chore(quality): rebaseline file-size for #11448/#11495/#11561 growth

.env.example

@@ -925,11 +925,6 @@ NEXT_PUBLIC_ENABLE_SOCKS5_PROXY=true
 # web_fetch). Default: 60000. Used by: open-sse/mcp-server/fetchTimeout.ts
 # OMNIROUTE_MCP_UPSTREAM_TIMEOUT_MS=60000
 
-# Maximum number of local-corpus index instances cached in memory.
-# Used by: src/lib/localCorpus/configured.ts — bounds the LRU cache of
-# LocalCorpusIndex objects (one per indexed root directory). Default: 5.
-# OMNIROUTE_CORPUS_CACHE_SIZE=5
-
 # Model catalog sync interval in hours.
 # Used by: src/shared/services/modelSyncScheduler.ts — periodic model refresh.
 # Default: 24
@@ -3067,9 +3062,3 @@ QUOTA_STORE_DRIVER=sqlite
 # without a configured budget are always considered affordable. Requires the
 # provider_quota_state table (migration 148).
 # OMNIROUTE_QUOTA_AWARE_ROUTING=0
-
-# ─── LOCAL CORPUS (opt-in document index) ───
-# Size of the in-memory LRU index cache for the local document corpus used by
-# corpus-aware retrieval. Higher values keep more index entries hot.
-# Used by: src/lib/localCorpus/configured.ts
-# OMNIROUTE_CORPUS_CACHE_SIZE=5

AGENTS.md

@@ -46,7 +46,7 @@ Repository map and Reference Documentation sections below.
 
 ## Project at a Glance
 
-**OmniRoute** — unified AI proxy/router. One endpoint, 354 LLM providers, auto-fallback.
+**OmniRoute** — unified AI proxy/router. One endpoint, 353 LLM providers, auto-fallback.
 
 | Layer         | Location                | Purpose                                                                                                                                                                   |
 | ------------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

changelog.d/features/nimble-search-and-fetch.md

@@ -1 +0,0 @@
-- **feat(providers):** add **Nimble** as a web-search and web-fetch provider (`nimble-search`) — `/v1/search` routes to Nimble's search API at `lite` depth (locale, freshness and include/exclude domain filters mapped onto the shared request contract), and `/v1/web/fetch` routes to Nimble Extract, which covers all four fetch formats (`markdown`, `html`, `links`, `screenshot`) from a single call. One API key serves both surfaces.

changelog.d/fixes/11602-provider-allowlist.md

@@ -1 +0,0 @@
-- fix(handoff): enforce provider allowlist for universal handoff (#11602) — universal handoff now skips summarization when the selected summary model's provider is not included in the configured provider allowlist.

changelog.d/fixes/11603-search-analytics-response-hardening.md

@@ -1 +0,0 @@
-- **fix(dashboard):** Show a stable error state when Search Analytics returns an HTTP error or malformed data ([#11603](https://github.com/diegosouzapw/OmniRoute/pull/11603)) — thanks @pacocartones

changelog.d/fixes/11604-profile-xp-consistency.md

@@ -1 +0,0 @@
-- **fix(dashboard):** Keep the Profile level and progress aligned with aggregate XP, including bounded handling for invalid totals ([#11604](https://github.com/diegosouzapw/OmniRoute/pull/11604)) — thanks @pacocartones

changelog.d/fixes/11605-profile-hidden-badge-details.md

@@ -1 +0,0 @@
-- **fix(dashboard):** Prevent locked hidden badges from revealing their icon or opening private badge details before they are earned ([#11605](https://github.com/diegosouzapw/OmniRoute/pull/11605)) — thanks @pacocartones

changelog.d/fixes/11607-modal-focus-restoration.md

@@ -1 +0,0 @@
-- **fix(dashboard):** Restore keyboard focus after shared modals close and cancel delayed autofocus during cleanup ([#11607](https://github.com/diegosouzapw/OmniRoute/pull/11607)) — thanks @pacocartones

changelog.d/fixes/11610-datatable-keyboard-activation.md

@@ -1 +0,0 @@
-- **fix(dashboard):** Enable Enter and Space activation for clickable data-table rows without hijacking nested controls ([#11610](https://github.com/diegosouzapw/OmniRoute/pull/11610)) — thanks @pacocartones

changelog.d/fixes/11625-retired-pool.md

@@ -1 +0,0 @@
-- **fix(autoCombo,sse):** vendor-retired catalog ids are dropped from the auto-combo candidate pool and no longer win on leftover `arena_elo` / `user_override` rows; `getModelLifecycleDecision` consults `model-lifecycle.json` (prefix-stripped) so aggregator traffic is not `untracked` for ids the snapshot already knows ([#11625](https://github.com/diegosouzapw/OmniRoute/issues/11625))

config/quality/eslint-suppressions.json

@@ -3093,6 +3093,11 @@
       "count": 1
     }
   },
+  "src/sse/services/auth.ts": {
+    "@typescript-eslint/no-unused-vars": {
+      "count": 1
+    }
+  },
   "src/sse/services/model.ts": {
     "no-restricted-imports": {
       "count": 2

config/quality/file-size-baseline.json

@@ -435,7 +435,7 @@
     "src/shared/components/analytics/charts.tsx": 1346,
     "src/shared/services/cliRuntime.ts": 1459,
     "src/sse/handlers/chat.ts": 2493,
-    "src/sse/services/auth.ts": 3432,
+    "src/sse/services/auth.ts": 3376,
     "_rebaseline_2026_08_24_lasterror_provider_error_detail": "PR (ntdat812) own growth: src/sse/services/auth.ts 3344->3346 (+2). One line is the import of describeUpstreamFailure from @/shared/utils/upstreamError, which replaces the string-only collapse `typeof errorText === \"string\" ? errorText.slice(0, 100) : \"Provider error\"` at the single markAccountUnavailable chokepoint (net 0 lines there) — the logic itself lives in upstreamError.ts, next to the extractErrorMessage it reuses, so nothing else moved into this file. The second line is the repo's own lint-staged prettier pass splitting a pre-existing two-statements-on-one-line at getProviderCredentials (`invalidateManagedLease(...);      log.warn(...)`); it re-applies on any commit that touches this file, so it is not separable from the change. Covered by tests/unit/provider-error-detail-lastError.test.ts.",
     "_rebaseline_2026_08_23_11186_synced_inventory_routing": "PR #11186 (pacocartones) own growth: src/sse/services/auth.ts 3260->3337 (+77, loadAdvertisedModelsForSelfHostedConnections + the modelNotAdvertised candidate-filter predicate — pins chat routing to the connection whose synced inventory actually advertises the model, fixing spurious model-not-found on multi-host self-hosted setups; at the existing credential-selection chokepoint, not extractable without splitting the selection flow). Covered by tests/unit/chat-routing-synced-inventory-11089.test.ts. Owner pre-authorized baseline bumps 2026-08-22.",
     "tests/unit/account-fallback-service.test.ts": 2044,
@@ -459,7 +459,7 @@
     "_rebaseline_2026_08_22_11156_enter_check_disabled": "PR #11156 (rqzbeh) own growth: AddApiKeyModal.tsx 1080->1082 (+2, Enter keydown handler now mirrors the isCheckDisabled condition — owner-requested post-merge polish from #11056; the rest of the diff is Prettier reflow). Covered by tests/unit/ui/add-api-key-modal-enter-key.test.tsx (jsdom render test, Enter dispatch assertions).",
     "src/app/(dashboard)/dashboard/providers/[id]/hooks/useProviderConnections.ts": 1051,
     "src/shared/components/ModelSelectModal.tsx": 1138,
-    "src/shared/constants/providers/apikey/gateways.ts": 1330,
+    "src/shared/constants/providers/apikey/gateways.ts": 1321,
     "open-sse/vendor/codex-chatgpt-web/bridge.ts": 1387,
     "_rebaseline_2026_08_11_v3850_merge_storm_provider_registry": "DRIFT do merge-storm 2026-08-11 (99 PRs mergeados no release/v3.8.50). AddApiKeyModal.tsx (PR #8949 ChatGPT Web provider) e useProviderConnections.ts/ModelSelectModal.tsx (PRs #9011 combo test-all, #9499 image combos) = UI nova legitima acima do cap; gateways.ts = god-file de catalogo de providers que cresceu com PRs #9009/#9421/#9468/#9594 (qualquer split arriscaria corromper o merge de novo — o proprio PR #9421 quebrou o arquivo); bridge.ts (PR #8949) = ponte Chromium vendored; proxyFetch.ts 1207->1220 = drift herdado de merges. Owner autorizou rebaseline com anotacao (2026-08-11).",
     "src/lib/modelCapabilities.ts": 1072,
@@ -480,8 +480,7 @@
     "src/lib/guardrails/videoBridgeRuntime.ts": 1009,
     "_rebaseline_2026_08_24_video_bridge_fu02_fu07_sampler": "PRs #11344 (FU-02 one-frame scene-aware determinism) + #11381 (FU-07 opt-in segment_aware structural sampling) own growth: videoBridgeRuntime.ts <1000->1009, +9 (sum of both boarded together in the same merge-batch). #11344 adds the deterministic one-frame midpoint fallback + policyEffective=uniform report at the existing scene_aware seam; #11381 adds the bounded local-only FFmpeg structural pre-analysis pass (scene/freeze/blur/exposure/SI-TI) and its budget-reallocation logic. Covered by tests/unit/guardrails/videoBridgeSampler.test.ts, tests/unit/guardrails/videoBridgeFu07StructuralSampling.test.ts, tests/integration/video-bridge-sampler-ffmpeg.test.ts. Owner pre-authorized rebaseline for legitimate PR growth (2026-08-19 directive).",
     "open-sse/services/autoCombo/virtualFactory.ts": 1130,
-    "src/lib/cloudflaredTunnel.ts": 1078,
-    "src/shared/components/RequestLoggerDetail.tsx": 1018
+    "src/lib/cloudflaredTunnel.ts": 1078
   },
   "_rebaseline_base_2026_08_10_proxyfetch": "Base-red fix (green-prs sweep, issue #9985): open-sse/utils/proxyFetch.ts 1207 > cap 1000 — new proxied-TLS fetch helper introduced by the Fal reference-image work. Owner-authorized quick rebaseline to green; structural slim tracked for v3.9.0.",
   "_rebaseline_2026_07_27_v3849_train2": "Merge-train 2 (7 PRs) — owner-approved 2026-07-27. Single entry: chatCore.ts 4955->5006 (#8595, Responses multi-turn image compaction before the context hard-reject). Genuine irreducible growth at the existing compaction chokepoint in handleChatCore — the PR adds a last-resort retry against the concrete budget plus the estimateFinalInputTokens helper, both wired at the pre-existing call site rather than a new branch. Covered by tests/unit/8560-responses-image-compaction.test.ts (4 tests).",
@@ -651,6 +650,5 @@
   "_rebaseline_2026_08_20_8338_cursor_image_provider": "PR (reimplementation of #8338, @valvesss): imageRegistry.ts 1019->1033 = new cursor IMAGE_PROVIDERS entry (Cursor plan image generation via Agent CLI), +14 lines of declarative provider metadata. Same god-registry no-split rationale as prior imageRegistry/gateways rebaselines.",
   "_rebaseline_2026_08_20_imageregistry_1034": "imageRegistry.ts 1033->1034: +1 line drift between #10842 (cursor image provider, froze at 1033) and its actual merged state on release (measured 1034) — trivial rebaseline, not a new feature.",
   "_rebaseline_2026_08_25_11146_subscription_first_auto": "PR #11146 (@yourspraveen, subscription-first auto groupings auto/subscription+auto/thrifty): open-sse/services/autoCombo/virtualFactory.ts is a NEW file in this PR landing at 1128 lines (+2 margin) — two opt-in flat auto ids built on the established auto/best-free pattern (connectionBillingCatalog + subscriptionLadder pure functions). Frozen at merge size per owner-authorized rebaseline directive (2026-08-19, merge-batch Step 4); no further growth without split rationale.",
-  "_rebaseline_2026_08_26_mergebatch_v3851_batch1": "/merge-batch 2026-08-26 (v3.8.51): three legitimate growths from this batch. #11448 src/app/api/providers/[id]/test/route.ts 1237->1262 (auto-test-on-create wiring). #11495 src/sse/services/auth.ts 3346->3376 (web-cookie health-sweep verify-only path). #11561 src/lib/cloudflaredTunnel.ts new named-tunnel mode, lands at 1078 (+78 over the 1000 new-file cap) for the CLOUDFLARED_CONFIG named-tunnel flow (login->create->route dns config parsing + readiness detection). Owner-authorized rebaseline per merge-batch Step 4 (2026-08-19 directive); no further growth without split rationale.",
-  "_rebaseline_2026_08_26_mergebatch_v3851_batch2": "/merge-batch 2026-08-26 (v3.8.51) batch 2: three legitimate growths. #11083 src/shared/components/RequestLoggerDetail.tsx new-file cap, lands at 1018 (+18 over 1000) — copy-all button for request detail modal. #11631 src/shared/constants/providers/apikey/gateways.ts 1321->1330 (1min.ai gateway entry). #11628 src/sse/services/auth.ts 3376->3432 (credential-health isolation from model failures). Owner-authorized rebaseline per merge-batch Step 4 (2026-08-19 directive); no further growth without split rationale."
+  "_rebaseline_2026_08_26_mergebatch_v3851_batch1": "/merge-batch 2026-08-26 (v3.8.51): three legitimate growths from this batch. #11448 src/app/api/providers/[id]/test/route.ts 1237->1262 (auto-test-on-create wiring). #11495 src/sse/services/auth.ts 3346->3376 (web-cookie health-sweep verify-only path). #11561 src/lib/cloudflaredTunnel.ts new named-tunnel mode, lands at 1078 (+78 over the 1000 new-file cap) for the CLOUDFLARED_CONFIG named-tunnel flow (login->create->route dns config parsing + readiness detection). Owner-authorized rebaseline per merge-batch Step 4 (2026-08-19 directive); no further growth without split rationale."
 }

docs/diagrams/cli-terminal.svg

@@ -1,4 +1,4 @@
-<svg viewBox="0 0 1200 350" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="Animated terminal demoing the OmniRoute CLI: omniroute providers list (354 providers registered, anthropic, codex, glm, kimi shown active), omniroute combo list (always-on priority, cost-saver, fusion-panel, context-relay) and omniroute health (healthy, 18412 requests in 24h, p95 412ms, circuit breakers 24 closed, 1 half-open, 0 open), cycling over 85 top-level commands: providers, oauth, keys, combo, nodes, models, cache, compression, cost, usage, quota, health, resilience, telemetry, logs, audit, mcp, a2a, cloud, memory, skills, eval, doctor, repl, tunnel, backup, sync, webhooks, policy, pricing, translator, simulate and more.">
+<svg viewBox="0 0 1200 350" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="Animated terminal demoing the OmniRoute CLI: omniroute providers list (353 providers registered, anthropic, codex, glm, kimi shown active), omniroute combo list (always-on priority, cost-saver, fusion-panel, context-relay) and omniroute health (healthy, 18412 requests in 24h, p95 412ms, circuit breakers 24 closed, 1 half-open, 0 open), cycling over 85 top-level commands: providers, oauth, keys, combo, nodes, models, cache, compression, cost, usage, quota, health, resilience, telemetry, logs, audit, mcp, a2a, cloud, memory, skills, eval, doctor, repl, tunnel, backup, sync, webhooks, policy, pricing, translator, simulate and more.">
 <desc>Compact animated terminal cycling three real OmniRoute CLI commands with a typewriter effect and a scrolling subcommand ticker; the first frame shows the completed providers-list screen.</desc>
 <defs><clipPath id="tickerClip"><rect x="12" y="304" width="1176" height="40"/></clipPath><clipPath id="tw0"><rect x="64" y="46" height="26" width="0"><animate attributeName="width" calcMode="discrete" values="0;31;61;92;122;153;184;214;245;245" keyTimes="0;0.012;0.018;0.024;0.030;0.036;0.042;0.048;0.054;1" dur="18s" repeatCount="indefinite"/></rect></clipPath><clipPath id="tw1"><rect x="64" y="46" height="26" width="0"><animate attributeName="width" calcMode="discrete" values="0;26;51;76;102;128;153;178;204;204" keyTimes="0;0.348;0.351;0.357;0.363;0.369;0.375;0.381;0.387;1" dur="18s" repeatCount="indefinite"/></rect></clipPath><clipPath id="tw2"><rect x="64" y="46" height="26" width="0"><animate attributeName="width" calcMode="discrete" values="0;20;41;61;82;102;122;143;163;163" keyTimes="0;0.678;0.684;0.690;0.696;0.702;0.708;0.714;0.720;1" dur="18s" repeatCount="indefinite"/></rect></clipPath></defs>
 <rect width="1200" height="350" fill="#0d1117"/>

docs/diagrams/comparison-table.svg

@@ -1,4 +1,4 @@
-<svg viewBox="0 0 1200 780" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="Comparison table: OmniRoute versus 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute is the only one with the full set: 354 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, a built-in MCP server with 110 tools, A2A protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, desktop/Termux/PWA, 43 UI locales and 100% MIT self-hosted. 9router has free providers, RTK compression and translation but no MCP, A2A, memory, guardrails, cloud agents or stealth. OpenRouter is a hosted SaaS with 400+ models, guardrails and a hosted MCP but is not self-hosted and lacks A2A, memory, cloud agents and stealth. CLIProxyAPI is a light OAuth proxy with two routing strategies. LiteLLM has 100+ providers, A2A and extensive guardrails but no memory, compression, free tier, stealth or cloud agents.">
+<svg viewBox="0 0 1200 780" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="Comparison table: OmniRoute versus 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute is the only one with the full set: 353 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, a built-in MCP server with 110 tools, A2A protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, desktop/Termux/PWA, 43 UI locales and 100% MIT self-hosted. 9router has free providers, RTK compression and translation but no MCP, A2A, memory, guardrails, cloud agents or stealth. OpenRouter is a hosted SaaS with 400+ models, guardrails and a hosted MCP but is not self-hosted and lacks A2A, memory, cloud agents and stealth. CLIProxyAPI is a light OAuth proxy with two routing strategies. LiteLLM has 100+ providers, A2A and extensive guardrails but no memory, compression, free tier, stealth or cloud agents.">
   <desc>Static-header comparison table where each capability row fades in top to bottom; the OmniRoute column is highlighted and shows a check or a leading value in every row, while competitors show a mix of checks, partials and crosses.</desc>
   <defs>
     <pattern id="gC" width="32" height="32" patternUnits="userSpaceOnUse"><path d="M 32 0 L 0 0 0 32" fill="none" stroke="#ffffff" stroke-opacity="0.05" stroke-width="1"/></pattern>

docs/diagrams/promise-pillars.svg

@@ -1,4 +1,4 @@
-<svg viewBox="0 0 1200 540" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="The OmniRoute promise: one endpoint and 354 providers. Six pillars. Resilient fallback: automatic routing continues while another healthy target is available. Save up to 95 percent of eligible tokens: RTK plus Caveman stacked compression averages about 89 percent on tool-heavy sessions. Zero dollars to start: 90+ providers with a free tier and 56 recurring or keyless free-forever providers. Every tool works: 35 CLI and agent integration records, including Claude Code, Codex, Cursor, Cline, Copilot and Antigravity, through one config. One endpoint: OpenAI, Claude, Gemini and Responses API translation at /v1. Production controls: circuit breakers, TLS stealth, MCP with 110 tools, A2A, memory, guardrails, evals, and 39,000+ static test declarations across 5,100+ tracked test files.">
+<svg viewBox="0 0 1200 540" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="The OmniRoute promise: one endpoint and 353 providers. Six pillars. Resilient fallback: automatic routing continues while another healthy target is available. Save up to 95 percent of eligible tokens: RTK plus Caveman stacked compression averages about 89 percent on tool-heavy sessions. Zero dollars to start: 90+ providers with a free tier and 56 recurring or keyless free-forever providers. Every tool works: 35 CLI and agent integration records, including Claude Code, Codex, Cursor, Cline, Copilot and Antigravity, through one config. One endpoint: OpenAI, Claude, Gemini and Responses API translation at /v1. Production controls: circuit breakers, TLS stealth, MCP with 110 tools, A2A, memory, guardrails, evals, and 39,000+ static test declarations across 5,100+ tracked test files.">
   <desc>Animated promise card: six pillar tiles fade in in reading order, then a soft colored border highlight sweeps from tile to tile in a continuous cycle.</desc>
   <defs>
     <pattern id="gridPaperP" width="32" height="32" patternUnits="userSpaceOnUse">
@@ -21,7 +21,7 @@
     <line x1="150" y1="53" x2="1160" y2="53" stroke="#232b38" stroke-width="1.5"/>
   </g>
   <g>
-    <text x="40" y="100" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="23" font-weight="600" fill="#c9d1d9">One endpoint. <tspan fill="#a78bfa" font-weight="800">354 providers.</tspan> Never stop building — OmniRoute picks <tspan fill="#7ee787" font-weight="700">the cheapest one that works</tspan>.</text>
+    <text x="40" y="100" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="23" font-weight="600" fill="#c9d1d9">One endpoint. <tspan fill="#a78bfa" font-weight="800">353 providers.</tspan> Never stop building — OmniRoute picks <tspan fill="#7ee787" font-weight="700">the cheapest one that works</tspan>.</text>
   </g>
 
