sync with release tip for /green-prs validation

check:file-size fails on the pristine release/v3.8.49 tip (30709255),
which takes the whole Fast Quality Gates job down for every PR against
the branch. Both offenders grew after the last rebaseline
(_rebaseline_2026_07_25_v3849_basered_filesize, measured at 36f8fd10)
and both came from already-merged PRs, so there is no offending branch
left to fix:

  src/lib/tokenHealthCheck.ts                     841 -> 843  (#8426, 4528fc455)
  src/app/(dashboard)/dashboard/providers/page.tsx 1927 -> 1990 (#8349, 58ab8b1d2)

Trust-but-verify: both values measured on the pristine tip with an empty
working tree. Same situation and remedy as the entry cited above and as
_rebaseline_2026_07_02_5798_release_green.

This commit is deliberately last and self-contained: drop it if the
captain would rather move the frozen values separately. Structural
reduction of the 1990-line providers page is not attempted here.

Co-authored-by: alexey.nazarov@softmg.ru <alexey.nazarov@softmg.ru>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>

changelog.d/fixes/7587-vscode-models-missing-openai.md

@@ -0,0 +1 @@
+- fix(api): expose Responses-API-format (OpenAI/Codex) chat models on every VS Code Ollama-compatible listing route, not just `/models` (#7587)

changelog.d/maintenance/lint-suppression-resync-proxy-registry.md

@@ -0,0 +1 @@
+- chore(ci): resync the stale `no-explicit-any` suppression count for `tests/unit/proxy-registry.test.ts` (frozen at 55, actual 54 since #8447) — ESLint was failing the whole run with "There are suppressions left that do not occur anymore", turning `npm run lint` red on `release/v3.8.49` for every PR branched off it

config/quality/eslint-suppressions.json

@@ -1937,7 +1937,7 @@
   },
   "tests/unit/proxy-registry.test.ts": {
     "@typescript-eslint/no-explicit-any": {
-      "count": 55
+      "count": 54
     }
   },
   "tests/unit/proxy-resolution-status-filter.test.ts": {

