+
+
@@ -439,7 +439,7 @@ All **19** strategies — mix & match per combo step: -
+
📊 Full methodology & per-feature detail vs 9router, OpenRouter, CLIProxyAPI & LiteLLM → [`docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md`](docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md)
@@ -513,7 +513,7 @@ Pix copia-e-cola:
- **🖼️ New endpoints** — `/v1/ocr` (Mistral OCR) and `/v1/audio/translations` (Whisper-style) round out the media surface. → [API Reference](docs/reference/API_REFERENCE.md)
- **🎨 Image / video / audio generation** — one API for media: xAI Grok Imagine & Novita AI video, ComfyUI, Freepik, Adobe Firefly, Microsoft Designer, Google Imagen, Segmind, EdgeTTS. → [API Reference](docs/reference/API_REFERENCE.md)
- **🌍 Deployment & ops** — reverse-proxy `basePath`, browser-language auto-detect, per-key device tracking, root-less MITM trust, zh-TW localization. → [Environment](docs/reference/ENVIRONMENT.md)
-- **🤝 More providers & agents** — Cursor Cloud Agent, Grok Build (xAI) with browser + OAuth login, Ollama first-class card, Claude Opus 5 & Sonnet 5, Kimi official partnership (Code/Web/Moonshot), Zed, Requesty, SenseNova, Yuanbao, Agnes AI… and a refreshed **290-provider catalog**. → [Providers](docs/reference/PROVIDER_REFERENCE.md)
+- **🤝 More providers & agents** — Cursor Cloud Agent, Grok Build (xAI) with browser + OAuth login, Ollama first-class card, Claude Opus 5 & Sonnet 5, Kimi official partnership (Code/Web/Moonshot), Zed, Requesty, SenseNova, Yuanbao, Agnes AI… and a refreshed **291-provider catalog**. → [Providers](docs/reference/PROVIDER_REFERENCE.md)
- **📡 Routing transparency** — every response carries an `X-OmniRoute-Decision` header naming the strategy/provider/latency that served it, a new `cache-optimized` combo strategy + Auto-Combo `cacheAffinity` factor route repeat requests back to the connection holding the cached prefix, and a read-only `/v1/auto-combo/{channel}/candidates` endpoint exposes an `auto/*` channel's live candidate pool. → [Auto-Combo](docs/routing/AUTO-COMBO.md)
- **⚡ Local performance & infra** — one-click local Redis, Cloudflare Workers / Deno Deploy relay deployers, Bifrost & Mux as supervised embedded services. → [Embedded Services](docs/frameworks/EMBEDDED-SERVICES.md)
@@ -574,11 +574,11 @@ Pix copia-e-cola:
-## 🌐 290 AI Providers — 90+ Free
+## 🌐 291 AI Providers — 90+ Free
-> The most complete catalog of any open-source router: **290 providers**, **90+ with a free tier**, **40+ free forever**.
+> The most complete catalog of any open-source router: **291 providers**, **90+ with a free tier**, **40+ free forever**.
diff --git a/config/quality/file-size-baseline.json b/config/quality/file-size-baseline.json
index 4034c147c2..9b8280ec8a 100644
--- a/config/quality/file-size-baseline.json
+++ b/config/quality/file-size-baseline.json
@@ -172,7 +172,7 @@
"_rebaseline_2026_07_25_8510_adobe_firefly_reference_images_tests": "#8510 (artickc, feat/adobe-firefly-reference-images) own test growth: tests/unit/adobe-firefly.test.ts 711->871 (+159, entirely this PR's diff — new referenceBlobs upload/dispatch coverage for handleAdobeFireflyImageGeneration, resolveAdobeSourceImageIds, and the storage-upload wire contract). Route-level /v1/images/edits coverage (credentials/rate-limit/4-ref-cap branches added to route.ts) lives in the new tests/unit/8510-adobe-firefly-edits-route.test.ts instead of growing this file further.",
"_rebaseline_basered_codebuddy_cn": "Base-red fix (#4664 CodeBuddy CN): oauth-providers-config.test.ts 867->870 (+3) to align the EXPECTED provider list/config with the codebuddy-cn provider that #4664 added to the registry without updating this test (it asserts 'exactly once').",
"_rebaseline_pr4613_compatible_provider_groups": "Reconcile #4613 already-merged growth: providers-page-utils.test.ts 1004->1052 (+48, buildCompatibleProviderGroups partition unit test). Fast-gate PR->release does not run check:file-size, so this surfaced post-merge.",
- "tests/integration/chat-pipeline.test.ts": 1592,
+ "tests/integration/chat-pipeline.test.ts": 1598,
"tests/integration/chatcore-compression-integration.test.ts": 1114,
"tests/unit/account-fallback-service.test.ts": 1563,
"tests/unit/batch_api.test.ts": 1324,
@@ -190,7 +190,7 @@
"tests/unit/models-catalog-route.test.ts": 1636,
"tests/unit/perplexity-web.test.ts": 1355,
"tests/unit/provider-models-route.test.ts": 1784,
- "tests/unit/provider-validation-specialty.test.ts": 2980,
+ "tests/unit/provider-validation-specialty.test.ts": 2985,
"tests/unit/providers-page-utils.test.ts": 1106,
"tests/unit/response-sanitizer.test.ts": 1063,
"tests/unit/route-edge-coverage.test.ts": 1241,
@@ -343,7 +343,7 @@
"_rebaseline_pr1043_minimax_tts": "Upstream port decolua/9router#1043 (toanalien) own growth: audioSpeech.ts 965->1061 (+96). Adds MiniMax T2A v2 TTS dispatch (handleMinimaxSpeech + hexToBytes helper) — provider entry was already in audioRegistry (format: minimax-tts) but no handler existed, falling through to the OpenAI-compatible default that fails (T2A has custom shape + hex-encoded audio + base_resp envelope). New branch sits next to the other inline provider branches (xiaomi-mimo, coqui, tortoise, aws-polly) — extracting would just create indirection. Covered by tests/unit/minimax-tts-1043.test.ts (3 tests, GREEN: success, base_resp error, invalid-hex).",
"_rebaseline_pr4592_exclude_exhausted_auto": "Reconcile #4592 already-merged growth: combo.ts 2991->3036 (+45, terminal-status quota-cutoff exclusion in buildAutoCandidates + opt-in gate). Fast-gate PR->release does not run check:file-size.",
"open-sse/executors/antigravity.ts": 1528,
- "open-sse/executors/base.ts": 1578,
+ "open-sse/executors/base.ts": 1623,
"open-sse/executors/chatgpt-web.ts": 3241,
"open-sse/executors/codex.ts": 1534,
"open-sse/executors/cursor.ts": 1560,
@@ -363,8 +363,8 @@
"open-sse/services/claudeCodeCompatible.ts": 1202,
"open-sse/services/combo.ts": 3648,
"open-sse/services/compression/strategySelector.ts": 1060,
- "open-sse/services/rateLimitManager.ts": 1060,
- "open-sse/translator/response/openai-responses.ts": 1174,
+ "open-sse/services/rateLimitManager.ts": 1105,
+ "open-sse/translator/response/openai-responses.ts": 1204,
"open-sse/utils/cursorAgentProtobuf.ts": 1505,
"open-sse/utils/stream.ts": 2889,
"src/app/(dashboard)/dashboard/HomePageClient.tsx": 1381,
@@ -405,7 +405,7 @@
"src/sse/handlers/chat.ts": 1845,
"src/sse/services/auth.ts": 2508,
"tests/unit/account-fallback-service.test.ts": 1572,
- "tests/unit/provider-validation-specialty.test.ts": 2980,
+ "tests/unit/provider-validation-specialty.test.ts": 2985,
"open-sse/executors/hyperagent.ts": 1026
},
"_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).",
@@ -418,5 +418,7 @@
"_rebaseline_2026_07_29_8281_home_quickstart_prefetch": "Release v3.8.49 base-red fix (no PR — captain sweep): src/app/(dashboard)/dashboard/HomePageClient.tsx 1377->1381 (+4). #8292 added prefetch={false} to the sidebar but left /home's five quick-start Links prefetching, so first paint still fired 12 speculative RSC requests — caught by navigation.spec.ts only after the e2e helper bug (APP_ROUTE_PATTERN missing /home) was repaired in the same cycle. Growth is the five prefetch attributes; it was offset first by extracting the repeated className literals (INLINE_LINK x4, DOCS_LINK x1), which collapsed five wrapped blocks back to one line each — a naive fix measured 1391. Guard: tests/unit/sidebar-prefetch-policy-8281.test.ts.",
"_rebaseline_2026_08_01_8964_xai_agent_tools": "PR #8964 own growth: chatCore.ts 5020->5034 at the existing native-passthrough chokepoint. Adds xAI Agent Tools passthrough for /v1/responses (xai/xai-oauth/xao): resolve nativeXaiResponsesPassthrough, force openai-responses targetFormat, stamp body marker, and OR into the existing nativeCodexPassthrough sites (web-search bypass + requestEndpointPath). Leaf logic in passthroughHelpers, responsesEndpoint, targetFormat, xai executor, responseSanitizer, usageTracking. Cohesive wiring at the Codex passthrough boundary.",
"_rebaseline_2026_08_01_8964_response_sanitizer": "PR #8964 own growth: responseSanitizer.ts 1115->1128. Keep cost_in_usd_ticks / server_side_tool_usage(_details) through sanitizeResponsesApiResponse allowlists so native xAI tool responses retain usage.",
- "_rebaseline_2026_08_02_v3850_agentrouter_responses": "Release v3.8.50 AgentRouter/Codex compatibility reconciliation. open-sse/executors/base.ts 1562->1578: #9190 wires AgentRouter's selected Claude/OpenAI/Responses protocol through the existing executor URL, auth, identity-header and fingerprint chokepoints; the reusable alternate resolver remains outside base.ts. open-sse/utils/stream.ts 2887->2889: #9213 evaluates Responses ID and usage normalization independently so response.completed always receives finite usage.total_tokens instead of short-circuiting after an ID rewrite. tests/unit/chatcore-translation-paths.test.ts 2769->2776: #9191 updates the existing Claude-Code bridge assertions for the dynamic AgentRouter wire image. PR #9224 offsets its own chatCore growth by extracting the AgentRouter protocol decisions into chatCore/agentRouterProtocol.ts, leaving chatCore below its frozen ceiling. Covered by agentrouter executor/chatCore protocol tests, chatcore translation-path tests, and responses-commentary-passthrough tests."