   <g font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif">
@@ -38,7 +38,7 @@
         <line x1="3.9" y1="3.9" x2="18.1" y2="18.1"/>
       </g>
       <text x="102" y="170" font-size="18" font-weight="800" fill="#74b9ff">Never hit limits</text>
-      <text x="66" y="204" font-size="13.5" fill="#a1a1aa">Auto-fallback across 354 providers in</text>
+      <text x="66" y="204" font-size="13.5" fill="#a1a1aa">Auto-fallback across 353 providers in</text>
       <text x="66" y="226" font-size="13.5" fill="#a1a1aa">milliseconds. Quota out? The next provider</text>
       <text x="66" y="248" font-size="13.5" fill="#a1a1aa">takes over while a healthy target remains.</text>
     </g>

docs/diagrams/readme-hero.svg

@@ -1,4 +1,4 @@
-<svg viewBox="0 0 1200 548" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="OmniRoute hero: Never stop coding. Every AI tool to 354 providers — 90+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot and Antigravity into free Claude, GPT and Gemini with auto-fallback. RTK + Caveman stacked compression saves 15 to 95 percent of tokens — about 89 percent average on tool-heavy sessions — so you never hit limits. Stats: 354 AI providers, 90+ free tiers, about 1.51B free tokens per month, 15 to 95 percent token savings, 19 routing strategies, zero dollars to start.">
+<svg viewBox="0 0 1200 548" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="OmniRoute hero: Never stop coding. Every AI tool to 353 providers — 90+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot and Antigravity into free Claude, GPT and Gemini with auto-fallback. RTK + Caveman stacked compression saves 15 to 95 percent of tokens — about 89 percent average on tool-heavy sessions — so you never hit limits. Stats: 353 AI providers, 90+ free tiers, about 1.51B free tokens per month, 15 to 95 percent token savings, 19 routing strategies, zero dollars to start.">
   <desc>Animated hero card: a pulse travels the divider line and a compression bar demo repeatedly shrinks a prompt by up to 95 percent; all headline content is static and readable on the first frame.</desc>
   <defs>
     <pattern id="gridPaperH" width="32" height="32" patternUnits="userSpaceOnUse">
@@ -28,7 +28,7 @@
   <text x="48" y="138" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="60" font-weight="800" fill="#e9edf3">Never stop coding<tspan fill="#a855f7">.</tspan></text>
 
   <!-- subheadline -->
-  <text x="48" y="184" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="25" font-weight="600" fill="#c9d1d9">Every AI tool → <tspan fill="#a78bfa" font-weight="800">354 providers</tspan> — <tspan fill="#7ee787" font-weight="800">90+ free</tspan> — through one endpoint.</text>
+  <text x="48" y="184" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="25" font-weight="600" fill="#c9d1d9">Every AI tool → <tspan fill="#a78bfa" font-weight="800">353 providers</tspan> — <tspan fill="#7ee787" font-weight="800">90+ free</tspan> — through one endpoint.</text>
 
   <!-- plug line -->
   <text x="48" y="222" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="16.5" fill="#a1a1aa">Claude Code · Codex · Cursor · Cline · Copilot · Antigravity&#160;&#160;→&#160;&#160;<tspan fill="#7ee787" font-weight="700">FREE</tspan> Claude / GPT / Gemini · auto-fallback</text>

docs/frameworks/SEARCH_TOOLS_STUDIO.md

@@ -57,7 +57,7 @@ New tab for extracting content from a URL via `POST /v1/web/fetch` (created in p
 - Submit → fetch → render `ScrapeResult.tsx`.
 - `ScrapeResult` renders markdown preview + raw toggle.
 - Cap: if response body > **256 KB**, UI shows `(truncated, view raw)` and opens raw in a Monaco modal (D21).
-- Metadata panel: provider (firecrawl/jina-reader/tavily-search/tinyfish/nimble-search), latency, cost, response size, links count.
+- Metadata panel: provider (firecrawl/jina-reader/tavily-search/tinyfish), latency, cost, response size, links count.
 - Uses `useScrapeFetch.ts` hook.
 
 ### Compare Tab
@@ -108,7 +108,7 @@ Runs the same query/URL across up to **4 providers in parallel** (D22):
 | Field                          | Source                                                                                     |
 | ------------------------------ | ------------------------------------------------------------------------------------------ |
 | `id`, `name`                   | `searchRegistry.ts`                                                                        |
-| `kind`                         | `"search"` or `"fetch"` (firecrawl, jina-reader, tavily-search, tinyfish, nimble-search)   |
+| `kind`                         | `"search"` (12 providers) or `"fetch"` (firecrawl, jina-reader, tavily-search, tinyfish)   |
 | `costPerQuery`                 | Registry data                                                                              |
 | `freeMonthlyQuota`             | Registry data                                                                              |
 | `searchTypes` / `fetchFormats` | Registry data                                                                              |
@@ -136,7 +136,7 @@ Only one backend change was needed for this feature:
 
 `src/app/api/search/providers/route.ts` was extended to:
 
-- Include every fetch provider (`firecrawl`, `jina-reader`, `tavily-search`, `tinyfish`, `nimble-search`) in the array.
+- Include all 4 fetch providers (`firecrawl`, `jina-reader`, `tavily-search`, `tinyfish`) in the array.
 - Add `kind: "search" | "fetch"` to every item.
 - Add `status: "configured" | "missing" | "rate_limited"` derived from live credential state.
 - Maintain backward compatibility — existing fields (`id`, `name`, etc.) unchanged.

docs/i18n/ar/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/az/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/bg/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/bn/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/cs/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/da/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/de/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/es/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/fa/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/fi/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/fr/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/gu/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/he/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/hi/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/hu/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/id/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/in/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/it/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/ja/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/ko/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/mr/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/ms/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/nl/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/no/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/phi/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/pl/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/pt-BR/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/pt/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/ro/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/ru/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/sk/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/sv/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/sw/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/ta/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/te/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/th/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/tr/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/uk-UA/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/ur/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/vi/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/zh-CN/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/i18n/zh-TW/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> 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 354 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.
+> 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 353 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
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

docs/reference/API_REFERENCE.md

@@ -529,7 +529,7 @@ Web/search provider abstraction (Tavily, Brave, Exa, Serper, etc.).
 ## Web Fetch API
 
 Extract content from a URL via a configured web-fetch provider (Firecrawl, Jina
-Reader, Tavily Extract, TinyFish Fetch, Nimble Extract).
+Reader, Tavily Extract, TinyFish Fetch).
 
 | Method | Path            | Description                                               |
 | ------ | --------------- | --------------------------------------------------------- |
@@ -538,8 +538,7 @@ Reader, Tavily Extract, TinyFish Fetch, Nimble Extract).
 **Auth:** Bearer API key (`extractApiKey` + `isValidApiKey`). Policy enforced via `enforceApiKeyPolicy`.
 
