap; limits apply)
-  2. kr/qwen3-coder-next
-
-Monthly cost: $0
-Quality: verify the model, limits, privacy, and SLA for your workload
-```
-
-### Case 3: "I need 24/7 coding, no interruptions"
-
-**Problem:** Deadlines, can't afford downtime
-
-```
-Combo: "always-on"
-  1. cc/claude-opus-4-7        (best quality)
-  2. cx/gpt-5.2-codex          (second subscription)
-  3. glm/glm-4.7               (cheap, resets daily)
-  4. minimax/MiniMax-M2.1      (cheapest, 5h reset)
-  5. if/kimi-k2-thinking       (free unlimited)
-
-Result: 5 fallback layers broaden resilience; upstream availability is not guaranteed
-Monthly cost: $20-200 (subscriptions) + $10-20 (backup)
-```
-
-### Case 4: "I want FREE AI in OpenClaw"
-
-**Problem:** Need AI assistant in messaging apps, completely free
-
-```
-Combo: "openclaw-free"
-  1. if/glm-4.7                (no published token cap; limits apply)
-  2. if/minimax-m2.1           (no published token cap; limits apply)
-  3. if/kimi-k2-thinking       (no published token cap; limits apply)
-
-Monthly cost: $0
-Access via: WhatsApp, Telegram, Slack, Discord, iMessage, Signal...
-```
-
----
-
-## 📖 Provider Setup
-
-### 🔐 Subscription Providers
-
-#### Claude Code (Pro/Max)
-
-```bash
-Dashboard → Providers → Connect Claude Code
-→ OAuth login → Auto token refresh
-→ 5-hour + weekly quota tracking
-
-Models:
-  cc/claude-opus-4-7
-  cc/claude-sonnet-4-5-20250929
-  cc/claude-haiku-4-5-20251001
-```
-
-**Pro Tip:** Use Opus for complex tasks, Sonnet for speed. OmniRoute tracks quota per model!
-
-#### OpenAI Codex (Plus/Pro)
-
-```bash
-Dashboard → Providers → Connect Codex
-→ OAuth login (port 1455)
-→ 5-hour + weekly reset
-
-Models:
-  cx/gpt-5.2-codex
-  cx/gpt-5.1-codex-max
-```
-
-#### GitHub Copilot
-
-```bash
-Dashboard → Providers → Connect GitHub
-→ OAuth via GitHub
-→ Monthly reset (1st of month)
-
-Models:
-  gh/gpt-5
-  gh/claude-4.5-sonnet
-  gh/gemini-3.1-pro-preview
-```
-
-### 💰 Cheap Providers
-
-#### GLM-4.7 (Daily reset, $0.6/1M)
-
-1. Sign up: [Zhipu AI](https://open.bigmodel.cn/)
-2. Get API key from Coding Plan
-3. Dashboard → Add API Key: Provider: `glm`, API Key: `your-key`
-
-**Use:** `glm/glm-4.7` — **Pro Tip:** Coding Plan offers 3× quota at 1/7 cost! Reset daily 10:00 AM.
-
-#### MiniMax M2.1 (5h reset, $0.20/1M)
-
-1. Sign up: [MiniMax](https://www.minimax.io/)
-2. Get API key → Dashboard → Add API Key
-
-**Use:** `minimax/MiniMax-M2.1` — **Pro Tip:** Cheapest option for long context (1M tokens)!
-
-#### Kimi K2 ($9/month flat)
-
-1. Subscribe: [Moonshot AI](https://platform.moonshot.ai/)
-2. Get API key → Dashboard → Add API Key
-
-**Use:** `kimi/kimi-latest` — **Pro Tip:** Fixed $9/month for 10M tokens = $0.90/1M effective cost!
-
-### 🆓 FREE Providers
-
-#### Qoder (8 FREE models)
-
-```bash
-Dashboard → Connect Qoder → OAuth login → Access is subject to current provider limits
-
-Models: if/kimi-k2-thinking, if/qwen3-coder-plus, if/glm-4.7, if/minimax-m2, if/deepseek-r1
-```
-
-
-#### Kiro (Claude FREE)
-
-```bash
-Dashboard → Connect Kiro → AWS Builder ID or Google/GitHub → Unlimited
-
-Models: kr/claude-sonnet-4.5, kr/claude-haiku-4.5
-```
-
----
-
-## 🎨 Combos
-
-You can reorder combo cards directly in **Dashboard → Combos** by dragging the handle on each card. The order is stored in SQLite and restored on reload.
-
-### Example 1: Maximize Subscription → Cheap Backup
-
-```
-Dashboard → Combos → Create New
-
-Name: premium-coding
-Models:
-  1. cc/claude-opus-4-7 (Subscription primary)
-  2. glm/glm-4.7 (Cheap backup, $0.6/1M)
-  3. minimax/MiniMax-M2.1 (Cheapest fallback, $0.20/1M)
-
-Use in CLI: premium-coding
-```
-
-### Example 2: Free-Only (Zero Cost)
-
-```
-Name: free-combo
-Models:
-  1. if/kimi-k2-thinking (no published token cap; provider limits may apply)
-  2. kr/qwen3-coder-next
-
-Cost: currently listed as $0; terms and availability may change
-```
-
----
-
-## 🔧 CLI Integration
-
-### Cursor IDE
-
-```
-Settings → Models → Advanced:
-  OpenAI API Base URL: http://localhost:20128/v1
-  OpenAI API Key: [from omniroute dashboard]
-  Model: cc/claude-opus-4-7
-```
-
-### Claude Code
-
-Edit `~/.claude/config.json`:
-
-```json
-{
-  "anthropic_api_base": "http://localhost:20128/v1",
-  "anthropic_api_key": "your-omniroute-api-key"
-}
-```
-
-### Codex CLI
-
-```bash
-export OPENAI_BASE_URL="http://localhost:20128"
-export OPENAI_API_KEY="your-omniroute-api-key"
-codex "your prompt"
-```
-
-### OpenClaw
-
-Edit `~/.openclaw/openclaw.json`:
-
-```json
-{
-  "agents": {
-    "defaults": {
-      "model": { "primary": "omniroute/if/glm-4.7" }
-    }
-  },
-  "models": {
-    "providers": {
-      "omniroute": {
-        "baseUrl": "http://localhost:20128/v1",
-        "apiKey": "your-omniroute-api-key",
-        "api": "openai-completions",
-        "models": [{ "id": "if/glm-4.7", "name": "glm-4.7" }]
-      }
-    }
-  }
-}
-```
-
-**Or use Dashboard:** CLI Tools → OpenClaw → Auto-config
-
-### Cline / Continue / RooCode
-
-```
-Provider: OpenAI Compatible
-Base URL: http://localhost:20128/v1
-API Key: [from dashboard]
-Model: cc/claude-opus-4-7
-```
-
----
-
-## तैनाती
-
-### Global npm install (Recommended)
-
-```bash
-npm install -g omniroute
-
-# Create config directory
-mkdir -p ~/.omniroute
-
-# Create .env file (see .env.example)
-cp .env.example ~/.omniroute/.env
-
-# Start server
-omniroute
-# Or with custom port:
-omniroute --port 3000
-```
-
-The CLI automatically loads `.env` from `~/.omniroute/.env` or `./.env`.
-
-### Uninstalling
-
-When you no longer need OmniRoute, we provide two quick scripts for a clean removal:
-
-| Command                  | Action                                                                              |
-| ------------------------ | ----------------------------------------------------------------------------------- |
-| `npm run uninstall`      | Removes the system app but **keeps your DB and configurations** in `~/.omniroute`.  |
-| `npm run uninstall:full` | Removes the app AND permanently **erases all configurations, keys, and databases**. |
-
-> Note: To run these commands, navigate to the OmniRoute project folder (if you cloned it) and run them. Alternatively, if globally installed, you can simply run `npm uninstall -g omniroute`.
-
-### VPS Deployment
-
-```bash
-git clone https://github.com/diegosouzapw/OmniRoute.git
-cd OmniRoute && npm install && npm run build
-
-export JWT_SECRET="your-secure-secret-change-this"
-export INITIAL_PASSWORD="your-password"
-export DATA_DIR="/var/lib/omniroute"
-export PORT="20128"
-export HOSTNAME="0.0.0.0"
-export NODE_ENV="production"
-export NEXT_PUBLIC_BASE_URL="http://localhost:20128"
-export API_KEY_SECRET="endpoint-proxy-api-key-secret"
-
-npm run start
-# Or: pm2 start npm --name omniroute -- start
-```
-
-### PM2 Deployment (Low Memory)
-
-For servers with limited RAM, use the memory limit option:
-
-```bash
-# With 512MB limit (default)
-pm2 start npm --name omniroute -- start
-
-# Or with custom memory limit
-OMNIROUTE_MEMORY_MB=512 pm2 start npm --name omniroute -- start
-
-# Or using ecosystem.config.js
-pm2 start ecosystem.config.js
-```
-
-Create `ecosystem.config.js`:
-
-```javascript
-module.exports = {
-  apps: [
-    {
-      name: "omniroute",
-      script: "npm",
-      args: "start",
-      env: {
-        NODE_ENV: "production",
-        OMNIROUTE_MEMORY_MB: "512",
-        JWT_SECRET: "your-secret",
-        INITIAL_PASSWORD: "your-password",
-      },
-      node_args: "--max-old-space-size=512",
-      max_memory_restart: "300M",
-    },
-  ],
-};
-```
-
-### Docker
-
-```bash
-# Build image (default = runner-cli with codex/claude/droid preinstalled)
-docker build -t omniroute:cli .
-
-# Portable mode (recommended)
-docker run -d --name omniroute -p 20128:20128 --env-file ./.env -v omniroute-data:/app/data omniroute:cli
-```
-
-For host-integrated mode with CLI binaries, see the Docker section in the main docs.
-
-### Void Linux (xbps-src)
-
-Void Linux users can package and install OmniRoute natively using the `xbps-src` cross-compilation framework. This automates the Node.js standalone build along with the required `better-sqlite3` native bindings.
-
-<details>
-<summary><b>View xbps-src template</b></summary>
-
-```bash
-# Template file for 'omniroute'
-pkgname=omniroute
-version=3.2.4
-revision=1
-hostmakedepends="nodejs python3 make"
-depends="openssl"
-short_desc="Universal AI gateway with smart routing for multiple LLM providers"
-maintainer="zenobit <zenobit@disroot.org>"
-license="MIT"
-homepage="https://github.com/diegosouzapw/OmniRoute"
-distfiles="https://github.com/diegosouzapw/OmniRoute/archive/refs/tags/v${version}.tar.gz"
-checksum=009400afee90a9f32599d8fe734145cfd84098140b7287990183dde45ae2245b
-system_accounts="_omniroute"
-omniroute_homedir="/var/lib/omniroute"
-export NODE_ENV=production
-export npm_config_engine_strict=false
-export npm_config_loglevel=error
-export npm_config_fund=false
-export npm_config_audit=false
-
-do_build() {
-	# Determine target CPU arch for node-gyp
-	local _gyp_arch
-	case "$XBPS_TARGET_MACHINE" in
-		aarch64*) _gyp_arch=arm64 ;;
-		armv7*|armv6*) _gyp_arch=arm ;;
-		i686*) _gyp_arch=ia32 ;;
-		*) _gyp_arch=x64 ;;
-	esac
-
-	# 1) Install all deps – skip scripts
-	NODE_ENV=development npm ci --ignore-scripts
-
-	# 2) Build the Next.js standalone bundle
-	npm run build
-
-	# 3) Copy static assets into standalone
-	cp -r .next/static .next/standalone/.next/static
-	[ -d public ] && cp -r public .next/standalone/public || true
-
-	# 4) Compile better-sqlite3 native binding
-	local _node_gyp=/usr/lib/node_modules/npm/node_modules/node-gyp/bin/node-gyp.js
-	(cd node_modules/better-sqlite3 && node "$_node_gyp" rebuild --arch="$_gyp_arch")
-
-	# 5) Place the compiled binding into the standalone bundle
-	local _bs3_release=.next/standalone/node_modules/better-sqlite3/build/Release
-	mkdir -p "$_bs3_release"
-	cp node_modules/better-sqlite3/build/Release/better_sqlite3.node "$_bs3_release/"
-
-	# 6) Remove arch-specific sharp bundles
-	rm -rf .next/standalone/node_modules/@img
-
-	# 7) Copy pino runtime deps omitted by Next.js static analysis:
-	for _mod in pino-abstract-transport split2 process-warning; do
-		cp -r "node_modules/$_mod" .next/standalone/node_modules/
-	done
-}
-
-do_check() {
-	npm run test:unit
-}
-
-do_install() {
-	vmkdir usr/lib/omniroute/.next
-	vcopy .next/standalone/. usr/lib/omniroute/.next/standalone
-
-	# Prevent removal of empty Next.js app router dirs by the post-install hook
-	for _d in \
-		.next/standalone/.next/server/app/dashboard \
-		.next/standalone/.next/server/app/dashboard/settings \
-		.next/standalone/.next/server/app/dashboard/providers; do
-		touch "${DESTDIR}/usr/lib/omniroute/${_d}/.keep"
-	done
-
-	cat > "${WRKDIR}/omniroute" <<'EOF'
-#!/bin/sh
-export PORT="${PORT:-20128}"
-export DATA_DIR="${DATA_DIR:-${XDG_DATA_HOME:-${HOME}/.local/share}/omniroute}"
-export APP_LOG_TO_FILE="${APP_LOG_TO_FILE:-false}"
-mkdir -p "${DATA_DIR}"
-exec node /usr/lib/omniroute/.next/standalone/server.js "$@"
-EOF
-	vbin "${WRKDIR}/omniroute"
-}
-
-post_install() {
-	vlicense LICENSE
-}
-```
-
-</details>
-
-### Environment Variables
-
-| Variable                                | Default                              | Description                                                                                               |
-| --------------------------------------- | ------------------------------------ | --------------------------------------------------------------------------------------------------------- |
-| `JWT_SECRET`                            | `omniroute-default-secret-change-me` | JWT signing secret (**change in production**)                                                             |
-| `INITIAL_PASSWORD`                      | `123456`                             | First login password                                                                                      |
-| `DATA_DIR`                              | `~/.omniroute`                       | Data directory (db, usage, logs)                                                                          |
-| `PORT`                                  | framework default                    | Service port (`20128` in examples)                                                                        |
-| `HOSTNAME`                              | framework default                    | Bind host (Docker defaults to `0.0.0.0`)                                                                  |
-| `NODE_ENV`                              | runtime default                      | Set `production` for deploy                                                                               |
-| `BASE_URL`                              | `http://localhost:20128`             | Server-side internal base URL                                                                             |
-| `CLOUD_URL`                             | `https://omniroute.dev`              | Cloud sync endpoint base URL                                                                              |
-| `API_KEY_SECRET`                        | `endpoint-proxy-api-key-secret`      | HMAC secret for generated API keys                                                                        |
-| `REQUIRE_API_KEY`                       | `false`                              | Enforce Bearer API key on `/v1/*`                                                                         |
-| `ALLOW_API_KEY_REVEAL`                  | `false`                              | Allow Api Manager to copy full API keys on demand                                                         |
-| `PROVIDER_LIMITS_SYNC_INTERVAL_MINUTES` | `70`                                 | Server-side refresh cadence for cached Provider Limits data; UI refresh buttons still trigger manual sync |
-| `DISABLE_SQLITE_AUTO_BACKUP`            | `false`                              | Disable automatic SQLite snapshots before writes/import/restore; manual backups still work                |
-| `APP_LOG_TO_FILE`                       | `true`                               | Enables application and audit log output to disk                                                          |
-| `AUTH_COOKIE_SECURE`                    | `false`                              | Force `Secure` auth cookie (behind HTTPS reverse proxy)                                                   |
-| `CLOUDFLARED_BIN`                       | unset                                | Use an existing `cloudflared` binary instead of managed download                                          |
-| `CLOUDFLARED_PROTOCOL`                  | `http2`                              | Transport for managed Quick Tunnels (`http2`, `quic`, or `auto`)                                          |
-| `OMNIROUTE_MEMORY_MB`                   | `512`                                | Node.js heap limit in MB                                                                                  |
-| `PROMPT_CACHE_MAX_SIZE`                 | `50`                                 | Max prompt cache entries                                                                                  |
-| `SEMANTIC_CACHE_MAX_SIZE`               | `100`                                | Max semantic cache entries                                                                                |
-
-For the full environment variable reference, see the [README](../README.md).
-
----
-
-## 📊 Available Models
-
-<details>
-<summary><b>View all available models</b></summary>
-
-**Claude Code (`cc/`)** — Pro/Max: `cc/claude-opus-4-7`, `cc/claude-sonnet-4-5-20250929`, `cc/claude-haiku-4-5-20251001`
-
-**Codex (`cx/`)** — Plus/Pro: `cx/gpt-5.2-codex`, `cx/gpt-5.1-codex-max`
-
-**GitHub Copilot (`gh/`)**: `gh/gpt-5`, `gh/claude-4.5-sonnet`
-
-**GLM (`glm/`)** — $0.6/1M: `glm/glm-4.7`
-
-**MiniMax (`minimax/`)** — $0.2/1M: `minimax/MiniMax-M2.1`
-
-**Qoder (`if/`)** — FREE: `if/kimi-k2-thinking`, `if/qwen3-coder-plus`, `if/deepseek-r1`
-
-
-**Kiro (`kr/`)** — FREE: `kr/claude-sonnet-4.5`, `kr/claude-haiku-4.5`
-
-**DeepSeek (`ds/`)**: `ds/deepseek-chat`, `ds/deepseek-reasoner`
-
-**Groq (`groq/`)**: `groq/llama-3.3-70b-versatile`, `groq/llama-4-maverick-17b-128e-instruct`
-
-**xAI (`xai/`)**: `xai/grok-4`, `xai/grok-4-0709-fast-reasoning`, `xai/grok-code-mini`
-
-**Mistral (`mistral/`)**: `mistral/mistral-large-2501`, `mistral/codestral-2501`
-
-**Perplexity (`pplx/`)**: `pplx/sonar-pro`, `pplx/sonar`
-
-**Together AI (`together/`)**: `together/meta-llama/Llama-3.3-70B-Instruct-Turbo`
-
-**Fireworks AI (`fireworks/`)**: `fireworks/accounts/fireworks/models/deepseek-v3p1`
-
-**Cerebras (`cerebras/`)**: `cerebras/llama-3.3-70b`
-
-**Cohere (`cohere/`)**: `cohere/command-r-plus-08-2024`
-
-**NVIDIA NIM (`nvidia/`)**: `nvidia/nvidia/llama-3.3-70b-instruct`
-
-</details>
-
----
-
-## 🧩 Advanced Features
-
-### Custom Models
-
-Add any model ID to any provider without waiting for an app update:
-
-```bash
-# Via API
-curl -X POST http://localhost:20128/api/provider-models \
-  -H "Content-Type: application/json" \
-  -d '{"provider": "openai", "modelId": "gpt-4.5-preview", "modelName": "GPT-4.5 Preview"}'
-
-# List: curl http://localhost:20128/api/provider-models?provider=openai
-# Remove: curl -X DELETE "http://localhost:20128/api/provider-models?provider=openai&model=gpt-4.5-preview"
-```
-
-Or use Dashboard: **Providers → [Provider] → Custom Models**.
-
-Notes:
-
-- OpenRouter and OpenAI/Anthropic-compatible providers are managed from **Available Models** only. Manual add, import, and auto-sync all land in the same available-model list, so there is no separate Custom Models section for those providers.
-- The **Custom Models** section is intended for providers that do not expose managed available-model imports.
-
-### Dedicated Provider Routes
-
-Route requests directly to a specific provider with model validation:
-
-```bash
-POST http://localhost:20128/v1/providers/openai/chat/completions
-POST http://localhost:20128/v1/providers/openai/embeddings
-POST http://localhost:20128/v1/providers/fireworks/images/generations
-```
-
-The provider prefix is auto-added if missing. Mismatched models return `400`.
-
-### Network Proxy Configuration
-
-```bash
-# Set global proxy
-curl -X PUT http://localhost:20128/api/settings/proxy \
-  -d '{"global": {"type":"http","host":"proxy.example.com","port":"8080"}}'
-
-# Per-provider proxy
-curl -X PUT http://localhost:20128/api/settings/proxy \
-  -d '{"providers": {"openai": {"type":"socks5","host":"proxy.example.com","port":"1080"}}}'
-
-# Test proxy
-curl -X POST http://localhost:20128/api/settings/proxy/test \
-  -d '{"proxy":{"type":"socks5","host":"proxy.example.com","port":"1080"}}'
-```
-
-**Precedence:** Key-specific → Combo-specific → Provider-specific → Global → Environment.
-
-### Model Catalog API
-
-```bash
-curl http://localhost:20128/api/models/catalog
-```
-
-Returns models grouped by provider with types (`chat`, `embedding`, `image`).
-
-### Cloud Sync
-
-- Sync providers, combos, and settings across devices
-- Automatic background sync with timeout + fail-fast
-- Prefer server-side `BASE_URL`/`CLOUD_URL` in production
-
-### Cloudflare Quick Tunnel
-
-- Available in **Dashboard → Endpoints** for Docker and other self-hosted deployments
-- Creates a temporary `https://*.trycloudflare.com` URL that forwards to your current OpenAI-compatible `/v1` endpoint
-- First enable installs `cloudflared` only when needed; later restarts reuse the same managed binary
-- Quick Tunnels are not auto-restored after an OmniRoute or container restart; re-enable them from the dashboard when needed
-- Tunnel URLs are ephemeral and change every time you stop/start the tunnel
-- Managed Quick Tunnels default to HTTP/2 transport to avoid noisy QUIC UDP buffer warnings in constrained containers
-- Set `CLOUDFLARED_PROTOCOL=quic` or `auto` if you want to override the managed transport choice
-- Set `CLOUDFLARED_BIN` if you prefer using a preinstalled `cloudflared` binary instead of the managed download
-
-### LLM Gateway Intelligence (Phase 9)
-
-- **Semantic Cache** — Auto-caches non-streaming, temperature=0 responses (bypass with `X-OmniRoute-No-Cache: true`)
-- **Request Idempotency** — Deduplicates requests within 5s via `Idempotency-Key` or `X-Request-Id` header
-- **Progress Tracking** — Opt-in SSE `event: progress` events via `X-OmniRoute-Progress: true` header
-
----
-
-### Translator Playground
-
-Access via **Dashboard → Translator**. Debug and visualize how OmniRoute translates API requests between providers.
-
-| Mode             | Purpose                                                                                |
-| ---------------- | -------------------------------------------------------------------------------------- |
-| **Playground**   | Select source/target formats, paste a request, and see the translated output instantly |
-| **Chat Tester**  | Send live chat messages through the proxy and inspect the full request/response cycle  |
-| **Test Bench**   | Run batch tests across multiple format combinations to verify translation correctness  |
-| **Live Monitor** | Watch real-time translations as requests flow through the proxy                        |
-
-**Use cases:**
-
-- Debug why a specific client/provider combination fails
-- Verify that thinking tags, tool calls, and system prompts translate correctly
-- Compare format differences between OpenAI, Claude, Gemini, and Responses API formats
-
----
-
-### Routing Strategies
-
-Configure via **Dashboard → Settings → Routing**.
-
-| Strategy                       | Description                                                                                      |
-| ------------------------------ | ------------------------------------------------------------------------------------------------ |
-| **Fill First**                 | Uses accounts in priority order — primary account handles all requests until unavailable         |
-| **Round Robin**                | Cycles through all accounts with a configurable sticky limit (default: 3 calls per account)      |
-| **P2C (Power of Two Choices)** | Picks 2 random accounts and routes to the healthier one — balances load with awareness of health |
-| **Random**                     | Randomly selects an account for each request using Fisher-Yates shuffle                          |
-| **Least Used**                 | Routes to the account with the oldest `lastUsedAt` timestamp, distributing traffic evenly        |
-| **Cost Optimized**             | Routes to the account with the lowest priority value, optimizing for lowest-cost providers       |
-
-#### External Sticky Session Header
-
-For external session affinity (for example, Claude Code/Codex agents behind reverse proxies), send:
-
-```http
-X-Session-Id: your-session-key
-```
-
-OmniRoute also accepts `x_session_id` and returns the effective session key in `X-OmniRoute-Session-Id`.
-
-If you use Nginx and send underscore-form headers, enable:
-
-```nginx
-underscores_in_headers on;
-```
-
-#### Wildcard Model Aliases
-
-Create wildcard patterns to remap model names:
-
-```
-Pattern: claude-sonnet-*     →  Target: cc/claude-sonnet-4-5-20250929
-Pattern: gpt-*               →  Target: gh/gpt-5.1-codex
-```
-
-Wildcards support `*` (any characters) and `?` (single character).
-
-#### Fallback Chains
-
-Define global fallback chains that apply across all requests:
-
-```
-Chain: production-fallback
-  1. cc/claude-opus-4-7
-  2. gh/gpt-5.1-codex
-  3. glm/glm-4.7
-```
-
----
-
-### Resilience & Circuit Breakers
-
-Configure via **Dashboard → Settings → Resilience**.
-
-OmniRoute implements provider-level resilience with four components:
-
-1. **Provider Profiles** — Per-provider configuration for:
-   - **Transient Cooldown** — Base cooldown for transient upstream failures
-   - **Rate Limit Cooldown** — Base cooldown for `429`-driven lockouts
-   - **Max Backoff Level** — Maximum exponential backoff level for repeated failures
-   - **CB Threshold** — Failure count before model quarantine / provider circuit breaker escalates
-   - **CB Reset Time** — Failure counting window and breaker reset timer
-
-2. **Editable Rate Limits** — System-level defaults configurable in the dashboard:
-   - **Requests Per Minute (RPM)** — Maximum requests per minute per account
-   - **Min Time Between Requests** — Minimum gap in milliseconds between requests
-   - **Max Concurrent Requests** — Maximum simultaneous requests per account
-   - Click **Edit** to modify, then **Save** or **Cancel**. Values persist via the resilience API.
-
-3. **Circuit Breaker** — Tracks failures per provider and automatically opens the circuit when the configured threshold is reached:
-   - **CLOSED** (Healthy) — Requests flow normally
-   - **OPEN** — Provider is temporarily blocked after repeated failures
-   - **HALF_OPEN** — Testing if provider has recovered
-
-   The same provider profile also drives model-scoped lockouts:
-   - Account/model lockouts react immediately to authoritative `429` / `404` signals and use the configured cooldown + backoff values
-   - Global provider/model quarantine only activates after repeated exhaustion hits the configured **CB Threshold** within **CB Reset Time**
-
-4. **Policies & Locked Identifiers** — Shows circuit breaker status and locked identifiers with force-unlock capability.
-
-5. **Rate Limit Auto-Detection** — Monitors `429` and `Retry-After` headers to proactively avoid hitting provider rate limits. When an upstream provider returns an explicit wait window, that authoritative `Retry-After` value overrides the base cooldown from the provider profile.
-
-**Pro Tip:** Use **Reset All** button to clear all circuit breakers and cooldowns when a provider recovers from an outage.
-
----
-
-### Database Export / Import
-
-Manage database backups in **Dashboard → Settings → System & Storage**.
-
-| Action                   | Description                                                                                                                                    |
-| ------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------- |
-| **Export Database**      | Downloads the current SQLite database as a `.sqlite` file                                                                                      |
-| **Export All (.tar.gz)** | Downloads a full backup archive including: database, settings, combos, provider connections (no credentials), API key metadata                 |
-| **Import Database**      | Upload a `.sqlite` file to replace the current database. A pre-import backup is automatically created unless `DISABLE_SQLITE_AUTO_BACKUP=true` |
-
-```bash
-# API: Export database
-curl -o backup.sqlite http://localhost:20128/api/db-backups/export
-
-# API: Export all (full archive)
-curl -o backup.tar.gz http://localhost:20128/api/db-backups/exportAll
-
-# API: Import database
-curl -X POST http://localhost:20128/api/db-backups/import \
-  -F "file=@backup.sqlite"
-```
-
-**Import Validation:** The imported file is validated for integrity (SQLite pragma check), required tables (`provider_connections`, `provider_nodes`, `combos`, `api_keys`), and size (max 100MB).
-
-**Use Cases:**
-
-- Migrate OmniRoute between machines
-- Create external backups for disaster recovery
-- Share configurations between team members (export all → share archive)
-
----
-
-### Settings Dashboard
-
-The settings page is organized into 6 tabs for easy navigation:
-
-| Tab            | Contents                                                                                       |
-| -------------- | ---------------------------------------------------------------------------------------------- |
-| **General**    | System storage tools, appearance settings, theme controls, and per-item sidebar visibility     |
-| **Security**   | Login/Password settings, IP Access Control, API auth for `/models`, and Provider Blocking      |
-| **Routing**    | Global routing strategy (6 options), wildcard model aliases, fallback chains, combo defaults   |
-| **Resilience** | Provider profiles, editable rate limits, circuit breaker status, policies & locked identifiers |
-| **AI**         | Thinking budget configuration, global system prompt injection, prompt cache stats              |
-| **Advanced**   | Global proxy configuration (HTTP/SOCKS5)                                                       |
-
----
-
-### Costs & Budget Management
-
-Access via **Dashboard → Costs**.
-
-| Tab         | Purpose                                                                                  |
-| ----------- | ---------------------------------------------------------------------------------------- |
-| **Budget**  | Set spending limits per API key with daily/weekly/monthly budgets and real-time tracking |
-| **Pricing** | View and edit model pricing entries — cost per 1K input/output tokens per provider       |
-
-```bash
-# API: Set a budget
-curl -X POST http://localhost:20128/api/usage/budget \
-  -H "Content-Type: application/json" \
-  -d '{"keyId": "key-123", "limit": 50.00, "period": "monthly"}'
-
-# API: Get current budget status
-curl http://localhost:20128/api/usage/budget
-```
-
-**Cost Tracking:** Every request logs token usage and calculates cost using the pricing table. View breakdowns in **Dashboard → Usage** by provider, model, and API key.
-
----
-
-### Audio Transcription
-
-OmniRoute supports audio transcription via the OpenAI-compatible endpoint:
-
-```bash
-POST /v1/audio/transcriptions
-Authorization: Bearer your-api-key
-Content-Type: multipart/form-data
-
-# Example with curl
-curl -X POST http://localhost:20128/v1/audio/transcriptions \
-  -H "Authorization: Bearer your-api-key" \
-  -F "file=@audio.mp3" \
-  -F "model=deepgram/nova-3"
-```
-
-Available providers: **Deepgram** (`deepgram/`), **AssemblyAI** (`assemblyai/`).
-
-Supported audio formats: `mp3`, `wav`, `m4a`, `flac`, `ogg`, `webm`.
-
----
-
-### Combo Balancing Strategies
-
-Configure per-combo balancing in **Dashboard → Combos → Create/Edit → Strategy**.
-
-| Strategy           | Description                                                              |
-| ------------------ | ------------------------------------------------------------------------ |
-| **Round-Robin**    | Rotates through models sequentially                                      |
-| **Priority**       | Always tries the first model; falls back only on error                   |
-| **Random**         | Picks a random model from the combo for each request                     |
-| **Weighted**       | Routes proportionally based on assigned weights per model                |
-| **Least-Used**     | Routes to the model with the fewest recent requests (uses combo metrics) |
-| **Cost-Optimized** | Routes to the cheapest available model (uses pricing table)              |
-
-Global combo defaults can be set in **Dashboard → Settings → Routing → Combo Defaults**.
-
----
-
-### Health Dashboard
-
-Access via **Dashboard → Health**. Real-time system health overview with 6 cards:
-
-| Card                  | What It Shows                                               |
-| --------------------- | ----------------------------------------------------------- |
-| **System Status**     | Uptime, version, memory usage, data directory               |
-| **Provider Health**   | Per-provider circuit breaker state (Closed/Open/Half-Open)  |
-| **Rate Limits**       | Active rate limit cooldowns per account with remaining time |
-| **Active Lockouts**   | Providers temporarily blocked by the lockout policy         |
-| **Signature Cache**   | Deduplication cache stats (active keys, hit rate)           |
-| **Latency Telemetry** | p50/p95/p99 latency aggregation per provider                |
-
-**Pro Tip:** The Health page auto-refreshes every 10 seconds. Use the circuit breaker card to identify which providers are experiencing issues.
-
----
-
-## 🖥️ Desktop Application (Electron)
-
-OmniRoute is available as a native desktop application for Windows, macOS, and Linux.
-
-### स्थापित करें
-
-```bash
-# From the electron directory:
-cd electron
-npm install
-
-# Development mode (connect to running Next.js dev server):
-npm run dev
-
-# Production mode (uses standalone build):
-npm start
-```
-
-### Building Installers
-
-```bash
-cd electron
-npm run build          # Current platform
-npm run build:win      # Windows (.exe NSIS)
-npm run build:mac      # macOS (.dmg universal)
-npm run build:linux    # Linux (.AppImage)
-```
-
-Output → `electron/dist-electron/`
-
-### Key Features
-
-| Feature                     | Description                                          |
-| --------------------------- | ---------------------------------------------------- |
-| **Server Readiness**        | Polls server before showing window (no blank screen) |
-| **System Tray**             | Minimize to tray, change port, quit from tray menu   |
-| **Port Management**         | Change server port from tray (auto-restarts server)  |
-| **Content Security Policy** | Restrictive CSP via session headers                  |
-| **Single Instance**         | Only one app instance can run at a time              |
-| **Offline Mode**            | Bundled Next.js server works without internet        |
-
-### Environment Variables
-
-| Variable              | Default | Description                      |
-| --------------------- | ------- | -------------------------------- |
-| `OMNIROUTE_PORT`      | `20128` | Server port                      |
-| `OMNIROUTE_MEMORY_MB` | `512`   | Node.js heap limit (64–16384 MB) |
-
-📖 Full documentation: [`electron/README.md`](../electron/README.md)
diff --git a/docs/i18n/in/docs/ops/COVERAGE_PLAN.md b/docs/i18n/in/docs/ops/COVERAGE_PLAN.md
deleted file mode 100644
index 380302f5c9..0000000000
--- a/docs/i18n/in/docs/ops/COVERAGE_PLAN.md
+++ /dev/null
@@ -1,170 +0,0 @@
-# Test Coverage Plan (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../../docs/COVERAGE_PLAN.md) · 🇪🇸 [es](../../es/docs/COVERAGE_PLAN.md) · 🇫🇷 [fr](../../fr/docs/COVERAGE_PLAN.md) · 🇩🇪 [de](../../de/docs/COVERAGE_PLAN.md) · 🇮🇹 [it](../../it/docs/COVERAGE_PLAN.md) · 🇷🇺 [ru](../../ru/docs/COVERAGE_PLAN.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/COVERAGE_PLAN.md) · 🇯🇵 [ja](../../ja/docs/COVERAGE_PLAN.md) · 🇰🇷 [ko](../../ko/docs/COVERAGE_PLAN.md) · 🇸🇦 [ar](../../ar/docs/COVERAGE_PLAN.md) · 🇮🇳 [hi](../../hi/docs/COVERAGE_PLAN.md) · 🇮🇳 [in](../../in/docs/COVERAGE_PLAN.md) · 🇹🇭 [th](../../th/docs/COVERAGE_PLAN.md) · 🇻🇳 [vi](../../vi/docs/COVERAGE_PLAN.md) · 🇮🇩 [id](../../id/docs/COVERAGE_PLAN.md) · 🇲🇾 [ms](../../ms/docs/COVERAGE_PLAN.md) · 🇳🇱 [nl](../../nl/docs/COVERAGE_PLAN.md) · 🇵🇱 [pl](../../pl/docs/COVERAGE_PLAN.md) · 🇸🇪 [sv](../../sv/docs/COVERAGE_PLAN.md) · 🇳🇴 [no](../../no/docs/COVERAGE_PLAN.md) · 🇩🇰 [da](../../da/docs/COVERAGE_PLAN.md) · 🇫🇮 [fi](../../fi/docs/COVERAGE_PLAN.md) · 🇵🇹 [pt](../../pt/docs/COVERAGE_PLAN.md) · 🇷🇴 [ro](../../ro/docs/COVERAGE_PLAN.md) · 🇭🇺 [hu](../../hu/docs/COVERAGE_PLAN.md) · 🇧🇬 [bg](../../bg/docs/COVERAGE_PLAN.md) · 🇸🇰 [sk](../../sk/docs/COVERAGE_PLAN.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/COVERAGE_PLAN.md) · 🇮🇱 [he](../../he/docs/COVERAGE_PLAN.md) · 🇵🇭 [phi](../../phi/docs/COVERAGE_PLAN.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/COVERAGE_PLAN.md) · 🇨🇿 [cs](../../cs/docs/COVERAGE_PLAN.md) · 🇹🇷 [tr](../../tr/docs/COVERAGE_PLAN.md)
-
----
-
-Last updated: 2026-03-28
-
-## Baseline
-
-There are multiple coverage numbers depending on how the report is computed. For planning, only one of them is useful.
-
-| Metric               | Scope                                                 | Statements / Lines | Branches | Functions | Notes                                               |
-| -------------------- | ----------------------------------------------------- | -----------------: | -------: | --------: | --------------------------------------------------- |
-| Legacy               | Old `npm run test:coverage`                           |             79.42% |   75.15% |    67.94% | Inflated: counts test files and excludes `open-sse` |
-| Diagnostic           | Source-only, excluding tests and excluding `open-sse` |             68.16% |   63.55% |    64.06% | Useful only to isolate `src/**`                     |
-| Recommended baseline | Source-only, excluding tests and including `open-sse` |             56.95% |   66.05% |    57.80% | This is the project-wide baseline to improve        |
-
-The recommended baseline is the number to optimize against.
-
-## Rules
-
-- Coverage targets apply to source files, not to `tests/**`.
-- `open-sse/**` is part of the product and must remain in scope.
-- New code should not reduce coverage in touched areas.
-- Prefer testing behavior and branch outcomes over implementation details.
-- Prefer temp SQLite databases and small fixtures over broad mocks for `src/lib/db/**`.
-
-## Current command set
-
-- `npm run test:coverage`
-  - Main source coverage gate for the unit test suite
-  - Generates `text-summary`, `html`, `json-summary`, and `lcov`
-- `npm run coverage:report`
-  - Detailed file-by-file report from the latest run
-- `npm run test:coverage:legacy`
-  - Historical comparison only
-
-## Milestones
-
-| Phase   |                 Target | Focus                                             |
-| ------- | ---------------------: | ------------------------------------------------- |
-| Phase 1 | 60% statements / lines | Quick wins and low-risk utility coverage          |
-| Phase 2 | 65% statements / lines | DB and route foundations                          |
-| Phase 3 | 70% statements / lines | Provider validation and usage analytics           |
-| Phase 4 | 75% statements / lines | `open-sse` translators and helpers                |
-| Phase 5 | 80% statements / lines | `open-sse` handlers and executor branches         |
-| Phase 6 | 85% statements / lines | Harder edge cases, branch debt, regression suites |
-| Phase 7 | 90% statements / lines | Final sweep, gap closure, strict ratchet          |
-
-Branches and functions should ratchet upward with each phase, but the primary hard target is statements / lines.
-
-## Priority hotspots
-
-These files or areas offer the best return for the next phases:
-
-1. `open-sse/handlers`
-   - `chatCore.ts` at 7.57%
-   - Overall directory at 29.07%
-2. `open-sse/translator/request`
-   - Overall directory at 36.39%
-   - Many translators are still near single-digit coverage
-3. `open-sse/translator/response`
-   - Overall directory at 8.07%
-4. `open-sse/executors`
-   - Overall directory at 36.62%
-5. `src/lib/db`
-   - `models.ts` at 20.66%
-   - `registeredKeys.ts` at 34.46%
-   - `modelComboMappings.ts` at 36.25%
-   - `settings.ts` at 46.40%
-   - `webhooks.ts` at 33.33%
-6. `src/lib/usage`
-   - `usageHistory.ts` at 21.12%
-   - `usageStats.ts` at 9.56%
-   - `costCalculator.ts` at 30.00%
-7. `src/lib/providers`
-   - `validation.ts` at 41.16%
-8. Low-risk utility and API files for early gains
-   - `src/shared/utils/upstreamError.ts`
-   - `src/shared/utils/apiAuth.ts`
-   - `src/lib/api/errorResponse.ts`
-   - `src/app/api/settings/require-login/route.ts`
-   - `src/app/api/providers/[id]/models/route.ts`
-
-## Execution checklist
-
-### Phase 1: 56.95% -> 60%
-
-- [x] Fix coverage metric so it reflects source code instead of test files
-- [x] Keep a legacy coverage script for comparison
-- [x] Record the baseline and hotspots in-repo
-- [ ] Add focused tests for low-risk utilities:
-  - `src/shared/utils/upstreamError.ts`
-  - `src/shared/utils/fetchTimeout.ts`
-  - `src/lib/api/errorResponse.ts`
-  - `src/shared/utils/apiAuth.ts`
-  - `src/lib/display/names.ts`
-- [ ] Add route tests for:
-  - `src/app/api/settings/require-login/route.ts`
-  - `src/app/api/providers/[id]/models/route.ts`
-
-### Phase 2: 60% -> 65%
-
-- [ ] Add DB-backed tests for:
-  - `src/lib/db/modelComboMappings.ts`
-  - `src/lib/db/settings.ts`
-  - `src/lib/db/registeredKeys.ts`
-- [ ] Cover branch behavior in:
-  - `src/lib/providers/validation.ts`
-  - `src/app/api/v1/embeddings/route.ts`
-  - `src/app/api/v1/moderations/route.ts`
-
-### Phase 3: 65% -> 70%
-
-- [ ] Add usage analytics tests for:
-  - `src/lib/usage/usageHistory.ts`
-  - `src/lib/usage/usageStats.ts`
-  - `src/lib/usage/costCalculator.ts`
-- [ ] Expand route coverage for proxy management and settings branches
-
-### Phase 4: 70% -> 75%
-
-- [ ] Cover translator helpers and central translation paths:
-  - `open-sse/translator/index.ts`
-  - `open-sse/translator/helpers/*`
-  - `open-sse/translator/request/*`
-  - `open-sse/translator/response/*`
-
-### Phase 5: 75% -> 80%
-
-- [ ] Add handler-level tests for:
-  - `open-sse/handlers/chatCore.ts`
-  - `open-sse/handlers/responsesHandler.js`
-  - `open-sse/handlers/imageGeneration.js`
-  - `open-sse/handlers/embeddings.js`
-- [ ] Add executor branch coverage for provider-specific auth, retries, and endpoint overrides
-
-### Phase 6: 80% -> 85%
-
-- [ ] Merge more edge-case suites into the main coverage path
-- [ ] Increase function coverage for DB modules with weak constructor/helper coverage
-- [ ] Close branch gaps in `settings.ts`, `registeredKeys.ts`, `validation.ts`, and translator helpers
-
-### Phase 7: 85% -> 90%
-
-- [ ] Treat the remaining low-coverage files as blockers
-- [ ] Add regression tests for every uncovered production bug fixed during the push to 90%
-- [ ] Raise the coverage gate in CI only after the local baseline is stable for at least two consecutive runs
-
-## Ratchet policy
-
-Update `npm run test:coverage` thresholds only after the project actually exceeds the next milestone with a comfortable buffer.
-
-Recommended ratchet sequence:
-
-1. 55/60/55
-2. 60/62/58
-3. 65/64/62
-4. 70/66/66
-5. 75/70/72
-6. 80/75/78
-7. 85/80/84
-8. 90/85/88
-
-Order is `statements-lines / branches / functions`.
-
-## Known gap
-
-The current coverage command measures the main Node unit suite and includes source reached from it, including `open-sse`. It does not yet merge Vitest coverage into a single unified report. That merge is worth doing later, but it is not a blocker for starting the 60% -> 80% climb.
diff --git a/docs/i18n/in/docs/ops/FLY_IO_DEPLOYMENT_GUIDE.md b/docs/i18n/in/docs/ops/FLY_IO_DEPLOYMENT_GUIDE.md
deleted file mode 100644
index 9822fca933..0000000000
--- a/docs/i18n/in/docs/ops/FLY_IO_DEPLOYMENT_GUIDE.md
+++ /dev/null
@@ -1,455 +0,0 @@
-# OmniRoute Fly.io 部署指南 (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../../docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇪🇸 [es](../../es/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇫🇷 [fr](../../fr/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇩🇪 [de](../../de/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇮🇹 [it](../../it/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇷🇺 [ru](../../ru/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇯🇵 [ja](../../ja/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇰🇷 [ko](../../ko/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇸🇦 [ar](../../ar/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇮🇳 [hi](../../hi/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇮🇳 [in](../../in/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇹🇭 [th](../../th/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇻🇳 [vi](../../vi/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇮🇩 [id](../../id/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇲🇾 [ms](../../ms/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇳🇱 [nl](../../nl/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇵🇱 [pl](../../pl/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇸🇪 [sv](../../sv/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇳🇴 [no](../../no/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇩🇰 [da](../../da/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇫🇮 [fi](../../fi/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇵🇹 [pt](../../pt/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇷🇴 [ro](../../ro/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇭🇺 [hu](../../hu/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇧🇬 [bg](../../bg/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇸🇰 [sk](../../sk/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇮🇱 [he](../../he/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇵🇭 [phi](../../phi/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇨🇿 [cs](../../cs/docs/FLY_IO_DEPLOYMENT_GUIDE.md) · 🇹🇷 [tr](../../tr/docs/FLY_IO_DEPLOYMENT_GUIDE.md)
-
----
-
-本文档记录 OmniRoute 在 Fly.io 上的实际部署方法，适用于两类场景：
-
-- 首次把当前项目部署到 Fly.io
-- 后续代码更新后继续发布
-- 新项目参考同样流程部署
-
-本文基于当前项目已经验证通过的配置整理，应用名为 `omniroute`。
-
----
-
-## 1. 部署目标
-
-- 平台：Fly.io
-- 部署方式：本地 `flyctl` 直接发布
-- 运行方式：使用仓库内现有 `Dockerfile` 和 `fly.toml`
-- 数据持久化：Fly Volume 挂载到 `/data`
-- 访问地址：`https://omniroute.fly.dev/`
-
----
-
-## 2. 当前项目关键配置
-
-当前仓库中的 `fly.toml` 已确认包含以下关键项：
-
-```toml
-app = 'omniroute'
-primary_region = 'sin'
-
-[[mounts]]
-  source = 'data'
-  destination = '/data'
-
-[processes]
-  app = 'node run-standalone.mjs'
-
-[http_service]
-  internal_port = 20128
-
-[env]
-  TZ = "Asia/Shanghai"
-  HOST = "0.0.0.0"
-  HOSTNAME = "0.0.0.0"
-  BIND = "0.0.0.0"
-```
-
-说明：
-
-- `app = 'omniroute'` 决定实际部署到哪个 Fly 应用
-- `destination = '/data'` 决定持久卷挂载目录
-- 本项目必须让 `DATA_DIR=/data`，否则数据库和密钥会写到容器临时目录
-
----
-
-## 3. 必备工具
-
-### 3.1 安装 Fly CLI
-
-Windows PowerShell：
-
-```powershell
-pwsh -Command "iwr https://fly.io/install.ps1 -useb | iex"
-```
-
-如果安装脚本在当前环境失败，也可以手动下载 `flyctl` 二进制并放到 `PATH` 中。
-
-### 3.2 登录 Fly 账号
-
-```powershell
-flyctl auth login
-```
-
-### 3.3 检查登录状态
-
-```powershell
-flyctl auth whoami
-flyctl version
-```
-
----
-
-## 4. 首次部署当前项目
-
-### 4.1 获取代码并进入目录
-
-```powershell
-git clone https://github.com/diegosouzapw/OmniRoute.git
-cd OmniRoute
-```
-
-### 4.2 确认应用名
-
-打开 `fly.toml`，重点看这一行：
-
-```toml
-app = 'omniroute'
-```
-
-如果你准备部署到自己的新应用，可改成全局唯一名称，例如：
-
-```toml
-app = 'omniroute-yourname'
-```
-
-注意：
-
-- 控制台里要看的是与 `fly.toml` 里 `app` 一致的应用
-- 以前如果用过别的名字，例如 `oroute`，不要和 `omniroute` 混淆
-
-### 4.3 创建应用
-
-如果该应用尚不存在：
-
-```powershell
-flyctl apps create omniroute
-```
-
-如果你已经改成别的应用名，把 `omniroute` 替换成你的名字。
-
-### 4.4 首次部署
-
-```powershell
-flyctl deploy
-```
-
----
-
-## 5. 必配参数
-
-本项目在 Fly.io 上建议至少配置以下参数。
-
-### 5.1 已验证使用的参数
-
-这些参数已经在当前 `omniroute` 应用上实际部署：
-
-- `API_KEY_SECRET`
-- `DATA_DIR`
-- `JWT_SECRET`
-- `MACHINE_ID_SALT`
-- `NEXT_PUBLIC_BASE_URL`
-- `STORAGE_ENCRYPTION_KEY`
-
-### 5.2 关于 `INITIAL_PASSWORD`
-
-当前项目没有设置 `INITIAL_PASSWORD`，因为本次部署按需求不使用它。
-
-如果不设置：
-
-- 启动日志会提示默认密码是 `CHANGEME`
-- 部署后应尽快在系统设置中修改登录密码
-
-如果你希望无人值守初始化后台密码，也可以后续补：
-
-- `INITIAL_PASSWORD`
-
----
-
-## 6. 推荐参数说明
-
-### 6.1 Secrets 中设置
-
-建议放入 Fly Secrets：
-
-| 变量名                   | 是否推荐 | 说明                           |
-| ------------------------ | -------- | ------------------------------ |
-| `API_KEY_SECRET`         | 必需     | API Key 生成与校验使用         |
-| `JWT_SECRET`             | 必需     | 登录态和 JWT 签名使用          |
-| `STORAGE_ENCRYPTION_KEY` | 强烈推荐 | 加密存储敏感连接信息           |
-| `MACHINE_ID_SALT`        | 推荐     | 生成稳定机器标识               |
-| `INITIAL_PASSWORD`       | 可选     | 首次部署时直接指定后台初始密码 |
-| OAuth/API 私密凭证       | 按需     | 各类外部平台鉴权配置           |
-
-### 6.2 当前项目推荐值
-
-| 变量名                 | 推荐值                      |
-| ---------------------- | --------------------------- |
-| `DATA_DIR`             | `/data`                     |
-| `NEXT_PUBLIC_BASE_URL` | `https://omniroute.fly.dev` |
-
-说明：
-
-- `DATA_DIR=/data` 非常关键，必须与 Fly Volume 挂载点一致
-- `NEXT_PUBLIC_BASE_URL` 用于调度器和前端回调等场景
-
----
-
-## 7. 一键设置参数
-
-下面命令会生成安全随机值，并把当前项目需要的参数一次性写入 Fly Secrets。
-
-说明：
-
-- 不包含 `INITIAL_PASSWORD`
-- 适用于当前项目 `omniroute`
-
-```powershell
-$apiKeySecret = [Convert]::ToHexString((1..32 | ForEach-Object { Get-Random -Minimum 0 -Maximum 256 })).ToLower()
-$jwtSecret = [Convert]::ToHexString((1..64 | ForEach-Object { Get-Random -Minimum 0 -Maximum 256 })).ToLower()
-$machineIdSalt = [Convert]::ToHexString((1..32 | ForEach-Object { Get-Random -Minimum 0 -Maximum 256 })).ToLower()
-$storageKey = [Convert]::ToHexString((1..32 | ForEach-Object { Get-Random -Minimum 0 -Maximum 256 })).ToLower()
-
-flyctl secrets set `
-  API_KEY_SECRET=$apiKeySecret `
-  JWT_SECRET=$jwtSecret `
-  MACHINE_ID_SALT=$machineIdSalt `
-  STORAGE_ENCRYPTION_KEY=$storageKey `
-  DATA_DIR=/data `
-  NEXT_PUBLIC_BASE_URL=https://omniroute.fly.dev `
-  -a omniroute
-```
-
-如果你还要加初始密码：
-
-```powershell
-flyctl secrets set INITIAL_PASSWORD=你的强密码 -a omniroute
-```
-
----
-
-## 8. 查看当前参数
-
-```powershell
-flyctl secrets list -a omniroute
-```
-
-如果控制台 `Secrets` 页面没有显示你期待的变量，先检查：
-
-- 看的应用是不是 `omniroute`
-- `fly.toml` 的 `app` 是否和控制台应用一致
-
----
-
-## 9. 后续更新发布
-
-代码有更新后，发布步骤很简单：
-
-```powershell
-git pull
-flyctl deploy
-```
-
-如果只更新参数，不改代码：
-
-```powershell
-flyctl secrets set KEY=value -a omniroute
-```
-
-Fly 会自动滚动更新机器。
-
-### 9.1 跟踪原仓库更新并保留 fork 的 `fly.toml`
-
-如果当前仓库是 fork，并且你要同步上游 `https://github.com/diegosouzapw/OmniRoute` 的更新，推荐按下面流程执行。
-
-先确认远程：
-
-```powershell
-git remote -v
-```
-
-应至少包含：
-
-- `origin` 指向你自己的 fork
-- `upstream` 指向原仓库
-
-如果没有 `upstream`，先添加：
-
-```powershell
-git remote add upstream https://github.com/diegosouzapw/OmniRoute.git
-```
-
-同步上游前，先抓取最新提交和标签：
-
-```powershell
-git fetch upstream --tags
-```
-
-查看当前版本和上游标签：
-
-```powershell
-git describe --tags --always
-git show --no-patch --oneline v3.4.7
-```
-
-如果你想合并上游最新 `main`，并强制保留 fork 当前的 `fly.toml`，可按下面流程执行：
-
-```powershell
-git merge upstream/main
-git checkout HEAD~1 -- fly.toml
-git add -- fly.toml
-git commit -m "chore(deploy): keep fork fly.toml"
-git push origin main
-```
-
-说明：
-
-- `git merge upstream/main` 用于同步原仓库最新代码
-- `git checkout HEAD~1 -- fly.toml` 用于恢复合并前你 fork 自己的 `fly.toml`
-- 如果上游没有改 `fly.toml`，这一步不会带来额外差异
-- 如果上游改了 `fly.toml`，这一步能确保 Fly 应用名、挂载卷、区域等 fork 自定义部署配置不被覆盖
-
-如果你明确只想对齐某个发布标签，例如 `v3.4.7`，也可以先确认标签是否已经包含在 `upstream/main`：
-
-```powershell
-git merge-base --is-ancestor v3.4.7 upstream/main
-```
-
-返回成功表示 `upstream/main` 已经包含该版本，直接合并 `upstream/main` 即可。
-
-### 9.2 同步上游后的标准发布顺序
-
-同步原仓库完成后，推荐按下面顺序发布：
-
-1. `git fetch upstream --tags`
-2. `git merge upstream/main`
-3. 恢复 fork 的 `fly.toml`
-4. `git push origin main`
-5. `flyctl deploy`
-6. `flyctl status -a omniroute`
-7. `flyctl logs --no-tail -a omniroute`
-
-这就是当前项目升级到 `v3.4.7` 时使用的实际流程。
-
----
-
-## 10. 发布后检查
-
-### 10.1 查看应用状态
-
-```powershell
-flyctl status -a omniroute
-```
-
-### 10.2 查看启动日志
-
-```powershell
-flyctl logs --no-tail -a omniroute
-```
-
-### 10.3 检查网站可访问
-
-```powershell
-try {
-  (Invoke-WebRequest -Uri "https://omniroute.fly.dev" -MaximumRedirection 5 -UseBasicParsing).StatusCode
-} catch {
-  if ($_.Exception.Response) {
-    $_.Exception.Response.StatusCode.value__
-  } else {
-    throw
-  }
-}
-```
-
-返回 `200` 说明站点已正常响应。
-
----
-
-## 11. 成功标志
-
-部署成功后，日志里应看到类似内容：
-
-```text
-[bootstrap] Secrets persisted to: /data/server.env
-[DB] SQLite database ready: /data/storage.sqlite
-```
-
-这两个点很关键：
-
-- `/data/server.env` 说明运行时密钥落到了持久卷
-- `/data/storage.sqlite` 说明数据库写入持久卷
-
-如果你看到的是 `/app/data/...`，说明 `DATA_DIR` 没配对，需要立即修正。
-
----
-
-## 12. 常见问题
-
-### 12.1 `Secrets` 页面是空的
-
-通常有两种原因：
-
-- 你还没执行 `flyctl secrets set`
-- 你打开的是另一个应用，例如 `oroute`，不是 `omniroute`
-
-### 12.2 `flyctl deploy` 报 `app not found`
-
-先创建应用：
-
-```powershell
-flyctl apps create omniroute
-```
-
-### 12.3 `fly.toml` 解析失败
-
-重点检查：
-
-- 注释里是否有乱码字符
-- TOML 引号和缩进是否正确
-
-### 12.4 数据没有持久化
-
-检查以下两点：
-
-- `fly.toml` 中是否存在 `destination = '/data'`
-- `DATA_DIR` 是否设置为 `/data`
-
-### 12.5 不设置 `INITIAL_PASSWORD` 是否能跑
-
-可以运行，但会回退到默认 `CHANGEME`。生产环境建议尽快修改后台密码。
-
----
-
-## 13. 新项目复用建议
-
-如果以后是新项目照着这份文档部署，最少改这几项：
-
-1. 修改 `fly.toml` 里的 `app`
-2. 修改 `NEXT_PUBLIC_BASE_URL`
-3. 保持 `DATA_DIR=/data`
-4. 重新生成 `API_KEY_SECRET`、`JWT_SECRET`、`MACHINE_ID_SALT`、`STORAGE_ENCRYPTION_KEY`
-5. 首次部署后检查日志是否写入 `/data`
-
-不要直接复用旧项目的密钥。
-
----
-
-## 14. 当前项目的最小发布清单
-
-当前项目后续最常用的命令如下：
-
-```powershell
-flyctl auth whoami
-flyctl status -a omniroute
-flyctl secrets list -a omniroute
-flyctl deploy
-flyctl logs --no-tail -a omniroute
-```
-
-如果只是正常发版，核心就是：
-
-```powershell
-flyctl deploy
-```
-
-如果是新环境首次部署，核心就是：
-
-1. `flyctl auth login`
-2. `flyctl apps create omniroute`
-3. `flyctl secrets set ... -a omniroute`
-4. `flyctl deploy`
-5. `flyctl logs --no-tail -a omniroute`
diff --git a/docs/i18n/in/docs/ops/RELEASE_CHECKLIST.md b/docs/i18n/in/docs/ops/RELEASE_CHECKLIST.md
deleted file mode 100644
index 1108a3ad61..0000000000
--- a/docs/i18n/in/docs/ops/RELEASE_CHECKLIST.md
+++ /dev/null
@@ -1,44 +0,0 @@
-# Release Checklist (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../../docs/RELEASE_CHECKLIST.md) · 🇪🇸 [es](../../es/docs/RELEASE_CHECKLIST.md) · 🇫🇷 [fr](../../fr/docs/RELEASE_CHECKLIST.md) · 🇩🇪 [de](../../de/docs/RELEASE_CHECKLIST.md) · 🇮🇹 [it](../../it/docs/RELEASE_CHECKLIST.md) · 🇷🇺 [ru](../../ru/docs/RELEASE_CHECKLIST.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/RELEASE_CHECKLIST.md) · 🇯🇵 [ja](../../ja/docs/RELEASE_CHECKLIST.md) · 🇰🇷 [ko](../../ko/docs/RELEASE_CHECKLIST.md) · 🇸🇦 [ar](../../ar/docs/RELEASE_CHECKLIST.md) · 🇮🇳 [hi](../../hi/docs/RELEASE_CHECKLIST.md) · 🇮🇳 [in](../../in/docs/RELEASE_CHECKLIST.md) · 🇹🇭 [th](../../th/docs/RELEASE_CHECKLIST.md) · 🇻🇳 [vi](../../vi/docs/RELEASE_CHECKLIST.md) · 🇮🇩 [id](../../id/docs/RELEASE_CHECKLIST.md) · 🇲🇾 [ms](../../ms/docs/RELEASE_CHECKLIST.md) · 🇳🇱 [nl](../../nl/docs/RELEASE_CHECKLIST.md) · 🇵🇱 [pl](../../pl/docs/RELEASE_CHECKLIST.md) · 🇸🇪 [sv](../../sv/docs/RELEASE_CHECKLIST.md) · 🇳🇴 [no](../../no/docs/RELEASE_CHECKLIST.md) · 🇩🇰 [da](../../da/docs/RELEASE_CHECKLIST.md) · 🇫🇮 [fi](../../fi/docs/RELEASE_CHECKLIST.md) · 🇵🇹 [pt](../../pt/docs/RELEASE_CHECKLIST.md) · 🇷🇴 [ro](../../ro/docs/RELEASE_CHECKLIST.md) · 🇭🇺 [hu](../../hu/docs/RELEASE_CHECKLIST.md) · 🇧🇬 [bg](../../bg/docs/RELEASE_CHECKLIST.md) · 🇸🇰 [sk](../../sk/docs/RELEASE_CHECKLIST.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/RELEASE_CHECKLIST.md) · 🇮🇱 [he](../../he/docs/RELEASE_CHECKLIST.md) · 🇵🇭 [phi](../../phi/docs/RELEASE_CHECKLIST.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/RELEASE_CHECKLIST.md) · 🇨🇿 [cs](../../cs/docs/RELEASE_CHECKLIST.md) · 🇹🇷 [tr](../../tr/docs/RELEASE_CHECKLIST.md)
-
----
-
-Use this checklist before tagging or publishing a new OmniRoute release.
-
-## Version and Changelog
-
-1. Bump `package.json` version (`x.y.z`) in the release branch.
-2. Move release notes from `## [Unreleased]` in `CHANGELOG.md` to a dated section:
-   - `## [x.y.z] — YYYY-MM-DD`
-3. Keep `## [Unreleased]` as the first changelog section for upcoming work.
-4. Ensure the latest semver section in `CHANGELOG.md` equals `package.json` version.
-
-## API Docs
-
-1. Update `docs/reference/openapi.yaml`:
-   - `info.version` must equal `package.json` version.
-2. Validate endpoint examples if API contracts changed.
-
-## Runtime Docs
-
-1. Review `docs/architecture/ARCHITECTURE.md` for storage/runtime drift.
-2. Review `docs/guides/TROUBLESHOOTING.md` for env var and operational drift.
-3. Verify the release/runtime Node.js version still satisfies the supported secure floor:
-   - `>=20.20.2 <21` or `>=22.22.2 <23`
-   - `npm run check:node-runtime`
-4. Validate the npm publish artifact after building the standalone package:
-   - `npm run build:cli`
-   - `npm run check:pack-artifact`
-   - confirm no `app.__qa_backup`, `scripts/scratch`, `package-lock.json`, or other local residue
-5. Update localized docs if source docs changed significantly.
-
-## Automated Check
-
-Run the sync guard locally before opening PR:
-
-```bash
-npm run check:docs-sync
-```
-
-CI also runs this check in `.github/workflows/ci.yml` (lint job).
diff --git a/docs/i18n/in/docs/ops/VM_DEPLOYMENT_GUIDE.md b/docs/i18n/in/docs/ops/VM_DEPLOYMENT_GUIDE.md
deleted file mode 100644
index e06a037c3b..0000000000
--- a/docs/i18n/in/docs/ops/VM_DEPLOYMENT_GUIDE.md
+++ /dev/null
@@ -1,407 +0,0 @@
-# OmniRoute — Deployment Guide on VM with Cloudflare (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../../docs/VM_DEPLOYMENT_GUIDE.md) · 🇪🇸 [es](../../es/docs/VM_DEPLOYMENT_GUIDE.md) · 🇫🇷 [fr](../../fr/docs/VM_DEPLOYMENT_GUIDE.md) · 🇩🇪 [de](../../de/docs/VM_DEPLOYMENT_GUIDE.md) · 🇮🇹 [it](../../it/docs/VM_DEPLOYMENT_GUIDE.md) · 🇷🇺 [ru](../../ru/docs/VM_DEPLOYMENT_GUIDE.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/VM_DEPLOYMENT_GUIDE.md) · 🇯🇵 [ja](../../ja/docs/VM_DEPLOYMENT_GUIDE.md) · 🇰🇷 [ko](../../ko/docs/VM_DEPLOYMENT_GUIDE.md) · 🇸🇦 [ar](../../ar/docs/VM_DEPLOYMENT_GUIDE.md) · 🇮🇳 [hi](../../hi/docs/VM_DEPLOYMENT_GUIDE.md) · 🇮🇳 [in](../../in/docs/VM_DEPLOYMENT_GUIDE.md) · 🇹🇭 [th](../../th/docs/VM_DEPLOYMENT_GUIDE.md) · 🇻🇳 [vi](../../vi/docs/VM_DEPLOYMENT_GUIDE.md) · 🇮🇩 [id](../../id/docs/VM_DEPLOYMENT_GUIDE.md) · 🇲🇾 [ms](../../ms/docs/VM_DEPLOYMENT_GUIDE.md) · 🇳🇱 [nl](../../nl/docs/VM_DEPLOYMENT_GUIDE.md) · 🇵🇱 [pl](../../pl/docs/VM_DEPLOYMENT_GUIDE.md) · 🇸🇪 [sv](../../sv/docs/VM_DEPLOYMENT_GUIDE.md) · 🇳🇴 [no](../../no/docs/VM_DEPLOYMENT_GUIDE.md) · 🇩🇰 [da](../../da/docs/VM_DEPLOYMENT_GUIDE.md) · 🇫🇮 [fi](../../fi/docs/VM_DEPLOYMENT_GUIDE.md) · 🇵🇹 [pt](../../pt/docs/VM_DEPLOYMENT_GUIDE.md) · 🇷🇴 [ro](../../ro/docs/VM_DEPLOYMENT_GUIDE.md) · 🇭🇺 [hu](../../hu/docs/VM_DEPLOYMENT_GUIDE.md) · 🇧🇬 [bg](../../bg/docs/VM_DEPLOYMENT_GUIDE.md) · 🇸🇰 [sk](../../sk/docs/VM_DEPLOYMENT_GUIDE.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/VM_DEPLOYMENT_GUIDE.md) · 🇮🇱 [he](../../he/docs/VM_DEPLOYMENT_GUIDE.md) · 🇵🇭 [phi](../../phi/docs/VM_DEPLOYMENT_GUIDE.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/VM_DEPLOYMENT_GUIDE.md) · 🇨🇿 [cs](../../cs/docs/VM_DEPLOYMENT_GUIDE.md) · 🇹🇷 [tr](../../tr/docs/VM_DEPLOYMENT_GUIDE.md)
-
----
-
-Complete guide to install and configure OmniRoute on a VM (VPS) with domain managed via Cloudflare.
-
----
-
-## Prerequisites
-
-| Item       | Minimum                  | Recommended      |
-| ---------- | ------------------------ | ---------------- |
-| **CPU**    | 1 vCPU                   | 2 vCPU           |
-| **RAM**    | 1 GB                     | 2 GB             |
-| **Disk**   | 10 GB SSD                | 25 GB SSD        |
-| **OS**     | Ubuntu 22.04 LTS         | Ubuntu 24.04 LTS |
-| **Domain** | Registered on Cloudflare | —                |
-| **Docker** | Docker Engine 24+        | Docker 27+       |
-
-**Tested providers**: Akamai (Linode), DigitalOcean, Vultr, Hetzner, AWS Lightsail.
-
----
-
-## 1. Configure the VM
-
-### 1.1 Create the instance
-
-On your preferred VPS provider:
-
-- Choose Ubuntu 24.04 LTS
-- Select the minimum plan (1 vCPU / 1 GB RAM)
-- Set a strong root password or configure SSH key
-- Note the **public IP** (e.g., `203.0.113.10`)
-
-### 1.2 Connect via SSH
-
-```bash
-ssh root@203.0.113.10
-```
-
-### 1.3 Update the system
-
-```bash
-apt update && apt upgrade -y
-```
-
-### 1.4 Install Docker
-
-```bash
-# Install dependencies
-apt install -y ca-certificates curl gnupg
-
-# Add official Docker repository
-install -m 0755 -d /etc/apt/keyrings
-curl -fsSL https://download.docker.com/linux/ubuntu/gpg | gpg --dearmor -o /etc/apt/keyrings/docker.gpg
-chmod a+r /etc/apt/keyrings/docker.gpg
-echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu $ (. /etc/os-release && echo “$VERSION_CODENAME”) stable" | tee /etc/apt/sources.list.d/docker.list > /dev/null
-apt update
-apt install -y docker-ce docker-ce-cli containerd.io docker-compose-plugin
-```
-
-### 1.5 Install nginx
-
-```bash
-apt install -y nginx
-```
-
-### 1.6 Configure Firewall (UFW)
-
-```bash
-ufw default deny incoming
-ufw default allow outgoing
-ufw allow 22/tcp    # SSH
-ufw allow 80/tcp    # HTTP (redirect)
-ufw allow 443/tcp   # HTTPS
-ufw enable
-```
-
-> **Tip**: For maximum security, restrict ports 80 and 443 to Cloudflare IPs only. See the [Advanced Security](#advanced-security) section.
-
----
-
-## 2. Install OmniRoute
-
-### 2.1 Create configuration directory
-
-```bash
-mkdir -p /opt/omniroute
-```
-
-### 2.2 Create environment variables file
-
-```bash
-cat > /opt/omniroute/.env << ‘EOF’
-# === Security ===
-JWT_SECRET=CHANGE-TO-A-UNIQUE-64-CHAR-SECRET-KEY
-INITIAL_PASSWORD=YourSecurePassword123!
-API_KEY_SECRET=REPLACE-WITH-ANOTHER-SECRET-KEY
-STORAGE_ENCRYPTION_KEY=REPLACE-WITH-THIRD-SECRET-KEY
-STORAGE_ENCRYPTION_KEY_VERSION=v1
-MACHINE_ID_SALT=CHANGE-TO-A-UNIQUE-SALT
-
-# === App ===
-PORT=20128
-NODE_ENV=production
-HOSTNAME=0.0.0.0
-DATA_DIR=/app/data
-STORAGE_DRIVER=sqlite
-APP_LOG_TO_FILE=true
-AUTH_COOKIE_SECURE=false
-REQUIRE_API_KEY=false
-
-# === Domain (change to your domain) ===
-BASE_URL=https://llms.seudominio.com
-NEXT_PUBLIC_BASE_URL=https://llms.seudominio.com
-
-# === Cloud Sync (optional) ===
-# CLOUD_URL=https://cloud.omniroute.online
-# NEXT_PUBLIC_CLOUD_URL=https://cloud.omniroute.online
-EOF
-```
-
-> ⚠️ **IMPORTANT**: Generate unique secret keys! Use `openssl rand -hex 32` for each key.
-
-### 2.3 Start the container
-
-```bash
-docker pull diegosouzapw/omniroute:latest
-
-docker run -d \
-  --name omniroute \
-  --restart unless-stopped \
-  --env-file /opt/omniroute/.env \
-  -p 20128:20128 \
-  -v omniroute-data:/app/data \
-  diegosouzapw/omniroute:latest
-```
-
-### 2.4 Verify that it is running
-
-```bash
-docker ps | grep omniroute
-docker logs omniroute --tail 20
-```
-
-It should display: `[DB] SQLite database ready` and `listening on port 20128`.
-
----
-
-## 3. Configure nginx (Reverse Proxy)
-
-### 3.1 Generate SSL certificate (Cloudflare Origin)
-
-In the Cloudflare dashboard:
-
-1. Go to **SSL/TLS → Origin Server**
-2. Click **Create Certificate**
-3. Keep the defaults (15 years, \*.yourdomain.com)
-4. Copy the **Origin Certificate** and the **Private Key**
-
-```bash
-mkdir -p /etc/nginx/ssl
-
-# Paste the certificate
-nano /etc/nginx/ssl/origin.crt
-
-# Paste the private key
-nano /etc/nginx/ssl/origin.key
-
-chmod 600 /etc/nginx/ssl/origin.key
-```
-
-### 3.2 Nginx Configuration
-
-```bash
-cat > /etc/nginx/sites-available/omniroute << ‘NGINX’
-# Default server — blocks direct access via IP
-server {
-    listen 80 default_server;
-    listen [::]:80 default_server;
-    listen 443 ssl default_server;
-    listen [::]:443 ssl default_server;
-    ssl_certificate     /etc/nginx/ssl/origin.crt;
-    ssl_certificate_key /etc/nginx/ssl/origin.key;
-    server_name _;
-    return 444;
-}
-
-# OmniRoute — HTTPS
-server {
-    listen 443 ssl;
-    listen [::]:443 ssl;
-    server_name llms.yourdomain.com;  # Change to your domain
-
-    ssl_certificate     /etc/nginx/ssl/origin.crt;
-    ssl_certificate_key /etc/nginx/ssl/origin.key;
-    ssl_protocols TLSv1.2 TLSv1.3;
-
-    client_max_body_size 100M;
-
-    location / {
-        proxy_pass http://127.0.0.1:20128;
-        proxy_set_header Host $host;
-        proxy_set_header X-Real-IP $remote_addr;
-        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-        proxy_set_header X-Forwarded-Proto $scheme;
-
-        # WebSocket support
-        proxy_http_version 1.1;
-        proxy_set_header Upgrade $http_upgrade;
-        proxy_set_header Connection “upgrade”;
-
-        # SSE (Server-Sent Events) — streaming AI responses
-        proxy_buffering off;
-        proxy_cache off;
-        proxy_read_timeout 600s;
-        proxy_send_timeout 600s;
-    }
-}
-
-# HTTP → HTTPS redirect
-server {
-    listen 80;
-    listen [::]:80;
-    server_name llms.yourdomain.com;
-    return 301 https://$server_name$request_uri;
-}
-NGINX
-```
-
-Keep reverse-proxy stream timeouts aligned with your OmniRoute timeout env vars. If you raise
-`FETCH_TIMEOUT_MS` / `STREAM_IDLE_TIMEOUT_MS`, raise `proxy_read_timeout` / `proxy_send_timeout`
-above the same threshold.
-
-### 3.3 Enable and Test
-
-```bash
-# Remove default configuration
-rm -f /etc/nginx/sites-enabled/default
-
-# Enable OmniRoute
-ln -sf /etc/nginx/sites-available/omniroute /etc/nginx/sites-enabled/omniroute
-
-# Test and reload
-nginx -t && systemctl reload nginx
-```
-
----
-
-## 4. Configure Cloudflare DNS
-
-### 4.1 Add DNS record
-
-In the Cloudflare dashboard → DNS:
-
-| Type | Name   | Content                | Proxy      |
-| ---- | ------ | ---------------------- | ---------- |
-| A    | `llms` | `203.0.113.10` (VM IP) | ✅ Proxied |
-
-### 4.2 Configure SSL
-
-Under **SSL/TLS → Overview**:
-
-- Mode: **Full (Strict)**
-
-Under **SSL/TLS → Edge Certificates**:
-
-- Always Use HTTPS: ✅ On
-- Minimum TLS Version: TLS 1.2
-- Automatic HTTPS Rewrites: ✅ On
-
-### 4.3 Testing
-
-```bash
-curl -sI https://llms.seudominio.com/health
-# Should return HTTP/2 200
-```
-
----
-
-## 5. Operations and Maintenance
-
-### Upgrade to a new version
-
-```bash
-docker pull diegosouzapw/omniroute:latest
-docker stop omniroute && docker rm omniroute
-docker run -d --name omniroute --restart unless-stopped \
-  --env-file /opt/omniroute/.env \
-  -p 20128:20128 \
-  -v omniroute-data:/app/data \
-  diegosouzapw/omniroute:latest
-```
-
-### View logs
-
-```bash
-docker logs -f omniroute          # Real-time stream
-docker logs omniroute --tail 50   # Last 50 lines
-```
-
-### Manual database backup
-
-```bash
-# Copy data from the volume to the host
-docker cp omniroute:/app/data ./backup-$(date +%F)
-
-# Or compress the entire volume
-docker run --rm -v omniroute-data:/data -v $(pwd):/backup \
-  alpine tar czf /backup/omniroute-data-$(date +%F).tar.gz /data
-```
-
-### Restore from backup
-
-```bash
-docker stop omniroute
-docker run --rm -v omniroute-data:/data -v $(pwd):/backup \
-  alpine sh -c “rm -rf /data/* && tar xzf /backup/omniroute-data-YYYY-MM-DD.tar.gz -C /”
-docker start omniroute
-```
-
----
-
-## 6. Advanced Security
-
-### Restrict nginx to Cloudflare IPs
-
-```bash
-cat > /etc/nginx/cloudflare-ips.conf << ‘CF’
-# Cloudflare IPv4 ranges — update periodically
-# https://www.cloudflare.com/ips-v4/
-set_real_ip_from 173.245.48.0/20;
-set_real_ip_from 103.21.244.0/22;
-set_real_ip_from 103.22.200.0/22;
-set_real_ip_from 103.31.4.0/22;
-set_real_ip_from 141.101.64.0/18;
-set_real_ip_from 108.162.192.0/18;
-set_real_ip_from 190.93.240.0/20;
-set_real_ip_from 188.114.96.0/20;
-set_real_ip_from 197.234.240.0/22;
-set_real_ip_from 198.41.128.0/17;
-set_real_ip_from 162.158.0.0/15;
-set_real_ip_from 104.16.0.0/13;
-set_real_ip_from 104.24.0.0/14;
-set_real_ip_from 172.64.0.0/13;
-set_real_ip_from 131.0.72.0/22;
-real_ip_header CF-Connecting-IP;
-CF
-```
-
-Add the following to `nginx.conf` inside the `http {}` block:
-
-```nginx
-include /etc/nginx/cloudflare-ips.conf;
-```
-
-### Install fail2ban
-
-```bash
-apt install -y fail2ban
-systemctl enable fail2ban
-systemctl start fail2ban
-
-# Check status
-fail2ban-client status sshd
-```
-
-### Block direct access to the Docker port
-
-```bash
-# Prevent direct external access to port 20128
-iptables -I DOCKER-USER -p tcp --dport 20128 -j DROP
-iptables -I DOCKER-USER -i lo -p tcp --dport 20128 -j ACCEPT
-
-# Persist the rules
-apt install -y iptables-persistent
-netfilter-persistent save
-```
-
----
-
-## 7. Deploy to Cloudflare Workers (Optional)
-
-For remote access via Cloudflare Workers (without exposing the VM directly):
-
-```bash
-# In the local repository
-cd omnirouteCloud
-npm install
-npx wrangler login
-npx wrangler deploy
-```
-
-See the full documentation at [omnirouteCloud/README.md](../omnirouteCloud/README.md).
-
----
-
-## Port Summary
-
-| Port  | Service     | Access                     |
-| ----- | ----------- | -------------------------- |
-| 22    | SSH         | Public (with fail2ban)     |
-| 80    | nginx HTTP  | Redirect → HTTPS           |
-| 443   | nginx HTTPS | Via Cloudflare Proxy       |
-| 20128 | OmniRoute   | Localhost only (via nginx) |
diff --git a/docs/i18n/in/docs/reference/API_REFERENCE.md b/docs/i18n/in/docs/reference/API_REFERENCE.md
deleted file mode 100644
index cb259418b6..0000000000
--- a/docs/i18n/in/docs/reference/API_REFERENCE.md
+++ /dev/null
@@ -1,488 +0,0 @@
-# API Reference (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../../docs/API_REFERENCE.md) · 🇪🇸 [es](../../es/docs/API_REFERENCE.md) · 🇫🇷 [fr](../../fr/docs/API_REFERENCE.md) · 🇩🇪 [de](../../de/docs/API_REFERENCE.md) · 🇮🇹 [it](../../it/docs/API_REFERENCE.md) · 🇷🇺 [ru](../../ru/docs/API_REFERENCE.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/API_REFERENCE.md) · 🇯🇵 [ja](../../ja/docs/API_REFERENCE.md) · 🇰🇷 [ko](../../ko/docs/API_REFERENCE.md) · 🇸🇦 [ar](../../ar/docs/API_REFERENCE.md) · 🇮🇳 [hi](../../hi/docs/API_REFERENCE.md) · 🇮🇳 [in](../../in/docs/API_REFERENCE.md) · 🇹🇭 [th](../../th/docs/API_REFERENCE.md) · 🇻🇳 [vi](../../vi/docs/API_REFERENCE.md) · 🇮🇩 [id](../../id/docs/API_REFERENCE.md) · 🇲🇾 [ms](../../ms/docs/API_REFERENCE.md) · 🇳🇱 [nl](../../nl/docs/API_REFERENCE.md) · 🇵🇱 [pl](../../pl/docs/API_REFERENCE.md) · 🇸🇪 [sv](../../sv/docs/API_REFERENCE.md) · 🇳🇴 [no](../../no/docs/API_REFERENCE.md) · 🇩🇰 [da](../../da/docs/API_REFERENCE.md) · 🇫🇮 [fi](../../fi/docs/API_REFERENCE.md) · 🇵🇹 [pt](../../pt/docs/API_REFERENCE.md) · 🇷🇴 [ro](../../ro/docs/API_REFERENCE.md) · 🇭🇺 [hu](../../hu/docs/API_REFERENCE.md) · 🇧🇬 [bg](../../bg/docs/API_REFERENCE.md) · 🇸🇰 [sk](../../sk/docs/API_REFERENCE.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/API_REFERENCE.md) · 🇮🇱 [he](../../he/docs/API_REFERENCE.md) · 🇵🇭 [phi](../../phi/docs/API_REFERENCE.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/API_REFERENCE.md) · 🇨🇿 [cs](../../cs/docs/API_REFERENCE.md) · 🇹🇷 [tr](../../tr/docs/API_REFERENCE.md)
-
----
-
-Complete reference for all OmniRoute API endpoints.
-
----
-
-## Table of Contents
-
-- [Chat Completions](#chat-completions)
-- [Embeddings](#embeddings)
-- [Image Generation](#image-generation)
-- [List Models](#list-models)
-- [Compatibility Endpoints](#compatibility-endpoints)
-- [Semantic Cache](#semantic-cache)
-- [Dashboard & Management](#dashboard--management)
-- [Request Processing](#request-processing)
-- [Authentication](#authentication)
-
----
-
-## Chat Completions
-
-```bash
-POST /v1/chat/completions
-Authorization: Bearer your-api-key
-Content-Type: application/json
-
-{
-  "model": "cc/claude-opus-4-6",
-  "messages": [
-    {"role": "user", "content": "Write a function to..."}
-  ],
-  "stream": true
-}
-```
-
-### Custom Headers
-
-| Header                   | Direction | Description                                      |
-| ------------------------ | --------- | ------------------------------------------------ |
-| `X-OmniRoute-No-Cache`   | Request   | Set to `true` to bypass cache                    |
-| `X-OmniRoute-Progress`   | Request   | Set to `true` for progress events                |
-| `X-Session-Id`           | Request   | Sticky session key for external session affinity |
-| `x_session_id`           | Request   | Underscore variant also accepted (direct HTTP)   |
-| `Idempotency-Key`        | Request   | Dedup key (5s window)                            |
-| `X-Request-Id`           | Request   | Alternative dedup key                            |
-| `X-OmniRoute-Cache`      | Response  | `HIT` or `MISS` (non-streaming)                  |
-| `X-OmniRoute-Idempotent` | Response  | `true` if deduplicated                           |
-| `X-OmniRoute-Progress`   | Response  | `enabled` if progress tracking on                |
-| `X-OmniRoute-Session-Id` | Response  | Effective session ID used by OmniRoute           |
-
-> Nginx note: if you rely on underscore headers (for example `x_session_id`), enable `underscores_in_headers on;`.
-
----
-
-## Embeddings
-
-```bash
-POST /v1/embeddings
-Authorization: Bearer your-api-key
-Content-Type: application/json
-
-{
-  "model": "nebius/Qwen/Qwen3-Embedding-8B",
-  "input": "The food was delicious"
-}
-```
-
-Available providers: Nebius, OpenAI, Mistral, Together AI, Fireworks, NVIDIA, **OpenRouter**, **GitHub Models**.
-
-```bash
-# List all embedding models
-GET /v1/embeddings
-```
-
----
-
-## Image Generation
-
-```bash
-POST /v1/images/generations
-Authorization: Bearer your-api-key
-Content-Type: application/json
-
-{
-  "model": "openai/gpt-image-2",
-  "prompt": "A beautiful sunset over mountains",
-  "size": "1024x1024"
-}
-```
-
-Available providers: OpenAI (GPT Image 2), xAI (Grok Image), Together AI (FLUX), Fireworks AI, Nebius (FLUX), Hyperbolic, NanoBanana, **OpenRouter**, SD WebUI (local), ComfyUI (local).
-
-```bash
-# List all image models
-GET /v1/images/generations
-```
-
----
-
-## List Models
-
-```bash
-GET /v1/models
-Authorization: Bearer your-api-key
-
-→ Returns all chat, embedding, and image models + combos in OpenAI format
-```
-
----
-
-## Compatibility Endpoints
-
-| Method | Path                        | Format                 |
-| ------ | --------------------------- | ---------------------- |
-| POST   | `/v1/chat/completions`      | OpenAI                 |
-| POST   | `/v1/messages`              | Anthropic              |
-| POST   | `/v1/responses`             | OpenAI Responses       |
-| POST   | `/v1/embeddings`            | OpenAI                 |
-| POST   | `/v1/images/generations`    | OpenAI                 |
-| GET    | `/v1/models`                | OpenAI                 |
-| POST   | `/v1/messages/count_tokens` | Anthropic              |
-| GET    | `/v1beta/models`            | Gemini                 |
-| POST   | `/v1beta/models/{...path}`  | Gemini generateContent |
-| POST   | `/v1/api/chat`              | Ollama                 |
-
-### Dedicated Provider Routes
-
-```bash
-POST /v1/providers/{provider}/chat/completions
-POST /v1/providers/{provider}/embeddings
-POST /v1/providers/{provider}/images/generations
-```
-
-The provider prefix is auto-added if missing. Mismatched models return `400`.
-
----
-
-## Semantic Cache
-
-```bash
-# Get cache stats
-GET /api/cache/stats
-
-# Clear all caches
-DELETE /api/cache/stats
-```
-
-Response example:
-
-```json
-{
-  "semanticCache": {
-    "memorySize": 42,
-    "memoryMaxSize": 500,
-    "dbSize": 128,
-    "hitRate": 0.65
-  },
-  "idempotency": {
-    "activeKeys": 3,
-    "windowMs": 5000
-  }
-}
-```
-
----
-
-## Dashboard & Management
-
-### Authentication
-
-| Endpoint                      | Method  | Description           |
-| ----------------------------- | ------- | --------------------- |
-| `/api/auth/login`             | POST    | Login                 |
-| `/api/auth/logout`            | POST    | Logout                |
-| `/api/settings/require-login` | GET/PUT | Toggle login required |
-
-### Provider Management
-
-| Endpoint                     | Method                | Description                                    |
-| ---------------------------- | --------------------- | ---------------------------------------------- |
-| `/api/providers`             | GET/POST              | List / create providers                        |
-| `/api/providers/[id]`        | GET/PUT/DELETE        | Manage a provider                              |
-| `/api/providers/[id]/test`   | POST                  | Test provider connection                       |
-| `/api/providers/[id]/models` | GET                   | List provider models                           |
-| `/api/providers/validate`    | POST                  | Validate provider config                       |
-| `/api/provider-nodes*`       | Various               | Provider node management                       |
-| `/api/provider-models`       | GET/POST/PATCH/DELETE | Custom models (add, update, hide/show, delete) |
-
-### OAuth Flows
-
-| Endpoint                         | Method  | Description             |
-| -------------------------------- | ------- | ----------------------- |
-| `/api/oauth/[provider]/[action]` | Various | Provider-specific OAuth |
-
-### Routing & Config
-
-| Endpoint              | Method   | Description                   |
-| --------------------- | -------- | ----------------------------- |
-| `/api/models/alias`   | GET/POST | Model aliases                 |
-| `/api/models/catalog` | GET      | All models by provider + type |
-| `/api/combos*`        | Various  | Combo management              |
-| `/api/keys*`          | Various  | API key management            |
-| `/api/pricing`        | GET      | Model pricing                 |
-
-### Usage & Analytics
-
-| Endpoint                    | Method | Description          |
-| --------------------------- | ------ | -------------------- |
-| `/api/usage/history`        | GET    | Usage history        |
-| `/api/usage/logs`           | GET    | Usage logs           |
-| `/api/usage/request-logs`   | GET    | Request-level logs   |
-| `/api/usage/[connectionId]` | GET    | Per-connection usage |
-
-### Settings
-
-| Endpoint                        | Method        | Description            |
-| ------------------------------- | ------------- | ---------------------- |
-| `/api/settings`                 | GET/PUT/PATCH | General settings       |
-| `/api/settings/proxy`           | GET/PUT       | Network proxy config   |
-| `/api/settings/proxy/test`      | POST          | Test proxy connection  |
-| `/api/settings/ip-filter`       | GET/PUT       | IP allowlist/blocklist |
-| `/api/settings/thinking-budget` | GET/PUT       | Reasoning token budget |
-| `/api/settings/system-prompt`   | GET/PUT       | Global system prompt   |
-
-### Monitoring
-
-| Endpoint                 | Method     | Description                                                                                          |
-| ------------------------ | ---------- | ---------------------------------------------------------------------------------------------------- |
-| `/api/sessions`          | GET        | Active session tracking                                                                              |
-| `/api/rate-limits`       | GET        | Per-account rate limits                                                                              |
-| `/api/monitoring/health` | GET        | Health check + provider summary (`catalogCount`, `configuredCount`, `activeCount`, `monitoredCount`) |
-| `/api/cache/stats`       | GET/DELETE | Cache stats / clear                                                                                  |
-
-### Backup & Export/Import
-
-| Endpoint                    | Method | Description                             |
-| --------------------------- | ------ | --------------------------------------- |
-| `/api/db-backups`           | GET    | List available backups                  |
-| `/api/db-backups`           | PUT    | Create a manual backup                  |
-| `/api/db-backups`           | POST   | Restore from a specific backup          |
-| `/api/db-backups/export`    | GET    | Download database as .sqlite file       |
-| `/api/db-backups/import`    | POST   | Upload .sqlite file to replace database |
-| `/api/db-backups/exportAll` | GET    | Download full backup as .tar.gz archive |
-
-### Cloud Sync
-
-| Endpoint               | Method  | Description           |
-| ---------------------- | ------- | --------------------- |
-| `/api/sync/cloud`      | Various | Cloud sync operations |
-| `/api/sync/initialize` | POST    | Initialize sync       |
-| `/api/cloud/*`         | Various | Cloud management      |
-
-### Tunnels
-
-| Endpoint                   | Method | Description                                                             |
-| -------------------------- | ------ | ----------------------------------------------------------------------- |
-| `/api/tunnels/cloudflared` | GET    | Read Cloudflare Quick Tunnel install/runtime status for the dashboard   |
-| `/api/tunnels/cloudflared` | POST   | Enable or disable the Cloudflare Quick Tunnel (`action=enable/disable`) |
-
-### CLI Tools
-
-| Endpoint                           | Method | Description         |
-| ---------------------------------- | ------ | ------------------- |
-| `/api/cli-tools/claude-settings`   | GET    | Claude CLI status   |
-| `/api/cli-tools/codex-settings`    | GET    | Codex CLI status    |
-| `/api/cli-tools/droid-settings`    | GET    | Droid CLI status    |
-| `/api/cli-tools/openclaw-settings` | GET    | OpenClaw CLI status |
-| `/api/cli-tools/runtime/[toolId]`  | GET    | Generic CLI runtime |
-
-CLI responses include: `installed`, `runnable`, `command`, `commandPath`, `runtimeMode`, `reason`.
-
-### ACP Agents
-
-| Endpoint          | Method | Description                                              |
-| ----------------- | ------ | -------------------------------------------------------- |
-| `/api/acp/agents` | GET    | List all detected agents (built-in + custom) with status |
-| `/api/acp/agents` | POST   | Add custom agent or refresh detection cache              |
-| `/api/acp/agents` | DELETE | Remove a custom agent by `id` query param                |
-
-GET response includes `agents[]` (id, name, binary, version, installed, protocol, isCustom) and `summary` (total, installed, notFound, builtIn, custom).
-
-### Resilience & Rate Limits
-
-| Endpoint                | Method    | Description                     |
-| ----------------------- | --------- | ------------------------------- |
-| `/api/resilience`       | GET/PATCH | Get/update resilience profiles  |
-| `/api/resilience/reset` | POST      | Reset circuit breakers          |
-| `/api/rate-limits`      | GET       | Per-account rate limit status   |
-| `/api/rate-limit`       | GET       | Global rate limit configuration |
-
-### Evals
-
-| Endpoint     | Method   | Description                       |
-| ------------ | -------- | --------------------------------- |
-| `/api/evals` | GET/POST | List eval suites / run evaluation |
-
-### Policies
-
-| Endpoint        | Method          | Description             |
-| --------------- | --------------- | ----------------------- |
-| `/api/policies` | GET/POST/DELETE | Manage routing policies |
-
-### Compliance
-
-| Endpoint                    | Method | Description                   |
-| --------------------------- | ------ | ----------------------------- |
-| `/api/compliance/audit-log` | GET    | Compliance audit log (last N) |
-
-### v1beta (Gemini-Compatible)
-
-| Endpoint                   | Method | Description                       |
-| -------------------------- | ------ | --------------------------------- |
-| `/v1beta/models`           | GET    | List models in Gemini format      |
-| `/v1beta/models/{...path}` | POST   | Gemini `generateContent` endpoint |
-
-These endpoints mirror Gemini's API format for clients that expect native Gemini SDK compatibility.
-
-### Internal / System APIs
-
-| Endpoint                 | Method | Description                                          |
-| ------------------------ | ------ | ---------------------------------------------------- |
-| `/api/init`              | GET    | Application initialization check (used on first run) |
-| `/api/tags`              | GET    | Ollama-compatible model tags (for Ollama clients)    |
-| `/api/restart`           | POST   | Trigger graceful server restart                      |
-| `/api/shutdown`          | POST   | Trigger graceful server shutdown                     |
-| `/api/system/env/repair` | POST   | Repair OAuth provider environment variables          |
-| `/api/system-info`       | GET    | Generate system diagnostics report                   |
-
-> **Note:** These endpoints are used internally by the system or for Ollama client compatibility. They are not typically called by end users.
-
-### OAuth Environment Repair _(v3.6.1+)_
-
-```bash
-POST /api/system/env/repair
-Content-Type: application/json
-
-{
-  "provider": "claude-code"
-}
-```
-
-Repairs missing or corrupted OAuth environment variables for a specific provider. Returns:
-
-```json
-{
-  "success": true,
-  "repaired": ["CLAUDE_CODE_OAUTH_CLIENT_ID", "CLAUDE_CODE_OAUTH_CLIENT_SECRET"],
-  "backupPath": "/home/user/.omniroute/backups/env-repair-2026-04-11.bak"
-}
-```
-
----
-
-## Audio Transcription
-
-```bash
-POST /v1/audio/transcriptions
-Authorization: Bearer your-api-key
-Content-Type: multipart/form-data
-```
-
-Transcribe audio files using Deepgram or AssemblyAI.
-
-**Request:**
-
-```bash
-curl -X POST http://localhost:20128/v1/audio/transcriptions \
-  -H "Authorization: Bearer your-api-key" \
-  -F "file=@recording.mp3" \
-  -F "model=deepgram/nova-3"
-```
-
-**Response:**
-
-```json
-{
-  "text": "Hello, this is the transcribed audio content.",
-  "task": "transcribe",
-  "language": "en",
-  "duration": 12.5
-}
-```
-
-**Supported providers:** `deepgram/nova-3`, `assemblyai/best`.
-
-**Supported formats:** `mp3`, `wav`, `m4a`, `flac`, `ogg`, `webm`.
-
----
-
-## Ollama Compatibility
-
-For clients that use Ollama's API format:
-
-```bash
-# Chat endpoint (Ollama format)
-POST /v1/api/chat
-
-# Model listing (Ollama format)
-GET /api/tags
-```
-
-Requests are automatically translated between Ollama and internal formats.
-
----
-
-## Telemetry
-
-```bash
-# Get latency telemetry summary (p50/p95/p99 per provider)
-GET /api/telemetry/summary
-```
-
-**Response:**
-
-```json
-{
-  "providers": {
-    "claudeCode": { "p50": 245, "p95": 890, "p99": 1200, "count": 150 },
-    "github": { "p50": 180, "p95": 620, "p99": 950, "count": 320 }
-  }
-}
-```
-
----
-
-## Budget
-
-```bash
-# Get budget status for all API keys
-GET /api/usage/budget
-
-# Set or update a budget
-POST /api/usage/budget
-Content-Type: application/json
-
-{
-  "keyId": "key-123",
-  "limit": 50.00,
-  "period": "monthly"
-}
-```
-
----
-
-## Model Availability
-
-```bash
-# Get real-time model availability across all providers
-GET /api/models/availability
-
-# Check availability for a specific model
-POST /api/models/availability
-Content-Type: application/json
-
-{
-  "model": "claude-sonnet-4-5-20250929"
-}
-```
-
----
-
-## Request Processing
-
-1. Client sends request to `/v1/*`
-2. Route handler calls `handleChat`, `handleEmbedding`, `handleAudioTranscription`, or `handleImageGeneration`
-3. Model is resolved (direct provider/model or alias/combo)
-4. Credentials selected from local DB with account availability filtering
-5. For chat: `handleChatCore` — format detection, translation, cache check, idempotency check
-6. Provider executor sends upstream request
-7. Response translated back to client format (chat) or returned as-is (embeddings/images/audio)
-8. Usage/logging recorded
-9. Fallback applies on errors according to combo rules
-
-Full architecture reference: [`ARCHITECTURE.md`](ARCHITECTURE.md)
-
----
-
-## Authentication
-
-- Dashboard routes (`/dashboard/*`) use `auth_token` cookie
-- Login uses saved password hash; fallback to `INITIAL_PASSWORD`
-- `requireLogin` toggleable via `/api/settings/require-login`
-- `/v1/*` routes optionally require Bearer API key when `REQUIRE_API_KEY=true`
diff --git a/docs/i18n/in/docs/reference/CLI-TOOLS.md b/docs/i18n/in/docs/reference/CLI-TOOLS.md
deleted file mode 100644
index 83d18197ba..0000000000
--- a/docs/i18n/in/docs/reference/CLI-TOOLS.md
+++ /dev/null
@@ -1,778 +0,0 @@
-# CLI-TOOLS (Bahasa Indonesia (Alt))
-
-🌐 **Languages:** 🇺🇸 [English](../../../../reference/CLI-TOOLS.md) · 🇸🇦 [ar](../../../ar/docs/reference/CLI-TOOLS.md) · 🇦🇿 [az](../../../az/docs/reference/CLI-TOOLS.md) · 🇧🇬 [bg](../../../bg/docs/reference/CLI-TOOLS.md) · 🇧🇩 [bn](../../../bn/docs/reference/CLI-TOOLS.md) · 🇨🇿 [cs](../../../cs/docs/reference/CLI-TOOLS.md) · 🇩🇰 [da](../../../da/docs/reference/CLI-TOOLS.md) · 🇩🇪 [de](../../../de/docs/reference/CLI-TOOLS.md) · 🇪🇸 [es](../../../es/docs/reference/CLI-TOOLS.md) · 🇮🇷 [fa](../../../fa/docs/reference/CLI-TOOLS.md) · 🇫🇮 [fi](../../../fi/docs/reference/CLI-TOOLS.md) · 🇫🇷 [fr](../../../fr/docs/reference/CLI-TOOLS.md) · 🇮🇳 [gu](../../../gu/docs/reference/CLI-TOOLS.md) · 🇮🇱 [he](../../../he/docs/reference/CLI-TOOLS.md) · 🇮🇳 [hi](../../../hi/docs/reference/CLI-TOOLS.md) · 🇭🇺 [hu](../../../hu/docs/reference/CLI-TOOLS.md) · 🇮🇩 [id](../../../id/docs/reference/CLI-TOOLS.md) · 🇮🇹 [it](../../../it/docs/reference/CLI-TOOLS.md) · 🇯🇵 [ja](../../../ja/docs/reference/CLI-TOOLS.md) · 🇰🇷 [ko](../../../ko/docs/reference/CLI-TOOLS.md) · 🇮🇳 [mr](../../../mr/docs/reference/CLI-TOOLS.md) · 🇲🇾 [ms](../../../ms/docs/reference/CLI-TOOLS.md) · 🇳🇱 [nl](../../../nl/docs/reference/CLI-TOOLS.md) · 🇳🇴 [no](../../../no/docs/reference/CLI-TOOLS.md) · 🇵🇭 [phi](../../../phi/docs/reference/CLI-TOOLS.md) · 🇵🇱 [pl](../../../pl/docs/reference/CLI-TOOLS.md) · 🇵🇹 [pt](../../../pt/docs/reference/CLI-TOOLS.md) · 🇧🇷 [pt-BR](../../../pt-BR/docs/reference/CLI-TOOLS.md) · 🇷🇴 [ro](../../../ro/docs/reference/CLI-TOOLS.md) · 🇷🇺 [ru](../../../ru/docs/reference/CLI-TOOLS.md) · 🇸🇰 [sk](../../../sk/docs/reference/CLI-TOOLS.md) · 🇸🇪 [sv](../../../sv/docs/reference/CLI-TOOLS.md) · 🇰🇪 [sw](../../../sw/docs/reference/CLI-TOOLS.md) · 🇮🇳 [ta](../../../ta/docs/reference/CLI-TOOLS.md) · 🇮🇳 [te](../../../te/docs/reference/CLI-TOOLS.md) · 🇹🇭 [th](../../../th/docs/reference/CLI-TOOLS.md) · 🇹🇷 [tr](../../../tr/docs/reference/CLI-TOOLS.md) · 🇺🇦 [uk-UA](../../../uk-UA/docs/reference/CLI-TOOLS.md) · 🇵🇰 [ur](../../../ur/docs/reference/CLI-TOOLS.md) · 🇻🇳 [vi](../../../vi/docs/reference/CLI-TOOLS.md) · 🇨🇳 [zh-CN](../../../zh-CN/docs/reference/CLI-TOOLS.md) · 🇹🇼 [zh-TW](../../../zh-TW/docs/reference/CLI-TOOLS.md)
-
----
-
----
-
-title: "Alat CLI — OmniRoute"
-version: 3.8.50
-lastUpdated: 2026-08-18
----
-
-# Alat CLI — OmniRoute
-
-Terakhir diperbarui: 2026-08-18
-
-OmniRoute terintegrasi dengan tiga kategori alat CLI yang tersebar di tiga halaman dasbor khusus:
-
-| Halaman      | Rute                    | Konsep                                                                              | Jumlah         |
-| ------------ | ----------------------- | ----------------------------------------------------------------------------------- | -------------- |
-| **Kode CLI** | `/dashboard/cli-code`   | Alat pengkodean yang Anda arahkan ke OmniRoute (Klien → CLI → OmniRoute → Penyedia) | 26             |
-| **Agen CLI** | `/dashboard/cli-agents` | Agen otonom yang Anda arahkan ke OmniRoute (alur yang sama, cakupan lebih luas)     | 8              |
-| **Agen ACP** | `/dashboard/acp-agents` | CLI yang diluncurkan OmniRoute sebagai backend melalui stdio/ACP (alur terbalik)    | lihat registri |
-
-Rute warisan mengalihkan melalui 308: `/dashboard/cli-tools` → `/dashboard/cli-code`, `/dashboard/agents` → `/dashboard/acp-agents`.
-
----
-
-## Cara Kerjanya
-
-```
-Kode CLI / Agen CLI (alur konsumsi):
-Claude / Codex / OpenCode / Cline / KiloCode / Continue / Hermes Agent / Goose / ...
-           │
-           ▼  (semua mengarah ke OmniRoute)
-    http://YOUR_SERVER:20128/v1
-           │
-           ▼  (OmniRoute mengarahkan ke penyedia yang tepat)
-    Anthropic / OpenAI / Gemini / DeepSeek / Groq / Mistral / ...
-
-Agen ACP (alur peluncuran terbalik):
-    Permintaan Klien → OmniRoute → meluncurkan CLI melalui stdio/ACP → respons
-```
-
-**Manfaat:**
-
-- Satu kunci API untuk mengelola semua alat
-- Pelacakan biaya di semua CLI di dasbor
-- Pergantian model tanpa mengonfigurasi ulang setiap alat
-- Bekerja secara lokal dan di server jarak jauh (VPS, Docker, Akamai, Cloudflare Tunnel)
-
----
-
-## Konfigurasi otomatis dengan `setup-*`
-
-Anda tidak perlu menulis konfigurasi setiap alat dengan tangan. OmniRoute menyediakan perintah `setup-*`
-untuk setiap CLI yang didukung yang membaca katalog model **langsung** dari OmniRoute yang berjalan
-(lokal atau jarak jauh) dan menulis konfigurasi alat itu sendiri di mesin Anda:
-
-```bash
-omniroute setup-codex        omniroute setup-claude       omniroute setup-opencode
-omniroute setup-cline        omniroute setup-kilo         omniroute setup-continue
-omniroute setup-cursor       omniroute setup-roo          omniroute setup-crush
-omniroute setup-goose        omniroute setup-qwen         omniroute setup-aider
-```
-
-Setiap perintah menerima `--remote <url> --api-key <key>` (mengonfigurasi alat lokal terhadap
-OmniRoute jarak jauh), `--dry-run` (prabaca tanpa menulis), dan `--port`. Alat
-tanpa penemuan model otomatis (Cline, Kilo, Roo, Goose, Aider, Qwen) menggunakan
-`--model <id>` (dan `--yes` untuk eksekusi non-interaktif). Untuk meluncurkan CLI dengan
-lingkungan yang tepat disuntikkan dan tanpa konfigurasi yang ditulis sama sekali, gunakan
-peluncur generik `omniroute run <target>` (claude, codex, aider, goose, opencode, qwen,
-gemini — target dan alias berasal dari `bin/cli/cli-manifest.mjs`); peluncur per-alat warisan
-`omniroute launch` (Claude Code) dan `omniroute launch-codex`
-(Codex) tetap tersedia. CLI Gemini hanya untuk peluncuran: ini adalah target `omniroute run`
-tetapi tidak memiliki resep `setup-*`/`configure`.
-
-> **Referensi lengkap:** tabel master — apa yang ditulis setiap perintah, setiap bendera,
-> lokal vs jarak jauh, dan alat mana yang memerlukan akhiran `/v1` — ada di
-> **[Integrasi CLI](../guides/CLI-INTEGRATIONS.md)**.
-
-### Menjalankan ini di dalam kontainer
-
-Perintah `setup-*` yang dieksekusi di dalam kontainer OmniRoute menulis ke
-rumah kontainer itu sendiri, yang tidak dibaca oleh CLI host dan yang menghilang dengan
-kontainer. OmniRoute mendeteksi hal itu dan keluar dengan `2` dengan instruksi daripada
-menulis. Dua cara yang didukung untuk melanjutkan — instal CLI di host dan
-`omniroute connect` ke kontainer, atau bind-mount direktori konfigurasi dan set
-`CLI_CONFIG_HOME` (profil `host` compose). Setiap perintah `setup-*`, ditambah
-`omniroute configure` dan `omniroute config set`, menerima
-`--allow-container-write` ketika mengonfigurasi CLI kontainer itu sendiri adalah yang sebenarnya Anda maksud; `OMNIROUTE_ALLOW_CONTAINER_CONFIG_WRITE=true` melakukan hal yang sama untuk
-server. Lihat
-[Panduan Docker → Mengonfigurasi alat CLI host](../guides/DOCKER_GUIDE.md#configuring-host-cli-tools-when-omniroute-runs-in-docker).
-
-**Endpoint terapkan** di dasbor (`POST /api/cli-tools/apply`) menerapkan
-penjagaan yang sama: di dalam kontainer, penulisan yang targetnya tidak bind-mounted dari
-host menjawab **`422`** dengan `containerEphemeralTarget: true`, teks kesalahan yang aman
-dan — untuk alat dengan resep host (claude, codex, opencode, cline,
-kilo, continue) — sebuah `hostSetupCommand` (misalnya `omniroute setup-opencode`) untuk dijalankan
-di host sebagai gantinya; tidak ada yang ditulis. `dryRun: true` tetap berfungsi dalam mode
-kontainer dan mengembalikan konten yang dihasilkan + jalur target tanpa menyentuh disk, sehingga
-Anda dapat prabaca dari dasbor dan menerapkan di host. Perilaku ini
-sengaja dan dilindungi regresi oleh
-`tests/unit/api/cli-tools/apply-container-guard.test.ts` — jangan pernah "memperbaiki" 422
-dengan menghapus penjagaan.
-
-## Sumber Kebenaran
-
-Katalog terpadu berada di `src/shared/constants/cliTools.ts` sebagai `CLI_TOOLS: Record<string, CliCatalogEntry>`.
-
-Setiap entri memiliki bidang-bidang berikut (didefinisikan di `src/shared/schemas/cliCatalog.ts`):
-
-| Bidang                                          | Tipe                                                         | Deskripsi                                                    |
-| ----------------------------------------------- | ------------------------------------------------------------ | ------------------------------------------------------------ |
-| `category`                                      | `"code" \| "agent"`                                          | Halaman mana alat tersebut muncul                            |
-| `vendor`                                        | `string`                                                     | Asal alat ("Anthropic", "OSS (P. Gauthier)")                 |
-| `acpSpawnable`                                  | `boolean`                                                    | Juga dapat digunakan sebagai ACP Agent (lencana ditampilkan) |
-| `baseUrlSupport`                                | `"full" \| "partial" \| "none"`                              | Tingkat dukungan endpoint kustom. `"none"` = backlog MITM    |
-| `configType`                                    | `"env" \| "custom" \| "guide" \| "custom-builder" \| "mitm"` | Mekanisme konfigurasi                                        |
-| `id`, `name`, `color`, `description`, `docsUrl` | standar                                                      | Bidang tampilan inti                                         |
-
-Entri dengan `baseUrlSupport: "none"` **tidak ditampilkan** di halaman dasbor — mereka terdaftar di backlog MITM untuk rencana 11 (lihat `_tasks/features-v3.8.6/refactorpages/_orchestration/_plan11-mitm-backlog.md`).
-
-### Tingkatan Kapabilitas (tercatalog × terdeteksi × terkonfigurasi × dapat diluncurkan)
-
-Tidak setiap alat yang tercatalog dapat terdeteksi, terkonfigurasi, atau dapat diluncurkan. Setiap tingkatan memiliki satu sumber deklarasi, dan tes drift menjaga mereka tetap selaras:
-
-| Tingkatan        | Arti                                                                    | Dideklarasikan di                                                 |
-| ---------------- | ----------------------------------------------------------------------- | ----------------------------------------------------------------- |
-| **Cataloged**    | Muncul di katalog dasbor (nama, vendor, dokumen, tipe konfigurasi)      | `src/shared/constants/cliTools.ts` (`CLI_TOOLS`)                  |
-| **Detectable**   | Deteksi biner/konfigurasi, pemeriksaan kesehatan, jalur konfigurasi     | `src/shared/services/cliRuntime.ts` (`CLI_TOOLS` runtime catalog) |
-| **Configurable** | Didukung oleh `omniroute configure <cli>` (resep pengaturan ada)        | `bin/cli/cli-manifest.mjs` (`configure: true`)                    |
-| **Launchable**   | Didukung oleh `omniroute run <target>` (injeksi env/args didefinisikan) | `bin/cli/cli-manifest.mjs` (`run: true`)                          |
-
-`bin/cli/cli-manifest.mjs` adalah manifest eksekusi kanonik untuk perintah CLI yang muncul: `run`, `configure` dan generator penyelesaian shell semuanya mengambil daftar target, resolusi alias (misalnya `kilocode`/`kilo-code`/`kilo_cli` → `kilo`) dan pengkabelan flag `--model` darinya. Penjaga drift `tests/unit/cli/cli-manifest-drift.test.ts` memastikan bahwa manifest, katalog runtime, katalog UI, dan setiap permukaan konsumen tetap sinkron — target yang ditambahkan ke satu permukaan tanpa yang lainnya akan gagal dalam suite alih-alih mengalir diam-diam.
-
-## 1. Katalog Kode CLI (26 alat)
-
-Semua alat yang muncul di `/dashboard/cli-code`. Alat yang memiliki `baseUrlSupport: none` terhubung melalui MITM atau panduan manual alih-alih URL dasar kustom:
-
-| id           | nama                       | vendor                         | baseUrlSupport | configType     | acpSpawnable |
-| ------------ | -------------------------- | ------------------------------ | -------------- | -------------- | ------------ |
-| claude       | Claude Code                | Anthropic                      | penuh          | env            | true         |
-| codex        | OpenAI Codex CLI           | OpenAI                         | penuh          | kustom         | true         |
-| zcode        | ZCode (Rencana Koding GLM) | Z.ai                           | tidak ada      | kustom         | false        |
-| cline        | Cline                      | OSS (mantan-Pengembang Claude) | penuh          | kustom         | true         |
-| kilo         | Kilo Code                  | Kilo-Org                       | penuh          | kustom         | false        |
-| roo          | Roo Code                   | Roo (OSS)                      | penuh          | panduan        | false        |
-| continue     | Continue                   | continue.dev                   | penuh          | panduan        | false        |
-| aider        | Aider                      | OSS (P. Gauthier)              | penuh          | panduan        | true         |
-| forge        | ForgeCode                  | Antinomy HQ                    | penuh          | kustom         | true         |
-| jcode        | jcode                      | 1jehuang (OSS)                 | penuh          | kustom         | false        |
-| deepseek-tui | DeepSeek TUI               | Hunter Bown (OSS)              | penuh          | kustom         | false        |
-| codewhale    | CodeWhale                  | Hmbown (OSS)                   | penuh          | kustom         | false        |
-| opencode     | OpenCode                   | Anomaly (mantan-SST)           | penuh          | panduan        | true         |
-| droid        | Factory Droid              | Factory AI                     | sebagian       | panduan        | false        |
-| copilot      | GitHub Copilot CLI         | GitHub/MS                      | penuh          | kustom         | false        |
-| cursor-cli   | Cursor CLI                 | Anysphere                      | sebagian       | panduan        | true         |
-| smelt        | Smelt                      | leonardcser (OSS)              | penuh          | kustom         | false        |
-| pi           | Pi (agen-koding-pi)        | M. Zechner (OSS)               | penuh          | kustom         | false        |
-| grok-build   | Grok Build                 | xAI                            | penuh          | kustom         | false        |
-| crush        | Crush                      | OSS (Charm)                    | penuh          | kustom         | false        |
-| qwen         | Qwen Code                  | Alibaba                        | penuh          | panduan        | true         |
-| cursor       | Cursor                     | Anysphere                      | tidak ada      | panduan        | false        |
-| antigravity  | Antigravity                | Google                         | tidak ada      | mitm           | false        |
-| hermes       | Hermes                     | Nous Research                  | tidak ada      | panduan        | false        |
-| kiro         | Kiro AI                    | Amazon                         | tidak ada      | mitm           | false        |
-| custom       | Custom CLI                 | —                              | penuh          | pembuat-kustom | false        |
-
-Alat dengan `baseUrlSupport: "partial"` menunjukkan lencana "⚠ Base URL parcial" di kartu dasbor.
-
-## 2. Katalog Agen CLI (8 alat)
-
-Agen otonom yang muncul di `/dashboard/cli-agents`:
-
-| id           | nama             | vendor                   | dukunganBaseUrl | dapatDibuatACP |
-| ------------ | ---------------- | ------------------------ | --------------- | -------------- |
-| hermes-agent | Hermes Agent     | Nous Research            | penuh           | false          |
-| openclaw     | OpenClaw         | OSS (P. Steinberger)     | penuh           | true           |
-| goose        | Goose            | Block / Linux Foundation | penuh           | true           |
-| interpreter  | Open Interpreter | OSS                      | penuh           | true           |
-| warp         | Warp AI          | Warp Inc.                | sebagian        | true           |
-| agent-deck   | Agent Deck       | asheshgoplani (OSS)      | penuh           | false          |
-| omp          | Oh My Pi         | OSS                      | penuh           | true           |
-| letta        | Letta CLI        | Letta                    | penuh           | false          |
-
----
-
-## 3. Agen ACP (/dashboard/acp-agents)
-
-Halaman ini (yang diganti namanya dari `/dashboard/agents`) menunjukkan CLI yang dapat **dibuat** oleh OmniRoute sebagai mesin eksekusi backend melalui protokol stdio/ACP. Katalog ini dikelola secara terpisah di `src/lib/acp/registry.ts` dan **tidak** sama dengan `CLI_TOOLS`.
-
----
-
-## 4. Daftar Tugas MITM (tidak ditampilkan di dasbor)
-
-CLI berikut tidak mendukung URL dasar kustom secara native dan **tidak terdaftar** di halaman Kode CLI atau Agen CLI. Mereka adalah kandidat untuk intersepsi MITM dalam rencana 11:
-
-| CLI                 | Alasan                                                            |
-| ------------------- | ----------------------------------------------------------------- |
-| windsurf            | BYOK terbatas pada model Claude tertentu + URL/token perusahaan   |
-| amp                 | Ekosistem tertutup (Sourcegraph)                                  |
-| amazon-q / kiro-cli | Autentikasi AWS SSO, tidak ada URL kustom                         |
-| cowork              | Anthropic Desktop, tidak ada titik akhir yang dapat dikonfigurasi |
-
-Lihat `_tasks/features-v3.8.6/refactorpages/_orchestration/_plan11-mitm-backlog.md` untuk referensi silang lengkap.
-
----
-
-## 5. API Deteksi Batch
-
-Semua deteksi alat digabungkan melalui satu titik akhir:
-
-**`GET /api/cli-tools/all-statuses`**
-
-- Auth: `requireCliToolsAuth(request)` (sama seperti rute `/api/cli-tools/` lainnya)
-- Mengembalikan: `Record<toolId, ToolBatchStatus>` (tipe: `src/shared/types/cliBatchStatus.ts`)
-- Strategi: `Promise.all` untuk semua alat, timeout 5s per alat
-- Cache: dalam memori LRU yang diindeks oleh file konfigurasi `mtime`. Cache tidak valid ketika mtime berubah. Reset saat server di-restart.
-
-Bentuk respons per alat:
-
-```ts
-interface ToolBatchStatus {
-  detection: {
-    installed: boolean;
-    runnable: boolean;
-    version?: string;
-    command?: string;
-    commandPath?: string;
-    reason?: string;
-  };
-  config: {
-    status: "configured" | "not_configured" | "not_installed" | "unknown" | "other";
-    endpoint?: string | null;
-    lastConfiguredAt?: string | null;
-  };
-  error?: string; // disanitasi, tidak ada jejak tumpukan
-}
-```
-
-## 6. Pengatur Pengaturan untuk Alat Baru
-
-Alat baru dengan `configType: "custom"` memiliki rute API pengaturan yang didedikasikan:
-
-| Rute                                        | Alat                                                                  |
-| ------------------------------------------- | --------------------------------------------------------------------- |
-| `POST /api/cli-tools/forge-settings`        | ForgeCode (.forge.toml)                                               |
-| `POST /api/cli-tools/jcode-settings`        | jcode (--base-url flag)                                               |
-| `POST /api/cli-tools/deepseek-tui-settings` | DeepSeek TUI (OPENAI_BASE_URL, legacy)                                |
-| `POST /api/cli-tools/codewhale-settings`    | CodeWhale (OPENAI_BASE_URL, primary + legacy `~/.deepseek` sync)      |
-| `POST /api/cli-tools/smelt-settings`        | Smelt                                                                 |
-| `POST /api/cli-tools/pi-settings`           | Agen pengkodean Pi                                                    |
-| `POST /api/cli-tools/grok-build-settings`   | Grok Build (~/.grok/config.toml, `[model.omniroute]`)                 |
-| `POST /api/cli-tools/qwen-settings`         | Qwen Code (`~/.qwen/settings.json` + kunci `.env` yang didedikasikan) |
-
-Semua rute menggunakan `sanitizeErrorMessage()` untuk respons kesalahan (Aturan Keras #12).
-
----
-
-## 7. Arsitektur Halaman Dasbor
-
-### Kode CLI (`/dashboard/cli-code`)
-
-- `src/app/(dashboard)/dashboard/cli-code/page.tsx` — komponen server
-- `src/app/(dashboard)/dashboard/cli-code/CliCodePageClient.tsx` — grid klien
-- `src/app/(dashboard)/dashboard/cli-code/[id]/page.tsx` — halaman detail alat
-- `src/app/(dashboard)/dashboard/cli-code/components/` — 12 kartu alat khusus + `ToolDetailClient.tsx`
-
-### Agen CLI (`/dashboard/cli-agents`)
-
-- `src/app/(dashboard)/dashboard/cli-agents/page.tsx` — komponen server
-- `src/app/(dashboard)/dashboard/cli-agents/CliAgentsPageClient.tsx` — grid klien
-- `src/app/(dashboard)/dashboard/cli-agents/[id]/page.tsx` — menggunakan kembali `ToolDetailClient`
-
-### Agen ACP (`/dashboard/acp-agents`)
-
-- `src/app/(dashboard)/dashboard/acp-agents/page.tsx` — komponen server (dipindahkan dari `agents/`)
-
-### Komponen UI Bersama (`src/shared/components/cli/`)
-
-| File                    | Tujuan                                                 |
-| ----------------------- | ------------------------------------------------------ |
-| `CliToolCard.tsx`       | Kartu status pintar (deteksi + konfigurasi + endpoint) |
-| `CliConceptCard.tsx`    | Kartu penjelasan konsep per halaman                    |
-| `CliComparisonCard.tsx` | Perbandingan tiga kolom di berbagai jenis CLI          |
-| `BaseUrlSelect.tsx`     | Dropdown endpoint (Lokal/Awan/Kustom)                  |
-| `ApiKeySelect.tsx`      | Pemilih kunci API                                      |
-| `ManualConfigModal.tsx` | Modal cuplikan konfigurasi yang dapat disalin          |
-
-### Hook Bersama (`src/shared/hooks/cli/`)
-
-| File                      | Tujuan                                                                    |
-| ------------------------- | ------------------------------------------------------------------------- |
-| `useToolBatchStatuses.ts` | Mengambil `/api/cli-tools/all-statuses`, mengelola status loading/refresh |
-
-## 8. i18n
-
-Namespace baru ditambahkan dalam rencana 14 F9:
-
-| Namespace   | Tujuan                                                                              |
-| ----------- | ----------------------------------------------------------------------------------- |
-| `cliCommon` | String yang dibagikan (label kartu, teks konsep/perbandingan, label halaman detail) |
-| `cliCode`   | String halaman CLI Code                                                             |
-| `cliAgents` | String halaman CLI Agents                                                           |
-| `acpAgents` | String halaman ACP Agents                                                           |
-
-Terjemahan lengkap PT-BR dan EN disediakan. 39 lokal lainnya secara otomatis menggunakan EN melalui penggabungan tingkat namespace di `src/i18n/request.ts`.
-
----
-
-## 9. Memulai dengan Cepat
-
-### Langkah 1 — Dapatkan Kunci API OmniRoute
-
-1. Buka `/dashboard/api-manager` → **Buat Kunci API**
-2. Beri nama (misalnya `cli-tools`) dan pilih semua izin
-3. Salin kunci tersebut — Anda akan membutuhkannya untuk setiap CLI di bawah ini
-
-> Kunci Anda terlihat seperti: `sk-xxxxxxxxxxxxxxxx-xxxxxxxxx`
-
----
-
-### Langkah 2 — Instal Alat CLI
-
-Semua alat berbasis npm memerlukan Node.js 22.22.2+ atau 24.x:
-
-```bash
-# Claude Code (Anthropic)
-npm install -g @anthropic-ai/claude-code
-
-# OpenAI Codex
-npm install -g @openai/codex
-
-# OpenCode
-npm install -g opencode-ai
-
-# Cline
-npm install -g cline
-
-# KiloCode
-npm install -g kilocode
-
-# Qwen Code
-npm install -g @qwen-code/qwen-code
-
-# Google Gemini CLI (dapat diluncurkan melalui `omniroute run gemini` → /v1beta surface)
-npm install -g @google/gemini-cli
-
-# Aider
-pip install aider-chat
-
-# Smelt
-cargo install smelt  # Berbasis Rust
-
-# Agen pemrograman Pi
-# lihat https://github.com/zechnerj/pi-coding-agent untuk instalasi
-
-# jcode
-# lihat https://github.com/1jehuang/jcode untuk instalasi
-```
-
----
-
-### Langkah 3 — Konfigurasi melalui Dashboard
-
-1. Pergi ke `http://localhost:20128/dashboard/cli-code`
-2. Temukan alat Anda di grid
-3. Klik kartu untuk membuka halaman detail alat
-4. Pilih kunci API dan URL dasar Anda
-5. Klik **Terapkan Konfigurasi** atau salin potongan konfigurasi manual
-
----
-
-### Langkah 4 — Atur Variabel Lingkungan Global
-
-```bash
-# OmniRoute Universal Endpoint
-export OPENAI_BASE_URL="http://localhost:20128/v1"
-export OPENAI_API_KEY="sk-your-omniroute-key"
-export ANTHROPIC_BASE_URL="http://localhost:20128"
-export ANTHROPIC_AUTH_TOKEN="sk-your-omniroute-key"
-# Gemini CLI membaca GOOGLE_GEMINI_BASE_URL di ROOT (SDK-nya menambahkan /v1beta/... sendiri)
-export GOOGLE_GEMINI_BASE_URL="http://localhost:20128"
-export GEMINI_API_KEY="sk-your-omniroute-key"
-```
-
-> Untuk **server jarak jauh** ganti `localhost:20128` dengan IP atau domain server,
-> misalnya `http://<your-server-ip>:20128`.
-
----
-
-### Langkah 4 — Konfigurasi Setiap Alat
-
-#### Claude Code
-
-```bash
-# Buat ~/.claude/settings.json:
-mkdir -p ~/.claude && cat > ~/.claude/settings.json << EOF
-{
-  "env": {
-    "ANTHROPIC_BASE_URL": "http://localhost:20128",
-    "ANTHROPIC_AUTH_TOKEN": "sk-your-omniroute-key"
-  }
-}
-EOF
-```
-
-Gunakan root gateway Anthropic yang terpadu untuk Claude Code. Jangan tambahkan `/v1` di sini.
-
-**Uji:** `claude "say hello"`
-
----
-
-#### OpenAI Codex
-
-Codex modern (v0.137+) hanya membaca `~/.codex/config.toml` — `config.yaml` lama milik CLI npm warisan dan diabaikan tanpa suara. Kunci API tetap di variabel lingkungan `OMNIROUTE_API_KEY` (`env_key`), tidak pernah di dalam file:
-
-```bash
-mkdir -p ~/.codex && cat > ~/.codex/config.toml << EOF
-model_provider = "omniroute"
-
-[model_providers.omniroute]
-name                 = "OmniRoute"
-base_url             = "http://localhost:20128/v1"
-env_key              = "OMNIROUTE_API_KEY"
-requires_openai_auth = false
-EOF
-export OMNIROUTE_API_KEY="sk-your-omniroute-key"
-```
-
-Referensi lengkap (profil, `wire_api`, jendela konteks): [CODEX-CLI-CONFIGURATION.md](../guides/CODEX-CLI-CONFIGURATION.md).
-
-**Uji:** `codex "what is 2+2?"`
-
----
-
-#### OpenCode
-
-```bash
-mkdir -p ~/.config/opencode && cat > ~/.config/opencode/opencode.json << EOF
-{
-  "\$schema": "https://opencode.ai/config.json",
-  "provider": {
-    "omniroute": {
-      "npm": "@ai-sdk/openai-compatible",
-      "name": "OmniRoute",
-      "options": {
-        "baseURL": "http://localhost:20128/v1",
-        "apiKey": "sk-your-omniroute-key"
-      },
-      "models": {
-        "claude-sonnet-4-5": { "name": "claude-sonnet-4-5" },
-        "claude-sonnet-4-5-thinking": { "name": "claude-sonnet-4-5-thinking" },
-        "gemini-3-flash": { "name": "gemini-3-flash" }
-      }
-    }
-  }
-}
-EOF
-```
-
-**Uji:** `opencode`
-
-> Gunakan `opencode run "your prompt" --model omniroute/claude-sonnet-4-5-thinking --variant high`
-> untuk mengirim varian berpikir.
-
----
-
-#### Cline (CLI atau VS Code)
-
-**Mode CLI:**
-
-```bash
-mkdir -p ~/.cline/data && cat > ~/.cline/data/globalState.json << EOF
-{
-  "apiProvider": "openai",
-  "openAiBaseUrl": "http://localhost:20128/v1",
-  "openAiApiKey": "sk-your-omniroute-key"
-}
-EOF
-```
-
-**Mode VS Code:**
-Pengaturan ekstensi Cline → Penyedia API: `OpenAI Compatible` → URL Dasar: `http://localhost:20128/v1`
-
-Atau gunakan dashboard OmniRoute → **CLI Tools → Cline → Terapkan Konfigurasi**.
-
----
-
-#### KiloCode (CLI atau VS Code)
-
-**Mode CLI:**
-
-```bash
-kilocode --api-base http://localhost:20128/v1 --api-key sk-your-omniroute-key
-```
-
-**Pengaturan VS Code:**
-
-```json
-{
-  "kilo-code.openAiBaseUrl": "http://localhost:20128/v1",
-  "kilo-code.apiKey": "sk-your-omniroute-key"
-}
-```
-
-Atau gunakan dashboard OmniRoute → **CLI Tools → KiloCode → Terapkan Konfigurasi**.
-
----
-
-#### Continue (Ekstensi VS Code)
-
-Edit `~/.continue/config.yaml`:
-
-```yaml
-models:
-  - name: OmniRoute
-    provider: openai
-    model: auto
-    apiBase: http://localhost:20128/v1
-    apiKey: sk-your-omniroute-key
-    default: true
-```
-
-Mulai ulang VS Code setelah mengedit.
-
----
-
-#### VS Code Insiders (`chatLanguageModels.json`)
-
-Gunakan ini ketika VS Code Insiders dikonfigurasi untuk model endpoint kustom dan Anda ingin OmniRoute berfungsi tanpa bidang header kustom.
-
-**Lokasi yang Disarankan:**
-
-- Linux: `~/.config/Code - Insiders/User/chatLanguageModels.json`
-- Windows: `%APPDATA%/Code - Insiders/User/chatLanguageModels.json`
-
-**Contoh menggunakan alias OmniRoute yang ditokenisasi:**
-
-```json
-[
-  {
-    "vendor": "customendpoint",
-    "id": "auto",
-    "name": "OmniRoute Auto",
-    "family": "gpt-4",
-    "version": "1.0.0",
-    "url": "http://localhost:20128/api/v1/vscode/sk-your-omniroute-key/chat/completions",
-    "modelsUrl": "http://localhost:20128/api/v1/vscode/sk-your-omniroute-key/models",
-    "requestFormat": "openai-chat-completions",
-    "contextWindow": 256000,
-    "maxOutputTokens": 32768,
-    "auth": {
-      "type": "none"
-    }
-  }
-]
-```
-
-**Catatan:**
-
-- Ganti `sk-your-omniroute-key` dengan kunci API yang dibuat di OmniRoute.
-- Bidang `url` harus mengarah ke `/api/v1/vscode/{token}/chat/completions`.
-- Bidang `modelsUrl` harus mengarah ke `/api/v1/vscode/{token}/models`.
-- Utamakan alur normal `/v1` + header Bearer ketika klien mendukung header kustom.
-- Token yang tertanam dalam URL adalah fallback kompatibilitas dan mungkin muncul dalam log editor atau riwayat proxy.
-
----
-
-#### Kiro CLI (Amazon)
-
-```bash
-# Masuk ke akun AWS/Kiro Anda:
-kiro-cli login
-
-# CLI menggunakan otentikasi sendiri — OmniRoute tidak diperlukan sebagai backend untuk Kiro CLI itu sendiri.
-# Gunakan kiro-cli bersamaan dengan OmniRoute untuk alat lainnya.
-kiro-cli status
-```
-
-Untuk aplikasi desktop **Kiro IDE**, gunakan endpoint MITM yang diekspos oleh OmniRoute
-di bawah `/dashboard/cli-tools → Kiro`.
-
----
-
-## 10. Internal OmniRoute CLI
-
-Biner `omniroute` menyediakan perintah untuk siklus hidup server, pengaturan, diagnostik, dan manajemen penyedia. Titik masuk: `bin/omniroute.mjs`.
-
-```bash
-omniroute                              # Mulai server (port default 20128)
-omniroute setup                        # Wizard pengaturan interaktif
-omniroute doctor                       # Periksa konfigurasi, DB, port, runtime
-omniroute providers list               # Koneksi penyedia yang dikonfigurasi
-omniroute providers test-all           # Uji setiap koneksi aktif
-omniroute reset-password               # Atur ulang kata sandi admin
-omniroute logs                         # Streaming log permintaan
-omniroute health                       # Kesehatan terperinci (pemutus, cache, memori)
-omniroute --version                    # Cetak versi
-omniroute --help                       # Tampilkan semua perintah
-```
-
-### Pengaturan & Inisialisasi
-
-```bash
-omniroute setup                        # Wizard pengaturan interaktif
-omniroute setup --non-interactive      # Mode CI/automasi (membaca variabel env + flag)
-omniroute setup --password '<value>'   # Atur kata sandi admin langsung
-omniroute setup --add-provider \
-  --provider openai \
-  --api-key '<value>' \
-  --test-provider                      # Tambah dan uji penyedia dalam satu langkah
-```
-
-Variabel lingkungan yang dikenali untuk pengaturan non-interaktif:
-
-| Var                 | Tujuan                                                                 |
-| ------------------- | ---------------------------------------------------------------------- |
-| `OMNIROUTE_API_KEY` | Kunci API penyedia (terikat ke `--api-key` melalui Commander `.env()`) |
-| `DATA_DIR`          | Ganti direktori data OmniRoute                                         |
-
-Semua input non-interaktif lainnya diteruskan sebagai flag, bukan variabel lingkungan:
-`--password`, `--provider`, `--provider-name`, `--provider-base-url`, `--default-model`
-(lihat opsi `omniroute setup` di atas).
-
-### Diagnostik
-
-```bash
-omniroute doctor                       # Periksa konfigurasi, DB, port, runtime, memori, keberlangsungan
-omniroute doctor --json                # JSON yang dapat dibaca mesin
-omniroute doctor --no-liveness         # Lewati probe kesehatan HTTP
-omniroute doctor --host 0.0.0.0        # Ganti host keberlangsungan
-omniroute doctor --liveness-url <url>  # Ganti URL endpoint kesehatan penuh
-```
-
-Dokter menjalankan pemeriksaan ini: `Konfigurasi`, `Database`, `Penyimpanan/enkripsi`,
-`Ketersediaan Port`, `Runtime Node`, `Biner asli` (better-sqlite3),
-`Memori`, dan `Keberlangsungan Server`. Ia keluar dengan status non-nol jika ada pemeriksaan yang `gagal`.
-
-### Manajemen Penyedia
-
-```bash
-omniroute providers available                       # Katalog penyedia OmniRoute
-omniroute providers available --search openai       # Filter katalog berdasarkan id/nama/alias/kategori
-omniroute providers available --category api-key    # Filter berdasarkan kategori (api-key, oauth, gratis, ...)
-omniroute providers available --json                # JSON yang dapat dibaca mesin
-
-omniroute providers list                            # Koneksi penyedia yang dikonfigurasi
-omniroute providers list --json
-
-omniroute providers test <id|name>                  # Uji satu koneksi yang dikonfigurasi
-omniroute providers test-all                        # Uji setiap koneksi aktif
-omniroute providers validate                        # Validasi struktural lokal saja
-omniroute providers add <provider> --credential-env PROVIDER_KEY
-omniroute providers import ./providers.json --dry-run --json
-omniroute providers auth <provider>                 # Alur OAuth yang ada
-omniroute providers edit <id|name> --default-model <model>
-omniroute providers remove <id|name> --yes
-```
-
-`providers add/import/auth/edit/remove` bersifat API-first dan oleh karena itu bekerja terhadap
-konteks lokal atau jarak jauh yang aktif. Input kredensial harus menggunakan
-`--credential-stdin` atau `--credential-env`; `--dry-run --json` hanya melaporkan
-keberadaan/bentuk yang disunting. `providers available` membaca katalog OmniRoute;
-`providers list/test/test-all/validate` mempertahankan perilaku SQLite lokal mereka dan
-tidak memerlukan server untuk berjalan.
-
-### Pemulihan & Atur Ulang
-
-```bash
-omniroute reset-password                # Atur ulang kata sandi admin (juga: omniroute-reset-password)
-omniroute reset-encrypted-columns       # Tampilkan peringatan + dry-run untuk atur ulang kredensial terenkripsi
-omniroute reset-encrypted-columns --force  # Benar-benar menghapus kredensial terenkripsi di SQLite
-```
-
-### Ekspor Kredensial (⚠ tangani dengan hati-hati)
-
-```bash
-omniroute auth export                                 # Tampilkan peringatan + gerbang konfirmasi — tidak ada akses DB
-omniroute auth export --force                          # Ekspor SEMUA kredensial KONEKSI yang DECRYPTED ke stdout sebagai JSON
-omniroute auth export --force --id <id>                 # Ekspor hanya koneksi yang cocok
-omniroute auth export --force --format env               # Emit OMNIROUTE_<PROVIDER>_<FIELD>=<value> baris
-omniroute auth export --force --out creds.json           # Tulis ke file (dibuat dengan izin 0600)
-```
-
-`auth export` bersifat **lokal saja** (baca SQLite langsung, tidak ada rute HTTP) dan sengaja mencetak/menulis
-nilai **plaintext** `apiKey`/`accessToken`/`refreshToken`/`idToken` — itu adalah fitur, bukan
-bug. Tidak ada yang dibaca dari database, dan tidak ada yang didekripsi, tanpa `--force`. Sebuah banner peringatan stderr
-selalu dicetak sebelum ada plaintext yang dikeluarkan. Memerlukan `STORAGE_ENCRYPTION_KEY` untuk
-diatur. Sebuah field yang gagal didekripsi (kunci kadaluarsa, ciphertext rusak) dilaporkan sebagai
-`<field>DecryptFailed: true` alih-alih menghentikan seluruh ekspor atau membocorkan kesalahan yang mendasarinya.
-
-### Subperintah Lainnya
-
-Ini mengasumsikan server OmniRoute yang berjalan, kecuali dinyatakan sebaliknya:
-
-```bash
-omniroute status                       # Status runtime yang komprehensif
-omniroute logs                         # Streaming log permintaan (--json, --search, --follow)
-omniroute config show                  # Tampilkan konfigurasi saat ini
-
-omniroute provider list                # Daftar penyedia yang tersedia (alias dari providers list)
-omniroute provider add                 # Daftarkan OmniRoute sebagai penyedia di alat
-omniroute keys add | list | remove     # Kelola kunci API
-omniroute models [provider]            # Daftar model (--json, --search)
-omniroute combo list | switch | create | delete
-
-omniroute backup                       # Snapshot konfigurasi + DB
-omniroute restore                      # Pulihkan dari snapshot sebelumnya
-
-omniroute health                       # Kesehatan terperinci (pemutus, cache, memori)
-omniroute quota                        # Penggunaan kuota penyedia
-omniroute cache                        # Status cache
-omniroute cache clear                  # Hapus cache semantik + tanda tangan
-
-omniroute mcp status | restart         # Status server MCP / restart
-omniroute a2a status | card            # Status server A2A / kartu agen
-
-omniroute tunnel list | create | stop  # Kelola terowongan (cloudflare/tailscale/ngrok)
-omniroute env show | get <k> | set <k> <v>  # Periksa / atur variabel env (sementara)
-
-omniroute test                         # Uji konektivitas penyedia
-omniroute update                       # Periksa pembaruan
-omniroute completion                   # Hasilkan penyelesaian shell
-```
-
-### Flag Umum
-
-| Flag                | Deskripsi                                                    |
-| ------------------- | ------------------------------------------------------------ |
-| `--no-open`         | Jangan otomatis membuka browser saat mulai                   |
-| `--port <n>`        | Ganti port API (default 20128)                               |
-| `--mcp`             | Jalankan sebagai server MCP melalui stdio (untuk IDE)        |
-| `--non-interactive` | Mode CI (tanpa prompt; membaca dari env/flags)               |
-| `--json`            | Output JSON yang dapat dibaca mesin (dokter, penyedia, dll.) |
-| `--help`, `-h`      | Tampilkan bantuan spesifik perintah                          |
-| `--version`, `-v`   | Cetak versi yang terinstal                                   |
-
-## Endpoint API yang Tersedia
-
-| Endpoint                   | Deskripsi                        | Digunakan Untuk                      |
-| -------------------------- | -------------------------------- | ------------------------------------ |
-| `/v1/chat/completions`     | Obrolan standar (semua penyedia) | Semua alat modern                    |
-| `/v1/responses`            | API respons (format OpenAI)      | Codex, alur kerja agentik            |
-| `/v1/completions`          | Penyelesaian teks warisan        | Alat lama yang menggunakan `prompt:` |
-| `/v1/embeddings`           | Embedding teks                   | RAG, pencarian                       |
-| `/v1/images/generations`   | Generasi gambar                  | GPT-Image, Flux, dll.                |
-| `/v1/audio/speech`         | Teks-ke-suara                    | ElevenLabs, OpenAI TTS               |
-| `/v1/audio/transcriptions` | Suara-ke-teks                    | Deepgram, AssemblyAI                 |
-
-Contoh siap-tempel dengan URL OmniRoute yang ter-tokenisasi:
-
-```txt
-Token contoh: sk-a3ab3c080beaee3a-69f4a4-070d71af
-
-Basis OpenAI standar: http://localhost:20128/v1
-Model VS Code: http://localhost:20128/api/v1/vscode/sk-a3ab3c080beaee3a-69f4a4-070d71af/models
-Obrolan VS Code: http://localhost:20128/api/v1/vscode/sk-a3ab3c080beaee3a-69f4a4-070d71af/chat/completions
-Respons VS Code: http://localhost:20128/api/v1/vscode/sk-a3ab3c080beaee3a-69f4a4-070d71af/responses
-Tag Ollama: http://localhost:20128/api/v1/vscode/sk-a3ab3c080beaee3a-69f4a4-070d71af/api/tags
-Obrolan Ollama: http://localhost:20128/api/v1/vscode/sk-a3ab3c080beaee3a-69f4a4-070d71af/api/chat
-```
-
----
-
-## Pemecahan Masalah
-
-| Kesalahan                                              | Penyebab                          | Perbaikan                                           |
-| ------------------------------------------------------ | --------------------------------- | --------------------------------------------------- |
-| `Connection refused`                                   | OmniRoute tidak berjalan          | `omniroute serve`                                   |
-| `401 Unauthorized`                                     | Kunci API salah                   | Periksa di `/dashboard/api-manager`                 |
-| `No combo configured`                                  | Tidak ada kombinasi routing aktif | Atur di `/dashboard/combos`                         |
-| CLI menunjukkan "not installed"                        | Biner tidak ada di PATH           | Periksa `which <command>`                           |
-| Dashboard menunjukkan "not detected" setelah instalasi | Cache usang                       | Klik "⟳ Refresh detection" di dashboard             |
-| Tautan lama `/dashboard/cli-tools`                     | Bookmark sebelum v3.8.6           | Dialihkan otomatis ke `/dashboard/cli-code` (308)   |
-| Tautan lama `/dashboard/agents`                        | Bookmark sebelum v3.8.6           | Dialihkan otomatis ke `/dashboard/acp-agents` (308) |
diff --git a/docs/i18n/in/docs/reference/ENVIRONMENT.md b/docs/i18n/in/docs/reference/ENVIRONMENT.md
deleted file mode 100644
index 2a54e2ca21..0000000000
--- a/docs/i18n/in/docs/reference/ENVIRONMENT.md
+++ /dev/null
@@ -1,665 +0,0 @@
-# Environment Variables Reference (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../../docs/ENVIRONMENT.md) · 🇪🇸 [es](../../es/docs/ENVIRONMENT.md) · 🇫🇷 [fr](../../fr/docs/ENVIRONMENT.md) · 🇩🇪 [de](../../de/docs/ENVIRONMENT.md) · 🇮🇹 [it](../../it/docs/ENVIRONMENT.md) · 🇷🇺 [ru](../../ru/docs/ENVIRONMENT.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/ENVIRONMENT.md) · 🇯🇵 [ja](../../ja/docs/ENVIRONMENT.md) · 🇰🇷 [ko](../../ko/docs/ENVIRONMENT.md) · 🇸🇦 [ar](../../ar/docs/ENVIRONMENT.md) · 🇮🇳 [hi](../../hi/docs/ENVIRONMENT.md) · 🇮🇳 [in](../../in/docs/ENVIRONMENT.md) · 🇹🇭 [th](../../th/docs/ENVIRONMENT.md) · 🇻🇳 [vi](../../vi/docs/ENVIRONMENT.md) · 🇮🇩 [id](../../id/docs/ENVIRONMENT.md) · 🇲🇾 [ms](../../ms/docs/ENVIRONMENT.md) · 🇳🇱 [nl](../../nl/docs/ENVIRONMENT.md) · 🇵🇱 [pl](../../pl/docs/ENVIRONMENT.md) · 🇸🇪 [sv](../../sv/docs/ENVIRONMENT.md) · 🇳🇴 [no](../../no/docs/ENVIRONMENT.md) · 🇩🇰 [da](../../da/docs/ENVIRONMENT.md) · 🇫🇮 [fi](../../fi/docs/ENVIRONMENT.md) · 🇵🇹 [pt](../../pt/docs/ENVIRONMENT.md) · 🇷🇴 [ro](../../ro/docs/ENVIRONMENT.md) · 🇭🇺 [hu](../../hu/docs/ENVIRONMENT.md) · 🇧🇬 [bg](../../bg/docs/ENVIRONMENT.md) · 🇸🇰 [sk](../../sk/docs/ENVIRONMENT.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/ENVIRONMENT.md) · 🇮🇱 [he](../../he/docs/ENVIRONMENT.md) · 🇵🇭 [phi](../../phi/docs/ENVIRONMENT.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/ENVIRONMENT.md) · 🇨🇿 [cs](../../cs/docs/ENVIRONMENT.md) · 🇹🇷 [tr](../../tr/docs/ENVIRONMENT.md)
-
----
-
-> Complete reference for every environment variable recognized by OmniRoute.