config/quality/file-size-baseline.json

@@ -253,7 +253,7 @@
     "src/app/(dashboard)/dashboard/providers/[id]/hooks/useProviderSettings.ts": 264,
     "src/app/(dashboard)/dashboard/providers/[id]/providerPageHelpers.ts": 1054,
     "src/app/(dashboard)/dashboard/providers/components/onboarding/ProviderOnboardingWizard.tsx": 948,
-    "src/app/(dashboard)/dashboard/providers/page.tsx": 1927,
+    "src/app/(dashboard)/dashboard/providers/page.tsx": 1990,
     "src/app/(dashboard)/dashboard/runtime/RuntimePageClient.tsx": 1201,
     "src/app/(dashboard)/dashboard/settings/components/AppearanceTab.tsx": 819,
     "src/app/(dashboard)/dashboard/settings/components/ComboDefaultsTab.tsx": 903,
@@ -324,7 +324,7 @@
     "open-sse/executors/huggingchat.ts": 813,
     "_rebaseline_2026_07_01_v3843_release_5609": "Rebaseline v3.8.43 (PR #5609 release reconciliation). DRIFT dos 109 commits do ciclo: 8 god-files existentes cresceram (ApiManagerPageClient 2983->3017, combos/page 4594->4608, AddApiKeyModal 868->869, providerPageHelpers 974->996, chat.ts 1635->1647, auth.ts 2401->2403, batchProcessor 828->915, combo.ts 3368->3387) + 2 novos acima do cap (huggingchat.ts 813, tests web-cookie-providers-new 827) + 4 test files cresceram. Modularizacao deferida (blast-radius mid-release); congelado no estado atual p/ o proximo ciclo ratchetar daqui.",
     "src/lib/providers/validation/webProvidersA.ts": 809,
-    "src/lib/tokenHealthCheck.ts": 841,
+    "src/lib/tokenHealthCheck.ts": 843,
     "_rebaseline_2026_07_09_6587_kiro_api_key_auth": "PR #6587 (@strangersp) own growth for Kiro long-lived API-key auth, merged onto v3.8.47 tip: openai-to-kiro.ts 890->912 (+22, auth-header selection for API-key-vs-OAuth-token connections), providerLimits.ts 998->1000 (+2, API-key auth-type branch), translator-openai-to-kiro.test.ts 1234->1257 (+23), providers-page-utils.test.ts 1109->1107 (net -2 after merging with parallel release drift; connectionMatchesProviderCard api_key coverage added), provider-validation-specialty.test.ts 2856->2980 (+124 net after merge with parallel release drift; this PR also removed the file's `@typescript-eslint/no-explicit-any` eslint-suppression entry by fixing all `any` usages, adding typed replacements). Cohesive additive feature growth, well tested; not extractable without splitting the existing chokepoints mid-merge.",
     "_rebaseline_2026_07_19_7787_ic2_localdb_reexports": "PR #7787 (IC2 raw connections cache + lazy-decrypt) own growth: localDb.ts 805->807 (gate units, +2). localDb.ts is the re-export-only layer (hard rule #2 — no logic); the PR adds 4 new db/readCache re-exports (touchConnectionLastUsed, getCachedRawProviderConnections, getCachedProviderConnectionById, getCachedProviderNodes) required by existing barrel importers. Irreducible for a re-export list; frozen so it can only shrink.",
     "_rebaseline_2026_07_20_7819_autocandidateoverrides_reexport": "PR for #7819 (Level 1+2: read-only auto/* candidate transparency + per-API-key exclusions) own growth: localDb.ts 807->808 (+1). Adds a single `export * from \"./db/autoCandidateOverrides\"` barrel re-export (hard rule #2 — no logic) for the new DB module backing per-apiKey candidate exclusions. Irreducible for a re-export list; frozen so it can only shrink.",
@@ -470,5 +470,6 @@
   "_rebaseline_2026_07_23_v3849_merge_train_15": "Own-growth do merge-train de 15 PRs (2026-07-23), medido na tip combinada, release pura abaixo do baseline (auth.ts 2448, muse-spark 1393, translator-test 1523). auth.ts 2462->2475 (#8321 cookie-auth 401 cooldown-em-vez-de-terminal + #8324 noauth opencode-zen via proxy — wiring de classificação no chokepoint getProviderCredentials/markAccountUnavailable, não extraível), muse-spark-web.ts 1394->1396 (#8298 sanitizeErrorMessage runtime repairs isolados do #8177), tests/unit/translator-openai-to-gemini.test.ts 1553->1616 (#8312 cobertura do cap de thinking budget no path budget_tokens explícito). Owner-approved. Frozen; shrink estrutural em #3501.",
   "_rebaseline_2026_07_22_providerLimits_webcookie_chain": "providerLimits.ts 1003->1005: own-growth from web-cookie provider usage-fetcher entries (#7994/#8006/#8027 chain) landing after the prior rebaseline.",
   "_rebaseline_2026_07_22_8056_headroom_minrows": "#8056 (@RaviTharuma, persist Headroom minRows) own growth: src/lib/db/compression.ts 850->866 (+16 HeadroomConfig+DEFAULT_HEADROOM_CONFIG+normalize/store in get/updateCompressionSettings) and open-sse/services/compression/strategySelector.ts 1054->1060 (+6 merge settings.headroom into stacked stepConfig). Cohesive settings-persistence + stacked-merge wiring at existing chokepoints, frozen at new size.",
-  "_rebaseline_2026_07_25_v3849_basered_filesize": "Base-red unblock (2026-07-25): check:file-size was failing on release/v3.8.49 at its own HEAD (36f8fd10), so the quality.yml fast-gates job was red for EVERY PR->release regardless of content — growth inherited from already-merged PRs, with no offending PR branch left to fix (same situation as _rebaseline_2026_07_02_5798_release_green). Prod frozen raised to the current base values: src/lib/tokenHealthCheck.ts 832->841, src/sse/handlers/chat.ts 1865->1866, src/sse/services/auth.ts 2475->2486, open-sse/services/accountFallback.ts 1941->1966, open-sse/services/combo.ts 3630->3642. accountFallback.ts was first frozen here at 1960 (the base value at 36f8fd10) and re-measured to 1966 at base tip 1cafd328c a few hours later — the same inherited drift this entry exists for, since check:file-size does not run on the PR->release fast path and so accrues unmeasured between release rebaselines. These files remain frozen and cannot grow further; any in-flight PR that adds lines to them (e.g. #8482 touches accountFallback.ts and combo.ts) bumps its own entry as usual. The release captain rebaseline-at-release supersedes this note."
+  "_rebaseline_2026_07_25_v3849_basered_filesize": "Base-red unblock (2026-07-25): check:file-size was failing on release/v3.8.49 at its own HEAD (36f8fd10), so the quality.yml fast-gates job was red for EVERY PR->release regardless of content — growth inherited from already-merged PRs, with no offending PR branch left to fix (same situation as _rebaseline_2026_07_02_5798_release_green). Prod frozen raised to the current base values: src/lib/tokenHealthCheck.ts 832->841, src/sse/handlers/chat.ts 1865->1866, src/sse/services/auth.ts 2475->2486, open-sse/services/accountFallback.ts 1941->1966, open-sse/services/combo.ts 3630->3642. accountFallback.ts was first frozen here at 1960 (the base value at 36f8fd10) and re-measured to 1966 at base tip 1cafd328c a few hours later — the same inherited drift this entry exists for, since check:file-size does not run on the PR->release fast path and so accrues unmeasured between release rebaselines. These files remain frozen and cannot grow further; any in-flight PR that adds lines to them (e.g. #8482 touches accountFallback.ts and combo.ts) bumps its own entry as usual. The release captain rebaseline-at-release supersedes this note.",
+  "_rebaseline_2026_07_25_v3849_basered_filesize_2": "Base-red unblock (2026-07-25, second pass): after _rebaseline_2026_07_25_v3849_basered_filesize (measured at 36f8fd10) two more already-merged PRs grew frozen files on release/v3.8.49, so check:file-size — and with it the whole Fast Quality Gates job — is red for EVERY PR->release again, with no offending PR branch left to fix. src/lib/tokenHealthCheck.ts 841->843 (#8426 4528fc455, excludes local CLI providers from expiration) and src/app/(dashboard)/dashboard/providers/page.tsx 1927->1990 (#8349 58ab8b1d2, scroll-position restore on provider-card back-navigation). Trust-but-verify: both values measured on the pristine release tip 30709255 with no working-tree changes. Same situation and remedy as _rebaseline_2026_07_02_5798_release_green. Structural reduction of providers/page.tsx stays tracked separately — it is a 1990-line page, not something to extract inside a base-repair PR."
 }