 **Quota-aware fallback (#8297):** when no explicit `provider` is given, the pool
-(`firecrawl` → `jina-reader` → `tavily-search` → `tinyfish` → `nimble-search`) is
-walked in fixed
+(`firecrawl` → `jina-reader` → `tavily-search` → `tinyfish`) is walked in fixed
 priority order (fill-first) — a rate-limited-but-configured provider is skipped
 instead of short-circuiting the request, and a retryable/quota upstream failure
 (HTTP 429 always; 402/403 for Firecrawl/Tavily/TinyFish quota-style free tiers —
@@ -662,21 +661,11 @@ refusal. On success:
 {
   "allowed": true,
   // present only when the key opted into per-key usage limits (daily/weekly USD):
-  "personal": {
-    "dailySpentUsd": 1.25,
-    "dailyLimitUsd": 5,
-    "dailyResetAtIso": "…",
-    "weeklySpentUsd": 8,
-    "weeklyLimitUsd": 20,
-    "weeklyResetAtIso": "…" /* … */,
-  },
+  "personal": { "dailySpentUsd": 1.25, "dailyLimitUsd": 5, "dailyResetAtIso": "…", "weeklySpentUsd": 8, "weeklyLimitUsd": 20, "weeklyResetAtIso": "…" /* … */ },
   // the selected provider quota snapshot, or null when nothing is cached yet:
-  "provider": { "connectionId": "…", "provider": "claude", "plan": "…", "quotas": {/* … */} },
+  "provider": { "connectionId": "…", "provider": "claude", "plan": "…", "quotas": { /* … */ } },
   // every connection's snapshot, so a UI can render several providers side by side:
-  "providers": [
-    { "connectionId": "…", "provider": "claude" /* … */ },
-    { "provider": "codex" /* … */ },
-  ],
+  "providers": [ { "connectionId": "…", "provider": "claude", /* … */ }, { "provider": "codex", /* … */ } ]
 }
 ```
 
@@ -685,7 +674,7 @@ On refusal (`401` bad key / `403` not allowed) the same route returns
 (key allowed, nothing learned yet) is a different state from a refusal, and only the JSON form
 distinguishes them.
 
-**Auth:** the caller's own Bearer API key, validated with `isValidApiKey` — this is _not_ the
+**Auth:** the caller's own Bearer API key, validated with `isValidApiKey` — this is *not* the
 management surface (`/api/keys/…`), which stays behind `requireManagementAuth`.
 
 ---

docs/reference/ENVIRONMENT.md

@@ -512,7 +512,6 @@ detection above).
 | `OMNIROUTE_MCP_DESCRIPTION_COMPRESSION`         | `rtk`                                               | `open-sse/mcp-server/descriptionCompressor.ts`              | Compression algorithm/profile. Disable values: `0`, `false`, `off`.                                                                                                     |
 | `OMNIROUTE_MCP_FETCH_TIMEOUT_MS`                | `10000`                                             | `open-sse/mcp-server/fetchTimeout.ts`                       | Abort budget (ms) for MCP-server internal management reads (health, resilience, combos, quota, usage).                                                                  |
 | `OMNIROUTE_MCP_UPSTREAM_TIMEOUT_MS`             | `60000`                                             | `open-sse/mcp-server/fetchTimeout.ts`                       | Abort budget (ms) for MCP hops that wait on a provider (`route_request`, `web_search`, `web_fetch`).                                                                    |
-| `OMNIROUTE_CORPUS_CACHE_SIZE`                   | `5`                                                 | `src/lib/localCorpus/configured.ts`                         | Maximum number of local-corpus index instances cached in memory (LRU, one per indexed root directory). Clamped to a minimum of `1`.                                       |
 | `MODEL_SYNC_INTERVAL_HOURS`                     | `24`                                                | `src/shared/services/modelSyncScheduler.ts`                 | Model catalog sync interval in hours.                                                                                                                                   |
 | `PROVIDER_LIMITS_SYNC_INTERVAL_MINUTES`         | `70`                                                | `src/lib/usage/providerLimits.ts`                           | Provider rate-limit and quota polling interval.                                                                                                                         |
 | `PROVIDER_LIMITS_SYNC_SPACING_MS`               | `1500`                                              | `src/lib/usage/providerLimits.ts`                           | Gap (ms) between consecutive OAuth quota fetches in a bulk sync; OAuth connections are fetched one at a time to avoid bursting an upstream. `0` opts out (concurrent).  |

docs/reference/PROVIDER_REFERENCE.md

@@ -380,7 +380,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `vllm` | `vllm` | vLLM | Local, self-hosted | [link](https://github.com/vllm-project/vllm) | API key optional. Configure the local vLLM OpenAI-compatible base URL (default: http://localhost:8000/v1). |
 | `xinference` | `xinference` | XInference | Local, self-hosted | [link](https://inference.readthedocs.io) | API key optional. Configure the local XInference OpenAI-compatible base URL (default: http://localhost:9997/v1). |
 
-## Search Providers (16)
+## Search Providers (15)
 
 | ID | Alias | Name | Tags | Website | Notes |
 |----|-------|------|------|---------|-------|
@@ -390,7 +390,6 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `firecrawl` | `fc` | Firecrawl | Search | [link](https://firecrawl.dev) | API key from firecrawl.dev/app/api-keys (or set your self-hosted Firecrawl base URL) |
 | `google-pse-search` | `google-pse` | Google Programmable Search | Search | [link](https://developers.google.com/custom-search/v1/overview) | Requires a Google API key and your Programmable Search Engine ID (cx) |
 | `linkup-search` | `linkup` | Linkup Search | Search | [link](https://docs.linkup.so) | Bearer API key from the Linkup dashboard |
-| `nimble-search` | `nimble` | Nimble Search | Search | [link](https://docs.nimbleway.com/nimble-sdk/web-tools/search) | Bearer API key from the Nimble dashboard |
 | `ollama-search` | `ollama-search` | Ollama Search | Search | [link](https://ollama.com/settings/keys) | Same API key as Ollama Cloud (from ollama.com/settings/keys) |
 | `perplexity-search` | `pplx-search` | Perplexity Search | Search | [link](https://docs.perplexity.ai/guides/search-quickstart) | Same API key as Perplexity (pplx-...) |
 | `searchapi-search` | `searchapi` | SearchAPI | Search | [link](https://www.searchapi.io/docs/google) | API key from SearchAPI (query param or Bearer auth) |
@@ -443,7 +442,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 
 - Catalog: [`src/shared/constants/providers.ts`](../../src/shared/constants/providers.ts)
 - Registry (per-model details): [`open-sse/config/providerRegistry.ts`](../../open-sse/config/providerRegistry.ts)
-- Executors: [`open-sse/executors/`](../../open-sse/executors/) (110 implementations)
+- Executors: [`open-sse/executors/`](../../open-sse/executors/) (109 implementations)
 - Translators: [`open-sse/translator/`](../../open-sse/translator/)
 
 ## See Also

llm.txt

@@ -1,6 +1,6 @@
 # OmniRoute
 
-> 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 354 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.
+> 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 353 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
 
@@ -277,7 +277,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **353 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 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, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -475,7 +475,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **353-provider catalog** with 90+ 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`
 - **14-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)

open-sse/config/nimble.ts

@@ -1,17 +0,0 @@
-/**
- * Nimble shared client constants.
- *
- * Nimble asks every integration to identify itself with a stable client-source
- * header so calls can be attributed to the host product. Both Nimble surfaces
- * in OmniRoute — search (`POST /v1/search`, wired in open-sse/handlers/search.ts)
- * and fetch (`POST /v1/extract`, open-sse/executors/nimble-fetch.ts) — send it,
- * and both read the value from here so the two can never drift apart.
- *
- * Docs: https://docs.nimbleway.com/api-reference/introduction
- */
-
-/** Header Nimble uses to attribute a request to the calling product. */
-export const NIMBLE_CLIENT_SOURCE_HEADER = "X-Client-Source";
-
-/** The value OmniRoute sends. Do not vary it per surface or per request. */
-export const NIMBLE_CLIENT_SOURCE = "omniroute";

open-sse/config/providers/index.ts

@@ -63,7 +63,6 @@ import { nubeProvider } from "./registry/nube/index.ts";
 import { clinepassProvider } from "./registry/clinepass/index.ts";
 import { sparkdeskProvider } from "./registry/sparkdesk/index.ts";
 import { nlpcloudProvider } from "./registry/nlpcloud/index.ts";
-import { oneminaiProvider } from "./registry/oneminai/index.ts";
 import { nvidiaProvider } from "./registry/nvidia/index.ts";
 import { api_airforceProvider } from "./registry/api-airforce/index.ts";
 import { mistralProvider } from "./registry/mistral/index.ts";
@@ -333,7 +332,6 @@ export const REGISTRY: Record<string, RegistryEntry> = {
   clinepass: clinepassProvider,
   sparkdesk: sparkdeskProvider,
   nlpcloud: nlpcloudProvider,
-  oneminai: oneminaiProvider,
   nvidia: nvidiaProvider,
   "api-airforce": api_airforceProvider,
   mistral: mistralProvider,

open-sse/config/providers/registry/oneminai/index.ts

@@ -1,30 +0,0 @@
-import type { RegistryEntry } from "../../shared.ts";
-
-// 1min.ai (docs.1min.ai) — a chat aggregator exposing many upstream models
-// through one custom API. Not OpenAI-compatible at the wire level (single
-// `promptObject.prompt` string instead of a `messages` array, real SSE with
-// event:/data: framing instead of raw text deltas, "API-KEY" auth header
-// instead of Authorization: Bearer) — see open-sse/executors/oneminai.ts for
-// the request/response translation. `format: "openai"` here describes the
-// client-facing surface OmniRoute exposes, not 1min.ai's actual wire format.
-export const oneminaiProvider: RegistryEntry = {
-  id: "oneminai",
-  alias: "1min",
-  format: "openai",
-  executor: "default",
-  baseUrl: "https://api.1min.ai/api/chat-with-ai",
-  authType: "apikey",
-  authHeader: "api-key",
-  // The model catalog is loaded dynamically per-account/plan on 1min.ai's own
-  // dashboard rather than published as a stable public list, so only the
-  // model shown in every one of 1min.ai's own docs examples is statically
-  // catalogued; passthroughModels lets any other slug the account has access
-  // to be used by id.
-  passthroughModels: true,
-  liveCatalogAuthoritative: false,
-  // No tool/function-calling, JSON mode, or vision support is wired up by the
-  // executor's translation (1min.ai's attachments.images/files feature would
-  // need separate Asset API upload plumbing this provider doesn't implement).
-  unsupportedParams: ["tools", "tool_choice", "functions", "function_call", "response_format"],
-  models: [{ id: "gpt-4o-mini", name: "GPT-4o Mini" }],
-};

open-sse/config/searchRegistry.ts

@@ -116,27 +116,6 @@ export const SEARCH_PROVIDERS: Record<string, SearchProviderConfig> = {
     cacheTTLMs: 5 * 60 * 1000,
   },
 
-  // Nimble also serves POST /v1/web/fetch through the same credential — see
-  // open-sse/executors/nimble-fetch.ts.
-  "nimble-search": {
-    id: "nimble-search",
-    name: "Nimble Search",
-    baseUrl: "https://sdk.nimbleway.com/v1/search",
-    method: "POST",
-    authType: "apikey",
-    authHeader: "bearer",
-    costPerQuery: 0.005,
-    freeMonthlyQuota: 0,
-    searchTypes: ["web", "news"],
-    defaultMaxResults: 5,
-    maxMaxResults: 100,
-    // Kept below GLOBAL_TIMEOUT_MS (handlers/search.ts) so a stalled Nimble call
-    // still leaves budget for the failover provider instead of burning the whole
-    // request window.
-    timeoutMs: 10_000,
-    cacheTTLMs: 5 * 60 * 1000,
-  },
-
   firecrawl: {
     id: "firecrawl",
     name: "Firecrawl",

open-sse/executors/index.ts

@@ -60,8 +60,6 @@ const lazyExecutors: Record<string, () => Promise<BaseExecutor>> = {
   gitlab: () => import("./gitlab.ts").then((m) => new m.GitlabExecutor()),
   "gitlab-duo": () => import("./gitlab.ts").then((m) => new m.GitlabExecutor("gitlab-duo")),
   nlpcloud: () => import("./nlpcloud.ts").then((m) => new m.NlpCloudExecutor()),
-  oneminai: () => import("./oneminai.ts").then((m) => new m.OneMinAiExecutor()),
-  "1min": () => import("./oneminai.ts").then((m) => new m.OneMinAiExecutor()), // Alias
   pollinations: () => import("./pollinations.ts").then((m) => new m.PollinationsExecutor()),
   pol: () => import("./pollinations.ts").then((m) => new m.PollinationsExecutor()), // Alias
   "cloudflare-ai": () => import("./cloudflare-ai.ts").then((m) => new m.CloudflareAIExecutor()),

open-sse/executors/kiro.ts

@@ -243,14 +243,6 @@ export function resolveKiroRegion(
 // kiroRuntimeHost from this executor keep working.
 export { kiroRuntimeHost };
 
-/**
- * Status codes for which trying the next candidate endpoint may succeed where the
- * current one failed (auth/profile mismatch, not a payload problem). Mirrors
- * 9router's KIRO_ENDPOINT_FALLBACK_STATUSES — a 400 (malformed body) is deliberately
- * excluded since resending the same body to another host cannot fix it.
- */
-const KIRO_ENDPOINT_FALLBACK_STATUSES = new Set([401, 403, 404]);
-
 /**
  * KiroExecutor - Executor for Kiro AI (AWS CodeWhisperer)
  * Uses AWS CodeWhisperer streaming API with AWS EventStream binary format
@@ -342,47 +334,17 @@ export class KiroExecutor extends BaseExecutor {
     // Center accounts (e.g. eu-central-1) are rejected by the default us-east-1 host; only the
     // regional endpoint accepts the region-bound token + profileArn.
     const region = resolveKiroRegion(credentials);
-    const regionalUrl = `${kiroRuntimeHost(region)}/generateAssistantResponse`;
-
-    // The Kiro IDE's own branded gateway (runtime.*.kiro.dev) only exists for
-    // us-east-1 and only accepts Kiro OIDC/social tokens — it rejects
-    // TokenType=API_KEY and external-IdP/IdC SSO tokens outright (403 "bearer
-    // token invalid"), so those auth methods go straight to the region-resolved
-    // CodeWhisperer/Amazon Q surface (mirrors 9router's getOrderedBaseUrls in
-    // open-sse/executors/kiro.js). For everything else, try the branded gateway
-    // first — it is the surface the native Kiro IDE itself talks to — and fall
-    // back to the raw AWS host on an auth/profile-shaped failure.
-    const authMethod =
-      typeof credentials.providerSpecificData?.authMethod === "string"
-        ? credentials.providerSpecificData.authMethod
-        : undefined;
-    const isCodeWhispererOnly =
-      authMethod === "api_key" || authMethod === "idc" || isExternalIdpAuthMethod(authMethod);
-    const candidateUrls =
-      region === "us-east-1" && !isCodeWhispererOnly
-        ? ["https://runtime.us-east-1.kiro.dev/generateAssistantResponse", regionalUrl]
-        : [regionalUrl];
-
+    const url = `${kiroRuntimeHost(region)}/generateAssistantResponse`;
     const headers = this.buildHeaders(credentials, stream);
     mergeUpstreamExtraHeaders(headers, upstreamExtraHeaders);
     const transformedBody = await this.transformRequest(model, body, stream, credentials);
-    const requestBody = JSON.stringify(transformedBody);
 
-    let response!: Response;
-    let url = candidateUrls[0];
-    for (let i = 0; i < candidateUrls.length; i++) {
-      url = candidateUrls[i];
-      response = await fetch(url, {
-        method: "POST",
-        headers,
-        body: requestBody,
-        signal,
-      });
-      const hasFallback = i + 1 < candidateUrls.length;
-      if (response.ok || !hasFallback || !KIRO_ENDPOINT_FALLBACK_STATUSES.has(response.status)) {
-        break;
-      }
-    }
+    const response = await fetch(url, {
+      method: "POST",
+      headers,
+      body: JSON.stringify(transformedBody),
+      signal,
+    });
 
     if (!response.ok) {
       return { response, url, headers, transformedBody };

open-sse/executors/nimble-fetch.ts

@@ -1,222 +0,0 @@
-/**
- * Nimble Web Fetch Executor
- *
- * Fetches content from a URL using the Nimble Extract API.
- * POST https://sdk.nimbleway.com/v1/extract
- *
- * Extract returns the requested formats side by side under `data`, so one call
- * covers every OmniRoute fetch format: `markdown`, `html`, `links` and
- * `screenshot` (base64 PNG, surfaced as a data URL).
- *
- * Docs: https://docs.nimbleway.com/nimble-sdk/web-tools/extract/quickstart
- */
-
-import { sanitizeErrorMessage, buildErrorBody } from "../utils/error.ts";
-import { NIMBLE_CLIENT_SOURCE, NIMBLE_CLIENT_SOURCE_HEADER } from "../config/nimble.ts";
-import type { WebFetchResult, WebFetchFormat, WebFetchCredentials } from "../handlers/webFetch.ts";
-
-const NIMBLE_EXTRACT_URL = "https://sdk.nimbleway.com/v1/extract";
-const NIMBLE_TIMEOUT_MS = 30_000;
-
-/** Max characters kept from an HTML <title> / meta description. */
-const META_MAX_CHARS = 500;
-
-// These run over untrusted upstream HTML, so every quantifier is over a character
-// class that cannot cross its own terminator — no backtracking (see AGENTS.md →
-// "Regex Security"). Length is capped by META_MAX_CHARS after the match, not by the
-// quantifier: bounding the capture instead would make an over-long title fail to
-// match at all rather than truncate.
-const TITLE_RE = /<title[^>]{0,200}>([^<]*)<\/title>/i;
-// One pattern per quote style. A shared ["'] class for the closing delimiter would
-// cut a double-quoted description at its first apostrophe ("Don't miss…" → "Don").
-const META_DESCRIPTION_DOUBLE_RE =
-  /<meta[^>]{0,200}name=["']description["'][^>]{0,200}content="([^"]*)"/i;
-const META_DESCRIPTION_SINGLE_RE =
-  /<meta[^>]{0,200}name=["']description["'][^>]{0,200}content='([^']*)'/i;
-
-/** Map an OmniRoute fetch format onto the Nimble Extract format name. */
-function mapFormat(format: WebFetchFormat): string {
-  switch (format) {
-    case "html":
-      return "html";
-    case "links":
-      return "links";
-    case "screenshot":
-      return "screenshot";
-    case "markdown":
-    default:
-      return "markdown";
-  }
-}
-
-function readString(source: Record<string, unknown>, key: string): string {
-  const value = source[key];
-  return value != null ? String(value) : "";
-}
-
-/**
- * Pull a title / description out of raw HTML.
- * Extract has no dedicated metadata format, so metadata is only available when
- * the caller asked for it and we requested `html` alongside their format.
- */
-function parseHtmlMetadata(html: string): { title: string | null; description: string | null } {
-  if (!html) return { title: null, description: null };
-
-  const title = TITLE_RE.exec(html)?.[1]?.trim().slice(0, META_MAX_CHARS);
-  const rawDescription =
-    META_DESCRIPTION_DOUBLE_RE.exec(html)?.[1] ?? META_DESCRIPTION_SINGLE_RE.exec(html)?.[1];
-  const description = rawDescription?.trim().slice(0, META_MAX_CHARS);
-
-  return {
-    title: title ? title : null,
-    description: description ? description : null,
-  };
-}
-
-interface NimbleFetchOptions {
-  url: string;
-  format: WebFetchFormat;
-  includeMetadata: boolean;
-  credentials: WebFetchCredentials;
-}
-
-/**
- * Execute a Nimble Extract request.
- */
-export async function nimbleFetch(opts: NimbleFetchOptions): Promise<WebFetchResult> {
-  const { url, format, includeMetadata, credentials } = opts;
-
-  if (!credentials.apiKey) {
-    const body = buildErrorBody(401, "Nimble API key required");
-    return { success: false, status: 401, error: body.error.message };