-> For a quick-start template, see [`.env.example`](../.env.example).
-
----
-
-## Table of Contents
-
-- [1. Required Secrets](#1-required-secrets)
-- [2. Storage & Database](#2-storage--database)
-- [3. Network & Ports](#3-network--ports)
-- [4. Security & Authentication](#4-security--authentication)
-- [5. Input Sanitization & PII Protection](#5-input-sanitization--pii-protection)
-- [6. Tool & Routing Policies](#6-tool--routing-policies)
-- [7. URLs & Cloud Sync](#7-urls--cloud-sync)
-- [8. Outbound Proxy](#8-outbound-proxy)
-- [9. CLI Tool Integration](#9-cli-tool-integration)
-- [10. Internal Agent & MCP Integrations](#10-internal-agent--mcp-integrations)
-- [11. OAuth Provider Credentials](#11-oauth-provider-credentials)
-- [12. Provider User-Agent Overrides](#12-provider-user-agent-overrides)
-- [13. CLI Fingerprint Compatibility](#13-cli-fingerprint-compatibility)
-- [14. API Key Providers](#14-api-key-providers)
-- [15. Timeout Settings](#15-timeout-settings)
-- [16. Logging](#16-logging)
-- [17. Memory Optimization](#17-memory-optimization)
-- [18. Pricing Sync](#18-pricing-sync)
-- [19. Model Sync (Dev)](#19-model-sync-dev)
-- [20. Provider-Specific Settings](#20-provider-specific-settings)
-- [21. Proxy Health](#21-proxy-health)
-- [22. Debugging](#22-debugging)
-- [23. GitHub Integration](#23-github-integration)
-- [Deployment Scenarios](#deployment-scenarios)
-- [Audit: Removed / Dead Variables](#audit-removed--dead-variables)
-
----
-
-## 1. Required Secrets
-
-These **must** be set before the first run. Without them, the application will either refuse to start or operate with insecure defaults.
-
-| Variable           | Required | Default  | Source File             | Description                                                                                                                      |
-| ------------------ | -------- | -------- | ----------------------- | -------------------------------------------------------------------------------------------------------------------------------- |
-| `JWT_SECRET`       | **Yes**  | _(none)_ | `src/lib/auth`          | Signs/verifies all dashboard session cookies (JWT). Generate with `openssl rand -base64 48`.                                     |
-| `API_KEY_SECRET`   | **Yes**  | _(none)_ | `src/lib/db/apiKeys.ts` | AES encryption key for API key values at rest in SQLite. Generate with `openssl rand -hex 32`.                                   |
-| `INITIAL_PASSWORD` | **Yes**  | `123456` | Bootstrap script        | Sets the initial admin dashboard password. **Change before first use.** After login, change via Dashboard → Settings → Security. |
-
-### Generation Commands
-
-```bash
-# Generate all three secrets at once:
-echo "JWT_SECRET=$(openssl rand -base64 48)"
-echo "API_KEY_SECRET=$(openssl rand -hex 32)"
-echo "INITIAL_PASSWORD=$(openssl rand -base64 16)"
-```
-
-> [!CAUTION]
-> Never commit `.env` files with real secrets to version control. The `.gitignore` already excludes `.env`, but verify before pushing.
-
----
-
-## 2. Storage & Database
-
-OmniRoute uses **SQLite** (via `better-sqlite3`) for all persistence. These variables control data location, encryption, and lifecycle.
-
-| Variable                         | Default              | Source File                                     | Description                                                                                                        |
-| -------------------------------- | -------------------- | ----------------------------------------------- | ------------------------------------------------------------------------------------------------------------------ |
-| `DATA_DIR`                       | `~/.omniroute/`      | `src/lib/db/core.ts`                            | Root directory for SQLite DB, backups, and data files. Override for Docker volumes or custom paths.                |
-| `STORAGE_ENCRYPTION_KEY`         | _(empty = disabled)_ | `src/lib/db/encryption.ts`                      | AES key for full SQLite database encryption at rest. Generate with `openssl rand -hex 32`.                         |
-| `STORAGE_ENCRYPTION_KEY_VERSION` | `v1`                 | `scripts/bootstrap-env.mjs`, `electron/main.js` | Version label for the encryption key. Increment when performing key rotation to support decryption of old backups. |
-| `DISABLE_SQLITE_AUTO_BACKUP`     | `false`              | `src/lib/db/backup.ts`                          | When `true`, skips the automatic database backup that runs before migrations on every startup.                     |
-| `OMNIROUTE_CRYPT_KEY`            | _(unset)_            | `src/lib/db/encryption.ts`                      | **Legacy alias** for `STORAGE_ENCRYPTION_KEY`. Accepted as a fallback when the primary variable is absent.         |
-| `OMNIROUTE_API_KEY_BASE64`       | _(unset)_            | `src/lib/db/encryption.ts`                      | **Legacy alias** (Base64-encoded form) accepted as a fallback. Decoded automatically before use.                   |
-
-### Scenarios
-
-| Scenario              | Configuration                                                                    |
-| --------------------- | -------------------------------------------------------------------------------- |
-| **Local development** | Leave all defaults. DB lives at `~/.omniroute/omniroute.db`.                     |
-| **Docker**            | `DATA_DIR=/data` + mount a volume at `/data`.                                    |
-| **Encrypted at rest** | Set `STORAGE_ENCRYPTION_KEY` + keep backups of the key! Losing it = losing data. |
-| **CI/Testing**        | `DATA_DIR=/tmp/omniroute-test` — ephemeral, no encryption needed.                |
-
----
-
-## 3. Network & Ports
-
-| Variable              | Default      | Source File                | Description                                                                            |
-| --------------------- | ------------ | -------------------------- | -------------------------------------------------------------------------------------- |
-| `PORT`                | `20128`      | `src/lib/runtime/ports.ts` | Primary port for both Dashboard UI and API endpoints (single-port mode).               |
-| `API_PORT`            | _(unset)_    | `src/lib/runtime/ports.ts` | When set, serves the `/v1/*` proxy API on this separate port.                          |
-| `API_HOST`            | `0.0.0.0`    | `src/lib/runtime/ports.ts` | Bind address for the API port.                                                         |
-| `DASHBOARD_PORT`      | _(unset)_    | `src/lib/runtime/ports.ts` | When set, serves the Dashboard UI on this separate port.                               |
-| `PROD_DASHBOARD_PORT` | `20130`      | `docker-compose.prod.yml`  | Host-side published port for the Dashboard in Docker production mode.                  |
-| `PROD_API_PORT`       | `20131`      | `docker-compose.prod.yml`  | Host-side published port for the API in Docker production mode.                        |
-| `OMNIROUTE_PORT`      | _(unset)_    | `src/lib/runtime/ports.ts` | Takes precedence over `PORT` when running inside Electron or other wrappers.           |
-| `NODE_ENV`            | `production` | Next.js core               | Controls logging verbosity, caching, error detail exposure, and Next.js optimizations. |
-
-### Port Modes
-
-```
-┌─────────────────────────── Single Port (default) ──────────────────────────┐
-│  PORT=20128                                                                 │
-│  → Dashboard: http://localhost:20128                                        │
-│  → API:       http://localhost:20128/v1/chat/completions                    │
-└─────────────────────────────────────────────────────────────────────────────┘
-
-┌─────────────────────────── Split Ports ─────────────────────────────────────┐
-│  DASHBOARD_PORT=20128                                                       │
-│  API_PORT=20129                                                             │
-│  API_HOST=0.0.0.0                                                           │
-│  → Dashboard: http://localhost:20128                                        │
-│  → API:       http://0.0.0.0:20129/v1/chat/completions                     │
-│  Use case: Expose API to LAN while restricting Dashboard to localhost.      │
-└─────────────────────────────────────────────────────────────────────────────┘
-
-┌─────────────────────────── Docker Production ──────────────────────────────┐
-│  PROD_DASHBOARD_PORT=443   PROD_API_PORT=8443                              │
-│  → Maps container ports to host ports in docker-compose.prod.yml.          │
-└─────────────────────────────────────────────────────────────────────────────┘
-```
-
----
-
-## 4. Security & Authentication
-
-| Variable                      | Default               | Source File                              | Description                                                                                               |
-| ----------------------------- | --------------------- | ---------------------------------------- | --------------------------------------------------------------------------------------------------------- |
-| `MACHINE_ID_SALT`             | `endpoint-proxy-salt` | `src/lib/auth`                           | Salt combined with hardware identifiers for machine fingerprinting. Change per-deployment for isolation.  |
-| `AUTH_COOKIE_SECURE`          | `false`               | `src/lib/auth`                           | Sets the `Secure` flag on session cookies. **Must be `true`** when running behind HTTPS.                  |
-| `REQUIRE_API_KEY`             | `false`               | API middleware                           | When `true`, all `/v1/*` proxy requests must include a valid API key.                                     |
-| `ALLOW_API_KEY_REVEAL`        | `false`               | Dashboard providers page                 | Allows revealing full API key values in the Dashboard UI. Security risk on shared instances.              |
-| `NO_LOG_API_KEY_IDS`          | _(empty)_             | `src/lib/compliance/index.ts`            | Comma-separated API key IDs that bypass request logging (GDPR compliance).                                |
-| `MAX_BODY_SIZE_BYTES`         | `10485760` (10 MB)    | `src/shared/middleware/bodySizeGuard.ts` | Maximum allowed request body size. Rejects payloads exceeding this limit.                                 |
-| `CORS_ORIGIN`                 | `*`                   | Next.js middleware                       | CORS `Access-Control-Allow-Origin` value. Restrict for production.                                        |
-| `OUTBOUND_SSRF_GUARD_ENABLED` | `true`                | `src/shared/network/outboundUrlGuard.ts` | Block provider calls targeting private/loopback/link-local IP ranges. Disable only in isolated test envs. |
-
-### Hardening Checklist
-
-```bash
-# Production security minimum:
-AUTH_COOKIE_SECURE=true        # Requires HTTPS
-REQUIRE_API_KEY=true           # Authenticate all proxy calls
-ALLOW_API_KEY_REVEAL=false     # Never expose keys in UI
-CORS_ORIGIN=https://your.domain.com
-MAX_BODY_SIZE_BYTES=5242880    # 5 MB limit
-```
-
----
-
-## 5. Input Sanitization & PII Protection
-
-OmniRoute provides a two-layer defense: request-side injection scanning and response-side PII stripping.
-
-### Request-Side: Prompt Injection Guard
-
-| Variable                  | Default   | Source File                              | Description                                                                                 |
-| ------------------------- | --------- | ---------------------------------------- | ------------------------------------------------------------------------------------------- |
-| `INPUT_SANITIZER_ENABLED` | `true`    | `src/middleware/promptInjectionGuard.ts` | Enable scanning of incoming messages for prompt injection patterns.                         |
-| `INPUT_SANITIZER_MODE`    | `warn`    | `src/middleware/promptInjectionGuard.ts` | `warn` = log only, `block` = reject request with 400, `redact` = strip suspicious patterns. |
-| `INJECTION_GUARD_MODE`    | _(unset)_ | `src/middleware/promptInjectionGuard.ts` | Legacy alias for `INPUT_SANITIZER_MODE` — same behavior.                                    |
-| `PII_REDACTION_ENABLED`   | `false`   | `src/middleware/promptInjectionGuard.ts` | Detect PII (emails, phones, SSNs) in incoming requests.                                     |
-
-### Response-Side: PII Sanitizer
-
-| Variable                         | Default  | Source File               | Description                                                             |
-| -------------------------------- | -------- | ------------------------- | ----------------------------------------------------------------------- |
-| `PII_RESPONSE_SANITIZATION`      | `false`  | `src/lib/piiSanitizer.ts` | Scan LLM responses for leaked PII before returning to client.           |
-| `PII_RESPONSE_SANITIZATION_MODE` | `redact` | `src/lib/piiSanitizer.ts` | `redact` = mask PII, `warn` = log only, `block` = drop entire response. |
-
-### Scenarios
-
-| Scenario                  | Configuration                                                                                                                |
-| ------------------------- | ---------------------------------------------------------------------------------------------------------------------------- |
-| **Enterprise compliance** | `INPUT_SANITIZER_ENABLED=true`, `INPUT_SANITIZER_MODE=block`, `PII_REDACTION_ENABLED=true`, `PII_RESPONSE_SANITIZATION=true` |
-| **Monitoring only**       | `INPUT_SANITIZER_ENABLED=true`, `INPUT_SANITIZER_MODE=warn` — logs but never blocks                                          |
-| **Personal use**          | Leave all disabled — zero overhead                                                                                           |
-
----
-
-## 6. Tool & Routing Policies
-
-| Variable           | Default    | Source File             | Description                                                                                                                               |
-| ------------------ | ---------- | ----------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
-| `TOOL_POLICY_MODE` | `disabled` | `src/lib/toolPolicy.ts` | Controls LLM tool/function-calling access. `allowlist` = only listed tools, `denylist` = all except listed, `disabled` = no restrictions. |
-
----
-
-## 7. URLs & Cloud Sync
-
-| Variable                | Default                  | Source File                                 | Description                                                                                                     |
-| ----------------------- | ------------------------ | ------------------------------------------- | --------------------------------------------------------------------------------------------------------------- |
-| `BASE_URL`              | `http://localhost:20128` | `src/lib/cloudSync.ts`                      | Server-side URL for internal sync jobs to call `/api/sync/cloud`.                                               |
-| `CLOUD_URL`             | _(empty)_                | `src/lib/cloudSync.ts`                      | Cloud relay endpoint URL (premium feature).                                                                     |
-| `CLOUD_SYNC_TIMEOUT_MS` | `12000`                  | `src/lib/cloudSync.ts`                      | HTTP timeout for cloud sync requests.                                                                           |
-| `NEXT_PUBLIC_BASE_URL`  | `http://localhost:20128` | OAuth, Dashboard, sync                      | Public-facing URL for OAuth redirect_uri, Dashboard links. **Must match your public URL behind reverse proxy.** |
-| `NEXT_PUBLIC_CLOUD_URL` | _(empty)_                | Client-side                                 | Client-side mirror of `CLOUD_URL`.                                                                              |
-| `NEXT_PUBLIC_APP_URL`   | _(unset)_                | `src/shared/services/cloudSyncScheduler.ts` | Legacy fallback for `NEXT_PUBLIC_BASE_URL`.                                                                     |
-
-> [!IMPORTANT]
-> When deploying behind a reverse proxy (nginx, Caddy), `NEXT_PUBLIC_BASE_URL` **must** be set to your public URL (e.g., `https://omniroute.example.com`). Without this, OAuth callbacks will fail because the redirect_uri won't match.
-
----
-
-## 8. Outbound Proxy
-
-Route upstream LLM provider calls through an HTTP or SOCKS5 proxy for egress control, geo-routing, or IP masking.
-
-| Variable                          | Default   | Source File          | Description                                                                         |
-| --------------------------------- | --------- | -------------------- | ----------------------------------------------------------------------------------- |
-| `ENABLE_SOCKS5_PROXY`             | `true`    | `open-sse/executors` | Enable SOCKS5 proxy agent for upstream calls.                                       |
-| `NEXT_PUBLIC_ENABLE_SOCKS5_PROXY` | `true`    | Client-side          | Client-side awareness of SOCKS5 availability.                                       |
-| `HTTP_PROXY`                      | _(unset)_ | Node.js standard     | HTTP proxy for upstream calls.                                                      |
-| `HTTPS_PROXY`                     | _(unset)_ | Node.js standard     | HTTPS proxy for upstream calls.                                                     |
-| `ALL_PROXY`                       | _(unset)_ | Node.js standard     | Universal proxy (supports `socks5://`).                                             |
-| `NO_PROXY`                        | _(unset)_ | Node.js standard     | Comma-separated hostnames/IPs to bypass the proxy.                                  |
-| `ENABLE_TLS_FINGERPRINT`          | `false`   | `open-sse/executors` | Spoof TLS fingerprint using wreq-js (mimics Chrome 124). Counters JA3/JA4 blocking. |
-
-### Scenarios
-
-| Scenario                      | Configuration                                                                                                             |
-| ----------------------------- | ------------------------------------------------------------------------------------------------------------------------- |
-| **SOCKS5 through SSH tunnel** | `ALL_PROXY=socks5://127.0.0.1:7890`, `ENABLE_SOCKS5_PROXY=true`                                                           |
-| **Corporate HTTP proxy**      | `HTTP_PROXY=http://proxy.corp.com:3128`, `HTTPS_PROXY=http://proxy.corp.com:3128`, `NO_PROXY=localhost,internal.corp.com` |
-| **Anti-fingerprint**          | `ENABLE_TLS_FINGERPRINT=true` — requires `wreq-js` (included)                                                             |
-
----
-
-## 9. CLI Tool Integration
-
-Controls how OmniRoute discovers and launches CLI sidecars (Claude Code, Codex, etc.).
-
-| Variable                  | Default    | Source File                         | Description                                                                |
-| ------------------------- | ---------- | ----------------------------------- | -------------------------------------------------------------------------- |
-| `CLI_MODE`                | `auto`     | `src/shared/services/cliRuntime.ts` | `auto` = search system PATH; `manual` = use explicit paths only.           |
-| `CLI_EXTRA_PATHS`         | _(unset)_  | `src/shared/services/cliRuntime.ts` | Additional PATH entries for CLI binary discovery (colon-separated).        |
-| `CLI_CONFIG_HOME`         | _(unset)_  | `src/shared/services/cliRuntime.ts` | Override home directory for reading CLI configs (`~/.claude`, `~/.codex`). |
-| `CLI_ALLOW_CONFIG_WRITES` | `false`    | `src/shared/services/cliRuntime.ts` | Allow OmniRoute to write CLI config files (token refresh, session data).   |
-| `CLI_CLAUDE_BIN`          | `claude`   | `src/shared/services/cliRuntime.ts` | Custom path to Claude CLI binary.                                          |
-| `CLI_CODEX_BIN`           | `codex`    | `src/shared/services/cliRuntime.ts` | Custom path to Codex CLI binary.                                           |
-| `CLI_DROID_BIN`           | `droid`    | `src/shared/services/cliRuntime.ts` | Custom path to Droid CLI binary.                                           |
-| `CLI_OPENCLAW_BIN`        | `openclaw` | `src/shared/services/cliRuntime.ts` | Custom path to OpenClaw CLI binary.                                        |
-| `CLI_CURSOR_BIN`          | `agent`    | `src/shared/services/cliRuntime.ts` | Custom path to Cursor agent binary.                                        |
-| `CLI_CLINE_BIN`           | `cline`    | `src/shared/services/cliRuntime.ts` | Custom path to Cline CLI binary.                                           |
-| `CLI_CONTINUE_BIN`        | `cn`       | `src/shared/services/cliRuntime.ts` | Custom path to Continue CLI binary.                                        |
-| `CLI_QODER_BIN`           | `qoder`    | `src/shared/services/cliRuntime.ts` | Custom path to Qoder CLI binary.                                           |
-
-### Docker Example
-
-```bash
-# Mount host binaries into the container and tell OmniRoute where they are:
-CLI_EXTRA_PATHS=/host-cli/bin
-CLI_CONFIG_HOME=/root
-CLI_ALLOW_CONFIG_WRITES=true
-CLI_CLAUDE_BIN=/host-cli/bin/claude
-```
-
----
-
-## 10. Internal Agent & MCP Integrations
-
-| Variable                                | Default     | Source File                                 | Description                                                                                                                   |
-| --------------------------------------- | ----------- | ------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------- |
-| `OMNIROUTE_BASE_URL`                    | auto-detect | `open-sse/mcp-server/server.ts`             | Explicit URL for MCP/A2A tools to reach OmniRoute. Overrides localhost auto-detection.                                        |
-| `OMNIROUTE_API_KEY`                     | _(unset)_   | MCP/A2A modules                             | API key for internal MCP tool and A2A skill calls.                                                                            |
-| `OMNIROUTE_API_KEY_ID`                  | _(unset)_   | `open-sse/mcp-server/audit.ts`              | Key ID for MCP audit log attribution.                                                                                         |
-| `ROUTER_API_KEY`                        | _(unset)_   | Legacy                                      | Legacy alias for `OMNIROUTE_API_KEY`.                                                                                         |
-| `OMNIROUTE_MCP_ENFORCE_SCOPES`          | `false`     | `open-sse/mcp-server/server.ts`             | Enforce scope-based access control on MCP tool calls.                                                                         |
-| `OMNIROUTE_MCP_SCOPES`                  | _(all)_     | `open-sse/mcp-server/server.ts`             | Comma-separated scopes: `admin`, `combos`, `health`, `models`, `routing`, `budget`, `metrics`, `pricing`, `memory`, `skills`. |
-| `MODEL_SYNC_INTERVAL_HOURS`             | `24`        | `src/shared/services/modelSyncScheduler.ts` | Model catalog sync interval in hours.                                                                                         |
-| `PROVIDER_LIMITS_SYNC_INTERVAL_MINUTES` | `70`        | `src/server-init.ts`                        | Provider rate-limit and quota polling interval.                                                                               |
-| `OMNIROUTE_DISABLE_BACKGROUND_SERVICES` | `false`     | `src/instrumentation-node.ts`               | Disable all background services (sync, pricing, model refresh). Useful for CI/test.                                           |
-| `OMNIROUTE_BOOTSTRAPPED`                | `false`     | `src/app/(dashboard)/dashboard/page.tsx`    | Set `true` by bootstrap script after initial setup. Controls setup wizard visibility.                                         |
-| `OMNIROUTE_ALLOW_BODY_PROJECT_OVERRIDE` | `0`         | `open-sse/executors/antigravity.ts`         | Escape hatch: allow request body to override the Antigravity project field.                                                   |
-
-### OAuth CLI Bridge (Internal)
-
-| Variable            | Default     | Source File                     | Description                               |
-| ------------------- | ----------- | ------------------------------- | ----------------------------------------- |
-| `OMNIROUTE_SERVER`  | auto-detect | `src/lib/oauth/config/index.ts` | Server URL for CLI↔OmniRoute auth bridge. |
-| `OMNIROUTE_TOKEN`   | _(unset)_   | `src/lib/oauth/config/index.ts` | Auth token for CLI bridge.                |
-| `OMNIROUTE_USER_ID` | `cli`       | `src/lib/oauth/config/index.ts` | User ID for CLI bridge sessions.          |
-| `SERVER_URL`        | _(unset)_   | `src/lib/oauth/config/index.ts` | Legacy alias for `OMNIROUTE_SERVER`.      |
-| `CLI_TOKEN`         | _(unset)_   | `src/lib/oauth/config/index.ts` | Legacy alias for `OMNIROUTE_TOKEN`.       |
-| `CLI_USER_ID`       | _(unset)_   | `src/lib/oauth/config/index.ts` | Legacy alias for `OMNIROUTE_USER_ID`.     |
-
----
-
-## 11. OAuth Provider Credentials
-
-Built-in credentials for **localhost development**. For remote deployments, register your own at each provider's developer console.
-
-| Variable                          | Provider                | Notes                                                                             |
-| --------------------------------- | ----------------------- | --------------------------------------------------------------------------------- |
-| `CLAUDE_OAUTH_CLIENT_ID`          | Claude Code (Anthropic) | Public client — no secret needed.                                                 |
-| `CLAUDE_CODE_REDIRECT_URI`        | Claude Code             | Override redirect URI. Default: `https://platform.claude.com/oauth/code/callback` |
-| `CODEX_OAUTH_CLIENT_ID`           | Codex / OpenAI          | Public client.                                                                    |
-| `GEMINI_OAUTH_CLIENT_ID`          | Gemini (Google)         | Requires matching `_SECRET`.                                                      |
-| `GEMINI_OAUTH_CLIENT_SECRET`      | Gemini (Google)         | —                                                                                 |
-| `QWEN_OAUTH_CLIENT_ID`            | Qwen (Alibaba)          | Public client.                                                                    |
-| `KIMI_CODING_OAUTH_CLIENT_ID`     | Kimi Coding (Moonshot)  | Public client.                                                                    |
-| `ANTIGRAVITY_OAUTH_CLIENT_ID`     | Antigravity (Google)    | Requires matching `_SECRET`.                                                      |
-| `ANTIGRAVITY_OAUTH_CLIENT_SECRET` | Antigravity (Google)    | —                                                                                 |
-| `GITHUB_OAUTH_CLIENT_ID`          | GitHub Copilot          | Public client.                                                                    |
-| `QODER_OAUTH_CLIENT_SECRET`       | Qoder                   | —                                                                                 |
-| `QODER_OAUTH_AUTHORIZE_URL`       | Qoder                   | Set to enable Qoder OAuth.                                                        |
-| `QODER_OAUTH_TOKEN_URL`           | Qoder                   | —                                                                                 |
-| `QODER_OAUTH_USERINFO_URL`        | Qoder                   | —                                                                                 |
-| `QODER_OAUTH_CLIENT_ID`           | Qoder                   | —                                                                                 |
-| `QODER_PERSONAL_ACCESS_TOKEN`     | Qoder                   | Direct API key fallback (bypasses OAuth).                                         |
-| `QODER_CLI_WORKSPACE`             | Qoder                   | Workspace ID for Qoder CLI.                                                       |
-| `OMNIROUTE_QODER_WORKSPACE`       | Qoder                   | Alias for `QODER_CLI_WORKSPACE`.                                                  |
-
-> [!WARNING]
->
-> 1. Go to [Google Cloud Console → Credentials](https://console.cloud.google.com/apis/credentials)
-> 2. Create an OAuth 2.0 Client ID (type: "Web application")
-> 3. Add your server URL as Authorized redirect URI
-> 4. Replace the credential values in `.env`.
-
----
-
-## 12. Provider User-Agent Overrides
-
-Override the `User-Agent` header sent to each upstream provider. This is dynamically resolved at runtime by the executor base class:
-
-```
-process.env[`${PROVIDER_ID}_USER_AGENT`]
-```
-
-> **Source:** `open-sse/executors/base.ts` → `buildHeaders()`
-
-| Variable                 | Default Value                                 | When to Update                                                |
-| ------------------------ | --------------------------------------------- | ------------------------------------------------------------- |
-| `CLAUDE_USER_AGENT`      | `claude-cli/2.1.219 (external, cli)`          | When Anthropic releases a new CLI version                     |
-| `CODEX_USER_AGENT`       | `codex-cli/0.132.0 (Windows 10.0.26200; x64)` | When OpenAI updates the Codex CLI                             |
-| `CODEX_CLIENT_VERSION`   | `0.131.0`                                     | Override Codex client version independently of full UA string |
-| `GITHUB_USER_AGENT`      | `GitHubCopilotChat/0.45.1`                    | When GitHub Copilot Chat updates                              |
-| `ANTIGRAVITY_USER_AGENT` | `antigravity/2.0.1 darwin/arm64`              | When Antigravity IDE updates                                  |
-| `KIRO_USER_AGENT`        | `AWS-SDK-JS/3.0.0 kiro-ide/1.0.0`             | When Kiro IDE updates                                         |
-| `QODER_USER_AGENT`       | `Qoder-Cli`                                   | When Qoder CLI updates                                        |
-| `QWEN_USER_AGENT`        | `QwenCode/0.15.11 (linux; x64)`               | When Qwen Code updates                                        |
-| `CURSOR_USER_AGENT`      | `connect-es/1.6.1`                            | When Cursor updates                                           |
-
-> [!TIP]
-> You can add User-Agent overrides for **any** provider using the pattern `{PROVIDER_ID}_USER_AGENT`. The executor dynamically constructs the env var name.
-
----
-
-## 13. CLI Fingerprint Compatibility
-
-When enabled, OmniRoute reorders HTTP headers and JSON body fields to match the exact signature of official CLI tools. This reduces the risk of account flagging while preserving your proxy IP.
-
-**Source:** `open-sse/config/cliFingerprints.ts`, `open-sse/executors/base.ts`
-
-### Per-Provider
-
-| Variable                   | Effect                                  |
-| -------------------------- | --------------------------------------- |
-| `CLI_COMPAT_CODEX=1`       | Mimics Codex CLI request signature      |
-| `CLI_COMPAT_CLAUDE=1`      | Mimics Claude Code request signature    |
-| `CLI_COMPAT_GITHUB=1`      | Mimics GitHub Copilot request signature |
-| `CLI_COMPAT_ANTIGRAVITY=1` | Mimics Antigravity request signature    |
-| `CLI_COMPAT_KIRO=1`        | Mimics Kiro IDE request signature       |
-| `CLI_COMPAT_CURSOR=1`      | Mimics Cursor request signature         |
-| `CLI_COMPAT_KIMI_CODING=1` | Mimics Kimi Coding request signature    |
-| `CLI_COMPAT_KILOCODE=1`    | Mimics Kilo Code request signature      |
-| `CLI_COMPAT_CLINE=1`       | Mimics Cline request signature          |
-| `CLI_COMPAT_QWEN=1`        | Mimics Qwen Code request signature      |
-
-### Global
-
-| Variable           | Effect                                                          |
-| ------------------ | --------------------------------------------------------------- |
-| `CLI_COMPAT_ALL=1` | Enable fingerprint compatibility for **all** providers at once. |
-
-> [!NOTE]
-> This feature works alongside the User-Agent overrides (§12). The fingerprint system handles header ordering and body field ordering, while User-Agent overrides handle the specific UA string. Both can be enabled independently.
-
----
-
-## 14. API Key Providers
-
-API keys for providers that use direct authentication. **Preferred setup:** Dashboard → Providers → Add API Key.
-
-Setting via environment variables is an alternative for Docker or headless deployments.
-
-Recognized pattern: `{PROVIDER_ID}_API_KEY`
-
-| Variable             | Provider            |
-| -------------------- | ------------------- |
-| `DEEPSEEK_API_KEY`   | DeepSeek            |
-| `GROQ_API_KEY`       | Groq                |
-| `XAI_API_KEY`        | xAI (Grok)          |
-| `MISTRAL_API_KEY`    | Mistral AI          |
-| `PERPLEXITY_API_KEY` | Perplexity          |
-| `TOGETHER_API_KEY`   | Together AI         |
-| `FIREWORKS_API_KEY`  | Fireworks AI        |
-| `CEREBRAS_API_KEY`   | Cerebras            |
-| `COHERE_API_KEY`     | Cohere              |
-| `NVIDIA_API_KEY`     | NVIDIA NIM          |
-| `NEBIUS_API_KEY`     | Nebius (embeddings) |
-
-> [!TIP]
-> Keys set via the Dashboard are stored encrypted in SQLite and take precedence over environment variables.
-
----
-
-## 15. Timeout Settings
-
-All values are in **milliseconds**. Centralized resolution in `src/shared/utils/runtimeTimeouts.ts`.
-
-### Timeout Hierarchy
-
-```
-REQUEST_TIMEOUT_MS (global override)
-├─→ FETCH_TIMEOUT_MS (upstream provider calls, default: 600000)
-│   ├─→ FETCH_HEADERS_TIMEOUT_MS (inherits from FETCH_TIMEOUT_MS)
-│   ├─→ FETCH_BODY_TIMEOUT_MS (inherits from FETCH_TIMEOUT_MS)
-│   ├─→ TLS_CLIENT_TIMEOUT_MS (inherits from FETCH_TIMEOUT_MS)
-│   ├── FETCH_CONNECT_TIMEOUT_MS (independent, default: 30000)
-│   └── FETCH_KEEPALIVE_TIMEOUT_MS (independent, default: 4000)
-├─→ STREAM_IDLE_TIMEOUT_MS (inherits from REQUEST_TIMEOUT_MS, default: 600000)
-└─→ API_BRIDGE_PROXY_TIMEOUT_MS (inherits from REQUEST_TIMEOUT_MS, default: 600000)
-    ├─→ API_BRIDGE_SERVER_REQUEST_TIMEOUT_MS (derived, default: 600000)
-    ├── API_BRIDGE_SERVER_HEADERS_TIMEOUT_MS (default: 60000)
-    ├── API_BRIDGE_SERVER_KEEPALIVE_TIMEOUT_MS (default: 5000)
-    └── API_BRIDGE_SERVER_SOCKET_TIMEOUT_MS (default: 0 = disabled)
-```
-
-| Variable                                 | Default              | Description                                                                                 |
-| ---------------------------------------- | -------------------- | ------------------------------------------------------------------------------------------- |
-| `REQUEST_TIMEOUT_MS`                     | _(unset)_            | Global shortcut — overrides both `FETCH_TIMEOUT_MS` and `STREAM_IDLE_TIMEOUT_MS` defaults.  |
-| `FETCH_TIMEOUT_MS`                       | `600000`             | Total HTTP request timeout for upstream provider calls.                                     |
-| `STREAM_IDLE_TIMEOUT_MS`                 | `600000`             | Max silence between SSE chunks before aborting. Extended-thinking models rarely pause >90s. |
-| `FETCH_HEADERS_TIMEOUT_MS`               | = `FETCH_TIMEOUT_MS` | Time to receive response headers.                                                           |
-| `FETCH_BODY_TIMEOUT_MS`                  | = `FETCH_TIMEOUT_MS` | Time to receive the full response body.                                                     |
-| `FETCH_CONNECT_TIMEOUT_MS`               | `30000`              | TCP connection establishment timeout.                                                       |
-| `FETCH_KEEPALIVE_TIMEOUT_MS`             | `4000`               | Keep-alive socket idle timeout.                                                             |
-| `TLS_CLIENT_TIMEOUT_MS`                  | = `FETCH_TIMEOUT_MS` | TLS fingerprint proxy (wreq-js) timeout.                                                    |
-| `API_BRIDGE_PROXY_TIMEOUT_MS`            | `600000`             | Proxy hop timeout for `/v1` bridge requests.                                                |
-| `API_BRIDGE_SERVER_REQUEST_TIMEOUT_MS`   | `600000`             | Overall server request timeout for the bridge.                                              |
-| `API_BRIDGE_SERVER_HEADERS_TIMEOUT_MS`   | `60000`              | Time to send response headers via the bridge.                                               |
-| `API_BRIDGE_SERVER_KEEPALIVE_TIMEOUT_MS` | `5000`               | Bridge keep-alive idle timeout.                                                             |
-| `API_BRIDGE_SERVER_SOCKET_TIMEOUT_MS`    | `0`                  | Raw socket timeout (0 = disabled).                                                          |
-| `SHUTDOWN_TIMEOUT_MS`                    | `30000`              | Grace period on SIGTERM/SIGINT before force-exit.                                           |
-
-### Scenarios
-
-| Scenario                         | Configuration                                          |
-| -------------------------------- | ------------------------------------------------------ |
-| **Long-running code generation** | `REQUEST_TIMEOUT_MS=900000` (15 min)                   |
-| **Fast-fail for production API** | `API_BRIDGE_PROXY_TIMEOUT_MS=10000`                    |
-| **Extended thinking models**     | `STREAM_IDLE_TIMEOUT_MS=300000` (5 min between chunks) |
-
----
-
-## 16. Logging
-
-The logging system writes to both stdout and rotated log files. All configuration is read by `src/lib/logEnv.ts`.
-
-| Variable                    | Default                    | Description                                                                  |
-| --------------------------- | -------------------------- | ---------------------------------------------------------------------------- |
-| `APP_LOG_LEVEL`             | `info`                     | Minimum log level: `debug`, `info`, `warn`, `error`.                         |
-| `APP_LOG_FORMAT`            | `text`                     | Output format: `text` (human-readable) or `json` (structured).               |
-| `APP_LOG_TO_FILE`           | `true`                     | Write logs to file alongside stdout.                                         |
-| `APP_LOG_FILE_PATH`         | `logs/application/app.log` | Log file path (relative to project root or `DATA_DIR`).                      |
-| `APP_LOG_MAX_FILE_SIZE`     | `50M`                      | Max file size before rotation. Accepts: `50M`, `1G`, `512K`, or plain bytes. |
-| `APP_LOG_RETENTION_DAYS`    | `7`                        | Days to keep rotated application log files.                                  |
-| `APP_LOG_MAX_FILES`         | `20`                       | Maximum rotated log file backups.                                            |
-| `CALL_LOG_RETENTION_DAYS`   | `7`                        | Days to keep request/call log entries in the database.                       |
-| `CALL_LOG_MAX_ENTRIES`      | `10000`                    | Max call log entries in the in-memory buffer.                                |
-| `CALL_LOGS_TABLE_MAX_ROWS`  | `100000`                   | Max rows in the `call_logs` SQLite table before pruning.                     |
-| `PROXY_LOGS_TABLE_MAX_ROWS` | `100000`                   | Max rows in the `proxy_logs` SQLite table before pruning.                    |
-
----
-
-## 17. Memory Optimization
-
-| Variable                   | Default            | Description                                                                                          |
-| -------------------------- | ------------------ | ---------------------------------------------------------------------------------------------------- |
-| `OMNIROUTE_MEMORY_MB`      | `512`              | Runtime V8 heap limit. Docker standalone and `omniroute serve` use it to set `--max-old-space-size`. |
-| `PROMPT_CACHE_MAX_SIZE`    | `50`               | Max cached system prompt entries.                                                                    |
-| `PROMPT_CACHE_MAX_BYTES`   | `2097152` (2 MB)   | Max total prompt cache size.                                                                         |
-| `PROMPT_CACHE_TTL_MS`      | `300000` (5 min)   | Prompt cache entry TTL.                                                                              |
-| `SEMANTIC_CACHE_MAX_SIZE`  | `100`              | Max cached temperature=0 responses.                                                                  |
-| `SEMANTIC_CACHE_MAX_BYTES` | `4194304` (4 MB)   | Max total semantic cache size.                                                                       |
-| `SEMANTIC_CACHE_TTL_MS`    | `1800000` (30 min) | Semantic cache entry TTL.                                                                            |
-| `STREAM_HISTORY_MAX`       | `50`               | Max recent stream events in the Dashboard live view buffer.                                          |
-| `CONTEXT_LENGTH_DEFAULT`   | `128000`           | Global fallback max context length for models without explicit config.                               |
-| `USAGE_TOKEN_BUFFER`       | `100`              | Extra token headroom reserved when tracking usage quotas.                                            |
-
-### Low-RAM Docker Example
-
-```bash
-OMNIROUTE_MEMORY_MB=128
-PROMPT_CACHE_MAX_SIZE=20
-PROMPT_CACHE_MAX_BYTES=524288        # 512 KB
-SEMANTIC_CACHE_MAX_SIZE=25
-SEMANTIC_CACHE_MAX_BYTES=1048576     # 1 MB
-STREAM_HISTORY_MAX=10
-```
-
----
-
-## 18. Pricing Sync
-
-Automatic model pricing data synchronization from external sources.
-
-| Variable                | Default       | Source File              | Description                   |
-| ----------------------- | ------------- | ------------------------ | ----------------------------- |
-| `PRICING_SYNC_ENABLED`  | `false`       | `src/lib/pricingSync.ts` | Opt-in periodic pricing sync. |
-| `PRICING_SYNC_INTERVAL` | `86400` (24h) | `src/lib/pricingSync.ts` | Sync interval in seconds.     |
-| `PRICING_SYNC_SOURCES`  | `litellm`     | `src/lib/pricingSync.ts` | Comma-separated data sources. |
-
----
-
-## 19. Model Sync (Dev)
-
-| Variable                   | Default       | Source File                | Description                                              |
-| -------------------------- | ------------- | -------------------------- | -------------------------------------------------------- |
-| `MODELS_DEV_SYNC_INTERVAL` | `86400` (24h) | `src/lib/modelsDevSync.ts` | Development-time model catalog sync interval in seconds. |
-
----
-
-## 20. Provider-Specific Settings
-
-| Variable                                  | Default            | Source File                                | Description                                                                           |
-| ----------------------------------------- | ------------------ | ------------------------------------------ | ------------------------------------------------------------------------------------- |
-| `OPENROUTER_CATALOG_TTL_MS`               | `86400000` (24h)   | `src/lib/catalog/openrouterCatalog.ts`     | OpenRouter model catalog cache TTL.                                                   |
-| `NANOBANANA_POLL_TIMEOUT_MS`              | `120000`           | `open-sse/handlers/imageGeneration.ts`     | Max wait for NanoBanana image generation jobs.                                        |
-| `NANOBANANA_POLL_INTERVAL_MS`             | `2500`             | `open-sse/handlers/imageGeneration.ts`     | NanoBanana job polling frequency.                                                     |
-| `CLOUDFLARE_ACCOUNT_ID`                   | _(unset)_          | `open-sse/executors/cloudflare-ai.ts`      | Account ID for Cloudflare Workers AI.                                                 |
-| `CLOUDFLARED_BIN`                         | auto-detect        | `src/lib/cloudflaredTunnel.ts`             | Custom path to `cloudflared` binary.                                                  |
-| `SEARCH_CACHE_TTL_MS`                     | `300000` (5 min)   | `open-sse/services/searchCache.ts`         | TTL for search API (Perplexity, Brave, etc.) response caching.                        |
-| `ALLOW_MULTI_CONNECTIONS_PER_COMPAT_NODE` | `false`            | `src/app/api/providers/route.ts`           | Allow multiple simultaneous connections per OpenAI-compatible provider.               |
-| `ENABLE_CC_COMPATIBLE_PROVIDER`           | `false`            | `src/shared/utils/featureFlags.ts`         | Enable experimental Claude Code compatible provider endpoint.                         |
-| `CLIPROXYAPI_HOST`                        | `127.0.0.1`        | `open-sse/executors/cliproxyapi.ts`        | CLIProxyAPI bridge host (legacy integration).                                         |
-| `CLIPROXYAPI_PORT`                        | `5544`             | `open-sse/executors/cliproxyapi.ts`        | CLIProxyAPI bridge port.                                                              |
-| `CLIPROXYAPI_CONFIG_DIR`                  | `~/.cli-proxy-api` | `src/lib/versionManager/processManager.ts` | CLIProxyAPI config directory.                                                         |
-| `LOCAL_HOSTNAMES`                         | _(empty)_          | `open-sse/config/providerRegistry.ts`      | Comma-separated additional hostnames treated as "local" (Docker service names, etc.). |
-
----
-
-## 21. Proxy Health
-
-| Variable                     | Default          | Source File                              | Description                                                                                                         |
-| ---------------------------- | ---------------- | ---------------------------------------- | ------------------------------------------------------------------------------------------------------------------- |
-| `PROXY_FAST_FAIL_TIMEOUT_MS` | `2000`           | `src/lib/proxyHealth.ts`                 | Fast-fail health check timeout.                                                                                     |
-| `PROXY_HEALTH_CACHE_TTL_MS`  | `30000`          | `src/lib/proxyHealth.ts`                 | Health check result cache TTL.                                                                                      |
-| `RATE_LIMIT_MAX_WAIT_MS`     | `120000` (2 min) | `open-sse/services/rateLimitManager.ts`  | Max time to wait on a 429 before failing the request.                                                               |
-| `REQUEST_RETRY`              | `2`              | `src/sse/services/cooldownAwareRetry.ts` | Number of automatic retries on model-scoped cooldown responses before returning error to client.                    |
-| `MAX_RETRY_INTERVAL_SEC`     | `30`             | `src/sse/services/cooldownAwareRetry.ts` | Max backoff interval (seconds) between cooldown retries. Capped by this value regardless of upstream `Retry-After`. |
-
----
-
-## 22. Debugging
-
-> [!CAUTION]
-> These variables produce **verbose output** and may leak sensitive data. **Never enable in production.**
-
-| Variable                         | Default   | Source File                               | Description                                                    |
-| -------------------------------- | --------- | ----------------------------------------- | -------------------------------------------------------------- |
-| `CURSOR_PROTOBUF_DEBUG`          | _(unset)_ | `open-sse/utils/cursorProtobuf.ts`        | Set `1` to dump Cursor protobuf decode/encode details.         |
-| `CURSOR_STREAM_DEBUG`            | _(unset)_ | `open-sse/executors/cursor.ts`            | Set `1` to dump raw Cursor SSE stream data.                    |
-| `DEBUG_RESPONSES_SSE_TO_JSON`    | _(unset)_ | `open-sse/handlers/responseTranslator.ts` | Set `true` to log Responses API SSE→JSON translation details.  |
-| `NEXT_PUBLIC_OMNIROUTE_E2E_MODE` | _(unset)_ | E2E test harness                          | Set `true` to enable E2E test mode (relaxed auth, test hooks). |
-
----
-
-## 23. GitHub Integration
-
-Allow users to report issues directly from the Dashboard.
-
-| Variable              | Default   | Source File                             | Description                                             |
-| --------------------- | --------- | --------------------------------------- | ------------------------------------------------------- |
-| `GITHUB_ISSUES_REPO`  | _(unset)_ | `src/app/api/v1/issues/report/route.ts` | Repository in `owner/repo` format.                      |
-| `GITHUB_ISSUES_TOKEN` | _(unset)_ | `src/app/api/v1/issues/report/route.ts` | GitHub Personal Access Token with `issues:write` scope. |
-
----
-
-## Deployment Scenarios
-
-### Minimal Local Development
-
-```bash
-JWT_SECRET=$(openssl rand -base64 48)
-API_KEY_SECRET=$(openssl rand -hex 32)
-INITIAL_PASSWORD=dev123
-PORT=20128
-NODE_ENV=development
-```
-
-### Docker Production
-
-```bash
-JWT_SECRET=<generated>
-API_KEY_SECRET=<generated>
-INITIAL_PASSWORD=<generated>
-STORAGE_ENCRYPTION_KEY=<generated>
-DATA_DIR=/data
-PORT=20128
-API_PORT=20129
-NODE_ENV=production
-AUTH_COOKIE_SECURE=true
-REQUIRE_API_KEY=true
-NEXT_PUBLIC_BASE_URL=https://omniroute.example.com
-BASE_URL=http://localhost:20128
-OMNIROUTE_MEMORY_MB=512
-CORS_ORIGIN=https://your-frontend.example.com
-```
-
-### Air-Gapped / CI
-
-```bash
-JWT_SECRET=test-jwt-secret-for-ci
-API_KEY_SECRET=test-api-key-secret-for-ci
-INITIAL_PASSWORD=testpass
-NODE_ENV=production
-OMNIROUTE_DISABLE_BACKGROUND_SERVICES=true
-APP_LOG_TO_FILE=false
-```
-
-### VPS with Reverse Proxy (nginx + Cloudflare)
-
-```bash
-JWT_SECRET=<generated>
-API_KEY_SECRET=<generated>
-STORAGE_ENCRYPTION_KEY=<generated>
-PORT=20128
-AUTH_COOKIE_SECURE=true
-REQUIRE_API_KEY=true
-NEXT_PUBLIC_BASE_URL=https://omniroute.example.com
-BASE_URL=http://127.0.0.1:20128
-CORS_ORIGIN=https://omniroute.example.com
-ENABLE_TLS_FINGERPRINT=true
-CLI_COMPAT_ALL=1
-```
-
----
-
-## Audit: Removed / Dead Variables
-
-The following variables appeared in previous versions of `.env.example` but have **no runtime references** in the current codebase. They have been removed:
-
-| Variable                                              | Reason                                                                                                  |
-| ----------------------------------------------------- | ------------------------------------------------------------------------------------------------------- |
-| `STORAGE_DRIVER=sqlite`                               | Never read by any source file. SQLite is the only supported driver — no selection needed.               |
-| `INSTANCE_NAME=omniroute`                             | Present in old docs/env templates but unused at runtime. May return in a future multi-instance feature. |
-| `SQLITE_MAX_SIZE_MB=2048`                             | Not referenced in source code. Database size is not artificially limited.                               |
-| `SQLITE_CLEAN_LEGACY_FILES=true`                      | Not referenced in source code. Legacy cleanup was likely removed.                                       |
-| `CLI_ROO_BIN`                                         | Not registered in `src/shared/services/cliRuntime.ts`.                                                  |
-| `CLI_KIMI_CODING_BIN`                                 | Not registered in `src/shared/services/cliRuntime.ts` (Kimi Coding uses OAuth, not a CLI binary).       |
-| `IFLOW_OAUTH_CLIENT_ID` / `IFLOW_OAUTH_CLIENT_SECRET` | Not referenced anywhere in source code.                                                                 |
-
-### Default Value Corrections
-
-| Variable                  | Old `.env.example` Value | Actual Code Default | Fixed                                                  |
-| ------------------------- | ------------------------ | ------------------- | ------------------------------------------------------ |
-| `APP_LOG_RETENTION_DAYS`  | `90`                     | `7`                 | ✅ Removed misleading value; documented `7` as default |
-| `CALL_LOG_RETENTION_DAYS` | `90`                     | `7`                 | ✅ Removed misleading value; documented `7` as default |
diff --git a/docs/i18n/in/docs/routing/AUTO-COMBO.md b/docs/i18n/in/docs/routing/AUTO-COMBO.md
deleted file mode 100644
index 9a1e3afeec..0000000000
--- a/docs/i18n/in/docs/routing/AUTO-COMBO.md
+++ /dev/null
@@ -1,67 +0,0 @@
-# OmniRoute Auto-Combo Engine (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../../docs/AUTO-COMBO.md) · 🇪🇸 [es](../../es/docs/AUTO-COMBO.md) · 🇫🇷 [fr](../../fr/docs/AUTO-COMBO.md) · 🇩🇪 [de](../../de/docs/AUTO-COMBO.md) · 🇮🇹 [it](../../it/docs/AUTO-COMBO.md) · 🇷🇺 [ru](../../ru/docs/AUTO-COMBO.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/AUTO-COMBO.md) · 🇯🇵 [ja](../../ja/docs/AUTO-COMBO.md) · 🇰🇷 [ko](../../ko/docs/AUTO-COMBO.md) · 🇸🇦 [ar](../../ar/docs/AUTO-COMBO.md) · 🇮🇳 [hi](../../hi/docs/AUTO-COMBO.md) · 🇮🇳 [in](../../in/docs/AUTO-COMBO.md) · 🇹🇭 [th](../../th/docs/AUTO-COMBO.md) · 🇻🇳 [vi](../../vi/docs/AUTO-COMBO.md) · 🇮🇩 [id](../../id/docs/AUTO-COMBO.md) · 🇲🇾 [ms](../../ms/docs/AUTO-COMBO.md) · 🇳🇱 [nl](../../nl/docs/AUTO-COMBO.md) · 🇵🇱 [pl](../../pl/docs/AUTO-COMBO.md) · 🇸🇪 [sv](../../sv/docs/AUTO-COMBO.md) · 🇳🇴 [no](../../no/docs/AUTO-COMBO.md) · 🇩🇰 [da](../../da/docs/AUTO-COMBO.md) · 🇫🇮 [fi](../../fi/docs/AUTO-COMBO.md) · 🇵🇹 [pt](../../pt/docs/AUTO-COMBO.md) · 🇷🇴 [ro](../../ro/docs/AUTO-COMBO.md) · 🇭🇺 [hu](../../hu/docs/AUTO-COMBO.md) · 🇧🇬 [bg](../../bg/docs/AUTO-COMBO.md) · 🇸🇰 [sk](../../sk/docs/AUTO-COMBO.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/AUTO-COMBO.md) · 🇮🇱 [he](../../he/docs/AUTO-COMBO.md) · 🇵🇭 [phi](../../phi/docs/AUTO-COMBO.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/AUTO-COMBO.md) · 🇨🇿 [cs](../../cs/docs/AUTO-COMBO.md) · 🇹🇷 [tr](../../tr/docs/AUTO-COMBO.md)
-
----
-
-> Self-managing model chains with adaptive scoring
-
-## How It Works
-
-The Auto-Combo Engine dynamically selects the best provider/model for each request using a **6-factor scoring function**:
-
-| Factor     | Weight | Description                                     |
-| :--------- | :----- | :---------------------------------------------- |
-| Quota      | 0.20   | Remaining capacity [0..1]                       |
-| Health     | 0.25   | Circuit breaker: CLOSED=1.0, HALF=0.5, OPEN=0.0 |
-| CostInv    | 0.20   | Inverse cost (cheaper = higher score)           |
-| LatencyInv | 0.15   | Inverse p95 latency (faster = higher)           |
-| TaskFit    | 0.10   | Model × task type fitness score                 |
-| Stability  | 0.10   | Low variance in latency/errors                  |
-
-## Mode Packs
-
-| Pack                    | Focus        | Key Weight       |
-| :---------------------- | :----------- | :--------------- |
-| 🚀 **Ship Fast**        | Speed        | latencyInv: 0.35 |
-| 💰 **Cost Saver**       | Economy      | costInv: 0.40    |
-| 🎯 **Quality First**    | Best model   | taskFit: 0.40    |
-| 📡 **Offline Friendly** | Availability | quota: 0.40      |
-
-## Self-Healing
-
-- **Temporary exclusion**: Score < 0.2 → excluded for 5 min (progressive backoff, max 30 min)
-- **Circuit breaker awareness**: OPEN → auto-excluded; HALF_OPEN → probe requests
-- **Incident mode**: >50% OPEN → disable exploration, maximize stability
-- **Cooldown recovery**: After exclusion, first request is a "probe" with reduced timeout
-
-## Bandit Exploration
-
-5% of requests (configurable) are routed to random providers for exploration. Disabled in incident mode.
-
-## API
-
-```bash
-# Create auto-combo
-curl -X POST http://localhost:20128/api/combos/auto \
-  -H "Content-Type: application/json" \
-  -d '{"id":"my-auto","name":"Auto Coder","candidatePool":["anthropic","google","openai"],"modePack":"ship-fast"}'
-
-# List auto-combos
-curl http://localhost:20128/api/combos/auto
-```
-
-## Task Fitness
-
-30+ models scored across 6 task types (`coding`, `review`, `planning`, `analysis`, `debugging`, `documentation`). Supports wildcard patterns (e.g., `*-coder` → high coding score).
-
-## Files
-
-| File                                         | Purpose                               |
-| :------------------------------------------- | :------------------------------------ |
-| `open-sse/services/autoCombo/scoring.ts`     | Scoring function & pool normalization |
-| `open-sse/services/autoCombo/taskFitness.ts` | Model × task fitness lookup           |
-| `open-sse/services/autoCombo/engine.ts`      | Selection logic, bandit, budget cap   |
-| `open-sse/services/autoCombo/selfHealing.ts` | Exclusion, probes, incident mode      |
-| `open-sse/services/autoCombo/modePacks.ts`   | 4 weight profiles                     |
-| `src/app/api/combos/auto/route.ts`           | REST API                              |
diff --git a/docs/i18n/in/llm.txt b/docs/i18n/in/llm.txt
deleted file mode 100644
index 224371a5b4..0000000000
--- a/docs/i18n/in/llm.txt
+++ /dev/null
@@ -1,507 +0,0 @@
-# OmniRoute (हिन्दी (IN))
-
-🌐 **Languages:** 🇺🇸 [English](../../../llm.txt) · 🇸🇦 [ar](../ar/llm.txt) · 🇧🇬 [bg](../bg/llm.txt) · 🇧🇩 [bn](../bn/llm.txt) · 🇨🇿 [cs](../cs/llm.txt) · 🇩🇰 [da](../da/llm.txt) · 🇩🇪 [de](../de/llm.txt) · 🇪🇸 [es](../es/llm.txt) · 🇮🇷 [fa](../fa/llm.txt) · 🇫🇮 [fi](../fi/llm.txt) · 🇫🇷 [fr](../fr/llm.txt) · 🇮🇳 [gu](../gu/llm.txt) · 🇮🇱 [he](../he/llm.txt) · 🇮🇳 [hi](../hi/llm.txt) · 🇭🇺 [hu](../hu/llm.txt) · 🇮🇩 [id](../id/llm.txt) · 🇮🇳 [in](../in/llm.txt) · 🇮🇹 [it](../it/llm.txt) · 🇯🇵 [ja](../ja/llm.txt) · 🇰🇷 [ko](../ko/llm.txt) · 🇮🇳 [mr](../mr/llm.txt) · 🇲🇾 [ms](../ms/llm.txt) · 🇳🇱 [nl](../nl/llm.txt) · 🇳🇴 [no](../no/llm.txt) · 🇵🇭 [phi](../phi/llm.txt) · 🇵🇱 [pl](../pl/llm.txt) · 🇵🇹 [pt](../pt/llm.txt) · 🇧🇷 [pt-BR](../pt-BR/llm.txt) · 🇷🇴 [ro](../ro/llm.txt) · 🇷🇺 [ru](../ru/llm.txt) · 🇸🇰 [sk](../sk/llm.txt) · 🇸🇪 [sv](../sv/llm.txt) · 🇰🇪 [sw](../sw/llm.txt) · 🇮🇳 [ta](../ta/llm.txt) · 🇮🇳 [te](../te/llm.txt) · 🇹🇭 [th](../th/llm.txt) · 🇹🇷 [tr](../tr/llm.txt) · 🇺🇦 [uk-UA](../uk-UA/llm.txt) · 🇵🇰 [ur](../ur/llm.txt) · 🇻🇳 [vi](../vi/llm.txt) · 🇨🇳 [zh-CN](../zh-CN/llm.txt)
-
----
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 355 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-## Overview
-
-OmniRoute solves the problem of managing multiple AI provider subscriptions, quotas, and rate limits. It sits between your AI-powered tools (IDE agents, CLI tools) and AI providers, routing requests intelligently through a 4-tier fallback system: Subscription → API Key → Cheap → Free.
-
-**Key value:** One endpoint (`http://localhost:20128/v1`), unlimited models, zero downtime, minimal cost.
-
-**Current version:** 3.8.51
-
-## Tech Stack
-
-- **Runtime:** Node.js `>=22.22.2 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
-- **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 167 migrations)
-- **State management:** Zustand (client), SQLite (server persistence)
-- **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
-- **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
-- **Schemas:** Zod v4 for all API / MCP input validation
-- **Background jobs:** Custom token health check scheduler, 24h model auto-sync
-- **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
-- **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
-- **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
-- **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
-
-## Project Structure
-
-```
-/
-├── src/                          # Main application source
-│   ├── app/                      # Next.js App Router pages and API routes
-│   │   ├── (dashboard)/          # Dashboard UI pages
-│   │   │   └── dashboard/
-│   │   │       ├── agents/       # ACP Agents dashboard (CLI agent detection + custom agents)
-│   │   │       ├── analytics/    # Usage analytics and charts
-│   │   │       ├── api-manager/  # API key management
-│   │   │       ├── audit/        # Audit logs
-│   │   │       ├── auto-combo/   # Auto-combo engine dashboard
-│   │   │       ├── cache/        # Cache dashboard (semantic cache stats)
-│   │   │       ├── cli-tools/    # CLI tool configuration (Claude Code, Codex, etc.)
-│   │   │       ├── combos/       # Model combo management (19 strategies + 4 templates)
-│   │   │       ├── costs/        # Cost tracking per provider/model
-│   │   │       ├── endpoint/     # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs
-│   │   │       ├── health/       # System health (uptime, circuit breakers, latency)
-│   │   │       ├── limits/       # Rate limits dashboard
-│   │   │       ├── logs/         # Request, Proxy, Audit, Console logs (tabbed)
-│   │   │       ├── media/        # Image/video/music generation + transcription
-│   │   │       ├── memory/       # Memory system dashboard
-│   │   │       ├── onboarding/   # Onboarding wizard
-│   │   │       ├── playground/   # Model playground (Monaco editor, streaming)
-│   │   │       ├── providers/    # Provider management (OAuth + API key + free)
-│   │   │       ├── search-tools/ # Search tools configuration
-│   │   │       ├── settings/     # Settings tabs (General, Appearance, Security, Routing, Resilience, Advanced)
-│   │   │       ├── skills/       # Skills system dashboard
-│   │   │       ├── translator/   # Format translator + debug tools
-│   │   │       └── usage/        # Usage history
-│   │   ├── api/                  # REST API endpoints (100+ route directories)
-│   │   │   ├── v1/               # OpenAI-compatible API (chat, completions, models, embeddings,
-│   │   │   │                     #   images, audio, videos, music, moderations, rerank, search,
-│   │   │   │                     #   responses, messages, registered-keys, quotas, accounts)
-│   │   │   ├── v1beta/           # Gemini-compatible API
-│   │   │   ├── a2a/              # A2A agent management API
-│   │   │   ├── acp/              # ACP agent management API
-│   │   │   ├── oauth/            # OAuth flows per provider
-│   │   │   ├── providers/        # Provider CRUD and batch testing
-│   │   │   ├── models/           # Dashboard model listing and aliases
-│   │   │   ├── combos/           # Combo CRUD (multi-model fallback chains)
-│   │   │   ├── memory/           # Memory system API
-│   │   │   ├── skills/           # Skills system API
-│   │   │   ├── evals/            # Eval runner API
-│   │   │   ├── mcp/              # MCP HTTP transport API
-│   │   │   ├── search/           # Search provider API
-│   │   │   ├── webhooks/         # Webhook management
-│   │   │   ├── tunnels/          # Cloudflare tunnel management
-│   │   │   └── ...               # Other endpoints (usage, logs, health, settings, pricing, etc.)
-│   │   ├── landing/              # Landing page
-│   │   ├── login/                # Login page
-│   │   ├── forgot-password/      # Password recovery
-│   │   ├── status/               # Status page
-│   │   └── docs/                 # In-app documentation
-│   ├── domain/                   # Domain types and policy engine
-│   │   ├── policyEngine.ts       # Central policy engine
-│   │   ├── comboResolver.ts      # Combo resolution logic
-│   │   ├── costRules.ts          # Cost calculation rules
-│   │   ├── degradation.ts        # Graceful degradation
-│   │   ├── fallbackPolicy.ts     # Fallback behavior
-│   │   ├── lockoutPolicy.ts      # Account lockout logic
-│   │   ├── modelAvailability.ts  # Model availability checks
-│   │   ├── providerExpiration.ts # Provider credential expiration
-│   │   ├── quotaCache.ts         # Quota caching layer
-│   │   ├── configAudit.ts        # Configuration auditing
-│   │   └── responses.ts          # Domain response types
-│   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
-│   ├── lib/                      # Core libraries
-│   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
-│   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
-│   │   │   ├── taskManager.ts    # Task lifecycle with TTL cleanup
-│   │   │   └── streaming.ts      # SSE streaming for A2A
-│   │   ├── acp/                  # Agent Communication Protocol registry and manager
-│   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (122 modules + migrations)
-│   │   │   ├── core.ts           # Database initialization, connection, schema
-│   │   │   ├── providers.ts      # Provider connection CRUD
-│   │   │   ├── models.ts         # Model catalog management
-│   │   │   ├── combos.ts         # Combo configuration
-│   │   │   ├── apiKeys.ts        # API key management
-│   │   │   ├── settings.ts       # Settings persistence
-│   │   │   ├── backup.ts         # Database backup/restore
-│   │   │   ├── proxies.ts        # Proxy registry
-│   │   │   ├── prompts.ts        # Prompt templates
-│   │   │   ├── webhooks.ts       # Webhook subscriptions
-│   │   │   ├── detailedLogs.ts   # Detailed request logging
-│   │   │   ├── domainState.ts    # Domain state persistence
-│   │   │   ├── registeredKeys.ts # Registered API keys with quotas
-│   │   │   ├── quotaSnapshots.ts # Quota snapshot history
-│   │   │   ├── modelComboMappings.ts # Model-to-combo mappings
-│   │   │   ├── cliToolState.ts   # CLI tool state tracking
-│   │   │   ├── encryption.ts     # Data encryption
-│   │   │   ├── readCache.ts      # Read-through cache layer
-│   │   │   ├── secrets.ts        # Secrets management
-│   │   │   ├── stateReset.ts     # State reset utilities
-│   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 167 versioned SQL migration files
-│   │   ├── evals/                # Eval runner and scheduler
-│   │   ├── memory/               # Persistent conversational memory
-│   │   │   ├── extraction.ts     # Memory extraction from conversations
-│   │   │   ├── injection.ts      # Memory injection into context
-│   │   │   ├── retrieval.ts      # Memory retrieval/search
-│   │   │   ├── store.ts          # Memory persistence layer
-│   │   │   └── summarization.ts  # Memory summarization
-│   │   ├── oauth/                # OAuth providers, services, and utilities
-│   │   │   ├── constants/        # Default OAuth credentials (overridable via env)
-│   │   │   ├── providers/        # Provider-specific OAuth configs
-│   │   │   ├── services/         # Provider-specific token exchange logic
-│   │   │   └── utils/            # PKCE, callback server, token helpers
-│   │   ├── plugins/              # Plugin system
-│   │   ├── skills/               # Extensible skill framework
-│   │   │   ├── registry.ts       # Skill registration
-│   │   │   ├── executor.ts       # Skill execution engine
-│   │   │   ├── sandbox.ts        # Skill sandbox environment
-│   │   │   ├── builtin/          # Built-in skills
-│   │   │   ├── interception.ts   # Skill request interception
-│   │   │   └── injection.ts      # Skill context injection
-│   │   ├── usage/                # Usage tracking system
-│   │   │   ├── callLogs.ts       # Call log persistence
-│   │   │   ├── costCalculator.ts # Cost calculation engine
-│   │   │   └── usageHistory.ts   # Usage history queries
-│   │   ├── cloudSync.ts          # Cloud sync via Cloudflare Workers
-│   │   ├── cloudflaredTunnel.ts  # Cloudflare tunnel management
-│   │   ├── pricingSync.ts        # LiteLLM pricing data sync
-│   │   ├── semanticCache.ts      # Semantic caching layer
-│   │   ├── tokenHealthCheck.ts   # Background OAuth token refresh scheduler
-│   │   ├── webhookDispatcher.ts  # Webhook event dispatcher
-│   │   └── localDb.ts            # Unified re-export layer for all DB modules
-│   ├── middleware/               # Request middleware
-│   │   └── promptInjectionGuard.ts # Prompt injection detection
-│   ├── mitm/                     # MITM proxy capability
-│   │   ├── cert/                 # Certificate management
-│   │   ├── dns/                  # DNS handling
-│   │   ├── targets/              # Target routing
-│   │   └── manager.ts            # MITM proxy manager
-│   ├── shared/                   # Shared utilities, components, and constants
-│   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (352), model lists, pricing, routing strategies, MCP scopes
-│   │   ├── contracts/            # Shared API contracts
-│   │   ├── hooks/                # React hooks
-│   │   ├── middleware/           # Shared middleware utilities
-│   │   ├── schemas/              # Shared Zod schemas
-│   │   ├── services/             # Shared services
-│   │   ├── types/                # Shared TypeScript types
-│   │   ├── validation/           # Zod schemas (settings, providers, routes)
-│   │   └── utils/                # Helpers (auth, CORS, error codes, machine ID)
-│   ├── sse/                      # SSE proxy pipeline
-│   │   ├── services/             # Auth resolution, format translation, response handling
-│   │   └── middleware/           # Rate limiting, circuit breaker, caching, idempotency
-│   ├── store/                    # Zustand client-side stores (theme, providers, etc.)
-│   └── types/                    # TypeScript type definitions
-├── open-sse/                     # Standalone SSE server (npm workspace)
-│   ├── config/                   # Model registries (providerRegistry, embedding, image, audio, video,
-│   │                             #   music, rerank, moderation, search, CLI fingerprints, Ollama models)
-│   ├── executors/                # Provider-specific request executors (104 executor modules)
-│   │   ├── base.ts               # Base executor with shared logic
-│   │   ├── default.ts            # Default OpenAI-compatible executor
-│   │   ├── cursor.ts             # Cursor IDE (protobuf + checksum)
-│   │   ├── codex.ts              # OpenAI Codex CLI
-│   │   ├── antigravity.ts        # Antigravity IDE
-│   │   ├── github.ts             # GitHub Copilot
-│   │   ├── kiro.ts               # Kiro AI
-│   │   ├── qoder.ts              # Qoder AI
-│   │   ├── vertex.ts             # Vertex AI (Service Account JSON)
-│   │   ├── cloudflare-ai.ts      # Cloudflare Workers AI
-│   │   ├── opencode.ts           # OpenCode Zen/Go
-│   │   └── pollinations.ts       # Pollinations AI
-│   ├── handlers/                 # Request handlers per API type (25 handlers)
-│   │   ├── chatCore.ts           # Main chat completions handler
-│   │   ├── responsesHandler.ts   # OpenAI Responses API handler
-│   │   ├── embeddings.ts         # Embedding generation
-│   │   ├── imageGeneration.ts    # Image generation (GPT-Image, FLUX, SD, etc.)
-│   │   ├── videoGeneration.ts    # Video generation
-│   │   ├── musicGeneration.ts    # Music generation
-│   │   ├── audioSpeech.ts        # Text-to-speech
-│   │   ├── audioTranscription.ts # Speech-to-text (Whisper, Deepgram, AssemblyAI)
-│   │   ├── moderations.ts        # Content moderation
-│   │   ├── rerank.ts             # Reranking API
-│   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
-│   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
-│   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
-│   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
-│   │   ├── audit.ts              # Tool call audit logging
-│   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
-│   │   └── httpTransport.ts      # HTTP transport handler
-│   ├── services/                 # 220+ service modules
-│   │   ├── combo.ts              # Core routing engine
-│   │   ├── usage.ts              # Usage tracking
-│   │   ├── tokenRefresh.ts       # OAuth token refresh
-│   │   ├── rateLimitManager.ts   # Rate limit management
-│   │   ├── accountFallback.ts    # Multi-account fallback
-│   │   ├── sessionManager.ts     # Session management
-│   │   ├── wildcardRouter.ts     # Wildcard model routing
-│   │   ├── autoCombo/            # Auto-combo engine (16-factor scoring, bandit exploration)
-│   │   ├── intentClassifier.ts   # Request intent classification
-│   │   ├── taskAwareRouter.ts    # Task-aware routing
-│   │   ├── thinkingBudget.ts     # Thinking budget management
-│   │   ├── contextManager.ts     # Context window management
-│   │   ├── modelDeprecation.ts   # Model deprecation handling
-│   │   ├── modelFamilyFallback.ts # Intra-family model fallback
-│   │   ├── emergencyFallback.ts  # Emergency fallback
-│   │   ├── workflowFSM.ts        # Workflow state machine
-│   │   ├── backgroundTaskDetector.ts # Background task detection
-│   │   ├── ipFilter.ts           # IP-based access control
-│   │   ├── signatureCache.ts     # CLI signature caching
-│   │   ├── volumeDetector.ts     # Request volume detection
-│   │   ├── contextHandoff.ts    # Context relay handoff generation and injection
-│   │   ├── codexQuotaFetcher.ts # Codex quota fetching for context-relay
-│   │   └── ...                   # Additional services (14 more modules)
-│   ├── transformer/              # Responses API transformer
-│   │   └── responsesTransformer.ts
-│   ├── translator/               # Format translators (OpenAI ↔ Claude ↔ Gemini ↔ Responses ↔ Ollama ↔ DeepSeek)
-│   │   ├── request/              # Request translators per provider
-│   │   ├── response/             # Response translators per provider
-│   │   ├── helpers/              # Translation helpers
-│   │   └── image/                # Image format translation
-│   └── utils/                    # 100+ utility modules (stream, TLS, proxy, logging, etc.)
-├── electron/                     # Electron desktop app (cross-platform)
-│   ├── main.js                   # Electron main process
-│   ├── preload.js                # Preload script (IPC bridge)
-│   └── assets/                   # App icons and assets
-├── tests/                        # Test suites
-│   ├── unit/                     # 5,000+ unit test files
-│   ├── integration/              # Integration tests
-│   ├── e2e/                      # Playwright E2E tests
-│   ├── security/                 # Security tests
-│   ├── translator/               # Translator-specific tests
-│   └── load/                     # Load tests
-├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
-│   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
-│   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
-│   ├── routing/                  # AUTO-COMBO.md (16-factor scoring), REASONING_REPLAY.md
-│   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
-│   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
-│   ├── ops/                      # RELEASE_CHECKLIST.md, TUNNELS_GUIDE.md, VM deployment
-│   ├── openapi.yaml              # OpenAPI specification
-│   └── screenshots/              # Dashboard screenshots
-├── bin/                          # CLI entry points (omniroute, reset-password)
-├── scripts/                      # Build and utility scripts
-└── .env.example                  # Environment variable template
-```
-
-## Key Features (v3.8.50)
-
-### Core Proxy
-- **355 AI providers** with automatic format translation
-- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
-- **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
-- **4-tier fallback**: Subscription → API Key → Cheap → Free
-- **Context Relay strategy**: Session handoff summaries on account rotation for continuity
-- **Auto-combo engine**: Self-healing routing optimization with **16-factor scoring** (see `docs/routing/AUTO-COMBO.md`), bandit exploration, progressive cooldown
-- **Semantic caching** with cache hit/miss headers
-- **Idempotency** with configurable dedup window
-- **3-layer resilience**: Provider Circuit Breaker / Connection Cooldown / Model Lockout
-- **Provider Icons**: 130+ provider logos via `@lobehub/icons` (SVG) with PNG fallback
-- **Model Auto-Sync**: 24h scheduler refreshes model lists across connected providers
-- **Registered Keys API**: Auto-provision API keys via `POST /api/v1/registered-keys` with quota enforcement
-- **Memory System**: Persistent conversational memory with extraction, injection, retrieval, and summarization
-- **Skills System**: Extensible skill framework with registry, executor, sandbox, built-in and custom skills
-- **Cloud Agents**: Codex Cloud, Cursor, Devin, Jules — autonomous coding agents with task lifecycle management
-- **Guardrails Framework**: Hot-reloadable registry with vision-bridge, pii-masker, prompt-injection (priority-ordered)
-- **MITM Proxy**: Certificate management, DNS handling, and target routing
-- **Cloudflare Tunnels**: Managed tunnel creation for remote access
-- **Coverage gate**: ratchet vs `quality-baseline.json`; absolute floor 60% statements/lines/functions/branches
-
-### Security
-- **Data Loss Prevention**: SQLite migration safety bounds abort startup on dangerous massive schema overrides. Pre-migration `VACUUM INTO` backups isolate rollback snapshots.
-- **CodeQL security**: Fixed 10+ CodeQL alerts (polynomial-redos, insecure-randomness, shell-injection, SSRF, incomplete URLs)
-- **Web Crypto session IDs**: `generateSessionId` uses `crypto.getRandomValues()` instead of `Math.random()`
-- **Route validation**: All API routes validated with Zod v4 schemas + `validateBody()`
-- **omniModel tag sanitization**: Internal `<omniModel>` tags never leak to clients in SSE streams
-- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint to reduce bot detection
-- **CLI Fingerprint Matching** — Per-provider request signature matching
-- **Prompt injection guard** — Request middleware detection
-- **Provider constants validated at module load** via Zod (`src/shared/validation/providerSchema.ts`)
-- **PII sanitizer** — Sensitive data scrubbing in logs
-
-### Dashboard Pages (50+ sections)
-- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons
-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 19 strategies
-- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics
-- **Analytics** — Token consumption, cost, heatmaps, distributions
-- **Health** — Uptime, memory, latency percentiles, circuit breakers
-- **Logs** — Request, Proxy, Audit, Console (tabbed)
-- **Audit** — Audit trail and compliance logging
-- **Costs** — Cost tracking per provider/model
-- **Limits** — Rate limit monitoring
-- **Cache** — Semantic cache statistics and management
-- **CLI Tools** — One-click configuration for 10+ AI CLI tools
-- **CLI Agents** — Grid of 14+ built-in agents with ProviderIcon and install detection + custom agent registration
-- **Playground** — Test any model with Monaco editor, streaming responses
-- **Media** — Image/video/music generation (GPT-Image, FLUX, etc.) + audio transcription (up to 2GB files)
-- **Search Tools** — Search provider configuration and testing
-- **Memory** — Memory system management and visualization
-- **Skills** — Skills framework management and execution
-- **Translator** — Format debugging: playground, chat tester, test bench, live monitor
-- **Settings** — General, Appearance (7 color themes), Security (TLS/CLI fingerprint, IP filter), Routing, Resilience, Advanced
-- **Endpoint** — Unified: Endpoint Proxy, MCP Server, A2A Server, API Endpoints (tabbed)
-- **Onboarding** — Setup wizard for new users
-- **Usage** — Usage history and analytics
-- **API Manager** — API key management with scoped permissions
-
-### Protocol Support
-- **OpenAI-compatible** — `/v1/chat/completions`, `/v1/models`, `/v1/embeddings`, `/v1/images/generations`, `/v1/audio/transcriptions`, `/v1/audio/speech`, `/v1/moderations`, `/v1/rerank`, `/v1/videos/generations`, `/v1/music/generations`
-- **Anthropic** — `/v1/messages`, `/v1/messages/count_tokens`
-- **OpenAI Responses** — `/v1/responses`
-- **Gemini** — `/v1beta/models`, `/v1beta/models/{...path}`
-- **Ollama** — `/v1/api/chat`, `/api/tags`
-- **Search** — `/v1/search` (Perplexity, Serper, Brave, Exa, Tavily)
-- **MCP** — 110-tool MCP server with scope-based auth (3 transports: stdio, SSE, streamable HTTP)
-- **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
-- **ACP** — Agent Communication Protocol registry and manager
-
-### MCP Server (110 Tools)
-
-110 tools across modules: **45 canonical** (health, combos, quotas, routing, cost, models, cache,
-diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
-**obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
-`docs/frameworks/MCP-SERVER.md`.
-
-**MCP Auth Scopes (33):** e.g. `read:health`, `read:combos`, `write:combos`, `read:quota`,
-`read:usage`, `read:models`, `execute:completions`, `execute:search`, `write:budget`,
-`write:resilience`, plus memory/skills/pool/plugin scopes — full list in
-`docs/frameworks/MCP-SERVER.md`.
-
-### Provider Categories
-
-
-**OAuth Providers (24):** Claude Code, Antigravity, OpenAI Codex, GitHub Copilot, Cursor IDE, Kimi Coding, Kilo Code, Cline, Kiro, Qoder, Gemini, Windsurf, GitLab Duo
-
-**API Key Providers (236):** OpenAI, Anthropic, Gemini (Google AI Studio), DeepSeek, Groq, xAI (Grok), Mistral, Perplexity, Together AI, Fireworks AI, Cerebras, Cohere, NVIDIA NIM, Nebius AI, SiliconFlow, Hyperbolic, HuggingFace, OpenRouter, Vertex AI, Cloudflare Workers AI, Scaleway AI, AI/ML API, Pollinations AI, LongCat AI, Alibaba, Alibaba (China), Kimi, Kimi Coding (API Key), Minimax, Minimax (China), Blackbox AI, Synthetic, Kilo Gateway, Z.AI, GLM Coding, Deepgram, AssemblyAI, ElevenLabs, Cartesia, PlayHT, Inworld, NanoBanana, SD WebUI, ComfyUI, Ollama Cloud, Perplexity Search, Serper Search, Brave Search, Exa Search, Tavily Search, OpenCode Zen, OpenCode Go, Alibaba Coding Plan
-
-**Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
-
-### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
-- Language switcher in documentation
-
-## Key Architectural Decisions
-
-1. **OpenAI-compatible API surface:** All incoming requests follow the OpenAI API format. This makes OmniRoute a drop-in replacement for any tool that supports custom OpenAI endpoints.
-
-2. **Provider abstraction via format translators:** Each AI provider has a translator in `open-sse/translator/` that converts between OpenAI format and the provider's native format transparently.
-
-3. **Connection-based provider model:** Providers are stored as "connections" in SQLite. Each connection has an `id`, `provider`, `authType` (oauth/apikey/free), `isActive` flag, and credentials. Multiple connections per provider for multi-account rotation.
-
-4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 19 strategies including auto-combo with self-healing and context-relay for session continuity.
-
-5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.
-
-6. **SQLite for persistence:** All state (providers, combos, logs, settings, API keys, memory, skills) stored in a single SQLite database via 122 domain-specific modules. All DB operations go through `src/lib/db/` modules, never raw SQL in routes.
-
-7. **OAuth with PKCE:** OAuth flows use PKCE for security. Token refresh handled by background job (`tokenHealthCheck.ts`).
-
-8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
-
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 122 `src/lib/db/` modules with 167 SQL migrations.
-
-10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
-
-11. **Memory/Skills cross-cutting systems:** Memory and Skills affect the MCP tools, request pipeline, and A2A skills. Memory provides persistent context across sessions; Skills provide extensible tool execution with sandbox isolation.
-
-12. **Domain policy engine:** `src/domain/` contains policy engine modules (policyEngine, comboResolver, costRules, degradation, fallbackPolicy, lockoutPolicy, modelAvailability, providerExpiration, quotaCache, configAudit) that govern routing decisions independently from the pipeline.
-
-13. **Provider constants validated at load:** All provider definitions validated via Zod schemas at module load time (`src/shared/validation/providerSchema.ts`). Invalid providers fail fast.
-
-## Main Flows
-
-### Proxy Request Flow
-1. Client sends OpenAI-format request to `/v1/chat/completions`
-2. API key validation
-3. Model resolution: direct model or combo lookup
-4. For combos: iterate through models with selected strategy
-5. Auth resolution: get credentials for the target provider
-6. Format translation: OpenAI → provider native format
-7. CLI fingerprint matching (if enabled for provider)
-8. Upstream request with circuit breaker and rate limiting
-9. Response translation: provider → OpenAI format
-10. omniModel tag sanitization (strip internal tags)
-11. SSE streaming back to client
-12. Memory extraction (if memory system enabled)
-13. Usage logging and cost calculation
-
-### OAuth Flow
-1. Dashboard initiates `/api/oauth/[provider]/authorize`
-2. User completes OAuth login in browser
-3. Callback hits `/api/oauth/[provider]/exchange`
-4. Tokens stored as a provider connection in SQLite
-5. Background job refreshes tokens before expiry
-
-## Important Notes for LLMs
-
-1. **Two model endpoints exist:** `/api/models` (dashboard, all models) and `/v1/models` (OpenAI-compatible, active only).
-
-2. **Provider IDs vs aliases:** Providers have both an ID (`claude`, `github`) and a short alias (`cc`, `gh`). Models are referenced as `alias/model-name` (e.g., `cc/claude-opus-4-6`).
-
-3. **The `open-sse/` directory is a separate npm workspace** with its own config, handlers, executors, translators, and services.
-
-4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
-
-5. **Database layer:** Operations go through `src/lib/db/` modules (122 domain-specific files, 167 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
-
-6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
-
-7. **MCP and A2A pages are embedded as tabs inside `/dashboard/endpoint`**, not standalone routes.
-
-8. **ACP agents** are in `src/lib/acp/registry.ts` with detection cache. Custom agents stored via settings DB.
-
-9. **Auto-combo engine** in `open-sse/services/autoCombo/` — **16-factor scoring** (weights and factors in `docs/routing/AUTO-COMBO.md`), 6 mode packs, bandit exploration, progressive cooldown.
-
-10. **Docker:** Dockerfile has two targets: `runner-base` and `runner-cli`. `docker-compose.yml` for dev (8 profiles), `docker-compose.prod.yml` for production (port 20130).
-
-11. **Electron desktop app** in `electron/` with main.js and preload.js. Build with `npm run electron:build` (supports Windows, macOS, Linux).
-
-12. **Pricing data** syncs from LiteLLM via `src/lib/pricingSync.ts`. Use `sync_pricing` MCP tool or API endpoint.
-
-13. **Memory system** in `src/lib/memory/` provides extraction, injection, retrieval, summarization, and persistent store. Exposed via MCP memory tools and `/api/memory/ API.
-
-14. **Skills system** in `src/lib/skills/` provides registry, executor, sandbox isolation, built-in skills, custom skill support, request interception, and context injection. Exposed via MCP skill tools and `/api/skills/` API.
-
-15. **Zod v4** is used for all validation. Import from `zod` package. Provider schemas validated at module load time.
-
-16. **Context Relay** strategy (`context-relay`) is split across two layers: `combo.ts` decides if a handoff should be generated after a successful turn; `chat.ts` injects the handoff only after account resolution. Handoff data lives in `context_handoffs` SQLite table. Config: `handoffThreshold`, `handoffModel`, `handoffProviders`.
-
-17. **Proxy enforcement** is now comprehensive: token health checks resolve proxy per connection, provider validation wraps in `runWithProxyContext`, and proxy dispatchers use `undici.fetch()` instead of the Node built-in `fetch()` to avoid dispatcher incompatibilities on Node 22.
-
-18. **Node.js 24+ compatibility**: The login page (`/api/settings/require-login`) detects the Node.js version and sends `nodeVersion`/`nodeCompatible` fields. The login UI renders a warning banner when `nodeCompatible` is false.
-
-19. **Cloud Agents** in `src/lib/cloudAgent/` — four external autonomous coding agents (Codex Cloud, Cursor, Devin, Jules) with task lifecycle endpoints under `/api/v1/agents/tasks/`. Require management auth, not client auth.
-
-20. **Guardrails framework** in `src/lib/guardrails/` — hot-reloadable registry. Built-ins (priority-ordered): `vision-bridge` (5) → `audio-bridge` (6) → `video-bridge` (7) → `pii-masker` (10) → `prompt-injection` (20) → `credential-masker` (95). Fail-open model: exceptions never block traffic. Per-request opt-out via `x-omniroute-disabled-guardrails` header.
-
-21. **Authz pipeline** (`src/server/authz/`): every request is classified as `PUBLIC`, `CLIENT_API`, or `MANAGEMENT`, then run through policy + enforce stages. See `docs/architecture/AUTHZ_GUIDE.md`.
-
-22. **Three resilience layers** are distinct (do not conflate them):
-    - **Provider Circuit Breaker** (`src/shared/utils/circuitBreaker.ts`) — whole-provider scope.
-    - **Connection Cooldown** (`src/sse/services/auth.ts::markAccountUnavailable`) — one key/account scope.
-    - **Model Lockout** (`open-sse/services/accountFallback.ts`) — provider + connection + model scope.
-
-## v3.8.x Highlights
-
-- **352-provider catalog** with 150+ free tiers, one-click account imports, and bulk key add
-- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
-- **16-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
-- **Cloud Agents** (Codex Cloud, Cursor, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
-- **Embedded services** manager (install/start/stop bundled services from the dashboard)
-- **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic
-- Full changelog: `CHANGELOG.md`
-
-## Links
-
-- Repository: https://github.com/diegosouzapw/OmniRoute
-- Website: https://omniroute.online
-- npm: https://www.npmjs.com/package/omniroute
-- Docker Hub: https://hub.docker.com/r/diegosouzapw/omniroute
-- Documentation: See `/docs/` directory
-
-### Documentation Index
-
-- **Architecture & Reference**: `docs/architecture/ARCHITECTURE.md`, `docs/architecture/CODEBASE_DOCUMENTATION.md`, `docs/architecture/REPOSITORY_MAP.md`, `docs/reference/API_REFERENCE.md`, `docs/reference/PROVIDER_REFERENCE.md`, `docs/reference/openapi.yaml`
-- **Operator guides**: `docs/guides/USER_GUIDE.md`, `docs/reference/CLI-TOOLS.md`, `docs/guides/TROUBLESHOOTING.md`, `docs/ops/COVERAGE_PLAN.md`
-- **Protocols**: `docs/frameworks/MCP-SERVER.md`, `docs/frameworks/A2A-SERVER.md`, `docs/frameworks/AGENT_PROTOCOLS_GUIDE.md`, `docs/frameworks/CLOUD_AGENT.md`
-- **Routing & resilience**: `docs/routing/AUTO-COMBO.md`, `docs/architecture/RESILIENCE_GUIDE.md`
-- **Security**: `docs/architecture/AUTHZ_GUIDE.md`, `docs/security/GUARDRAILS.md`, `docs/security/COMPLIANCE.md`, `docs/security/STEALTH_GUIDE.md`
-- **Extensibility**: `docs/frameworks/SKILLS.md`, `docs/frameworks/MEMORY.md`, `docs/frameworks/EVALS.md`, `docs/frameworks/WEBHOOKS.md`, `docs/routing/REASONING_REPLAY.md`
-- **Platform**: `docs/guides/ELECTRON_GUIDE.md`, `docs/ops/TUNNELS_GUIDE.md`
-- **AI agents**: `CLAUDE.md`, `AGENTS.md`, `GEMINI.md`
diff --git a/docs/i18n/it/llm.txt b/docs/i18n/it/llm.txt
index 83fe17538d..ceea0b5629 100644
--- a/docs/i18n/it/llm.txt
+++ b/docs/i18n/it/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/ja/llm.txt b/docs/i18n/ja/llm.txt
index d2e467bae3..c9a2c38d0b 100644
--- a/docs/i18n/ja/llm.txt
+++ b/docs/i18n/ja/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/ko/llm.txt b/docs/i18n/ko/llm.txt
index 604d91e5c8..bd947d8a1f 100644
--- a/docs/i18n/ko/llm.txt
+++ b/docs/i18n/ko/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/mr/llm.txt b/docs/i18n/mr/llm.txt
index 3951cd5b2f..26255dd50d 100644
--- a/docs/i18n/mr/llm.txt
+++ b/docs/i18n/mr/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/ms/llm.txt b/docs/i18n/ms/llm.txt
index 803c5a5456..a6c87dff47 100644
--- a/docs/i18n/ms/llm.txt
+++ b/docs/i18n/ms/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/nl/llm.txt b/docs/i18n/nl/llm.txt
index 6136d36574..fa20a10080 100644
--- a/docs/i18n/nl/llm.txt
+++ b/docs/i18n/nl/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/no/llm.txt b/docs/i18n/no/llm.txt
index 89204a67d2..3cf2552f6d 100644
--- a/docs/i18n/no/llm.txt
+++ b/docs/i18n/no/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/phi/llm.txt b/docs/i18n/phi/llm.txt
index e2117f53b6..6e6e88fd3a 100644
--- a/docs/i18n/phi/llm.txt
+++ b/docs/i18n/phi/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/pl/llm.txt b/docs/i18n/pl/llm.txt
index 59e3b55802..850d016390 100644
--- a/docs/i18n/pl/llm.txt
+++ b/docs/i18n/pl/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/pt-BR/llm.txt b/docs/i18n/pt-BR/llm.txt
index 050bccae37..85b44c5a16 100644
--- a/docs/i18n/pt-BR/llm.txt
+++ b/docs/i18n/pt-BR/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/pt/llm.txt b/docs/i18n/pt/llm.txt
index ba0ac3b997..a2c48f59b4 100644
--- a/docs/i18n/pt/llm.txt
+++ b/docs/i18n/pt/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/ro/llm.txt b/docs/i18n/ro/llm.txt
index 488f319a24..f3970fd340 100644
--- a/docs/i18n/ro/llm.txt
+++ b/docs/i18n/ro/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/ru/llm.txt b/docs/i18n/ru/llm.txt
index 55a640091a..185768e7a6 100644
--- a/docs/i18n/ru/llm.txt
+++ b/docs/i18n/ru/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/sk/llm.txt b/docs/i18n/sk/llm.txt
index 3d9cb70999..dfede586df 100644
--- a/docs/i18n/sk/llm.txt
+++ b/docs/i18n/sk/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/sv/llm.txt b/docs/i18n/sv/llm.txt
index b8c9565ca9..1d25949a50 100644
--- a/docs/i18n/sv/llm.txt
+++ b/docs/i18n/sv/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/sw/llm.txt b/docs/i18n/sw/llm.txt
index 22f4341a71..3c89f36e34 100644
--- a/docs/i18n/sw/llm.txt
+++ b/docs/i18n/sw/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/ta/llm.txt b/docs/i18n/ta/llm.txt
index b2e0455d6c..25af4e56f0 100644
--- a/docs/i18n/ta/llm.txt
+++ b/docs/i18n/ta/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/te/llm.txt b/docs/i18n/te/llm.txt
index 535e6bcd18..37e360f540 100644
--- a/docs/i18n/te/llm.txt
+++ b/docs/i18n/te/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/th/llm.txt b/docs/i18n/th/llm.txt
index 57ddded05e..cca3b2a061 100644
--- a/docs/i18n/th/llm.txt
+++ b/docs/i18n/th/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/tr/llm.txt b/docs/i18n/tr/llm.txt
index f3bffa57f1..a8173b9259 100644
--- a/docs/i18n/tr/llm.txt
+++ b/docs/i18n/tr/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/uk-UA/llm.txt b/docs/i18n/uk-UA/llm.txt
index d9e88525eb..32688fcb3a 100644
--- a/docs/i18n/uk-UA/llm.txt
+++ b/docs/i18n/uk-UA/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/ur/llm.txt b/docs/i18n/ur/llm.txt
index a5a158fe3e..75a150999f 100644
--- a/docs/i18n/ur/llm.txt
+++ b/docs/i18n/ur/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/vi/llm.txt b/docs/i18n/vi/llm.txt
index e20235b199..670af2110d 100644
--- a/docs/i18n/vi/llm.txt
+++ b/docs/i18n/vi/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/zh-CN/llm.txt b/docs/i18n/zh-CN/llm.txt
index 9122fc6694..80a275b537 100644
--- a/docs/i18n/zh-CN/llm.txt
+++ b/docs/i18n/zh-CN/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/i18n/zh-TW/llm.txt b/docs/i18n/zh-TW/llm.txt
index cfc263ea21..1da8bfc46d 100644
--- a/docs/i18n/zh-TW/llm.txt
+++ b/docs/i18n/zh-TW/llm.txt
@@ -26,7 +26,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -98,7 +98,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -263,7 +263,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -371,8 +371,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/docs/ops/VM_DEPLOYMENT_GUIDE.md b/docs/ops/VM_DEPLOYMENT_GUIDE.md
index 41a77d9e98..94ecebee15 100644
--- a/docs/ops/VM_DEPLOYMENT_GUIDE.md
+++ b/docs/ops/VM_DEPLOYMENT_GUIDE.md
@@ -6,7 +6,7 @@ lastUpdated: 2026-06-28
 
 # OmniRoute — Deployment Guide on VM with Cloudflare
 
-🌐 **Languages:** 🇺🇸 [English](./VM_DEPLOYMENT_GUIDE.md) | 🇧🇷 [Português (Brasil)](../i18n/pt-BR/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇪🇸 [Español](../i18n/es/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇫🇷 [Français](../i18n/fr/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇮🇹 [Italiano](../i18n/it/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇷🇺 [Русский](../i18n/ru/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇨🇳 [中文 (简体)](../i18n/zh-CN/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇩🇪 [Deutsch](../i18n/de/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇮🇳 [हिन्दी](../i18n/in/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇹🇭 [ไทย](../i18n/th/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇺🇦 [Українська](../i18n/uk-UA/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇸🇦 [العربية](../i18n/ar/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇯🇵 [日本語](../i18n/ja/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇻🇳 [Tiếng Việt](../i18n/vi/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇧🇬 [Български](../i18n/bg/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇩🇰 [Dansk](../i18n/da/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇫🇮 [Suomi](../i18n/fi/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇮🇱 [עברית](../i18n/he/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇭🇺 [Magyar](../i18n/hu/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇮🇩 [Bahasa Indonesia](../i18n/id/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇰🇷 [한국어](../i18n/ko/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇲🇾 [Bahasa Melayu](../i18n/ms/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇳🇱 [Nederlands](../i18n/nl/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇳🇴 [Norsk](../i18n/no/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇵🇹 [Português (Portugal)](../i18n/pt/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇷🇴 [Română](../i18n/ro/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇵🇱 [Polski](../i18n/pl/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇸🇰 [Slovenčina](../i18n/sk/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇸🇪 [Svenska](../i18n/sv/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇵🇭 [Filipino](../i18n/phi/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇨🇿 [Čeština](../i18n/cs/docs/ops/VM_DEPLOYMENT_GUIDE.md)
+🌐 **Languages:** 🇺🇸 [English](./VM_DEPLOYMENT_GUIDE.md) | 🇧🇷 [Português (Brasil)](../i18n/pt-BR/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇪🇸 [Español](../i18n/es/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇫🇷 [Français](../i18n/fr/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇮🇹 [Italiano](../i18n/it/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇷🇺 [Русский](../i18n/ru/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇨🇳 [中文 (简体)](../i18n/zh-CN/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇩🇪 [Deutsch](../i18n/de/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇹🇭 [ไทย](../i18n/th/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇺🇦 [Українська](../i18n/uk-UA/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇸🇦 [العربية](../i18n/ar/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇯🇵 [日本語](../i18n/ja/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇻🇳 [Tiếng Việt](../i18n/vi/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇧🇬 [Български](../i18n/bg/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇩🇰 [Dansk](../i18n/da/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇫🇮 [Suomi](../i18n/fi/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇮🇱 [עברית](../i18n/he/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇭🇺 [Magyar](../i18n/hu/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇮🇩 [Bahasa Indonesia](../i18n/id/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇰🇷 [한국어](../i18n/ko/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇲🇾 [Bahasa Melayu](../i18n/ms/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇳🇱 [Nederlands](../i18n/nl/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇳🇴 [Norsk](../i18n/no/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇵🇹 [Português (Portugal)](../i18n/pt/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇷🇴 [Română](../i18n/ro/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇵🇱 [Polski](../i18n/pl/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇸🇰 [Slovenčina](../i18n/sk/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇸🇪 [Svenska](../i18n/sv/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇵🇭 [Filipino](../i18n/phi/docs/ops/VM_DEPLOYMENT_GUIDE.md) | 🇨🇿 [Čeština](../i18n/cs/docs/ops/VM_DEPLOYMENT_GUIDE.md)
 
 Complete guide to install and configure OmniRoute on a VM (VPS) with domain managed via Cloudflare.
 
diff --git a/docs/reference/API_REFERENCE.md b/docs/reference/API_REFERENCE.md
index 42dbb44632..47f459cd54 100644
--- a/docs/reference/API_REFERENCE.md
+++ b/docs/reference/API_REFERENCE.md
@@ -6,7 +6,7 @@ lastUpdated: 2026-08-31
 
 # API Reference
 
-🌐 **Languages:** 🇺🇸 [English](./API_REFERENCE.md) | 🇧🇷 [Português (Brasil)](../i18n/pt-BR/docs/reference/API_REFERENCE.md) | 🇪🇸 [Español](../i18n/es/docs/reference/API_REFERENCE.md) | 🇫🇷 [Français](../i18n/fr/docs/reference/API_REFERENCE.md) | 🇮🇹 [Italiano](../i18n/it/docs/reference/API_REFERENCE.md) | 🇷🇺 [Русский](../i18n/ru/docs/reference/API_REFERENCE.md) | 🇨🇳 [中文 (简体)](../i18n/zh-CN/docs/reference/API_REFERENCE.md) | 🇩🇪 [Deutsch](../i18n/de/docs/reference/API_REFERENCE.md) | 🇮🇳 [हिन्दी](../i18n/in/docs/reference/API_REFERENCE.md) | 🇹🇭 [ไทย](../i18n/th/docs/reference/API_REFERENCE.md) | 🇺🇦 [Українська](../i18n/uk-UA/docs/reference/API_REFERENCE.md) | 🇸🇦 [العربية](../i18n/ar/docs/reference/API_REFERENCE.md) | 🇯🇵 [日本語](../i18n/ja/docs/reference/API_REFERENCE.md) | 🇻🇳 [Tiếng Việt](../i18n/vi/docs/reference/API_REFERENCE.md) | 🇧🇬 [Български](../i18n/bg/docs/reference/API_REFERENCE.md) | 🇩🇰 [Dansk](../i18n/da/docs/reference/API_REFERENCE.md) | 🇫🇮 [Suomi](../i18n/fi/docs/reference/API_REFERENCE.md) | 🇮🇱 [עברית](../i18n/he/docs/reference/API_REFERENCE.md) | 🇭🇺 [Magyar](../i18n/hu/docs/reference/API_REFERENCE.md) | 🇮🇩 [Bahasa Indonesia](../i18n/id/docs/reference/API_REFERENCE.md) | 🇰🇷 [한국어](../i18n/ko/docs/reference/API_REFERENCE.md) | 🇲🇾 [Bahasa Melayu](../i18n/ms/docs/reference/API_REFERENCE.md) | 🇳🇱 [Nederlands](../i18n/nl/docs/reference/API_REFERENCE.md) | 🇳🇴 [Norsk](../i18n/no/docs/reference/API_REFERENCE.md) | 🇵🇹 [Português (Portugal)](../i18n/pt/docs/reference/API_REFERENCE.md) | 🇷🇴 [Română](../i18n/ro/docs/reference/API_REFERENCE.md) | 🇵🇱 [Polski](../i18n/pl/docs/reference/API_REFERENCE.md) | 🇸🇰 [Slovenčina](../i18n/sk/docs/reference/API_REFERENCE.md) | 🇸🇪 [Svenska](../i18n/sv/docs/reference/API_REFERENCE.md) | 🇵🇭 [Filipino](../i18n/phi/docs/reference/API_REFERENCE.md) | 🇨🇿 [Čeština](../i18n/cs/docs/reference/API_REFERENCE.md)
+🌐 **Languages:** 🇺🇸 [English](./API_REFERENCE.md) | 🇧🇷 [Português (Brasil)](../i18n/pt-BR/docs/reference/API_REFERENCE.md) | 🇪🇸 [Español](../i18n/es/docs/reference/API_REFERENCE.md) | 🇫🇷 [Français](../i18n/fr/docs/reference/API_REFERENCE.md) | 🇮🇹 [Italiano](../i18n/it/docs/reference/API_REFERENCE.md) | 🇷🇺 [Русский](../i18n/ru/docs/reference/API_REFERENCE.md) | 🇨🇳 [中文 (简体)](../i18n/zh-CN/docs/reference/API_REFERENCE.md) | 🇩🇪 [Deutsch](../i18n/de/docs/reference/API_REFERENCE.md) | 🇹🇭 [ไทย](../i18n/th/docs/reference/API_REFERENCE.md) | 🇺🇦 [Українська](../i18n/uk-UA/docs/reference/API_REFERENCE.md) | 🇸🇦 [العربية](../i18n/ar/docs/reference/API_REFERENCE.md) | 🇯🇵 [日本語](../i18n/ja/docs/reference/API_REFERENCE.md) | 🇻🇳 [Tiếng Việt](../i18n/vi/docs/reference/API_REFERENCE.md) | 🇧🇬 [Български](../i18n/bg/docs/reference/API_REFERENCE.md) | 🇩🇰 [Dansk](../i18n/da/docs/reference/API_REFERENCE.md) | 🇫🇮 [Suomi](../i18n/fi/docs/reference/API_REFERENCE.md) | 🇮🇱 [עברית](../i18n/he/docs/reference/API_REFERENCE.md) | 🇭🇺 [Magyar](../i18n/hu/docs/reference/API_REFERENCE.md) | 🇮🇩 [Bahasa Indonesia](../i18n/id/docs/reference/API_REFERENCE.md) | 🇰🇷 [한국어](../i18n/ko/docs/reference/API_REFERENCE.md) | 🇲🇾 [Bahasa Melayu](../i18n/ms/docs/reference/API_REFERENCE.md) | 🇳🇱 [Nederlands](../i18n/nl/docs/reference/API_REFERENCE.md) | 🇳🇴 [Norsk](../i18n/no/docs/reference/API_REFERENCE.md) | 🇵🇹 [Português (Portugal)](../i18n/pt/docs/reference/API_REFERENCE.md) | 🇷🇴 [Română](../i18n/ro/docs/reference/API_REFERENCE.md) | 🇵🇱 [Polski](../i18n/pl/docs/reference/API_REFERENCE.md) | 🇸🇰 [Slovenčina](../i18n/sk/docs/reference/API_REFERENCE.md) | 🇸🇪 [Svenska](../i18n/sv/docs/reference/API_REFERENCE.md) | 🇵🇭 [Filipino](../i18n/phi/docs/reference/API_REFERENCE.md) | 🇨🇿 [Čeština](../i18n/cs/docs/reference/API_REFERENCE.md)
 
 Core reference for the OmniRoute API. It covers the public `/v1` surface and the most-used management endpoints; the machine-readable [`docs/openapi.yaml`](../openapi.yaml) and the route tree under `src/app/api/` are the exhaustive sources.
 
diff --git a/llm.txt b/llm.txt
index 12bdfe1ffb..c8e4c0806d 100644
--- a/llm.txt
+++ b/llm.txt
@@ -22,7 +22,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler, 24h model auto-sync
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting, auto-combo engine
-- **i18n:** next-intl with 43 languages
+- **i18n:** next-intl with 42 languages
 - **Desktop:** Electron (cross-platform: Windows, macOS, Linux)
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
 
@@ -94,7 +94,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── configAudit.ts        # Configuration auditing
 │   │   └── responses.ts          # Domain response types
 │   ├── i18n/                     # Internationalization
-│   │   └── messages/             # 43 language JSON files
+│   │   └── messages/             # 42 language JSON files
 │   ├── lib/                      # Core libraries
 │   │   ├── a2a/                  # Agent-to-Agent v0.3 protocol server
 │   │   │   ├── skills/           # A2A skills (quotaManagement, smartRouting)
@@ -259,7 +259,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── translator/               # Translator-specific tests
 │   └── load/                     # Load tests
 ├── docs/                         # Documentation
-│   ├── i18n/                     # 43-language translated docs
+│   ├── i18n/                     # 41-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
 │   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
@@ -367,8 +367,8 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 **Custom Providers:** OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) with custom base URLs
 
 ### Internationalization
-- 43 languages for UI (all dashboard pages)
-- 42 translated documentation sets in docs/i18n/
+- 42 languages for UI (all dashboard pages)
+- 41 translated documentation sets in docs/i18n/
 - Language switcher in documentation
 
 ## Key Architectural Decisions
diff --git a/scripts/i18n/generate-multilang.mjs b/scripts/i18n/generate-multilang.mjs
index 9f61aff9ab..c8411e1103 100644
--- a/scripts/i18n/generate-multilang.mjs
+++ b/scripts/i18n/generate-multilang.mjs
@@ -269,15 +269,6 @@ const LOCALE_SPECS = [
     readmeName: "Bahasa Indonesia",
     docsName: "Bahasa Indonesia",
   },
-  {
-    code: "in",
-    googleTl: "id",
-    label: "IN",
-    flag: "🇮🇩",
-    languageName: "Bahasa Indonesia (Alt)",
-    readmeName: "Bahasa Indonesia (Alt)",
-    docsName: "Bahasa Indonesia (Alt)",
-  },
   {
     code: "ko",
     googleTl: "ko",
diff --git a/scripts/i18n/i18n_autotranslate.py b/scripts/i18n/i18n_autotranslate.py
index 417e66b592..78a1156cfe 100755
--- a/scripts/i18n/i18n_autotranslate.py
+++ b/scripts/i18n/i18n_autotranslate.py
@@ -38,7 +38,7 @@ def get_language_name(lang_code):
     lang_map = {
         "pt-BR": "Portuguese (Brazil)", "es": "Spanish", "fr": "French", 
         "it": "Italian", "ru": "Russian", "zh-CN": "Simplified Chinese", 
-        "de": "German", "in": "Hindi", "th": "Thai", "uk-UA": "Ukrainian", 
+        "de": "German", "th": "Thai", "uk-UA": "Ukrainian", 
         "ar": "Arabic", "az": "Azerbaijani", "ja": "Japanese", "vi": "Vietnamese", "bg": "Bulgarian", 
         "da": "Danish", "fi": "Finnish", "he": "Hebrew", "hu": "Hungarian", 
         "id": "Indonesian", "ko": "Korean", "ms": "Malay", "nl": "Dutch", 
diff --git a/src/i18n/messages/in.json b/src/i18n/messages/in.json
deleted file mode 100644
index 7af3f51c52..0000000000
--- a/src/i18n/messages/in.json
+++ /dev/null
@@ -1,14071 +0,0 @@
-{
-  "common": {
-    "save": "Save",
-    "cancel": "Cancel",
-    "delete": "Delete",
-    "loading": "Loading...",
-    "selectOption": "Pilih opsi",
-    "error": "An error occurred",
-    "success": "Success",
-    "confirm": "Are you sure?",
-    "refresh": "Refresh",
-    "close": "Close",
-    "previousPage": "Halaman sebelumnya",
-    "nextPage": "Halaman berikutnya",
-    "capsLockOn": "Caps Lock aktif",
-    "dismissNotification": "Abaikan pemberitahuan",
-    "toggleColumns": "Alihkan kolom",
-    "confirmTitle": "Konfirmasi",
-    "confirmAction": "Konfirmasi",
-    "add": "Add",
-    "edit": "Edit",
-    "search": "Search",
-    "back": "Back",
-    "next": "Next",
-    "submit": "Submit",
-    "reset": "Reset",
-    "copy": "Copy",
-    "copied": "Copied!",
-    "enabled": "Enabled",
-    "disabled": "Disabled",
-    "active": "Active",
-    "inactive": "Inactive",
-    "noData": "No data available",
-    "nothingHere": "Nothing here yet",
-    "configure": "Configure",
-    "manualConfig": "Konfigurasi manual",
-    "manage": "Manage",
-    "name": "Name",
-    "actions": "Actions",
-    "status": "Status",
-    "type": "Type",
-    "model": "Model",
-    "models": "models",
-    "provider": "Provider",
-    "unknownProvider": "Penyedia tidak dikenal",
-    "account": "Account",
-    "time": "Time",
-    "details": "Details",
-    "created": "Created",
-    "lastUsed": "Last Refreshed",
-    "loadMore": "Load More",
-    "noResults": "No results found",
-    "reloadPage": "Reload Page",
-    "connected": "Connected",
-    "disconnected": "Disconnected",
-    "notConfigured": "Not configured",
-    "testConnection": "Test Connection",
-    "enable": "Enable",
-    "disable": "Disable",
-    "columns": "Columns",
-    "newest": "Newest",
-    "oldest": "Oldest",
-    "all": "All",
-    "none": "None",
-    "yes": "Yes",
-    "no": "No",
-    "on": "AKTIF",
-    "off": "NONAKTIF",
-    "warning": "Warning",
-    "note": "Note",
-    "free": "Free",
-    "skipToContent": "Skip to content",
-    "maintenanceServerIssues": "Server is experiencing issues. Some features may be unavailable.",
-    "maintenanceServerUnreachable": "Server is unreachable. Reconnecting...",
-    "accept": "Accept",
-    "accountId": "Account ID",
-    "alias": "Alias",
-    "apiKeyId": "API Key ID",
-    "apiKeyName": "API Key Name",
-    "apiKeySecret": "API Key Secret",
-    "authorization": "Authorization",
-    "content-type": "Content Type",
-    "content-length": "Content Length",
-    "cookie": "Cookie",
-    "file": "File",
-    "host": "Host",
-    "id": "ID",
-    "import": "Import",
-    "limit": "Limit",
-    "offset": "Offset",
-    "open": "Open",
-    "origin": "Origin",
-    "promptTokens": "Prompt Tokens",
-    "completionTokens": "Completion Tokens",
-    "totalTokens": "Total Tokens",
-    "rawModel": "Raw Model",
-    "scope": "Scope",
-    "skill": "Skill",
-    "sortBy": "Sort By",
-    "sortOrder": "Sort Order",
-    "tab": "Tab",
-    "text": "Text",
-    "textarea": "Textarea",
-    "tool": "Tool",
-    "toolId": "Tool ID",
-    "web": "Web",
-    "whereUsed": "Where Used",
-    "whitelist": "Whitelist",
-    "blacklist": "Blacklist",
-    "resolve": "Resolve",
-    "force": "Force",
-    "base64url": "Base64 URL",
-    "hex": "Hex",
-    "range": "Range",
-    "component": "Component",
-    "redirect_uri": "Redirect URI",
-    "idempotency-key": "Idempotency Key",
-    "error_description": "Error Description",
-    "code": "Code",
-    "compatible": "Compatible",
-    "chat-completions": "Chat Completions",
-    "oauth": "OAuth",
-    "auth_token": "Auth Token",
-    "crypto": "Crypto",
-    "hours": "Hours",
-    "selfsigned": "Self-signed",
-    "proxy_id": "Proxy ID",
-    "proxyId": "Proxy ID",
-    "connectionId": "Connection ID",
-    "resolveConnectionId": "Resolve Connection ID",
-    "resolve_connection_id": "Resolve Connection ID",
-    "scope_id": "Scope ID",
-    "scopeId": "Scope ID",
-    "jwtSecret": "JWT Secret",
-    "keytar": "Keytar",
-    "better-sqlite3": "better-sqlite3",
-    "undici": "undici",
-    "builder-id": "Builder ID",
-    "musicDesc": "Music Description",
-    "musicGeneration": "Music Generation",
-    "idc": "IDC",
-    "cloud-status-changed": "Cloud status changed",
-    "where_used": "Where Used",
-    "windowMs": "Window (ms)",
-    "social-github": "GitHub",
-    "social-google": "Google",
-    "TOOL_ALLOWLIST": "Tool Allowlist",
-    "TOOL_DENYLIST": "Tool Denylist",
-    "Failed to save pricing": "Failed to save pricing",
-    "Failed to reset pricing": "Failed to reset pricing",
-    "apikey": "API Key",
-    "http": "HTTP",
-    "goToDashboard": "Go to Dashboard",
-    "checkSystemStatus": "Check System Status",
-    "selectModel": "Select Model",
-    "addModel": "Tambah model",
-    "effortNone": "Tidak ada",
-    "effortLow": "Rendah",
-    "effortMedium": "Sedang",
-    "effortHigh": "Tinggi",
-    "effortExtraHigh": "Sangat tinggi",
-    "effortMax": "Maks",
-    "effortUltra": "Ultra",
-    "reasoningEffort": "Upaya penalaran",
-    "wireApi": "Wire API",
-    "modelAliases": "Alias model",
-    "combos": "Combos",
-    "noModelsFound": "No models found",
-    "clear": "Clear",
-    "done": "Done",
-    "selectAll": "Pilih semua",
-    "unselectAll": "Batalkan semua pilihan",
-    "visibleModels": "terlihat",
-    "selectAllConfirm": "Tambahkan {count} model ke kombinasi ini?",
-    "testSelectedProviders": "Penyedia Uji",
-    "testingSelectedProviders": "Mengujicoba {done}/{total}...",
-    "noProvidersSelectedToTest": "Periksa setidaknya satu penyedia di bawah ini terlebih dahulu",
-    "noModelsToTestForProviders": "Tidak ada model untuk diuji untuk penyedia yang dipilih",
-    "testSelectedProvidersResults": "{ok} dari {total} model berfungsi",
-    "selectWorkingModels": "Tambahkan bekerja",
-    "unselectWorkingModels": "Batalkan pilihan bekerja",
-    "noWorkingModelsToSelect": "Tidak ada model yang dapat ditambahkan lagi",
-    "providerTestHint": "Tip: periksa penyedia → Uji → Tambahkan yang berfungsi. Klik lagi untuk membatalkan pilihan.",
-    "selectAllProviders": "Periksa semua penyedia",
-    "clearProviderSelection": "Hapus centang penyedia",
-    "providersSelectedCount": "{count} penyedia diperiksa",
-    "errorOccurred": "Error Occurred",
-    "comboDeleted": "Combo Deleted",
-    "hide": "Hide",
-    "creating": "Creating",
-    "comboCreated": "Combo Created",
-    "swapFormats": "Swap Formats",
-    "daysAgo": "Days Ago",
-    "retries": "Retries",
-    "errorDuringRestore": "Error During Restore",
-    "eventsAppearHint": "Events Appear Hint",
-    "noLockouts": "No Lockouts",
-    "webSearchDesc": "Web Search Desc",
-    "audioProvidersHeading": "Audio Providers Heading",
-    "cloudAgentProviders": "Penyedia Agen Cloud",
-    "minutesAgo": "Minutes Ago",
-    "a": "A",
-    "liveAutoRefreshing": "Live Auto Refreshing",
-    "webSearch": "Web Search",
-    "anthropicPrefixPlaceholder": "Anthropic Prefix Placeholder",
-    "addModelToCombo": "Add Model To Combo",
-    "failedToLoad": "Failed To Load",
-    "categoryMedia": "Category Media",
-    "enableCloud": "Enable Cloud",
-    "expirationBannerExpiringSoon": "Expiration Banner Expiring Soon",
-    "retry": "Retry",
-    "embeddings": "Embeddings",
-    "errorCount": "Error Count",
-    "backupReasonManual": "Backup Reason Manual",
-    "safeSearchModerate": "Safe Search Moderate",
-    "activeLimiters": "Active Limiters",
-    "a2aCardTitle": "A2A Card Title",
-    "cloudWorkerUnreachable": "Cloud Worker Unreachable",
-    "testFailed": "Test Failed",
-    "compatibleBaseUrlHint": "Compatible Base Url Hint",
-    "usageTracking": "Usage Tracking",
-    "disableCloudTitle": "Disable Cloud Title",
-    "noConnections": "No Connections",
-    "providerHealth": "Provider Health",
-    "confirmDbImport": "Confirm Db Import",
-    "notAvailableSymbol": "Not Available Symbol",
-    "backupsAvailable": "Backups Available",
-    "providerAuto": "Provider Auto",
-    "newProviderNamePlaceholder": "New Provider Name Placeholder",
-    "a2aQuickStartStep2": "A2A Quick Start Step2",
-    "ok": "Ok",
-    "available": "Available",
-    "noBackupYet": "No Backup Yet",
-    "more": "More",
-    "noCompatibleYet": "No Compatible Yet",
-    "multiProvider": "Multi Provider",
-    "repairEnvHint": "Repair Env Hint",
-    "disablingCloud": "Disabling Cloud",
-    "testBench": "Test Bench",
-    "valid": "Valid",
-    "cloudBenefitShare": "Cloud Benefit Share",
-    "mcpCardTitle": "Mcp Card Title",
-    "disableConfirm": "Disable Confirm",
-    "filters": "Filters",
-    "expirationBannerExpiredDesc": "Expiration Banner Expired Desc",
-    "saveComboDefaults": "Save Combo Defaults",
-    "cloudConnectedVerified": "Cloud Connected Verified",
-    "uptime": "Uptime",
-    "compatibleProdPlaceholder": "Compatible Prod Placeholder",
-    "fallbackChainsTitle": "Fallback Chains Title",
-    "oauthLabel": "Oauth Label",
-    "a2aCardDescription": "A2A Card Description",
-    "okShort": "Ok Short",
-    "maintenance": "Maintenance",
-    "formatConverter": "Format Converter",
-    "zedImportNetworkError": "Zed Import Network Error",
-    "apiKeyLabel": "Api Key Label",
-    "noModelsForProvider": "No Models For Provider",
-    "mcpCardDescription": "Mcp Card Description",
-    "apiTypeLabel": "Api Type Label",
-    "configuredProvidersLabel": "Configured Providers Label",
-    "maxRetriesLabel": "Max Retries Label",
-    "title": "Title",
-    "output": "Output",
-    "prefixHint": "Prefix Hint",
-    "skipWizard": "Skip Wizard",
-    "failedCount": "Failed Count",
-    "confirmDbImportDesc": "Confirm Db Import Desc",
-    "entries": "Entries",
-    "until": "Until",
-    "disableCombo": "Disable Combo",
-    "liveMonitorDescriptionPrefix": "Live Monitor Description Prefix",
-    "runningCount": "Running Count",
-    "noActiveConnectionsInGroup": "No Active Connections In Group",
-    "savedSuccessfully": "Saved Successfully",
-    "systemStorage": "System Storage",
-    "videoDesc": "Video Desc",
-    "maxResults": "Max Results",
-    "timeRangeMonth": "Time Range Month",
-    "testSummary": "Test Summary",
-    "failedSetPassword": "Failed Set Password",
-    "audio": "Audio",
-    "restore": "Restore",
-    "disableWarning": "Disable Warning",
-    "moderationsDesc": "Moderations Desc",
-    "providerHealthStatusAria": "Provider Health Status Aria",
-    "modelNamePlaceholder": "Model Name Placeholder",
-    "mcpQuickStartStep2": "Mcp Quick Start Step2",
-    "quickStart": "Quick Start",
-    "fullExportFailedWithError": "Full Export Failed With Error",
-    "loadingBackups": "Loading Backups",
-    "anthropicBaseUrlPlaceholder": "Anthropic Base Url Placeholder",
-    "description": "Description",
-    "noProviderFound": "No Provider Found",
-    "auto": "Auto",
-    "protocolsDescription": "Protocols Description",
-    "cloudSessionNote": "Cloud Session Note",
-    "advancedSettings": "Advanced Settings",
-    "defaultStrategy": "Default Strategy",
-    "purgeExpiredLogs": "Purge Expired Logs",
-    "justNow": "Just Now",
-    "providerTestFailed": "Provider Test Failed",
-    "openaiBaseUrlPlaceholder": "Openai Base Url Placeholder",
-    "image": "Image",
-    "failedCreateChain": "Failed Create Chain",
-    "importDatabase": "Import Database",
-    "allDataLocal": "All Data Local",
-    "sectionTitle": "Section Title",
-    "failedToggle": "Failed Toggle",
-    "editCombo": "Edit Combo",
-    "testResults": "Test Results",
-    "searchQuery": "Search Query",
-    "addCcCompatible": "Add Cc Compatible",
-    "duplicate": "Duplicate",
-    "createCombo": "Create Combo",
-    "searchTypeWeb": "Search Type Web",
-    "addChain": "Add Chain",
-    "prefixLabel": "Prefix Label",
-    "listModelsDesc": "List Models Desc",
-    "databaseSize": "Database Size",
-    "chainCreated": "Chain Created",
-    "providerTestTimeout": "Provider Test Timeout",
-    "routingStrategy": "Routing Strategy",
-    "translateAction": "Translate Action",
-    "exportFailed": "Export Failed",
-    "connectedVerificationPending": "Connected Verification Pending",
-    "a2aQuickStartTitle": "A2A Quick Start Title",
-    "couldNotTest": "Could Not Test",
-    "testAllCompatible": "Test All Compatible",
-    "anthropicCompatibleName": "Anthropic Compatible Name",
-    "disabling": "Disabling",
-    "failedEnable": "Failed Enable",
-    "categoryUtility": "Category Utility",
-    "customUrlOptional": "Custom Url Optional",
-    "localProviders": "Local Providers",
-    "comboNamePlaceholder": "Combo Name Placeholder",
-    "memoryRss": "Memory Rss",
-    "disableProvider": "Disable Provider",
-    "welcomeDesc": "Welcome Desc",
-    "nameLabel": "Name Label",
-    "allOperational": "All Operational",
-    "backupNow": "Backup Now",
-    "providerMaxRetriesAria": "Provider Max Retries Aria",
-    "textToSpeechDesc": "Text To Speech Desc",
-    "machineId": "Machine Id",
-    "globalProxy": "Global Proxy",
-    "hitsMisses": "Hits Misses",
-    "testDesc": "Test Desc",
-    "chatDesc": "Chat Desc",
-    "importSuccess": "Import Success",
-    "chat": "Chat",
-    "a2aQuickStartStep1": "A2A Quick Start Step1",
-    "importFailed": "Import Failed",
-    "inputPlaceholder": "Input Placeholder",
-    "providerModelsTitle": "Provider Models Title",
-    "lastBackup": "Last Backup",
-    "yourEndpoint": "Your Endpoint",
-    "autoDisableThresholdDesc": "Auto Disable Threshold Desc",
-    "rerankDesc": "Rerank Desc",
-    "modelsPathPlaceholder": "Models Path Placeholder",
-    "noCombosYet": "No Combos Yet",
-    "connectedVerificationPendingWithError": "Connected Verification Pending With Error",
-    "comboDefaultsGuideHint1": "Combo Defaults Guide Hint1",
-    "enableCloudTitle": "Enable Cloud Title",
-    "configuredProvidersHint": "Configured Providers Hint",
-    "paused": "Paused",
-    "llmProviders": "Llm Providers",
-    "enableCombo": "Enable Combo",
-    "removeProviderOverrideAria": "Remove Provider Override Aria",
-    "nodeVersion": "Node Version",
-    "openai": "Openai",
-    "exportFailedWithError": "Export Failed With Error",
-    "proxyConfigured": "Proxy Configured",
-    "concurrencyPerModel": "Concurrency Per Model",
-    "protocolTasksLabel": "Protocol Tasks Label",
-    "oauthProviders": "Oauth Providers",
-    "lockedCount": "Locked Count",
-    "deleteChainConfirm": "Delete Chain Confirm",
-    "recentTranslations": "Recent Translations",
-    "zedImportButton": "Zed Import Button",
-    "responsesDesc": "Responses Desc",
-    "testedCount": "Tested Count",
-    "providersCommaSeparatedPlaceholder": "Providers Comma Separated Placeholder",
-    "signatureDefaults": "Signature Defaults",
-    "errorCreating": "Error Creating",
-    "timeRangeYear": "Time Range Year",
-    "compatibleLabel": "Compatible Label",
-    "cloudDisabledSuccess": "Cloud Disabled Success",
-    "deleteConfirm": "Delete Confirm",
-    "check": "Check",
-    "safeSearch": "Safe Search",
-    "protocolLastActivity": "Protocol Last Activity",
-    "openMcpDashboard": "Open Mcp Dashboard",
-    "testBenchTab": "Test Bench",
-    "chatPathLabel": "Chat Path Label",
-    "retryDelay": "Retry Delay",
-    "errorUpdating": "Error Updating",
-    "ideCliIntegrations": "Ide Cli Integrations",
-    "imageGeneration": "Image Generation",
-    "apiKeyRequired": "Api Key Required",
-    "resetAllTitle": "Reset All Title",
-    "connectionError": "Connection Error",
-    "modelName": "Model Name",
-    "apiKeyForCheck": "Api Key For Check",
-    "cloudRequestTimeout": "Cloud Request Timeout",
-    "showConfiguredOnly": "Show Configured Only",
-    "showFreeOnly": "Hanya gratis",
-    "addFirstProvider": "Tambahkan penyedia pertama Anda",
-    "addFirstProviderDesc": "Hubungkan penyedia AI untuk memulai perutean permintaan melalui OmniRoute. Anda dapat menggunakan penyedia gratis, kunci API, atau akun OAuth.",
-    "learnMore": "Pelajari lebih lanjut",
-    "includeDomains": "Include Domains",
-    "promptCache": "Prompt Cache",
-    "cloudConnected": "Cloud Connected",
-    "deleteChain": "Delete Chain",
-    "chatPathPlaceholder": "Chat Path Placeholder",
-    "databasePath": "Database Path",
-    "usingLocalServer": "Using Local Server",
-    "globalComboConfig": "Global Combo Config",
-    "backupFailed": "Backup Failed",
-    "tabProtocols": "Tab Protocols",
-    "continue": "Continue",
-    "categorySearch": "Category Search",
-    "rateLimitStatus": "Rate Limit Status",
-    "repairEnvSuccess": "Repair Env Success",
-    "nameRequired": "Name Required",
-    "country": "Country",
-    "trackMetricsDesc": "Track Metrics Desc",
-    "durationSecondsShort": "Duration Seconds Short",
-    "formatConverterDescription": "Format Converter Description",
-    "cloudBenefitAccess": "Cloud Benefit Access",
-    "maxRetries": "Max Retries",
-    "queueTimeout": "Queue Timeout",
-    "queueDepth": "Kedalaman Antrean",
-    "addProvider": "Add Provider",
-    "realtime": "Realtime",
-    "totalTranslations": "Total Translations",
-    "protocolActiveStreamsLabel": "Protocol Active Streams Label",
-    "repairEnv": "Repair Env",
-    "modelsCount": "Models Count",
-    "viewBackups": "View Backups",
-    "responsesApi": "Responses Api",
-    "copyComboName": "Copy Combo Name",
-    "failures": "Failures",
-    "failedUpdate": "Failed Update",
-    "imageDesc": "Image Desc",
-    "failedCreate": "Failed Create",
-    "remainingOfLimit": "Remaining Of Limit",
-    "protocolsTitle": "Protocols Title",
-    "expirationBannerExpiringSoonDesc": "Expiration Banner Expiring Soon Desc",
-    "source": "Source",
-    "failed": "Failed",
-    "apiKeyMgmt": "Api Key Mgmt",
-    "mcpQuickStartStep1": "Mcp Quick Start Step1",
-    "runTest": "Run Test",
-    "loadingFallbackChains": "Loading Fallback Chains",
-    "healthy": "Healthy",
-    "version": "Version",
-    "saveBlockWeighted": "Save Block Weighted",
-    "zedImportNone": "Zed Import None",
-    "noBackupsYet": "No Backups Yet",
-    "noGlobalProxy": "No Global Proxy",
-    "noModels": "No Models",
-    "stickyLimit": "Sticky Limit",
-    "passedCount": "Passed Count",
-    "zedImportFailed": "Zed Import Failed",
-    "saving": "Saving",
-    "testAll": "Test All",
-    "globalProxyDesc": "Global Proxy Desc",
-    "latencyP99": "Latency P99",
-    "connectingToCloud": "Connecting To Cloud",
-    "responses": "Responses",
-    "errorDeleting": "Error Deleting",
-    "openaiPrefixPlaceholder": "Openai Prefix Placeholder",
-    "enterPassword": "Enter Password",
-    "openA2aDashboard": "Open A2A Dashboard",
-    "enableProvider": "Enable Provider",
-    "modeTest": "Mode Test",
-    "failedDeleteChain": "Failed Delete Chain",
-    "providerDesc": "Provider Desc",
-    "templateLoadHint": "Template Load Hint",
-    "lastFailure": "Last Failure",
-    "moveDown": "Move Down",
-    "providerLabel": "Provider Label",
-    "clearCacheFailed": "Clear Cache Failed",
-    "imagesGenerations": "Images Generations",
-    "repairEnvWorking": "Repair Env Working",
-    "millisecondsShort": "Milliseconds Short",
-    "globalLabel": "Global Label",
-    "failuresPlural": "Failures Plural",
-    "completionsLegacyDesc": "Completions Legacy Desc",
-    "searchProviders": "Search Providers",
-    "chatPathHint": "Chat Path Hint",
-    "defaultStrategyDesc": "Default Strategy Desc",
-    "latencyP95": "Latency P95",
-    "textToSpeech": "Text To Speech",
-    "searchType": "Search Type",
-    "messages": "Messages",
-    "aggregatorsGateways": "Aggregators Gateways",
-    "comboStrategyAria": "Combo Strategy Aria",
-    "input": "Input",
-    "testingConnection": "Testing Connection",
-    "excludeDomains": "Exclude Domains",
-    "webCookieProviders": "Web Cookie Providers",
-    "allTestsPassed": "All Tests Passed",
-    "openaiCompatibleName": "Openai Compatible Name",
-    "warningCostOptimizedPartialPricing": "Warning Cost Optimized Partial Pricing",
-    "comboDefaultsGuideTitle": "Combo Defaults Guide Title",
-    "hoursAgo": "Hours Ago",
-    "notAvailable": "Not Available",
-    "skipAndContinue": "Skip And Continue",
-    "moderations": "Moderations",
-    "proxyConfig": "Proxy Config",
-    "upstreamProxyProviders": "Upstream Proxy Providers",
-    "exportAll": "Export All",
-    "queuedCount": "Queued Count",
-    "resetAll": "Reset All",
-    "noTranslations": "No Translations",
-    "avgLatency": "Avg Latency",
-    "throttleStatus": "Throttle Status",
-    "backupRetentionDesc": "Backup Retention Desc",
-    "noCBData": "No Cb Data",
-    "chainDeleted": "Chain Deleted",
-    "timeLeft": "Time Left",
-    "expirationBannerExpired": "Expiration Banner Expired",
-    "language": "Language",
-    "invalidFileType": "Invalid File Type",
-    "monitoredProviders": "Monitored Providers",
-    "errors": "Errors",
-    "heap": "Heap",
-    "chatCompletions": "Chat Completions",
-    "exampleTemplatesHint": "Example Templates Hint",
-    "retryDelayLabel": "Retry Delay Label",
-    "audioTranscription": "Audio Transcription",
-    "fallbackChainsDesc": "Fallback Chains Desc",
-    "exampleTemplates": "Example Templates",
-    "connectionsCount": "Connections Count",
-    "modelsPathLabel": "Models Path Label",
-    "activeProvidersHint": "Active Providers Hint",
-    "activeLockouts": "Active Lockouts",
-    "invalid": "Invalid",
-    "skipPassword": "Skip Password",
-    "moveUp": "Move Up",
-    "timeRange": "Time Range",
-    "stickyLimitDesc": "Sticky Limit Desc",
-    "cloudBenefitEdge": "Cloud Benefit Edge",
-    "custom": "Custom",
-    "verifying": "Verifying",
-    "baseUrlLabel": "Base Url Label",
-    "setPassword": "Set Password",
-    "safeSearchStrict": "Safe Search Strict",
-    "noChangesSinceBackup": "No Changes Since Backup",
-    "modelsPathHint": "Models Path Hint",
-    "audioTranscriptions": "Audio Transcriptions",
-    "testCombo": "Test Combo",
-    "mcpQuickStartTitle": "Mcp Quick Start Title",
-    "comboUpdated": "Combo Updated",
-    "weighted": "Weighted",
-    "providers": "Providers",
-    "ccCompatibleLabel": "Cc Compatible Label",
-    "noFallbackChainsDesc": "No Fallback Chains Desc",
-    "yesImport": "Yes Import",
-    "lockoutsAutoRefreshHint": "Lockouts Auto Refresh Hint",
-    "tabApis": "Tab Apis",
-    "sectionDescription": "Section Description",
-    "filter": "Filter",
-    "purgeLogsFailed": "Purge Logs Failed",
-    "latency": "Latency",
-    "testAllOAuth": "Test All O Auth",
-    "mcpQuickStartStep3": "Mcp Quick Start Step3",
-    "repairEnvFailed": "Repair Env Failed",
-    "zedImportHint": "Zed Import Hint",
-    "modelsAcrossEndpoints": "Models Across Endpoints",
-    "autoDisableBannedAccounts": "Auto Disable Banned Accounts",
-    "securityDesc": "Security Desc",
-    "listModels": "List Models",
-    "backupRestore": "Backup Restore",
-    "target": "Target",
-    "zedImportSuccess": "Zed Import Success",
-    "lastHeaderUpdate": "Last Header Update",
-    "categoryCore": "Category Core",
-    "noFallbackChains": "No Fallback Chains",
-    "noSearchProviders": "No Search Providers",
-    "autoBalance": "Auto Balance",
-    "noModelsYet": "No Models Yet",
-    "signatureFamily": "Signature Family",
-    "externalApiCalls": "External Api Calls",
-    "providerOverridesDesc": "Provider Overrides Desc",
-    "signatureTool": "Signature Tool",
-    "connectionFailed": "Connection Failed",
-    "activeLimitersPlural": "Active Limiters Plural",
-    "doneDesc": "Done Desc",
-    "down": "Down",
-    "noDataYet": "No Data Yet",
-    "activeProviders": "Active Providers",
-    "nameInvalid": "Name Invalid",
-    "skip": "Skip",
-    "createChain": "Create Chain",
-    "audioSpeech": "Audio Speech",
-    "cacheCleared": "Cache Cleared",
-    "searchTypeNews": "Search Type News",
-    "durationMillisecondsShort": "Duration Milliseconds Short",
-    "addOpenAICompatible": "Add Open Ai Compatible",
-    "chatTesterTab": "Chat Tester",
-    "queued": "Queued",
-    "domainPlaceholder": "Domain Placeholder",
-    "durationMinutesShort": "Duration Minutes Short",
-    "verifyingConnection": "Verifying Connection",
-    "imageProviders": "Image Providers",
-    "protocolToolsLabel": "Protocol Tools Label",
-    "queryPlaceholder": "Query Placeholder",
-    "videoGeneration": "Video Generation",
-    "timeRangeWeek": "Time Range Week",
-    "limitExhausted": "Limit Exhausted",
-    "failedDisable": "Failed Disable",
-    "inMemoryNote": "In Memory Note",
-    "compatibleHint": "Compatible Hint",
-    "errorShort": "Error Short",
-    "advancedHint": "Advanced Hint",
-    "restoreFailed": "Restore Failed",
-    "searchProvidersHeading": "Search Providers Heading",
-    "comboName": "Combo Name",
-    "autoDisableDescription": "Auto Disable Description",
-    "embeddingsDesc": "Embeddings Desc",
-    "operational": "Operational",
-    "testAllApiKey": "Test All Api Key",
-    "backupCreated": "Backup Created",
-    "errorDuringImport": "Error During Import",
-    "comboDefaultsGuideHint2": "Combo Defaults Guide Hint2",
-    "connecting": "Connecting",
-    "fillModelAndProviders": "Fill Model And Providers",
-    "syncing": "Syncing",
-    "resetConfirm": "Reset Confirm",
-    "trackMetrics": "Track Metrics",
-    "successful": "Successful",
-    "recovering": "Recovering",
-    "autoDisableThreshold": "Auto Disable Threshold",
-    "anthropic": "Anthropic",
-    "syncingData": "Syncing Data",
-    "cloudBenefitPorts": "Cloud Benefit Ports",
-    "compatibleProviders": "Compatible Providers",
-    "freeTierProviders": "Penyedia Tingkat Gratis",
-    "freeTierLabel": "Tersedia tingkat gratis",
-    "freeTierProvidersDesc": "Penyedia dengan tingkatan gratis — beberapa memerlukan pendaftaran kunci API, yang lain tidak memerlukan kredensial sama sekali.",
-    "clearCache": "Clear Cache",
-    "reqs": "Reqs",
-    "addAnthropicCompatible": "Add Anthropic Compatible",
-    "apiKeyProviders": "Api Key Providers",
-    "tabsAria": "Tabs Aria",
-    "resetting": "Resetting",
-    "millisecondsAbbr": "Milliseconds Abbr",
-    "backupReasonPreRestore": "Backup Reason Pre Restore",
-    "disableCloud": "Disable Cloud",
-    "newProviderNameAria": "New Provider Name Aria",
-    "passwordsMismatch": "Passwords Mismatch",
-    "a2aQuickStartStep3": "A2A Quick Start Step3",
-    "liveMonitorDescriptionSuffix": "Live Monitor Description Suffix",
-    "failedAddProvider": "Failed Add Provider",
-    "addAtLeastOneProvider": "Add At Least One Provider",
-    "reasonSeparator": "Reason Separator",
-    "zedImporting": "Zed Importing",
-    "confirmPasswordPlaceholder": "Confirm Password Placeholder",
-    "whatYouGet": "What You Get",
-    "signatureSession": "Signature Session",
-    "errorCountNoCode": "Error Count No Code",
-    "testing": "Testing",
-    "providersCommaSeparated": "Providers Comma Separated",
-    "exportDatabase": "Export Database",
-    "hitRate": "Hit Rate",
-    "completionsLegacy": "Completions Legacy",
-    "removeModel": "Remove Model",
-    "timeRangeDay": "Time Range Day",
-    "cloudRequestFailed": "Cloud Request Failed",
-    "updatedAt": "Updated At",
-    "monitoredProvidersHint": "Monitored Providers Hint",
-    "connectionSuccessful": "Connection Successful",
-    "latencyP50": "Latency P50",
-    "logsDeleted": "Logs Deleted",
-    "chatTester": "Chat Tester",
-    "safeSearchOff": "Safe Search Off",
-    "nameHint": "Name Hint",
-    "debugToggle": "Debug Toggle",
-    "embedding": "Embedding",
-    "issuesLabel": "Issues Label",
-    "optionAny": "Option Any",
-    "maxNestingDepth": "Max Nesting Depth",
-    "rerank": "Rerank",
-    "checking": "Checking",
-    "getStarted": "Get Started",
-    "restoreSuccess": "Restore Success",
-    "issuesDetected": "Issues Detected",
-    "signatureCache": "Signature Cache",
-    "modelLockouts": "Model Lockouts",
-    "usingCloudProxy": "Using Cloud Proxy",
-    "loadingHealth": "Loading Health",
-    "providerOverrides": "Provider Overrides",
-    "audioTranscriptionDesc": "Audio Transcription Desc",
-    "learnedFromHeaders": "Learned From Headers",
-    "totalRequests": "Total Requests",
-    "cloudUnstableNote": "Cloud Unstable Note",
-    "gamificationAdmin": "Admin Gamifikasi",
-    "monitorAnomaliesAndHealth": "Pantau anomali dan kesehatan sistem",
-    "flaggedAnomalies": "Anomali yang Ditandai",
-    "noAnomaliesDetected": "Tidak ada anomali yang terdeteksi",
-    "apiKey": "Kunci API",
-    "xpLastHour": "XP (1 jam)",
-    "zScore": "Skor-Z",
-    "suspicious": "__MISSING__:Suspicious",
-    "tokensCommunityServers": "Server Komunitas",
-    "tokensServerNamePlaceholder": "Nama server",
-    "tokensApiKeyPlaceholder": "Kunci API",
-    "tokensTokenBalance": "Saldo Token",
-    "tokensSendTokens": "Kirim Token",
-    "tokensRecipientApiKeyId": "ID Kunci API Penerima",
-    "tokensRecipientApiKeyIdPlaceholder": "Masukkan ID kunci API penerima",
-    "tokensReasonOptional": "Alasan (opsional)",
-    "tokensReasonPlaceholder": "misalnya bonus, hadiah",
-    "tokensTransactionHistory": "Riwayat Transaksi",
-    "tokensNoTransactionsYet": "Belum ada transaksi",
-    "tokensInviteCodes": "Kode Undangan",
-    "tokensMaxUses": "Penggunaan Maks",
-    "tokensRedeemCode": "Tukarkan Kode",
-    "tokensRedeemCodePlaceholder": "Masukkan kode undangan",
-    "tokensYourActiveInvites": "Undangan Aktif Anda",
-    "tokensTransferSuccess": "Transfer berhasil ({idempotencyKey})",
-    "tokensTransferFailed": "Transfer gagal",
-    "tokensCreateInviteFailed": "Gagal membuat undangan",
-    "tokensRevokeInviteFailed": "Gagal membatalkan undangan",
-    "tokensRedeemSuccess": "Undangan ditukarkan. Server: {server}",
-    "tokensRedeemFailed": "Gagal menukarkan undangan",
-    "tokensConnectServerFailed": "Gagal menghubungkan server",
-    "tokensDisconnectServerFailed": "Gagal memutuskan sambungan server",
-    "tokensAmount": "Jumlah",
-    "tokensSending": "Mengirim...",
-    "tokensFrom": "Dari",
-    "tokensTo": "Ke",
-    "tokensReason": "Alasan",
-    "tokensDate": "Tanggal",
-    "tokensSent": "Terkirim",
-    "tokensReceived": "Diterima",
-    "tokensCreatingInvite": "Membuat...",
-    "tokensCreateInvite": "Buat Undangan",
-    "tokensInviteCreated": "Kode undangan dibuat",
-    "tokensRedeeming": "Menukarkan...",
-    "tokensRedeem": "Tukarkan",
-    "tokensInviteUses": "{used}/{max} penggunaan",
-    "tokensRevoked": "DICABUT",
-    "tokensRevoke": "Cabut",
-    "tokensConnecting": "Menghubungkan...",
-    "tokensConnectServer": "Hubungkan Server",
-    "tokensNoServersConnected": "Tidak ada server yang terhubung. Hubungkan ke server komunitas untuk membagikan papan peringkat.",
-    "tokensServerStatus": {
-      "connected": "Terhubung",
-      "disconnected": "Terputus",
-      "pending": "Tertunda",
-      "syncing": "Menyinkronkan",
-      "error": "Kesalahan"
-    },
-    "tokensLastSync": "Sinkronisasi terakhir: {date}",
-    "tokensDisconnect": "Putuskan Sambungan",
-    "tierCoverageTitle": "Cakupan tingkat",
-    "tierCoverageSubtitle": "Penyedia dikonfigurasi per tingkat cadangan",
-    "batchDetailCopyId": "Salin ID",
-    "batchDetailClose": "Tutup",
-    "batchDetailEndpoint": "Titik akhir",
-    "batchDetailModel": "Model",
-    "batchDetailWindow": "Jendela",
-    "batchDetailCreated": "Dibuat",
-    "providerTopologyEmpty": "Belum ada penyedia yang terhubung",
-    "badgeToastUnlocked": "Lencana Tidak Terkunci!",
-    "batchListSearchPlaceholder": "Telusuri berdasarkan ID, titik akhir, model…",
-    "batchListDeleteAllCompletedTitle": "Hapus semua batch yang sudah selesai",
-    "batchListBatchesTable": "kumpulan",
-    "changelogViewerLoading": "Memuat log perubahan dari GitHub...",
-    "profile": "__MISSING__:Profile",
-    "profileLoading": "Memuat profil...",
-    "profileHowToEarn": "Bagaimana cara mendapatkan penghasilan",
-    "bootstrapBannerDismiss": "Singkirkan",
-    "batchListDeleteBatchTitle": "Hapus batch dan file-filenya",
-    "leaderboardYourRank": "Peringkat Anda",
-    "leaderboardLoading": "Memuat papan peringkat...",
-    "batchFileDetailCopyId": "Salin ID",
-    "batchFileDetailClose": "Tutup",
-    "batchFileDetailFailedToLoad": "Gagal memuat konten file",
-    "batchFileDetailLoadError": "Kesalahan saat memuat konten berkas",
-    "batchFilesListSearchPlaceholder": "Cari berdasarkan ID atau nama file…",
-    "batchFilesListFilesTable": "File",
-    "batchFilesCount": "{count, plural, one {# berkas} other {# berkas}}",
-    "batchFilesAllPurposes": "Semua tujuan",
-    "batchFilesFilename": "Nama berkas",
-    "batchFilesPurpose": "Tujuan",
-    "batchFilesExpires": "Kedaluwarsa",
-    "batchFilesNoneFound": "Berkas tidak ditemukan",
-    "batchFilesNeverExpires": "Tidak pernah",
-    "batchFileInUseByActiveBatch": "Berkas sedang digunakan oleh batch aktif",
-    "batchFilePurpose": {
-      "batch": "Input batch",
-      "batch-output": "Output batch",
-      "fine-tune": "Fine-tuning",
-      "assistants": "Asisten"
-    },
-    "batchPageLoadingMore": "Memuat lebih banyak…",
-    "recommended": "Direkomendasikan",
-    "understand": "Saya mengerti",
-    "batchConceptTitle": "Batch processing",
-    "batchConceptSubtitle": "Process thousands of requests asynchronously at ~50% of the cost (24h window). Ideal for evaluations, classification, and embeddings.",
-    "batchConceptHowItWorks": "How it works",
-    "batchConceptBenefit50pct": "50% discount on input + output tokens",
-    "batchConceptAsync24h": "Async with a 24h completion window",
-    "batchConceptUseCases": "Best for bulk classification, evaluations, and embeddings",
-    "batchHeaderSubtitle": "Run many requests as one job",
-    "batchStep1": "1 · Upload JSONL",
-    "batchStep1Desc": "Add requests",
-    "batchStep2": "2 · Create batch",
-    "batchStep2Desc": "Run job",
-    "batchStep3": "3 · Get results",
-    "batchStep3Desc": "Download output",
-    "filesConceptTitle": "Batch files",
-    "filesConceptSubtitle": "JSONL files used by batches: input requests, results, and errors.",
-    "filesConceptInput": "Input — your JSONL with one request per line",
-    "filesConceptOutput": "Output — results from completed requests",
-    "filesConceptError": "Errors — requests that failed",
-    "filesConceptRetention": "Retention: 30 days by default (29 days on Anthropic)",
-    "wizardTitle": "New batch",
-    "wizardClose": "Close",
-    "wizardNext": "Next",
-    "wizardBack": "Back",
-    "wizardCancel": "Cancel",
-    "wizardCreate": "Create batch",
-    "wizardCreating": "Creating…",
-    "wizardStep1Destination": "Destination",
-    "wizardStep2Input": "Input",
-    "wizardStep3Validate": "Validate",
-    "wizardStep4Cost": "Cost & create",
-    "wizardProviderLabel": "Provider",
-    "wizardEndpointLabel": "Endpoint",
-    "wizardModelLabel": "Model",
-    "wizardInputKindJsonl": "JSONL",
-    "wizardInputKindCsv": "CSV (we'll convert)",
-    "wizardDropOrPick": "Drop a file or click to pick",
-    "wizardCsvMappingTitle": "Map CSV columns → request fields",
-    "wizardCsvMappingAddField": "Add field",
-    "wizardCsvNoColumns": "Tidak ada kolom yang terdeteksi di header CSV.",
-    "wizardCsvIgnoreColumn": "— abaikan —",
-    "wizardCsvCustomIdMapped": "custom_id dipetakan",
-    "wizardCsvContentMapped": "Kolom konten dipetakan (messages, input, atau prompt)",
-    "wizardCsvApplyMapping": "Terapkan pemetaan",
-    "wizardCsvRowsParsed": "{count} baris diurai",
-    "wizardCsvRowsSkipped": "{count} baris dilewati",
-    "wizardCsvRowError": "Baris {row}: {reason}",
-    "wizardValidationOk": "All lines valid",
-    "wizardValidating": "Memvalidasi…",
-    "wizardValidationParseFailed": "Validasi gagal — tidak dapat mengurai konten.",
-    "wizardValidationSummary": "{lines} baris · {ids} custom_ids unik",
-    "wizardValidationErrorCount": "{count, plural, one {# galat} other {# galat}} ditemukan",
-    "wizardValidationDuplicateIds": "Duplikat custom_ids terdeteksi:",
-    "wizardValidationFirstErrors": "Galat ({count} pertama):",
-    "wizardValidationLine": "Baris {line}",
-    "wizardValidationErrors": "Validation errors",
-    "wizardValidationPreview": "Preview (first 5 requests)",
-    "wizardValidationSamplingNote": "File is large — validated by sampling (first 1000 + last 100 lines). Full validation runs server-side.",
-    "wizardCostSync": "Sync cost",
-    "wizardCostBatch": "Batch cost (-50%)",
-    "wizardCostSavings": "Savings",
-    "wizardCostEstimatedNotice": "Estimated cost — real billing may vary.",
-    "wizardErrorUpload": "Failed to upload file. Try again.",
-    "wizardErrorCreate": "Failed to create batch. Try again.",
-    "wizardEmptyProviders": "Connect a provider with batch support (OpenAI, Anthropic, or Gemini) to create a batch.",
-    "uploadModalTitle": "Upload batch file",
-    "uploadModalDropOrPick": "Drop a .jsonl file or click to pick",
-    "uploadModalUpload": "Upload",
-    "uploadModalCancel": "Cancel",
-    "uploadModalError": "Upload failed. Try again.",
-    "uploadModalSuccess": "Uploaded",
-    "uploadModalSizeLimit": "Max 512 MB",
-    "batchListNewButton": "New batch",
-    "batchListAutoRefresh": "Auto-refresh 30s",
-    "batchListCostColumn": "Cost",
-    "batchActionCancel": "Cancel",
-    "batchActionDownloadOutput": "Download output",
-    "batchActionDownloadErrors": "Download errors",
-    "batchActionRetry": "Retry failed",
-    "batchActionRetryConfirm": "Retry {n} failed request(s)? Final cost depends on actual tokens consumed.",
-    "expirationBadgeCritical": "Critical",
-    "expirationBadgeWarning": "Soon",
-    "expirationBadgeNormal": "Pending",
-    "expirationBadgeExpired": "Expired",
-    "filesListUploadButton": "Upload",
-    "filesListUsedByColumn": "Used by",
-    "filesListUsedByNone": "None",
-    "filesListUsedByRoleInput": "input",
-    "filesListUsedByRoleOutput": "output",
-    "filesListUsedByRoleError": "error",
-    "filesListSizeColumn": "Size",
-    "batchListProgressPartial": "(partial)",
-    "batchListProviderColumn": "Provider",
-    "batchListProviderUnknown": "—",
-    "batchListProviderOther": "Other",
-    "batchListTitle": "Batches",
-    "batchListCount": "{count} batches",
-    "batchListRemovingCompleted": "Removing…",
-    "batchListRemoveCompleted": "Remove completed",
-    "batchListTableStatus": "Status",
-    "batchListTableId": "ID",
-    "batchListTableEndpoint": "Endpoint",
-    "batchListTableModel": "Model",
-    "batchListTableProgress": "Progress",
-    "batchListTableCreated": "Created",
-    "batchListTableExpires": "Expires",
-    "batchListLoading": "Loading…",
-    "batchListEmpty": "No batches found",
-    "batchListValidating": "Validating…",
-    "batchStatusAll": "All statuses",
-    "batchStatusInProgress": "In progress",
-    "batchStatusValidating": "Validating",
-    "batchStatusFinalizing": "Finalizing",
-    "batchStatusCompleted": "Completed",
-    "batchStatusFailed": "Failed",
-    "batchStatusCancelled": "Cancelled",
-    "batchStatusCancelling": "Cancelling",
-    "batchStatusExpired": "Expired",
-    "batchStatusCompletedWithFailures": "completed with failures",
-    "batchStatusInProgressWithFailures": "in progress (with failures)",
-    "batchStatusFinalizingWithFailures": "finalizing (with failures)",
-    "batchStatusCancelledWithFailures": "cancelled with failures",
-    "batchStatusExpiredWithFailures": "expired (partial)",
-    "wizardCostEstimating": "Estimating cost…",
-    "wizardCostRequests": "Requests",
-    "wizardCostInputTok": "input tok",
-    "wizardCostOutputTok": "output tok",
-    "wizardCostWindow": "Window",
-    "wizardDestinationSelectProvider": "Select a provider…",
-    "wizardDestinationSelectModel": "Select a model…",
-    "wizardDestinationConnectProvider": "Connect a provider",
-    "batchListBatchCreated": "Batch {id} created — refreshing list…",
-    "batchListBatchCreatedDismiss": "Dismiss",
-    "batchListRefreshing": "Refreshing…",
-    "batchListRefresh": "Refresh",
-    "uploadFileModalRemove": "Remove",
-    "uploadFileModalUploading": "Uploading…",
-    "wizardInputReading": "Reading file…",
-    "wizardInputReady": "Ready",
-    "wizardInputLargeFileLabel": "Large file — sampling validation",
-    "wizardInputCsvJsonlReady": "JSONL generated — ready to validate.",
-    "wizardInputLargeFileWarning": "Large file detected — validation runs by sampling (first 5 MB + last 100 KB). Full validation happens server-side.",
-    "wizardCostWindow24h": "24h completion window",
-    "wizardValidationFieldsOk": "required fields valid",
-    "filesListDelete": "Delete",
-    "filesListDownload": "Download",
-    "batchDetailActionCancel": "Cancel batch",
-    "batchDetailActionRetry": "Retry failed requests",
-    "batchDetailCancelling": "Cancelling…",
-    "batchDetailRetrying": "Preparing retry…",
-    "batchDetailCancelConfirm": "Cancel this batch? In-progress requests will stop.",
-    "batchActionCancelError": "Failed to cancel batch. Try again.",
-    "batchActionRetryError": "Failed to retry failed requests. Try again.",
-    "batchConceptRetentionNote": "Results and error files are retained for 30 days (Anthropic: 29 days)",
-    "batchFilesSizeColumn": "Ukuran",
-    "toggleNoAuthProvider": "Alihkan penyedia tanpa otentikasi",
-    "loadingModels": "Memuat model…",
-    "selectAModel": "Pilih model",
-    "degraded": "Menurun",
-    "zeroConfigBannerTitle": "Berjalan dalam mode tanpa konfigurasi",
-    "zeroConfigBannerBody": "OmniRoute secara otomatis menghasilkan kunci enkripsi aman pada peluncuran pertama. Kunci tersebut disimpan di <code>{dataDir}</code>. Tidak ada tindakan yang diperlukan — data Anda terenkripsi dan aman. Untuk menggunakan kunci kustom, tambahkan <code>JWT_SECRET</code> dan <code>STORAGE_ENCRYPTION_KEY</code> ke file tersebut.",
-    "batchRelativeTimeIn": "dalam {value}",
-    "batchRelativeTimeAgo": "{value} yang lalu",
-    "batchDetailsTitle": "Detail Batch",
-    "batchProgress": "Kemajuan",
-    "batchCompletedCount": "{count} selesai",
-    "batchFailedCount": "{count} gagal",
-    "batchPendingCount": "{count} tertunda",
-    "batchTimeline": "Garis Waktu",
-    "batchTimelineInProgress": "Dalam Proses",
-    "batchTimelineFinalizing": "Menyelesaikan",
-    "batchTimelineCompleted": "Selesai",
-    "batchTimelineFailed": "Gagal",
-    "batchTimelineExpires": "Kedaluwarsa",
-    "batchTimelineExpired": "Kedaluwarsa",
-    "batchTimelineCancelling": "Membatalkan",
-    "batchTimelineCancelled": "Dibatalkan",
-    "batchTokenUsage": "Penggunaan Token",
-    "batchMetadata": "Metadata",
-    "batchFileContents": "Isi Berkas",
-    "batchFileUsedByCount": "Digunakan oleh {count, plural, one {# batch} other {# batches}}",
-    "batchFilePreview": "Prabaca",
-    "batchFilePreviewTruncated": "Menampilkan {shown} baris pertama ({total} total baris)",
-    "batchFileDownloadFull": "Unduh File Lengkap"
-  },
-  "disabled": "Dinonaktifkan",
-  "featureFlagOmnirouteEmergencyFallbackDescription": "Rute permintaan yang kehabisan anggaran ke penyedia/model cadangan gratis darurat.",
-  "featureFlagArenaEloSyncEnabledDescription": "Aktifkan sinkronisasi ELO papan peringkat Arena AI berkala untuk peringkat kecerdasan model.",
-  "featureFlagUniversalContextHandoffEnabledDescription": "__MISSING__:Generate and inject conversation summaries when combo routing switches models. Disable to treat model switches independently and prevent background handoff requests for all existing and future combos.",
-  "featureFlagExposeCcDiscoveryAliasesDescription": "Iklankan claude/&lt;provider&gt;/&lt;model&gt; mirror ids di /v1/models sehingga daftar penemuan model gateway Claude Code mencantumkan model non-Claude. Peringatan: menggandakan entri katalog untuk semua klien saat diaktifkan secara global.",
-  "featureFlagNoThinkingAliasEnabledDescription": "__MISSING__:Master switch for the no-think/&lt;provider&gt;/&lt;model&gt; gateway aliases. On (default): /v1/models advertises a no-thinking variant for every eligible thinking-capable Claude model, and a no-think/ id sent on a request resolves back to the real model with reasoning suppressed. Off: no variants are advertised and a no-think/ id is treated like any other unknown model id. The per-model ModelSpec.noThinkingAlias opt-in/opt-out still applies while this is on.",
-  "featureFlagChatVirtualLanesEnabledDescription": "Aktifkan jalur penerimaan virtual adaptif per-tenant untuk pengiriman penyedia (#9654): lonjakan satu tenant tidak lagi mengembalikan 503 ke tenant lain. Variabel lingkungan OMNIROUTE_CHAT_VIRTUAL_LANES menang atas pengaturan dasbor ini; perubahan berlaku setelah server dimulai ulang.",
-  "sidebar": {
-    "home": "Home",
-    "dashboard": "Dashboard",
-    "providers": "Providers",
-    "combos": "Combos",
-    "usage": "Usage",
-    "analytics": "Analytics",
-    "costs": "Costs",
-    "health": "Health",
-    "proxy": "Proksi",
-    "limits": "Limits & Quotas",
-    "cliTools": "CLI Tools",
-    "media": "Media",
-    "settings": "Settings",
-    "translator": "Translator",
-    "playground": "Playground",
-    "searchTools": "Search Tools",
-    "agents": "Agents",
-    "cloudAgents": "Agen Awan",
-    "memory": "Memory",
-    "skills": "Skills",
-    "omniSkills": "Keahlian Omni",
-    "agentSkills": "Keterampilan Agen",
-    "chaosConfig": "Chaos Mode",
-    "docs": "Docs",
-    "issues": "Issues",
-    "endpoints": "Endpoints",
-    "endpointsSubtitle": "URL koneksi AI Anda",
-    "apiManager": "API Keys",
-    "apiManagerSubtitle": "Kelola kunci dan akses API",
-    "embeddedServices": "Layanan Tertanam",
-    "embeddedServicesSubtitle": "Kelola layanan proxy lokal",
-    "logs": "Logs",
-    "webhooks": "Webhook",
-    "webhooksSubtitle": "Dapatkan pemberitahuan tentang acara",
-    "logExport": "Ekspor log",
-    "logExportSubtitle": "Kirim log panggilan ke luar",
-    "combosSubtitle": "Penyedia grup untuk failover",
-    "batchSubtitle": "Proses beberapa permintaan",
-    "contextCavemanSubtitle": "Kompresi yang cepat",
-    "contextRtkSubtitle": "Pemfilteran keluaran",
-    "auditLog": "Audit Log",
-    "shutdown": "Shutdown",
-    "restart": "Restart",
-    "shutdownConfirm": "Shut down OmniRoute?",
-    "restartConfirm": "Restart OmniRoute?",
-    "version": "v{version}",
-    "debug": "Debug",
-    "system": "System",
-    "help": "Help",
-    "primarySection": "Main",
-    "cliSection": "CLI",
-    "debugSection": "Debug",
-    "systemSection": "System",
-    "helpSection": "Help",
-    "serverDisconnected": "Server Disconnected",
-    "serverDisconnectedMsg": "The proxy server has been stopped or is restarting.",
-    "expandSidebar": "Expand sidebar",
-    "collapseSidebar": "Collapse sidebar",
-    "themes": "Themes",
-    "presetColors": "Popular colors",
-    "createTheme": "Create theme",
-    "chooseColor": "Pick one color",
-    "themeCoral": "Coral",
-    "themeBlue": "Blue",
-    "themeRed": "Red",
-    "themeGreen": "Green",
-    "themeViolet": "Violet",
-    "themeOrange": "Orange",
-    "themeCyan": "Cyan",
-    "cliToolsShort": "Tools",
-    "cache": "Cache",
-    "cacheShort": "Cache",
-    "batch": "Batch Testing",
-    "themeSystem": "Theme System",
-    "whitelabelingDesc": "Whitelabeling Desc",
-    "switchThemes": "Switch Themes",
-    "themeAccentDesc": "Theme Accent Desc",
-    "uploadFavicon": "Upload Favicon",
-    "themeDark": "Theme Dark",
-    "customLogoDesc": "Custom Logo Desc",
-    "sidebarVisibilityToggle": "Sidebar Visibility Toggle",
-    "themeAccent": "Theme Accent",
-    "resetFavicon": "Reset Favicon",
-    "whitelabeling": "Whitelabeling",
-    "darkMode": "Dark Mode",
-    "uploadLogo": "Upload Logo",
-    "themeLight": "Theme Light",
-    "appName": "App Name",
-    "appNameDesc": "App Name Desc",
-    "resetLogo": "Reset Logo",
-    "customFavicon": "Custom Favicon",
-    "hideHealthLogs": "Hide Health Logs",
-    "customLogo": "Custom Logo",
-    "appearance": "Appearance",
-    "themeSelectionAria": "Theme Selection Aria",
-    "themeCreate": "Theme Create",
-    "customFaviconDesc": "Custom Favicon Desc",
-    "logoPreview": "Logo Preview",
-    "themeCustom": "Theme Custom",
-    "hideHealthLogsDesc": "Hide Health Logs Desc",
-    "faviconPreview": "Favicon Preview",
-    "changelog": "Changelog",
-    "contextSection": "Context & Cache",
-    "contextCaveman": "Caveman",
-    "contextRtk": "RTK",
-    "contextCombos": "Engine Combos",
-    "contextLite": "Lite",
-    "contextAggressive": "Aggressive",
-    "contextUltra": "Ultra",
-    "contextOmniglyph": "OmniGlyph",
-    "contextSettings": "Compression Settings",
-    "contextHeadroom": "Headroom",
-    "contextSessionDedup": "Session Dedup",
-    "contextCcr": "CCR",
-    "contextLlmlingua": "LLMLingua",
-    "combosLive": "Combo Studio",
-    "combosLiveSubtitle": "Kaskade perutean langsung",
-    "compressionStudio": "Compression Studio",
-    "compressionExclusions": "Pengecualian",
-    "contextSettingsSubtitle": "Bawaan global",
-    "contextHeadroomSubtitle": "Pemadatan tabular",
-    "contextSessionDedupSubtitle": "Deduplikasi lintas-giliran",
-    "contextCcrSubtitle": "Ambil penanda",
-    "contextLlmlinguaSubtitle": "Pemangkasan semantik",
-    "contextLiteSubtitle": "Pembersihan spasi putih cepat",
-    "contextAggressiveSubtitle": "Ringkasan dan penuaan",
-    "contextUltraSubtitle": "Pemangkasan heuristik",
-    "contextOmniglyphSubtitle": "Konteks sebagai gambar",
-    "compressionStudioSubtitle": "Kaskade mesin langsung",
-    "compressionExclusionsSubtitle": "Per-model/endpoint bypass",
-    "chaosConfigSubtitle": "Eksekusi paralel multi-model",
-    "routingSection": "Routing",
-    "protocolsSection": "Protocols",
-    "agentsAiSection": "Agents & AI",
-    "cacheContextSection": "Cache & Context",
-    "analyticsSection": "Analytics",
-    "costsSection": "Costs",
-    "monitoringSection": "Monitoring",
-    "auditSecuritySection": "Audit & Security",
-    "devtoolsSection": "Dev Tools",
-    "configurationSection": "Configuration",
-    "aiFeaturesSection": "AI Features",
-    "mcp": "MCP",
-    "a2a": "A2A",
-    "plugins": "Pengaya",
-    "apiEndpoints": "API Endpoints",
-    "batchFiles": "Files",
-    "analyticsEvals": "Evals",
-    "analyticsSearch": "Search",
-    "analyticsUtilization": "Utilization",
-    "analyticsComboHealth": "Combo Health",
-    "analyticsCompression": "Compression",
-    "costsBudget": "Budget",
-    "costsFreeTiers": "Anggaran Tingkat Gratis",
-    "costsFreeTiersSubtitle": "Jatah token gratis bulanan",
-    "freeProviderRankings": "Peringkat Penyedia Gratis",
-    "freeProviderRankingsSubtitle": "Penyedia gratis terbaik yang diurutkan berdasarkan skor ELO model",
-    "radar": "रडार कैटलॉग",
-    "radarSubtitle": "समुदाय-समृद्ध मुफ्त मॉडल कैटलॉग",
-    "costsQuotaShare": "Quota Sharing",
-    "costsPricing": "Pricing",
-    "logsProxy": "Proxy Logs",
-    "logsConsole": "Console",
-    "logsActivity": "Activity",
-    "auditMcp": "MCP Audit",
-    "auditA2a": "Audit A2A",
-    "settingsGeneral": "General",
-    "settingsAppearance": "Appearance",
-    "settingsAi": "AI Settings",
-    "settingsSecurity": "Security",
-    "settingsAccessTokens": "Token Akses",
-    "settingsFeatureFlags": "Bendera Fitur",
-    "settingsCache": "Cache",
-    "settingsAuthz": "Authz",
-    "settingsRouting": "Routing",
-    "settingsResilience": "Resilience",
-    "modelLockout": "Penguncian Model",
-    "settingsAdvanced": "Advanced",
-    "omniProxySection": "OmniProxy",
-    "quotaTracker": "Provider Quota",
-    "providerQuota": "Provider Quota",
-    "runtime": "Runtime",
-    "consoleLogs": "Console Logs",
-    "logsTimeline": "Timeline",
-    "logsTimelineSubtitle": "Garis Waktu Permintaan Visual",
-    "conversations": "Conversations",
-    "conversationsSubtitle": "Multi-turn agentic conversations",
-    "globalRouting": "Global Routing",
-    "mitmProxy": "MITM Proxy",
-    "oneProxy": "1Proxy",
-    "agenticFeaturesSection": "Agentic Features",
-    "otherFeaturesSection": "Other Features",
-    "compressionContextGroup": "Compression Context",
-    "gamificationGroup": "Gamification",
-    "toolsGroup": "Tools",
-    "integrationsGroup": "Integrations",
-    "proxyGroup": "Proxy",
-    "costsParametersGroup": "Costs Parameters",
-    "auditGroup": "Audit",
-    "batchGroup": "Batch",
-    "homeSubtitle": "Dashboard overview",
-    "providersSubtitle": "Manage AI providers",
-    "quotaTrackerSubtitle": "Track usage limits",
-    "providerQuotaSubtitle": "Track provider usage limits",
-    "runtimeSubtitle": "Realtime resilience & sessions",
-    "contextCombosSubtitle": "Combine compression engines",
-    "cliToolsSubtitle": "Configure CLI runtimes",
-    "agentsSubtitle": "Manage local agents",
-    "cloudAgentsSubtitle": "Manage cloud-based agents",
-    "apiEndpointsSubtitle": "Expose custom endpoints",
-    "proxySubtitle": "HTTP proxy settings",
-    "mitmProxySubtitle": "MITM interception",
-    "oneProxySubtitle": "Public proxy gateway",
-    "leaderboard": "Leaderboard",
-    "profile": "Profile",
-    "tokens": "Tokens",
-    "gamificationAdmin": "__MISSING__:Gamification Admin",
-    "leaderboardSubtitle": "Rankings and achievements",
-    "profileSubtitle": "Account and preferences",
-    "tokensSubtitle": "Token usage and budgets",
-    "gamificationAdminSubtitle": "__MISSING__:Anomaly monitoring and anti-cheat",
-    "usageSubtitle": "Traffic and usage stats",
-    "analyticsComboHealthSubtitle": "Combo target reliability",
-    "analyticsUtilizationSubtitle": "Provider utilization",
-    "costsSubtitle": "Spend breakdown",
-    "cacheSubtitle": "Cache hit rates",
-    "analyticsCompressionSubtitle": "Token savings stats",
-    "analyticsSearchSubtitle": "Search tool analytics",
-    "analyticsEvalsSubtitle": "Eval suite results",
-    "providerStats": "Statistik Penyedia",
-    "providerStatsSubtitle": "Metrik latensi dan performa",
-    "logsSubtitle": "Application logs",
-    "logsProxySubtitle": "Proxy traffic logs",
-    "consoleLogsSubtitle": "Console output",
-    "logsActivitySubtitle": "User activity log",
-    "healthSubtitle": "System health check",
-    "costsPricingSubtitle": "Per-model pricing rules",
-    "costsBudgetSubtitle": "Budget limits",
-    "costsQuotaShareSubtitle": "Share provider quotas across keys",
-    "auditLogSubtitle": "Authorization audit",
-    "auditMcpSubtitle": "MCP server audit",
-    "auditA2aSubtitle": "A2A protocol audit",
-    "translatorSubtitle": "Format conversion",
-    "playgroundSubtitle": "Test prompts live",
-    "searchToolsSubtitle": "Search tool registry",
-    "memorySubtitle": "Persistent agent memory",
-    "omniSkillsSubtitle": "Sandbox skill registry",
-    "agentSkillsSubtitle": "A2A skill registry",
-    "mcpSubtitle": "MCP server controls",
-    "a2aSubtitle": "A2A protocol server",
-    "pluginsSubtitle": "Pasar & instalasi pengaya",
-    "mediaSubtitle": "Cached media files",
-    "batchFilesSubtitle": "Batch input/output files",
-    "settingsSubtitle": "All settings",
-    "settingsGeneralSubtitle": "App basics",
-    "settingsAppearanceSubtitle": "Theme and layout",
-    "settingsAiSubtitle": "AI behavior defaults",
-    "globalRoutingSubtitle": "Global routing rules",
-    "settingsResilienceSubtitle": "Retries and breakers",
-    "settingsAdvancedSubtitle": "Power user options",
-    "settingsSecuritySubtitle": "Auth and encryption",
-    "settingsAccessTokensSubtitle": "Token CLI bercakupan untuk mode jarak jauh",
-    "settingsFeatureFlagsSubtitle": "Alihkan kemampuan sistem",
-    "settingsCacheSubtitle": "Katalog Model dan Cache Respons",
-    "settingsSidebar": "Sidebar",
-    "settingsSidebarSubtitle": "Customize sidebar layout",
-    "settingsAuthzSubtitle": "Inventaris rute dan kebijakan pintasan",
-    "docsSubtitle": "Documentation",
-    "issuesSubtitle": "Report a bug",
-    "changelogSubtitle": "Release notes",
-    "costsQuotaPlans": "Paket & Kuota",
-    "costsQuotaPlansSubtitle": "Konfigurasikan paket berdasarkan penyedia",
-    "activity": "Aktivitas",
-    "activitySubtitle": "Umpan ramah dari peristiwa terbaru",
-    "logsGroup": "Log",
-    "systemGroup": "Sistem",
-    "costsOverview": "Ikhtisar",
-    "costsOverviewSubtitle": "Analisis biaya terkonsolidasi",
-    "agentBridge": "Agent Bridge",
-    "agentBridgeSubtitle": "Cegat lalu lintas agen IDE",
-    "trafficInspector": "Pemeriksa Lalu Lintas",
-    "trafficInspectorSubtitle": "__MISSING__:Inspect request and response traffic from your apps",
-    "trafficInspectorPurpose": "See exactly what your application sends to and receives from AI providers. Works with any OpenAI-compatible client.",
-    "cliCode": "Kode CLI",
-    "cliCodeSubtitle": "Alat kode yang mengarah ke OmniRoute",
-    "cliAgents": "Agen CLI",
-    "cliAgentsSubtitle": "Agen CLI otonom",
-    "acpAgents": "Agen ACP",
-    "acpAgentsSubtitle": "CLI yang dipicu oleh OmniRoute",
-    "skipToContent": "Lompati ke konten",
-    "mainNavigation": "Navigasi utama",
-    "unpinSection": "Lepas pin bagian",
-    "pinSectionOpen": "Sematkan bagian agar tetap terbuka",
-    "reloadPage": "Muat Ulang Halaman",
-    "dragReorderSection": "Seret untuk menyusun ulang bagian",
-    "dragReorderItem": "Seret untuk menyusun ulang",
-    "cannotHide": "Item ini tidak dapat disembunyikan",
-    "alwaysVisible": "Selalu terlihat",
-    "groupSeparatorLabel": "Pemisah",
-    "discovery": "Penemuan",
-    "discoverySubtitle": "Pindai penyedia untuk akses gratis",
-    "conductor": "Konduktor",
-    "conductorSubtitle": "Armada CLI-agent",
-    "orchestration": "Orkestrasi",
-    "orchestrationSubtitle": "Tampilan langsung dari semua yang sedang berjalan",
-    "resilienceConnections": "Resiliensi Koneksi",
-    "resilienceConnectionsSubtitle": "Cooldown, breaker, status penguncian",
-    "settingsModalityBridge": "Jembatan Modalitas",
-    "settingsModalityBridgeSubtitle": "Fallback teks untuk model hanya teks dari gambar/audio",
-    "commandPalette": {
-      "title": "Palet Perintah",
-      "searchPlaceholder": "Cari halaman, pengaturan, alat...",
-      "clearSearch": "Bersihkan pencarian",
-      "noResults": "Tidak ada hasil",
-      "navigate": "navigasi",
-      "open": "buka",
-      "close": "tutup"
-    },
-    "noResults": "Tidak ada hasil"
-  },
-  "webhooks": {
-    "title": "Webhook",
-    "description": "Konfigurasikan panggilan balik HTTP untuk kejadian sistem.",
-    "configuredWebhooks": "Webhook yang Dikonfigurasi",
-    "configuredWebhooksDesc": "Kelola titik akhir pengiriman, acara berlangganan, status, dan pengiriman pengujian.",
-    "addWebhook": "Tambahkan Webhook",
-    "editWebhook": "Sunting Webhook",
-    "name": "Nama",
-    "namePlaceholder": "Pemantauan produksi",
-    "unnamedWebhook": "Webhook tanpa nama",
-    "url": "URL titik akhir",
-    "events": "Acara",
-    "allEvents": "Semua acara",
-    "secret": "Rahasia",
-    "secretPlaceholder": "Biarkan kosong untuk membuat rahasia secara otomatis",
-    "secretEditPlaceholder": "Biarkan kosong untuk menjaga rahasia saat ini",
-    "status": "Status",
-    "active": "Aktif",
-    "inactive": "Tidak aktif",
-    "errored": "Salah",
-    "total": "Jumlah",
-    "lastTriggered": "Terakhir Dipicu",
-    "actions": "Tindakan",
-    "enabled": "Diaktifkan",
-    "enabledDesc": "Webhook yang dinonaktifkan tetap disimpan tetapi tidak menerima pengiriman.",
-    "refresh": "Segarkan",
-    "loading": "Memuat webhook...",
-    "never": "Tidak pernah",
-    "failureCount": "{count, plural, =0 {no failures} one {# failure} other {# failures}}",
-    "testWebhook": "Kirim Tes",
-    "testSuccess": "Uji webhook berhasil dikirim.",
-    "testFailed": "Pengujian webhook gagal.",
-    "saveSuccess": "Webhook berhasil disimpan.",
-    "saveFailed": "Gagal menyimpan webhook.",
-    "loadFailed": "Gagal memuat webhook.",
-    "delete": "Hapus",
-    "deleteConfirm": "Apakah Anda yakin ingin menghapus webhook ini?",
-    "deleteSuccess": "Webhook berhasil dihapus.",
-    "deleteFailed": "Gagal menghapus webhook.",
-    "edit": "Sunting",
-    "enable": "Aktifkan",
-    "disable": "Nonaktifkan",
-    "noWebhooks": "Belum ada webhook yang dikonfigurasi.",
-    "signatureTitle": "Tanda Tangan Webhook",
-    "signatureDescription": "Setiap pengiriman menyertakan header X-Webhook-Signature yang ditandatangani dengan HMAC-SHA256 menggunakan rahasia webhook. Verifikasi tanda tangan sebelum mempercayai payload.",
-    "wizard": {
-      "cancel": "Batal",
-      "step1Title": "Pilih Integrasi",
-      "step2Title": "Konfigurasikan Target",
-      "step3Title": "Peristiwa & Pengujian",
-      "back": "Kembali",
-      "next": "Berikutnya",
-      "finish": "Selesai",
-      "step1Desc": "Pilih sistem integrasi target untuk webhook ini."