package-lock.json

@@ -44,7 +44,7 @@
         "ink-text-input": "^6.0.0",
         "ioredis": "^5.10.1",
         "jose": "^6.2.3",
-        "js-yaml": "^5.0.0",
+        "js-yaml": "^5.2.2",
         "jsonc-parser": "^3.3.1",
         "lowdb": "^7.0.1",
         "lucide-react": "^1.21.0",
@@ -103,7 +103,7 @@
         "@testing-library/jest-dom": "^6.9.1",
         "@testing-library/react": "^16.3.2",
         "@types/better-sqlite3": "^7.6.13",
-        "@types/bun": "*",
+        "@types/bun": "latest",
         "@types/node": "^26.1.0",
         "@types/react": "^19.2.15",
         "@types/react-dom": "^19.2.3",
@@ -23683,9 +23683,9 @@
       "license": "MIT"
     },
     "node_modules/js-yaml": {
-      "version": "5.2.1",
-      "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-5.2.1.tgz",
-      "integrity": "sha512-zfLtNfQqxVqq3uaTqSkh4x4hZw3KHobGUA0fJUj4wawW8bsQLTVqpHdXSIzidh7o+4lEW36tANuAGdaFx6Zgnw==",
+      "version": "5.2.2",
+      "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-5.2.2.tgz",
+      "integrity": "sha512-dayzUzKkJ1MkuUtZglSebU43utNXH0OWQByK9rKOOuYIO8M5TV1y+n8ALMdG0rdzBnfNkOmZEqrURepb0ejqBw==",
       "funding": [
         {
           "type": "github",
@@ -27778,9 +27778,9 @@
       "optional": true
     },
     "node_modules/nanoid": {
-      "version": "3.3.11",
-      "resolved": "https://registry.npmjs.org/nanoid/-/nanoid-3.3.11.tgz",
-      "integrity": "sha512-N8SpfPUnUp1bK+PMYW8qSWdl9U+wwNWI4QKxOYDy9JAro3WMX7p2OeVRF9v+347pnakNevPmiHhNmZ2HbFA76w==",
+      "version": "3.3.16",
+      "resolved": "https://registry.npmjs.org/nanoid/-/nanoid-3.3.16.tgz",
+      "integrity": "sha512-bzlKTyNJ7+LdGIIwy8ijFpIqEQIvafahV7eYykJ8Cvh42EdJeODoJ6gUJXpQJvej1BddH8OqTXZNE/KfbWAu8Q==",
       "funding": [
         {
           "type": "github",
@@ -30080,9 +30080,9 @@
       }
     },
     "node_modules/postcss": {
-      "version": "8.5.14",
-      "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.5.14.tgz",
-      "integrity": "sha512-SoSL4+OSEtR99LHFZQiJLkT59C5B1amGO1NzTwj7TT1qCUgUO6hxOvzkOYxD+vMrXBM3XJIKzokoERdqQq/Zmg==",
+      "version": "8.5.23",
+      "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.5.23.tgz",
+      "integrity": "sha512-g50586zr4bZmwFiTlflMu8E0bDTb5I5gertgwAKmsdUlTQIhZtunzUlD1WSzwcVWPoAVpsrA6vlfCD7oXvRwgg==",
       "funding": [
         {
           "type": "opencollective",
@@ -30099,7 +30099,7 @@
       ],
       "license": "MIT",
       "dependencies": {
-        "nanoid": "^3.3.11",
+        "nanoid": "^3.3.16",
         "picocolors": "^1.1.1",
         "source-map-js": "^1.2.1"
       },

package.json

@@ -265,7 +265,7 @@
     "ink-text-input": "^6.0.0",
     "ioredis": "^5.10.1",
     "jose": "^6.2.3",
-    "js-yaml": "^5.0.0",
+    "js-yaml": "^5.2.2",
     "jsonc-parser": "^3.3.1",
     "lowdb": "^7.0.1",
     "lucide-react": "^1.21.0",
@@ -394,7 +394,7 @@
     "dompurify": "^3.4.12",
     "fast-xml-parser": "^5.10.1",
     "sharp": "^0.35.0",
-    "postcss": "^8.5.14",
+    "postcss": "^8.5.18",
     "ip-address": "10.2.0",
     "qs": "^6.15.2",
     "uuid": "^14.0.0",
@@ -418,6 +418,12 @@
     "concurrently": {
       "shell-quote": "^1.9.0"
     },
-    "adm-zip": "^0.6.0"
+    "adm-zip": "^0.6.0",
+    "promptfoo": {
+      "js-yaml": "^5.2.2",
+      "@apidevtools/json-schema-ref-parser": {
+        "js-yaml": "^4.2.0"
+      }
+    }
   }
 }