-  }
-
-  const requested = mapFormat(format);
-
-  // `links` always comes back so WebFetchResponse.links is populated; `html` is
-  // added only when the caller asked for metadata, since it is the sole source
-  // of a page title/description.
-  const formats = [...new Set([requested, "links", ...(includeMetadata ? ["html"] : [])])];
-
-  const requestBody: Record<string, unknown> = {
-    url,
-    formats,
-    // Extract types `render` as `boolean | "auto"`; "auto" lets Nimble select the
-    // driver per target domain rather than forcing a browser on every static page.
-    render: "auto",
-  };
-
-  const controller = new AbortController();
-  const timeoutId = setTimeout(() => {
-    const err = new Error(`nimble-fetch timeout after ${NIMBLE_TIMEOUT_MS}ms`);
-    err.name = "TimeoutError";
-    controller.abort(err);
-  }, NIMBLE_TIMEOUT_MS);
-
-  try {
-    const response = await fetch(NIMBLE_EXTRACT_URL, {
-      method: "POST",
-      headers: {
-        "Content-Type": "application/json",
-        Authorization: `Bearer ${credentials.apiKey}`,
-        [NIMBLE_CLIENT_SOURCE_HEADER]: NIMBLE_CLIENT_SOURCE,
-      },
-      body: JSON.stringify(requestBody),
-      signal: controller.signal,
-    });
-
-    if (!response.ok) {
-      // Nimble returns a plain-text body on auth failures, so this must be
-      // sanitized before it can reach a response.
-      const rawError = await response.text().catch(() => `HTTP ${response.status}`);
-      const msg = sanitizeErrorMessage(`Nimble error ${response.status}: ${rawError}`);
-      const body = buildErrorBody(response.status, msg);
-      return { success: false, status: response.status, error: body.error.message };
-    }
-
-    const payload = (await response.json()) as Record<string, unknown>;
-
-    // A 200 can still carry a failed extraction — Extract reports the target's own
-    // outcome in the envelope. Without this the caller would get an empty document
-    // marked successful, and the pool in /v1/web/fetch would never fall through to
-    // the next provider.
-    const taskStatus = typeof payload.status === "string" ? payload.status : "";
-    const taskStatusCode = typeof payload.status_code === "number" ? payload.status_code : null;
-    if (
-      (taskStatus && taskStatus !== "success") ||
-      (taskStatusCode !== null && taskStatusCode >= 400)
-    ) {
-      const detail = taskStatus || `status ${taskStatusCode}`;
-      const msg = sanitizeErrorMessage(`Nimble extraction did not succeed: ${detail}`);
-      const body = buildErrorBody(502, msg);
-      return { success: false, status: 502, error: body.error.message };
-    }
-
-    const data = (payload.data as Record<string, unknown> | null) ?? {};
-
-    const rawLinks = data.links;
-    const links: string[] = Array.isArray(rawLinks) ? rawLinks.map((l) => String(l)) : [];
-
-    const screenshot = readString(data, "screenshot");
-    const screenshotUrl =
-      format === "screenshot" && screenshot
-        ? screenshot.startsWith("data:")
-          ? screenshot
-          : `data:image/png;base64,${screenshot}`
-        : null;
-
-    // The requested format must actually be present. An absent key means Extract
-    // succeeded but produced nothing for what the caller asked for; returning an
-    // empty document as a success would stop /v1/web/fetch from trying the next
-    // provider. An empty *value* is legitimate (a genuinely blank page) and passes.
-    if (!(requested in data)) {
-      const msg = sanitizeErrorMessage(`Nimble returned no ${requested} content for the request`);
-      const body = buildErrorBody(502, msg);
-      return { success: false, status: 502, error: body.error.message };
-    }
-
-    let content: string;
-    switch (format) {
-      case "html":
-        content = readString(data, "html");
-        break;
-      case "links":
-        content = JSON.stringify(links);
-        break;
-      case "screenshot":
-        content = "";
-        break;
-      case "markdown":
-      default:
-        content = readString(data, "markdown");
-        break;
-    }
-
-    const metadata = includeMetadata ? parseHtmlMetadata(readString(data, "html")) : null;
-
-    return {
-      success: true,
-      data: {
-        provider: "nimble-search",
-        url,
-        content,
-        links,
-        metadata,
-        screenshot_url: screenshotUrl,
-      },
-    };
-  } catch (err: unknown) {
-    // The abort reason above is named "TimeoutError"; an external abort surfaces as
-    // "AbortError". Both must reach the 504 branch.
-    if (err instanceof Error && (err.name === "TimeoutError" || err.name === "AbortError")) {
-      const body = buildErrorBody(504, "Nimble request timed out");
-      return { success: false, status: 504, error: body.error.message };
-    }
-    const msg =
-      err instanceof Error ? sanitizeErrorMessage(err.message) : sanitizeErrorMessage(String(err));
-    const body = buildErrorBody(502, msg);
-    return { success: false, status: 502, error: body.error.message };
-  } finally {
-    clearTimeout(timeoutId);
-  }
-}

open-sse/executors/oneminai.ts

@@ -1,313 +0,0 @@
-import { randomUUID } from "node:crypto";
-
-import {
-  BaseExecutor,
-  mergeUpstreamExtraHeaders,
-  type ExecuteInput,
-  type ProviderCredentials,
-} from "./base.ts";
-import { PROVIDERS } from "../config/constants.ts";
-import { buildErrorBody } from "../utils/error.ts";
-
-type JsonRecord = Record<string, unknown>;
-type OpenAIMessage = {
-  role?: string;
-  content?: unknown;
-};
-
-const CHAT_URL = "https://api.1min.ai/api/chat-with-ai";
-const ROLE_LABELS: Record<string, string> = {
-  system: "System",
-  developer: "System",
-  user: "User",
-  assistant: "Assistant",
-};
-
-function asRecord(value: unknown): JsonRecord {
-  return value && typeof value === "object" && !Array.isArray(value) ? (value as JsonRecord) : {};
-}
-
-function extractTextContent(content: unknown): string {
-  if (typeof content === "string") return content;
-  if (!Array.isArray(content)) return "";
-  return content
-    .map((part) => {
-      if (!part || typeof part !== "object") return "";
-      const item = part as Record<string, unknown>;
-      return item.type === "text" && typeof item.text === "string" ? item.text : "";
-    })
-    .filter((text) => text.length > 0)
-    .join("\n");
-}
-
-/**
- * 1min.ai's Chat with AI API takes one `promptObject.prompt` string, not an
- * OpenAI `messages` array — multi-turn context is normally carried server-side
- * via `promptObject.conversationId` (see docs.1min.ai/docs/api/chat-with-ai-api),
- * which requires a prior POST /api/conversations call and a stable conversation
- * identity that stateless OpenAI-compatible clients don't provide. Rather than
- * half-implement that, a single user message passes through unchanged and
- * multi-turn history is flattened into a labeled transcript.
- */
-export function buildPrompt(messages: OpenAIMessage[] | undefined): string {
-  const list = Array.isArray(messages) ? messages : [];
-  if (list.length === 1 && list[0]?.role === "user") {
-    return extractTextContent(list[0].content);
-  }
-  return list
-    .map((message) => {
-      const role = String(message?.role || "user").toLowerCase();
-      const text = extractTextContent(message?.content);
-      const label = ROLE_LABELS[role] || role;
-      return `${label}: ${text}`;
-    })
-    .filter((line) => line.length > 0)
-    .join("\n\n");
-}
-
-function buildSseChunk(data: unknown): string {
-  return `data: ${JSON.stringify(data)}\n\n`;
-}
-
-function buildOpenAiJsonCompletion(content: string, model: string, id: string, created: number): Response {
-  return new Response(
-    JSON.stringify({
-      id,
-      object: "chat.completion",
-      created,
-      model,
-      choices: [{ index: 0, message: { role: "assistant", content }, finish_reason: "stop" }],
-      // 1min.ai's response shape carries no token-usage fields.
-      usage: { prompt_tokens: 0, completion_tokens: 0, total_tokens: 0 },
-    }),
-    { status: 200, headers: { "Content-Type": "application/json" } }
-  );
-}
-
-function toOpenAiErrorResponse(status: number, message: string, upstreamDetails?: unknown): Response {
-  return new Response(JSON.stringify(buildErrorBody(status, message, upstreamDetails)), {
-    status,
-    headers: { "Content-Type": "application/json" },
-  });
-}
-
-/**
- * Parse 1min.ai's real Server-Sent Events (event: content|result|done|error,
- * data: {...}) from the upstream Response body and re-emit them as standard
- * OpenAI chat.completion.chunk SSE.
- */
-function translateSseStream(upstreamBody: ReadableStream<Uint8Array>, model: string, id: string, created: number): ReadableStream<Uint8Array> {
-  const decoder = new TextDecoder();
-  const encoder = new TextEncoder();
-
-  return new ReadableStream<Uint8Array>({
-    async start(controller) {
-      controller.enqueue(
-        encoder.encode(
-          buildSseChunk({
-            id,
-            object: "chat.completion.chunk",
-            created,
-            model,
-            choices: [{ index: 0, delta: { role: "assistant" }, finish_reason: null }],
-          })
-        )
-      );
-
-      const reader = upstreamBody.getReader();
-      let buffer = "";
-      let finished = false;
-
-      const finish = () => {
-        if (finished) return;
-        finished = true;
-        controller.enqueue(
-          encoder.encode(
-            buildSseChunk({
-              id,
-              object: "chat.completion.chunk",
-              created,
-              model,
-              choices: [{ index: 0, delta: {}, finish_reason: "stop" }],
-            })
-          )
-        );
-        controller.enqueue(encoder.encode("data: [DONE]\n\n"));
-        controller.close();
-      };
-
-      const emitContent = (text: string) => {
-        if (!text) return;
-        controller.enqueue(
-          encoder.encode(
-            buildSseChunk({
-              id,
-              object: "chat.completion.chunk",
-              created,
-              model,
-              choices: [{ index: 0, delta: { content: text }, finish_reason: null }],
-            })
-          )
-        );
-      };
-
-      // SSE event framing: "event:"/"data:" lines, blank-line separated records.
-      const processEvent = (eventText: string) => {
-        let eventType = "message";
-        const dataLines: string[] = [];
-        for (const rawLine of eventText.split("\n")) {
-          if (rawLine.startsWith("event:")) {
-            eventType = rawLine.slice(6).trim();
-          } else if (rawLine.startsWith("data:")) {
-            dataLines.push(rawLine.slice(5).trim());
-          }
-        }
-        const data = dataLines.join("\n");
-        if (eventType === "content") {
-          try {
-            const parsed = asRecord(JSON.parse(data));
-            if (typeof parsed.content === "string") emitContent(parsed.content);
-          } catch {
-            // Ignore malformed content events rather than surfacing partial JSON.
-          }
-        } else if (eventType === "error") {
-          emitContent(`\n[1min.ai error: ${data}]`);
-          finish();
-        } else if (eventType === "done") {
-          finish();
-        }
-        // "result" carries the final full aiRecord, redundant with the content
-        // events already streamed — intentionally ignored.
-      };
-
-      try {
-        while (!finished) {
-          const { done, value } = await reader.read();
-          if (done) break;
-          buffer += decoder.decode(value, { stream: true });
-          let separatorIndex = buffer.indexOf("\n\n");
-          while (separatorIndex !== -1) {
-            processEvent(buffer.slice(0, separatorIndex));
-            buffer = buffer.slice(separatorIndex + 2);
-            separatorIndex = buffer.indexOf("\n\n");
-          }
-        }
-        if (!finished && buffer.trim()) processEvent(buffer);
-        finish();
-      } catch (error) {
-        controller.error(error);
-      } finally {
-        reader.releaseLock();
-      }
-    },
-  });
-}
-
-export class OneMinAiExecutor extends BaseExecutor {
-  constructor() {
-    super("oneminai", PROVIDERS["oneminai"] || { format: "openai", baseUrl: CHAT_URL });
-  }
-
-  buildUrl(_model: string, stream: boolean): string {
-    return stream ? `${CHAT_URL}?isStreaming=true` : CHAT_URL;
-  }
-
-  buildHeaders(credentials: ProviderCredentials | null): Record<string, string> {
-    const key = credentials?.apiKey || credentials?.accessToken || "";
-    return {
-      "Content-Type": "application/json",
-      "API-KEY": key,
-    };
-  }
-
-  transformRequest(model: string, body: unknown): JsonRecord {
-    const payload = asRecord(body);
-    const messages = Array.isArray(payload.messages) ? (payload.messages as OpenAIMessage[]) : [];
-    return {
-      type: "UNIFY_CHAT_WITH_AI",
-      model,
-      promptObject: { prompt: buildPrompt(messages) },
-    };
-  }
-
-  async execute({ model, body, stream, credentials, signal, upstreamExtraHeaders }: ExecuteInput) {
-    const url = this.buildUrl(model, stream);
-    const headers = this.buildHeaders(credentials);
-    mergeUpstreamExtraHeaders(headers, upstreamExtraHeaders);
-    const payload = this.transformRequest(model, body);
-
-    const id = `chatcmpl-oneminai-${randomUUID()}`;
-    const created = Math.floor(Date.now() / 1000);
-
-    try {
-      this.assertOutboundUrlAllowed(url);
-      const response = await fetch(url, {
-        method: "POST",
-        headers,
-        body: JSON.stringify(payload),
-        signal,
-      });
-
-      if (!response.ok) {
-        const errorText = await response.text();
-        let message = `1min.ai API failed with status ${response.status}`;
-        try {
-          const parsed = asRecord(JSON.parse(errorText));
-          const err = asRecord(parsed.error);
-          if (typeof err.message === "string") message = err.message;
-        } catch {
-          if (errorText) message = errorText;
-        }
-        return {
-          response: toOpenAiErrorResponse(response.status, message),
-          url,
-          headers,
-          transformedBody: payload,
-        };
-      }
-
-      if (stream) {
-        if (!response.body) {
-          return {
-            response: toOpenAiErrorResponse(502, "1min.ai returned an empty stream"),
-            url,
-            headers,
-            transformedBody: payload,
-          };
-        }
-        return {
-          response: new Response(translateSseStream(response.body, model, id, created), {
-            status: 200,
-            headers: { "Content-Type": "text/event-stream" },
-          }),
-          url,
-          headers,
-          transformedBody: payload,
-        };
-      }
-
-      const json = asRecord(await response.json());
-      const aiRecord = asRecord(json.aiRecord);
-      const detail = asRecord(aiRecord.aiRecordDetail);
-      const resultObject = Array.isArray(detail.resultObject) ? detail.resultObject : [];
-      const content = resultObject.filter((part): part is string => typeof part === "string").join("");
-
-      return {
-        response: buildOpenAiJsonCompletion(content, model, id, created),
-        url,
-        headers,
-        transformedBody: payload,
-      };
-    } catch (error) {
-      const message = error instanceof Error ? error.message : String(error || "Unknown error");
-      return {
-        response: toOpenAiErrorResponse(502, `1min.ai fetch error: ${message}`),
-        url,
-        headers,
-        transformedBody: payload,
-      };
-    }
-  }
-}
-
-export default OneMinAiExecutor;

open-sse/handlers/chatCore.ts

@@ -704,9 +704,8 @@ export async function handleChatCore({
   const recordKeyHealthStatus = (
     status: number,
     creds: Record<string, unknown> | null | undefined,
-    transport?: string,
-    failureDetail?: string
-  ): void => recordKeyHealthStatusFor(status, creds, log, transport, failureDetail);
+    transport?: string
+  ): void => recordKeyHealthStatusFor(status, creds, log, transport);
   // ── Phase 9.2: Idempotency check ──
   // Resolve the idempotency key once here and reuse it at the Phase 9.2 save site below,
   // rather than re-deriving it. (#3821-review LEDGER-6)
@@ -3175,20 +3174,11 @@ export async function handleChatCore({
               });
 
               if (
-                stream &&
-                (res.response.ok ||
-                  res.response.status === HTTP_STATUS.UNAUTHORIZED ||
-                  res.response.status === HTTP_STATUS.FORBIDDEN) &&
+                res.response.status === 401 &&
                 executionConnectionId &&
                 !(await shouldIsolateProbeFailures())
               ) {
-                const failureDetail = res.response.ok
-                  ? ""
-                  : await res.response
-                      .clone()
-                      .text()
-                      .catch(() => "");
-                recordKeyHealthStatus(res.response.status, execCreds, res.transport, failureDetail);
+                recordKeyHealthStatus(401, execCreds);
               }
 
               if (isModelScope() && res.response.status === 429 && attempts < maxAttempts - 1) {
@@ -3539,6 +3529,13 @@ export async function handleChatCore({
         // Non-stream: release semaphore immediately after reading full response body.
         const status = rawResult.response.status;
 
+        // Use execution credentials captured during request processing
+        if (
+          rawResult._executionCredentials?.connectionId &&
+          rawResult._executionCredentials?.apiKey
+        ) {
+          recordKeyHealthStatus(status, rawResult._executionCredentials, rawResult.transport);
+        }
         releaseRawResultAccountSemaphore =
           typeof rawResult._accountSemaphoreRelease === "function"
             ? rawResult._accountSemaphoreRelease
@@ -3564,19 +3561,6 @@ export async function handleChatCore({
           contentType,
           upstreamStream
         );
-        // Use the exact execution credential selected for this request. Model capability
-        // failures stay in routing telemetry; authoritative success only recovers this key.
-        if (
-          rawResult._executionCredentials?.connectionId &&
-          (rawResult._executionCredentials.apiKey || rawResult._executionCredentials.accessToken)
-        ) {
-          recordKeyHealthStatus(
-            status,
-            rawResult._executionCredentials,
-            rawResult.transport,
-            status >= 400 ? payload : ""
-          );
-        }
         releaseRawResultAccountSemaphore();
         releaseRawResultAccountSemaphore = () => {};
 
@@ -4257,84 +4241,79 @@ export async function handleChatCore({
                 `[provider] Node ${errorConnectionId} probe ${errorType} (${statusCode}) — connection stays active`
               );
             } else {
-              // Kimi's 403 says "billing cycle" for both an exhausted subscription and a
-              // temporary request window. Read its official usage endpoint before making
-              // the connection terminal: a non-zero Weekly quota plus an empty Ratelimit
-              // window must recover automatically at the reported reset time.
-              let kimiRateLimitResetAt: string | null = null;
-              if (provider === "kimi-coding") {
-                try {
-                  const { fetchAndPersistProviderLimits } =
-                    await import("@/lib/usage/providerLimits");
-                  const { usage } = await fetchAndPersistProviderLimits(
-                    errorConnectionId,