+ "_rebaseline_2026_08_02_v3850_agentrouter_responses": "Release v3.8.50 AgentRouter/Codex compatibility reconciliation. open-sse/executors/base.ts 1562->1578: #9190 wires AgentRouter's selected Claude/OpenAI/Responses protocol through the existing executor URL, auth, identity-header and fingerprint chokepoints; the reusable alternate resolver remains outside base.ts. open-sse/utils/stream.ts 2887->2889: #9213 evaluates Responses ID and usage normalization independently so response.completed always receives finite usage.total_tokens instead of short-circuiting after an ID rewrite. tests/unit/chatcore-translation-paths.test.ts 2769->2776: #9191 updates the existing Claude-Code bridge assertions for the dynamic AgentRouter wire image. PR #9224 offsets its own chatCore growth by extracting the AgentRouter protocol decisions into chatCore/agentRouterProtocol.ts, leaving chatCore below its frozen ceiling. Covered by agentrouter executor/chatCore protocol tests, chatcore translation-path tests, and responses-commentary-passthrough tests.",
+ "_rebaseline_2026_08_05_9323_agentrouter_waf_retry": "PR #9323 (fix(agentrouter): retry on 400 content-blocked + burst guard) own growth: open-sse/executors/base.ts 1578->1623 (check-file-size.mjs conta via split(\"\\n\").length; wc -l ve 1622). As +45 linhas sao o WAF_RETRY_CONFIG + o burst guard via gateOutboundRequest() para o WAF do agentrouter.org, com comentarios explicando o porque de cada mitigacao e cobertos por tests/unit/base-executor-waf-retry.test.ts e tests/unit/wafRateLimit.test.ts. Crescimento funcional legitimo, nao inchaco.",
+ "_rebaseline_2026_08_05_9529_own_growth": "PR #9529 own growth (base release/v3.8.50 medida EXATAMENTE nos frozen antigos, entao o modo base-relative #8522 nao cobre): open-sse/services/rateLimitManager.ts 1060->1105 (+45: helper applyLimiterSettings() que re-arma o heartbeat do reservoir apos updateSettings — fix do bug Bottleneck 2.19.5 que congelava a fila weighted; TDD em tests/unit/ratelimit-reservoir-refresh.test.ts); tests/integration/chat-pipeline.test.ts 1592->1598 (+6: User-Agent do codex derivado de getCodexClientVersion() em vez de literal pinado — teste-irmao alinhado ao contrato); tests/unit/provider-validation-specialty.test.ts 2980->2985 (+5: cobertura NOVA claude-web 429 -> valid:false, alinhamento #9406); open-sse/translator/response/openai-responses.ts 1174->1204 (+30: buildResponsesReasoningSummaryDelta MOVIDA do leaf pureHelpers.ts para o host — a funcao do #9500 muta stream state e violava o contrato do leaf puro; o LOC total do par host+leaf nao cresceu, o pureHelpers encolheu o mesmo tanto). Crescimento por fix de producao + cobertura adicional + realocacao arquitetural, nao inchaco."
}
diff --git a/config/quality/test-masking-allowlist.json b/config/quality/test-masking-allowlist.json
index e01abf42cc..e15040cb47 100644
--- a/config/quality/test-masking-allowlist.json
+++ b/config/quality/test-masking-allowlist.json
@@ -109,5 +109,7 @@
"tests/unit/usage-service-hardening.test.ts": "v3.8.49 #7866/#8565/#8013: qwen removido (−3 asserts); o Kimi/Kiro builder-id (uso profileless) passou a ter SUCESSO real em vez de erro de ARN — supportsProfilelessKiroUsage(\"builder-id\") retorna true —, trocando 1 assert de regex de erro por 3 asserts de valor; e os ids de bucket de quota do Antigravity foram atualizados para o catálogo atual. Rodado no HEAD: 23/23 passam. Net 210→209. Verificado legítimo. Prune após v3.8.49 mergear para main.",
"tests/unit/virtual-auto-combo.test.ts": "v3.8.49 #7928/#8183: o pooling de contas passou a agrupar conexões web-session do mesmo provider numa entrada lógica com allowedConnectionIds (campo confirmado em open-sse/services/autoCombo/virtualFactory.ts), e o pool no-auth virou uma allowlist fixa (AUTO_COMBO_NOAUTH_ALLOWLIST = opencode, felo-web) — os testes antigos esperavam duplicatas e a inclusão de duckduckgo-web/theoldllm/chipotle, que hoje são corretamente excluídos. Guard dedicado em noauth-autocombo-allowlist.test.ts. Rodado no HEAD: 10/10 passam. Net 39→31. Verificado legítimo. Prune após v3.8.49 mergear para main.",
"open-sse/services/__tests__/tierResolver.test.ts": "v3.8.49 #7866: refactor(qwen) remove o provider OAuth legado — o teste \"classifies Qwen as free\" e a entrada de qwen na lista do batch saíram junto com o provider, e os índices do batch desceram de 10 para 9 elementos (net 61→59). Superfície extinta, não enfraquecimento. Verificado legítimo. Prune após v3.8.49 mergear para main.",
- "tests/unit/plugins-welcome-banner-e2e.test.ts": "v3.8.50 #9126 (commit 8fac6bcd48): o teste único 'BUILTIN_EVENTS has all 14 events' (13 asserts .ok/.equal) foi reestruturado em 3 testes mais específicos — 'contains only emitted/public events' (assert.deepEqual da lista completa), 'does not advertise dead events' (7 asserts .equal(false) para eventos sem emissor real: onModelSelect/onComboResolve/onRateLimit/onQuotaExhaust/onProviderError/onStreamStart/onStreamEnd) e 'lifecycle events remain represented' (4 asserts .ok). Contrato mais forte (agora também nega presença dos eventos mortos), não mais fraco — a contagem líquida cai (73→61) porque o assert.deepEqual único substitui múltiplos assert.ok redundantes com a mesma cobertura. Asserts restruturados, não removidos sem substituição. Verificado legítimo."