-    },
-    "howItWorks": {
-      "step1": "Pilih penyedia integrasi (mis. Slack, Discord, webhook kustom) dan atur detail koneksi.",
-      "step2": "Konfigurasikan peristiwa sistem untuk berlangganan (mis. kesalahan penyelesaian, fallback model, atau batas penggunaan).",
-      "step3": "Verifikasi konfigurasi dengan mengirimkan muatan uji untuk memastikan titik akhir menerimanya.",
-      "step4": "Amankan titik akhir Anda dengan memvalidasi header X-Webhook-Signature HMAC-SHA256 menggunakan rahasia webhook.",
-      "title": "Cara Kerja Webhook",
-      "customOnly": "Hanya berlaku untuk integrasi titik akhir kustom.",
-      "hmacRecipeTitle": "Resep Verifikasi HMAC",
-      "hmacRecipe": "Untuk memverifikasi muatan webhook di Node.js, hitung HMAC-SHA256 dari body permintaan mentah menggunakan kunci rahasia Anda. Bandingkan dengan header X-Webhook-Signature menggunakan timingSafeEqual.",
-      "timeoutNote": "Pengiriman webhook memiliki batas waktu 10 detik.",
-      "retryNote": "Pengiriman yang gagal akan dicoba kembali hingga 5 kali dengan backoff eksponensial.",
-      "docsLink": "Baca panduan lengkap pengembang Webhook",
-      "hmacRecipePython": "Verifikasi HMAC Python: hmac.new(secret, body, hashlib.sha256).hexdigest()",
-      "hmacRecipeBash": "Verifikasi HMAC Bash: echo -n \"$body\" | openssl dgst -sha256 -hmac \"$secret\""
-    },
-    "deliveries": {
-      "title": "Log Pengiriman",
-      "loadFailed": "Gagal memuat log pengiriman webhook.",
-      "empty": "Belum ada pengiriman yang tercatat. Picu peristiwa atau kirim muatan uji coba.",
-      "status": "Status",
-      "event": "Peristiwa",
-      "latency": "Latensi",
-      "at": "Dikirim Pada"
-    },
-    "kinds": {
-      "comingSoon": "Segera Hadir",
-      "slack": "Slack",
-      "slackDesc": "Kirim peristiwa sistem secara langsung ke saluran Slack",
-      "telegram": "Telegram",
-      "telegramDesc": "Kirim pesan peristiwa menggunakan bot Telegram",
-      "discord": "Discord",
-      "discordDesc": "Kirim pembaruan waktu nyata secara langsung ke server Discord",
-      "custom": "Webhook Kustom",
-      "customDesc": "Kirim muatan peristiwa sistem ke titik akhir HTTPS apa pun",
-      "email": "Notifikasi Surel",
-      "emailDesc": "Terima pembaruan ringkasan melalui surel",
-      "pagerduty": "PagerDuty",
-      "pagerdutyDesc": "Picu peringatan di PagerDuty untuk masalah sistem yang kritis",
-      "teams": "Microsoft Teams",
-      "teamsDesc": "Teruskan notifikasi sistem ke saluran Microsoft Teams"
-    },
-    "testPayloadSent": "Muatan Uji Coba Dikirim",
-    "testResponse": "Respons Uji Coba",
-    "validateUrl": {
-      "checking": "Memeriksa URL...",
-      "ok": "URL valid",
-      "blockedPrivate": "URL adalah alamat pribadi yang diblokir",
-      "invalidUrl": "Format URL tidak valid"
-    },
-    "custom": {
-      "endpointUrl": "URL Titik Akhir",
-      "endpointUrlPlaceholder": "https://api.yourdomain.com/webhook",
-      "secretKey": "Kunci Rahasia",
-      "secretKeyPlaceholder": "Masukkan kunci rahasia atau biarkan kosong untuk membuat secara otomatis",
-      "secretKeyHint": "Digunakan untuk menandatangani header payload untuk otentikasi."
-    },
-    "discord": {
-      "webhookUrl": "URL Webhook Discord",
-      "webhookUrlPlaceholder": "https://discord.com/api/webhooks/...",
-      "webhookUrlHint": "URL webhook yang disalin dari pengaturan integrasi saluran Discord Anda.",
-      "tutorial": "Cara membuat webhook Discord:"
-    },
-    "slack": {
-      "webhookUrl": "URL Webhook Slack",
-      "webhookUrlPlaceholder": "https://hooks.slack.com/services/...",
-      "webhookUrlHint": "URL webhook yang disalin dari integrasi Incoming Webhooks Slack Anda.",
-      "tutorial": "Cara membuat webhook Slack:"
-    },
-    "telegram": {
-      "botToken": "Token Bot Telegram",
-      "botTokenPlaceholder": "123456789:ABCdefGhIJKlmNoPQRsTUVwxyZ",
-      "botTokenHint": "Token API HTTP yang diterima dari @BotFather saat membuat bot Anda.",
-      "chatId": "ID Obrolan / Saluran Telegram",
-      "chatIdPlaceholder": "-100123456789 atau @channelname",
-      "chatIdHint": "Pengidentifikasi numerik unik atau nama pengguna publik dari obrolan/saluran.",
-      "tutorial": "Cara mengonfigurasi webhook Telegram:"
-    }
-  },
-  "compliance": {
-    "auditTitle": "Audit",
-    "auditDescription": "Tinjau peristiwa kepatuhan dan panggilan alat MCP dari satu tampilan operasional.",
-    "complianceTab": "Kepatuhan",
-    "mcpTab": "Audit MCP",
-    "title": "Audit Kepatuhan",
-    "description": "Kebijakan, akses, penyedia, dan peristiwa keamanan dicatat oleh log audit kepatuhan.",
-    "eventType": "Jenis Acara",
-    "eventTypePlaceholder": "Filter berdasarkan tindakan atau jenis peristiwa",
-    "severity": "Keparahan",
-    "allSeverities": "Semua tingkat keparahan",
-    "info": "Informasi",
-    "warning": "Peringatan",
-    "critical": "Kritis",
-    "sourceIp": "Sumber IP",
-    "userOrKey": "Pengguna / Kunci",
-    "action": "Tindakan",
-    "result": "Hasil",
-    "details": "Detail",
-    "timestamp": "Stempel waktu",
-    "from": "Dari",
-    "to": "Untuk",
-    "refresh": "Segarkan",
-    "export": "Ekspor",
-    "clearFilters": "Hapus filter",
-    "loading": "Memuat peristiwa audit...",
-    "showing": "Menampilkan {count} dari {total} acara",
-    "policyViolation": "Pelanggaran Kebijakan",
-    "accessDenied": "Akses Ditolak",
-    "injectionBlocked": "Injeksi Diblokir",
-    "noEvents": "Tidak ada peristiwa kepatuhan yang tercatat.",
-    "failedFetch": "Gagal mengambil log audit kepatuhan.",
-    "viewDetails": "Lihat detailnya",
-    "closeDetails": "Tutup detailnya",
-    "notAvailable": "—",
-    "system": "sistem",
-    "previous": "Sebelumnya",
-    "next": "Selanjutnya",
-    "mcpAudit": "Audit MCP",
-    "mcpAuditDesc": "Entri audit panggilan alat dicatat oleh server MCP.",
-    "failedFetchMcpAudit": "Gagal mengambil log audit MCP.",
-    "tool": "Alat",
-    "toolPlaceholder": "Filter berdasarkan nama alat",
-    "duration": "Durasi",
-    "apiKey": "Kunci API",
-    "output": "Keluaran",
-    "allResults": "Semua hasil",
-    "success": "Sukses",
-    "failure": "Kegagalan",
-    "noMcpEvents": "Tidak ada peristiwa audit MCP yang dicatat.",
-    "a2aAudit": "Audit A2A",
-    "a2aAuditDesc": "Jejak audit pelaksanaan tugas dicatat oleh server A2A.",
-    "a2aShowingTasks": "Menampilkan {count} dari {total} tugas",
-    "a2aSkill": "Keterampilan",
-    "a2aSkillPlaceholder": "Filter berdasarkan nama keterampilan",
-    "a2aState": "Negara",
-    "a2aAllStates": "Semua negara bagian",
-    "a2aStateSubmitted": "Dikirim",
-    "a2aStateWorking": "Bekerja",
-    "a2aStateCompleted": "Selesai",
-    "a2aStateFailed": "Gagal",
-    "a2aStateCancelled": "Dibatalkan",
-    "a2aTaskId": "ID Tugas",
-    "a2aEvents": "Acara",
-    "a2aArtifacts": "Artefak",
-    "a2aNoTasks": "Tidak ada tugas A2A yang dicatat.",
-    "a2aLoadingTasks": "Memuat tugas A2A...",
-    "actor": "Aktor",
-    "actorPlaceholder": "Filter berdasarkan aktor",
-    "eventTypes": {
-      "apiKey.activate": "Kunci API Diaktifkan",
-      "apiKey.ban": "Kunci API Dicekal",
-      "apiKey.deactivate": "Kunci API Dinonaktifkan",
-      "apiKey.regenerate": "Kunci API Diregenerasi",
-      "apiKey.scopes.grant": "Cakupan Kunci API Diberikan",
-      "apiKey.scopes.revoke": "Cakupan Kunci API Dicabut",
-      "apiKey.scopes.update": "Cakupan Kunci API Diperbarui",
-      "apiKey.unban": "Kunci API Batal Dicekal",
-      "auth.login.error": "Kesalahan Masuk",
-      "auth.login.failed": "Gagal Masuk",
-      "auth.login.locked": "Masuk Terkunci",
-      "auth.login.misconfigured": "Masuk Salah Konfigurasi",
-      "auth.login.setup_required": "Diperlukan Penyiapan Masuk",
-      "auth.login.success": "Berhasil Masuk",
-      "auth.logout.success": "Berhasil Keluar",
-      "compliance.cleanup": "Pembersihan Kepatuhan",
-      "provider.credentials.applied": "Kredensial Penyedia Diterapkan",
-      "provider.credentials.batch_revoked": "Kredensial Penyedia Batch Dicabut",
-      "provider.credentials.bulk_created": "Kredensial Penyedia Massal Dibuat",
-      "provider.credentials.bulk_imported": "Kredensial Penyedia Massal Diimpor",
-      "provider.credentials.created": "Kredensial Penyedia Dibuat",
-      "provider.credentials.imported": "Kredensial Penyedia Diimpor",
-      "provider.credentials.revoked": "Kredensial Penyedia Dicabut",
-      "provider.credentials.updated": "Kredensial Penyedia Diperbarui",
-      "provider.validation.ssrf_blocked": "SSRF Penyedia Diblokir",
-      "quota.plan.updated": "Paket Kuota Diperbarui",
-      "quota.pool.created": "Pool Kuota Dibuat",
-      "quota.pool.deleted": "Pool Kuota Dihapus",
-      "quota.pool.updated": "Pool Kuota Diperbarui",
-      "quota.store.driver_changed": "Driver Penyimpanan Kuota Diubah",
-      "server.start": "Server Dimulai",
-      "service.reveal_api_key": "Kunci API Layanan Ditampilkan",
-      "settings.update": "Pengaturan Diperbarui",
-      "settings.update_failed": "Pembaruan Pengaturan Gagal",
-      "sync.token.created": "Token Sinkronisasi Dibuat",
-      "sync.token.revoked": "Token Sinkronisasi Dicabut"
-    },
-    "mcpMetricCalls24h": "Panggilan (24j)",
-    "mcpMetricSuccessRate": "Tingkat keberhasilan",
-    "mcpMetricAvgDuration": "Durasi rata-rata",
-    "mcpMetricTopTool": "Alat Terbaik"
-  },
-  "themesPage": {
-    "title": "Themes",
-    "description": "Choose a preset theme or create your own with a single color",
-    "presetColors": "Popular colors",
-    "customTheme": "Custom theme",
-    "customThemeDesc": "Click create theme and pick one color",
-    "createTheme": "Create theme",
-    "activePreset": "Active theme"
-  },
-  "header": {
-    "logout": "Logout",
-    "quickNavigation": "Navigasi cepat",
-    "quickNavigationTitle": "Navigasi cepat (⌘K / Ctrl+K)",
-    "openQuickNavigation": "Buka navigasi cepat",
-    "switchToLightMode": "Beralih ke mode terang",
-    "switchToDarkMode": "Beralih ke mode gelap",
-    "language": "Language",
-    "providers": "Providers",
-    "providerDescription": "Manage your AI provider connections",
-    "combos": "Combos",
-    "comboDescription": "Model combos with fallback",
-    "usage": "Usage & Analytics",
-    "usageDescription": "Monitor your API usage, token consumption, and request logs",
-    "analytics": "Analytics",
-    "analyticsDescription": "Charts, trends, and evaluation insights",
-    "cliTools": "CLI Tools",
-    "cliToolsDescription": "Configure CLI tools",
-    "home": "Home",
-    "homeDescription": "Welcome to OmniRoute",
-    "endpoint": "Endpoints",
-    "endpointDescription": "Manage proxy endpoints, MCP, A2A, and API endpoints",
-    "mcp": "MCP",
-    "mcpDescription": "Model Context Protocol server management and tools",
-    "a2a": "A2A",
-    "a2aDescription": "Agent-to-Agent protocol tasks and observability",
-    "settings": "Settings",
-    "settingsDescription": "Manage your preferences",
-    "openaiCompatible": "OpenAI Compatible",
-    "anthropicCompatible": "Anthropic Compatible",
-    "media": "Media",
-    "mediaDescription": "Generate images, videos, and music",
-    "themes": "Themes",
-    "themesDescription": "Choose a color theme for the whole dashboard panel",
-    "costsDescription": "Track spending, analyze trends, and manage your AI budget across all providers",
-    "cacheDescription": "Monitor provider prompt cache efficiency and local semantic response reuse.",
-    "limitsDescription": "Configure rate limits and quotas per API key and provider",
-    "runtimeDescription": "Live runtime observability — circuit breakers, cooldowns, model lockouts, sessions and quota alerts",
-    "apiManagerDescription": "Manage API keys and access control for your OmniRoute instance",
-    "batchDescription": "Process large volumes of requests asynchronously with batched API calls",
-    "contextCavemanDescription": "Rule-based message compression, language packs, analytics and output mode controls.",
-    "contextRtkDescription": "Command-aware compression for tool output, terminal logs and build results.",
-    "contextCombosDescription": "Define how engines are combined for different routing scenarios.",
-    "changelogDescription": "Stay up to date with the latest platform features and announcements.",
-    "agentsDescription": "Manage and configure AI agent tools: Codex, Devin, Jules, and custom agents",
-    "cloudAgentsDescription": "Orchestrate cloud-based AI agents with live task tracking and plan approval",
-    "memoryDescription": "Persistent conversational memory with semantic search and FTS5 full-text indexing",
-    "skillsDescription": "Install and manage sandbox skills for automated prompt and tool execution",
-    "agentSkillsDescription": "Agent-ready skills catalog with one-click URL copy for AI client integration",
-    "translatorDescription": "Translate and test prompts across API formats: OpenAI ↔ Claude ↔ Gemini",
-    "playgroundDescription": "Test prompts interactively with live provider responses and format inspection",
-    "searchToolsDescription": "Search analytics, provider breakdown, cache hit rates, and cost tracking",
-    "logsDescription": "Real-time request logs, error traces, and streaming event inspector",
-    "auditDescription": "Compliance audit trail of API key usage, MCP tool calls, and policy events",
-    "webhooksDescription": "Configure webhook endpoints to receive real-time event notifications",
-    "healthDescription": "System health overview: providers, circuit breakers, rate limits, and database",
-    "proxyDescription": "Configure upstream proxy settings for outbound provider connections",
-    "apiEndpointsDescription": "Manage custom API endpoint configurations and routing overrides",
-    "batchFilesDescription": "Browse and manage batch job output files and results",
-    "analyticsEvalsDescription": "Model evaluation results and performance benchmarks",
-    "analyticsSearchDescription": "Search query analytics, cache hit rates, and cost tracking",
-    "analyticsUtilizationDescription": "Provider utilization metrics and capacity planning",
-    "analyticsComboHealthDescription": "Real-time health and performance of combo routing configurations",
-    "analyticsCompressionDescription": "Context compression analytics and token savings",
-    "costsBudgetDescription": "Budget limits and spending alerts per API key and provider",
-    "costsPricingDescription": "Custom pricing configuration for token cost calculations",
-    "logsProxyDescription": "Upstream proxy request logs and traffic inspection",
-    "logsConsoleDescription": "Application console output and debug logs",
-    "logsActivityDescription": "Audit trail of user actions and system events",
-    "auditMcpDescription": "MCP tool invocation audit trail and compliance records",
-    "auditA2a": "Audit A2A",
-    "auditA2aDescription": "Jejak audit eksekusi tugas A2A, transisi status, dan catatan pemanggilan keterampilan",
-    "settingsGeneralDescription": "Storage, database, and general instance configuration",
-    "settingsAppearanceDescription": "Theme, branding, and visual customization",
-    "settingsAiDescription": "AI behaviors, thinking budgets, vision, and memory settings",
-    "settingsCacheDescription": "TTL untuk entri cache katalog model",
-    "settingsSecurityDescription": "Authentication, authorization, and access control settings",
-    "featureFlags": "Bendera Fitur",
-    "featureFlagsDescription": "Kemampuan sistem kontrol dan fitur eksperimental",
-    "featureFlagsActive": "{count} aktif",
-    "featureFlagsInactive": "{count} tidak aktif",
-    "featureFlagsOverrides": "{count} penggantian DB",
-    "featureFlagsSearch": "Bendera pencarian...",
-    "featureFlagsCategoryAll": "Semua",
-    "featureFlagsCategorySecurity": "Keamanan",
-    "featureFlagsCategoryNetwork": "Jaringan",
-    "featureFlagsCategoryPolicies": "Kebijakan",
-    "featureFlagsCategoryRuntime": "Waktu proses",
-    "featureFlagsCategoryCli": "CLI",
-    "featureFlagsCategoryHealth": "Kesehatan",
-    "featureFlagsSourceDb": "DB",
-    "featureFlagsSourceEnv": "ENV",
-    "featureFlagsSourceDefault": "DEF",
-    "featureFlagsReset": "Setel ulang",
-    "featureFlagsResetAll": "Atur Ulang Semua Penggantian",
-    "featureFlagsResetAllConfirm": "Apakah Anda yakin ingin menyetel ulang semua penggantian tanda fitur? Ini akan mengembalikan semua tanda ke ENV atau nilai defaultnya.",
-    "featureFlagsRestartRequired": "Mulai ulang diperlukan untuk mendaftar",
-    "featureFlagsNoResults": "Tidak ada tanda yang cocok dengan penelusuran Anda",
-    "featureFlagsSaved": "Bendera diperbarui",
-    "featureFlagsError": "Gagal memperbarui tanda",
-    "settingsRoutingDescription": "Routing rules, model aliases, combo defaults, and degradation settings",
-    "settingsResilienceDescription": "Circuit breaker, retry, and fallback configuration",
-    "settingsAdvancedDescription": "Advanced payload rules, request limits, and proxy API settings",
-    "mitmProxyDescription": "Configure MITM proxy settings for traffic inspection and debugging",
-    "oneProxyDescription": "Configure 1Proxy settings for advanced proxy chaining",
-    "omniSkillsDescription": "Instal dan kelola skill sandbox untuk eksekusi prompt dan alat otomatis"
-  },
-  "cloudSyncStatus": {
-    "synced": "Tersinkronisasi",
-    "syncing": "Menyinkronkan...",
-    "off": "Sinkronisasi mati",
-    "error": "Galat sinkronisasi",
-    "disabled": "Dinonaktifkan",
-    "connected": "terhubung",
-    "disconnected": "terputus",
-    "lastSync": "Sinkronisasi pengaturan jarak jauh {status} — Sinkronisasi terakhir: {time}",
-    "statusLabel": "Status sinkronisasi pengaturan jarak jauh: {status}"
-  },
-  "breadcrumbs": {
-    "ariaLabel": "Breadcrumb",
-    "dashboard": "Dasbor",
-    "providers": "Penyedia",
-    "combos": "Kombo",
-    "settings": "Pengaturan",
-    "general": "Umum",
-    "appearance": "Tampilan",
-    "ai": "Pengaturan AI",
-    "routing": "Perutean",
-    "resilience": "Ketahanan",
-    "advanced": "Lanjutan",
-    "accessTokens": "Token Akses",
-    "featureFlags": "Flag Fitur",
-    "logs": "Log",
-    "auditLog": "Log Audit",
-    "console": "Konsol",
-    "logger": "Logger",
-    "translator": "Penerjemah",
-    "playground": "Playground",
-    "add": "Tambah",
-    "edit": "Edit",
-    "apiKeys": "Kunci API",
-    "models": "Model",
-    "cliCode": "Kode CLI",
-    "cliAgents": "Agen CLI",
-    "acpAgents": "Agen ACP",
-    "endpoint": "Endpoint",
-    "apiManager": "Manajer API",
-    "context": "Konteks",
-    "compression": "Kompresi",
-    "services": "Layanan",
-    "analytics": "Analitik",
-    "costs": "Biaya",
-    "health": "Kesehatan",
-    "runtime": "Runtime",
-    "webhooks": "Webhook",
-    "home": "Beranda",
-    "activity": "Aktivitas",
-    "agentSkills": "AgentSkills",
-    "comboHealth": "Kesehatan Kombo",
-    "evals": "Evaluasi",
-    "search": "Cari",
-    "utilization": "Utilisasi",
-    "apiEndpoints": "Endpoint API",
-    "audit": "Audit",
-    "a2a": "A2A",
-    "mcp": "MCP",
-    "batch": "Batch",
-    "files": "File",
-    "media": "Media",
-    "cache": "Cache",
-    "changelog": "Catatan Perubahan",
-    "chaos": "Chaos",
-    "cloudAgents": "Agen Cloud",
-    "live": "Langsung",
-    "studio": "Studio",
-    "aggressive": "Agresif",
-    "caveman": "Caveman",
-    "ccr": "CCR",
-    "headroom": "Headroom",
-    "lite": "Lite",
-    "llmlingua": "LLMLingua",
-    "omniglyph": "OmniGlyph",
-    "rtk": "RTK",
-    "sessionDedup": "Dedup Sesi",
-    "ultra": "Ultra",
-    "budget": "Anggaran",
-    "pricing": "Harga",
-    "quotaShare": "Pembagian Kuota",
-    "discovery": "Penemuan",
-    "freeProviderRankings": "Peringkat Penyedia Gratis",
-    "radar": "Radar",
-    "setup": "Setup",
-    "freeTiers": "Tingkat Gratis",
-    "gamification": "Gamifikasi",
-    "leaderboard": "Papan Peringkat",
-    "limits": "Batasan",
-    "profile": "Profil",
-    "plugins": "Plugin",
-    "providerStats": "Statistik Penyedia",
-    "new": "Baru",
-    "quota": "Kuota",
-    "relay": "Relay",
-    "searchTools": "Alat Pencarian",
-    "security": "Keamanan",
-    "sidebar": "Bilah Sisi",
-    "tokens": "Token",
-    "tools": "Alat",
-    "agentBridge": "Jembatan Agen",
-    "trafficInspector": "Pemeriksa Lalu Lintas",
-    "usage": "Penggunaan",
-    "orchestration": "Orkestrasi"
-  },
-  "home": {
-    "quickStart": "Quick Start",
-    "quickStartDesc": "Get up and running in 4 steps. Connect providers, route models, monitor everything.",
-    "fullDocs": "Full Docs",
-    "step1Title": "1. Create API key",
-    "step1Desc": "Go to <endpoint>Endpoint</endpoint> -> Registered Keys. Generate one key per environment.",
-    "step2Title": "2. Connect providers",
-    "step2Desc": "Add accounts in <providers>Providers</providers>. Supports OAuth, API Key, and free tiers.",
-    "step3Title": "3. Point your client",
-    "step3Desc": "Set base URL to {url} in your IDE or API client.",
-    "step4Title": "4. Monitor & optimize",
-    "step4Desc": "Track tokens, cost and errors in <logs>Request Logs</logs> and <analytics>Analytics</analytics>.",
-    "providersOverview": "Providers Overview",
-    "configuredOf": "{configured} configured of {total} available providers",
-    "noModelsAvailable": "No models available for this provider.",
-    "noProvidersConfigured": "Belum ada penyedia yang dikonfigurasi",
-    "addProvider": "Tambahkan penyedia",
-    "configureFirst": "Configure a connection first in {providers}",
-    "configureProvider": "Configure Provider",
-    "modelAvailable": "{count} model available",
-    "modelsAvailable": "{count} models available",
-    "connectionsActive": "{count} connection active",
-    "connectionsActivePlural": "{count} connections active",
-    "copyModelName": "Copy model name",
-    "documentation": "Documentation",
-    "healthMonitor": "Health Monitor",
-    "reportIssue": "Report issue",
-    "activeError": "{active} active · {errors} error",
-    "oauthLabel": "OAuth",
-    "apiKeyLabel": "API Key",
-    "requestsShort": "{count} reqs",
-    "providerModelsTitle": "{provider} - Models",
-    "copiedModel": "Copied: {model}",
-    "aliasLabel": "alias",
-    "updateNow": "Update Now",
-    "updating": "Updating...",
-    "updateAvailableDesc": "A new version is available. Click to update.",
-    "updateStarted": "Update started...",
-    "reloadingPageAutomatically": "Memuat ulang halaman secara otomatis...",
-    "providerTopology": "Topologi Penyedia",
-    "recentRequests": "Recent Requests",
-    "recentRequestsEmpty": "No requests yet.",
-    "recentRequestsModel": "Model",
-    "recentRequestsTokens": "In / Out",
-    "recentRequestsWhen": "When",
-    "downloadDmg": "Unduh DMG (macOS)",
-    "downloadDmgDescription": "Versi baru dari aplikasi desktop OmniRoute tersedia. Silakan unduh dan instal penginstal DMG macOS untuk memperbarui (sekarang: v{version}).",
-    "downloadExe": "Unduh EXE (Windows)",
-    "downloadExeDescription": "Versi baru dari aplikasi desktop OmniRoute tersedia. Silakan unduh dan instal penginstal EXE Windows untuk memperbarui (sekarang: v{version}).",
-    "downloadAppImage": "Unduh AppImage (Linux)",
-    "downloadAppImageDescription": "Versi baru dari aplikasi desktop OmniRoute tersedia. Silakan unduh paket AppImage Linux untuk memperbarui (sekarang: v{version}).",
-    "downloadUpdate": "Unduh Pembaruan",
-    "downloadUpdateDescription": "Versi baru dari aplikasi desktop OmniRoute tersedia. Silakan unduh format aplikasi yang sesuai untuk sistem Anda untuk memperbarui (sekarang: v{version}).",
-    "updateQueued": "Pembaruan ter排an ke v{version}.",
-    "updateDockerRebuilding": "Gambar Docker sedang dibangun kembali di latar belakang.",
-    "updateWaitingRestart": "Menunggu OmniRoute untuk memulai ulang dengan versi baru.",
-    "updateInstalling": "Menginstal v{version}.",
-    "updateRunning": "OmniRoute sekarang berjalan di v{version}.",
-    "updateCompleted": "OmniRoute diperbarui ke v{version}.",
-    "updateDockerStillRebuilding": "Gambar Docker masih dibangun ulang untuk v{version}.",
-    "updateInstallingBackground": "Menginstal v{version} di latar belakang.",
-    "updateWaitingVersion": "Menunggu OmniRoute untuk kembali di v{version}.",
-    "updateDockerStillInProgress": "Docker rebuild masih dalam proses.",
-    "updateRestarting": "Proses restart layanan sedang berlangsung. Menunggu OmniRoute untuk kembali online...",
-    "updateTimeout": "Pembaruan dimulai, tetapi v{version} tidak tersedia sebelum waktu habis. Segarkan halaman atau periksa log server.",
-    "updateTimedOut": "Pembaruan ke v{version} telah habis waktu.",
-    "updateStartFailed": "Gagal memulai pembaruan.",
-    "noResponseStream": "Tidak ada aliran respons yang diterima.",
-    "updateComplete": "Pembaruan selesai!",
-    "updateFailed": "Pembaruan gagal.",
-    "updateNetworkError": "Kesalahan jaringan — koneksi terputus selama pembaruan.",
-    "stepInstallPackage": "Instal Paket",
-    "stepRebuildNativeModules": "Bangun Ulang Modul Native",
-    "stepRestartService": "Mulai Ulang Layanan",
-    "stepComplete": "Lengkap",
-    "stepError": "Kesalahan",
-    "updateCompleteTitle": "Pembaruan Selesai!",
-    "updateFailedTitle": "Pembaruan Gagal",
-    "updatingTitle": "Memperbarui OmniRoute...",
-    "reloadNotice": "Halaman akan dimuat ulang secara otomatis dalam beberapa detik.",
-    "retryNotice": "Silakan coba lagi atau perbarui secara manual melalui CLI.",
-    "restartNotice": "Jangan tutup halaman ini. Sistem akan restart secara otomatis.",
-    "reloadNow": "Muat Ulang Sekarang",
-    "closeUpdate": "Tutup",
-    "retryUpdate": "Coba Lagi",
-    "updateAvailableTitle": "Pembaruan Tersedia: v{version}{desktop}",
-    "desktopAppLabel": "(Aplikasi Desktop)",
-    "checkingForUpdates": "Memeriksa pembaruan...",
-    "versionAvailableForDownload": "Versi v{version} tersedia untuk diunduh.",
-    "downloadingUpdate": "Mengunduh pembaruan... {percent}% selesai.",
-    "updateDownloaded": "Pembaruan berhasil diunduh! Klik Restart & Install untuk menerapkan.",
-    "autoUpdateFailed": "Pembaruan otomatis gagal: {reason}.",
-    "unknownUpdateError": "Kesalahan tidak dikenal",
-    "versionAvailableDesktop": "Versi v{version} tersedia untuk aplikasi desktop.",
-    "manualUpdateRequired": "Pembaruan manual diperlukan untuk jenis instalasi ini.",
-    "restartAndInstall": "Mulai Ulang & Instal",
-    "checkForUpdate": "Periksa Pembaruan",
-    "manualUpdate": "Pembaruan Manual",
-    "directDownloadHint": "Atau unduh format penginstal yang sesuai secara langsung:",
-    "releaseNotes": "Catatan Rilis",
-    "readMore": "Baca Selengkapnya",
-    "noAuthLabel": "Tidak Ada Autentikasi",
-    "readinessEyebrow": "Get ready to route",
-    "readinessTitle": "Send your first request",
-    "readinessSubtitle": "Four small steps. OmniRoute checks readiness as you go.",
-    "readinessStep1": "Connect a provider",
-    "readinessStep2": "Configure endpoint authentication",
-    "readinessStep3": "Copy your endpoint",
-    "readinessStep4": "Send a test request",
-    "readinessContinue": "Continue setup",
-    "readinessDismiss": "Dismiss for now"
-  },
-  "analytics": {
-    "title": "Analytics",
-    "usageAnalyticsTitle": "Analisis Penggunaan",
-    "diversityScoreTitle": "Keanekaragaman Penyedia",
-    "diversityScoreDesc": "Cuplikan konsentrasi penyedia untuk jendela lalu lintas terkini.",
-    "diversityShannonEntropy": "Entropi Shannon",
-    "diversityWindow": "Jendela: {count} req · {mins} mnt terakhir",
-    "diversityHealthy": "Distribusi Sehat",
-    "diversityRiskHigh": "Risiko Keterikatan Vendor Tinggi",
-    "diversityRiskModerate": "Distribusi Sedang",
-    "diversityScoreLabel": "skor",
-    "diversityHigherExplanation": "Nilai yang lebih tinggi berarti lalu lintas tersebar di beberapa penyedia.",
-    "diversityNoData": "Tidak ada data penggunaan terbaru yang tersedia.",
-    "chartRequests": "Permintaan",
-    "chartInput": "Input",
-    "chartOutput": "Output",
-    "chartTotal": "Total",
-    "chartCost": "Biaya",
-    "chartShare": "Porsi",
-    "chartServiceTier": "Tingkat Layanan",
-    "chartServiceTierSplit": "Pembagian biaya Cepat / Standar",
-    "chartCostPct": "{pct}% dari biaya",
-    "chartUsageDetail": "Rincian Penggunaan",
-    "chartCacheRead": "Baca cache",
-    "chartCostByProvider": "Biaya berdasarkan Penyedia",
-    "chartNoCostData": "Tidak ada data biaya",
-    "chartModelUsageOverTime": "Penggunaan Model dari Waktu ke Waktu",
-    "chartNoData": "Tidak ada data",
-    "chartWeekly": "Mingguan",
-    "activitySummary": "{active} hari aktif · {tokens} token · {days} hari",
-    "activityCellTitle": "{date}: {tokens} token",
-    "activityLess": "Lebih sedikit",
-    "activityMore": "Lebih banyak",
-    "chartApiKeyBreakdown": "Rincian Kunci API",
-    "chartApiKey": "Kunci API",
-    "mostActiveDay": "Hari Paling Aktif",
-    "datedTokenCount": "{date} · {tokens} token",
-    "noDataLast7Days": "Tidak ada data dalam 7 hari terakhir",
-    "requestTokenSummary": "{requests} permintaan · {tokens} token",
-    "chartByAccount": "Berdasarkan Akun",
-    "chartByApiKey": "Berdasarkan Kunci API",
-    "unknownApiKey": "Kunci API tidak dikenal",
-    "chartModelBreakdown": "Rincian Model",
-    "chartModel": "Model",
-    "chartProvider": "Penyedia",
-    "chartProviderBreakdown": "Rincian Penyedia",
-    "chartDate": "Tanggal",
-    "chartRequestsByProviderDate": "Permintaan berdasarkan Penyedia & Tanggal",
-    "filterAllKeys": "Semua Kunci",
-    "filterSearchKeys": "Cari kunci…",
-    "filterNoKeysMatch": "Tidak ada kunci yang cocok",
-    "filterOneKey": "1 kunci",
-    "filterMultipleKeys": "{count} kunci",
-    "rangeToday": "Hari ini",
-    "rangeYesterday": "Kemarin",
-    "rangeLast3Days": "3 hari terakhir",
-    "rangeThisWeek": "Minggu ini",
-    "rangeLast14Days": "14 hari terakhir",
-    "rangeThisMonth": "Bulan ini",
-    "rangeQuickSelect": "Pilih Cepat",
-    "rangeStart": "Mulai",
-    "rangeEnd": "Selesai",
-    "rangeCancel": "Batal",
-    "rangeApply": "Terapkan",
-    "rangeErrorInvalid": "Mulai harus sebelum selesai",
-    "period1D": "1H",
-    "period7D": "7H",
-    "period30D": "30H",
-    "period90D": "90H",
-    "periodYTD": "YTD",
-    "periodAll": "Semua",
-    "totalTokens": "Total Token",
-    "inputTokens": "Token Masukan",
-    "outputTokens": "Token Keluaran",
-    "estCost": "Perkiraan Biaya",
-    "infraTitle": "Infrastruktur",
-    "infraAccounts": "Akun",
-    "infraProviders": "Penyedia",
-    "infraApiKeys": "Kunci API",
-    "infraModels": "Model",
-    "perfTitle": "Kinerja",
-    "perfAvgTokens": "Rata-rata Token/Permintaan",
-    "perfCostReq": "Biaya/Permintaan",
-    "perfIoRatio": "Rasio I/O",
-    "perfFastReq": "Permintaan Cepat",
-    "highlightsTitle": "Sorotan",
-    "highlightsTopModel": "Model Teratas",
-    "highlightsTopProvider": "Penyedia Teratas",
-    "highlightsBusiestDay": "Hari Tersibuk",
-    "highlightsDiversity": "Keberagaman",
-    "highlightsFallbackRate": "Tingkat Fallback",
-    "customRange": "Kustom",
-    "overviewDescription": "Monitor your API usage patterns, token consumption, costs, and activity trends across all providers and models.",
-    "evalsDescription": "Run evaluation suites to test and validate your LLM endpoints. Compare model quality, detect regressions, and benchmark latency.",
-    "overview": "Overview",
-    "evals": "Evals",
-    "search": "Cari",
-    "utilization": "Utilization",
-    "routeTrace": "Pelacakan Rute",
-    "sectionsAria": "Bagian analitik",
-    "utilizationDescription": "Provider quota usage trends and rate limit tracking",
-    "modelStatus": "Model Status",
-    "modelStatusCooldown": "Cooldown",
-    "modelStatusUnavailable": "Unavailable",
-    "modelStatusError": "Error",
-    "comboHealth": "Combo Health",
-    "comboHealthDescription": "Combo-level quota, usage distribution, and performance metrics",
-    "compressionAnalyticsTitle": "Compression",
-    "compressionAnalyticsDescription": "Compression analytics - token savings, mode breakdown, and provider stats.",
-    "autoRoutingTotalAutoRequests": "Total Permintaan Otomatis",
-    "autoRoutingAvgSelectionScore": "Skor Seleksi Rata-rata",
-    "autoRoutingExplorationRate": "Tingkat Eksplorasi",
-    "autoRoutingLkgpHitRate": "Tingkat Hit LKGP",
-    "autoRoutingRequestsByVariant": "Permintaan berdasarkan Varian",
-    "autoRoutingTopRoutedProviders": "Penyedia yang Dirutekan Teratas",
-    "comboHealthWorstQuotaLeft": "Sisa kuota terburuk",
-    "comboHealthUsageSkew": "Penggunaannya miring",
-    "comboHealthSuccessRate": "Tingkat keberhasilan",
-    "comboHealthQuotaHealth": "Kesehatan kuota",
-    "comboHealthRequests": "Permintaan",
-    "comboHealthTokens": "Token",
-    "comboHealthAvgLatency": "Latensi rata-rata",
-    "comboHealthTotalRequests": "Jumlah permintaan",
-    "comboHealthExecutionTargets": "Target eksekusi",
-    "comboHealthSuccess": "Sukses",
-    "comboHealthLatency": "Latensi",
-    "comboHealthQuota": "Kuota",
-    "comboHealthTitle": "Kesehatan kombo",
-    "comboHealthUnableToLoad": "Tidak dapat memuat kesehatan kombo",
-    "comboHealthGettingStarted": "Memulai",
-    "comboHealthForecastTitle": "Prakiraan biaya & kuota",
-    "comboHealthForecastDescription": "Proyeksi linier dari riwayat lalu lintas kombo dan cuplikan kuota.",
-    "comboHealthQuotaRisk": "Risiko kuota {level}",
-    "comboHealthConfidence": "Keyakinan {level}",
-    "comboHealthProjectedCost": "Proyeksi biaya",
-    "comboHealthCostHistory": "riwayat {total} · {daily}/hari",
-    "comboHealthProjectedRequests": "Proyeksi permintaan",
-    "comboHealthRequestsInRange": "{count} dalam rentang yang dipilih",
-    "comboHealthWorstProjectedQuota": "Proyeksi kuota terburuk",
-    "comboHealthNoDepletionEstimate": "Tidak ada estimasi penipisan",
-    "comboHealthDaysToExhaust": "{days}h hingga habis",
-    "comboHealthTraffic": "lalu lintas",
-    "comboHealthProjectedQuota": "Proyeksi kuota",
-    "comboHealthPricingCoverage": "Cakupan harga",
-    "comboHealthAutopilotTitle": "Autopilot Kesehatan Kombo",
-    "comboHealthAutopilotDescription": "Rekomendasi yang diprioritaskan dari kesehatan kombo, prakiraan, kuota, dan kesehatan penyedia.",
-    "comboHealthIssues": "Masalah",
-    "comboHealthActionable": "{count} dapat ditindaklanjuti",
-    "comboHealthDown": "Mati",
-    "comboHealthDegraded": "Terdegradasi",
-    "comboHealthHealthy": "Sehat",
-    "comboHealthNoActiveIssues": "Tidak ada masalah kesehatan kombo aktif yang terdeteksi untuk rentang yang dipilih.",
-    "comboHealthScoringInspector": "Inspektur penilaian cerdas",
-    "comboHealthReadOnlyRecompute": "Hitung ulang hanya-baca",
-    "comboHealthScoringDescription": "Penjelasan tingkat faktor untuk peringkat target menggunakan kesehatan saat ini, prakiraan, dan heuristik perutean.",
-    "comboHealthTask": "Tugas: {task}",
-    "comboHealthSelectedRank": "Peringkat #1 yang dipilih",
-    "comboHealthFactor": {
-      "quota": "Kuota",
-      "health": "Kesehatan",
-      "costInv": "Biaya",
-      "latencyInv": "Latensi",
-      "taskFit": "Kesesuaian tugas",
-      "stability": "Stabilitas",
-      "tierPriority": "Tier",
-      "tierAffinity": "Kesesuaian tier",
-      "specificityMatch": "Spesifisitas",
-      "contextAffinity": "Konteks",
-      "resetWindowAffinity": "Jendela atur ulang"
-    },
-    "comboHealthQuotaValue": "Kuota {value}",
-    "comboHealthLatencyValue": "Latensi {value}ms",
-    "comboHealthIssueCount": "Masalah {count}",
-    "comboHealthNoInspectableTargets": "Tidak ada target yang dapat diperiksa untuk kombo ini.",
-    "comboHealthAutopilotState": {
-      "down": "Down",
-      "degraded": "Perlu perhatian",
-      "healthy": "Sehat"
-    },
-    "comboHealthModelProviderCount": "{models} model di {providers} penyedia",
-    "comboHealthGiniCoefficient": "Koefisien Gini",
-    "comboHealthRequestCount": "{count} permintaan",
-    "comboHealthQuotaHealthDescription": "Sisa kuota terendah di antara penyedia dengan sinyal tren pendek.",
-    "comboHealthRemainingQuota": "Sisa kuota {value}",
-    "comboHealthTrend": {
-      "improving": "Membaik",
-      "declining": "Menurun",
-      "stable": "Stabil"
-    },
-    "comboHealthUsageSkewDescription": "Pangsa permintaan model dan pangsa token dalam kombo ini.",
-    "comboHealthShareSummary": "Pangsa permintaan {requests} · Pangsa token {tokens}",
-    "comboHealthPerformance": "Kinerja",
-    "comboHealthPerformanceDescription": "Keandalan dan throughput untuk lalu lintas kombo yang dirutekan.",
-    "comboHealthExecutionTargetsDescription": "Metrik runtime tingkat langkah dan visibilitas kuota untuk target kombo terstruktur.",
-    "comboHealthRequestShort": "{count} req",
-    "comboHealthQuotaScope": "Cakupan kuota: {scope}",
-    "comboHealthTrendValue": "Tren: {trend}",
-    "comboHealthFetchFailed": "Gagal mengambil data kesehatan kombo",
-    "unknownError": "Kesalahan tidak dikenal",
-    "comboHealthIntro": "Pantau tekanan kuota, penggunaan model yang tidak merata, dan kinerja pengiriman berdasarkan kombo.",
-    "comboHealthForecastHorizon": "Proyeksi {value}",
-    "comboHealthNoData": "Tidak ada data kesehatan kombo yang tersedia",
-    "comboHealthNoDataDescription": "Snapshot kuota kombo dan permintaan yang dirutekan akan muncul di sini setelah lalu lintas mulai mengalir.",
-    "comboHealthStepCreate": "Buat kombo di <strong>Combos</strong> dengan beberapa penyedia",
-    "comboHealthStepSend": "Kirim permintaan ke endpoint kombo untuk menghasilkan data lalu lintas",
-    "comboHealthStepAutomatic": "Metrik kesehatan akan muncul secara otomatis saat permintaan dirutekan",
-    "comboHealthTracking": "Melacak {count} kombo untuk {range}",
-    "compressionAnalyticsTotalRequests": "Jumlah Permintaan",
-    "compressionAnalyticsTokensSaved": "Token Tersimpan",
-    "compressionAnalyticsAvgSavings": "Penghematan Rata-rata",
-    "compressionAnalyticsAvgDuration": "Durasi Rata-Rata",
-    "compressionAnalyticsReceipts": "Tanda terima",
-    "compressionAnalyticsFallbacks": "Penggantian",
-    "compressionAnalyticsPromptTokens": "Token yang cepat",
-    "compressionAnalyticsCompletionTokens": "Token penyelesaian",
-    "compressionAnalyticsTotalTokens": "Jumlah token",
-    "compressionAnalyticsCacheTokens": "Token cache",
-    "compressionAnalyticsNoDataYet": "Belum ada data kompresi",
-    "compressionAnalyticsLoading": "Memuat analitik kompresi…",
-    "compressionAnalyticsNoDataDescription": "Permintaan kompresi akan muncul di sini setelah permintaan pertama melalui /v1/chat/completions dengan kompresi diaktifkan.",
-    "rangeLast24h": "24 jam terakhir",
-    "rangeLast7d": "7 hari terakhir",
-    "rangeLast30d": "30 hari terakhir",
-    "rangeAllTime": "Sepanjang waktu",
-    "compressionAnalyticsModeStats": "{count} permintaan · {tokens} token dihemat",
-    "compressionAnalyticsSkipped": " · {count} dilewati (no-op)",
-    "compressionAnalyticsRealTokens": "{count} token riil",
-    "compressionAnalyticsValidationRestores": "pemulihan validasi",
-    "compressionAnalyticsRealUsageReceipts": "Tanda Terima Penggunaan Riil",
-    "compressionAnalyticsSources": "Sumber",
-    "compressionAnalyticsModeBreakdown": "Rincian Mode",
-    "compressionAnalyticsProviderBreakdown": "Rincian Penyedia",
-    "compressionAnalyticsLast24HoursActivity": "24 Jam Terakhir (Aktivitas)",
-    "compressionAnalyticsChartPoint": "{hour}: {count} permintaan, {tokens} token dihemat",
-    "compressionAnalyticsMaxRequests": "Permintaan maks/jam: {count}",
-    "compressionAnalyticsMaxTokens": "Token maks/jam: {count}",
-    "compressionAnalyticsStartTracking": "Gunakan <code>POST /v1/chat/completions</code> dengan konfigurasi kompresi untuk mulai melacak analitik kompresi.",
-    "compressionAnalyticsInfo": "<strong>Analitik kompresi:</strong> Penghematan token dilacak per mode (off, lite, standard, aggressive, ultra, RTK, stacked), mesin, kombo kompresi, dan penyedia. Arahkan kursor ke bagan untuk detailnya. Gunakan pemilih waktu untuk melihat periode waktu yang berbeda.",
-    "searchAnalyticsTotalSearches": "Jumlah Pencarian",
-    "searchAnalyticsCacheHitRate": "Tingkat Hit Cache",
-    "searchAnalyticsTotalCost": "Jumlah Biaya",
-    "searchAnalyticsAvgResponse": "Respon Rata-Rata",
-    "searchAnalyticsNoSearchesYet": "Belum ada pencarian",
-    "providerUtilizationTitle": "Pemanfaatan penyedia",
-    "providerUtilizationFailedToLoad": "Gagal memuat data pemanfaatan",
-    "providerUtilizationNoData": "Tidak ada data pemanfaatan yang tersedia",
-    "providerUtilizationGettingStarted": "Memulai",
-    "providerUtilizationLatestSnapshot": "Cuplikan kuota terbaru",
-    "providerUtilizationRemainingCapacity": "Kapasitas yang tersisa",
-    "utilizationRange": {
-      "1h": "Jam terakhir",
-      "24h": "24 jam terakhir",
-      "7d": "7 hari terakhir",
-      "30d": "30 hari terakhir"
-    },
-    "providerUtilizationGlobalView": "Tampilan Global",
-    "providerUtilizationAccountSplit": "Pembagian Akun",
-    "providerUtilizationLoading": "Memuat data utilisasi…",
-    "retrying": "Mencoba kembali…",
-    "retry": "Coba Lagi",
-    "providerUtilizationNoDataDescription": "Snapshot kuota penyedia akan muncul di sini setelah data utilisasi dikumpulkan.",
-    "providerUtilizationStepConnect": "Hubungkan penyedia melalui OAuth atau kunci API di <strong>Penyedia</strong>",
-    "providerUtilizationStepEnable": "Aktifkan pelacakan kuota dengan menggunakan penyedia dalam kombo atau permintaan langsung",
-    "providerUtilizationStepAutomatic": "Data akan muncul secara otomatis saat snapshot kuota dikumpulkan",
-    "statusExhausted": "Habis",
-    "statusLow": "Rendah",
-    "statusHealthy": "Sehat",
-    "remainingQuota": "Sisa kuota",
-    "routeTraceTitle": "Tampilan Pelacakan Rute",
-    "routeTraceDescription": "Periksa jejak permintaan yang dipertahankan: target yang dipilih, faktor perutean, bukti fallback, pemutaran ulang skor saat ini, latensi, token, dan kesehatan target.",
-    "routeTraceRequestLog": "Log permintaan",
-    "routeWeight": "Bobot {weight}%",
-    "routeNoRelatedEvidence": "Belum ada bukti target terkait yang disimpan.",
-    "unknown": "tidak diketahui",
-    "selected": "Terpilih",
-    "routeNoStepId": "tidak ada id langkah",
-    "routeNoStep": "tidak ada langkah",
-    "routeMatchesTopTarget": "Cocok dengan target teratas saat ini",
-    "routeDiffersFromTop": "Berbeda dari teratas saat ini",
-    "routeTargetMissingNow": "Target hilang sekarang",
-    "routeNotComboRouted": "Tidak dirutekan kombo",
-    "routeWhyTarget": "Mengapa target ini?",
-    "routeWhyTargetSubtitle": "Metadata runtime persis ditambah pemutaran ulang penilaian baca-saja",
-    "routeExactRuntimeLog": "Log runtime persis",
-    "routeCallLogsExact": "call_logs persis",
-    "routeReadOnlyRecompute": "Hitung ulang baca-saja",
-    "routeRuntimeRankNow": "Peringkat runtime saat ini",
-    "routeRuntimeScoreNow": "Skor runtime saat ini",
-    "routeWouldSelectNow": "Akan memilih sekarang",
-    "routeNoRecomputeCandidates": "Tidak ada peringkat kandidat kombo yang dapat dihitung ulang untuk permintaan ini.",
-    "runtime": "Runtime",
-    "routeTopNow": "Teratas saat ini",
-    "routeFetchLogsFailed": "Gagal mengambil log permintaan",
-    "routeExplainFailed": "Gagal menjelaskan rute",
-    "direct": "langsung",
-    "routeUnableToLoad": "Tidak dapat memuat penjelasan rute",
-    "routeNoRequestLogs": "Tidak ada log permintaan yang tersedia",
-    "routeNoRequestLogsDescription": "Kirim lalu lintas melalui OmniRoute terlebih dahulu. Penjelasan rute dihasilkan dari log panggilan terstruktur yang disimpan.",
-    "routeDecisionSummary": "Ringkasan keputusan",
-    "routeConfidence": "{confidence} keyakinan",
-    "routeScore": "Skor rute",
-    "latency": "Latensi",
-    "routeRecentSuccess": "Keberhasilan baru-baru ini",
-    "routeAvgTargetLatency": "Latensi target rata-rata",
-    "routeSelectedTarget": "Target terpilih",
-    "provider": "Penyedia",
-    "model": "Model",
-    "account": "Akun",
-    "connection": "Koneksi",
-    "combo": "Kombo",
-    "routeStep": "Langkah",
-    "tokens": "Token",
-    "notAvailable": "n/a",
-    "routeTokenCounts": "{input} masuk · {output} keluar",
-    "routeEvidence": "Bukti",
-    "routeFactors": "Faktor perutean",
-    "routeFactorsSubtitle": "Sinyal berbobot yang digunakan untuk penjelasan ini",
-    "routeFallbackTimeline": "Linimasa cadangan dan target",
-    "routeFallbackTimelineSubtitle": "Disimpulkan dari log panggilan persisten di sekitar permintaan ini",
-    "routeRecommendations": "Rekomendasi",
-    "routeLimitations": "Batasan",
-    "routeNoKnownLimitations": "Tidak ada batasan yang diketahui untuk penjelasan ini.",
-    "searchAnalyticsLoading": "Memuat analitik pencarian…",
-    "searchAnalyticsNoData": "Belum ada data pencarian yang tersedia.",
-    "searchAnalyticsNoDataDescription": "Permintaan pencarian akan muncul di sini setelah pencarian pertama melalui <code>/v1/search</code>.",
-    "searchAnalyticsToday": "{count} hari ini",
-    "searchAnalyticsCachedRequests": "{count} permintaan yang di-cache",
-    "searchAnalyticsApiCosts": "biaya API pencarian",
-    "searchAnalyticsErrors": "{count} kesalahan",
-    "searchAnalyticsNoErrors": "Tidak ada kesalahan",
-    "searchAnalyticsProviderBreakdown": "Rincian Penyedia",
-    "searchAnalyticsQueries": "kueri",
-    "searchAnalyticsEmptyDescription": "Gunakan <code>POST /v1/search</code> untuk memulai pengalihan pencarian web.",
-    "searchAnalyticsFreeTier": "<strong>Tingkat gratis tersedia:</strong> Serper (2.500/bulan), Brave (2.000/bulan), Exa (1.000/bulan), Tavily (1.000/bulan) — total 6.500+ pencarian gratis/bulan dengan failover otomatis.",
-    "autoRoutingNoDataAvailable": "Tidak ada analitik auto-routing yang tersedia. Buat permintaan menggunakan awalan auto/ untuk melihat metrik.",
-    "defaultVariantLabel": "Bawaan",
-    "freeTierAvailable": "Tingkat gratis tersedia"
-  },
-  "apiManager": {
-    "title": "API Keys",
-    "createKey": "Create API Key",
-    "key": "Key",
-    "revokeKey": "Revoke Key",
-    "revokeConfirm": "Are you sure you want to revoke this API key?",
-    "noKeys": "No API keys yet",
-    "noKeysDesc": "Create your first API key to authenticate requests to your endpoint",
-    "keyLabel": "Key Label",
-    "permissions": "Permissions",
-    "expiresAt": "Expires",
-    "never": "Never",
-    "revoke": "Revoke",
-    "showKey": "Show Key",
-    "hideKey": "Hide Key",
-    "copyKey": "Copy API Key",
-    "allModels": "All models",
-    "selectedModels": "Selected Models",
-    "readOnly": "Read Only",
-    "fullAccess": "Full Access",
-    "keyManagement": "API Key Management",
-    "keyManagementDesc": "Create and manage API keys for authenticating requests to your endpoint",
-    "requestFlowAria": "Your app sends requests through an API key to OmniRoute",
-    "requestFlowYourApp": "Your app",
-    "requestFlowApiKey": "API key",
-    "requestFlowOmniRoute": "OmniRoute",
-    "totalKeys": "Total Keys",
-    "restricted": "Restricted",
-    "totalRequests": "Total Requests",
-    "modelsAvailable": "Models Available",
-    "registeredKeys": "Registered Keys",
-    "keysRegistered": "{count} keys registered",
-    "keyRegistered": "{count} key registered",
-    "keysSecurityNote": "Each key isolates usage tracking and can be revoked independently. Keys are masked after creation for security.",
-    "createFirstKey": "Create Your First Key",
-    "name": "Name",
-    "usage": "Usage",
-    "created": "Created",
-    "actions": "Actions",
-    "reqs": "reqs",
-    "neverUsed": "Never used",
-    "deleteConfirm": "Delete this API key?",
-    "usageTips": "Usage Tips",
-    "tipAuth": "Use API keys in the Authorization header as Bearer YOUR_KEY",
-    "tipSecure": "Keys are only shown once during creation — store them securely",
-    "tipSeparate": "Create separate keys for different clients or environments",
-    "tipRestrict": "Restrict keys to specific models for better security and cost control",
-    "keyName": "Key Name",
-    "keyNamePlaceholder": "e.g., Production Key, Development Key",
-    "keyNameDesc": "Choose a descriptive name to identify this key's purpose",
-    "managementAccessDesc": "Izinkan kunci API ini mengelola konfigurasi OmniRoute.",
-    "selfServiceVisibility": "Visibilitas layanan mandiri",
-    "selfServiceVisibilityDesc": "Kontrol apa yang dapat dilihat kunci ini tentang penggunaannya sendiri dan kuota upstream bersama.",
-    "ownUsageVisibility": "Biaya dan penggunaan token sendiri",
-    "ownUsageVisibilityDesc": "Izinkan kunci ini memanggil endpoint statusnya untuk melihat penggunaan USD, persen anggaran, dan total tokennya sendiri.",
-    "sharedAccountQuotaVisibility": "Kuota akun bersama",
-    "sharedAccountQuotaVisibilityDesc": "Izinkan kunci ini melihat kuota akun upstream bersama saat satu koneksi eksplisit dikonfigurasi.",
-    "localUsageCommand": "Izinkan perintah penggunaan lokal",
-    "localUsageCommandDesc": "Mengizinkan kunci API ini menggunakan @@om-usage untuk mengambil informasi penggunaan dan kuota yang disimpan di cache tanpa memanggil penyedia hulu.",
-    "localUsageCommandBadge": "Perintah penggunaan",
-    "keyCreated": "API Key Created",
-    "keyCreatedSuccess": "Key created successfully!",
-    "keyCreatedNote": "Copy and store this key now — it won't be shown again.",
-    "done": "Done",
-    "savePermissions": "Save Permissions",
-    "endpointRestrictions": "Allowed Endpoints",
-    "allEndpointsAllowed": "This key can access all API endpoints.",
-    "endpointsRestricted": "Restricted to {count} endpoint{count, plural, one {} other {s}}.",
-    "autoResolve": "Auto-Resolve",
-    "autoResolveDesc": "Auto-resolve ambiguous model names to native provider for this API key.",
-    "streamDefaultMode": "Kompatibilitas Bawaan Aliran",
-    "streamDefaultModeDesc": "Mengontrol bendera `stream` yang diabaikan untuk kunci ini. Mode JSON mengembalikan respons non-aliran kecuali klien secara eksplisit meminta SSE.",
-    "streamDefaultLegacy": "Warisan",
-    "streamDefaultJson": "Kompatibel dengan JSON",
-    "streamDefaultBadge": "Bawaan aliran JSON",
-    "keyActive": "Key Active",
-    "keyActiveDesc": "Enable or disable this API key. Disabled keys are immediately rejected with 403.",
-    "accessSchedule": "Access Schedule",
-    "accessScheduleDesc": "Restrict access to specific hours and days of the week.",
-    "scheduleFrom": "From",
-    "scheduleUntil": "Until",
-    "scheduleDays": "Days",
-    "scheduleTimezone": "Timezone",
-    "scheduleTimezoneHint": "Use IANA timezone names, e.g. America/New_York, Europe/Berlin",
-    "scheduleActive": "Schedule",
-    "disabled": "Disabled",
-    "daySun": "Sun",
-    "dayMon": "Mon",
-    "dayTue": "Tue",
-    "dayWed": "Wed",
-    "dayThu": "Thu",
-    "dayFri": "Fri",
-    "daySat": "Sat",
-    "allowAll": "Allow All",
-    "restrict": "Restrict",
-    "allowAllInfo": "This key can access all available models.",
-    "restrictInfo": "This key can access {selected} of {total} models.",
-    "selected": "{count} selected",
-    "all": "All",
-    "clear": "Clear",
-    "searchModels": "Search models by name or provider...",
-    "noModelsFound": "No models found",
-    "keyNameRequired": "Key name is required",
-    "keyNameTooLong": "Key name must be {max} characters or less",
-    "keyNameInvalid": "Key name can only contain letters, numbers, spaces, hyphens, and underscores",
-    "invalidKeyName": "Invalid key name",
-    "failedCreateKey": "Failed to create key",
-    "failedCreateKeyRetry": "Failed to create key. Please try again.",
-    "invalidKeyId": "Invalid key ID",
-    "failedDeleteKey": "Failed to delete key",
-    "failedDeleteKeyRetry": "Failed to delete key. Please try again.",
-    "invalidModelsSelection": "Invalid models selection",
-    "cannotSelectMoreThanModels": "Cannot select more than {max} models",
-    "failedUpdatePermissions": "Failed to update permissions",
-    "failedUpdatePermissionsRetry": "Failed to update permissions. Please try again.",
-    "unknownProvider": "unknown",
-    "copyMaskedKey": "Copy masked key",
-    "keyOnlyAvailableAtCreation": "Full key available only at creation time — copy it when you first create the key",
-    "modelsCount": "{count, plural, one {# model} other {# models}}",
-    "devicesCount": "{count, plural, one {# perangkat} other {# perangkat}}",
-    "devicesTooltip": "{count, plural, one {# perangkat IP/User-Agent berbeda terlihat dengan kunci ini (30 menit terakhir)} other {# perangkat IP/User-Agent berbeda terlihat dengan kunci ini (30 menit terakhir)}}",
-    "lastUsedOn": "Last: {date}",
-    "viewCostsFor": "Lihat biaya untuk {name}",
-    "editPermissions": "Edit permissions",
-    "deleteKey": "Delete key",
-    "regenerateKey": "Regenerasi kunci",
-    "regenerateConfirm": "Apakah Anda yakin ingin membuat ulang kunci API ini? Kunci lama akan segera dibatalkan.",
-    "failedRegenerateKey": "Gagal membuat ulang kunci API",
-    "failedRegenerateKeyRetry": "Gagal membuat ulang kunci API. Silakan coba lagi.",
-    "model": "{count} model",
-    "models": "{count} models",
-    "permissionsTitle": "Permissions: {name}",
-    "allowAllDesc": "This key can access all available models.",
-    "restrictLoading": "Memuat katalog model…",
-    "restrictCatalogUnavailable": "Katalog model tidak tersedia; kunci ini memiliki {selectedCount} pembatasan model yang dipilih.",
-    "restrictDesc": "This key can access {selectedCount} of {totalModels} models.",
-    "selectedCount": "{count} selected",
-    "maxActiveSessions": "Sesi Aktif Maks",
-    "maxActiveSessionsDescription": "0 = tidak terbatas. Kembalikan 429 ketika kunci ini melebihi sesi lekat bersamaan.",
-    "throttleDelay": "Penundaan Pembatasan",
-    "throttleDelayDescription": "Tambahkan penundaan tetap sebelum permintaan untuk kunci ini dirutekan. 0 = tanpa perlambatan.",
-    "expandClaudeCodeFamilies": "Perluas keluarga Claude Code",
-    "removeClaudeCodeDefault": "Hapus bawaan Claude Code",
-    "allowedCombos": "Kombinasi yang Diizinkan",
-    "allCombosAllowed": "Kunci ini dapat menggunakan kombinasi apa pun.",
-    "restrictedComboCount": "{count, plural, one {Dibatasi untuk # kombinasi} other {Dibatasi untuk # kombinasi}}.",
-    "preservedComboRules": "__MISSING__:{count, plural, one {# stored entry is} other {# stored entries are}} not in this combo list (for example routing rules) and will be kept as saved.",
-    "preservedComboRuleHint": "__MISSING__:Kept as stored. This entry is not a combo in the list above, so it can only be changed through the API.",
-    "apiManagerCustomRateLimits": "Batas Tarif Khusus",
-    "apiManagerCustomRateLimitsDesc": "Ganti batas default global. Biarkan kosong untuk menggunakan default.",
-    "apiManagerRateLimitRequestsPlaceholder": "Permintaan",
-    "apiManagerRateLimitReqPer": "permintaan /",
-    "apiManagerRateLimitSecondsPlaceholder": "Detik",
-    "apiManagerRemoveLimitTitle": "Hapus batas",
-    "apiManagerTimezonePlaceholder": "Amerika/Sao_Paulo",
-    "noLogPayloadPrivacy": "Privasi Muatan Tanpa Log",
-    "bannedStatus": "Status Terlarang",
-    "managementApiAccess": "Akses API Manajemen",
-    "expirationDate": "Tanggal Kedaluwarsa",
-    "managementAccess": "Akses Manajemen",
-    "allowedConnections": "Koneksi yang Diizinkan",
-    "searchPlaceholder": "Cari berdasarkan nama atau token...",
-    "activeOnly": "Hanya yang aktif",
-    "filterStatus": "STATUS",
-    "filterType": "TIPE",
-    "filterAll": "Semua",
-    "filterStatusActive": "Aktif",
-    "filterStatusDisabled": "Dinonaktifkan",
-    "filterStatusBanned": "Dicekal",
-    "filterStatusExpired": "Kedaluwarsa",
-    "filterTypeStandard": "Standar",
-    "filterTypeManage": "Kelola",
-    "filterTypeRestricted": "Dibatasi",
-    "shownOf": "{shown} dari {total} ditampilkan",
-    "emptyFilterTitle": "Tidak ada kunci yang cocok dengan filter Anda",
-    "emptyFilterClear": "Hapus filter",
-    "disableNonPublicModels": "Nonaktifkan Model Non-Publik",
-    "disableNonPublicModelsDesc": "Tolak permintaan untuk model yang tidak ditemukan atau tidak ditandai sebagai publik dalam katalog penyedia",
-    "normalKeysSection": "Kunci normal",
-    "quotaKeysSection": "Kunci kuota",
-    "bypassProviderQuota": "Lewati batas kuota penyedia",
-    "bypassProviderQuotaDescription": "Mengizinkan kunci ini untuk mengabaikan kebijakan batas akun/penyedia hulu selama perutean. Kuota USD kunci API tetap berlaku.",
-    "quotaPill": "KUOTA",
-    "quotaModeOnly": "hanya-qtSd",
-    "exclusiveLease": "__MISSING__:Exclusive Lease",
-    "exclusiveLeaseNoticeTitle": "__MISSING__:Exclusive Lease",
-    "exclusiveLeaseNoticeDesc": "__MISSING__:This API key has exclusive lease permissions for dedicated connection routing.",
-    "allConnections": "__MISSING__:All connections",
-    "onlySelectedConnections": "__MISSING__:Only selected connections",
-    "selectAtLeastOneConnection": "__MISSING__:Select at least one connection or choose All connections.",
-    "allConnectionsDesc": "__MISSING__:This key can use any active connection.",
-    "restrictedToConnections": "__MISSING__:Restricted to {count, plural, one {# connection} other {# connections}}."
-  },
-  "auditLog": {
-    "title": "Audit Log",
-    "searchPlaceholder": "Search actions...",
-    "action": "Action",
-    "actor": "Actor",
-    "target": "Target",
-    "ipAddress": "IP Address",
-    "timestamp": "Timestamp",
-    "noEntries": "No audit entries found",
-    "filterByAction": "Filter by action...",
-    "filterByActor": "Filter by actor...",
-    "filterEntriesAria": "Filter audit log entries",
-    "filterByActionTypeAria": "Filter by action type",
-    "filterByActorAria": "Filter by actor",
-    "refreshAuditLogAria": "Refresh audit log",
-    "tableAria": "Audit log entries",
-    "failedFetchAuditLog": "Failed to fetch audit log",
-    "notAvailable": "—",
-    "description": "Administrative actions and security events",
-    "showing": "Showing {count} entries (offset {offset})",
-    "previous": "Previous"
-  },
-  "media": {
-    "title": "Media Playground",
-    "subtitle": "Generate images, videos, and music",
-    "model": "Model",
-    "prompt": "Prompt",
-    "generate": "Generate",
-    "generating": "Generating...",
-    "loadingModels": "Loading available models...",
-    "noModels": "No models available. Configure providers with media capabilities first.",
-    "error": "Generation Failed",
-    "result": "Result",
-    "imageDescription": "Generate images from text prompts using OpenAI, xAI, Together, Hyperbolic, SD WebUI, ComfyUI and more.",
-    "videoDescription": "Create videos with AnimateDiff, Stable Video Diffusion via ComfyUI or SD WebUI.",
-    "musicDescription": "Compose music using Stable Audio Open or MusicGen via ComfyUI.",
-    "kinds": {
-      "embedding": "Penyematan",
-      "image": "Gambar",
-      "imageToText": "Gambar ke Teks",
-      "tts": "Teks ke Ucapan",
-      "stt": "Ucapan ke Teks",
-      "webSearch": "Pencarian Web",
-      "webFetch": "Pengambilan Web",
-      "video": "Video",
-      "music": "Musik",
-      "ocr": "OCR"
-    },
-    "noProviders": "Belum ada penyedia yang dikonfigurasi untuk jenis ini.",
-    "addConnection": "Tambah Koneksi",
-    "backToProviders": "Kembali ke Penyedia",
-    "connections": "{count} Koneksi",
-    "noConnections": "Belum ada koneksi — tambahkan satu dari halaman penyedia.",
-    "loading": "Memuat...",
-    "suggestedModels": "Model yang disarankan dari penyedia",
-    "imageGeneration": "Pembuatan Gambar",
-    "imageToText": "Gambar ke Teks",
-    "imageToTextComingSoon": "Playground Gambar-ke-Teks inline akan tersedia setelah <code>/api/v1/images/understanding</code> diimplementasikan.",
-    "disabled": "Dinonaktifkan",
-    "videoGeneration": "Pembuatan Video",
-    "musicGeneration": "Pembuatan Musik",
-    "textToSpeech": "Teks ke Ucapan",
-    "transcription": "Transkripsi",
-    "imagePromptPlaceholder": "Pemandangan tenang dengan pegunungan saat matahari terbenam...",
-    "videoPromptPlaceholder": "Selang waktu bunga yang mekar...",
-    "musicPromptPlaceholder": "Musik elektronik yang ceria dengan synth pad...",
-    "speechTextPlaceholder": "Halo! Selamat datang di OmniRoute, gerbang AI cerdas Anda...",
-    "transcriptionPlaceholder": "Unggah berkas audio untuk ditranskripsi...",
-    "noImagesReturned": "Tidak ada gambar yang dikembalikan. Penyedia mungkin telah menerima permintaan tetapi mengembalikan data kosong.",
-    "generatedImageAlt": "Gambar yang dihasilkan {index}",
-    "save": "Simpan",
-    "enterTextToSynthesize": "Silakan masukkan teks untuk disintesis.",
-    "selectAudioToTranscribe": "Silakan pilih berkas audio untuk ditranskripsi.",
-    "noSpeechDetected": "Tidak ada ucapan yang terdeteksi dalam berkas audio. Jika Anda mengunggah musik atau berkas hening, coba berkas audio dengan kata-kata yang diucapkan. Penyedia: \"{provider}\".",
-    "emptyTranscription": "Transkripsi mengembalikan teks kosong. Audio mungkin tidak berisi ucapan yang dapat dikenali, atau kunci API \"{provider}\" mungkin tidak valid. Periksa Dasbor → Log → Proksi untuk detailnya.",
-    "topazRequiresImage": "Topaz memerlukan gambar masukan.",
-    "enterPrompt": "Silakan masukkan prompt.",
-    "enhanceThisImage": "Tingkatkan gambar ini",
-    "failedToReadFile": "Gagal membaca berkas",
-    "generationFailed": "Pembuatan gagal",
-    "requestFailed": "Permintaan gagal ({status})",
-    "provider": "Penyedia",
-    "credentialsRequired": "Memerlukan kunci API <provider></provider> di <providers>Penyedia</providers>",
-    "voice": "Suara",
-    "format": "Format",
-    "audioVideoFile": "Berkas Audio / Video",
-    "fileTooLarge": "Berkas terlalu besar ({size}). Maksimum yang diperbolehkan: {max}.",
-    "audioVideoFileHint": "Mendukung berkas audio dan video hingga 4 GB",
-    "sourceImage": "Gambar Sumber",
-    "sourceImageHint": "Opsional untuk alur kerja gambar-ke-gambar, pengeditan, dan peningkatan skala.",
-    "maskImage": "Gambar Topeng",
-    "maskImageHint": "Opsional. Digunakan oleh model bergaya inpaint yang mendukung topeng.",
-    "text": "Teks",
-    "promptOptional": "Prompt (opsional)",
-    "enhancementInstructionsPlaceholder": "Instruksi peningkatan opsional...",
-    "synthesizing": "Menyintesis...",
-    "transcribing": "Mentranskripsi...",
-    "synthesizeSpeech": "Sintesis Ucapan",
-    "transcribeAudio": "Transkripsi Audio",
-    "generateModality": "Hasilkan {modality}",
-    "apiKeyRequired": "Kunci API Diperlukan",
-    "configureApiKeys": "Konfigurasikan kunci API di Penyedia",
-    "downloadFormat": "Unduh {format}",
-    "noTextReturned": "Tidak ada teks yang dikembalikan",
-    "wordTimestamps": "Stempel waktu tingkat kata ({count} kata)",
-    "providerCount": "{count} penyedia",
-    "imageToTextBridgeAvailable": "Modality Bridge sekarang dapat mendeskripsikan gambar untuk model teks saja. Playground inline akan tersedia ketika <code>/api/v1/images/understanding</code> diimplementasikan.",
-    "imageToTextBridgeCta": "Konfigurasikan jembatan Gambar→Teks di pengaturan Jembatan Modalitas",
-    "sttBridgeCta": "Konfigurasikan jembatan Speech→Text di pengaturan Modality Bridge",
-    "existingConnection": "Koneksi yang ada",
-    "openrouterSttDescription": "Model speech-to-text OpenRouter menggunakan koneksi OpenRouter yang telah Anda konfigurasikan. Tidak diperlukan kredensial terpisah."
-  },
-  "search": {
-    "searchQuery": "Search Query",
-    "searchResults": "Search Results",
-    "cachedResult": "Cached",
-    "searchCost": "Cost",
-    "searchTools": "Search Tools",
-    "searchToolsDesc": "Advanced search testing with provider comparison",
-    "compareProviders": "Compare Providers",
-    "rerankResults": "Rerank Results",
-    "searchHistory": "Search History",
-    "urlOverlap": "URL Overlap",
-    "noSearchProviders": "No search providers configured. Add providers in Settings.",
-    "noRerankModels": "No rerank model available",
-    "webSearch": "Web Search",
-    "provider": "Provider",
-    "searchType": "Search Type",
-    "maxResults": "Max Results",
-    "filters": "Filters",
-    "country": "Country",
-    "language": "Language",
-    "timeRange": "Time Range",
-    "includeDomains": "Include Domains",
-    "excludeDomains": "Exclude Domains",
-    "safeSearch": "Safe Search",
-    "safeSearchOff": "Off",
-    "safeSearchModerate": "Moderate",
-    "safeSearchStrict": "Strict",
-    "queryPlaceholder": "Enter search query...",
-    "providerAuto": "auto (cheapest)",
-    "searchTypeWeb": "web",
-    "searchTypeNews": "news",
-    "optionAny": "any",
-    "timeRangeDay": "Past day",
-    "timeRangeWeek": "Past week",
-    "timeRangeMonth": "Past month",
-    "timeRangeYear": "Past year",
-    "domainPlaceholder": "example.com",
-    "requestTimedOut": "Request timed out ({seconds}s)",
-    "networkError": "Network error",
-    "formatted": "Formatted",
-    "rawJson": "JSON",
-    "cacheMiss": "cache miss",
-    "cacheHit": "cache hit",
-    "latency": "Latency",
-    "cost": "Cost",
-    "results": "Results",
-    "rerank": "Rerank",
-    "rerankModel": "Rerank Model",
-    "positionDelta": "Position Change",
-    "emptyState": "Send a search query to see results",
-    "copy": "Salin",
-    "resetToDefault": "Atur ulang ke default",
-    "tabSearch": "Search",
-    "tabScrape": "Scrape",
-    "tabCompare": "Compare",
-    "modalitiesGuide": "Modalities guide",
-    "searchConceptTitle": "Search",
-    "searchConceptDesc": "Search = fetches a list of web results (title, URL, snippet, relevance score)",
-    "scrapeConceptTitle": "Scrape",
-    "scrapeConceptDesc": "Scrape = extracts the full content of a URL (markdown, text or HTML)",
-    "compareConceptTitle": "Compare",
-    "compareConceptDesc": "Compare = runs the same query across N providers side-by-side to compare latency, cost and result overlap",
-    "rerankConceptTitle": "Rerank",
-    "rerankConceptDesc": "Rerank = reorders results via LLM to improve relevance based on the query",
-    "autoConceptTitle": "Auto (cheapest)",
-    "autoConceptDesc": "Auto (cheapest) = automatically picks the cheapest available provider with configured credentials",
-    "providerCatalogTitle": "Provider Catalog",
-    "kindSearch": "Search",
-    "kindFetch": "Fetch/Scrape",
-    "statusConfigured": "Configured",
-    "statusMissing": "No credential",
-    "statusRateLimited": "Rate limited",
-    "configureProvider": "Configure in Providers",
-    "loadingProviders": "Loading providers…",
-    "failedToLoadProviders": "Failed to load providers",
-    "costPerQuery": "Cost/query",
-    "freeQuota": "Free quota/mo",
-    "scrapeUrl": "URL to scrape",
-    "scrapeUrlPlaceholder": "https://example.com",
-    "scrapeUrlRequired": "URL wajib diisi",
-    "scrapeUrlInvalid": "URL tidak valid — harus dimulai dengan http:// atau https://",
-    "scrapeExtract": "Extract",
-    "scrapeExtracting": "Extracting…",
-    "scrapeFullPage": "Full page",
-    "scrapeFormat": "Format",
-    "formatMarkdown": "Markdown",
-    "formatHtml": "HTML",
-    "formatText": "Text",
-    "scrapePreview": "Preview",
-    "scrapeRaw": "Raw",
-    "scrapeContentTruncated": "(truncated, view raw)",
-    "scrapeMetadata": "Metadata",
-    "scrapeProvider": "Provider",
-    "scrapeSize": "Size",
-    "scrapeEmptyState": "Masukkan URL untuk mengekstrak kontennya",
-    "scrapeProvidersAvailable": "Penyedia yang tersedia: Firecrawl, Jina Reader, Tavily, TinyFish.",
-    "compareRun": "Compare",
-    "compareRunning": "Comparing…",
-    "autoProvider": "Auto (cheapest)",
-    "configuredStatus": "Configured",
-    "rateLimitedStatus": "Rate limited",
-    "noCredential": "No credential",
-    "searchTypeLabel": "Type",
-    "rerankModelLabel": "Rerank model",
-    "noneOption": "None",
-    "size": "Size",
-    "configurationPane": "Panel konfigurasi",
-    "configuration": "Konfigurasi",
-    "status": "Status",
-    "compareProviderHint": "Pilih hingga 4 penyedia pada tab Bandingkan untuk membandingkannya secara berdampingan.",
-    "history": "Riwayat",
-    "historyHint": "Riwayat tersedia pada tab Cari.",
-    "noActiveProvider": "Tidak ada penyedia pencarian yang aktif",
-    "configureMoreProviders": "Konfigurasikan lebih banyak penyedia",
-    "links": "Tautan",
-    "contentTruncated": "Konten dipotong menjadi 256 KB (ukuran asli: {size})",
-    "viewFullRaw": "Lihat konten mentah selengkapnya",
-    "rawScrapedContent": "Konten mentah hasil ekstraksi",
-    "rawContent": "Konten mentah — {size}",
-    "closeRawModal": "Tutup modal konten mentah",
-    "httpError": "Galat {status}",
-    "failed": "Gagal",
-    "requestFailed": "Permintaan gagal",
-    "embedding": "Penyematan",
-    "embeddingSample": "Halo, dunia!",
-    "image": "Gambar",
-    "imageSample": "Pemandangan tenang dengan pegunungan saat matahari terbenam",
-    "music": "Musik",
-    "musicSample": "Piano jazz yang ceria dengan perkusi ringan",
-    "noAudioUrl": "Tidak ada URL audio dalam respons: {response}",
-    "documentUrl": "URL Dokumen",
-    "fileTooLarge25Mb": "Berkas terlalu besar — maks. 25 MB",
-    "selectAudioFirst": "Silakan pilih berkas audio terlebih dahulu.",
-    "speechToText": "Ucapan ke Teks",
-    "chooseFile": "Pilih berkas…",
-    "audioFormats25Mb": "mp3, wav, m4a, ogg, flac — maks. 25 MB",
-    "textToSpeech": "Teks ke Ucapan",
-    "ttsSample": "Halo, ini adalah pengujian teks-ke-ucapan.",
-    "video": "Video",
-    "videoSample": "Selang waktu awan di atas pegunungan",
-    "webFetch": "Web Fetch",
-    "webSearchSample": "Apa itu OmniRoute AI gateway?",
-    "noActiveProviderDescription": "Tidak ada penyedia pencarian aktif. Konfigurasikan satu di Penyedia.",
-    "configureProviders": "Konfigurasikan penyedia",
-    "compareQuery": "Kueri untuk dibandingkan",
-    "compareQueryPlaceholder": "tren kecerdasan buatan 2026",
-    "selectedProviders": "Penyedia ({count} dipilih):",
-    "selectAll": "Pilih semua",
-    "clear": "Bersihkan",
-    "maxCompareProviders": "Maksimal {count} penyedia dapat dibandingkan sekaligus.",
-    "compareResults": "Hasil — “{query}”",
-    "resultCount": "{count} hasil",
-    "noResults": "Tidak ada hasil",
-    "sharedResultTitle": "Sama dengan penyedia lain",
-    "sharedResult": "Sama",
-    "overlapSummary": "{first} vs {second}: {overlap} sama",
-    "compareEmptyTitle": "Pilih penyedia dan masukkan kueri untuk dibandingkan",
-    "compareEmptyDescription": "Hasil akan ditampilkan berdampingan dengan latensi, biaya, dan tumpang tindih URL"
-  },
-  "cliTools": {
-    "title": "CLI Tools",
-    "classifierCompatTitle": "Kompatibilitas pengklasifikasi izin otomatis",
-    "classifierCompatDescription": "Hubung-singkatkan pengklasifikasi keamanan <code>--permission-mode auto</code> Claude Code dengan respons izin sintetis sehingga rute fallback tidak gagal tertutup. Nonaktif secara default.",
-    "classifierCompatCycle": "Siklus: nonaktif → otomatis → selalu",
-    "classifierCompatLoadFailed": "Gagal memuat setelan",
-    "classifierCompatMode": {
-      "off": "Nonaktif",
-      "auto": "Otomatis",
-      "always": "Selalu"
-    },
-    "ccDiscoveryInfoButton": "Cara mengaktifkan penemuan di Claude Code",
-    "ccDiscoveryInfoTooltip": "Iklankan model non-Claude di bawah claude/&lt;provider&gt;/&lt;model&gt; ID cermin agar penemuan model gateway Claude Code dapat mencantumkannya. Menggandakan entri katalog untuk semua klien saat diaktifkan secara global.",
-    "ccDiscoveryInfoLink": "Buka Fitur Bendera",
-    "ccOnboardingTitle": "settings.json untuk penemuan model gateway",
-    "ccOnboardingCopy": "Salin",
-    "ccOnboardingCopied": "Disalin",
-    "ccOnboardingKeyPlaceholder": "<kunci API OmniRoute Anda>",
-    "ccOnboardingWindowNote": "Claude Code mengasumsikan jendela konteks 200K untuk setiap ID model yang tidak dikenalnya. Untuk model dengan jendela nyata yang berbeda, tambahkan CLAUDE_CODE_AUTO_COMPACT_WINDOW tepat di bawahnya agar kompak otomatis tidak aktif terlalu awal.",
-    "failedSave": "Gagal menyimpan",
-    "profileSyncTitle": "Sinkronisasi otomatis profil CLI",
-    "profileSyncDescription": "Setelah model penyedia disinkronkan, buat ulang profil alat CLI secara otomatis dari katalog langsung. Nonaktif secara default — hanya berkas profil yang ditulis; konfigurasi aktif/default tidak pernah diubah.",
-    "profileSyncLoadFailed": "Gagal memuat setelan",
-    "codexProfiles": "Profil Codex",
-    "codexProfilesDescription": "Buat ulang ~/.codex/*.config.toml setelah penemuan model.",
-    "claudeProfiles": "Profil Claude Code",
-    "claudeProfilesDescription": "Buat ulang setiap ~/.claude/profiles/…/settings.json setelah penemuan model.",
-    "noActiveProviders": "No active providers",
-    "noActiveProvidersDesc": "Please add and connect providers first to configure CLI tools.",
-    "mapModels": "Map Models",
-    "testConnection": "Test Connection",
-    "connectionStatus": "Connection Status",
-    "configureEndpoint": "Configure Endpoint",
-    "instructions": "Instructions",
-    "modelMapping": "Model Mapping",
-    "reasoningEffort": "Upaya penalaran untuk {model}",
-    "effortNone": "Tidak ada",
-    "effortLow": "Rendah",
-    "effortMedium": "Sedang",
-    "effortHigh": "Tinggi",
-    "effortExtraHigh": "Ekstra tinggi",
-    "effortMax": "Maks",
-    "effortUltra": "Ultra",
-    "wireApi": "Wire API",
-    "modelAliases": "Alias model",
-    "addModel": "Tambah model",
-    "routeModelPlaceholder": "Rute {model} ke...",
-    "baseUrl": "Base URL",
-    "apiKey": "API Key",
-    "configured": "Configured",
-    "notConfigured": "Not configured",
-    "notInstalled": "Not installed",
-    "custom": "Custom",
-    "unknown": "Unknown",
-    "lastSavedAt": "Last saved: {date}",
-    "never": "Never",
-    "justNow": "just now",
-    "minutesAgoShort": "{count}m ago",
-    "hoursAgoShort": "{count}h ago",
-    "daysAgoShort": "{count}d ago",
-    "monthsAgoShort": "{count}mo ago",
-    "yearsAgoShort": "{count}y ago",
-    "runtimeCheckFailed": "Runtime check failed",
-    "yourApiKeyPlaceholder": "your-api-key",
-    "modelPlaceholder": "provider/model-id",
-    "configurationSaved": "Configuration saved successfully.",
-    "failedToSave": "Failed to save configuration.",
-    "noApiKeysCreateOne": "No API keys - Create one in Keys page",
-    "defaultOmnirouteKey": "sk_omniroute (default)",
-    "selectModel": "Select Model",
-    "selectModelForAlias": "Select model for {alias}",
-    "selectModelForTool": "Select Model for {tool}",
-    "select": "Select",
-    "clear": "Clear",
-    "comingSoon": "Coming soon",
-    "checkingRuntime": "Checking runtime status...",
-    "guideOnlyIntegration": "Guide-only integration (no local runtime required)",
-    "cliRuntimeDetected": "CLI runtime detected and ready",
-    "cliFoundNotRunnable": "CLI found but not runnable{reason}",
-    "cliRuntimeNotDetected": "CLI runtime not detected",
-    "binary": "Binary",
-    "configPath": "Config path",
-    "configPathShort": "Config",
-    "failedCheckRuntimeStatus": "Failed to check runtime status.",
-    "copy": "Copy",
-    "copied": "Copied",
-    "copyConfig": "Copy Config",
-    "saveConfig": "Save Config",
-    "selectionSaved": "Selection saved",
-    "guide": "Guide",
-    "detected": "Detected",
-    "notReady": "Not ready",
-    "active": "Active",
-    "inactive": "Inactive",
-    "startMitm": "Start MITM",
-    "stopMitm": "Stop MITM",
-    "mitmStarted": "MITM started successfully!",
-    "mitmStopped": "MITM stopped successfully!",
-    "failedStart": "Failed to start MITM",
-    "failedStop": "Failed to stop MITM",
-    "saveMappings": "Save Mappings",
-    "mappingsSaved": "Mappings saved!",
-    "failedSaveMappings": "Failed to save mappings",
-    "reasoningEffortDefault": "Bawaan",
-    "reasoningEffortHint": "Bawaan mempertahankan upaya penalaran yang dikirim oleh agen",
-    "reasoningEffortTier": {
-      "none": "Tidak ada",
-      "low": "Rendah",
-      "medium": "Sedang",
-      "high": "Tinggi",
-      "xhigh": "Ekstra Tinggi"
-    },
-    "howItWorks": "How it works:",
-    "antigravityHowWorksDesc": "Antigravity sends requests to Google's endpoint. MITM intercepts and redirects them to OmniRoute.",
-    "antigravityStep1": "1. Start MITM to route requests through OmniRoute.",
-    "antigravityStep2Prefix": "2. Add",
-    "antigravityStep2Suffix": "to your hosts file as 127.0.0.1.",
-    "antigravityStep3": "3. Open Antigravity and requests will be proxied.",
-    "mitmHowWorksDesc": "{toolName} sends requests to its provider endpoint. MITM intercepts and redirects them to OmniRoute.",
-    "mitmStep1": "1. Start MITM to route requests through OmniRoute.",
-    "mitmStep2Prefix": "2. Add",
-    "mitmStep2Suffix": "to your hosts file as 127.0.0.1.",
-    "mitmStep3": "3. Open {toolName} and requests will be proxied.",
-    "sudoPasswordRequiredTitle": "Sudo Password Required",
-    "sudoPasswordHint": "Administrator password is required to modify hosts file and system proxy settings.",
-    "enterSudoPassword": "Enter sudo password",
-    "sudoPasswordRequiredError": "Sudo password is required.",
-    "cancel": "Cancel",
-    "confirm": "Confirm",
-    "settingsApplied": "Settings applied successfully!",
-    "failedApplySettings": "Failed to apply settings",
-    "settingsReset": "Settings reset successfully!",
-    "failedResetSettings": "Failed to reset settings",
-    "backupRestored": "Backup restored!",
-    "failedRestore": "Failed to restore",
-    "checkingCli": "Checking {tool} CLI...",
-    "cliNotRunnable": "{tool} CLI installed but not runnable",
-    "cliNotInstalled": "{tool} CLI not installed",
-    "cliNotDetected": "{tool} CLI not detected",
-    "cliDetectedReady": "{tool} CLI detected and ready",
-    "cliFoundFailedHealthcheck": "{tool} CLI was found but failed runtime healthcheck{reason}.",
-    "installCliPrompt": "Please install {tool} CLI to use this feature.",
-    "installCodexPrompt": "Please install Codex CLI to use auto-apply feature.",
-    "hide": "Hide",
-    "howToInstall": "How to Install",
-    "installationGuide": "Installation Guide",
-    "platforms": "macOS / Linux / Windows:",
-    "afterInstallationRun": "After installation, run",
-    "toVerify": "to verify.",
-    "current": "Current",
-    "baseUrlPlaceholder": "https://.../v1",
-    "resetToDefault": "Reset to default",
-    "providerModelPlaceholder": "provider/model-id",
-    "apply": "Apply",
-    "reset": "Reset",
-    "manualConfig": "Manual Config",
-    "backups": "Backups",
-    "configBackups": "Config Backups",
-    "noBackupsYet": "No backups yet. Backups are created automatically before each Apply or Reset.",
-    "restore": "Restore",
-    "backupRestoredReloading": "Backup restored! Reloading status...",
-    "failedRestoreBackup": "Failed to restore backup",
-    "applied": "Applied!",
-    "failed": "Failed",
-    "resetDone": "Reset!",
-    "omnirouteConfiguredOpenAiCompatible": "OmniRoute is configured as OpenAI-compatible provider",
-    "provider": "Provider",
-    "model": "Model",
-    "providers": "Providers",
-    "auth": "Auth",
-    "noApiKeysAvailable": "No API keys available",
-    "usingDefaultOmniroute": "Using default: sk_omniroute",
-    "updateConfig": "Update Config",
-    "applyConfig": "Apply Config",
-    "noBackupsAvailable": "No backups available.",
-    "profileSaved": "Profile \"{name}\" saved!",
-    "failedSaveProfile": "Failed to save profile",
-    "profileActivated": "Profile activated!",
-    "failedActivateProfile": "Failed to activate profile",
-    "profiles": "Profiles",
-    "savedProfiles": "Saved Profiles",
-    "noProfilesYet": "No profiles saved yet. Save current config as a profile below.",
-    "activate": "Activate",
-    "deleteProfile": "Delete profile",
-    "profileNamePlaceholder": "Profile name (e.g. Personal Account)",
-    "saveCurrent": "Save Current",
-    "codexAuthNotePrefix": "Codex uses",
-    "codexAuthNoteMiddle": "with",
-    "codexAuthNoteSuffix": "Click \"Apply\" to auto-configure.",
-    "claudeManualConfiguration": "Claude CLI - Manual Configuration",
-    "codexManualConfiguration": "Codex CLI - Manual Configuration",
-    "droidManualConfiguration": "Factory Droid - Manual Configuration",
-    "openClawManualConfiguration": "Open Claw - Manual Configuration",
-    "clineManualConfiguration": "Cline Manual Configuration",
-    "kiloManualConfiguration": "Kilo Code Manual Configuration",
-    "whenToUseLabel": "When to use",
-    "openToolDocs": "Open tool docs",
-    "toolUseCases": {
-      "claude": "Use when you want strong planning workflows and long multi-file refactors with Claude Code.",
-      "codex": "Use when your team is standardized on OpenAI Codex CLI flows and profile-based auth.",
-      "droid": "Use when you need a lightweight terminal agent focused on fast coding and command execution loops.",
-      "openclaw": "Use when you want an Open Claw style coding agent but routed through OmniRoute policies.",
-      "cline": "Use when you configure coding agents inside editors and want guided setup with OmniRoute models.",
-      "kilo": "Use when your workflow depends on Kilo Code commands and fast iterative edits.",
-      "cursor": "Use when coding in Cursor and you need custom OpenAI-compatible models through OmniRoute.",
-      "continue": "Use when running Continue in IDEs and you need portable JSON-based provider configuration.",
-      "opencode": "Use when you prefer terminal-native agent runs and scripted automation via OpenCode.",
-      "kiro": "Use when integrating Kiro and controlling model routing centrally from OmniRoute.",
-      "windsurf": "Use when you want an AI-first IDE with Codeium/Windsurf models routed through OmniRoute.",
-      "antigravity": "Use when Antigravity/Kiro traffic must be intercepted through MITM and routed to OmniRoute.",
-      "copilot": "Use when you want Copilot chat style UX while enforcing OmniRoute keys and routing rules.",
-      "amp": "Use when you want Amp shorthand workflows but still need OmniRoute alias and routing rules enforcement.",
-      "hermes": "Use when you need a lightweight terminal-native AI assistant for quick tasks.",
-      "hermes-agent": "Gunakan saat Anda memerlukan Hermes Agent (oleh Nousresearch) dengan model bawaan, delegasi, visi, dan tambahan yang dirutekan melalui OmniRoute.",
-      "custom": "Use for custom tool implementations or generic OpenAI-compatible configurations."
-    },
-    "toolDescriptions": {
-      "antigravity": "Google Antigravity IDE with MITM",
-      "claude": "Anthropic Claude Code CLI",
-      "codex": "OpenAI Codex CLI",
-      "grok-build": "Agen pengodean TUI xAI Grok Build dengan dukungan penyedia kustom",
-      "droid": "Factory Droid AI Assistant",
-      "openclaw": "Open Claw AI Assistant",
-      "cline": "Cline AI Coding Assistant CLI",
-      "kilo": "Kilo Code AI Assistant CLI",
-      "qwen": "Qwen Code CLI",
-      "cursor": "Cursor AI Code Editor",
-      "continue": "Continue AI Assistant",
-      "opencode": "OpenCode AI coding agent (Terminal)",
-      "kiro": "Amazon Kiro — AI-powered IDE",
-      "windsurf": "Windsurf AI Code Editor",
-      "copilot": "GitHub Copilot AI Assistant",
-      "amp": "Sourcegraph Amp coding assistant CLI",
-      "hermes": "Hermes AI Terminal Assistant",
-      "hermes-agent": "Hermes Agent (oleh Nousresearch) - AI terminal tingkat lanjut dengan dukungan multi-model (delegasi, visi, kompresi, dll.)",
-      "custom": "Generic OpenAI-compatible CLI or SDK configuration generator",
-      "aider": "CLI pemrograman berpasangan Aider AI dengan URL dasar yang kompatibel dengan OpenAI",
-      "forge": "CLI agen pengodean ForgeCode dengan penyedia kustom",
-      "cursor-cli": "CLI Cursor Agent dalam mode agen headless",
-      "roo": "Asisten AI Roo Code untuk VS Code",
-      "jcode": "agen pengodean terminal jcode",
-      "deepseek-tui": "Agen pengodean TUI DeepSeek yang ditulis dalam Rust",
-      "codewhale": "Agen pengodean CodeWhale, penerus DeepSeek TUI",
-      "smelt": "CLI agen pengodean Smelt",
-      "pi": "Agen pengodean terminal Pi yang ringan",
-      "crush": "Agen pengodean terminal Crush oleh Charm",
-      "goose": "CLI agen otonom Goose",
-      "interpreter": "CLI agen pengodean otonom Open Interpreter",
-      "omp": "Agen pengodean terminal Oh My Pi",
-      "letta": "Agen CLI Letta dengan memori persisten dan penggunaan alat",
-      "prime-agent": "Prime Agent — self-improving RLM coding harness with OpenAI-compatible provider support",
-      "warp": "Terminal Warp AI dengan dukungan penyedia kustom",
-      "agent-deck": "Orkestrator multi-agen Agent Deck",
-      "5dive": "5dive — armada agen coding yang di-host sendiri; satu profil auth mengarahkan semuanya ke OmniRoute"
-    },
-    "guides": {
-      "cursor": {
-        "notes": {
-          "0": "Requires Cursor Pro account to use this feature.",
-          "1": "Cursor routes requests through its own server, so local endpoint is not supported. Please enable Cloud Endpoint in Settings."
-        },
-        "steps": {
-          "1": {
-            "title": "Open Settings",
-            "desc": "Go to Settings -> Models"
-          },
-          "2": {
-            "title": "Enable OpenAI API",
-            "desc": "Enable \"OpenAI API key\" option"
-          },
-          "3": {
-            "title": "Base URL"
-          },
-          "4": {
-            "title": "API Key"
-          },
-          "5": {
-            "title": "Add Custom Model",
-            "desc": "Click \"View All Model\" -> \"Add Custom Model\""
-          },
-          "6": {
-            "title": "Select Model"
-          }
-        }
-      },
-      "continue": {
-        "steps": {
-          "1": {
-            "title": "Open Config",
-            "desc": "Open Continue configuration file"
-          },
-          "2": {
-            "title": "API Key"
-          },
-          "3": {
-            "title": "Select Model"
-          },
-          "4": {
-            "title": "Add Model Config",
-            "desc": "Add the following configuration to your models array:"
-          }
-        },
-        "notes": {
-          "0": "Continue uses JSON config file."
-        }
-      },
-      "opencode": {
-        "steps": {
-          "1": {
-            "title": "Install OpenCode",
-            "desc": "Install via npm: npm install -g opencode-ai"
-          },
-          "2": {
-            "title": "API Key"
-          },
-          "3": {
-            "title": "Set Base URL",
-            "desc": "opencode config set baseUrl {baseUrl}"
-          },
-          "4": {
-            "title": "Select Model"
-          },
-          "5": {
-            "title": "Use Thinking Variant",
-            "desc": "For thinking models, run with --variant high/low/max (example command below)."
-          }
-        },
-        "notes": {
-          "0": "OpenCode requires API key configuration.",
-          "1": "Set the base URL to your OmniRoute endpoint."
-        }
-      },
-      "kiro": {
-        "steps": {
-          "1": {
-            "title": "Open Kiro Settings",
-            "desc": "Go to Settings → AI Provider"
-          },
-          "2": {
-            "title": "Base URL",
-            "desc": "Paste your OmniRoute endpoint URL"
-          },
-          "3": {
-            "title": "API Key"
-          },
-          "4": {
-            "title": "Select Model"
-          }
-        },
-        "notes": {
-          "0": "Kiro requires Amazon account."