scripts/check/check-db-rules.mjs

@@ -48,6 +48,7 @@ export const INTENTIONALLY_INTERNAL = new Set([
   "comboForecast", // intentionally-internal: src/lib/usage/comboForecast.ts
   "commandCodeAuth", // intentionally-internal: 5 API routes em /api/providers/command-code/auth/*
   "compression", // intentionally-internal: 2 API routes (settings/compression, context/rtk/config)
+  "compressionDetailNormalizers", // db-internal: importado só por db/compression.ts (normalizeSessionDedupConfig/normalizeCcrConfig/buildDetailConfigDefaults/applyDetailConfigUpdate — normalizadores do detail-config split do compression.ts, #8404)
   "vacuumScheduler", // intentionally-internal: src/instrumentation-node.ts (dynamic import, lifecycle wiring per Rule #2)
   "detailedLogs", // intentionally-internal: 3 callers (callLogs.ts, logs/detail route, embeddings handler)
   "discovery", // DEAD?: 0 importers na auditoria de 2026-06-11; lib/discovery/index.ts não usa db/discovery

src/app/api/v1/vscode/[token]/api/show/route.ts

@@ -16,6 +16,7 @@ import {
 } from "@/app/api/v1/vscode/[token]/serviceTierVariants";
 import { getFamilyFirstModelCandidates, getFamilyFirstPublishedModelId } from "@/app/api/v1/vscode/[token]/familyFirstModelIds";
 import { withPathTokenApiKey } from "@/app/api/v1/vscode/[token]/tokenizedRequest";
+import { isUsableChatModel } from "@/app/api/v1/vscode/[token]/usableChatModel";
 
 type OpenAiCatalogModel = {
   id?: string;
@@ -33,35 +34,6 @@ type OpenAiCatalogModel = {
   supported_endpoints?: string[];
 };
 
-function isUsableChatModel(model: OpenAiCatalogModel) {
-  if (typeof model.owned_by === "string" && model.owned_by.trim().toLowerCase() === "combo") {
-    return false;
-  }
-  if (typeof model.parent === "string" && model.parent.length > 0) return false;
-  if (typeof model.type === "string" && model.type !== "chat") return false;
-
-  const apiFormat = typeof model.api_format === "string" ? model.api_format : "chat-completions";
-  if (apiFormat !== "chat-completions") return false;
-
-  if (
-    Array.isArray(model.supported_endpoints) &&
-    model.supported_endpoints.length > 0 &&
-    !model.supported_endpoints.includes("chat")
-  ) {
-    return false;
-  }
-
-  if (
-    Array.isArray(model.output_modalities) &&
-    model.output_modalities.length > 0 &&
-    !model.output_modalities.includes("text")
-  ) {
-    return false;
-  }
-
-  return true;
-}
-
 function getCatalogModelId(model: OpenAiCatalogModel) {
   return model.id || model.name || model.root || "unknown";
 }

src/app/api/v1/vscode/[token]/api/tags/route.ts

@@ -19,6 +19,7 @@ import {
 } from "@/app/api/v1/vscode/[token]/serviceTierVariants";
 import { getFamilyFirstPublishedModelId } from "@/app/api/v1/vscode/[token]/familyFirstModelIds";
 import { withPathTokenApiKey } from "@/app/api/v1/vscode/[token]/tokenizedRequest";
+import { isUsableChatModel } from "@/app/api/v1/vscode/[token]/usableChatModel";
 
 type OpenAiCatalogModel = {
 	id?: string;
@@ -64,35 +65,6 @@ async function selectPreferredModels(models: OpenAiCatalogModel[]) {
 	return codexModels.length > 0 ? codexModels : models;
 }
 
-function isUsableChatModel(model: OpenAiCatalogModel) {
-	if (typeof model.owned_by === "string" && model.owned_by.trim().toLowerCase() === "combo") {
-		return false;
-	}
-	if (typeof model.parent === "string" && model.parent.length > 0) return false;
-	if (typeof model.type === "string" && model.type !== "chat") return false;
-
-	const apiFormat = typeof model.api_format === "string" ? model.api_format : "chat-completions";
-	if (apiFormat !== "chat-completions") return false;
-
-	if (
-		Array.isArray(model.supported_endpoints) &&
-		model.supported_endpoints.length > 0 &&
-		!model.supported_endpoints.includes("chat")
-	) {
-		return false;
-	}
-
-	if (
-		Array.isArray(model.output_modalities) &&
-		model.output_modalities.length > 0 &&
-		!model.output_modalities.includes("text")
-	) {
-		return false;
-	}
-
-	return true;
-}
-
 function getOllamaModelFamily(model: OpenAiCatalogModel, canonicalFamily?: string | null) {
 	const rawModelId = getModelName(model).trim();
 	const tierParsedModel = parseVscodeServiceTierVariantModelId(rawModelId);

src/app/api/v1/vscode/[token]/models/route.ts

@@ -25,6 +25,7 @@ import {
 	parseVscodeServiceTierVariantModelId,
 } from "@/app/api/v1/vscode/[token]/serviceTierVariants";
 import { getFamilyFirstPublishedModelId } from "@/app/api/v1/vscode/[token]/familyFirstModelIds";
+import { isUsableChatModel } from "@/app/api/v1/vscode/[token]/usableChatModel";
 
 type CatalogModelEntry = {
 	id?: string;
@@ -72,12 +73,6 @@ type EnrichModelForVscodeOptions = {
 	preserveNativeId?: boolean;
 };
 
