diff --git a/.env.example b/.env.example index 7d92b7cad5..a2156902a6 100644 --- a/.env.example +++ b/.env.example @@ -65,6 +65,12 @@ INITIAL_PASSWORD=CHANGEME # OMNIROUTE_RELEASE_REF=origin/main # OMNIROUTE_ALLOW_CANARY_BUILD=1 +# Build-phase signal (#10060). Set to 1 by scripts/build/build-next-isolated.mjs and +# inherited by every spawned build worker so the DB layer returns a no-op stub instead +# of loading the native better-sqlite3 addon (which aborts the worker on exit). +# Never set this for the running server. Used by: src/lib/buildPhase.ts, src/lib/db/core.ts +# OMNIROUTE_BUILDING=1 + # Encryption key for SQLite database encryption at rest. # Used by: src/lib/db/encryption.ts — encrypts the entire SQLite database. # Generate: openssl rand -hex 32 | Leave empty to disable DB encryption. diff --git a/config/quality/dependency-allowlist.json b/config/quality/dependency-allowlist.json index c4476f95d1..92e6ef7e8d 100644 --- a/config/quality/dependency-allowlist.json +++ b/config/quality/dependency-allowlist.json @@ -1,5 +1,9 @@ { "_comment": "Allowlist anti-slopsquatting (check-deps.mjs). Toda dep nova exige adicao EXPLICITA aqui apos verificar que e legitima.", + "_justifications": { + "@testing-library/dom": "Peer dep obrigatoria de @testing-library/react v16 (adicionada no PR #11224); Refs #9985.", + "@testing-library/user-event": "Utilitario oficial do ecossistema testing-library para testes de UI (adicionada no PR #11224); Refs #9985." + }, "allowed": [ "@atjsh/llmlingua-2", "@aws-sdk/client-bedrock-runtime", @@ -20,8 +24,10 @@ "@stryker-mutator/tap-runner", "@swc/helpers", "@tailwindcss/postcss", + "@testing-library/dom", "@testing-library/jest-dom", "@testing-library/react", + "@testing-library/user-event", "@toon-format/toon", "@types/better-sqlite3", "@types/bun", diff --git a/docs/reference/CLI-TOOLS.md b/docs/reference/CLI-TOOLS.md index c32b433fbd..79d4a7d5e3 100644 --- a/docs/reference/CLI-TOOLS.md +++ b/docs/reference/CLI-TOOLS.md @@ -1,19 +1,19 @@ --- title: "CLI Tools — OmniRoute" version: 3.8.50 -lastUpdated: 2026-08-18 +lastUpdated: 2026-08-23 --- # CLI Tools — OmniRoute -Last updated: 2026-08-18 +Last updated: 2026-08-23 OmniRoute integrates with three categories of CLI tools spread across three dedicated dashboard pages: | Page | Route | Concept | Count | | -------------- | ----------------------- | ------------------------------------------------------------------------- | ------------ | | **CLI Code's** | `/dashboard/cli-code` | Coding tools you point at OmniRoute (Client → CLI → OmniRoute → Provider) | 26 | -| **CLI Agents** | `/dashboard/cli-agents` | Autonomous agents you point at OmniRoute (same flow, broader scope) | 8 | +| **CLI Agents** | `/dashboard/cli-agents` | Autonomous agents you point at OmniRoute (same flow, broader scope) | 9 | | **ACP Agents** | `/dashboard/acp-agents` | CLIs that OmniRoute spawns as backend via stdio/ACP (reverse flow) | see registry | Legacy routes redirect via 308: `/dashboard/cli-tools` → `/dashboard/cli-code`, `/dashboard/agents` → `/dashboard/acp-agents`. diff --git a/docs/reference/ENVIRONMENT.md b/docs/reference/ENVIRONMENT.md index 2681ba5478..e9ef0df9c2 100644 --- a/docs/reference/ENVIRONMENT.md +++ b/docs/reference/ENVIRONMENT.md @@ -88,6 +88,7 @@ OmniRoute uses **SQLite** (via `better-sqlite3`) for all persistence. These vari | `OMNIROUTE_RELEASE_REF` | `origin/main` | `scripts/build/buildProvenance.ts` | Ref the pack-artifact provenance gate checks the build SHA against (#10427). | | `OMNIROUTE_ALLOW_CANARY_BUILD` | _(unset)_ | `scripts/build/buildProvenance.ts` | Set to `1` to allow packing a build whose SHA is not on the release line, recording it as a deliberate canary instead of failing the gate (#10427). | | `OMNIROUTE_SMOKE_API_KEY` | _(unset)_ | `scripts/ops/deploy-canary.mjs` | API key for the canary-deploy smoke probe, sent as `Authorization: Bearer` on `/v1/chat/completions`. Only used by the deploy script (#10429), never by the server. Not related to the `OMNIROUTE_SMOKE_*` variables of the opt-in CLI smoke harness (`RUN_CLI_SMOKE=1`, `OMNIROUTE_SMOKE_BASE_URL/MODEL/API_KEY_ENV/TARGETS/TIMEOUT_MS` in `tests/integration/upstream-cli-smoke.int.test.ts`) — see [CLI Integrations → Real smoke sweep](../guides/CLI-INTEGRATIONS.md). | +| `OMNIROUTE_BUILDING` | _(unset)_ | `src/lib/buildPhase.ts` | Build-phase signal (#10060): set to `1` by `scripts/build/build-next-isolated.mjs` and inherited by every spawned build worker so the DB layer returns a no-op stub instead of loading the native better-sqlite3 addon (which aborts the worker on exit). Never set for the running server. | | `OMNIROUTE_DATA_DIR` | _(unset)_ | `open-sse/executors/promptql/threadSticky.ts` | **Fallback alias** for `DATA_DIR`, checked only when `DATA_DIR` is unset. Used to locate the PromptQL executor's on-disk thread-sticky session cache (`/promptql-thread-sessions.json`); if neither var is set, the cache stays in-memory only (not persisted across restarts). | | `STORAGE_ENCRYPTION_KEY` | _(empty = disabled)_ | `src/lib/db/encryption.ts` | AES key for full SQLite database encryption at rest. Generate with `openssl rand -hex 32`. | | `STORAGE_ENCRYPTION_KEY_VERSION` | `v1` | `scripts/build/bootstrap-env.mjs`, `electron/main.js` | Version label for the encryption key. Increment when performing key rotation to support decryption of old backups. | diff --git a/open-sse/handlers/chatCore.ts b/open-sse/handlers/chatCore.ts index 10e6c32ae6..07e3a25857 100644 --- a/open-sse/handlers/chatCore.ts +++ b/open-sse/handlers/chatCore.ts @@ -1218,7 +1218,12 @@ export async function handleChatCore({ credentials?.providerSpecificData?.preserveEncryptedReasoning === true, onIncompatibleReasoning: resolveIncompatibleReasoningAction({ reasoningTransportFallback, - isComboStep: Boolean(comboStepId || comboExecutionKey), + // #11178 regressed combo steps whose combo record carries no explicit + // stepId/executionKey (plain model-list combos): their explicit + // `reasoningTransportFallback: "skip"` config was silently degraded to + // "drop". `isCombo` is the combo marker; step ids are optional + // finer-grained metadata that plain combos never set. + isComboStep: Boolean(isCombo) || Boolean(comboStepId || comboExecutionKey), headers: clientRawRequest?.headers ?? null, }), } diff --git a/src/app/(dashboard)/dashboard/providers/[id]/components/modals/EditConnectionModal.tsx b/src/app/(dashboard)/dashboard/providers/[id]/components/modals/EditConnectionModal.tsx index e2eb3288e2..ed4649d89e 100644 --- a/src/app/(dashboard)/dashboard/providers/[id]/components/modals/EditConnectionModal.tsx +++ b/src/app/(dashboard)/dashboard/providers/[id]/components/modals/EditConnectionModal.tsx @@ -290,6 +290,11 @@ export default function EditConnectionModal({ connection.providerSpecificData?.quotaPerUnit != null ? String(connection.providerSpecificData.quotaPerUnit) : ""; + // Modal-open form initialization from the loaded connection (sync with an + // external system on `isOpen`); remounting the 30+ field form per + // connection id is a behavior-risking restructure out of scope here + // (#11251 follow-up, #9985). + // eslint-disable-next-line react-hooks/set-state-in-effect setFormData({ name: connection.name || "", priority: connection.priority || 1, diff --git a/src/i18n/messages/en.json b/src/i18n/messages/en.json index e45ebbd04f..f3cab6d48c 100644 --- a/src/i18n/messages/en.json +++ b/src/i18n/messages/en.json @@ -1221,12 +1221,6 @@ "consoleLogsSubtitle": "Console output", "logsActivitySubtitle": "User activity log", "healthSubtitle": "System health check", - "healthVerdictReady": "OmniRoute is ready", - "healthVerdictActionRequired": "Action required to restore full operation", - "healthVerdictCoolingDown": "Cooling down after recent changes", - "advancedDiagnosticsTitle": "Advanced diagnostics", - "hide": "Hide", - "show": "Show", "costsPricingSubtitle": "Per-model pricing rules", "costsBudgetSubtitle": "Budget limits", "costsQuotaShareSubtitle": "Share provider quotas across keys", @@ -2928,6 +2922,7 @@ "interpreter": "Open Interpreter autonomous coding agent CLI", "omp": "Oh My Pi terminal coding agent", "letta": "Letta CLI agent with persistent memory and tool use", + "prime-agent": "Prime Agent — self-improving RLM coding harness