-                    "manual"
-                  );
-                  kimiRateLimitResetAt = getKimiTemporaryRateLimitResetAt(usage);
-                } catch {
-                  // Preserve the existing quota handling when Kimi's usage endpoint is unavailable.
-                }
+            // Kimi's 403 says "billing cycle" for both an exhausted subscription and a
+            // temporary request window. Read its official usage endpoint before making
+            // the connection terminal: a non-zero Weekly quota plus an empty Ratelimit
+            // window must recover automatically at the reported reset time.
+            let kimiRateLimitResetAt: string | null = null;
+            if (provider === "kimi-coding") {
+              try {
+                const { fetchAndPersistProviderLimits } =
+                  await import("@/lib/usage/providerLimits");
+                const { usage } = await fetchAndPersistProviderLimits(errorConnectionId, "manual");
+                kimiRateLimitResetAt = getKimiTemporaryRateLimitResetAt(usage);
+              } catch {
+                // Preserve the existing quota handling when Kimi's usage endpoint is unavailable.
               }
+            }
 
-              // Providers with per-model quotas — lock the model only, not the connection
-              const quotaCooldownMs = kimiRateLimitResetAt
-                ? Math.max(new Date(kimiRateLimitResetAt).getTime() - Date.now(), 0)
-                : retryAfterMs || COOLDOWN_MS.rateLimit;
-              const accountSemaphoreKey = resolveAccountSemaphoreKey({
-                provider,
-                model: currentModel,
-                connectionId: errorConnectionId,
-                credentials,
+            // Providers with per-model quotas — lock the model only, not the connection
+            const quotaCooldownMs = kimiRateLimitResetAt
+              ? Math.max(new Date(kimiRateLimitResetAt).getTime() - Date.now(), 0)
+              : retryAfterMs || COOLDOWN_MS.rateLimit;
+            const accountSemaphoreKey = resolveAccountSemaphoreKey({
+              provider,
+              model: currentModel,
+              connectionId: errorConnectionId,
+              credentials,
+            });
+            if (accountSemaphoreKey) {
+              markAccountSemaphoreBlocked(accountSemaphoreKey, quotaCooldownMs);
+            }
+            if (kimiRateLimitResetAt) {
+              await updateProviderConnection(errorConnectionId, {
+                testStatus: "unavailable",
+                rateLimitedUntil: kimiRateLimitResetAt,
+                backoffLevel: 0,
+                lastErrorType: PROVIDER_ERROR_TYPES.RATE_LIMITED,
+                lastError: message,
+                errorCode: statusCode,
               });
-              if (accountSemaphoreKey) {
-                markAccountSemaphoreBlocked(accountSemaphoreKey, quotaCooldownMs);
-              }
-              if (kimiRateLimitResetAt) {
-                await updateProviderConnection(errorConnectionId, {
-                  testStatus: "unavailable",
-                  rateLimitedUntil: kimiRateLimitResetAt,
-                  backoffLevel: 0,
-                  lastErrorType: PROVIDER_ERROR_TYPES.RATE_LIMITED,
+              console.warn(
+                `[provider] Node ${errorConnectionId} Kimi request window exhausted (${statusCode}) — retrying after ${kimiRateLimitResetAt}`
+              );
+            } else if (isModelScope() && errorConnectionId) {
+              const lockFn = provider === "antigravity" ? lockExactModel : lockModel;
+              lockFn(provider, errorConnectionId, model, "quota_exhausted", quotaCooldownMs);
+              console.warn(
+                `[provider] Node ${errorConnectionId} ModelScope model quota exhausted (${statusCode}) for ${model} - ${Math.ceil(quotaCooldownMs / 1000)}s (connection stays active)`
+              );
+            } else if (
+              lockModelIfPerModelQuota(
+                provider,
+                errorConnectionId,
+                model,
+                "quota_exhausted",
+                quotaCooldownMs
+              )
+            ) {
+              const quotaScope = getQuotaScopeLabelForProvider(provider, model);
+              console.warn(
+                `[provider] Node ${errorConnectionId} ${quotaScope}-only quota exhausted (${statusCode}) for ${model} - ${Math.ceil(quotaCooldownMs / 1000)}s (cooldown_scope=${quotaScope}, ttl_source=${retryAfterMs ? "upstream" : "inferred"}, connection stays active)`
+              );
+            } else {
+              await writeTerminalStatus(
+                errorConnectionId,
+                {
+                  testStatus: "credits_exhausted",
                   lastError: message,
-                  errorCode: statusCode,
-                });
-                console.warn(
-                  `[provider] Node ${errorConnectionId} Kimi request window exhausted (${statusCode}) — retrying after ${kimiRateLimitResetAt}`
-                );
-              } else if (isModelScope() && errorConnectionId) {
-                const lockFn = provider === "antigravity" ? lockExactModel : lockModel;
-                lockFn(provider, errorConnectionId, model, "quota_exhausted", quotaCooldownMs);
-                console.warn(
-                  `[provider] Node ${errorConnectionId} ModelScope model quota exhausted (${statusCode}) for ${model} - ${Math.ceil(quotaCooldownMs / 1000)}s (connection stays active)`
-                );
-              } else if (
-                lockModelIfPerModelQuota(
-                  provider,
-                  errorConnectionId,
-                  model,
-                  "quota_exhausted",
-                  quotaCooldownMs
-                )
-              ) {
-                const quotaScope = getQuotaScopeLabelForProvider(provider, model);
-                console.warn(
-                  `[provider] Node ${errorConnectionId} ${quotaScope}-only quota exhausted (${statusCode}) for ${model} - ${Math.ceil(quotaCooldownMs / 1000)}s (cooldown_scope=${quotaScope}, ttl_source=${retryAfterMs ? "upstream" : "inferred"}, connection stays active)`
-                );
-              } else {
-                await writeTerminalStatus(
-                  errorConnectionId,
-                  {
-                    testStatus: "credits_exhausted",
-                    lastError: message,
-                    lastErrorType: errorType,
-                    errorCode: String(statusCode),
-                  },
-                  "production"
-                );
-                console.warn(
-                  `[provider] Node ${errorConnectionId} exhausted quota (${statusCode})`
-                );
-              }
+                  lastErrorType: errorType,
+                  errorCode: String(statusCode),
+                },
+                "production"
+              );
+              console.warn(`[provider] Node ${errorConnectionId} exhausted quota (${statusCode})`);
+            }
             } // close probeIsolated3 else
           }
         } else if (errorType === PROVIDER_ERROR_TYPES.UNAUTHORIZED) {

open-sse/handlers/chatCore/keyHealth.ts

@@ -6,13 +6,12 @@
  * handleChatCore. Translates an upstream HTTP status into the in-memory key-health state
  * (apiKeyRotator) for the connection's currently-selected key, and persists the change to the
  * provider connection so it survives process restarts:
- *   - genuine 401/403 credential rejection → record a failure (warning, then invalid at the
- *     threshold), always persisted.
+ *   - 401 → record a failure (warning, then invalid at the threshold), always persisted.
  *   - 402 → terminal (insufficient balance); mark the current key invalid immediately (#5239),
  *           persisted on the active→invalid transition.
  *   - 2xx → record a success, persisted only when recovering from a warning/invalid state.
- * Model availability failures remain model/routing telemetry even when an upstream reports them
- * with 401/403. Any other status only refreshes the tracked extra-key set.
+ * Any other status only refreshes the tracked extra-key set. The handler binds its `log` once and
+ * delegates here, keeping the existing call sites unchanged.
  */
 
 import {
@@ -22,7 +21,6 @@ import {
   trackConnectionExtraKeys,
   type KeyHealth,
 } from "../../services/apiKeyRotator.ts";
-import { isModelUnavailableError } from "../../services/modelFamilyFallback.ts";
 import { updateProviderConnection } from "@/lib/db/providers";
 
 type KeyHealthLog = {
@@ -30,38 +28,11 @@ type KeyHealthLog = {
   error?: (tag: string, message: string) => void;
 } | null;
 
-const CREDENTIAL_FAILURE_PATTERNS = [
-  /\b(?:invalid|incorrect|expired|missing|revoked)\s+api[\s_-]?key\b/i,
-  /\bapi[\s_-]?key\s+(?:is\s+)?(?:invalid|incorrect|expired|missing|revoked|not\s+valid)\b/i,
-  /\bauthentication[\s_-]+(?:failed|error|required)\b/i,
-  /\b(?:invalid|expired|missing|revoked)\s+(?:token|credentials?|bearer)\b/i,
-  /\bunauthorized\b/i,
-  /\bnot\s+authenticated\b/i,
-  /\bforbidden\b/i,
-  /\baccess\s+denied\b/i,
-];
-
-function isModelCapabilityFailure(status: number, failureDetail: string): boolean {
-  if (!failureDetail) return false;
-  const normalizedDetail = failureDetail.replace(/[_-]+/g, " ");
-  // Model-family fallback already owns these phrases. Use a model-capable status for
-  // classification because some aggregators misreport the same model rejection as 401.
-  return isModelUnavailableError(status === 401 ? 403 : status, normalizedDetail);
-}
-
-function isCredentialFailure(status: number, failureDetail: string): boolean {
-  if (status !== 401 && status !== 403) return false;
-  if (isModelCapabilityFailure(status, failureDetail)) return false;
-  if (status === 401) return true;
-  return CREDENTIAL_FAILURE_PATTERNS.some((pattern) => pattern.test(failureDetail));
-}
-
 export function recordKeyHealthStatus(
   status: number,
   creds: Record<string, unknown> | null | undefined,
   log?: KeyHealthLog,
-  transport?: string,
-  failureDetail = ""
+  transport?: string
 ): void {
   // CLIProxyAPI owns a shared external credential pool. Its auth failures cannot be
   // attributed to the native OmniRoute connection selected before proxy dispatch.
@@ -84,11 +55,11 @@ export function recordKeyHealthStatus(
 
   trackConnectionExtraKeys(connId, extraKeys);
 
-  if (isCredentialFailure(status, failureDetail)) {
+  if (status === 401) {
     const updatedHealth = recordKeyFailure(connId, currentKeyId);
     log?.warn?.(
       "AUTH",
-      `${status} on connection ${connId.slice(0, 8)} - key marked as failed (failure #${updatedHealth.failures})`
+      `401 on connection ${connId.slice(0, 8)} - key marked as failed (failure #${updatedHealth.failures})`
     );
 
     // Persist health status to DB on every failure (not just invalid transitions)

open-sse/handlers/search.ts

@@ -24,7 +24,6 @@ import {
   isUnconfiguredLoopbackSearchProvider,
   type SearchProviderConfig,
 } from "../config/searchRegistry.ts";
-import { NIMBLE_CLIENT_SOURCE, NIMBLE_CLIENT_SOURCE_HEADER } from "../config/nimble.ts";
 import { buildPerplexityRequest, parsePerplexitySearchOptions } from "./search/perplexitySearch.ts";
 import * as fcSearch from "./search/firecrawlSearch.ts";
 import { type FirecrawlSearchEnvelope } from "./search/firecrawlSearch.ts";
@@ -476,38 +475,6 @@ function buildTavilyRequest(
   };
 }
 
-function buildNimbleRequest(
-  config: SearchProviderConfig,
-  params: SearchRequestParams
-): { url: string; init: RequestInit } {
-  if (!params.token) throw new Error("Nimble Search requires an API key");
-  const { includes, excludes } = parseDomainFilter(params.domainFilter);
-  const body: Record<string, unknown> = {
-    query: params.query,
-    max_results: Math.min(params.maxResults, config.maxMaxResults),
-    search_depth: "lite",
-    output_format: "plain_text",
-    focus: params.searchType === "news" ? "news" : "general",
-  };
-  if (params.country) body.country = params.country.toUpperCase();
-  if (params.language) body.locale = params.language;
-  if (params.timeRange && params.timeRange !== "any") body.time_range = params.timeRange;
-  if (includes.length) body.include_domains = includes.slice(0, 50);
-  if (excludes.length) body.exclude_domains = excludes.slice(0, 50);
-  return {
-    url: resolveSearchBaseUrl(config, params),
-    init: {
-      method: "POST",
-      headers: {
-        "Content-Type": "application/json",
-        Authorization: `Bearer ${params.token}`,
-        [NIMBLE_CLIENT_SOURCE_HEADER]: NIMBLE_CLIENT_SOURCE,
-      },
-      body: JSON.stringify(body),
-    },
-  };
-}
-
 function buildGooglePseRequest(
   config: SearchProviderConfig,
   params: SearchRequestParams
@@ -740,7 +707,6 @@ const requestBuilders: Record<string, SearchRequestBuilder> = {
   "perplexity-search": buildPerplexityRequest,
   "exa-search": buildExaRequest,
   "tavily-search": buildTavilyRequest,
-  "nimble-search": buildNimbleRequest,
   firecrawl: fcSearch.buildFirecrawlSearchRequest,
   "google-pse-search": buildGooglePseRequest,
   "linkup-search": buildLinkupRequest,
@@ -862,47 +828,6 @@ function normalizeTavilyResponse(
   return { results, totalResults: results.length };
 }
 
-interface NimbleSearchItem {
-  title?: string;
-  url?: string;
-  description?: string;
-  content?: string;
-}
-
-interface NimbleSearchEnvelope {
-  results?: NimbleSearchItem[];
-  total_results?: number;
-}
-
-function normalizeNimbleResponse(
-  data: unknown,
-  _query: string,
-  _searchType: string
-): { results: SearchResult[]; totalResults: number | null } {
-  const now = new Date().toISOString();
-  const envelope = (data ?? {}) as NimbleSearchEnvelope;
-  if (!Array.isArray(envelope.results)) return { results: [], totalResults: null };
-  const results = envelope.results.map((item, idx) =>
-    makeResult(
-      "nimble-search",
-      {
-        title: item.title,
-        url: item.url,
-        snippet: item.description || item.content?.slice(0, 300) || "",
-        full_text: item.content || undefined,
-        text_format: "text",
-      },
-      idx,
-      now
-    )
-  );
-  return {
-    results,
-    totalResults:
-      typeof envelope.total_results === "number" ? envelope.total_results : results.length,
-  };
-}
-
 function normalizeGooglePseResponse(
   data: any,
   _query: string,
@@ -1358,7 +1283,6 @@ const responseNormalizers: Record<string, SearchResponseNormalizer> = {
   "perplexity-search": normalizePerplexityResponse,
   "exa-search": normalizeExaResponse,
   "tavily-search": normalizeTavilyResponse,
-  "nimble-search": normalizeNimbleResponse,
   firecrawl: (data: FirecrawlSearchEnvelope, _query: string, searchType: string) =>
     fcSearch.normalizeFirecrawlSearchResponse(data, searchType, makeResult),
   "google-pse-search": normalizeGooglePseResponse,

open-sse/handlers/webFetch.ts

@@ -21,14 +21,12 @@ import { firecrawlFetch } from "../executors/firecrawl-fetch.ts";
 import { jinaReaderFetch } from "../executors/jina-reader-fetch.ts";
 import { tavilyFetch } from "../executors/tavily-fetch.ts";
 import { tinyfishFetch } from "../executors/tinyfish-fetch.ts";
-import { nimbleFetch } from "../executors/nimble-fetch.ts";
 
 export type WebFetchFormat = "markdown" | "html" | "links" | "screenshot";
 
 export interface WebFetchRequest {
   url: string;
-  provider?:
-    "firecrawl" | "jina-reader" | "tavily-search" | "tinyfish" | "context7" | "nimble-search";
+  provider?: "firecrawl" | "jina-reader" | "tavily-search" | "tinyfish" | "context7";
   format?: WebFetchFormat;
   depth?: 0 | 1 | 2;
   wait_for_selector?: string;
@@ -63,7 +61,6 @@ export const WEB_FETCH_PROVIDERS = Object.freeze([
   "tavily-search",
   "tinyfish",
   "context7",
-  "nimble-search",
 ] as const);
 // Derived from the array — adding a provider to WEB_FETCH_PROVIDERS
 // automatically widens the union; they cannot drift apart.
@@ -142,14 +139,6 @@ export async function handleWebFetch(
           credentials,
         });
 
-      case "nimble-search":
-        return await nimbleFetch({
-          url: req.url,
-          format,
-          includeMetadata,
-          credentials,
-        });
-
       case "context7":
         // Context7 returns llms.txt text only: html/links/screenshot formats are
         // unsupported, and the format field is validated/ignored below.

open-sse/mcp-server/schemas/tools.ts

@@ -557,7 +557,7 @@ export const webFetchInput = z.object({
     .min(1, "URL is required")
     .describe("The URL to fetch content from"),
   provider: z
-    .enum(["firecrawl", "jina-reader", "tavily-search", "tinyfish", "context7", "nimble-search"])
+    .enum(["firecrawl", "jina-reader", "tavily-search", "tinyfish", "context7"])
     .optional()
     .describe(
       "Specific fetch provider to use (default: first available). " +

open-sse/mcp-server/server.ts

@@ -694,8 +694,7 @@ async function handleXSearch(args: {
 
 async function handleWebFetch(args: {
   url: string;
-  provider?:
-    "firecrawl" | "jina-reader" | "tavily-search" | "tinyfish" | "context7" | "nimble-search";
+  provider?: "firecrawl" | "jina-reader" | "tavily-search" | "tinyfish" | "context7";
   format?: "markdown" | "html" | "links" | "screenshot";
   include_metadata?: boolean;
   depth?: number;

open-sse/services/antigravityProjectBootstrap.ts

@@ -30,16 +30,6 @@ const BOOTSTRAP_TIMEOUT_MS = 8_000;
 const ONBOARD_TIMEOUT_MS = 15_000;
 const DEFAULT_TIER_ID = "legacy-tier";
 
-// onboardUser is a Long-Running Operation: Google frequently answers the
-// first call with {"done": false} (no cloudaicompanionProject field yet) and
-// expects the SAME request re-sent every couple of seconds until the
-// operation settles with {"done": true, response: {...}}. Treating the
-// first "done:false" response as "no project" (BYOP) misclassifies a normal
-// in-progress onboarding as "bring your own project" and permanently caches
-// that wrong verdict. Poll bounded, matching 9router's onboardUser().
-const ONBOARD_POLL_MAX_ATTEMPTS = 5;
-const ONBOARD_POLL_INTERVAL_MS = 2_000;
-
 /** Ordered list of loadCodeAssist endpoint URLs. */
 export function getAntigravityLoadCodeAssistUrls(): string[] {
   return ANTIGRAVITY_BOOTSTRAP_BASE_URLS.map((base) => `${base}${LOAD_CODE_ASSIST_PATH}`);
@@ -172,31 +162,10 @@ async function tryLoadCodeAssist(
   return { projectId: null, tierId: DEFAULT_TIER_ID };
 }
 
-/**
- * Extract the project id from a settled ({done:true}) onboardUser response body.
- * The documented LRO shape nests it under `response.cloudaicompanionProject`
- * (matches 9router's onboardUser and Google's Operation envelope), but some
- * observed responses put it at the top level — check both.
- */
-function extractProjectIdFromOnboardResponse(data: Record<string, unknown> | null): string | null {
-  const nested = (data?.response as Record<string, unknown> | undefined)?.cloudaicompanionProject;
-  const project = nested ?? data?.cloudaicompanionProject;
-  if (typeof project === "string") {
-    const id = project.trim();
-    return id || null;
-  }
-  if (project && typeof project === "object") {
-    const id = (project as Record<string, unknown>).id;
-    if (typeof id === "string" && id.trim()) return id.trim();
-  }
-  return null;
-}
-
 /**
  * Attempt onboardUser to create a Cloud Code project for the account.
  * Called when loadCodeAssist returns no project — the account has never
- * been onboarded. Polls the same endpoint on {done:false} responses (an
- * in-progress LRO) before concluding anything about the account.
+ * been onboarded. Returns true if any endpoint reports success.
  */
 async function tryOnboardUser(