-const TEXT_GENERATION_API_FORMATS = new Set([
-	"chat-completions",
-	"responses",
-	"openai-responses",
-]);
-
 function usesResponsesApi(model: CatalogModelEntry) {
 	return (
 		model.api_format === "responses" ||
@@ -86,41 +81,6 @@ function usesResponsesApi(model: CatalogModelEntry) {
 	);
 }
 
-function excludesChatAndResponsesEndpoints(model: CatalogModelEntry) {
-	return (
-		Array.isArray(model.supported_endpoints) &&
-		model.supported_endpoints.length > 0 &&
-		!model.supported_endpoints.includes("chat") &&
-		!model.supported_endpoints.includes("responses")
-	);
-}
-
-function excludesTextOutputModality(model: CatalogModelEntry) {
-	return (
-		Array.isArray(model.output_modalities) &&
-		model.output_modalities.length > 0 &&
-		!model.output_modalities.includes("text")
-	);
-}
-
-function isUsableChatModel(model: CatalogModelEntry) {
-	if (typeof model.owned_by === "string" && model.owned_by.trim().toLowerCase() === "combo") {
-		return false;
-	}
-	if (typeof model.parent === "string" && model.parent.length > 0) return false;
-	if (typeof model.type === "string" && model.type !== "chat") return false;
-	if (
-		typeof model.api_format === "string" &&
-		!TEXT_GENERATION_API_FORMATS.has(model.api_format)
-	) {
-		return false;
-	}
-	if (excludesChatAndResponsesEndpoints(model)) return false;
-	if (excludesTextOutputModality(model)) return false;
-
-	return true;
-}
-
 function getModelImportReasoningEffortValues(model: VscodeCatalogModel, reasoningEffortValues: string[]) {
 	const providerId =
 		(model.owned_by || "").trim() ||

src/app/api/v1/vscode/[token]/usableChatModel.ts

@@ -0,0 +1,63 @@
+// Shared "is this catalog model usable as a VS Code chat model" filter.
+//
+// Historically this predicate was copy-pasted independently into every VS
+// Code listing route (models, api/tags, api/show — both the token-prefixed
+// and `raw` token variants). PR #7012 widened only the `models/route.ts`
+// copy to accept Responses-API-format models (api_format "responses" /
+// "openai-responses", or supported_endpoints containing "responses")
+// alongside plain "chat-completions" models — the other 4 copies were left
+// on the old, stricter filter, silently hiding OpenAI/Codex "responses"
+// models from every Ollama-compatible listing endpoint (#7587).
+//
+// Centralizing the predicate here means a future widening only has to
+// happen once.
+
+export type UsableChatModelCandidate = {
+	owned_by?: string;
+	parent?: string | null;
+	type?: string;
+	api_format?: string;
+	supported_endpoints?: string[];
+	output_modalities?: string[];
+};
+
+export const TEXT_GENERATION_API_FORMATS = new Set([
+	"chat-completions",
+	"responses",
+	"openai-responses",
+]);
+
+function excludesChatAndResponsesEndpoints(model: UsableChatModelCandidate) {
+	return (
+		Array.isArray(model.supported_endpoints) &&
+		model.supported_endpoints.length > 0 &&
+		!model.supported_endpoints.includes("chat") &&
+		!model.supported_endpoints.includes("responses")
+	);
+}
+
+function excludesTextOutputModality(model: UsableChatModelCandidate) {
+	return (
+		Array.isArray(model.output_modalities) &&
+		model.output_modalities.length > 0 &&
+		!model.output_modalities.includes("text")
+	);
+}
+
+export function isUsableChatModel(model: UsableChatModelCandidate) {
+	if (typeof model.owned_by === "string" && model.owned_by.trim().toLowerCase() === "combo") {
+		return false;
+	}
+	if (typeof model.parent === "string" && model.parent.length > 0) return false;
+	if (typeof model.type === "string" && model.type !== "chat") return false;
+	if (
+		typeof model.api_format === "string" &&
+		!TEXT_GENERATION_API_FORMATS.has(model.api_format)
+	) {
+		return false;
+	}
+	if (excludesChatAndResponsesEndpoints(model)) return false;
+	if (excludesTextOutputModality(model)) return false;
+
+	return true;
+}

src/app/api/v1/vscode/raw/[token]/api/show/route.ts

@@ -14,6 +14,7 @@ import {
 import { parseVscodeServiceTierVariantModelId } from "@/app/api/v1/vscode/raw/[token]/serviceTierVariants";
 import { getFamilyFirstModelCandidates } from "@/app/api/v1/vscode/raw/[token]/familyFirstModelIds";
 import { withPathTokenApiKey } from "@/app/api/v1/vscode/raw/[token]/tokenizedRequest";
+import { isUsableChatModel } from "@/app/api/v1/vscode/[token]/usableChatModel";
 
 type OpenAiCatalogModel = {
   id?: string;
@@ -31,35 +32,6 @@ type OpenAiCatalogModel = {
   supported_endpoints?: string[];
 };
 