-        }
-      },
-      "windsurf": {
-        "steps": {
-          "1": {
-            "title": "Open AI Settings",
-            "desc": "Click the AI Settings icon in Windsurf or go to Settings"
-          },
-          "2": {
-            "title": "Add Custom Provider",
-            "desc": "Select \"Add custom provider\" (OpenAI-compatible)"
-          },
-          "3": {
-            "title": "Base URL",
-            "desc": "http://127.0.0.1:20128/v1"
-          },
-          "4": {
-            "title": "API Key",
-            "desc": "Select your OmniRoute API key"
-          },
-          "5": {
-            "title": "Select Model",
-            "desc": "Choose a model from the dropdown"
-          }
-        }
-      }
-    },
-    "autoConfiguredTab": "Auto-Configured",
-    "toolCategoriesDesc": "Configure AI coding assistants to route through OmniRoute",
-    "allToolsTab": "All Tools",
-    "guidedClientsTab": "Guided Clients",
-    "mitmClientsTab": "MITM Clients",
-    "customCliTab": "CLI khusus",
-    "toolCategories": "Tool Categories",
-    "visibleToolsCount": "{count} tools available",
-    "customCliBuilderTitle": "Pembuat CLI yang kompatibel dengan OpenAI",
-    "customCliBuilderDescription": "Hasilkan env vars dan cuplikan JSON untuk CLI atau SDK apa pun yang menerima URL dasar, kunci API, dan ID model yang kompatibel dengan OpenAI.",
-    "customCliNoModels": "Hubungkan setidaknya satu penyedia untuk mengisi pemilih model.",
-    "customCliNameLabel": "nama CLI",
-    "customCliNamePlaceholder": "misalnya CLI Tim saya",
-    "customCliDefaultModelLabel": "Model bawaan",
-    "customCliDefaultModelHelp": "Gunakan ID atau kombo model OmniRoute apa pun. Kebanyakan CLI yang kompatibel dengan OpenAI hanya memerlukan URL dasar /v1 ditambah string model.",
-    "customCliKeyHelper": "Untuk instalasi lokal OmniRoute dapat menggunakan sk_omniroute. Dalam mode cloud, pilih salah satu kunci API manajemen Anda.",
-    "customCliAliasMappingsLabel": "Pemetaan alias",
-    "customCliAliasMappingsHelp": "Alias pembantu opsional untuk skrip pembungkus atau file konfigurasi yang menginginkan nama steno yang stabil.",
-    "customCliAddAlias": "Tambahkan alias",
-    "customCliNoMappings": "Belum ada pemetaan alias. Tambahkan satu jika skrip pembungkus atau tim Anda menggunakan nama pendek yang stabil.",
-    "customCliAliasPlaceholder": "misalnya ulasan",
-    "customCliTargetModelLabel": "Model sasaran",
-    "customCliEndpointHintLabel": "Cara menyambungkan titik akhir",
-    "customCliEndpointHint": "Arahkan klien yang kompatibel dengan OpenAI ke URL dasar OmniRoute /v1. Titik akhir penyelesaian obrolan mentah adalah {endpoint}. Gunakan blok JSON saat alat menginginkan objek penyedia, atau skrip env saat membaca variabel OPENAI_*.",
-    "customCliEnvBlockTitle": "Cuplikan env / shell",
-    "customCliJsonBlockTitle": "Blok JSON penyedia",
-    "networkError": "Galat jaringan",
-    "other": "Lainnya",
-    "preview": "Pratinjau",
-    "refreshAll": "Segarkan semua",
-    "hermesRoleDefault": "Bawaan (utama)",
-    "hermesRoleDefaultDesc": "Model percakapan utama",
-    "hermesRoleDelegation": "Delegasi (subagen)",
-    "hermesRoleDelegationDesc": "Model orkestrator dan subagen",
-    "hermesRoleVision": "Visi",
-    "hermesRoleVisionDesc": "Pemahaman gambar dan tangkapan layar",
-    "hermesRoleCompression": "Kompresi",
-    "hermesRoleCompressionDesc": "Kompresi dan peringkasan prompt",
-    "hermesRoleWebExtract": "Ekstrak Web",
-    "hermesRoleWebExtractDesc": "Ekstraksi konten halaman web",
-    "hermesRoleSkillsHub": "Hub Keterampilan",
-    "hermesRoleSkillsHubDesc": "Penalaran keterampilan dan penggunaan alat",
-    "hermesRoleApproval": "Persetujuan",
-    "hermesRoleApprovalDesc": "Keputusan keamanan dan persetujuan",
-    "hermesRoleMcp": "MCP",
-    "hermesRoleMcpDesc": "Panggilan alat server MCP",
-    "hermesRoleTitleGeneration": "Generasi Judul",
-    "hermesRoleTitleGenerationDesc": "Generasi Judul Sesi",
-    "hermesRoleMemoryQueryRewrite": "Tulis Ulang Kuery Memori",
-    "hermesRoleMemoryQueryRewriteDesc": "Penulisan ulang kueri pencarian memori",
-    "hermesRoleTtsAudioTags": "Tag Audio TTS",
-    "hermesRoleTtsAudioTagsDesc": "Generasi tag audio TTS",
-    "hermesRoleTriageSpecifier": "Spesifikasi Triage",
-    "hermesRoleTriageSpecifierDesc": "Spesifikasi Triage Isu dan PR",
-    "hermesRoleKanbanDecomposer": "Kanban Decomposer",
-    "hermesRoleKanbanDecomposerDesc": "Dekomposisi tugas Kanban",
-    "hermesRoleProfileDescriber": "Deskripsi Profil",
-    "hermesRoleProfileDescriberDesc": "Deskripsi profil pengguna",
-    "hermesRoleGoalJudge": "Goal Judge",
-    "hermesRoleGoalJudgeDesc": "Penilaian penyelesaian tujuan",
-    "hermesRoleCurator": "Kurator",
-    "hermesRoleCuratorDesc": "Kurasi Keterampilan dan Memori",
-    "hermesRoleMonitor": "Monitor",
-    "hermesRoleMonitorDesc": "Pemantauan Latar Belakang",
-    "hermesRoleBackgroundReview": "Tinjauan Latar Belakang",
-    "hermesRoleBackgroundReviewDesc": "Tinjauan kode latar belakang",
-    "hermesSelectBeforePreview": "Pilih model untuk peran, atau pastikan peran telah dimuat, sebelum melihat pratinjau.",
-    "hermesPreviewFailed": "Gagal membuat pratinjau",
-    "hermesSavedTo": "Disimpan ke {path}",
-    "hermesFirstSetupTitle": "Pertama kali disiapkan melalui OmniRoute pada {date}",
-    "hermesSinceSetup": "{time} sejak penyiapan",
-    "hermesConfiguredRoles": "{configured}/{total} peran",
-    "hermesQuickApply": "Terapkan model yang sama ke semua peran dengan cepat:",
-    "hermesApplyModelToAll": "Terapkan {model} ke setiap peran",
-    "hermesViaOmniRoute": "{provider} (melalui OmniRoute)",
-    "hermesNotOmniRoute": "{provider} (bukan OmniRoute)",
-    "hermesRemovePendingRole": "Hapus peran ini dari perubahan yang tertunda",
-    "hermesApply": "Terapkan ke Hermes Agent",
-    "hermesRolesWillUpdate": "{count, plural, one {# peran akan diperbarui} other {# peran akan diperbarui}}",
-    "hermesPreviewPath": "Pratinjau — akan menulis ke ~/.hermes/config.yaml",
-    "hermesSaveDescription": "Menyimpan model yang dipilih untuk setiap peran ke dalam",
-    "copilotConfigGenerator": "Generator Konfigurasi Salinan GitHub",
-    "copilotGeneratorDescriptionPrefix": "Menghasilkan",
-    "copilotGeneratorDescriptionSuffix": "blok untuk VS Code GitHub Copilot menggunakan pola vendor Azure. Pilih model yang Anda inginkan, lalu salin JSON ke dalam file konfigurasi Anda.",
-    "copilotCompatibilityWarning": "Konfigurasi ini menggunakan solusi vendor Azure untuk daftar model kustom. Diuji dengan <vscode>VS Code ≥ 1.109</vscode> dan <copilot>GitHub Copilot Chat ≥ v0.37</copilot>. Pembaruan ekstensi di masa mendatang dapat mengubah perilaku ini.",
-    "copilotApiKey": "Kunci API",
-    "copilotSelectModels": "Pilih model ({selected}/{total})",
-    "selectAll": "Pilih semua",
-    "loadingModels": "Memuat model...",
-    "advancedOptions": "Opsi lanjutan",
-    "vision": "Visi",
-    "copilotCopyConfigForModels": "Salin konfigurasi ({count, plural, one {# model} other {# model}})",
-    "copilotFilterModelsPlaceholder": "menyaring model...",
-    "copilotMaxInputTokens": "Token Masukan Maks",
-    "copilotMaxOutputTokens": "Token Output Maks",
-    "copilotToolCalling": "Panggilan Alat",
-    "copilotPasteInto": "Tempel ke:",
-    "copilotReloadInstruction": "Kemudian muat ulang VS Code dan atur kunci API di prompt input.",
-    "wireApiChatCompletions": "Penyelesaian Obrolan (/chat/penyelesaian)",
-    "wireApiResponses": "API Respons (/respons)",
-    "cliproxyapiActionFailed": "Tindakan gagal",
-    "cliproxyapiActionSucceeded": "Tindakan berhasil",
-    "cliproxyapiCheckUpdates": "Periksa Pembaruan",
-    "cliproxyapiDescription": "Fallback proxy hulu (OAuth berbasis Go)",
-    "cliproxyapiHealth": "Kesehatan",
-    "cliproxyapiHealthy": "Sehat",
-    "cliproxyapiInstall": "Instal",
-    "cliproxyapiNotInstalledValue": "Tidak terpasang",
-    "cliproxyapiPort": "Port",
-    "cliproxyapiRequestFailed": "Permintaan gagal",
-    "cliproxyapiRestart": "Mulai Ulang",
-    "cliproxyapiStart": "Mulai",
-    "cliproxyapiStatusError": "Kesalahan",
-    "cliproxyapiStatusInstalled": "Terpasang",
-    "cliproxyapiStatusNotInstalled": "Tidak Terpasang",
-    "cliproxyapiStatusRunning": "Sedang Berjalan",
-    "cliproxyapiStatusStopped": "Dihentikan",
-    "cliproxyapiStop": "Berhenti",
-    "cliproxyapiUnhealthy": "Tidak Sehat",
-    "cliproxyapiUnknown": "Tidak Dikenal",
-    "cliproxyapiUpdate": "Perbarui",
-    "cliproxyapiUpdateAvailable": "Pembaruan tersedia: v{current} → v{latest}",
-    "cliproxyapiVersion": "Versi"
-  },
-  "combos": {
-    "title": "Combos",
-    "description": "Create model combos with weighted routing and fallback support",
-    "autoCatalogTitle": "Katalog perutean otomatis",
-    "autoCatalogTemplateCount": "{count} templat",
-    "autoCatalogDescription": "Kombo otomatis/* bawaan diselesaikan secara dinamis dari penyedia yang terhubung. Gunakan salah satu ID ini sebagai bidang model — tidak perlu penyiapan.",
-    "autoCatalogExpand": "Perluas katalog perutean otomatis",
-    "autoCatalogCollapse": "Ciutkan katalog perutean otomatis",
-    "createCombo": "Create Combo",
-    "editCombo": "Edit Combo",
-    "deleteCombo": "Delete Combo",
-    "noModels": "No models",
-    "noModelsYet": "No models added yet",
-    "addModel": "Add Model",
-    "addModelToCombo": "Add Model to Combo",
-    "routingStrategy": "Routing Strategy",
-    "maxRetries": "Max Retries",
-    "timeout": "Timeout (ms)",
-    "healthcheck": "Healthcheck",
-    "priority": "Priority",
-    "fallback": "Fallback",
-    "roundRobin": "Round Robin",
-    "random": "Random",
-    "leastLatency": "Least Latency",
-    "comboName": "Combo Name",
-    "comboNamePlaceholder": "my-combo",
-    "comboDescription": "Deskripsi",
-    "comboDescriptionPlaceholder": "Catatan opsional yang menjelaskan kombo ini",
-    "deleteConfirm": "Delete this combo?",
-    "noCombosYet": "No combos yet",
-    "comboCreated": "Combo created successfully",
-    "comboUpdated": "Combo updated successfully",
-    "comboDeleted": "Combo deleted",
-    "failedCreate": "Failed to create combo",
-    "failedUpdate": "Failed to update combo",
-    "errorCreating": "Error creating combo",
-    "errorUpdating": "Error updating combo",
-    "errorDeleting": "Error deleting combo",
-    "testFailed": "Test request failed",
-    "failedToggle": "Failed to toggle combo",
-    "testResults": "Test Results — {name}",
-    "resolvedBy": "Resolved by:",
-    "more": "+{count} more",
-    "reqs": "reqs",
-    "success": "success",
-    "proxyConfigured": "Proxy configured",
-    "copyComboName": "Copy combo name",
-    "enableCombo": "Enable combo",
-    "disableCombo": "Disable combo",
-    "testCombo": "Test combo",
-    "duplicate": "Duplicate",
-    "proxyConfig": "Proxy configuration",
-    "nameRequired": "Name is required",
-    "nameInvalid": "Only letters, numbers, -, _, / and . allowed",
-    "nameHint": "Letters, numbers, -, _, / and . allowed",
-    "priorityDesc": "Sequential fallback: tries model 1 first, then 2, etc.",
-    "weightedDesc": "Distributes traffic by weight percentage with fallback",
-    "roundRobinDesc": "Circular distribution: each request goes to the next model in rotation",
-    "contextRelay": "Context Relay",
-    "contextRelayDesc": "Preserves session continuity with handoff summaries when accounts rotate",
-    "randomDesc": "Uniform random selection, then fallback to remaining models",
-    "leastUsedDesc": "Picks the model with fewest requests, balancing load over time",
-    "costOptimizedDesc": "Routes to the cheapest model first based on pricing",
-    "cacheOptimizedDesc": "Routes each reusable prompt prefix consistently to the same provider account",
-    "resetAware": "RR Sadar Reset",
-    "resetAwareDesc": "Menyeimbangkan sisa kuota dengan reset 5 jam dan mingguan, lalu menghitung skor serupa secara round-robin",
-    "strictRandom": "Strict Random",
-    "strictRandomDesc": "Shuffle deck — uses each model once before reshuffling",
-    "fusion": "Fusi",
-    "fusionDesc": "Menyebarkan prompt ke setiap model panel secara paralel, lalu model penilai mensintesis satu jawaban akhir",
-    "fusionJudgeModel": "Model penilai",
-    "fusionJudgeModelHelp": "Model yang mensintesis jawaban panel menjadi satu respons akhir. Biarkan kosong untuk menggunakan model panel pertama.",
-    "fusionMinPanel": "Min panel",
-    "fusionMinPanelHelp": "Jawaban panel yang berhasil diperlukan sebelum model yang tertinggal mendapatkan masa tenggang (default 2).",
-    "fusionStragglerGraceMs": "Masa tenggang straggler (ms)",
-    "fusionStragglerGraceMsHelp": "Berapa lama menunggu model panel yang lambat setelah kuorum tercapai (default 8000).",
-    "fusionPanelHardTimeoutMs": "Batas waktu mutlak panel (ms)",
-    "fusionPanelHardTimeoutMsHelp": "Batas mutlak agar satu model yang macet tidak menghentikan seluruh panel (default 90000).",
-    "models": "Models",
-    "autoBalance": "Auto-balance",
-    "advancedSettings": "Advanced Settings",
-    "retryDelay": "Retry Delay (ms)",
-    "concurrencyPerModel": "Concurrency / Model",
-    "queueTimeout": "Queue Timeout (ms)",
-    "contextRelayHandoffThreshold": "Handoff Threshold",
-    "contextRelayHandoffThresholdHelp": "When quota usage reaches this threshold, OmniRoute generates a structured handoff summary before the active account is exhausted.",
-    "contextRelayMaxMessages": "Max Messages For Summary",
-    "contextRelayMaxMessagesHelp": "Limits how much recent history is condensed into the relay summary.",
-    "contextRelaySummaryModel": "Summary Model",
-    "contextRelaySummaryModelHelp": "Optional override model used only for generating the handoff summary. Leave empty to reuse the active combo model.",
-    "contextRelayProviderNote": "Context Relay currently generates handoffs for Codex account rotation. Pair it with multiple accounts of the same provider for the best continuity.",
-    "advancedHint": "Leave empty to use global defaults. These override per-provider settings.",
-    "failoverBeforeRetry": "Failover Sebelum Coba Lagi",
-    "maxSetRetries": "Percobaan Ulang Set Maks",
-    "setRetryDelayMs": "Setel Penundaan Coba Ulang (md)",
-    "moveUp": "Move up",
-    "moveDown": "Move down",
-    "removeModel": "Remove",
-    "saving": "Saving...",
-    "liveNoProviders": "Belum ada penyedia yang teramati.",
-    "liveFleetDataHint": "Data armada masuk melalui peristiwa kombo langsung.",
-    "liveActiveCount": "Aktif ({count})",
-    "liveErrorCount": "Galat ({count})",
-    "liveInactiveCount": "Tidak Aktif ({count})",
-    "liveNoRun": "Tidak ada eksekusi kombo yang tersedia.",
-    "liveDataHint": "Data langsung masuk melalui saluran kombo WebSocket.",
-    "liveDisconnected": "Langsung dinonaktifkan — WebSocket terputus. Menampilkan status terakhir yang diketahui.",
-    "liveSelectCombo": "Pilih kombo",
-    "liveSelectComboPlaceholder": "— pilih kombo —",
-    "liveTargetCount": "{count, plural, one {# target} other {# target}}",
-    "liveSingle": "Tunggal",
-    "liveFleet": "Armada",
-    "playgroundStatusAvailable": "Tersedia",
-    "playgroundStatusNoQuota": "Tidak Ada Kuota",
-    "playgroundStatusDegraded": "Terdegradasi",
-    "playgroundStatusError": "Galat",
-    "playgroundStatusUnknown": "Tidak Diketahui",
-    "playgroundNetworkError": "Galat jaringan selama simulasi",
-    "playgroundTitle": "Playground Kombo",
-    "playgroundDescription": "Simulasikan bagaimana permintaan akan dirutekan melalui kombo Anda",
-    "playgroundConfiguration": "Konfigurasi",
-    "playgroundNoCombosConfigured": "Tidak ada kombo yang dikonfigurasi",
-    "active": "aktif",
-    "inactive": "tidak aktif",
-    "playgroundEstimatedPromptTokens": "Perkiraan Token Prompt",
-    "playgroundSimulating": "Mensimulasikan...",
-    "playgroundSimulateRoute": "Simulasikan Rute",
-    "playgroundRoutingPath": "Jalur Perutean",
-    "playgroundStrategy": "Strategi",
-    "playgroundEstimatedCost": "Perkiraan Biaya",
-    "playgroundEstimatedLatency": "Est. Latensi",
-    "playgroundFallback": "cadangan",
-    "playgroundWeight": "bobot {value}",
-    "playgroundWarningCount": "Peringatan ({count})",
-    "playgroundErrorCount": "Kesalahan ({count})",
-    "playgroundEmptyHint": "Pilih kombo dan klik <strong>Simulasikan Rute</strong> untuk melihat jalur perutean.",
-    "playgroundNoCombosYet": "Belum ada kombo yang dikonfigurasi.",
-    "playgroundCreateFirst": "Buat terlebih dahulu",
-    "weighted": "Weighted",
-    "leastUsed": "Least-Used",
-    "costOpt": "Cost-Opt",
-    "strategyGuideTitle": "How to use this strategy",
-    "strategyGuideWhen": "When to use",
-    "strategyGuideAvoid": "Avoid when",
-    "strategyGuideExample": "Example",
-    "strategyGuide": {
-      "priority": {
-        "when": "You have one preferred model and only want fallback on failure.",
-        "avoid": "You need request distribution across models.",
-        "example": "Primary coding model with cheaper backup for outages."
-      },
-      "weighted": {
-        "when": "You need controlled traffic split across models.",
-        "avoid": "You cannot maintain accurate weights over time.",
-        "example": "80% stable model + 20% canary model rollout."
-      },
-      "round-robin": {
-        "when": "You want predictable and even distribution.",
-        "avoid": "Models differ too much in latency or cost.",
-        "example": "Same model on multiple accounts to spread throughput."
-      },
-      "random": {
-        "when": "You want simple distribution with minimal setup.",
-        "avoid": "You need strict traffic guarantees.",
-        "example": "Quick prototyping with equivalent models."
-      },
-      "least-used": {
-        "when": "You want adaptive balancing based on live demand.",
-        "avoid": "Traffic is too low to benefit from usage balancing.",
-        "example": "Mixed workloads where one model often gets overloaded."
-      },
-      "cost-optimized": {
-        "when": "Cost reduction is your top priority.",
-        "avoid": "Pricing data is missing or outdated.",
-        "example": "Background or batch jobs where lower cost is preferred."
-      },
-      "reset-aware": {
-        "when": "Anda merutekan beberapa akun dengan telemetri kuota dan jendela pengaturan ulang yang berbeda.",
-        "avoid": "Telemetri kuota tidak tersedia untuk sebagian besar akun.",
-        "example": "Lebih suka pengaturan ulang akun mingguan 60% besok daripada pengaturan ulang akun 80% nanti."
-      },
-      "strict-random": {
-        "when": "Use when you want perfectly even spread — each model used once before repeating.",
-        "avoid": "Avoid when models have different quality or latency and order matters.",
-        "example": "Example: Multiple accounts of the same model to distribute usage evenly."
-      },
-      "p2c": {
-        "when": "Use when you want low-latency selection using Power-of-Two-Choices algorithm.",
-        "avoid": "Avoid for small combos with 2 or fewer models — no benefit over round-robin.",
-        "example": "Example: High-throughput inference across 4+ equivalent model endpoints."
-      },
-      "context-relay": {
-        "when": "Use when long sessions must survive account rotation without losing the working context.",
-        "avoid": "Avoid when account switching is rare or when you do not want extra summarization requests.",
-        "example": "Example: Codex sessions that rotate across multiple accounts near quota exhaustion."
-      },
-      "fill-first": {
-        "when": "Use when you want to fully exhaust one provider's quota before moving to the next.",
-        "avoid": "Avoid when you need request-level load balancing across providers.",
-        "example": "Example: Use all $200 Deepgram credits before falling back to Groq."
-      },
-      "auto": {
-        "when": "Use when you need multi-factor scoring routing based on cost, latency, and quality.",
-        "avoid": "Avoid when you need strict priority ordering or historical persistence.",
-        "example": "Example: Balance requests across models with different strengths."
-      },
-      "lkgp": {
-        "when": "Use when you want to route based on historical success rates and performance.",
-        "avoid": "Avoid when historical data is limited or unreliable.",
-        "example": "Example: Route to models with a good track record on specific tasks."
-      },
-      "context-optimized": {
-        "when": "Use when you need to optimize context window usage across models.",
-        "avoid": "Avoid when models have similar context lengths or tasks are simple.",
-        "example": "Example: Distribute long conversations across models with larger context windows."
-      }
-    },
-    "advancedHelp": {
-      "maxRetries": "How many retries are attempted before failing a request.",
-      "retryDelay": "Initial wait between retries. Higher values reduce burst pressure.",
-      "timeout": "Maximum request duration before aborting.",
-      "healthcheck": "Skips unhealthy models/providers from routing decisions.",
-      "concurrencyPerModel": "Max simultaneous requests allowed per model in round-robin.",
-      "queueTimeout": "How long a request can wait in queue before timing out.",
-      "failoverBeforeRetry": "Jika diaktifkan, kesalahan upstream apa pun akan langsung memicu failover ke target kombo berikutnya, sehingga melewatkan semua percobaan ulang dan URL cadangan.",
-      "maxSetRetries": "Berapa kali untuk mencoba kembali set target penuh ketika setiap target gagal. 0 = tidak ada percobaan ulang pada tingkat set.",
-      "setRetryDelayMs": "Penundaan antara upaya percobaan ulang tingkat set, memberikan waktu untuk menyelesaikan masalah sementara.",
-      "disableSessionStickiness": "Beralih ke koneksi yang berbeda pada setiap permintaan alih-alih menyematkan seluruh percakapan ke satu koneksi berdasarkan hash pesan pertama. Mengesampingkan default global. Biarkan pada Warisi untuk mempertahankan hit prompt-cache untuk obrolan multi-putaran."
-    },
-    "templatesTitle": "Quick templates",
-    "templatesDescription": "Apply a starting profile, then adjust models and config.",
-    "templateApply": "Apply template",
-    "templateHighAvailability": "High availability",
-    "templateHighAvailabilityDesc": "Priority routing with health checks and safe retries.",
-    "templateCostSaver": "Cost saver",
-    "templateCostSaverDesc": "Cost-optimized routing for budget-first workloads.",
-    "templateBalanced": "Balanced load",
-    "templateBalancedDesc": "Least-used routing to spread demand over time.",
-    "usageGuideHide": "Hide",
-    "usageGuideDontShowAgain": "Don't show again",
-    "usageGuideShow": "Show guide",
-    "quickTestTitle": "Combo ready to validate",
-    "quickTestDescription": "Run a test now to confirm fallback and latency behavior.",
-    "testNow": "Test now",
-    "pricingCoverage": "Pricing coverage",
-    "pricingCoverageHint": "Cost-optimized works best when all combo models have pricing.",
-    "pricingAvailable": "Pricing available",
-    "pricingMissing": "No pricing",
-    "pricingAvailableShort": "priced",
-    "pricingMissingShort": "no-price",
-    "fallbackOnlyOnQuotaExhaustion": "Hanya maju saat kuota habis",
-    "fallbackOnlyOnQuotaExhaustionShort": "fallback hanya kuota",
-    "warningRoundRobinSingleModel": "Round-robin is most useful with at least 2 models.",
-    "warningCostOptimizedPartialPricing": "Only {priced} of {total} models have pricing. Routing may be partially cost-aware.",
-    "warningCostOptimizedNoPricing": "No pricing data found for this combo. Cost-optimized may route unexpectedly.",
-    "filterAll": "All",
-    "filterIntelligent": "Intelligent",
-    "filterDeterministic": "Deterministic",
-    "filterEmptyTitle": "No combos match this strategy filter.",
-    "filterEmptyIntelligentDescription": "Create an auto or LKGP combo to populate the intelligent routing dashboard.",
-    "filterEmptyDeterministicDescription": "Only auto and LKGP combos exist right now. Switch back to All or create a deterministic combo.",
-    "readinessTitle": "Ready to save?",
-    "readinessDescription": "Review the checklist before creating or updating this combo.",
-    "readinessCheckName": "Combo name is valid",
-    "readinessCheckModels": "At least one model is selected",
-    "readinessCheckWeights": "Weighted total is 100%",
-    "readinessCheckWeightsOptional": "Weight rule not required",
-    "readinessCheckPricing": "Pricing data is available",
-    "readinessCheckPricingOptional": "Pricing rule not required",
-    "saveBlockedTitle": "Save is blocked until the following items are fixed:",
-    "saveBlockName": "Define a combo name.",
-    "saveBlockModels": "Add at least one model.",
-    "saveBlockWeighted": "Set weights to 100% (current: {total}%).",
-    "saveBlockPricing": "Add pricing for at least one model or choose a different strategy.",
-    "recommendationsLabel": "Recommended setup",
-    "applyRecommendations": "Apply recommendations",
-    "recommendationsUpdated": "Recommendations updated for {strategy}.",
-    "recommendationsApplied": "Recommendations applied to this combo.",
-    "intelligentPanelTitle": "Intelligent Routing Dashboard",
-    "intelligentPanelDesc": "Real-time scoring and health status for this auto-routing combo.",
-    "configOnlyStatus": "Tampilan Konfigurasi",
-    "configOnlyHint": "Panel ini hanya menampilkan input perutean. Status pemutus langsung tersedia di halaman Kesehatan.",
-    "routingInputs": "Input Perutean",
-    "routingInputsHint": "Paket mode dan pembobotan tetap di sini; status runtime pemutus tetap di halaman Kesehatan.",
-    "emailVisibilityHint": "Email akun di sini mengikuti pengalihan privasi global.",
-    "emailVisibilityTooltip": "Gunakan ikon mata untuk menampilkan atau menyembunyikan email akun secara global di seluruh layar kombo, penyedia, dan kuota.",
-    "builderModeStep": "Langkah demi langkah (Penyedia → Model)",
-    "builderModeGlobal": "Pencarian model global (Kombinasi kustom)",
-    "builderGlobalSearchPlaceholder": "Cari model di semua penyedia (mis. opus, sonnet, deepseek, kimi, qwen)...",
-    "builderGlobalAddAll": "Tambahkan semua",
-    "builderGlobalShortcuts": "Pintasan:",
-    "builderGlobalNoResults": "Tidak ada model yang ditemukan untuk \"{query}\".",
-    "builderGlobalProviderLabel": "Penyedia:",
-    "builderGlobalAccountCount": "{count, plural, one {# akun} other {# akun}}",
-    "builderGlobalAdded": "Ditambahkan",
-    "builderGlobalAdd": "Tambahkan",
-    "manualModel": "Model manual",
-    "manualModelInvalid": "Masukkan model sebagai provider/model.",
-    "manualModelUnknownProvider": "Awalan penyedia tidak dikenal.",
-    "builderDynamicAccountShort": "Akun dinamis",
-    "builderNeedValidName": "Tentukan nama kombo yang valid sebelum melanjutkan.",
-    "statusOverview": "Status Overview",
-    "normalOperation": "Normal Operation",
-    "allProvidersHealthy": "Providers are reporting healthy routing conditions.",
-    "incidentMode": "Incident Mode",
-    "highCircuitBreakerRate": "High circuit breaker trip rate detected.",
-    "activeModePack": "Active Mode Pack",
-    "modePackUpdated": "Mode pack updated to {pack}.",
-    "modePackHint": "Switch presets to bias the routing engine without rebuilding the combo.",
-    "providerScores": "Provider Scores",
-    "allProvidersEvaluated": "No candidate pool configured. All active providers are evaluated at runtime.",
-    "excludedProviders": "Excluded Providers",
-    "excludedProvidersHint": "Providers with an OPEN circuit breaker are temporarily excluded from routing.",
-    "noExcludedProviders": "No providers are currently excluded.",
-    "cooldownMinutes": "Cooldown: {minutes}m",
-    "builderIntelligentTitle": "Intelligent Routing Configuration",
-    "builderIntelligentDesc": "Configure the multi-factor scoring engine for this auto-routing combo.",
-    "candidatePoolLabel": "Candidate Pool",
-    "candidatePoolHint": "Select which providers this engine should evaluate. Leave empty to use all active providers.",
-    "candidatePoolEmpty": "No active providers available yet.",
-    "candidatePoolAllProviders": "All providers",
-    "modePackLabel": "Mode Pack",
-    "routerStrategyLabel": "Router Strategy",
-    "strategyRules": "Rules (6-Factor Scoring)",
-    "explorationRateLabel": "Exploration Rate",
-    "explorationRateHint": "{percent}% of requests can explore non-optimal providers.",
-    "budgetCapLabel": "Budget Cap (USD / request)",
-    "budgetCapPlaceholder": "No limit",
-    "advancedWeightsTitle": "Advanced: Scoring Weights",
-    "nestedComboFlatten": "Ratakan kombo bersarang",
-    "nestedComboExecute": "Jalankan kombo bersarang sebagai target",
-    "effectiveRoutingShare": "Pangsa perutean efektif (bobot ÷ total)",
-    "weightQuota": "Quota",
-    "weightHealth": "Health",
-    "weightCostInv": "Cost",
-    "weightLatencyInv": "Latency",
-    "weightTaskFit": "Task Fit",
-    "weightStability": "Stability",
-    "weightTierPriority": "Tier",
-    "weightCacheAffinity": "Cache Hit Affinity",
-    "weightSessionAvailability": "Ketersediaan Sesi",
-    "reviewIntelligentTitle": "Intelligent Routing Config",
-    "strategyRecommendations": {
-      "priority": {
-        "title": "Fail-safe baseline",
-        "description": "Use one primary model and keep fallback chain short and reliable.",
-        "tip1": "Put your most reliable model first.",
-        "tip2": "Keep 1-2 backup models with similar quality.",
-        "tip3": "Use safe retries to absorb transient provider failures."
-      },
-      "weighted": {
-        "title": "Controlled traffic split",
-        "description": "Great for canary rollouts and gradual migration between models.",
-        "tip1": "Start with conservative split like 90/10.",
-        "tip2": "Keep the total at 100% and auto-balance after changes.",
-        "tip3": "Monitor success and latency before increasing canary weight."
-      },
-      "round-robin": {
-        "title": "Predictable load sharing",
-        "description": "Best when models are equivalent and you need smooth distribution.",
-        "tip1": "Use at least 2 models.",
-        "tip2": "Set concurrency limits to avoid burst overload.",
-        "tip3": "Use queue timeout to fail fast under saturation."
-      },
-      "random": {
-        "title": "Quick spread with low setup",
-        "description": "Use when you need simple distribution without strict guarantees.",
-        "tip1": "Use models with similar latency profiles.",
-        "tip2": "Keep retries enabled to absorb random misses.",
-        "tip3": "Prefer this for experimentation, not strict SLAs."
-      },
-      "least-used": {
-        "title": "Adaptive balancing",
-        "description": "Routes to less-used models to reduce hotspots over time.",
-        "tip1": "Works better under continuous traffic.",
-        "tip2": "Combine with health checks for safer balancing.",
-        "tip3": "Track per-model usage to validate distribution gains."
-      },
-      "cost-optimized": {
-        "title": "Budget-first routing",
-        "description": "Routes to lower-cost models when pricing metadata is available.",
-        "tip1": "Ensure pricing coverage for all selected models.",
-        "tip2": "Keep a quality fallback for hard prompts.",
-        "tip3": "Use for batch/background jobs where cost is the main KPI."
-      },
-      "reset-aware": {
-        "title": "Rotasi akun yang sadar akan pengaturan ulang",
-        "description": "Menyeimbangkan sisa kuota penyedia dengan waktu reset.",
-        "tip1": "Gunakan langkah akun eksplisit atau perutean tag akun untuk penyedia dengan telemetri kuota.",
-        "tip2": "Sesi penyesuaian vs beban mingguan ketika kelelahan jangka pendek lebih berisiko.",
-        "tip3": "Jaga agar tali pengikatnya tetap kecil sehingga akun-akun yang setara masih dapat berputar dengan adil."
-      },
-      "strict-random": {
-        "title": "Shuffle deck distribution",
-        "description": "Each model is used exactly once per cycle before reshuffling.",
-        "tip1": "Use at least 2 models for meaningful distribution.",
-        "tip2": "Works best with equivalent-performance models.",
-        "tip3": "Ideal for load balancing across multiple API accounts."
-      },
-      "fill-first": {
-        "description": "Exhaust provider quotas sequentially before falling back.",
-        "tip1": "Use for quota-based routing with clear fallback chains.",
-        "tip2": "Set quotas accurately to avoid premature fallback.",
-        "tip3": "Works best with providers offering free tiers or credit buckets.",
-        "title": "Quota Exhaustion"
-      },
-      "auto": {
-        "description": "Route based on real-time scoring for cost, latency, quality, and health.",
-        "tip1": "Let the engine balance multiple factors automatically.",
-        "tip2": "Monitor which factors drive routing decisions in logs.",
-        "tip3": "Use for complex workloads where no single factor dominates.",
-        "title": "Multi-Factor Optimization"
-      },
-      "lkgp": {
-        "description": "Route based on historical performance and success patterns.",
-        "tip1": "Requires sufficient request history for accurate predictions.",
-        "tip2": "Good for workloads with consistent model performance patterns.",
-        "tip3": "Monitor prediction accuracy and adjust weights as needed.",
-        "title": "History-Based Routing"
-      },
-      "context-optimized": {
-        "description": "Optimize routing based on context window usage and token efficiency.",
-        "tip1": "Route long conversations to models with larger context windows.",
-        "tip2": "Monitor context utilization to avoid token waste.",
-        "tip3": "Best for conversational AI requiring extensive context retention.",
-        "title": "Context Optimization"
-      },
-      "context-relay": {
-        "description": "Best when account rotation is expected and the next account must inherit a simplified task summary.",
-        "tip1": "Use with providers rotating accounts for the same model family.",
-        "tip2": "Set handoff threshold below hard quota cutoffs for summary generation time.",
-        "tip3": "Only set a dedicated summary model if the primary is too expensive or unstable.",
-        "title": "Session Continuity Priority"
-      },
-      "p2c": {
-        "description": "Route to the provider with the lowest current load based on real-time metrics.",
-        "tip1": "Monitor provider health metrics for accurate load assessment.",
-        "tip2": "Works best with homogeneous provider pools.",
-        "tip3": "Adjust sensitivity to avoid oscillation during traffic spikes.",
-        "title": "Power of Two Choices"
-      }
-    },
-    "templateFreeStack": "Free Stack ($0)",
-    "templateFreeStackDesc": "Round-robin across all free providers: Kiro (Claude), Qoder (5 models), Qwen (4 models). Zero cost, never stops coding.",
-    "auto": "Intelligent Auto",
-    "autoDesc": "Self-healing smart routing pool with multi-factor scoring",
-    "lkgp": "LKGP Mode",
-    "lkgpDesc": "Prioritizes the last provider that successfully completed a request",
-    "wizardGuideTitle": "Getting Started with Combos",
-    "wizardGuideDesc": "Create model combos to route AI traffic intelligently",
-    "wizardGuideHint": "or click + Create Combo above",
-    "createFirstCombo": "Create Your First Combo",
-    "wizardStep1Title": "Name Your Combo",
-    "wizardStep1Desc": "Give your combo a unique name to identify it in routing rules",
-    "wizardStep2Title": "Add Models",
-    "wizardStep2Desc": "Select AI models and arrange their fallback priority order",
-    "wizardStep3Title": "Choose Strategy",
-    "wizardStep3Desc": "Pick how requests are distributed across your models - 13 strategies available",
-    "wizardStep4Title": "Review & Save",
-    "wizardStep4Desc": "Review your configuration and activate the combo",
-    "usageGuideInvokeTitle": "How to call this combo",
-    "usageGuideInvokeDesc": "Send the combo's exact name as the model, e.g. model: \"my-combo\" (or combo/my-combo).",
-    "usageGuideInvokeAutoNote": "auto and auto/* are a separate zero-config router that does not use your combos (unless a combo is literally named auto).",
-    "usageGuideInvokeOpenrouterNote": "openrouter/auto is a real paid OpenRouter product (Auto Best Available), not an OmniRoute alias — exclude it via Settings → Routing → Hide paid models.",
-    "emailVisibilityStateOn": "On",
-    "emailVisibilityStateOff": "Off",
-    "reorderHandle": "Drag to reorder",
-    "failedReorder": "Failed to reorder models",
-    "builderFlowTitle": "Combo Builder Flow",
-    "builderStage": {
-      "basics": {
-        "label": "Basics",
-        "description": "Name and starting template"
-      },
-      "steps": {
-        "label": "Steps",
-        "description": "Provider, model, and account selection"
-      },
-      "strategy": {
-        "label": "Strategy",
-        "description": "Routing behavior and advanced settings"
-      },
-      "intelligent": {
-        "label": "Smart Routing",
-        "description": "Auto-routing candidate pool, presets, and scoring"
-      },
-      "review": {
-        "label": "Review",
-        "description": "Final validation before saving"
-      }
-    },
-    "builderStageVisited": "Stage completed",
-    "builderStageCurrent": "Current stage",
-    "builderStagePending": "Pending",
-    "builderStageLocked": "Locked — complete previous stage first",
-    "builderTitle": "Build a Combo",
-    "builderBrowseCatalog": "Browse catalog",
-    "builderProvider": "Provider",
-    "builderLoadingProviders": "Loading providers...",
-    "builderSelectProvider": "Select provider",
-    "builderModel": "Model",
-    "builderSelectModel": "Select model",
-    "builderProviderFirst": "Pick provider first",
-    "builderAccount": "Account",
-    "builderPreview": "Preview",
-    "builderAddStep": "Add step",
-    "builderDuplicateExact": "This exact provider/model/account step is already in the combo.",
-    "builderComboRef": "Combo Ref",
-    "builderAddComboRef": "Add combo reference",
-    "builderComboRefStep": "Add combo reference",
-    "builderPinnedAccount": "Pinned Account",
-    "builderLegacyEntry": "Legacy entry",
-    "reviewName": "Name",
-    "reviewStrategy": "Strategy",
-    "reviewSteps": "Steps",
-    "reviewAccounts": "Accounts",
-    "reviewProviders": "Providers",
-    "reviewComboRefs": "Combo References",
-    "reviewAdvanced": "Advanced Settings",
-    "reviewAgentFlags": "Agent Flags",
-    "reviewSequence": "Model Sequence",
-    "reviewNoSteps": "No steps configured",
-    "builderStagesDescription": "Complete each stage in order to define combos, build steps, select routing strategy, and review results.",
-    "builderStepsDescription": "Build each combo step in order: provider, model, then account. This allows reusing the same provider and model across different accounts.",
-    "selectProvider": "Select Provider",
-    "selectProviderPlaceholder": "Select a provider",
-    "selectModel": "Select Model",
-    "selectModelPlaceholder": "Select a provider first",
-    "selectAccount": "Select Account",
-    "selectComboToReference": "Select combo to reference",
-    "comboReference": "Combo Reference",
-    "addComboReference": "Add Combo Reference",
-    "addStepBeforeContinue": "Please add at least one step before proceeding to the next stage.",
-    "previewNextStep": "Preview next step",
-    "autoSelectAccount": "Automatically select account at runtime",
-    "modePackBalanced": "Balanced",
-    "modePackBudget": "Budget",
-    "modePackPerformance": "Performance",
-    "modePackCustom": "Custom",
-    "browseLegacyCatalog": "Browse legacy combo catalog",
-    "agentFeaturesTitle": "Agent Features",
-    "agentFeaturesDescription": "Enable advanced features for agents using this combo",
-    "responseValidationTitle": "Validasi respons",
-    "responseValidationHelp": "Alihkan ke target berikutnya saat isi 200 OK gagal dalam pemeriksaan ini (konten asisten).",
-    "responseValidationForbidden": "Substring terlarang (satu per baris)",
-    "responseValidationRequired": "Substring yang diperlukan (satu per baris)",
-    "responseValidationMinLength": "Panjang konten minimum (karakter)",
-    "responseValidationJsonPaths": "Pemeriksaan JSON-path",
-    "responseValidationAddCheck": "+ Tambah pemeriksaan",
-    "agentFeaturesSystemMessageOverride": "Override system message",
-    "agentFeaturesSystemMessagePlaceholder": "You are an expert assistant...",
-    "agentFeaturesSystemMessageHint": "System message override for agents",
-    "agentFeaturesToolFilterRegex": "/regex-pattern/",
-    "agentFeaturesToolFilterHint": "Tool filter regex for agents",
-    "agentFeaturesContextCacheHint": "Enable in-context cache for agent tools",
-    "agentFeaturesContextCacheProtection": "Protect cache from agent tool mutations",
-    "agentFeaturesContextLength": "Panjang konteks",
-    "agentFeaturesContextLengthPlaceholder": "misalnya 128000",
-    "agentFeaturesContextLengthHint": "Mendefinisikan jendela konteks untuk kombo ini di /v1/models.",
-    "agentFeaturesContextLengthErrorInteger": "Panjang konteks harus berupa bilangan bulat yang valid",
-    "agentFeaturesContextLengthErrorRange": "Panjang konteks harus antara 1000 dan 2000000",
-    "compressionOverride": "Penggantian Kompresi",
-    "modePack": "Paket Modus",
-    "disableSessionStickiness": "Nonaktifkan kelengketan sesi",
-    "sessionStickinessEnabled": "Kelengketan aktif",
-    "sessionStickinessDisabled": "Kelengketan nonaktif",
-    "kimiPresetTitle": "Preset Kimi Coding",
-    "kimiPresetDescription": "Kimi K3 sebagai model utama (Moonshot API), dengan pengalihan otomatis (fallback) ke koneksi Kimi Code Anda (kimi-coding, kimi-web) saat dikonfigurasi.",
-    "kimiPresetCta": "Tambah preset",
-    "intelligentComboCount": "{count, plural, one {# kombinasi cerdas} other {# kombinasi cerdas}}",
-    "providersInScope": "{count, plural, one {# penyedia dalam lingkup} other {# penyedia dalam lingkup}}",
-    "savingModePack": "Menyimpan {pack}…",
-    "errorTitle": "Gagal memuat kombinasi",
-    "errorDescription": "Kami tidak dapat memuat data kombinasi saat ini. Periksa koneksi Anda dan coba lagi.",
-    "errorId": "ID Kesalahan: {id}",
-    "errorRetry": "Coba Lagi",
-    "comboLabel": "Kombinasi",
-    "duplicateAutoComboConfirm": "Buat kombo statis dari \"{name}\"?",
-    "duplicateAutoComboSnapshotMsg": "Ini akan mengambil snapshot penyedia/model yang terhubung saat ini yang cocok dengan templat ini ke dalam kombo yang dapat diedit.",
-    "duplicateAutoComboFailedPrefix": "Gagal menduplikasi kombo otomatis:",
-    "duplicateAutoComboUnknownError": "Kesalahan tidak diketahui",
-    "duplicateAutoComboTitle": "Buat kombo statis dari {name}"
-  },
-  "costs": {
-    "title": "Costs",
-    "pageDescription": "Track spending, analyze trends, and manage your AI budget across all providers",
-    "overview": "Overview",
-    "budget": "Budget",
-    "totalCost": "Total Cost",
-    "breakdown": "Cost Breakdown",
-    "noData": "No cost data",
-    "byModel": "By Model",
-    "byProvider": "By Provider",
-    "range7d": "7 Days",
-    "range30d": "30 Days",
-    "range90d": "90 Days",
-    "range180d": "180 Days",
-    "range365d": "365 Days",
-    "rangeAll": "All Time",
-    "spend30d": "Spend 30D",
-    "activeModels": "Active Models",
-    "flatRateEstimateNotice": "__MISSING__:Includes token-price estimates for flat-rate subscriptions, not billed cost.",
-    "flatRateEstimateForecast": "__MISSING__:Projection includes flat-rate estimates.",
-    "selectedWindow": "Selected Window",
-    "activeProviders": "Active Providers",
-    "overviewTitle": "Cost Overview",
-    "spend7d": "Spend 7D",
-    "avgCostPerRequest": "Avg Cost / Request",
-    "noCostDataDescription": "Start making requests to see cost data appear here. Costs are tracked automatically for all providers.",
-    "spendToday": "Spend Today",
-    "overviewLoadFailed": "Failed to load cost overview",
-    "overviewDescription": "Real-time spending breakdown across all connected providers and models",
-    "providerShare": "Provider Share",
-    "topProviders": "Top Providers",
-    "costTrend": "Cost Trend",
-    "noCostDataTitle": "No cost data yet",
-    "topModels": "Top Models",
-    "requestsInWindow": "Requests in Window",
-    "tokenUsage": "Penggunaan Token",
-    "totalTokens": "Jumlah Token",
-    "inputTokens": "Token Masukan",
-    "outputTokens": "Token Keluaran",
-    "inputOutputRatio": "Rasio Masukan/Keluaran",
-    "tokens": "token",
-    "routingEfficiency": "Efisiensi Perutean",
-    "fallbackCount": "Permintaan Penggantian",
-    "fallbackRate": "Tingkat Penggantian",
-    "modelCoverage": "Cakupan Model",
-    "modelCoverageDesc": "% permintaan dengan model eksplisit",
-    "outOfRequests": "dari {total} permintaan",
-    "costByApiKey": "Biaya berdasarkan Kunci API",
-    "costByAccount": "Biaya berdasarkan Akun",
-    "apiKeyName": "Kunci API",
-    "account": "Akun",
-    "requests": "Permintaan",
-    "cost": "Biaya",
-    "dayStreak": "hari berturut-turut",
-    "weeklyUsagePattern": "Pola Penggunaan Mingguan",
-    "activityHeatmap": "Aktivitas (365 hari)",
-    "less": "Kurang",
-    "more": "Lebih lanjut",
-    "monthlyForecast": "Prakiraan Bulanan",
-    "forecastBasis": "Berdasarkan {days} hari terakhir",
-    "avgDailyCost": "Rata-rata biaya harian",
-    "daysRemaining": "{days} hari tersisa",
-    "periodComparison": "Perbandingan Periode",
-    "previousPeriod": "Babak Sebelumnya",
-    "currentPeriod": "Setengah Saat Ini",
-    "exportCSV": "Ekspor sebagai CSV",
-    "exportJSON": "Ekspor sebagai JSON",
-    "legacyFreeLabel": "Legacy / Gratis",
-    "costExplorerTitle": "Cost Explorer",
-    "costExplorerDescription": "Explore spend by provider, model, API key, account, or service tier.",
-    "groupProvider": "Provider",
-    "groupModel": "Model",
-    "groupApiKey": "API Key",
-    "groupAccount": "Account",
-    "groupServiceTier": "Service Tier",
-    "serviceTierFast": "Cepat",
-    "serviceTierFlex": "Flex",
-    "serviceTierStandard": "Standar",
-    "serviceTierBreakdownTitle": "Tingkat Layanan",
-    "serviceTierBreakdownSubtitle": "Pembagian Cepat / Flex / Standar",
-    "serviceTierUsageSaved": "penggunaan disimpan",
-    "serviceTierCostSaved": "tersimpan",
-    "serviceTierCostShareSuffix": "dari biaya",
-    "dimension": "Dimension",
-    "share": "Share",
-    "legacyOrFree": "Legacy / Free",
-    "filterRows": "Filter rows…",
-    "filterCostExplorerRows": "Filter Cost Explorer rows",
-    "noMatchingCostRows": "No matching cost rows",
-    "noMatchingCostRowsDescription": "Adjust the search text, grouping, or selected time window.",
-    "showingCostRows": "Showing {shown} of {total} matching rows.",
-    "showingTopCostRows": "Showing {shown} of {total} matching rows (top 50)."
-  },
-  "endpoint": {
-    "title": "API Endpoint",
-    "subtitle": "Use the OpenAI-compatible endpoint with most SDKs and tools.",
-    "testEndpoint": "Test endpoint →",
-    "advancedProtocols": "Advanced protocols",
-    "available": "Available Endpoints",
-    "cloudProxy": "Cloud Proxy",
-    "disableConfirm": "Are you sure you want to disable cloud proxy?",
-    "baseUrl": "Base URL",
-    "apiKeyLabel": "API Key",
-    "registeredKeys": "Registered Keys",
-    "chatCompletions": "Chat Completions",
-    "responses": "Responses",
-    "listModels": "List Models",
-    "usingCloudProxy": "Using Cloud Proxy",
-    "usingLocalServer": "Using Local Server",
-    "machineId": "Machine ID: {id}...",
-    "disableCloud": "Disable Cloud",
-    "enableCloud": "Enable Cloud",
-    "modelsAcrossEndpoints": "{models} models across {endpoints} endpoints",
-    "loadingModels": "Loading available models...",
-    "chatDesc": "Streaming & non-streaming chat with all providers",
-    "embeddings": "Embeddings",
-    "embeddingsDesc": "Text embeddings for search & RAG pipelines",
-    "imageGeneration": "Image Generation",
-    "imageDesc": "Generate images from text prompts",
-    "rerank": "Rerank",
-    "rerankDesc": "Rerank documents by relevance to a query",
-    "audioTranscription": "Audio Transcription",
-    "audioTranscriptionDesc": "Transcribe audio files to text (Whisper)",
-    "textToSpeech": "Text to Speech",
-    "textToSpeechDesc": "Convert text to natural-sounding speech",
-    "musicGeneration": "Music Generation",
-    "musicDesc": "Generate music and audio tracks via ComfyUI (Stable Audio, MusicGen)",
-    "moderations": "Moderations",
-    "moderationsDesc": "Content moderation and safety classification",
-    "responsesDesc": "OpenAI Responses API for Codex and advanced agentic workflows",
-    "listModelsDesc": "List all available models across all connected providers",
-    "settingsApiDesc": "Read and modify OmniRoute configuration via API",
-    "settingsApi": "Settings API",
-    "categoryCore": "Core APIs",
-    "categoryMedia": "Media & Multi-Modal",
-    "categorySearch": "Search & Discovery",
-    "categoryUtility": "Utility & Management",
-    "webSearch": "Web Search",
-    "webSearchDesc": "Unified web search across multiple providers with automatic failover and caching",
-    "searchProvider": "Search Provider",
-    "searchProviderDesc": "This provider is used for web search via POST /v1/search. No model configuration needed — search providers are ready to use once an API key is connected.",
-    "enableCloudTitle": "Enable Cloud Proxy",
-    "whatYouGet": "What you will get",
-    "cloudBenefitAccess": "Access your API from anywhere in the world",
-    "cloudBenefitShare": "Share endpoint with your team easily",
-    "cloudBenefitPorts": "No need to open ports or configure firewall",
-    "cloudBenefitEdge": "Fast global edge network",
-    "cloudSessionNote": "Cloud will keep your auth session for 1 day. If not used, it will be automatically deleted.",
-    "cloudUnstableNote": "Cloud is currently unstable with Claude Code OAuth in some cases.",
-    "cloudConnected": "Cloud Proxy connected!",
-    "connectingToCloud": "Connecting to cloud...",
-    "verifyingConnection": "Verifying connection...",
-    "connecting": "Connecting...",
-    "verifying": "Verifying...",
-    "connected": "Connected!",
-    "disableCloudTitle": "Disable Cloud Proxy",
-    "disableWarning": "All auth sessions will be deleted from cloud.",
-    "syncingData": "Syncing latest data...",
-    "disablingCloud": "Disabling cloud...",
-    "syncing": "Syncing...",
-    "disabling": "Disabling...",
-    "cloudConnectedVerified": "Cloud Proxy connected and verified!",
-    "connectedVerificationPending": "Connected — verification pending",
-    "connectedVerificationPendingWithError": "Connected — verification pending: {error}",
-    "cloudDisabledSuccess": "Cloud disabled successfully",
-    "syncedSuccess": "Synced successfully",
-    "failedDisable": "Failed to disable cloud",
-    "failedEnable": "Failed to enable cloud",
-    "cloudRequestTimeout": "Cloud request timeout",
-    "cloudRequestFailed": "Cloud request failed",
-    "cloudWorkerUnreachable": "Could not reach cloud worker. Make sure the cloud service is running (npm run dev in /cloud).",
-    "connectionFailed": "Connection failed",
-    "syncFailed": "Failed to sync cloud data",
-    "cloudflaredTitle": "Cloudflare Quick Tunnel",
-    "cloudflaredDescription": "Create a Cloudflare Quick Tunnel for this endpoint.",
-    "cloudflaredUrlNotice": "Creates a temporary Cloudflare Quick Tunnel. The URL changes after every restart.",
-    "cloudflaredEnable": "Enable Tunnel",
-    "cloudflaredInstallAndEnable": "Install & Enable",
-    "cloudflaredDisable": "Stop Tunnel",
-    "cloudflaredRunning": "Running",
-    "cloudflaredStarting": "Starting",
-    "cloudflaredStoppedState": "Stopped",
-    "cloudflaredNotInstalled": "Not installed",
-    "cloudflaredUnsupported": "Unsupported",
-    "cloudflaredError": "Error",
-    "cloudflaredStarted": "Cloudflare tunnel started",
-    "cloudflaredStopped": "Cloudflare tunnel stopped",
-    "cloudflaredRequestFailed": "Failed to update Cloudflare tunnel",
-    "cloudflaredTemporaryNote": "Quick Tunnel URLs are temporary and will change after every restart.",
-    "cloudflaredUnsupportedNote": "This platform is not supported for managed installs. Install cloudflared manually or point CLOUDFLARED_BIN to an existing binary.",
-    "cloudflaredIdleNote": "Create a temporary Cloudflare Quick Tunnel for this endpoint.",
-    "cloudflaredLastError": "Last error: {error}",
-    "providerModelsTitle": "{provider} — Models",
-    "noModelsForProvider": "No models available for this provider.",
-    "chat": "Chat",
-    "embedding": "Embedding",
-    "image": "Image",
-    "custom": "custom",
-    "modelsCount": "{count, plural, one {# model} other {# models}}",
-    "sectionTitle": "Integration Surface",
-    "sectionDescription": "OpenAI-compatible APIs and operational protocol endpoints",
-    "tabApis": "API",
-    "tabProtocols": "Protocols",
-    "tabsAria": "Endpoint sections",
-    "protocolsTitle": "Protocols",
-    "protocolsDescription": "MCP and A2A are first-class endpoints with dedicated observability and controls.",
-    "mcpCardTitle": "MCP Server",
-    "mcpCardDescription": "Model Context Protocol over stdio",
-    "a2aCardTitle": "A2A Server",
-    "a2aCardDescription": "Agent2Agent JSON-RPC endpoint",
-    "protocolToolsLabel": "Tools",
-    "protocolTasksLabel": "Tasks",
-    "protocolActiveStreamsLabel": "Active streams",
-    "protocolLastActivity": "Last activity",
-    "quickStart": "Quick Start",
-    "openMcpDashboard": "Open MCP management",
-    "openA2aDashboard": "Open A2A management",
-    "mcpQuickStartTitle": "MCP Quick Start",
-    "mcpQuickStartStep1": "Run the MCP server via `omniroute --mcp`.",
-    "mcpQuickStartStep2": "Configure your MCP client to connect over stdio transport.",
-    "mcpQuickStartStep3": "Invoke tools such as `omniroute_get_health` and `omniroute_list_combos`.",
-    "a2aQuickStartTitle": "A2A Quick Start",
-    "a2aQuickStartStep1": "Discover the agent card at `/.well-known/agent.json`.",
-    "a2aQuickStartStep2": "Send JSON-RPC requests to `POST /a2a` using `message/send` or `message/stream`.",
-    "a2aQuickStartStep3": "Track and control tasks using `tasks/get` and `tasks/cancel`.",
-    "completionsLegacy": "Completions (Legacy)",
-    "completionsLegacyDesc": "Legacy OpenAI text completions — accepts both prompt string and messages array format",
-    "messagesApi": "Pesan",
-    "messagesApiDesc": "Format API Pesan Antropik Asli untuk penyedia yang kompatibel dengan Claude",
-    "imageEdits": "Pengeditan Gambar",
-    "imageEditsDesc": "Edit dan modifikasi gambar yang ada dengan AI (inpainting, outpainting, variasi)",
-    "batchApi": "API kumpulan",
-    "batchApiDesc": "Memproses permintaan dalam jumlah besar secara asinkron (kompatibel dengan OpenAI)",
-    "filesApi": "API File",
-    "filesApiDesc": "Unggah dan kelola file untuk pemrosesan batch",
-    "videoGeneration": "Video Generation",
-    "videoDesc": "Generate videos using AI models like ComfyUI and Stable Video Diffusion.",
-    "tailscaleRequestFailed": "Failed to load Tailscale status",
-    "tailscaleEnableFailed": "Failed to enable Tailscale Funnel",
-    "tailscaleWaitingForLogin": "Complete the Tailscale login in the opened browser tab. OmniRoute will retry automatically.",
-    "tailscaleLoginTimedOut": "Timed out waiting for Tailscale login",
-    "tailscaleWaitingForFunnel": "Enable Funnel for this device in the opened browser tab. OmniRoute will keep polling.",
-    "tailscaleFunnelTimedOut": "Timed out waiting for Tailscale Funnel to be enabled",
-    "tailscaleStarted": "Tailscale Funnel enabled",
-    "tailscaleDisableFailed": "Failed to disable Tailscale Funnel",
-    "tailscaleStopped": "Tailscale Funnel disabled",
-    "tailscaleInstallFailed": "Failed to install Tailscale",
-    "tailscaleInstallProgress": "Working...",
-    "tailscaleInstalled": "Tailscale installed successfully",
-    "tailscaleRunning": "Running",
-    "tailscaleNeedsLogin": "Needs Login",
-    "tailscaleStoppedState": "Stopped",
-    "tailscaleNotInstalled": "Not installed",
-    "tailscaleUnsupported": "Unsupported",
-    "tailscaleError": "Error",
-    "tailscaleDisable": "Stop Funnel",
-    "tailscaleInstallAndEnable": "Install & Enable",
-    "tailscaleLoginAndEnable": "Login & Enable",
-    "tailscaleEnable": "Enable Funnel",
-    "tailscaleUrlNotice": "Uses your Tailscale .ts.net address. Login and Funnel approval may be required on first use.",
-    "tailscaleTitle": "Tailscale Funnel",
-    "tailscaleNeedsLoginHint": "Authenticate this machine with Tailscale, then enable Funnel.",
-    "tailscaleBinaryPath": "Binary: {path}",
-    "tailscaleLastError": "Last error: {error}",
-    "tailscaleInstallTitle": "Install Tailscale",
-    "tailscaleInstallIntro": "Installs Tailscale on this machine and prepares OmniRoute to enable Funnel.",
-    "tailscaleInstallPasswordHint": "On macOS and Linux, sudo may be required for the package install and daemon start.",
-    "tailscaleSudoPlaceholder": "Optional sudo password",
-    "tailscaleInstalling": "Installing",
-    "tailscaleSudoLabel": "Sudo Password (required on macOS/Linux)",
-    "ngrokTitle": "Terowongan ngrok",
-    "ngrokRunning": "Berlari",
-    "ngrokStarting": "Mulai",
-    "ngrokStoppedState": "Berhenti",
-    "ngrokNeedsAuth": "Membutuhkan Otentikasi",
-    "ngrokNotInstalled": "Tidak dipasang",
-    "ngrokUnsupported": "Tidak didukung",
-    "ngrokError": "Kesalahan",
-    "ngrokEnable": "Aktifkan Terowongan",
-    "ngrokDisable": "Hentikan Terowongan",
-    "ngrokUrlNotice": "Membuat terowongan ngrok publik.",
-    "ngrokAuthTokenLabel": "Authtoken (Diperlukan jika NGROK_AUTHTOKEN tidak disetel)",
-    "ngrokAuthTokenPlaceholder": "Masukkan token asli ngrok Anda",
-    "ngrokLastError": "Kesalahan terakhir: {error}",
-    "ngrokStarted": "terowongan ngrok dimulai",
-    "ngrokStopped": "terowongan ngrok terhenti",
-    "ngrokRequestFailed": "Gagal memperbarui terowongan ngrok",
-    "apiEndpointsCatalogUnavailable": "Katalog API tidak tersedia",
-    "apiEndpointsSearchPlaceholder": "Titik akhir pencarian...",
-    "apiEndpointsRequiresAuth": "Membutuhkan autentikasi",
-    "apiEndpointsNoMatch": "Tidak ada titik akhir yang cocok dengan filter Anda",
-    "endpointSections": "Bagian endpoint",
-    "tabMcp": "MCP",
-    "tabA2a": "A2A",
-    "tabContextSources": "Sumber Konteks",
-    "activeEndpoints": "Endpoint Aktif",
-    "activeLocal": "Lokal",
-    "activeCloud": "Cloud",
-    "copyUrlTitle": "Salin {url}",
-    "statusRunning": "Berjalan",
-    "tunnels": "Tunnel",
-    "activeTunnelCount": "{active} / {total} aktif",
-    "badgeLocal": "LOKAL",
-    "badgeProtected": "DILINDUNGI",
-    "badgeInternal": "INTERNAL",
-    "catalogLoadFailed": "Permintaan katalog API gagal dengan HTTP {status}",
-    "catalogLoadFailedGeneric": "Gagal memuat katalog API",
-    "apiKeysLoadFailed": "Gagal memuat kunci API ({status})",
-    "apiKeysLoadFailedGeneric": "Gagal memuat kunci API",
-    "apiKeyRevealDisabled": "Penyingkapan kunci API dinonaktifkan (ALLOW_API_KEY_REVEAL). Ubah di halaman Feature Flags atau tempel kunci API secara manual.",
-    "apiKeyRevealFailed": "Gagal menampilkan kunci API ({status})",
-    "apiKeyRevealInvalid": "Penyingkapan kunci API mengembalikan respons tidak valid",
-    "apiKeyRequired": "Kunci API diperlukan untuk endpoint ini.",
-    "requestFailed": "Permintaan gagal ({status})",
-    "errorStatus": "Kesalahan",
-    "catalogStats": "{endpoints} endpoint di {categories} kategori",
-    "catalogUnavailableDescription": "Spesifikasi OpenAPI tidak dapat dimuat.",
-    "openJsonResponse": "Buka respons JSON",
-    "all": "Semua",
-    "more": "+{count} lainnya",
-    "showInternalTooltip": "Tampilkan atau sembunyikan rute internal (tersembunyi secara default)",
-    "bearerAuth": "Bearer Auth",
-    "requestBody": "Badan Permintaan",
-    "close": "Tutup",
-    "tryIt": "Coba",
-    "example": "Contoh",
-    "apiKey": "Kunci API",
-    "switchToSelection": "Beralih ke Pilihan",
-    "enterManually": "Masukkan Secara Manual",
-    "pasteApiKey": "Tempel kunci API Anda di sini",
-    "noActiveApiKeys": "Tidak ada kunci API aktif yang ditemukan. Alihkan entri manual untuk menempelkannya.",
-    "requestBodyJson": "Badan Permintaan (JSON)",
-    "sending": "Mengirim...",
-    "sendRequest": "Kirim Permintaan",
-    "dataSchemas": "Skema Data",
-    "vscodeAliasTitle": "Alias Token VS Code",
-    "vscodeAliasDescriptionReady": "URL kompatibilitas siap-tempel menggunakan endpoint /api/v1/vscode/TOKEN/...",
-    "vscodeAliasDescriptionError": "Menampilkan URL placeholder karena kunci CLI tidak dapat dimuat dalam sesi ini.",
-    "vscodeAliasDescriptionLoading": "Memuat kunci CLI. URL placeholder ditampilkan hingga kunci tersedia.",
-    "vscodeAliasDescriptionPlaceholder": "Menampilkan URL placeholder. Buat atau aktifkan kunci API di Alat CLI untuk menggantikan TOKEN.",
-    "vscodeAliasManage": "Alat CLI",
-    "vscodeAliasBaseLabel": "Basis VS Code",
-    "vscodeAliasModelsLabel": "Model VS Code",
-    "vscodeAliasChatLabel": "Obrolan VS Code",
-    "localServer": "Server Lokal",
-    "cloudOmniroute": "Cloud OmniRoute",
-    "copyUrl": "Salin URL",
-    "badgeLoopbackTooltip": "Endpoint ini hanya dapat diakses secara lokal (hanya loopback)",
-    "badgeAlwaysProtectedTooltip": "Endpoint ini selalu dilindungi dan memerlukan otorisasi",
-    "badgeInternalTooltip": "Ini adalah endpoint sistem internal",
-    "tierAll": "Semua",
-    "tierAuth": "Terautentikasi",
-    "tierLoopback": "Loopback",
-    "tierAlwaysProtected": "Selalu Dilindungi",
-    "tierPublic": "Publik",
-    "hideInternal": "Sembunyikan Internal",
-    "showInternal": "Tampilkan Internal",
-    "customSystemPromptTitle": "Custom System Prompt",
-    "customSystemPromptDescription": "Inject a custom system prompt into every model request",
-    "customSystemPromptPlaceholder": "e.g. Always respond in pirate speak...",
-    "obsidianEnterToken": "Silakan masukkan token API Obsidian",
-    "obsidianConnectFailed": "Gagal menyambung",
-    "obsidianConnectionFailed": "Koneksi gagal",
-    "obsidianDisconnectFailed": "Gagal memutuskan sambungan",
-    "obsidianEnterVaultPath": "Silakan masukkan jalur direktori vault",
-    "obsidianWebdavEnabledMessage": "Sinkronisasi WebDAV diaktifkan. Konfigurasikan perangkat seluler Anda di bawah ini.",
-    "obsidianEnableWebdavFailed": "Gagal mengaktifkan WebDAV",
-    "obsidianWebdavDisabledMessage": "Sinkronisasi WebDAV dinonaktifkan",
-    "obsidianDisableWebdavFailed": "Gagal menonaktifkan WebDAV",
-    "obsidianConnected": "Terhubung",
-    "obsidianNotConnected": "Tidak terhubung",
-    "obsidianWebdavSync": "Sinkronisasi WebDAV",
-    "obsidianDescription": "Cari, baca, tulis, dan kelola catatan di Obsidian melalui model AI yang dirutekan",
-    "obsidianRestToken": "Token REST API Lokal Obsidian",
-    "obsidianApiKeyPlaceholder": "Kunci API Obsidian",
-    "obsidianConnect": "Hubungkan",
-    "obsidianBaseUrlOptional": "URL Dasar (opsional)",
-    "obsidianPortWarning": "Port 27124 adalah endpoint MCP (HTTPS, sertifikat self-signed). REST API menggunakan HTTP pada port 27123.",
-    "obsidianRemoteVaultHint": "Default: {defaultUrl}. Untuk vault jarak jauh, masukkan IP Tailscale + port (misalnya, http://100.x.x.x:27123). Aktifkan plugin Local REST API pada mesin yang menjalankan Obsidian.",
-    "obsidianTokenConfigured": "Token dikonfigurasi. Alat Obsidian tersedia melalui MCP.",
-    "obsidianDisconnect": "Putuskan",
-    "obsidianVaultSync": "Sinkronisasi Vault (WebDAV)",
-    "obsidianVaultSyncDescription": "Sinkronkan vault Anda ke Obsidian mobile menggunakan WebDAV melalui Tailscale. Obsidian mobile memiliki dukungan WebDAV bawaan — tidak memerlukan plugin.",
-    "obsidianVaultDirectoryPath": "Jalur Direktori Vault",
-    "obsidianEnable": "Aktifkan",
-    "obsidianWebdavEnabled": "Sinkronisasi WebDAV diaktifkan",
-    "obsidianDisable": "Nonaktifkan",
-    "obsidianConfigureMobile": "Konfigurasikan Obsidian Mobile",
-    "obsidianMobileInstructions": "Di Obsidian mobile: Pengaturan → Sinkronisasi → WebDAV → masukkan berikut ini:",
-    "obsidianWebdavUrl": "URL WebDAV",
-    "obsidianUsername": "Nama Pengguna",
-    "obsidianPassword": "Kata Sandi",
-    "obsidianTailscaleHint": "Gunakan IP Tailscale Anda alih-alih localhost jika menghubungkan dari perangkat seluler. Kedua perangkat harus berada di jaringan Tailscale yang sama.",
-    "cloudSyncNotConfigured": "Sinkronisasi awan tidak dikonfigurasi pada instance ini.",
-    "notionConnect": "Sambungkan",
-    "notionConnectFailed": "Gagal terhubung",
-    "notionConnected": "Terkoneksi",
-    "notionConnectionFailed": "Koneksi gagal",
-    "notionDescription": "Cari, baca, kueri, dan tulis ke Notion melalui model AI yang diarahkan",
-    "notionDisconnect": "Putuskan Koneksi",
-    "notionDisconnectFailed": "Gagal untuk memutuskan koneksi",
-    "notionEnterToken": "Silakan masukkan token integrasi Notion",
-    "notionIntegrationHelp": "Buat Integrasi Internal di",
-    "notionIntegrationToken": "Token Integrasi Internal Notion",
-    "notionNotConnected": "Tidak terhubung",
-    "notionTokenConfigured": "Token telah dikonfigurasi. Alat Notion tersedia melalui MCP."
-  },
-  "endpoints": {
-    "tabProxy": "Endpoint Proxy",
-    "tabApiEndpoints": "API Endpoints",
-    "apiEndpointsTitle": "API Endpoints",
-    "apiEndpointsDescription": "Backend API endpoints that can be consumed by other applications and services. This section will list all available REST APIs with documentation and testing capabilities.",
-    "comingSoon": "Coming Soon",
-    "plannedFeatures": "Planned Features",
-    "featureRestApi": "REST API endpoint catalog with interactive documentation",
-    "featureWebhooks": "Webhook configuration and event subscriptions",
-    "featureSwagger": "OpenAPI / Swagger spec auto-generation",
-    "featureAuth": "API key and OAuth scope management per endpoint"
-  },
-  "mcpDashboard": {
-    "loading": "Loading MCP dashboard...",
-    "activate": "activate",
-    "deactivate": "deactivate",
-    "confirmSwitchCombo": "Confirm {action} combo \"{combo}\"?",
-    "switchComboFailed": "Failed to switch combo state.",
-    "switchComboSuccess": "Combo \"{combo}\" updated.",
-    "confirmApplyProfile": "Apply resilience profile \"{profile}\"?",
-    "applyProfileFailed": "Failed to apply resilience profile.",
-    "applyProfileSuccess": "Profile \"{profile}\" applied.",
-    "confirmResetBreakers": "Reset all circuit breakers?",
-    "resetBreakersFailed": "Failed to reset circuit breakers.",
-    "resetBreakersSuccess": "Circuit breakers reset.",
-    "processStatus": "Process status",
-    "online": "Online",
-    "offline": "Offline",
-    "disableLabel": "Nonaktifkan {label}",
-    "enableLabel": "Aktifkan {label}",
-    "transportMode": "Mode Transpor",
-    "transportStdioDesc": "Lokal — IDE memunculkan proses melalui omniroute --mcp",
-    "transportSseDesc": "Jarak Jauh — Server-Sent Events melalui HTTP",
-    "transportStreamableHttpDesc": "Jarak Jauh — HTTP dua arah modern",
-    "copy": "Salin",
-    "mcpDashboardCopyUrl": "Salin URL",
-    "mcpDisabledTitle": "MCP dinonaktifkan",
-    "mcpDisabledDesc": "Aktifkan MCP di atas untuk mengonfigurasi mode transpor dan melihat telemetri server.",
-    "mcpIntro": "Model Context Protocol — {tools} alat di {scopes} cakupan, {transports} transpor (stdio / SSE / Streamable HTTP).",
-    "mcpStep1": "Jalankan melalui {code}",
-    "mcpStep2": "Konfigurasikan klien MCP Anda untuk terhubung melalui transpor stdio.",
-    "mcpStep3": "Panggil alat seperti {code1} dan {code2}.",
-    "pid": "PID",
-    "sessionUptime": "Session uptime",
-    "lastHeartbeat": "Last heartbeat",
-    "activity24h": "Activity (24h)",
-    "totalCalls": "Total calls",
-    "successRate": "Success rate",
-    "avgLatency": "Avg latency",
-    "topTools": "Top tools",
-    "noToolCalls24h": "No tool calls in the last 24 hours.",
-    "runtimeDetails": "Runtime details",
-    "transport": "Transport",
-    "scopesEnforced": "Scopes enforced",
-    "yes": "yes",
-    "no": "no",
-    "lastCall": "Last call",
-    "heartbeatPath": "Heartbeat path",
-    "operationalControls": "Operational controls",
-    "switchCombo": "Switch combo",
-    "inactive": "inactive",
-    "active": "active",
-    "activateCombo": "Activate combo",
-    "deactivateCombo": "Deactivate combo",
-    "applyResilienceProfile": "Apply resilience profile",
-    "profileAggressive": "aggressive",
-    "profileBalanced": "balanced",
-    "profileConservative": "conservative",
-    "applyProfile": "Apply profile",
-    "resetCircuitBreakers": "Reset circuit breakers",
-    "resetCircuitBreakersHelp": "Clears current breaker state and failure counters for providers.",
-    "resetAllBreakers": "Reset all breakers",
-    "toolsAndScopes": "Tools and scopes",
-    "tableTool": "Tool",
-    "tableScopes": "Scopes",
-    "tablePhase": "Phase",
-    "tableAudit": "Audit",
-    "auditLog": "Audit log",
-    "auditSummary": "Calls: {total} | page {page} of {totalPages}",
-    "allTools": "All tools",
-    "allResults": "All results",
-    "success": "Success",
-    "failure": "Failure",
-    "apiKeyIdPlaceholder": "apiKeyId",
-    "loadingAuditEntries": "Loading audit entries...",
-    "noAuditEntriesForFilters": "No audit entries found for current filters.",
-    "tableTimestamp": "Timestamp",
-    "tableDuration": "Duration",
-    "tableResult": "Result",
-    "tableApiKey": "API key",
-    "failed": "failed",
-    "previous": "Previous",
-    "next": "Next",
-    "apiKeyId": "Api Key Id",
-    "offset": "Offset",
-    "limit": "Limit",
-    "tool": "Tool"
-  },
-  "a2aDashboard": {
-    "loading": "Loading A2A dashboard...",
-    "confirmCancelTask": "Cancel task {taskId}?",
-    "cancelTaskFailed": "Failed to cancel task.",
-    "cancelTaskSuccess": "Task {taskId} cancelled.",
-    "smokeSendFailed": "message/send smoke test failed.",
-    "smokeSendSuccessWithTask": "message/send ok (task {taskId}).",
-    "smokeSendSuccess": "message/send ok.",
-    "smokeStreamFailed": "message/stream smoke test failed.",
-    "smokeStreamSuccessWithTask": "message/stream ok (task {taskId}{stateSuffix}).",
-    "smokeStreamNoTaskId": "message/stream finished without task id.",
-    "health": "Health",
-    "ok": "ok",
-    "totalTasks": "Total tasks",
-    "activeStreams": "Active streams",
-    "lastTask": "Last task",
-    "taskStateOverview": "Task state overview",
-    "state": {
-      "submitted": "submitted",
-      "working": "working",
-      "completed": "completed",
-      "failed": "failed",
-      "cancelled": "cancelled"
-    },
-    "agentCard": "Agent card",
-    "agentCardPath": "/.well-known/agent.json",
-    "version": "Version",
-    "url": "URL",
-    "capabilities": "Capabilities",
-    "agentCardNotAvailable": "Agent card not available.",
-    "quickValidation": "Quick validation",
-    "quickValidationDescription": "Executes smoke calls through the live `/a2a` endpoint.",
-    "runMessageSend": "Run message/send",
-    "runMessageStream": "Run message/stream",
-    "taskManagement": "Task management",
-    "taskSummary": "{total} tasks | page {page} of {totalPages}",
-    "allStates": "all",
-    "allSkills": "all skills",
-    "loadingTasks": "Loading tasks...",
-    "noTasksForFilters": "No tasks found for current filters.",
-    "tableTask": "Task",
-    "tableSkill": "Skill",
-    "tableState": "State",
-    "tableUpdated": "Updated",
-    "tableActions": "Actions",
-    "view": "View",
-    "cancel": "Cancel",
-    "previous": "Previous",
-    "next": "Next",
-    "taskDetail": "Task detail",
-    "close": "Close",
-    "metadata": "Metadata",
-    "events": "Events",
-    "artifacts": "Artifacts",
-    "tablePhase": "Table Phase",
-    "offset": "Offset",
-    "limit": "Limit",
-    "skill": "Skill",
-    "rpcEndpoint": "POSTING /a2a",
-    "rpcMethodSend": "pesan/kirim",
-    "rpcMethodStream": "pesan/aliran",
-    "rpcMethodGet": "tugas/dapatkan",
-    "rpcMethodCancel": "tugas/batal",
-    "serviceLabel": "A2A",
-    "online": "Online",
-    "offline": "Offline",
-    "disableLabel": "Nonaktifkan {label}",
-    "enableLabel": "Aktifkan {label}",
-    "a2aDisabledTitle": "A2A dinonaktifkan",
-    "a2aDisabledDesc": "Aktifkan A2A di atas untuk melihat telemetri tugas, detail agen, dan alat validasi.",
-    "a2aIntro": "Endpoint JSON-RPC 2.0 Agent2Agent — kirim tugas, streaming respons, batalkan pekerjaan yang sedang berjalan.",
-    "a2aStep1": "Temukan kartu agen di {code}.",
-    "a2aStep2": "Kirim JSON-RPC ke {code1} menggunakan {code2} atau {code3}.",
-    "a2aStep3": "Lacak dan batalkan tugas dengan {code1} dan {code2}."
-  },
-  "memory": {
-    "a": "A",
-    "actions": "Actions",
-    "addMemory": "Add Memory",
-    "allTypes": "All Types",
-    "cancel": "Batalkan",
-    "checkHealth": "Periksa kesehatan",
-    "checkingHealth": "Memeriksa…",
-    "compactOld": "Padatkan yang lama",
-    "concept": {
-      "title": "Memori Percakapan",
-      "description": "OmniRoute belajar dari setiap percakapan, mengingat fakta, episode, prosedur, dan konsep semantik yang membuat tanggapan lebih akurat dan sadar konteks.",
-      "howWorksToggle": "Cara kerja",
-      "howWorksContent": "1. Ekstraksi otomatis: di akhir setiap tanggapan, fakta dan episode dideteksi dan disimpan secara otomatis.\n2. Pengambilan: sebelum setiap tanggapan, memori yang paling relevan dicari melalui FTS5 (persis), vektor (semantik), atau RRF hibrida.\n3. Injeksi: memori yang relevan dimasukkan ke dalam konteks asisten untuk meningkatkan kualitas tanggapan.\n4. Manajemen: gunakan halaman ini untuk melihat, mengedit, mengekspor, dan memadatkan memori lama."
-    },
-    "content": "Content",
-    "contentPlaceholder": "Nilai atau konten JSON yang perlu diingat",
-    "created": "Created",
-    "delete": "Delete",
-    "deleteConfirmDesc": "Tindakan ini tidak dapat dibatalkan. Memori akan dihapus secara permanen.",
-    "deleteConfirmTitle": "Hapus memori?",
-    "description": "View and manage stored memory entries",
-    "editMemory": "Ubah memori",
-    "editModal": {
-      "title": "Ubah Memori",
-      "metadataLabel": "Metadata (JSON)",
-      "metadataInvalid": "JSON tidak valid",
-      "saveFailed": "Gagal menyimpan memori"
-    },
-    "embedding": {
-      "autoLabel": "Otomatis",
-      "autoDesc": "Menggunakan yang terbaik yang tersedia: penyedia jarak jauh > statis > transformers",
-      "remoteLabel": "Penyedia jarak jauh",
-      "remoteDesc": "Menggunakan penyematan via API penyedia (memerlukan kunci API)",
-      "staticLabel": "Lokal statis (potion)",
-      "staticDesc": "Penyematan lokal tanpa WASM atau dependensi eksternal",
-      "transformersLabel": "Transformers.js (MiniLM)",
-      "transformersDesc": "Penyematan lokal via @huggingface/transformers (~400MB RAM)",
-      "providerModelLabel": "Penyedia / Model",
-      "noRemoteProviders": "Tidak ada penyedia dengan kunci API yang dikonfigurasi",
-      "selectProviderModel": "Pilih model",
-      "customBaseUrlLabel": "URL dasar kustom (opsional)",
-      "customModelIdLabel": "ID model kustom (opsional)",
-      "customEndpointHelp": "Gunakan endpoint /embeddings yang kompatibel dengan OpenAI. Endpoint lokal diperbolehkan; target metadata cloud diblokir.",
-      "customEndpointSave": "Terapkan endpoint kustom",
-      "customEndpointInvalid": "Masukkan baik URL dasar HTTP(S) yang valid dan ID model, atau biarkan kedua kolom kosong.",
-      "customEndpointSaveFailed": "Endpoint penyisipan kustom tidak dapat disimpan.",
-      "staticEnabledLabel": "Aktifkan Static Potion",
-      "staticEnabledDesc": "Unduh dan gunakan model potion-base-8M secara lokal",
-      "transformersEnabledLabel": "Aktifkan Transformers.js",
-      "transformersEnabledDesc": "Pilih untuk menggunakan MiniLM lokal (~400MB RAM, ~3d cold start)",
-      "transformersWarning": "Memerlukan ~400MB RAM dan ~3d cold start pada kueri semantik pertama."
-    },
-    "emptyState": {
-      "title": "Belum ada memori",
-      "description": "Memori dibuat secara otomatis dari percakapan. Anda juga dapat menambahkannya secara manual menggunakan tombol di atas."
-    },
-    "engine": {
-      "statusTitle": "Status Mesin",
-      "embeddingTitle": "Sumber Penyematan",
-      "rerankTitle": "Peringkat ulang (opsional)",
-      "reindexNow": "Indeks ulang sekarang",
-      "reindexStarted": "Pengindeksan ulang dimulai ({pending} tertunda)",
-      "reindexFailed": "Gagal memulai pengindeksan ulang",
-      "keywordLabel": "Kata kunci (FTS5)",
-      "keywordReason": "Pencarian kata kunci selalu tersedia",
-      "embeddingLabel": "Embedding",
-      "vectorStoreLabel": "Penyimpanan Vektor",
-      "qdrantLabel": "Qdrant",
-      "rerankLabel": "Rerank",
-      "qdrantDisabled": "Dinonaktifkan",
-      "qdrantOk": "Sehat ({latencyMs}ms)",
-      "qdrantError": "Galat koneksi",
-      "needsReindex": "{count} memori perlu diindeks ulang",
-      "configureCta": "Konfigurasi",
-      "vectorStoreInstallHint": "Untuk mengaktifkan pencarian vektor: npm install sqlite-vec (memerlukan Node.js asli, bukan WASM), lalu mulai ulang."
-    },
-    "episodic": "Episodic",
-    "export": "Export",
-    "factual": "Factual",
-    "healthUnknown": "Kesehatan tidak diketahui",
-    "hitRate": "Hit Rate",
-    "import": "Import",
-    "importError": "Gagal mengimpor berkas",
-    "importResult": "{imported} diimpor, {skipped} dilewati",
-    "key": "Key",
-    "keyPlaceholder": "misalnya pengguna.preferensi.tema",
-    "loading": "Loading memories...",
-    "memories": "Memories",
-    "next": "Selanjutnya",
-    "noMemories": "No memories found",
-    "pageInfo": "Halaman {page} dari {totalPages} (total {total})",
-    "pipelineError": "Kesalahan saluran pipa",
-    "pipelineOk": "Saluran Pipa Oke ({latencyMs}ms)",
-    "playground": {
-      "infoTitle": "Playground Memori",
-      "infoDesc": "Simulasikan apa yang akan diambil untuk kueri tertentu. Tidak ada memori yang diubah — pratinjau baca-saja.",
-      "queryLabel": "Kueri uji",
-      "queryPlaceholder": "Ketik pertanyaan atau frasa uji...",
-      "strategyLabel": "Strategi",
-      "strategyExact": "Eksak (FTS5)",
-      "strategySemantic": "Semantik (vektor)",
-      "strategyHybrid": "Hibrida (RRF)",
-      "budgetLabel": "Anggaran (token)",
-      "simulate": "Simulasikan",
-      "resultsTitle": "{count} hasil",
-      "resolutionTitle": "Resolusi pencarian",
-      "resolutionEmbedding": "Embedding",
-      "resolutionStore": "Penyimpanan vektor",
-      "resolutionStrategy": "Strategi yang digunakan",
-      "rerankApplied": "Rerank diterapkan",
-      "fallback": "Fallback",
-      "noResults": "Tidak ada memori yang ditemukan untuk kueri ini.",
-      "tokensUsed": "token digunakan",
-      "none": "tidak ada",
-      "errorFetch": "Gagal mengambil pratinjau"
-    },
-    "previous": "Sebelumnya",
-    "procedural": "Procedural",
-    "qdrant": {
-      "title": "Qdrant (Penyimpanan Vektor Tingkat 2)",
-      "description": "Integrasi Qdrant opsional untuk pencarian semantik yang dapat diskalakan",
-      "enableLabel": "Aktifkan Qdrant",
-      "enableDesc": "Jika diaktifkan, Qdrant digunakan sebagai penyimpanan vektor utama",
-      "banner": "Penyimpanan vektor Tingkat 2 — alternatif eksternal yang dapat diskalakan untuk sqlite-vec bawaan (Tingkat 1). Aktifkan hanya jika Anda memiliki kumpulan memori yang sangat besar atau menginginkan memori bersama di berbagai instans; sebagian besar pengguna cukup menggunakan sqlite-vec. Jika diaktifkan, ini menjadi penyimpanan utama dan secara otomatis beralih kembali ke sqlite-vec jika tidak dapat dijangkau.",
-      "hostHelp": "Docker Lokal: http://localhost:6333 · Qdrant Cloud: URL klaster Anda",
-      "collectionHelp": "Nama apa saja — OmniRoute membuatnya pada penggunaan pertama",
-      "embeddingModelHelp": "Menyetel dimensi vektor secara otomatis pada penggunaan pertama. Memori yang ada tidak diisi ulang, dan mengubah model setelah data ada memerlukan koleksi baru.",
-      "testConnection": "Uji koneksi",
-      "testing": "Menguji...",
-      "statusActive": "Aktif",
-      "statusError": "Galat",
-      "statusDisabled": "Dinonaktifkan",
-      "healthOk": "Koneksi OK ({latencyMs}ms)",
-      "healthError": "Galat koneksi",
-      "saved": "Pengaturan disimpan",
-      "saveError": "Gagal menyimpan",
-      "portLabel": "Port",
-      "embeddingModelLabel": "Model Embedding",
-      "optional": "opsional",
-      "apiKeyKeepPlaceholder": "Biarkan kosong untuk mempertahankan kunci saat ini",
-      "apiKeyOptional": "Biarkan kosong jika tidak menggunakan autentikasi",
-      "removeApiKey": "Hapus",
-      "quickSelectModel": "Pilih cepat",
-      "searchTestTitle": "Uji pencarian semantik",
-      "searchPlaceholder": "Ketik kueri uji...",
-      "searching": "Mencari...",
-      "search": "Cari",
-      "cleanupTitle": "Bersihkan titik lama",
-      "cleanupDesc": "Hapus titik Qdrant untuk memori yang kedaluwarsa (periode retensi).",
-      "cleaning": "Membersihkan...",
-      "cleanNow": "Bersihkan sekarang",
-      "cleanupSuccess": "{count} titik dihapus",
-      "cleanupFailed": "Pembersihan gagal",
-      "hostLabel": "Tuan Rumah",
-      "collectionLabel": "Koleksi"
-    },
-    "rerank": {
-      "enableLabel": "Aktifkan Rerank",
-      "enableDesc": "Mengurutkan ulang hasil dengan model rerank setelah pencarian",
-      "warning": "Rerank menambah latensi +200-500ms dan biaya tambahan per permintaan. Gunakan dengan hemat.",
-      "providerModelLabel": "Penyedia / Model Rerank",
-      "noProviderWithKey": "Tidak ada penyedia dengan kunci API yang dikonfigurasi. Konfigurasikan penyedia untuk menggunakan rerank.",
-      "selectProviderModel": "Pilih penyedia/model"
-    },
-    "save": "Simpan",
-    "saving": "Menyimpan...",
-    "search": "Search memories...",
-    "semantic": "Semantic",
-    "summarize": {
-      "title": "Padatkan memori lama",
-      "noCandidates": "Tidak ada memori yang memenuhi syarat untuk pemadatan (kriteria: berusia >30 hari).",
-      "candidatesDesc": "{count} memori akan dipadatkan menjadi ringkasan. Tindakan ini tidak dapat dibatalkan.",
-      "confirm": "Padatkan sekarang"
-    },
-    "tabs": {
-      "memories": "Memori",
-      "playground": "Playground",
-      "engine": "Mesin"
-    },
-    "title": "Memory Management",
-    "tokensUsed": "Tokens Used",
-    "tooltip": {
-      "totalEntries": "Total memori yang disimpan untuk kunci API ini",
-      "tokensUsed": "Estimasi total token yang ditempati oleh memori aktif",
-      "hitRate": "Rasio hit tembolok Baca-berdasarkan-ID (bukan akurasi pemanggilan semantik)",
-      "factual": "Fakta objektif dan permanen dari konteks pengguna",
-      "episodic": "Peristiwa dan pengalaman dari riwayat percakapan",
-      "procedural": "Prosedur, alur kerja, dan instruksi yang harus diikuti oleh asisten",
-      "semantic": "Konsep, preferensi, dan pengetahuan domain"
-    },
-    "totalEntries": "Total Entries",
-    "type": "Type",
-    "memoryEnabled": "Memori diaktifkan"
-  },
-  "skills": {
-    "title": "Skills",
-    "description": "Manage and monitor AI skills",
-    "skillsTab": "Skills",
-    "executionsTab": "Executions",
-    "selectSkillToInspect": "Pilih keahlian di sebelah kiri untuk memeriksa.",
-    "schemaTab": "Skema",
-    "handlerTab": "Penangan",
-    "inputSchema": "Skema Masukan",
-    "outputSchema": "Skema Keluaran",
-    "handlerCode": "Kode Penangan",
-    "handlerUnavailable": "Penangan tidak tersedia",
-    "runTestPlaceholder": "Jalankan pengujian (placeholder)",
-    "setModeAria": "Atur mode {mode}",
-    "uninstallSkill": "Copot pemasangan keahlian",
-    "sandboxTab": "Sandbox",
-    "loading": "Loading skills...",
-    "noSkills": "No skills found",
-    "noExecutions": "No executions found",
-    "enabled": "Enabled",
-    "disabled": "Disabled",
-    "delete": "Hapus",
-    "version": "Version",
-    "tableDescription": "Description",
-    "skill": "Skill",
-    "status": "Status",
-    "duration": "Duration",
-    "time": "Time",
-    "sandboxConfig": "Sandbox Configuration",
-    "cpuLimit": "CPU Limit",
-    "cpuLimitDesc": "Maximum execution time per skill",
-    "memoryLimit": "Memory Limit",
-    "memoryLimitDesc": "Maximum memory allocation",
-    "timeout": "Timeout",
-    "timeoutDesc": "Maximum wait time for response",
-    "networkAccess": "Network Access",
-    "networkAccessDesc": "Allow outbound network requests",
-    "mode": "Mode",
-    "q": "Q",
-    "filterSkillsPlaceholder": "Filter keterampilan berdasarkan nama, deskripsi, atau tag",
-    "allModes": "Semua mode",
-    "totalSkills": "Total Keahlian",
-    "enabledSkills": "Diaktifkan",
-    "totalExecutions": "Eksekusi",
-    "successRate": "Tingkat Keberhasilan",
-    "marketplaceTab": "Pasar",
-    "applyFilters": "Terapkan filter",
-    "popularDefaultsLabel": "Populer secara bawaan untuk penyedia yang dipilih:",
-    "onMode": "AKTIF",
-    "offMode": "NONAKTIF",
-    "autoMode": "OTOMATIS",
-    "installSkillButton": "Pasang Keahlian",
-    "installSkillModalTitle": "Pasang Keahlian",
-    "installJsonPlaceholder": "Tempel JSON manifes keahlian di sini...",
-    "installing": "Memasang...",
-    "installSuccess": "Keahlian terpasang ({id})",
-    "installError": "Pemasangan gagal",
-    "invalidJson": "JSON tidak valid",
-    "searchMarketplacePlaceholder": "Cari keahlian...",
-    "searchMarketplace": "Cari Pasar",
-    "marketplaceEmpty": "Tidak ada keahlian yang ditemukan di pasar",
-    "marketplaceError": "Pencarian gagal",
-    "installingFromMarketplace": "Memasang dari marketplace...",
-    "popularSkills": "Keahlian Populer",
-    "skillsMarketplace": "Pasar Keterampilan",
-    "searching": "Mencari...",
-    "pageInfo": "Halaman {page} dari {totalPages} (total {total})",
-    "previous": "Sebelumnya",
-    "next": "Berikutnya",
-    "activeProvider": "Penyedia aktif:",
-    "changeInSettings": "Ubah ini di Setelan → Memori & Keahlian.",
-    "installs": "pemasangan",
-    "marketplaceSkillsMpHint": "Konfigurasikan kunci API SkillsMP Anda di Setelan untuk menjelajahi marketplace.",
-    "marketplaceSkillsShHint": "Cari direktori terbuka skills.sh untuk menemukan dan memasang keahlian agen.",
-    "installSkillModalDesc": "Tempel JSON manifes keahlian atau unggah berkas .json.",
-    "uploadJson": "Unggah JSON",
-    "cancel": "Batal",
-    "installSkill": "Instal Keterampilan"
-  },
-  "health": {
-    "title": "System Health",
-    "description": "Real-time monitoring of your OmniRoute instance",
-    "healthy": "Healthy",
-    "degraded": "Degraded",
-    "down": "Down",
-    "uptime": "Uptime",
-    "memory": "Memory",
-    "memoryRss": "Memory (RSS)",
-    "heap": "Heap",
-    "cpu": "CPU",
-    "database": "Database",
-    "version": "Version",
-    "lastCheck": "Last Check",
-    "providerHealth": "Provider Health",
-    "systemMetrics": "System Metrics",
-    "tokenHealth": "Token Health",
-    "refreshAll": "Refresh All",
-    "checkNow": "Check Now",
-    "loadingHealth": "Loading health data...",
-    "failedToLoad": "Failed to load health data: {error}",
-    "retry": "Retry",
-    "allOperational": "All systems operational",
-    "issuesDetected": "System issues detected",
-    "healthVerdictReady": "OmniRoute is ready",
-    "healthVerdictActionRequired": "Action required to restore full operation",
-    "healthVerdictCoolingDown": "Cooling down after recent changes",
-    "healthSubtitle": "System health check",
-    "advancedDiagnosticsTitle": "Advanced diagnostics",
-    "hide": "Hide",
-    "show": "Show",
-    "updatedAt": "Updated {time}",
-    "latency": "Latency",
-    "latencyP50": "p50",
-    "latencyP95": "p95",
-    "latencyP99": "p99",
-    "millisecondsShort": "{value}ms",
-    "notAvailable": "—",
-    "totalRequests": "Total requests",
-    "noDataYet": "No data yet",
-    "promptCache": "Prompt Cache",
-    "entries": "Entries",
-    "hitRate": "Hit Rate",
-    "hitsMisses": "Hits / Misses",
-    "signatureCache": "Signature Cache",
-    "signatureDefaults": "Defaults",
-    "signatureTool": "Tool",
-    "signatureFamily": "Family",
-    "signatureSession": "Session",
-    "recovering": "Recovering",
-    "noCBData": "No circuit breaker data available. Make some requests first.",
-    "providerHealthStatusAria": "Provider health status",
-    "issuesLabel": "Issues Detected",
-    "operational": "Operational",
-    "providers": "Providers",
-    "configuredProvidersLabel": "Configured in dashboard",
-    "configuredProvidersHint": "Providers with credentials saved in /dashboard/providers, regardless of runtime state.",
-    "activeProviders": "{count} active",
-    "activeProvidersHint": "Configured providers currently enabled for routing requests.",
-    "monitoredProviders": "{count} monitored",
-    "monitoredProvidersHint": "Providers currently tracked by circuit-breaker health monitors.",
-    "healthyCount": "{count} healthy",
-    "nodeVersion": "Node {version}",
-    "failures": "{count} failure",
-    "failuresPlural": "{count} failures",
-    "lastFailure": "Last",
-    "rateLimitStatus": "Rate Limit Status",
-    "activeLimiters": "{count} active limiter",
-    "activeLimitersPlural": "{count} active limiters",
-    "queued": "Queued",
-    "queuedCount": "{count} queued",
-    "running": "running",
-    "runningCount": "{count} running",
-    "ok": "OK",
-    "activeLockouts": "Active Lockouts",
-    "resetConfirm": "Reset all circuit breakers to healthy state? This will clear all failure counts and restore all providers to operational status.",
-    "resetAllTitle": "Reset all circuit breakers to healthy state",
-    "resetting": "Resetting...",
-    "resetAll": "Reset All",
-    "until": "Until {time}",
-    "limitExhausted": "Exhausted",
-    "learnedFromHeaders": "Learned from headers",
-    "remainingOfLimit": "{remaining}/{limit} remaining",
-    "throttleStatus": "Throttle: {value}",
-    "lastHeaderUpdate": "Header update: {age}",
-    "databaseHealth": "Kesehatan Basis Data",
-    "databaseHealthDescription": "Diagnosis dan perbaiki baris kuota/domain usang serta referensi kombo yang rusak.",
-    "status": "Status",
-    "attentionNeeded": "Perlu perhatian",
-    "repairs": "Perbaikan",
-    "repairing": "Memperbaiki...",
-    "runAutoRepair": "Jalankan Perbaikan Otomatis",
-    "repairBackupCreated": "Cadangan perbaikan telah dibuat sebelum melakukan mutasi.",
-    "sessionActivity": "Aktivitas Sesi",
-    "activeCount": "{count} aktif",
-    "requestCount": "{count, plural, one {# permintaan} other {# permintaan}}",
-    "idleSeconds": "{count}d menganggur",
-    "ageSeconds": "{count}d usia",
-    "quotaMonitors": "Pemantau Kuota",
-    "alerting": "Peringatan",
-    "errors": "Galat",
-    "degradationFull": "Penuh",
-    "degradationReduced": "Dikurangi",
-    "degradationMinimal": "Minimal",
-    "degradationDefault": "Bawaan",
-    "sinceTime": "Sejak {time}",
-    "retryIn": "coba lagi dalam {duration}",
-    "stickyBoundSessions": "Sesi yang terikat erat",
-    "sessionsByApiKey": "Sesi berdasarkan kunci API",
-    "noActiveSessionsTracked": "Belum ada sesi aktif yang terlacak.",
-    "noSessionQuotaMonitorsActive": "Tidak ada monitor kuota sesi yang aktif.",
-    "gracefulDegradationStatus": "Status Degradasi Anggun",
-    "additionalModels": "+{count} model lainnya",
-    "providerHealthMatrixTitle": "Matriks Kesehatan Penyedia",
-    "providerHealthMatrixDescription": "Status penyedia × akun × model dari pemutus, masa tenang, penguncian, dan log.",
-    "healthMatrixRange": "Rentang matriks kesehatan",
-    "providerFilter": "Filter penyedia",
-    "onlyIssues": "Hanya masalah",
-    "refresh": "Segarkan",
-    "accounts": "Akun",
-    "models": "Model",
-    "issues": "Masalah",
-    "loadingProviderHealthMatrix": "Memuat matriks kesehatan penyedia...",
-    "failedProviderHealthMatrix": "Gagal memuat Matriks Kesehatan Penyedia: {error}",
-    "noProvidersMatchedFilters": "Tidak ada penyedia yang cocok dengan filter saat ini.",
-    "modelPillSummary": "{requests} req · {successRate} sukses · {latency} rata-rata",
-    "modelLockoutSummary": "{reason} · {duration} tersisa",
-    "locked": "terkunci",
-    "inferred": "disimpulkan",
-    "inactive": "Tidak Aktif",
-    "noConnectionId": "tidak ada id koneksi",
-    "accountModelSummary": "{connectionId} · {count} model",
-    "cooldown": "masa jeda",
-    "durationRemaining": "{duration} tersisa",
-    "noSyncedModelsOrTraffic": "Belum ada model yang disinkronkan atau lalu lintas terkini.",
-    "providerRowSummary": "{active}/{total} akun aktif · {requests} req · {successRate} sukses · {latency} rata-rata",
-    "cooldownCount": "{count} masa jeda",
-    "lockoutCount": "{count} penguncian",
-    "issueCount": "{count} masalah",
-    "score": "Skor",
-    "lastRequest": "Permintaan terakhir",
-    "lastError": "Galat terakhir"
-  },
-  "telemetry": {
-    "title": "Telemetri Sistem",
-    "description": "Sinyal permintaan, runtime, sesi, dan memori bergulir dari proses OmniRoute ini.",
-    "uptime": "Waktu aktif",
-    "totalRequests": "Jumlah Permintaan",
-    "avgLatency": "Rata-rata Latensi",
-    "errorRate": "Tingkat Kesalahan",
-    "activeConnections": "Koneksi Aktif",
-    "memoryUsage": "Penggunaan Memori",
-    "latencyTrend": "Tren latensi",
-    "throughputTrend": "Tren throughput",
-    "memoryTrend": "Tren memori",
-    "refresh": "Segarkan",
-    "updatedAt": "Diperbarui {time}",
-    "loadFailed": "Gagal memuat telemetri.",
-    "partialData": "Telemetri tersedia sebagian: {error}"
-  },
-  "mitm": {
-    "title": "Proksi MITM",
-    "description": "Proksi transparan untuk mencegat dan merutekan permintaan klien.",
-    "enable": "Aktifkan Proksi MITM",
-    "enableDesc": "Memulai atau menghentikan proses intersepsi lokal dan penggantian DNS.",
-    "status": "Status",
-    "running": "Berlari",
-    "stopped": "Berhenti",
-    "start": "Mulai",
-    "stop": "Berhenti",
-    "refresh": "Segarkan",
-    "port": "Pelabuhan Proksi",
-    "apiKey": "Kunci API Router",
-    "apiKeyPlaceholder": "Opsional; jatuh kembali ke kunci lokal",
-    "sudoPassword": "Kata Sandi Sudo",
-    "cachedPassword": "Di-cache untuk proses ini",
-    "saveSettings": "Simpan Pengaturan",
-    "settingsSaved": "Pengaturan MITM disimpan.",
-    "startedSuccess": "Proksi MITM dimulai.",
-    "stoppedSuccess": "Proksi MITM berhenti.",
-    "saveFailed": "Gagal memperbarui pengaturan MITM.",
-    "loadFailed": "Gagal memuat pengaturan MITM.",
-    "invalidPort": "Intersepsi MITM transparan saat ini memerlukan port 443.",
-    "certificate": "Sertifikat CA",
-    "certificateReady": "Sertifikat tersedia untuk instalasi kepercayaan klien.",
-    "certificateMissing": "Sertifikat belum dibuat.",
-    "available": "Tersedia",
-    "missing": "Hilang",
-    "downloadCert": "Unduh Sertifikat CA",
-    "regenerateCert": "Sertifikat Regenerasi",
-    "regenerateConfirm": "Ini akan membatalkan kepercayaan klien yang ada. Melanjutkan?",
-    "regenerateSuccess": "Sertifikat MITM dibuat ulang.",
-    "regenerateFailed": "Gagal membuat ulang sertifikat MITM.",
-    "targetRoutes": "Rute Sasaran",
-    "interceptedRequests": "Permintaan yang Disadap",
-    "activeConnections": "Koneksi Aktif",
-    "dnsConfigured": "DNS Dikonfigurasi",
-    "pid": "PID",
-    "lastIntercept": "Intersepsi Terakhir",
-    "target": "Sasaran",
-    "host": "Tuan rumah",
-    "localPort": "Pelabuhan Lokal",
-    "endpoints": "Titik akhir",
-    "enabled": "Diaktifkan",
-    "configured": "Dikonfigurasi",
-    "yes": "Ya",
-    "no": "Tidak",
-    "noTargets": "Tidak ada rute target yang dikonfigurasi."
-  },
-  "limits": {
-    "title": "Limits & Quotas",
-    "rateLimit": "Rate Limit",
-    "remaining": "Remaining",
-    "requestsPerMinute": "Requests/min",
-    "tokensPerMinute": "Tokens/min",
-    "dailyLimit": "Daily Limit"
-  },
-  "logs": {
-    "title": "Logs",
-    "requestLogs": "Request Logs",
-    "proxyLogs": "Proxy Logs",
-    "auditLog": "Audit Log",
-    "console": "Console",
-    "auditLogDesc": "Administrative actions and security events",
-    "loading": "Loading...",
-    "refresh": "Refresh",
-    "filterByAction": "Filter by action...",
-    "filterByActor": "Filter by actor...",
-    "filterEntriesAria": "Filter audit log entries",
-    "filterByActionTypeAria": "Filter by action type",
-    "filterByActorAria": "Filter by actor",
-    "refreshAuditLogAria": "Refresh audit log",
-    "tableAria": "Audit log entries",
-    "failedFetchAuditLog": "Failed to fetch audit log",
-    "showing": "Showing {count} entries (offset {offset})",
-    "search": "Search",
-    "timestamp": "Timestamp",
-    "action": "Action",
-    "actor": "Actor",
-    "target": "Target",
-    "details": "Details",
-    "ipAddress": "IP Address",
-    "notAvailable": "—",
-    "noEntries": "No audit log entries found",
-    "previous": "Previous",
-    "next": "Next",
-    "providerWarningTitle": "Provider Warnings",
-    "viewDetails": "View Details",
-    "eventMetadata": "Event Metadata",
-    "eventPayload": "Event Payload",
-    "requestId": "Request Id",
-    "providerWarningDesc": "Some providers returned warnings during request processing",
-    "a": "A",
-    "offset": "Offset",
-    "limit": "Limit",
-    "status": "Status",
-    "resourceType": "Resource Type",
-    "totalEntries": "Total Entries",
-    "tab": "Tab",
-    "auditModalSubtitle": "Event details and metadata",
-    "close": "Close",
-    "runningRequests": "Active Requests",
-    "runningRequestsDesc": "Real-time view of currently running upstream requests",
-    "clearAll": "Hapus Semua",
-    "confirmClearActiveRequests": "Hapus semua permintaan aktif?",
-    "model": "Model",
-    "provider": "Provider",
-    "account": "Account",
-    "elapsed": "Elapsed",
-    "activeStage": "Tahap",
-    "activeStageUnknown": "Belum dikirim ke upstream",
-    "activeStageRegistered": "Terdaftar",
-    "activeStagePayloadPrepared": "Payload disiapkan",
-    "activeStageWaitingAccountSlot": "Menunggu slot akun",
-    "activeStageWaitingRateLimit": "Menunggu pembatas laju",
-    "activeStageRateLimitSlotAcquired": "Slot pembatas laju diperoleh",
-    "activeStageSendingToProvider": "Mengirim ke upstream",
-    "activeStageProviderResponseStarted": "Respons upstream dimulai",
-    "count": "Count",
-    "payloads": "Payloads",
-    "viewPayloads": "View",
-    "activeCount": "{count} active",
-    "clientPayload": "Client Request Payload",
-    "upstreamPayload": "Upstream Provider Payload",
-    "upstreamNotSentYet": "Not sent to upstream yet",
-    "runningRequestDetailMeta": "Account: {account} — Elapsed: {elapsed}",
-    "export": "Export",
-    "exporting": "Exporting...",
-    "exportFailed": "Export failed",
-    "cleanHistoryButton": "Bersihkan riwayat",
-    "cleanHistoryTitle": "Bersihkan riwayat log?",
-    "cleanHistoryMessage": "Ini akan menghapus secara permanen semua baris log permintaan, baris detail lama, dan berkas artefak lokal di bawah DATA_DIR/call_logs. Halaman langsung akan disegarkan setelah pembersihan.",
-    "cleanHistoryConfirm": "Bersihkan riwayat",
-    "cleanHistoryCancel": "Batal",
-    "cleanHistorySuccess": "Berhasil membersihkan {deleted} entri log, {deletedArtifacts} artefak, dan {deletedDetailedLogs} baris detail lama.",
-    "cleanHistoryEmpty": "Tidak ada riwayat log permintaan yang ditemukan.",
-    "cleanHistoryFailed": "Gagal membersihkan riwayat log.",
-    "timeRange": "Time Range",
-    "lastNHours": "Last {hours}",
-    "defaultRange": "default",
-    "consoleViewer": {
-      "fetchFailed": "Failed to fetch logs",
-      "copyFailed": "Failed to copy log entry",
-      "copyLogEntry": "Copy log entry",
-      "filterByLevel": "Saring berdasarkan tingkat log",
-      "searchPlaceholder": "Cari log…",
-      "searchAria": "Cari entri log",
-      "disableAutoScroll": "Nonaktifkan gulir otomatis",
-      "enableAutoScroll": "Aktifkan gulir otomatis",
-      "autoScroll": "Gulir otomatis",
-      "entryCount": "{count, plural, one {# entri} other {# entri}}",
-      "lastHour": "1 jam terakhir",
-      "updatedAt": "Diperbarui {time}",
-      "fileLoggingRequired": "Pastikan aplikasi menulis log ke berkas (APP_LOG_TO_FILE=true)",
-      "consoleAria": "Log konsol aplikasi",
-      "applicationConsole": "Konsol Aplikasi",
-      "emptyFileLoggingHint": "Pastikan APP_LOG_TO_FILE=true diatur dalam berkas .env Anda"
-    },
-    "compressionLogTitle": "Log Kompresi",
-    "compressionLogEmpty": "Belum ada permintaan terkompresi. Statistik kompresi akan muncul di sini ketika permintaan diproses dengan kompresi diaktifkan.",
-    "tokens": "token"
-  },
-  "onboarding": {
-    "welcome": "Welcome",
-    "tiers": "Tingkat",
-    "security": "Security",
-    "test": "Test",
-    "ready": "Ready!",
-    "setPassword": "Set Password",
-    "addProvider": "Add your first provider",
-    "getStarted": "Get Started",
-    "skip": "Skip",
-    "skipWizard": "Skip wizard entirely",
-    "skipPassword": "Skip password setup",
-    "skipAndContinue": "Skip & Continue",
-    "passwordLabel": "Password",
-    "confirmPassword": "Confirm Password",
-    "enterPassword": "Enter password",
-    "confirmPasswordPlaceholder": "Confirm password",
-    "passwordsMismatch": "Passwords do not match",
-    "setupComplete": "Setup Complete!",
-    "goToDashboard": "Go to Dashboard →",
-    "welcomeDesc": "OmniRoute is your local AI API proxy. It routes requests to multiple AI providers with load balancing, failover, and usage tracking.",
-    "multiProvider": "Multi-Provider",
-    "usageTracking": "Usage Tracking",
-    "securityDesc": "Set a password to protect your dashboard, or skip for now.",
-    "securityDescSkipWarning": "⚠️ Without a password, you won't be able to add providers during setup. You can add them later from the dashboard after setting a password.",
-    "providerDesc": "Connect your first AI provider. You can add more later.",
-    "providerRequiresPassword": "You need to set a password first to add providers. Please go back to the security step and set a password, or add providers later from the dashboard.",
-    "apiKeyRequired": "API Key (required)",
-    "customUrlOptional": "Custom URL (optional)",
-    "testDesc": "Let's verify your provider connection works.",
-    "runTest": "Run Connection Test",
-    "testingConnection": "Testing connection...",
-    "connectionSuccessful": "Connection successful! Your provider is ready.",
-    "noProviderFound": "No provider found. You can add one from the dashboard later.",
-    "testFailed": "Test failed, but you can configure this later.",
-    "couldNotTest": "Could not test right now. You can test from the dashboard.",
-    "doneDesc": "You're all set! Your OmniRoute instance is configured and ready to proxy AI requests.",
-    "yourEndpoint": "Your endpoint:",
-    "continue": "Continue",
-    "retry": "Retry",
-    "failedSetPassword": "Failed to set password. Try again.",
-    "failedAddProvider": "Failed to add provider. Try again.",
-    "connectionError": "Connection error. Please try again.",
-    "provider": "Provider",
-    "apiKeyHelp": "Kunci API adalah kata sandi untuk layanan AI. Dapatkan satu dari situs web penyedia Anda (mis., platform.openai.com, console.anthropic.com).",
-    "tier": {
-      "subtitle": "OmniRoute mengatur penyedia menjadi tiga tingkatan sehingga perutean memilih jalur yang paling andal dan berbiaya terendah terlebih dahulu.",
-      "flowCaption": "Permintaan mengalir melalui kuota langganan Anda terlebih dahulu, kemudian penyedia murah bayar-per-token, lalu penyedia tingkat gratis — otomatis, tanpa konfigurasi.",
-      "afterSetup": "setelah penyiapan.",
-      "tier1": {
-        "label": "Klien premium",
-        "description": "CLI kelas satu dengan alur autentikasi asli dan model penalaran."
-      },
-      "tier2": {
-        "label": "Dioptimalkan biaya",
-        "description": "Penyedia murah dan throughput tinggi yang digunakan untuk lalu lintas sehari-hari."
-      },
-      "tier3": {
-        "label": "Pengganti & spesialisasi",
-        "description": "Titik akhir yang dihosting secara lokal atau khusus digunakan sebagai cadangan."
-      },
-      "configure": "Konfigurasikan penyedia"
-    },
-    "tierFlowDiagramAlt": "Diagram cadangan 3 tingkat OmniRoute",
-    "apiKeyMgmt": "API Key Mgmt",
-    "freeProviders": {
-      "title": "Siapkan penyedia gratis",
-      "description": "Opsional untuk mengaktifkan penyedia tanpa pendaftaran yang dipilih. Tinjau pemberitahuan dan situs masing-masing penyedia sebelum melanjutkan; ketersediaan dan batasan tarif dikendalikan oleh pihak ketiga.",
-      "loading": "Memuat penyedia gratis...",
-      "loadFailed": "Tidak dapat memuat penyedia gratis.",
-      "alreadyConfigured": "Semua penyedia gratis yang memenuhi syarat sudah dikonfigurasi.",
-      "reviewProviderSite": "Tinjau situs penyedia dan syaratnya",
-      "confirmation": "Saya telah meninjau penyedia pihak ketiga ini dan ingin OmniRoute untuk membuat koneksi yang dipilih.",
-      "setupSelected": "Atur penyedia yang dipilih",
-      "settingUp": "Menyiapkan...",
-      "setupFailed": "Tidak dapat mengatur penyedia yang dipilih. Tidak ada yang diubah.",
-      "retryFailed": "Coba ulang penyedia yang gagal",
-      "orUseApiKey": "atau sambungkan dengan kunci API",
-      "result": {
-        "created": "dibuat",
-        "skipped": "sudah dikonfigurasi",
-        "failed": "gagal"
-      }
-    }
-  },
-  "providers": {
-    "title": "Providers",
-    "Account Deactivated": "Akun Dinonaktifkan",
-    "allProviders": "Semua Penyedia",
-    "audioProviders": "Penyedia Audio",
-    "showFreeOnly": "Hanya gratis",
-    "addProvider": "Add Provider",
-    "addFirstProvider": "Tambahkan penyedia pertama Anda",
-    "addFirstProviderDesc": "Hubungkan penyedia AI untuk memulai perutean permintaan melalui OmniRoute. Anda dapat menggunakan penyedia gratis, kunci API, atau akun OAuth.",
-    "learnMore": "Pelajari lebih lanjut",
-    "importFromFile": "Impor dari berkas",
-    "importFromFileTitle": "Impor penyedia dari berkas",
-    "importFromFileDescription": "Unggah berkas CSV atau JSON yang mencantumkan beberapa penyedia (setiap baris dapat berupa jenis penyedia yang berbeda). Tinjau baris yang diurai di bawah ini dan pilih mana yang akan diimpor.",
-    "importFromFileChoose": "Pilih berkas",
-    "importFromFileSelectHint": "{count} dari {total} terpilih",
-    "importFromFileColProvider": "Penyedia",
-    "importFromFileColName": "Nama",
-    "importFromFileColBaseUrl": "URL Dasar",
-    "importFromFileErrorLine": "Baris {line}: {reason}",
-    "importErrorMissingProvider": "penyedia tidak ada",
-    "importErrorMissingName": "nama tidak ada",
-    "importErrorMissingApiKey": "kunci API tidak ada",
-    "importErrorInvalidPriority": "prioritas tidak valid (harus 1-100)",
-    "importErrorMalformedRow": "baris tidak sesuai format",
-    "importErrorNotArray": "berkas harus berisi larik JSON",
-    "importFromFileImporting": "Mengimpor…",
-    "importFromFileImport": "Impor {count} penyedia",
-    "importFromFileResult": "Berhasil mengimpor {success} penyedia ({failed} gagal)",
-    "adaptaTutorial": {
-      "title": "How to connect Adapta Web",
-      "introPrefix": "Adapta authenticates through Clerk. The token",
-      "introSuffix": "is a long-lived JWT that lets OmniRoute refresh sessions automatically.",
-      "or": "or",
-      "step1Title": "Open Adapta chat",
-      "step1DescPrefix": "Open",
-      "step1DescSuffix": "and sign in with your Gold or Business account.",
-      "step2Title": "Open DevTools",
-      "step2DescPrefix": "Press",
-      "step2DescSuffix": "to open Developer Tools.",
-      "step3Title": "Go to Application → Cookies",
-      "step3DescPrefix": "In the",
-      "step3DescMiddle": "expand",
-      "step3DescSuffix": "and click",
-      "step4Title": "Copy the cookie value for",
-      "step4DescPrefix": "Find the cookie named",
-      "step4DescMiddle": "in the list. Click it and copy the content from the",
-      "step4DescSuffix": "column. It starts with",
-      "step5Title": "Paste it here and save",
-      "step5DescPrefix": "Click",
-      "step5DescMiddle": "paste the",
-      "step5DescSuffix": "value into the API Key field, then save. OmniRoute will refresh the session automatically.",
-      "tipLabel": "Tip:",
-      "tipPrefix": "The",
-      "tipSuffix": "cookie is long-lived, usually for months. You only need to renew it if you sign out or Adapta invalidates the session."