   accessToken: string,
@@ -207,74 +176,47 @@ async function tryOnboardUser(
 ): Promise<AntigravityOnboardStatus> {
   const urls = getAntigravityOnboardUrls();
   const headers = getAntigravityContentHeaders(clientProfile, accessToken);
-  const body = JSON.stringify({
-    tier_id: tierId,
-    metadata: getAntigravityLoadCodeAssistMetadata(),
-  });
 
   for (const url of urls) {
-    for (let attempt = 1; attempt <= ONBOARD_POLL_MAX_ATTEMPTS; attempt++) {
-      if (signal?.aborted) throw signal.reason;
-      try {
-        const timeoutSignal = AbortSignal.timeout(ONBOARD_TIMEOUT_MS);
-        const response = await fetchImpl(url, {
-          method: "POST",
-          headers,
-          body,
-          signal: signal ? AbortSignal.any([signal, timeoutSignal]) : timeoutSignal,
-        });
+    if (signal?.aborted) throw signal.reason;
+    try {
+      const timeoutSignal = AbortSignal.timeout(ONBOARD_TIMEOUT_MS);
+      const response = await fetchImpl(url, {
+        method: "POST",
+        headers,
+        body: JSON.stringify({
+          tier_id: tierId,
+          metadata: getAntigravityLoadCodeAssistMetadata(),
+        }),
+        signal: signal ? AbortSignal.any([signal, timeoutSignal]) : timeoutSignal,
+      });
 
-        if (!response.ok) {
+      if (response.ok) {
+        // Accounts Google expects to Bring Their Own Project: onboardUser
+        // returns 200 without a `cloudaicompanionProject` in the body — no
+        // automatic project creation for standard-tier/personal accounts
+        // (tracked in #8491). Detect that so we can fail fast with a clear
+        // instruction instead of retrying forever or fabricating an id that
+        // Google later rejects with a delayed 429 RESOURCE_EXHAUSTED.
+        const body = await response.text().catch(() => "");
+        if (body && !/cloudaicompanionProject/.test(body)) {
           console.warn(
-            `[models] antigravity onboardUser failed at ${url} (${response.status}) — trying next`
+            `[models] antigravity onboardUser done but no project in response at ${url} — Google BYOP (user-defined GCP project) required`
           );
-          break;
+          return "requires_manual_project";
         }
-
-        const data = (await response.json().catch(() => null)) as Record<string, unknown> | null;
-
-        // Only an EXPLICIT `done: false` means "in-progress LRO, poll again".
-        // A proper Google Operation always carries `done` when it is one; a
-        // response with `done` absent entirely (e.g. `{}`) is not an LRO in
-        // progress — it's Google's immediate, settled "no project" answer for
-        // BYOP accounts (#8491) and must fall through to that classification
-        // on the first attempt, same as before this polling was added.
-        if (data?.done === false) {
-          // In-progress LRO — Google hasn't decided (project created, or
-          // BYOP required) yet. Re-send the same request after a short wait.
-          if (attempt < ONBOARD_POLL_MAX_ATTEMPTS) {
-            console.warn(
-              `[models] antigravity onboardUser at ${url} not done yet (attempt ${attempt}/${ONBOARD_POLL_MAX_ATTEMPTS}) — waiting`
-            );
-            await new Promise((resolve) => setTimeout(resolve, ONBOARD_POLL_INTERVAL_MS));
-            continue;
-          }
-          console.warn(
-            `[models] antigravity onboardUser at ${url} still not done after ${ONBOARD_POLL_MAX_ATTEMPTS} attempts — treating as failed`
-          );
-          break;
-        }
-
-        // done:true — Google has settled the operation. Accounts Google
-        // expects to Bring Their Own Project answer with done:true and no
-        // cloudaicompanionProject — no automatic project creation for
-        // standard-tier/personal accounts (tracked in #8491). Only now is it
-        // safe to draw that conclusion.
-        if (extractProjectIdFromOnboardResponse(data)) {
-          return "onboarded";
-        }
-        console.warn(
-          `[models] antigravity onboardUser done but no project in response at ${url} — Google BYOP (user-defined GCP project) required`
-        );
-        return "requires_manual_project";
-      } catch (error) {
-        if (signal?.aborted || (error instanceof Error && error.name === "AbortError")) {
-          throw signal?.reason ?? error;
-        }
-        const msg = error instanceof Error ? error.message : String(error);
-        console.warn(`[models] antigravity onboardUser threw for ${url}: ${msg} — trying next`);
-        break;
+        return "onboarded";
       }
+
+      console.warn(
+        `[models] antigravity onboardUser failed at ${url} (${response.status}) — trying next`
+      );
+    } catch (error) {
+      if (signal?.aborted || (error instanceof Error && error.name === "AbortError")) {
+        throw signal?.reason ?? error;
+      }
+      const msg = error instanceof Error ? error.message : String(error);
+      console.warn(`[models] antigravity onboardUser threw for ${url}: ${msg} — trying next`);
     }
   }
   return "failed";

open-sse/services/apiKeyRotator.ts

@@ -31,10 +31,7 @@ const MAX_CONNECTION_EXTRA_KEYS = 500;
  */
 export function trackConnectionExtraKeys(connectionId: string, extraKeys: string[]): void {
   const validExtras = extraKeys.filter((k) => typeof k === "string" && k.trim().length > 0);
-  if (
-    !_connectionExtraKeys.has(connectionId) &&
-    _connectionExtraKeys.size >= MAX_CONNECTION_EXTRA_KEYS
-  ) {
+  if (!_connectionExtraKeys.has(connectionId) && _connectionExtraKeys.size >= MAX_CONNECTION_EXTRA_KEYS) {
     const oldest = _connectionExtraKeys.keys().next().value;
     if (oldest !== undefined) _connectionExtraKeys.delete(oldest);
   }
@@ -311,29 +308,6 @@ export function syncHealthFromDB(connectionId: string, health?: Record<string, K
   }
 }
 
-/** Recover one authoritatively validated key without changing sibling-key health. */
-export function recoverKeyHealth(
-  connectionId: string,
-  keyId: string,
-  providerSpecificData: unknown
-): Record<string, unknown> | undefined {
-  const data =
-    providerSpecificData && typeof providerSpecificData === "object"
-      ? (providerSpecificData as Record<string, unknown>)
-      : {};
-  const health = data.apiKeyHealth as Record<string, KeyHealth> | undefined;
-  const currentHealth = health?.[keyId];
-  if (!currentHealth || (currentHealth.status === "active" && currentHealth.failures === 0)) {
-    return undefined;
-  }
-
-  syncHealthFromDB(connectionId, health);
-  return {
-    ...data,
-    apiKeyHealth: { ...health, [keyId]: recordKeySuccess(connectionId, keyId) },
-  };
-}
-
 /**
  * Reset the rotation index for a connection.
  * Call this when a key fails (401/403) to skip the bad key next time.

open-sse/services/autoCombo/taskFitness.ts

@@ -10,9 +10,6 @@
  * 2b. Layers 1-2 retried against the base model this id inherits quality scores
  *     from, when `resolveScoresAs` resolves one (#11489). Reported as
  *     `<source>:inherited`.
- * 2c. If the request id or its scoresAs base is vendor-retired (#11625), layers
- *     1–3 are skipped so a leftover arena row cannot short-circuit the layer-3
- *     veto, and a dead *codex id cannot keep the coding wildcard boost.
  * 3. Models.dev tier — derived from `model_capabilities` table capability data,
  *     with a vendor-lifecycle veto (#11508: a retired id never earns a tier
  *     score) and the same base-model inheritance as layers 1–2
@@ -46,7 +43,6 @@ import {
 } from "../../../src/lib/db/modelIntelligence.ts";
 import { readFileSync } from "node:fs";
 import { resolveScoresAs } from "./scoresAs.ts";
-import { isVendorRetiredId } from "../modelLifecycle.ts";
 
 // #11508 — vendor lifecycle snapshot (#11507). An id the vendor has retired
 // must never earn a capability-derived tier score: models.dev keeps listing
@@ -467,60 +463,48 @@ export function getTaskFitness(model: string, taskType: string): number {
   return getTaskFitnessWithSource(model, taskType).score;
 }
 
-function isFitnessRetired(modelId: string): boolean {
-  if (isVendorRetiredId(modelId)) return true;
-  const { base, via } = resolveScoresAs(modelId);
-  return via !== null && isVendorRetiredId(base);
-}
-
 export function getTaskFitnessWithSource(
   model: string,
   taskType: string
 ): { score: number; source: string } {
   const normalizedModel = model.toLowerCase();
   const normalizedTask = taskType.toLowerCase();
-  const fitnessRetired = isFitnessRetired(normalizedModel);
 
-  if (!fitnessRetired) {
-    const userOverride = queryModelIntelligence(normalizedModel, normalizedTask, "user_override");
-    if (userOverride !== null) {
-      return { score: userOverride, source: "user_override" };
-    }
-
-    const arenaElo = queryModelIntelligence(normalizedModel, normalizedTask, "arena_elo");
-    if (arenaElo !== null) {
-      return { score: arenaElo, source: "arena_elo" };
-    }
-
-    // Layers 1-2, retried against the base model this id inherits quality from
-    // (#11489). Every DB-backed source publishes scores for BASE models only, so
-    // a variant id — an effort suffix (`gpt-5.6-sol-xhigh`), a vendor alias
-    // (`gpt-5.6`), a `-free` tier marker (`mimo-v2.5-free`, #4517) — misses both
-    // literal lookups and used to fall all the way to the wildcard 0.5, losing
-    // every comparison against a base model that happens to be benchmarked.
-    // The score is inherited VERBATIM: the 12-factor scoring already prices cost
-    // and latency per variant, so there is no basis for inventing an effort
-    // delta. `:inherited` keeps the indirection visible to callers.
-    const inherited = lookupInheritedFitness(normalizedModel, normalizedTask);
-    if (inherited !== null) {
-      return inherited;
-    }
-
-    const tierScore = getModelsDevTierFitness(normalizedModel, normalizedTask);
-    if (tierScore !== null) {
-      return { score: tierScore, source: "models_dev_tier" };
-    }
-
-    const staticScore = lookupStaticFitnessTable(normalizedModel, normalizedTask);
-    if (staticScore !== null) {
-      return { score: staticScore, source: "fitness_table" };
-    }
-
-    return { score: lookupWildcardBoosts(normalizedModel, normalizedTask), source: "wildcard_boost" };
+  const userOverride = queryModelIntelligence(normalizedModel, normalizedTask, "user_override");
+  if (userOverride !== null) {
+    return { score: userOverride, source: "user_override" };
   }
 
-  // Retired: 0.5 is "no evidence", never a quality claim and never a *codex boost.
-  return { score: 0.5, source: "wildcard_boost" };
+  const arenaElo = queryModelIntelligence(normalizedModel, normalizedTask, "arena_elo");
+  if (arenaElo !== null) {
+    return { score: arenaElo, source: "arena_elo" };
+  }
+
+  // Layers 1-2, retried against the base model this id inherits quality from
+  // (#11489). Every DB-backed source publishes scores for BASE models only, so
+  // a variant id — an effort suffix (`gpt-5.6-sol-xhigh`), a vendor alias
+  // (`gpt-5.6`), a `-free` tier marker (`mimo-v2.5-free`, #4517) — misses both
+  // literal lookups and used to fall all the way to the wildcard 0.5, losing
+  // every comparison against a base model that happens to be benchmarked.
+  // The score is inherited VERBATIM: the 12-factor scoring already prices cost
+  // and latency per variant, so there is no basis for inventing an effort
+  // delta. `:inherited` keeps the indirection visible to callers.
+  const inherited = lookupInheritedFitness(normalizedModel, normalizedTask);
+  if (inherited !== null) {
+    return inherited;
+  }
+
+  const tierHit = getModelsDevTierFitnessWithSource(normalizedModel, normalizedTask);
+  if (tierHit !== null) {
+    return tierHit;
+  }
+
+  const staticScore = lookupStaticFitnessTable(normalizedModel, normalizedTask);
+  if (staticScore !== null) {
+    return { score: staticScore, source: "fitness_table" };
+  }
+
+  return { score: lookupWildcardBoosts(normalizedModel, normalizedTask), source: "wildcard_boost" };
 }
 
 /**
@@ -540,7 +524,6 @@ function lookupInheritedFitness(
   const { base, via } = resolveScoresAs(normalizedModel);
   if (via === null || base === normalizedModel) return null;
   const normalizedBase = base.toLowerCase();
-  if (isVendorRetiredId(normalizedBase)) return null;
 
   for (const source of ["user_override", "arena_elo"] as const) {
     const score = queryModelIntelligence(normalizedBase, normalizedTask, source);

open-sse/services/combo.ts

@@ -70,7 +70,6 @@ import { resolveProviderId } from "../../src/shared/constants/providers.ts";
 import * as semaphore from "./rateLimitSemaphore.ts";
 import { getCircuitBreaker } from "../../src/shared/utils/circuitBreaker";
 import { parseModel } from "./model.ts";
-import { rejectRetiredAutoComboCandidates } from "./modelLifecycle.ts";
 import { createComboContext } from "./combo/context.ts";
 import { phaseComboSetup } from "./combo/comboSetup.ts";
 import { checkCredentialGate, logCredentialSkip } from "./credentialGate.ts";
@@ -628,14 +627,11 @@ export async function buildAutoCandidates(
     })
   );
 
-  // Filter out candidates whose model is hidden by the user in the dashboard,
-  // then drop vendor-retired ids so auto-combo cannot pick them (#11625).
-  return rejectRetiredAutoComboCandidates(
-    candidates.filter((c) => {
-      const hiddenModels = hiddenModelsMap.get(c.provider);
-      return !hiddenModels?.has(c.model);
-    })
-  );
+  // Filter out candidates whose model is hidden by the user in the dashboard
+  return candidates.filter((c) => {
+    const hiddenModels = hiddenModelsMap.get(c.provider);
+    return !hiddenModels?.has(c.model);
+  });
 }
 
 // Context-cache pin health gate — moved to combo/dispatchPrelude.ts alongside the

open-sse/services/contextHandoff.ts

@@ -230,10 +230,7 @@ function formatMessagesForPrompt(messages: MessageLike[]): string {
     .join("\n\n");
 }
 
-export function selectMessagesForSummary(
-  messages: MessageLike[],
-  maxMessages: number
-): MessageLike[] {
+export function selectMessagesForSummary(messages: MessageLike[], maxMessages: number): MessageLike[] {
   const validMessages = messages.filter((m) => m && typeof m === "object");
   const system = validMessages.filter(
     (m) => typeof m.role === "string" && (m.role === "system" || m.role === "developer")
@@ -629,15 +626,6 @@ async function generateUniversalHandoffAsync(options: {
 
   const summaryPrompt = HANDOFF_PROMPT_TEMPLATE.replace("{HISTORY}", historyText);
   const summaryModel = options.handoffModel || options.currModel;
-
-  if (options.providerAllowlist.length > 0) {
-    const slashIdx = summaryModel.indexOf("/");
-    const modelProvider = slashIdx > 0 ? summaryModel.slice(0, slashIdx) : "";
-    if (modelProvider && !options.providerAllowlist.includes(modelProvider)) {
-      return;
-    }
-  }
-
   const summaryBody: Record<string, unknown> = {
     model: summaryModel,
     messages: [{ role: "user", content: summaryPrompt }],

open-sse/services/modelLifecycle.ts

@@ -4,14 +4,7 @@
  * Replacement model IDs are migration guidance only. This module never rewrites a
  * request: shutdown models are rejected, deprecated models remain callable until
  * their shutdown date, and untracked models pass through unchanged.
- *
- * Dated OpenAI rows in MODEL_LIFECYCLE_RECORDS stay provider-scoped (a warn-before-
- * shutdown date on `openai` must not leak onto an aggregator that still serves the
- * id). Snapshot `status: "retired"` ids from config/quality/model-lifecycle.json
- * are id-scoped and prefix-stripped (#11625): `openai/gpt-5.2-codex` on openrouter
- * is the same retired vendor id as `gpt-5.2-codex`.
  */
-import { readFileSync } from "node:fs";
 
 export const OPENAI_MODEL_DEPRECATIONS_URL = "https://developers.openai.com/api/docs/deprecations";
 
@@ -135,67 +128,6 @@ function shutdownTimestamp(shutdownAt: string): number {
   return Date.parse(`${shutdownAt}T00:00:00.000Z`);
 }
 
-const SNAPSHOT_URL = new URL("../../config/quality/model-lifecycle.json", import.meta.url);
-const SNAPSHOT_SOURCE = "config/quality/model-lifecycle.json";
-
-type VendorRetiredEntry = {
-  vendor?: string;
-  status?: string;
-  retiredOn?: string | null;
-  replacement?: string | null;
-};
-
-let _retiredIds: Set<string> | null = null;
-let _retiredEntries: Map<string, VendorRetiredEntry> | null = null;
-
-function loadVendorRetiredSnapshot(): {
-  ids: Set<string>;
-  entries: Map<string, VendorRetiredEntry>;
-} {
-  if (_retiredIds && _retiredEntries) return { ids: _retiredIds, entries: _retiredEntries };
-  const ids = new Set<string>();
-  const entries = new Map<string, VendorRetiredEntry>();
-  try {
-    const parsed = JSON.parse(readFileSync(SNAPSHOT_URL, "utf8")) as {
-      retired?: Record<string, VendorRetiredEntry>;
-    };
-    for (const [id, entry] of Object.entries(parsed.retired ?? {})) {
-      if (entry?.status !== "retired") continue;
-      const key = id.toLowerCase();
-      ids.add(key);
-      entries.set(key, entry);
-    }
-  } catch {
-    // Snapshot missing → no id-scoped veto. Dated OpenAI rows still apply.
-  }
-  _retiredIds = ids;
-  _retiredEntries = entries;
-  return { ids, entries };
-}
-
-/** True when `modelId` or its last `vendor/` path segment is `status: "retired"` in the snapshot. */
-export function isVendorRetiredId(modelId: string | null | undefined): boolean {
-  if (typeof modelId !== "string" || modelId.length === 0) return false;
-  const lower = modelId.toLowerCase();
-  const { ids } = loadVendorRetiredSnapshot();
-  if (ids.has(lower)) return true;
-  const slash = lower.lastIndexOf("/");
-  return slash !== -1 && ids.has(lower.slice(slash + 1));
-}
-
-function lookupVendorRetiredEntry(modelId: string): VendorRetiredEntry | null {
-  const lower = modelId.toLowerCase();
-  const { entries } = loadVendorRetiredSnapshot();
-  return entries.get(lower) ?? entries.get(lower.slice(lower.lastIndexOf("/") + 1)) ?? null;
-}
-
-/** Drop auto-combo candidates whose model id the vendor has retired (#11625). */
-export function rejectRetiredAutoComboCandidates<T extends { model: string }>(
-  candidates: readonly T[]
-): T[] {
-  return candidates.filter((candidate) => !isVendorRetiredId(candidate.model));
-}
-
 export function getModelLifecycleDecision(
   provider: string | null | undefined,
   model: string | null | undefined,
@@ -206,24 +138,6 @@ export function getModelLifecycleDecision(
   const record = RECORDS_BY_KEY.get(lifecycleKey(normalizedProvider, normalizedModel));
 
   if (!record) {
-    if (isVendorRetiredId(normalizedModel)) {
-      const entry = lookupVendorRetiredEntry(normalizedModel);
-      const replacementId =
-        typeof entry?.replacement === "string" && entry.replacement.length > 0
-          ? entry.replacement
-          : null;
-      return {
-        provider: normalizedProvider,
-        model: normalizedModel,
-        status: "shutdown",
-        action: "reject",
-        shutdownAt: typeof entry?.retiredOn === "string" ? entry.retiredOn : null,
-        replacement: replacementId
-          ? { provider: entry?.vendor ?? "", model: replacementId }
-          : null,
-        source: SNAPSHOT_SOURCE,
-      };
-    }
     return {
       provider: normalizedProvider,
       model: normalizedModel,
@@ -256,8 +170,7 @@ export function formatModelLifecycleMessage(decision: ModelLifecycleDecision): s
     ? ` Use "${decision.replacement.provider}/${decision.replacement.model}" instead.`
     : "";
   if (decision.status === "shutdown") {
-    const when = decision.shutdownAt ? ` was shut down on ${decision.shutdownAt}` : " has been retired by its vendor";