+ "tests/unit/plugins-welcome-banner-e2e.test.ts": "v3.8.50 #9126 (commit 8fac6bcd48): o teste único 'BUILTIN_EVENTS has all 14 events' (13 asserts .ok/.equal) foi reestruturado em 3 testes mais específicos — 'contains only emitted/public events' (assert.deepEqual da lista completa), 'does not advertise dead events' (7 asserts .equal(false) para eventos sem emissor real: onModelSelect/onComboResolve/onRateLimit/onQuotaExhaust/onProviderError/onStreamStart/onStreamEnd) e 'lifecycle events remain represented' (4 asserts .ok). Contrato mais forte (agora também nega presença dos eventos mortos), não mais fraco — a contagem líquida cai (73→61) porque o assert.deepEqual único substitui múltiplos assert.ok redundantes com a mesma cobertura. Asserts restruturados, não removidos sem substituição. Verificado legítimo.",
+ "tests/unit/web-tools-translation-2820.test.ts": "v3.8.50 #9343 (commit d969555417): fix(security) exige envelope explicito — JSON puro NAO deve mais ser promovido a tool_calls. Os 5 testes foram REESCRITOS para o contrato oposto (antes: 'promove e valida name/arguments'; agora: 'toolCalls === null e content preservado'), o que naturalmente usa menos asserts: verificar a NAO-promocao custa 2 asserts, verificar o objeto promovido custava 4. Contrato mais restritivo, nao mais fraco (39->35). Verificado legitimo — a inversao esta explicita nos proprios nomes dos testes ('does NOT promote ... (#9343)').",
+ "tests/unit/deepseek-web-tools-execute-2820.test.ts": "v3.8.50 ed661f2126 (alinhamento ao #9343): o teste 'parses bare JSON reply into OpenAI tool_calls' foi reescrito para o contrato INVERTIDO do fix de seguranca #9343 — JSON puro sem envelope NAO deve mais ser promovido. Verificar a nao-promocao custa 3 asserts (finish_reason stop, sem tool_calls, content preservado verbatim) onde validar o objeto promovido custava 5 (23->21). Mesma classe da entrada web-tools-translation-2820 acima. Contrato mais restritivo, nao mais fraco."
}
diff --git a/open-sse/services/rateLimitManager.ts b/open-sse/services/rateLimitManager.ts
index c39b39c18e..87f48a46fa 100644
--- a/open-sse/services/rateLimitManager.ts
+++ b/open-sse/services/rateLimitManager.ts
@@ -164,13 +164,58 @@ function buildLimiterDefaults() {
};
}
-function updateAllLimiterSettings() {
- const defaults = buildLimiterDefaults();
- for (const limiter of limiters.values()) {
- limiter.updateSettings(defaults);
+/**
+ * Apply new settings to a Bottleneck limiter and re-arm its reservoir-refresh
+ * heartbeat.
+ *
+ * Bottleneck 2.19.5 (frozen upstream dependency, no release since 2019) has a
+ * bug in `LocalDatastore#_startHeartbeat()`
+ * (node_modules/bottleneck/lib/LocalDatastore.js:29,56): the guard
+ * `if (this.heartbeat == null && ...)` only (re)creates the periodic
+ * reservoir-refresh interval the FIRST time it runs. Every later call —
+ * including the one `updateSettings()` itself triggers internally — falls
+ * into the `else` branch and does `clearInterval(this.heartbeat)` WITHOUT
+ * resetting `this.heartbeat` back to `null`. Because the stale reference is
+ * left in place, every future `_startHeartbeat()` call keeps taking the same
+ * dead `else` branch: the periodic reservoir refresh is gone forever after
+ * the FIRST manual `updateSettings()` call on a limiter — every limiter here
+ * starts with a live heartbeat (buildLimiterDefaults() always sets
+ * reservoirRefreshInterval/reservoirRefreshAmount), so that "first call" is
+ * whichever of the 5 updateSettings() call sites in this file runs first.
+ *
+ * Work around it here instead of patching node_modules: null out the stale
+ * reference ourselves and re-invoke `_startHeartbeat()` so it takes the
+ * "start a fresh interval" branch again. Every `limiter.updateSettings(...)`
+ * call in this file MUST go through this helper, never Bottleneck's method
+ * directly.
+ */
+async function applyLimiterSettings(
+ limiter: Bottleneck,
+ updates: Bottleneck.ConstructorOptions
+): Promise {
+ await limiter.updateSettings(updates);
+ const store = (
+ limiter as unknown as {
+ _store?: {
+ heartbeat?: ReturnType | null;
+ _startHeartbeat?: () => void;
+ };
+ }
+ )._store;
+ if (store && typeof store._startHeartbeat === "function") {
+ if (store.heartbeat != null) clearInterval(store.heartbeat);
+ store.heartbeat = null;
+ store._startHeartbeat();
}
}
+async function updateAllLimiterSettings() {
+ const defaults = buildLimiterDefaults();
+ await Promise.all(
+ Array.from(limiters.values(), (limiter) => applyLimiterSettings(limiter, defaults))
+ );
+}
+
function reconcileEnabledConnections(
connectionsRaw: unknown[],
requestQueueSettings: RequestQueueSettings
@@ -381,7 +426,7 @@ export async function initializeRateLimits() {
connections as unknown[],
currentRequestQueueSettings
);
- updateAllLimiterSettings();
+ await updateAllLimiterSettings();
// Load per-connection rate limit overrides
connectionRateLimitOverrides.clear();
@@ -414,7 +459,7 @@ export async function applyRequestQueueSettings(nextSettings: RequestQueueSettin
const { getCachedProviderConnections } = await import("@/lib/localDb");
const connections = await getCachedProviderConnections();
reconcileEnabledConnections(connections as unknown[], currentRequestQueueSettings);
- updateAllLimiterSettings();
+ await updateAllLimiterSettings();
}
/**
@@ -779,9 +824,7 @@ export function updateFromHeaders(provider, connectionId, headers, status, model
logRateLimit(
`⚠️ [RATE-LIMIT] ${provider}:${connectionId.slice(0, 8)} — near capacity, slowing down`
);
- limiter.updateSettings({
- minTime: 200, // Add 200ms between requests
- });
+ trackAsyncOperation(applyLimiterSettings(limiter, { minTime: 200 }));
return;
}
@@ -812,7 +855,7 @@ export function updateFromHeaders(provider, connectionId, headers, status, model
}
}
- limiter.updateSettings(updates);
+ trackAsyncOperation(applyLimiterSettings(limiter, updates));
// Persist learned limits (debounced)
recordLearnedLimit(
@@ -1014,7 +1057,7 @@ async function loadPersistedLimits() {
const limiter = limiters.get(key);
if (limiter && limit > 0) {
const inferredMinTime = minTime || Math.max(0, Math.floor(60000 / limit) - 10);
- limiter.updateSettings({ minTime: inferredMinTime });
+ await applyLimiterSettings(limiter, { minTime: inferredMinTime });
count++;
}
}
@@ -1050,10 +1093,12 @@ export function updateFromResponseBody(provider, connectionId, responseBody, sta
`🚫 [RATE-LIMIT] ${provider}:${connectionId.slice(0, 8)} — body-parsed retry: ${Math.ceil(retryAfterMs / 1000)}s (${reason})`
);
- limiter.updateSettings({
- reservoir: 0,
- reservoirRefreshAmount: 60,
- reservoirRefreshInterval: retryAfterMs,
- });
+ trackAsyncOperation(
+ applyLimiterSettings(limiter, {
+ reservoir: 0,
+ reservoirRefreshAmount: 60,
+ reservoirRefreshInterval: retryAfterMs,
+ })
+ );
}
}
diff --git a/open-sse/translator/response/openai-responses.ts b/open-sse/translator/response/openai-responses.ts
index 1b22d5ce3a..346c23ffa9 100644
--- a/open-sse/translator/response/openai-responses.ts
+++ b/open-sse/translator/response/openai-responses.ts
@@ -18,7 +18,6 @@ import {
normalizeOutputIndex,
normalizeUpstreamFailure,
getVisibleResponsesReasoningSummaryText,
- buildResponsesReasoningSummaryDelta,
} from "./openai-responses/pureHelpers.ts";
import { createEventEmitter } from "./openai-responses/eventEmitter.ts";
import { buildResponsesToolCallItem } from "./responsesToolItem.ts";
@@ -727,6 +726,37 @@ function markResponsesReasoningDeltaEmitted(state, itemId) {
state.reasoningItemsWithDelta.add(id);
}
+// #9500 — streaming separator helper. When summary_index increments mid-stream
+// for a given item_id, a new reasoning segment begins; prefix "\n\n" so segments
+// don't arrive back-to-back. Only prefixes when a delta was already emitted for
+// the item AND the index advanced — never on the first segment. Lives here (not
+// in pureHelpers.ts) because it reads and mutates stream state, which the pure
+// leaf must not hold.