-    },
-    "editProvider": "Edit Provider",
-    "deleteProvider": "Delete Provider",
-    "noProviders": "No providers configured",
-    "modelAvailability": "Model Availability",
-    "accounts": "Accounts",
-    "newAccount": "New Account",
-    "deleteConfirm": "Are you sure you want to delete this provider?",
-    "testing": "Testing...",
-    "testConnection": "Test Connection",
-    "testSuccess": "Connection successful",
-    "testFailed": "Connection failed",
-    "available": "Available",
-    "cooldown": "Cooldown",
-    "unavailable": "Unavailable",
-    "unknown": "Unknown",
-    "oauthLabel": "OAuth",
-    "compatibleLabel": "Compatible",
-    "chat": "Chat",
-    "responses": "Responses",
-    "messages": "Messages",
-    "oauthProviders": "OAuth Providers",
-    "freeProviders": "Free Providers",
-    "apiKeyProviders": "API Key Providers",
-    "compatibleProviders": "API Key Compatible Providers",
-    "testAll": "Test All",
-    "reorderByAvailability": "पुनः क्रमबद्ध करें",
-    "reorderByAvailabilityTitle": "उपलब्धता के अनुसार कनेक्शन पुनः क्रमबद्ध करें",
-    "reorderByAvailabilityError": "उपलब्धता के अनुसार कनेक्शन पुनः क्रमबद्ध करने में विफल",
-    "distributeProxies": "Distribute Proxies",
-    "distributing": "Distributing...",
-    "selectedCount": "{count, plural, one {# selected} other {# selected}}",
-    "accountsCount": "{count, plural, one {# account} other {# accounts}}",
-    "testAllOAuth": "Test all OAuth connections",
-    "testAllFree": "Test all Free connections",
-    "testAllApiKey": "Test all API Key connections",
-    "testAllCompatible": "Test all Compatible connections",
-    "testAllModels": "Test all models",
-    "testAllModelsConfirm": "Test all visible models? Failed models will be hidden if auto-hide is enabled.",
-    "testingAllModels": "Testing {done}/{total}...",
-    "testAllResults": "{ok} of {total} models working",
-    "noModelsToTest": "No models match the current filter",
-    "showAllModels": "All",
-    "showVisibleOnly": "Visible only",
-    "freeFilterAll": "All",
-    "freeFilterFreeOnly": "Free only",
-    "freeFilterPaidOnly": "Paid only",
-    "sortFreeFirst": "Free first",
-    "showHiddenOnly": "Hanya yang tersembunyi",
-    "filterByVisibility": "Filter berdasarkan visibilitas",
-    "autoHideFailed": "Sembunyikan otomatis model yang gagal",
-    "autoHideFailedHint": "Jika diaktifkan, Uji semua menyembunyikan kegagalan non-transien dari katalog publik seperti /v1/models. Pengujian model tunggal tidak pernah menyembunyikan secara otomatis.",
-    "connected": "{count} Connected",
-    "errorCount": "{count} Error ({code})",
-    "errorCountNoCode": "{count} Error",
-    "testAllCompleted": "Menguji {total} model: {ok} OK, {failed} gagal",
-    "modelAutoHidden": "Model {model} disembunyikan otomatis (uji gagal)",
-    "filterAll": "Semua",
-    "filterVisible": "Hanya yang terlihat",
-    "filterHidden": "Hanya yang tersembunyi",
-    "modelsHiddenCount": "{count} tersembunyi",
-    "warningCount": "{count} Peringatan",
-    "noConnections": "No connections",
-    "expiredBadge": "Expired",
-    "expiringSoonBadge": "Expiring Soon",
-    "freeTier": "Tingkat Gratis",
-    "freeTierAvailable": "Tersedia tingkat gratis",
-    "hasFreeTooltip": "Tingkat gratis tersedia",
-    "noAuthLabel": "Tanpa Autentikasi",
-    "noAuthProviders": "Tanpa Penyedia Autentikasi",
-    "upstreamProxyLabel": "Proksi Upstream",
-    "freeAggregated": "Semua penyedia dengan tingkat gratis (juga ditampilkan dalam kategori aslinya)",
-    "deprecated": "Tidak digunakan lagi",
-    "deprecatedProvider": "Penyedia ini sudah tidak digunakan lagi",
-    "riskNotice": {
-      "title": "Sebelum melanjutkan",
-      "detailsTitle": "Usage caveats",
-      "tooltip": "Penyedia dengan peringatan penggunaan — klik untuk detail",
-      "oauth": "Penyedia ini menggunakan sesi produk/OAuth resmi Anda, yang tidak diizinkan untuk penggunaan proksi/router. Kami tidak menyarankan penggunaan agen otonom yang intensif (gaya OpenCloud, alur multi-langkah yang panjang, batch besar) — upstream mungkin bereaksi dengan membatasi atau memblokir akun. Gunakan dengan risiko Anda sendiri.",
-      "webCookie": "Penyedia ini mengautentikasi melalui kuki sesi web Anda. Layanan upstream dapat membatalkan sesi kapan saja, mengharuskan Anda untuk masuk kembali. Tidak disarankan untuk operasi jangka panjang tanpa pengawasan. Gunakan dengan risiko Anda sendiri.",
-      "deprecated": "Penyedia ini telah dihentikan oleh upstream-nya dan mungkin berhenti berfungsi tanpa pemberitahuan. Koneksi yang ada mungkin terus berfungsi hingga upstream sepenuhnya menghapus akses. Pertimbangkan alternatif lain.",
-      "dontShowAgain": "Jangan tunjukkan ini lagi untuk penyedia ini",
-      "understand": "Saya mengerti, lanjutkan",
-      "cancel": "Batal"
-    },
-    "warningNotice": {
-      "tooltip": "{count} connection(s) flagged — up to {maxFailures} recent failures{lastFailureSuffix}. Click to view connection health.",
-      "lastFailureSuffix": " (last failure {time})",
-      "ariaLabel": "View connection health details, {count} warning(s)"
-    },
-    "disabled": "Disabled",
-    "enableProvider": "Enable provider",
-    "disableProvider": "Disable provider",
-    "testResults": "Test Results",
-    "noCompatibleYet": "No compatible providers added yet",
-    "compatibleHint": "Use the buttons above to add OpenAI or Anthropic compatible endpoints",
-    "addOpenAICompatible": "Add OpenAI Compatible",
-    "addAnthropicCompatible": "Add Anthropic Compatible",
-    "addNewProvider": "Add New Provider",
-    "backToProviders": "Back to Providers",
-    "configureNewProvider": "Configure a new AI provider to use with your applications.",
-    "providerLabel": "Provider",
-    "selectProvider": "Select a provider",
-    "selectedProvider": "Selected provider",
-    "authMethod": "Authentication Method",
-    "apiKeyLabel": "API Key",
-    "apiKeyRequired": "API Key is required",
-    "selectProviderRequired": "Please select a provider",
-    "enterApiKey": "Enter your API key",
-    "apiKeySecure": "Your API key will be encrypted and stored securely.",
-    "oauth2Connect": "Connect with OAuth2",
-    "oauth2Label": "OAuth2",
-    "oauth2Desc": "Connect your account using OAuth2 authentication.",
-    "displayName": "Display Name",
-    "displayNamePlaceholder": "e.g., Production API, Dev Environment",
-    "displayNameHint": "Optional. A friendly name to identify this configuration.",
-    "active": "Active",
-    "activeDescription": "Enable this provider for use in your applications",
-    "cancel": "Cancel",
-    "createProvider": "Create Provider",
-    "failedCreate": "Failed to create provider",
-    "errorOccurred": "An error occurred. Please try again.",
-    "modelStatus": "Model Status",
-    "showConfiguredOnly": "Configured only",
-    "allModelsOperational": "All models operational",
-    "modelsWithIssues": "{count} model(s) with issues",
-    "allModelsNormal": "All models are responding normally.",
-    "cooldownCleared": "Cooldown cleared for {model}",
-    "failedClearCooldown": "Failed to clear cooldown",
-    "loadingAvailability": "Loading model availability...",
-    "clearCooldown": "Clear",
-    "clearing": "Clearing...",
-    "until": "Until {time}",
-    "providerTestFailed": "Provider test failed",
-    "providerTestTimeout": "Provider test timed out — too many connections to test at once",
-    "modeTest": "{mode} Test",
-    "passedCount": "{count} passed",
-    "failedCount": "{count} failed",
-    "testedCount": "{count} tested",
-    "millisecondsAbbr": "{value}ms",
-    "okShort": "OK",
-    "errorShort": "ERROR",
-    "noActiveConnectionsInGroup": "No active connections found for this group.",
-    "allTestsPassed": "All {total} tests passed",
-    "testSummary": "{passed}/{total} passed, {failed} failed",
-    "nameLabel": "Name",
-    "prefixLabel": "Prefix",
-    "baseUrlLabel": "Base URL",
-    "apiTypeLabel": "API Type",
-    "prefixHint": "Required. Unique prefix for model names.",
-    "nameHint": "Required. A friendly label for this node.",
-    "baseUrlHint": "Required. Provider API base URL.",
-    "iconUrlLabel": "URL Ikon",
-    "iconUrlHint": "Opsional. URL gambar yang ditampilkan sebagai ikon penyedia ini.",
-    "iconUrlInvalid": "URL ikon tidak valid. Gunakan URL http(s):// atau data:image/*;base64.",
-    "anthropicPrefixPlaceholder": "ac-prod",
-    "openaiPrefixPlaceholder": "oc-prod",
-    "anthropicBaseUrlPlaceholder": "https://api.anthropic.com/v1",
-    "openaiBaseUrlPlaceholder": "https://api.openai.com/v1",
-    "validateConnection": "Validate Connection",
-    "validating": "Validating...",
-    "connectionValid": "Connection is valid!",
-    "connectionFailed": "Connection failed. Check URL and key.",
-    "testKeyLabel": "Test API Key",
-    "testKeyPlaceholder": "sk-... (for validation only)",
-    "providerNotFound": "Provider not found",
-    "deleteConnectionConfirm": "Delete this connection?",
-    "deleteConnectionConfirmNamed": "Are you sure you want to delete {name}? This action cannot be undone.",
-    "batchDeleteSelected": "Delete Selected ({count})",
-    "batchDeleteConfirm": "Delete {count} connection(s)? This action cannot be undone.",
-    "batchDeleteSuccess": "Deleted {count} connection(s)",
-    "batchActivateSelected": "Aktifkan",
-    "batchDeactivateSelected": "Nonaktifkan",
-    "batchRetestSelected": "Uji ulang",
-    "batchActivateSuccess": "Mengaktifkan {count} koneksi",
-    "batchDeactivateSuccess": "Menonaktifkan {count} koneksi",
-    "batchUpdatePartial": "{count} diperbarui, {skipped} dilewati (tidak ada lagi)",
-    "batchUpdateNone": "Tidak ada koneksi yang diperbarui (mungkin tidak ada lagi)",
-    "batchRetestLimit": "Uji ulang hingga {max} koneksi sekaligus",
-    "noConnectionsToTest": "Tidak ada koneksi yang cocok untuk diuji",
-    "batchDeleteConfirmTitle": "Hapus koneksi",
-    "batchDeleteConfirmButton": "Hapus",
-    "filterActive": "Aktif",
-    "filterError": "Kesalahan",
-    "filterBanned": "Diblokir",
-    "filterCreditsExhausted": "Kredit habis",
-    "accountSearchPlaceholder": "Search accounts…",
-    "noFilteredConnections": "Tidak ada koneksi yang cocok dengan filter saat ini.",
-    "failedSetAlias": "Failed to set alias",
-    "setAliasSuccess": "Alias {alias} diatur",
-    "deleteAliasSuccess": "Alias {alias} dihapus",
-    "failedSaveConnection": "Failed to save connection",
-    "failedSaveConnectionRetry": "Failed to save connection. Please try again.",
-    "failedRetestConnection": "Failed to retest connection",
-    "deleteCompatibleNodeConfirm": "Delete this {type} Compatible node?",
-    "anthropicCompatibleDetails": "Anthropic Compatible Details",
-    "openaiCompatibleDetails": "OpenAI Compatible Details",
-    "messagesApi": "Messages API",
-    "responsesApi": "Responses API",
-    "embeddings": "Embeddings",
-    "audioTranscriptions": "Audio Transcriptions",
-    "audioSpeech": "Audio Speech",
-    "imagesGenerations": "Images Generations",
-    "chatCompletions": "Chat Completions",
-    "importingModels": "Importing...",
-    "importFromModels": "Import from /models",
-    "modelsImported": "{count} models imported",
-    "allModelsAlreadyImported": "All models already imported",
-    "noNewModelsToImport": "No new models to import — all models are already in the registry or custom models list",
-    "skippingExistingModels": "Skipping {count} existing models",
-    "autoSync": "Auto-Sync",
-    "autoSyncShort": "Sync",
-    "autoFetchModels": "Ambil model upstream secara otomatis",
-    "autoFetchModelsTooltip": "Ambil dan simpan model upstream saat diperlukan",
-    "autoFetchModelsEnabled": "Model hulu auto-fetch diaktifkan",
-    "autoFetchModelsDisabled": "Model upstream auto-fetch dinonaktifkan",
-    "autoFetchModelsToggleFailed": "Gagal untuk mengubah model upstream auto-fetch",
-    "autoFetchModelsPartialFailure": "Beberapa koneksi diperbarui, tetapi pengambilan otomatis model upstream tidak berubah di mana-mana",
-    "overridesUpstreamModel": "Mengganti upstream",
-    "overridesUpstreamModelHint": "Pengaturan Anda menimpa model upstream ini",
-    "resetToUpstreamDefaults": "Kembalikan pengaturan default upstream",
-    "resetToUpstreamDefaultsSuccess": "Mengembalikan pengaturan model upstream ke default",
-    "resetToUpstreamDefaultsFailed": "Gagal mengembalikan pengaturan model upstream ke default",
-    "autoSyncTooltip": "Automatically refresh model list every 24h (configurable via MODEL_SYNC_INTERVAL_HOURS)",
-    "autoSyncEnabled": "Auto-sync enabled — models will refresh periodically",
-    "autoSyncDisabled": "Auto-sync disabled",
-    "autoSyncToggleFailed": "Failed to toggle auto-sync",
-    "autoSyncPartialFailure": "Auto-sync updated for some connections, but not all",
-    "clearAllModels": "Clear All Models",
-    "clearAllModelsConfirm": "Are you sure you want to remove all models for this provider? This cannot be undone.",
-    "clearAllModelsSuccess": "All models cleared",
-    "clearAllModelsFailed": "Failed to clear models",
-    "addConnectionToImport": "Add a connection to enable importing.",
-    "noModelsConfigured": "No models configured",
-    "connectionCount": "{count} connection(s)",
-    "fetchingModels": "Fetching available models...",
-    "failedFetchModels": "Failed to fetch models",
-    "noFreeModelsFound": "Tidak ada model gratis yang ditemukan untuk penyedia ini — tidak ada yang diimpor.",
-    "fetchModelsSuccess": "Menemukan {count} model baru",
-    "fetchModelsFailed": "Tidak dapat mengambil model secara otomatis (Anda dapat mencoba lagi dari pengaturan)",
-    "noModelsFound": "No models found",
-    "importFailed": "Import failed",
-    "noNewModelsAdded": "No new models were added.",
-    "adding": "Adding...",
-    "close": "Close",
-    "importingModelsTitle": "Importing Models",
-    "copyModel": "Copy model",
-    "filterModels": "Filter models...",
-    "testAllRateLimited": "Batas laju tercapai, dihentikan lebih awal",
-    "hideFailedAuto": "Sembunyikan otomatis model yang gagal",
-    "selectAllModels": "Select all",
-    "hideAllModels": "Sembunyikan semua",
-    "modelsActive": "Active",
-    "showModel": "Show model",
-    "hideModel": "Hide model",
-    "removeModel": "Remove model",
-    "rateLimitProtected": "Protected",
-    "rateLimitUnprotected": "Unprotected",
-    "providerQuotaShort": "Kuota",
-    "hideConnectionFromProviderQuota": "Sembunyikan akun ini dari Kuota Penyedia",
-    "showConnectionInProviderQuota": "Tampilkan akun ini di Kuota Penyedia",
-    "quotaVisibilityUpdateFailed": "Gagal memperbarui visibilitas Kuota Penyedia",
-    "enableRateLimitProtection": "Click to enable rate limit protection",
-    "disableRateLimitProtection": "Click to disable rate limit protection",
-    "testAllProgress": "Diuji {done}/{total}",
-    "testAllFailedHidden": "{count} model yang gagal disembunyikan",
-    "testAllDone": "Semua model telah diuji",
-    "productionKey": "Production Key",
-    "enterNewApiKey": "Enter new API key",
-    "codexApplyModalTitle": "Berlaku untuk Codex Lokal",
-    "codexApplyTargetLabel": "Jalur sasaran",
-    "codexApplyBackupLabel": "Cadangan",
-    "codexApplyWarning": "Ini akan menggantikan auth.json yang ada. Melanjutkan?",
-    "codexApplyConfirmCheckbox": "Saya mengonfirmasi bahwa saya ingin mengganti auth.json yang ada",
-    "codexApply": "Terapkan",
-    "bulkTabSingle": "Lajang",
-    "bulkTabBulkAdd": "Tambah Massal",
-    "bulkAddFormatHint": "Satu kunci per baris. Format: nama|apiKey atau hanya apiKey (dinamai otomatis berdasarkan indeks).",
-    "bulkValidateKeys": "Validasi setiap kunci sebelum menyimpan (lebih lambat)",
-    "bulkAddAllKeys": "Tambahkan Semua Kunci",
-    "bulkAddedCount": "{count, plural, one {# key added} other {# keys added}}",
-    "bulkFailedCount": "{count, plural, one {# failed} other {# failed}}",
-    "optional": "Optional",
-    "anthropicCompatibleName": "Anthropic Compatible",
-    "openaiCompatibleName": "OpenAI Compatible",
-    "compatibleDefaultModelLabel": "Model Default",
-    "compatibleDefaultModelHint": "Masukkan ID model persis seperti yang diharapkan oleh endpoint kompatibel Anda. Model ini akan disimpan sebagai default koneksi.",
-    "failedImportModels": "Failed to import models",
-    "noModelsReturnedFromEndpoint": "No models returned from /models endpoint.",
-    "importingModelsProgress": "Importing {current} of {total} models...",
-    "foundModelsStartingImport": "Found {count} models. Starting import...",
-    "importingModelById": "Importing {modelId}...",
-    "importSuccessCount": "Successfully imported {count, plural, one {# model} other {# models}}!",
-    "noNewModelsAddedExisting": "No new models were added (all already exist).",
-    "importDoneCount": "✓ Done! {count, plural, one {# model imported.} other {# models imported.}}",
-    "unexpectedErrorOccurred": "An unexpected error occurred",
-    "getApiKey": "Dapatkan kunci API",
-    "getApiKeyDescription": "Daftar atau mendaftar untuk kunci API",
-    "connectionCountLabel": "{count, plural, one {# connection} other {# connections}}",
-    "messagesPath": "messages",
-    "responsesPath": "responses",
-    "chatCompletionsPath": "chat/completions",
-    "add": "Add",
-    "edit": "Edit",
-    "delete": "Delete",
-    "anthropic": "Anthropic",
-    "openai": "OpenAI",
-    "singleConnectionPerCompatible": "Only one connection is allowed per compatible node. Add another node if you need more connections.",
-    "connections": "Connections",
-    "providerProxyTitleConfigured": "Provider proxy: {host}",
-    "configured": "configured",
-    "providerProxyConfigureHint": "Configure proxy for all connections of this provider",
-    "providerProxy": "Provider Proxy",
-    "repairEnv": "Repair env",
-    "repairEnvWorking": "Repairing...",
-    "repairEnvHint": "Restore missing OAuth defaults into .env without overwriting existing values.",
-    "repairEnvSuccess": "OAuth defaults restored",
-    "repairEnvFailed": "Failed to repair .env",
-    "noConnectionsYet": "No connections yet",
-    "addFirstConnectionHint": "Add your first connection to get started",
-    "addConnection": "Add Connection",
-    "availableModels": "Available Models",
-    "builtInModels": "Built-in models",
-    "builtInModelsHint": "Registry models for this provider. Use the pencil to set compatibility options.",
-    "pageAutoRefresh": "Page will refresh automatically...",
-    "statusDisabled": "disabled",
-    "statusConnected": "connected",
-    "statusRuntimeIssue": "runtime issue",
-    "statusAuthFailed": "auth failed",
-    "statusRateLimited": "rate limited",
-    "statusNetworkIssue": "network issue",
-    "statusTestUnsupported": "test unsupported",
-    "statusUnavailable": "unavailable",
-    "statusFailed": "failed",
-    "statusError": "error",
-    "oauthAccount": "OAuth Account",
-    "errorTypeRuntime": "Local runtime",
-    "errorTypeUpstreamAuth": "Upstream auth",
-    "errorTypeMissingCredential": "Missing credential",
-    "errorTypeRefreshFailed": "Refresh failed",
-    "errorTypeTokenExpired": "Token expired",
-    "errorTypeRateLimited": "Rate limited",
-    "errorTypeUpstreamUnavailable": "Upstream unavailable",
-    "errorTypeNetworkError": "Network error",
-    "errorTypeTestUnsupported": "Test unsupported",
-    "errorTypeUpstreamError": "Upstream error",
-    "errorTypeCreditsExhausted": "Tidak ada kredit",
-    "errorTypeBanned": "403 Diblokir",
-    "proxySourceGlobal": "Global",
-    "proxySourceProvider": "Provider",
-    "proxySourceKey": "Key",
-    "proxyConfiguredBySource": "Proxy ({source}): {host}",
-    "proxyOn": "Proksi Aktif",
-    "proxyOff": "Langsung (lewati proksi)",
-    "proxyEnabledTitle": "Proksi diaktifkan untuk koneksi ini",
-    "proxyDisabledTitle": "Koneksi langsung — melewati setiap proksi (termasuk proksi global) untuk koneksi ini",
-    "perKeyProxyOn": "Per-kunci",
-    "perKeyProxyOff": "Koneksi",
-    "perKeyProxyEnabledTitle": "Penetapan proksi per-kunci diaktifkan untuk penyedia ini",
-    "perKeyProxyDisabledTitle": "Penetapan proksi per-kunci dinonaktifkan untuk penyedia ini",
-    "autoPriority": "Auto: {priority}",
-    "proxy": "Proxy",
-    "retestAuthentication": "Retest authentication",
-    "retest": "Retest",
-    "disableConnection": "Disable connection",
-    "enableConnection": "Enable connection",
-    "reauthenticateConnection": "Re-authenticate this connection",
-    "proxyConfig": "Proxy config",
-    "aliasExistsAlert": "Alias \"{alias}\" already exists. Please use a different model or edit existing alias.",
-    "aliasInputPlaceholder": "alias name",
-    "clickToSetAlias": "Click to set alias",
-    "clickToEditAlias": "Alias: {alias} (click to edit)",
-    "openRouterAnyModelHint": "OpenRouter supports any model. Add models and create aliases for quick access.",
-    "modelIdFromOpenRouter": "Model ID (from OpenRouter)",
-    "openRouterModelPlaceholder": "anthropic/claude-3-opus",
-    "customModels": "Custom Models",
-    "customModelsHint": "Add model IDs not in the default list. These will be available for routing.",
-    "normalizeToolCallIdLabel": "Normalize tool call IDs to 9 characters (e.g. Mistral)",
-    "preserveDeveloperRoleLabel": "Keep OpenAI Responses developer role (do not map to system)",
-    "compatAdjustmentsTitle": "Compatibility",
-    "compatButtonLabel": "Compatibility",
-    "compatToolIdShort": "Tool ID 9",
-    "compatDeveloperShort": "Developer role",
-    "compatDoNotPreserveDeveloper": "Do not preserve developer role",
-    "compatBadgeNoPreserve": "No preserve",
-    "compatProtocolLabel": "Client request protocol",
-    "compatProtocolHint": "These options apply when OmniRoute detects this request shape (OpenAI Chat, Responses API, or Anthropic Messages).",
-    "compatProtocolOpenAI": "OpenAI Chat Completions",
-    "compatProtocolOpenAIResponses": "OpenAI Responses API",
-    "compatProtocolClaude": "Anthropic Messages",
-    "targetFormatLabel": "Format Target",
-    "targetFormatHint": "Ganti format wire upstream. Gunakan 'Anthropic Messages' untuk merutekan penyedia yang kompatibel dengan OpenAI (mis. opencode-go) melalui endpoint /v1/messages.",
-    "targetFormatAuto": "Default (otomatis)",
-    "targetFormatGemini": "Gemini",
-    "targetFormatAntigravity": "Antigravity",
-    "contextWindowOverrideLabel": "Override Jendela Konteks",
-    "contextWindowOverridePlaceholder": "mis. 131072",
-    "contextWindowOverrideHint": "Atur jendela konteks (token) sebenarnya dari model ini secara manual saat penyedia salah melaporkannya. Mengesampingkan nilai yang terdeteksi otomatis/katalog dan mencegah perutean kombo menghapus model.",
-    "contextWindowOverrideInvalid": "Override jendela konteks harus berupa bilangan bulat positif token",
-    "visionCapableLabel": "Mendukung visi",
-    "visionCapableHint": "Tandai model ini secara manual sebagai mendukung visi saat metadata penemuan penyedia tidak melaporkan modalitas input gambar (umum untuk backend yang di-host sendiri/lokal).",
-    "compatParamFiltersLabel": "Filter Parameter",
-    "compatBlockedParamsHint": "Parameter yang diblokir (dihapus dari permintaan)",
-    "compatAllowedParamsHint": "Parameter yang diizinkan (ditambahkan kembali setelah penolakan)",
-    "paramFiltersSectionTitle": "Filter Parameter",
-    "paramFiltersSectionHint": "Hapus atau tambahkan kembali parameter permintaan sebelum mengirim ke penyedia ini. Digunakan untuk menghindari kesalahan 400 dari penyedia yang menolak parameter tertentu (mis. NVIDIA NIM menolak <code>thinking</code>).",
-    "paramFiltersBlockedLabel": "Parameter yang diblokir",
-    "paramFiltersBlockedHint": "Parameter ini dihapus dari permintaan keluar (denylist).",
-    "paramFiltersAllowedLabel": "Parameter yang diizinkan",
-    "paramFiltersAllowedHint": "Parameter ini ditambahkan kembali setelah penghapusan denylist (hanya jika klien mengirimkannya).",
-    "paramFiltersAutoLearnLabel": "Pelajari otomatis dari galat 400",
-    "paramFiltersAutoLearnHint": "Saat diaktifkan, jika upstream mengembalikan 400 dengan \"Unsupported parameter: X\", parameter tersebut secara otomatis ditambahkan ke daftar blokir dan permintaan dicoba kembali.",
-    "paramFiltersSaving": "Menyimpan…",
-    "paramFiltersSaveChanges": "Simpan Perubahan",
-    "paramFiltersResetToDefault": "Setel Ulang ke Default",
-    "paramFiltersLoadError": "Gagal memuat konfigurasi filter parameter: {error}",
-    "paramFiltersSaveSuccess": "Konfigurasi filter parameter disimpan",
-    "paramFiltersSaveError": "Gagal menyimpan konfigurasi filter parameter: {error}",
-    "paramFiltersResetSuccess": "Konfigurasi filter parameter disetel ulang ke default",
-    "paramFiltersResetError": "Gagal menyetel ulang konfigurasi filter parameter: {error}",
-    "interceptionSectionTitle": "Intersepsi Alat Web",
-    "interceptionSectionHint": "Rute panggilan alat web_search / web_fetch bawaan penyedia ini melalui endpoint pencarian dan pengambilan milik OmniRoute alih-alih membiarkan penyedia menjalankannya secara bawaan. Nonaktif secara default — perilaku yang ada tidak berubah.",
-    "interceptSearchLabel": "Intersepsi web_search",
-    "interceptSearchHint": "Tulis ulang panggilan alat web_search bawaan ke /v1/search milik OmniRoute.",
-    "interceptFetchLabel": "Intersepsi web_fetch",
-    "interceptFetchHint": "Tulis ulang panggilan alat web_fetch bawaan ke /v1/web/fetch milik OmniRoute.",
-    "interceptionLoadError": "Gagal memuat pengaturan intersepsi: {error}",
-    "interceptionSaveError": "Gagal menyimpan pengaturan intersepsi: {error}",
-    "ccAliasSectionTitle": "Expose in Claude Code (claude/…)",
-    "ccAliasSectionHint": "Advertise this provider's models under claude/&lt;provider&gt;/&lt;model&gt; mirror ids so Claude Code's gateway model discovery can list them. Off by default — enabling this doubles catalog entries for all clients.",
-    "ccAliasProviderLevelLabel": "Provider default",
-    "ccAliasModelOverridesLabel": "Per-model overrides",
-    "ccAliasModelOverrideAriaLabel": "Override for {modelId}",
-    "ccAliasStateInherit": "Inherit",
-    "ccAliasStateOn": "On",
-    "ccAliasStateOff": "Off",
-    "ccAliasAddModelPlaceholder": "Model id (e.g. gpt-4o)",
-    "ccAliasAddModelButton": "Add override",
-    "ccAliasLoadError": "Failed to load discovery-alias settings: {error}",
-    "ccAliasSaveError": "Failed to save discovery-alias setting: {error}",
-    "compatUpstreamHeadersLabel": "Extra upstream headers",
-    "compatUpstreamHeadersHint": "High-privilege setting — same trust level as editing provider API credentials; only trusted admins should use it. Merged after OmniRoute adds auth from the provider API key. If a custom header uses the same name as an existing one (e.g. Authorization), your value fully replaces the auto-generated header (including the Bearer token) — the upstream only sees what you typed, not the key from settings. Misconfiguration can cause 401 or broken upstream auth. One row per header (e.g. extra Authentication for some gateways). Hover or focus the value to preview. Saves on blur, outside click, or closing this panel.",
-    "compatUpstreamHeaderName": "Header name",
-    "compatUpstreamHeaderValue": "Value",
-    "compatUpstreamAddRow": "Add header",
-    "compatUpstreamRemoveRow": "Remove row",
-    "compatBadgeUpstreamHeaders": "Headers",
-    "perModelQuotaLabel": "Per-Model Quota",
-    "perModelQuotaDescription": "When enabled, 429/404 errors only lock the specific model, not the entire connection. Use for providers with per-model rate limits (e.g., ModelScope).",
-    "importFreeModelsOnlyLabel": "Impor hanya model gratis",
-    "importFreeModelsOnlyHint": "Saat diaktifkan, hanya model gratis dari penyedia ini yang diimpor. Model berbayar dilewati.",
-    "perModelQuotaToggle": "Per-Model Quota Toggle",
-    "modelId": "Model ID",
-    "customModelPlaceholder": "e.g. gpt-4.5-turbo",
-    "loading": "Loading...",
-    "removeCustomModel": "Remove custom model",
-    "noCustomModels": "No custom models added yet.",
-    "allSuggestedAliasesExist": "All suggested aliases already exist. Please choose a different model or remove conflicting aliases.",
-    "failedSaveCustomModel": "Failed to save custom model",
-    "modelAddedSuccess": "Model {modelId} added successfully",
-    "failedAddModelTryAgain": "Failed to add model. Please try again.",
-    "failedSaveImportedModel": "Failed to save imported model to custom database",
-    "failedImportModelsTryAgain": "Failed to import models. Please try again.",
-    "failedRemoveModelFromDatabase": "Failed to remove model from database",
-    "modelRemovedSuccess": "Model removed successfully",
-    "failedDeleteModelTryAgain": "Failed to delete model. Please try again.",
-    "compatibleModelsDescription": "Add {type}-compatible models manually or import them from the /models endpoint.",
-    "anthropicCompatibleModelPlaceholder": "claude-3-opus-20240229",
-    "openaiCompatibleModelPlaceholder": "gpt-4o",
-    "apiKeyValidationFailed": "API key validation failed. Please check your key and try again.",
-    "addProviderApiKeyTitle": "Add {provider} API Key",
-    "checking": "Checking...",
-    "check": "Check",
-    "valid": "Valid",
-    "invalid": "Invalid",
-    "creating": "Creating...",
-    "validationChecksAnthropicCompatible": "Validation checks {provider} by verifying the API key.",
-    "validationChecksOpenAiCompatible": "Validation checks {provider} via /models on your base URL.",
-    "priorityLabel": "Priority",
-    "saving": "Saving...",
-    "save": "Save",
-    "editConnection": "Edit Connection",
-    "accountName": "Account name",
-    "email": "Email",
-    "healthCheckMinutes": "Health Check (min)",
-    "healthCheckHint": "Proactive token refresh interval. 0 = disabled.",
-    "deselectAllModels": "Deselect all",
-    "modelsActiveCount": "{active}/{total} active",
-    "noModelsMatch": "No models match \"{filter}\"",
-    "groupLabel": "Environment",
-    "groupPlaceholder": "e.g. eKaizen, Personal",
-    "failedTestConnection": "Failed to test connection",
-    "failed": "Failed",
-    "leaveBlankKeepCurrentApiKey": "Leave blank to keep the current API key.",
-    "editCompatibleTitle": "Edit {type} Compatible",
-    "compatibleBaseUrlHint": "Root URL of your {type}-compatible API. Use Advanced Settings for custom endpoint paths.",
-    "apiKeyForCheck": "API Key (for Check)",
-    "testModelIdLabel": "ID Model (opsional)",
-    "testModelIdPlaceholder": "mis. my-model-id",
-    "testModelIdHint": "Jika penyedia tidak memiliki endpoint /models, masukkan ID model untuk memvalidasi melalui /chat/completions sebagai gantinya.",
-    "compatibleProdPlaceholder": "{type} Compatible (Prod)",
-    "tokenRefreshed": "Token refreshed successfully",
-    "tokenRefreshFailed": "Token refresh failed",
-    "cursorSessionUnchanged": "Sesi sudah saat ini",
-    "applyCodexAuthLocal": "Apply auth",
-    "exportCodexAuthFile": "Export auth",
-    "applyClaudeAuthLocal": "Terapkan autentikasi",
-    "exportClaudeAuthFile": "Ekspor autentikasi",
-    "importClaudeAuth": "Impor autentikasi",
-    "claudeApplyModalTitle": "Berlaku pada Kode Claude Lokal",
-    "claudeApplyTargetLabel": "Jalur sasaran",
-    "claudeApplyBackupLabel": "Cadangan",
-    "claudeApplyMcpHint": "Status MCP OAuth yang ada akan dipertahankan.",
-    "claudeApplyWarning": "Ini akan menggantikan bagian claudeAiOauth yang ada. Melanjutkan?",
-    "claudeApplyConfirmCheckbox": "Saya mengonfirmasi bahwa saya ingin mengganti bagian claudeAiOauth yang ada",
-    "claudeApply": "Terapkan",
-    "claudeAuthAppliedLocal": "Autentikasi Claude diterapkan secara lokal",
-    "claudeAuthApplyFailed": "Gagal menerapkan autentikasi Claude secara lokal",
-    "claudeAuthExported": "File autentikasi Claude diekspor",
-    "claudeAuthExportFailed": "Gagal mengekspor file autentikasi Claude",
-    "claudeImportModalTitle": "Impor Claude Auth",
-    "claudeImportTabSingle": "Lajang",
-    "claudeImportTabBulk": "Massal",
-    "claudeImportTabUpload": "Unggah berkas",
-    "claudeImportTabPaste": "Tempel JSON",
-    "claudeImportFileLabel": "Pilih .credentials.json",
-    "claudeImportPasteLabel": "Tempelkan konten JSON",
-    "claudeImportEmailLabel": "Email akun",
-    "claudeImportNameLabel": "Nama koneksi (opsional)",
-    "claudeImportOverwriteLabel": "Ganti koneksi yang ada jika akun sudah ada",
-    "claudeImportSubmit": "Impor",
-    "claudeImportSuccess": "Koneksi Claude berhasil diimpor",
-    "claudeImportInvalidJson": "Tidak dapat menguraikan file sebagai JSON",
-    "claudeImportInvalidShape": "File tersebut bukan .credentials.json yang valid",
-    "claudeImportDuplicate": "Akun sudah ada — aktifkan \"Ganti yang ada\" untuk menimpa",
-    "claudeImportIdentityUnverified": "Bootstrap tidak dapat memverifikasi akun. Aktifkan \"Ganti yang ada\" atau berikan email.",
-    "claudeImportFailed": "Gagal mengimpor autentikasi Claude",
-    "claudeImportBulkModeUpload": "Unggah file",
-    "claudeImportBulkModePaste": "Tempel larik JSON",
-    "claudeImportBulkModeZip": "Unggah ZIP",
-    "claudeImportBulkUploadHint": "Letakkan atau ambil hingga 50 file .credentials.json (masing-masing 256KB, total 10MB).",
-    "claudeImportBulkPasteHint": "Tempelkan array objek: [{ json, name?, email? }...]",
-    "claudeImportBulkZipHint": "ZIP berisi entri .json. Maks 50 entri, 10MB dibongkar.",
-    "claudeImportBulkSubmit": "Impor semua",
-    "claudeImportBulkSuccess": "Koneksi {count} Claude yang diimpor",
-    "claudeImportBulkFailed": "Beberapa entri gagal diimpor",
-    "claudeImportBulkZipExtracting": "Mengekstrak ZIP…",
-    "claudeImportBulkZipError": "Gagal mengekstrak ZIP",
-    "geminiAuthAppliedLocal": "Autentikasi Gemini diterapkan secara lokal",
-    "geminiAuthApplyFailed": "Gagal menerapkan autentikasi Gemini secara lokal",
-    "geminiAuthExported": "File autentikasi Gemini diekspor",
-    "geminiAuthExportFailed": "Gagal mengekspor file autentikasi Gemini",
-    "geminiImportModalTitle": "Impor Otentikasi Gemini",
-    "geminiImportTabSingle": "Lajang",
-    "geminiImportTabBulk": "Massal",
-    "geminiImportTabUpload": "Unggah berkas",
-    "geminiImportTabPaste": "Tempel JSON",
-    "geminiImportFileLabel": "Pilih oauth_creds.json",
-    "geminiImportPasteLabel": "Tempelkan konten JSON",
-    "geminiImportEmailLabel": "Email akun",
-    "geminiImportNameLabel": "Nama koneksi (opsional)",
-    "geminiImportOverwriteLabel": "Ganti koneksi yang ada jika akun sudah ada",
-    "geminiImportSubmit": "Impor",
-    "geminiImportSuccess": "Koneksi Gemini berhasil diimpor",
-    "geminiImportInvalidJson": "Tidak dapat menguraikan file sebagai JSON",
-    "geminiImportInvalidShape": "File tersebut bukan oauth_creds.json yang valid",
-    "geminiImportDuplicate": "Akun sudah ada — aktifkan \"Ganti yang ada\" untuk menimpa",
-    "geminiImportIdentityUnverified": "Tidak dapat memverifikasi identitas dari id_token. Aktifkan \"Ganti yang ada\" atau berikan email.",
-    "geminiImportFailed": "Gagal mengimpor autentikasi Gemini",
-    "geminiImportBulkModeUpload": "Unggah file",
-    "geminiImportBulkModePaste": "Tempel larik JSON",
-    "geminiImportBulkModeZip": "Unggah ZIP",
-    "geminiImportBulkUploadHint": "Letakkan atau ambil hingga 50 file oauth_creds.json (masing-masing 256KB, total 10MB).",
-    "geminiImportBulkPasteHint": "Tempelkan array objek: [{ json, name?, email? }...]",
-    "geminiImportBulkZipHint": "ZIP berisi entri oauth_creds.json. Maks 50 entri, 10MB dibongkar.",
-    "geminiImportBulkSubmit": "Impor semua",
-    "geminiImportBulkSuccess": "Koneksi {count} Gemini yang diimpor",
-    "geminiImportBulkFailed": "Beberapa entri gagal diimpor",
-    "geminiImportBulkZipExtracting": "Mengekstrak ZIP…",
-    "geminiImportBulkZipError": "Gagal mengekstrak ZIP",
-    "codexAuthAppliedLocal": "Codex auth.json applied locally",
-    "codexAuthApplyFailed": "Failed to apply Codex auth.json locally",
-    "codexAuthExported": "Codex auth.json exported",
-    "codexAuthExportFailed": "Failed to export Codex auth.json",
-    "codexCliGuideButton": "Panduan CLI Codex",
-    "codexCliGuideTitle": "Panduan CLI Codex",
-    "codexCliGuideLoading": "Memuat panduan...",
-    "codexCliGuideLoadFailed": "Tidak dapat memuat panduan.",
-    "codexExternalLinkButton": "Tautan Codex eksternal",
-    "codexExternalLinkModalTitle": "Tautan Codex eksternal",
-    "codexExternalLinkModalDescription": "Bagikan tautan sekali pakai ini kepada orang yang akan mengautentikasi akun Codex. Mereka membukanya di peramban mereka sendiri, menyelesaikan login OpenAI, dan koneksi akan terdaftar di sini. Tautan kedaluwarsa dalam 15 menit.",
-    "codexExternalLinkGenerating": "Membuat tautan...",
-    "codexExternalLinkWaiting": "Menunggu autentikasi peramban. Jendela ini diperbarui secara otomatis.",
-    "codexExternalLinkCreateFailed": "Gagal membuat tautan.",
-    "codexExternalLinkNetworkError": "Tidak dapat menghubungi server.",
-    "codexExternalLinkConnected": "Akun Codex terhubung melalui tautan eksternal.",
-    "codexExternalLinkExpired": "Tautan kedaluwarsa sebelum selesai.",
-    "importCodexAuth": "Impor autentikasi",
-    "codexImportModalTitle": "Impor Codex Auth",
-    "codexImportTabSingle": "Lajang",
-    "codexImportTabBulk": "Massal",
-    "codexImportTabUpload": "Unggah berkas",
-    "codexImportTabPaste": "Tempel JSON",
-    "codexImportFileLabel": "Pilih auth.json",
-    "codexImportFileHint": "Pilih file auth.json yang diekspor dari Codex atau dari OmniRoute.",
-    "codexImportPasteLabel": "Tempelkan konten JSON",
-    "codexImportEmailLabel": "Email akun",
-    "codexImportEmailHint": "Terdeteksi secara otomatis dari file; edit jika diperlukan.",
-    "codexImportNameLabel": "Nama koneksi (opsional)",
-    "codexImportOverwriteLabel": "Ganti koneksi yang ada jika akun sudah ada",
-    "codexImportSubmit": "Impor",
-    "codexImportSuccess": "Koneksi codex berhasil diimpor",
-    "codexImportInvalidJson": "Tidak dapat menguraikan file sebagai JSON",
-    "codexImportInvalidShape": "File tersebut bukan Codex auth.json yang valid",
-    "codexImportDuplicate": "Akun sudah ada — aktifkan \"Ganti yang ada\" untuk menimpa",
-    "codexImportFailed": "Gagal mengimpor autentikasi Codex",
-    "codexImportDetectedEmail": "Terdeteksi: {email}",
-    "codexImportNoEmailDetected": "Tidak ada email yang terdeteksi dalam file",
-    "codexImportBulkModeUpload": "Unggah file",
-    "codexImportBulkModePaste": "Tempel daftar",
-    "codexImportBulkModeZip": "Arsip ZIP",
-    "codexImportBulkUploadHint": "Pilih beberapa file .json atau seret dan lepas",
-    "codexImportBulkPasteHint": "Array JSON [ {...}, {...} ] atau beberapa JSON dipisahkan oleh --- pada barisnya sendiri",
-    "codexImportBulkZipHint": "Unggah .zip yang berisi file auth.json (maks 50 file, 10 MB)",
-    "codexImportBulkSubmit": "Impor akun {count}",
-    "codexImportBulkLimit": "Maksimum 50 file per impor",
-    "codexImportBulkSuccess": "{count} diimpor",
-    "codexImportBulkFailed": "{count} gagal",
-    "codexImportBulkZipExtracting": "Mengekstrak ZIP…",
-    "codexImportBulkZipError": "Gagal mengekstrak ZIP",
-    "advancedSettings": "Advanced Settings",
-    "chatPathLabel": "Chat Endpoint Path",
-    "chatPathPlaceholder": "/chat/completions",
-    "chatPathHint": "Custom chat path for providers with non-standard APIs (e.g. /v4/chat/completions)",
-    "modelsPathLabel": "Models Endpoint Path",
-    "modelsPathPlaceholder": "/models",
-    "modelsPathHint": "Custom models path for validation (e.g. /v4/models)",
-    "clientIdentityLabel": "Identitas Klien",
-    "clientIdentityHint": "Opsional. Menambahkan header sidik jari klien (mis. User-Agent) yang cocok dengan CLI yang dikenal untuk gateway kompatibel yang membutuhkannya.",
-    "statusDeactivated": "Deactivated (Manual)",
-    "statusBanned": "Banned / Sandbox Violation",
-    "statusCreditsExhausted": "Insufficient Balance / Quota Exhausted",
-    "showEmails": "Show all emails",
-    "hideEmails": "Hide all emails",
-    "a": "A",
-    "accountConcurrencyCapHint": "Account Concurrency Cap Hint",
-    "accountConcurrencyCapLabel": "Account Concurrency Cap Label",
-    "accountIdHint": "Account Id Hint",
-    "accountIdLabel": "Account Id Label",
-    "accountIdPlaceholder": "Account Id Placeholder",
-    "addAnotherApiKey": "Add another API key or paste multiple keys",
-    "addCcCompatible": "Add Cc Compatible",
-    "aggregatorsGateways": "Aggregators Gateways",
-    "enterpriseCloud": "Perusahaan & Awan",
-    "apiFormatLabel": "Api Format Label",
-    "apiKeyOptionalHint": "Api Key Optional Hint",
-    "apiKeyOptionalLabel": "Api Key Optional Label",
-    "apiRegionChina": "Api Region China",
-    "apiRegionHint": "Api Region Hint",
-    "apiRegionInternational": "Api Region International",
-    "apiRegionLabel": "Api Region Label",
-    "apikey": "Apikey",
-    "audio": "Audio",
-    "audioProvidersHeading": "Audio Providers Heading",
-    "cloudAgentProviders": "Penyedia Agen Cloud",
-    "audioShortLabel": "Audio Short Label",
-    "azureOpenAiBaseUrlHint": "Azure Open Ai Base Url Hint",
-    "bailianBaseUrlHint": "Bailian Base Url Hint",
-    "claudeWebCookieHint": "Open claude.ai → DevTools → Application → Cookies → claude.ai, copy the 'sessionKey' value. Also need cf_clearance, __cf_bm, _cfuvid for Cloudflare.",
-    "claudeWebCookiePlaceholder": "sessionKey=sk-ant-...",
-    "blackboxWebCookieHint": "Blackbox Web Cookie Hint",
-    "blackboxWebCookiePlaceholder": "Blackbox Web Cookie Placeholder",
-    "t3ChatWebCookieHint": "Buka t3.chat → DevTools → Aplikasi → Penyimpanan Lokal → https://t3.chat, salin 'convex-session-id'. Lalu buka DevTools → Jaringan, salin header Cookie lengkap dari permintaan obrolan apa pun. Tempelkan kedua nilai pada kolom di bawah.",
-    "t3ChatWebCookiePlaceholder": "id-sesi-cembung=abc123...",
-    "grokWebCookieHint": "Grok Web Cookie Hint",
-    "blockClaudeExtraUsageDescription": "Saat diaktifkan, OmniRoute menandai koneksi Claude ini tidak tersedia segera setelah API penggunaan melaporkan penggunaan ekstra yang antre, sehingga fallback beralih ke koneksi lain alih-alih melanjutkan dengan penagihan ekstra bayar sesuai penggunaan.",
-    "blockClaudeExtraUsageLabel": "Blokir penggunaan Claude yang berlebihan",
-    "disableCoolingDescription": "Lewati cooldown sementara agar koneksi ini tetap memenuhi syarat bahkan setelah kesalahan yang dapat dipulihkan (status terminal seperti diblokir/kedaluwarsa tetap berlaku).",
-    "disableCoolingLabel": "Nonaktifkan cooldown untuk koneksi ini",
-    "bulkPasteAdded": "{count, plural, one {1 key added} other {# keys added}}",
-    "bulkPasteDuplicatesIgnored": "{count, plural, one {1 duplicate skipped} other {# duplicates skipped}}",
-    "bulkPasteHint": "Paste one API key per line. Empty lines are ignored and duplicate keys are skipped.",
-    "ccCompatibleBaseUrlHint": "Cc Compatible Base Url Hint",
-    "ccCompatibleBaseUrlPlaceholder": "Cc Compatible Base Url Placeholder",
-    "ccCompatibleChatPathHint": "Cc Compatible Chat Path Hint",
-    "ccCompatibleContext1mDescription": "Cc Compatible Context1M Description",
-    "ccCompatibleContext1mLabel": "Cc Compatible Context1M Label",
-    "ccCompatibleRedactThinkingDescription": "Adds the redact-thinking beta header for CC Compatible upstreams that require hidden Claude thinking streams.",
-    "ccCompatibleRedactThinkingLabel": "Enable redact-thinking beta",
-    "ccCompatibleSummarizeThinkingDescription": "Adds `display: \"summarized\"` to CC Compatible thinking requests so supported Claude models stream visible thinking deltas.",
-    "ccCompatibleSummarizeThinkingLabel": "Enable summarized thinking display",
-    "ccCompatibleDetailsTitle": "Cc Compatible Details Title",
-    "ccCompatibleLabel": "Cc Compatible Label",
-    "ccCompatibleModelsDescription": "Cc Compatible Models Description",
-    "ccCompatibleNameHint": "Cc Compatible Name Hint",
-    "ccCompatibleNamePlaceholder": "Cc Compatible Name Placeholder",
-    "ccCompatiblePrefixHint": "Cc Compatible Prefix Hint",
-    "ccCompatiblePrefixPlaceholder": "Cc Compatible Prefix Placeholder",
-    "ccCompatibleValidationHint": "Cc Compatible Validation Hint",
-    "claudeExtraUsageShort": "Claude Extra Usage Short",
-    "claudeExtraUsageToggleTitle": "Claude Extra Usage Toggle Title",
-    "codex5hToggleTitle": "Codex5H Toggle Title",
-    "codexFastServiceTierDescription": "Use the priority service tier for Codex requests when available.",
-    "codexFastServiceTierLabel": "Codex fast service tier",
-    "codexWeeklyToggleTitle": "Codex Weekly Toggle Title",
-    "compatUpstreamHeaderNamePlaceholder": "Compat Upstream Header Name Placeholder",
-    "compatUpstreamHeaderValuePlaceholder": "Compat Upstream Header Value Placeholder",
-    "compatible": "Compatible",
-    "configuredCount": "Configured Count",
-    "consoleApiKeyOracleHint": "Console Api Key Oracle Hint",
-    "consoleApiKeyOracleLabel": "Console Api Key Oracle Label",
-    "consoleApiKeyOraclePlaceholder": "Console Api Key Oracle Placeholder",
-    "newApiUserIdLabel": "New-API User ID",
-    "newApiUserIdPlaceholder": "e.g. 12345",
-    "newApiUserIdHint": "AgentRouter New-Api-User header value, used together with the console API key to fetch quota balance.",
-    "newApiAggregatorToggleLabel": "Gerbang Agregator",
-    "newApiAggregatorToggleHint": "Aktifkan deteksi saldo untuk node agregator New-API / One-API / Sub2API. Dasbor akan menampilkan lencana saldo dan pengalihan kuota-preflight akan melewati akun yang habis.",
-    "newApiAggregatorConsoleApiKeyHint": "Token Akses Sistem untuk endpoint /api/user/self agregator. Bukan kunci API routing.",
-    "newApiAggregatorUserIdHint": "Nilai header New-Api-User digunakan untuk mengambil saldo kuota pengguna agregator.",
-    "newApiAggregatorQuotaPerUnitLabel": "Kuota Per Unit",
-    "newApiAggregatorQuotaPerUnitHint": "Unit Kredit New-API per $1 (default: 500000). Ganti jika agregator Anda menggunakan tarif yang berbeda.",
-    "featureFlagNewApiAggregatorBalanceDescription": "Aktifkan deteksi saldo untuk node yang kompatibel dengan New-API / One-API / Sub2API aggregator",
-    "cpaModeDisabledTitle": "Cpa Mode Disabled Title",
-    "cpaModeEnabledTitle": "Cpa Mode Enabled Title",
-    "customUserAgentHint": "Custom User Agent Hint",
-    "customUserAgentLabel": "Custom User Agent Label",
-    "databricksBaseUrlHint": "Databricks Base Url Hint",
-    "defaultThinkingStrengthHint": "Used when a request does not specify reasoning effort.",
-    "defaultThinkingStrengthLabel": "Default thinking strength",
-    "deleteAllExtraApiKeys": "Delete all",
-    "excludedModelsHint": "Excluded Models Hint",
-    "excludedModelsLabel": "Excluded Models Label",
-    "excludedModelsPlaceholder": "Excluded Models Placeholder",
-    "expirationBannerExpired": "Expiration Banner Expired",
-    "expirationBannerExpiredDesc": "Expiration Banner Expired Desc",
-    "expirationBannerExpiringSoon": "Expiration Banner Expiring Soon",
-    "expirationBannerExpiringSoonDesc": "Expiration Banner Expiring Soon Desc",
-    "extraApiKeyMasked": "Key {index}: {prefix}••••{suffix}",
-    "extraApiKeysHint": "Extra Api Keys Hint",
-    "extraApiKeysLabel": "Extra Api Keys Label",
-    "apiKeyHealthLabel": "API Key Health",
-    "apiKeyStatusActive": "Active",
-    "apiKeyStatusWarning": "Warning ({count} failures)",
-    "apiKeyStatusInvalid": "Invalid",
-    "primaryKey": "Primary Key",
-    "apiKeyInvalidAlert": "{count} API key(s) marked as invalid due to authentication failures in connections: {connections}. They will be skipped in rotation. Click to review.",
-    "apiKeyInvalidAlertTitle": "API Key Health Alert",
-    "apiKeyWarningAlert": "{count} API key(s) in warning state due to elevated failure rate in connections: {connections}. Review to prevent rotation issues.",
-    "apiKeyWarningAlertTitle": "API Key Warning",
-    "googlePseInfo": "Google Pse Info",
-    "antigravityProjectIdHint": "Penggantian opsional untuk permintaan Antigravity Cloud Code. Biarkan kosong untuk menggunakan proyek yang ditemukan selama Google OAuth.",
-    "antigravityClientProfileLabel": "Profil klien",
-    "antigravityClientProfileHint": "Pilih identitas klien Antigravity mana yang ditampilkan OmniRoute ke API.",
-    "antigravityClientProfileIde": "IDE",
-    "antigravityClientProfileCli": "Harness / CLI",
-    "codexFastTierActiveChip": "Tingkat Codex Fast aktif",
-    "tierFast": "Cepat",
-    "antigravityProjectIdLabel": "ID Proyek Google Cloud",
-    "antigravityProjectIdPlaceholder": "id-proyek-gcp-saya",
-    "grokWebCookiePlaceholder": "Grok Web Cookie Placeholder",
-    "herokuBaseUrlHint": "Heroku Base Url Hint",
-    "hideEmail": "Hide Email",
-    "imageProviders": "Image Providers",
-    "videoProviders": "Pembuatan Video",
-    "embeddingRerankProviders": "Penyematan & Pemeringkatan Ulang",
-    "imagesShortLabel": "Images Short Label",
-    "llmProviders": "Llm Providers",
-    "localProviderApiKeyOptionalHint": "Local Provider Api Key Optional Hint",
-    "localProviderBaseUrlHint": "Local Provider Base Url Hint",
-    "localProviders": "Local Providers",
-    "maxConcurrentWholeNumberError": "Max Concurrent Whole Number Error",
-    "m365TierLabel": "Tingkat Copilot",
-    "m365TierHint": "Pilih permukaan Microsoft 365 Copilot mana yang digunakan koneksi ini. Individu adalah BizChat konsumen default; Pendidikan dan Enterprise (kerja) memilih masuk ke permukaan tenant mereka.",
-    "m365TierIndividualOption": "Individu (default)",
-    "m365TierEduOption": "Pendidikan",
-    "m365TierEnterpriseOption": "Enterprise / Kerja",
-    "tierOverrideLabel": "Penggantian tingkat",
-    "tierOverrideAuto": "Otomatis (perutean yang menentukan)",
-    "tierOverrideFree": "Gratis",
-    "tierOverrideCheap": "Murah",
-    "tierOverridePremium": "Premium",
-    "tierOverrideHelpText": "Sematkan penyedia ini ke tingkat perutean alih-alih membiarkan OmniRoute menyimpulkannya dari harga model.",
-    "museSparkWebCookieHint": "Muse Spark Web Cookie Hint",
-    "museSparkWebCookiePlaceholder": "Muse Spark Web Cookie Placeholder",
-    "oauth": "Oauth",
-    "openCliTools": "Open Cli Tools",
-    "openSettings": "Open Settings",
-    "openaiResponsesStoreDescription": "Allow compatible Responses API requests to preserve stored response state.",
-    "openaiResponsesStoreLabel": "OpenAI Responses store",
-    "perplexitySearchSharedKeyInfo": "Perplexity Search Shared Key Info",
-    "perplexityWebCookieHint": "Perplexity Web Cookie Hint",
-    "perplexityWebCookiePlaceholder": "Perplexity Web Cookie Placeholder",
-    "personalAccessTokenLabel": "Personal Access Token Label",
-    "qoderPatHint": "Qoder Pat Hint",
-    "qoderPatPlaceholder": "Qoder Pat Placeholder",
-    "rateLimitOverridesSection": "Penggantian Batas Laju",
-    "rateLimitOverridesMaxConcurrentHint": "Penggantian permintaan bersamaan maks untuk koneksi ini. Menggantikan batas tingkat akun.",
-    "rateLimitOverridesMaxConcurrentLabel": "Maks Bersamaan (Batas Laju)",
-    "rateLimitOverridesMaxWaitMsHint": "__MISSING__:Maximum time (ms) a request may wait for a rate-limit slot before failing. Overrides the global Resilience setting for this connection only.",
-    "rateLimitOverridesMaxWaitMsLabel": "__MISSING__:Max Queue Wait (ms)",
-    "rateLimitOverridesMinTimeHint": "Waktu minimum (ms) antar permintaan. Menggantikan penundaan pembatas laju default.",
-    "rateLimitOverridesMinTimeLabel": "Interval Min (ms)",
-    "rateLimitOverridesRpdHint": "Permintaan maksimum per hari untuk koneksi ini. Mengganti default penyedia.",
-    "rateLimitOverridesRpdLabel": "RPD (Permintaan/hari)",
-    "rateLimitOverridesRpmHint": "Permintaan maks per menit untuk koneksi ini. Menggantikan default penyedia.",
-    "rateLimitOverridesRpmLabel": "RPM (Permintaan/mnt)",
-    "rateLimitOverridesTpdHint": "Token maks per hari untuk koneksi ini. Menggantikan default penyedia.",
-    "rateLimitOverridesTpdLabel": "TPD (Token/hari)",
-    "rateLimitOverridesTpmHint": "Token maks per menit untuk koneksi ini. Menggantikan default penyedia.",
-    "rateLimitOverridesTpmLabel": "TPM (Token/mnt)",
-    "refreshOauthTokenTitle": "Refresh Oauth Token Title",
-    "regionHint": "Region Hint",
-    "regionLabel": "Region Label",
-    "removeThisKey": "Remove This Key",
-    "routingTagsHint": "Routing Tags Hint",
-    "routingTagsLabel": "Routing Tags Label",
-    "routingTagsPlaceholder": "Routing Tags Placeholder",
-    "search": "Search",
-    "searchEngineIdHint": "Search Engine Id Hint",
-    "searchEngineIdLabel": "Search Engine Id Label",
-    "searchEngineIdRequired": "Search Engine Id Required",
-    "searchProvider": "Search Provider",
-    "searchProviderDesc": "Search Provider Desc",
-    "searchProviders": "Search Providers",
-    "searchByModel": "Cari berdasarkan model…",
-    "searchProvidersHeading": "Search Providers Heading",
-    "searxngBaseUrlHint": "Searxng Base Url Hint",
-    "searxngInfo": "Searxng Info",
-    "sessionCookieLabel": "Session Cookie Label",
-    "showEmail": "Show Email",
-    "snowflakeBaseUrlHint": "Snowflake Base Url Hint",
-    "supportedEndpointAudio": "Supported Endpoint Audio",
-    "supportedEndpointChat": "Supported Endpoint Chat",
-    "supportedEndpointEmbeddings": "Supported Endpoint Embeddings",
-    "supportedEndpointImages": "Supported Endpoint Images",
-    "supportedEndpointsLabel": "Supported Endpoints Label",
-    "tagGroupHint": "Tag Group Hint",
-    "tagGroupLabel": "Tag Group Label",
-    "tagGroupPlaceholder": "Tag Group Placeholder",
-    "testModel": "Test Model",
-    "testingModel": "Testing Model",
-    "modelTestQuotaTooltip": "Kuota habis — akan direset besok atau perlu pengisian ulang",
-    "toggleOffShort": "Toggle Off Short",
-    "toggleOnShort": "Toggle On Short",
-    "tokenExpiredBadge": "Token Expired Badge",
-    "tokenExpiredTitle": "Token Expired Title",
-    "tokenExpiresSoonTitle": "Token Expires Soon Title",
-    "tokenShort": "Token Short",
-    "totalKeysRotating": "{count, plural, one {1 key rotating} other {# keys rotating}}",
-    "unhideModel": "Unhide Model",
-    "upstreamProxyProviders": "Upstream Proxy Providers",
-    "validationModelIdHint": "Model yang digunakan untuk memverifikasi kunci API. Biarkan kosong untuk menggunakan model pertama yang tersedia dari penyedia.",
-    "validationModelIdLabel": "Model validasi",
-    "validationModelIdPlaceholder": "mis. meta-llama/llama-3.1-8b-instruct",
-    "vertexServiceAccountPlaceholder": "Paste your Service Account JSON ({\"type\":\"service_account\",\"project_id\":\"…\",\"client_email\":\"…\",\"private_key\":\"…\"}) or an OAuth access_token",
-    "webCookieProviders": "Web Cookie Providers",
-    "weeklyShort": "Weekly Short",
-    "xiaomiMimoBaseUrlHint": "Xiaomi Mimo Base Url Hint",
-    "globalCodexServiceMode": "Mode layanan Codex global",
-    "connect": "Hubungkan",
-    "manualApiKey": "Kunci API manual",
-    "addPat": "Tambah PAT",
-    "experimentalOauth": "OAuth eksperimental",
-    "importAuth": "Impor autentikasi",
-    "importGrokAuth": "Impor autentikasi Grok Build",
-    "zedImportTitle": "Impor dari Zed Keychain",
-    "zedImportDescription": "Temukan kredensial penyedia AI (OpenAI, Anthropic, Google, Mistral, xAI) yang disimpan oleh Zed IDE di keychain OS dan impor sebagai koneksi. Zed IDE harus terpasang di mesin ini.",
-    "zedImportButton": "Impor dari Zed",
-    "zedImportFailed": "Impor Zed gagal",
-    "zedImportHint": "Zed Import Hint",
-    "zedImportNetworkError": "Zed Import Network Error",
-    "zedImportNone": "Zed Import None",
-    "zedImportSuccess": "Diimpor {credentials} kredensial dari Zed untuk {providers} penyedia",
-    "zedImporting": "Mengimpor…",
-    "zedNoCredentials": "Tidak ada kredensial Zed yang ditemukan di keychain",
-    "zedUnsupportedCredentials": "Ditemukan {count} kredensial keychain, tetapi tidak ada yang cocok dengan penyedia yang didukung",
-    "zedManualTitle": "Impor Token Manual",
-    "zedManualDescription": "Gunakan ini saat OmniRoute berjalan di Docker atau keychain tidak tersedia. Tempel kunci API yang disimpan Zed di bawah <path>~/.config/zed/settings.json</path>, atau salin dari panel pengaturan Zed AI.",
-    "zedPasteApiKey": "Tempel kunci API…",
-    "zedSaving": "Menyimpan…",
-    "zedImportAction": "Impor",
-    "cursorAgentNudgeTitle": "Aktifkan pembaruan sesi Kursor otomatis",
-    "cursorAgentNudgeBody": "Instal cursor-agent untuk pembaruan sesi otomatis — tanpa itu, koneksi Cursor memerlukan penyambungan manual secara berkala kira-kira setiap 24 jam.",
-    "cursorAgentNudgeDismiss": "Abaikan",
-    "zedManualImportFailed": "Impor manual gagal",
-    "zedManualImportSuccess": "Token {provider} diimpor dari Zed",
-    "grokImportTitle": "Impor Autentikasi Grok Build",
-    "grokImportDescription": "Impor berkas Grok Build <authPath>~/.grok/auth.json</authPath> Anda. Anda bisa mendapatkannya dengan menjalankan <command>grok login</command> di terminal Anda.",
-    "grokUploadFile": "Unggah berkas",
-    "grokPasteJson": "Tempel JSON",
-    "grokInvalidAuth": "Ini bukan berkas auth.json Grok Build yang valid. Diharapkan objek dengan kunci yang berisi JWT.",
-    "grokParseFailed": "Tidak dapat mengurai JSON",
-    "grokImportFailed": "Gagal mengimpor autentikasi Grok Build",
-    "grokImportSuccess": "Koneksi Grok Build berhasil diimpor",
-    "grokValidToken": "Token Grok Build yang valid terdeteksi",
-    "grokRefreshIncluded": "Refresh token disertakan — pembaruan token otomatis diaktifkan",
-    "grokRefreshMissing": "Tidak ada refresh token yang ditemukan — impor ulang setelah token kedaluwarsa",
-    "grokConnectionName": "Nama koneksi (opsional)",
-    "grokSaving": "Menyimpan…",
-    "grokSaveConnection": "Simpan Koneksi",
-    "freeTierProviders": "Penyedia Tingkat Gratis",
-    "freeTierLabel": "Tersedia tingkat gratis",
-    "freeTierProvidersDesc": "Penyedia dengan tingkatan gratis — beberapa memerlukan pendaftaran kunci API, yang lain tidak memerlukan kredensial sama sekali.",
-    "providerSummaryAll": "Jumlah",
-    "ideProviders": "Penyedia IDE",
-    "ideProvidersDesc": "Editor dengan langganan AI bawaan. Gunakan halaman penyedia untuk mengimpor kredensial langsung dari gantungan kunci IDE.",
-    "noIdeProviders": "Tidak ada penyedia IDE yang cocok dengan filter saat ini.",
-    "providerDetailFastTierTooltip": "Terapkan tingkat Codex Fast ke semua koneksi Codex secara default",
-    "providerDetailFastDefaultLabel": "Standar cepat",
-    "providerDetailBrowserManualConnect": "Koneksi browser/manual",
-    "providerDetailAuthUrl": "URL Otentikasi",
-    "providerDetailCallbackUrl": "URL panggilan balik",
-    "providerDetailValidClaudeCredentialsFile": "File kredensial Claude yang valid",
-    "providerDetailPathAutoDetectedAllOs": "Jalur terdeteksi secara otomatis per OS (Linux/Mac/Windows).",
-    "providerDetailMyClaudeAccountPlaceholder": "Akun Claude-ku",
-    "providerDetailPathAutoDetected": "Jalur terdeteksi secara otomatis per OS (Linux/Mac).",
-    "compatBlockedParamsPlaceholder": "thinking, … (dipisahkan koma)",
-    "compatAllowedParamsPlaceholder": "reasoning, … (dipisahkan koma)",
-    "compatSaving": "menyimpan…",
-    "paramFiltersBlockedPlaceholder": "thinking, reasoning_budget, … (dipisahkan koma)",
-    "paramFiltersAllowedPlaceholder": "reasoning, … (dipisahkan koma)",
-    "customGatewayNamePlaceholder": "Gateway Saya",
-    "inherit": "Warisi",
-    "claudeImportEntryName": "entri {number}",
-    "claudeImportParseError": "kesalahan penguraian",
-    "claudeImportNoValidEntries": "Tidak ada entri valid untuk diimpor",
-    "webFetch": "Web Fetch",
-    "webFetchTooltip": "Penyedia yang mengekstrak konten dari URL web (HTML → Markdown, scrape, screenshot)",
-    "webFetchProvidersHeading": "Penyedia Web Fetch",
-    "compatibleProvidersDesc": "Titik akhir yang kompatibel dengan OpenAI dan Anthropic yang Anda hosting atau konfigurasikan. Arahkan SDK OpenAI apa pun ke URL Anda sendiri dan rutekan permintaan ke sini.",
-    "oauthProvidersDesc": "Penyedia yang diautentikasi melalui OAuth — masuk sekali dan OmniRoute menangani rotasi token secara otomatis.",
-    "webCookieProvidersDesc": "Penyedia ini menggunakan sesi web browser, cookie, atau token web, bukan kunci API. Buka penyedia untuk menambahkan kredensial sesi yang diperlukan.",
-    "apiKeyProvidersDesc": "Penyedia kunci API standar. Tambahkan kunci Anda sekali dan OmniRoute merutekan, mencoba ulang, dan membatasi laju atas nama Anda.",
-    "noAuthProvidersDesc": "Titik akhir terbuka yang tidak memerlukan kredensial — siap digunakan segera tanpa pendaftaran apa pun.",
-    "upstreamProxyProvidersDesc": "Rute lalu lintas keluar melalui proksi hulu sebelum mencapai penyedia. Berguna untuk jaringan perusahaan atau inspeksi lalu lintas.",
-    "webFetchProvidersDesc": "Penyedia yang mengambil dan mengekstrak konten dari URL web. Gunakan untuk memperkuat prompt dengan data web langsung.",
-    "aggregatorsGatewaysDesc": "Agregator multi-penyedia dan gateway AI yang mengekspos satu API terpadu di puluhan model yang mendasarinya.",
-    "enterpriseCloudDesc": "Model tingkat enterprise dan di-host di cloud dengan SLA yang ditingkatkan, sertifikasi kepatuhan, dan kapasitas khusus.",
-    "cloudAgentProvidersDesc": "Agen cloud otonom yang mengeksekusi tugas jangka panjang dengan persetujuan rencana dan pelacakan status langsung.",
-    "localProvidersDesc": "Model yang di-host mandiri berjalan di perangkat keras Anda sendiri. Tidak ada data yang meninggalkan infrastruktur Anda.",
-    "searchProvidersDesc": "Penyedia pencarian web dan dokumen. Lampirkan ke panggilan LLM untuk Retrieval-Augmented Generation.",
-    "audioProvidersDesc": "Penyedia text-to-speech dan speech-to-text untuk I/O suara dan alur transkripsi audio.",
-    "embeddingRerankProvidersDesc": "Penyedia vector embedding dan reranking untuk pencarian semantik, alur RAG, dan penilaian kesamaan.",
-    "imageProvidersDesc": "Penyedia pembuatan gambar dan visi — buat gambar dari teks atau analisis gambar yang ada.",
-    "videoProvidersDesc": "Penyedia pembuatan video. Buat klip video pendek dari prompt teks atau gambar.",
-    "onboardingWizard": "Wisaya Orientasi Penyedia",
-    "onboardingWizardShort": "Wisaya Orientasi",
-    "onboardingWizardDescription": "Hubungkan penyedia kunci API, kompatibilitas khusus, dan OAuth dengan validasi, persistensi, dan pengujian koneksi langsung.",
-    "onboardingStepType": "Ketik",
-    "onboardingStepProvider": "Penyedia",
-    "onboardingStepCredentials": "Kredensial",
-    "onboardingStepResult": "Hasil",
-    "onboardingTypeApiKeyTitle": "Penyedia kunci API",
-    "onboardingTypeApiKeyText": "Gunakan penyedia bawaan seperti OpenAI, Anthropic, Gemini, Groq, Azure, dan banyak lagi.",
-    "onboardingTypeCustomTitle": "Penyedia khusus yang kompatibel",
-    "onboardingTypeCustomText": "Buat titik akhir yang kompatibel dengan OpenAI, Anthropic, atau Claude Code dan tambahkan kuncinya.",
-    "onboardingTypeOAuthTitle": "Penyedia OAuth",
-    "onboardingTypeOAuthText": "Gunakan kembali OAuth, kode perangkat, atau alur impor lokal yang ada untuk penyedia pengkodean.",
-    "onboardingChooseOAuthProvider": "Pilih penyedia OAuth",
-    "onboardingChooseApiKeyProvider": "Pilih penyedia kunci API",
-    "onboardingChooseProviderDescription": "Pilih penyedia, lalu wizard akan memandu Anda melalui kredensial dan pengujian.",
-    "onboardingChangeType": "Ubah jenis",
-    "onboardingChangeProvider": "Ganti penyedia",
-    "onboardingSearchProviders": "Penyedia pencarian…",
-    "onboardingApiKeyOptional": "Kunci API opsional",
-    "onboardingProviderConnected": "Penyedia terhubung",
-    "onboardingProviderSavedWithWarnings": "Penyedia disimpan dengan peringatan",
-    "onboardingProviderFinished": "Orientasi penyedia selesai",
-    "onboardingYourProviderConnection": "Koneksi penyedia Anda",
-    "onboardingTestPassed": "Tes lulus",
-    "onboardingTestFailed": "Tes gagal",
-    "onboardingOpenProviderDetails": "Buka detail penyedia",
-    "onboardingTryInPlayground": "Cobalah di taman bermain",
-    "onboardingDefaultConnectionName": "{provider} Pratama",
-    "onboardingTestingConnection": "Menguji koneksi penyedia…",
-    "onboardingValidatingCredentials": "Memvalidasi kredensial…",
-    "onboardingSavingConnection": "Menyimpan koneksi penyedia…",
-    "onboardingProviderFailed": "Orientasi penyedia gagal",
-    "onboardingCreatingCompatibleProvider": "Membuat penyedia yang kompatibel…",
-    "onboardingSavingCompatibleConnection": "Menyimpan koneksi penyedia yang kompatibel…",
-    "onboardingCustomProviderFallbackName": "Penyedia khusus",
-    "onboardingCustomProviderFailed": "Orientasi penyedia khusus gagal",
-    "onboardingLoadingOAuthConnection": "Memuat koneksi OAuth…",
-    "onboardingOAuthNoConnectionFound": "OAuth selesai, namun koneksi penyedia tidak ditemukan.",
-    "onboardingOAuthFailed": "Orientasi OAuth gagal",
-    "onboardingAddProvider": "Tambahkan {provider}",
-    "onboardingConnectionName": "Nama koneksi",
-    "onboardingApiKeyOptionalLabel": "Kunci API (opsional)",
-    "onboardingBaseUrlOverride": "Penggantian URL dasar",
-    "onboardingBaseUrlOverrideHint": "Opsional. Disimpan sebagai penyediaSpecificData.baseUrl.",
-    "onboardingRegion": "Wilayah",
-    "onboardingSearchCx": "Cari CX / ID mesin",
-    "onboardingProviderSpecificIdPlaceholder": "ID khusus penyedia opsional",
-    "onboardingCustomUserAgent": "Agen Pengguna Khusus",
-    "onboardingWorking": "Bekerja…",
-    "onboardingValidateSaveTest": "Validasi, simpan, dan uji",
-    "onboardingBack": "Kembali",
-    "onboardingCreateCustomCompatibleProvider": "Buat penyedia khusus yang kompatibel",
-    "onboardingCreateCustomCompatibleDescription": "Wizard membuat node penyedia terlebih dahulu, lalu menyimpan dan menguji koneksi kunci API-nya.",
-    "onboardingProtocol": "Protokol",
-    "onboardingOpenAiCompatible": "Kompatibel dengan OpenAI",
-    "onboardingAnthropicCompatible": "Kompatibel dengan antropik",
-    "onboardingClaudeCodeCompatible": "Kompatibel dengan Kode Claude",
-    "onboardingProviderPrefix": "Awalan penyedia",
-    "onboardingProviderPrefixHint": "Digunakan untuk menghasilkan id penyedia terkelola.",
-    "onboardingChatPath": "Jalur obrolan",
-    "onboardingModelsPath": "Jalur model",
-    "onboardingCreateSaveTest": "Buat, simpan, dan uji",
-    "onboardingConnectProvider": "Hubungkan {provider}",
-    "onboardingOAuthFlowDescription": "OmniRoute akan membuka aliran OAuth yang ada untuk penyedia ini. Setelah login, wizard memuat ulang koneksi yang disimpan dan menjalankan tes koneksi yang sama seperti halaman penyedia.",
-    "onboardingStartOAuthFlow": "Mulai alur OAuth",
-    "onboardingProviderDescriptions": {
-      "360ai": "Dapatkan kunci API di ai.360.cn",
-      "agentrouter": "Dapatkan kredit gratis $200 di https://agentrouter.org/register — tidak memerlukan kartu kredit.",
-      "unorouter": "Buat kunci API di https://unorouter.ai, lalu tempelkan di sini sebagai token Bearer.",
-      "agnes": "Dapatkan kunci API di agnes-ai.com",
-      "aimlapi": "Tingkat gratis dijeda (2026) — AI/ML API sekarang hanya bayar sesuai penggunaan (isi ulang min $20); tidak ada kredit gratis berulang.",
-      "ai21": "Kredit uji coba $10 saat pendaftaran (berlaku 3 bulan), tidak memerlukan kartu kredit",
-      "alibaba": "Hubungkan Alibaba dengan kunci API.",
-      "alibaba-cn": "Hubungkan Alibaba (China) dengan kunci API.",
-      "bailian-coding-plan": "Hubungkan Alibaba Coding Plan dengan kunci API.",
-      "bedrock": "Integrasi Bedrock bawaan: penemuan model menggunakan model fondasi Bedrock dan profil inferensi, sedangkan obrolan menggunakan API Bedrock Runtime Converse/ConverseStream regional.",
-      "anthropic": "Hubungkan Anthropic dengan kunci API.",
-      "ant-ling": "Daftar dan buat kunci API di konsol API Ant Ling (https://chat.ant-ling.com/open), lalu tempelkan di sini. OmniRoute mengarahkan lalu lintas obrolan ke https://api.ant-ling.com/v1/chat/completions; penyedia ini kompatibel dengan OpenAI dan juga menyediakan antarmuka yang kompatibel dengan Anthropic.",
-      "api-airforce": "Dapatkan kunci API Anda dari https://panel.api.airforce — titik akhir yang kompatibel dengan OpenAI di https://api.airforce/v1",
-      "arcee-ai": "Dapatkan kunci API di arcee.ai",
-      "azure-ai": "Foundry menggunakan permukaan OpenAI v1 dengan nama penerapan sebagai model. OmniRoute menormalisasi URL sumber daya root ke titik akhir obrolan v1 dan /models.",
-      "azure-openai": "Gunakan kunci API Azure OpenAI Anda. URL Dasar harus berupa titik akhir sumber daya Anda, misalnya https://my-resource.openai.azure.com.",
-      "bai": "Kunci API Bearer untuk gateway LLM b.ai yang kompatibel dengan OpenAI (berbeda dari TheB.AI). Buat kunci di https://docs.b.ai, lalu gunakan https://api.b.ai/v1 sebagai URL dasar yang kompatibel dengan OpenAI.",
-      "baichuan": "Dapatkan kunci API di platform.baichuan-ai.com",
-      "baidu": "Dapatkan kunci API di console.bce.baidu.com",
-      "qianfan": "Gunakan kunci API Qianfan dari Baidu AI Cloud. Titik akhir default kompatibel dengan OpenAI v2.",
-      "baseten": "Kredit uji coba gratis $30 untuk inferensi GPU",
-      "bazaarlink": "Buat kunci API gratis di https://bazaarlink.ai — model 'auto:free' merutekan ke inferensi tanpa biaya. Semua model menggunakan format provider/model-name, mis. xiaomi/mimo-v2.5-pro.",
-      "black-forest-labs": "Hubungkan Black Forest Labs dengan kunci API.",
-      "blackbox": "Tingkat gratis: obrolan dasar tanpa batas plus Minimax-M2.5, tidak memerlukan kartu kredit",
-      "bluesminds": "Dapatkan kunci API Anda di https://www.bluesminds.com — titik akhir yang kompatibel dengan OpenAI di https://api.bluesminds.com/v1 dengan kredit harian gratis. Model VIP (Claude Opus 4.5, Gemini 2.5 Pro) menggunakan kredit pi.",
-      "byteplus": "Hubungkan BytePlus ModelArk dengan kunci API.",
-      "bytez": "Kredit gratis $1, diperbarui setiap 4 minggu",
-      "cerebras": "Uji Coba Gratis: 1M token/hari, 30K TPM, 5 RPM — tanpa kartu kredit.",
-      "charm-hyper": "Buat kunci API di https://hyper.charm.land, lalu tempelkan di sini sebagai token Bearer.",
-      "chutes": "Kunci API Bearer untuk gateway Chutes yang kompatibel dengan OpenAI.",
-      "clarifai": "Clarifai mengekspos obrolan, respons, dan /models yang kompatibel dengan OpenAI pada /v2/ext/openai/v1. Model publik/komunitas biasanya memerlukan PAT; kunci dengan cakupan aplikasi hanya berfungsi untuk sumber daya di dalam aplikasi tersebut.",
-      "cloudflare-ai": "Memerlukan Token API DAN ID Akun (ditemukan di dash.cloudflare.com)",
-      "clova-studio": "CLOVA Studio (HyperCLOVA X) kompatibel dengan OpenAI di /v1/openai. OmniRoute memeriksa /v1/openai/models dan mengarahkan lalu lintas chat ke /v1/openai/chat/completions. Menggunakan host clovastudio.stream.ntruss.com saat ini — endpoint legacy clovastudio.apigw.ntruss.com sedang dihentikan.",
-      "codestral": "Hubungkan Codestral dengan kunci API.",
-      "cohere": "Uji Coba Gratis: 1.000 panggilan API/bulan untuk pengujian, tidak memerlukan kartu kredit",
-      "command-code": "Buat atau salin kunci API dari Command Code, lalu tempelkan di sini sebagai token Bearer.",
-      "coze": "Dapatkan kunci API di coze.com/open/api",
-      "crof": "Hubungkan CrofAI dengan kunci API.",
-      "databricks": "Hubungkan Databricks dengan kunci API.",
-      "datarobot": "Gateway default mengatalogkan model aktif dari /genai/llmgw/catalog/. URL penerapan juga didukung untuk permintaan obrolan langsung yang kompatibel dengan OpenAI.",
-      "deepinfra": "Kredit pendaftaran gratis untuk pengujian API dan eksplorasi model",
-      "deepseek": "5M token gratis saat pendaftaran - tidak memerlukan kartu kredit",
-      "dgrid": "Buat kunci API DGrid di https://dgrid.ai, lalu gunakan https://api.dgrid.ai/v1 sebagai URL dasar yang kompatibel dengan OpenAI.",
-      "dify": "Dapatkan kunci API dari instans Dify Anda.",
-      "digitalocean": "Hubungkan DigitalOcean dengan kunci API.",
-      "dit": "dit.ai (Distributed Intelligence Trade) adalah perute/gateway yang kompatibel dengan OpenAI dengan penetapan harga dinamis per permintaan, mengekspos /v1/chat/completions di https://api.dit.ai/v1. OmniRoute menggunakan protokol OpenAI; analitik pengeluaran/penghematan berada di dasbor dit.ai.",
-      "doubao": "Dapatkan kunci API di console.volcengine.com",
-      "empower": "Empower mengekspos obrolan yang kompatibel dengan OpenAI di https://app.empower.dev/api/v1 dengan dukungan pemanggilan alat pada empower-functions.",
-      "factory": "Dapatkan kunci API Factory Anda di https://app.factory.ai/settings/api-keys, lalu tempelkan sebagai token Bearer. Titik akhir yang kompatibel dengan OpenAI di https://api.factory.ai/v1.",
-      "fal-ai": "Hubungkan Fal.ai dengan kunci API.",
-      "featherless-ai": "Tingkat gratis tersedia — tidak memerlukan kartu kredit",
-      "fenayai": "Kunci API Bearer untuk gateway FenayAI yang kompatibel dengan OpenAI.",
-      "firecrawl": "Hubungkan Firecrawl dengan kunci API.",
-      "fireworks": "Kredit pemula gratis $1 saat pendaftaran untuk pengujian API",
-      "freeaiapikey": "Proksi API berdiskon untuk 40+ model termasuk GPT-5, Claude Opus 4.6, Claude Sonnet 4.6, Qwen 3.5. Dapatkan kunci API Anda di https://freeaiapikey.com/dashboard. URL Dasar: https://freeaiapikey.com/v1.",
-      "freemodel-dev": "Dapatkan kredit API gratis $300 di https://freemodel.dev — tidak memerlukan info pembayaran. Titik akhir yang kompatibel dengan OpenAI. Model GPT-5.4 dan GPT-5.5 tersedia.",
-      "friendliai": "Tingkat gratis untuk inferensi serverless — tidak memerlukan kartu kredit",
-      "gemini": "Gratis selamanya: 1.500 req/hari untuk Gemini 2.5 Flash — tanpa kartu kredit, dapatkan kunci di aistudio.google.com",
-      "gigachat": "Hubungkan GigaChat (Sber) dengan kunci API.",
-      "gitlab": "Token akses pribadi GitLab untuk Code Suggestions API publik. Konfigurasikan URL dasar yang di-host sendiri saat tidak menggunakan gitlab.com.",
-      "gitlawb-gmi": "Dapatkan kunci API Anda dari dasbor Gitlawb Opengateway.",
-      "gitlawb": "Dapatkan kunci API Anda dari dasbor Gitlawb Opengateway.",
-      "glm": "Hubungkan GLM Coding dengan kunci API.",
-      "glm-cn": "Hubungkan GLM Coding (China) dengan kunci API.",
-      "glmt": "Profil GLM prasetel dengan anggaran token lebih tinggi, pemikiran diaktifkan, dan batas waktu lebih lama.",
-      "getgoapi": "Hubungkan GoAPI dengan kunci API.",
-      "groq": "Tingkat gratis: 30 RPM / 14.4K RPD — tanpa kartu kredit",
-      "haiper": "Dapatkan kunci API di haiper.ai/haiper-api",
-      "heroku": "Hubungkan Heroku AI dengan kunci API.",
-      "hcnsec": "Dapatkan kunci API di api.hcnsec.cn",
-      "huggingface": "API Inferensi Gratis untuk ribuan model (Whisper, VITS, SDXL…)",
-      "hyperbolic": "Kredit uji coba $1-5 saat pendaftaran untuk inferensi serverless",
-      "watsonx": "Gateway model watsonx mengekspos /chat/completions dan /models yang kompatibel dengan OpenAI di bawah /ml/gateway/v1.",
-      "ideogram": "Dapatkan kunci API di ideogram.ai/docs/api",
-      "iflytek": "Dapatkan kunci API di console.xfyun.cn",
-      "inception": "Inception Labs kompatibel dengan OpenAI di https://api.inceptionlabs.ai/v1. mercury-2 adalah dLLM (diffusion LLM) pertama dalam katalog — 5-10x lebih cepat dalam menghasilkan dibandingkan model autoregressive yang sebanding, dengan pemanggilan alat, json_mode, dan keluaran terstruktur.",
-      "inference-net": "Kredit gratis $25 saat pendaftaran ditambah hibah penelitian yang tersedia",
-      "internlm": "Kuota bulanan gratis ~1M input / 3M output token (~10 RPM)",
-      "jina-ai": "Kunci API Bearer untuk API rerank Jina AI.",
-      "jina-reader": "Hubungkan Jina Reader dengan kunci API.",
-      "kenari": "Kenari mengekspos endpoint chat completions yang kompatibel dengan OpenAI di https://kenari.id/v1/chat/completions, ditambah katalog /v1/models langsung yang mencakup Claude, GPT, DeepSeek, GLM, Kimi, dan lainnya. OmniRoute menggunakan protokol OpenAI dan mencantumkan model via passthrough.",
-      "kie": "Hubungkan KIE.AI dengan kunci API.",
-      "kilo-gateway": "Hubungkan Kilo Gateway dengan kunci API.",
-      "kimi": "Hubungkan Kimi dengan kunci API.",
-      "kimi-coding-apikey": "Hubungkan Kimi Coding (API Key) dengan kunci API.",
-      "lambda-ai": "Hubungkan Lambda AI dengan kunci API.",
-      "laozhang": "Hubungkan LaoZhang AI dengan kunci API.",
-      "leonardo": "Dapatkan kunci API di leonardo.ai/developer",
-      "liquid": "Dapatkan kunci API di liquid.ai",
-      "llamagate": "Hubungkan LlamaGate dengan kunci API.",
-      "llm7": "Bekerja tanpa kunci API (gunakan 'unused' sebagai kunci). Dapatkan token gratis di token.llm7.io untuk batas yang lebih tinggi.",
-      "longcat": "Gratis: hibah 10M-token satu kali setelah pendaftaran akun + verifikasi KYC (LongCat-2.0). Hanya satu kali — bukan tunjangan harian/bulanan yang berulang.",
-      "maritalk": "Hubungkan Maritalk dengan kunci API.",
-      "meta-llama": "Hubungkan Meta Llama API dengan kunci API.",
-      "minimax-cn": "Hubungkan Minimax (China) dengan kunci API.",
-      "minimax": "Hubungkan Minimax Coding dengan kunci API.",
-      "mistral": "Tingkat Eksperimen Gratis: akses dengan batas tingkat ke semua model, tidak memerlukan kartu kredit",
-      "modal": "Modal biasanya melayani aplikasi yang kompatibel dengan OpenAI yang di-host pengguna di /v1. OmniRoute akan menyelidiki /v1/models dan merutekan lalu lintas obrolan ke /v1/chat/completions.",
-      "modelscope": "Tingkat gratis via ModelScope API-Inference — memerlukan akun Alibaba.",
-      "monsterapi": "Dapatkan kunci API di monsterapi.ai",
-      "moonshot": "Hubungkan Moonshot AI dengan kunci API.",
-      "morph": "Tingkat gratis: 250K kredit/bulan, $0",
-      "nanogpt": "Hubungkan NanoGPT dengan kunci API.",
-      "nebius": "Kredit uji coba ~$1 saat pendaftaran untuk pengujian API",
-      "nlpcloud": "NLP Cloud menggunakan API chatbot berpemilik alih-alih chat/completions OpenAI. OmniRoute mengadaptasi pesan OpenAI ke input/konteks/riwayat dan mengekspos katalog lokal model chatbot yang didukung.",
-      "nomic": "Dapatkan kunci API di atlas.nomic.ai",
-      "nous-research": "Nous mengekspos permukaan /v1 yang kompatibel dengan OpenAI dengan katalog /models jarak jauh yang besar. Endpoint /chat/completions memerlukan kunci API yang valid untuk inferensi terprogram.",
-      "novita": "Kredit uji coba $0.50 saat pendaftaran (berlaku sekitar 1 tahun)",
-      "nscale": "Kredit gratis $5 saat pendaftaran untuk pengujian inferensi",
-      "nube": "Hubungkan Nube.sh dengan kunci API.",
-      "nvidia": "Akses pengembang gratis: ~40 RPM, 70+ model (Kimi K2.5, GLM 4.7, DeepSeek V3.2...)",
-      "oci": "OCI mengekspos endpoint chat dan responses yang kompatibel dengan OpenAI. Project ID bersifat opsional di OmniRoute tetapi mungkin diperlukan untuk Responses dan alur kerja agentic.",
-      "ollama-cloud": "Hubungkan Ollama Cloud dengan kunci API.",
-      "openadapter": "OpenAdapter mengekspos endpoint chat completions yang kompatibel dengan OpenAI di https://api.openadapter.in/v1/chat/completions, menggabungkan 70+ model sumber terbuka (DeepSeek, Qwen, Kimi, MiniMax, GLM, Llama, Mistral, …). OmniRoute menggunakan protokol OpenAI.",
-      "openai": "Hubungkan OpenAI dengan kunci API.",
-      "opencode-go": "Hubungkan OpenCode Go dengan kunci API.",
-      "opencode-zen": "Hubungkan OpenCode Zen dengan kunci API.",
-      "openrouter": "Model gratis seharga $0/token dengan akhiran :free - 20 RPM / 200 RPD",
-      "openvecta": "Kredit gratis saat pendaftaran untuk inferensi yang kompatibel dengan OpenAI di seluruh LLM, embedding, dan model penalaran",
-      "orcarouter": "Buat kunci API (dimulai dengan sk-orca-) di https://www.orcarouter.ai, lalu tempelkan sebagai token Bearer. Endpoint yang kompatibel dengan OpenAI di https://api.orcarouter.ai/v1.",
-      "ovhcloud": "Hubungkan OVHcloud AI dengan kunci API.",
-      "perplexity": "Hubungkan Perplexity dengan kunci API.",
-      "piapi": "Hubungkan PiAPI dengan kunci API.",
-      "pioneer": "Kredit penggunaan gratis $75 — tidak memerlukan kartu kredit",
-      "plamo": "PLaMo kompatibel dengan OpenAI di https://api.platform.preferredai.jp/v1. Dibuat oleh Preferred Networks dan dioptimalkan untuk bahasa Jepang. Dokumen terutama dalam bahasa Jepang.",
-      "poe": "Poe mengekspos chat dan responses yang kompatibel dengan OpenAI di https://api.poe.com/v1, dengan pemeriksaan saldo terautentikasi pada /usage/current_balance.",
-      "pollinations": "Tingkat gratis tanpa kunci: openai, openai-fast, openai-large, qwen-coder, mistral, deepseek, grok, gemini-flash-lite-3.1, perplexity-fast, perplexity-reasoning. Model premium (claude, gemini, midijourney) memerlukan kunci API Pollinations dari enter.pollinations.ai.",
-      "publicai": "Memerlukan kunci API — kredit pendaftaran satu kali, selanjutnya berbayar",
-      "qiniu": "Buat kunci API inferensi Qiniu AI di https://portal.qiniu.com/ai-inference/api-key, lalu tempelkan di sini sebagai token Bearer. Endpoint yang kompatibel dengan OpenAI di https://api.qnaigc.com/v1, memproksi DeepSeek, Claude, Kimi, dan lainnya di balik satu kunci.",
-      "recraft": "Hubungkan Recraft dengan kunci API.",
-      "reka": "Reka Chat kompatibel dengan OpenAI pada /v1. OmniRoute menyelidiki /v1/models dan mengarahkan lalu lintas chat ke /v1/chat/completions.",
-      "requesty": "Buat kunci API di https://app.requesty.ai, lalu tempelkan di sini sebagai token Bearer. Endpoint yang kompatibel dengan OpenAI di https://router.requesty.ai/v1, dengan katalog /v1/models langsung.",
-      "runwayml": "Pembuatan video Runway berbasis tugas. OmniRoute mengirimkan pekerjaan text-to-video atau image-to-video, melakukan polling pada /v1/tasks/[id], dan menormalisasi output video yang selesai kembali ke dalam respons /v1/videos/generations yang mirip OpenAI.",
-      "sambanova": "Kredit gratis $5 saat pendaftaran (masa berlaku 30 hari), tidak memerlukan kartu kredit",
-      "sap": "Penemuan model menggunakan /v2/lm/scenarios/foundation-models/models pada AI_API_URL. Permintaan chat menggunakan deploymentUrl/chat/completions dan memerlukan AI-Resource-Group.",
-      "sarvam": "Sarvam AI kompatibel dengan OpenAI di /v1. OmniRoute memeriksa /v1/models dan mengarahkan lalu lintas obrolan ke /v1/chat/completions. Model disesuaikan untuk bahasa-bahasa India.",
-      "scaleway": "1M token gratis untuk akun baru — patuh EU/GDPR (Paris), Qwen3 235B & Llama 70B",
-      "sensenova": "Dapatkan kunci API di platform.sensenova.cn",
-      "siliconflow": "Kredit gratis $1 ditambah model gratis permanen setelah verifikasi identitas",
-      "snowflake": "Hubungkan Snowflake Cortex dengan kunci API.",
-      "sparkdesk": "Dapatkan kunci API di console.xfyun.cn",
-      "stability-ai": "Hubungkan Stability AI dengan kunci API.",
-      "stepfun": "Dapatkan kunci API di platform.stepfun.com",
-      "sumopod": "SumoPod mengekspos endpoint chat completions yang kompatibel dengan OpenAI di https://ai.sumopod.com/v1/chat/completions, ditambah katalog /v1/models langsung. OmniRoute menggunakan protokol OpenAI dan mencantumkan model melalui passthrough.",
-      "suno": "Tempelkan cookie sesi dari suno.ai (autentikasi Clerk)",
-      "synthetic": "Hubungkan Synthetic dengan kunci API.",
-      "tencent": "Dapatkan kunci API di console.cloud.tencent.com",
-      "thebai": "Kunci API Bearer untuk gateway yang kompatibel dengan OpenAI dari TheB.AI.",
-      "tinyfish": "X-API-Key dari agent.tinyfish.ai/api-keys",
-      "together": "Hubungkan Together AI dengan kunci API.",
-      "tokenrouter": "TokenRouter mengekspos endpoint chat completions yang kompatibel dengan OpenAI di https://api.tokenrouter.com/v1/chat/completions, ditambah katalog /v1/models yang berfungsi. OmniRoute menggunakan protokol OpenAI.",
-      "topaz": "Hubungkan Topaz dengan kunci API.",
-      "typhoon": "Typhoon kompatibel dengan OpenAI di /v1. Dibuat oleh SCB 10X (Thailand); typhoon-v2.5-30b-a3b-instruct adalah model multibahasa yang mengutamakan bahasa Thai.",
-      "udio": "Tempelkan cookie sesi dari udio.com (autentikasi Supabase)",
-      "uncloseai": "Tidak memerlukan autentikasi. API menerima string apa pun yang tidak kosong sebagai kunci untuk identifikasi.",
-      "upstage": "Hubungkan Upstage dengan kunci API.",
-      "v0-vercel": "Hubungkan v0 (Vercel) dengan kunci API.",
-      "venice": "Hubungkan Venice.ai dengan kunci API.",
-      "vercel-ai-gateway": "Hubungkan Vercel AI Gateway dengan kunci API.",
-      "vertex": "Sediakan JSON Akun Layanan atau access_token OAuth",
-      "vertex-partner": "Sediakan JSON Akun Layanan yang sama yang digunakan untuk model mitra Vertex AI.",
-      "volcengine": "Hubungkan Volcengine dengan kunci API.",
-      "voyage-ai": "Kunci API Bearer untuk API embedding dan rerank Voyage AI.",
-      "wafer": "Kunci API dari https://wafer.ai",
-      "wandb": "Hubungkan Weights & Biases Inference dengan kunci API.",
-      "writer": "Writer Palmyra kompatibel dengan OpenAI di https://api.writer.com/v1. palmyra-x5 menawarkan jendela konteks 1M-token.",
-      "x5lab": "X5Lab menyediakan endpoint penyelesaian obrolan yang kompatibel dengan OpenAI di https://api.x5lab.dev/v1/chat/completions, ditambah katalog /v1/models langsung. OmniRoute menggunakan protokol OpenAI dan mencantumkan model via passthrough.",
-      "xai": "Hubungkan xAI (Grok) dengan kunci API.",
-      "xiaomi-mimo": "Hubungkan Xiaomi MiMo dengan kunci API.",
-      "yi": "Dapatkan kunci API di platform.lingyiwanwu.com",
-      "zai": "Kunci API dari https://open.bigmodel.cn/usercenter/apikeys",
-      "zenmux": "ZenMux menyediakan endpoint penyelesaian obrolan yang kompatibel dengan OpenAI di /api/v1/chat/completions, ditambah permukaan protokol Anthropic Messages (/api/anthropic/v1/messages) dan Google Gemini (/api/vertex-ai). OmniRoute menggunakan protokol OpenAI.",
-      "galadriel": "Hubungkan Galadriel dengan kunci API.",
-      "predibase": "Kredit uji coba gratis $25 (validitas 30 hari)",
-      "chenzk": "Gateway yang kompatibel dengan OpenAI dengan katalog model langsung di chenzk.top.",
-      "magnific": "Hasilkan gambar dengan Mystic API dari Magnific.",
-      "freetheai": "Gateway gratis yang kompatibel dengan OpenAI dengan dukungan model passthrough.",
-      "g4f-gemini": "Gateway g4f.space jarak jauh ke Gemini. Akses anonim memerlukan kredit proof-of-work dari g4f.dev/chat atau kunci API anggota dari g4f.dev/members.html; batas dapat berubah.",
-      "g4f-groq": "Gateway g4f.space jarak jauh ke Groq. Akses anonim memerlukan kredit proof-of-work dari g4f.dev/chat atau kunci API anggota dari g4f.dev/members.html; batas dapat berubah.",
-      "g4f-nvidia": "Gateway g4f.space jarak jauh ke NVIDIA NIM. Akses anonim memerlukan kredit proof-of-work dari g4f.dev/chat atau kunci API anggota dari g4f.dev/members.html; batas dapat berubah.",
-      "g4f-ollama": "Gateway g4f.space jarak jauh ke Ollama. Akses anonim memerlukan kredit proof-of-work dari g4f.dev/chat atau kunci API anggota dari g4f.dev/members.html; batas dapat berubah.",
-      "g4f-pollinations": "Gateway g4f.space jarak jauh ke Pollinations. Akses anonim memerlukan kredit proof-of-work dari g4f.dev/chat atau kunci API anggota dari g4f.dev/members.html; batas dapat berubah.",
-      "mixedbread": "Buat embedding dengan API Mixedbread.",
-      "segmind": "Hasilkan gambar dan video dengan model ter-host Segmind.",
-      "amazon-q": "Menggunakan ID Pembangun AWS atau alur refresh-token impor yang sama dengan Kiro, tetapi menjaga koneksi Amazon Q tetap terpisah.",
-      "antigravity": "Hubungkan Antigravity dengan alur OAuth yang ada.",
-      "agy": "Impor login CLI Antigravity (`agy`) Anda (tempel/unggah berkas tokennya), deteksi otomatis login CLI lokal, atau masuk dengan Google. Berbagi backend Antigravity (termasuk model Claude).",
-      "claude": "Hubungkan Claude Code dengan alur OAuth yang ada.",
-      "cline": "Hubungkan Cline dengan alur OAuth yang ada.",
-      "cursor": "Hubungkan Cursor IDE dengan alur OAuth yang ada.",
-      "cursor-api": "Connect Cursor with a user API key (crsr_...) from cursor.com/dashboard/api; no IDE session needed.",
-      "github": "Hubungkan GitHub Copilot dengan alur OAuth yang ada.",
-      "gitlab-duo": "Aplikasi OAuth dengan cakupan ai_features + read_user. Konfigurasikan GITLAB_DUO_OAUTH_CLIENT_ID dan secara opsional GITLAB_DUO_OAUTH_CLIENT_SECRET pada instansi OmniRoute ini.",
-      "kilocode": "Hubungkan Kilo Code dengan alur OAuth yang ada.",
-      "kimi-coding": "Hubungkan Kimi Coding dengan alur OAuth yang ada.",
-      "kiro": "Tingkat gratis: 50 kredit/bulan (~25K–100K token). ⚠️ Kiro ToS melarang penggunaan proksi/harness pihak ketiga.",
-      "codex": "Hubungkan OpenAI Codex dengan alur OAuth yang ada.",
-      "qwen": "Hubungkan Qwen Code dengan alur OAuth yang ada.",
-      "github-models": "Buat PAT GitHub dengan cakupan 'models: read' di github.com/settings/tokens"
-    },
-    "passthroughModelsDescription": "{provider} menerima ID model asli penyedia. Impor dari /models atau tambahkan ID khusus untuk perutean.",
-    "bedrockModelsDescription": "Model Amazon Bedrock dicakup berdasarkan wilayah AWS. Impor dari /models atau tambahkan ID model Batuan Dasar yang diaktifkan di wilayah yang dipilih.",
-    "bedrockModelPlaceholder": "antropik.claude-soneta-4-6",
-    "addProviderSessionCookieTitle": "Tambahkan cookie sesi {provider}",
-    "openWebProviderSite": "Buka {host}",
-    "addProviderWebTokenTitle": "Tambahkan token web {provider}",
-    "addProviderConnectionTitle": "Tambahkan koneksi {provider}",
-    "webTokenCredentialLabel": "Token sesi web",
-    "webNoAuthCredentialLabel": "Tidak diperlukan kredensial",
-    "webCookieCredentialHint": "Cookie yang diperlukan: {credential}. Tempelkan nilai header Cookie dari sesi web {provider} yang Anda gunakan untuk masuk. Jangan sertakan awalan Cookie:.",
-    "webTokenCredentialHint": "Kredensial: {credential}. Tempelkan nilai token dari sesi web {provider} yang Anda masuki, atau ekspor HAR DevTools jika penyedia mendukungnya.",
-    "webCookieEditHint": "Biarkan kosong untuk menyimpan cookie sesi saat ini. Cookie yang diperlukan: {credential}.",
-    "webTokenEditHint": "Biarkan kosong untuk mempertahankan token sesi web saat ini. Kredensial: {credential}.",
-    "webSessionGuideTitle": "Cara mendapatkan kredensial sesi",
-    "webSessionGuideIntro": "{provider} menggunakan sesi web browser alih-alih kunci API.",
-    "webCookieRequiredCredential": "Cookie yang diperlukan: {credential}",
-    "webTokenRequiredCredential": "Token yang diperlukan: {credential}",
-    "webSessionGuideStep1": "Masuk ke {provider} di browser Anda.",
-    "webSessionGuideStep2": "Buka alat pengembang browser dan periksa permintaan yang dibuat oleh aplikasi web.",
-    "webSessionGuideStep2Fast": "Jalur cepat: instal ekstensi Cookie Editor (chromewebstore.google.com → Cookie Editor), buka di tab {provider}, temukan {credential} (pilih semua bagian bernomor jika terpisah), dan klik Ekspor → Salin dengan format ekspor diatur ke “Cookie header”.",
-    "webSessionGuideStep3": "Salin kredensial yang diperlukan dari domain penyedia itu sendiri. Untuk cookie, salin hanya nilai header Cookie dan hilangkan Cookie:.",
-    "webSessionGuideStep3Manual": "Jalur manual: buka alat pengembang browser (F12 → Jaringan), segarkan halaman, buka permintaan yang terautentikasi, dan salin nilai header Cookie dari Header Permintaan — abaikan awalan Cookie:.",
-    "webSessionGuideStep4": "Rekatkan di sini dan periksa koneksinya. Jika berhenti berfungsi, masuk lagi dan ganti dengan nilai baru.",
-    "harImportButtonLabel": "Import .har file",
-    "harImportButtonBusy": "Importing…",
-    "harImportButtonHint": "Export from DevTools Network tab after sending at least one chat message.",
-    "harImportStatusValid": "Imported — valid for ~{minutes}m.",
-    "harImportStatusExpiringSoon": "Imported — valid for only ~{minutes}m more.",
-    "harImportStatusExpired": "Imported, but this token already expired ({minutes}m ago) — export a fresh HAR.",
-    "harImportStatusUnknownExpiry": "Imported. Couldn't read its expiry.",
-    "harImportErrorNotJson": "That file isn't valid JSON — is it really a .har export?",
-    "harImportErrorNoEntries": "This HAR has no network entries recorded.",
-    "harImportErrorNoChathubUrl": "No Copilot chat connection found in this HAR. Send at least one chat message in m365.cloud.microsoft before exporting.",
-    "harImportErrorUnparsableUrl": "Found the chat connection, but couldn't read its URL.",
-    "harImportErrorMissingFields": "Found the chat connection, but the token was missing from it.",
-    "harImportErrorReadFailed": "Couldn't read that file.",
-    "harImportErrorUnknown": "Couldn't extract a credential from that HAR file.",
-    "webSessionSecurityHint": "Perlakukan ini seperti kata sandi: kata sandi tersebut dapat mengakses akun web yang Anda masuki hingga masa berlakunya habis atau dicabut.",
-    "webNoAuthGuideTitle": "Tidak diperlukan kredensial",
-    "webNoAuthGuideBody": "{provider} tidak memerlukan kunci API atau cookie. Simpan koneksi untuk menggunakan titik akhir web gratisnya.",
-    "webSessionCredentialValidationFailed": "Validasi kredensial sesi gagal. Masuk lagi, salin kredensial baru, dan coba lagi.",
-    "checkCookie": "Periksa kue",
-    "checkWebToken": "Periksa token",
-    "huggingchatLabel": "HuggingChat (Gratis)",
-    "huggingchatDesc": "Obrolan LLM gratis via huggingface.co/chat",
-    "poeWebLabel": "Poe Web",
-    "poeWebDesc": "Obrolan multi-model via poe.com",
-    "veniceWebLabel": "Venice Web",
-    "veniceWebDesc": "Obrolan AI yang berfokus pada privasi",
-    "v0VercelWebLabel": "v0 Vercel Web",
-    "v0VercelWebDesc": "Pembuatan kode AI via v0.dev",
-    "kimiWebLabel": "Kimi Web",
-    "kimiWebDesc": "Obrolan konsumen Moonshot AI via www.kimi.com (internasional, Connect-RPC API)",
-    "doubaoWebLabel": "Dola Web",
-    "doubaoWebDesc": "Obrolan AI ByteDance via dola.com",
-    "overrideBaseUrlAdvanced": "Lanjutan: timpa URL dasar",
-    "overrideBaseUrlHint": "Lanjutan: arahkan penyedia bawaan ini ke endpoint kustom. Biarkan kosong untuk menggunakan default.",
-    "apiProtocolLabel": "Protokol API",
-    "apiProtocolDefault": "Kompatibel dengan OpenAI (default)",
-    "apiProtocolHint": "Beberapa penyedia menerbitkan model yang sama melalui lebih dari satu protokol. Biarkan default kecuali Anda memerlukan alternatif.",
-    "bulkAddFormatHintCloudflare": "Satu kunci per baris. Format: name|accountId|apiKey (Cloudflare account ID + API token).",
-    "lmarenaWebCookieHint": "Buka arena.ai, masuk, lalu salin header Cookie lengkap dari permintaan Jaringan. Sertakan arena-auth-prod-v1.0 and arena-auth-prod-v1.1 (dan bagian selanjutnya jika ada), sebaiknya dengan cf_clearance. Jangan tempel hanya cookie arena-auth-prod-v1 yang kosong. Opsional: providerSpecificData.recaptchaV3Token jika create-evaluation masih mengembalikan 403.",
-    "kimiOfficialSupporterBadge": "Sahabat Pendiri",
-    "kimiOfficialSupporterTooltip": "Kimi (Moonshot AI) adalah sahabat open source pendiri OmniRoute",
-    "cheaperInferenceSupporterBadge": "Teman Open Source",
-    "cheaperInferenceSupporterTooltip": "Cheaper Inference mendukung OmniRoute sebagai Teman Open Source",
-    "kimiPartnerLinkNote": "Tautan mitra — mendukung OmniRoute tanpa biaya tambahan bagi Anda",
-    "codexQuotaPools": "Kumpulan kuota Codex",
-    "codexPoolAvailable": "Tersedia",
-    "codexPoolPartiallyLimited": "Dibatasi sebagian",
-    "codexPoolFullyLimited": "Dibatasi sepenuhnya",
-    "codexPoolLimited": "{count} dibatasi",
-    "codexPoolQuotaExhausted": "Kuota habis",
-    "codexPoolCoolingDown": "Dalam masa tunggu",
-    "codexPoolUsed": "terpakai",
-    "codexPoolUntil": "Hingga {value}",
-    "anonymousFallbackTitle": "Fallback anonim",
-    "anonymousFallbackDesc": "Ketika semua koneksi yang dikonfigurasi habis (kuota, kredit, atau masa berlaku), gunakan sementara tingkat tanpa kunci penyedia ini. Matikan untuk melewati penyedia ini alih-alih mengirim permintaan anonim — disarankan ketika tingkat tanpa kunci menolak permintaan tersebut (401).",
-    "anonymousFallbackEnabled": "Fallback anonim diaktifkan untuk {provider}",
-    "anonymousFallbackDisabled": "Fallback anonim dinonaktifkan untuk {provider} — koneksi yang habis akan melewati penyedia ini",
-    "anonymousFallbackUpdateFailed": "Gagal memperbarui pengaturan fallback anonim",
-    "batchDeleteFailed": "Penghapusan batch gagal",
-    "batchDeleteNetworkError": "Kesalahan jaringan saat menghapus batch",
-    "batchUpdateFailed": "Pembaruan batch gagal",
-    "batchUpdateNetworkError": "Kesalahan jaringan selama pembaruan batch",
-    "categoryAudio": "Audio",
-    "categoryCloudAgent": "Agen Cloud",
-    "categoryIde": "IDE",
-    "categoryLocal": "Lokal",
-    "categorySearch": "Cari",
-    "categoryWebCookie": "Kue Web",
-    "claudeExtraUsageBlockingDisabled": "Pemblokiran penggunaan ekstra Claude dinonaktifkan (penggunaan ekstra diizinkan)",
-    "claudeExtraUsageBlockingEnabled": "Pemblokiran penggunaan ekstra Claude diaktifkan (penggunaan ekstra akan diblokir)",
-    "claudeRoutingPreferenceDisabled": "Model Claude tanpa prefiks tidak lagi lebih memilih Claude Code",
-    "claudeRoutingPreferenceEnabled": "Model Claude tanpa prefiks sekarang lebih memilih Claude Code",
-    "clearMediaFilter": "Bersihkan",
-    "cliproxyRoutingDisabled": "Permintaan sekarang menggunakan OmniRoute asli (langsung)",
-    "cliproxyRoutingEnabled": "Permintaan sekarang diarahkan melalui CLIProxyAPI (emulasi yang lebih dalam)",
-    "codexLimitPolicyUpdated": "Kebijakan batas Codex diperbarui",
-    "codexServiceModeUpdated": "Mode layanan Codex diperbarui",
-    "codexServiceTierActive": "Tingkat layanan Codex {tier} aktif",
-    "codexTierFastLabel": "Cepat",
-    "codexTierFlexLabel": "Flex",
-    "commandCodeApplyFailed": "Gagal menerapkan Kode Perintah auth",
-    "commandCodeApplyingApproval": "Browser disetujui, menerapkan…",
-    "commandCodeApplyingKey": "Menerapkan kunci yang disetujui oleh browser…",
-    "commandCodeApprovalInstructions": "Buka URL otorisasi, setujui akses, lalu tempelkan kunci/JSON/URL yang dikembalikan di bawah ini…",
-    "commandCodeAuthExpired": "Kode Perintah auth telah kedaluwarsa",
-    "commandCodeConnected": "Kode Perintah terhubung",
-    "commandCodeConnectionAdded": "Koneksi Kode Perintah ditambahkan",
-    "commandCodeLinkExpired": "Tautan Kode Perintah telah kedaluwarsa",
-    "commandCodeOpeningStudio": "Membuka Command Code Studio…",
-    "commandCodePopupBlocked": "Popup diblokir. Silakan izinkan popup dan coba lagi Command Code Connect.",
-    "commandCodeStartFailed": "Gagal memulai Command Code auth",
-    "connectionDeleted": "Koneksi dihapus",
-    "connectionFallback": "koneksi",
-    "coolingConnectionsDescription": "Koneksi ini mengembalikan 429 (batas-laju) pada permintaan terakhir mereka. OmniRoute akan melewatkan mereka sampai timer berakhir — tidak perlu menonaktifkan secara manual.",
-    "coolingConnectionsTitle": "Saat ini pendinginan ({count})",
-    "failedDeleteAlias": "Gagal menghapus alias",
-    "failedDeleteConnection": "Gagal menghapus koneksi",
-    "failedDistributeProxies": "Gagal untuk mendistribusikan proxy.",
-    "failedSaveModelEndpointSettings": "Gagal menyimpan pengaturan endpoint model",
-    "failedUpdateClaudeExtraUsagePolicy": "Gagal memperbarui kebijakan penggunaan ekstra Claude",
-    "failedUpdateClaudeRoutingPreference": "Gagal memperbarui preferensi routing kode Claude",
-    "failedUpdateCliproxyRouting": "Gagal memperbarui routing CLIProxyAPI",
-    "failedUpdateCodexLimitPolicy": "Gagal memperbarui kebijakan batas Codex",
-    "failedUpdateCodexServiceMode": "Gagal memperbarui mode layanan Codex",
-    "filterByMedia": "Media",
-    "freeBadge": "Gratis",
-    "kimiCodeApiKeyLabel": "Kunci API Kimi Code",
-    "modelTestFailed": "Pengujian model gagal",
-    "modelTestNetworkError": "Kesalahan jaringan menguji model",
-    "networkError": "Kesalahan jaringan",
-    "networkErrorDeletingAlias": "Kesalahan jaringan saat menghapus alias",
-    "networkErrorSettingAlias": "Kesalahan jaringan saat mengatur alias",
-    "noProvidersMatch": "Tidak ada penyedia yang cocok dengan pencarian Anda.",
-    "noSavedProxies": "Tidak ada proxy yang disimpan. Tambahkan proxy di Pengaturan → Proxy terlebih dahulu.",
-    "pageLoadErrorDescription": "Kami tidak dapat memuat data penyedia saat ini. Periksa koneksi Anda dan coba lagi.",
-    "pageLoadErrorId": "ID Kesalahan: {id}",
-    "pageLoadErrorRetry": "Coba Lagi",
-    "pageLoadErrorTitle": "Gagal memuat penyedia",
-    "playgroundTitle": "Tempat Bermain",
-    "providerDetailConnectionFlexActive": "Tingkat layanan Codex flex aktif untuk koneksi ini",
-    "providerDetailConnectionPriorityActive": "Tingkat layanan prioritas Codex aktif untuk koneksi ini",
-    "providerDetailGlobalFlexActive": "Tingkat layanan Global Codex flex aktif",
-    "providerDetailGlobalPriorityActive": "Tingkat layanan prioritas Global Codex aktif",
-    "proxiesDistributed": "Distribusi penugasan proxy {assigned} di seluruh {tagLabel}{total} koneksi.",
-    "rerankEndpoint": "Rerank",
-    "savedModelEndpointSettings": "Pengaturan endpoint model yang disimpan",
-    "searchByModelAria": "Cari berdasarkan model",
-    "selectSupportedEndpoint": "Pilih setidaknya satu endpoint yang didukung",
-    "antigravityClientProfileHarness": "Harness / CLI",
-    "clearConnectionCooldown": "Clear cooldown",
-    "clearConnectionCooldownInProgress": "Clearing…",
-    "clearConnectionCooldownTitle": "Clear the cooldown now — use when the quota has already refreshed upstream",
-    "connectionCooldownCleared": "Cooldown cleared — connection rejoined routing",
-    "failedClearConnectionCooldown": "Failed to clear cooldown"
-  },
-  "settings": {
-    "title": "Settings",
-    "general": "General",
-    "security": "Security",
-    "appearance": "Appearance",
-    "routing": "Routing",
-    "cache": "Cache",
-    "resilience": "Resilience",
-    "description": "Deskripsi",
-    "enable": "Aktifkan",
-    "disable": "Nonaktifkan",
-    "update": "Perbarui",
-    "routingSettingsIntro": "Mengontrol bagaimana permintaan Anda dirutekan, diubah, dan dikirim ke penyedia AI.",
-    "routingOpDropParagraphContainsLabel": "Hapus paragraf (berisi)",
-    "routingOpDropParagraphStartsWithLabel": "Hapus paragraf (dimulai dengan)",
-    "routingOpReplaceTextLabel": "Ganti teks",
-    "routingOpReplaceRegexLabel": "Ganti regex",
-    "routingOpDropBlockContainsLabel": "Hapus blok (berisi)",
-    "routingOpPrependSystemBlockLabel": "Tambahkan blok sistem di awal",
-    "routingOpAppendSystemBlockLabel": "Tambahkan blok sistem di akhir",
-    "routingOpInjectBillingHeaderLabel": "Suntikkan header penagihan",
-    "routingOpObfuscateWordsLabel": "Samarkan kata (ZWJ)",
-    "routingOpDropParagraphContainsDesc": "Menghapus paragraf apa pun (blok teks yang dipisahkan oleh baris kosong) di dalam prompt sistem yang teksnya berisi SALAH SATU dari substring yang terdaftar. Gunakan untuk menghapus sidik jari klien pihak ketiga seperti 'github.com/anomalyco/opencode' atau 'docs.openwebui.com' yang ditandai oleh pengklasifikasi Anthropic.",
-    "routingOpDropParagraphStartsWithDesc": "Menghapus paragraf apa pun yang DIMULAI DENGAN salah satu awalan yang terdaftar. Gunakan untuk baris identitas seperti 'You are OpenCode' atau 'You are Open WebUI' yang mengumumkan klien pemanggil.",
-    "routingOpReplaceTextDesc": "Mengganti substring literal dengan substring literal lainnya. Gunakan untuk frasa pemicu yang diketahui — mis. menulis ulang 'Here is some useful information about the environment you are running in:' menjadi 'Environment context you are running in:' (frasa pemicu yang divalidasi secara empiris).",
-    "routingOpReplaceRegexDesc": "Mengganti teks yang cocok dengan ekspresi reguler. Gunakan saat Anda memerlukan pola (kelas karakter, spasi opsional, jangkar) alih-alih substring literal. Pola yang salah bentuk akan terdeteksi saat runtime ketika operasi dijalankan.",
-    "routingOpDropBlockContainsDesc": "Menghapus SELURUH blok sistem (bukan hanya paragraf) yang teksnya berisi salah satu substring yang terdaftar. Gunakan ketika seluruh blok membawa sidik jari dan Anda ingin menghapusnya — mis. deskripsi server-MCP yang disuntikkan.",
-    "routingOpPrependSystemBlockDesc": "Menyisipkan blok teks baru di BAGIAN DEPAN array sistem. Gunakan untuk menambahkan identitas SDK 'You are a Claude agent, built on Anthropic's Claude Agent SDK.' yang diharapkan oleh pengklasifikasi Anthropic.",
-    "routingOpAppendSystemBlockDesc": "Menyisipkan blok teks baru di BAGIAN AKHIR array sistem. Gunakan untuk tambahan kosmetik yang tidak perlu berada di posisi [0].",
-    "routingOpInjectBillingHeaderDesc": "Menambahkan blok teks khusus 'x-anthropic-billing-header: cc_version=...; cc_entrypoint=...; cch=...;' di awal yang divalidasi oleh pengklasifikasi Anthropic. Diperlukan untuk endpoint relai jembatan CC; untuk penyedia claude asli OmniRoute sudah menyuntikkan baris penagihannya sendiri sehingga operasi ini biasanya mubazir di sana.",
-    "routingOpObfuscateWordsDesc": "Menyisipkan karakter Zero-Width-Joiner setelah huruf pertama dari setiap kata yang terdaftar, sehingga 'opencode' menjadi 'o‍pencode'. Terbaca identik bagi manusia tetapi melewati pencocokan kata pengklasifikasi. Menargetkan blok sistem, pesan pengguna/asisten, dan deskripsi alat.",
-    "routingNeedlesHint": "Daftar substring. Paragraf cocok jika berisi SALAH SATU dari mereka. Tambahkan satu per baris via 'Add entry'.",
-    "routingPrefixesHint": "Daftar string. Paragraf cocok jika dimulai dengan salah satu dari mereka (spasi di awal dipangkas sebelum pencocokan).",
-    "routingCaseSensitiveHint": "Saat AKTIF, 'OpenCode' and 'opencode' adalah string yang berbeda. Saat NONAKTIF (default), perbandingan mengabaikan huruf besar/kecil.",
-    "routingMatchLiteralHint": "Substring literal persis yang ingin dicari. Tanpa sintaks regex — karakter khusus seperti . * ? diperlakukan sebagaimana adanya.",
-    "routingReplacementTextHint": "String pengganti. Biarkan kosong untuk menghapus pencocokan. Output mempertahankan teks di sekitarnya.",
-    "routingAllOccurrencesHint": "Saat AKTIF (default), setiap kemunculan diganti. Saat NONAKTIF, hanya pencocokan pertama yang diganti.",
-    "routingPatternHint": "Sumber regex JavaScript. Jangan dibungkus dengan garis miring — cukup 'foo(.*)bar'. Server menolak pola yang gagal dikompilasi.",
-    "routingRegexFlagsHint": "Bendera regex JavaScript (g = semua pencocokan, i = tidak sensitif huruf besar/kecil, s = titik cocok dengan baris baru, m = multibaris). Default 'g'.",
-    "routingBlockTextHint": "Teks lengkap dari blok sistem baru. Gunakan string literal; blok sistem hanya menyimpan teks.",
-    "routingIdempotencyKeyHint": "Opsional. Jika disetel, operasi dilewati ketika blok yang teksnya dimulai dengan kunci ini sudah ada. Mencegah penambahan ganda di awal pada percobaan ulang.",
-    "routingBillingEntrypointHint": "Nilai yang disuntikkan sebagai 'cc_entrypoint='. Anthropic menerima 'sdk-cli' (Agent SDK), 'cli' (Claude Code CLI), atau nilai terdokumentasi lainnya.",
-    "routingBillingVersionFormatHint": "Bagaimana hash build 3-karakter setelah cc_version= dihitung. 'ex-machina' = sha256 dari CCH_SALT+karakter-dari-pesan-pengguna-pertama+versi (per pesan). 'omniroute-daystamp' = sha256 dari YYYY-MM-DD+versi (stabil per hari).",
-    "routingBillingCchAlgoHint": "Bagaimana token cch= 5-karakter dihitung. 'sha256-first-user' = sha256 dari teks pesan pengguna pertama. 'xxhash64-body' = penandatanganan tingkat bodi mengisinya nanti. 'static-zero' = placeholder literal '00000'.",
-    "routingObfuscateWordsHint": "Kata-kata huruf kecil untuk disamarkan. Penyisipan ZWJ diterapkan tanpa sensitif huruf besar/kecil, sehingga 'opencode' juga cocok dengan 'OpenCode' dan 'OPENCODE'.",
-    "routingObfuscateTargetsHint": "Wilayah bodi mana yang akan dipindai untuk kata-kata tersebut: blok sistem, pesan pengguna/asisten, dan/atau deskripsi alat.",
-    "routingObfuscateTargetsLabel": "Target",
-    "routingSummarizeDropParagraphContains": "buang paragraf yang berisi: {items}",
-    "routingSummarizeDropParagraphStartsWith": "buang paragraf yang dimulai dengan: {items}",
-    "routingSummarizeReplaceText": "ganti \"{match}\" → \"{replacement}\"",
-    "routingSummarizeReplaceRegex": "regex /{pattern}/{flags} → \"{replacement}\"",
-    "routingSummarizeDropBlockContains": "buang blok yang berisi: {items}",
-    "routingSummarizePrependSystemBlock": "tambahkan blok di awal: \"{text}\"",
-    "routingSummarizeAppendSystemBlock": "tambahkan blok di akhir: \"{text}\"",
-    "routingSummarizeInjectBillingHeader": "suntikkan header penagihan (entrypoint={entrypoint}, version={versionFormat}, cch={cchAlgo})",
-    "routingSummarizeObfuscateWords": "samarkan {count} kata via ZWJ di {targets}",
-    "routingDefaultAutoVariantLKGP": "Penyedia Terakhir yang Diketahui Baik",
-    "routingDefaultAutoVariantLKGPDesc": "Penyedia Terakhir yang Diketahui Baik",
-    "routingDefaultAutoVariantCoding": "Kualitas diutamakan untuk kode",
-    "routingDefaultAutoVariantCodingDesc": "Kualitas diutamakan untuk kode",
-    "routingDefaultAutoVariantFast": "Perutean latensi rendah",
-    "routingDefaultAutoVariantFastDesc": "Perutean latensi rendah",
-    "routingDefaultAutoVariantCheap": "Dioptimalkan untuk biaya",
-    "routingDefaultAutoVariantCheapDesc": "Dioptimalkan untuk biaya",
-    "routingDefaultAutoVariantOffline": "Ketersediaan tinggi",
-    "routingDefaultAutoVariantOfflineDesc": "Ketersediaan tinggi",
-    "routingDefaultAutoVariantSmart": "Penemuan terbaik (10% eksplorasi)",
-    "routingDefaultAutoVariantSmartDesc": "Penemuan terbaik (10% eksplorasi)",
-    "routingOpSummaryCount": "{count, plural, =0 {tidak ada op} one {# op} other {# op}}",
-    "routingOpEnabled": "diaktifkan",
-    "routingOpDisabled": "dinonaktifkan",
-    "routingOpStatusSeparator": " ·",
-    "resilienceSettingsIntro": "Percobaan ulang, cooldown, dan fallback otomatis ketika penyedia gagal.",
-    "aiSettingsIntro": "Pengaturan khusus AI untuk memikirkan anggaran, perilaku model, dan kompresi.",
-    "systemPrompt": "System Prompt",
-    "thinkingBudget": "Thinking Budget",
-    "proxy": "Proxy",
-    "httpProxy": "HTTP Proxy",
-    "1proxy": "1proxy",
-    "proxySubTabsAria": "Proxy sections",
-    "requestBodyLimitTitle": "Request Body Limit",
-    "requestBodyLimitDescription": "Maximum API payload size accepted before a request body is parsed. Dedicated upload routes keep at least their built-in 100 MB limit.",
-    "requestBodyLimitInputLabel": "Request body limit in MB",
-    "requestBodyLimitEmptyError": "Enter a limit in MB",
-    "requestBodyLimitWholeNumberError": "Use a whole number",
-    "requestBodyLimitMinimumError": "Minimum is {min} MB",
-    "requestBodyLimitMaximumError": "Maximum is {max} MB",
-    "requestBodyLimitLoadFailed": "Failed to load request limit settings",
-    "requestBodyLimitSaveSuccess": "Request body limit saved",
-    "requestBodyLimitSaveFailed": "Failed to save request body limit",
-    "requestBodyLimitSaving": "Saving...",
-    "requestBodyLimitSave": "Save",
-    "requestBodyLimitCurrent": "Current: {value}",
-    "cacheConfigLoadFailed": "Gagal memuat pengaturan cache",
-    "cacheConfigSaveSuccess": "Pengaturan cache disimpan",
-    "cacheConfigSaveFailed": "Gagal menyimpan pengaturan cache",
-    "modelCatalogTtlWholeNumberError": "Gunakan angka bulat",
-    "modelCatalogTtlMinimumError": "Minimum adalah {min} ms",
-    "modelCatalogTtlMaximumError": "Maksimum adalah {max} ms",
-    "modelCatalogCacheTtl": "Model Catalog Cache TTL",
-    "modelCatalogCacheTtlDescription": "Berapa lama respons katalog model disimpan dalam cache sebelum diperbarui",
-    "modelCatalogCacheTtlLabel": "TTL cache katalog model dalam milidetik",
-    "modelCatalogCacheTtlSaving": "Menyimpan...",
-    "modelCatalogCacheTtlSave": "Simpan",
-    "modelCatalogCacheTtlCurrent": "Saat Ini: {value} ms",
-    "mitmProxy": "Proksi MITM",
-    "pricing": "Pricing",
-    "storage": "Storage",
-    "policies": "Policies",
-    "ipFilter": "IP Filter",
-    "comboDefaults": "Combo Defaults",
-    "fallbackChains": "Fallback Chains",
-    "changePassword": "Change Password",
-    "enablePassword": "Enable Password",
-    "darkMode": "Dark Mode",
-    "lightMode": "Light Mode",
-    "memoryTitle": "Memory",
-    "memoryDesc": "Persistent cross-session conversational memory",
-    "memoryEnabled": "Enable Memory",
-    "memoryEnabledDesc": "When enabled, OmniRoute will inject relevant past context.",
-    "memoryTokenCostWarning": "Perhatian: dengan memori diaktifkan, OmniRoute menyisipkan hingga {tokens} token konteks yang diambil ke dalam setiap permintaan obrolan — ini meningkatkan penggunaan token dan biaya. Untuk melewati penyisipan pada permintaan tertentu, kirim header \"x-omniroute-no-memory: true\".",
-    "maxTokens": "Max Tokens",
-    "retentionDays": "Retention",
-    "recent": "Recent",
-    "recentDesc": "Chronological window",
-    "semantic": "Semantic",
-    "semanticDesc": "Vector search",
-    "hybrid": "Hybrid",
-    "hybridDesc": "Recent + Semantic",
-    "skillsTitle": "Skills",
-    "skillsDesc": "Tools for models",
-    "skillsEnabled": "Enable Skills",
-    "skillsEnabledDesc": "Allows agents to trigger functions.",
-    "skillsComingSoon": "Skills marketplace coming soon.",
-    "memorySkillsTitle": "Memory & Skills",
-    "memorySkillsDesc": "Persistent context & capabilities",
-    "modelsDevTitle": "Model Database",
-    "modelsDevDesc": "Auto-sync pricing, capabilities & specs from models.dev",
-    "modelsDevEnabled": "Enable models.dev Sync",
-    "modelsDevEnabledDesc": "Fetch model pricing, capabilities, and specs from the open-source models.dev database",
-    "modelsDevInterval": "Sync Interval",
-    "syncNow": "Sync Now",
-    "syncing": "Syncing...",
-    "lastSync": "Last sync",
-    "never": "Never",
-    "justNow": "Just now",
-    "modelsDevStats": "Sync Statistics",
-    "modelsDevStatsDesc": "Current models.dev data coverage",
-    "providers": "Providers",
-    "modelsWithPricing": "Models with Pricing",
-    "capabilities": "Capabilities",
-    "lastSyncCount": "Last Sync Count",
-    "lastSyncFull": "Last full sync",
-    "modelsDevInfo": "How It Works",
-    "modelsDevInfoDesc": "models.dev is an open-source database of AI model specifications maintained by the SST/OpenCode team. It provides pricing, capabilities, context limits, and modalities for 4,000+ models across 100+ providers.",
-    "modelsDevInfoResolution": "Pricing resolution order (highest priority first):",
-    "modelsDevInfoOrder": "User Override → models.dev → LiteLLM → Hardcoded Default",
-    "systemTheme": "System Theme",
-    "debugToggle": "Enable Debug Mode",
-    "logToolSourcesToggle": "Log Sumber Alat",
-    "logToolSourcesDescription": "Hasilkan baris log diagnostik per permintaan yang merangkum jumlah alat dan rincian sumber MCP/dihosting/klien.",
-    "homePinProviderQuotaToHome": "Pin Information to Home Page",
-    "homePinnedSectionsDesc": "Pilih bagian mana yang ingin disematkan ke bagian atas halaman Beranda.",
-    "homeProviderQuotaLimits": "Provider Quota Limits",
-    "homeProviderQuotaLimitsDesc": "Pin the Provider Quota status container (with Refresh All button) to the top of the Home page.",
-    "homeQuickStart": "Quick Start",
-    "homeQuickStartDesc": "Show the Quick Start panel on the Home page.",
-    "homeProviderTopology": "Provider Topology",
-    "homeProviderTopologyDesc": "Show the Provider Topology on the Home page.",
-    "accountEmailVisibility": "Visibilitas email akun",
-    "accountEmailVisibilityDesc": "Tampilkan email akun lengkap di seluruh layar penyedia, kombo, log, kuota, dan playground. Nonaktifkan ini untuk menyamarkannya secara default.",
-    "comboConfigMode": "Mode konfigurasi kombo",
-    "comboConfigModeDesc": "Pilih bagaimana dialog pembuatan dan pengeditan kombo diatur.",
-    "comboConfigModeGuided": "Terpandu",
-    "comboConfigModeGuidedDesc": "Gunakan pembuat kombo langkah-demi-langkah saat ini.",
-    "comboConfigModeExpert": "Pakar",
-    "comboConfigModeExpertDesc": "Tampilkan setiap opsi kombo pada satu halaman dan aktifkan entri model langsung.",
-    "providerQuotaAutoRefresh": "Penyegaran otomatis Kuota Penyedia",
-    "providerQuotaAutoRefreshDesc": "Segarkan tampilan Batasan Penyedia secara otomatis saat tetap terbuka.",
-    "providerQuotaAutoRefreshToggle": "Penyegaran otomatis",
-    "providerQuotaAutoRefreshToggleDesc": "Segarkan tampilan kuota setiap beberapa menit saat halaman terlihat.",
-    "providerQuotaAutoRefreshInterval": "Interval penyegaran",
-    "providerQuotaAutoRefreshIntervalDesc": "Seberapa sering tampilan kuota harus disegarkan, dalam detik.",
-    "seconds": "detik",
-    "sidebarVisibilityToggle": "Show Sidebar Items",
-    "enableCache": "Enable Cache",
-    "cacheTTL": "Cache TTL",
-    "maxCacheSize": "Max Cache Size",
-    "clearCache": "Clear Cache",
-    "cacheCleared": "Cache cleared successfully",
-    "clearCacheFailed": "Failed to clear cache",
-    "cacheHits": "Cache Hits",
-    "cacheMisses": "Cache Misses",
-    "hitRate": "Hit Rate",
-    "cacheEntries": "Cache Entries",
-    "cacheSettings": "Cache Settings",
-    "semanticCache": "Semantic Cache",
-    "maxEntries": "Max Entries",
-    "ttlMinutes": "TTL (minutes)",
-    "promptCache": "Prompt Cache",
-    "strategy": "Strategy",
-    "preserveClientCache": "Preserve Client Cache",
-    "enabled": "Enabled",
-    "loading": "Loading...",
-    "saving": "Saving...",
-    "save": "Save",
-    "circuitBreaker": "Circuit Breaker",
-    "retryPolicy": "Retry Policy",
-    "maxRetries": "Max Retries",
-    "retryDelay": "Retry Delay",
-    "timeoutMs": "Timeout (ms)",
-    "enableSystemPrompt": "Enable System Prompt",
-    "systemPromptText": "System Prompt Text",
-    "autoDisableBannedAccounts": "Auto-Disable Banned Accounts",
-    "autoDisableDescription": "Permanently mark provider connections as deactivated if they return specific terminal ban signals (e.g. HTTP 403 'verify your account'). This removes them from the combo rotation.",
-    "autoDisableThreshold": "Ban Threshold",
-    "autoDisableThresholdDesc": "Consecutive ban signals required before permanent deactivation.",
-    "autoDisableBannedScope": "Apply auto-disable to",
-    "autoDisableBannedScopeDesc": "Login seats (paid subscriptions and free accounts) can be locked by the upstream if OmniRoute keeps retrying after a ban. Paid prepaid API keys do not have that risk — leave them in the pool so fill-first can use the next key.",
-    "autoDisableBannedScopeAll": "All connections",
-    "autoDisableBannedScopeAllDesc": "Deactivate every connection that returns a permanent ban signal, including prepaid API keys.",
-    "autoDisableBannedScopeSubscription": "Login / subscription accounts only",
-    "autoDisableBannedScopeSubscriptionDesc": "Deactivate OAuth, cookie, session, and web-login seats (paid or free). Prepaid API keys stay active so routing can fail over.",
-    "customBannedSignals": "Kata Kunci yang Dilarang",
-    "customBannedSignalsDesc": "Kata kunci tambahan yang memicu deteksi pemblokiran akun permanen. Kata kunci bawaan selalu berlaku.",
-    "customBannedSignalsPlaceholder": "mis. api key revoked",
-    "noCustomBannedSignals": "Tidak ada kata kunci kustom. Hanya kata kunci bawaan yang aktif.",
-    "resilienceStructureTitle": "Resilience Structure",
-    "resilienceStructureDesc": "Halaman ini hanya mengonfigurasi perilaku. Status pemutusan langsung ditampilkan di halaman Kesehatan. Percobaan ulang khusus kombo dan kontrol slot round-robin tetap pada pengaturan kombo.",
-    "enableThinking": "Enable Thinking",
-    "maxThinkingTokens": "Max Thinking Tokens",
-    "enableProxy": "Enable Proxy",
-    "perKeyProxyEnabled": "Aktifkan penetapan proksi per-kunci",
-    "perKeyProxyEnabledDesc": "Jika diaktifkan, setiap koneksi penyedia dapat menggunakan penetapan proksinya sendiri",
-    "proxyUrl": "Proxy URL",
-    "pricingRates": "Pricing Rates Format",
-    "currentPricing": "Current Pricing Overview",
-    "loadingPricing": "Loading pricing data...",
-    "noPricing": "No pricing data available",
-    "input": "Input",
-    "output": "Output",
-    "cached": "Cached",
-    "reasoning": "Reasoning",
-    "cacheCreation": "Cache Creation",
-    "customPricing": "Custom Pricing",
-    "databaseSize": "Database Size",
-    "backupDb": "Backup Database",
-    "restoreDb": "Restore Database",
-    "exportData": "Export Data",
-    "importData": "Import Data",
-    "clearData": "Clear All Data",
-    "clearDataConfirm": "This will permanently delete all data. Are you sure?",
-    "enableRequestLogs": "Enable Request Logs",
-    "logRetention": "Log Retention",
-    "ipWhitelist": "IP Whitelist",
-    "ipBlacklist": "IP Blacklist",
-    "addIP": "Add IP",
-    "savedSuccessfully": "Settings saved successfully",
-    "ai": "AI",
-    "advanced": "Advanced",
-    "localMode": "Local Mode — All data stored on your machine",
-    "settingsSectionsAria": "Settings sections",
-    "switchThemes": "Switch between light and dark themes",
-    "themeSelectionAria": "Theme selection",
-    "themeLight": "Light",
-    "themeDark": "Dark",
-    "themeSystem": "System",
-    "endpointTunnelVisibility": "Visibilitas terowongan titik akhir",
-    "endpointTunnelVisibilityDesc": "Sembunyikan kontrol terowongan dari halaman Titik Akhir tanpa mengubah status terowongan.",
-    "showCloudflareTunnel": "Terowongan Cepat Cloudflare",
-    "showCloudflareTunnelDesc": "Tampilkan kontrol Cloudflare Quick Tunnel di halaman Endpoint.",
-    "showTailscaleFunnel": "Corong Sisik Ekor",
-    "showTailscaleFunnelDesc": "Tampilkan kontrol Corong Tailscale di halaman Titik Akhir.",
-    "showNgrokTunnel": "Terowongan ngrok",
-    "showNgrokTunnelDesc": "Tampilkan kontrol Terowongan ngrok di halaman Titik Akhir.",
-    "sidebarVisibility": "Hide sidebar items",
-    "sidebarVisibilityDesc": "Hide any sidebar navigation entry to reduce visual clutter without disabling any features",
-    "sidebarVisibilityHint": "Any sidebar section is hidden automatically when all of its entries are hidden",
-    "presetAll": "All",
-    "presetAllDesc": "Show everything",
-    "presetEssentials": "Essentials",
-    "presetEssentialsDesc": "Beginner path - Advanced tools stay searchable",
-    "presetMinimal": "Minimal",
-    "presetMinimalDesc": "Core pages only",
-    "presetDeveloper": "Developer",
-    "presetDeveloperDesc": "Dev & proxy tools",
-    "presetAdmin": "Admin",
-    "presetAdminDesc": "Monitoring & audit",
-    "settingsSidebarTitle": "Sidebar Customization",
-    "settingsSidebarDesc": "Choose which sidebar items to show. Essentials keeps Advanced tools searchable.",
-    "hideHealthLogs": "Hide Health Check Logs",
-    "hideHealthLogsDesc": "When ON, suppress [HealthCheck] messages in server console",
-    "themeAccent": "Theme color",
-    "themeAccentDesc": "Choose a preset color or create your own theme with one color",
-    "themeCreate": "Create theme",
-    "themeCustom": "Custom theme",
-    "themeBlue": "Blue",
-    "themeRed": "Red",
-    "themeGreen": "Green",
-    "themeViolet": "Violet",
-    "themeOrange": "Orange",
-    "themeCyan": "Cyan",
-    "whitelabeling": "Branding",
-    "whitelabelingDesc": "Customize the application name and logo",
-    "appName": "Application Name",
-    "appNameDesc": "Display name shown in sidebar and browser tab",
-    "customLogo": "Custom Logo URL",
-    "customLogoDesc": "URL to your custom logo image",
-    "uploadLogo": "Upload Logo",
-    "resetLogo": "Reset to Default",
-    "logoPreview": "Preview",
-    "customFavicon": "Browser Favicon",
-    "customFaviconDesc": "URL to your custom favicon (shown in browser tab)",
-    "uploadFavicon": "Upload Favicon",
-    "resetFavicon": "Reset Favicon",
-    "faviconPreview": "Favicon Preview",
-    "logoFileTooLarge": "Berkas logo harus berukuran kurang dari 500KB",
-    "faviconFileTooLarge": "Berkas favicon harus berukuran kurang dari 50KB",
-    "invalidLogoFileType": "Tipe berkas tidak valid. Silakan unggah PNG, JPG, SVG, GIF, atau WebP.",
-    "invalidFaviconFileType": "Tipe berkas tidak valid. Silakan unggah PNG, ICO, SVG, GIF, or WebP.",
-    "failedToReadFile": "Gagal membaca berkas",
-    "startOnLogin": "Mulai saat Login",
-    "startOnLoginDesc": "Luncurkan OmniRoute secara otomatis saat sistem dinyalakan dan jalankan secara diam-diam di baki latar belakang.",
-    "flushCache": "Flush Cache",
-    "flushing": "Flushing…",
-    "size": "Size",
-    "hits": "Hits",
-    "evictions": "Evictions",
-    "loadingCacheStats": "Loading cache stats…",
-    "globalProxy": "Global Proxy",
-    "globalProxyDesc": "Configure a global outbound proxy for all API calls. Individual providers, combos, and keys can override this.",
-    "noGlobalProxy": "No global proxy configured",
-    "proxyPool": "Kumpulan Proksi",
-    "freePool": "Kumpulan Gratis",
-    "proxyDocumentation": "Dokumentasi Proksi",
-    "proxyGlobalConfigTab": "Konfigurasi Global",
-    "proxyPoolTab": "Kumpulan Proksi",
-    "freePoolTab": "Pool Gratis",
-    "proxyDocumentationTab": "Dokumentasi",
-    "proxySubscriptionsTab": "Langganan",
-    "proxySubscription": {
-      "error": {
-        "LOCAL_CORE_ENDPOINT_INVALID": "Titik akhir proxy-core lokal tidak sahih; node SS/VMess/Trojan/VLESS diabaikan.",
-        "NEEDS_CORE_NOT_CONFIGURED": "Langganan ini memiliki node yang memerlukan core proxy lokal (SS/VMess/Trojan/VLESS); mereka tidak dirutekan hingga Anda mengonfigurasi titik akhir SOCKS5 core-lokal.",
-        "NO_USABLE_NODES": "Langganan tidak menghasilkan node yang dapat digunakan (http/https/socks5 atau node dengan titik akhir core lokal)."