-    return `Model "${modelRef}"${when} and cannot be routed automatically.${replacement}`;
+    return `Model "${modelRef}" was shut down on ${decision.shutdownAt} and cannot be routed automatically.${replacement}`;
   }
   return `Model "${modelRef}" is deprecated and is scheduled to shut down on ${decision.shutdownAt}.${replacement}`;
 }

open-sse/translator/request/claude-to-gemini.ts

@@ -2,6 +2,7 @@ import { register } from "../registry.ts";
 import { FORMATS } from "../formats.ts";
 import {
   DEFAULT_SAFETY_SETTINGS,
+  tryParseJSON,
   cleanJSONSchemaForAntigravity,
 } from "../helpers/geminiHelper.ts";
 import { buildGeminiTools, sanitizeGeminiToolName } from "../helpers/geminiToolsSanitizer.ts";
@@ -185,6 +186,13 @@ export function claudeToGeminiRequest(model, body, stream, credentials = null) {
                   .map((c) => (c.type === "text" ? c.text : JSON.stringify(c)))
                   .join("\n");
               }
+              let parsedContent = tryParseJSON(content);
+              if (parsedContent === null) {
+                parsedContent = { result: content };
+              } else if (typeof parsedContent !== "object") {
+                parsedContent = { result: parsedContent };
+              }
+
               const toolUseId = block.tool_use_id;
               const name = toolUseNames[toolUseId] || "unknown";
 
@@ -202,7 +210,7 @@ export function claudeToGeminiRequest(model, body, stream, credentials = null) {
                 functionResponse: {
                   ...(stripFunctionCallId ? {} : { id: toolUseId }),
                   name,
-                  response: { result: content },
+                  response: { result: parsedContent },
                 },
               });
               break;

open-sse/translator/request/openai-to-gemini.ts

@@ -511,12 +511,18 @@ function openaiToGeminiBase(
               name = sanitizeToolName(name);
 
               const resp = toolResponses[fid];
+              let parsedResp = tryParseJSON(resp);
+              if (parsedResp === null) {
+                parsedResp = { result: resp };
+              } else if (typeof parsedResp !== "object") {
+                parsedResp = { result: parsedResp };
+              }
 
               toolParts.push({
                 functionResponse: {
                   ...(toolNameOptions.stripFunctionCallId ? {} : { id: fid }),
                   name: name,
-                  response: { result: resp },
+                  response: { result: parsedResp },
                 },
               });
             }

package-lock.json

@@ -86,6 +86,7 @@
         "undici": "^8.10.0",
         "update-notifier": "^7.3.1",
         "uuid": "^14.0.0",
+        "wreq-js": "3.1.0",
         "ws": "^8.21.3",
         "xxhash-wasm": "^1.1.0",
         "yazl": "^3.3.1",
@@ -109,7 +110,7 @@
         "@testing-library/react": "^16.3.2",
         "@testing-library/user-event": "^14.6.6",
         "@types/better-sqlite3": "^9.6.0",
-        "@types/bun": "latest",
+        "@types/bun": "*",
         "@types/node": "^26.2.0",
         "@types/react": "^19.2.18",
         "@types/react-dom": "^19.2.4",
@@ -160,7 +161,7 @@
         "better-sqlite3": "^13.0.2",
         "js-tiktoken": "^1.0.20",
         "keytar": "^7.9.0",
-        "onnxruntime-node": "1.24.3",
+        "onnxruntime-node": "1.27.0",
         "sqlite-vec": "^0.1.9",
         "tls-client-node": "^0.2.0",
         "wreq-js": "^3.1.0"
@@ -15120,14 +15121,6 @@
         "url": "https://opencollective.com/express"
       }
     },
-    "node_modules/boolean": {
-      "version": "3.2.0",
-      "resolved": "https://registry.npmjs.org/boolean/-/boolean-3.2.0.tgz",
-      "integrity": "sha512-d0II/GO9uf9lfUHH2BQsjxzRJZBdsjgsBiW4BvhWk/3qoKwQFjIDVN19PfX8F2D/r9PCMTtLWjYVCFrpeYUzsw==",
-      "deprecated": "Package no longer supported. Contact Support at https://www.npmjs.com/support for more info.",
-      "license": "MIT",
-      "optional": true
-    },
     "node_modules/bottleneck": {
       "version": "2.19.5",
       "resolved": "https://registry.npmjs.org/bottleneck/-/bottleneck-2.19.5.tgz",
@@ -18213,13 +18206,6 @@
         "node": ">=8"
       }
     },
-    "node_modules/detect-node": {
-      "version": "2.1.0",
-      "resolved": "https://registry.npmjs.org/detect-node/-/detect-node-2.1.0.tgz",
-      "integrity": "sha512-T0NIuQpnTvFDATNuHN5roPwSBG83rFsuO+MXXH9/3N1eFbn4wcPjttvjMLEPWJ0RGUYgQE7cGgS3tNxbqCGM7g==",
-      "license": "MIT",
-      "optional": true
-    },
     "node_modules/detect-node-es": {
       "version": "1.1.0",
       "resolved": "https://registry.npmjs.org/detect-node-es/-/detect-node-es-1.1.0.tgz",
@@ -19065,13 +19051,6 @@
         "benchmarks"
       ]
     },
-    "node_modules/es6-error": {
-      "version": "4.1.1",
-      "resolved": "https://registry.npmjs.org/es6-error/-/es6-error-4.1.1.tgz",
-      "integrity": "sha512-Um/+FxMr9CISWh0bi5Zv0iOD+4cFh5qLeks1qhAopKVAJw3drgKbKySikp7wGhDL0HPeaja0P5ULZrxLkniUVg==",
-      "license": "MIT",
-      "optional": true
-    },
     "node_modules/es6-promisify": {
       "version": "7.0.0",
       "resolved": "https://registry.npmjs.org/es6-promisify/-/es6-promisify-7.0.0.tgz",
@@ -21878,18 +21857,16 @@
       }
     },
     "node_modules/global-agent": {
-      "version": "3.0.0",
-      "resolved": "https://registry.npmjs.org/global-agent/-/global-agent-3.0.0.tgz",
-      "integrity": "sha512-PT6XReJ+D07JvGoxQMkT6qji/jVNfX/h364XHZOWeRzy64sSFr+xJ5OX7LI3b4MPQzdL4H8Y8M0xzPpsVMwA8Q==",
+      "version": "4.1.3",
+      "resolved": "https://registry.npmjs.org/global-agent/-/global-agent-4.1.3.tgz",
+      "integrity": "sha512-KUJEViiuFT3I97t+GYMikLPJS2Lfo/S2F+DQuBWzuzaMPnvt5yyZePzArx36fBzpGTxZjIpDbXLeySLgh+k76g==",
       "license": "BSD-3-Clause",
       "optional": true,
       "dependencies": {
-        "boolean": "^3.0.1",
-        "es6-error": "^4.1.1",
-        "matcher": "^3.0.0",
-        "roarr": "^2.15.3",
-        "semver": "^7.3.2",
-        "serialize-error": "^7.0.1"
+        "globalthis": "^1.0.2",
+        "matcher": "^4.0.0",
+        "semver": "^7.3.5",
+        "serialize-error": "^8.1.0"
       },
       "engines": {
         "node": ">=10.0"
@@ -25447,13 +25424,6 @@
         "url": "https://github.com/sponsors/isaacs"
       }
     },
-    "node_modules/json-stringify-safe": {
-      "version": "5.0.1",
-      "resolved": "https://registry.npmjs.org/json-stringify-safe/-/json-stringify-safe-5.0.1.tgz",
-      "integrity": "sha512-ZClg6AaYvamvYEE82d3Iyd3vSSIjQ+odgjaTzRuO3s7toCdFKczob2i0zCh7JE8kWn17yvAWhUVxvqGwUalsRA==",
-      "license": "ISC",
-      "optional": true
-    },
     "node_modules/json5": {
       "version": "2.2.3",
       "resolved": "https://registry.npmjs.org/json5/-/json5-2.2.3.tgz",
@@ -27322,9 +27292,9 @@
       }
     },
     "node_modules/matcher": {
-      "version": "3.0.0",
-      "resolved": "https://registry.npmjs.org/matcher/-/matcher-3.0.0.tgz",
-      "integrity": "sha512-OkeDaAZ/bQCxeFAozM55PKcKU0yJMPGifLwV4Qgjitu+5MoAfSQN4lsLJeXZ1b8w0x+/Emda6MZgXS1jvsapng==",
+      "version": "4.0.0",
+      "resolved": "https://registry.npmjs.org/matcher/-/matcher-4.0.0.tgz",
+      "integrity": "sha512-S6x5wmcDmsDRRU/c2dkccDwQPXoFczc5+HpQ2lON8pnvHlnvHAHj5WlLVvw6n6vNyHuVugYrFohYxbS+pvFpKQ==",
       "license": "MIT",
       "optional": true,
       "dependencies": {
@@ -27332,6 +27302,9 @@
       },
       "engines": {
         "node": ">=10"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/sindresorhus"
       }
     },
     "node_modules/material-symbols": {
@@ -30304,16 +30277,16 @@
       }
     },
     "node_modules/onnxruntime-common": {
-      "version": "1.24.3",
-      "resolved": "https://registry.npmjs.org/onnxruntime-common/-/onnxruntime-common-1.24.3.tgz",
-      "integrity": "sha512-GeuPZO6U/LBJXvwdaqHbuUmoXiEdeCjWi/EG7Y1HNnDwJYuk6WUbNXpF6luSUY8yASul3cmUlLGrCCL1ZgVXqA==",
+      "version": "1.27.0",
+      "resolved": "https://registry.npmjs.org/onnxruntime-common/-/onnxruntime-common-1.27.0.tgz",
+      "integrity": "sha512-3KxL5wIVqa8Ex08jxSzncm9CMgw8CjOFyOQ7SxvG9o0cVLlhTNKXyIQuTbtX4tGPJEf73OER2xrjt4HJSBL4ow==",
       "license": "MIT",
       "optional": true
     },
     "node_modules/onnxruntime-node": {
-      "version": "1.24.3",
-      "resolved": "https://registry.npmjs.org/onnxruntime-node/-/onnxruntime-node-1.24.3.tgz",
-      "integrity": "sha512-JH7+czbc8ALA819vlTgcV+Q214/+VjGeBHDjX81+ZCD0PCVCIFGFNtT0V4sXG/1JXypKPgScQcB3ij/hk3YnTg==",
+      "version": "1.27.0",
+      "resolved": "https://registry.npmjs.org/onnxruntime-node/-/onnxruntime-node-1.27.0.tgz",
+      "integrity": "sha512-QEzGwrvNBgv4uPVdnbHsOGG4G6T96mdlcFI8aAKPjMU8wOPpVocPXb6k3QGkaZagVTv2G9Bnnbo6Z3JdXr1fQw==",
       "hasInstallScript": true,
       "license": "MIT",
       "optional": true,
@@ -30324,8 +30297,8 @@
       ],
       "dependencies": {
         "adm-zip": "^0.5.16",
-        "global-agent": "^3.0.0",
-        "onnxruntime-common": "1.24.3"
+        "global-agent": "^4.1.3",
+        "onnxruntime-common": "1.27.0"
       }
     },
     "node_modules/onnxruntime-web": {
@@ -34002,24 +33975,6 @@
         "url": "https://github.com/sponsors/isaacs"
       }
     },
-    "node_modules/roarr": {
-      "version": "2.15.4",
-      "resolved": "https://registry.npmjs.org/roarr/-/roarr-2.15.4.tgz",
-      "integrity": "sha512-CHhPh+UNHD2GTXNYhPWLnU8ONHdI+5DI+4EYIAOaiD63rHeYlZvyh8P+in5999TTSFgUYuKUAjzRI4mdh/p+2A==",
-      "license": "BSD-3-Clause",
-      "optional": true,
-      "dependencies": {
-        "boolean": "^3.0.1",
-        "detect-node": "^2.0.4",
-        "globalthis": "^1.0.1",
-        "json-stringify-safe": "^5.0.1",
-        "semver-compare": "^1.0.0",
-        "sprintf-js": "^1.1.2"
-      },
-      "engines": {
-        "node": ">=8.0"
-      }
-    },
     "node_modules/robot3": {
       "version": "0.4.1",
       "resolved": "https://registry.npmjs.org/robot3/-/robot3-0.4.1.tgz",
@@ -34379,13 +34334,6 @@
         "semver": "bin/semver.js"
       }
     },
-    "node_modules/semver-compare": {
-      "version": "1.0.0",
-      "resolved": "https://registry.npmjs.org/semver-compare/-/semver-compare-1.0.0.tgz",
-      "integrity": "sha512-YM3/ITh2MJ5MtzaM429anh+x2jiLVjqILF4m4oyQB18W7Ggea7BfqdH/wGMK7dDiMghv/6WG7znWMwUDzJiXow==",
-      "license": "MIT",
-      "optional": true
-    },
     "node_modules/send": {
       "version": "1.2.1",
       "resolved": "https://registry.npmjs.org/send/-/send-1.2.1.tgz",
@@ -34413,13 +34361,13 @@
       }
     },
     "node_modules/serialize-error": {
-      "version": "7.0.1",
-      "resolved": "https://registry.npmjs.org/serialize-error/-/serialize-error-7.0.1.tgz",
-      "integrity": "sha512-8I8TjW5KMOKsZQTvoxjuSIa7foAwPWGOts+6o7sgjz41/qMD9VQHEDxi6PBvK2l0MXUmqZyNpUK+T2tQaaElvw==",
+      "version": "8.1.0",
+      "resolved": "https://registry.npmjs.org/serialize-error/-/serialize-error-8.1.0.tgz",
+      "integrity": "sha512-3NnuWfM6vBYoy5gZFvHiYsVbafvI9vZv/+jlIigFn4oP4zjNPK3LhcY0xSCgeb1a5L8jO71Mit9LlNoi2UfDDQ==",
       "license": "MIT",
       "optional": true,
       "dependencies": {
-        "type-fest": "^0.13.1"
+        "type-fest": "^0.20.2"
       },
       "engines": {
         "node": ">=10"
@@ -34429,9 +34377,9 @@
       }
     },
     "node_modules/serialize-error/node_modules/type-fest": {
-      "version": "0.13.1",
-      "resolved": "https://registry.npmjs.org/type-fest/-/type-fest-0.13.1.tgz",
-      "integrity": "sha512-34R7HTnG0XIJcBSn5XhDd7nNFPRcXYRZrBB2O2jdKqYODldSzBAqzsWoZYYvduky73toYS/ESqxPvkDf/F0XMg==",
+      "version": "0.20.2",
+      "resolved": "https://registry.npmjs.org/type-fest/-/type-fest-0.20.2.tgz",
+      "integrity": "sha512-Ne+eE4r0/iWnpAxD852z3A+N0Bt5RN//NjJwRd2VFHEmrywxf5vsZlh4R6lixl6B+wz/8d+maTSAkN1FIkI3LQ==",
       "license": "(MIT OR CC0-1.0)",
       "optional": true,
       "engines": {
@@ -35201,13 +35149,6 @@
         "node": ">= 10.x"
       }
     },
-    "node_modules/sprintf-js": {
-      "version": "1.1.3",
-      "resolved": "https://registry.npmjs.org/sprintf-js/-/sprintf-js-1.1.3.tgz",
-      "integrity": "sha512-Oo+0REFV59/rz3gfJNKQiBlwfHaSESl1pcGyABQsnnIfWOFt6JNj5gCog2U6MLZ//IGYD+nA8nI+mTShREReaA==",
-      "license": "BSD-3-Clause",
-      "optional": true
-    },
     "node_modules/sql.js": {
       "version": "1.14.2",
       "resolved": "https://registry.npmjs.org/sql.js/-/sql.js-1.14.2.tgz",

package.json

@@ -1,7 +1,7 @@
 {
   "name": "omniroute",
   "version": "3.8.51",
-  "description": "Unified AI router with 354 providers, RTK+Caveman compression, auto fallback, MCP/A2A, desktop, PWA, and OpenAI-compatible APIs.",
+  "description": "Unified AI router with 353 providers, RTK+Caveman compression, auto fallback, MCP/A2A, desktop, PWA, and OpenAI-compatible APIs.",
   "type": "module",
   "bin": {
     "omniroute": "bin/omniroute.mjs",
@@ -252,7 +252,7 @@
     "postinstall": "node scripts/build/postinstall.mjs",
     "uninstall": "node scripts/build/uninstall.mjs",
     "uninstall:full": "node scripts/build/uninstall.mjs --full",
-    "prepare": "node -e \"try{require.resolve('husky')}catch(e){process.exit(0)};require('child_process').execSync('husky',{stdio:'inherit'})\"",
+    "prepare": "husky",
     "system-info": "node scripts/dev/system-info.mjs",
     "build:cli-api": "node --import tsx/esm scripts/cli/generate-api-commands.mjs",
     "postbuild": "node scripts/build/colocate-standalone.mjs",
@@ -347,7 +347,7 @@
     "better-sqlite3": "^13.0.2",
     "js-tiktoken": "^1.0.20",
     "keytar": "^7.9.0",
-    "onnxruntime-node": "1.24.3",
+    "onnxruntime-node": "1.27.0",
     "sqlite-vec": "^0.1.9",
     "tls-client-node": "^0.2.0",
     "wreq-js": "^3.1.0"
@@ -436,7 +436,7 @@
     "unrs-resolver": true
   },
   "overrides": {
-    "onnxruntime-node": "1.24.3",
+    "onnxruntime-node": "1.27.0",
     "fast-xml-parser": "^5.10.1",
     "sharp": "^0.35.3",
     "postcss": "^8.5.18",

public/providers/nimble-search.svg

@@ -1,7 +0,0 @@
-<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" role="img" aria-label="Nimble">
-  <rect width="24" height="24" rx="5" fill="#6D28D9" />
-  <path
-    d="M7 17V7h2.1l5.8 6.6V7H17v10h-2.1L9.1 10.4V17H7z"
-    fill="#fff"
-  />
-</svg>

scripts/ad-hoc/nvidia-startswith-diag.ts

@@ -19,20 +19,12 @@
  */
 
 const KEY = process.env.NVIDIA_API_KEY ?? "";
-const BASE_URL =
-  process.env.NVIDIA_BASE_URL || "https://integrate.api.nvidia.com/v1/chat/completions";
+const BASE_URL = process.env.NVIDIA_BASE_URL || "https://integrate.api.nvidia.com/v1/chat/completions";
 const MODEL = process.env.NVIDIA_MODEL || "openai/gpt-oss-120b";
 
 // Neutralize CR/LF before logging so env-derived values (NVIDIA_MODEL, etc.)
-// cannot forge extra log lines (S5145 log injection). Also strip any raw
-// occurrence of the API key so an upstream error/response that echoes it
-// back (e.g. inside err.stack or a validation result) never reaches the
-// terminal in clear text (js/clear-text-logging, CWE-312/532).
-const line = (s = "") => {
-  let out = String(s).replace(/[\r\n]+/g, " ");
-  if (KEY) out = out.split(KEY).join("[REDACTED]");
-  console.log(out);
-};
+// cannot forge extra log lines (S5145 log injection).
+const line = (s = "") => console.log(String(s).replace(/[\r\n]+/g, " "));
 const hr = () => line("─".repeat(72));
 
 function show(label: string, value: unknown) {
@@ -60,13 +52,8 @@ async function partA() {
     });
     line("  ✅ validateProviderApiKey retornou (sem crash):");
     show("resultado", result);
-    if (
-      typeof (result as any)?.error === "string" &&
-      (result as any).error.includes("startsWith")
-    ) {
-      line(
-        "  ⚠️  A mensagem de erro contém 'startsWith' → crash CAPTURADO dentro do try/catch da validação."
-      );
+    if (typeof (result as any)?.error === "string" && (result as any).error.includes("startsWith")) {
+      line("  ⚠️  A mensagem de erro contém 'startsWith' → crash CAPTURADO dentro do try/catch da validação.");
     }
   } catch (err: any) {
     line("  ❌ validateProviderApiKey LANÇOU (crash não tratado):");

src/app/(dashboard)/dashboard/analytics/SearchAnalyticsTab.tsx

@@ -22,52 +22,6 @@ interface SearchStats {
   avgDurationMs: number;
 }
 
-function isFiniteNumber(value: unknown): value is number {
-  return typeof value === "number" && Number.isFinite(value);
-}
-
-function isSearchStats(value: unknown): value is SearchStats {
-  if (!value || typeof value !== "object") return false;
-
-  const candidate = value as Partial<SearchStats>;
-  return (
-    isFiniteNumber(candidate.total) &&
-    isFiniteNumber(candidate.today) &&
-    isFiniteNumber(candidate.cached) &&
-    isFiniteNumber(candidate.errors) &&
-    isFiniteNumber(candidate.totalCostUsd) &&
-    isFiniteNumber(candidate.cacheHitRate) &&
-    isFiniteNumber(candidate.avgDurationMs) &&
-    !!candidate.byProvider &&
-    typeof candidate.byProvider === "object" &&
-    !Array.isArray(candidate.byProvider) &&
-    Object.values(candidate.byProvider).every(
-      (provider) =>
-        !!provider &&
-        typeof provider === "object" &&
-        isFiniteNumber(provider.count) &&
-        isFiniteNumber(provider.costUsd)
-    ) &&
-    Array.isArray(candidate.last24h) &&
-    candidate.last24h.every(
-      (point) => typeof point.hour === "string" && isFiniteNumber(point.count)
-    )
-  );
-}
-
-async function readSearchStats(response: Response): Promise<SearchStats> {
-  const body: unknown = await response.json().catch(() => null);
-  if (!response.ok) {
-    const message =
-      body && typeof body === "object" && "error" in body && typeof body.error === "string"
-        ? body.error
-        : null;
-    throw new Error(message ?? "searchAnalyticsNoData");
-  }
-  if (!isSearchStats(body)) throw new Error("searchAnalyticsNoData");
-  return body;
-}
-
 function StatCard({
   icon,
   label,
@@ -131,25 +85,16 @@ export default function SearchAnalyticsTab() {
   const [error, setError] = useState<string | null>(null);
 
   useEffect(() => {
-    let cancelled = false;
-    const controller = new AbortController();
-    async function loadStats() {
-      try {
-        const response = await fetch("/api/v1/search/analytics", { signal: controller.signal });
-        const nextStats = await readSearchStats(response);
-        if (!cancelled) setStats(nextStats);
-      } catch (cause) {
-        const message = cause instanceof Error ? cause.message : "searchAnalyticsNoData";
-        if (!cancelled) setError(message);
-      } finally {
-        if (!cancelled) setLoading(false);
-      }
-    }
-    void loadStats();
-    return () => {
-      cancelled = true;
-      controller.abort();
-    };
+    fetch("/api/v1/search/analytics")
+      .then((r) => r.json())
+      .then((d) => {
+        setStats(d);
+        setLoading(false);
+      })
+      .catch((e) => {
+        setError(e.message);
+        setLoading(false);
+      });
   }, []);
 
   if (loading) {

src/app/(dashboard)/dashboard/profile/page.tsx

@@ -249,23 +249,21 @@ export default function ProfilePage() {
           <div className="grid grid-cols-2 sm:grid-cols-3 md:grid-cols-4 lg:grid-cols-5 gap-4">
             {allBadges.map((badge) => {
               const isEarned = earnedIds.has(badge.id);
-              const isHiddenAndLocked = Boolean(badge.hidden) && !isEarned;
               const earnedInfo = earnedBadges.find((b) => b.badgeId === badge.id);
               const rarityColor = RARITY_COLORS[badge.rarity] || RARITY_COLORS.common;
 
               return (
                 <button
                   key={badge.id}
-                  onClick={() => !isHiddenAndLocked && setSelectedBadge(badge)}
-                  disabled={isHiddenAndLocked}
+                  onClick={() => setSelectedBadge(badge)}