-function isUsableChatModel(model: OpenAiCatalogModel) {
-  if (typeof model.owned_by === "string" && model.owned_by.trim().toLowerCase() === "combo") {
-    return false;
-  }
-  if (typeof model.parent === "string" && model.parent.length > 0) return false;
-  if (typeof model.type === "string" && model.type !== "chat") return false;
-
-  const apiFormat = typeof model.api_format === "string" ? model.api_format : "chat-completions";
-  if (apiFormat !== "chat-completions") return false;
-
-  if (
-    Array.isArray(model.supported_endpoints) &&
-    model.supported_endpoints.length > 0 &&
-    !model.supported_endpoints.includes("chat")
-  ) {
-    return false;
-  }
-
-  if (
-    Array.isArray(model.output_modalities) &&
-    model.output_modalities.length > 0 &&
-    !model.output_modalities.includes("text")
-  ) {
-    return false;
-  }
-
-  return true;
-}
-
 function getCatalogModelId(model: OpenAiCatalogModel) {
   return model.id || model.name || model.root || "unknown";
 }

src/app/api/v1/vscode/raw/[token]/api/tags/route.ts

@@ -14,6 +14,7 @@ import {
 } from "@/app/api/v1/vscode/raw/[token]/reasoningMetadata";
 import { parseVscodeServiceTierVariantModelId } from "@/app/api/v1/vscode/raw/[token]/serviceTierVariants";
 import { withPathTokenApiKey } from "@/app/api/v1/vscode/raw/[token]/tokenizedRequest";
+import { isUsableChatModel } from "@/app/api/v1/vscode/[token]/usableChatModel";
 
 type OpenAiCatalogModel = {
 	id?: string;
@@ -59,35 +60,6 @@ async function selectPreferredModels(models: OpenAiCatalogModel[]) {
 	return codexModels.length > 0 ? codexModels : models;
 }
 
-function isUsableChatModel(model: OpenAiCatalogModel) {
-	if (typeof model.owned_by === "string" && model.owned_by.trim().toLowerCase() === "combo") {
-		return false;
-	}
-	if (typeof model.parent === "string" && model.parent.length > 0) return false;
-	if (typeof model.type === "string" && model.type !== "chat") return false;
-
-	const apiFormat = typeof model.api_format === "string" ? model.api_format : "chat-completions";
-	if (apiFormat !== "chat-completions") return false;
-
-	if (
-		Array.isArray(model.supported_endpoints) &&
-		model.supported_endpoints.length > 0 &&
-		!model.supported_endpoints.includes("chat")
-	) {
-		return false;
-	}
-
-	if (
-		Array.isArray(model.output_modalities) &&
-		model.output_modalities.length > 0 &&
-		!model.output_modalities.includes("text")
-	) {
-		return false;
-	}
-
-	return true;
-}
-
 function getOllamaModelFamily(model: OpenAiCatalogModel, canonicalFamily?: string | null) {
 	const rawModelId = getModelName(model).trim();
 	const tierParsedModel = parseVscodeServiceTierVariantModelId(rawModelId);

stryker.conf.json

@@ -49,6 +49,8 @@
       "tests/unit/8247-accountfallback-model-unhealthy.test.ts",
       "tests/unit/8248-accountfallback-nvidia-degraded.test.ts",
       "tests/unit/8332-combo-vision-fallback.test.ts",
+      "tests/unit/8376-econnrefused-breaker.test.ts",
+      "tests/unit/8396-cooldown-429-cap.test.ts",
       "tests/unit/account-fallback-anthropic-quota.test.ts",
       "tests/unit/account-fallback-lockout-eviction.test.ts",
       "tests/unit/account-fallback-retry-after-json.test.ts",
@@ -251,6 +253,7 @@
       "tests/unit/rate-limit-enhanced.test.ts",
       "tests/unit/rate-limit-manager.test.ts",
       "tests/unit/rate-limit-queue-timeout-lockout.test.ts",
+      "tests/unit/repro-7503-no-choices.test.ts",
       "tests/unit/repro-antigravity-404-family-cooldown-hijack.test.ts",
       "tests/unit/responses-handler.test.ts",
       "tests/unit/rotation-config-omniroute.test.ts",

tests/unit/check-db-rules-classification.test.ts

@@ -121,7 +121,7 @@ test("INTENTIONALLY_INTERNAL is exported from check-db-rules.mjs", () => {
   assert.ok(INTENTIONALLY_INTERNAL.size > 0, "INTENTIONALLY_INTERNAL must not be empty");
 });
 