+function buildResponsesReasoningSummaryDelta(state, data, reasoningDelta) {
+ const itemId = data.item_id != null ? String(data.item_id) : "";
+ const summaryIndex = typeof data.summary_index === "number" ? data.summary_index : null;
+ if (!(state.reasoningSummaryIndex instanceof Map)) {
+ state.reasoningSummaryIndex = new Map();
+ }
+ const lastIndex = itemId ? state.reasoningSummaryIndex.get(itemId) : undefined;
+ const alreadyEmittedForItem = itemId
+ ? state.reasoningItemsWithDelta instanceof Set && state.reasoningItemsWithDelta.has(itemId)
+ : Boolean(state.reasoningDeltaEmitted);
+ let deltaText = reasoningDelta;
+ if (
+ summaryIndex !== null &&
+ lastIndex !== undefined &&
+ summaryIndex > lastIndex &&
+ alreadyEmittedForItem
+ ) {
+ deltaText = `\n\n${reasoningDelta}`;
+ }
+ if (itemId && (lastIndex === undefined || summaryIndex > lastIndex)) {
+ state.reasoningSummaryIndex.set(itemId, summaryIndex);
+ }
+ return deltaText;
+}
+
// #5786 — build a Chat-format reasoning delta chunk in the shape the client renders in
// its thinking panel (`reasoning_content`, or `reasoning_text` for Copilot-compatible
// clients). Mirrors the `response.reasoning_summary_text.delta` branch.
diff --git a/open-sse/translator/response/openai-responses/pureHelpers.ts b/open-sse/translator/response/openai-responses/pureHelpers.ts
index e010b2c6f4..e35ad24854 100644
--- a/open-sse/translator/response/openai-responses/pureHelpers.ts
+++ b/open-sse/translator/response/openai-responses/pureHelpers.ts
@@ -177,37 +177,6 @@ export function extractResponsesReasoningSummaryText(item) {
.join("\n\n");
}
-// #9500 — streaming separator helper. When summary_index increments mid-stream
-// for a given item_id, a new reasoning segment begins; prefix "\n\n" so segments
-// don't arrive back-to-back. Only prefixes when a delta was already emitted for
-// the item AND the index advanced — never on the first segment.
-export function buildResponsesReasoningSummaryDelta(state, data, reasoningDelta) {
- const itemId = data.item_id != null ? String(data.item_id) : "";
- const summaryIndex =
- typeof data.summary_index === "number" ? data.summary_index : null;
- if (!(state.reasoningSummaryIndex instanceof Map)) {
- state.reasoningSummaryIndex = new Map();
- }
- const lastIndex = itemId ? state.reasoningSummaryIndex.get(itemId) : undefined;
- const alreadyEmittedForItem = itemId
- ? state.reasoningItemsWithDelta instanceof Set &&
- state.reasoningItemsWithDelta.has(itemId)
- : Boolean(state.reasoningDeltaEmitted);
- let deltaText = reasoningDelta;
- if (
- summaryIndex !== null &&
- lastIndex !== undefined &&
- summaryIndex > lastIndex &&
- alreadyEmittedForItem
- ) {
- deltaText = `\n\n${reasoningDelta}`;
- }
- if (itemId && (lastIndex === undefined || summaryIndex > lastIndex)) {
- state.reasoningSummaryIndex.set(itemId, summaryIndex);
- }
- return deltaText;
-}
-
// #7095/#7176 — when Codex exposes a reasoning item only as encrypted private
// reasoning (no plaintext summary), chat clients would otherwise see nothing in
// their thinking panel. Reconciles two goals that used to be in tension:
diff --git a/scripts/check/check-test-masking.mjs b/scripts/check/check-test-masking.mjs
index 0f94b55d6a..9bb8832586 100644
--- a/scripts/check/check-test-masking.mjs
+++ b/scripts/check/check-test-masking.mjs
@@ -251,7 +251,7 @@ export function findReimplementedConditions(prodSources, testSource, testImports
* (filtro D do git diff --diff-filter=MDR).
*
* `deletionAllowlist` (`_deletedWithReplacement` no test-masking-allowlist.json)
- * isenta uma deleção de duas formas, cada uma com sua própria verificação:
+ * isenta uma deleção de três formas, cada uma com sua própria verificação:
* 1. `replacement` (path string) — o substituto declarado existe no HEAD e é
* ele próprio um arquivo de teste — o caso "reescrito em outro path sem
* rename detectável" (conteúdo novo demais para o -M do git).
@@ -259,12 +259,19 @@ export function findReimplementedConditions(prodSources, testSource, testImports
* os arquivos de produção listados precisam estar ausentes no HEAD (sem
* substituto porque não há mais código a testar). Usar apenas quando a
* remoção do código-fonte está confirmada na mesma commit/PR.
+ * 3. `strayFromCommit` (hash) + `reason` (não-vazio) — o arquivo entrou no
+ * repositório POR ACIDENTE no commit declarado (ex.: um commit de docs
+ * que varreu artefatos de worktree de outra sessão, caso f4e93f339d) e a
+ * deleção devolve o arquivo ao seu fluxo dono (um PR/issue aberto). O
+ * gate verifica via git que o commit declarado é exatamente o que ADICIONOU
+ * o arquivo; o `reason` deve nomear o PR/issue dono para a revisão humana.
* Qualquer entrada cuja condição declarada não se verifique continua flagada.
*/
export function evaluateDeletedFiles(
deletedPaths,
deletionAllowlist = {},
- fileExists = fs.existsSync
+ fileExists = fs.existsSync,
+ addedByCommit = lookupAddedByCommit
) {
const flags = [];
for (const f of deletedPaths) {
@@ -285,6 +292,21 @@ export function evaluateDeletedFiles(
);
continue;
}
+ if (entry && typeof entry.strayFromCommit === "string" && entry.strayFromCommit.trim()) {
+ if (typeof entry.reason !== "string" || !entry.reason.trim()) {
+ flags.push(
+ `${f}: deleção allowlistada como stray mas sem \`reason\` — nomeie o PR/issue dono do arquivo`
+ );
+ continue;
+ }
+ const actual = addedByCommit(f);
+ const declared = entry.strayFromCommit.trim();
+ if (actual && (actual === declared || actual.startsWith(declared))) continue;
+ flags.push(
+ `${f}: deleção allowlistada como stray de ${declared} mas o commit que adicionou o arquivo é ${actual ?? "desconhecido"}`
+ );
+ continue;
+ }
flags.push(
`${f}: arquivo de teste deletado — revisão humana obrigatória (mascaramento alto-sinal)`
);
@@ -292,6 +314,26 @@ export function evaluateDeletedFiles(
return flags;
}
+/**
+ * (subcheck 1, forma 3) Hash COMPLETO do commit que adicionou `path` (o add
+ * mais recente — cobre o caso deletado-e-readicionado). `null` quando o git
+ * não conhece o path.