-      },
-      "description": "Tempelkan tautan berlangganan proksi Anda. Setelah diaktifkan, lalu lintas dirutekan melalui kumpulan proksi dalam mode global atau aturan (Penyedia tertentu). Node langganan secara otomatis disinkronkan ke kumpulan proksi dan menggunakan kembali mekanisme polling, pemeriksaan kesehatan, dan anti-kebocoran yang ada.",
-      "addSubscription": "Tambahkan Langganan",
-      "newSubscription": "Tambahkan Langganan",
-      "editSubscription": "Sunting Langganan",
-      "name": "Nama",
-      "namePlaceholder": "misalnya Langganan Saya A",
-      "url": "URL langganan",
-      "urlPlaceholder": "https://.../berlangganan?token=...",
-      "mode": "Modus",
-      "globalMode": "Modus Global",
-      "ruleMode": "Modus Aturan",
-      "globalModeDesc": "Semua lalu lintas Penyedia melewati kumpulan proksi langganan ini.",
-      "ruleModeDesc": "Hanya lalu lintas Penyedia terpilih yang melewati proxy; sisanya terhubung langsung.",
-      "localCoreEndpoint": "Titik Akhir SOCKS5/HTTP Inti Lokal (Opsional)",
-      "localCoreEndpointPlaceholder": "kaus kaki5://127.0.0.1:1080",
-      "localCoreEndpointDesc": "Hanya menerima 127.0.0.1 / localhost (SS/VMess/Trojan/VLESS memerlukan inti sing-box/clash lokal).",
-      "routeByProvider": "Rute berdasarkan Penyedia (pilihan banyak)",
-      "loadingProviders": "Memuat daftar Penyedia…",
-      "autoRefreshInterval": "Interval Penyegaran Otomatis (menit)",
-      "enableAfterCreate": "Aktifkan saat pembuatan (sinkronkan dan segera terapkan)",
-      "saving": "Menyimpan…",
-      "saveChanges": "Simpan Perubahan",
-      "createSubscription": "Buat Langganan",
-      "loading": "Memuat…",
-      "noSubscriptions": "Belum ada langganan. Klik \"Tambahkan Langganan\" untuk memulai.",
-      "statusOk": "Oke",
-      "statusError": "Kesalahan",
-      "statusEmpty": "Kosong",
-      "global": "Global",
-      "rule": "Aturan",
-      "enabled": "Diaktifkan",
-      "disabled": "Dengan disabilitas",
-      "nodeCount": "Node: {count}",
-      "needsCoreCount": "{count} membutuhkan inti lokal",
-      "lastSynced": "Terakhir disinkronkan: {time}",
-      "consecutiveFailures": "{count} kegagalan berturut-turut",
-      "lastError": "Kesalahan terakhir: {time}",
-      "coreHintTitle": "Langganan ini memiliki {count} node yang memerlukan inti proxy lokal (SS/VMess/Trojan/VLESS, dll.) dan saat ini tidak dirutekan.",
-      "coreHintDesc": "Protokol ini tidak dapat diteruskan secara langsung oleh OmniRoute. Silakan mulai inti sing-box atau Clash (Clash.Meta) di mesin Anda, ekspos sebagai titik akhir SOCKS5/HTTP, dan isi melalui Edit (hanya 127.0.0.1 / localhost yang diterima).",
-      "copy": "Salin",
-      "goConfigure": "Konfigurasikan",
-      "disable": "Nonaktifkan",
-      "enable": "Aktifkan",
-      "refreshNodes": "Segarkan Node",
-      "edit": "Sunting",
-      "delete": "Hapus",
-      "confirmDelete": "Apakah Anda yakin ingin menghapus langganan \"{name}\"? Node proxy terkait juga akan dihapus.",
-      "nameRequired": "Silakan masukkan nama",
-      "urlRequired": "Silakan masukkan URL langganan",
-      "ruleModeProviderRequired": "Harap pilih setidaknya satu Penyedia dalam mode aturan",
-      "saveFailed": "Gagal menyimpan",
-      "loadFailed": "Gagal memuat daftar langganan",
-      "toggleFailed": "Gagal mengalihkan tombol",
-      "refreshFailed": "Gagal menyegarkan",
-      "deleteFailed": "Gagal menghapus",
-      "add": "Tambahkan",
-      "cancel": "Batalkan",
-      "configure": "Konfigurasi",
-      "copyEndpoint": "Salin Endpoint",
-      "coreEndpointHint": "Petunjuk Endpoint Inti",
-      "coreNodesHint": "Petunjuk Node Inti",
-      "create": "Buat",
-      "deleteConfirm": "Hapus Konfirmasi",
-      "empty": "Kosong",
-      "globalModeDescription": "Deskripsi Mode Global",
-      "localCoreHint": "Petunjuk Inti Lokal",
-      "nodeSummary": "Ringkasan Node",
-      "providerRequired": "Penyedia Diperlukan",
-      "providerRouting": "Routing Penyedia",
-      "refresh": "Segarkan",
-      "refreshInterval": "Interval Penyegaran",
-      "ruleModeDescription": "Deskripsi Mode Aturan"
-    },
-    "bulkHealthcheck": "Bulk Healthcheck",
-    "bulkHealthcheckDesc": "Test all configured proxies against a target URL to find which ones work.",
-    "healthcheckTesting": "Testing...",
-    "healthcheckAll": "Healthcheck All",
-    "healthcheckFailed": "Failed to run healthcheck",
-    "healthcheckTestingAll": "Testing all proxies in parallel...",
-    "healthcheckTotal": "Total",
-    "healthcheckWorking": "Working",
-    "healthcheckFailedLabel": "Failed",
-    "healthcheckStatus": "Status",
-    "healthcheckProxyUrl": "Proxy URL",
-    "healthcheckLatency": "Latency",
-    "proxyDocumentationScopeTitle": "Resolusi cakupan proksi",
-    "proxyDocumentationScopeDescBefore": "OmniRoute menyelesaikan proksi keluar dalam urutan prioritas:",
-    "proxyDocumentationScopeOrder": "combo → account → provider → global",
-    "proxyDocumentationScopeDescAfter": ". Cakupan yang paling spesifik yang menang.",
-    "proxyDocumentationAddTitle": "Menambahkan proksi kustom",
-    "proxyDocumentationAddDescBefore": "Buka",
-    "proxyDocumentationAddDescMiddle": "tab → klik",
-    "proxyDocumentationAddCta": "+ Tambah proksi",
-    "proxyDocumentationAddDescAfter": ". Isi tipe (http/https/socks5), host, dan port. Secara opsional tetapkan ke suatu cakupan.",
-    "proxyDocumentationBulkTitle": "Format impor massal",
-    "proxyDocumentationBulkDesc": "Kolom dipisahkan dengan pipa:",
-    "proxyDocumentationSocks5DescBefore": "Proksi SOCKS5 dinonaktifkan secara baku. Atur",
-    "proxyDocumentationFreePoolDesc": "Tab Pool Gratis menggabungkan proksi dari 1proxy, Proxifly, and IPLocate. Gunakan ⊕ untuk menguji dan mempromosikan proksi ke registri Anda. Hanya proksi yang lolos uji konektivitas yang akan ditambahkan.",
-    "proxyDocumentationVercelRelayDescBefore": "Relay Vercel adalah relay edge keluar — bukan terowongan masuk (inbound tunnel). Menerapkannya akan mengirimkan panggilan API LLM melalui IP dinamis Vercel, melewati pemblokiran geografis pusat data dan batas laju. Relay ini dilindungi oleh header rahasia yang dihasilkan",
-    "proxyDocumentationVercelRelayDescAfter": "Token Vercel Anda hanya digunakan selama penerapan dan tidak pernah disimpan.",
-    "vercelRelayTokenRequired": "Token diperlukan",
-    "vercelRelayDeployFailed": "Penerapan gagal",
-    "vercelRelayTokenHint": "Token hanya digunakan selama penerapan — tidak pernah disimpan.",
-    "denoRelayTokenRequired": "Token Deno Deploy diperlukan",
-    "denoRelayOrgDomainRequired": "Domain organisasi diperlukan",
-    "denoRelayDeployFailed": "Deno Deploy gagal",
-    "denoRelayTokenHint": "Token organisasi (awalan ddo_) dari console.deno.com → Organization → Settings → Organization Tokens. Digunakan sekali untuk penerapan dan tidak pernah disimpan.",
-    "denoRelayOrgDomainHint": "Domain baku organisasi Deno Deploy Anda (mis. acme.deno.net). Relay akan dapat diakses di https://&lt;app-name&gt;.&lt;org-slug&gt;.deno.net.",
-    "proxyFreePoolFilterProtocol": "Saring berdasarkan protokol",
-    "proxyFreePoolProtocol": "Protokol",
-    "proxyFreePoolCountryPlaceholder": "Negara (mis. US)",
-    "proxyFreePoolFilterCountry": "Saring berdasarkan negara",
-    "proxyFreePoolMinQualityPlaceholder": "Kualitas min",
-    "proxyFreePoolMinQualityLabel": "Skor kualitas minimum",
-    "proxyFreePoolSyncAll": "Sinkronkan Semua",
-    "proxyFreePoolTotal": "Total",
-    "proxyFreePoolInPool": "Dalam pool",
-    "proxyFreePoolAvgQuality": "Kualitas rata-rata",
-    "proxyFreePoolSelected": "{count} terpilih",
-    "proxyFreePoolAddSelected": "Tambahkan yang terpilih ke pool",
-    "proxyFreePoolAddVisible": "Tambahkan semua yang terlihat ke pool",
-    "proxyFreePoolSource": "Sumber",
-    "proxyFreePoolHostPort": "Host:Port",
-    "proxyFreePoolType": "Jenis",
-    "proxyFreePoolCountry": "Negara",
-    "proxyFreePoolQuality": "Kualitas",
-    "proxyFreePoolLatency": "Latensi",
-    "proxyFreePoolEmpty": "Proksi tidak ditemukan. Klik Sinkronkan Semua untuk mengambil dari sumber.",
-    "proxyToggleSources": "Alihkan sumber proksi",
-    "proxyFreePoolTesting": "Menguji proksi...",
-    "proxyFreePoolBulkResult": "{succeeded} ditambahkan, {failed} gagal",
-    "proxyFreePoolPageSummary": "Halaman {page} dari {totalPages} (total {total} proksi)",
-    "proxyFreePoolTotalSummary": "Total {total} proksi",
-    "proxyFreePoolSearchPlaceholder": "Cari host…",
-    "proxyFreePoolSearchLabel": "Cari proksi berdasarkan host",
-    "proxyFreePoolSortLabel": "Urutkan proksi",
-    "proxyFreePoolSortQuality": "Kualitas",
-    "proxyFreePoolSortLatency": "Latensi",
-    "proxyFreePoolSortRecent": "Baru saja divalidasi",
-    "proxyFreePoolListTotal": "Terdaftar",
-    "proxyFreePoolLoadMore": "Muat lebih banyak",
-    "close": "Tutup",
-    "cancel": "Batal",
-    "globalLabel": "Global",
-    "configure": "Configure",
-    "globalSystemPrompt": "Global System Prompt",
-    "saved": "Saved",
-    "beforePromptLabel": "Sebelum Prompt",
-    "beforePromptDesc": "Disisipkan sebelum instruksi sistem agen/penyedia",
-    "beforePromptPlaceholder": "Instruksi disisipkan sebelum prompt agen/penyedia...",
-    "afterPromptLabel": "Setelah Prompt",
-    "afterPromptDesc": "Disisipkan setelah instruksi sistem agen/penyedia",
-    "afterPromptPlaceholder": "Instruksi disisipkan setelah prompt agen/penyedia...",
-    "chars": "{count} chars",
-    "thinkingBudgetTitle": "Thinking Budget",
-    "thinkingBudgetDesc": "Control AI reasoning token usage across all requests",
-    "thinkingBudgetIndependenceHint": "Fitur kompresi, pengalihan, dan batas-token terus berfungsi di setiap mode. Auto tidak berarti \"auto-show thinking\" — itu menghapus bidang penalaran klien.",
-    "passthrough": "Passthrough",
-    "passthroughDesc": "No changes — client controls thinking budget",
-    "thinkingModePassthrough": "Lewati",
-    "thinkingModePassthroughDesc": "Biarkan alasan klien tidak berubah (usaha, ringkasan, blok pemikiran). Diperlukan untuk pemikiran terlihat Codex/Desktop. Default.",
-    "thinkingModeAuto": "Auto (strip)",
-    "thinkingModeAutoDesc": "Hapus semua bidang pemikiran/alasan klien (reasoning, reasoning_effort, Claude thinking, Gemini thinking_config) dan biarkan penyedia menciptakan default. Dapat menyembunyikan panel pemikiran dan memutuskan permintaan ringkasan klien.",
-    "thinkingModeCustom": "Kustom",
-    "thinkingModeCustomDesc": "Timpakan setiap permintaan dengan anggaran token pemikiran tetap yang Anda tetapkan di bawah ini.",
-    "thinkingModeAdaptive": "Adaptif",
-    "thinkingModeAdaptiveDesc": "Skala anggaran pemikiran dari upaya dasar menggunakan jumlah pesan, alat, dan panjang prompt.",
-    "auto": "Auto Combo",
-    "autoDesc": "Self-healing smart routing pool (Performance optimized)",
-    "custom": "Custom",
-    "customDesc": "Set a fixed token budget for all requests",
-    "adaptive": "Adaptive",
-    "adaptiveDesc": "Scale budget based on request complexity",
-    "effortNone": "None (0 tokens)",
-    "effortLow": "Low (1K tokens)",
-    "effortMedium": "Medium (10K tokens)",
-    "effortHigh": "High (128K tokens)",
-    "tokenBudget": "Token Budget",
-    "tokens": "tokens",
-    "baseEffortLevel": "Base Effort Level",
-    "adaptiveHint": "Adaptive mode scales from this base level based on message count, tool usage, and prompt length.",
-    "requireLogin": "Require login",
-    "requireLoginDesc": "When ON, dashboard requires password. When OFF, access without login.",
-    "currentPassword": "Current Password",
-    "enterCurrentPassword": "Enter current password",
-    "newPassword": "New Password",
-    "enterNewPassword": "Enter new password",
-    "confirmPassword": "Confirm New Password",
-    "confirmPasswordPlaceholder": "Confirm new password",
-    "passwordsNoMatch": "Passwords do not match",
-    "passwordUpdated": "Password updated successfully",
-    "failedUpdatePassword": "Failed to update password",
-    "errorOccurred": "An error occurred",
-    "updatePassword": "Update Password",
-    "setPassword": "Set Password",
-    "apiEndpointProtection": "API Endpoint Protection",
-    "requireAuthModels": "Require API key for /models",
-    "requireAuthModelsDesc": "When ON, the /v1/models endpoint returns 404 for unauthenticated requests. Prevents model discovery by unauthorized users.",
-    "authModelHeading": "Model otorisasi aktif",
-    "authModelClient": "Titik akhir API klien (/v1/*, /chat/*, /responses/*, /codex/*, /messages/*) memerlukan kunci API Pembawa.",
-    "authModelManagement": "Titik akhir manajemen (/dashboard, /api/*) memerlukan sesi dasbor atau kredensial manajemen.",
-    "authModelPublic": "Hanya rute login, kesehatan, dan bootstrap yang bersifat publik.",
-    "bruteForceProtection": "Masuk perlindungan brute force",
-    "bruteForceProtectionDesc": "Batasi dan kunci /api/auth/login setelah kegagalan berulang kali dari IP yang sama.",
-    "corsAllowedOrigins": "CORS mengizinkan asal",
-    "corsAllowedOriginsDesc": "Daftar asal browser yang dipisahkan koma diizinkan untuk memanggil server ini. Daftar kosong = tidak ada akses CORS browser (server-ke-server masih berfungsi). Gunakan CORS_ALLOW_ALL=true env var hanya untuk pengembangan.",
-    "blockedProviders": "Blocked Providers",
-    "blockedProvidersDesc": "Hide specific providers from the /v1/models response. Blocked providers will not appear in model listings.",
-    "providersBlocked": "{count} provider(s) blocked from /models",
-    "blockProviderTitle": "Block {provider}",
-    "unblockProviderTitle": "Unblock {provider}",
-    "cliFingerprint": "CLI Fingerprint Matching",
-    "cliFingerprintDesc": "Match native CLI binary signatures when proxying requests. Reorders headers and body fields to look identical to the official CLI tools. Your proxy IP is preserved.",
-    "cliFingerprintEnabled": "{count} provider(s) with CLI fingerprint active",
-    "enableFingerprintTitle": "Enable fingerprint for {provider}",
-    "disableFingerprintTitle": "Disable fingerprint for {provider}",
-    "systemTransforms": "Alur Transformasi Blok Sistem",
-    "systemTransformsDesc": "Alur transformasi yang dipesan per penyedia diterapkan ke isi permintaan sebelum meneruskan. Mendukung ID penyedia apa pun.",
-    "systemTransformsAddProvider": "Tambahkan penyedia",
-    "systemTransformsAddProviderPlaceholder": "Pilih penyedia…",
-    "systemTransformsAddProviderAllConfigured": "Semua penyedia sudah dikonfigurasi",
-    "systemTransformsRemoveProvider": "Hapus penyedia",
-    "systemTransformsNoProviders": "Tidak ada penyedia yang dikonfigurasi. Tambahkan penyedia untuk memulai.",
-    "systemTransformsOpMoveUp": "Naik",
-    "systemTransformsOpMoveDown": "Pindah ke bawah",
-    "systemTransformsOpDelete": "Hapus operasi",
-    "routingStrategy": "Routing Strategy",
-    "routingAdvancedGuideTitle": "Advanced routing guidance",
-    "routingAdvancedGuideHint1": "Use Fill First for predictable priority, Round Robin for fairness, and P2C for latency resilience.",
-    "routingAdvancedGuideHint2": "If providers vary in quality/cost, start with Cost Opt for background work and Least Used for balanced wear.",
-    "fillFirst": "Fill First",
-    "fillFirstDesc": "Use accounts in priority order",
-    "roundRobin": "Round Robin",
-    "roundRobinDesc": "Cycle through all accounts",
-    "p2c": "P2C",
-    "p2cDesc": "Pick 2 random, use the healthier one",
-    "random": "Random",
-    "randomDesc": "Random account each request",
-    "leastUsed": "Least Used",
-    "leastUsedDesc": "Pick least recently used account",
-    "costOpt": "Cost Opt",
-    "costOptDesc": "Prefer cheapest available account",
-    "resetAware": "RR Sadar Reset",
-    "resetAwareDesc": "Lebih suka akun dengan sisa kuota yang sehat dan hampir disetel ulang",
-    "strictRandom": "Strict Random",
-    "strictRandomDesc": "Shuffle deck — uses each account once before reshuffling",
-    "stickyLimit": "Sticky Limit",
-    "stickyLimitDesc": "Calls per account before switching",
-    "routingStrategyTitle": "Strategi Perutean",
-    "routingStrategySubtitle": "Sesuaikan dengan 9router: akun round-robin, batas sticky, dan rotasi kombo",
-    "accountRoundRobin": "Round Robin",
-    "accountRoundRobinDesc": "Gilir akun untuk mendistribusikan beban",
-    "comboRoundRobin": "Round Robin Kombo",
-    "comboRoundRobinDesc": "Gilir target kombo alih-alih selalu memulai dari yang pertama",
-    "comboStickyLimit": "Batas Sticky Kombo",
-    "comboStickyLimitDesc": "Panggilan per target kombo sebelum beralih",
-    "routingStrategyAccountSummary": "Mendistribusikan permintaan ke seluruh akun dengan {limit} panggilan per akun.",
-    "routingStrategyFillFirstSummary": "Menggunakan akun dalam urutan prioritas (Isi Dahulu).",
-    "routingStrategyComboSummary": " Kombo berotasi setelah {limit} panggilan per target.",
-    "routingStrategyComboFallbackSummary": " Kombo menggunakan strategi terkonfigurasi dari masing-masing kombo (prioritas/cadangan default).",
-    "providerAccountRoutingTitle": "Perutean multi-akun",
-    "providerAccountRoutingDesc": "Kesampingkan strategi akun global untuk penyedia ini (paritas 9router).",
-    "providerRoutingStrategy": "Strategi akun",
-    "providerRoutingInheritGlobal": "Warisi bawaan global",
-    "quotaPreflightTitle": "Quota Preflight Cutoff",
-    "quotaPreflightSubtitle": "Skip accounts that are out of quota before sending the request upstream",
-    "quotaPreflightEnable": "Enable quota preflight",
-    "quotaPreflightEnableDesc": "Before each request, check the account's remaining quota (5h / weekly / monthly windows). Accounts at or below the cutoff are skipped without an upstream call. Per-window cutoffs set on the Provider Quota page always win over the default here.",
-    "quotaPreflightCutoff": "Global cutoff (min remaining %)",
-    "quotaPreflightCutoffDesc": "Stop using an account when its remaining quota drops to this percent or below, for every window without its own cutoff. Matches the remaining-% bars on the Provider Quota page.",
-    "quotaPreflightWindowsHint": "Windows with their own per-window or per-provider cutoff (set in the Cutoff modal on the Provider Quota page) are unaffected by this default.",
-    "quotaPreflightLoadFailed": "Unable to load quota preflight settings.",
-    "modelAliases": "Model Aliases",
-    "modelAliasesTitle": "Model Aliases",
-    "modelAliasesDesc": "Remap model names using exact matches or wildcard patterns.",
-    "addCustomAlias": "Add Custom Alias",
-    "deprecatedModelId": "Deprecated model ID",
-    "newModelId": "New model ID",
-    "customAliases": "Custom Aliases",
-    "builtInAliases": "Built-in Aliases",
-    "backgroundDegradationTitle": "Background Task Degradation",
-    "backgroundDegradationDesc": "Auto-detect background tasks (titles, summaries) and route to cheaper models",
-    "enableDegradation": "Enable Background Degradation",
-    "enableDegradationHint": "When enabled, background tasks like title generation and summarization are routed to cheaper models automatically",
-    "tasksDetected": "Tasks detected",
-    "degradationMap": "Model Degradation Map",
-    "premiumModel": "Premium model",
-    "cheapModel": "Cheap model",
-    "detectionPatterns": "Detection Patterns",
-    "newPattern": "e.g. \"generate a title\"",
-    "aliasPatternPlaceholder": "claude-sonnet-*",
-    "aliasTargetPlaceholder": "claude-sonnet-4-20250514",
-    "pattern": "Pattern",
-    "targetModel": "Target Model",
-    "add": "+ Add",
-    "session": "Session",
-    "sessionDetailsAria": "Session details",
-    "status": "Status",
-    "authenticated": "Authenticated",
-    "guest": "Guest",
-    "loginTime": "Login Time",
-    "sessionAge": "Session Age",
-    "browser": "Browser",
-    "clearLocalData": "Clear Local Data",
-    "logout": "Logout",
-    "clearLocalDataConfirm": "Clear all local data? This will reset your preferences.",
-    "unknown": "Unknown",
-    "systemActor": "system",
-    "ipAccessControl": "IP Access Control",
-    "ipAccessControlDesc": "Block or allow specific IP addresses",
-    "ipModeDisabled": "Disabled",
-    "ipModeBlacklist": "Blacklist",
-    "ipModeWhitelist": "Whitelist",
-    "ipModeWhitelistPriority": "WL Priority",
-    "addIpAddress": "Add IP Address",
-    "ipAddressPlaceholder": "192.168.1.0/24 or 10.0.*.*",
-    "block": "+ Block",
-    "allow": "+ Allow",
-    "blocked": "Blocked ({count})",
-    "allowed": "Allowed ({count})",
-    "temporaryBans": "Temporary Bans ({count})",
-    "minLeft": "{min}m left",
-    "auditLog": "Audit Log",
-    "searchAuditLogs": "Search audit logs...",
-    "failedLoadAuditLog": "Failed to load audit log",
-    "noAuditEvents": "No audit events found",
-    "action": "Action",
-    "actor": "Actor",
-    "details": "Details",
-    "time": "Time",
-    "fallbackChainsTitle": "Fallback Chains",
-    "fallbackChainsDesc": "Define provider fallback order per model",
-    "addChain": "+ Add Chain",
-    "modelName": "Model Name",
-    "modelNamePlaceholder": "claude-sonnet-4-20250514",
-    "providersCommaSeparated": "Providers (comma-separated, in priority order)",
-    "providersCommaSeparatedPlaceholder": "anthropic, openai, gemini",
-    "createChain": "Create Chain",
-    "noFallbackChains": "No Fallback Chains",
-    "noFallbackChainsDesc": "Create a chain to define provider fallback order for a model.",
-    "loadingFallbackChains": "Loading fallback chains...",
-    "deleteChainConfirm": "Delete fallback chain for \"{model}\"?",
-    "chainCreated": "Chain created for {model}",
-    "chainDeleted": "Chain deleted for {model}",
-    "failedCreateChain": "Failed to create chain",
-    "failedDeleteChain": "Failed to delete chain",
-    "deleteChain": "Delete chain",
-    "fillModelAndProviders": "Please fill model name and providers",
-    "addAtLeastOneProvider": "Add at least one provider",
-    "comboDefaultsTitle": "Combo Defaults",
-    "comboDefaultsGuideTitle": "How to tune combo defaults",
-    "comboDefaultsGuideHint1": "Keep retries low in low-latency flows; increase timeout only for long generation tasks.",
-    "comboDefaultsGuideHint2": "Use provider overrides when one provider needs different timeout/retry behavior than global defaults.",
-    "globalComboConfig": "Global combo configuration",
-    "moveUp": "Pindahkan ke atas",
-    "moveDown": "Pindahkan ke bawah",
-    "allProvidersAdded": "Semua penyedia telah ditambahkan",
-    "noProvidersFound": "Penyedia tidak ditemukan",
-    "defaultStrategy": "Default Strategy",
-    "defaultStrategyDesc": "Applied to new combos without explicit strategy",
-    "comboStrategyAria": "Combo strategy",
-    "priority": "Priority",
-    "weighted": "Weighted",
-    "contextRelay": "Context Relay",
-    "contextRelayDesc": "Priority-style routing with automatic context handoffs when account rotation happens",
-    "maxRetriesLabel": "Max Retries",
-    "retryDelayLabel": "Retry Delay (ms)",
-    "timeoutLabel": "Timeout (ms)",
-    "healthCheck": "Health Check",
-    "healthCheckDesc": "Pre-check provider availability",
-    "trackMetrics": "Track Metrics",
-    "trackMetricsDesc": "Record per-combo request metrics",
-    "providerOverrides": "Provider Overrides",
-    "providerOverridesDesc": "Override timeout and retries per provider. Provider settings override global defaults.",
-    "providerMaxRetriesAria": "{provider} max retries",
-    "providerTimeoutAria": "{provider} timeout ms",
-    "removeProviderOverrideAria": "Remove {provider} override",
-    "selectProviderPlaceholder": "Pilih penyedia...",
-    "searchProviderPlaceholder": "Cari penyedia...",
-    "searchProviderAria": "Cari penyedia",
-    "newProviderNamePlaceholder": "e.g. google, openai...",
-    "newProviderNameAria": "New provider name",
-    "retries": "retries",
-    "ms": "ms",
-    "saveComboDefaults": "Save Combo Defaults",
-    "maxNestingDepth": "Max Nesting Depth",
-    "concurrencyPerModel": "Concurrency / Model",
-    "queueTimeout": "Queue Timeout (ms)",
-    "queueDepth": "Kedalaman Antrean",
-    "contextRelayHandoffThreshold": "Handoff Threshold",
-    "contextRelayMaxMessages": "Max Messages For Summary",
-    "contextRelaySummaryModel": "Summary Model",
-    "contextRelayProviderNote": "Context Relay currently generates handoffs for Codex accounts and uses these values as global defaults for new or unconfigured combos.",
-    "providerProfiles": "Provider Profiles",
-    "providerProfilesDesc": "Separate resilience settings for OAuth (session-based) and API Key (metered) providers. OAuth providers have stricter thresholds due to lower rate limits.",
-    "oauthProviders": "OAuth Providers",
-    "apiKeyProviders": "API Key Providers",
-    "transientCooldown": "Transient Cooldown",
-    "rateLimitCooldown": "Rate Limit Cooldown",
-    "maxBackoffLevel": "Max Backoff Level",
-    "cbThreshold": "CB Threshold",
-    "cbResetTime": "CB Reset Time",
-    "rateLimiting": "Rate Limiting",
-    "rateLimitingDesc": "API Key providers are automatically rate-limited with safe defaults. Limits are learned from response headers and adapt over time.",
-    "defaultSafetyNet": "Default Safety Net",
-    "rpm": "RPM",
-    "minGap": "Min Gap",
-    "maxConcurrent": "Max Concurrent",
-    "activeLimiters": "Active Limiters",
-    "noActiveLimiters": "No active rate limiters yet.",
-    "reservoir": "Reservoir",
-    "running": "Running",
-    "queued": "Queued",
-    "circuitBreakers": "Circuit Breakers",
-    "breakerStateClosed": "Closed",
-    "breakerStateOpen": "Open",
-    "breakerStateHalfOpen": "Half-Open",
-    "tripped": "{count} tripped",
-    "healthy": "{count} healthy",
-    "resetAll": "Reset All",
-    "noCircuitBreakers": "No circuit breakers active yet. They are created automatically when requests flow through the combo pipeline.",
-    "failures": "{count} failure(s)",
-    "policiesLocked": "Policies & Locked Identifiers",
-    "allOperational": "All systems operational — no lockouts or tripped breakers",
-    "loadingPolicies": "Loading policies...",
-    "lockedIdentifiers": "Locked Identifiers",
-    "unlockedIdentifier": "Unlocked: {identifier}",
-    "sinceDate": "since {date}",
-    "forceUnlock": "Force Unlock",
-    "unlocking": "Unlocking...",
-    "failedUnlock": "Failed to unlock",
-    "failedLoadWithStatus": "Failed to load: {status}",
-    "failedLoadResilience": "Failed to load resilience status",
-    "saveFailed": "Save failed",
-    "resetFailed": "Reset failed",
-    "loadingResilience": "Loading resilience status...",
-    "retry": "Retry",
-    "systemStorage": "System & Storage",
-    "allDataLocal": "All data stored locally on your machine",
-    "databasePath": "Database Path",
-    "export": "Ekspor",
-    "exportDatabase": "Export Database",
-    "exportAll": "Export All (.tar.gz)",
-    "importDatabase": "Import Database",
-    "confirmDbImport": "Confirm Database Import",
-    "confirmDbImportDesc": "This will replace all current data with the content from {file}. A backup will be created automatically before the import.",
-    "yesImport": "Yes, Import",
-    "lastBackup": "Last Backup",
-    "noBackupYet": "No backup yet",
-    "backupNow": "Backup Now",
-    "backupRestore": "Backup & Restore",
-    "viewBackups": "View Backups",
-    "hide": "Hide",
-    "backupRetentionDesc": "Database snapshots are created automatically before restore and every 15 minutes when data changes. Retention: 24 hourly + 30 daily backups with smart rotation.",
-    "loadingBackups": "Loading backups...",
-    "noBackupsYet": "No backups available yet. Backups will be created automatically when data changes.",
-    "backupsAvailable": "{count} backup(s) available",
-    "refresh": "Refresh",
-    "confirm": "Confirm?",
-    "yes": "Yes",
-    "no": "No",
-    "restore": "Restore",
-    "invalidFileType": "Invalid file type. Only .sqlite files are accepted.",
-    "exportFailed": "Export failed",
-    "exportFailedWithError": "Export failed: {error}",
-    "fullExportFailedWithError": "Full export failed: {error}",
-    "backupCreated": "Backup created: {file}",
-    "restoreSuccess": "Restored! {connections} connections, {nodes} nodes, {combos} combos, {apiKeys} API keys.",
-    "importSuccess": "Database imported! {connections} connections, {nodes} nodes, {combos} combos, {apiKeys} API keys.",
-    "minutesAgo": "{count}m ago",
-    "hoursAgo": "{count}h ago",
-    "daysAgo": "{count}d ago",
-    "backupReasonManual": "manual",
-    "backupReasonPreRestore": "pre-restore",
-    "connectionsCount": "{count, plural, one {# connection} other {# connections}}",
-    "noChangesSinceBackup": "No changes since last backup",
-    "backupFailed": "Backup failed",
-    "restoreFailed": "Restore failed",
-    "importFailed": "Import failed",
-    "errorDuringRestore": "An error occurred during restore",
-    "errorDuringImport": "An error occurred during import",
-    "modelPricing": "Model Pricing",
-    "modelPricingDesc": "Configure cost rates per model • All rates in $/1M tokens",
-    "pricingCoverage": "Cakupan",
-    "pricingAuth": "Autentikasi",
-    "pricingSort": "Urutkan",
-    "pricingAll": "Semua",
-    "pricingAuthUnknown": "Tidak diketahui",
-    "pricingMostModels": "Model terbanyak",
-    "pricingHighestCoverage": "Cakupan tertinggi",
-    "pricingLowestCoverage": "Cakupan terendah",
-    "pricingNameAscending": "Nama (A–Z)",
-    "pricingCoverageGaps": "Kesenjangan cakupan",
-    "pricingClearFilters": "Bersihkan filter",
-    "pricingShowingProviders": "Menampilkan {visible} dari {total}",
-    "pricingFilteredFrom": "(difilter dari {count})",
-    "pricingShowMoreProviders": "Tampilkan {count} lagi ({remaining} tersisa)",
-    "modelOverridesTitle": "Penimpaan Model",
-    "modelOverridesDesc": "Timpa kemampuan penyedia/model yang digunakan oleh perutean dan pembentukan permintaan. Target menggunakan format penyedia/model yang sama dengan kombo.",
-    "searchModelOverrideTargets": "Cari penyedia/model...",
-    "selectedModel": "Model terpilih",
-    "configured": "dikonfigurasi",
-    "none": "Tidak ada",
-    "modelOverrideValuePlaceholder": "Nilai numerik",
-    "modelOverrideReasoningEffortsPlaceholder": "English comma-separated, e.g. low, medium, high",
-    "addKeyValue": "Tambah nilai kunci",
-    "noModelOverrides": "Tidak ada penimpaan yang dikonfigurasi untuk model ini.",
-    "modelOverrideLoadFailed": "Gagal memuat penimpaan model",
-    "modelOverrideSaved": "Penimpaan model disimpan",
-    "modelOverrideRemoved": "Penimpaan model dihapus",
-    "modelOverrideSaveFailed": "Gagal menyimpan penimpaan model",
-    "modelOverrideRemoveFailed": "Gagal menghapus penimpaan model",
-    "registry": "Registry",
-    "priced": "Priced",
-    "searchProvidersModels": "Search providers or models...",
-    "showAll": "Show All",
-    "noProvidersMatch": "No providers match your search.",
-    "howPricingWorks": "How Pricing Works",
-    "cacheWrite": "Cache Write",
-    "unsaved": "unsaved",
-    "resetDefaults": "Atur Ulang ke Default",
-    "saveProvider": "Save Provider",
-    "model": "Model",
-    "models": "models",
-    "moreProviders": "{count} more providers",
-    "withPricing": "with pricing configured",
-    "policiesCircuitBreakers": "Policies & Circuit Breakers",
-    "activeIssuesDetected": "Active issues detected",
-    "off": "Off",
-    "resetPricingConfirm": "Reset all pricing for {provider} to defaults?",
-    "pricingDescInput": "Input: tokens sent to the model",
-    "pricingDescOutput": "Output: tokens generated",
-    "pricingDescCached": "Cached: reused input (~50% of input rate)",
-    "pricingDescReasoning": "Reasoning: thinking tokens (falls back to Output)",
-    "pricingDescCacheWrite": "Cache Write: creating cache entries (falls back to Input)",
-    "pricingDescFormula": "Cost = (input × input_rate) + (output × output_rate) + (cached × cached_rate) per million tokens.",
-    "pricingSettingsTitle": "Pricing Settings",
-    "totalModels": "Total Models",
-    "active": "Active",
-    "costCalculation": "Cost Calculation",
-    "costCalculationDesc": "Costs are calculated based on token usage and pricing rates configured for each model.",
-    "pricingFormat": "Pricing Format",
-    "pricingFormatDesc": "All rates are in $/1M tokens (dollars per million tokens).",
-    "tokenTypes": "Token Types",
-    "inputTokenDesc": "Standard prompt tokens",
-    "outputTokenDesc": "Completion/response tokens",
-    "cachedTokenDesc": "Cached input tokens (typically 50% of input rate)",
-    "reasoningTokenDesc": "Special reasoning/thinking tokens (fallback to output rate)",
-    "cacheCreationTokenDesc": "Tokens used to create cache entries (fallback to input rate)",
-    "customPricingNote": "You can override default pricing for specific models. Custom overrides take priority over auto-detected pricing.",
-    "editPricing": "Edit Pricing",
-    "viewFullDetails": "View Full Details",
-    "themeCoral": "Coral",
-    "adaptiveVolumeRouting": "Adaptive Volume Routing",
-    "adaptiveVolumeRoutingDesc": "Scale connections dynamically based on payload volume and throughput pressure.",
-    "lkgpToggleTitle": "Last Known Good Provider (LKGP)",
-    "lkgpToggleDesc": "When enabled, the router remembers which provider last served a successful response and tries it first on subsequent requests.",
-    "echoRequestedModelTitle": "Gemakan nama model yang diminta dalam respons",
-    "echoRequestedModelDesc": "Saat diaktifkan, bidang `model` respons menggemakan nama alias atau kombo yang diminta klien alih-alih nama model upstream. Memperbaiki klien ketat (mis. Claude Desktop) yang menolak respons yang modelnya tidak cocok dengan permintaan.",
-    "webSearchRouteTitle": "Perutean pencarian web",
-    "webSearchRouteDesc": "Saat permintaan menyertakan alat web_search bawaan, arahkan seluruh permintaan ke model ini alih-alih default — berguna untuk penyedia yang tidak menerapkan alat server web_search Anthropic. Biarkan kosong untuk menonaktifkan.",
-    "webSearchRoutePlaceholder": "Cari atau pilih model…",
-    "paidModelPatternWarning": "Pola ini hanya cocok dengan model berbayar — aktifkan model berbayar atau sesuaikan polanya.",
-    "clearLkgpCache": "Clear LKGP Cache",
-    "lkgpCacheCleared": "LKGP cache cleared successfully",
-    "lkgpCacheClearFailed": "Failed to clear LKGP cache",
-    "days": "Days",
-    "lkgp": "LKGP Mode",
-    "lkgpDesc": "Last Known Good Provider (Predictable resilience)",
-    "maintenance": "Maintenance",
-    "purgeExpiredLogs": "Purge Expired Logs",
-    "purgeLogsFailed": "Failed to purge logs",
-    "logsDeleted": "{count, plural, =0 {Tidak ada log kedaluwarsa yang dibersihkan} one {# log kedaluwarsa dibersihkan} other {# log kedaluwarsa dibersihkan}}",
-    "resetUsageData": "Setel Ulang Data Penggunaan",
-    "resetUsageDataDesc": "Pilih seberapa jauh ke belakang Anda ingin menghapus data penggunaan, log permintaan, dan analitik. Konfigurasi penyedia, koneksi, kunci API, kombo, dan pengaturan tetap dipertahankan. Tindakan ini tidak dapat dibatalkan.",
-    "resetUsagePeriod_5m": "5 menit",
-    "resetUsagePeriod_1h": "1 jam",
-    "resetUsagePeriod_3h": "3 jam",
-    "resetUsagePeriod_6h": "6 jam",
-    "resetUsagePeriod_12h": "12 jam",
-    "resetUsagePeriod_1d": "1 hari",
-    "resetUsagePeriod_7d": "7 hari",
-    "resetUsagePeriod_30d": "30 hari",
-    "resetUsagePeriod_all": "Sepanjang waktu",
-    "resetUsageSuccess": "{count, plural, =0 {Tidak ada baris data penggunaan yang dihapus} one {Setel ulang data penggunaan (# baris dihapus)} other {Setel ulang data penggunaan (# baris dihapus)}}",
-    "resetUsageFailed": "Gagal menyetel ulang data penggunaan",
-    "reset": "Setel Ulang",
-    "resetting": "Menyetel ulang...",
-    "contextOpt": "Context Optimized",
-    "contextOptDesc": "Routes based on context window requirements and conversation length",
-    "cacheOpt": "Cache Optimized",
-    "cacheOptDesc": "Keeps the same reusable prompt prefix on the same provider account",
-    "priorityDesc": "Sequential fallback - tries provider 1 first, then provider 2, and so on",
-    "weightedDesc": "Distributes traffic by percentage weights across providers",
-    "modelRoutingTitle": "Model Routing Rules",
-    "modelRoutingDesc": "Automatically route models to specific combos using glob patterns",
-    "addRule": "Add Rule",
-    "routeToCombo": "Route to Combo",
-    "selectCombo": "Select combo...",
-    "priorityHint": "Higher = checked first. Use 10+ for specific patterns.",
-    "patternHint": "Use * for any chars, ? for single char. Case-insensitive.",
-    "noRoutingRules": "No routing rules configured. Requests use the global combo by default.",
-    "routingRuleHint": "Add a rule like claude-opus* -> frontier-combo to automatically route requests.",
-    "deleteRoutingRule": "Delete this model routing rule?",
-    "exactMatchMode": "Exact Match",
-    "wildcardPatternMode": "Wildcard Pattern",
-    "exactMatchModeDesc": "Use exact aliases for deprecated or renamed model IDs.",
-    "wildcardPatternModeDesc": "Use wildcard aliases with * and ? when a family of models should map to one target.",
-    "noExactAliasesConfigured": "No exact-match aliases configured.",
-    "wildcardRulesTitle": "Wildcard Rules",
-    "noWildcardAliasesConfigured": "No wildcard aliases configured.",
-    "overview": "Overview",
-    "unknownError": "Unknown Error",
-    "pricingSourceLiteLLM": "LiteLLM (Community)",
-    "clearSyncedPricingConfirm": "Clear all synced pricing data? Provider defaults will be used instead.",
-    "clearSyncedPricingFailed": "Failed to clear synced pricing",
-    "pricingSourceUser": "User Override",
-    "pageDescription": "Manage application settings, model aliases, pricing, and routing rules",
-    "pricingSyncStatus": "Sync Status",
-    "whitelist": "Whitelist",
-    "syncDisabled": "Sync Disabled",
-    "pricingLoadFailed": "Failed to load pricing data",
-    "pricingSyncDescription": "Automatically sync model pricing from external sources to keep cost calculations accurate",
-    "clearSyncedPricingSuccess": "Synced pricing data cleared",
-    "clearSyncedPricingFailedWithReason": "Failed to clear pricing: {reason}",
-    "pricingSourceDefault": "Built-in Default",
-    "pricingSyncSuccess": "Pricing synced successfully",
-    "enableSyncError": "Failed to toggle pricing sync",
-    "syncEnabled": "Sync Enabled",
-    "blacklist": "Blacklist",
-    "pricingSourceModelsDev": "Models.dev",
-    "syncedModels": "Synced Models",
-    "budget": "Budget",
-    "pricingSyncTitle": "Pricing Sync",
-    "pricingResetFailedWithReason": "Failed to reset pricing: {reason}",
-    "tab": "Tab",
-    "pricingSavedProvider": "Pricing saved for {provider}",
-    "pricingSyncFailed": "Pricing sync failed",
-    "pricingSaveFailedWithReason": "Failed to save pricing: {reason}",
-    "pricingResetProvider": "Pricing reset for {provider}",
-    "nextSync": "Next Sync",
-    "pricingSyncFailedWithReason": "Pricing sync failed: {reason}",
-    "clearSyncedPricing": "Clear Synced Pricing",
-    "compressionTitle": "Prompt Compression",
-    "compressionDesc": "Reduce token usage by compressing prompts before sending to providers",
-    "compressionGuidanceFullGuideLink": "Panduan kompresi lengkap",
-    "compressionGuidanceShow": "Detail",
-    "compressionGuidanceHide": "Sembunyikan detail",
-    "compressionGuidanceSafeDefault": "Default aman",
-    "compressionGuidanceCacheImpact": "Dampak cache",
-    "tokenSaverTitle": "Penghemat Token",
-    "tokenSaverSubtitle": "Gunakan lebih sedikit token pada setiap permintaan.",
-    "tokenSaverToolOutput": "Output alat",
-    "tokenSaverToolOutputDesc": "Bersihkan output git, grep, ls, tree, dan log sebelum mencapai penyedia.",
-    "tokenSaverLlmOutput": "Output LLM",
-    "tokenSaverLlmOutputDesc": "Sisipkan instruksi respons ringkas tanpa menulis ulang output penyedia.",
-    "tokenSaverInputCompression": "Kompresi input",
-    "tokenSaverInputCompressionDesc": "Tulis ulang riwayat obrolan yang memenuhi syarat sambil mempertahankan kode, URL, dan maksud.",
-    "tokenSaverFineTunePrefix": "Sempurnakan setiap mesin pada",
-    "tokenSaverFineTuneSuffix": "atau gabungkan mesin per permintaan pada",
-    "compressionMode": "Compression Mode",
-    "compressionModeOff": "Off",
-    "compressionModeOffDesc": "No compression applied",
-    "compressionModeLite": "Lite",
-    "compressionModeLiteDesc": "Whitespace and blank line reduction",
-    "compressionModeStandard": "Standard (Caveman)",
-    "compressionModeStandardDesc": "Rule-based compression with 30+ patterns, preserves code blocks and URLs",
-    "compressionModeAggressive": "Agresif",
-    "compressionModeAggressiveDesc": "Peringkasan + kompresi hasil alat + penuaan progresif untuk penghematan maksimum",
-    "compressionModeUltra": "Sangat",
-    "compressionModeUltraDesc": "Pemangkasan token heuristik dengan fallback SLM lokal opsional",
-    "compressionAggressiveConfig": "Konfigurasi Mesin Agresif",
-    "compressionAggressiveConfigDesc": "Sempurnakan ringkasan, kompresi alat, dan ambang batas penuaan",
-    "compressionUltraConfig": "Konfigurasi Mesin Ultra",
-    "compressionUltraConfigDesc": "Sempurnakan pemangkasan heuristik, penggantian SLM, dan ambang batas per pesan",
-    "compressionUltraRate": "Pertahankan Nilai",
-    "compressionUltraMinScore": "Ambang Batas Skor Minimum",
-    "compressionUltraSlmFallback": "Mundur ke Agresif",
-    "compressionUltraModelPath": "Jalur Model SLM",
-    "compressionUltraEngine": "Tingkat Ultra",
-    "compressionUltraEngineHeuristic": "Heuristik (Tingkat-A, default)",
-    "compressionUltraEngineSlm": "SLM (LLMLingua-2, opt-in)",
-    "compressionUltraSlmHint": "SLM mengunduh model ONNX kecil pada penggunaan pertama (cold-start) dan secara transparan beralih kembali ke heuristik saat batas waktu habis atau jika tidak tersedia.",
-    "compressionUltraSlmPrewarm": "Pra-hangatkan model SLM saat diaktifkan",
-    "compressionSummarizerEnabled": "Aktifkan Peringkas",
-    "compressionMaxTokensPerMessage": "Token Maksimum Per Pesan",
-    "compressionMinSavings": "Ambang Batas Penghematan Min",
-    "compressionAgingThresholds": "Ambang Batas Penuaan",
-    "compressionAgingThresholdsDesc": "Jumlah pesan terbaru yang disimpan pada setiap tingkatan penuaan (lebih tinggi = lebih dipertahankan)",
-    "compressionToolStrategies": "Strategi Hasil Alat",
-    "compressionToolStrategiesDesc": "Alihkan strategi kompresi untuk jenis hasil alat yang berbeda",
-    "compressionGeneral": "General Settings",
-    "compressionAutoTrigger": "Auto-Trigger Threshold",
-    "compressionCacheTTL": "Cache TTL",
-    "compressionPreserveSystem": "Preserve System Prompt",
-    "compressionPreserveSystemAlways": "Selalu",
-    "compressionPreserveSystemWhenNoCache": "Saat tidak ada cache",
-    "compressionPreserveSystemNever": "Tidak Pernah",
-    "compressionLiveZoneTitle": "Live Zone Selaras Cache",
-    "compressionLiveZoneDesc": "Pertahankan kestabilan awalan percakapan yang dikompresi dan hanya proses item yang baru ditambahkan.",
-    "compressionExclusionsTitle": "Pengecualian Kompresi",
-    "compressionExclusionsDesc": "ID model atau pola penyedia/model yang tidak boleh dikompresi. `*` adalah satu-satunya wildcard (misalnya `openai/*`, `*embedding*`). Permintaan yang cocok akan melewati byte-identik — tidak ada mesin kompresi yang dijalankan.",
-    "compressionExclusionsPlaceholder": "Satu pola per baris, misalnya  \nopenai/text-embedding-3-large  \nanthropic/*",
-    "compressionExclusionsSave": "Simpan",
-    "compressionExclusionsSaved": "Disimpan",
-    "compressionExclusionsCount": "{count, plural, one {# pengecualian} other {# pengecualian}} dikonfigurasi",
-    "compressionExclusionsEmpty": "Tidak ada pengecualian yang dikonfigurasi — setiap model/endpoint memenuhi syarat untuk kompresi (perilaku default).",
-    "compressionCavemanConfig": "Caveman Engine Configuration",
-    "compressionCavemanConfigDesc": "Fine-tune the rule-based compression engine",
-    "compressionCavemanPanelHint": "Status aktif/nonaktif dan levelnya diatur di panel:",
-    "compressionRoles": "Compress Message Roles",
-    "compressionRoleUser": "User",
-    "compressionRoleAssistant": "Assistant",
-    "compressionRoleSystem": "System",
-    "compressionMinLength": "Minimum Message Length",
-    "compressionSkipRules": "Skip Compression Rules",
-    "compressionSkipRulesDesc": "Click rules to skip them during compression",
-    "compressionPreservePatterns": "Preserve Patterns",
-    "compressionPreservePatternsDesc": "Regex patterns that are never compressed (one per line)",
-    "compressionLogTitle": "Compression Log",
-    "compressionLogEmpty": "No compressed requests yet. Compression stats will appear here when requests are processed with compression enabled.",
-    "minutes": "menit",
-    "compressionModeRtk": "RTK",
-    "compressionModeRtkDesc": "Command-aware tool output filtering",
-    "compressionModeCodexResponses": "Responses tool output",
-    "compressionModeCodexResponsesDesc": "Conservative compression for eligible shell, patch, search, build, and JSON outputs",
-    "compressionModeStacked": "Stacked",
-    "compressionModeStackedDesc": "RTK tool-output filtering followed by Caveman message compression",
-    "qdrantTitle": "Qdrant (Vector memory)",
-    "qdrantDesc": "Optional. Indexes semantic memories in an external vector database for faster retrieval.",
-    "qdrantStatusActive": "Active",
-    "qdrantStatusError": "Error",
-    "qdrantStatusDisabled": "Disabled",
-    "qdrantEnable": "Enable Qdrant",
-    "qdrantEnableDesc": "When enabled, semantic/hybrid strategy can use Qdrant to retrieve memories.",
-    "qdrantTesting": "Testing...",
-    "qdrantTestConnection": "Test connection",
-    "qdrantSaved": "Configuration saved",
-    "qdrantSaveError": "Failed to save configuration",
-    "qdrantHostHint": "Without port. Example: 127.0.0.1 or http://qdrant",
-    "qdrantPort": "Port",
-    "qdrantPortHint": "Qdrant default: 6333",
-    "qdrantCollectionHint": "Where memory points will be stored.",
-    "qdrantEmbeddingModel": "Embedding model",
-    "qdrantHelpTitle": "Quick setup help",
-    "qdrantHelpQuickTitle": "Quick setup (Qdrant + OpenRouter)",
-    "qdrantHelpStep1": "1. Host: Qdrant IP/URL, Port: 6333, Collection: omniroute_memory.",
-    "qdrantHelpStep2": "2. If using nvidia/llama-nemotron-embed-vl-1b-v2:free, use collection dimension 2048.",
-    "qdrantHelpStep3": "3. Model field: openrouter/nvidia/llama-nemotron-embed-vl-1b-v2:free.",
-    "qdrantHelpStep4": "4. Save, test connection, then test search.",
-    "qdrantEmbeddingQuickSelect": "Quick select from discovered models...",
-    "qdrantEmbeddingInputPlaceholder": "openai/text-embedding-3-small",
-    "qdrantEmbeddingHint": "Format: provider/model. The provider credential must be configured.",
-    "qdrantApiKeyPlaceholderKeep": "(leave empty to keep current key)",
-    "qdrantApiKeyPlaceholderOptional": "(leave empty if not used)",
-    "qdrantSaveHint": "Tip: edit host/port/collection/model and click Save. API key is optional.",
-    "qdrantSearchTestTitle": "Search test",
-    "qdrantSearchTestDesc": "Generates embedding and searches in Qdrant.",
-    "qdrantSearchPlaceholder": "Example: user preferences, history, etc",
-    "qdrantNoResults": "No results (or Qdrant is not configured).",
-    "qdrantCleanupTitle": "Retention and cleanup",
-    "qdrantCleanupDesc": "Removes expired and old points based on",
-    "searching": "Searching...",
-    "cleaning": "Cleaning...",
-    "cleanNow": "Clean now",
-    "optional": "Opsional",
-    "current": "Saat ini",
-    "remove": "Hapus",
-    "search": "Cari",
-    "oneproxyTitle": "1proxy Pasar Proxy Gratis",
-    "oneproxyTotalProxies": "Total Proksi",
-    "oneproxyAvgQuality": "Kualitas Rata-Rata",
-    "resilienceScope": "Ruang lingkup:",
-    "resilienceTrigger": "Pemicu:",
-    "resilienceEffect": "Efek:",
-    "resilienceRequestQueueTitle": "Request Queue & Rate",
-    "resilienceAutoEnableApiKeyProviders": "Auto-enable for API-key providers",
-    "resilienceRequestsPerMinute": "Requests per minute",
-    "resilienceMinTimeBetweenRequests": "Minimum time between requests",
-    "resilienceConcurrentRequests": "Concurrent requests",
-    "resilienceConnectionScopeConcurrentRequests": "__MISSING__:Concurrent requests per connection/quota scope",
-    "resilienceGlobalConcurrentRequests": "__MISSING__:Global concurrent upstream requests (0 = disabled)",
-    "resilienceMaxQueueWaitTime": "Waktu tunggu antrian maksimum",
-    "resilienceBaseCooldown": "Base cooldown",
-    "resilienceUseUpstreamRetryHints": "Use upstream retry hints",
-    "resilienceDefaultPerProvider": "Default (per provider)",
-    "resilienceAlwaysOn": "Always on",
-    "resilienceAlwaysOff": "Always off",
-    "routingRemoveEntry": "Hapus entri",
-    "routingNeedlesSubstrings": "Jarum (substring yang cocok)",
-    "routingCaseSensitive": "Peka huruf besar-kecil",
-    "routingPrefixes": "Awalan",
-    "routingMatch": "Cocok",
-    "routingReplacement": "Penggantian",
-    "routingReplaceAllOccurrences": "Ganti semua kejadian",
-    "routingPatternRegex": "Pola (regex)",
-    "routingFlags": "Bendera",
-    "routingNeedles": "jarum",
-    "routingBlockText": "Blokir teks",
-    "routingIdempotencyKey": "Kunci idempotensi",
-    "routingEntrypoint": "Titik masuk",
-    "routingVersionFormat": "Format versi",
-    "routingCchAlgorithm": "Algoritma CCH",
-    "routingWordsToObfuscate": "Kata-kata untuk dikaburkan (ZWJ disisipkan setelah karakter pertama)",
-    "logsSettingsTitle": "Pengaturan Log",
-    "detailedLogsLabel": "Log Terperinci Diaktifkan",
-    "detailedLogsDesc": "Aktifkan pencatatan permintaan/respons terperinci",
-    "callLogPipelineLabel": "Saluran Log Panggilan",
-    "callLogPipelineDesc": "Aktifkan alur pemrosesan log panggilan",
-    "maxDetailSizeLabel": "Ukuran Detail Maks (KB)",
-    "maxDetailSizeDesc": "Ukuran maksimum untuk entri log terperinci",
-    "ringBufferSizeLabel": "Ukuran Penyangga Cincin",
-    "ringBufferSizeDesc": "Ukuran buffer cincin untuk log",
-    "semanticCacheEnabledLabel": "Cache Semantik Diaktifkan",
-    "semanticCacheMaxSizeLabel": "Ukuran Maksimum Cache Semantik",
-    "semanticCacheMaxSizeDesc": "Jumlah maksimum entri cache semantik",
-    "semanticCacheTTLLabel": "TTL Cache Semantik",
-    "promptCacheEnabledLabel": "Cache Prompt Diaktifkan",
-    "promptCacheEnabledDesc": "Aktifkan cache cepat",
-    "promptCacheStrategyLabel": "Strategi Cache Cepat",
-    "promptCacheStrategyDesc": "Strategi untuk cache yang cepat",
-    "alwaysPreserveClientCacheLabel": "Selalu Pertahankan Cache Klien",
-    "alwaysPreserveClientCacheDesc": "Kebijakan pelestarian cache klien",
-    "logRetentionPolicyTitle": "Kebijakan penyimpanan log",
-    "resilienceUseUpstream429HintsForBreaker": "Gunakan petunjuk 429 hulu (pemutus)",
-    "appearanceLogoPreviewAlt": "Pratinjau logo",
-    "appearanceFaviconPreviewAlt": "Pratinjau favicon",
-    "oneproxyLastSync": "Sinkronisasi Terakhir",
-    "oneproxyAllProtocols": "Semua Protokol",
-    "oneproxyCountryCodePlaceholder": "Kode negara (misalnya AS)",
-    "oneproxyMinQualityPlaceholder": "kualitas minimal",
-    "oneproxyLoadingProxies": "Memuat proxy...",
-    "oneproxyLastSyncLabel": "Sinkronisasi terakhir:",
-    "oneproxyProxiesFetched": "Proksi diambil:",
-    "oneproxyConsecutiveFailures": "Kegagalan berturut-turut:",
-    "oneproxyErrorLabel": "Kesalahan:",
-    "oneproxyNever": "Tidak pernah",
-    "oneproxySyncStatusTitle": "Status Sinkronisasi",
-    "oneproxySuccess": "Sukses",
-    "oneproxyFailed": "Gagal",
-    "routingAntigravitySignatureTitle": "Mode Cache Tanda Tangan Antigravitasi",
-    "routingAntigravitySignatureDesc": "Kontrol apakah OmniRoute hanya menggunakan kembali tanda tangan pemikiran Gemini yang tersimpan atau menerima tanda tangan tervalidasi yang disediakan klien dalam alur pemanggilan alat yang kompatibel dengan Antigravity.",
-    "routingAntigravitySignatureEnabledLabel": "Diaktifkan",
-    "routingAntigravitySignatureEnabledDesc": "Perilaku saat ini. Abaikan tanda tangan yang disediakan klien dan tetap gunakan alur OmniRoute yang tersimpan.",
-    "routingAntigravitySignatureBypassLabel": "Bypass",
-    "routingAntigravitySignatureBypassDesc": "Terima tanda tangan yang disediakan klien setelah validasi ringan dan kembali ke tanda tangan yang tersimpan jika tidak valid.",
-    "routingAntigravitySignatureBypassStrictLabel": "Bypass Ketat",
-    "routingAntigravitySignatureBypassStrictDesc": "Wajibkan validasi protobuf penuh sebelum menerima tanda tangan yang disediakan klien.",
-    "routingHeaderFingerprintTitle": "Sidik jari header (per penyedia)",
-    "routingServerRejectedSave": "⚠ Server menolak penyimpanan:",
-    "routingAddTransformOp": "Tambahkan operasi transformasi",
-    "routingClientCacheControlTitle": "Kontrol Cache Klien",
-    "routingClientCacheControlDesc": "Konfigurasikan apakah OmniRoute mempertahankan penanda cache_control yang disediakan klien",
-    "routingClientCacheControlAutoDesc": "Untuk alur kompatibel Claude yang deterministik, pertahankan cache_control yang disediakan klien apa adanya. Jika permintaan tidak memiliki cache_control, OmniRoute tidak menyuntikkan penanda milik bridge apa pun demi kompatibilitas proksi pihak ketiga yang kompatibel dengan CC.",
-    "routingClientCacheControlAlwaysLabel": "Selalu Pertahankan",
-    "routingClientCacheControlAlwaysDesc": "Selalu teruskan header cache_control yang disediakan klien ke penyedia upstream apa adanya.",
-    "routingClientCacheControlNeverLabel": "Jangan Pernah Pertahankan",
-    "routingClientCacheControlNeverDesc": "Selalu hapus header cache_control klien dan biarkan OmniRoute mengelola caching jika alur penyedia native mendukungnya.",
-    "routingZeroConfigTitle": "Perutean Otomatis Tanpa Konfigurasi",
-    "routingZeroConfigDesc": "Aktifkan pemilihan penyedia otomatis menggunakan awalan auto/. Saat diaktifkan, permintaan ke auto, auto/coding, auto/fast, dll. akan dirutekan secara dinamis ke semua penyedia yang terhubung.",
-    "routingDefaultAutoVariant": "Varian Otomatis Default",
-    "visionBridge": "Jembatan Visi",
-    "visionBridgeDesc": "Jalankan fallback vision-ke-teks otomatis sebelum merutekan permintaan gambar ke model khusus teks.",
-    "visionBridgeEnabledLabel": "Diaktifkan",
-    "visionBridgeEnabledDesc": "Alihkan bridge pra-panggilan yang menggantikan bagian gambar dengan teks yang diekstrak.",
-    "visionBridgeRerouteTextOnlyLabel": "Arahkan ulang model teks saja",
-    "visionBridgeRerouteTextOnlyDesc": "Kirim permintaan lengkap, termasuk gambar, ke model jembatan ketika model yang dipilih tidak memiliki input gambar.",
-    "visionBridgeModel": "Model Jembatan",
-    "visionBridgeModelPlaceholder": "openai/gpt-4o-mini",
-    "visionBridgeModelHint": "ID model OmniRoute apa pun yang mendukung vision dapat digunakan di sini.",
-    "visionBridgePrompt": "Jembatan Cepat",
-    "visionBridgePromptPlaceholder": "Jelaskan gambar ini secara singkat.",
-    "visionBridgePromptHint": "Dikirim ke model vision sebelum deskripsi yang diekstrak disuntikkan kembali ke dalam permintaan asli.",
-    "visionBridgeTimeoutMs": "Batas waktu (md)",
-    "visionBridgeMaxImagesPerRequest": "Gambar Maks Per Permintaan",
-    "resilienceMaxBackoffSteps": "Max backoff steps",
-    "resilienceProviderBreakerTitle": "Circuit Breaker per Provider",
-    "resilienceFailureThreshold": "Failure threshold",
-    "resilienceDegradationThreshold": "Degradation threshold",
-    "resilienceResetTimeout": "Setel ulang batas waktu",
-    "resilienceFailureThresholdLabel": "Ambang batas kegagalan",
-    "resilienceResetTimeoutLabel": "Setel ulang batas waktu",
-    "resilienceConnectionCooldownTitle": "Connection Cooldown",
-    "resilienceUseUpstreamRetryHintsLabel": "Gunakan petunjuk coba ulang hulu",
-    "resilienceUseUpstream429BreakerLabel": "Gunakan petunjuk 429 hulu (pemutus)",
-    "resilienceMaxBackoffStepsLabel": "Langkah mundur maksimal",
-    "resilienceYes": "Ya",
-    "resilienceNo": "Tidak",
-    "resilienceDefault": "Default",
-    "storageDatabaseBackupRetention": "Retensi cadangan basis data",
-    "storageDatabaseBackups": "Cadangan basis data",
-    "storageBackupRetentionDescription": "Cadangan SQLite otomatis disimpan di",
-    "storageBackupRetentionHelp": "Konfigurasikan berapa banyak snapshot yang akan disimpan dan secara opsional hapus cadangan yang lebih lama dari jumlah hari yang dipilih.",
-    "storageBackupCount": "{count} cadangan",
-    "storageBackupMaximum": "Maks {count}",
-    "storageBackupAgeRetention": "Retensi {count} hari",
-    "storageBackupAgeRetentionOff": "Retensi usia nonaktif",
-    "storageBackupKeepLatest": "Simpan cadangan terbaru",
-    "storageBackupDeleteOlderThan": "Hapus yang lebih lama dari (hari)",
-    "storageBackupSaveRetention": "Simpan retensi",
-    "storageBackupCleanOld": "Bersihkan cadangan lama",
-    "storageDatabaseStatistics": "Statistik Basis Data",
-    "storageIntegrityNotChecked": "Belum diperiksa",
-    "backupRetentionSaved": "Retensi cadangan disimpan.",
-    "backupRetentionSaveFailed": "Gagal menyimpan retensi cadangan",
-    "backupCleanupSuccess": "Menghapus {backups} set cadangan dan {files} berkas.",
-    "backupCleanupFailed": "Gagal membersihkan cadangan basis data",
-    "purgeQuotaSnapshotsSuccess": "Membersihkan {count} snapshot kuota",
-    "purgeQuotaSnapshotsFailed": "Gagal membersihkan snapshot kuota",
-    "purgeCallLogsSuccess": "Membersihkan {count} log panggilan",
-    "purgeCallLogsFailed": "Gagal membersihkan log panggilan",
-    "purgeDetailedLogsSuccess": "Membersihkan {count} log terperinci",
-    "purgeDetailedLogsFailed": "Gagal membersihkan log terperinci",
-    "vacuumCompleted": "VACUUM selesai",
-    "vacuumFailed": "VACUUM gagal",
-    "jsonExportFailed": "Ekspor JSON gagal",
-    "invalidJsonFileType": "Jenis berkas tidak valid. Hanya berkas .json yang diizinkan.",
-    "legacyJsonImportSuccess": "JSON Legacy berhasil diimpor!",
-    "jsonImportFailed": "Gagal mengimpor JSON",
-    "jsonImportError": "Terjadi kesalahan saat mengimpor JSON",
-    "storagePurgeData": "Bersihkan Data",
-    "storagePurgeDataDesc": "Segera hapus semua rekaman tanpa menerapkan pemeriksaan retensi. Gunakan dengan hati-hati.",
-    "storageRetentionCleanup": "Pengaturan Retensi",
-    "storageRetentionCleanupDesc": "Konfigurasikan retensi rekaman operasional dan pembersihan cadangan basis data.",
-    "retentionCallDays": "Panggilan {count}h",
-    "retentionAppDays": "Aplikasi {count}h",
-    "retentionRows": "{count} baris",
-    "retentionQuotaSnapshots": "Cuplikan Kuota (hari)",
-    "retentionCompressionAnalytics": "Analisis Kompresi (hari)",
-    "retentionMcpAudit": "Audit MCP (hari)",
-    "retentionA2aEvents": "Acara A2A (hari)",
-    "retentionCallLogs": "Log Panggilan (hari)",
-    "retentionUsageHistory": "Riwayat Penggunaan (hari)",
-    "retentionMemoryEntries": "Entri Memori (hari)",
-    "retentionXpAuditLog": "Log Audit XP (hari)",
-    "saveRetentionSettings": "Simpan pengaturan retensi",
-    "storageAutoVacuumMode": "Mode Vakum Otomatis",
-    "storageScheduledVacuum": "Vakum Terjadwal",
-    "storageVacuumHour": "Jam Vakum (0-23)",
-    "storagePageSize": "Ukuran Halaman (byte)",
-    "storageOptimizationSettings": "Pengaturan Optimasi",
-    "storageJournalModeNone": "Tidak Ada",
-    "storageJournalModeFull": "Penuh",
-    "storageJournalModeIncremental": "Inkremental",
-    "storageVacuumNever": "Tidak Pernah",
-    "storageVacuumDaily": "Harian",
-    "storageVacuumWeekly": "Mingguan",
-    "storageVacuumMonthly": "Bulanan",
-    "storageCacheSizeKb": "Ukuran Cache (KB)",
-    "storageOptimizeOnStartup": "Optimalkan saat Startup",
-    "storageSaveOptimization": "Simpan Pengaturan Optimasi",
-    "storageCompressionAggregation": "Pengaturan Kompresi & Agregasi",
-    "storageEnableAggregation": "Aktifkan Agregasi Data",
-    "storageRawDataRetention": "Retensi Data Mentah (hari)",
-    "storageGranularity": "Granularitas",
-    "storageHourly": "Per Jam",
-    "storageDaily": "Harian",
-    "storageWeekly": "Mingguan",
-    "storageSaveAggregation": "Simpan Pengaturan Agregasi",
-    "exportJson": "Ekspor JSON",
-    "importJson": "Impor JSON",
-    "manualVacuum": "VACUUM Manual",
-    "purgeQuotaSnapshots": "Bersihkan Snapshot Kuota",
-    "purgeCallLogs": "Bersihkan Log Panggilan",
-    "purgeDetailedLogs": "Bersihkan Log Terperinci",
-    "storageDatabaseSize": "Ukuran Basis Data",
-    "storagePageCount": "Jumlah Halaman",
-    "storageFreelistCount": "Jumlah Daftar Bebas",
-    "storageLastVacuum": "Vakum Terakhir",
-    "storageLastOptimization": "Optimasi Terakhir",
-    "storageIntegrityCheck": "Pemeriksaan Integritas",
-    "storageIntegrityOk": "✓ Oke",
-    "storageIntegrityError": "✗ Kesalahan",
-    "storageUsageTokenBuffer": "Penyangga Token Penggunaan",
-    "storageUsageTokenBufferDesc": "Token ekstra yang ditambahkan ke penggunaan yang dilaporkan untuk memperhitungkan overhead prompt sistem.",
-    "storageUsageTokenBufferHint": "Atur ke 0 untuk melaporkan jumlah token penyedia mentah. Default: 2000.",
-    "storageUsageTokenBufferCurrent": "Saat ini: {value}",
-    "redisLauncherTitle": "Redis Lokal",
-    "redisLauncherDesc": "Luncurkan kontainer Redis 7 (Podman atau Docker) dengan satu klik untuk cache respons, pelacakan kuota, dan pembatasan laju.",
-    "redisLauncherRefresh": "Segarkan",
-    "redisLauncherStop": "Hentikan",
-    "redisLauncherLaunching": "Meluncurkan...",
-    "redisLauncherLaunch": "Luncurkan Redis",
-    "redisLauncherContainer": "Kontainer",
-    "redisLauncherRunning": "Berjalan",
-    "redisLauncherReachable": "Dapat Dijangkau",
-    "redisLauncherError": "Galat: {message}",
-    "redisLauncherHint": "Setara dengan menjalankan `omniroute redis up`. Kontainer diberi nama `omniroute-redis` dan mendengarkan pada 127.0.0.1:6379.",
-    "compressionSettingsAutoTriggerMode": "Mode pemicu otomatis",
-    "compressionSettingsMcpDescriptionCompression": "Kompresi deskripsi MCP",
-    "mcpAccessibilityTitle": "Output aksesibilitas MCP",
-    "compressionSettingsCavemanIntensity": "Intensitas manusia gua",
-    "compressionSettingsCavemanOutputMode": "Mode keluaran manusia gua",
-    "compressionSettingsOutputStyles": "Gaya output",
-    "compressionStylesTileTitle": "Gaya output",
-    "compressionSettingsOutputIntensity": "Intensitas keluaran",
-    "compressionSettingsAutoClarityBypass": "Bypass kejelasan otomatis",
-    "compressionEffectivePipeline": "Pipeline efektif:",
-    "compressionDerivedOff": "nonaktif",
-    "compressionDerivedRuns": "eksekusi: {pipeline}",
-    "compressionDerivedMode": "mode: {mode}",
-    "compressionAdaptiveOff": "Anggaran konteks adaptif: nonaktif (pemicu otomatis lawas)",
-    "compressionAdaptiveTarget": "Adaptif ({mode}, kebijakan: {policy}) — target ≈ {target, number} token (untuk jendela {contextLimit, number} token)",
-    "compressionOutputStylesDescription": "Sisipkan instruksi pembentukan respons tanpa menulis ulang output penyedia. Gabungkan secara bebas.",
-    "mcpAccessibilityDescription": "Mencakup output alat MCP (penyimpanan terpisah).",
-    "compressionStylesTileSummary": "{tokens, number} token dihemat · {runs, plural, one {# eksekusi diberi gaya} other {# eksekusi diberi gaya}}",
-    "compressionStylesTileEmpty": "Belum ada eksekusi yang diberi gaya.",
-    "compressionLevel": {
-      "minimal": "Minimal",
-      "standard": "Standar",
-      "aggressive": "Agresif",
-      "lite": "Lite",
-      "full": "Penuh",
-      "ultra": "Ultra"
-    },
-    "compressionEngine": {
-      "session-dedup": {
-        "label": "Dedup Sesi",
-        "description": "Deduplikasi blok lintas-giliran."
-      },
-      "ccr": {
-        "label": "CCR (Pengambilan)",
-        "description": "Penanda pengambilan beralamat konten."
-      },
-      "lite": {
-        "label": "Lite",
-        "description": "Pembersihan spasi kosong dan format."
-      },
-      "rtk": {
-        "label": "RTK",
-        "description": "Penyaringan keluaran perintah."
-      },
-      "codex-responses": {
-        "label": "Responses Tool Output",
-        "description": "Conservative compression for supported Responses tool outputs."
-      },
-      "headroom": {
-        "label": "Headroom",
-        "description": "Pemadatan JSON tabular."
-      },
-      "relevance": {
-        "label": "Relevansi",
-        "description": "Penilaian kalimat ekstraktif terhadap kueri pengguna terakhir."
-      },
-      "caveman": {
-        "label": "Caveman",
-        "description": "Kompresi prosa berbasis aturan."
-      },
-      "aggressive": {
-        "label": "Agresif",
-        "description": "Ringkas dan usangkan giliran lama."
-      },
-      "llmlingua": {
-        "label": "LLMLingua (SLM)",
-        "description": "Pemangkasan semantik (ONNX)."
-      },
-      "ultra": {
-        "label": "Ultra",
-        "description": "Pemangkasan token heuristik dengan SLM opsional."
-      },
-      "omniglyph": {
-        "label": "OmniGlyph",
-        "description": "Konteks sebagai gambar (Claude Fable 5, rute langsung)."
-      }
-    },
-    "compressionOutputStyle": {
-      "terse-prose": {
-        "label": "Prosa ringkas",
-        "description": "Buang kata pengisi, artikel, dan kata peragu dengan tetap menjaga substansi teknis secara tepat."
-      },
-      "less-code": {
-        "label": "Lebih sedikit kode",
-        "description": "Tangga YAGNI: perubahan kerja terkecil, tanpa abstraksi yang tidak diminta."
-      },
-      "ponytail": {
-        "label": "Ponytail (lazy senior dev)",
-        "description": "Lazy senior-dev discipline: climb the YAGNI ladder, fix root cause, smallest working diff."
-      },
-      "i-have-adhd": {
-        "label": "I have ADHD (action-first)",
-        "description": "Action-first output: next action leads, steps numbered, one concrete next step, no preamble."
-      },
-      "terse-cjk": {
-        "label": "CJK Ringkas (文言)",
-        "description": "Gaya ultra-ringkas Tionghoa Klasik (hanya tersedia untuk bahasa Tionghoa)."
-      }
-    },
-    "resilienceWaitForCooldown": "Tunggu Cooldown",
-    "resilienceEnableServerSideWait": "Aktifkan menunggu di sisi server",
-    "resilienceMaximumRetries": "Percobaan ulang maksimum",
-    "resilienceMaximumWaitPerRetry": "Waktu tunggu maksimum untuk setiap percobaan ulang",
-    "memorySkillsSkillsmpMarketplace": "Pasar KeterampilanMP",
-    "memorySkillsFailedToSave": "Gagal menyimpan",
-    "memorySkillsApiKey": "Kunci API",
-    "memorySkillsActiveSkillsProvider": "Penyedia Keterampilan Aktif",
-    "cliproxyapiFallback": "Penggantian CLIProxyAPI",
-    "cliproxyapiEnableFallback": "Aktifkan Penggantian CLIProxyAPI",
-    "cliproxyapiUrl": "URL CLIProxyAPI",
-    "cliproxyapiStatus": "Status CLIProxyAPI",
-    "cliproxyapiNotDetected": "Tidak terdeteksi",
-    "cliproxyapiImportAuthTitle": "Impor akun dari CLIProxyAPI",
-    "cliproxyapiImportAuthDesc": "Impor akun OAuth yang telah disimpan oleh CLIProxyAPI di ~/.cli-proxy-api/ sebagai koneksi OmniRoute, sehingga Anda tidak perlu masuk ke setiap akun lagi. Jenis akun yang didukung (Gemini, Codex, Claude, Antigravity, Qwen, Kimi) akan diimpor; yang lain akan dilewati.",
-    "cliproxyapiImportAuthButton": "Impor akun",
-    "payloadRulesTitle": "Aturan Muatan",
-    "payloadRulesDesc": "Konfigurasikan mutasi muatan permintaan berdasarkan model dan protokol. Perubahan disimpan dalam setelan dan langsung dimuat ulang ke runtime segera setelah disimpan.",
-    "payloadRuleDefaultTitle": "bawaan",
-    "payloadRuleDefaultDesc": "Menerapkan parameter hanya ketika jalur target hilang dari muatan keluar.",
-    "payloadRuleOverrideTitle": "timpa",
-    "payloadRuleOverrideDesc": "Memaksa nilai ke dalam muatan, menggantikan apa pun yang sudah ada pada jalur tersebut.",
-    "payloadRuleFilterTitle": "filter",
-    "payloadRuleFilterDesc": "Menghapus parameter yang diblokir dari payload sebelum permintaan upstream dikirim.",
-    "payloadRuleDefaultRawTitle": "defaultRaw",
-    "payloadRuleDefaultRawDesc": "Seperti default, tetapi nilai string diurai sebagai JSON terlebih dahulu jika memungkinkan. Alias input lawas default-raw juga diterima saat menyimpan.",
-    "payloadEditorTitle": "Editor",
-    "payloadEditorDesc": "Gunakan bentuk skema runtime: default, override, filter, defaultRaw. API juga menerima kunci input lawas default-raw.",
-    "payloadEditorReady": "Siap",
-    "payloadResetInfo": "Editor diatur ulang ke templat netral. Simpan untuk menerapkannya.",
-    "payloadSaveSuccess": "Aturan payload disimpan dan dimuat ulang seketika.",
-    "payloadJsonParseError": "Galat penguraian JSON: {error}",
-    "payloadMustBeObject": "Aturan payload harus berupa objek JSON.",
-    "payloadInvalidJson": "Payload JSON tidak valid.",
-    "payloadValidJsonRequired": "Aturan payload harus berupa JSON yang valid sebelum disimpan.",
-    "savePayloadRules": "Simpan Aturan Payload",
-    "requestLimitsTitle": "Batas Permintaan",
-    "requestLimitsDesc": "Konfigurasikan batas permintaan global dan pengaman konkurensi.",
-    "maxRequestSizeLabel": "Ukuran Permintaan Maks (MB)",
-    "maxRequestSizeDesc": "Ukuran maksimum yang diizinkan untuk permintaan API masuk.",
-    "maxResponseSizeLabel": "Ukuran Respons Maks (MB)",
-    "maxResponseSizeDesc": "Ukuran maksimum yang diizinkan untuk respons API keluar.",
-    "maxRequestTokensLabel": "Token Permintaan Maks",
-    "maxRequestTokensDesc": "Total token maksimum yang diizinkan dalam satu permintaan.",
-    "maxResponseTokensLabel": "Token Respons Maks",
-    "maxResponseTokensDesc": "Total token maksimum yang diizinkan dalam satu respons.",
-    "modelCooldownsTitle": "Model dalam cooldown",
-    "modelCooldownsEmpty": "Tidak ada model dalam cooldown saat ini.",
-    "modelCooldownsDescription": "Model diisolasi sementara setelah kegagalan. Saat masa jeda berakhir, model akan kembali secara otomatis.",
-    "modelCooldownsLoadFailed": "Gagal memuat masa jeda",
-    "modelCooldownReactivated": "Model diaktifkan kembali: {model}",
-    "modelCooldownClearFailed": "Gagal menghapus masa jeda",
-    "modelCooldownsAllReactivated": "Semua model dalam masa jeda telah diaktifkan kembali.",
-    "modelCooldownsClearFailed": "Gagal menghapus masa jeda",
-    "modelCooldownsReactivateAll": "Aktifkan kembali semua",
-    "modelCooldownsReasonRemaining": "alasan: {reason} • tersisa: {remaining}",
-    "modelCooldownsReactivate": "Aktifkan kembali",
-    "responsesStateTitle": "Status Respons",
-    "responsesStateDesc": "Kontrol cara OmniRoute meneruskan previous_response_id.",
-    "responsesStateModeLabel": "Penanganan previous_response_id",
-    "responsesStateModeAuto": "Otomatis",
-    "responsesStateModeStrip": "Hapus",
-    "responsesStateModePreserve": "Pertahankan",
-    "responsesStateHint": "Otomatis menghapus previous_response_id kecuali jika koneksi secara eksplisit mengaktifkan penyimpanan OpenAI Responses. Hapus adalah yang paling aman untuk klien stateless seperti VS Code Custom Endpoint; konteks kemudian bergantung pada klien yang mengirimkan riwayat lengkap.",
-    "responsesStateSaveError": "Gagal memperbarui setelan status Respons",
-    "codexFastTierTitle": "Tingkat Cepat Codex",
-    "codexFastTierDesc": "Menyuntikkan service_tier=priority secara global untuk permintaan OpenAI Codex.",
-    "codexFastTierHint": "Saat diaktifkan, OmniRoute menambahkan service_tier=priority ke permintaan Codex keluar untuk koneksi yang belum menentukan tingkat. Tingkat prioritas memerlukan kunci OpenAI Enterprise API atau jalur Codex autentikasi ChatGPT; jenis kunci lainnya akan menerima kesalahan terkait tingkatan dari OpenAI. Pengaturan per koneksi pada halaman penyedia Codex diutamakan.",
-    "codexFastTierSaveError": "Gagal memperbarui pengaturan Codex Fast Tier",
-    "codexAutoPingTitle": "Codex Quota Auto-Ping",
-    "codexAutoPingDesc": "Opt-in per connection: sends a tiny request right after a Codex session window resets so it isn't cold when you need it.",
-    "codexAutoPingWarning": "Consumes a small amount of real Codex quota on every ping. Off by default — enable only for connections you actively rely on.",
-    "codexAutoPingSaveError": "Failed to update Codex Auto-Ping setting",
-    "codexAutoPingToggleAria": "Toggle Codex quota auto-ping for {connection}",
-    "codexFastTierTierLabel": "Tingkat layanan",
-    "codexFastTierTierPriority": "Prioritas",
-    "codexFastTierTierFlex": "Flex",
-    "codexFastTierTierDefault": "Bawaan",
-    "codexFastTierModelsLabel": "Model tingkat cepat",
-    "codexFastTierModelsHint": "Hanya model yang dicentang yang menerima service_tier saat Fast Tier diaktifkan.",
-    "codexFastTierModelCheckbox": "Aktifkan Fast Tier untuk {model}",
-    "claudeFastModeTitle": "Mode Cepat Claude",
-    "claudeFastModeDesc": "Ikut sertakan permintaan Claude yang dipilih ke dalam Mode Cepat Antropik (kecepatan: \"cepat\").",
-    "claudeFastModeHint": "Anthropic tidak secara resmi mendukung Mode Cepat untuk klien bergaya SDK. Saat diaktifkan, OmniRoute meneruskan header X-CPA-Force-Fast-Mode sehingga build CLIProxyAPI yang dipasangkan dapat ikut serta memalsukan titik masuk. Hanya model Opus yang terdaftar yang dilindungi oleh pemeriksaan sisi klien Anthropic. Tingkat langganan, paket Maks, dan saldo kredit Mode Cepat masih diterapkan di sisi server — Anthropic dapat mengembalikan out_of_credits meskipun tombolnya aktif.",
-    "claudeFastModeModelsLabel": "Diterapkan pada model ({count})",
-    "claudeFastModeModelCheckbox": "Aktifkan Mode Cepat untuk {model}",
-    "claudeFastModeSaveError": "Gagal memperbarui pengaturan Mode Cepat Claude",
-    "authz": {
-      "cors": {
-        "wildcard": {
-          "title": "CORS terbuka untuk semua origin (CORS_ALLOW_ALL=true)",
-          "desc": "Situs web mana pun dapat memanggil API server ini dari peramban pengunjung. Gunakan hanya pada jaringan terpercaya — tetapkan origin secara eksplisit di ALLOWED_ORIGINS dan nonaktifkan CORS_ALLOW_ALL di produksi."
-        }
-      },
-      "title": "Inventaris Otorisasi",
-      "description": "Klasifikasi rute 5-tingkat dengan kebijakan bypass langsung. Read menampilkan taksonomi lengkap; mutasi meminta kembali kata sandi manajemen.",
-      "loading": "Memuat inventaris…",
-      "loadError": "Gagal memuat inventaris authz",
-      "tier": {
-        "LOCAL_ONLY": "Hanya lokal",
-        "ALWAYS_PROTECTED": "Selalu dilindungi",
-        "MANAGEMENT": "Manajemen",
-        "CLIENT_API": "API Klien",
-        "PUBLIC": "Publik"
-      },
-      "bypass": {
-        "section": "Bypass cakupan-manajemen",
-        "kill_switch": {
-          "label": "Kill-switch bypass",
-          "desc": "Tombol utama. Saat mati, tidak ada prefiks LOCAL_ONLY yang dapat dijangkau dari non-loopback terlepas dari daftar per-prefiks."
-        },
-        "prefix": {
-          "label": "Prefiks yang dapat dibypass",
-          "desc": "Prefiks LOCAL_ONLY yang dapat dijangkau oleh kunci API cakupan-manajemen (atau sesi dasbor) dari host non-loopback.",
-          "add": "Tambah prefiks",
-          "placeholder": "/api/mcp/v2/",
-          "empty": "Tidak ada prefiks yang dikonfigurasi. Bypass secara efektif mati."
-        },
-        "cli_tools_runtime_note": "Prefiks yang mendukung spawn. Penolakan waktu-kompilasi; tidak dapat dibuat agar bisa dibypass. Ditampilkan sebagai baca-saja."
-      },
-      "password": {
-        "prompt": {
-          "label": "Kata sandi saat ini",
-          "desc": "Konfirmasi ulang untuk menerapkan perubahan yang berdampak pada keamanan."
-        },
-        "placeholder": "Kata sandi manajemen saat ini",
-        "cancel": "Batal",
-        "submit": "Terapkan"
-      },
-      "save": "Simpan perubahan",
-      "saved": "Pengaturan authz diperbarui",
-      "pending": "Perubahan yang belum disimpan",
-      "badge": {
-        "bypassable": "Dapat dibypass melalui cakupan manajemen",
-        "strict": "Loopback ketat",
-        "auth_required": "Diperlukan autentikasi",
-        "public": "Publik",
-        "always_protected": "Selalu dilindungi",
-        "spawn_capable": "Mampu-spawn"
-      },
-      "error": {
-        "PASSWORD_REQUIRED": "Kata sandi saat ini diperlukan untuk menerapkan perubahan ini.",
-        "PASSWORD_MISMATCH": "Kata sandi saat ini salah.",
-        "INSUFFICIENT_SCOPE": "Kunci API tidak memiliki cakupan manage.",
-        "BYPASS_PREFIX_NOT_ALLOWED": "Satu atau beberapa prefiks menargetkan rute yang mampu-spawn dan tidak dapat dilewati.",
-        "GENERIC": "Gagal memperbarui setelan authz."
-      },
-      "remove": "Hapus"
-    },
-    "resilienceBaseCooldownLabel": "Cooldown dasar",
-    "scopeLabel": "Ruang lingkup",
-    "triggerLabel": "Pemicu",
-    "effectLabel": "Efek",
-    "statusEnabled": "Diaktifkan",
-    "statusDisabled": "Dengan disabilitas",
-    "resilienceRequestQueueScope": "Per antrian permintaan",
-    "resilienceRequestQueueTrigger": "Sebelum dikirim ke hulu",
-    "resilienceRequestQueueEffect": "Mengantri permintaan, membatasi konkurensi, dan membatasi panggilan",
-    "resilienceRequestQueueDesc": "Lapisan ini hanya mengontrol antrian dan mondar-mandir. Itu tidak menyimpan cooldown atau pemutus sirkuit terbuka.",
-    "resilienceAutoEnableApiKeyProvidersDesc": "Mengaktifkan perlindungan antrean secara default untuk koneksi kunci API aktif.",
-    "resilienceMaxQueueWait": "Waktu tunggu antrian maksimum",
-    "resilienceMaxExecutionWait": "Batas waktu eksekusi (batas pengaman rate-limit)",
-    "resilienceConnectionCooldownScope": "Koneksi individu",
-    "resilienceConnectionCooldownTrigger": "Ketika koneksi mengembalikan kegagalan hulu sementara",
-    "resilienceConnectionCooldownEffect": "Melewati koneksi itu untuk sementara dan meningkatkan backoff jika terjadi kegagalan berulang",
-    "resilienceConnectionCooldownDesc": "Cooldown dasar mencakup kegagalan koneksi sementara. Saat petunjuk percobaan ulang upstream diaktifkan, jendela eksplisit penyedia akan menggantikan cooldown lokal.",
-    "resilienceUseUpstreamRetryHintsDesc": "Menggunakan nilai coba lagi setelah/reset dari penyedia upstream bila tersedia.",
-    "resilienceUseUpstream429BreakerHints": "Gunakan petunjuk 429 hulu untuk cooldown pemutus",
-    "resilienceUseUpstream429BreakerHintsShort": "Gunakan petunjuk 429 hulu",
-    "resilienceUseUpstream429BreakerHintsDesc": "Menerapkan sinyal Retry-After / kuota habis dari 429 respons ke durasi cooldown pemutus sirkuit. Defaultnya menggunakan kebijakan per penyedia: default penyedia cloud langsung aktif; penyedia proksi terbalik, yang dihosting sendiri, dan didukung CLI tidak aktif secara default. Tidak bergantung pada \"Gunakan petunjuk coba ulang hulu\".",
-    "resilienceProviderBreakerScope": "Seluruh penyedia",
-    "resilienceProviderBreakerTrigger": "Kegagalan transportasi/server terakhir setelah penggantian koneksi habis",
-    "resilienceProviderBreakerEffect": "Blokir sementara penyedia tersebut hingga waktu penyetelan ulang berakhir",
-    "resilienceProviderBreakerDesc": "Status pemutusan langsung hanya muncul di halaman Kesehatan. Batas kecepatan 429 cakupan koneksi tetap berada dalam Masa Tenang Koneksi dan tidak membuat pemutus penyedia tersandung.",
-    "resilienceResetTime": "Atur ulang waktu",
-    "resilienceWaitForCooldownTitle": "Tunggu Cooldown",
-    "resilienceWaitForCooldownScope": "Permintaan klien saat ini",
-    "resilienceWaitForCooldownTrigger": "Ketika semua koneksi kandidat sudah cooldown",
-    "resilienceWaitForCooldownEffect": "Menunggu di server dan mencoba lagi ketika cooldown pertama berakhir",
-    "resilienceWaitForCooldownDesc": "Ini hanya mempengaruhi permintaan saat ini. Itu tidak menyimpan koneksi atau status penyedia.",
-    "resilienceEnableServerWait": "Aktifkan menunggu di sisi server",
-    "resilienceEnableServerWaitDesc": "Saat diaktifkan, OmniRoute menunggu hingga cooldown pertama berakhir dan mencoba lagi secara otomatis.",
-    "resilienceMaxAttempts": "Upaya maksimal",
-    "resilienceMaxWaitPerAttempt": "Penantian maksimum per upaya",
-    "resilienceComboCooldownWaitTitle": "Waktu tunggu cooldown kombo kuota-bersama",
-    "resilienceComboCooldownWaitDesc": "Hanya untuk kombo kuota-bersama: tunggu cooldown transien singkat dan kirim ulang alih-alih segera mengembalikan 429. Tidak pernah menunggu pada quota_exhausted.",
-    "resilienceComboCooldownWaitToggleDesc": "Hanya kombo kuota-bersama; tidak pernah menunggu pada quota_exhausted.",
-    "resilienceComboCooldownMaxWaitMs": "Tunggu maksimum per upaya",
-    "resilienceComboCooldownBudgetMs": "Total anggaran tunggu",
-    "resilienceQuotaShareConcurrencyTitle": "Konkurensi per-koneksi kuota-bersama",
-    "resilienceQuotaShareConcurrencyDesc": "Hanya untuk kombo kuota-bersama: ketika koneksi menetapkan batas Maks Konkuren (Max Concurrent), serialisasikan permintaan konkuren ke akun langganan tersebut agar tidak pernah dibanjiri melampaui batas atasnya. Permintaan berlebih menunggu dalam antrean alih-alih mendapatkan 429. Batas tersebut berasal dari bidang Max Concurrent di setiap koneksi; sakelar ini hanya mengaktifkan atau menonaktifkan kepatuhan terhadap batas tersebut.",
-    "resilienceQuotaShareConcurrencyToggleDesc": "Hanya kombo kuota-bersama; mematuhi batas Max Concurrent dari setiap koneksi.",
-    "resilienceProviderCooldownTitle": "Cooldown Penyedia",
-    "resilienceProviderCooldownScope": "Semua permintaan kombo",
-    "resilienceProviderCooldownTrigger": "Ketika penyedia/koneksi gagal",
-    "resilienceProviderCooldownEffect": "Melewati penyedia yang gagal selama periode cooldown sebelum mencoba lagi",
-    "resilienceProviderCooldownDesc": "Mencegah permintaan berikutnya untuk kembali menelusuri penyedia gagal yang sama. Cooldown meningkat secara eksponensial dengan kegagalan berturut-turut.",
-    "resilienceProviderCooldownEnabled": "Aktifkan cooldown penyedia global",
-    "resilienceProviderCooldownEnabledDesc": "Jika diaktifkan, penyedia yang gagal akan dilacak secara global dan dilewati selama periode cooldown.",
-    "resilienceProviderCooldownMin": "Cooldown minimum",
-    "resilienceProviderCooldownMax": "Cooldown maksimum",
-    "resilienceCredentialHealthTitle": "__MISSING__:Credential Health Check",
-    "resilienceCredentialHealthScope": "__MISSING__:All active API-key and OAuth connections",
-    "resilienceCredentialHealthTrigger": "__MISSING__:Periodically, on a fixed cadence",
-    "resilienceCredentialHealthEffect": "__MISSING__:Probes each connection's credential and marks it active/error; failed connections back off exponentially",
-    "resilienceCredentialHealthDesc": "__MISSING__:Background sweep that validates every active connection's credential by calling its provider. Set 0 to disable the sweep entirely. Per-connection Health Check values (on each connection's edit dialog) always override this global default.",
-    "resilienceCredentialHealthInterval": "__MISSING__:Global check interval",
-    "resilienceCredentialHealthEveryMinutes": "__MISSING__:Every {minutes} min",
-    "resilienceCredentialHealthHint": "__MISSING__:0 disables the background sweep (max 1440 min = 24 h). Connections with their own Health Check value ignore this global default; a per-connection 0 opts that connection out even when the global sweep is on.",
-    "forcedFingerprintTitle": "Always enabled for {provider} — required for OAuth account safety; cannot be turned off.",
-    "forcedFingerprintBadge": "Required",
-    "sessionAffinityTitle": "Afinitas sesi",
-    "sessionAffinityDesc": "Menjaga satu percakapan pada akun yang sama selama sekian detik ini, untuk penyedia mana pun. 0 menonaktifkannya.",
-    "sessionAffinityTtl": "TTL Afinitas (detik)",
-    "resetAwareQuotaCacheTitle": "Cache kuota yang dapat disetel ulang",
-    "resetAwareQuotaCacheDesc": "Menyimpan telemetri kuota dalam cache hanya untuk pemesanan yang diatur ulang. Preflight kuota tetap melindungi permintaan. 0/0 terus mengambil langsung.",
-    "resetAwareQuotaCacheTtl": "TTL baru (detik)",
-    "resetAwareQuotaCacheMaxStale": "Maks basi (detik)",
-    "qdrantCleanupSuccess": "Oke: menghapus {count} poin (retensi: {days} hari)",
-    "qdrantCleanupFailed": "Pembersihan gagal",
-    "qdrantCleanupError": "Kesalahan: {error}",
-    "vercelRelaySuccess": "Relay Vercel berhasil di-deploy",
-    "vercelRelayButton": "Deploy Relay Vercel",
-    "vercelRelayModalTitle": "Deploy Relay Vercel",
-    "vercelRelayWarning": "Peringatan: Token deployment Vercel diperlukan. Token ini hanya akan digunakan untuk membuat relay serverless dan tidak akan pernah disimpan oleh OmniRoute.",
-    "vercelRelayTokenLabel": "Token Akses Vercel",
-    "vercelRelayProjectNameLabel": "Nama Proyek Vercel",
-    "vercelRelayFreeTierNote": "Relay adalah endpoint proksi ringan yang di-deploy pada tingkat gratis Vercel untuk melewati batasan jaringan/wilayah lokal.",
-    "vercelRelayDeploying": "Mendeploy...",
-    "vercelRelayDeploy": "Deploy",
-    "deployRelayButton": "Deploy Relay",
-    "denoRelayButton": "Deploy Relay Deno",
-    "denoRelayModalTitle": "Deploy Relay Deno",
-    "denoRelayWarning": "Peringatan: Token organisasi Deno Deploy diperlukan. Token ini hanya akan digunakan untuk membuat aplikasi relay dan tidak akan pernah disimpan oleh OmniRoute.",
-    "denoRelayTokenLabel": "Token Organisasi Deno Deploy",
-    "denoRelayOrgDomainLabel": "Domain Organisasi",
-    "denoRelayProjectNameLabel": "Nama Aplikasi Deno",
-    "denoRelayFreeTierNote": "Deno Deploy v2 berjalan pada jaringan edge global. Tingkat gratis: 1 juta permintaan & 100GiB lalu lintas keluar per bulan, tanpa batasan CPU per permintaan, hingga 20 aplikasi aktif & 50 domain kustom.",
-    "denoRelayDeploying": "Menyebarkan...",
-    "denoRelayDeploy": "Sebarkan",
-    "cloudflareRelaySuccess": "Relay Cloudflare berhasil disebarkan",
-    "cloudflareRelayButton": "Sebarkan Relay Cloudflare",
-    "cloudflareRelayModalTitle": "Sebarkan Relay Worker Cloudflare",
-    "cloudflareRelayWarning": "Menyebarkan Worker Cloudflare yang memproksi permintaan LLM melalui jaringan edge Cloudflare — menyamarkan IP host di balik alamat Cloudflare dinamis. Worker tersebut menerapkan rahasia autentikasi sekali pakai sehingga URL workers.dev publik tidak dapat digunakan kembali sebagai relay terbuka.",
-    "cloudflareRelayTokenHowto": "Buat token API di bawah Profil Saya -> Token API -> Buat Token -> Token Kustom -> Akun / Skrip Worker / Edit.",
-    "cloudflareRelayAccountIdLabel": "ID Akun Cloudflare",
-    "cloudflareRelayAccountIdHint": "Ditemukan di sisi kanan halaman ikhtisar dasbor Cloudflare.",
-    "cloudflareRelayApiTokenLabel": "Token API Cloudflare",
-    "cloudflareRelayApiTokenHint": "Memerlukan izin 'Workers Scripts: Edit'. Token ini hanya digunakan pada saat penyebaran dan tidak pernah disimpan.",
-    "cloudflareRelayProjectNameLabel": "Nama Worker",
-    "cloudflareRelayFreeTierNote": "Tingkat gratis: 100.000 permintaan/hari per akun Cloudflare.",
-    "cloudflareRelayDeploying": "Menyebarkan...",
-    "cloudflareRelayDeploy": "Sebarkan",
-    "cloudflareRelayCredsRequired": "ID Akun dan Token API diperlukan",
-    "cloudflareRelayDeployFailed": "Penyebaran gagal",
-    "modelLockout": "Penguncian Model",
-    "modelLockoutPageDescription": "Konfigurasikan kode kesalahan HTTP mana yang memicu penguncian per-model dan kendalikan perilaku masa tenang.",
-    "modelLockoutLoadFailed": "Gagal memuat pengaturan penguncian model",
-    "modelLockoutSaveFailed": "Gagal menyimpan pengaturan penguncian model",
-    "modelLockoutLoading": "Memuat pengaturan penguncian model...",
-    "modelLockoutBaseRangeError": "Masa Tenang Dasar harus antara 5.000ms dan 600.000ms",
-    "modelLockoutMaxRangeError": "Masa Tenang Maksimum harus antara 5.000ms dan 3.600.000ms",
-    "modelLockoutOrderError": "Masa Tenang Maksimum harus lebih besar dari atau sama dengan Masa Tenang Dasar",
-    "modelLockoutStepsRangeError": "Langkah Backoff Maksimum harus antara 0 dan 20",
-    "removeErrorCode": "Hapus {code}",
-    "addErrorCode": "Tambah kode kesalahan...",
-    "suggestions": "Saran:",
-    "modelLockoutMaxCooldownHint": "≥ Masa Tenang Dasar — 3.600.000ms",
-    "modelLockoutEnabled": "Aktifkan Penguncian Model",
-    "modelLockoutEnabledDescription": "Jika diaktifkan, model yang gagal dengan kode kesalahan yang dikonfigurasi akan dikunci sementara untuk mencegah perulangan percobaan kembali.",
-    "modelLockoutErrorCodes": "Kode Kesalahan",
-    "modelLockoutErrorCodesDescription": "Kode status HTTP yang memicu penguncian model. Ketik kode dan klik Tambah, atau pilih dari saran.",
-    "modelLockoutBaseCooldown": "Masa Tenang Dasar (ms)",
-    "modelLockoutBaseCooldownDescription": "Durasi masa tenang awal dalam milidetik sebelum model dapat dicoba kembali.",
-    "modelLockoutMaxCooldown": "Masa Tenang Maksimum (ms)",
-    "modelLockoutMaxCooldownDescription": "Durasi pendinginan maksimum dalam milidetik. Mencegah penguncian yang terlalu lama.",
-    "modelLockoutExponentialBackoff": "Backoff Eksponensial",
-    "modelLockoutExponentialBackoffDescription": "Jika diaktifkan, setiap kegagalan berturut-turut akan meningkatkan durasi pendinginan secara eksponensial.",
-    "modelLockoutMaxBackoffSteps": "Langkah Backoff Maksimum",
-    "modelLockoutMaxBackoffStepsDescription": "Jumlah maksimum langkah backoff sebelum durasi pendinginan berhenti bertambah. Batas Pendinginan Maksimum biasanya dicapai lebih dulu pada sebagian besar konfigurasi, menjadikan ini sebagai batas pengaman ketika Pendinginan Maksimum dinaikkan.",
-    "disableSessionStickiness": "Nonaktifkan kelekatan sesi",
-    "disableSessionStickinessDesc": "Kombo round-robin dan acak beralih ke koneksi yang berbeda pada setiap permintaan, alih-alih menetapkan seluruh percakapan ke satu koneksi berdasarkan hash pesan pertama. Biarkan nonaktif untuk mempertahankan hit prompt-cache pada obrolan multi-putaran. Pengabaian per-kombo memiliki prioritas lebih tinggi.",
-    "promptCacheAffinity": "Prompt-cache locality routing",
-    "promptCacheAffinityDesc": "Prefer the same provider account for matching prompt-cache keys while preserving health and quota failover.",
-    "reasoningTokenBuffer": "Reasoning token buffer",
-    "reasoningTokenBufferDesc": "Allow combo routing to add max_tokens headroom only for known reasoning models when the full buffer fits inside a known output cap.",
-    "zeroLatencyOptimizations": "Zero-latency optimizations",
-    "zeroLatencyOptimizationsDesc": "Opt in to hedging, predictive TTFT skips, and proactive fallback compression. Leave off to prevent these latency features from racing targets or compressing fallback requests.",
-    "credentialRedaction": "Redaksi Kredensial",
-    "credentialRedactionDesc": "Redaksikan kunci API, token, dan rahasia dari konteks yang dikirim ke penyedia dan dari respons.",
-    "enableCredentialRedaction": "Aktifkan redaksi kredensial",
-    "enableCredentialRedactionDesc": "Membersihkan kunci API, token, kunci privat, dan JWT dari pesan, panggilan alat, dan respons.",
-    "pricingAutoSyncDisabled": "Automatic Sync Disabled",
-    "pricingAutoSyncEnabled": "Automatic Sync Enabled",
-    "modalityBridgeIntro": "Ubah konten multimodal menjadi teks sebelum mencapai model khusus teks. Jembatan visi, audio, dan video tersedia serta dapat dikonfigurasi.",
-    "modalityBridgeVisionTab": "Visi",
-    "modalityBridgeAudioTab": "Audio",
-    "modalityBridgeVideoTab": "Video",
-    "modalityBridgeSubTabsAria": "Bagian Jembatan Modalitas",
-    "modalityBridgeVisionTitle": "Jembatan Visi",
-    "modalityBridgeVisionDesc": "Deskripsikan gambar dengan model visi dan lanjutkan dengan model teks yang dipilih pengguna.",
-    "modalityBridgeMode": "Mode",
-    "modalityBridgeModeAuto": "Otomatis (disarankan)",
-    "modalityBridgeModeAutoHint": "Heuristik warisan: alihkan model individu tanpa kredensial; jelaskan sebaliknya.",
-    "modalityBridgeModeDescribe": "Selalu deskripsikan",
-    "modalityBridgeModeDescribeHint": "Model yang Anda pilih selalu menjawab; gambar digantikan oleh deskripsi teks.",
-    "modalityBridgeModeReroute": "Selalu alihkan",
-    "modalityBridgeModeRerouteHint": "Kirim seluruh permintaan ke model dengan kemampuan visi terbaik (kembali ke deskripsi ketika tidak ada yang dapat digunakan).",
-    "modalityBridgeVisionModel": "Model Visi",
-    "modalityBridgeVisionModelAuto": "Otomatis (terbaik yang tersedia)",
-    "modalityBridgeTaskAware": "Deskripsi yang Sadar Tugas",
-    "modalityBridgeTaskAwareDesc": "Sertakan pertanyaan pengguna sebagai fokus sehingga model visi menggambarkan apa yang penting dan mentranskripsikan teks yang terlihat.",
-    "modalityBridgePrompt": "Deskripsi prompt",
-    "modalityBridgeAdvanced": "Lanjutan",
-    "modalityBridgeTimeoutMs": "Waktu Habis (ms)",
-    "modalityBridgeMaxImages": "Maksimal gambar per permintaan",
-    "visionMaxCharsLabel": "Karakter deskripsi maksimum",
-    "visionMaxCharsHint": "Batasi panjang deskripsi model visi. 0 = tidak terbatas — tingkatkan untuk tugas OCR yang kaya detail.",
-    "modalityBridgeCacheEnabled": "Deskripsi cache",
-    "modalityBridgeCacheEnabledDesc": "Gunakan deskripsi yang sama untuk gambar yang identik (berbasis SHA-256, di memori).",
-    "modalityBridgeCacheTtlMinutes": "Cache TTL (menit)",
-    "modalityBridgeCacheMaxEntries": "Cache maksimum entri",
-    "modalityBridgeStatsBridged": "jembatan",
-    "modalityBridgeStatsCacheHits": "cache hits",
-    "modalityBridgeStatsFailures": "kegagalan",
-    "modalityBridgeStatsLastUsed": "terakhir digunakan",
-    "modalityBridgeStatsNever": "tidak pernah",
-    "modalityBridgeTestButton": "Uji dengan gambar contoh",
-    "modalityBridgeTestRunning": "Pengujian…",
-    "modalityBridgeTestOk": "Bridge OK — {count} gambar yang dijelaskan oleh {model}",
-    "modalityBridgeTestReroute": "Jembatan mengalihkan permintaan ke {model}",
-    "modalityBridgeTestNoop": "Jembatan tidak diaktifkan (model mungkin mendukung visi secara native atau jembatan dinonaktifkan)",
-    "modalityBridgeTestError": "Uji coba gagal: {message}",
-    "modalityBridgeAudioComingSoon": "Jembatan Audio (ucapan → teks melalui /v1/audio/transcriptions) akan hadir di rilis berikutnya. Kunci pengaturannya sudah dipesan.",
-    "modalityBridgeMovedTitle": "Vision Bridge dipindahkan",
-    "modalityBridgeMovedBody": "Pengaturan Vision Bridge sekarang tersedia di halaman Modality Bridge yang khusus.",
-    "modalityBridgeMovedCta": "Buka pengaturan Jembatan Modality",
-    "modalityBridgeAudioTitle": "Jembatan Audio",
-    "modalityBridgeAudioDesc": "Transkripsikan audio dengan model ucapan-ke-teks sebelum melanjutkan dengan model teks yang dipilih.",
-    "modalityBridgeAudioEnabled": "Aktifkan Jembatan Audio",
-    "modalityBridgeAudioEnabledDesc": "Ganti bagian audio dengan transkrip ketika model target tidak dapat memproses audio.",
-    "modalityBridgeAudioModel": "Model Ucapan-ke-Teks",
-    "modalityBridgeAudioModelAuto": "Auto (penyedia STT yang terhubung pertama)",
-    "modalityBridgeAudioMaxClips": "Maksimal klip audio per permintaan",
-    "modalityBridgeAudioTestButton": "Uji dengan audio contoh",
-    "modalityBridgeAudioTestRunning": "Menguji audio…",
-    "modalityBridgeAudioTestOk": "Audio Bridge OK — {count} klip telah ditranskripsi oleh {model}",
-    "modalityBridgeAudioTestNoop": "Audio Bridge tidak diaktifkan (target mungkin mendukung audio, tidak ada penyedia STT yang terhubung, atau jembatan dinonaktifkan)",
-    "modalityBridgeAudioTestError": "Uji audio gagal: {message}",
-    "modalityBridgeVideoTitle": "Jembatan Video",
-    "modalityBridgeVideoDesc": "Ambil sampel bingkai video, deskripsikan dengan model visi, lalu lanjutkan dengan model teks yang dipilih.",
-    "modalityBridgeVideoRuntimeReady": "Runtime siap",
-    "modalityBridgeVideoRuntimeChecking": "Memeriksa runtime…",
-    "modalityBridgeVideoRuntimeUnavailable": "Runtime tidak tersedia",
-    "modalityBridgeVideoRuntimeInstall": "Pasang FFmpeg dan ffprobe di PATH server untuk mengaktifkan ekstraksi video.",
-    "modalityBridgeVideoEnabled": "Aktifkan Jembatan Video",
-    "modalityBridgeVideoEnabledDesc": "Ganti bagian video dengan deskripsi bingkai berstempel waktu ketika model tujuan tidak dapat memproses video.",
-    "modalityBridgeVideoModel": "Model deskripsi bingkai",
-    "modalityBridgeVideoModelInherited": "Gunakan model Jembatan Visi",
-    "modalityBridgeVideoFrameCount": "Bingkai per video",
-    "modalityBridgeVideoMaxVideos": "Maksimum video per permintaan",
-    "modelRoutingDescriptionPlaceholder": "Rute Model Opus ke Kombinasi Frontier",
-    "cliproxyapiFallbackCodes": "Kode Cadangan Cliproxyapi",
-    "cliproxyapiFallbackDescription": "Deskripsi Cadangan Cliproxyapi",
-    "cliproxyapiHealthLabel": "Label Kesehatan Cliproxyapi",
-    "cliproxyapiImportFailed": "Cliproxyapi Gagal Diimpor",
-    "cliproxyapiImportResult": "Hasil Impor Cliproxyapi",
-    "cliproxyapiInvalidUrl": "Cliproxyapi URL Tidak Valid",
-    "cliproxyapiLifecycleNoticeAfter": "Pemberitahuan Siklus Hidup Cliproxyapi Setelah",
-    "cliproxyapiLifecycleNoticeBefore": "Pemberitahuan Siklus Hidup Cliproxyapi Sebelum",
-    "cliproxyapiLifecycleNoticeLink": "Tautan Pemberitahuan Siklus Hidup Cliproxyapi",
-    "cliproxyapiPortLabel": "Label Port Cliproxyapi",
-    "cliproxyapiStatusLabel": "Label Status Cliproxyapi",
-    "cliproxyapiVersionLabel": "Label Versi Cliproxyapi",
-    "collection": "Koleksi",
-    "errorPage": {
-      "description": "Kami tidak dapat memuat pengaturan saat ini. Silakan coba lagi dalam beberapa detik.",
-      "errorId": "ID Kesalahan: {id}",
-      "retry": "Coba Lagi",
-      "title": "Gagal memuat pengaturan"
-    },
-    "host": "Tuan Rumah",
-    "notInstalled": "Tidak terpasang",
-    "oneproxyActions": "Tindakan Oneproxy",
-    "oneproxyActive": "Oneproxy Aktif",
-    "oneproxyAnonymity": "Anonymitas Oneproxy",
-    "oneproxyCountry": "Negara Oneproxy",
-    "oneproxyDelete": "Oneproxy Hapus",
-    "oneproxyEmpty": "Oneproxy Kosong",
-    "oneproxyHost": "Oneproxy Host",
-    "oneproxyLatency": "Oneproxy Latensi",
-    "oneproxyProtocol": "Protokol Oneproxy",
-    "oneproxyQuality": "Kualitas Oneproxy",
-    "oneproxySyncFailed": "Sinkronisasi gagal: {error}",
-    "oneproxySyncSuccess": "Disinkronkan {total} proxy ({added} baru, {updated} diperbarui)",
-    "proxyDocumentationSocks5DescAfter": "Dokumentasi Proxy Socks5 Desc Setelah",
-    "proxyFreePoolAddProxy": "Tambahkan Proxy Kolam Gratis",
-    "proxyFreePoolAdding": "Menambahkan Kolam Proxy Gratis",
-    "proxyFreePoolSelectProxy": "Pilih Proxy Kolam Gratis",
-    "proxyStatusActive": "Status Proxy Aktif",
-    "proxyStatusInactive": "Status Proxy Tidak Aktif",
-    "routingAddEntry": "Tambahkan entri",
-    "settingSaveFailed": "Penyimpanan Pengaturan Gagal",
-    "settingSaved": "Pengaturan Disimpan",
-    "skillsmpApiKeyHintAfter": ". Batas permintaan: {limit} permintaan/hari.",
-    "skillsmpApiKeyHintBefore": "Dapatkan kunci API Anda dari",
-    "syncFailed": "Sinkronisasi gagal",
-    "unhealthy": "Tidak Sehat",
-    "oneproxyDescription": "Ambil dan putar proxy yang divalidasi gratis dari platform komunitas 1proxy",
-    "oneproxySyncing": "Menyinkronkan...",
-    "oneproxySyncNow": "Sinkronkan Sekarang",
-    "oneproxyClearAll": "Bersihkan Semua",
-    "oneproxyGoogle": "Google",
-    "oneproxyClearAllConfirm": "Hapus semua proksi 1proxy?",
-    "memorySkillsSkillsmpDescription": "Sambungkan ke SkillsMP untuk menemukan dan menginstal keterampilan dari pasar.",
-    "memorySkillsActiveProviderDescription": "Pilih penyedia mana yang digunakan halaman Keterampilan untuk pencarian dan instalasi.",
-    "memorySkillsSkillsmpProviderTitle": "Pasar SkillsMP",
-    "memorySkillsSkillsmpProviderDescription": "Marketplace yang Terautentikasi (menggunakan kunci API SkillsMP Anda).",
-    "memorySkillsSkillsshProviderTitle": "Direktori skills.sh",
-    "memorySkillsSkillsshProviderDescription": "Penyedia direktori publik (tidak memerlukan kunci API).",
-    "routingCcBridgeCatalogName": "Jembatan CC yang kompatibel dengan Anthropic",
-    "routingClaudeProviderName": "Claude (OAuth)",
-    "routingClaudeProviderDescription": "Penyedia Claude asli dengan token yang diterbitkan oleh OAuth.",
-    "routingCcBridgeName": "Jembatan Claude-Code",
-    "routingCcBridgeDescription": "Titik akhir relay menggunakan kunci API (anthropic-compatible-cc-*).",
-    "routingCustomProviderDescription": "Penyedia kustom.",
-    "routingUnknownOpKind": "Jenis op tidak dikenal: {kind}",
-    "routingInvalidJson": "JSON Tidak Valid: {error}",
-    "routingConfigMustBeObject": "Konfigurasi harus berupa objek JSON",
-    "routingEnabledMustBeBoolean": "`enabled` harus true atau false",
-    "routingPipelineMustBeArray": "`pipeline` harus berupa array ops",
-    "routingPipelineTooLong": "Pipeline tidak boleh melebihi 50 ops",
-    "routingOpMissingKind": "Op #{index}: `kind` hilang atau tidak valid",
-    "routingOpUnknownKind": "Op #{index}: jenis tidak dikenal \"{kind}\"",
-    "routingJsonEditorHide": "Sembunyikan editor JSON",
-    "routingJsonEditorImportExport": "Impor / ekspor JSON",
-    "routingJsonEditorLabel": "JSON (edit dan terapkan, atau tempel untuk mengimpor)",
-    "routingApplyJson": "Terapkan JSON",
-    "routingTransformsFootnote": "Semua operasi transformasi bersifat idempoten pada pengulangan. Perubahan berlaku segera pada permintaan berikutnya.",
-    "cliproxyapiUnknown": "Tidak Dikenal",
-    "cliproxyapiVersion": "Versi",
-    "cliproxyapiHealth": "Kesehatan",
-    "cliproxyapiPort": "Port",
-    "qdrantHost": "Tuan Rumah",
-    "qdrantCollection": "Koleksi"
-  },
-  "contextRtk": {
-    "title": "RTK Engine",
-    "description": "Command-aware compression for tool output, terminal logs and build results.",
-    "enabled": "Enabled",
-    "intensity": "Intensity",
-    "intensityMinimal": "Minimal",
-    "intensityStandard": "Standard",
-    "intensityAggressive": "Aggressive",
-    "toolResults": "Tool results",
-    "assistantMessages": "Assistant messages",
-    "codeBlocks": "Code blocks",
-    "filterCatalog": "Katalog Filter",
-    "filterCatalogDesc": "Filter keluaran tersedia berdasarkan kategori",
-    "guidedConfig": "Konfigurasi",
-    "guidedConfigDesc": "Sesuaikan cara RTK memfilter keluaran terminal Anda",
-    "maxLines": "Max lines",
-    "maxChars": "Max chars",
-    "deduplicateThreshold": "Ambang batas penghapusan duplikat",
-    "customFilters": "Filter khusus",
-    "detectedType": "Tipe terdeteksi",
-    "confidence": "Keyakinan",
-    "beforeAfter": "Sebelum / Sesudah",
-    "trustProjectFilters": "Percayai filter proyek",
-    "rawOutputRetention": "Retensi keluaran mentah",
-    "rawOutputNever": "Tidak pernah",
-    "rawOutputFailures": "Kegagalan",
-    "rawOutputAlways": "Selalu",
-    "rawOutputMaxBytes": "Byte maks keluaran mentah",
-    "filterTesting": "Filter Testing",
-    "pasteOutput": "Paste tool output to test filtering...",
-    "presetHigh": "Agresif",
-    "presetLow": "Ringan",
-    "presetMaxChars": "Karakter keluaran maksimal",
-    "presetMaxLines": "Jalur keluaran maksimal",
-    "presetMedium": "Standar",
-    "run": "Run",
-    "result": "Result",
-    "previewEmpty": "Run a sample to preview RTK output.",
-    "detected": "Detected",
-    "masterSwitchOffAlert": "Sakelar utama Penghemat Token dalam keadaan MATI — pengaturan ini tidak akan memengaruhi permintaan hingga Anda mengaktifkannya dari halaman Titik Akhir.",
-    "tokensFiltered": "Tokens filtered",
-    "filtersActive": "Filters active",
-    "requests": "Requests",
-    "avgSavings": "Avg savings",
-    "simpleMode": "Sederhana",
-    "advancedMode": "Lanjutan",
-    "searchFilters": "Filter pencarian...",
-    "tooltipDedup": "Betapa agresifnya menghilangkan garis yang berulang.",
-    "tooltipMaxChars": "Karakter maksimum per blok keluaran.",
-    "tooltipMaxLines": "Garis maksimum yang harus dijaga dari keluaran perintah. Kelebihannya terpotong.",
-    "learnDiscoverTitle": "Pelajari & Temukan filter",
-    "learnDiscoverDesc": "Gali output perintah yang Anda tangkap (retensi Output Mentah harus aktif) untuk menyarankan filter RTK baru. Hanya saran — Anda meninjau dan menyimpannya.",
-    "discoverHeading": "Temukan derau berulang",
-    "discoverButton": "Pindai sampel",
-    "discoverScanning": "Memindai…",
-    "discoverEmpty": "Tidak ada derau berulang yang ditemukan. Aktifkan retensi Output Mentah dan jalankan beberapa perintah terlebih dahulu.",
-    "discoverSamples": "{count} sampel dipindai",
-    "discoverHits": "{hits}× di seluruh sampel",
-    "learnHeading": "Pelajari filter untuk suatu perintah",
-    "learnCommandPlaceholder": "mis. npm install",
-    "learnButton": "Sarankan filter",
-    "learnEmpty": "Belum ada saran. Ketik perintah yang telah Anda jalankan lalu pindai.",
-    "learnSamplesUsed": "Dipelajari dari {count} sampel yang cocok",
-    "suggestionError": "Gagal memuat saran. Periksa autentikasi manajemen dan coba lagi.",
-    "tomlImportTitle": "Impor filter TOML RTK",
-    "tomlImportDesc": "Validasi filter skema v1 TOML RTK dan pasang secara global. Pemasangan akan menulis ke DATA_DIR/rtk/filters.toml; berkas yang ada hanya akan diganti setelah konfirmasi eksplisit.",
-    "tomlChooseFile": "Pilih berkas TOML",
-    "tomlImportPlaceholder": "Tempel konten filters.toml RTK di sini...",
-    "tomlValidate": "Validasi",
-    "tomlValidating": "Memvalidasi…",
-    "tomlInstall": "Pasang secara global",
-    "tomlInstalling": "Memasang…",
-    "tomlConfirmOverwrite": "Ganti berkas global yang ada dan buat cadangan",
-    "tomlValidationPassed": "Validasi berhasil",
-    "tomlValidationFailed": "Validasi selesai dengan pengujian inline yang gagal",
-    "tomlValidationSummary": "{filters} filter, {tests} pengujian inline",
-    "tomlInstalled": "Dipasang di {path}",
-    "tomlBackupCreated": "Cadangan dari berkas sebelumnya telah dibuat.",
-    "tomlTestCount": "{count} pengujian",
-    "tomlTestPassed": "Lulus",
-    "tomlTestFailed": "Gagal",
-    "tomlImportError": "Tidak dapat memproses berkas TOML RTK.",
-    "tomlFileReadError": "Tidak dapat membaca berkas TOML yang dipilih."
-  },
-  "compressionEngineConfig": {
-    "loading": "Memuat…",
-    "loadFailed": "Gagal memuat informasi mesin.",
-    "engineNotFound": "Mesin \"{engine}\" tidak ditemukan.",
-    "saveFailed": "Gagal menyimpan konfigurasi.",
-    "previewFailed": "Pratinjau gagal.",
-    "panelPointerPrefix": "Aktifkan atau nonaktifkan lapisan ini dan atur tingkatannya di",
-    "compressionSettings": "Pengaturan Kompresi",
-    "panelPointerSuffix": ". Halaman ini hanya mengedit konfigurasi detailnya.",
-    "configuration": "Konfigurasi",
-    "noAdditionalConfiguration": "Tidak ada konfigurasi tambahan.",
-    "save": "Simpan",
-    "saving": "Menyimpan…",
-    "globalSettingsOnly": "Lapisan ini dikonfigurasi oleh pengaturan global; belum ada pengabaian per-mesin yang dapat disimpan di sini.",
-    "preview": "Pratinjau",
-    "previewInput": "Pratinjau masukan",
-    "processing": "Memproses…",
-    "previewSample": "Rubah cokelat yang cepat melompati anjing yang malas. Ini adalah contoh pesan yang digunakan untuk pratinjau kompresi. Ini berisi cukup teks untuk menunjukkan penghematan token yang berarti.",
-    "originalTokens": "Token asli",
-    "compressedTokens": "Token terkompresi",
-    "savings": "Penghematan",
-    "original": "Asli",
-    "compressed": "Terkompresi",
-    "diff": "Perbedaan",
-    "last7Days": "7 hari terakhir",
-    "noDataYet": "Belum ada data",
-    "runs": "Eksekusi",
-    "tokensSaved": "Token yang dihemat",
-    "averageSavings": "Rata-rata penghematan",
-    "diffLabels": {
-      "change": "Perubahan",
-      "added": "Ditambahkan",
-      "removed": "Dihapus",
-      "modified": "Diubah"
-    },
-    "engines": {
-      "headroom": {
-        "name": "Headroom SmartCrusher",
-        "description": "Kompaksi tabular tanpa kehilangan (lossless) dari larik JSON homogen dengan penanda jumlah baris eksplisit."
-      },
-      "session-dedup": {
-        "name": "Deduplikasi Sesi",
-        "description": "Dedupikasi blok lintas-giliran dengan penanda konten yang dapat dipulihkan."
-      },
-      "ccr": {
-        "name": "CCR",
-        "description": "Penanda pengambilan berbasis alamat konten untuk blok konteks berulang."
-      },
-      "llmlingua": {
-        "name": "LLMLingua-2 (Pemangkasan Semantik)",
-        "description": "Klasifikasi token semantik berbasis ONNX. Hanya mengompresi prosa; blok kode dan konstruksi yang dipertahankan dilindungi. Gagal terbuka pada kesalahan model atau pekerja."
-      },
-      "lite": {
-        "name": "Ringan",
-        "description": "Pengurangan cepat spasi kosong, hasil alat, dan URL gambar."
-      },
-      "aggressive": {
-        "name": "Agresif",
-        "description": "Peringkasan, kompresi hasil alat, dan penuaan progresif."
-      },
-      "ultra": {
-        "name": "Ultra",
-        "description": "Pemangkasan token heuristik dengan cadangan SLM lokal opsional."
-      }
-    },
-    "fields": {
-      "minBlockChars": {
-        "label": "Karakter blok minimum",
-        "description": "Jumlah karakter minimum agar blok sufiks menjadi kandidat dedupikasi."
-      },
-      "fuzzy": {
-        "label": "Dedupikasi hampir-duplikat samar",
-        "description": "Aktifkan opsi untuk mengganti seluruh pesan yang setidaknya sekitar 85% mirip dengan pesan sebelumnya dengan penanda CCR yang dapat dipulihkan."
-      },
-      "minChars": {
-        "label": "Karakter blok minimum",
-        "description": "Jumlah karakter minimum agar blok menjadi kandidat CCR."
-      },
-      "retrievalRampFactor": {
-        "label": "Faktor peningkatan pengambilan (H8)",
-        "description": "Mengontrol seberapa kuat blok yang sering diambil menolak kompresi. Setiap pengambilan sebelumnya meningkatkan ukuran blok minimum efektif secara linier; 1 menonaktifkan peningkatan."
-      },
-      "model": {
-        "label": "Model"
-      },
-      "minTokens": {
-        "label": "Token minimum (batas bawah)"
-      },
-      "compressionRate": {
-        "label": "Rasio kompresi"
-      },
-      "modelPath": {
-        "label": "Jalur model"
-      },
-      "minRows": {
-        "label": "Baris minimum untuk dipadatkan",
-        "description": "Jumlah baris minimum dalam larik JSON homogen yang diperlukan untuk memicu pemadatan tabular. Default: 8."
-      },
-      "preserveSystemPrompt": {
-        "label": "Pertahankan prompt sistem"
-      },
-      "summarizerEnabled": {
-        "label": "Aktifkan peringkas"
-      },
-      "maxTokensPerMessage": {
-        "label": "Token maksimum per pesan"
-      },
-      "minSavingsThreshold": {
-        "label": "Ambang batas penghematan minimum"
-      },
-      "minScoreThreshold": {
-        "label": "Ambang batas skor minimum"
-      },
-      "slmFallbackToAggressive": {
-        "label": "Kembali ke Agresif"
-      },
-      "intensity": {
-        "label": "Intensitas"
-      },
-      "minMessageLength": {
-        "label": "Panjang pesan minimum"
-      },
-      "compressToolResults": {
-        "label": "Secara proaktif memotong hasil alat yang panjang",
-        "description": "Memotong hasil alat lebih dari 2.000 karakter selama kompresi Lite. Perlindungan overflow darurat mungkin masih memangkas konten ketika konteks melebihi anggaran model."
-      }
-    },
-    "engineFields": {
-      "llmlingua": {
-        "compressionRate": {
-          "label": "Rasio kompresi (rasio pertahankan)"
-        },
-        "modelPath": {
-          "label": "Jalur model (pengabaian luring)"
-        }
-      }
-    },
-    "options": {
-      "model": {
-        "tinybert": "TinyBERT (57 MB, cepat — default)",
-        "bert-base": "BERT-base (710 MB, akurasi lebih tinggi)"
-      },
-      "intensity": {
-        "lite": "Ringan",
-        "full": "Penuh",
-        "ultra": "Ultra"
-      }
-    },
-    "modeOptions": {
-      "default": "Bawaan",
-      "off": "Matikan",
-      "lite": "Lite",
-      "standard": "Standar",
-      "aggressive": "Agresif",
-      "ultra": "Ultra",
-      "responsesToolOutput": "Keluaran alat respons"
-    }
-  },
-  "contextCombos": {
-    "title": "Compression Combos",
-    "description": "Define how engines are combined for different routing scenarios.",
-    "createCombo": "Create Compression Combo",
-    "editCombo": "Edit",
-    "deleteCombo": "Delete",
-    "deleteConfirm": "Delete this compression combo?",
-    "pipeline": "Pipeline",
-    "addStep": "Add Step",
-    "removeStep": "Remove",
-    "name": "Name",
-    "descriptionField": "Description",
-    "languagePacks": "Language Packs",
-    "outputMode": "Output Mode",
-    "assignToRouting": "Assign to Routing Combos",
-    "noAssignments": "No routing combos available",
-    "default": "Default",
-    "setAsDefault": "Set as Default",
-    "save": "Save",
-    "cancel": "Cancel",
-    "enabled": "Enabled",
-    "loading": "Memuat…",
-    "hubTitle": "Pusat Kompresi",
-    "hubDescription": "Pilih profil kompresi mana yang berjalan secara global.",
-    "hideExplanation": "Sembunyikan penjelasan",
-    "howItWorks": "Cara kerja",
-    "saveSettingsFailed": "Gagal menyimpan pengaturan.",
-    "explanationIntro": "Kompresi mengurangi <strong>token dan biaya</strong> dengan menulis ulang riwayat sebelum dikirim ke penyedia dengan tetap mempertahankan maknanya.",
-    "explanationActiveProfile": "<strong>Profil aktif</strong>: memilih profil kompresi mana yang berjalan secara global — Default turunan panel atau salah satu kombo bernama yang Anda simpan.",
-    "explanationDefault": "<strong>Default (dari panel)</strong>: diturunkan dari sakelar utama dan sakelar per-mesin yang Anda konfigurasikan di Pengaturan Kompresi.",
-    "explanationNamedCombos": "<strong>Kombo bernama</strong>: alur pipa tersimpan yang Anda buat di editor kombo bernama. Memilih salah satu menjadikannya profil aktif untuk setiap permintaan.",
-    "explanationPreview": "<strong>Pratinjau</strong>: menunjukkan mesin mana yang dijalankan oleh profil aktif, secara berurutan.",
-    "activeProfile": "Profil aktif",
-    "activeProfileDescription": "Pilih profil kompresi mana yang berjalan secara global — Default turunan panel atau kombo bernama yang disimpan.",
-    "defaultFromPanel": "Default (dari panel)",
-    "runs": "Menjalankan:",
-    "defaultConfiguredPrefix": "Default — dikonfigurasi di",
-    "compressionSettings": "Pengaturan Kompresi",
-    "providerDelegated": "Kompresi yang didelegasikan penyedia",
-    "contextEditingClaude": "Penyuntingan Konteks (Claude)",
-    "contextEditingDescription": "Memungkinkan penyedia menghapus blok penggunaan alat yang lama di sisi server, tanpa menulis ulang pesan.",
-    "contextEditingAria": "Penyuntingan Konteks",
-    "contextEditingNote": "Saat ini hanya tersedia untuk Claude (Anthropic) hanya. Ini adalah mode delegasi: penyedia menghapus blok penggunaan alat yang lama di sisi server — kami tidak menulis ulang pesan. Ini tidak memengaruhi penyedia lain.",
-    "namedCombos": "Kombo bernama",
-    "namedCombosDescription": "Simpan alur pipa yang berbeda dan tetapkan ke kombo perutean tertentu.",
-    "comboNamePlaceholder": "Nama kombo",
-    "descriptionPlaceholder": "Deskripsi",
-    "nameRequired": "Masukkan nama kombo sebelum menyimpan.",
-    "pipelineRequired": "Tambahkan setidaknya satu langkah alur pipa sebelum menyimpan.",
-    "saveComboFailed": "Gagal menyimpan kombo (HTTP {status}).",
-    "deleteNamedConfirm": "Hapus kombo “{name}”?",
-    "intensityLite": "Ringan",
-    "intensityFull": "Penuh",
-    "intensityUltra": "Ultra",
-    "active": "Aktif",
-    "languagePacksList": "Paket bahasa: {packs}",
-    "dragToReorder": "Seret untuk mengurutkan ulang langkah",
-    "engine": "Mesin",
-    "intensity": "Intensitas"
-  },
-  "compressionStudio": {
-    "noRun": "Tidak ada proses kompresi yang tersedia.",
-    "liveDataHint": "Data langsung tiba melalui saluran kompresi WebSocket.",
-    "cockpitView": "Tampilan kokpit",
-    "canvas": "Kanvas",
-    "waterfall": "Waterfall",
-    "replayDone": "Putar ulang selesai",
-    "pauseReplay": "Jeda putar ulang",
-    "playReplay": "Mainkan putar ulang",
-    "pause": "Jeda",
-    "replay": "Putar ulang",
-    "resetReplay": "Atur ulang putar ulang",
-    "stepProgress": "langkah {current}/{total}",
-    "inlineView": "Segaris",
-    "splitComingSoon": "Tampilan terpisah (segera hadir)",
-    "inputPlaceholder": "Tempelkan prompt, keluaran alat, atau konteks…",
-    "activeCombined": "Aktif dalam alur gabungan",
-    "requiresOnnx": "memerlukan model ONNX",
-    "verifyFidelity": "Verifikasi fidelitas (tolak lapisan apa pun yang merusak konten)",
-    "fuzzyDedup": "Deduplikasi samar (hampir-duplikat → CCR)",
-    "protectSensitive": "Lindungi konten sensitif (gerbang risiko)",
-    "quantumLock": "QuantumLock (stabilkan prefiks tembolok)",
-    "saliencyHeatmap": "Peta panas saliensi",
-    "running": "Berjalan…",
-    "run": "Jalankan",
-    "laneRejected": "ditolak: {reason}",
-    "error": "kesalahan",
-    "combinedFlow": "Alur gabungan",
-    "eachLayer": "Setiap lapisan secara terpisah",
-    "diff": "Perbedaan",
-    "combined": "digabungkan",
-    "skipped": "lewati",
-    "input": "MASUKAN",
-    "output": "KELUARAN",
-    "tokenCount": "{count, number} token",
-    "tokenShort": "tok",
-    "provider": "Penyedia",
-    "judgeModel": "Model penilai",
-    "judgeModelPlaceholder": "mis. claude-haiku",
-    "maxCostUsd": "Batas USD",
-    "enterJudgeModel": "Masukkan model penilai",
-    "verifying": "Memverifikasi…",
-    "verifyAll": "Verifikasi semua",
-    "spent": "terpakai ${spent} / ${cap}",
-    "capReached": "batas tercapai",
-    "loadAb": "Muat A/B",
-    "engine": "Mesin",
-    "savings": "Penghematan",
-    "retention": "Retensi",
-    "outputTokensShort": "Token keluaran",
-    "fidelity": "Fidelitas",
-    "playTab": "Putar",
-    "compareTab": "Bandingkan",
-    "encoderComparison": "Enkoder A/B — {count} larik",
-    "encoderWinner": "pemenang: {winner}",
-    "encoder": "enkoder",
-    "bytes": "bita",
-    "tokensCl100k": "token (cl100k)"
-  },
-  "omniglyph": {
-    "preview": "Pratinjau",
-    "description": "Kompresi konteks-sebagai-gambar. Merender prompt sistem, dokumentasi alat, dan riwayat padat sebagai halaman PNG ringkas yang dibaca Claude Fable 5 alih-alih teks. Token gambar ditagih berdasarkan dimensi alih-alih karakter, sehingga blok yang dikonversi berbiaya sekitar 10× lebih murah. Hanya untuk rute Anthropic langsung.",
-    "economicsTitle": "Aspek ekonomi",
-    "economics": {
-      "fewerTokens": "lebih sedikit token pada blok yang dikonversi",
-      "savings": "penghematan menyeluruh (terukur)",
-      "imageTokens": "token gambar untuk halaman 1568×728 (sekitar 28 ribu karakter)",
-      "accuracy": "akurasi pembacaan pada Fable 5 (n=30)"
-    },
-    "beforeAfterTitle": "Sebelum → sesudah",
-    "blockSavings": "−{percent}% token pada blok ini",
-    "realRender": "Render nyata dari {characters, number} karakter dokumentasi alat yang padat — bukan maket.",
-    "textTokens": "Teks · ≈ {tokens, number} token",
-    "renderedTokens": "Halaman terender · ≈ {tokens, number} token",
-    "renderedImageAlt": "Halaman padat terender, {width}×{height}px",
-    "gatesTitle": "Saat dipicu",
-    "gatesDescription": "Gagal-tertutup: setiap gerbang harus lolos, atau permintaan akan diteruskan tanpa diubah (setiap pengabaian dicatat sebagai <code>skip:&lt;reason&gt;</code>).",
-    "gates": {
-      "model": {
-        "label": "Model",
-        "pass": "claude-fable-5",
-        "why": "Hanya Fable 5 yang membaca halaman padat dengan akurasi 100% (terukur, n=30). GPT-5.5 dan Gemini 2.5 Flash diblokir."
-      },
-      "transport": {
-        "label": "Transportasi",
-        "pass": "Anthropic langsung",
-        "why": "Agregator melakukan sampel ulang gambar dan merusak keterbacaan — hanya rute langsung yang otoritatif."
-      },
-      "format": {
-        "label": "Format",
-        "pass": "Claude asli",
-        "why": "Bagian isi harus menggunakan format Claude dan tidak boleh memasukkan peran sistem di dalam pesan."
-      },
-      "profitable": {
-        "label": "Menguntungkan",
-        "pass": "cukup padat",
-        "why": "Gerbang biaya patch 28px yang tepat menentukan per permintaan; teks kecil atau jarang dilewatkan tanpa diubah."
-      }
-    },
-    "enableTitle": "Aktifkan mesin",
-    "enableDescription": "Berjalan terakhir dalam tumpukan (setelah RTK/Caveman membersihkan teks, OmniGlyph mengonversi sisanya menjadi gambar) dan juga berjalan mandiri melalui mode <code>omniglyph</code>. Ini adalah pratinjau dan tetap nonaktif secara default hingga validasi menyeluruh selesai.",
-    "profileTitle": "Compression profile",
-    "profileDescription": "The profile is a ceiling, not a floor: a stricter profile cannot be reopened by a per-step override. Measured on this codebase: with coding-safe or balanced, a session that has not accumulated history yet compresses nothing, because both raise the minimum-characters threshold and keep the system prompt, tool schemas and tool results native.",
-    "profiles": {
-      "aggressive": {
-        "label": "Aggressive (default)",
-        "description": "The policy the published receipts measured. Images the system prompt, tool documentation and dense history."
-      },
-      "balanced": {
-        "label": "Balanced",
-        "description": "Keeps live state native and protects the last 8 turns; only collapses older closed history."
-      },
-      "codingSafe": {
-        "label": "Coding-safe",
-        "description": "Keeps authority, tool schemas and live tool output native, protecting the last 12 turns. Compresses nothing until the session accumulates history."
-      },
-      "passthrough": {
-        "label": "Passthrough",
-        "description": "Routes without transforming. The engine is skipped and the request is forwarded untouched."
-      }
-    },
-    "profileAria": "Select the OmniGlyph compression profile",
-    "saved": "Tersimpan.",
-    "saveFailed": "Tidak dapat menyimpan.",
-    "enableAria": "Aktifkan mesin OmniGlyph",
-    "title": "OmniGlyph"
-  },
-  "embeddedServices": {
-    "title": "Layanan Tertanam",
-    "description": "Mesin lokal dikelola sesuai permintaan — CLIProxyAPI, 9Router, Mux, dan Bifrost. Hanya dapat diakses pada loopback.",
-    "stateRunning": "Berjalan",
-    "stateStopped": "Dihentikan",
-    "stateStarting": "Memulai",
-    "stateStopping": "Menghentikan",
-    "stateError": "Kesalahan",
-    "stateNotInstalled": "Tidak terpasang",
-    "stateUnknown": "Tidak diketahui",
-    "port": "port {port}",
-    "externalBadge": "Dikelola secara eksternal",
-    "externalTitle": "9Router eksternal terdeteksi",
-    "externalDescription": "OmniRoute menemukan 9Router di {host}:{port}. Siklus hidup, log, pembaruan, dan kunci layanannya tetap dikelola oleh instalasi eksternal.",
-    "start": "Mulai",
-    "starting": "Memulai…",
-    "stop": "Hentikan",
-    "stopping": "Menghentikan…",
-    "restart": "Mulai ulang",
-    "restarting": "Memulai ulang…",
-    "update": "Perbarui",
-    "updating": "Memperbarui…",
-    "install": "Instal",
-    "installing": "Menginstal…",
-    "autoStart": "Mulai otomatis",
-    "autoStartDescription": "Luncurkan {name} secara otomatis saat OmniRoute dimulai",
-    "apiKey": "Kunci API",
-    "apiKeyDescription": "Kunci yang digunakan oleh OmniRoute untuk mengautentikasi dengan {name}",
-    "keyRotated": "Kunci dirotasi — {name} dimulai ulang untuk menerapkan kunci baru",
-    "keyRotateFailed": "Gagal merotasi kunci",
-    "keyRevealFailed": "Gagal menampilkan kunci",
-    "keyRevealEmpty": "Gagal menampilkan: kunci tidak dikembalikan",
-    "reveal": "Tampilkan",
-    "revealing": "Menampilkan…",
-    "hide": "Sembunyikan",
-    "rotateKey": "Rotasi kunci",
-    "rotating": "Memutar…",
-    "keyAutoHide": "Kunci akan disembunyikan secara otomatis dalam 30 detik.",
-    "revealTitle": "Tampilkan Kunci API",
-    "revealConfirm": "Menampilkan kunci API akan dicatat dalam jejak audit. Lanjutkan?",
-    "cancel": "Batal",
-    "install9Router": "Instal 9Router",
-    "install9RouterDescription": "Mengunduh dan menginstal 9Router melalui npm. Memerlukan ruang disk sekitar 500 MB.",
-    "version": "Versi",
-    "versionHint": "Masukkan “latest” atau versi tertentu (misalnya, 1.2.3).",
-    "servicePort": "Port",
-    "servicePortHint": "OmniRoute dan 9Router harus menggunakan port yang berbeda. Port default 9Router adalah 20130.",
-    "installationFailed": "Instalasi gagal (HTTP {status})",
-    "installationSucceeded": "9Router berhasil diinstal. Memulai…",
-    "networkInstallFailed": "Kesalahan jaringan — tidak dapat menjangkau endpoint instalasi",
-    "availableModels": "Model yang Tersedia",
-    "modelsLoading": "Memuat…",
-    "modelsDiscovered": "{count, plural, one {# model ditemukan} other {# model ditemukan}}",
-    "modelsLoadFailed": "Gagal memuat model",
-    "refreshing": "Menyegarkan…",
-    "refreshNow": "Segarkan sekarang",
-    "noModels": "Tidak ada model yang ditemukan. Pilih “Segarkan sekarang” untuk menyinkronkan dari layanan yang sedang berjalan.",
-    "unavailable": "Tidak tersedia",
-    "pageOf": "Halaman {page} dari {total}",
-    "previous": "Sebelumnya",
-    "next": "Berikutnya",
-    "providerExposure": "Eksposur Penyedia",
-    "providerExposureDescription": "Ekspos model 9Router sebagai target perutean di bawah prefiks <prefix>9router/</prefix>.",
-    "providerExposureLabel": "Ekspos sebagai <prefix>9router/…</prefix>",
-    "providerExposureHint": "Saat diaktifkan, model yang ditemukan akan muncul di pemilih penyedia di seluruh OmniRoute.",
-    "providerExposureUpdateFailed": "Gagal memperbarui (HTTP {status})",
-    "providerExposureNetworkFailed": "Kesalahan jaringan — tidak dapat memperbarui pengaturan eksposur penyedia",
-    "webUi": "UI Web 9Router",
-    "openNewTab": "Buka di tab baru",
-    "filterLogs": "Filter log…",
-    "resume": "Lanjutkan",
-    "pause": "Jeda",
-    "clear": "Bersihkan",
-    "download": "Unduh",
-    "noLogs": "Belum ada keluaran log.",
-    "logStreamFailed": "Tidak dapat mengalirkan log {name}. Periksa akses lokal dan status layanan.",
-    "fallbackRouting": "Perutean Fallback",
-    "fallbackRoutingDescription": "Coba lagi permintaan penyedia yang gagal melalui CLIProxyAPI",
-    "enableFallback": "Aktifkan fallback",
-    "cliproxyUrl": "URL CLIProxyAPI",
-    "fallbackCodes": "Kode status fallback (dipisahkan koma)",
-    "invalidUrl": "URL tidak valid — harus dimulai dengan http:// atau https://",
-    "saved": "Tersimpan",
-    "saveFailed": "Gagal menyimpan pengaturan",
-    "modelMapping": "Pemetaan Model",
-    "modelMappingDescription": "Petakan ID model OmniRoute ke ID model CLIProxyAPI (misalnya, <example>\"gpt-4o\": \"openai-gpt-4o\"</example>)",
-    "modelMappingEditor": "Editor JSON pemetaan model",
-    "mappingSaved": "Pemetaan disimpan",
-    "mappingSaveFailed": "Gagal menyimpan pemetaan",
-    "mappingInvalidJson": "JSON tidak valid.",
-    "mappingMustBeObject": "Pemetaan harus berupa objek JSON, bukan array atau nilai primitif.",
-    "mappingValueMustBeString": "Nilai untuk kunci “{key}” harus berupa string.",
-    "save": "Simpan"
-  },
-  "contextCaveman": {
-    "title": "Caveman Engine",
-    "description": "Rule-based message compression, language packs, analytics and output mode controls.",
-    "advancedConfig": "Konfigurasi Lanjutan",
-    "advancedConfigDesc": "Sempurnakan perilaku kompresi",
-    "aggressiveSettings": "Pengaturan Agresif",
-    "aggressiveSettingsDesc": "Kompresi maksimum dengan potensi pengorbanan kualitas",
-    "requests": "Requests",
-    "tokensSaved": "Tokens saved",
-    "savingsPercent": "Savings %",
-    "avgLatency": "Avg latency",
-    "languagePacks": "Language Packs",
-    "languagePacksDesc": "Enable compression rules for specific languages.",
-    "labelAutoTrigger": "Kompres otomatis ketika konteks melebihi",
-    "labelCompressionRate": "Kekuatan kompresi",
-    "labelMaxTokens": "Targetkan token per pesan",
-    "labelMinLength": "Panjang pesan minimum",
-    "labelMinSavings": "Token minimum untuk disimpan",
-    "enabled": "Enabled",
-    "autoDetect": "Auto-detect language",
-    "rulesCount": "{count} rules",
-    "inputCompressionTitle": "Kompresi input",
-    "inputCompressionDesc": "Tulis ulang riwayat obrolan dengan kata-kata yang lebih singkat. Mengurangi token input sekitar ~50%.",
-    "analyticsTitle": "Compression Analytics",
-    "noAnalytics": "No compression analytics yet.",
-    "masterDisabledWarning": "Sakelar utama Token Saver NONAKTIF — pengaturan ini tidak akan memengaruhi permintaan hingga Anda mengaktifkannya dari Pengaturan Kompresi atau mengubahnya di sini.",
-    "outputMode": "Modus Keluaran",
-    "outputModeDesc": "Instructs the LLM to respond in a terse, compact format.",
-    "outputModeTitle": "Output Mode",
-    "quickSettings": "Pengaturan Cepat",
-    "quickSettingsDesc": "Pengaturan kompresi dasar untuk memulai",
-    "autoClarity": "Auto-Clarity Bypass",
-    "bypassConditions": "Bypass conditions",
-    "bypassConditionsList": "keamanan, tidak dapat diubah, klarifikasi, peka terhadap perintah",
-    "simpleMode": "Sederhana",
-    "advancedMode": "Lanjutan",
-    "tooltipAutoTrigger": "Kompres secara otomatis ketika konteks melebihi ukuran ini.",
-    "tooltipCompressionRate": "0,0 = tidak ada, 1,0 = maksimal. 0,5 = seimbang.",
-    "tooltipMaxTokens": "Jumlah token target setelah kompresi. Lebih rendah = lebih agresif.",
-    "tooltipMinLength": "Pesan yang lebih pendek dari ini tidak dikompresi. Lebih rendah = lebih banyak kompresi.",
-    "tooltipMinSavings": "Hanya kompres jika menyimpan setidaknya token sebanyak ini.",
-    "ultraSettings": "Pengaturan Ultra",
-    "ultraSettingsDesc": "Kompresi semantik bertenaga SLM",
-    "preview": {
-      "lite": "Respond concise. Preserve technical terms, code, errors, URLs, and identifiers.",
-      "full": "Respond terse and compact. Preserve all technical substance.",
-      "ultra": "Respond ultra terse with common technical abbreviations. Preserve exact symbols."
-    }
-  },
-  "translator": {
-    "title": "Translator",
-    "metaTitle": "Translator Playground | OmniRoute",
-    "metaDescription": "Debug, test, and visualize API format translations between providers",
-    "playgroundTitle": "Translator Playground",
-    "playground": "Playground",
-    "realtime": "Real-Time Translation Activity",
-    "chatTester": "Chat Tester",
-    "testBench": "Test Bench",
-    "liveMonitor": "Live Monitor",
-    "modeDescriptionPlayground": "Paste any API request body and see how OmniRoute translates it between provider formats (OpenAI ↔ Claude ↔ Gemini ↔ Responses API)",
-    "modeDescriptionChatTester": "Send real chat requests through OmniRoute and inspect the full round-trip: input, translated request, provider response, and translated output.",
-    "modeDescriptionTestBench": "Run predefined scenarios and compare compatibility across providers and models.",
-    "modeDescriptionLiveMonitor": "Watch translation events in real time as requests flow through OmniRoute.",
-    "modeDescriptionFallback": "Debug, test, and visualize how OmniRoute translates API requests between providers.",
-    "recentTranslations": "Recent Translations",
-    "noTranslations": "No translations yet",
-    "source": "Source",
-    "target": "Target",
-    "time": "Time",
-    "model": "Model",
-    "status": "Status",
-    "latency": "Latency",
-    "totalTranslations": "Total Translations",
-    "successful": "Successful",
-    "errors": "Errors",
-    "avgLatency": "Avg Latency",
-    "millisecondsShort": "{value}ms",
-    "notAvailableSymbol": "—",
-    "liveAutoRefreshing": "Live — Auto-refreshing",
-    "paused": "Paused",
-    "eventsAppearHint": "Translation events appear here as requests flow through OmniRoute. Use any of these methods to generate events:",
-    "chatTesterTab": "Chat Tester",
-    "testBenchTab": "Test Bench",
-    "externalApiCalls": "External API calls",
-    "ideCliIntegrations": "IDE/CLI integrations",
-    "inMemoryNote": "Note: Events are stored in-memory and reset when the server restarts.",
-    "ok": "OK",
-    "errorShort": "ERR",
-    "formatConverter": "Format Converter",
-    "formatConverterDescription": "Paste or type a JSON request body. The translator will auto-detect the source format and convert it to the target format. Use this to debug how OmniRoute translates requests between formats (OpenAI ↔ Claude ↔ Gemini ↔ Responses API).",
-    "translationPathHubSpoke": "{source} → OpenAI (menengah) → {target}",
-    "translationPathDirect": "{source} → {target} (penerjemah langsung)",
-    "translationPathPassthrough": "Format yang sama — tidak perlu terjemahan",
-    "openaiIntermediatePanel": "OpenAI Menengah",
-    "autoFeaturesTitle": "Apa yang dilakukan OmniRoute secara otomatis",
-    "autoFeaturesCount": "8 fitur",
-    "featureReasoningCache": "Tembolok Penalaran",
-    "featureReasoningCacheDesc": "Menyuntikkan kembali penalaran_konten yang di-cache untuk model mode berpikir (DeepSeek V4, Kimi K2, Qwen) ketika klien menghilangkannya dari riwayat percakapan.",
-    "featureSchemaCoercion": "Pemaksaan Skema",
-    "featureSchemaCoercionDesc": "Memperbaiki skema alat yang rusak: menambahkan Properti tambahan yang hilang, membersihkan deskripsi panjang, menormalkan objek bersarang.",
-    "featureRoleNormalization": "Normalisasi Peran",
-    "featureRoleNormalizationDesc": "Pengembang peta→sistem untuk target non-OpenAI. Sistem peta→pengguna untuk model yang tidak mendukung peran sistem.",
-    "featureToolCallIds": "Normalisasi ID Panggilan Alat",
-    "featureToolCallIdsDesc": "Menghasilkan ID panggilan_alat unik saat hilang. Menormalkan ke format 9 karakter untuk penyedia seperti Mistral.",
-    "featureMissingToolResponse": "Injeksi Respon Alat",
-    "featureMissingToolResponseDesc": "Menyuntikkan pesan tool_result kosong ketika klien mengirim tool_calls tanpa respons yang sesuai.",
-    "featureThinkingBudget": "Memikirkan Anggaran",
-    "featureThinkingBudgetDesc": "Secara otomatis mengelola konfigurasi pemikiran. Menghapus parameter pemikiran ketika pesan terakhir bukan dari pengguna.",
-    "featureDirectPaths": "Jalur Terjemahan Langsung",
-    "featureDirectPathsDesc": "Beberapa pasangan format (Claude→Gemini) memiliki penerjemah langsung yang melewati hub OpenAI, sehingga menghasilkan keluaran yang lebih akurat.",
-    "featureImageMapping": "Pemetaan Ukuran Gambar",
-    "featureImageMappingDesc": "Menerjemahkan konvensi dimensi gambar antar format API (misalnya, tingkat detail OpenAI → dimensi Gemini).",
-    "input": "Input",
-    "output": "Output",
-    "auto": "Auto",
-    "swapFormats": "Swap formats",
-    "translateAction": "Translate",
-    "clear": "Clear",
-    "inputPlaceholder": "Paste a request body here or select a template below...",
-    "exampleTemplates": "Example Templates",
-    "exampleTemplatesHint": "— Click to load",
-    "templateLoadHint": "Template loads the request in {format} format. Change Source Format to load in a different format.",
-    "compatibilityTester": "Compatibility Tester",
-    "compatibilityReport": "Compatibility Report",
-    "testBenchDescription": "Run predefined scenarios (Simple Chat, Tool Calling, etc.) to verify translation and provider compatibility. Select a source format and target provider, then run all tests to see a compatibility percentage. Use this to find which features work across providers.",
-    "targetProvider": "Target Provider",
-    "runAllTests": "Run All Tests",
-    "runTest": "Run Test",
-    "reRun": "Re-run",
-    "running": "Running...",
-    "passed": "passed",
-    "failed": "failed",
-    "passedIconLabel": "✅ Passed",
-    "chunks": "chunks",
-    "scenarioSimpleChat": "Simple Chat",
-    "scenarioToolCalling": "Tool Calling",
-    "scenarioMultiTurn": "Multi-turn",
-    "scenarioThinking": "Thinking",
-    "scenarioSystemPrompt": "System Prompt",
-    "scenarioStreaming": "Streaming",
-    "templateNames": {
-      "simple-chat": "Simple Chat",
-      "tool-calling": "Tool Calling",
-      "multi-turn": "Multi-turn",
-      "thinking": "Thinking",
-      "system-prompt": "System Prompt",
-      "streaming": "Streaming",
-      "vision": "Visi",
-      "schema-coercion": "Pemaksaan Skema"
-    },
-    "templateDescriptions": {
-      "simple-chat": "Basic text message",
-      "tool-calling": "Function/tool invocation",
-      "multi-turn": "Conversation with history",
-      "thinking": "Extended thinking / reasoning",
-      "system-prompt": "Complex system instructions",
-      "streaming": "SSE streaming request",
-      "vision": "Permintaan multimodal dengan input gambar",
-      "schema-coercion": "Penegakan skema keluaran terstruktur/JSON"
-    },
-    "templatePayloads": {
-      "simpleChat": {
-        "system": "You are a helpful assistant.",
-        "userGreeting": "Hello! How are you today?"
-      },
-      "toolCalling": {
-        "userWeather": "What's the weather in São Paulo?",
-        "toolDescription": "Get current weather for a location",
-        "cityNameDescription": "City name"
-      },
-      "multiTurn": {
-        "system": "You are a coding assistant.",
-        "userInitial": "Write a function to sort an array in Python.",
-        "assistantExample": "Here's a simple sort function: ```python\ndef sort_array(arr): return sorted(arr)\n```",
-        "userFollowUp": "Now make it sort in descending order."
-      },
-      "thinking": {
-        "question": "What is the sum of the first 100 prime numbers?"
-      },
-      "systemPrompt": {
-        "systemInstruction": "You are a senior software engineer specializing in distributed systems. Answer questions concisely using industry best practices. Always provide code examples when relevant. Format your responses using markdown.",
-        "question": "How do I implement a circuit breaker pattern?"
-      },
-      "streaming": {
-        "prompt": "Tell me a short story about a robot learning to paint."
-      },
-      "vision": {
-        "system": "Anda adalah asisten yang mendeskripsikan gambar dengan tepat.",
-        "userPrompt": "Apa yang ditampilkan pada gambar ini?",
-        "imageUrl": "https://upload.wikimedia.org/wikipedia/commons/thumb/4/47/PNG_transparency_demonstration_1.png/600px-PNG_transparency_demonstration_1.png"
-      },
-      "schemaCoercion": {
-        "userPrompt": "Cari tahu cuaca di Tokyo menggunakan satuan metrik dan sertakan rincian per jamnya.",
-        "toolDescription": "Ambil cuaca untuk kota dengan opsi terstruktur.",
-        "cityDescription": "Kota yang akan ditanyakan, mis. 'Tokyo' atau 'New York'."