-test("INTENTIONALLY_INTERNAL contains the expected 36 audited modules", () => {
+test("INTENTIONALLY_INTERNAL contains the expected 37 audited modules", () => {
   const expected = [
     "_rowTypes",
     "accessTokens",
@@ -133,6 +133,7 @@ test("INTENTIONALLY_INTERNAL contains the expected 36 audited modules", () => {
     "comboForecast",
     "commandCodeAuth",
     "compression",
+    "compressionDetailNormalizers",
     "detailedLogs",
     "discovery",
     "domainState",

tests/unit/error-classification.test.ts

@@ -98,13 +98,21 @@ test("502 transient: exponential backoff doubles until the configured max backof
     assert.equal(result.newBackoffLevel, level + 1);
     assert.equal(result.reason, RateLimitReason.SERVER_ERROR);
   }
+  // #8396: the scaled cooldown is now clamped by capScaledCooldownMs
+  // (open-sse/services/accountFallback/cooldownCap.ts). With no provider the
+  // ceiling is BACKOFF_CONFIG.max, so the doubling stops there instead of
+  // running on to transientInitial * 32.
+  assert.ok(
+    COOLDOWN_MS.transientInitial * 32 > BACKOFF_CONFIG.max,
+    "precondition: the 6th step must exceed the cap, or this test proves nothing"
+  );
   assert.deepEqual(cooldowns, [
     COOLDOWN_MS.transientInitial,
     COOLDOWN_MS.transientInitial * 2,
     COOLDOWN_MS.transientInitial * 4,
     COOLDOWN_MS.transientInitial * 8,
     COOLDOWN_MS.transientInitial * 16,
-    COOLDOWN_MS.transientInitial * 32,
+    BACKOFF_CONFIG.max,
   ]);
 });
 
@@ -237,8 +245,14 @@ test("subscription quota uses long cooldown when upstream retry hints are disabl
 test("high transient backoff levels clamp to the configured maxBackoffSteps", () => {
   const result = checkFallbackError(502, "", BACKOFF_CONFIG.maxLevel + 5, null, null);
   assert.equal(result.newBackoffLevel, BACKOFF_CONFIG.maxLevel);
+  // #8396: the level still clamps at maxLevel, but the resulting duration is
+  // additionally capped — unclamped this would be ~45.5h, which is the blackout
+  // that PR removed.
   assert.equal(
     result.cooldownMs,
-    COOLDOWN_MS.transientInitial * Math.pow(2, BACKOFF_CONFIG.maxLevel)
+    Math.min(
+      COOLDOWN_MS.transientInitial * Math.pow(2, BACKOFF_CONFIG.maxLevel),
+      BACKOFF_CONFIG.max
+    )
   );
 });

tests/unit/thundering-herd.test.ts

@@ -39,9 +39,15 @@ test("API profile has shorter transient cooldown", () => {
 test("Exponential backoff clamps to the configured maxBackoffLevel", () => {
   const result = checkFallbackError(502, "", 20, null, null);
   assert.equal(result.newBackoffLevel, BACKOFF_CONFIG.maxLevel);
+  // #8396: the level still clamps at maxLevel, but capScaledCooldownMs also
+  // bounds the duration — with no provider profile the ceiling is
+  // BACKOFF_CONFIG.max rather than the unbounded baseCooldownMs * 2^level.
   assert.equal(
     result.cooldownMs,
-    COOLDOWN_MS.transientInitial * Math.pow(2, BACKOFF_CONFIG.maxLevel)
+    Math.min(
+      COOLDOWN_MS.transientInitial * Math.pow(2, BACKOFF_CONFIG.maxLevel),
+      BACKOFF_CONFIG.max
+    )
   );
 });
 