                   className={`relative p-4 rounded-xl border transition-all text-left ${
                     isEarned
                       ? `${rarityColor} bg-surface hover:shadow-md`
-                      : "border-border/50 bg-surface/50 opacity-50 grayscale enabled:hover:opacity-70 disabled:cursor-default"
+                      : "border-border/50 bg-surface/50 opacity-50 grayscale hover:opacity-70"
                   }`}
                 >
                   <div className="text-3xl mb-2">
-                    <BadgeIcon icon={isHiddenAndLocked ? null : badge.icon} earned={isEarned} />
+                    <BadgeIcon icon={badge.icon} earned={isEarned} />
                   </div>
                   <p className="font-semibold text-sm truncate">
                     {badge.hidden && !isEarned ? "???" : translateBadge(badge, "name")}

src/app/(dashboard)/dashboard/providers/[id]/components/PeakHourProtectionEditor.tsx

@@ -1,247 +0,0 @@
-"use client";
-
-import { Button, Input, Select, Toggle } from "@/shared/components";
-import {
-  PEAK_HOUR_PROTECTION_DAYS,
-  type PeakHourProtectionConfig,
-  type PeakHourProtectionDay,
-  type PeakHourProtectionMode,
-  type PeakHourWindow,
-} from "@/lib/providers/peakHourProtection";
-import { providerText, type ProviderMessageTranslator } from "../providerPageHelpers";
-
-export const EMPTY_PEAK_HOUR_PROTECTION: PeakHourProtectionConfig = {
-  enabled: false,
-  mode: "block",
-  windows: [],
-};
-
-const DAY_LABELS: Record<PeakHourProtectionDay, string> = {
-  mon: "Mon",
-  tue: "Tue",
-  wed: "Wed",
-  thu: "Thu",
-  fri: "Fri",
-  sat: "Sat",
-  sun: "Sun",
-};
-
-function cloneConfig(value: unknown): PeakHourProtectionConfig {
-  if (!value || typeof value !== "object" || Array.isArray(value)) {
-    return { ...EMPTY_PEAK_HOUR_PROTECTION, windows: [] };
-  }
-  const record = value as Record<string, unknown>;
-  const mode: PeakHourProtectionMode = record.mode === "avoid" ? "avoid" : "block";
-  const windows = Array.isArray(record.windows)
-    ? record.windows
-        .filter((entry): entry is PeakHourWindow => !!entry && typeof entry === "object")
-        .map((entry) => ({
-          id: typeof entry.id === "string" ? entry.id : crypto.randomUUID(),
-          name: typeof entry.name === "string" ? entry.name : "",
-          days: Array.isArray(entry.days)
-            ? entry.days.filter((day): day is PeakHourProtectionDay =>
-                (PEAK_HOUR_PROTECTION_DAYS as readonly string[]).includes(day)
-              )
-            : [],
-          startUtc: typeof entry.startUtc === "string" ? entry.startUtc : "06:00",
-          endUtc: typeof entry.endUtc === "string" ? entry.endUtc : "10:00",
-        }))
-    : [];
-  return { enabled: record.enabled === true, mode, windows };
-}
-
-function newWindow(): PeakHourWindow {
-  return { id: crypto.randomUUID(), name: "", days: [], startUtc: "06:00", endUtc: "10:00" };
-}
-
-function weekdayWindow(startUtc: string, endUtc: string): PeakHourWindow {
-  return {
-    id: crypto.randomUUID(),
-    name: "Weekday peak",
-    days: ["mon", "tue", "wed", "thu", "fri"],
-    startUtc,
-    endUtc,
-  };
-}
-
-export function normalizePeakHourProtectionForSave(
-  value: PeakHourProtectionConfig
-): PeakHourProtectionConfig | null {
-  const windows = value.windows
-    .map((window) => ({
-      ...(window.name?.trim() ? { name: window.name.trim() } : {}),
-      ...(window.days && window.days.length > 0 ? { days: window.days } : {}),
-      startUtc: window.startUtc,
-      endUtc: window.endUtc,
-    }))
-    .filter(
-      (window) => /^\d{2}:\d{2}$/.test(window.startUtc) && /^\d{2}:\d{2}$/.test(window.endUtc)
-    );
-  if (!value.enabled && windows.length === 0) return null;
-  return { enabled: value.enabled, mode: value.mode, windows };
-}
-
-export function formatPeakHourSummary(value: unknown): string | null {
-  const config = cloneConfig(value);
-  if (!config.enabled || config.windows.length === 0) return null;
-  const mode = config.mode === "avoid" ? "Avoid" : "Block";
-  return `${mode} during ${config.windows.length} peak window${config.windows.length === 1 ? "" : "s"}`;
-}
-
-export default function PeakHourProtectionEditor({
-  value,
-  onChange,
-  t,
-}: {
-  value: PeakHourProtectionConfig;
-  onChange: (next: PeakHourProtectionConfig) => void;
-  t: ProviderMessageTranslator;
-}) {
-  const updateWindow = (id: string | undefined, patch: Partial<PeakHourWindow>) => {
-    onChange({
-      ...value,
-      windows: value.windows.map((window) => (window.id === id ? { ...window, ...patch } : window)),
-    });
-  };
-
-  const toggleDay = (window: PeakHourWindow, day: PeakHourProtectionDay) => {
-    const days = new Set(window.days || []);
-    if (days.has(day)) days.delete(day);
-    else days.add(day);
-    updateWindow(window.id, { days: Array.from(days) });
-  };
-
-  const applyPreset = (provider: "deepseek" | "zai") => {
-    const windows =
-      provider === "deepseek"
-        ? [weekdayWindow("01:00", "04:00"), weekdayWindow("06:00", "10:00")]
-        : [{ ...newWindow(), name: "Daily peak", startUtc: "06:00", endUtc: "10:00" }];
-    onChange({ enabled: true, mode: value.mode, windows });
-  };
-
-  return (
-    <div className="flex flex-col gap-4 rounded-lg border border-amber-500/30 bg-amber-500/5 p-4">
-      <Toggle
-        checked={value.enabled}
-        onChange={(enabled) => onChange({ ...value, enabled })}
-        label={providerText(t, "peakHourProtectionLabel", "Peak-hour protection")}
-        description={providerText(
-          t,
-          "peakHourProtectionDescription",
-          "Block this connection during configured UTC peak-hour windows. This avoids uncertain peak multipliers instead of trying to price them."
-        )}
-      />
-      <Select
-        label={providerText(t, "peakHourProtectionModeLabel", "Protection mode")}
-        value={value.mode}
-        options={[
-          {
-            value: "block",
-            label: providerText(t, "peakHourProtectionModeBlock", "Block requests"),
-          },
-          {
-            value: "avoid",
-            label: providerText(t, "peakHourProtectionModeAvoid", "Avoid in routing"),
-          },
-        ]}
-        onChange={(event) =>
-          onChange({ ...value, mode: event.target.value === "avoid" ? "avoid" : "block" })
-        }
-        hint={providerText(
-          t,
-          "peakHourProtectionModeHint",
-          "Direct requests fail while active; combo/auto routing skips protected connections when alternatives exist."
-        )}
-      />
-      <div className="flex flex-wrap gap-2">
-        <Button size="sm" variant="secondary" onClick={() => applyPreset("deepseek")}>
-          {providerText(t, "peakHourDeepSeekPreset", "Use DeepSeek preset")}
-        </Button>
-        <Button size="sm" variant="secondary" onClick={() => applyPreset("zai")}>
-          {providerText(t, "peakHourZaiPreset", "Use Z.ai preset")}
-        </Button>
-        <Button
-          size="sm"
-          variant="secondary"
-          icon="add"
-          onClick={() => onChange({ ...value, windows: [...value.windows, newWindow()] })}
-        >
-          {providerText(t, "peakHourAddWindow", "Add window")}
-        </Button>
-      </div>
-      <div className="flex flex-col gap-3">
-        {value.windows.length === 0 ? (
-          <p className="text-xs text-text-muted">
-            {providerText(t, "peakHourNoWindows", "No peak-hour windows configured.")}
-          </p>
-        ) : (
-          value.windows.map((window) => (
-            <div key={window.id} className="rounded-lg border border-border/70 bg-surface/50 p-3">
-              <div className="mb-3 flex items-center justify-between gap-2">
-                <Input
-                  label={providerText(t, "peakHourWindowName", "Window name")}
-                  value={window.name || ""}
-                  onChange={(event) => updateWindow(window.id, { name: event.target.value })}
-                  placeholder={providerText(
-                    t,
-                    "peakHourWindowNamePlaceholder",
-                    "e.g. weekday peak"
-                  )}
-                />
-                <Button
-                  size="sm"
-                  variant="ghost"
-                  icon="delete"
-                  onClick={() =>
-                    onChange({
-                      ...value,
-                      windows: value.windows.filter((entry) => entry.id !== window.id),
-                    })
-                  }
-                />
-              </div>
-              <div className="grid grid-cols-1 gap-3 sm:grid-cols-2">
-                <Input
-                  label={providerText(t, "peakHourStartUtc", "Start UTC")}
-                  type="time"
-                  value={window.startUtc}
-                  onChange={(event) => updateWindow(window.id, { startUtc: event.target.value })}
-                />
-                <Input
-                  label={providerText(t, "peakHourEndUtc", "End UTC")}
-                  type="time"
-                  value={window.endUtc}
-                  onChange={(event) => updateWindow(window.id, { endUtc: event.target.value })}
-                />
-              </div>
-              <div className="mt-3">
-                <p className="mb-2 text-xs font-medium text-text-muted">
-                  {providerText(t, "peakHourDays", "Days (empty = every day)")}
-                </p>
-                <div className="flex flex-wrap gap-1.5">
-                  {PEAK_HOUR_PROTECTION_DAYS.map((day) => {
-                    const active = (window.days || []).includes(day);
-                    return (
-                      <button
-                        type="button"
-                        key={day}
-                        onClick={() => toggleDay(window, day)}
-                        className={`rounded-full px-2 py-1 text-xs font-medium transition-colors ${
-                          active
-                            ? "bg-amber-500 text-white"
-                            : "bg-muted/60 text-text-muted hover:bg-muted"
-                        }`}
-                      >
-                        {DAY_LABELS[day]}
-                      </button>
-                    );
-                  })}
-                </div>
-              </div>
-            </div>
-          ))
-        )}
-      </div>
-    </div>
-  );
-}

src/app/(dashboard)/dashboard/providers/[id]/components/modals/EditConnectionModal.tsx

@@ -59,12 +59,6 @@ import AgentrouterConsoleFields from "./AgentrouterConsoleFields";
 import QuotaScrapingFields, { EMPTY_QUOTA_SCRAPING_FIELDS } from "./QuotaScrapingFields";
 import GlmTeamQuotaFields, { EMPTY_GLM_TEAM_QUOTA_FIELDS } from "./GlmTeamQuotaFields";
 import ProviderRegionField, { getProviderRegionConfig } from "./AlibabaProviderRegionField";
-import PeakHourProtectionEditor, {
-  EMPTY_PEAK_HOUR_PROTECTION,
-  formatPeakHourSummary,
-  normalizePeakHourProtectionForSave,
-} from "../PeakHourProtectionEditor";
-import type { PeakHourProtectionConfig } from "@/lib/providers/peakHourProtection";
 export interface EditConnectionModalConnection {
   id?: string;
   name?: string;
@@ -160,7 +154,6 @@ export default function EditConnectionModal({
     runtimeKey: "",
     connectorName: stringField(connectionProviderSpecificData?.connectorName) || "OmniRoute Codex",
     m365Tier: normalizeM365TierValue(connectionProviderSpecificData?.tier) as M365TierValue,
-    peakHourProtection: { ...EMPTY_PEAK_HOUR_PROTECTION, windows: [] } as PeakHourProtectionConfig,
   });
   const [testing, setTesting] = useState(false);
   const [testResult, setTestResult] = useState(null);
@@ -398,22 +391,6 @@ export default function EditConnectionModal({
         connectorName:
           stringField(connection.providerSpecificData?.connectorName) || "OmniRoute Codex",
         m365Tier: normalizeM365TierValue(connection.providerSpecificData?.tier) as M365TierValue,
-        peakHourProtection: {
-          ...EMPTY_PEAK_HOUR_PROTECTION,
-          ...((connection.providerSpecificData?.peakHourProtection as PeakHourProtectionConfig) ||
-            {}),
-          windows: Array.isArray(
-            (
-              connection.providerSpecificData?.peakHourProtection as
-                PeakHourProtectionConfig | undefined
-            )?.windows
-          )
-            ? [
-                ...(connection.providerSpecificData?.peakHourProtection as PeakHourProtectionConfig)
-                  .windows,
-              ]
-            : [],
-        },
       });
       const existing = connection.providerSpecificData?.extraApiKeys;
       setExtraApiKeys(Array.isArray(existing) ? existing : []);
@@ -722,9 +699,6 @@ export default function EditConnectionModal({
       }
       if (updates.providerSpecificData) {
         updates.providerSpecificData.disableCooling = formData.disableCooling ? true : undefined;
-        updates.providerSpecificData.peakHourProtection = normalizePeakHourProtectionForSave(
-          formData.peakHourProtection
-        );
         // Explicit `null`, not `undefined`: the PUT route merges
         // { ...existing, ...incoming }, so omitting the key would keep the previous
         // choice and switching back to the default would never take effect.
@@ -870,16 +844,6 @@ export default function EditConnectionModal({
             label={t("disableCoolingLabel")}
             description={t("disableCoolingDescription")}
           />
-          <PeakHourProtectionEditor
-            value={formData.peakHourProtection}
-            onChange={(peakHourProtection) => setFormData({ ...formData, peakHourProtection })}
-            t={t}
-          />
-          {formatPeakHourSummary(formData.peakHourProtection) && (
-            <p className="text-xs text-text-muted">
-              {formatPeakHourSummary(formData.peakHourProtection)}
-            </p>
-          )}
         </div>
         <QuotaScrapingFields
           provider={provider}

src/app/api/providers/[id]/test/route.ts

@@ -29,7 +29,7 @@ import {
 import { providerAllowsOptionalApiKey } from "@/shared/constants/providers";
 import { shouldUseApiKeyConnectionTest } from "./webSessionTestDispatch";
 import { testCodexAppServerConnection, makeDiagnosis } from "./codexAppServerHealth";
-import { recoverKeyHealth } from "@omniroute/open-sse/services/apiKeyRotator.ts";
+import { removeConnectionHealth } from "@omniroute/open-sse/services/apiKeyRotator.ts";
 import { shouldClearErrorStateOnValidProbe } from "@/lib/usage/providerLimits";
 import { isConnectionUnavailableToAuxiliaryActivity } from "@/lib/exclusiveLeaseIsolation";
 import { classifyAmbiguousOrAuthError, type ClassifyFailureArgs } from "./mistralAmbiguousAuth";
@@ -1125,11 +1125,7 @@ export async function testSingleConnection(connectionId: string, validationModel
     lastError: clearErrorState ? null : result.valid ? connection.lastError : result.error,
     lastErrorAt: clearErrorState ? null : result.valid ? connection.lastErrorAt : now,
     lastTested: now,
-    lastErrorType: clearErrorState
-      ? null
-      : result.valid
-        ? connection.lastErrorType
-        : diagnosis.type,
+    lastErrorType: clearErrorState ? null : result.valid ? connection.lastErrorType : diagnosis.type,
     lastErrorSource: clearErrorState
       ? null
       : result.valid
@@ -1151,11 +1147,16 @@ export async function testSingleConnection(connectionId: string, validationModel
 
   if (clearErrorState) {
     updateData.backoffLevel = 0;
-  }
 
-  if (result.valid && (connection.apiKey || connection.accessToken)) {
-    const recovered = recoverKeyHealth(connectionId, "primary", connection.providerSpecificData);
-    if (recovered) updateData.providerSpecificData = recovered;
+    const psd = connection?.providerSpecificData as Record<string, unknown> | undefined;
+    updateData.providerSpecificData = {
+      ...(psd || {}),
+      apiKeyHealth: {},
+    };
+
+    try {
+      removeConnectionHealth(connectionId);
+    } catch {}
   }
 
   // If token was refreshed, update tokens in DB

src/app/api/search/providers/route.ts

@@ -54,13 +54,6 @@ const FETCH_PROVIDERS: FetchProviderDef[] = [
     freeMonthlyQuota: 0,
     fetchFormats: ["markdown", "html"],
   },
-  {
-    id: "nimble-search",
-    name: "Nimble Extract",
-    costPerQuery: 0.005,
-    freeMonthlyQuota: 0,
-    fetchFormats: ["markdown", "html", "links", "screenshot"],
-  },
 ];
 
 // ---------------------------------------------------------------------------

src/i18n/messages/ar.json

@@ -11314,9 +11314,7 @@
       "noPayload": "لا توجد بيانات حمولة متاحة لهذه السجل.",
       "correlationId": "معرف الترابط",
       "correlationIdValue": "معرّف الارتباط: {id}",
-      "detailedPayloadInfo": "قم بتمكين تسجيل الدخول التفصيلي أولاً إذا كنت ترغب في عرض الحمولة من أربعة مراحل للعميل/المزود للطلبات الجديدة.",
-      "copyAll": "Copy all",
-      "copiedAll": "Copied all"
+      "detailedPayloadInfo": "قم بتمكين تسجيل الدخول التفصيلي أولاً إذا كنت ترغب في عرض الحمولة من أربعة مراحل للعميل/المزود للطلبات الجديدة."
     }
   },
   "proxyLogger": {

src/i18n/messages/az.json

@@ -11314,9 +11314,7 @@
       "noPayload": "Bu log girişi üçün heç bir yük məlumatı mövcud deyil.",
       "correlationId": "Korrelyasiya ID-si",
       "correlationIdValue": "Korrelyasiya ID: {id}",
-      "detailedPayloadInfo": "Əvvəlcə ətraflı qeydiyyatı aktiv edin, əgər yeni tələblər üçün dörd mərhələli müştəri/təchizatçı yük görünüşünü istəyirsinizsə.",
-      "copyAll": "Copy all",
-      "copiedAll": "Copied all"
+      "detailedPayloadInfo": "Əvvəlcə ətraflı qeydiyyatı aktiv edin, əgər yeni tələblər üçün dörd mərhələli müştəri/təchizatçı yük görünüşünü istəyirsinizsə."
     }
   },
   "proxyLogger": {

src/i18n/messages/bg.json

@@ -11314,9 +11314,7 @@
       "noPayload": "Няма налични данни за полезен товар за този запис в логовете.",
       "correlationId": "Идентификатор на корелацията",
       "correlationIdValue": "Идентификатор на корелация: {id}",
-      "detailedPayloadInfo": "Първо активирайте подробното регистриране, ако искате изгледа на четирите етапа на клиент/доставчик за нови заявки.",
-      "copyAll": "Copy all",
-      "copiedAll": "Copied all"
+      "detailedPayloadInfo": "Първо активирайте подробното регистриране, ако искате изгледа на четирите етапа на клиент/доставчик за нови заявки."
     }
   },
   "proxyLogger": {

src/i18n/messages/bn.json

@@ -11314,9 +11314,7 @@
       "noPayload": "এই লগ এন্ট্রির জন্য কোনো পেলোড ডেটা উপলব্ধ নেই।",
       "correlationId": "সংযোগ আইডি",
       "correlationIdValue": "সংযোগ আইডি: {id}",
-      "detailedPayloadInfo": "নতুন অনুরোধের জন্য চার-পর্যায়ের ক্লায়েন্ট/প্রদানকারী পে-লোড ভিউ পেতে হলে প্রথমে বিস্তারিত লগিং সক্ষম করুন।",
-      "copyAll": "Copy all",
-      "copiedAll": "Copied all"
+      "detailedPayloadInfo": "নতুন অনুরোধের জন্য চার-পর্যায়ের ক্লায়েন্ট/প্রদানকারী পে-লোড ভিউ পেতে হলে প্রথমে বিস্তারিত লগিং সক্ষম করুন।"
     }
   },
   "proxyLogger": {

src/i18n/messages/cs.json

@@ -11314,9 +11314,7 @@
       "noPayload": "Žádná data o payloadu nejsou k dispozici pro tento záznam.",
       "correlationId": "ID korelace",
       "correlationIdValue": "ID korelace: {id}",
-      "detailedPayloadInfo": "Nejprve povolte podrobné protokolování, pokud chcete čtyřstupňový pohled na payload klienta/poskytovatele pro nové požadavky.",
-      "copyAll": "Copy all",
-      "copiedAll": "Copied all"
+      "detailedPayloadInfo": "Nejprve povolte podrobné protokolování, pokud chcete čtyřstupňový pohled na payload klienta/poskytovatele pro nové požadavky."
     }
   },
   "proxyLogger": {