+ */
+function lookupAddedByCommit(path) {
+ try {
+ const out = execFileSync("git", ["log", "--diff-filter=A", "--format=%H", "--", path], {
+ encoding: "utf8",
+ });
+ const hashes = out
+ .split("\n")
+ .map((s) => s.trim())
+ .filter(Boolean);
+ return hashes.length ? hashes[0] : null;
+ } catch {
+ return null;
+ }
+}
+
/**
* Parse `git diff --name-status -M --diff-filter=DR` output, separating TRUE
* test-file deletions ("D\tpath") from RENAMES ("R\told\tnew").
diff --git a/scripts/quality/validate-release-green.mjs b/scripts/quality/validate-release-green.mjs
index e1adca9927..f9693aa92e 100644
--- a/scripts/quality/validate-release-green.mjs
+++ b/scripts/quality/validate-release-green.mjs
@@ -96,9 +96,7 @@ export function firstFailureLine(out) {
.split("\n")
.map((l) => l.trim())
.filter(Boolean);
- const hit = lines.find((l) =>
- /✖|✗|not ok|AssertionError|error TS|FAIL|Error:|REGRESS/i.test(l)
- );
+ const hit = lines.find((l) => /✖|✗|not ok|AssertionError|error TS|FAIL|Error:|REGRESS/i.test(l));
return (hit || lines[lines.length - 1] || "failed").slice(0, 200);
}
@@ -570,10 +568,20 @@ async function main() {
// release — that is why it is a HARD pre-flight gate.
const slow = [
{
+ // Raised 45→100min 2026-08-05: a hermetic-env run on the loaded devbox
+ // (load 7-26) was still inside invocation 1 of 3 at 76min when killed;
+ // contention factor 2-3× was measured against idle windows, and no idle
+ // measurement exists yet. The pre-flight's REAL condition is exactly
+ // this contended one (unit runs in Promise.all with integration+vitest
+ // plus whatever else the devbox carries), and there 45min provably
+ // killed a healthy suite and fabricated a false base-red. The ceiling's
+ // purpose — turning a genuine hang (stuck SQLite handle = zero progress
+ // forever) into a visible failure — survives at 100min.
+ // TODO: measure on the idle .113 box and re-tighten to ~1.8× measured.
id: "unit",
- label: "Unit tests (full suite, CI concurrency — runs ~20-35min silently)",
+ label: "Unit tests (full suite, CI concurrency — ~30-50min idle, up to ~100min under load)",
args: ["run", "test:unit:ci"],
- timeout: 45 * 60 * 1000,
+ timeout: 100 * 60 * 1000,
},
{
id: "vitest",
@@ -582,10 +590,16 @@ async function main() {
timeout: 15 * 60 * 1000,
},
{
+ // Measured 2026-08-05 on an idle 16-core box: 22m08s hermetic (935 tests,
+ // 112 files at --test-concurrency=1, i.e. strictly serial because ~16 of
+ // them bind a port or share a DB). The old "~3-10min" estimate was stale by
+ // ~3x and the 20min ceiling killed a healthy run. 40min keeps the ceiling's
+ // real purpose — turning a genuine hang (unreleased DB handle) into a
+ // visible failure — without punishing a long-but-healthy suite.
id: "integration",
- label: "Integration tests (~3-10min)",
+ label: "Integration tests (~20-25min)",
args: ["run", "test:integration"],
- timeout: 20 * 60 * 1000,
+ timeout: 40 * 60 * 1000,
},
];
if (WITH_BUILD) {
diff --git a/src/lib/guardrails/visionBridge.ts b/src/lib/guardrails/visionBridge.ts
index 11f7555197..34fa2f10bd 100644
--- a/src/lib/guardrails/visionBridge.ts
+++ b/src/lib/guardrails/visionBridge.ts
@@ -241,7 +241,14 @@ export class VisionBridgeGuardrail extends BaseGuardrail {
typeof settings.visionBridgeModel === "string" && settings.visionBridgeModel.trim()
? settings.visionBridgeModel.trim()
: undefined;
- const bestModel = await getBestVisionModel({ fixedModel: configuredModel });
+ // Propagate the same resolved credential check used by the adjacent
+ // checkCreds() calls above/below (#8430) — without this, the router
+ // falls back to the real DB-backed hasUsableCredentialsForModel and
+ // ignores an injected `deps.hasUsableCredentials` test/DI override.
+ const bestModel = await getBestVisionModel(
+ { fixedModel: configuredModel },
+ { hasUsableCredentials: checkCreds }
+ );
if (bestModel && bestModel !== model) {
const bestUsable = await checkCreds(bestModel);
// Only block the reroute when we KNOW the target is unusable (false).
diff --git a/tests/integration/chat-pipeline.test.ts b/tests/integration/chat-pipeline.test.ts
index a9568a0271..8144c972c0 100644
--- a/tests/integration/chat-pipeline.test.ts
+++ b/tests/integration/chat-pipeline.test.ts
@@ -689,7 +689,13 @@ test("chat pipeline applies Codex CLI fingerprint to OAuth responses requests",
assert.equal(call.headers.Version, getCodexClientVersion());
assert.equal(call.headers["Openai-Beta"], "responses=experimental");
assert.equal(call.headers["X-Codex-Beta-Features"], "responses_websockets");
- assert.equal(call.headers["User-Agent"], "codex-cli/0.144.1 (Windows 10.0.26200; x64)");
+ // Derive from the same source the code reads (see getCodexClientVersion() two
+ // lines above) instead of pinning the literal — #9323's version bump to 0.146.0
+ // broke this assertion while the rest of the test kept passing.
+ assert.equal(
+ call.headers["User-Agent"],
+ `codex-cli/${getCodexClientVersion()} (Windows 10.0.26200; x64)`
+ );
assert.equal(call.headers["x-codex-window-id"], "conv_codex_fingerprint:0");
assert.ok(call.headers["x-client-request-id"], "expected Codex request id header");
assert.ok(call.headers["x-codex-turn-metadata"], "expected Codex turn metadata header");
diff --git a/tests/unit/8189-classifier-compat-auto-narrow.test.ts b/tests/unit/8189-classifier-compat-auto-narrow.test.ts
index 4f6df06a6c..9070bf5c0b 100644
--- a/tests/unit/8189-classifier-compat-auto-narrow.test.ts
+++ b/tests/unit/8189-classifier-compat-auto-narrow.test.ts
@@ -11,6 +11,12 @@
*
* Fix: in "auto" mode, the SECURITY_MONITOR_MARKER system-prompt text is now a
* necessary condition. `stop_sequences` alone is no longer sufficient.
+ *
+ * Follow-up (#9276): "always" mode previously short-circuited EVERY Claude-format
+ * request unconditionally, regardless of signal shape. That let a normal chat
+ * request through /v1/messages be silently swallowed by an operator's "always"
+ * opt-in. The unconditional `if (mode === "always") return true` branch was
+ * removed — "always" now requires the same SECURITY_MONITOR_MARKER as "auto".