-      }
-    },
-    "openaiCompatibleLabel": "OpenAI Compatible",
-    "anthropicCompatibleLabel": "Anthropic Compatible",
-    "noTemplateForFormat": "No template for this format",
-    "translationFailed": "Translation failed: {error}",
-    "pipelineDebugger": "Pipeline Debugger",
-    "translationPipeline": "Translation Pipeline",
-    "loading": "Memuat…",
-    "compressionOriginal": "Asli",
-    "compressionCompressed": "Dikompresi",
-    "compressionSaved": "Dihemat",
-    "compressionDuration": "Durasi",
-    "pipelineStepsAria": "Langkah-langkah pipeline",
-    "copyIntermediateJson": "Salin JSON perantara",
-    "copyOutputJson": "Salin JSON output",
-    "pipelineVisualization": "Pipeline visualization",
-    "pipelineVisualizationHint": "Send a message to see how your request flows through detection → translation → provider call.",
-    "chatTesterDescription": "Send messages as a specific client format and inspect each step of the translation pipeline.",
-    "chatTesterFlow": "Client Request → Format Detection → OpenAI Intermediate → Provider Format → Response",
-    "clickStepToInspect": "Click any step to inspect the data at that stage.",
-    "clientFormat": "Client Format",
-    "provider": "Provider",
-    "modelPlaceholder": "Select or type a model name...",
-    "sendMessageToSeePipeline": "Send a message to see the translation pipeline",
-    "chatMessageHintPrefix": "Your message will be formatted as a",
-    "chatMessageHintSuffix": "request, translated through the pipeline, and sent to the selected provider.",
-    "youWithFormat": "You ({format})",
-    "assistant": "Assistant",
-    "typeMessage": "Type a message...",
-    "send": "Send",
-    "clientRequest": "Client Request",
-    "clientRequestDescription": "The request body as your client would send it",
-    "formatDetected": "Format Detected",
-    "formatDetectedDescription": "OmniRoute auto-detects the API format from the request structure",
-    "openaiIntermediate": "OpenAI Intermediate",
-    "openaiIntermediateDescription": "All formats are first normalized to OpenAI format (the universal bridge)",
-    "providerFormat": "Provider Format",
-    "providerFormatDescription": "OpenAI format is translated to the provider's native format",
-    "providerResponse": "Provider Response",
-    "providerResponseRawDescription": "The raw response from the provider API",
-    "providerResponseSseDescription": "The raw SSE stream from the provider API",
-    "unexpectedError": "An unexpected error occurred",
-    "error": "Error",
-    "errorMessage": "Error: {message}",
-    "requestFailed": "Request failed",
-    "noTextExtracted": "(No text extracted)",
-    "liveMonitorMemoryNote": "Acara disimpan dalam memori dan hilang saat restart.",
-    "liveMonitorMemoryCapNote": "Maksimum 200 acara dipertahankan.",
-    "eventSourcesLabel": "Sumber acara:",
-    "eventSourceTranslatorPage": "• Halaman Penerjemah (Penguji Obrolan, Bangku Tes)",
-    "eventSourceMainPipeline": "• Pipeline permintaan utama (lalu lintas CLI/IDE/API)",
-    "liveMonitorDescriptionPrefix": "Shows translation events as API calls flow through OmniRoute. Events come from the in-memory buffer (resets on restart). Use",
-    "liveMonitorDescriptionSuffix": ", or external API calls to generate events.",
-    "streamTransformer": "Transformator Aliran",
-    "modeDescriptionStreamTransformer": "Jalankan penyelesaian obrolan aliran SSE melalui transformator Respons.",
-    "streamTransformerTitle": "Tanggapan Transformator Aliran",
-    "streamTransformerDescription": "Tempelkan aliran SSE penyelesaian obrolan, jalankan melalui transformator Respons OmniRoute, dan periksa peristiwa respons yang dipancarkan.* sebelum menghubungkan klien.",
-    "loadTextSample": "Muat sampel teks",
-    "loadToolSample": "Muat sampel panggilan alat",
-    "transformToResponses": "Transformasikan ke Respons",
-    "rawChatSseInput": "Penyelesaian obrolan mentah SSE",
-    "transformedResponsesSse": "SSE API Respons yang Diubah",
-    "noResultsYet": "Belum ada hasil",
-    "transformedEvents": "Peristiwa yang diubah",
-    "uniqueEventTypes": "Jenis acara unik",
-    "inputLines": "Jalur masukan",
-    "outputLines": "Jalur keluaran",
-    "transformedEventTimeline": "Garis waktu acara yang diubah",
-    "transformerTimelineHint": "Jalankan transformator untuk memeriksa peristiwa respon.output_* yang dipancarkan secara berurutan.",
-    "eventType": "Jenis acara",
-    "eventPreview": "Pratinjau",
-    "comboRouted": "Kombo dialihkan",
-    "uniqueEndpoints": "Titik akhir yang unik",
-    "routeDetails": "Detail rute",
-    "comboBadge": "kombo",
-    "routeEndpointLabel": "Titik akhir",
-    "routeConnectionLabel": "Koneksi",
-    "scenarioVision": "Visi (pemahaman gambar)",
-    "scenarioSchemaCoercion": "Pemaksaan skema (keluaran terstruktur)",
-    "techniques": "Teknik:",
-    "friendlyTitle": "Penerjemah",
-    "friendlySubtitle": "Gunakan aplikasi Anda yang sudah ada dengan penyedia mana pun — tanpa menulis ulang kode.",
-    "conceptHeadline": "Aplikasi Anda menggunakan \"bahasa\" satu API. Penerjemah mengonversinya untuk menggunakan penyedia lain.",
-    "conceptDiagramAppLabel": "Aplikasi Anda",
-    "conceptDiagramSourceLabel": "Format sumber",
-    "conceptDiagramHubLabel": "OpenAI (hub)",
-    "conceptDiagramTargetLabel": "Penyedia target",
-    "conceptDiagramExampleApp": "mis. Anthropic SDK",
-    "conceptDiagramExampleSource": "claude",
-    "conceptDiagramExampleTarget": "Gemini",
-    "conceptHowItWorksToggle": "Cara kerja",
-    "conceptHowItWorksBody": "Aplikasi Anda mengirimkan permintaan dalam formatnya sendiri. Translator mendeteksi format tersebut, mengonversinya melalui OpenAI sebagai hub perantara (atau secara langsung jika penerjemah langsung tersedia), mengirimkannya ke penyedia yang dipilih, dan mengembalikan respons yang telah dikonversi kembali ke format aplikasi Anda.",
-    "tabTranslate": "Terjemahkan",
-    "tabMonitor": "Pantau",
-    "tabTranslateAriaLabel": "Buka tab Terjemahkan",
-    "tabMonitorAriaLabel": "Buka tab Pantau",
-    "simpleAppUsesLabel": "Aplikasi saya menggunakan",
-    "simpleAppUsesHint": "Format API yang digunakan aplikasi Anda (mis. Anthropic SDK = claude).",
-    "simpleSendToLabel": "Kirim ke",
-    "simpleSendToHint": "Tujuan pengiriman permintaan yang sebenarnya (penyedia yang terhubung di OmniRoute).",
-    "simpleStartWithLabel": "Mulai dengan",
-    "simpleStartWithExamplePlaceholder": "Pilih contoh siap pakai",
-    "simpleStartWithCustomOption": "Tempel permintaan Anda (lanjutan)",
-    "simpleModeLabel": "Mode",
-    "simpleModePreview": "Pratinjau terjemahan saja",
-    "simpleModeSend": "Kirim dan lihat respons",
-    "simpleAdvancedToggle": "Lanjutan",
-    "simpleInputPanelTitle": "Masukan",
-    "simpleInputPanelHint": "Pesan teks bebas atau contoh siap pakai",
-    "simpleResultPanelTitle": "Terjemahan + Respons",
-    "narratedDetected": "✓ Terdeteksi: {format}",
-    "narratedTranslating": "Menerjemahkan ke {target}...",
-    "narratedSending": "Mengirim ke {target}...",
-    "narratedSuccess": "→ diterjemahkan ke {target} · respons dalam {latency}ms",
-    "narratedError": "Gagal: {reason}",
-    "narratedSeeTranslatedJson": "lihat JSON yang diterjemahkan",
-    "narratedSeePipeline": "lihat pipeline",
-    "advancedSectionTitle": "Lanjutan",
-    "advancedSectionSubtitle": "JSON mentah, pipeline, dan alat teknis. Semua yang ada di sini sama dengan tab lama — hanya ditata ulang.",
-    "advancedRawJsonTitle": "JSON Mentah (deteksi otomatis + Monaco)",
-    "advancedRawJsonSubtitle": "Tempel permintaan JSON; format akan terdeteksi secara otomatis.",
-    "advancedPipelineTitle": "Pipeline perantara OpenAI",
-    "advancedPipelineSubtitle": "Visualisasikan setiap langkah penerjemahan (hub-and-spoke).",
-    "advancedStreamTransformTitle": "Stream Transformer (Chat → Responses SSE)",
-    "advancedStreamTransformSubtitle": "Mengonversi Chat Completions SSE menjadi Responses API.",
-    "advancedTestBenchTitle": "Test Bench (8 skenario)",
-    "advancedTestBenchSubtitle": "Menjalankan semua skenario dan melaporkan lulus/gagal + % kompatibilitas.",
-    "advancedCompressionTitle": "Pratinjau Kompresi",
-    "advancedCompressionSubtitle": "Perkirakan penghematan token di berbagai mode kompresi.",
-    "monitorOriginHint": "Peristiwa yang dihasilkan oleh Translate atau pipeline utama muncul di sini secara real-time.",
-    "monitorEmptyCta": "Buka tab Terjemahkan dan kirim permintaan — itu akan muncul di sini.",
-    "monitorOpenTranslateButton": "Buka Terjemahkan",
-    "pipelineStepClientRequest": "Permintaan Klien",
-    "pipelineStepClientRequestDesc": "Permintaan diterima dalam format klien",
-    "pipelineStepFormatDetected": "Format Terdeteksi",
-    "pipelineStepFormatDetectedDesc": "Format sumber terdeteksi otomatis",
-    "pipelineStepOpenAIIntermediate": "Perantara OpenAI",
-    "pipelineStepOpenAIIntermediateDesc": "Diterjemahkan ke format hub OpenAI",
-    "pipelineStepProviderFormat": "Format Penyedia",
-    "pipelineStepProviderFormatDesc": "Diterjemahkan ke format target penyedia",
-    "pipelineStepProviderResponse": "Respons Penyedia",
-    "pipelineStepProviderResponseDesc": "Respons streaming dari penyedia",
-    "conceptDiagramArrow1": "menggunakan",
-    "conceptDiagramArrow2": "menerjemahkan",
-    "conceptDiagramArrow3": "mengonversi",
-    "conceptDiagramExampleHub": "OpenAI",
-    "conceptDiagramHubTooltip": "Hub perantara yang digunakan oleh penerjemah untuk mengonversi antarformat yang tidak memiliki pemetaan langsung.",
-    "conceptDiagramSourceTooltip": "Format API yang digunakan aplikasi Anda (misalnya, Anthropic SDK = claude).",
-    "conceptDiagramTargetTooltip": "Penyedia tempat permintaan sebenarnya akan dikirim.",
-    "compressionEmptyHint": "Isi bidang input pada tab Terjemahkan (Kontrol Sederhana atau JSON Mentah) untuk mengaktifkan pratinjau.",
-    "compressionModeLabel": "Mode kompresi",
-    "compressionPreviewButton": "Pratinjau Kompresi",
-    "compressionPreviewing": "Mempratinjau…",
-    "compressionPreviewFailed": "Pratinjau kompresi gagal",
-    "tokens": "token",
-    "pauseAutoRefresh": "Jeda penyegaran otomatis",
-    "resumeAutoRefresh": "Lanjutkan penyegaran otomatis",
-    "live": "Langsung",
-    "copyInput": "Salin input",
-    "copyOutput": "Salin output",
-    "streamTransformFailed": "Gagal mentransformasi stream"
-  },
-  "usage": {
-    "title": "Usage",
-    "grokExtraUsageCredits": "Kredit Penggunaan Tambahan",
-    "grokAutoTopUp": "Isi Ulang Otomatis",
-    "grokAutoTopUpUnavailable": "Tidak Tersedia",
-    "grokAutoTopUpEnabled": "Diaktifkan",
-    "grokAutoTopUpDisabled": "Dinonaktifkan",
-    "grokAutoTopUpAt": "di",
-    "grokAutoTopUpAdd": "tambahkan",
-    "grokAutoTopUpMax": "maksimum",
-    "grokAutoTopUpMonth": "bulan",
-    "grokAdditionalCredits": "Kredit Tambahan",
-    "kimiExtraUsageCredits": "Extra Usage Credits",
-    "kimiExtraUsage": "Extra Usage",
-    "kimiExtraUsageEnabled": "Enabled",
-    "kimiExtraUsageDisabled": "Disabled",
-    "kimiExtraUsageFrozen": "Frozen",
-    "kimiExtraUsageUnavailable": "Unavailable",
-    "kimiMonthlyUsed": "Used this month",
-    "kimiMonthlyLimit": "Monthly limit",
-    "kimiMonthlyLimitUnlimited": "Unlimited",
-    "kimiAdditionalCredits": "Additional Credits",
-    "loggerTab": "Logger",
-    "proxyTab": "Proxy",
-    "budgetManagement": "Budget Management",
-    "budgetSaved": "Budget limits saved",
-    "budgetSaveFailed": "Failed to save budget",
-    "loadingBudgetData": "Loading budget data...",
-    "noApiKeysTitle": "No API Keys",
-    "noApiKeysDescription": "Add API keys first to set up budget limits.",
-    "apiKey": "API Key",
-    "todaysSpend": "Today's Spend",
-    "thisMonth": "This Month",
-    "setLimits": "Set Limits",
-    "dailyLimitUsd": "Daily Limit (USD)",
-    "monthlyLimitUsd": "Monthly Limit (USD)",
-    "warningThresholdPercent": "Warning Threshold (%)",
-    "dailyLimitPlaceholder": "e.g. 5.00",
-    "monthlyLimitPlaceholder": "e.g. 50.00",
-    "warningThresholdPlaceholder": "80",
-    "saveLimits": "Save Limits",
-    "budgetOk": "Budget OK — {remaining} remaining",
-    "budgetExceeded": "Budget exceeded — requests may be blocked",
-    "totalRequests": "Total requests",
-    "noDataYet": "No data yet",
-    "latency": "Latency",
-    "latencyP50": "p50",
-    "latencyP95": "p95",
-    "latencyP99": "p99",
-    "promptCache": "Prompt Cache",
-    "systemHealth": "System Health",
-    "entries": "Entries",
-    "activeCount": "{count} active",
-    "openCircuitBreakersDetected": "Open circuit breakers detected",
-    "hitRate": "Hit Rate",
-    "hitsMisses": "Hits / Misses",
-    "circuitBreakers": "Circuit Breakers",
-    "lockedIPs": "Locked IPs",
-    "lockoutsAutoRefreshHint": "Per-model rate limit locks • Auto-refresh 10s",
-    "lockedCount": "{count, plural, one {# locked} other {# locked}}",
-    "timeLeft": "{time} left",
-    "howItWorks": "How It Works",
-    "howItWorksSubtitle": "Learn how evaluations validate your LLM responses",
-    "define": "Define",
-    "defineStepDescription": "Create test cases with input prompts and expected output criteria using strategies like contains, regex, or exact match.",
-    "run": "Run",
-    "runStepDescription": "Execute test cases against your LLM endpoints through OmniRoute. Each case is sent as a real API request.",
-    "evaluate": "Evaluate",
-    "evaluateStepDescription": "Responses are compared against expected criteria. See pass/fail for each case with latency metrics and detailed feedback.",
-    "evalsStrategyContainsLabel": "Berisi",
-    "evalsStrategyExactLabel": "Cocok Persis",
-    "evalsStrategyRegexLabel": "Regex",
-    "evalsStrategyCustomLabel": "Logika Kustom",
-    "evalsStrategyContainsDescription": "Memeriksa apakah output LLM berisi substring yang diharapkan.",
-    "evalsStrategyExactDescription": "Memeriksa apakah output LLM sama persis dengan nilai yang diharapkan.",
-    "evalsStrategyRegexDescription": "Memvalidasi output LLM terhadap pola ekspresi reguler.",
-    "evalsStrategyCustomDescription": "Logika evaluasi kustom (dikonfigurasi melalui JSON).",
-    "historyColumnSuiteName": "Nama Suite",
-    "historyColumnTarget": "Target",
-    "historyColumnPassRate": "Tingkat Kelulusan",
-    "historyColumnAvgLatencyMs": "Latensi Rata-rata",
-    "historyColumnCreatedAt": "Dieksekusi",
-    "evalSuites": "Evaluation Suites",
-    "evalSuitesHint": "Click a suite to view test cases, then run to evaluate your LLM endpoints",
-    "evalsLoading": "Loading eval suites...",
-    "noEvalSuitesFound": "No Eval Suites Found",
-    "noEvalSuitesDescription": "Eval suites can be defined via the API or in code. They test model outputs against expected results using strategies like contains, regex, exact match, and custom functions.",
-    "columnCase": "Case",
-    "columnStatus": "Status",
-    "columnLatency": "Latency",
-    "columnDetails": "Details",
-    "columnModel": "Model",
-    "columnStrategy": "Strategy",
-    "columnExpected": "Expected",
-    "statsSuites": "Suites",
-    "statsTestCases": "Test Cases",
-    "statsModels": "Models",
-    "statsCoverage": "Coverage",
-    "statsStrategiesCount": "{count} strategies",
-    "evaluationStrategies": "Evaluation Strategies",
-    "modelsUnderTest": "Models Under Test",
-    "searchSuitesPlaceholder": "Search suites...",
-    "passSuffix": "pass",
-    "casesCount": "{count, plural, one {# case} other {# cases}}",
-    "runEval": "Run Eval",
-    "runAllSuites": "Jalankan Semua",
-    "runAllRunning": "Menjalankan semua...",
-    "runAllProgress": "Menjalankan {current}/{total}: {name}",
-    "runAllFailedSuites": "{count, plural, one {# suite failed} other {# suites failed}}",
-    "runAllCompleted": "Jalankan {suites} suite — {passed} lulus, {failed} gagal",
-    "runAllCompletedWithFailures": "Menjalankan {completed} suite; {failedSuites} gagal diselesaikan",
-    "runningProgress": "Running {current}/{total}...",
-    "passRate": "pass rate",
-    "summaryBreakdown": "{passed} passed · {failed} failed · {total} total",
-    "passedIconLabel": "✅ Passed",
-    "failedIconLabel": "❌ Failed",
-    "resultPassed": "Lulus",
-    "resultFailed": "Gagal",
-    "expandResult": "Perluas detail hasil",
-    "collapseResult": "Ciutkan detail hasil",
-    "detailsContains": "Contains: \"{term}\"",
-    "detailsRegex": "Regex: {pattern}",
-    "detailsExpected": "Expected: \"{expected}\"",
-    "expectedOutputLabel": "Keluaran yang Diharapkan",
-    "noResultsYet": "No results yet",
-    "testCasesCount": "Test Cases ({count})",
-    "noTestCasesDefined": "No test cases defined",
-    "runEvalHint": "Click \"Run Eval\" to execute all cases against your LLM endpoint. Each test sends a real request through OmniRoute.",
-    "notifyNoTestCases": "No test cases defined for this suite",
-    "notifyAllCasesPassed": "All {total} cases passed ✅",
-    "notifySomeCasesFailed": "{passed}/{total} passed, {failed} failed",
-    "notifyEvalRunFailed": "Eval run failed",
-    "notifyEvalTitle": "Eval: {name}",
-    "modelEvals": "Model Evaluations",
-    "evalsHeroDescription": "Test and validate your LLM endpoints by running predefined evaluation suites. Each suite contains test cases that send real prompts through OmniRoute and compare responses against expected criteria — helping you detect regressions, compare models, and ensure response quality across providers.",
-    "qualityValidation": "Quality Validation",
-    "modelComparison": "Model Comparison",
-    "regressionDetection": "Regression Detection",
-    "latencyBenchmarks": "Latency Benchmarks",
-    "modelLockouts": "Model Lockouts",
-    "noLockouts": "No models currently locked",
-    "activeSessions": "Active Sessions",
-    "noSessions": "No active sessions",
-    "sessionsHint": "Sessions appear as requests flow through the proxy",
-    "sessionsTrackedHint": "Tracked via request fingerprinting • Auto-refresh 5s",
-    "session": "Session",
-    "age": "Age",
-    "requests": "Requests",
-    "connection": "Connection",
-    "durationMillisecondsShort": "{value}ms",
-    "durationSecondsShort": "{value}s",
-    "durationMinutesShort": "{value}m",
-    "durationHoursShort": "{value}h",
-    "reasonSeparator": "-",
-    "notAvailableSymbol": "-",
-    "providerLimits": "Provider Limits",
-    "noProviders": "No Providers Connected",
-    "connectProvidersForQuota": "Connect to providers with OAuth to track your API quota limits and usage.",
-    "accountsCount": "{count, plural, one {# account} other {# accounts}}",
-    "filteredFromCount": "(filtered from {count})",
-    "autoRefresh": "Auto-refresh",
-    "refreshAll": "Refresh All",
-    "loadingQuotas": "Loading...",
-    "showMoreQuotas": "Tampilkan {count} lagi",
-    "showLessQuotas": "Tampilkan lebih sedikit",
-    "hideQuotaRow": "Sembunyikan baris kuota ini",
-    "showQuotaRow": "Tampilkan baris kuota ini",
-    "hiddenQuotaRowsLabel": "Tersembunyi:",
-    "quotaVisibilityUpdateFailed": "Gagal memperbarui visibilitas kuota",
-    "account": "Account",
-    "modelQuotas": "Model Quotas",
-    "lastUsed": "Last Refreshed",
-    "actions": "Actions",
-    "refreshQuota": "Refresh quota",
-    "today": "Today",
-    "tomorrow": "Tomorrow",
-    "dayTimeFormat": "{day}, {time}",
-    "inDuration": "in {duration}",
-    "notApplicable": "N/A",
-    "rawPlanWithValue": "Raw plan: {plan}",
-    "noPlanFromProvider": "No plan from provider",
-    "tokenExpiresIn": "Token kedaluwarsa dalam {time}",
-    "tokenExpired": "Token kedaluwarsa",
-    "noQuotaData": "No quota data",
-    "cardExpand": "Perluas",
-    "cardCollapse": "Ciutkan",
-    "moreQuotas": "+{count} lagi",
-    "ungrouped": "Ungrouped",
-    "viewFlat": "Flat",
-    "viewByEnvironment": "By Environment",
-    "noQuotaDataAvailable": "No quota data available",
-    "noAccountsForTierFilter": "No accounts found for tier filter",
-    "tierAll": "All",
-    "tierEnterprise": "Enterprise",
-    "tierTeam": "Team",
-    "tierBusiness": "Business",
-    "tierUltra": "Ultra",
-    "tierPro": "Pro",
-    "tierPlus": "Plus",
-    "tierFree": "Free",
-    "tierLite": "Lite",
-    "tierUnknown": "Unknown",
-    "statTotal": "Total",
-    "statCritical": "Kritis",
-    "statAlert": "Peringatan",
-    "statHealthy": "Sehat",
-    "filterPurchaseTypeLabel": "Tipe",
-    "filterTierLabel": "Tingkat",
-    "purchaseAll": "Semua",
-    "purchaseOauthSub": "Langganan",
-    "purchaseOauthFree": "OAuth Gratis",
-    "purchaseApiKey": "Kunci API",
-    "creditsLabel": "Kredit",
-    "creditBalanceHint": "Saldo tersisa",
-    "unlimitedLabel": "Tak terbatas",
-    "refreshing": "Menyegarkan",
-    "resetsIn": "Direset dalam",
-    "usdCost": "Biaya USD",
-    "editCutoffs": "Edit potongan",
-    "forceRefresh": "Segarkan sekarang",
-    "resetCreditsLabel": "Kredit reset",
-    "redeemResetCredit": "Tukarkan reset",
-    "manageResetCredits": "Lihat kredit",
-    "viewResetCredits": "Lihat kredit reset",
-    "resetCreditsModalTitle": "Kredit reset Codex",
-    "resetCreditsModalExplainer": "Kredit diurutkan berdasarkan kedaluwarsa. Penukaran otomatis selalu menggunakan kredit yang kedaluwarsa lebih dahulu.",
-    "resetCreditsLoadFailed": "Gagal memuat kredit reset",
-    "resetCreditsDetailsUnavailable": "Detail kredit saat ini tidak tersedia. Segarkan dan coba lagi.",
-    "noResetCreditsAvailable": "Tidak ada kredit setel ulang jang tersedia.",
-    "resetCreditDefaultTitle": "Setel ulang penuh",
-    "resetCreditExpiresFirst": "Kadaluwarsa lebih dahulu",
-    "resetCreditExpiresAt": "Kadaluwarsa {date}",
-    "resetCreditNoExpiry": "Tidak ada tanggal kadaluwarsa",
-    "redeemThisResetCredit": "Tukarkan",
-    "confirmRedeemResetCreditTitle": "Tukarkan kredit setel ulang ini?",
-    "confirmRedeemResetCredit": "Penukaran akan segera menjetel ulang djendela penggunaan Codex jang memenuhi sjarat dan menghabiskan kredit ini setjara permanen.",
-    "confirmRedeemResetCreditButton": "Tukarkan kredit",
-    "resetCreditRedeemed": "Setel ulang telah ditukarkan",
-    "resetCreditRedeemFailed": "Gagal menukarkan kredit setel ulang",
-    "suiteBuilderSaveFailed": "Failed to save suite",
-    "clone": "Klon",
-    "exportSuite": "Ekspor",
-    "importSuite": "Impor",
-    "suiteExported": "Suite diekspor",
-    "suiteExportFailed": "Gagal mengekspor rangkaian",
-    "suiteImportReady": "Impor suite dimuat untuk ditinjau",
-    "suiteImportFailed": "Gagal mengimpor rangkaian",
-    "suiteImportInvalid": "JSON rangkaian evaluasi tidak valid",
-    "suiteBuilderCloneSuffix": "salin",
-    "suiteBuilderImportedSuite": "Suite yang Diimpor",
-    "scorecardTitle": "Scorecard",
-    "evalApiKey": "API Key",
-    "scorecardPassRate": "Pass Rate",
-    "targetTypeModel": "Model",
-    "actualOutputLabel": "Actual Output",
-    "evalTargetHint": "Select a model or combo to evaluate.",
-    "suiteBuilderDeleted": "Suite deleted successfully",
-    "suiteBuilderCaseCardHint": "Define the input prompt and expected output criteria.",
-    "nextResetUtc": "Next reset (UTC)",
-    "scorecardHint": "Aggregated pass rates across all evaluation suites.",
-    "suiteLatestRunsHint": "Most recent evaluation runs for this suite.",
-    "saving": "Saving",
-    "suiteBuilderCaseModelLabel": "Model (optional)",
-    "evalControlsTitle": "Evaluation Controls",
-    "suiteBuilderEditTitle": "Edit Eval Suite",
-    "suiteBuilderCaseStrategyLabel": "Validation Strategy",
-    "notifySelectDifferentCompareTarget": "Please select a different target for comparison",
-    "recentRunsHint": "Showing the most recent evaluation runs. Click a run to see detailed results.",
-    "evalCompareHint": "Optionally compare results against a second target.",
-    "suiteBuilderCaseInvalid": "This case has validation errors. Please fix before saving.",
-    "historyEmpty": "No evaluation history yet",
-    "suiteBuilderUpdated": "Suite updated successfully",
-    "resetInterval": "Reset Interval",
-    "suiteBuilderCreateTitle": "Create Eval Suite",
-    "activePeriodSpend": "Active Period Spend",
-    "evalApiKeyHint": "Select which API key to use for evaluation requests.",
-    "evalCompareOptional": "Compare (optional)",
-    "suiteBuilderDeleteFailed": "Failed to delete suite",
-    "suiteBuilderCaseSystemPromptPlaceholder": "Optional system instructions...",
-    "scorecardCases": "Cases",
-    "runCompletedWithScore": "Evaluation completed — {score}% pass rate",
-    "suiteBuilderCustomBadge": "Custom",
-    "targetSuiteDefaults": "Suite defaults",
-    "suiteBuilderDeleteConfirm": "Are you sure you want to delete this suite? This action cannot be undone.",
-    "suiteBuilderNameLabel": "Suite Name",
-    "scorecardSuites": "Suites",
-    "evalCompareTarget": "Compare Target",
-    "suiteBuilderCaseModelPlaceholder": "e.g. gpt-4o-mini",
-    "evalControlsHint": "Configure your evaluation target and API key, then run suites to validate model quality.",
-    "recentRunsTitle": "Recent Runs",
-    "suiteBuilderCaseSystemPromptLabel": "System Prompt",
-    "suiteBuilderCaseExpectedPlaceholder": "e.g. def fibonacci",
-    "suiteBuilderCaseExpectedPlaceholderContains": "misalnya def fibonacci",
-    "suiteBuilderCaseExpectedPlaceholderExact": "Tempelkan respons yang diharapkan secara tepat",
-    "suiteBuilderCaseExpectedPlaceholderRegex": "misalnya ^\\\\s*\\\\{.*\\\\}\\\\s*$",
-    "suiteBuilderCaseExpectedHintRegex": "Gunakan ekspresi reguler JavaScript tanpa menambahkan garis miring.",
-    "suiteBuilderNamePlaceholder": "e.g. Coding Quality Suite",
-    "suiteBuilderAddCase": "Add Case",
-    "cancel": "Cancel",
-    "evalTarget": "Target",
-    "suiteBuilderCaseNameLabel": "Case Name",
-    "weeklyLimitUsd": "Weekly Limit (USD)",
-    "suiteBuilderCaseUserPromptPlaceholder": "e.g. Write a fibonacci function in Python",
-    "suiteBuilderNameRequired": "Suite name is required",
-    "suiteBuilderCaseUserPromptLabel": "User Prompt",
-    "daily": "Daily",
-    "resultErrorLabel": "Error",
-    "suiteBuilderBuiltInBadge": "Built-in",
-    "suiteBuilderCaseCardTitle": "Test Case",
-    "suiteBuilderDuplicateCase": "Duplikat",
-    "weeklyLimitPlaceholder": "e.g. 50.00",
-    "suiteBuilderCaseTagsHint": "Comma-separated tags for organizing test cases.",
-    "notifyEvalRunFailedWithReason": "Evaluation failed: {reason}",
-    "weekly": "Weekly",
-    "runEvalRunning": "Running evaluation...",
-    "delete": "Delete",
-    "resetTimeUtc": "Reset Time (UTC)",
-    "evalApiKeyAuto": "Auto (use default)",
-    "suiteBuilderDescriptionPlaceholder": "Optional description of what this suite tests...",
-    "targetComparisonTitle": "Target Comparison",
-    "save": "Save",
-    "suiteBuilderCreated": "Suite created successfully",
-    "suiteLatestRuns": "Latest Runs",
-    "suiteBuilderCaseExpectedLabel": "Expected Value",
-    "historyLatency": "Latency",
-    "suiteBuilderCaseTagsPlaceholder": "e.g. coding, python",
-    "targetTypeCombo": "Combo",
-    "scorecardPassed": "Passed",
-    "suiteBuilderCaseTagsLabel": "Tags",
-    "suiteBuilderNewSuite": "New Suite",
-    "notifyEvalLoadFailed": "Failed to load evaluation data",
-    "notConfigured": "Not Configured",
-    "suiteBuilderCaseNamePlaceholder": "e.g. Python fibonacci test",
-    "intervalLabel": "Interval",
-    "suiteBuilderCreateAction": "Create Suite",
-    "suiteBuilderCasesHint": "Each case sends a prompt and validates the response.",
-    "suiteBuilderUpdatedAt": "Updated",
-    "errorBadge": "Error",
-    "suiteBuilderCasesTitle": "Test Cases",
-    "edit": "Edit",
-    "monthly": "Monthly",
-    "suiteBuilderCasesRequired": "At least one test case is required",
-    "weeklyLimitSummary": "Weekly budget limit summary",
-    "suiteBuilderDescriptionLabel": "Description",
-    "targetComparisonHint": "Side-by-side comparison of evaluation results between targets.",
-    "compareCompletedWithScore": "Comparison completed — {score}% pass rate",
-    "staleQuotaTooltip": "Last refresh failed — showing cached data",
-    "quotaThresholdLabel": "menit ke kiri",
-    "quotaCutoffsColumnHelp": "Hentikan permintaan ketika sisa kuota mencapai persentase ini atau lebih rendah.",
-    "quotaCutoffsButtonDefault": "Bawaan",
-    "quotaCutoffsButtonHelp": "Edit batas sisa kuota minimum untuk akun ini.",
-    "quotaCutoffsButtonDisabled": "Belum ada jendela kuota yang tersedia untuk akun ini.",
-    "deactivateAccount": "Nonaktifkan akun (hentikan perutean)",
-    "activateAccount": "Aktifkan akun (landjutkan perutean)",
-    "accountActivated": "Akun diaktifkan",
-    "accountDeactivated": "Akun dinonaktifkan",
-    "toggleActiveFailed": "Gagal memperbarui status akun",
-    "quotaCutoffsTitle": "Pemotongan kuota untuk {name} ({provider})",
-    "quotaCutoffsExplainer": "Ganti persentase sisa kuota minimum saat akun ini berhenti dipilih untuk setiap jendela kuota. Biarkan kosong untuk mewarisi default penyedia.",
-    "quotaCutoffsDefaultHint": "Sisa minimum default: {default}%",
-    "quotaCutoffsResetAll": "Setel ulang semua",
-    "quotaCutoffsNoWindows": "Belum ada jendela kuota yang tersedia untuk akun ini.",
-    "quotaThresholdInvalid": "Masukkan bilangan bulat dari 0 hingga 100.",
-    "budgetKpiToday": "Hari ini",
-    "budgetKpiThisMonth": "Bulan ini",
-    "budgetKpiProjEom": "Proyek EOM",
-    "budgetKpiBlocked": "Diblokir",
-    "budgetKpiAtRisk": "Beresiko",
-    "budgetKpiActiveKeys": "Kunci aktif",
-    "budgetPageTitle": "Anggaran",
-    "budgetPageDescription": "Atur batas pengeluaran harian, mingguan, dan bulanan untuk setiap kuntji API.",
-    "budgetTemplateStorageHint": "{count, plural, one {# templat} other {# templat}} · sunting melalui localStorage:",
-    "budgetAboveLimitShort": "di atas batas ⚠",
-    "budgetOnTrackShort": "sesuai djalur",
-    "budgetAtOrAboveWarning": "≥ ambang batas peringatan",
-    "budgetTemplates": "Templat",
-    "budgetSelectKeysFirst": "Pilih kuntji terlebih dahulu untuk menerapkan",
-    "budgetApplyToSelected": "Terapkan ke {count, plural, one {# kuntji jang dipilih} other {# kuntji jang dipilih}}",
-    "budgetSelectedTemplateHint": "{count, plural, one {# terpilih} other {# terpilih}} · klik templat untuk menerapkan",
-    "budgetTemplateMonthlyAmount": "${amount}/bulan",
-    "budgetTemplateDailyAmount": "${amount}/hari",
-    "budgetNoKeysSelected": "Tidak ada kuntji jang dipilih",
-    "budgetTemplateApplied": "Menerapkan \"{template}\" ke {count, plural, one {# kuntji} other {# kuntji}}",
-    "budgetTemplateApplyFailed": "Gagal menerapkan templat",
-    "budgetTemplateNames": {
-      "tpl-prod": "Produksi",
-      "tpl-dev": "Pengembangan",
-      "tpl-ci": "CI"
-    },
-    "budgetStatus": {
-      "all": "Semua",
-      "blocked": "Diblokir",
-      "alerting": "Peringatan",
-      "warning": "Peringatan",
-      "safe": "Aman",
-      "no-limit": "Tanpa batas"
-    },
-    "budgetColumnKey": "Kunci",
-    "budgetColumnToday": "Hari ini",
-    "budgetColumnMonth": "Bulan",
-    "budgetColumnStatus": "Status",
-    "budgetSearchKeysPlaceholder": "Kunci pencarian...",
-    "budgetSortPctUsed": "Urutkan: % Digunakan ↓",
-    "budgetSortTodayDollar": "Urutkan: Hari ini $ ↓",
-    "budgetSortMonthDollar": "Urutkan: Bulan $ ↓",
-    "budgetSortNameAZ": "Sortir: Nama (A–Z)",
-    "budgetColDailyLim": "Batas harian",
-    "budgetColMonthlyLim": "Batas bulanan",
-    "budgetColUsedPct": "% terpakai",
-    "percentUsed": "{pct}% digunakan",
-    "budgetLoading": "Memuat…",
-    "budgetNoKeysMatch": "Tidak ada kunci yang cocok dengan filter",
-    "budgetLinearExtrapolation": "ekstrapolasi linier",
-    "budgetThisMonthSoFar": "Bulan ini sejauh ini",
-    "budgetProjectedEndOfMonth": "Proyeksi akhir bulan",
-    "budgetByProvider": "oleh penyedia",
-    "budgetProjection": "Proyeksi",
-    "budgetAboveMonthlyLimit": "⚠ di atas {limit}/bulan",
-    "budgetCostBreakdown30d": "Rincian biaya (30 hari)",
-    "budgetLimits": "Batasan",
-    "budgetResetDaily": "Harian",
-    "budgetResetWeekly": "Mingguan",
-    "budgetResetMonthly": "Bulanan",
-    "budgetNextReset": "Reset berikutnya",
-    "budgetHardCapComingSoon": "Kebijakan batas tegas dan peringatan email akan segera hadir",
-    "unknownProvider": "Penyedia tidak dikenal",
-    "budgetDailyDollar": "Setiap hari $",
-    "budgetWeeklyDollar": "Mingguan $",
-    "budgetMonthlyDollar": "$bulanan",
-    "budgetWarnAtPct": "Peringatkan pada%",
-    "quotaAlerts": "Peringatan kuota",
-    "quotaTableRefreshing": "⟳ Menyegarkan...",
-    "noSpendLast30Days": "Tidak ada pembelanjaan dalam 30 hari terakhir",
-    "updatedShort": "Diperbarui",
-    "lastRefreshed": "Terakhir disegarkan",
-    "providerQuota": "Kuota Penyedia",
-    "providerQuotaHomeHint": "Status langsung di seluruh akun yang terhubung"
-  },
-  "modals": {
-    "waitingAuth": "Waiting for Authorization",
-    "verificationUrl": "Verification URL",
-    "yourCode": "Your Code",
-    "remoteAccess": "Remote access:",
-    "connectedSuccess": "Connected Successfully!",
-    "connectionFailed": "Connection Failed",
-    "chooseAuthMethod": "Choose your authentication method:",
-    "awsBuilderId": "AWS Builder ID",
-    "awsIamIdentity": "AWS IAM Identity Center",
-    "googleAccount": "Google Account",
-    "githubAccount": "GitHub Account",
-    "importToken": "Import Token",
-    "pasteToken": "Paste refresh token from Kiro IDE.",
-    "awsRegion": "AWS Region",
-    "autoDetecting": "Auto-detecting tokens...",
-    "readingFromCache": "Reading from AWS SSO cache",
-    "readingFromCursor": "Reading from Cursor IDE database",
-    "initializing": "Initializing...",
-    "pricingConfig": "Pricing Configuration",
-    "loadingPricing": "Loading pricing data...",
-    "pricingRatesFormat": "Pricing Rates Format",
-    "noPricingData": "No pricing data available",
-    "noModelsFound": "No models found"
-  },
-  "loggers": {
-    "allProviders": "All Providers",
-    "allModels": "All Models",
-    "allAccounts": "All Accounts",
-    "allApiKeys": "All API Keys",
-    "allTypes": "All Types",
-    "allLevels": "All Levels",
-    "modelAZ": "Model A-Z",
-    "modelZA": "Model Z-A",
-    "loadingLogs": "Loading logs...",
-    "loadingProxyLogs": "Loading proxy logs...",
-    "noLogEntries": "No log entries found",
-    "noPayloadData": "No payload data available for this log entry.",
-    "proxyEvent": "Proxy Event",
-    "proxy": "Proxy",
-    "level": "Level",
-    "directNative": "Direct (native)",
-    "combo": "Combo",
-    "inputTokens": "I:",
-    "outputTokens": "O:"
-  },
-  "stats": {
-    "usageOverview": "Usage Overview",
-    "outputTokens": "Output Tokens",
-    "totalCost": "Total Cost",
-    "usageByModel": "Usage by Model",
-    "usageByAccount": "Usage by Account",
-    "failedToLoad": "Failed to load usage statistics.",
-    "tokenHealth": "Token Health",
-    "totalOAuth": "Total OAuth",
-    "healthy": "Healthy",
-    "warning": "Warning",
-    "errored": "Errored",
-    "lastCheck": "Last check",
-    "noData": "No data",
-    "share": "Share",
-    "unableToLoad": "Unable to load system metrics",
-    "product": "Product",
-    "resources": "Resources",
-    "company": "Company",
-    "tokenHealthTooltips": {
-      "allHealthy": "Semua token sehat",
-      "needsAttention": "Beberapa token perlu perhatian",
-      "refreshFailures": "Kegagalan penyegaran token terdeteksi",
-      "unknown": "Status kesehatan tidak diketahui"
-    },
-    "systemMonitor": {
-      "metricsAriaLabel": "Metrik sistem",
-      "memory": "Memori",
-      "memoryShort": "mem",
-      "uptime": "Waktu Aktif",
-      "ariaLabel": "Pemantauan Sistem",
-      "title": "Pemantau Sistem",
-      "version": "Versi",
-      "connections": "Koneksi",
-      "circuitBreakers": "Pemutus Sirkuit",
-      "open": "{count} terbuka",
-      "memoryUsage": "Penggunaan Memori"
-    },
-    "never": "Tidak Pernah",
-    "justNow": "Baru saja",
-    "minutesAgo": "{count}m yang lalu",
-    "hoursAgo": "{count}j yang lalu",
-    "tokens": "Token",
-    "costs": "Biaya",
-    "autoRefresh": "Penyegaran Otomatis ({seconds}s)",
-    "toggleAutoRefresh": "Alihkan penyegaran otomatis",
-    "activeRequests": "Permintaan Aktif",
-    "totalRequests": "Total Permintaan",
-    "totalInputTokens": "Total Input Tokens",
-    "model": "Model",
-    "provider": "Penyedia",
-    "requests": "Permintaan",
-    "lastUsed": "Terakhir Digunakan",
-    "inputTokens": "Token Masukan",
-    "totalTokens": "Total Token",
-    "inputCost": "Biaya Input",
-    "outputCost": "Biaya Output",
-    "noUsageData": "Belum ada penggunaan yang tercatat. Lakukan beberapa permintaan untuk melihat data di sini.",
-    "account": "Akun",
-    "accountLabel": "Akun {id}",
-    "noAccountUsage": "Belum ada penggunaan spesifik akun yang tercatat. Lakukan permintaan menggunakan akun OAuth untuk melihat data di sini."
-  },
-  "auth": {
-    "welcome": "Welcome",
-    "signIn": "Sign in",
-    "enterPassword": "Enter your password to continue",
-    "password": "Password",
-    "unifiedProxy": "Unified AI API Proxy",
-    "unifiedAiApiProxy": "Unified AI API Proxy",
-    "unifiedAiApiProxyDesc": "Route requests to multiple AI providers through a single endpoint. Load balancing, failover, and usage tracking built in.",
-    "passwordNotEnabled": "Password protection is not enabled",
-    "loading": "Loading...",
-    "invalidPassword": "Invalid password",
-    "errorOccurredRetry": "An error occurred. Please try again.",
-    "configureInstance": "Let's get your OmniRoute instance configured",
-    "runOnboardingWizard": "Run the onboarding wizard to set up your password and connect your first AI provider.",
-    "startOnboarding": "Start Onboarding",
-    "secureYourInstance": "Secure Your Instance",
-    "setPasswordDescription": "Set a password to protect your dashboard and secure your API endpoints from unauthorized access.",
-    "configurePassword": "Configure Password",
-    "continue": "Continue",
-    "windowWillClose": "This window will close automatically...",
-    "closeTabNow": "You can close this tab now.",
-    "copyUrlManual": "Please copy the URL from the address bar and paste it in the application.",
-    "accessDeniedDescription": "You don't have permission to access this resource. Check your API key or contact the administrator.",
-    "goToDashboard": "Go to Dashboard",
-    "featureMultiProviderTitle": "Multi-Provider",
-    "featureMultiProviderDesc": "OpenAI, Anthropic, Google, and more",
-    "featureLoadBalancingTitle": "Load Balancing",
-    "featureLoadBalancingDesc": "Distribute requests intelligently",
-    "featureUsageTrackingTitle": "Usage Tracking",
-    "featureUsageTrackingDesc": "Monitor costs and tokens",
-    "resetPassword": "Reset Password",
-    "resetDescription": "Choose a method to recover access to your dashboard",
-    "stopServer": "Stop the OmniRoute server",
-    "processing": "Processing...",
-    "pleaseWait": "Please wait while we complete the authorization.",
-    "authSuccess": "Authorization Successful!",
-    "copyUrl": "Copy This URL",
-    "accessDenied": "Access Denied",
-    "methodCliTitle": "Method 1: CLI Reset",
-    "methodCliDescription": "Run the following command on the server where OmniRoute is running:",
-    "methodCliHint": "This will prompt you to set a new password. The server must be stopped first.",
-    "methodManualTitle": "Method 2: Manual Reset",
-    "methodManualDescription": "Delete the password from the database and set a new one on startup:",
-    "setPasswordInYour": "Set a new password in your",
-    "fileLabelSuffix": "file:",
-    "newPasswordPlaceholder": "your_new_password",
-    "deleteSettingsFile": "Delete",
-    "orRemovePasswordHashField": "or remove the passwordHash field",
-    "restartServerWithNewPassword": "Restart the server - it will use the new password",
-    "backToLogin": "Back to Login",
-    "forgotPassword": "Forgot password?",
-    "continueWithOidc": "Lanjutkan dengan OIDC",
-    "defaultPasswordHint": "Default password: CHANGEME (unless INITIAL_PASSWORD was set)",
-    "Authorization": "Authorization",
-    "Content-Disposition": "Content-Disposition",
-    "waitingForAuthorization": "Waiting for authorization...",
-    "waitingForGoogleAuthorization": "Waiting for Google authorization...",
-    "waitingForOpenAIAuthorization": "Waiting for OpenAI authorization...",
-    "waitingForAntigravityAuthorization": "Waiting for Antigravity authorization...",
-    "waitingForQoderAuthorization": "Waiting for Qoder authorization...",
-    "exchangingCodeForTokens": "Exchanging code for tokens...",
-    "nodeIncompatibleTitle": "Incompatible Node.js Version",
-    "nodeIncompatibleDesc": "You are running Node.js {version}, which is outside OmniRoute's supported secure runtime policy. Use a patched Node.js 20.x or 22.x LTS release.",
-    "nodeIncompatibleFixLabel": "Fix: install a patched Node.js 22 LTS release",
-    "nodeIncompatibleHint": "OmniRoute requires Node.js 22.22.2+ (22.x LTS) or 24.0.0+ (24.x LTS). Node 24 LTS is recommended.",
-    "resetViaAppDataTitle": "Reset melalui Data Aplikasi",
-    "resetViaAppDataDescription": "Hapus file pengaturan dari direktori data aplikasi untuk mengatur ulang kata sandi Anda:",
-    "quitDesktopApp": "Tutup aplikasi desktop OmniRoute sepenuhnya",
-    "navigateToAppDataDirectory": "Navigasikan ke direktori data aplikasi:",
-    "checkSystemAppDataFolder": "(Cek folder data aplikasi sistem Anda)",
-    "relaunchDesktopFreshSetup": "Luncurkan kembali aplikasi desktop OmniRoute — itu akan memulai pengaturan baru",
-    "alternativeSetPasswordTitle": "Alternatif: Atur Kata Sandi Baru",
-    "alternativeSetPasswordDescription": "Atur kata sandi awal yang baru melalui file lingkungan server:",
-    "openServerEnvFilePrefix": "Buka",
-    "relaunchDesktopApp": "Luncurkan kembali aplikasi desktop OmniRoute",
-    "codexLinkInvalidOrExpired": "Tautan ini tidak valid atau telah kedaluwarsa.",
-    "codexValidationServerError": "Tidak dapat menghubungi server untuk memvalidasi tautan ini.",
-    "codexSaveConnectionError": "Tidak dapat menyimpan koneksi. Tautan mungkin telah kedaluwarsa.",
-    "codexDeviceLoginDisabled": "Login kode perangkat dinonaktifkan untuk akun OpenAI ini. Aktifkan di pengaturan keamanan ChatGPT (atau tanyakan kepada admin ruang kerja Anda).",
-    "codexAuthorizationTimedOut": "Waktu otorisasi habis. Klik Mulai lagi untuk mencoba kembali.",
-    "authenticationCancelled": "Autentikasi dibatalkan.",
-    "unexpectedAuthenticationError": "Kesalahan tak terduga selama otentikasi. Silakan coba lagi.",
-    "connectOpenAiCodexTitle": "Sambungkan OpenAI Codex",
-    "codexConnectDescription": "Otorisasi akun ChatGPT untuk menyelesaikan pengaturan koneksi ini.",
-    "validatingCodexLink": "Memvalidasi tautan…",
-    "codexGenerateCodeDescription": "Klik di bawah untuk menghasilkan kode sekali pakai, lalu masuk ke OpenAI.",
-    "startCodexFlow": "Mulai",
-    "requestingOpenAiCode": "Meminta kode dari OpenAI…",
-    "codexVerificationInstructions": "1. Buka halaman verifikasi OpenAI dan 2. masukkan kode ini. Halaman ini diperbarui secara otomatis setelah Anda memberikan otorisasi.",
-    "yourCode": "Kode Anda",
-    "openVerificationPage": "Buka halaman verifikasi",
-    "copyUrlShort": "Salin URL",
-    "savingConnection": "Menyimpan koneksi…",
-    "codexConnected": "Terhubung!",
-    "codexConnectionRegistered": "Akun Codex telah terdaftar. Anda dapat menutup tab ini.",
-    "tryAgain": "Coba lagi",
-    "traeAuthorizationSuccess": "Trae otorisasi ✓",
-    "traeAuthorizationFailed": "Trae otorisasi gagal",
-    "closeAuthorizationWindow": "Anda dapat menutup jendela ini.",
-    "returnToDashboard": "Kembali ke dasbor.",
-    "resetViaAppData": "Reset melalui Data Aplikasi",
-    "deleteSettingsToReset": "Hapus file pengaturan dari direktori data aplikasi untuk mengatur ulang kata sandi Anda:",
-    "quitAppCompletely": "Keluar dari aplikasi desktop OmniRoute sepenuhnya",
-    "navigateToAppData": "Navigasikan ke direktori data aplikasi",
-    "checkAppDataFolder": "Periksa folder data aplikasi sistem Anda",
-    "deleteSettingsJson": "Hapus",
-    "relaunchAppFresh": "Luncurkan kembali aplikasi desktop OmniRoute — itu akan memulai pengaturan baru",
-    "alternativeSetPassword": "Alternatif: Atur Kata Sandi Baru",
-    "setNewPasswordViaEnv": "Atur kata sandi awal baru melalui file lingkungan server:",
-    "openServerEnv": "Buka",
-    "inDataDirectory": "di direktori data",
-    "addOrUpdate": "Tambahkan atau perbarui",
-    "deleteAndRelaunch": "Hapus",
-    "settingsJson": "settings.json",
-    "fromDataDir": "dari direktori data",
-    "relaunchApp": "Luncurkan kembali aplikasi desktop OmniRoute"
-  },
-  "landing": {
-    "brandName": "OmniRoute",
-    "navigateHome": "Navigate to home",
-    "toggleMenu": "Toggle menu",
-    "featuresLink": "Features",
-    "docsLink": "Docs",
-    "github": "GitHub",
-    "versionLive": "v1.0 is now live",
-    "oneEndpoint": "One Endpoint for",
-    "allProviders": "All AI Providers",
-    "heroDescription": "AI endpoint proxy with web dashboard - A JavaScript port of CLIProxyAPI. Works seamlessly with Claude Code, OpenAI Codex, Cline, RooCode, and other CLI tools.",
-    "getStarted": "Get Started",
-    "viewOnGithub": "View on GitHub",
-    "powerfulFeatures": "Powerful Features",
-    "featuresSubtitle": "Everything you need to manage your AI infrastructure in one place, built for scale.",
-    "featureUnifiedEndpointTitle": "Unified Endpoint",
-    "featureUnifiedEndpointDesc": "Access all providers via a single standard API URL.",
-    "featureEasySetupTitle": "Easy Setup",
-    "featureEasySetupDesc": "Get up and running in minutes with npx command.",
-    "featureModelFallbackTitle": "Model Fallback",
-    "featureModelFallbackDesc": "Automatically switch providers on failure or high latency.",
-    "featureUsageTrackingTitle": "Usage Tracking",
-    "featureUsageTrackingDesc": "Detailed analytics and cost monitoring across all models.",
-    "featureOAuthApiKeysTitle": "OAuth & API Keys",
-    "featureOAuthApiKeysDesc": "Securely manage credentials in one vault.",
-    "featureCloudSyncTitle": "Cloud Sync",
-    "featureCloudSyncDesc": "Sync your configurations across devices instantly.",
-    "featureCliSupportTitle": "CLI Support",
-    "featureCliSupportDesc": "Works with Claude Code, Codex, Cline, Cursor, and more.",
-    "featureDashboardTitle": "Dashboard",
-    "featureDashboardDesc": "Visual dashboard for real-time traffic analysis.",
-    "howItWorks": "How OmniRoute Works",
-    "howItWorksDescription": "Data flows seamlessly from your application through our intelligent routing layer to the best provider for the job.",
-    "howItWorksStep1Title": "1. CLI & SDKs",
-    "howItWorksStep1Description": "Your requests start from your favorite tools or our unified SDK. Just change the base URL.",
-    "howItWorksStep2Title": "2. OmniRoute Hub",
-    "howItWorksStep2Description": "Our engine analyzes the prompt, checks provider health, and routes for lowest latency or cost.",
-    "howItWorksStep3Title": "3. AI Providers",
-    "howItWorksStep3Description": "The request is fulfilled by OpenAI, Anthropic, Gemini, or others instantly.",
-    "getStartedIn30Seconds": "Get Started in 30 Seconds",
-    "getStartedDescription": "Install OmniRoute, configure your providers via web dashboard, and start routing AI requests.",
-    "installOmniRoute": "Install OmniRoute",
-    "installStepDescription": "Run npx command to start the server instantly",
-    "openDashboard": "Open Dashboard",
-    "openDashboardStepDescription": "Configure providers and API keys via web interface",
-    "routeRequests": "Route Requests",
-    "routeRequestsStepDescription": "Point your CLI tools to {endpoint}",
-    "terminal": "terminal",
-    "copy": "Copy",
-    "copied": "✓ Copied",
-    "startingOmniRoute": "Starting OmniRoute...",
-    "serverRunningOnLabel": "Server running on",
-    "dashboardLabel": "Dashboard",
-    "readyToRoute": "Ready to route! ✓",
-    "configureProvidersNote": "📝 Configure providers in dashboard or use environment variables",
-    "dataLocation": "Data Location:",
-    "dataLocationMacLinux": "macOS/Linux:",
-    "dataLocationWindows": "Windows:",
-    "product": "Product",
-    "dashboardLink": "Dashboard",
-    "changelog": "Changelog",
-    "resources": "Resources",
-    "documentation": "Documentation",
-    "npm": "NPM",
-    "legal": "Legal",
-    "mitLicense": "MIT License",
-    "footerTagline": "The unified endpoint for AI generation. Connect, route, and manage your AI providers with ease.",
-    "copyright": "© {year} OmniRoute. All rights reserved.",
-    "flowToolClaudeCode": "Claude Code",
-    "flowToolOpenAICodex": "OpenAI Codex",
-    "flowToolCline": "Cline",
-    "flowToolCursor": "Cursor",
-    "flowProviderOpenAI": "OpenAI",
-    "flowProviderAnthropic": "Anthropic",
-    "flowProviderGemini": "Gemini",
-    "flowProviderGithubCopilot": "GitHub Copilot",
-    "interactiveDiagram": "Interactive diagram visible on desktop",
-    "ctaTitle": "Ready to Simplify Your AI Infrastructure?",
-    "ctaDescription": "Join developers who are streamlining their AI integrations with OmniRoute. Open source and free to start.",
-    "startFree": "Start Free",
-    "readDocumentation": "Read Documentation",
-    "company": "Perusahaan",
-    "pricing": "Harga",
-    "apiReference": "Referensi API",
-    "helpCenter": "Pusat Bantuan",
-    "about": "Tentang",
-    "blog": "Blog",
-    "contact": "Kontak",
-    "terms": "Syarat",
-    "privacy": "Privasi",
-    "license": "Lisensi",
-    "footerDescription": "Antarmuka terpadu untuk infrastruktur AI modern. Aman, dapat diamati, dan dapat diskalakan.",
-    "communityDiscussions": "Diskusi Komunitas"
-  },
-  "docs": {
-    "title": "Documentation",
-    "quickStart": "Quick Start",
-    "deploymentGuides": "Panduan Penerapan",
-    "features": "Features",
-    "supportedProviders": "Supported Providers",
-    "supportedProvidersToc": "Providers",
-    "commonUseCases": "Common Use Cases",
-    "clientCompatibility": "Client Compatibility",
-    "protocolsToc": "Protocols",
-    "apiReference": "API Reference",
-    "managementApiReference": "Management API Reference",
-    "managementApiDescription": "Automation endpoints for proxy registry, scope assignments, and legacy proxy migration.",
-    "method": "Method",
-    "path": "Path",
-    "notes": "Notes",
-    "modelPrefixes": "Model Prefixes",
-    "prefix": "Prefix",
-    "troubleshooting": "Troubleshooting",
-    "supportsChat": "Supports both chat and responses endpoints.",
-    "oauthAutoRefresh": "OAuth connection with automatic token refresh.",
-    "fullStreaming": "Full streaming support for all models.",
-    "docsLabel": "Docs",
-    "docsHeroDescription": "AI gateway for multi-provider LLMs. One endpoint for OpenAI, Anthropic, Gemini, DeepSeek, GitHub Copilot, Claude Code, Cursor, and 100+ more providers.",
-    "openDashboard": "Open Dashboard",
-    "endpointPage": "Endpoint Page",
-    "github": "GitHub",
-    "reportIssue": "Report Issue",
-    "onThisPage": "On this page",
-    "documentationVersion": "Documentation - v{version}",
-    "quickStartStep1Title": "1. Install and run",
-    "quickStartStep1Prefix": "Run",
-    "quickStartStep1Middle": "or clone from GitHub and run",
-    "quickStartStep2Title": "2. Create API key",
-    "quickStartStep2Text": "Go to Endpoint -> Registered Keys. Generate one key per environment.",
-    "quickStartStep3Title": "3. Connect providers",
-    "quickStartStep3Text": "Add provider accounts via OAuth login, API key, or free-tier auto-connect.",
-    "quickStartStep4Title": "4. Set client base URL",
-    "quickStartStep4Prefix": "Point your IDE or API client to",
-    "quickStartStep4Suffix": "Use provider prefix, for example",
-    "deploySetupTitle": "Panduan Pengaturan",
-    "deploySetupText": "Instalasi langkah demi langkah, konfigurasi lingkungan, dan panduan pertama kali dijalankan untuk OmniRoute.",
-    "deployElectronTitle": "Desktop Elektron",
-    "deployElectronText": "Jalankan OmniRoute sebagai aplikasi desktop asli di Windows, macOS, dan Linux.",
-    "deployDockerTitle": "buruh pelabuhan",
-    "deployDockerText": "Penerapan dalam container dengan Docker Compose; siap untuk tumpukan produksi dan Kubernetes.",
-    "deployVmTitle": "Mesin Virtual",
-    "deployVmText": "Host mandiri di VM Linux apa pun. Termasuk unit systemd, rotasi log, dan perkakas cadangan.",
-    "deployFlyTitle": "Terbang.io",
-    "deployFlyText": "Terapkan ke runtime Fly.io edge dengan satu fly.toml dan satu perintah penerapan.",
-    "deployPwaTitle": "PWA",
-    "deployPwaText": "Instal OmniRoute sebagai Aplikasi Web Progresif di browser Android, iOS, dan desktop.",
-    "deployTermuxTitle": "Termux (Android)",
-    "deployTermuxText": "Run OmniRoute headless on Android via Termux. Access the dashboard from your mobile browser.",
-    "featureRoutingTitle": "Multi-Provider Routing",
-    "featureRoutingText": "Route requests to 30+ AI providers through a single OpenAI-compatible endpoint. Supports chat, responses, audio, and image APIs.",
-    "featureCombosTitle": "Combos and Balancing",
-    "featureCombosText": "Create model combos with fallback chains and balancing strategies: round-robin, priority, random, least-used, and cost-optimized.",
-    "featureUsageTitle": "Usage and Cost Tracking",
-    "featureUsageText": "Real-time token counting, cost calculation per provider/model, and detailed usage breakdown by API key and account.",
-    "featureAnalyticsTitle": "Analytics Dashboard",
-    "featureAnalyticsText": "Visual analytics with charts for requests, tokens, errors, latency, costs, and model popularity over time.",
-    "featureHealthTitle": "Health Monitoring",
-    "featureHealthText": "Live health checks, provider status, circuit breaker states, and automatic rate limit detection with exponential backoff.",
-    "featureCliTitle": "CLI Tools",
-    "featureCliText": "Manage IDE configurations, export/import backups, discover codex profiles, and configure settings from the dashboard.",
-    "featureSecurityTitle": "Security and Policies",
-    "featureSecurityText": "API key authentication, IP filtering, prompt injection guard, domain policies, session management, and audit logging.",
-    "featureCloudSyncTitle": "Cloud Sync",
-    "featureCloudSyncText": "Sync your configuration to Cloudflare Workers for remote access with encrypted credentials and automatic failover.",
-    "providersAcrossConnectionTypes": "{count} providers across three connection types.",
-    "manageProviders": "Manage Providers",
-    "providersCount": "{count} providers",
-    "providerTypeFree": "Free Tier",
-    "providerTypeOAuth": "OAuth",
-    "providerTypeApiKey": "API Key",
-    "useCaseSingleEndpointTitle": "Single endpoint for many providers",
-    "useCaseSingleEndpointText": "Point clients to one base URL and route by model prefix (for example: gh/, cc/, kr/, openai/).",
-    "useCaseFallbackTitle": "Fallback and model switching with combos",
-    "useCaseFallbackText": "Create combo models in Dashboard and keep client config stable while providers rotate internally.",
-    "useCaseUsageVisibilityTitle": "Usage, cost and debug visibility",
-    "useCaseUsageVisibilityText": "Track tokens and cost by provider, account, and API key in Usage and Analytics tabs.",
-    "clientCherryStudioTitle": "Cherry Studio",
-    "baseUrlLabel": "Base URL",
-    "chatEndpointLabel": "Chat endpoint",
-    "modelRecommendationLabel": "Model recommendation: explicit prefix",
-    "clientCodexTitle": "Codex / GitHub Copilot Models",
-    "clientCodexBullet1": "Use model IDs with",
-    "clientCodexBullet2": "Codex-family models auto-route to",
-    "clientCodexBullet3": "Non-Codex models continue on",
-    "clientCursorTitle": "Cursor IDE",
-    "clientCursorBullet1": "Use",
-    "clientCursorBullet1Suffix": "prefix for Cursor models.",
-    "clientCursorBullet2": "OAuth connection - login from the Providers page.",
-    "clientClaudeTitle": "Claude Code / Antigravity",
-    "clientClaudeBullet1Prefix": "Use",
-    "clientClaudeBullet1Middle": "(Claude) or",
-    "clientClaudeBullet1Suffix": "(Antigravity) prefix.",
-    "clientWindsurfTitle": "Windsurf",
-    "clientWindsurfBullet1": "Use OmniRoute as an OpenAI-compatible base URL and keep explicit provider prefixes for deterministic routing.",
-    "clientWindsurfBullet2": "Point models to `/v1/chat/completions` for general traffic and preserve `/v1/responses` for Codex-style flows.",
-    "clientWindsurfBullet3": "Use Dashboard -> CLI Tools for a ready-made Windsurf configuration guide.",
-    "clientClineTitle": "Cline",
-    "clientClineBullet1": "Cline works best with explicit provider/model prefixes so the router never has to guess the backend.",
-    "clientClineBullet2": "Use `/v1/chat/completions` for general models and reuse the same OmniRoute base URL across different accounts.",
-    "clientClineBullet3": "Use the Providers dashboard to validate OAuth/API key before debugging Cline runtime issues.",
-    "clientKimiTitle": "Kimi Coding",
-    "clientKimiBullet1": "Use OmniRoute as a stable base URL while rotating accounts or provider combos underneath.",
-    "clientKimiBullet2": "Prefer prefixed models in coding flows so fallback and audit trail remain explicit.",
-    "clientKimiBullet3": "Use `/v1/responses` when you want native Responses-style routing for tool-using clients.",
-    "protocolsTitle": "Protocols: MCP & A2A",
-    "protocolsDescription": "OmniRoute exposes two operational protocols in addition to OpenAI-compatible APIs: MCP for tool execution and A2A for agent-to-agent workflows.",
-    "protocolMcpTitle": "MCP (Model Context Protocol)",
-    "protocolMcpDesc": "Use MCP over stdio to let clients discover and call OmniRoute tools with audit visibility.",
-    "protocolMcpStep1": "Start MCP transport with `omniroute --mcp`.",
-    "protocolMcpStep2": "Point your MCP client to stdio transport.",
-    "protocolMcpStep3": "Call `omniroute_get_health` and `omniroute_list_combos` to validate connectivity.",
-    "protocolA2aTitle": "A2A (Agent2Agent)",
-    "protocolA2aDesc": "Use A2A JSON-RPC to submit tasks synchronously or via SSE streaming.",
-    "protocolA2aStep1": "Read `/.well-known/agent.json` for agent discovery.",
-    "protocolA2aStep2": "Send `message/send` or `message/stream` requests to `POST /a2a`.",
-    "protocolA2aStep3": "Manage task lifecycle with `tasks/get` and `tasks/cancel`.",
-    "protocolTroubleshootingTitle": "Protocol Troubleshooting",
-    "protocolTroubleshooting1": "If MCP status is offline, verify the stdio process is running and heartbeat file is updating.",
-    "protocolTroubleshooting2": "If A2A tasks stay in `working`, inspect `/api/a2a/tasks/:id` and stream events for terminal state.",
-    "protocolTroubleshooting3": "Use `/dashboard/mcp` and `/dashboard/a2a` for operational controls and audit visibility.",
-    "endpointChatNote": "OpenAI-compatible chat endpoint (default).",
-    "endpointResponsesNote": "Responses API endpoint (Codex, o-series).",
-    "endpointModelsNote": "Model catalog for all connected providers.",
-    "endpointAudioNote": "Audio transcription (Deepgram, AssemblyAI).",
-    "endpointSpeechNote": "Text-to-speech generation (ElevenLabs, OpenAI TTS).",
-    "endpointEmbeddingsNote": "Text embedding generation (OpenAI, Cohere, Voyage).",
-    "endpointImagesNote": "Image generation (NanoBanana).",
-    "endpointRewriteChatNote": "Rewrite helper for clients without /v1.",
-    "endpointRewriteResponsesNote": "Rewrite helper for Responses without /v1.",
-    "endpointRewriteModelsNote": "Rewrite helper for model discovery without /v1.",
-    "mgmtProxiesListNote": "List saved proxy registry items (supports pagination).",
-    "mgmtProxiesCreateNote": "Create a reusable proxy item in the registry.",
-    "mgmtProxiesHealthNote": "Get 24h/rolling health metrics per saved proxy from proxy logs.",
-    "mgmtProxiesBulkAssignNote": "Assign or clear one proxy across many scope IDs in one request.",
-    "mgmtAssignmentsListNote": "List proxy assignments by scope, scope_id, or proxy_id.",
-    "mgmtAssignmentsUpdateNote": "Assign or clear proxy for global/provider/account/combo scope.",
-    "mgmtLegacyMigrationNote": "Import legacy proxyConfig maps into registry assignments.",
-    "modelPrefixesDescriptionStart": "Use the provider prefix before the model name to route to a specific provider. Example:",
-    "modelPrefixesDescriptionEnd": "routes to GitHub Copilot.",
-    "provider": "Provider",
-    "type": "Type",
-    "troubleshootingModelRouting": "If the client fails with model routing, use explicit provider/model (for example: gh/gpt-5.1-codex).",
-    "troubleshootingAmbiguousModels": "If you receive ambiguous model errors, pick a provider prefix instead of a bare model ID.",
-    "troubleshootingCodexFamily": "For GitHub Codex-family models, keep model as gh/codex-model; router selects /responses automatically.",
-    "troubleshootingTestConnection": "Use Dashboard > Providers > Test Connection before testing from IDEs or external clients.",
-    "troubleshootingCircuitBreaker": "If a provider shows circuit breaker open, wait for the cooldown or check Health page for details.",
-    "troubleshootingOAuth": "For OAuth providers, re-authenticate if tokens expire. Check the provider card status indicator.",
-    "endpointCompletionsNote": "Legacy completions endpoint for text generation.",
-    "endpointModerationsNote": "Content moderation and safety classification.",
-    "endpointRerankNote": "Document reranking for retrieval-augmented generation (Cohere, Jina).",
-    "endpointSearchNote": "Web search with 5 providers (Serper, Brave, Exa, Tavily, Perplexity).",
-    "endpointSearchAnalyticsNote": "Analytics and metrics for search requests.",
-    "endpointVideoNote": "Video generation (ComfyUI, SD WebUI workflows).",
-    "endpointMusicNote": "Music generation via ComfyUI workflows.",
-    "endpointMessagesNote": "Anthropic-native messages endpoint.",
-    "endpointCountTokensNote": "Count tokens for a given message payload.",
-    "endpointFilesNote": "File upload for multimodal inputs.",
-    "endpointBatchesNote": "Batch processing for bulk API requests.",
-    "endpointWsNote": "WebSocket endpoint for real-time streaming.",
-    "mgmtProvidersListNote": "List all registered provider connections.",
-    "mgmtProvidersCreateNote": "Create a new provider connection.",
-    "mgmtProvidersUpdateNote": "Update an existing provider connection.",
-    "mgmtProvidersDeleteNote": "Delete a provider connection.",
-    "mgmtProvidersTestNote": "Test connectivity and authentication for a provider.",
-    "mgmtProvidersModelsNote": "List available models for a specific provider.",
-    "mgmtSettingsGetNote": "Retrieve current application settings.",
-    "mgmtSettingsUpdateNote": "Update application settings.",
-    "mgmtPayloadRulesGetNote": "Get payload transformation rules.",
-    "mgmtPayloadRulesUpdateNote": "Update payload transformation rules.",
-    "mcpToolsTitle": "MCP Tools",
-    "mcpToolsDescription": "OmniRoute exposes {count} tools via Model Context Protocol for agent orchestration.",
-    "mcpToolsCount": "{count} tools",
-    "mcpToolsToc": "MCP Tools",
-    "mcpToolsRoutingTitle": "Routing & Discovery",
-    "mcpToolsRoutingDesc": "Health checks, combo management, quota monitoring, cost reporting, and model catalog access.",
-    "mcpToolsOperationsTitle": "Operations & Strategy",
-    "mcpToolsOperationsDesc": "Route simulation, budget guards, strategy switching, resilience profiles, and provider metrics.",
-    "mcpToolsCacheTitle": "Cache Management",
-    "mcpToolsCacheDesc": "View cache statistics and flush semantic or signature caches.",
-    "mcpToolsCompressionTitle": "Mesin Kompresi",
-    "mcpToolsCompressionDesc": "Konfigurasikan kompresi RTK/Brotli, tukar mesin, dan periksa analisis kompresi berdasarkan kombo.",
-    "mcpToolsOneProxyTitle": "1Proxy / Terowongan",
-    "mcpToolsOneProxyDesc": "Kelola proxy keluar, rotasikan IP perumahan, dan periksa kesehatan proxy.",
-    "mcpToolsMemoryTitle": "Memory",
-    "mcpToolsMemoryDesc": "Search, add, and clear persistent conversational memory entries.",
-    "mcpToolsSkillsTitle": "Skills",
-    "mcpToolsSkillsDesc": "List, enable, execute, and monitor custom skill executions.",
-    "featureAutoComboTitle": "Auto-Combo",
-    "featureAutoComboText": "Automatically create optimized combos based on your connected providers, usage patterns, and model capabilities.",
-    "featureSearchTitle": "Web Search",
-    "featureSearchText": "Integrated web search with 5 providers (Serper, Brave, Exa, Tavily, Perplexity) including analytics and cost tracking.",
-    "featureMemoryTitle": "Memory System",
-    "featureMemoryText": "Persistent conversational memory with extraction, injection, retrieval, and summarization across sessions.",
-    "featureSkillsTitle": "Skills Framework",
-    "featureSkillsText": "Extensible skill system with built-in and custom skills, sandbox execution, request interception, and context injection.",
-    "featureAcpTitle": "Agent Communication",
-    "featureAcpText": "Agent Communication Protocol (ACP) registry for managing agent-to-agent workflows and tool orchestration.",
-    "protocolAcpTitle": "ACP (Agent Communication)",
-    "protocolAcpDesc": "Register and manage agents via the ACP registry for inter-agent communication and tool sharing.",
-    "protocolAcpStep1": "Navigate to Dashboard → Agents to view registered ACP agents.",
-    "protocolAcpStep2": "Register new agents with capabilities and endpoint configuration.",
-    "protocolAcpStep3": "Use CLI Tools to configure agent communication channels.",
-    "metadataTitleTemplate": "%s — Dokumen OmniRoute",
-    "metadataDefaultTitle": "Dokumentasi OmniRoute",
-    "metadataDescription": "Dokumentasi komprehensif untuk gerbang OmniRoute AI — pengaturan, API, kompresi, penyebaran, dan lainnya.",
-    "layoutNavTitle": "Dokumen OmniRoute",
-    "layoutHomeLink": "Beranda Dokumen",
-    "layoutDashboardLink": "← Kembali ke Dasbor",
-    "homeTitle": "Dokumentasi OmniRoute",
-    "homeMetadataDescription": "Semua yang Anda butuhkan untuk merutekan, mengompres, dan menskalakan AI Anda — panduan pengaturan, referensi API, kompresi, penyebaran, dan lainnya.",
-    "homeTwitterDescription": "Dokumen komprehensif untuk gerbang OmniRoute AI",
-    "homeDescription": "Segala yang Anda butuhkan untuk merutekan, mengompres, dan menskalakan AI Anda",
-    "homeSearchHint": "Tekan <kbd>Ctrl K</kbd> untuk mencari dokumen",
-    "featuredQuickStartTitle": "Panduan Cepat",
-    "featuredQuickStartDescription": "Jalankan OmniRoute dalam 3 menit",
-    "featuredAutoComboTitle": "Panduan Auto-Combo",
-    "featuredAutoComboDescription": "Biarkan OmniRoute memilih AI terbaik untuk Anda",
-    "featuredProvidersTitle": "Panduan Penyedia",
-    "featuredProvidersDescription": "Sambungkan penyedia AI dalam hitungan menit",
-    "nonTechUsersTitle": "Untuk Pengguna Non-Teknis",
-    "nonTechUsersSubtitle": "Mulai dengan cepat — tidak perlu latar belakang teknis",
-    "techUsersTitle": "Untuk Pengguna Teknologi",
-    "techUsersSubtitle": "Mendalami arsitektur, API, dan internal",
-    "apiExplorerMetadataTitle": "API Explorer — Dokumen OmniRoute",
-    "apiExplorerMetadataDescription": "Penjelajah API Interaktif — coba endpoint OmniRoute secara langsung dengan respons waktu nyata",
-    "apiExplorerTitle": "Penjelajah API",
-    "apiExplorerDescription": "Coba endpoint OmniRoute secara langsung. Pilih sebuah endpoint, atur permintaan Anda, dan lihat responsnya secara real time.",
-    "apiExplorerSseStarted": "Aliran SSE dimulai — periksa terminal/devtools untuk output waktu nyata.",
-    "apiExplorerError": "Kesalahan: {message}",
-    "apiExplorerAuth": "otentikasi",
-    "apiExplorerResponseLabel": "Tanggapan",
-    "apiExplorerSelectEndpoint": "Pilih endpoint untuk dijelajahi",
-    "apiExplorerChooseApi": "Pilih API dari sidebar untuk melihat detail dan mencobanya secara langsung",
-    "feedbackThanks": "Terima kasih atas masukan Anda!",
-    "feedbackQuestion": "Apakah halaman ini bermanfaat?",
-    "pageMetadataTitle": "{title} — Dokumen OmniRoute",
-    "pageMetadataDescription": "Dokumentasi OmniRoute: {title}",
-    "breadcrumb": "Jalur Navigasi",
-    "apiReferenceTable": {
-      "parameters": "Parameter",
-      "name": "Nama",
-      "type": "Tipe",
-      "description": "Deskripsi",
-      "returns": "Mengembalikan",
-      "typePrefix": "Tipe:"
-    }
-  },
-  "legal": {
-    "privacyPolicy": "Privacy Policy",
-    "termsOfService": "Terms of Service",
-    "providerConfigurations": "Provider configurations",
-    "apiKeys": "API keys",
-    "usageLogs": "Usage logs",
-    "applicationSettings": "Application settings",
-    "viewExportAnalytics": "View and export usage analytics",
-    "clearHistory": "Clear usage history at any time",
-    "configureRetention": "Configure log retention policies",
-    "backupRestore": "Back up and restore your database",
-    "privacyMetadataTitle": "Privacy Policy | OmniRoute",
-    "privacyMetadataDescription": "Privacy policy for the OmniRoute AI API proxy router.",
-    "termsMetadataTitle": "Terms of Service | OmniRoute",
-    "termsMetadataDescription": "Terms of service for the OmniRoute AI API proxy router.",
-    "backToHome": "Back to home",
-    "lastUpdated": "Last updated: {date}",
-    "policyLastUpdatedDate": "February 13, 2026",
-    "listSeparator": "-",
-    "questionsVisit": "Questions? Visit our",
-    "githubRepository": "GitHub repository",
-    "privacySection1Title": "1. Local-First Architecture",
-    "privacySection1Text": "OmniRoute is designed as a local-first application. All data processing and storage occurs entirely on your machine. There is no centralized server collecting your information.",
-    "privacySection2Title": "2. Data We Store",
-    "privacyDataStoredIn": "The following data is stored locally in",
-    "privacyDataProviderConfigurationsDesc": "connection URLs, provider types, and priority settings",
-    "privacyDataApiKeysDesc": "encrypted and stored locally for authenticating with AI providers",
-    "privacyDataUsageLogsDesc": "request counts, token usage, model names, timestamps, and response times",
-    "privacyDataApplicationSettingsDesc": "theme preferences, routing strategy, and combo configurations",
-    "privacySection3Title": "3. No Telemetry",
-    "privacySection3Text": "OmniRoute does not collect telemetry, analytics, or crash reports. No data is sent to us or any third party. Your usage patterns, API calls, and configurations remain entirely private.",
-    "privacySection4Title": "4. Third-Party AI Providers",
-    "privacySection4Text": "When you make API calls through OmniRoute, your requests are forwarded to the AI providers you have configured (for example: OpenAI, Anthropic, Google). These providers have their own privacy policies that govern how they handle your data. Please review:",
-    "privacyOpenAiPolicy": "OpenAI Privacy Policy",
-    "privacyAnthropicPolicy": "Anthropic Privacy Policy",
-    "privacyGooglePolicy": "Google Privacy Policy",
-    "privacySection5Title": "5. Cloud Sync (Optional)",
-    "privacySection5Text": "If you enable the optional cloud sync feature, provider configurations and API keys may be transmitted to a configured cloud endpoint. This feature is disabled by default and requires explicit opt-in.",
-    "privacySection6Title": "6. Logging",
-    "privacyLoggingIntro": "Request logs can be configured through the dashboard settings. You can:",
-    "privacySection7Title": "7. Your Rights",
-    "privacySection7TextStart": "Since all data is stored locally, you have full control. You can delete your data at any time by removing the",
-    "privacySection7TextEnd": "directory or using the database backup and restore features in the dashboard.",
-    "termsSection1Title": "1. Overview",
-    "termsSection1Text": "OmniRoute is a local-first AI API proxy router that operates entirely on your machine. It routes requests to multiple AI providers with load balancing, failover, and usage tracking.",
-    "termsSection2Title": "2. User Responsibilities",
-    "termsResponsibilityApiKeys": "You are solely responsible for managing your own API keys and credentials for third-party AI providers (OpenAI, Anthropic, Google, etc.).",
-    "termsResponsibilityCompliance": "You must comply with the terms of service of each AI provider whose API you access through OmniRoute.",
-    "termsResponsibilitySecurity": "You are responsible for the security of your local OmniRoute installation, including setting a password and restricting network access.",
-    "termsSection3Title": "3. How It Works",
-    "termsSection3Text": "OmniRoute acts as an intermediary proxy. API calls sent to OmniRoute are translated and forwarded to your configured AI providers. OmniRoute does not modify the content of your requests or responses beyond the necessary protocol translation.",
-    "termsSection4Title": "4. Data Handling",
-    "termsDataStoredLocally": "All data is stored locally on your machine in a SQLite database.",
-    "termsNoTransmission": "OmniRoute does not transmit any data to external servers unless you explicitly enable cloud sync features.",
-    "termsDataLocationText": "Usage logs, API keys, and configuration are stored in",
-    "termsSection5Title": "5. Disclaimer",
-    "termsSection5Text": "OmniRoute is provided \"as is\" without warranty of any kind. We are not responsible for any costs incurred through API usage, service disruptions, or data loss. Always maintain backups of your configuration.",
-    "termsSection6Title": "6. Open Source",
-    "termsSection6Text": "OmniRoute is open-source software. You are free to inspect, modify, and distribute it under the terms of its license."
-  },
-  "agents": {
-    "title": "CLI Agents",
-    "description": "Discover installed CLI agents on your system. Add custom agents for auto-detection.",
-    "refresh": "Refresh",
-    "installed": "Installed",
-    "notFound": "Not Found",
-    "builtIn": "Built-in",
-    "custom": "Custom",
-    "remove": "Remove",
-    "addCustomAgent": "Add Custom Agent",
-    "addCustomAgentDesc": "Register any CLI tool for detection. It will be scanned automatically on refresh.",
-    "agentName": "Agent Name",
-    "binaryName": "Binary Name",
-    "versionCommand": "Version Command",
-    "spawnArgs": "Spawn Args",
-    "addAgent": "Add Agent",
-    "scanning": "Scanning system for CLI agents...",
-    "opencodeIntegration": "OpenCode Integration",
-    "opencodeDetected": "opencode {version} detected",
-    "opencodeDesc": "Generate a ready-to-use {configFile} with your OmniRoute base URL and all available models — drop it in your project root and run {command}.",
-    "downloadConfig": "Download {file}",
-    "downloaded": "Downloaded!",
-    "setupGuideTitle": "Setup guide",
-    "openCliTools": "Open CLI Tools",
-    "setupGuideDetectCliTitle": "Detect installed CLIs",
-    "setupGuideDetectCliDesc": "Click Refresh after installing or updating a CLI so OmniRoute can rescan binaries and versions.",
-    "setupGuideCustomAgentTitle": "Register custom binary",
-    "setupGuideCustomAgentDesc": "Use Add Custom Agent when your CLI is not in the built-in list. Provide binary name and version command.",
-    "setupGuideCommandMissingTitle": "Fix 'command not found'",
-    "setupGuideCommandMissingDesc": "Ensure the CLI command exists in PATH, open a new terminal session, and rerun Refresh.",
-    "cliToolsRedirectTitle": "Cli Tools Redirect Title",
-    "cliToolsRedirectDesc": "Cli Tools Redirect Desc",
-    "spawnArgsPlaceholder": "Spawn Args Placeholder",
-    "binaryNamePlaceholder": "Binary Name Placeholder",
-    "versionCommandPlaceholder": "Version Command Placeholder",
-    "architectureTitle": "Architecture Title",
-    "flowLocalBinary": "Flow Local Binary",
-    "flowOmniRoute": "Flow Omni Route",
-    "agentNamePlaceholder": "Agent Name Placeholder",
-    "architectureDescription": "Architecture Description",
-    "flowExecute": "Flow Execute",
-    "flowSpawn": "Flow Spawn",
-    "cliToolsRedirectCta": "Cli Tools Redirect Cta",
-    "comparisonTitle": "Alat CLI vs Target Agen — Apa Bedanya?",
-    "comparisonCliToolsLabel": "halaman Alat CLI",
-    "comparisonCliToolsTitle": "IDE Anda mengirimkan permintaan melalui OmniRoute",
-    "comparisonCliToolsDesc": "Konfigurasikan Claude Code, Codex, Cursor, dan IDE lainnya untuk menggunakan OmniRoute sebagai URL dasar API-nya. OmniRoute bertindak sebagai proksi, merutekan permintaan ke penyedia Anda yang dikonfigurasi.",
-    "comparisonAgentsLabel": "Halaman ini (Target Agen)",
-    "comparisonAgentsTitle": "OmniRoute mengirimkan permintaan ke alat CLI lokal",
-    "comparisonAgentsDesc": "OmniRoute dapat menghasilkan binari CLI lokal (claude, codex, goose) sebagai backend eksekusi. Alat CLI memproses permintaan menggunakan autentikasinya sendiri dan mengembalikan hasilnya.",
-    "comparisonSummary": "Singkatnya: CLI Tools = Anda mengonfigurasi alat untuk menunjuk ke OmniRoute. Agen Target = OmniRoute menggunakan alat sebagai titik akhirnya.",
-    "agentUseCaseHint": "Dapat digunakan sebagai target eksekusi melalui protokol ACP",
-    "flowDiagramClient": "Aplikasi Klien",
-    "flowDiagramClientDesc": "SDK, API, atau layanan upstream",
-    "flowDiagramOmniRoute": "OmniRoute",
-    "flowDiagramOmniRouteDesc": "Menerima permintaan dan memilih target",
-    "flowDiagramSpawn": "Proses Pemijahan",
-    "flowDiagramSpawnDesc": "Meluncurkan biner CLI melalui stdio",
-    "flowDiagramCli": "Agen CLI",
-    "flowDiagramCliDesc": "Proses dengan autentikasi/model sendiri",
-    "fingerprintSettingsHint": "Pencocokan sidik jari CLI (menyamarkan permintaan sebagai alat CLI tertentu) dapat dikonfigurasi",
-    "settingsRoutingLink": "Pengaturan/Perutean",
-    "openSettings": "Pengaturan",
-    "copyRawUrlTitle": "Salin URL mentah ke clipboard",
-    "copied": "Disalin!",
-    "copyUrl": "Salin URL",
-    "startHere": "Mulai Disini",
-    "badgeNew": "Baru",
-    "viewOnGithub": "Lihat di GitHub",
-    "howToUse": "Cara menggunakan",
-    "browseAllSkillsOnGithub": "Jelajahi semua keterampilan di GitHub",
-    "apiSkills": "Keterampilan API",
-    "cliSkills": "Keterampilan CLI",
-    "apiSkillsSubtitle": "{count} kemampuan — kendalikan OmniRoute via REST / HTTP",
-    "cliSkillsSubtitle": "{count} kemampuan — kendalikan OmniRoute via biner terminal omniroute",
-    "howToUseStep1": "Klik <bold>{copyUrl}</bold> pada kemampuan yang Anda ingin agen Anda ketahui.",
-    "howToUseStep2": "Di agen AI Anda (Claude, Cursor, Cline…), katakan:",
-    "howToUseStep2Code": "Gunakan kemampuan di [pasted-url]",
-    "howToUseStep3": "Agen mengambil SKILL.md dan mempelajari API atau CLI OmniRoute — tidak memerlukan dokumentasi manual."
-  },
-  "cloudAgents": {
-    "title": "Agen Awan",
-    "description": "Kelola agen pengkodean otonom (Jules, Devin, Codex Cloud)",
-    "loading": "Memuat tugas...",
-    "aboutTitle": "Tentang Agen Cloud",
-    "aboutDescription": "Agen cloud adalah asisten pengkodean AI jarak jauh yang dapat menjalankan tugas secara mandiri. Cara kerjanya berbeda dari agen CLI lokal - Anda berinteraksi dengan mereka melalui API OmniRoute.",
-    "howItWorksTitle": "Cara kerjanya:",
-    "howItWorksDesc": "Buat tugas → Agen menganalisis dan mengusulkan rencana → Anda menyetujui → Agen mengeksekusi → Hasil dikembalikan",
-    "newTaskTitle": "Buat Tugas Baru",
-    "newTaskDescription": "Mulai tugas baru dengan agen cloud",
-    "selectAgent": "Pilih Agen",
-    "taskDescription": "Deskripsi Tugas",
-    "taskDescriptionPlaceholder": "Jelaskan apa yang Anda ingin agen lakukan...",
-    "startTask": "Mulai Tugas",
-    "tasks": "Tugas",
-    "taskDetail": "Detil Tugas",
-    "noTasks": "Belum ada tugas. Buat satu untuk memulai.",
-    "noTasksTitle": "Belum ada tugas",
-    "noTasksDesc": "Buat tugas pertama Anda untuk memulai.",
-    "tasksTab": "Tugas",
-    "agentsTab": "Agen",
-    "settingsTab": "Pengaturan",
-    "agentsEnabled": "Diaktifkan",
-    "agentsDisabled": "Dinonaktifkan",
-    "filterAllProviders": "Semua Penyedia",
-    "filterAll": "Semua",
-    "autoRefreshing": "Menyegarkan otomatis",
-    "viewPR": "Lihat Pull Request",
-    "connected": "Terhubung",
-    "notConnected": "Tidak terhubung",
-    "configure": "Konfigurasi",
-    "settingsTitle": "Pengaturan Agen Awan",
-    "settingsDesc": "Konfigurasikan preferensi lokal untuk agen awan.",
-    "settingEnableAgents": "Aktifkan agen awan",
-    "settingEnableAgentsDesc": "Izinkan OmniRoute untuk mengorkestrasi agen pengodean otonom.",
-    "settingAutoPR": "Buat PR otomatis",
-    "settingAutoPRDesc": "Ketika tugas selesai, buat Pull Request secara otomatis dengan perubahan tersebut.",
-    "settingRequireApproval": "Wajibkan persetujuan rencana",
-    "settingRequireApprovalDesc": "Selalu tunggu persetujuan manual sebelum agen mengeksekusi rencana yang diusulkan.",
-    "untitledTask": "Tugas Tanpa Judul",
-    "created": "Dibuat",
-    "conversation": "Percakapan",
-    "result": "Hasil",
-    "error": "Kesalahan",
-    "planReady": "Rencana Siap untuk Persetujuan",
-    "approvePlan": "Setujui Rencana",
-    "rejectPlan": "Tolak & Batalkan",
-    "sendMessagePlaceholder": "Kirim pesan ke agen...",
-    "cancel": "Batalkan",
-    "delete": "Hapus",
-    "selectTaskPrompt": "Pilih tugas untuk melihat detailnya",
-    "statusPending": "Tertunda",
-    "statusRunning": "Berlari",
-    "statusWaitingApproval": "Menunggu Persetujuan",
-    "statusCompleted": "Selesai",
-    "statusFailed": "Gagal",
-    "statusCancelled": "Dibatalkan",
-    "repositoryName": "Nama repositori",
-    "repositoryUrl": "URL repositori",
-    "branch": "Cabang",
-    "agentDescriptions": {
-      "jules": "Agen pengodean otonom Google",
-      "devin": "Insinyur perangkat lunak AI Cognition",
-      "codexCloud": "Agen pengodean berbasis awan OpenAI",
-      "cursorCloud": "Agen Latar Belakang / Awan Cursor (kunci API resmi)"
-    },
-    "activityTypes": {
-      "plan": "Rencana",
-      "command": "Perintah",
-      "code_change": "Perubahan kode",
-      "message": "Pesan",
-      "error": "Galat",
-      "completion": "Penyelesaian"
-    }
-  },
-  "templateNames": {
-    "simple-chat": "Simple Chat",
-    "streaming": "Streaming",
-    "system-prompt": "System Prompt",
-    "thinking": "Thinking",
-    "tool-calling": "Tool Calling",
-    "multi-turn": "Multi-turn",
-    "vision": "Visi",
-    "schema-coercion": "Pemaksaan Skema"
-  },
-  "templateDescriptions": {
-    "simple-chat": "Basic chat template with system message",
-    "streaming": "Template for streaming responses",
-    "system-prompt": "Template with custom system prompt",
-    "thinking": "Template with reasoning/thinking budget",
-    "tool-calling": "Template for tool/function calling",
-    "multi-turn": "Template for multi-turn conversations",
-    "vision": "Templat multimodal dengan masukan gambar",
-    "schema-coercion": "Penegakan skema keluaran terstruktur/JSON"
-  },
-  "templatePayloads": {
-    "simpleChat": {
-      "system": "You are a helpful AI assistant.",
-      "userGreeting": "Hello! How can I help you today?"
-    },
-    "streaming": {
-      "prompt": "Write a story about"
-    },
-    "systemPrompt": {
-      "question": "What is the meaning of life?",
-      "systemInstruction": "Provide a thoughtful, philosophical answer."
-    },
-    "thinking": {
-      "question": "Explain quantum computing"
-    },
-    "toolCalling": {
-      "cityNameDescription": "The name of the city to get weather for",
-      "toolDescription": "Get current weather for a location",
-      "userWeather": "What's the weather in Tokyo?"
-    },
-    "multiTurn": {
-      "system": "You are a helpful assistant.",
-      "assistantExample": "I'd be happy to help you with that.",
-      "userInitial": "I need help with",
-      "userFollowUp": "Can you elaborate on that?"
-    }
-  },
-  "cache": {
-    "title": "Cache Management",
-    "description": "Monitor provider prompt cache efficiency and local semantic response reuse.",
-    "refresh": "Refresh",
-    "clearAll": "Clear Semantic Cache",
-    "memoryEntries": "Memory Entries",
-    "memoryEntriesSub": "In-memory LRU",
-    "dbEntries": "DB Entries",
-    "dbEntriesSub": "Persisted (SQLite)",
-    "cacheHits": "Cache Hits",
-    "cacheHitsSub": "of {total} total",
-    "tokensSaved": "Tokens Saved",
-    "tokensSavedSub": "Estimated from hits",
-    "hitRate": "Hit Rate",
-    "performance": "Cache Performance",
-    "autoRefresh": "Auto-refreshes every {seconds}s",
-    "hits": "Hits",
-    "misses": "Misses",
-    "total": "Total",
-    "behavior": "Cache Behavior",
-    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
-    "behaviorBypass": "Bypass with header {header}.",
-    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
-    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
-    "idempotency": "Idempotency Layer",
-    "activeDedupKeys": "Active Dedup Keys",
-    "dedupWindow": "Dedup Window",
-    "clearSuccess": "Semantic cache cleared. {count} entries removed.",
-    "clearError": "Failed to clear cache.",
-    "unavailable": "Cache unavailable",
-    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
-    "loadingCacheAria": "Memuat tembolok",
-    "promptCache": "Prompt Cache (Provider-Side)",
-    "semanticCache": "Semantic Cache",
-    "promptCacheSectionDesc": "Shows provider-side prompt caching activity from usage history so you can see where cache control is active and how much input reuse you are getting.",
-    "promptTrendDesc": "Hourly request volume, cache coverage, and cache read volume across the last 24 hours.",
-    "cachedRequests": "Cached Requests",
-    "cachedRequests24h": "Cached Requests (24h)",
-    "cacheHitRate": "Cache Hit Rate",
-    "cacheRate": "Cache Rate",
-    "cacheRateDesc": "of total requests",
-    "cachedTokens": "Cache Read Tokens",
-    "cacheCreationTokens": "Cache Write Tokens",
-    "cacheMetrics": "Prompt Cache Metrics",
-    "withCacheControl": "With Cache Control",
-    "cachedTokensRead": "Read from cache",
-    "cacheCreationWrite": "Written to cache",
-    "cacheReuseRatio": "Cache Reuse Ratio",
-    "cacheReuseRatioDesc": "Cache read tokens / Total input tokens",
-    "estCostSaved": "Est. Cost Saved",
-    "lastUpdated": "Last updated",
-    "hoursTracked": "hours tracked",
-    "busiestHour": "Busiest Hour",
-    "peakCacheRate": "Peak Cache Rate",
-    "trendHour": "Hour",
-    "activityVolume": "Activity",
-    "requestsShort": "reqs",
-    "inputShort": "In",
-    "cachedShort": "Cached",
-    "writeShort": "Write",
-    "resetting": "Resetting...",
-    "resetMetrics": "Reset Metrics",
-    "byProvider": "Breakdown by Provider",
-    "providerCacheRateDesc": "Each provider exposes total input tokens, cache read tokens, and cache write tokens so you can verify the reuse ratio against raw totals.",
-    "provider": "Provider",
-    "requests": "Requests",
-    "inputTokens": "Total Input Tokens",
-    "cachedTokensCol": "Cache Read",
-    "cacheCreation": "Cache Write",
-    "trend24h": "Cache Trend (24h)",
-    "peakCached": "Peak cached",
-    "cached": "Cached",
-    "overview": "Overview",
-    "tableProvider": "Penyedia",
-    "tableModel": "Model",
-    "performanceTitle": "Kinerja",
-    "semanticCacheSectionDesc": "OmniRoute's own deterministic response cache. When enabled, repeated non-streaming temperature=0 requests can be served locally without hitting the upstream provider.",
-    "semanticCacheDisabledDesc": "Semantic cache is disabled. OmniRoute will skip local response reuse until you turn it back on in Settings.",
-    "semanticEntriesDesc": "Persisted semantic cache records currently stored in SQLite. Provider-side prompt cache activity is not listed here.",
-    "searchEntries": "Search entries...",
-    "search": "Search",
-    "loading": "Loading...",
-    "entriesLoadError": "Failed to load semantic cache entries.",
-    "noEntries": "No cache entries found",
-    "noPromptCacheData": "No provider-side prompt cache activity has been recorded yet.",
-    "noTrendData": "No prompt cache activity has been recorded over the last 24 hours.",
-    "signature": "Signature",
-    "model": "Model",
-    "created": "Created",
-    "expires": "Expires",
-    "actions": "Actions",
-    "deduplicatedRequests": "Deduplicated Requests",
-    "savedCalls": "Saved API Calls",
-    "totalProcessed": "Total Requests Processed",
-    "disabled": "Disabled",
-    "totalRequests": "Total Requests",
-    "reasoningCache": "Pemutaran Ulang Penalaran",
-    "reasoningCacheDesc": "Mempertahankan pemikiran model untuk alur pemanggilan alat multi-putaran",
-    "reasoningEntries": "Entri Aktif",
-    "reasoningReplayRate": "Tingkat Pemutaran Ulang",
-    "reasoningReplays": "Total Pemutaran Ulang",
-    "reasoningCharsCached": "Karakter Di-cache",
-    "reasoningMisses": "Cache Hilang",
-    "reasoningByProvider": "Oleh Penyedia",
-    "reasoningByModel": "Berdasarkan Model",
-    "reasoningRecentEntries": "Entri Terbaru",
-    "reasoningToolCallId": "ID Panggilan Alat",
-    "reasoningChars": "Karakter",
-    "reasoningAge": "Usia",
-    "reasoningView": "Lihat",
-    "reasoningDetail": "Konten Penalaran",
-    "reasoningBehavior": "Perilaku",
-    "reasoningBehaviorCapture": "Menangkap penalaran_konten dari respons streaming",
-    "reasoningBehaviorReplay": "Menyuntikkan kembali pada giliran berikutnya ketika klien menghilangkannya",
-    "reasoningBehaviorFallback": "Mengutamakan memori dengan fallback SQLite untuk pemulihan kerusakan",
-    "reasoningBehaviorTtl": "TTL: 2 jam | Entri maksimal: 2.000 (memori)",
-    "reasoningBehaviorModels": "Didukung: DeepSeek, Kimi, Qwen-Thinking, GLM",
-    "reasoningClearAll": "Hapus Cache Penalaran",
-    "reasoningClearSuccess": "Menghapus entri cache alasan {count}",
-    "reasoningClearError": "Gagal menghapus cache alasan",
-    "reasoningNoData": "Belum ada entri alasan yang di-cache. Entri muncul ketika model berpikir menggunakan pemanggilan alat.",
-    "cachePerformanceRetry": "Coba lagi",
-    "cachePerformanceHitRate": "Tingkat Hit",
-    "cachePerformanceAvgLatency": "Rata-rata Latensi (ms)",
-    "cachePerformanceP95Latency": "p95 Latensi (ms)",
-    "retry": "Coba lagi",
-    "reasoningAvgChars": "Karakter Rata-Rata",
-    "tableShare": "Bagikan",
-    "justNow": "baru saja",
-    "minutesAgo": "{minutes}m yang lalu",
-    "hoursAgo": "{hours}j yang lalu",
-    "daysAgo": "{days}h yang lalu",
-    "entries": "Entries"
-  },
-  "proxyConfigModal": {
-    "levelGlobal": "Global",
-    "levelProvider": "Provider",
-    "levelCombo": "Combo",
-    "levelKey": "Key",
-    "levelDirect": "Direct (no proxy)",
-    "titleGlobal": "Global Proxy Configuration",
-    "titleLevel": "{level} Proxy — {label}",
-    "loading": "Loading proxy configuration...",
-    "inheritingFrom": "Inheriting from",
-    "source": "Source",
-    "savedProxy": "Saved Proxy",
-    "custom": "Custom",
-    "selectSavedProxyPlaceholder": "Select saved proxy...",
-    "proxyType": "Proxy Type",
-    "host": "Host",
-    "hostPlaceholder": "1.2.3.4 or proxy.example.com",
-    "port": "Port",
-    "authOptional": "Authentication (optional)",
-    "username": "Username",
-    "usernamePlaceholder": "Username",
-    "password": "Password",
-    "passwordPlaceholder": "Password",
-    "connected": "Connected",
-    "ip": "IP:",
-    "connectionFailed": "Connection failed",
-    "testConnection": "Test connection",
-    "clear": "Clear",
-    "cancel": "Cancel",
-    "save": "Save",
-    "errorSelectSavedProxy": "Please select a saved proxy first.",
-    "errorSelectProxyFirst": "Please select a proxy first.",
-    "errorProxyNotFound": "Selected proxy not found.",
-    "errorClearSavedProxy": "Failed to clear saved proxy",
-    "errorSaveProxy": "Failed to save proxy configuration",
-    "errorClearProxy": "Failed to clear proxy configuration",
-    "errorSocks5Hidden": "SOCKS5 is configured but hidden because NEXT_PUBLIC_ENABLE_SOCKS5_PROXY=false."
-  },
-  "oauthModal": {
-    "title": "Connect {providerName}",
-    "waiting": "Waiting for authorization",
-    "completeAuthInPopup": "Complete authorization in popup.",
-    "popupClosedHint": "If the popup closed without redirecting back (e.g. Qoder), this dialog will auto-switch to manual URL entry mode.",
-    "popupBlocked": "Popup blocked? Enter URL manually",
-    "deviceCodeVisitUrl": "Visit the URL below and enter code:",
-    "deviceCodeVerificationUrl": "Verification URL",
-    "deviceCodeYourCode": "Your code",
-    "deviceCodeWaiting": "Waiting for authorization...",
-    "googleLoopbackTitle": "Masuk Google tidak dapat diselesaikan dari alamat ini",
-    "googleLoopbackWhatHappens": "Google hanya mengeluarkan kode otorisasi sekali <code>{redirectUri}</code> dapat diakses dari browser yang menyetujui masuk. Di sini alamat tersebut mengarah ke komputer ini, bukan ke server OmniRoute — jadi layar persetujuan terhenti alih-alih mengalihkan, dan tidak ada URL callback untuk disalin.",
-    "googleLoopbackRecommended": "Disarankan — jalankan ini di komputer Anda sendiri, lalu tempelkan hasilnya di bawah:",
-    "googleLoopbackHelperNote": "Ini membuka persetujuan Google secara lokal (di mana 127.0.0.1 berfungsi) dan mencetak blob omniroute-cred-v1.… satu baris. Tempelkan blob itu ke dalam kolom Langkah 2 di bawah — ini menerima blob kredensial serta URL callback.",
-    "googleLoopbackTunnelLabel": "Atau teruskan port dasbor melalui SSH dan muat ulang OmniRoute melalui terowongan:",
-    "googleLoopbackTunnelNote": "Ganti {userPlaceholder} dengan nama pengguna SSH Anda, biarkan terminal tetap terbuka, lalu buka {localUrl} dan sambungkan lagi dari sana.",
-    "googleLoopbackHeadlessAlt": "Untuk penggunaan sepenuhnya headless tanpa callback lokal sama sekali, <a>konfigurasikan kredensial Google OAuth Anda sendiri</a> ditambah URL dasar publik.",
-    "remoteAccessInfo": "Remote access: Since you're accessing OmniRoute remotely, after authorization you'll see an error page (localhost not found). This is normal — just copy the full URL from your browser address bar and paste it below.",
-    "loopbackMismatchTitle": "Masuk tidak dapat diselesaikan dari alamat ini",
-    "loopbackMismatchWhatHappened": "Apa yang terjadi",
-    "loopbackMismatchExplanation": "Setelah Anda menyetujui login, {providerName} selalu mengirimkan browser kembali ke <code>{redirectUri}</code>. Alamat itu mengarah ke komputer yang menjalankan browser ini, bukan ke server OmniRoute — jadi kode otorisasi tidak pernah sampai ke OmniRoute dan penyedia gagal melakukan masuk tanpa menampilkan kesalahan.",
-    "loopbackMismatchHowToFix": "Bagaimana cara memperbaikinya",
-    "loopbackMismatchStep1": "Di komputer ini, buka terminal dan mulai terowongan SSH ke server OmniRoute:",
-    "loopbackMismatchStep1Note": "Ganti {userPlaceholder} dengan nama pengguna SSH Anda. Biarkan terminal ini terbuka sampai koneksi menunjukkan sebagai aktif — kedua port diperlukan: satu melayani dasbor, yang lainnya menerima callback.",
-    "loopbackMismatchStep2": "Di browser ini, buka kembali OmniRoute melalui terowongan:",
-    "loopbackMismatchStep3": "Kemudian sambungkan {providerName} lagi dari tab baru. Callback sekarang mencapai server dan login selesai dengan normal.",
-    "loopbackMismatchAlternative": "Tidak ada akses SSH? Jika penyedia ini menawarkan tab impor token, sambungkan dengan token sebagai gantinya — jalur itu tidak menggunakan callback loopback.",
-    "step1OpenUrl": "Step 1: Open this URL in your browser",
-    "copy": "Copy",
-    "step2PasteCallback": "Step 2: Paste callback URL or authorization code here",
-    "step2Hint": "After authorization, paste the full callback URL. For Claude Code and Cline, you can also paste the authentication code directly, e.g. <code>code#state</code>.",
-    "connect": "Connect",
-    "cancel": "Cancel",
-    "success": "Connection successful!",
-    "successMessage": "Your {providerName} account has been connected.",
-    "done": "Done",
-    "error": "Connection failed",
-    "tryAgain": "Try again",
-    "errorSessionIncomplete": "Sesi OAuth tidak lengkap (URI pengalihan atau pengverifikasi kode hilang). Mulai ulang koneksi dan coba lagi.",
-    "errorExchangeFailed": "Pertukaran gagal",
-    "errorGoogleRedirectMismatch": "redirect_uri_mismatch: Kredensial Google OAuth default hanya berfungsi di localhost. Untuk penggunaan jarak jauh, konfigurasikan kredensial OAuth Anda sendiri melalui variabel lingkungan: ANTIGRAVITY_OAUTH_CLIENT_ID dan ANTIGRAVITY_OAUTH_CLIENT_SECRET. Lihat bagian README 'OAuth di Server Jarak Jauh'.",
-    "errorSaveFailed": "Simpan gagal",
-    "errorAuthorizationFailed": "Otorisasi gagal",
-    "errorAuthorizationTimeout": "Waktu Habis Otorisasi",
-    "errorRequestFailed": "Permintaan gagal",
-    "errorCallbackServerFailed": "Gagal memulai server callback",
-    "errorBrowserUnavailable": "Browser OAuth tidak tersedia untuk penyedia ini di lingkungan saat ini. Gunakan metode otentikasi yang didukung sebagai gantinya.",
-    "errorStateMismatch": "Ketidakcocokan status OAuth. Mulai ulang koneksi dan coba lagi.",
-    "errorImportAccessToken": "Gagal mengimpor token akses",
-    "errorSessionNotInitialized": "Sesi OAuth tidak diinisialisasi. Mulai ulang alur koneksi dan coba lagi.",
-    "errorNoAuthorizationCode": "Tidak ada kode otorisasi yang ditemukan. Tempelkan URL callback atau Kode Autentikasi.",
-    "tabDeviceCode": "Kode Perangkat",
-    "tabBrowserLogin": "Masuk Browser",
-    "tabImportAuthJson": "Impor auth.json",
-    "tabPasteApiKey": "Tempel Kunci API",
-    "windsurfPasteDescription": "Di Windsurf / VS Code IDE, jalankan perintah \"Windsurf: Provide Auth Token\" dari palet perintah (atau klik tombol Jupyter \"Get Windsurf Authentication Token\"), lalu salin token yang ditampilkan dan tempelkan di bawah. Membuka windsurf.com/show-auth-token secara langsung hanya menampilkan halaman \"Redirecting\" — IDE harus memulai alur tersebut.",
-    "grokAuthJsonDescription": "Tempelkan seluruh isi dari ~/.grok/auth.json (bukan hanya bidang \"key\" JWT). JWT yang kosong tidak memiliki refresh_token, jadi koneksi akan terputus setelah kedaluwarsa (#7610). Lebih baik menggunakan modal Impor auth.json yang khusus ketika tersedia.",
-    "devinDesktopPasteDescription": "Tempelkan kunci API Devin yang ada dari sesi Devin yang terautentikasi. Ketersediaan ekspor kunci dan langkah-langkahnya bervariasi tergantung versi Devin dan akun.",
-    "devinPasteDescription": "Berikan WINDSURF_API_KEY Anda (diperoleh melalui `devin auth login`, atau melalui perintah \"Windsurf: Provide Auth Token\" di Windsurf IDE).",
-    "grokAuthJsonPlaceholder": "{\"https://auth.x.ai::clientId\": {\"key\": \"eyJ...\", \"refresh_token\": \"...\"}}",
-    "grokAuthJsonLabel": "Grok Build auth.json",
-    "apiTokenPlaceholder": "ws-...",
-    "apiKeyTokenLabel": "Kunci API / Token",
-    "saving": "Menyimpan…",
-    "saveConnection": "Simpan Koneksi",
-    "gheDescription": "Masukkan URL dasar dari instance GitHub Enterprise Anda (misalnya <code>https://ghe.perusahaananda.com</code>).",
-    "gheUrlPlaceholder": "https://ghe.yourcompany.com",
-    "gheUrlLabel": "URL GitHub Enterprise",
-    "gheUrlRequired": "URL GitHub Enterprise diperlukan",
-    "gitlabDuoSetupTitle": "Pengaturan OAuth Duo GitLab",
-    "gitlabDuoSetupMessage": "GitLab Duo OAuth belum dikonfigurasi. Daftarkan aplikasi OAuth di {applicationsUrl} dengan URI pengalihan {redirectUri} dan cakupan \"{scopes}\", lalu atur {clientIdEnv} (dan opsional {clientSecretEnv}) dan mulai ulang.",
-    "gitlabDuoSetupDescription": "Setelah aplikasi terdaftar dan variabel env diatur pada instance OmniRoute ini, klik Lanjutkan untuk memulai login OAuth.",
-    "continue": "Lanjutkan"
-  },
-  "cursorAuthModal": {
-    "title": "Connect Cursor IDE",
-    "tabLogin": "Login with Cursor",
-    "tabImport": "Import token",
-    "loginDescription": "Opens Cursor's browser login. Works in Docker — approve in your host browser, then return here.",
-    "loginWithCursor": "Login with Cursor",
-    "startingLogin": "Starting…",
-    "waitingApproval": "Waiting for Cursor login approval…",
-    "openUrlHint": "If the browser did not open:",
-    "openLoginLink": "Open login page",
-    "cancelLogin": "Cancel login",
-    "autoDetecting": "Auto-detecting tokens...",
-    "readingFromCursor": "Reading from Cursor IDE or cursor-agent",
-    "tokensAutoDetected": "Tokens successfully auto-detected from Cursor IDE!",
-    "cursorNotDetected": "Cursor IDE not detected. Please manually paste your token.",
-    "dockerImportHint": "Running in Docker? Prefer Login with Cursor. IDE auto-import and cursor-agent are usually unavailable inside the container. See docs/providers/CURSOR-DOCKER.md.",
-    "accessToken": "Access Token",
-    "refreshToken": "Refresh Token",
-    "refreshTokenPlaceholder": "Optional — enables automatic token refresh",
-    "required": "*",
-    "accessTokenPlaceholder": "Access token will auto-populate...",
-    "machineId": "Machine ID",
-    "optional": "(optional)",
-    "machineIdPlaceholder": "Machine ID will auto-populate...",
-    "importing": "Importing...",
-    "importToken": "Import Token",
-    "cancel": "Cancel",
-    "errorAutoDetect": "Unable to auto-detect tokens",
-    "errorAutoDetectFailed": "Auto-detect tokens failed",
-    "errorEnterToken": "Please enter access token",
-    "errorImportFailed": "Import failed",
-    "errorLoginStart": "Failed to start Cursor login",
-    "errorLoginPoll": "Cursor login failed",
-    "errorLoginTimeout": "Cursor login timed out — try again"
-  },
-  "pricingModal": {
-    "title": "Pricing Configuration",
-    "loading": "Loading pricing data...",
-    "pricingRatesFormat": "Pricing Rates Format",
-    "ratesDescription": "All rates are in <strong>dollars per million tokens</strong> ($/1M tokens). Example: Input rate of 2.50 means $2.50 per 1,000,000 input tokens.",
-    "model": "Model",
-    "input": "Input",
-    "output": "Output",
-    "cached": "Cached",
-    "reasoning": "Reasoning",
-    "cacheCreation": "Cache Creation",
-    "noPricingData": "No pricing data available",
-    "resetToDefaults": "Reset to defaults",
-    "cancel": "Cancel",
-    "saving": "Saving...",
-    "saveChanges": "Save changes",
-    "resetConfirm": "Reset all pricing to defaults? This cannot be undone.",
-    "errorSaveFailed": "Failed to save pricing",
-    "errorResetFailed": "Failed to reset pricing"
-  },
-  "proxyRegistry": {
-    "selectAllProxies": "Pilih semua proksi",
-    "selectProxy": "Pilih {name}",
-    "title": "Proxy Registry",
-    "description": "Store reusable proxies and track assignments.",
-    "importLegacy": "Import Legacy",
-    "bulkAssign": "Bulk Assign",
-    "addProxy": "Add Proxy",
-    "loading": "Loading proxies...",
-    "noProxies": "No saved proxies yet.",
-    "tableName": "Name",
-    "tableEndpoint": "Endpoint",
-    "tableStatus": "Status",
-    "tableHealth": "Health (24h)",
-    "tableUsage": "Usage",
-    "tableActions": "Actions",
-    "test": "Test",
-    "edit": "Edit",
-    "delete": "Delete",
-    "modalCreateTitle": "Create Proxy",
-    "modalEditTitle": "Edit Proxy",
-    "labelName": "Name",
-    "labelType": "Type",
-    "labelFamily": "Keluarga IP",
-    "familyAuto": "Otomatis (dual-stack)",
-    "familyIpv4": "Hanya IPv4",
-    "familyIpv6": "Hanya IPv6",
-    "familyHint": "Keluarga alamat egress. Otomatis mempertahankan dual-stack; IPv4/IPv6 menyematkan proksi ini ke keluarga tersebut (mencegah kebocoran v4 di bawah proksi khusus IPv6).",
-    "labelHost": "Host",
-    "labelPort": "Port",
-    "labelUsername": "Username",
-    "labelPassword": "Password",
-    "labelRegion": "Region",
-    "labelStatus": "Status",
-    "labelNotes": "Notes",
-    "usernamePlaceholderEdit": "Leave blank to keep current username",
-    "passwordPlaceholderEdit": "Leave blank to keep current password",
-    "statusActive": "Active",
-    "statusInactive": "Inactive",
-    "cancel": "Cancel",
-    "save": "Save",
-    "bulkModalTitle": "Bulk Proxy Assignment",
-    "bulkLabelScope": "Scope",
-    "bulkLabelProxy": "Proxy",
-    "bulkClearAssignment": "(Clear assignment)",
-    "bulkLabelScopeIds": "Scope IDs (comma or newline separated)",
-    "bulkScopeIdsPlaceholder": "provider-openai,provider-anthropic",
-    "bulkApply": "Apply",
-    "labelScope": "Cakupan",
-    "labelProxy": "Proksi",
-    "scopeGlobal": "global",
-    "scopeProvider": "penyedia",
-    "scopeAccount": "akun",
-    "scopeCombo": "kombo",
-    "bulkImportErrorMissingName": "NAMA tidak ada",
-    "bulkImportErrorMissingHost": "HOST tidak ada",
-    "bulkImportErrorInvalidPort": "PORT tidak valid (harus 1-65535)",
-    "bulkImportErrorInvalidType": "TYPE tidak valid (gunakan http, https, atau sock5)",
-    "bulkImportErrorInvalidStatus": "STATUS tidak valid (gunakan aktif atau tidak aktif)",
-    "errorLoadFailed": "Failed to load proxy registry",
-    "errorNameHostRequired": "Name and host are required",
-    "errorSaveFailed": "Failed to save proxy",
-    "errorDeleteFailed": "Failed to delete proxy",
-    "errorForceDeleteConfirm": "This proxy is still assigned. Force delete and remove all assignments?",
-    "errorMigrateFailed": "Failed to migrate legacy proxy config",
-    "errorBulkFailed": "Failed to execute bulk assignment",
-    "success": "✓",
-    "failure": "✗",
-    "failed": "Failed",
-    "successRate": "{rate}% success",
-    "avgLatency": "{latency}ms average",
-    "assignmentsCount": "{count} assignments",
-    "noData": "—",
-    "testSuccess": "✓ {ip}",
-    "testLatency": "{latency}ms",
-    "testFailure": "✗ {error}",
-    "repair": "Perbaiki",
-    "relayAuthMissing": "autentikasi hilang",
-    "relayRepairTooltip": "Pulihkan autentikasi relai di tempat. Jika token tidak dapat dipulihkan (mis. setelah rotasi STORAGE_ENCRYPTION_KEY), terapkan ulang relai sebagai gantinya.",
-    "relayRepairRedeployRequired": "Autentikasi relai tidak dapat dipulihkan — terapkan ulang relai untuk menulis token baru.",
-    "relayRepairFailed": "Perbaikan relai gagal",
-    "relayRepairError": "perbaikan gagal",
-    "relayProbeSummary": "Pemeriksaan relai: {alive}/{tested} aktif",
-    "bulkImport": "Impor Massal",
-    "bulkImportTitle": "Proksi Impor Massal",
-    "bulkImportDescription": "Tempelkan profil proxy menggunakan format yang dibatasi pipa. Satu proxy per baris. Proksi yang ada (host + port yang sama) akan diperbarui.",
-    "bulkImportParse": "Mengurai",
-    "bulkImportImport": "Impor {count} Proksi",
-    "bulkImportImporting": "Mengimpor...",
-    "bulkImportParsed": "{count} proxy diurai",
-    "bulkImportSkipped": "{count} baris dilewati",
-    "bulkImportParseErrors": "{count} kesalahan",
-    "bulkImportNoValidEntries": "Tidak ada entri yang valid ditemukan. Periksa formatnya dan coba lagi.",
-    "bulkImportSuccess": "Impor selesai: {created} dibuat, {updated} diperbarui, {failed} gagal",
-    "bulkImportErrorLine": "Baris {line}: {reason}",
-    "bulkImportMaxExceeded": "Maksimum 100 proxy per impor",
-    "bulkImportPreview": "Pratinjau",
-    "clearAssignment": "(tugas yang jelas)",
-    "bulkProxyAssignment": "Penugasan Proksi Massal",
-    "testAll": "Uji Semua",
-    "errorTestFailed": "Gagal menguji proksi",
-    "batchSelectedCount": "{count} terpilih",
-    "batchDeleteSelected": "Hapus {count} terpilih",
-    "batchActivateSelected": "Aktifkan {count} terpilih",
-    "testPassed": "✓ OK",
-    "close": "Tutup",
-    "managePool": "Kelola Pool",
-    "poolTitle": "Pool & Rotasi Proksi",
-    "poolDescription": "Lampirkan beberapa proksi ke suatu cakupan dan rotasikan IP egress di antaranya. Cakupan dengan proksi tunggal berperilaku persis seperti penetapan biasa.",
-    "poolScopeIdLabel": "ID Cakupan",
-    "poolScopeIdPlaceholder": "id penyedia / id koneksi / id kombo",
-    "poolScopeIdRequired": "ID cakupan diperlukan untuk cakupan penyedia, akun, atau kombo.",
-    "poolLoad": "Muat Pool",
-    "poolLoadFailed": "Gagal memuat pool proksi",
-    "poolStrategyLabel": "Strategi rotasi",
-    "poolStrategyHint": "round-robin memutar anggota secara berurutan; random memilih secara seragam; sticky menahan satu anggota untuk jangka waktu tertentu; latency-optimized memilih yang tercepat berdasarkan log.",
-    "poolStrategyFailed": "Gagal memperbarui strategi rotasi",
-    "strategyRoundRobin": "Round-robin",
-    "strategyRandom": "Acak",
-    "strategySticky": "Sticky",
-    "strategyLatency": "Dioptimalkan untuk latensi",
-    "poolMembersLabel": "Anggota pool ({count})",
-    "poolNoMembers": "Belum ada proksi di pool ini.",
-    "poolRemove": "Hapus",
-    "poolRemoveFailed": "Gagal menghapus proksi dari pool",
-    "poolAddLabel": "Tambah proksi",
-    "poolAddMember": "Tambah",
-    "poolAddFailed": "Gagal menambahkan proksi ke pool",
-    "poolSelectProxy": "Pilih proksi…",
-    "poolSaveFailed": "Gagal menyimpan penetapan pool"
-  },
-  "playground": {
-    "title": "Model Playground",
-    "description": "Test any model directly from the dashboard. Select provider, model, and endpoint type, then send a request to see the raw response.",
-    "endpoint": "Endpoint",
-    "provider": "Provider",
-    "model": "Model",
-    "accountKey": "Account / Key",
-    "autoAccounts": "Auto ({count} accounts)",
-    "noAccounts": "No accounts",
-    "send": "Send",
-    "cancel": "Cancel",
-    "audioFile": "Audio File",
-    "attachImages": "Attach Images (Vision)",
-    "multipartFormData": "multipart/form-data",
-    "upToImages": "Up to 4 images",
-    "selectAudioFile": "Select audio file for transcription (mp3, wav, m4a, ogg, flac…)",
-    "clearAll": "Clear All",
-    "request": "Request",
-    "response": "Response",
-    "transcription": "Transcription",
-    "copy": "Copy",
-    "resetToDefault": "Reset to default",
-    "downloadAudio": "Download audio",
-    "copyText": "Copy text",
-    "transcriptionHint": "Transcription uses multipart/form-data. Upload the audio file above — the JSON below controls extra parameters (model, language).",
-    "imagesGenerated": "Generated {count} images",
-    "generatedImage": "Generated image {index}",
-    "save": "Save",
-    "endpointOptions": {
-      "chat": "Chat completions",
-      "responses": "Responses",
-      "completions": "Penyelesaian",
-      "images": "Image generation",
-      "embeddings": "Embeddings",
-      "speech": "Text-to-speech",
-      "transcription": "Audio transcription",
-      "video": "Video generation",
-      "music": "Music generation",
-      "moderations": "Moderasi",
-      "rerank": "Rerank",
-      "search": "Web search",
-      "webFetch": "Pengambilan web"
-    },
-    "conversationalChat": "Obrolan Percakapan",
-    "clearChat": "Hapus obrolan",
-    "typeMessagePlaceholder": "Ketik pesan... (Shift+Enter untuk baris baru)",
-    "tabChat": "Chat",
-    "tabCompare": "Compare",
-    "tabApi": "API",
-    "tabBuild": "Build",
-    "configPane": "Config",
-    "systemPrompt": "System prompt",
-    "systemPromptPlaceholder": "You are a helpful assistant.",
-    "modelPlaceholder": "e.g. openai/gpt-4o",
-    "endpointLabel": "Endpoint",
-    "parametersLabel": "Parameters",
-    "collapseConfig": "Collapse config pane",
-    "expandConfig": "Expand config pane",
-    "temperature": "Temperature",
-    "maxTokens": "Max tokens",
-    "topP": "Top-p",
-    "presencePenalty": "Presence penalty",
-    "frequencyPenalty": "Frequency penalty",
-    "reasoningLabel": "Penalaran",
-    "thinking": "Berpikir",
-    "effort": "Upaya",
-    "effortDefault": "Bawaan",
-    "seedPlaceholder": "Random (leave empty)",
-    "presetsLabel": "Presets",
-    "loadPreset": "Load preset",
-    "savePreset": "Save preset",
-    "noPresets": "No presets",
-    "presetNamePlaceholder": "Preset name",
-    "savingPreset": "Saving…",
-    "nameRequired": "Name is required",
-    "failedToSavePreset": "Failed to save preset",
-    "improvePrompt": "Improve prompt",
-    "improvingPrompt": "Improving…",
-    "improvePromptTitle": "Improve your prompt with AI",
-    "setModelFirst": "Set a model first",
-    "setModelInConfigFirst": "Atur model di panel Konfigurasi terlebih dahulu.",
-    "improvePromptFailed": "Gagal menyempurnakan prompt.",
-    "improvePromptAria": "Sempurnakan prompt menggunakan AI",
-    "confirmImprovePrompt": "Konfirmasi penyempurnaan prompt",
-    "improvePromptDescription": "Ini akan mengirimkan prompt sistem Anda saat ini ke <model></model> untuk menghasilkan versi yang disempurnakan.",
-    "improveQuotaWarning": "This will consume quota from the model configured in Config.",
-    "improveConfirm": "Improve",
-    "exportCode": "Export code",
-    "exportCodeTitle": "Export Code",
-    "exportShort": "Ekspor",
-    "noStateToExport": "No playground state available to export.",
-    "closeExportModal": "Tutup modal ekspor",
-    "close": "Tutup",
-    "exportRealKeyWarning": "Peringatan keamanan: ekspor diblokir — kunci API asli terdeteksi dalam keluaran. Silakan atur ulang kunci API Anda dan coba lagi.",
-    "placeholderHintPrefix": "Ganti",
-    "placeholderHintSuffix": "dengan kunci API Anda yang sebenarnya, atau atur sebagai variabel lingkungan.",
-    "copyLangCode": "Salin kode {language}",
-    "loadingPresets": "Memuat…",
-    "loadPresetPlaceholder": "Muat prasetel…",
-    "copyCode": "Copy",
-    "copiedCode": "Copied!",
-    "addModel": "+ Add model",
-    "runAll": "Run all",
-    "cancelAll": "Cancel all",
-    "maxColumnsReached": "Maximum {max} columns",
-    "modelPlaceholderCompare": "Model (Cmd+K)…",
-    "noModel": "Tanpa model",
-    "statusLabel": "Status: {status}",
-    "status": {
-      "idle": "idle",
-      "streaming": "streaming",
-      "done": "selesai",
-      "error": "galat"
-    },
-    "cancelStream": "Batalkan streaming",
-    "removeColumn": "Hapus kolom",
-    "removeModelColumn": "Hapus kolom untuk {model}",
-    "readyToRun": "Siap dijalankan.",
-    "errorLabel": "Galat",
-    "unknownError": "Terjadi galat yang tidak diketahui.",
-    "waitingForResponse": "Menunggu tanggapan…",
-    "ttft": "TTFT",
-    "tps": "TPS",
-    "metricsDisclaimer": "client-side estimate",
-    "tokensLabel": "Tokens",
-    "costLabel": "Cost",
-    "costEstimated": "(estimated)",
-    "ttftTitle": "Waktu hingga token pertama (perkiraan sisi klien)",
-    "tpsTitle": "Token per detik (perkiraan sisi klien)",
-    "tokenCountsTitle": "Token prompt ↑ / Token penyelesaian ↓",
-    "estimatedCostTitle": "Perkiraan biaya (tidak dijamin akurat)",
-    "toolsLabel": "Tools",
-    "toolsCount": "Alat ({count})",
-    "addTool": "Add tool",
-    "editTool": "Edit alat {name}",
-    "removeTool": "Hapus alat {name}",
-    "toolNamePlaceholder": "Function name",
-    "toolNameRequiredPlaceholder": "Nama fungsi *",
-    "toolDescPlaceholder": "Description (optional)",
-    "toolParamsLabel": "Parameter (skema JSON)",
-    "toolParamsJsonSchema": "Skema JSON untuk parameter",
-    "toolParamsInvalid": "Parameters must be valid JSON",
-    "structuredOutputLabel": "Structured Output",
-    "enableJsonMode": "Enable JSON mode",
-    "disableJsonMode": "Disable JSON mode",
-    "invalidJson": "Invalid JSON",
-    "jsonMode": "Mode JSON",
-    "jsonModeDescription": "Memaksa response_format: json_schema",
-    "schemaName": "Nama skema",
-    "jsonSchema": "Skema JSON",
-    "jsonSchemaEditor": "Editor skema JSON",
-    "schemaValidated": "Skema divalidasi",
-    "validateSchema": "Validasi skema",
-    "seed": "Seed",
-    "stopSequences": "Urutan henti",
-    "stopSequencesPlaceholder": "misal \"\\n\\n\" atau \"END\"",
-    "autoProvider": "Otomatis",
-    "httpError": "Galat {status}",
-    "requestCancelled": "Permintaan dibatalkan",
-    "networkError": "Galat jaringan",
-    "regenerateLastResponse": "Buat ulang respons terakhir",
-    "regenerate": "Buat ulang",
-    "startConversation": "Mulai percakapan — ketik pesan di bawah",
-    "role": {
-      "system": "sistem",
-      "user": "pengguna",
-      "assistant": "asisten"
-    },
-    "generating": "Menghasilkan…",
-    "typeMessageWithShortcut": "Ketik pesan... (Enter untuk mengirim, Shift+Enter untuk baris baru)",
-    "stop": "Berhenti",
-    "noResponseBody": "Tidak ada badan respons",
-    "comparePromptPlaceholder": "Masukkan prompt Anda di sini…",
-    "userPrompt": "Prompt pengguna",
-    "cancelAllStreams": "Batalkan semua aliran",
-    "runAllColumns": "Jalankan semua kolom",
-    "newColumnModelName": "Nama model untuk kolom baru",
-    "addColumn": "Tambah kolom",
-    "addModelColumn": "Tambah kolom model",
-    "columnCount": "{count}/{max} kolom",
-    "addModelToCompare": "Tambah kolom model untuk membandingkan",
-    "modelsSimultaneously": "Hingga {max} model secara bersamaan",
-    "running": "Running…",
-    "runLabel": "Run",
-    "enterToolResult": "Enter tool result…",
-    "build": {
-      "step1Label": "Apa yang ingin diuji?",
-      "step2Label": "Konfigurasi",
-      "step3Label": "Jalankan",
-      "step1Title": "Apa yang ingin Anda uji?",
-      "step1Subtitle": "Pilih kapabilitas yang ingin Anda jelajahi dalam sesi ini.",
-      "step2Title": "Konfigurasi",
-      "step2Subtitle": "Atur alat atau skema JSON yang akan digunakan dalam permintaan.",
-      "step3Title": "Jalankan",
-      "modeToolsTitle": "Alat",
-      "modeToolsDesc": "Uji pemanggilan fungsi — definisikan alat dan lihat bagaimana model memanggilnya.",
-      "modeJsonTitle": "JSON",
-      "modeJsonDesc": "Uji keluaran terstruktur — batasi respons ke skema JSON.",
-      "modeBothTitle": "Alat + JSON",
-      "modeBothDesc": "Gabungkan pemanggilan fungsi dan keluaran terstruktur dalam satu permintaan.",
-      "backButton": "Kembali",
-      "nextButton": "Berikutnya",
-      "runButton": "Jalankan",
-      "promptPlaceholder": "Masukkan pesan Anda… (Enter untuk mengirim, Shift+Enter untuk baris baru)"
-    }
-  },
-  "miniPlayground": {
-    "endpoint": "Endpoint",
-    "apiKey": "Kunci API",
-    "model": "Model",
-    "voice": "Suara",
-    "speed": "Kecepatan",
-    "input": "Input",
-    "url": "URL",
-    "format": "Format",
-    "depth": "Kedalaman",
-    "copyCurl": "Salin cURL",
-    "copied": "Tersalin!",
-    "run": "Jalankan",
-    "running": "Menjalankan...",
-    "loading": "Memuat...",
-    "retry": "Coba Lagi",
-    "response": "Respons",
-    "tunnel": "Tunnel",
-    "send": "Kirim",
-    "selectKey": "Pilih kunci",
-    "testLabel": "Uji",
-    "expandTest": "Luaskan pengujian",
-    "collapseTest": "Ciutkan pengujian",
-    "revealKey": "Tampilkan kunci",
-    "hideKey": "Sembunyikan kunci",
-    "download": "Unduh",
-    "play": "Putar",
-    "query": "Kueri",
-    "numResults": "Hasil maksimum",
-    "prompt": "Prompt",
-    "size": "Ukuran",
-    "duration": "Durasi",
-    "question": "Pertanyaan",
-    "audioFile": "Berkas audio",
-    "fileTooLarge25Mb": "Berkas terlalu besar. Ukuran maksimum: 25 MB.",
-    "selectAudioFirst": "Pilih berkas audio terlebih dahulu.",
-    "speechToText": "Ucapan ke Teks",
-    "chooseFile": "Pilih berkas",
-    "audioFormats25Mb": "MP3, WAV, M4A, OGG atau FLAC · Maksimum 25 MB",
-    "musicSample": "Trek ambien yang tenang dengan piano hangat dan gesekan dawai yang lembut",
-    "noAudioUrl": "Respons tidak menyertakan URL audio: {response}",
-    "music": "Musik",
-    "embeddingSample": "OmniRoute merutekan permintaan AI ke berbagai penyedia.",
-    "embedding": "Embedding",
-    "imageSample": "Kota futuristik saat matahari terbenam, pencahayaan sinematik",
-    "image": "Gambar",
-    "ttsSample": "Halo dari OmniRoute. Ini adalah uji coba teks-ke-ucapan.",
-    "textToSpeech": "Teks ke Ucapan",
-    "videoSample": "Pesawat kertas terbang di atas kota futuristik",
-    "video": "Video",
-    "webFetch": "Web Fetch",
-    "webSearchSample": "Apa itu OmniRoute?",
-    "webSearch": "Pencarian Web",
-    "documentUrl": "URL Dokumen",
-    "browserAudioUnsupported": "Peramban Anda tidak mendukung audio.",
-    "browserVideoUnsupported": "Peramban Anda tidak mendukung video.",
-    "searchResultFallback": "Hasil {number}",
-    "noKeysFound": "Kunci API tidak ditemukan. Tambahkan satu di bagian Kunci.",
-    "exampleLabel": "Contoh",
-    "latency": "{ms}ms",
-    "statsLine": "{ms}ms · {tokensIn} token masuk / {tokensOut} token keluar",
-    "defaultKey": "(bawaan)",
-    "clear": "Bersihkan",
-    "emptyConversation": "Kirim pesan untuk memulai percakapan",
-    "sendHint": "Shift+Enter untuk baris baru · Enter untuk mengirim",
-    "you": "Anda",
-    "assistant": "Asisten",
-    "errorLabel": "Kesalahan",
-    "requestFailed": "Permintaan gagal",
-    "stop": "Hentikan"
-  },
-  "requestLogger": {
-    "recording": "Recording",
-    "paused": "Paused",
-    "pipelineLogsOn": "Pipeline logs on",
-    "pipelineLogsOff": "Pipeline logs off",
-    "updatingPipelineLogs": "Updating pipeline logs...",
-    "updatePipelineFailed": "Failed to update pipeline logging",
-    "capturePipeline": "Capture pipeline payloads for new requests",
-    "searchPlaceholder": "Search models, providers, accounts, API keys, combos...",
-    "allProviders": "All providers",
-    "allModels": "All models",
-    "allAccounts": "All accounts",
-    "allApiKeys": "All API keys",
-    "total": "Total",
-    "ok": "Success",
-    "err": "Error",
-    "combo": "Combo",
-    "keys": "Keys",
-    "shown": "Shown",
-    "sortNewest": "Newest",
-    "sortOldest": "Oldest",
-    "sortTokensDesc": "Tokens ↓",
-    "sortTokensAsc": "Tokens ↑",
-    "sortDurationDesc": "Duration ↓",
-    "sortDurationAsc": "Duration ↑",
-    "sortStatusDesc": "Status ↓",
-    "sortStatusAsc": "Status ↑",
-    "sortModelAsc": "Model A-Z",
-    "sortModelDesc": "Model Z-A",
-    "sortLogs": "Sort logs",
-    "refresh": "Refresh",
-    "columnsLabel": "Columns",
-    "cacheSem": "SEM",
-    "cacheUp": "UP",
-    "semantic": "Semantic",
-    "upstream": "Upstream",
-    "semanticCacheHit": "Semantic cache hit (served by OmniRoute)",
-    "upstreamResponse": "Upstream provider response",
-    "noApiKey": "No API key",
-    "requestedRoutedTitle": "Requested {requested}, routed as {routed}",
-    "statusFilters": {
-      "all": "All",
-      "error": "Error",
-      "success": "Success",
-      "combo": "Combo"
-    },
-    "columns": {
-      "status": "Status",
-      "cacheSource": "Cache Source",
-      "model": "Model",
-      "requested": "Requested",
-      "provider": "Provider",
-      "protocol": "Request Protocol",
-      "account": "Account",
-      "apiKey": "API Key",
-      "combo": "Combo",
-      "tokens": "Tokens",
-      "compressed": "Kompresi",
-      "tps": "TPS",
-      "duration": "Duration",
-      "time": "Time",
-      "conversation": "Conversation",
-      "ttft": "TTFT"
-    },
-    "loadingLogs": "Loading logs...",
-    "noLogs": "No logs yet. Make some API calls to see them here.",
-    "noMatchingLogs": "No logs matching current filters.",
-    "callLogsInfo": "Call logs are also saved as JSON files to {dataDir} and rotated based on {retentionDays} and {maxEntries}.",
-    "loadMore": "Muat Lebih Banyak",
-    "loadingMore": "Memuat lebih banyak...",
-    "correlationId": "ID Korelasi",
-    "group": {
-      "showAllRows": "Tampilkan semua baris",
-      "showLatestPerCorrelation": "Tampilkan terbaru per ID korelasi",
-      "grouped": "Dikelompokkan"
-    },
-    "running": "berjalan",
-    "interval": {
-      "decrease": "Kurangi interval",
-      "title": "Interval penyegaran otomatis dalam detik",
-      "increase": "Tingkatkan interval"
-    },
-    "status": {
-      "inProgress": "Sedang diproses",
-      "recoveredByRetry": "Dipulihkan dengan mencoba lagi",
-      "goToParent": "Pergi ke permintaan induk",
-      "healedTitle": "Gagal, pulih setelah {count} percobaan",
-      "healed": "sembuh",
-      "failedTitle": "Semua {count} percobaan gagal",
-      "failed": "gagal",
-      "pinnedTitle": "Model yang dipilih melalui penetapan sesi cache konteks",
-      "pinned": "tersemat"
-    },
-    "attempts": "upaya",
-    "detail": {
-      "collapse": "Runtuhkan {title}",
-      "expand": "Perluas {title}",
-      "copyTitle": "Salin {title}",
-      "copied": "Disalin!",
-      "copy": "Salin",
-      "autoscrollOn": "Autoscroll: aktif",
-      "autoscrollOff": "Autoscroll: mati",
-      "collapseAllLevels": "__MISSING__:Collapse all",
-      "collapseOneLevel": "__MISSING__:Collapse one level",
-      "currentExpandLevel": "__MISSING__:Current expand level",
-      "expandOneLevel": "__MISSING__:Expand one level",
-      "expandAllLevels": "__MISSING__:Expand all",
-      "payload": {
-        "clientRawRequest": "Permintaan Mentah Klien",
-        "clientRequest": "Permintaan Klien",
-        "openaiRequest": "Permintaan OpenAI",
-        "providerRequest": "Permintaan Penyedia",
-        "providerResponse": "Respon Penyedia",
-        "clientResponse": "Tanggapan Klien",
-        "pipelineError": "Kesalahan Pipeline"
-      },
-      "payloadMissing": "Artifact payload yang terperinci tidak lagi tersedia untuk entri log ini.",
-      "payloadCorrupt": "Artifact payload yang rinci tidak dapat diparsing.",
-      "notAvailable": "N/A",
-      "semanticCache": "Semantik (OmniRoute)",
-      "upstreamCache": "Hulu (Penyedia)",
-      "ariaLabel": "Detail log permintaan",
-      "completed": "Selesai",
-      "upstreamStatus": "Hulu: {status}",
-      "statusDiscrepancy": "OmniRoute mengembalikan {status} meskipun penyedia mengembalikan {provider}",
-      "previousRequest": "Permintaan sebelumnya",
-      "nextRequest": "Permintaan berikutnya",
-      "close": "Tutup modal detail",
-      "startedAt": "Dimulai Pada",
-      "endedAt": "Berakhir Di",
-      "duration": "Durasi",
-      "model": "Model",
-      "provider": "Penyedia",
-      "account": "Akun",
-      "input": "Masukkan",
-      "totalIn": "Total Masuk: {value}",
-      "cacheRead": "Cache Baca: {value}",
-      "cacheWrite": "Cache Tulis: {value}",
-      "compressed": "Terkompresi: {from} → {to} ({percent}% dihemat)",
-      "output": "Keluaran",
-      "totalOut": "Total Keluar: {value}",
-      "reasoning": "Alasan: {value}",
-      "requestedModel": "Model yang Diminta",
-      "requestProtocol": "Protokol Req",
-      "cacheSource": "Sumber Cache",
-      "modelPinning": "Penetapan Model",
-      "activeModelPinning": "Aktif — model dipilih melalui penempelan sesi",
-      "rotated": "Diputar: {initial} -> {final}",
-      "apiKey": "Kunci API",
-      "noApiKey": "Tidak ada kunci API",
-      "combo": "Kombinasi",
-      "error": "Kesalahan",
-      "unblockAll": "Buka blokir semua",
-      "cleared": "Dihapus",
-      "unblock": "Buka Blokir",
-      "relatedRequests": "Permintaan Terkait ({count})",
-      "current": "saat ini",
-      "detailStatus": "Detail Status",
-      "loadingDetails": "Memuat rincian permintaan...",
-      "providerEventStream": "Aliran Acara Penyedia",
-      "clientEventStream": "Aliran Acara Klien",
-      "eventStream": "Aliran Acara",
-      "responsePayloadLegacy": "Payload Respon (Legacy)",
-      "requestPayloadLegacy": "Request Payload (Legacy)",
-      "noPayload": "Tidak ada data payload yang tersedia untuk entri log ini.",
-      "correlationId": "ID Korelasi",
-      "correlationIdValue": "ID Korelasi: {id}",
-      "detailedPayloadInfo": "Aktifkan logging terperinci terlebih dahulu jika Anda ingin tampilan payload klien/penyedia empat tahap untuk permintaan baru.",
-      "copyAll": "Copy all",
-      "copiedAll": "Copied all"
-    }
-  },
-  "proxyLogger": {
-    "filterAll": "All",
-    "filterErrors": "Errors",
-    "filterSuccess": "Success",
-    "filterTimeout": "Timeout",
-    "colStatus": "Status",
-    "colProxy": "Proxy",
-    "colTls": "TLS",
-    "colType": "Type",
-    "colLevel": "Level",
-    "colProvider": "Provider",
-    "colTarget": "Target",
-    "colLatency": "Latency",
-    "colClientIp": "Client IP",
-    "colTime": "Time",
-    "recording": "Recording",
-    "paused": "Paused",
-    "searchPlaceholder": "Search host, provider, target, IP...",
-    "allTypes": "All Types",
-    "allLevels": "All Levels",
-    "allProviders": "All Providers",
-    "total": "total",
-    "ok": "OK",
-    "err": "ERR",
-    "timeoutShort": "TMO",
-    "direct": "direct",
-    "newest": "Newest",
-    "oldest": "Oldest",
-    "latencyDesc": "Latency ↓",
-    "latencyAsc": "Latency ↑",
-    "refresh": "Refresh",
-    "columns": "Columns",
-    "loadingProxyLogs": "Loading proxy logs...",
-    "noProxyLogs": "No proxy logs yet. Configure proxies and make API calls to see them here.",
-    "noMatchingLogs": "No logs match the current filters.",
-    "tlsFingerprint": "Chrome 124 TLS Fingerprint",
-    "colPublicIp": "IP Publik"
-  },
-  "endpointOptions": {
-    "speech": "Speech",
-    "search": "Search",
-    "images": "Images",
-    "chat": "Chat",
-    "music": "Music",
-    "responses": "Responses",
-    "rerank": "Rerank",
-    "video": "Video",
-    "embeddings": "Embeddings",
-    "transcription": "Transcription"
-  },
-  "toolDescriptions": {
-    "cline": "Cline",
-    "openclaw": "Openclaw",
-    "droid": "Droid",
-    "codex": "Codex",
-    "claude": "Claude",
-    "kilo": "Kilo"
-  },
-  "runtime": {
-    "title": "Runtime",
-    "description": "Realtime observability — 3-layer resilience + sessions + quota alerts",
-    "pause": "Pause",
-    "resume": "Resume",
-    "refreshNow": "Refresh now",
-    "kpiSessions": "Sessions",
-    "kpiCircuits": "Circuits",
-    "kpiCooldowns": "Cooldowns",
-    "kpiLockouts": "Lockouts",
-    "hintStickyBound": "{count} sticky-bound",
-    "hintRecovering": "{count} recovering",
-    "hintAllHealthy": "all healthy",
-    "hintOpen": "open",
-    "hintConnsCooling": "connections cooling",
-    "hintModelsBlocked": "models blocked",
-    "resilienceTitle": "3-Layer Resilience",
-    "resilienceSubtitle": "Mirrors the documented resilience model",
-    "providersHealthy": "{percent}% providers healthy",
-    "layer": "Layer {n}",
-    "layer1Title": "Provider Circuit Breakers",
-    "layer1Desc": "Stop traffic to providers failing at the upstream level",
-    "layer2Title": "Connection Cooldowns",
-    "layer2Desc": "Skip one bad account/key; other connections keep serving",
-    "layer3Title": "Model Lockouts",
-    "layer3Desc": "Per-model rate-limit locks; same connection still serves other models",
-    "badgeAffectedOf": "{affected} of {total} affected",
-    "badgeCooling": "{count} cooling",
-    "badgeLocked": "{count} locked",
-    "emptyCircuits": "No circuit breakers active yet",
-    "emptyCooldowns": "No connection cooldowns active",
-    "emptyLockouts": "No model lockouts",
-    "moreCooldowns": "+{count} more cooldowns",
-    "moreLockouts": "+{count} more lockouts",
-    "feedTitle": "Live Feed",
-    "feedSubtitle": "Last {count} events",
-    "feedFilterAll": "All",
-    "feedFilterCircuits": "Circuits",
-    "feedFilterCooldowns": "Cooldowns",
-    "feedFilterLockouts": "Lockouts",
-    "feedFilterSessions": "Sessions",
-    "feedFilterQuotas": "Quotas",
-    "feedClear": "Clear",
-    "feedEmptyWaiting": "Waiting for events... (polled every 5s)",
-    "feedEmptyFiltered": "No events match this filter",
-    "sessionsTitle": "Active Sessions",
-    "sessionsSubtitle": "Sticky-bound request fingerprints (live)",
-    "sessionsActive": "{count} active",
-    "sessionsEmptyTitle": "No active sessions",
-    "sessionsEmptyHint": "Sessions appear as requests flow through the proxy",
-    "tblSession": "Session",
-    "tblAge": "Age",
-    "tblIdle": "Idle",
-    "tblReqs": "Reqs",
-    "tblBoundTo": "Bound to",
-    "topApiKeys": "Top API keys",
-    "quotaMonitorsTitle": "Quota Monitors",
-    "quotaMonitorsSubtitle": "Live quota state per account window",
-    "openQuota": "Open Quota",
-    "allQuotasHealthy": "All quotas healthy",
-    "statusExhausted": "EXHAUSTED",
-    "statusAlerting": "ALERTING",
-    "statusError": "ERROR",
-    "moreSuffix": "+{count} more"
-  },
-  "quotaShare": {
-    "weightPercent": "Bobot %",
-    "title": "Quota Sharing",
-    "description": "Share provider quotas across API keys with % limits",
-    "newPool": "New pool",
-    "betaTitle": "Beta — UI preview.",
-    "betaDescription": "Configuration is saved in localStorage (not yet persisted on the server). Per-request cap enforcement is not yet wired into the proxy pipeline. This screen lets you design and visualize the quota split; real enforcement will land in a future iteration with DB persistence and upstream call interception.",
-    "kpiActivePools": "Active pools",
-    "kpiKeysAllocated": "Keys allocated",
-    "kpiAvgUnallocated": "Avg unallocated",
-    "kpiProvidersWithQuota": "Providers w/ quota",
-    "emptyTitle": "No pools configured",
-    "emptyDescription": "Create a pool to assign API keys to share a provider's quota window with % allocations.",
-    "loading": "Loading…",
-    "removePool": "Remove pool",
-    "removeConfirm": "Remove this pool?",
-    "pool": "Pool",
-    "used": "used",
-    "allocationsCount": "Allocations ({count})",
-    "allocatedFree": "{allocated}% allocated · {free}% free",
-    "noAllocations": "No keys allocated yet",
-    "capLabel": "cap {value}",
-    "notTrackedYet": "(not tracked yet)",
-    "policy": "Policy",
-    "apiKeyColumn": "Kunci API",
-    "weightColumn": "Bobot",
-    "fairShareShort": "adil",
-    "policyHard": "hard",
-    "policySoft": "soft",
-    "policyBurst": "burst",
-    "policyHardHint": "Block when key exhausts allocation",
-    "policySoftHint": "Allow overflow, alert only",
-    "policyBurstHint": "Allow burst into free pool",
-    "editAllocations": "Edit allocations",
-    "newPoolTitle": "New quota pool",
-    "providerConnection": "Provider connection (account)",
-    "selectConnection": "Select a connection…",
-    "noEligibleConnections": "No connections with quota data. Refresh from /dashboard/quota first.",
-    "quotaWindow": "Quota window",
-    "selectWindow": "Select a window…",
-    "alreadyUsedSuffix": "(already used)",
-    "windowReset": "Reset",
-    "duplicatePoolError": "A pool for this connection + window already exists",
-    "cancel": "Cancel",
-    "createPool": "Create pool",
-    "editTitle": "Edit allocations",
-    "noKeysAdded": "No keys allocated. Add one below.",
-    "totalLabel": "Total: {percent}%",
-    "totalExceeded": "⚠ exceeds 100%",
-    "addKey": "+ Add key…",
-    "equalSplit": "Equal split",
-    "save": "Save allocations",
-    "betaPreviewLabel": "Beta — Pratinjau UI.",
-    "betaConfigSavedPrefix": "Konfigurasi disimpan di",
-    "betaConfigSavedSuffix": "(belum bertahan di server). Pemberlakuan batasan per permintaan belum dimasukkan ke dalam jalur proksi. Layar ini memungkinkan Anda merancang dan memvisualisasikan pembagian kuota; penegakan hukum yang nyata akan diterapkan pada iterasi mendatang dengan persistensi DB dan intersepsi panggilan upstream.",
-    "policyLabel": "Kebijakan:",
-    "resetIn": "ulang masuk",
-    "quotaTotal": "jumlah",
-    "kpiAvgUtilization": "Rata-rata utilisasi",
-    "kpiBorrowingNow": "Meminjam sekarang",
-    "conceptTitle": "Cara kerja Berbagi Kuota",
-    "conceptIntro": "Berbagi Kuota membagi kuota penyedia di antara beberapa kunci API menggunakan pembagian adil yang menghemat kerja: setiap kunci menerima bagian yang proporsional tetapi dapat meminjam dari saldo bebas tanpa melebihi batas global.",
-    "conceptFairShare": "Pembagian adil: setiap kunci menerima kuota yang proporsional dengan bobot yang dikonfigurasi",
-    "conceptBorrowing": "Peminjaman: kunci dapat mengonsumsi saldo bebas dari yang lain tanpa melanggar batas",
-    "conceptGlobalCap": "Batas global mutlak: batas absolut penyedia tidak pernah terlampaui",
-    "conceptWindows": "Jendela: 5j, per jam, harian, mingguan, bulanan — masing-masing dilacak secara independen",
-    "conceptKeyHowTitle": "Mengaktifkan kunci untuk kuota",
-    "conceptKeyHowDesc": "Buat kunci secara normal di Kunci API — kunci tersebut akan muncul di langkah kunci wisaya secara otomatis. Centang Eksklusif di sana untuk menjadikannya hanya-kuota. Tidak ada langkah pengaktifan terpisah.",
-    "conceptExclusiveTitle": "Apa fungsi \"Eksklusif\"",
-    "conceptExclusiveDesc": "Kunci eksklusif hanya melihat/menggunakan model quotaShared-* dari pool — setiap model lainnya disembunyikan dari /v1/models miliknya dan diblokir.",
-    "burnRateTitle": "Laju konsumsi",
-    "burnRateExhaustsIn": "Habis dalam",
-    "dimensionResetIn": "Direset dalam",
-    "realConsumedColumn": "Dikonsumsi",
-    "deficitColumn": "Defisit",
-    "borrowingIndicator": "meminjam",
-    "migratedFromLocalStorageNotice": "Pool berhasil dimigrasikan dari localStorage.",
-    "policyCapAbsoluteLabel": "Batas absolut",
-    "policyCapAbsolutePlaceholder": "Batas numerik (opsional)",
-    "multiDimensionLabel": "Multi-dimensi",
-    "stackedBarTitle": "Bagian per kunci API",
-    "usedSuffix": "digunakan {percent}%",
-    "wizardTitle": "Pool kuota baru",
-    "editPoolTitle": "Edit pool",
-    "saveChanges": "Simpan perubahan",
-    "wizardStep1Label": "Akun",
-    "wizardStep2Label": "Batas",
-    "wizardStep3Label": "Kunci",
-    "wizardStep1Title": "Pilih koneksi penyedia",
-    "wizardStep1Subtitle": "Pilih akun penyedia yang kuotanya akan dibagikan oleh pool ini, atur nama dan kebijakan default.",
-    "wizardStep2Title": "Konfigurasi dimensi kuota",
-    "wizardStep2Subtitle": "Tentukan dimensi paket kuota (unit, jendela, batas) untuk koneksi yang dipilih. Biarkan tidak berubah untuk mempertahankan pengaturan saat ini.",
-    "wizardStep3Title": "Alokasikan kunci API",
-    "wizardStep3Subtitle": "Tetapkan kunci API ke pool ini dengan alokasi % bobot dan batas opsional.",
-    "wizardPoolNameLabel": "Nama pool",
-    "wizardPoolNamePlaceholder": "Pool kuota saya",
-    "wizardNext": "Berikutnya",
-    "wizardBack": "Kembali",
-    "wizardCreatePool": "Buat pool",
-    "wizardDimensionsEditedNotice": "Dimensi diedit — akan disimpan sebagai penggantian manual saat pool dibuat.",
-    "wizardExclusiveLabel": "Kuota eksklusif",
-    "wizardExclusiveHint": "Saat diaktifkan, kunci API ini hanya akan diizinkan untuk menggunakan model virtual pool ini (rekonsiliasi allowedQuotas diterapkan saat menyimpan).",
-    "wizardPreviewLabel": "Pratinjau nama model virtual",
-    "wizardConnectionsLabel": "Koneksi penyedia",
-    "wizardPrimaryBadge": "utama",
-    "wizardAdditionalConnectionsNote": "Koneksi tambahan menggunakan batas default katalognya (dapat diedit nanti).",
-    "wizardSingleProviderNote": "Sebuah pool menggunakan satu penyedia",
-    "wizardPreviewMoreModels": "+{count} lainnya",
-    "accountQuotaTitle": "Kuota akun",
-    "accountQuotaNone": "—",
-    "logTitle": "Log penggunaan",
-    "logEmpty": "Belum ada penggunaan",
-    "groupLabel": "Grup",
-    "newGroup": "Grup baru",
-    "renameGroup": "Ganti nama grup",
-    "groupSelectHint": "Filter pool berdasarkan grup",
-    "groupAllocationNote": "Alokasi berlaku untuk semua pool dalam grup ini melalui lapisan kuota bersama.",
-    "groupNamePrompt": "Masukkan nama grup",
-    "wizardGroupLabel": "Grup",
-    "allGroups": "Semua grup",
-    "endpointsTitle": "Endpoint yang tersedia",
-    "endpointsHint": "Panggil model virtual ini dengan kunci apa pun yang dialokasikan — perutean + kuota ditangani per grup.",
-    "previewForKey": "Pratinjau untuk kunci",
-    "previewKeyNone": "(semua endpoint)",
-    "endpointsBaseUrl": "URL Dasar",
-    "endpointsCollapse": "Ciutkan",
-    "endpointsExpand": "Luaskan",
-    "endpointsAnthropicNote": "Anthropic-native",
-    "endpointsResponsesNote": "Respons OpenAI — codex/github",
-    "endpointsWsNote": "WebSocket — hanya codex",
-    "betaText": "Quota Share berfungsi tetapi bug mungkin terjadi. Menemukannya? Silakan laporkan.",
-    "betaReportLink": "Laporkan masalah",
-    "deleteGroup": "Hapus grup",
-    "deleteGroupConfirm": "Hapus grup ini? Pool di dalamnya harus dialihkan atau dihapus terlebih dahulu.",
-    "deleteGroupHasPools": "Grup ini masih memiliki pool — alihkan atau hapus terlebih dahulu.",
-    "ungroupedTitle": "Tanpa grup",
-    "ungroupedHint": "Pool ini tidak ditetapkan ke grup yang dikenal. Edit pool untuk memindahkannya ke grup yang sebenarnya.",
-    "removeFailed": "Could not remove this pool.",
-    "dismiss": "Dismiss"
-  },
-  "plugins": {
-    "title": "Plugins",
-    "description": "Install and manage plugins for extending OmniRoute functionality",
-    "loading": "Loading plugins...",
-    "scanning": "Scanning...",
-    "scanForPlugins": "Scan for Plugins",
-    "noPlugins": "No plugins installed",
-    "noPluginsDescription": "Place plugin directories in ~/.omniroute/plugins/ and click Scan.",
-    "activate": "Activate",
-    "deactivate": "Deactivate",
-    "uninstall": "Uninstall",
-    "uninstallConfirm": "Uninstall plugin \"{name}\"?",
-    "pluginScanComplete": "Plugin scan complete",
-    "pluginScanFailed": "Plugin scan failed",
-    "activated": "{name} activated",
-    "deactivated": "{name} deactivated",
-    "activateFailed": "Failed to activate {name}",
-    "deactivateFailed": "Failed to deactivate {name}",
-    "uninstalled": "{name} uninstalled",
-    "uninstallFailed": "Failed to uninstall {name}",
-    "configure": "Configure: {name}",
-    "configurePlugin": "Configure",
-    "noConfigSettings": "This plugin has no configurable settings.",
-    "saving": "Saving...",
-    "saveConfiguration": "Save Configuration",
-    "configurationSaved": "Configuration saved",
-    "saveConfigurationFailed": "Failed to save configuration",
-    "pluginNotFound": "Plugin not found",
-    "version": "Version",
-    "author": "Author",
-    "description_label": "Description",
-    "status": "Status",
-    "enabled": "Enabled",
-    "disabled": "Disabled",
-    "installedTab": "Terpasang",
-    "marketplaceTab": "Marketplace",
-    "marketplaceUrlLabel": "URL Marketplace Kustom",
-    "marketplaceUrlPlaceholder": "Biarkan kosong untuk registri resmi Omniroute",
-    "saveMarketplaceUrl": "Simpan & Muat Ulang",
-    "marketplaceUrlSaved": "URL Marketplace diperbarui",
-    "marketplaceEmpty": "Tidak ada plugin yang ditemukan di marketplace.",
-    "marketplaceInstallComingSoon": "Pemasangan marketplace akan segera hadir.",
-    "verified": "Terverifikasi",
-    "install": "Pasang",
-    "installedFromMarketplace": "Plugin {name} terpasang!",
-    "hooks": "Hooks"
-  },
-  "quotaPlans": {
-    "title": "Paket & Kuota",
-    "description": "Konfigurasikan paket kuota per penyedia — dimensi (%, permintaan, token, $) dan jendela waktu",
-    "providerLabel": "Penyedia / Koneksi",
-    "detectedPlanLabel": "Paket terdeteksi",
-    "manualPlanLabel": "Penggantian manual",
-    "unconfiguredLabel": "Belum dikonfigurasi — diperlukan manual",
-    "dimensionLabel": "Dimensi",
-    "addDimension": "Tambah dimensi",
-    "removeDimension": "Hapus",
-    "limitLabel": "Batas",
-    "unitOptions": {
-      "percent": "%",
-      "requests": "permintaan",
-      "tokens": "token",
-      "usd": "USD ($)"
-    },
-    "windowOptions": {
-      "5h": "5 jam",
-      "hourly": "Per jam",
-      "daily": "Harian",
-      "weekly": "Mingguan",
-      "monthly": "Bulanan"
-    },
-    "useCatalogButton": "Gunakan katalog",
-    "saveOverrideButton": "Simpan penggantian",
-    "revertToCatalogButton": "Kembalikan ke katalog",
-    "unknownProviderNotice": "Pilih penyedia di sebelah kiri untuk mengonfigurasi paket kuotanya.",
-    "catalogTitle": "Katalog yang diketahui",
-    "catalogDescription": "Paket yang terdeteksi secara otomatis untuk penyedia berikut:"
-  },
-  "activity": {
-    "title": "Aktivitas",
-    "description": "Umpan peristiwa terkini",
-    "emptyTitle": "Belum ada aktivitas",
-    "emptyDescription": "Saat Anda menambahkan penyedia, membuat kombo, atau merotasi kunci, peristiwa akan muncul di sini.",
-    "todayHeader": "Hari ini",
-    "yesterdayHeader": "Kemarin",
-    "filterAll": "Semua",
-    "filterProviders": "Penyedia",
-    "filterCombos": "Kombo",
-    "filterApiKeys": "Kunci API",
-    "filterSettings": "Pengaturan",
-    "filterQuota": "Kuota",
-    "filterAuth": "Autentikasi",
-    "filterSystem": "Sistem",
-    "filterAria": "Filter berdasarkan jenis peristiwa",
-    "refresh": "Segarkan",
-    "refreshAria": "Segarkan umpan aktivitas",
-    "loading": "Memuat",
-    "loadingActivity": "Memuat aktivitas…",
-    "fetchFailed": "Gagal mengambil aktivitas",
-    "relative": {
-      "justNow": "baru saja",
-      "minutesAgo": "{n} mnt yang lalu",
-      "hoursAgo": "{n} jam yang lalu",
-      "yesterday": "kemarin",
-      "daysAgo": "{n} hari yang lalu"
-    },
-    "eventVerb": {
-      "providerAdded": "{actor} menambahkan penyedia {target}",
-      "providerRemoved": "{actor} menghapus penyedia {target}",
-      "providerTested": "{actor} menguji penyedia {target}",
-      "comboCreated": "{actor} membuat kombo {target}",
-      "comboUpdated": "{actor} memperbarui kombo {target}",
-      "comboDeleted": "{actor} menghapus kombo {target}",
-      "apiKeyCreated": "{actor} membuat kunci API {target}",
-      "apiKeyRevoked": "{actor} mencabut kunci API {target}",
-      "apiKeyRotated": "{actor} merotasi kunci API {target}",
-      "budgetThreshold": "Ambang batas anggaran tercapai untuk {target}",
-      "settingUpdated": "{actor} memperbarui pengaturan {target}",
-      "authLogin": "{actor} masuk",
-      "authLogout": "{actor} keluar",
-      "cloudAgentSession": "Sesi agen cloud dimulai untuk {target}",
-      "mcpToolRegistered": "Alat MCP {target} terdaftar",
-      "webhookCreated": "{actor} membuat webhook {target}",
-      "webhookDeleted": "{actor} menghapus webhook {target}",
-      "quotaPoolCreated": "{actor} membuat pool kuota {target}",
-      "quotaPoolUpdated": "{actor} memperbarui pool kuota {target}",
-      "quotaPoolDeleted": "{actor} menghapus pool kuota {target}",
-      "quotaPlanUpdated": "{actor} memperbarui paket kuota {target}",
-      "quotaStoreDriverChanged": "Driver QuotaStore diubah",
-      "updateApplied": "Pembaruan {target} diterapkan",
-      "deployCompleted": "Penerapan selesai",
-      "skillInstalled": "{actor} memasang skill {target}",
-      "skillRemoved": "{actor} menghapus skill {target}",
-      "providerCredentialsCreated": "{actor} membuat kredensial untuk {target}",
-      "providerCredentialsApplied": "Kredensial untuk {target} diterapkan",
-      "providerCredentialsUpdated": "{actor} memperbarui kredensial untuk {target}",
-      "providerCredentialsRevoked": "{actor} mencabut kredensial untuk {target}",
-      "providerCredentialsBatchRevoked": "{actor} mencabut kredensial secara massal",
-      "providerCredentialsBatchUpdated": "{actor} memperbarui kredensial secara massal",
-      "providerCredentialsBulkCreated": "{actor} membuat kredensial secara massal",
-      "providerCredentialsBulkImported": "{actor} mengimpor kredensial secara massal",
-      "providerCredentialsImported": "{actor} mengimpor kredensial",
-      "providerSsrfBlocked": "Upaya SSRF diblokir untuk {target}",
-      "authLoginSuccess": "{actor} masuk",
-      "authLoginError": "Galat login untuk {actor}",
-      "authLoginFailed": "Login gagal untuk {actor}",
-      "authLoginLocked": "{actor} terkunci setelah terlalu banyak percobaan",
-      "authLoginMisconfigured": "Konfigurasi autentikasi tidak valid",
-      "authLoginSetupRequired": "Penyiapan autentikasi diperlukan",
-      "authLogoutSuccess": "{actor} keluar",
-      "syncTokenCreated": "{actor} membuat token sinkronisasi",
-      "syncTokenRevoked": "{actor} mencabut token sinkronisasi",
-      "settingsUpdate": "{actor} memperbarui pengaturan",
-      "settingsUpdateFailed": "Pembaruan pengaturan gagal",
-      "serviceRevealApiKey": "{actor} menampilkan kunci API untuk {target}",
-      "genericEvent": "{actor} {target}"
-    }
-  },
-  "agentBridge": {
-    "title": "AgentBridge",
-    "subtitle": "Gunakan agen IDE dengan model OmniRoute — tidak memerlukan konfigurasi",
-    "riskBannerTitle": "Gunakan atas risiko Anda sendiri",
-    "riskBannerBody": "AgentBridge mencegat lalu lintas HTTPS dari agen IDE. Dengan mengaktifkannya, Anda menerima tanggung jawab atas kepatuhan terhadap ketentuan layanan masing-masing agen. Jangan pernah gunakan pada perangkat atau jaringan di mana inspeksi TLS dilarang.",
-    "riskBannerDismiss": "Tutup",
-    "serverCardTitle": "Server AgentBridge",
-    "statusRunning": "Berjalan",
-    "statusStopped": "Dihentikan",
-    "statusActive": "Aktif",
-    "statusDnsOff": "DNS nonaktif",
-    "statusSetupRequired": "Penyiapan diperlukan",
-    "statusInvestigating": "Menyelidiki",
-    "serverPort": "Port",
-    "serverConns": "Koneksi",
-    "serverIntercepted": "Dicegat",
-    "serverLastStarted": "Terakhir dimulai",
-    "startServer": "Mulai",
-    "stopServer": "Hentikan",
-    "restartServer": "Mulai Ulang",
-    "trustCert": "Percayai Sertifikat",
-    "downloadCert": "Unduh Sertifikat",
-    "certManualTitle": "Sertifikat tidak dapat dipasang secara otomatis (mis. di dalam kontainer). Bridge masih dapat berjalan — percayai CA secara manual:",
-    "regenerateCert": "Buat Ulang Sertifikat",
-    "starting": "Memulai…",
-    "stopping": "Menghentikan…",
-    "restarting": "Memulai ulang…",
-    "trusting": "Mempercayai…",
-    "regenerating": "Membuat ulang…",
-    "upstreamCaLabel": "Sertifikat CA Upstream (korporat)",
-    "upstreamCaPlaceholder": "/etc/ssl/certs/corp-ca.pem",
-    "upstreamCaTest": "Uji TLS",
-    "upstreamCaTestOk": "Uji TLS berhasil",
-    "upstreamCaTestError": "Uji TLS gagal — periksa jalur dan berkas CA",
-    "bypassSectionTitle": "Daftar Bypass",
-    "bypassSectionDesc": "Host yang cocok dengan pola ini ditunnel secara langsung (tanpa dekripsi TLS). Default mencakup banks.gov, dan SSO korporat.",
-    "bypassDefaultsLabel": "Pola bypass default (hanya-baca)",
-    "bypassUserLabel": "Pola bypass kustom (satu per baris, glob atau regex)",
-    "saveBypassList": "Simpan daftar bypass",
-    "agentListTitle": "Agen IDE",
-    "filterAll": "Semua",
-    "filterActive": "Aktif",
-    "filterSetupRequired": "Penyiapan diperlukan",
-    "filterInvestigating": "Menyelidiki",
-    "searchAgents": "Cari agen…",
-    "noAgentsMatch": "Tidak ada agen yang cocok dengan filter saat ini",
-    "agentHosts": "Host yang dicegat",
-    "certTrusted": "Sertifikat tepercaya",
-    "certNotTrusted": "Sertifikat tidak tepercaya",
-    "investigatingNotice": "Agen ini sedang dalam penyelidikan. Host dan permukaan API masih dikonfirmasi. Penyiapan akan tersedia setelah API upstream didokumentasikan.",
-    "modelMappingsLabel": "Pemetaan model",
-    "sourceModel": "Model sumber (asli agen)",
-    "targetModel": "Model target (OmniRoute)",
-    "noMappings": "Tidak ada pemetaan model yang dikonfigurasi. Jalankan wisaya penyiapan untuk mendeteksi model secara otomatis.",
-    "noMappingsDesc": "Belum ada pemetaan model yang dikonfigurasi. Tambahkan pemetaan untuk mengarahkan permintaan agen melalui OmniRoute.",
-    "addMapping": "Tambahkan pemetaan",
-    "selectModel": "Pilih…",
-    "saveMappings": "Simpan pemetaan",
-    "setupWizard": "Wisaya penyiapan",
-    "startDns": "Mulai DNS",
-    "stopDns": "Hentikan DNS",
-    "toggling": "Mengalihkan…",
-    "viewTraffic": "Lihat lalu lintas",
-    "emptyNoProvidersTitle": "Belum ada penyedia yang dikonfigurasi",
-    "emptyNoProvidersBody": "Untuk menggunakan AgentBridge, hubungkan setidaknya satu penyedia terlebih dahulu. Ini akan menjadi tujuan rute permintaan IDE.",
-    "emptyGoToProviders": "Buka Penyedia",
-    "wizardTitle": "Wisaya penyiapan",
-    "wizardSubtitle": "Penyiapan 3 langkah",
-    "wizardStep1Label": "Verifikasi",
-    "wizardStep2Label": "DNS",
-    "wizardStep3Label": "Pemetaan",
-    "wizardStep1Desc": "Konfirmasikan bahwa server sedang berjalan dan sertifikat telah terpasang.",
-    "wizardStep2Desc": "Entri berikut akan ditambahkan ke /etc/hosts untuk mengalihkan lalu lintas melalui AgentBridge:",
-    "wizardStep3Desc": "Sekarang Anda dapat mengonfigurasi pemetaan model di kartu agen. Mulai ulang IDE untuk menerapkan perubahan.",
-    "wizardStep3Success": "Agen telah dikonfigurasi!",
-    "wizardServerCheck": "Server AgentBridge",
-    "wizardRunning": "berjalan",
-    "wizardNotRunning": "tidak berjalan",
-    "wizardCertCheck": "Sertifikat",
-    "wizardTrusted": "tepercaya",
-    "wizardNotTrusted": "belum tepercaya — gunakan tombol Trust Cert",
-    "wizardTutorialTitle": "Petunjuk penyiapan:",
-    "wizardEnableDns": "Tambahkan entri /etc/hosts",
-    "wizardDnsAlreadyEnabled": "DNS sudah diaktifkan untuk agen ini",
-    "enablingDns": "Mengaktifkan…",
-    "modelSelectorTitle": "Pilih model target",
-    "modelSelectorSearch": "Cari model…",
-    "noModelsFound": "Model tidak ditemukan",
-    "quickLinks": "Pranala cepat",
-    "quickLinkProviders": "Konfigurasikan penyedia",
-    "quickLinkInspector": "Lihat lalu lintas di Inspektur Lalu Lintas",
-    "unknownError": "Kesalahan tidak dikenal",
-    "maintenanceTitle": "Pemeliharaan & Diagnostik",
-    "maintenanceSubtitle": "Uji mandiri pipeline penangkapan, batalkan status sistem yang tersisa, dan pindahkan pengaturan Anda antar mesin.",
-    "orphanedStateWarning": "Sesi sebelumnya meninggalkan sisa status sistem (spoof DNS, CA, atau proksi sistem). Jalankan Perbaikan untuk membersihkannya.",
-    "diagnose": "Diagnosis",
-    "diagnosing": "Mendiagnosis…",
-    "diagnoseHealthy": "Pipeline penangkapan dalam kondisi sehat.",
-    "diagnoseUnhealthy": "Pipeline penangkapan mengalami masalah:",
-    "repair": "Perbaiki",
-    "repairing": "Memperbaiki…",
-    "repairDone": "Diperbaiki: {items}",
-    "repairNothing": "Tidak ada yang perlu diperbaiki — status sistem bersih.",
-    "removeCa": "Hapus CA",
-    "removeCaConfirm": "Hapus CA?",
-    "removeCaDone": "CA root MITM telah dihapus dari penyimpanan kepercayaan OS.",
-    "removing": "Menghapus…",
-    "confirm": "Konfirmasi",
-    "exportConfig": "Ekspor konfigurasi",
-    "exporting": "Mengekspor…",
-    "importConfig": "Impor konfigurasi",
-    "importing": "Mengimpor…",
-    "importInvalidJson": "Berkas yang dipilih bukan JSON yang valid.",
-    "importDone": "Berhasil mengimpor {bypass} bypass · {hosts} host · {agents} agen",
-    "save": "Simpan",
-    "saving": "Menyimpan…",
-    "cancel": "Batal",
-    "back": "Kembali",
-    "next": "Berikutnya",
-    "done": "Selesai",
-    "loading": "Memuat…",
-    "riskNoticeTitle": "Pengakuan risiko",
-    "riskNoticeBody": "AgentBridge akan mencegat lalu lintas HTTPS dari agen ini dengan mengalihkan host API-nya melalui DNS. Hanya aktifkan jika Anda menerima tanggung jawab atas kepatuhan terhadap ketentuan layanan agen dan kebijakan jaringan apa pun yang berlaku.",
-    "pageMoved": {
-      "goNow": "Pergi sekarang",
-      "message": "Proksi MITM sekarang berada di bawah AgentBridge.",
-      "title": "Halaman ini telah berpindah"
-    }
-  },
-  "providerStats": {
-    "unknownError": "Galat tidak dikenal",
-    "loading": "Memuat statistik penyedia...",
-    "loadFailed": "Gagal memuat statistik penyedia: {error}",
-    "retry": "Coba Lagi",
-    "updated": "Diperbarui {time}",
-    "refresh": "Segarkan",
-    "totalRequests": "Total Permintaan",
-    "avgLatency": "Latensi Rata-rata",
-    "successRate": "Tingkat Keberhasilan",
-    "activeProviders": "Penyedia Aktif",
-    "providerBreakdown": "Rincian Penyedia",
-    "providerCount": "{count} penyedia",
-    "provider": "Penyedia",
-    "requests": "Permintaan",
-    "success": "Berhasil",
-    "rate": "Tingkat",
-    "tokensIn": "Token Masuk",
-    "tokensOut": "Token Keluar",
-    "ttftAfterTool": "TTFT Setelah Alat",
-    "gapAfterTool": "Jeda Setelah Alat",
-    "model": "Model",
-    "noProviderData": "Belum ada data penyedia yang tercatat.",
-    "comboMetrics": "Metrik Kombo",
-    "comboMetricsDescription": "Latensi dan throughput per kombo dari streaming",
-    "avgTtft": "TTFT Rata-rata",
-    "avgTotal": "Total Rata-rata",
-    "requestTelemetry": "Telemetri Permintaan",
-    "requestTelemetryDescription": "Rincian pipeline 7 fase (5 menit terakhir)"
-  },
-  "relay": {
-    "title": "Proksi Relai Tanpa Server",
-    "description": "Buat titik akhir API publik yang memproksi ke OmniRoute dengan pembatasan laju dan kontrol akses",
-    "created": "Token relai dibuat",
-    "createFailed": "Gagal membuat token",
-    "toggleFailed": "Gagal mengalihkan token",
-    "deleteConfirm": "Hapus token relai ini? Tindakan ini tidak dapat dibatalkan.",
-    "deleted": "Token dihapus",
-    "deleteFailed": "Gagal menghapus token",
-    "cancel": "Batal",
-    "newToken": "Token Relai Baru",
-    "createTitle": "Buat Token Relai",
-    "nameRequired": "Nama *",
-    "tokenDescription": "Deskripsi",
-    "descriptionPlaceholder": "Untuk fungsi serverless saya",
-    "maxPerMinute": "Permintaan Maks/Menit",
-    "maxPerDay": "Permintaan Maks/Hari",
-    "createButton": "Buat Token",
-    "createdTitle": "Token Dibuat — Salin sekarang!",
-    "tokenFor": "Token untuk <strong>{name}</strong>:",
-    "shownOnce": "Token ini tidak akan ditampilkan lagi. Simpan dengan aman.",
-    "dismiss": "Tutup",
-    "usage": "Penggunaan",
-    "usageDescription": "Kirim permintaan ke endpoint relai Anda:",
-    "tokenCount": "Token Relai ({count})",
-    "loading": "Memuat...",
-    "empty": "Tidak ada token relai yang dikonfigurasi. Buat satu untuk memulai.",
-    "disable": "Nonaktifkan",
-    "enable": "Aktifkan",
-    "delete": "Hapus"
-  },
-  "trafficInspector": {
-    "title": "Pemeriksa Lalu Lintas",
-    "subtitle": "Pantau panggilan LLM dan debug lalu lintas HTTPS aplikasi apa pun",
-    "captureModesTitle": "Mode Penangkapan",
-    "agentBridgeMode": "AgentBridge",
-    "agentBridgeModeDesc": "Tangkap lalu lintas dari semua agen IDE yang terhubung",
-    "customHostsMode": "Host Kustom",
-    "customHostsModeDesc": "Tambahkan host tertentu untuk dicegat",
-    "httpProxyMode": "Proksi HTTP",
-    "httpProxyModeDesc": "Gunakan variabel lingkungan HTTP_PROXY",
-    "systemWideMode": "Seluruh sistem",
-    "systemWideModeDesc": "Cegat semua lalu lintas sistem (tingkat lanjut)",
-    "tproxyMode": "Dekripsi TPROXY",
-    "tproxyModeUnavailable": "Dekripsi TPROXY memerlukan Linux + root + addon bawaan",
-    "filterBarTitle": "Filter",
-    "profileLlmOnly": "Hanya LLM",
-    "profileCustom": "Kustom",
-    "profileAll": "Semua",
-    "filterHost": "Filter host…",
-    "filterAgent": "Agen",
-    "filterStatus": "Status",
-    "pauseBtn": "Jeda",
-    "resumeBtn": "Lanjutkan",
-    "clearBtn": "Bersihkan",
-    "exportHar": "Ekspor .har",
-    "recordSession": "REC",
-    "stopSession": "Hentikan",
-    "liveBadge": "langsung",
-    "offlineBadge": "luring",
-    "noRequests": "Belum ada permintaan yang ditangkap.",
-    "noRequestsDesc": "Pastikan AgentBridge sedang berjalan atau aktifkan mode penangkapan lain.",
-    "selectRequest": "Pilih permintaan untuk memeriksanya.",
-    "tabConversation": "Percakapan",
-    "tabHeaders": "Header",
-    "tabRequest": "Permintaan",
-    "tabResponse": "Respons",
-    "tabTiming": "Waktu",
-    "tabLlm": "LLM",
-    "tabStats": "Statistik",
-    "requestHeaders": "Header Permintaan",
-    "responseHeaders": "Header Respons",
-    "rawEvents": "Event mentah",
-    "mergedView": "Tampilan gabungan",
-    "noBody": "Tidak ada body.",
-    "streaming": "streaming…",
-    "manageHosts": "Kelola host",
-    "copySnippet": "Salin cuplikan proksi",
-    "addHost": "Tambah",
-    "hostPlaceholder": "api.openai.com",
-    "noHostsYet": "Belum ada host kustom yang ditambahkan.",
-    "noSessionsYet": "Belum ada sesi",
-    "allTraffic": "Semua lalu lintas (tanpa sesi)",
-    "sessionsDropdown": "Sesi",
-    "annotationPlaceholder": "Tambah catatan…",
-    "contextFingerprint": "Sidik jari konteks",
-    "llmProvider": "Penyedia yang terdeteksi",
-    "llmApiKind": "Jenis API",
-    "llmModel": "Model",
-    "llmMessages": "Pesan",
-    "llmStream": "Stream",
-    "llmMappedTo": "Dipetakan ke",
-    "llmCostEstimate": "Estimasi biaya",
-    "systemProxyExitWarning": "Proksi seluruh sistem masih aktif — tetap tinggalkan halaman?",
-    "customHostsTitle": "Host Kustom",
-    "loading": "Memuat…",
-    "copied": "Tersalin!",
-    "copy": "Salin",
-    "httpProxyTitle": "Cuplikan Proksi HTTP — port {port}",
-    "notRecording": "Tidak merekam",
-    "anyStatus": "Status apa pun",
-    "liveOnly": "Langsung",
-    "viewingRecordedSession": "Melihat sesi yang direkam",
-    "backToLive": "Kembali ke langsung",
-    "untitledSession": "Sesi tanpa judul",
-    "contextHistory": "Riwayat Konteks",
-    "modelResponse": "Respons Model",
-    "conversationNoMessages": "Tidak ada pesan yang ditemukan dalam permintaan ini.",
-    "conversationNotAvailable": "Data percakapan tidak tersedia. Ini mungkin bukan permintaan LLM atau body tidak dapat diurai.",
-    "loadingCharts": "Memuat grafik…",
-    "statsErrors": "Kesalahan",
-    "statsLatency": "Latensi (50 permintaan terakhir)",
-    "statsNoData": "Belum ada permintaan. Mulai perekaman sesi untuk menangkap data statistik.",
-    "statsStatusDistribution": "Distribusi status",
-    "statsSuccessful": "Berhasil",
-    "statsTotalRequests": "Total permintaan",
-    "timingProxyOverhead": "Overhead proksi",
-    "timingUpstreamResponse": "Respons upstream",
-    "timingNoData": "Tidak ada data waktu yang tersedia.",
-    "timingTotalLatency": "Total latensi",
-    "timingTimestamp": "Stempel waktu",
-    "timingMethod": "Metode",
-    "timingStatus": "Status",
-    "timingRequestSize": "Ukuran permintaan",
-    "timingResponseSize": "Ukuran respons",
-    "pausedNewBadge": "{count} baru",
-    "clearContextFilter": "bersihkan",
-    "invalidHostname": "Nama host tidak valid",
-    "invalidHost": "Host tidak valid",
-    "addHostFailed": "Gagal menambahkan host",
-    "networkError": "Kesalahan jaringan",
-    "close": "Tutup",
-    "removeHost": "Hapus {host}",
-    "requestDetails": "Detail permintaan",
-    "filterByContext": "Filter berdasarkan konteks ini",
-    "filteringContext": "Penyaringan: konteks {context}",
-    "clear": "bersihkan",
-    "trafficProfile": "Profil lalu lintas",
-    "roleSystem": "Sistem",
-    "roleUser": "Pengguna",
-    "roleAssistant": "Asisten",
-    "roleTool": "Alat",
-    "expand": "Perluas",
-    "collapse": "Ciutkan",
-    "systemPromptHidden": "Prompt sistem disembunyikan — klik untuk memperluas",
-    "sessionName": "Sesi {id}",
-    "sessions": "Sesi",
-    "requestCountShort": "{count} permintaan",
-    "deleteSession": "Hapus sesi",
-    "saving": "Menyimpan…",
-    "sensitiveHeaders": "Header sensitif",
-    "show": "Tampilkan",
-    "hide": "Sembunyikan",
-    "name": "Nama",
-    "value": "Nilai",
-    "noSseEvents": "Tidak ada event SSE",
-    "noRequestBody": "Tidak ada body permintaan.",
-    "noResponseBody": "Tidak ada body respons.",
-    "formatted": "Diformat",
-    "raw": "Mentah"
-  },
-  "cliCommon": {
-    "concept": {
-      "code": {
-        "title": "Kode CLI",
-        "phrase": "Alat kode yang Anda arahkan ke OmniRoute",
-        "flow": "Anda → Kode CLI → OmniRoute → Penyedia",
-        "seeOther": "Lihat →"
-      },
-      "agent": {
-        "title": "Agen CLI",
-        "phrase": "Agen CLI otonom serbaguna yang Anda arahkan ke OmniRoute",
-        "flow": "Anda → Agen CLI → OmniRoute → Penyedia",
-        "seeOther": "Lihat →"
-      },
-      "acp": {
-        "title": "Agen ACP",
-        "phrase": "CLI yang dijalankan OmniRoute sebagai backend eksekusi (alur balik)",
-        "warning": "Most users can ignore this — use only when an integration requires it.",
-        "flow": "Klien → OmniRoute → jalankan CLI (stdio/ACP) → respons",
-        "seeOther": "Lihat →"
-      }
-    },
-    "comparison": {
-      "title": "Pahami 3 tipe CLI di OmniRoute",
-      "thisPage": "Halaman ini",
-      "open": "Buka →",
-      "code": {
-        "title": "Alat kode",
-        "desc": "Mengarah ke Omni",
-        "flow": "Anda → CLI → Omni → penyedia",
-        "examples": "misal: claude, codex"
-      },
-      "agent": {
-        "title": "Agen otonom luas",
-        "desc": "Mengarah ke Omni",
-        "flow": "Anda → agen → Omni",
-        "examples": "misal: hermes, goose"
-      },
-      "acp": {
-        "title": "CLI digunakan sebagai backend oleh Omni",
-        "desc": "Eksekusi terbalik",
-        "flow": "Omni → spawn CLI → resp",
-        "examples": "misal: claude, codex (ACP)"
-      }
-    },
-    "card": {
-      "detected": "Terdeteksi",
-      "notDetected": "Tidak terdeteksi",
-      "configured": "Dikonfigurasi",
-      "notConfigured": "Belum dikonfigurasi",
-      "configure": "Konfigurasi →",
-      "howToInstall": "Cara menginstal →",
-      "versionNotFound": "tidak ditemukan",
-      "manualConfig": "Konfigurasi manual",
-      "installGuide": "Panduan instalasi",
-      "endpointLabel": "Endpoint",
-      "baseUrlFull": "URL Dasar Lengkap",
-      "baseUrlPartial": "URL Dasar Sebagian",
-      "refreshDetection": "Segarkan deteksi",
-      "alsoAcp": "juga ACP",
-      "connectProviderHint": "Hubungkan penyedia di Penyedia"
-    },
-    "detail": {
-      "back": "Kembali",
-      "apply": "Simpan",
-      "reset": "Bersihkan",
-      "manualConfig": "Konfigurasi manual",
-      "vendor": "Vendor",
-      "category": "Tipe",
-      "detectionStatus": "Deteksi",
-      "configStatus": "Konfigurasi",
-      "baseUrlLabel": "URL Dasar",
-      "apiKeyLabel": "Kunci API",
-      "modelMappingLabel": "Pemetaan model",
-      "noActiveProviders": "Tidak ada penyedia aktif.",
-      "noActiveProvidersDesc": "Buka Penyedia untuk menghubungkan minimal 1 penyedia sebelum mengonfigurasi CLI.",
-      "openProviders": "Buka Penyedia →"
-    }
-  },
-  "cliCode": {
-    "pageTitle": "Kode CLI",
-    "pageSubtitle": "Alat kode yang mengarah ke OmniRoute",
-    "searchPlaceholder": "Cari CLI…",
-    "filterDetectionLabel": "Deteksi",
-    "filterBaseUrlLabel": "URL Dasar",
-    "detectionAll": "Semua",
-    "detectionInstalled": "Terinstal",
-    "detectionNotFound": "Tidak ditemukan",
-    "baseUrlAll": "Semua",
-    "baseUrlFull": "Penuh",
-    "baseUrlPartial": "Sebagian"
-  },
-  "cliAgents": {
-    "pageTitle": "Agen CLI",
-    "pageSubtitle": "Agen CLI otonom serbaguna",
-    "refreshDetection": "Segarkan deteksi",
-    "searchPlaceholder": "Cari agen…",
-    "detectionFilterLabel": "Deteksi",
-    "detectionAll": "Semua",
-    "detectionInstalled": "Terinstal",
-    "detectionNotInstalled": "Tidak terinstal",
-    "visibleCount": "{count} terlihat",
-    "emptyState": "Tidak ada agen CLI yang ditemukan dengan filter saat ini."