tests/unit/vscode-token-routes-responses-listing.test.ts

@@ -0,0 +1,153 @@
+// #7587: PR #7012 widened only the `/models` route's isUsableChatModel copy to
+// accept Responses-API-format models (e.g. Codex-discovery-synced GPT models with
+// apiFormat "responses"); the other 4 duplicated copies (tags/show, token + raw)
+// still rejected anything that wasn't literally "chat-completions", silently
+// dropping every OpenAI/Codex "responses" model from the Ollama-compatible
+// listing endpoints VS Code's "Ollama" provider import flow actually uses.
+//
+// Split into its own file (rather than appended to vscode-token-routes.test.ts)
+// because that file is frozen by check-file-size.mjs's testFrozen baseline.
+import test from "node:test";
+import assert from "node:assert/strict";
+import fs from "node:fs";
+import os from "node:os";
+import path from "node:path";
+
+const TEST_DATA_DIR = fs.mkdtempSync(
+  path.join(os.tmpdir(), "omniroute-vscode-responses-listing-")
+);
+process.env.DATA_DIR = TEST_DATA_DIR;
+process.env.API_KEY_SECRET = process.env.API_KEY_SECRET || "vscode-responses-listing-secret";
+
+const core = await import("../../src/lib/db/core.ts");
+const providersDb = await import("../../src/lib/db/providers.ts");
+const settingsDb = await import("../../src/lib/db/settings.ts");
+const apiKeysDb = await import("../../src/lib/db/apiKeys.ts");
+const modelsDb = await import("../../src/lib/db/models.ts");
+const vscodeModelsRoute = await import("../../src/app/api/v1/vscode/[token]/models/route.ts");
+const vscodeTagsRoute = await import("../../src/app/api/v1/vscode/[token]/api/tags/route.ts");
+const vscodeShowRoute = await import("../../src/app/api/v1/vscode/[token]/api/show/route.ts");
+const vscodeRawTagsRoute =
+  await import("../../src/app/api/v1/vscode/raw/[token]/api/tags/route.ts");
+const vscodeRawShowRoute =
+  await import("../../src/app/api/v1/vscode/raw/[token]/api/show/route.ts");
+
+async function resetStorage() {
+  core.resetDbInstance();
+  apiKeysDb.resetApiKeyState();
+  fs.rmSync(TEST_DATA_DIR, { recursive: true, force: true });
+  fs.mkdirSync(TEST_DATA_DIR, { recursive: true });
+}
+
+test.beforeEach(async () => {
+  await resetStorage();
+});
+
+test.after(async () => {
+  core.resetDbInstance();
+  apiKeysDb.resetApiKeyState();
+  fs.rmSync(TEST_DATA_DIR, { recursive: true, force: true });
+});
+
+test("vscode Ollama-compatible tags/show routes (token + raw) expose Codex-discovered responses-format GPT models", async () => {
+  await settingsDb.updateSettings({
+    requireLogin: true,
+    password: "hashed-password",
+    requireAuthForModels: true,
+  });
+
+  // Note: the id deliberately avoids the "gpt-5.4" family — it collides with
+  // CODEX_DISCOVERY_EXCLUDED_ID_PREFIXES (src/shared/services/codexDiscoveryPolicy.ts)
+  // and would be dropped from the catalog before ever reaching the listing filter
+  // this test targets.
+  const connection = await providersDb.createProviderConnection({
+    provider: "codex",
+    authType: "apikey",
+    name: "codex-vscode-responses-listing",
+    apiKey: "sk-test",
+    isActive: true,
+    testStatus: "active",
+    providerSpecificData: {},
+  });
+  await modelsDb.replaceSyncedAvailableModelsForConnection("codex", connection.id, [
+    {
+      id: "gpt-6.9-responses-probe",
+      name: "GPT 6.9 Responses Probe",
+      apiFormat: "responses",
+      supportedEndpoints: ["responses"],
+      inputTokenLimit: 400000,
+      outputTokenLimit: 128000,
+    },
+  ]);
+  const key = await apiKeysDb.createApiKey(
+    "vscode-responses-listing",
+    "machine-vscode-responses-listing"
+  );
+
+  const modelsResponse = await vscodeModelsRoute.GET(
+    new Request(`http://localhost/api/v1/vscode/${encodeURIComponent(key.key)}/models`)
+  );
+  const modelsBody = (await modelsResponse.json()) as {
+    data?: Array<{ id?: string; owned_by?: string; api_format?: string }>;
+  };
+  const responsesModel = (modelsBody.data || []).find(
+    (model) => model.owned_by === "codex" && model.api_format === "responses"
+  );
+  assert.ok(
+    responsesModel,
+    "precondition failed: expected the responses-format GPT model on /models (PR #7012 fix)"
+  );
+
+  const tagsResponse = await vscodeTagsRoute.GET(
+    new Request(`http://localhost/api/v1/vscode/${encodeURIComponent(key.key)}/api/tags`)
+  );
+  const tagsBody = (await tagsResponse.json()) as { models?: Array<{ name?: string }> };
+  const tagNames = new Set((tagsBody.models || []).map((model) => model.name));
+  assert.ok(
+    tagNames.has(responsesModel!.id),
+    `expected /api/tags (Ollama flow) to also expose the responses-format GPT model, got: ${JSON.stringify(
+      Array.from(tagNames)
+    )}`
+  );
+
+  const rawTagsResponse = await vscodeRawTagsRoute.GET(
+    new Request(`http://localhost/api/v1/vscode/raw/${encodeURIComponent(key.key)}/api/tags`)
+  );
+  const rawTagsBody = (await rawTagsResponse.json()) as { models?: Array<{ name?: string }> };
+  const rawTagNames: string[] = (rawTagsBody.models || [])
+    .map((model) => model.name)
+    .filter((name): name is string => typeof name === "string");
+  const rawResponsesModelName = rawTagNames.find((name) =>
+    name.includes("gpt-6.9-responses-probe")
+  );
+  assert.ok(
+    rawResponsesModelName,
+    `expected raw /api/tags to also expose the responses-format GPT model, got: ${JSON.stringify(
+      rawTagNames
+    )}`
+  );
+
+  const showResponse = await vscodeShowRoute.POST(
+    new Request(`http://localhost/api/v1/vscode/${encodeURIComponent(key.key)}/api/show`, {
+      method: "POST",
+      body: JSON.stringify({ name: responsesModel!.id }),
+    })
+  );
+  assert.equal(
+    showResponse.status,
+    200,
+    "expected /api/show to find the responses-format GPT model by its tag name"
+  );
+
+  const rawShowResponse = await vscodeRawShowRoute.POST(
+    new Request(`http://localhost/api/v1/vscode/raw/${encodeURIComponent(key.key)}/api/show`, {
+      method: "POST",
+      body: JSON.stringify({ name: rawResponsesModelName }),
+    })
+  );
+  assert.equal(
+    rawShowResponse.status,
+    200,
+    "expected raw /api/show to find the responses-format GPT model by its tag name"
+  );
+});