*/
import test from "node:test";
@@ -52,24 +58,37 @@ test("issue #8189: 'auto' mode still short-circuits when the security-monitor ma
);
});
-test("issue #8189: 'always' mode is unaffected — every Claude-format request still short-circuits (operator opted in)", () => {
+test("issue #9276: 'always' mode does NOT short-circuit without the security-monitor marker (narrowed to match 'auto')", () => {
const body = {
system: "You are a helpful assistant that writes CMS page templates.",
stop_sequences: [""],
messages: [{ role: "user", content: "hello" }],
};
+ assert.equal(
+ shouldDefaultAllowClassifier(FORMATS.CLAUDE, body, "always"),
+ false,
+ "mode='always' must NOT short-circuit a request with no security-monitor marker, even " +
+ "with stop_sequences=[''] — #9276 removed the unconditional always-mode return"
+ );
+});
+
+test("issue #9276: 'always' mode still short-circuits when the security-monitor marker is present (operator opted in)", () => {
+ const body = {
+ system:
+ "You are a security monitor for autonomous AI coding agents. Evaluate the following action.",
+ stop_sequences: [],
+ messages: [{ role: "user", content: "Bash rm -rf / " }],
+ };
assert.equal(
shouldDefaultAllowClassifier(FORMATS.CLAUDE, body, "always"),
true,
- "mode='always' must short-circuit every Claude-format request regardless of signal shape"
+ "mode='always' must still short-circuit when the security-monitor marker is present"
);
});
test("issue #8189: 'off' mode (shipped default) never short-circuits", () => {
const body = {
- system: [
- { type: "text", text: "You are a security monitor for autonomous AI coding agents." },
- ],
+ system: [{ type: "text", text: "You are a security monitor for autonomous AI coding agents." }],
stop_sequences: [""],
};
assert.equal(shouldDefaultAllowClassifier(FORMATS.CLAUDE, body, "off"), false);
diff --git a/tests/unit/deepseek-web-tools-execute-2820.test.ts b/tests/unit/deepseek-web-tools-execute-2820.test.ts
index 49c01497d1..77854cebd6 100644
--- a/tests/unit/deepseek-web-tools-execute-2820.test.ts
+++ b/tests/unit/deepseek-web-tools-execute-2820.test.ts
@@ -132,7 +132,9 @@ test("execute (non-stream) parses reply into OpenAI tool_calls", async ()
assert.equal(choice.finish_reason, "tool_calls");
assert.equal(choice.message.tool_calls.length, 1);
assert.equal(choice.message.tool_calls[0].function.name, "get_weather");
- assert.deepEqual(JSON.parse(choice.message.tool_calls[0].function.arguments), { city: "Paris" });
+ assert.deepEqual(JSON.parse(choice.message.tool_calls[0].function.arguments), {
+ city: "Paris",
+ });
assert.ok(
!String(choice.message.content || "").includes(""),
"raw tool block stripped from content"
@@ -142,8 +144,9 @@ test("execute (non-stream) parses reply into OpenAI tool_calls", async ()
}
});
-test("execute (non-stream) parses bare JSON reply into OpenAI tool_calls", async () => {
- const mock = installMock('{"name":"getWeather","arguments":{"city":"Paris"}}');
+test("execute (non-stream) does NOT promote bare JSON reply to tool_calls (#9343)", async () => {
+ const bareJson = '{"name":"getWeather","arguments":{"city":"Paris"}}';
+ const mock = installMock(bareJson);
try {
const executor = new DeepSeekWebExecutor();
const result = await executor.execute({
@@ -156,11 +159,17 @@ test("execute (non-stream) parses bare JSON reply into OpenAI tool_calls", async
assert.ok(result.response.ok);
const json = JSON.parse(await result.response.text());
const choice = json.choices[0];
- assert.equal(choice.finish_reason, "tool_calls");
- assert.equal(choice.message.tool_calls.length, 1);
- assert.equal(choice.message.tool_calls[0].function.name, "get_weather");
- assert.deepEqual(JSON.parse(choice.message.tool_calls[0].function.arguments), { city: "Paris" });
- assert.equal(choice.message.content, null, "bare JSON tool call is stripped from content");
+ assert.equal(
+ choice.finish_reason,
+ "stop",
+ "bare JSON with no envelope must not be promoted to a tool call"
+ );
+ assert.ok(!choice.message.tool_calls, "no tool_calls on a bare JSON reply (#9343)");
+ assert.equal(
+ choice.message.content,
+ bareJson,
+ "bare JSON must be preserved verbatim as content, not stripped or promoted"
+ );
} finally {
mock.restore();
}
diff --git a/tests/unit/guardrails/visionBridge.test.ts b/tests/unit/guardrails/visionBridge.test.ts
index b1b0d9f7ec..9dc0db18c0 100644
--- a/tests/unit/guardrails/visionBridge.test.ts
+++ b/tests/unit/guardrails/visionBridge.test.ts
@@ -428,7 +428,7 @@ test("VB-S07: reroutes base64 image to vision model", async () => {
// ── VB-S03: Fail-open on vision error (via combo mapping path) ────────────
-test("VB-S03: preserves the original image when the vision API fails (#4012)", async () => {
+test("VB-S03/#8430: combo-mapping describe failure replaces the image with an error stub (not preserved)", async () => {
shouldVisionFail = true;
const guardrail = createGuardrail({
deps: {
@@ -464,12 +464,22 @@ test("VB-S03: preserves the original image when the vision API fails (#4012)", a
text?: string;
}>;
- // #4012: a failed describe must NOT replace the image with an "(unavailable)"
- // stub — the original image is preserved so a vision-capable upstream can see it.
+ // SEMANTIC CHANGE (#8430): in the combo describe path (forced here via
+ // checkModelHasComboMapping), when EVERY describe call fails, the upstream is
+ // a confirmed non-vision model that cannot handle raw images — the raw
+ // image_url part is now replaced with an "(unavailable)" error stub instead
+ // of being preserved. The original #4012 preserve-raw behavior still applies
+ // to the reroute path, where the upstream model might still be vision-capable
+ // (see tests/unit/vision-bridge-preserve-on-failure-4012.test.ts, updated by
+ // the same #8430 commit).
const imagePart = content.find((p) => p.type === "image_url");
- assert.ok(imagePart, "original image_url part must be preserved on describe failure");
+ assert.strictEqual(
+ imagePart,
+ undefined,
+ "raw image_url must be replaced when every describe call fails in the combo path"
+ );
const unavailPart = content.find((p) => p.type === "text" && p.text?.includes("unavailable"));
- assert.strictEqual(unavailPart, undefined);
+ assert.ok(unavailPart, "an 'unavailable' error stub should be present when describe fails");
});
test("VB-S03: logs warning when vision API fails (via combo mapping)", async () => {
@@ -771,21 +781,11 @@ test("VB-CRED-02: does NOT reroute to a vision model known to lack credentials",
});
test("isProviderConnectionUsable rejects noauth without api key", async () => {
- const { isProviderConnectionUsable } = await import(
- "../../../src/lib/guardrails/visionBridge.ts"
- );
- assert.strictEqual(
- isProviderConnectionUsable({ authType: "noauth", apiKey: null }),
- false
- );
- assert.strictEqual(
- isProviderConnectionUsable({ authType: "apikey", apiKey: "sk-real" }),
- true
- );
- assert.strictEqual(
- isProviderConnectionUsable({ authType: "oauth", refreshToken: "rt" }),
- true
- );
+ const { isProviderConnectionUsable } =
+ await import("../../../src/lib/guardrails/visionBridge.ts");
+ assert.strictEqual(isProviderConnectionUsable({ authType: "noauth", apiKey: null }), false);
+ assert.strictEqual(isProviderConnectionUsable({ authType: "apikey", apiKey: "sk-real" }), true);
+ assert.strictEqual(isProviderConnectionUsable({ authType: "oauth", refreshToken: "rt" }), true);
assert.strictEqual(
isProviderConnectionUsable({ authType: "apikey", apiKey: "x", testStatus: "banned" }),
false
diff --git a/tests/unit/guardrails/visionBridgeHelpers.callVisionModel.test.ts b/tests/unit/guardrails/visionBridgeHelpers.callVisionModel.test.ts
index 1465e927cb..8f812f5173 100644
--- a/tests/unit/guardrails/visionBridgeHelpers.callVisionModel.test.ts
+++ b/tests/unit/guardrails/visionBridgeHelpers.callVisionModel.test.ts
@@ -6,6 +6,8 @@ import test from "node:test";
import assert from "node:assert/strict";
import dns from "node:dns";
import { callVisionModel, type VisionModelConfig } from "@/lib/guardrails/visionBridgeHelpers";
+import { createProviderConnection } from "@/lib/db/providers";
+import { resetDbInstance } from "@/lib/db/core";
// Store original fetch
const originalFetch = globalThis.fetch;
@@ -30,6 +32,37 @@ process.on("exit", () => {
(dns.promises as { lookup: unknown }).lookup = originalDnsLookup;
});
+// (#8430) getBestVisionModel now validates that a `fixedModel` has a usable
+// connection (via hasUsableCredentialsForModel, which queries the real DB)
+// before returning it — an unreachable fixedModel falls through to
+// auto-selection and, with nothing else configured either, resolves to `null`,
+// which callVisionModel turns into a hard "No vision-capable provider
+// connected" error before it ever reaches the HTTP call these tests mock.
+// The router/credential-selection logic itself is already covered by
+// visionBridgeRouter.test.ts and repro-8430.test.ts; these tests exercise
+// callVisionModel's own request/response handling, so they just need one
+// usable connection seeded per provider they use ("openai/gpt-4o-mini",
+// "anthropic/claude-3-haiku") so getBestVisionModel resolves the requested
+// fixedModel unchanged instead of null.