-  },
-  "acpAgents": {
-    "pageTitle": "Agen ACP",
-    "pageSubtitle": "CLI yang dijalankan OmniRoute sebagai backend eksekusi",
-    "scanning": "Mendeteksi agen…",
-    "refresh": "Segarkan",
-    "setupGuideTitle": "Panduan penyiapan",
-    "setupGuideDetectCliTitle": "Deteksi CLI",
-    "setupGuideDetectCliDesc": "Agen diidentifikasi dengan menjalankan perintah --version di PATH.",
-    "setupGuideCustomAgentTitle": "Tambah agen kustom",
-    "setupGuideCustomAgentDesc": "Isi formulir di bawah ini untuk mendaftarkan agen CLI kustom.",
-    "setupGuideCommandMissingTitle": "Perintah tidak ditemukan",
-    "setupGuideCommandMissingDesc": "Periksa apakah biner ada di PATH.",
-    "fingerprintSettingsHint": "Konfigurasikan perutean dan sidik jari di",
-    "settingsRoutingLink": "Pengaturan → Perutean",
-    "installed": "Terinstal",
-    "notFound": "Tidak ditemukan",
-    "builtIn": "Bawaan",
-    "custom": "Kustom",
-    "agentUseCaseHint": "Tersedia untuk dijalankan via ACP.",
-    "remove": "Hapus",
-    "addCustomAgent": "Tambah agen kustom",
-    "addCustomAgentDesc": "Daftarkan agen CLI kustom untuk dijalankan via ACP.",
-    "addAgent": "Tambah agen",
-    "agentName": "Nama",
-    "agentNamePlaceholder": "misal: Agen Saya",
-    "binaryName": "Biner",
-    "binaryNamePlaceholder": "misal: myagent",
-    "versionCommand": "Perintah versi",
-    "versionCommandPlaceholder": "misal: myagent --version",
-    "spawnArgs": "Argumen spawn",
-    "spawnArgsPlaceholder": "misal: --quiet, --json",
-    "cliCodeRedirectCta": "Buka Kode CLI"
-  },
-  "agentSkills": {
-    "catalog": {
-      "omni-auth": {
-        "name": "Autentikasi",
-        "description": "Kelola autentikasi kunci API dan token sesi. Mulai di sini untuk mengautentikasi permintaan via token Bearer, mendapatkan kuki sesi, dan mengonfigurasi persyaratan masuk untuk API OmniRoute."
-      },
-      "omni-providers": {
-        "name": "Penyedia",
-        "description": "Kelola koneksi penyedia, kunci API, alur OAuth, dan pengujian koneksi via REST API. Cantumkan, tambah, perbarui, hapus, dan uji integrasi penyedia AI (OpenAI, Anthropic, Gemini, dan 160+)."
-      },
-      "omni-models": {
-        "name": "Model",
-        "description": "Kueri model AI yang tersedia di semua penyedia yang dikonfigurasi. Cantumkan model, selesaikan alias model, dan telusuri katalog model lengkap termasuk varian khusus penyedia."
-      },
-      "omni-combos-routing": {
-        "name": "Kombo & Perutean",
-        "description": "Buat dan kelola kombo perutean dengan 14 strategi (prioritas, berbobot, round-robin, Auto-combo, dll.). Konfigurasikan rantai fallback, uji hasil perutean, dan dapatkan metrik kombo."
-      },
-      "omni-api-keys": {
-        "name": "Kunci API",
-        "description": "Buat, cantumkan, putar, dan cabut kunci API OmniRoute. Kontrol cakupan per kunci, batas pengeluaran, dan kedaluwarsa. Kunci mengontrol akses ke semua titik akhir proksi dan manajemen."
-      },
-      "omni-usage-logs": {
-        "name": "Penggunaan & Log",
-        "description": "Akses log panggilan terperinci dan analitik penggunaan. Filter berdasarkan penyedia, model, rentang waktu, status, dan biaya. Ekspor log dan agregasikan penggunaan token di semua koneksi."
-      },
-      "omni-budget": {
-        "name": "Anggaran & Batas Tarif",
-        "description": "Konfigurasikan batas pengeluaran, kuota token, dan kebijakan batas tarif per kunci API atau secara global. Periksa konsumsi saat ini dan terapkan kontrol biaya di seluruh penyedia."
-      },
-      "omni-settings": {
-        "name": "Pengaturan",
-        "description": "Baca dan perbarui pengaturan aplikasi global: perintah sistem, anggaran berpikir, filter IP, aturan muatan, default kombo, dan konfigurasi wajib-masuk."
-      },
-      "omni-proxies": {
-        "name": "Konfigurasi Proksi",
-        "description": "Konfigurasikan proksi HTTP/HTTPS/SOCKS untuk permintaan penyedia hulu. Atur aturan proksi per penyedia atau global, uji konektivitas, dan kelola rotasi proksi."
-      },
-      "omni-cache": {
-        "name": "Tembolok",
-        "description": "Kelola tembolok respons LLM. Lihat statistik tembolok, hapus entri, konfigurasikan kebijakan TTL, dan kontrol ambang batas penembolokan kemiripan semantik."
-      },
-      "omni-compression": {
-        "name": "Kompresi",
-        "description": "Konfigurasikan mode kompresi RTK (output perintah), Caveman (prosa), dan bertumpuk. Kelola paket bahasa, aturan kustom, dan uji kompresi prompt yang mengurangi token sebesar 60–90%."
-      },
-      "omni-context-rtk": {
-        "name": "Konteks & RTK",
-        "description": "Konfigurasikan filter RTK, aturan rekayasa konteks, dan pengaturan relai konteks. Uji kompresi dengan sampel prompt nyata dan kelola alur transformasi konteks."
-      },
-      "omni-resilience": {
-        "name": "Ketahanan & Pemantauan",
-        "description": "Pantau kesehatan penyedia, status pemutus sirkuit, metrik latensi p50/p95/p99, dan peringatan penjaga anggaran. Periksa waktu tunggu koneksi dan penguncian model secara real-time."
-      },
-      "omni-cli-tools": {
-        "name": "Alat CLI",
-        "description": "Kelola integrasi perkakas CLI yang diekspos via API. Daftarkan, konfigurasikan, dan panggil plugin perkakas CLI yang memperluas permukaan otomatisasi OmniRoute."
-      },
-      "omni-tunnels": {
-        "name": "Tunnel",
-        "description": "Buat dan kelola tunnel aman (ngrok, Cloudflare Tunnel, kustom) untuk mengekspos OmniRoute ke internet atau berbagi akses dengan agen jarak jauh dan pipeline CI."
-      },
-      "omni-sync-cloud": {
-        "name": "Sinkronisasi Cloud",
-        "description": "Sinkronisasikan konfigurasi OmniRoute, koneksi penyedia, dan pengaturan ke/dari penyimpanan awan. Kelola autentikasi cloud worker dan target pencadangan jarak jauh."
-      },
-      "omni-db-backups": {
-        "name": "Basis Data & Cadangan",
-        "description": "Picu pencadangan sistem, pulihkan dari berkas cadangan, dan kelola siklus hidup basis data SQLite. Mendukung strategi ekspor, impor, dan snapshot inkremental."
-      },
-      "omni-webhooks": {
-        "name": "Webhook",
-        "description": "__MISSING__:Register, list, test, and remove webhook endpoints. Configure event subscriptions (request.completed, request.failed, quota.exceeded, etc.) and manage delivery retries."
-      },
-      "omni-mcp": {
-        "name": "Server MCP",
-        "description": "Hubungkan ke server MCP OmniRoute (110 perkakas, 3 transport: SSE/stdio/HTTP). Mencakup perutean, cache, kompresi, memori, keahlian, penyedia, dan perkakas audit di 33 cakupan izin."
-      },
-      "omni-agents-a2a": {
-        "name": "Agen & Protokol A2A",
-        "description": "Berinteraksi dengan OmniRoute via protokol agen-ke-agen JSON-RPC 2.0. 6 keahlian A2A bawaan: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities."
-      },
-      "omni-version-manager": {
-        "name": "Pengelola Versi",
-        "description": "Instal, mulai, hentikan, mulai ulang, dan perbarui layanan tertanam (9Router, CLIProxyAPI). Pantau status layanan, ambil log, dan konfigurasikan mulai-otomatis untuk endpoint layanan khusus lokal."
-      },
-      "omni-inference": {
-        "name": "Inferensi (Kompatibel dengan OpenAI)",
-        "description": "Endpoint inferensi inti yang kompatibel dengan OpenAI: penyelesaian obrolan, penyematan (embeddings), gambar, audio (TTS/STT), moderasi, pemeringkatan ulang (rerank), dan Responses API. Permukaan integrasi utama untuk agen AI."
-      },
-      "cli-serve": {
-        "name": "CLI: Serve",
-        "description": "Mulai, hentikan, dan mulai ulang server OmniRoute dari CLI. Kelola mode daemon, konfigurasi port, pemulihan otomatis, integrasi baki sistem, dan pintasan pembukaan dasbor."
-      },
-      "cli-health": {
-        "name": "CLI: Health",
-        "description": "Periksa kesehatan server, status komponen, dan metrik langsung dari CLI. Jalankan `health`, `health components`, dan `health watch` untuk dasbor waktu nyata dari pemutus sirkuit dan status penyedia."
-      },
-      "cli-providers": {
-        "name": "CLI: Penyedia",
-        "description": "Kelola koneksi penyedia dari CLI: tampilkan daftar penyedia yang tersedia/dikonfigurasi, tambah, uji, uji-semua, validasi, putar kunci API, dan lihat metrik per penyedia."
-      },
-      "cli-keys": {
-        "name": "CLI: Kunci API",
-        "description": "Buat, tampilkan daftar, putar, dan cabut kunci API OmniRoute dari CLI. Kelola alur OAuth untuk autentikasi penyedia dan periksa cakupan serta kedaluwarsa kunci."
-      },
-      "cli-models": {
-        "name": "CLI: Model",
-        "description": "Kueri model AI yang tersedia, tampilkan daftar alias model, dan telusuri katalog model lengkap dari CLI. Filter berdasarkan penyedia, cari berdasarkan kemampuan, dan selesaikan varian nama model."
-      },
-      "cli-chat": {
-        "name": "CLI: Obrolan",
-        "description": "Kirim penyelesaian obrolan, alirkan respons, dan mulai sesi REPL interaktif dari CLI. Mendukung semua penyedia OmniRoute, perutean kombo, dan konfigurasi perintah sistem."
-      },
-      "cli-routing": {
-        "name": "CLI: Perutean & Kombo",
-        "description": "Buat, tampilkan daftar, perbarui, dan hapus kombo perutean dari CLI. Uji strategi perutean, periksa metrik kombo, dan konfigurasikan rantai fallback secara interaktif."
-      },
-      "cli-resilience": {
-        "name": "CLI: Ketahanan & Kuota",
-        "description": "Periksa dan kelola status pemutus sirkuit, waktu tunggu koneksi, batas kuota, dan tingkat backoff dari CLI. Setel ulang penyedia yang macet dan konfigurasikan ambang batas ketahanan."
-      },
-      "cli-compression": {
-        "name": "CLI: Kompresi",
-        "description": "Konfigurasikan dan uji kompresi perintah dari CLI. Kelola filter RTK, aturan Caveman, mode kompresi bertumpuk, dan pratinjau output kompresi dengan perintah nyata."
-      },
-      "cli-contexts": {
-        "name": "CLI: Konteks & Sesi",
-        "description": "Kelola konfigurasi rekayasa konteks, set filter RTK, dan sesi percakapan dari CLI. Terapkan pengaturan relai konteks dan periksa alur konteks aktif."
-      },
-      "cli-cost-usage": {
-        "name": "CLI: Biaya & Penggunaan",
-        "description": "Lihat rincian biaya, penggunaan token, dan log panggilan dari CLI. Filter berdasarkan penyedia, model, atau rentang tanggal. Ekspor laporan penggunaan dan periksa pengeluaran per koneksi."
-      },
-      "cli-mcp": {
-        "name": "CLI: MCP",
-        "description": "Periksa status server MCP, buat daftar alat dan cakupan terdaftar, jalankan pemanggilan alat, dan kelola log audit MCP dari CLI."
-      },
-      "cli-a2a": {
-        "name": "CLI: Protokol A2A",
-        "description": "Berinteraksi dengan server OmniRoute A2A dari CLI. Kirim tugas, periksa riwayat eksekusi skill, dan uji protokol agent-to-agent JSON-RPC 2.0 secara interaktif."
-      },
-      "cli-tunnel": {
-        "name": "CLI: Tunnel",
-        "description": "Mulai dan hentikan koneksi tunnel (ngrok, Cloudflare, kustom) dari CLI. Periksa URL tunnel aktif, konfigurasikan autentikasi, dan uji keterjangkauan eksternal."
-      },
-      "cli-backup-sync": {
-        "name": "CLI: Pencadangan & Sinkronisasi",
-        "description": "Cadangkan dan pulihkan data OmniRoute dari CLI. Picu snapshot inkremental, sinkronkan ke penyimpanan cloud, kelola jadwal pencadangan, dan pulihkan dari file arsip."
-      },
-      "cli-policy-audit": {
-        "name": "CLI: Kebijakan & Audit",
-        "description": "Periksa log audit, kelola kebijakan akses, lihat data telemetri, dan tinjau riwayat permintaan dari CLI. Filter berdasarkan jenis peristiwa, pengguna, atau rentang waktu untuk alur kerja kepatuhan."
-      },
-      "cli-batches": {
-        "name": "CLI: Batch & File",
-        "description": "Kirim dan pantau tugas inferensi batch dari CLI. Unggah dan kelola file untuk pemrosesan batch, ambil hasil, dan integrasikan pipeline batch dengan alur kerja CI/CD."
-      },
-      "cli-eval": {
-        "name": "CLI: Evaluasi",
-        "description": "Buat dan jalankan rangkaian evaluasi, pantau progres tolok ukur langsung, lihat kartu skor, bandingkan performa model, dan integrasikan eksekusi evaluasi dengan alur kerja CI dari CLI."
-      },
-      "cli-plugins-skills": {
-        "name": "CLI: Plugin, Skill & Memori",
-        "description": "Kelola Omni Skills (daftar, instal, uji, hapus), plugin (buat, konfigurasikan), dan memori persisten (cari, tambah, bersihkan) dari CLI."
-      },
-      "cli-setup": {
-        "name": "CLI: Penyiapan & Konfigurasi",
-        "description": "Jalankan penyiapan awal, konfigurasikan pengaturan CLI global, kelola variabel lingkungan, periksa pembaruan, dan konfigurasikan autostart melalui perintah setup dan config CLI."
-      },
-      "cli-skill-collector": {
-        "name": "CLI: Pengumpul Agent Skill",
-        "description": "Deteksi alat pengodean CLI yang terinstal (Claude Code, Codex, Cursor, Copilot, Cline, dan lainnya), cari skill agen yang cocok di GitHub, dan instal ke alat yang terdeteksi melalui API bawaan OmniRoute."
-      },
-      "config-codex-cli": {
-        "name": "Konfigurasi: Codex CLI",
-        "description": "Alur kerja agen langkah demi langkah untuk mengonfigurasi OpenAI Codex CLI di mesin apa pun (Linux, macOS, Windows) agar menggunakan OmniRoute sebagai backend yang kompatibel dengan OpenAI. Mendeteksi OS dan shell, menulis config.toml dan 7 profil bernama, menyetel variabel lingkungan, serta memverifikasi penyiapan."
-      },
-      "omni-github-skills": {
-        "name": "Penemuan Skill GitHub",
-        "description": "Cari, beri skor, pindai, dan impor skill agen dari repositori GitHub yang berisi SKILL.md, CLAUDE.md, .cursorrules, dan file skill agen serupa. Temukan skill komunitas di 160+ kategori penyedia, evaluasi relevansi dengan penilaian heuristik, periksa malware atau rahasia yang di-hardcode, dan instal ke direktori agen Hermes, Claude Code, Gemini CLI, atau OpenCode."
-      }
-    },
-    "pageTitle": "Agent Skills",
-    "pageSubtitle": "Ajari agen Anda untuk mengoperasikan OmniRoute — 23 area API + 21 kelompok CLI",
-    "conceptCard": {
-      "agent": {
-        "title": "Agent Skills — Outbound",
-        "description": "Agent Skills adalah dokumen SKILL.md yang dapat dibaca mesin yang diambil oleh agen AI eksternal (Claude Code, Cursor, Copilot…) dari GitHub untuk mempelajari cara mengoperasikan OmniRoute melalui REST atau CLI. Dokumen ini dibaca oleh agen, bukan dieksekusi oleh OmniRoute.",
-        "crossLinkLabel": "Pahami perbedaannya →"
-      },
-      "omni": {
-        "title": "Omni Skills — Inbound",
-        "description": "Omni Skills adalah alat sandbox yang diinjeksikan OmniRoute ke dalam konteks model pada setiap permintaan. Alat ini dieksekusi oleh OmniRoute, bukan dibaca oleh agen.",
-        "crossLinkLabel": "Pahami perbedaannya →"
-      },
-      "comparison": {
-        "colAgent": "Agent Skills",
-        "colOmni": "Omni Skills",
-        "whatIs": {
-          "label": "Apa itu",
-          "agent": "SKILL.md yang dapat dibaca mesin yang mengajari agen eksternal untuk mengoperasikan OmniRoute",
-          "omni": "Alat yang dapat dieksekusi yang diinjeksikan OmniRoute sebagai alat ke dalam permintaan LLM"
-        },
-        "direction": {
-          "label": "Arah",
-          "agent": "Outbound — agen eksternal belajar mengontrol OmniRoute",
-          "omni": "Inbound — OmniRoute memberikan alat ke model yang melewatinya"
-        },
-        "executor": {
-          "label": "Eksekutor",
-          "agent": "Agen eksternal (membaca markdown → bertindak melalui API/CLI)",
-          "omni": "OmniRoute itu sendiri (mencegat tool_calls, sandbox Docker)"
-        },
-        "storage": {
-          "label": "Penyimpanan",
-          "agent": "Katalog dinamis (/api/agent-skills) → SKILL.md di GitHub",
-          "omni": "SQLite (SkillsMP / skills.sh / lokal)"
-        },
-        "tagline": {
-          "label": "Tagline",
-          "agent": "Ajari agen Anda untuk menggunakan OmniRoute",
-          "omni": "Berikan alat yang dapat dieksekusi ke model OmniRoute"
-        }
-      }
-    },
-    "filters": {
-      "category": "Kategori",
-      "area": "Area",
-      "searchPlaceholder": "Cari keahlian…"
-    },
-    "categoryApi": "API",
-    "categoryCli": "CLI",
-    "categoryConfig": "Konfigurasi",
-    "filterAll": "Semua",
-    "coverageLabel": "Cakupan",
-    "mcpUrl": "URL MCP",
-    "a2aLink": "A2A",
-    "mcpPrompt": "Tambahkan endpoint MCP ini ke agen Anda untuk memberikannya 37 alat OmniRoute.",
-    "a2aPrompt": "Daftarkan Agent Card ini dengan orchestrator Anda untuk mengaktifkan delegasi tugas A2A.",
-    "refresh": "Segarkan",
-    "copyUrl": "Salin URL",
-    "viewOnGithub": "Lihat di GitHub",
-    "previewLoading": "Memuat dokumentasi keahlian…",
-    "previewError": "Gagal memuat dokumentasi keahlian.",
-    "previewEmpty": "Pilih keahlian untuk melihat pratinjau dokumentasinya.",
-    "generateButton": "Hasilkan keahlian yang hilang",
-    "coverageBar": {
-      "complete": "Lengkap",
-      "partial": "Sebagian"
-    },
-    "noSkillsFound": "Tidak ada keahlian yang cocok dengan filter Anda.",
-    "regenerateConfirm": "Ini akan membuat ulang semua berkas SKILL.md yang hilang. Lanjutkan?",
-    "regenerateRunning": "Membuat ulang keahlian…",
-    "regenerateSuccess": "Keahlian berhasil dibuat ulang.",
-    "regenerateError": "Gagal membuat ulang keahlian."
-  },
-  "freeProviderRankingsPage": {
-    "title": "Peringkat Penyedia Gratis",
-    "subtitle": "Penyedia gratis terbaik yang diperingkatkan berdasarkan skor ELO model dari papan peringkat Arena AI",
-    "loading": "Memuat peringkat...",
-    "errorLoading": "Gagal memuat peringkat",
-    "emptyState": "Belum ada peringkat yang tersedia. Data Arena ELO disinkronkan saat startup (harian) — periksa kembali segera, atau picu sinkronisasi manual. Nonaktifkan Arena ELO Sync di Feature Flags atau atur ARENA_ELO_SYNC_ENABLED=false untuk memilih keluar.",
-    "bestModel": "Terbaik",
-    "allCategories": "Semua Kategori",
-    "categoryDefault": "Bawaan",
-    "categoryCoding": "Pengodean",
-    "categoryReview": "Peninjauan",
-    "categoryDocumentation": "Dokumentasi",
-    "categoryDebugging": "Debugging",
-    "colRank": "Peringkat",
-    "colProvider": "Penyedia",
-    "colTopModel": "Model Teratas",
-    "colScore": "Skor",
-    "colAvgScore": "Skor Rata-rata",
-    "colModels": "Model",
-    "colType": "Tipe",
-    "filterConfiguredOnly": "Hanya yang dikonfigurasi",
-    "filterAvailableOnly": "Hanya yang tersedia",
-    "filterAvailableOnlyHelp": "Sembunyikan penyedia yang semua koneksinya dibatasi laju atau kehabisan kuota.",
-    "configuredOnly": "Hanya yang Dikonfigurasi",
-    "configuredOnlyHint": "Tampilkan hanya penyedia dengan koneksi aktif",
-    "noConfiguredProviders": "Tidak ada penyedia terkonfigurasi yang ditemukan. Tambahkan koneksi penyedia terlebih dahulu.",
-    "colConfigured": "Status",
-    "typeAll": "Semua Tipe",
-    "typeNoauth": "Tanpa Pendaftaran",
-    "typeOauth": "Masuk OAuth",
-    "typeApikey": "Kunci API",
-    "sortTypeFirst": "Paling mudah terlebih dahulu",
-    "sortTypeFirstHelp": "Kelompokkan berdasarkan upaya pendaftaran (Tanpa Pendaftaran → Masuk OAuth → Kunci API), mempertahankan urutan kualitas dalam setiap kelompok",
-    "sortByReliability": "__MISSING__:Most reliable first",
-    "sortByReliabilityHelp": "__MISSING__:Order providers by the share of calls that succeeded in the selected window. Providers with too few calls to state a rate keep their score order, below the measured ones.",
-    "typeLegend": "Tanpa Pendaftaran = tanpa penyiapan · Masuk OAuth = masuk dengan akun Anda sendiri · Kunci API = bawa kunci Anda sendiri atau tingkat gratis penyedia tersebut",
-    "colReliability": "__MISSING__:Reliability",
-    "colReliabilityHelp": "__MISSING__:Share of calls this provider actually answered over the last 24 hours. A dash means it served too little traffic to state a rate.",
-    "reliabilitySample": "__MISSING__:{successes} of {requests} calls succeeded in the last {hours}h",
-    "reliabilityTooFew": "__MISSING__:Only {requests} calls in the last {hours}h — too few to state a rate",
-    "reliabilityNoTraffic": "__MISSING__:No calls recorded in the last 24h"
-  },
-  "discovery": {
-    "title": "Penemuan Penyedia",
-    "subtitle": "Pindai penyedia untuk metode akses gratis/tanpa batas dan tinjau temuan. Opt-in, hanya lokal.",
-    "scanLabel": "Penyedia untuk dipindai",
-    "scanPlaceholder": "mis. huggingchat",
-    "scan": "Pindai",
-    "scanning": "Memindai…",
-    "scanQueued": "Pemindaian selesai untuk {provider}.",
-    "scanFailed": "Pemindaian gagal.",
-    "loadFailed": "Gagal memuat hasil penemuan.",
-    "localOnlyNote": "Alat ini hanya lokal (loopback). Pemindaian berjalan dari mesin ini dan tidak pernah dapat dijangkau dari jarak jauh.",
-    "verify": "Verifikasi",
-    "verifyFailed": "Gagal memverifikasi temuan.",
-    "delete": "Hapus",
-    "deleteFailed": "Gagal menghapus temuan.",
-    "deleteTitle": "Hapus hasil penemuan",
-    "deleteConfirm": "Hapus temuan penemuan untuk {provider}? Tindakan ini tidak dapat dibatalkan.",
-    "emptyTitle": "Belum ada hasil penemuan",
-    "emptyDescription": "Jalankan pemindaian di atas untuk mencari metode akses gratis pada penyedia.",
-    "risk": "Risiko",
-    "method": "Metode",
-    "auth": "Autentikasi",
-    "feasibility": "Kelayakan",
-    "models": "Model"
-  },
-  "noAuthProvider": {
-    "title": "Tidak memerlukan autentikasi",
-    "description": "Penyedia ini siap digunakan segera — tidak perlu mendaftar atau kunci API.",
-    "accountDescription": "Siap digunakan — tidak perlu mendaftar. Tambahkan akun untuk rotasi batas laju.",
-    "addAccount": "Tambah Akun",
-    "accountName": "Akun {provider} {number}",
-    "accounts": "Akun ({count})",
-    "adding": "Menambahkan...",
-    "autoGeneratedAccount": "Menggunakan akun yang dibuat otomatis. Pilih “{addLabel}” untuk rotasi batas laju.",
-    "configureProxy": "Konfigurasikan proksi",
-    "proxyConfigured": "Proksi dikonfigurasi: {host}",
-    "removeAccount": "Hapus akun",
-    "proxyForAccount": "Proksi untuk Akun {number}",
-    "saved": "Tersimpan",
-    "custom": "Kustom",
-    "noSavedProxies": "Tidak ada proksi tersimpan — tambahkan di Pengaturan → Proksi",
-    "directConnection": "Langsung (tanpa proksi)",
-    "host": "Host",
-    "port": "Port",
-    "usernameOptional": "Nama pengguna (opsional)",
-    "passwordOptional": "Kata sandi (opsional)",
-    "cancel": "Batal",
-    "saving": "Menyimpan...",
-    "save": "Simpan",
-    "createConnectionFailed": "Gagal membuat koneksi",
-    "updateConnectionFailed": "Gagal memperbarui koneksi",
-    "fetchProxiesFailed": "Gagal mengambil proksi",
-    "noSavedProxiesError": "Tidak ada proksi tersimpan yang ditemukan. Tambahkan proksi di Pengaturan → Proksi terlebih dahulu.",
-    "updateProviderFailed": "Gagal memperbarui penyedia",
-    "providerEnabled": "{provider} diaktifkan",
-    "providerDisabled": "{provider} dinonaktifkan",
-    "providerAdded": "{provider} ditambahkan",
-    "add": "Tambah",
-    "manualApiKey": "Gunakan kunci API manual",
-    "createDahlTokenFailed": "Gagal membuat token Dahl",
-    "providerProxy": "Proxy",
-    "providerProxyConfigureHint": "Konfigurasi proxy",
-    "providerProxyTitleConfigured": "Proxy dikonfigurasi: {host}"
-  },
-  "gamification": {
-    "leaderboardScopes": {
-      "allTime": "Sepanjang Waktu",
-      "weekly": "Mingguan",
-      "monthly": "Bulanan",
-      "tokensShared": "Token Dibagikan"
-    },
-    "leaderboardLoadFailed": "Gagal memuat papan peringkat (HTTP {status})",
-    "scope": "Cakupan",
-    "tokensShared": "token dibagikan",
-    "points": "poin",
-    "rank": "Peringkat",
-    "name": "Nama",
-    "score": "Skor",
-    "leaderboardEmpty": "Belum ada entri untuk cakupan ini. Mulai gunakan OmniRoute untuk muncul di papan peringkat!",
-    "profileLoadFailed": "Gagal memuat data profil",
-    "levelTitles": {
-      "beginner": "Pemula",
-      "explorer": "Penjelajah",
-      "expert": "Pakar",
-      "master": "Master",
-      "legend": "Legenda"
-    },
-    "tiers": {
-      "bronze": "Perunggu",
-      "silver": "Perak",
-      "gold": "Emas",
-      "platinum": "Platinum",
-      "diamond": "Berlian"
-    },
-    "tierLabel": "Tingkat: {tier}",
-    "dayStreak": "Runtunan {count} hari",
-    "levelProgress": "Level {current} → {next}",
-    "totalXpEarned": "{count} total XP diperoleh",
-    "maintainStreak": "Terus gunakan OmniRoute setiap hari untuk mempertahankan runtunan Anda!",
-    "badgesTitle": "Lencana ({earned}/{total})",
-    "noBadges": "Belum ada lencana yang tersedia.",
-    "hiddenBadge": "Pencapaian tersembunyi",
-    "earnedDate": "Diperoleh {date}",
-    "earnedOn": "Diperoleh pada {date}",
-    "category": "Kategori",
-    "rarities": {
-      "common": "Biasa",
-      "uncommon": "Tidak Biasa",
-      "rare": "Langka",
-      "epic": "Epik",
-      "legendary": "Legendaris"
-    },
-    "categories": {
-      "usage": "Penggunaan",
-      "sharing": "Berbagi",
-      "contribution": "Kontribusi",
-      "streak": "Streak",
-      "rare": "Pencapaian langka"
-    },
-    "badges": {
-      "radar-supporter": {
-        "name": "Radar Supporter",
-        "description": "Verified a live OmniRoute Radar supporter feed",
-        "criteria": "Verify a signed live Radar supporter feed."
-      },
-      "first-token": {
-        "name": "Token Pertama",
-        "description": "Membuat permintaan API pertama Anda",
-        "criteria": "Selesaikan permintaan API pertama Anda melalui OmniRoute."
-      },
-      "token-consumer": {
-        "name": "Konsumen Token",
-        "description": "Membuat 1.000 permintaan API",
-        "criteria": "Selesaikan 1.000 permintaan API melalui OmniRoute."
-      },
-      "token-machine": {
-        "name": "Mesin Token",
-        "description": "Membuat 10.000 permintaan API",
-        "criteria": "Selesaikan 10.000 permintaan API melalui OmniRoute."
-      },
-      "token-whale": {
-        "name": "Paus Token",
-        "description": "Membuat 100.000 permintaan API",
-        "criteria": "Selesaikan 100.000 permintaan API melalui OmniRoute."
-      },
-      "generous": {
-        "name": "Dermawan",
-        "description": "Membagikan 1.000 token dengan orang lain",
-        "criteria": "Bagikan total 1.000 token dengan pengguna lain."
-      },
-      "philanthropist": {
-        "name": "Filantropis",
-        "description": "Membagikan 10.000 token dengan orang lain",
-        "criteria": "Bagikan total 10.000 token dengan pengguna lain."
-      },
-      "token-santa": {
-        "name": "Santa Token",
-        "description": "Membagikan 100.000 token dengan orang lain",
-        "criteria": "Bagikan total 100.000 token dengan pengguna lain."
-      },
-      "community-hero": {
-        "name": "Pahlawan Komunitas",
-        "description": "Membagikan 1.000.000 token dengan orang lain",
-        "criteria": "Bagikan total 1.000.000 token dengan pengguna lain."
-      },
-      "explorer": {
-        "name": "Penjelajah",
-        "description": "Menggunakan 5 penyedia berbeda",
-        "criteria": "Gunakan setidaknya 5 penyedia AI yang berbeda."
-      },
-      "polyglot": {
-        "name": "Poliglot",
-        "description": "Menggunakan 10 model berbeda",
-        "criteria": "Gunakan setidaknya 10 model AI yang berbeda."
-      },
-      "architect": {
-        "name": "Arsitek",
-        "description": "Membuat 3 rute kombo",
-        "criteria": "Buat 3 rute kombo."
-      },
-      "speedster": {
-        "name": "Speedster",
-        "description": "Mempertahankan latensi rata-rata di bawah 500 ms untuk 100 permintaan",
-        "criteria": "Jaga latensi rata-rata di bawah 500 ms di 100 permintaan."
-      },
-      "resilient": {
-        "name": "Tangguh",
-        "description": "Mempertahankan 100% uptime selama 7 hari",
-        "criteria": "Pertahankan 100% uptime selama 7 hari berturut-turut."
-      },
-      "daily-user": {
-        "name": "Pengguna Harian",
-        "description": "Aktif selama 3 hari berturut-turut",
-        "criteria": "Gunakan OmniRoute selama 3 hari berturut-turut."
-      },
-      "weekly-warrior": {
-        "name": "Pejuang Mingguan",
-        "description": "Aktif selama 7 hari berturut-turut",
-        "criteria": "Gunakan OmniRoute selama 7 hari berturut-turut."
-      },
-      "monthly-master": {
-        "name": "Master Bulanan",
-        "description": "Aktif selama 30 hari berturut-turut",
-        "criteria": "Gunakan OmniRoute selama 30 hari berturut-turut."
-      },
-      "unstoppable": {
-        "name": "Tak Terhentikan",
-        "description": "Aktif selama 365 hari berturut-turut",
-        "criteria": "Gunakan OmniRoute selama 365 hari berturut-turut."
-      },
-      "early-adopter": {
-        "name": "Pengadopsi Awal",
-        "description": "Bergabung dalam bulan pertama gamifikasi",
-        "criteria": "Bergabunglah dalam bulan pertama setelah gamifikasi diluncurkan."
-      },
-      "bug-hunter": {
-        "name": "Pemburu Bug",
-        "description": "Melaporkan 5 masalah",
-        "criteria": "Laporkan 5 masalah yang valid."
-      },
-      "contributor": {
-        "name": "Kontributor",
-        "description": "Menggabungkan 1 pull request",
-        "criteria": "Miliki 1 pull request yang digabungkan ke dalam OmniRoute."
-      },
-      "community-leader": {
-        "name": "Pemimpin Komunitas",
-        "description": "Mencapai 10 besar di papan peringkat mana pun",
-        "criteria": "Capai 10 besar di papan peringkat mana pun."
-      },
-      "secret-badge": {
-        "name": "???",
-        "description": "Pencapaian tersembunyi menanti...",
-        "criteria": "Selesaikan pencapaian tersembunyi untuk menampilkan lencana ini."
-      }
-    }
-  },
-  "featureFlags": {
-    "title": "Flag Fitur",
-    "activeCount": "{count} aktif",
-    "inactiveCount": "{count} tidak aktif",
-    "dbOverrideCount": "{count} penimpaan DB",
-    "searchPlaceholder": "Cari flag...",
-    "categories": {
-      "all": "Semua",
-      "security": "Keamanan",
-      "network": "Jaringan",
-      "policies": "Kebijakan",
-      "runtime": "Runtime",
-      "cli": "CLI",
-      "health": "Kesehatan",
-      "requiresRestart": "Memerlukan Mulai Ulang"
-    },
-    "categoryLabel": "Kategori: {category}",
-    "caution": "Perhatian",
-    "danger": "Bahaya",
-    "requiresRestart": "Memerlukan mulai ulang",
-    "source": "Sumber",
-    "ccDiscoveryAliasesEnvWarning": "Aktif melalui variabel lingkungan (EXPOSE_CC_DISCOVERY_ALIASES) — ini menimpa toggle dasbor apa pun di bawah.",
-    "resetFlag": "Setel ulang {label} ke default",
-    "reset": "Setel Ulang",
-    "loadFailed": "Gagal memuat flag fitur",
-    "updateFailedHttp": "Gagal memperbarui flag: HTTP {status}",
-    "updateFailed": "Gagal memperbarui flag",
-    "restartFailedHttp": "Mulai ulang gagal: HTTP {status}",
-    "restartFailed": "Mulai ulang gagal",
-    "resetOverridesFailedHttp": "Gagal menyetel ulang override: HTTP {status}",
-    "resetOverridesFailed": "Gagal menyetel ulang override",
-    "restartRequiredCount": "{count, plural, one {# perubahan memerlukan} other {# perubahan memerlukan}} mulai ulang server agar dapat diterapkan.",
-    "restartRequiredDescription": "Flag ini hanya berlaku setelah proses dimuat ulang. Mulai ulang sekarang atau lanjutkan mengedit — flag yang tertunda tetap antre hingga Anda mengonfirmasi.",
-    "restartServer": "Mulai Ulang Server",
-    "cancel": "Batal",
-    "restarting": "Memulai ulang…",
-    "confirmRestart": "Konfirmasi Mulai Ulang",
-    "restartViewDescription": "Flag ini hanya berlaku setelah server dimulai ulang. Alihkan flag ini seperti flag lainnya — perubahan langsung disimpan, tetapi nilai baru hanya dibaca saat proses dimulai. Gunakan spanduk <strong>Mulai Ulang Server</strong> di atas untuk menerapkan.",
-    "retry": "Coba Lagi",
-    "noSearchResults": "Tidak ada flag yang cocok dengan pencarian Anda",
-    "resetAllOverrides": "Setel Ulang Semua Override",
-    "confirmResetOverrides": "Setel ulang semua {count} override DB?",
-    "resetting": "Menyetel ulang...",
-    "confirmReset": "Konfirmasi Setel Ulang",
-    "enumValues": {
-      "off": "Mati",
-      "warn": "Peringatkan",
-      "block": "Blokir",
-      "redact": "Sensor",
-      "disabled": "Dinonaktifkan",
-      "dual": "Ganda",
-      "alias": "Alias",
-      "canonical": "Kanonik"
-    },
-    "definitions": {
-      "REQUIRE_API_KEY": {
-        "description": "Wajibkan kunci API untuk semua permintaan masuk."
-      },
-      "INPUT_SANITIZER_ENABLED": {
-        "description": "Aktifkan sanitasi input untuk semua permintaan."
-      },
-      "INJECTION_GUARD_MODE": {
-        "description": "Setel mode pelindung injeksi prompt."
-      },
-      "PII_REDACTION_ENABLED": {
-        "description": "Samarkan informasi identitas pribadi dari permintaan."
-      },
-      "PII_RESPONSE_SANITIZATION": {
-        "description": "Sanitasi informasi identitas pribadi dalam respons penyedia."
-      },
-      "PII_RESPONSE_SANITIZATION_MODE": {
-        "description": "Pilih cara penanganan PII respons: redact menggantinya, warn hanya mencatatnya, block menolak respons, dan off menonaktifkan sanitasi."
-      },
-      "OUTBOUND_SSRF_GUARD_ENABLED": {
-        "description": "Blokir permintaan keluar ke rentang IP privat atau internal."
-      },
-      "ALLOW_API_KEY_REVEAL": {
-        "description": "Izinkan pengguna dasbor terautentikasi untuk menampilkan kunci API yang disimpan alih-alih hanya melihat nilai yang disamarkan."
-      },
-      "ENABLE_TLS_FINGERPRINT": {
-        "description": "Aktifkan mode senyap sidik jari TLS."
-      },
-      "ONEPROXY_ENABLED": {
-        "description": "Aktifkan proksi permintaan melalui 1proxy."
-      },
-      "PROXY_AUTO_SELECT_ENABLED": {
-        "description": "Jika tidak ada proksi yang ditetapkan ke koneksi, pilih proksi registri pertama yang berfungsi secara otomatis. Nonaktif secara default karena jika tidak, satu proksi registri akan menjadi fallback global untuk semua lalu lintas (#3332)."
-      },
-      "OMNIROUTE_CONTROL_PLANE_PROXY_DIRECT_FALLBACK": {
-        "description": "Izinkan alur OAuth dan validasi penyedia untuk melewati proksi yang disematkan saat pemeriksaan keterjangkauan proksi gagal. Nonaktif secara default karena ini dapat mengubah IP egress akun."
-      },
-      "MITM_DISABLE_TLS_VERIFY": {
-        "description": "Nonaktifkan verifikasi sertifikat TLS untuk proksi MITM."
-      },
-      "OMNIROUTE_ALLOW_PRIVATE_PROVIDER_URLS": {
-        "description": "Izinkan URL penyedia yang mengarah ke jaringan privat atau internal."
-      },
-      "OMNIROUTE_ALLOW_LOCAL_PROVIDER_URLS": {
-        "description": "Izinkan penyedia pada localhost, LAN, dan rentang IP privat. Ini diperlukan untuk model lokal yang kompatibel dengan OpenAI dan diaktifkan secara default. Titik akhir metadata cloud seperti 169.254.169.254 tetap diblokir."
-      },
-      "ENABLE_CC_COMPATIBLE_PROVIDER": {
-        "description": "Aktifkan mode penyedia yang kompatibel dengan Claude Code."
-      },
-      "TOOL_POLICY_MODE": {
-        "description": "Atur mode penegakan kebijakan penggunaan alat."
-      },
-      "RATE_LIMIT_AUTO_ENABLE": {
-        "description": "Aktifkan pembatasan laju secara otomatis berdasarkan pola penggunaan."
-      },
-      "ALLOW_MULTI_CONNECTIONS_PER_COMPAT_NODE": {
-        "description": "Izinkan beberapa koneksi untuk setiap simpul kompatibilitas."
-      },
-      "DISABLE_CONTEXT_WINDOW_CHECKS": {
-        "label": "Disable Context Window Checks",
-        "description": "Skip OmniRoute's local context-window and max-input-token check for direct single-model requests. Upstream providers still enforce their actual limits. Prompt compression and output-token caps remain active."
-      },
-      "RESPONSES_PASSTHROUGH_DROP_COMMENTARY": {
-        "description": "Hapus item output fase komentar internal dari aliran passthrough API Respons sebelum meneruskannya ke klien. Nonaktifkan bendera ini untuk menerima komentar hulu mentah."
-      },
-      "OMNIROUTE_MCP_ENFORCE_SCOPES": {
-        "description": "Terapkan batasan cakupan untuk akses alat MCP."
-      },
-      "OMNIROUTE_MCP_COMPRESS_DESCRIPTIONS": {
-        "description": "Kompres deskripsi alat MCP untuk mengurangi penggunaan token."
-      },
-      "OMNIROUTE_ENABLE_RUNTIME_BACKGROUND_TASKS": {
-        "description": "Aktifkan pemrosesan tugas latar belakang saat runtime."
-      },
-      "OMNIROUTE_DISABLE_BACKGROUND_SERVICES": {
-        "description": "Nonaktifkan semua layanan latar belakang, termasuk penyegaran kuota dan sinkronisasi."
-      },
-      "OMNIROUTE_RTK_TRUST_PROJECT_FILTERS": {
-        "description": "Percayai filter RTK tingkat proyek tanpa validasi."
-      },
-      "OMNIROUTE_ENABLE_LIVE_WS": {
-        "description": "Mulai server WebSocket dasbor real-time saat impor pada port loopback 20132. Setel bendera ke 0 atau false untuk menonaktifkannya. Eksposur LAN juga memerlukan LIVE_WS_HOST=0.0.0.0 dan LIVE_WS_ALLOWED_ORIGINS."
-      },
-      "OMNIROUTE_CODEX_WS_ENABLED": {
-        "description": "Izinkan Codex menggunakan Respons melalui WebSocket. Jika dinonaktifkan, Codex akan beralih kembali ke Respons HTTP."
-      },
-      "OMNIROUTE_EMERGENCY_FALLBACK": {
-        "description": "Rute permintaan yang kehabisan anggaran ke penyedia dan model fallback gratis darurat."
-      },
-      "STREAM_RECOVERY_ENABLED": {
-        "description": "Coba lagi aliran SSE hulu yang terpotong secara transparan sebelum byte respons apa pun mencapai klien."
-      },
-      "STREAM_RECOVERY_MIDSTREAM_ENABLED": {
-        "description": "Izinkan pemulihan aliran untuk meminta respons kembali dan menyambungkannya setelah byte mencapai klien."
-      },
-      "MODEL_CATALOG_INCLUDE_NAMES": {
-        "description": "Sertakan bidang nama yang ramah tampilan dalam respons /v1/models. Nonaktifkan ini untuk klien yang hanya menerima ID model."
-      },
-      "MODELS_CATALOG_PREFIX_MODE": {
-        "description": "Kontrol prefiks ID model di /v1/models: dual memancarkan prefiks alias dan kanonis, alias memancarkan prefiks pendek saja, dan canonical memancarkan ID penyedia lengkap saja."
-      },
-      "ARENA_ELO_SYNC_ENABLED": {
-        "description": "Sinkronkan data ELO papan peringkat Arena AI secara berkala untuk peringkat kecerdasan model."
-      },
-      "CLI_COMPAT_ALL": {
-        "description": "Aktifkan mode kompatibilitas untuk semua klien CLI."
-      },
-      "MODEL_ALIAS_COMPAT_ENABLED": {
-        "description": "Aktifkan lapisan kompatibilitas alias model."
-      },
-      "PRICING_SYNC_ENABLED": {
-        "description": "Sinkronkan data harga secara otomatis. Variabel lingkungan PRICING_SYNC_ENABLED juga harus bernilai true."
-      },
-      "OMNIROUTE_AUTO_SYNC_CODEX_PROFILES": {
-        "description": "Setelah sinkronisasi model penyedia, buat ulang profil ~/.codex/*.config.toml dari katalog langsung. Ini tidak pernah mengubah konfigurasi Codex yang aktif atau default dan nonaktif secara default."
-      },
-      "OMNIROUTE_AUTO_SYNC_CLAUDE_PROFILES": {
-        "description": "Setelah sinkronisasi model penyedia, buat ulang profil ~/.claude/profiles/<name>/settings.json dari katalog langsung. Ini tidak pernah mengubah konfigurasi Claude yang aktif atau default dan nonaktif secara default."
-      },
-      "OMNIROUTE_DISABLE_LOCAL_HEALTHCHECK": {
-        "description": "Nonaktifkan titik akhir pemeriksaan kesehatan instans lokal."
-      },
-      "OMNIROUTE_DISABLE_TOKEN_HEALTHCHECK": {
-        "description": "Nonaktifkan pemeriksaan kesehatan validasi token."
-      },
-      "SKILLS_SANDBOX_NETWORK_ENABLED": {
-        "description": "Aktifkan akses jaringan di sandbox keahlian."
-      }
-    }
-  },
-  "combo": {
-    "sort": {
-      "label": "__MISSING__:Sort by",
-      "method": {
-        "manual": "__MISSING__:Manual",
-        "provider": "__MISSING__:Provider",
-        "score": "__MISSING__:Score (free models)",
-        "name": "__MISSING__:Name"
-      },
-      "scoreHint": "__MISSING__:Score ranking applies to free providers only; others stay in place."
-    }
-  },
-  "comboControl": {
-    "title": "Combo Control Center",
-    "unavailable": "Pusat Kontrol Combo tidak tersedia",
-    "backToCombos": "Kembali ke Combo",
-    "loadFailed": "Gagal memuat pusat kontrol combo",
-    "state": {
-      "healthy": "Sehat",
-      "warning": "Perlu perhatian",
-      "critical": "Kritis",
-      "idle": "Idle"
-    },
-    "active": "Aktif",
-    "disabled": "Dinonaktifkan",
-    "description": "Tampilan terpusat baca-saja untuk perilaku perutean, kesehatan, kuota, metrik runtime, dan keputusan terbaru untuk <combo></combo>.",
-    "refresh": "Segarkan",
-    "editInCombos": "Edit di Combo",
-    "requests": "Permintaan",
-    "success": "Berhasil",
-    "latency": "Latensi",
-    "quota": "Kuota",
-    "rangeWindow": "Jendela {range}",
-    "runtimeHealthBlend": "paduan runtime/kesehatan",
-    "averageResponseTime": "waktu respons rata-rata",
-    "worstQuota": "Kuota terburuk",
-    "providerAccountTelemetry": "telemetri penyedia/akun",
-    "overview": "Ikhtisar",
-    "overviewDescription": "Strategi, status runtime, dan tautan kontrol untuk combo ini.",
-    "strategy": "Strategi",
-    "targets": "Target",
-    "providers": "Penyedia",
-    "targetCounts": "{configured} dikonfigurasi · {resolved} diselesaikan",
-    "healthReasons": "Alasan kesehatan",
-    "healthReason": {
-      "noRecentTraffic": "Tidak ada lalu lintas combo baru-baru ini",
-      "lowSuccessRate": "Tingkat keberhasilan rendah",
-      "successBelowTarget": "Tingkat keberhasilan di bawah target",
-      "highFallbackRate": "Tingkat fallback tinggi",
-      "elevatedFallbackRate": "Tingkat fallback meningkat",
-      "quotaExhausted": "Setidaknya satu kuota telah habis",
-      "quotaNearlyExhausted": "Kuota hampir habis",
-      "quotaGettingLow": "Kuota mulai menipis",
-      "trafficHighlySkewed": "Distribusi lalu lintas sangat tidak merata",
-      "comboHealthy": "Combo tampak sehat"
-    },
-    "configuredTargets": "Target yang dikonfigurasi",
-    "configuredTargetsDescription": "Langkah-langkah combo yang disimpan, diperkaya dengan data kesehatan yang cocok jika tersedia.",
-    "noConfiguredTargets": "Tidak ada target yang dikonfigurasi.",
-    "runtimeConfig": "Konfigurasi runtime",
-    "runtimeConfigDescription": "Pengaturan lanjutan yang dipilih untuk kombo ini.",
-    "noRuntimeConfig": "Tidak ada konfigurasi runtime kustom.",
-    "resolvedTargets": "Target runtime yang diselesaikan",
-    "resolvedTargetsDescription": "Target yang diratakan setelah resolusi kombo bersarang dan metrik tingkat target.",
-    "noResolvedTargetHealth": "Belum ada status kesehatan target yang diselesaikan.",
-    "quotaDistribution": "Kuota dan distribusi",
-    "noQuotaSnapshots": "Tidak ada snapshot kuota untuk jendela kombo ini.",
-    "usageSkew": "Penyimpangan penggunaan",
-    "recentDecisions": "Keputusan perutean terbaru",
-    "recentDecisionsDescription": "Log panggilan terbaru yang difilter berdasarkan nama kombo ini. Buka Analitik untuk penjelasan lengkap.",
-    "noRecentLogs": "Tidak ada log panggilan kombo terbaru yang ditemukan.",
-    "quickLinks": "Tautan cepat",
-    "comboHealth": "Kesehatan Kombo",
-    "callLogs": "Log Panggilan",
-    "costs": "Biaya",
-    "playground": "Playground",
-    "nestedCombo": "Kombo bersarang",
-    "modelTarget": "Target model",
-    "weight": "Bobot {value}%",
-    "comboReference": "Referensi kombo",
-    "accountShort": "akun {id}",
-    "keyShort": "kunci {id}",
-    "stepShort": "langkah {id}",
-    "dynamic": "dinamis",
-    "unknown": "tidak diketahui",
-    "unknownProvider": "penyedia tidak diketahui",
-    "unknownModel": "model tidak diketahui",
-    "resolvedTargetMetrics": "{requests} req · {success} sukses · {latency} · kuota {quota}"
-  },
-  "usageLimits": {
-    "usdUsageQuota": "Kuota penggunaan USD",
-    "usdUsageQuotaDescription": "Memblokir kunci ini dengan kesalahan API 400 setelah pengeluaran USD lokalnya mencapai kuota harian atau mingguan yang dikonfigurasi.",
-    "dailyQuotaUsd": "Kuota harian (USD)",
-    "weeklyQuotaUsd": "Kuota mingguan (USD)",
-    "quotaWindowDescription": "Kuota mingguan mengikuti penyetelan ulang mingguan Claude yang tersimpan di cache jika tersedia; jika tidak, kuota akan kembali ke jendela 7 hari bergulir. Kuota harian menggunakan hari kalender Fortaleza.",
-    "apiKeyUsdQuota": "Kuota USD kunci API",
-    "apiKeyUsdQuotaDescription": "Jika diaktifkan, @@om-usage mengembalikan kuota harian, kuota mingguan, pengeluaran harian, dan pengeluaran mingguan dalam USD. Mingguan mengikuti penyetelan ulang Claude yang tersimpan di cache jika tersedia.",
-    "enabled": "Diaktifkan",
-    "disabled": "Dinonaktifkan",
-    "dailySpend": "Pengeluaran harian",
-    "weeklySpend": "Pengeluaran mingguan",
-    "dailyQuota": "Kuota harian",
-    "weeklyQuota": "Kuota mingguan",
-    "fallbackRollingDays": "cadangan: bergulir {days} hari",
-    "fallbackRollingDaysShort": "Cadangan bergulir {days}h",
-    "resetDueNow": "atur ulang jatuh tempo sekarang",
-    "resetsInHours": "diatur ulang dalam {count}j",
-    "resetsInDays": "diatur ulang dalam {count}h",
-    "saveFailed": "Gagal menyimpan batas penggunaan",
-    "saving": "Menyimpan...",
-    "saveQuota": "Simpan kuota",
-    "loadUsdCostsFailed": "Gagal memuat biaya USD",
-    "usdCost": "Biaya USD",
-    "close": "Tutup",
-    "loadingUsdCosts": "Memuat biaya USD",
-    "used": "Digunakan",
-    "quotaUsed": "Kuota digunakan",
-    "estimatedFullQuota": "Est. 100%",
-    "rows": "Baris",
-    "window": "Jendela",
-    "unknown": "tidak diketahui",
-    "fromRecordedReset": "Dari atur ulang {quota} yang tercatat",
-    "fromObservedReset": "Dari atur ulang {quota} yang teramati",
-    "fromReset": "Dari atur ulang {quota}",
-    "quotaEstimator": "Estimator kuota",
-    "noApiKeyUsage": "Tidak ada penggunaan kunci API di jendela penyedia ini.",
-    "requestTokenCounts": "{requests} permintaan · {tokens} token",
-    "noUsdLimit": "Tanpa batas USD"
-  },
-  "freeBudget": {
-    "title": "Anggaran token gratis",
-    "remaining": "tersisa {remaining} · {percent}% dari {total}",
-    "steadyMonth": "Stabil / bulan",
-    "firstMonth": "Bulan pertama (+ kredit)",
-    "usedThisMonth": "Digunakan bulan ini",
-    "segmentHint": "Setiap segmen = satu pool gratis · deduplikasi pool, penghitungan jujur (tanpa batas atas laju batas yang dinaikkan).",
-    "boost": "Buka ~{tokens} lagi/bln dengan sekali isi ulang OpenRouter $10 (50 → 1000 perm/hari)",
-    "uncapped": "Gratis selamanya, tanpa batas yang dipublikasikan (dibatasi laju) — akses nyata, tidak dihitung dalam tajuk utama:",
-    "tosRestricted": "{count, plural, one {# model} other {# model}} ditandai sebagai dibatasi ToS — Anda yang memutuskan",
-    "provider": "Penyedia",
-    "model": "Model",
-    "modelName": "Nama model",
-    "type": "Jenis",
-    "tokensMonth": "Token/bln",
-    "credit": "{tokens} kredit",
-    "hideTosRestricted": "Sembunyikan yang dibatasi ToS",
-    "sort": "Urutkan",
-    "freeType": {
-      "daily": "harian",
-      "monthly": "bulanan",
-      "creditMonthly": "kredit/bln",
-      "uncapped": "tanpa batas",
-      "signupCredit": "kredit pendaftaran",
-      "keyless": "tanpa kunci",
-      "discontinued": "dihentikan"
-    },
-    "tosTitle": {
-      "avoid": "Dibatasi ToS — tinjau ketentuan",
-      "caution": "Peringatan — klausul penggunaan pribadi / proksi",
-      "ok": "Umumnya permisif"
-    },
-    "allProviders": "Semua penyedia",
-    "noApiKeyRequired": "Tidak perlu kunci API"
-  },
-  "providerHealthAutopilot": {
-    "title": "Autopilot Kesehatan Penyedia",
-    "description": "Menemukan penyedia yang tidak stabil, masa tunggu akun, kesalahan usang, dan perbaikan manual yang aman.",
-    "loadFailed": "Gagal memuat laporan autopilot",
-    "actionApplied": "{action} diterapkan.",
-    "actionFailed": "Tindakan autopilot gagal",
-    "refresh": "Segarkan",
-    "status": "Status",
-    "issues": "Masalah",
-    "actions": "Tindakan",
-    "connections": "Koneksi",
-    "state": {
-      "healthy": "sehat",
-      "warning": "peringatan",
-      "critical": "kritis",
-      "loading": "memuat"
-    },
-    "loadingRecommendations": "Memuat rekomendasi penyedia...",
-    "noRecommendations": "Tidak ada rekomendasi kesehatan penyedia saat ini.",
-    "providerMetrics": "skor {score}% · aktif {active}/{total} · masa tunggu {cooldown} · penguncian model {lockouts}",
-    "providerState": {
-      "healthy": "sehat",
-      "degraded": "terdegradasi",
-      "down": "tidak aktif"
-    },
-    "severity": {
-      "info": "info",
-      "warning": "peringatan",
-      "critical": "kritis"
-    },
-    "remainingSeconds": "tersisa {seconds} detik",
-    "errorCode": "kode {code}",
-    "applying": "Menerapkan...",
-    "issue": {
-      "circuitOpenTitle": "Pemutus sirkuit penyedia terbuka",
-      "circuitOpenRecommendation": "Verifikasi pemulihan hulu, lalu atur ulang pemutus sirkuit penyedia atau tunggu jendela percobaan kembali.",
-      "circuitRecoveryTitle": "Penyedia sedang menguji pemulihan",
-      "circuitRecoveryRecommendation": "Biarkan pengujian berikutnya selesai atau atur ulang pemutus setelah verifikasi manual.",
-      "terminalTitle": "{label} memiliki status akun terminal",
-      "terminalRecommendation": "Periksa penagihan, autentikasi ulang, atau ganti kredensial sebelum mengaktifkannya kembali.",
-      "cooldownTitle": "{label} sedang dalam masa jeda sementara",
-      "cooldownRecommendation": "Tunggu jendela percobaan kembali hulu atau bersihkan masa jeda setelah memvalidasi pemulihan.",
-      "staleErrorTitle": "{label} memiliki status galat usang",
-      "staleErrorRecommendation": "Bersihkan bidang galat usang agar sambungan memenuhi syarat untuk perutean normal kembali.",
-      "inactiveTitle": "{label} dinonaktifkan",
-      "inactiveRecommendation": "Aktifkan kembali hanya jika ini tidak dinonaktifkan secara sengaja.",
-      "modelLockoutTitle": "{model} terkunci untuk satu sambungan",
-      "modelLockoutRecommendation": "Selesaikan status sambungan atau konfirmasi kuota/ketersediaan model telah pulih sebelum membersihkan penguncian.",
-      "quotaTitle": "Pemantau kuota melaporkan {status}",
-      "quotaRecommendation": "Tinjau penggunaan kuota dan rotasikan lalu lintas ke sambungan lain yang sehat jika diperlukan."
-    },
-    "action": {
-      "resetProviderBreaker": "Atur ulang pemutus penyedia",
-      "clearConnectionCooldown": "Bersihkan masa jeda sambungan",
-      "disableConnection": "Nonaktifkan sambungan ini",
-      "clearStaleError": "Bersihkan status galat usang",
-      "reactivateConnection": "Aktifkan kembali sambungan",
-      "clearModelLockout": "Bersihkan penguncian model"
-    }
-  },
-  "changelogPage": {
-    "newsTab": "Berita",
-    "changelogTab": "Catatan Perubahan",
-    "loading": "Memuat catatan perubahan...",
-    "announcementsLoadFailed": "Tidak dapat memuat pengumuman. Silakan coba lagi nanti.",
-    "noAnnouncements": "Tidak ada pengumuman baru saat ini.",
-    "learnMore": "Pelajari lebih lanjut",
-    "changelogLoadFailed": "Tidak dapat memuat catatan perubahan. Silakan coba lagi nanti.",
-    "retry": "Coba Lagi",
-    "viewFullHistory": "Lihat riwayat lengkap di GitHub"
-  },
-  "reasoningRouting": {
-    "title": "Reasoning routing policies",
-    "apiKeyTitle": "Reasoning routing for this API key",
-    "subtitle": "Reroute models and reasoning effort without requiring client support. Requests remain unchanged when no rule matches.",
-    "loadError": "Reasoning rules could not be loaded.",
-    "saveError": "The rule is invalid or could not be saved.",
-    "saved": "Reasoning rule saved.",
-    "deleteConfirm": "Delete this reasoning rule?",
-    "deleteError": "The reasoning rule could not be deleted.",
-    "empty": "No matching reasoning rules configured.",
-    "all": "All",
-    "any": "Any",
-    "enabled": "Enabled",
-    "disabled": "Disabled",
-    "filterSearch": "Search rules",
-    "filterScope": "Filter by scope",
-    "filterStatus": "Filter by status",
-    "allModels": "all models",
-    "keepModel": "Keep model",
-    "otherModel": "Other model",
-    "combo": "Combo",
-    "priorityShort": "priority {value}",
-    "toggleAria": "Enable {name}",
-    "edit": "Edit",
-    "delete": "Delete",
-    "name": "Name",
-    "description": "Description",
-    "scopeLabel": "Scope",
-    "apiKey": "API key",
-    "sourceCombo": "Source combo",
-    "connection": "Connection",
-    "sourceModel": "Source model or wildcard",
-    "sourceModelOptional": "Empty = all models",
-    "sourceModelExample": "e.g. gpt-5*",
-    "sourceEffort": "Source effort",
-    "missing": "Not specified",
-    "signalOnly": "Non-discrete reasoning signal",
-    "requestTags": "Request tags",
-    "requestTagsExample": "coding, internal",
-    "tagMode": "Tag matching",
-    "effortMode": "Effort mode",
-    "targetEffort": "Target effort",
-    "routingTarget": "Routing target",
-    "targetModel": "Target model",
-    "targetCombo": "Target combo",
-    "budgetAction": "Thinking budget",
-    "budgetTokens": "Budget tokens",
-    "priority": "Priority",
-    "saveChanges": "Save changes",
-    "add": "Add rule",
-    "cancel": "Cancel",
-    "simulateTitle": "Simulate rule",
-    "model": "Model",
-    "effort": "Effort",
-    "transport": "Transport",
-    "simulate": "Simulate without upstream",
-    "extendedComboWarning": "Max/Ultra is validated separately for every combo target during routing.",
-    "extendedUnknownWarning": "Enter a target model to verify Max/Ultra support.",
-    "extendedUnsupportedWarning": "Max/Ultra is only known to be supported by suitable Codex GPT-5.6 models. Unknown custom models are accepted by the server with a warning.",
-    "scope": {
-      "global": "Global",
-      "apiKey": "API key",
-      "combo": "Combo",
-      "model": "Model",
-      "connection": "Connection"
-    },
-    "mode": {
-      "inherit": "Inherit client",
-      "default": "Use default",
-      "force": "Force"
-    },
-    "budget": {
-      "preserve": "Preserve",
-      "remove": "Remove",
-      "set": "Set fixed value"
-    }
-  },
-  "chaosConfig": {
-    "pageTitle": "Mode Chaos",
-    "pageSubtitle": "Jalankan beberapa model AI secara paralel atau kolaboratif pada tugas yang sama",
-    "enableChaos": "Aktifkan Mode Chaos",
-    "enableChaosDesc": "Izinkan kunci API dengan mode chaos diaktifkan untuk menggunakan fitur ini",
-    "mode": "Mode Baku",
-    "modeParallel": "Paralel",
-    "modeCollaborative": "Kolaboratif",
-    "modeParallelDesc": "Semua model berjalan secara bersamaan — hasil tercepat",
-    "modeCollaborativeDesc": "Model merangkaikan keluaran — masing-masing melihat hasil sebelumnya",
-    "timeout": "Batas Waktu (ms)",
-    "timeoutDesc": "Waktu maks per panggilan model (5000-600000ms)",
-    "systemPrompt": "Prompt Sistem (opsional)",
-    "systemPromptDesc": "Instruksi khusus untuk semua instans model mode chaos",
-    "providerOverrides": "Penimpaan Penyedia",
-    "providerOverridesDesc": "Pilih model tertentu per penyedia untuk mode chaos",
-    "providerId": "Penyedia",
-    "modelId": "Model",
-    "addProvider": "Tambah Penyedia",
-    "removeProvider": "Hapus",
-    "saveConfig": "Simpan Konfigurasi",
-    "configSaved": "Konfigurasi chaos berhasil disimpan",
-    "configError": "Gagal menyimpan konfigurasi chaos",
-    "configReset": "Atur Ulang ke Default",
-    "keyPermission": "Akses Mode Chaos",
-    "keyPermissionDesc": "Izinkan kunci API ini untuk menggunakan Mode Chaos (eksekusi paralel multi-model)",
-    "testButton": "Uji Mode Chaos",
-    "testTask": "Tulis puisi singkat tentang kecerdasan buatan",
-    "loadingProviderModels": "Memuat penyedia...",
-    "systemPromptPlaceholder": "Opsional: timpa prompt sistem mode chaos default...",
-    "enabled": "Diaktifkan",
-    "disabled": "Dinonaktifkan",
-    "maxTokens": "Token Maks",
-    "maxTokensDesc": "Token maksimum per respons model. Nilai yang lebih tinggi memerlukan biaya lebih banyak dan memakan waktu lebih lama.",
-    "providerIdPlaceholder": "ID Penyedia (ketik atau pilih)",
-    "modelIdPlaceholder": "ID Model (opsional)",
-    "on": "AKTIF",
-    "off": "NONAKTIF",
-    "availableProviders": "Penyedia yang tersedia ({count})",
-    "noProviderOverrides": "Tidak ada penimpaan — semua penyedia aktif akan berpartisipasi dengan model default mereka",
-    "resetFailed": "Reset gagal",
-    "resetSuccess": "Pengaturan direset ke default",
-    "running": "Sedang berjalan...",
-    "testFailed": "Uji coba gagal"
-  },
-  "kimiSponsorBanner": {
-    "foundingFriendTitle": "Kimi (Moonshot AI) adalah Sahabat Open Source pendiri OmniRoute",
-    "description": "Pengguna baru mendapat 15% kredit API ekstra pada isi ulang pertama. Gunakan Kimi K3 di OmniRoute melalui Kimi API resmi.",
-    "cta": "Dapatkan Kunci API Kimi",
-    "partnerLinkNote": "Tautan mitra",
-    "dismissAriaLabel": "Tutup"
-  },
-  "vscodeCopilotBanner": {
-    "title": "OmniRoute kini berjalan di dalam VS Code Copilot Chat",
-    "description": "Instal ekstensi OmniCopilot gratis dan setiap model OmniRoute akan muncul langsung di pemilih model Copilot Chat yang sudah kamu gunakan.",
-    "cta": "Dapatkan Ekstensi",
-    "secondaryNote": "Juga tersedia di Open VSX (Cursor, Windsurf, VSCodium…)",
-    "dismissAriaLabel": "Tutup"
-  },
-  "featureFlagExposeFunctionalGatewayMirrorsDescription": "Iklankan id cermin <gateway-alias>/<model> di /v1/models untuk model yang pemilik kanoniknya tidak memiliki kredensial aktif tetapi gateway passthrough dengan kredensial aktif mengarahkannya. Peringatan: menambahkan entri katalog untuk semua klien saat diaktifkan secara global.",
-  "radarPage": {
-    "title": "रडार कैटलॉग",
-    "subtitle": "समुदाय की बुद्धिमत्ता से समृद्ध मुफ्त मॉडल कैटलॉग",
-    "loading": "कैटलॉग लोड हो रहा है...",
-    "errorLoading": "रडार कैटलॉग लोड करने में विफल",
-    "emptyState": "अभी तक कोई कैटलॉग डेटा नहीं है। नवीनतम फीड डाउनलोड करने के लिए समन्वय करें।",
-    "syncNow": "अभी समन्वय करें",
-    "syncing": "समन्वय हो रहा है...",
-    "syncCta": "अभी समन्वय करें",
-    "syncFailed": "समन्वय विफल",
-    "flagDisabled": "रडार अक्षम है",
-    "activationFailed": "सक्रियण विफल",
-    "feedVersion": "फीड संस्करण",
-    "feedTier": "स्तर",
-    "feedFetched": "अंतिम प्राप्त",
-    "tierLive": "लाइव (वास्तविक समय)",
-    "tierCommunity": "समुदाय (30-दिन की देरी)",
-    "activateTitle": "रडार सक्रिय करें",
-    "activateDescription": "__MISSING__:Compare Community and live access, understand what your installation exchanges, and then choose how to activate Radar.",
-    "activateButton": "__MISSING__:Activate Community",
-    "activating": "सक्रियण हो रहा है...",
-    "keySectionTitle": "Already have a supporter key?",
-    "keyInvalidFormatError": "Invalid key format. It must start with \"omr_\" followed by 40 hex characters.",
-    "activateWithKeyButton": "Activate supporter",
-    "changeKeyButton": "Change key",
-    "claimSectionTitle": "Don't have a supporter key yet?",
-    "contributorButton": "I'm a contributor",
-    "contributorHint": "__MISSING__:GitHub OAuth checks the current weekly ranking: Top 10 get 365 days and ranks 11–100 get 90 days. PR count alone never grants access outside the Top 100.",
-    "supporterButton": "Support the project",
-    "supporterHint": "__MISSING__:One-time 6-month, 1-year, and lifetime options have no automatic renewal; eligible periods accumulate and lifetime prevails.",
-    "colProvider": "प्रदाता",
-    "colModel": "मॉडल",
-    "colQuota": "कोटा",
-    "colContext": "संदर्भ",
-    "colCapabilities": "क्षमताएँ",
-    "colTos": "ToS जोखिम",
-    "colLimits": "__MISSING__:Rate limits",
-    "trainsOnPrompts": "__MISSING__:Trains on prompts",
-    "trainsOnPromptsHelp": "__MISSING__:This provider's terms state it may train on the prompts you send. Models without this badge either state they do not, or do not document it — an absent statement is not a guarantee.",
-    "newBadge": "नया",
-    "setupGuide": "सेटअप गाइड",
-    "disabledByFeed": "रडार फीड द्वारा अक्षम",
-    "capTools": "उपकरण",
-    "capVision": "दृष्टि",
-    "capThinking": "सोच",
-    "catalogTab": "Catalog",
-    "freeCreditsTab": "Free credits",
-    "freeCreditsSubtitle": "Referral links from Radar-tracked providers — using them costs you nothing extra and helps support OmniRoute.",
-    "fixedLinksEmpty": "No referral links available yet. Sync Radar to check for updates.",
-    "requiredActionLabel": "What to do:",
-    "claimButton": "Claim credits",
-    "campaignsTitle": "Limited-time campaigns",
-    "campaignsEmpty": "No active campaigns right now — check back later.",
-    "campaignsUpsellCommunity": "Limited-time campaigns are a supporter extra. Everything on this page's fixed links stays free for everyone.",
-    "campaignsValidUntil": "Valid until {date}",
-    "colActions": "Actions",
-    "localBadge": "local",
-    "editModel": "Edit",
-    "saveModel": "Save",
-    "cancelEdit": "Cancel",
-    "resetModel": "Reset local changes",
-    "hideModel": "Hide",
-    "restoreModel": "Restore",
-    "hiddenModelsTitle": "Hidden models",
-    "modelDisplayName": "Local display name",
-    "modelEnabled": "Enabled locally",
-    "localStateSaveFailed": "Failed to save local Radar settings",
-    "guidedCombos": "Guided combos",
-    "offers": "Offers",
-    "intel": "Intel",
-    "accessScaleTitle": "__MISSING__:Understand Radar access before activating",
-    "accessScaleIntro": "__MISSING__:Radar stays network-inert until you opt in. Choose Community access or activate a personal supporter key after reviewing these rules.",
-    "accessCommunityRule": "__MISSING__:Community — no key required: the complete catalog with a 30-day delay.",
-    "accessSingleUseRule": "__MISSING__:Star + follow — after GitHub OAuth verifies both, your GitHub account receives one live catalog read; then access returns to Community. This one-time access cannot be reissued for that account.",
-    "accessContributorRule": "__MISSING__:Contributors — merged PRs, commits, and lines only order the weekly ranking. Top 10 receive 365 days; ranks 11–100 receive 90 days; contributors outside the Top 100 receive no grant regardless of PR count. Leaving the ranking never shortens time already granted.",
-    "accessSupporterRule": "__MISSING__:Supporters — one-time purchases grant 6 months, 1 year, or lifetime with no automatic renewal. Purchases, donations, contributor periods, and manual grants accumulate; lifetime always prevails.",
-    "accessUseTitle": "__MISSING__:Personal use, recovery, and review",
-    "accessInstallationRule": "__MISSING__:Personal license — use the key on one active installation at a time. OmniRoute does not fingerprint hardware. Recovery revokes and replaces a lost key without resetting its expiration.",
-    "accessAbuseRule": "__MISSING__:Abuse review — the 4th distinct IP in 24 hours creates a manual review flag only; it never blocks or revokes a key automatically.",
-    "accessOffersRule": "__MISSING__:Live offers are manually curated and may change or expire.",
-    "privacyTitle": "__MISSING__:What Radar exchanges",
-    "privacyDownloadsRule": "__MISSING__:Downloads — your installation receives cryptographically signed catalog and referral metadata; a valid live key also unlocks signed offers and Intel.",
-    "privacySendsRule": "__MISSING__:Sends — server-side sync sends the supporter key as a Bearer token, and the HTTPS infrastructure receives the connection IP. Feed-request accounting stores neither value raw: it keeps key hashes, aggregate usage, and a daily rotating truncated IP HMAC for abuse review.",
-    "privacyNeverRule": "__MISSING__:Never collected — prompts, responses, conversations, provider credentials, model traffic, uptime, latency, and local provider configuration are never sent to Radar."
-  },
-  "radarCombosPage": {
-    "title": "Radar guided combos",
-    "subtitle": "Create priority fallbacks from equivalent free models curated by Radar.",
-    "backToRadar": "Back to Radar",
-    "loading": "Loading combo suggestions...",
-    "familyLabel": "Model family",
-    "modelsLabel": "Priority order",
-    "strategyReason": "Priority uses the largest recurring free budget first, then falls back across active providers.",
-    "generateButton": "Generate combo",
-    "generating": "Generating...",
-    "alreadyCreated": "Already created",
-    "created": "Combo created",
-    "noSuggestions": "No eligible model family currently has active connections to at least two providers.",
-    "catalogRequired": "Sync the Radar catalog first to load curated model families.",
-    "loadFailed": "Failed to load Radar combo suggestions.",
-    "createFailed": "Failed to create the combo. Review your provider connections and try again."
-  },
-  "radarSetupPage": {
-    "title": "प्रदाता सेटअप",
-    "setupTitle": "सेटअप: {provider}",
-    "setupSubtitle": "इस प्रदाता को कॉन्फ़िगर करने के लिए नीचे दिए गए चरणों का पालन करें",
-    "loading": "लोड हो रहा है...",
-    "loadFailed": "सेटअप डेटा लोड करने में विफल",
-    "flagDisabled": "रडार अक्षम है",
-    "providerNotFound": "कैटलॉग में प्रदाता \"{provider}\" नहीं मिला",
-    "noProvider": "कोई प्रदाता निर्दिष्ट नहीं किया गया। कैटलॉग पर लौटें और एक प्रदाता चुनें।",
-    "backToCatalog": "कैटलॉग पर वापस जाएं",
-    "providerConfigured": "प्रदाता कॉन्फ़िगर किया गया है और तैयार है",
-    "getApiKey": "अपना API कुंजी प्राप्त करें",
-    "setupSteps": "सेटअप चरण",
-    "noGuide": "इस प्रदाता के लिए कोई सेटअप गाइड उपलब्ध नहीं है।",
-    "visitDocs": "प्रदाता दस्तावेज़ पर जाएं",
-    "testConnection": "कनेक्शन का परीक्षण करें",
-    "testDescription": "सुनिश्चित करें कि आपका कनेक्शन सही ढंग से काम कर रहा है।",
-    "testButton": "कनेक्शन का परीक्षण करें",
-    "testing": "परीक्षण हो रहा है...",
-    "testSuccess": "कनेक्शन सफल!",
-    "testFailed": "कनेक्शन परीक्षण विफल",
-    "addConnection": "कनेक्शन जोड़ें",
-    "addConnectionDescription": "क्या आपके पास अभी तक कोई कनेक्शन नहीं है? प्रदाता डैशबोर्ड में एक जोड़ें।",
-    "addConnectionLink": "प्रदाताओं पर जाएं →"
-  },
-  "resilienceConnections": {
-    "title": "Resiliensi Koneksi",
-    "reassuranceTitle": "Your connections recover automatically",
-    "reassuranceDetail": "Usually no action is needed. OmniRoute temporarily rests a connection after failures, then safely tries it again.",
-    "plainStates": {
-      "healthy": "Requests can be sent",
-      "coolingDown": "Trying again soon",
-      "lockedOut": "Needs your attention"
-    },
-    "table": {
-      "status": "Status",
-      "provider": "Penyedia",
-      "connectionId": "Koneksi",
-      "authType": "Auth",
-      "backoffLevel": "Backoff",
-      "cooldown": "Cooldown",
-      "lastError": "Kesalahan Terakhir",
-      "lockouts": "Penguncian",
-      "healthy": "Sehat",
-      "coolingDown": "Cooldown",
-      "circuitOpen": "Sirkuit Terbuka",
-      "recovering": "Memulihkan",
-      "degraded": "Terdegradasi",
-      "terminal": "Terminal",
-      "unknown": "Tidak Diketahui",
-      "never": "-"
-    },
-    "timeline": {
-      "title": "Transisi Breaker",
-      "window": "Jendela",
-      "window1h": "1j",
-      "window6h": "6j",
-      "window24h": "24j",
-      "empty": "Tidak ada transisi dalam jendela terpilih",
-      "currentState": "Status Saat Ini",
-      "state": {
-        "open": "Terbuka",
-        "half_open": "Setengah Terbuka",
-        "closed": "Tertutup",
-        "degraded": "Terdegradasi"
-      },
-      "reason": {
-        "timeout-elapsed": "Waktu Habis",
-        "success-recovery": "Pemulihan karena Sukses",
-        "manual-reset": "Reset Manual",
-        "probe-success": "Probe Berhasil",
-        "recovery": "Pemulihan",
-        "probe-failed": "Probe Gagal"
-      }
-    },
-    "detail": {
-      "title": "Detail Koneksi",
-      "metadata": "Metadata",
-      "cooldown": "Cooldown",
-      "lastError": "Kesalahan Terakhir",
-      "breaker": "Circuit Breaker",
-      "lockouts": "Penguncian Model",
-      "rateLimitedUntil": "Dibatasi Kecepatan Sampai",
-      "backoffLevel": "Level Backoff",
-      "remaining": "Sisa",
-      "noLockouts": "Tidak ada penguncian aktif",
-      "provider": "Penyedia",
-      "id": "ID",
-      "authType": "Tipe Auth",
-      "priority": "Prioritas",
-      "isActive": "Aktif",
-      "errorCode": "Kode Kesalahan",
-      "lastErrorAt": "Kesalahan Terakhir Pada",
-      "yes": "Ya",
-      "no": "Tidak",
-      "close": "Tutup",
-      "never": "-",
-      "failureCount": "Jumlah Kegagalan",
-      "retryAfterMs": "Coba Lagi Setelah (ms)",
-      "lastFailureKind": "Tipe Kegagalan Terakhir"
-    },
-    "empty": {
-      "title": "Tidak ada koneksi",
-      "description": "Koneksi penyedia akan muncul di sini."
-    },
-    "loading": {
-      "title": "Memuat",
-      "description": "Mengambil status resiliensi koneksi..."
-    },
-    "summary": {
-      "total": "{count} koneksi",
-      "coolingDown": "{count} dalam cooldown",
-      "unhealthyBreakers": "{count} breaker belum tertutup",
-      "capped": "menampilkan 1000 pertama"
-    },
-    "pollingNote": "Catatan: melihat halaman ini memicu pemulihan lambat breaker (probe HALF_OPEN). Diperbarui setiap 30 detik.",
-    "retry": "Coba Lagi",
-    "pollErrorLocalOnly": "Halaman ini hanya dapat diakses dari localhost atau LAN (LOCAL_ONLY).",
-    "pollErrorStopped": "Polling dihentikan: server menolak permintaan (404/403).",
-    "pollErrorTransient": "Kesalahan mengambil data: mencoba lagi secara otomatis.",
-    "degraded": {
-      "message": "Data sebagian: sumber tidak tersedia: {sources}",
-      "source": {
-        "database": "Basis Data",
-        "circuitBreaker": "Circuit Breaker",
-        "modelLockouts": "Penguncian Model",
-        "count": "Jumlah Koneksi"
-      }
-    }
-  },
-  "featureFlagCapabilityFilterEnabledDescription": "Tolak permintaan sebelum pengiriman ketika model target tidak memiliki kemampuan yang diperlukan (visi, alat, output terstruktur, jendela konteks). Melindungi permintaan penyedia tunggal langsung yang melewati filter kompatibilitas lapisan kombinasi.",
-  "featureFlagDisableContextWindowChecksDescription": "Skip OmniRoute's local context-window and max-input-token check for direct single-model requests. Upstream providers still enforce their actual limits. Prompt compression and output-token caps remain active.",
-  "publicSystem": {
-    "notFound": {
-      "title": "Halaman tidak ditemukan",
-      "description": "Halaman yang Anda cari tidak ada atau telah dipindahkan.",
-      "dashboardAriaLabel": "Kembali ke dasbor",
-      "statusAriaLabel": "Buka halaman status sistem",
-      "systemStatus": "Status Sistem"
-    },
-    "error": {
-      "title": "Kesalahan Server Internal",
-      "description": "Terjadi kesalahan saat memproses permintaan Anda. Tim kami telah diberitahu dan sedang bekerja untuk memperbaikinya.",
-      "errorId": "ID Kesalahan: {id}",
-      "detailsAriaLabel": "Rincian kesalahan",
-      "retryAriaLabel": "Coba muat ulang halaman tersebut",
-      "tryAgain": "Coba Lagi",
-      "dashboardAriaLabel": "Kembali ke dasbor",
-      "statusAriaLabel": "Buka status sistem",
-      "systemStatus": "Status Sistem"
-    },
-    "globalError": {
-      "title": "Sesuatu telah salah",
-      "description": "Terjadi kesalahan yang tidak terduga. Ini telah dicatat dan tim kami akan menyelidiki.",
-      "detailsAriaLabel": "Rincian kesalahan",
-      "retryAriaLabel": "Coba muat ulang halaman tersebut",
-      "tryAgain": "Coba Lagi",
-      "statusAriaLabel": "Buka status sistem",
-      "systemStatus": "Status Sistem"
-    },
-    "offline": {
-      "title": "Masalah Konektivitas",
-      "description": "OmniRoute tidak dapat mengakses jaringan saat ini. Periksa pengaturan internet, VPN, atau proksi Anda.",
-      "connectionRestored": "Koneksi dipulihkan",
-      "offlineModeDetected": "Mode offline terdeteksi",
-      "retryConnection": "Coba Kembali Koneksi",
-      "openStatusPage": "Buka Halaman Status"
-    },
-    "maintenance": {
-      "title": "Pemeliharaan Terjadwal",
-      "description": "Beberapa layanan sementara tidak tersedia saat pemeliharaan sedang berlangsung. Routing inti biasanya tetap online, tetapi fitur manajemen mungkin mengalami penurunan.",
-      "suggestion1": "Coba lagi setelah beberapa menit.",
-      "suggestion2": "Periksa indikator kesehatan saat ini dan status penyedia sebelum mencoba lagi.",
-      "systemStatus": "Lihat Status Sistem",
-      "healthDashboard": "Buka Dasbor Kesehatan"
-    },
-    "status": {
-      "title": "Status Sistem",
-      "description": "Snapshot operasional langsung untuk layanan inti OmniRoute.",
-      "loadingHealth": "Memuat metrik kesehatan...",
-      "failedToLoad": "Gagal memuat kesehatan sistem.",
-      "unableToReachHealth": "Tidak dapat mengakses endpoint kesehatan. Periksa konektivitas dan coba lagi.",
-      "healthCheckFailed": "Pemeriksaan Kesehatan Gagal",
-      "openConnectivityHelp": "Buka Bantuan Konektivitas",
-      "maintenanceInfo": "Info Pemeliharaan",
-      "service": "Layanan",
-      "unknown": "tidak dikenal",
-      "notAvailable": "n/a",
-      "providersTracked": "Penyedia Yang Dilacak",
-      "circuitBreakerState": "Status Pemutus Sirkuit Penyedia",
-      "lastUpdate": "Pembaruan terakhir: {timestamp}",
-      "uptimeMinutes": "{minutes}m",
-      "uptimeHoursMinutes": "{hours}j {minutes}m"
-    },
-    "statusPages": {
-      "400": {
-        "title": "Permintaan Buruk",
-        "description": "Payload permintaan tidak valid atau tidak lengkap.",
-        "suggestion1": "Periksa kolom yang diperlukan dan format payload sebelum mencoba lagi.",
-        "suggestion2": "Jika Anda menggunakan API, validasi skema JSON secara lokal.",
-        "suggestion3": "Jika ini terus terjadi, buka permintaan di Translator Playground untuk memeriksa payload.",
-        "primaryAction": "Buka Dokumentasi",
-        "secondaryAction": "Buka Penerjemah"
-      },
-      "401": {
-        "title": "Tidak Berwenang",
-        "description": "Autentikasi diperlukan untuk mengakses sumber daya ini.",
-        "suggestion1": "Masuk kembali dan coba lagi operasi tersebut.",
-        "suggestion2": "Untuk panggilan API, pastikan token Bearer ada dan valid.",
-        "suggestion3": "Jika token baru saja diputar, perbarui kredensial klien Anda.",
-        "primaryAction": "Pergi ke Login",
-        "secondaryAction": "Kelola Kunci API"
-      },
-      "403": {
-        "title": "Dilarang",
-        "description": "Permintaan Anda dipahami, tetapi akses ditolak oleh kebijakan.",
-        "suggestion1": "Periksa aturan allowlist/blocklist IP di pengaturan.",
-        "suggestion2": "Verifikasi model dan kebijakan anggaran yang ditetapkan untuk kunci API Anda.",
-        "suggestion3": "Minta kepada administrator untuk memberikan ruang izin yang diperlukan.",
-        "primaryAction": "Bantuan Akses Terbuka",
-        "secondaryAction": "Buka Pengaturan Keamanan"
-      },
-      "408": {
-        "title": "Waktu Permintaan Habis",
-        "description": "Server tidak menerima permintaan lengkap tepat waktu.",
-        "suggestion1": "Coba ulang permintaan dengan payload yang lebih kecil.",
-        "suggestion2": "Periksa stabilitas jaringan Anda dan latensi VPN/proxy.",
-        "suggestion3": "Untuk operasi yang lama, aktifkan streaming atau bagi permintaan.",
-        "primaryAction": "Buka Panduan Endpoint",
-        "secondaryAction": "Periksa Status Jaringan"
-      },
-      "429": {
-        "title": "Terlalu Banyak Permintaan",
-        "description": "Batas penilaian telah terlampaui untuk klien, kunci, atau penyedia ini.",
-        "suggestion1": "Tunggu untuk cooldown dan coba lagi setelah interval yang disarankan.",
-        "suggestion2": "Beralih ke kombinasi dengan penyedia cadangan.",
-        "suggestion3": "Atur profil ketahanan penyedia/batas laju di pengaturan.",
-        "primaryAction": "Buka Pengaturan Ketahanan",
-        "secondaryAction": "Buka Kombinasi"
-      },
-      "500": {
-        "title": "Kesalahan Server Internal",
-        "description": "Terjadi kesalahan tidak terduga di sisi server saat memproses permintaan Anda.",
-        "suggestion1": "Coba lagi dalam beberapa detik.",
-        "suggestion2": "Periksa telemetri kesehatan dan log server untuk ID permintaan yang berkorelasi.",
-        "suggestion3": "Jika terus-menerus, laporkan masalah dengan cap waktu dan konteks permintaan.",
-        "primaryAction": "Buka Dasbor Kesehatan",
-        "secondaryAction": "Buka Log"
-      },
-      "502": {
-        "title": "Gerbang Buruk",
-        "description": "Penyedia hulu atau integrasi gateway mengembalikan respons yang tidak valid.",
-        "suggestion1": "Coba lagi dengan penyedia lain atau rute kombinasi aktif.",
-        "suggestion2": "Periksa kredensial penyedia dan ketersediaan model.",
-        "suggestion3": "Periksa keluaran penerjemah jika konversi format terlibat.",
-        "primaryAction": "Buka Penyedia",
-        "secondaryAction": "Buka Penerjemah"
-      },
-      "503": {
-        "title": "Layanan Tidak Tersedia",
-        "description": "Layanan tidak tersedia sementara karena pemeliharaan atau ketergantungan yang menurun.",
-        "suggestion1": "Tunggu sebentar dan coba lagi.",
-        "suggestion2": "Periksa pemberitahuan pemeliharaan dan status sistem.",
-        "suggestion3": "Gunakan penyedia cadangan jika alur kerja Anda sensitif terhadap latensi.",
-        "primaryAction": "Detail Pemeliharaan",
-        "secondaryAction": "Status Sistem"
-      }
-    }
-  },
-  "kiroAuthModal": {
-    "title": "Sambungkan {providerLabel}",
-    "chooseMethod": "Pilih metode otentikasi Anda:",
-    "builderId": "AWS Builder ID",
-    "builderDescription": "Direkomendasikan untuk sebagian besar pengguna. Masuk dengan akun AWS yang terhubung ke {providerLabel}.",
-    "organization": "Organisasi Anda (AWS IAM Identity Center)",
-    "organizationDescription": "Gunakan URL awal SSO perusahaan Anda (contoh: {url}).",
-    "googleAccount": "Akun Google",
-    "googleDescription": "Masuk dengan akun Google Anda.",
-    "githubAccount": "Akun GitHub",
-    "githubDescription": "Masuk dengan akun GitHub Anda.",
-    "importToken": "Impor Token",
-    "importDescription": "Tempelkan token penyegaran yang diekspor dari {providerLabel}.",
-    "apiKey": "Kunci API",
-    "apiKeyDescription": "Tempelkan kunci API {providerLabel} / CodeWhisperer yang memiliki masa hidup panjang. Ini disimpan sebagai kredensial bearer tanpa token penyegaran; penemuan profil dilakukan dengan upaya terbaik.",
-    "idcStartUrl": "URL Mulai IDC",
-    "idcStartUrlPlaceholder": "https://your-org.awsapps.com/start",
-    "idcStartUrlDescription": "URL Pusat Identitas AWS IAM Organisasi Anda",
-    "awsRegion": "Wilayah AWS",
-    "regionPlaceholder": "us-east-1",
-    "idcRegionDescription": "Wilayah AWS untuk Pusat Identitas Anda (default: us-east-1)",
-    "continue": "Lanjutkan",
-    "back": "Kembali",
-    "autoDetecting": "Mendeteksi token secara otomatis...",
-    "readingCredentials": "Membaca kredensial {providerLabel} dari cache AWS SSO",
-    "tokenNotDetected": "Token {providerLabel} tidak terdeteksi secara otomatis. Silakan tempelkan token penyegaran Anda secara manual.",
-    "refreshToken": "Token Segar",
-    "tokenPlaceholder": "Token akan diisi secara otomatis...",
-    "importing": "Mengimpor...",
-    "apiKeyPlaceholder": "Tempelkan kunci API {providerLabel} Anda...",
-    "apiKeyStoredDescription": "Disimpan terenkripsi sebagai kredensial pembawa yang bertahan lama. Tidak ada alur penyegaran.",
-    "apiKeyRegionDescription": "Wilayah AWS untuk kunci (default: us-east-1)",
-    "validating": "Memvalidasi...",
-    "validateAndSaveApiKey": "Validasi dan Simpan Kunci API",
-    "errorAutoDetect": "Tidak dapat mendeteksi token secara otomatis",
-    "errorAutoDetectFailed": "Gagal mendeteksi token secara otomatis",
-    "errorRefreshTokenRequired": "Silakan masukkan token penyegaran",
-    "errorImportFailed": "Impor gagal",
-    "errorApiKeyRequired": "Silakan masukkan kunci API Kiro",
-    "errorApiKeyImportFailed": "Impor kunci API gagal",
-    "errorIdcStartUrlRequired": "Silakan masukkan URL awal IDC Anda"
-  },
-  "kiroSocialOAuthModal": {
-    "title": "Sambungkan {providerLabel} melalui {providerName}",
-    "errorStartAuthorization": "Gagal memulai otorisasi",
-    "errorAuthorizationExpired": "Otorisasi telah kedaluwarsa. Mulai alur login lagi.",
-    "errorAuthorizationFailed": "Otorisasi gagal",
-    "initializing": "Menginisialisasi...",
-    "settingUp": "Mengatur otentikasi {providerName}",
-    "openIncognito": "Buka tautan ini di jendela Incognito",
-    "incognitoDescription": "Gunakan jendela Incognito/Pribadi untuk menghindari konflik sesi dengan akun yang ada.",
-    "copyLink": "Salin tautan",
-    "verificationCode": "Kode verifikasi",
-    "waiting": "Menunggu otorisasi...",
-    "cancel": "Batalkan",
-    "successTitle": "Terhubung Dengan Sukses!",
-    "successMessage": "Akun {providerLabel} Anda melalui {providerName} telah terhubung.",
-    "done": "Selesai",
-    "errorTitle": "Koneksi Gagal",
-    "close": "Tutup"
-  },
-  "traeAuthModal": {
-    "errorAuthorizationFailed": "Otorisasi gagal",
-    "errorPopupBlocked": "Popup diblokir — izinkan popup untuk situs ini, atau tempel token secara manual di bawah.",
-    "errorPopupClosed": "Jendela otorisasi ditutup sebelum selesai.",
-    "errorAccessTokenRequired": "Token akses diperlukan.",
-    "errorImportFailed": "Impor gagal",
-    "title": "Connect Trae SOLO",
-    "authorizeDescription": "Otorisasi melalui <code>trae.ai</code> dalam jendela pop-up. Jendela pop-up akan menutup dirinya sendiri setelah token diimpor.",
-    "authorizeImportant": "<strong>Penting:</strong> Anda harus masuk ke <code>trae.ai</code> di <em>browser</em> ini terlebih dahulu. Halaman otorisasi hanya mengonfirmasi sesi yang ada — tidak dapat masuk untuk Anda. Jika Anda melihat \"Login Gagal\", klik \"Buka solo.trae.ai\", masuk, lalu kembali ke sini.",
-    "waitingForAuthorization": "Menunggu trae.ai…",
-    "authorizeWithBrowser": "Otorisasi dengan Browser",
-    "openSoloTrae": "Buka solo.trae.ai",
-    "orPasteManually": "atau tempel token secara manual",
-    "manualInstructions": "Masuk ke <code>solo.trae.ai</code>, buka DevTools → Jaringan, kirim pesan obrolan apa pun, dan salin JWT dari header permintaan <code>Authorization: Cloud-IDE-JWT {tokenPlaceholder}</code>. Masa berlaku JWT adalah ~14 hari. Bidang identitas opsional berasal dari <code>common_params</code> dalam body permintaan yang sama.",
-    "accessTokenLabel": "Token Akses (Cloud-IDE-JWT)",
-    "webId": "ID Web",
-    "optional": "opsional",
-    "bizUserId": "ID Pengguna Biz",
-    "userUniqueId": "ID Unik Pengguna",
-    "scope": "Lingkup",
-    "tenant": "Penyewa",
-    "region": "Wilayah",
-    "importing": "Mengimpor…",
-    "importToken": "Impor Token",
-    "cancel": "Batalkan"
-  },
-  "sharedComponents": {
-    "distributeProxies": {
-      "distributing": "Mendistribusikan...",
-      "complete": "Lengkap",
-      "defaultLabel": "Sebarkan Proksi"
-    }
-  },
-  "providerTest": {
-    "dialogLabel": "Uji {provider}",
-    "deprecated": "tidak lagi digunakan",
-    "risk": "risiko",
-    "close": "Tutup",
-    "model": "Model",
-    "key": "Kunci",
-    "defaultKey": "default",
-    "clearConversation": "Hapus percakapan",
-    "clear": "Bersihkan",
-    "tabs": {
-      "test": "Tes",
-      "logs": "Log"
-    },
-    "loadingLogs": "Memuat log…",
-    "failedToLoadLogs": "Gagal memuat log",
-    "noLogsYet": "Belum ada log",
-    "noLogsDescription": "Kirim pesan uji dari tab Uji — log untuk penyedia ini akan muncul di sini.",
-    "openFullLogs": "Buka halaman log lengkap",
-    "live": "Langsung",
-    "tailingLast": "menampilkan {count} terakhir",
-    "refreshNow": "Segarkan sekarang",
-    "refresh": "Segarkan",
-    "unknownRequester": "pemberi permintaan tidak dikenal",
-    "fields": {
-      "timestamp": "Stempel Waktu",
-      "status": "Status",
-      "duration": "Durasi",
-      "model": "Model",
-      "requestedModel": "Model yang diminta",
-      "provider": "Penyedia",
-      "requester": "Pemohon",
-      "tokens": "Token"
-    }
-  },
-  "proxyLog": {
-    "detailAriaLabel": "Detail log proxy",
-    "event": "Acara Proxy",
-    "close": "Tutup modal detail proxy",
-    "time": "Waktu",
-    "latency": "Latensi",
-    "clientIp": "IP Klien",
-    "proxy": "Proxy",
-    "direct": "Langsung",
-    "type": "Tipe",
-    "level": "Tingkat",
-    "provider": "Penyedia",
-    "tlsFingerprint": "Jejak TLS",
-    "directNative": "Langsung",
-    "targetUrl": "URL Target",
-    "error": "Kesalahan",
-    "configuration": "Konfigurasi Proxy"
-  },
-  "requestTimeline": {
-    "title": "Garis Waktu Permintaan",
-    "modes": {
-      "follow": "Ikuti",
-      "followDescription": "Sumbu menggulir ke kiri, garis SEKARANG tetap di 75%",
-      "now": "Sekarang",
-      "nowDescription": "Lompat ke waktu saat ini, garis NOW direset ke tengah",
-      "pan": "Panci",
-      "panDescription": "Seret untuk menjelajahi, latar belakang beku"
-    },
-    "reset": "Atur Ulang",
-    "started": "Dimulai",
-    "ended": "Selesai",
-    "duration": "Durasi",
-    "status": "Status",
-    "provider": "Penyedia",
-    "tokens": "Token",
-    "active": "Aktif",
-    "other": "Lainnya",
-    "tenMinutes": "10menit",
-    "hour": "jam",
-    "day": "hari",
-    "unknownModel": "tidak diketahui",
-    "pending": "tertunda"
-  },
-  "metadata": {
-    "compressionTitle": "Kompresi",
-    "compressionDescription": "Konfigurasikan pengaturan kompresi konteks untuk mengurangi penggunaan token dan biaya.",
-    "relayTitle": "OmniRoute — Proksi Relay",
-    "relayDescription": "Endpoint proksi relay tanpa server untuk infrastruktur AI Anda",
-    "trafficInspectorTitle": "Traffic Inspector — OmniRoute",
-    "trafficInspectorDescription": "Pantau panggilan LLM + debug lalu lintas HTTPS aplikasi mana pun"
-  },
-  "conductor": {
-    "title": "Conductor — Armada CLI-agent",
-    "subtitle": "OmniConductor hub: pelari, antrean tugas dan dewan, langsung",
-    "runners": "Pelari",
-    "tasks": "Tugas",
-    "colName": "Nama",
-    "colClis": "CLIs",
-    "colStatus": "Status",
-    "colTask": "Tugas",
-    "colMode": "Mode",
-    "colRunner": "Pelari",
-    "colSummary": "Ringkasan",
-    "online": "daring",
-    "offline": "tidak terhubung",
-    "draining": "menguras",
-    "hubOffline": "Conductor hub offline atau tidak terkonfigurasi (CONDUCTOR_HUB_URL) — tidak menunjukkan apa-apa selain data yang usang.",
-    "noRunners": "Tidak ada pelari yang terdaftar",
-    "noTasks": "Belum ada tugas",
-    "detailTitle": "Detail Tugas",
-    "prompt": "Permintaan",
-    "branch": "Cabang",
-    "fetchHint": "Ambil hasil dengan: git fetch origin {branch}",
-    "council": "Dewan",
-    "candidates": "Kandidat",
-    "cancel": "Batalkan tugas",
-    "cancelConfirmTitle": "Batalkan tugas ini?",
-    "cancelConfirmMessage": "Hub akan membatalkan eksekusi pada runner. Ini tidak dapat dibatalkan.",
-    "cancelFailed": "Hub menolak pembatalan",
-    "close": "Tutup",
-    "error": "Kesalahan",
-    "faroTitle": "Faro — juru bicara armada",
-    "faroSubtitle": "Obrolan dan suara, berakar pada peristiwa armada nyata. Perintah yang merusak selalu meminta konfirmasi.",
-    "faroEmpty": "Tanya tentang armada — misalnya \"bagaimana keadaan armada?\"",
-    "faroPending": "Faro meminta konfirmasi",
-    "faroPlaceholder": "bicara dengan Faro…",
-    "faroSend": "kirim",
-    "faroOffline": "Faro (juru bicara) sedang offline",
-    "yes": "Ya",
-    "no": "Tidak",
-    "pushToTalk": "Tahan untuk berbicara",
-    "speakAnswers": "berbicara jawaban",
-    "voiceModels": "Model Suara (penyedia/model dari OmniRoute ini)",
-    "voiceIdle": "bicara",
-    "voiceListening": "mendengarkan…",
-    "voiceThinking": "berpikir…",
-    "voiceSpeaking": "berbicara…",
-    "sttFailed": "Transkripsi gagal (periksa model/penyedia STT)",
-    "ttsFailed": "Sintesis suara gagal (periksa model/penyedia TTS)",
-    "micDenied": "Mikrofon tidak tersedia atau izin ditolak"
-  },
-  "orchestration": {
-    "title": "Orkestrasi",
-    "description": "Semua yang sedang dijalankan OmniRoute saat ini — agen, armada, dan perutean",
-    "tabAgents": "Agen",
-    "tabRouting": "Perutean",
-    "tabOverview": "Ikhtisar",
-    "showCompleted": "Tampilkan yang selesai",
-    "searchPlaceholder": "Cari tugas…",
-    "filterStates": "Status",
-    "filterSources": "Sumber",
-    "filterProviders": "Penyedia",
-    "clearFilters": "Hapus filter",
-    "sourceCloudAgent": "Agen Cloud",
-    "sourceA2A": "A2A",
-    "sourceConductor": "Konduktor",
-    "sourceStale": "Kedaluwarsa sejak {since}",
-    "sourceOffline": "Offline",
-    "sourceCollapse": "Ciutkan",
-    "sourceExpand": "Perluas",
-    "stateQueued": "Dalam antrean",
-    "stateRunning": "Berjalan",
-    "stateWaitingApproval": "Menunggu persetujuan",
-    "stateSucceeded": "Berhasil",
-    "stateFailed": "Gagal",
-    "stateCancelled": "Dibatalkan",
-    "overflowMore": "+{count} lainnya",
-    "emptyTitle": "Belum ada yang berjalan",
-    "emptyCloudAgentCta": "Siapkan Agen Cloud",
-    "emptyA2ACta": "Buka A2A",
-    "emptyConductorCta": "Buka Konduktor",
-    "drawerObjective": "Tujuan",
-    "drawerTimeline": "Linimasa",
-    "drawerMetrics": "Metrik",
-    "drawerResult": "Hasil",
-    "drawerActions": "Tindakan",
-    "drawerClose": "Tutup",
-    "copyTrace": "Salin trace JSON",
-    "actionApprove": "Setujui rencana",
-    "actionCancel": "Batal",
-    "actionSeeInGraph": "Lihat di grafik",
-    "actionDone": "Tindakan diterapkan",
-    "actionFailed": "Tindakan gagal: {error}",
-    "detailFailed": "Gagal memuat detail: {error}",
-    "mirroredInA2A": "Dicerminkan di A2A"
-  },
-  "cliproxyProviderExposure": {
-    "title": "Paparan Penyedia",
-    "description": "Ekspos model CLIProxyAPI sebagai target routing di bawah prefix <prefix>cliproxyapi/</prefix> prefix.",
-    "label": "Expose sebagai <prefix>cliproxyapi/...</prefix>",
-    "hint": "Saat diaktifkan, model yang ditemukan muncul di pemilih penyedia di seluruh OmniRoute.",
-    "updateFailed": "Gagal memperbarui (HTTP {status})",
-    "networkError": "Kesalahan jaringan — tidak dapat memperbarui pengaturan eksposur penyedia"
-  },
-  "radarOffersPage": {
-    "title": "Supporter offers",
-    "subtitle": "Official discounts, credits, trials, and reviewed partner benefits from Radar.",
-    "backToRadar": "Back to Radar",
-    "loading": "Loading offers...",
-    "refresh": "Refresh offers",
-    "refreshing": "Refreshing...",
-    "loadFailed": "We couldn't refresh offers. The last verified local cache is kept.",
-    "empty": "No active offers are available right now.",
-    "keyRequiredTitle": "A supporter key is required",
-    "keyRequiredDescription": "Offers are a live Radar benefit. Add an existing supporter key on the Radar screen, verify your contributor status, or support the project to obtain one.",
-    "contributorButton": "I'm a contributor",
-    "supporterButton": "Support the project",
-    "partnerBadge": "Partner",
-    "officialBadge": "Official",
-    "conditionsLabel": "Conditions:",
-    "validUntil": "Valid until {date}",
-    "noExpiry": "No announced expiry",
-    "openOffer": "View offer",
-    "trialDays": "{days, plural, one {# day} other {# days}}"
-  },
-  "radarIntelPage": {
-    "title": "Radar Intel",
-    "subtitle": "Radar-owned ELO rankings and factual catalog movement.",
-    "backToRadar": "Back to Radar",
-    "loading": "Loading Intel...",
-    "refresh": "Refresh Intel",
-    "syncing": "Refreshing...",
-    "loadFailed": "We could not refresh Intel. The last verified local cache is kept.",
-    "empty": "No verified Intel snapshot is available yet.",
-    "supporterBadge": "Radar Supporter",
-    "methodology": "Methodology",
-    "eloMethod": "ELO, initial {initial}, K={factor}",
-    "freshness": "Catalog freshness",
-    "ageDays": "{days, plural, one {# day old} other {# days old}}",
-    "trend": "Catalog trend",
-    "modelDelta": "{current} models, +{added} / -{removed}",
-    "ranking": "Model ranking",
-    "noRankings": "No confirmed comparisons are available yet.",
-    "model": "Model",
-    "category": "Category",
-    "rating": "Rating",
-    "matches": "Matches",
-    "freshnessValues": {
-      "fresh": "Fresh",
-      "aging": "Aging",
-      "stale": "Stale"
-    },
-    "trendValues": {
-      "growing": "Growing",
-      "stable": "Stable",
-      "shrinking": "Shrinking"
-    }
-  },
-  "capabilityFilter": {
-    "visionMismatch": "Penyedia tidak mendukung visi untuk permintaan gambar ini",
-    "toolsMismatch": "Penyedia tidak mendukung pemanggilan alat",
-    "structuredOutputMismatch": "Penyedia tidak mendukung keluaran terstruktur",
-    "contextWindowMismatch": "Permintaan melebihi jendela konteks penyedia"
-  },
-  "cheaperInferenceSponsorBanner": {
-    "title": "Cheaper Inference is an OmniRoute Open Source Friend",
-    "description": "A cost-ranked gateway reselling dozens of frontier models behind one OpenAI-compatible endpoint — routing each request to the cheapest eligible provider, never above list price.",
-    "cta": "Get an API Key",
-    "partnerLinkNote": "Partner link",
-    "dismissAriaLabel": "Dismiss"
-  },
-  "featureFlagOmnirouteDisableThinkingLevelVariantsDescription": "Disable the generation of thinking level variants (e.g. -low, -medium, -high) in the /v1/models catalog."
-}