+test.before(async () => {
+ await createProviderConnection({
+ provider: "openai",
+ authType: "apikey",
+ name: "vision-bridge-test-openai",
+ apiKey: "sk-test-openai",
+ });
+ await createProviderConnection({
+ provider: "anthropic",
+ authType: "apikey",
+ name: "vision-bridge-test-anthropic",
+ apiKey: "sk-test-anthropic",
+ });
+});
+
+test.after(() => {
+ resetDbInstance();
+});
+
test("callVisionModel returns description on success", async () => {
// Mock global fetch
const mockResponse = {
diff --git a/tests/unit/issue-7859-gemini-web-redirect-valid.test.ts b/tests/unit/issue-7859-gemini-web-redirect-valid.test.ts
index 6944e288c7..bae36cd222 100644
--- a/tests/unit/issue-7859-gemini-web-redirect-valid.test.ts
+++ b/tests/unit/issue-7859-gemini-web-redirect-valid.test.ts
@@ -15,9 +15,8 @@
import test from "node:test";
import assert from "node:assert/strict";
-const { validateGeminiWebProvider } = await import(
- "../../src/lib/providers/validation/webProvidersB.ts"
-);
+const { validateGeminiWebProvider } =
+ await import("../../src/lib/providers/validation/webProvidersB.ts");
const originalFetch = globalThis.fetch;
@@ -25,13 +24,38 @@ test.afterEach(() => {
globalThis.fetch = originalFetch;
});
+// #9407 refined this contract: a redirect to accounts.google.com/ServiceLogin is
+// specifically an EXPIRED session (valid:false with re-paste guidance), while other
+// public accounts.google.com paths remain valid-with-warning. The original #7859
+// regression (public redirect must not fall through to the generic catch → invalid)
+// is still covered — by the non-ServiceLogin variant below.
+test("gemini-web validator: 302 redirect to ServiceLogin → expired session (#9407)", async () => {
+ globalThis.fetch = async (url) => {
+ const target = String(url);
+ if (target.includes("gemini.google.com/app")) {
+ return new Response(null, {
+ status: 302,
+ headers: { location: "https://accounts.google.com/ServiceLogin" },
+ });
+ }
+ throw new Error(`unexpected fetch: ${target}`);
+ };
+
+ const result = await validateGeminiWebProvider({
+ apiKey: "__Secure-1PSID=eyJvalidsession",
+ });
+
+ assert.equal(result.valid, false);
+ assert.match(result.error || "", /Session expired/i);
+});
+
test("gemini-web validator: 302 redirect to a PUBLIC host → valid (regression #7859)", async () => {
globalThis.fetch = async (url) => {
const target = String(url);
if (target.includes("gemini.google.com/app")) {
return new Response(null, {
status: 302,
- headers: { location: "https://accounts.google.com/ServiceLogin" },
+ headers: { location: "https://accounts.google.com/signin/continue" },
});
}
throw new Error(`unexpected fetch: ${target}`);
diff --git a/tests/unit/launch-codex-windows-spawn-6312.test.ts b/tests/unit/launch-codex-windows-spawn-6312.test.ts
index a08019e40f..c463f1ef77 100644
--- a/tests/unit/launch-codex-windows-spawn-6312.test.ts
+++ b/tests/unit/launch-codex-windows-spawn-6312.test.ts
@@ -5,16 +5,26 @@ import { resolveCodexSpawn } from "../../bin/cli/commands/launch-codex.mjs";
// Regression guard for #6312: on Windows the `codex` binary is an npm `.cmd`
// shim that `spawn` cannot resolve without a shell (bare "codex" → ENOENT).
-test("resolveCodexSpawn: win32 spawns codex.cmd through a shell", () => {
- const { command, shell } = resolveCodexSpawn("win32");
+// Since #9454 resolveCodexSpawn is async and probes PATH for a native .exe
+// first; the .cmd+shell fallback below is the original #6312 contract (the
+// .exe-preferred path is covered in cli/launch-claude-exe-windows-9454.test.ts).
+test("resolveCodexSpawn: win32 spawns codex.cmd through a shell when no .exe is found", async () => {
+ const { command, shell } = await resolveCodexSpawn("win32", { probe: async () => null });
assert.equal(command, "codex.cmd");
assert.equal(shell, true);
});
-test("resolveCodexSpawn: non-Windows platforms spawn the bare binary without a shell", () => {
+test("resolveCodexSpawn: non-Windows platforms spawn the bare binary without a shell", async () => {
for (const platform of ["linux", "darwin", "freebsd"]) {
- const { command, shell } = resolveCodexSpawn(platform);
+ let probeCalls = 0;
+ const { command, shell } = await resolveCodexSpawn(platform, {
+ probe: async () => {
+ probeCalls++;
+ return null;
+ },
+ });
assert.equal(command, "codex", `${platform} command`);
assert.equal(shell, undefined, `${platform} shell`);
+ assert.equal(probeCalls, 0, `${platform} must not probe PATH off Windows`);
}
});
diff --git a/tests/unit/mitm-cert-install-mode-9442.test.ts b/tests/unit/mitm-cert-install-mode-9442.test.ts
index 9c1fbb8fcd..979dee7d4c 100644
--- a/tests/unit/mitm-cert-install-mode-9442.test.ts
+++ b/tests/unit/mitm-cert-install-mode-9442.test.ts
@@ -31,6 +31,16 @@ import { execFileSync } from "node:child_process";
const originalPlatformDescriptor = Object.getOwnPropertyDescriptor(process, "platform")!;
const originalPath = process.env.PATH;
const originalNoSudo = process.env.OMNIROUTE_NO_SUDO;
+// The global test harness (tests/_setup/isolateDataDir.ts) sets
+// OMNIROUTE_SKIP_SYSTEM_TRUST=1 so no test mutates the host trust store —
+// which makes installCert() return before issuing any command, so this file
+// captures nothing and its install-gap assert can never pass under `npm run
+// test:unit` (it only passed when invoked directly, without the harness).
+// Clearing it here is safe: every spawned command (cp/mkdir/chmod/update-ca-*)
+// is a logging stub on PATH and OMNIROUTE_NO_SUDO=1 strips sudo, so nothing
+// touches the real system. Restored in test.after below.
+const originalSkipSystemTrust = process.env.OMNIROUTE_SKIP_SYSTEM_TRUST;
+delete process.env.OMNIROUTE_SKIP_SYSTEM_TRUST;
const tmpRoot = fs.mkdtempSync(path.join(os.tmpdir(), "omniroute-9442-"));
const binDir = path.join(tmpRoot, "bin");
@@ -68,6 +78,8 @@ test.after(() => {
process.env.PATH = originalPath;
if (originalNoSudo === undefined) delete process.env.OMNIROUTE_NO_SUDO;
else process.env.OMNIROUTE_NO_SUDO = originalNoSudo;
+ if (originalSkipSystemTrust === undefined) delete process.env.OMNIROUTE_SKIP_SYSTEM_TRUST;
+ else process.env.OMNIROUTE_SKIP_SYSTEM_TRUST = originalSkipSystemTrust;
fs.rmSync(tmpRoot, { recursive: true, force: true });
});
@@ -87,7 +99,10 @@ function fakeCertFile(seed: string): string {
const der = crypto.createHash("sha256").update(seed).digest();
const pem =
"-----BEGIN CERTIFICATE-----\n" +
- der.toString("base64").match(/.{1,64}/g)!.join("\n") +
+ der
+ .toString("base64")
+ .match(/.{1,64}/g)!
+ .join("\n") +
"\n-----END CERTIFICATE-----\n";
const certPath = path.join(tmpRoot, `${seed}.crt`);
fs.writeFileSync(certPath, pem);
@@ -156,11 +171,7 @@ test("filesystem proof: cp under umask 0077 creates mode 0600 (why the fix is ne
// the bare `cp` on PATH below is a logging stub from the install tests.
execFileSync("/usr/bin/cp", [src, dst]);
const mode = fs.statSync(dst).mode & 0o777;
- assert.equal(
- mode,
- 0o600,
- "cp under umask 0077 must produce 0600 — the bug this fix repairs"
- );
+ assert.equal(mode, 0o600, "cp under umask 0077 must produce 0600 — the bug this fix repairs");
} finally {
process.umask(oldUmask);
}
diff --git a/tests/unit/provider-validation-specialty.test.ts b/tests/unit/provider-validation-specialty.test.ts
index a9317bcb38..4cdd871eef 100644
--- a/tests/unit/provider-validation-specialty.test.ts
+++ b/tests/unit/provider-validation-specialty.test.ts
@@ -2415,7 +2415,12 @@ test("claude-web validator: 401 → invalid session cookie", async () => {
__setClaudeTlsFetchOverride(null);
});
-test("claude-web validator: 429 → valid (rate limited means auth passed)", async () => {
+// #9406 inverted this contract: a 429 session shows as UNHEALTHY (valid:false)
+// so the dashboard stops painting rate-limited sessions green. The dedicated
+// repro (tests/unit/repro-9406-claude-web-429-valid.test.ts) owns the full
+// contract incl. Retry-After forwarding; this sibling keeps the validator-level
+// assertion aligned with it.
+test("claude-web validator: 429 → invalid (rate limited session is not healthy, #9406)", async () => {
__setClaudeTlsFetchOverride(async () =>
makeClaudeTlsResponse(429, JSON.stringify({ error: "rate limited" }))
);
@@ -2425,7 +2430,7 @@ test("claude-web validator: 429 → valid (rate limited means auth passed)", asy
apiKey: "sessionKey=sk-ant-sid02-good-key",
});
- assert.equal(result.valid, true);
+ assert.equal(result.valid, false);
__setClaudeTlsFetchOverride(null);
});
diff --git a/tests/unit/ratelimit-reservoir-refresh.test.ts b/tests/unit/ratelimit-reservoir-refresh.test.ts
new file mode 100644
index 0000000000..7d218d31a6
--- /dev/null
+++ b/tests/unit/ratelimit-reservoir-refresh.test.ts
@@ -0,0 +1,132 @@
+/**
+ * TDD regression test — Bottleneck reservoir heartbeat death after updateSettings().
+ *
+ * Bug: Bottleneck 2.19.5 (frozen upstream dependency, no release since 2019) has a
+ * defect in `LocalDatastore#_startHeartbeat()`
+ * (node_modules/bottleneck/lib/LocalDatastore.js:26-58). The guard
+ * `if (this.heartbeat == null && ...)` only (re)creates the periodic
+ * reservoir-refresh `setInterval` the FIRST time it runs. Every later call —
+ * including the one `updateSettings()` itself triggers internally via
+ * `__updateSettings__` — falls into the `else` branch and does
+ * `clearInterval(this.heartbeat)` WITHOUT resetting `this.heartbeat` back to
+ * `null`. Because the stale (now-invalid) reference is left in place, every
+ * future `_startHeartbeat()` call keeps taking the same dead `else` branch:
+ * the periodic reservoir refresh is gone forever after the FIRST manual
+ * `limiter.updateSettings()` call.
+ *
+ * Every limiter created by rateLimitManager.ts starts with a live heartbeat
+ * (the constructor call inside `getLimiter()` always sets
+ * reservoirRefreshInterval/reservoirRefreshAmount — see buildLimiterDefaults()),
+ * so the very first `updateFromHeaders()`/`updateFromResponseBody()`/
+ * `applyRequestQueueSettings()` call against that limiter permanently kills its
+ * refresh. Once the reservoir then hits 0, it never refills again.
+ *
+ * Production symptom: an auto-enrolled apikey connection accumulates its
+ * default 60 requests, the reservoir zeroes, the request queue freezes for
+ * ~120s, the watchdog fires a synthetic 502 (RATE_LIMIT_QUEUE_WEDGED), the
+ * connection cools down and is excluded from weighted combo pools — turning a
+ * configured 70/30 split into ~50/50 (see
+ * tests/integration/combo-matrix/weighted.test.ts, the E2E proof for this
+ * same bug).
+ *
+ * This test drives the exact same sequence directly against
+ * open-sse/services/rateLimitManager.ts's public surface, without any DB or
+ * HTTP layer, to isolate the Bottleneck heartbeat defect on its own.
+ */
+import test from "node:test";
+import assert from "node:assert/strict";
+
+const rateLimitManager = await import("../../open-sse/services/rateLimitManager.ts");
+
+function wait(ms: number): Promise {
+ return new Promise((resolve) => setTimeout(resolve, ms));
+}
+
+const PROVIDER = "reservoir-refresh-test-provider";
+const CONNECTION_ID = "reservoir-refresh-test-conn";
+
+test.after(async () => {
+ await rateLimitManager.__resetRateLimitManagerForTests();
+});
+
+test("reservoir keeps refreshing after updateSettings() touches an already-heartbeating limiter", async () => {
+ rateLimitManager.enableRateLimitProtection(CONNECTION_ID);
+
+ // 1. First call creates the limiter. Bottleneck's LocalDatastore constructor
+ // starts heartbeat #1 (alive) because the default reservoirRefreshInterval/
+ // reservoirRefreshAmount are always set (buildLimiterDefaults()).
+ const warmup = await rateLimitManager.withRateLimit(
+ PROVIDER,
+ CONNECTION_ID,
+ null,
+ async () => "warmup"
+ );
+ assert.equal(warmup, "warmup");
+
+ // 2. Header-learned update — the first *manual* updateSettings() call on this
+ // limiter. remaining(2) < limit(6000)*0.1 takes updateFromHeaders' "throttle"
+ // branch, which sets a real reservoir=2 with a 1s refresh window (limit=6000
+ // keeps minTime at 0 so it doesn't pace the slot consumption below). This is
+ // exactly the call that kills the heartbeat under the unfixed Bottleneck bug.
+ rateLimitManager.updateFromHeaders(
+ PROVIDER,
+ CONNECTION_ID,
+ {
+ "x-ratelimit-limit-requests": "6000",
+ "x-ratelimit-remaining-requests": "2",
+ "x-ratelimit-reset-requests": "1s",
+ },
+ 200
+ );
+
+ // updateFromHeaders applies the limiter update asynchronously (fire-and-forget
+ // — see trackAsyncOperation in rateLimitManager.ts). Poll the test-only state
+ // hook until the reservoir actually lands at 2 instead of assuming a fixed
+ // number of event-loop ticks: Bottleneck's own updateSettings() goes through
+ // at least one real setTimeout(0) (yieldLoop) before storeOptions reflects the
+ // new value.
+ const pollDeadline = Date.now() + 2000;
+ let state = await rateLimitManager.__getLimiterStateForTests(PROVIDER, CONNECTION_ID, null);
+ while (state?.reservoir !== 2 && Date.now() < pollDeadline) {
+ await wait(10);
+ state = await rateLimitManager.__getLimiterStateForTests(PROVIDER, CONNECTION_ID, null);
+ }
+ assert.equal(state?.reservoir, 2, "reservoir must land at 2 before the slots below are consumed");
+
+ // 3. Consume both reservoir slots.
+ assert.equal(
+ await rateLimitManager.withRateLimit(PROVIDER, CONNECTION_ID, null, async () => "slot-1"),
+ "slot-1"
+ );
+ assert.equal(
+ await rateLimitManager.withRateLimit(PROVIDER, CONNECTION_ID, null, async () => "slot-2"),
+ "slot-2"
+ );
+
+ // 4. Reservoir is now 0. A healthy Bottleneck heartbeat refills it ~1s later
+ // from the reservoirRefreshInterval/reservoirRefreshAmount configured above.
+ // Race a 3rd request against a 5s timer: if the heartbeat died (unfixed bug),
+ // the request stays QUEUED forever and the timer wins instead.
+ const RACE_TIMEOUT_MS = 5000;
+ let timeoutHandle: ReturnType | undefined;
+ const timeout = new Promise<"timed-out">((resolve) => {
+ timeoutHandle = setTimeout(() => resolve("timed-out"), RACE_TIMEOUT_MS);
+ });
+ const request = rateLimitManager.withRateLimit(
+ PROVIDER,
+ CONNECTION_ID,
+ null,
+ async () => "slot-3" as const
+ );
+
+ const result = await Promise.race([request, timeout]);
+ if (timeoutHandle) clearTimeout(timeoutHandle);
+
+ assert.equal(
+ result,
+ "slot-3",
+ 'reservoir must refresh ~1s after being exhausted; "timed-out" means the Bottleneck ' +
+ "heartbeat died after updateSettings() and the reservoir never refilled " +
+ "(node_modules/bottleneck/lib/LocalDatastore.js _startHeartbeat clearInterval-without-null bug)"
+ );
+});