with OpenAI-compatible provider support", "warp": "Warp AI terminal with custom provider support", "agent-deck": "Agent Deck multi-agent orchestrator" }, @@ -4637,6 +4632,13 @@ "retry": "Retry", "allOperational": "All systems operational", "issuesDetected": "System issues detected", + "healthVerdictReady": "OmniRoute is ready", + "healthVerdictActionRequired": "Action required to restore full operation", + "healthVerdictCoolingDown": "Cooling down after recent changes", + "healthSubtitle": "System health check", + "advancedDiagnosticsTitle": "Advanced diagnostics", + "hide": "Hide", + "show": "Show", "updatedAt": "Updated {time}", "latency": "Latency", "latencyP50": "p50", diff --git a/src/i18n/messages/pt-BR.json b/src/i18n/messages/pt-BR.json index 7fbe30f278..1c5beedc69 100644 --- a/src/i18n/messages/pt-BR.json +++ b/src/i18n/messages/pt-BR.json @@ -970,6 +970,13 @@ "batchTimelineCancelled": "Cancelado", "batchTokenUsage": "Uso de Token", "batchMetadata": "Metadados", + "batchHeaderSubtitle": "Execute muitas requisições como um único job", + "batchStep1": "1 · Enviar JSONL", + "batchStep1Desc": "Adicionar requisições", + "batchStep2": "2 · Criar lote", + "batchStep2Desc": "Executar job", + "batchStep3": "3 · Obter resultados", + "batchStep3Desc": "Baixar saída", "batchFileContents": "Conteúdo do Arquivo", "batchFileUsedByCount": "Usado por {count, plural, one {# lote} other {# lotes}}", "batchFilePreview": "Prévia", @@ -2905,6 +2912,7 @@ "interpreter": "CLI do agente de codificação autônomo Open Interpreter", "omp": "Agente de codificação de terminal Oh My Pi", "letta": "Agente CLI Letta com memória persistente e uso de ferramentas", + "prime-agent": "Prime Agent — harness de codificação RLM autoevolutivo com suporte a API compatível com OpenAI", "warp": "Terminal de IA Warp com suporte a provedor personalizado", "agent-deck": "Orquestrador multi-agente Agent Deck" }, @@ -3831,6 +3839,9 @@ }, "endpoint": { "title": "Endpoint da API", + "subtitle": "Use o endpoint compatível com OpenAI na maioria dos SDKs e ferramentas.", + "testEndpoint": "Testar endpoint →", + "advancedProtocols": "Protocolos avançados", "available": "Endpoints Disponíveis", "cloudProxy": "Proxy na Nuvem", "disableConfirm": "Tem certeza que deseja desativar o proxy na nuvem?", @@ -4611,6 +4622,13 @@ "retry": "Tentar Novamente", "allOperational": "Todos os sistemas operacionais", "issuesDetected": "Problemas detectados no sistema", + "healthVerdictReady": "O OmniRoute está pronto", + "healthVerdictActionRequired": "Ação necessária para restaurar a operação plena", + "healthVerdictCoolingDown": "Em resfriamento após mudanças recentes", + "healthSubtitle": "Verificação de saúde do sistema", + "advancedDiagnosticsTitle": "Diagnósticos avançados", + "hide": "Ocultar", + "show": "Mostrar", "updatedAt": "Atualizado {time}", "latency": "Latência", "latencyP50": "p50", @@ -12035,6 +12053,7 @@ "acp": { "title": "ACP Agents", "phrase": "CLIs que o OmniRoute spawna como backend de execução (fluxo reverso)", + "warning": "A maioria dos usuários pode ignorar isto — use apenas quando uma integração exigir.", "flow": "Cliente → OmniRoute → spawn CLI (stdio/ACP) → resposta", "seeOther": "Ver →" } @@ -13342,6 +13361,13 @@ }, "resilienceConnections": { "title": "Resiliência de Conexão", + "reassuranceTitle": "Suas conexões se recuperam automaticamente", + "reassuranceDetail": "Normalmente nenhuma ação é necessária. O OmniRoute dá uma pausa temporária em uma conexão após falhas e depois a tenta novamente com segurança.", + "plainStates": { + "healthy": "Requisições podem ser enviadas", + "coolingDown": "Tentando novamente em breve", + "lockedOut": "Precisa da sua atenção" + }, "table": { "status": "Status", "provider": "Provedor", diff --git a/src/i18n/messages/vi.json b/src/i18n/messages/vi.json index 787e6dd7d9..9d5ed6c524 100644 --- a/src/i18n/messages/vi.json +++ b/src/i18n/messages/vi.json @@ -1300,13 +1300,7 @@ "open": "mở", "close": "đóng" }, - "noResults": "Không có kết quả", - "healthVerdictReady": "OmniRoute đã sẵn sàng", - "healthVerdictActionRequired": "Cần hành động để khôi phục hoạt động đầy đủ", - "healthVerdictCoolingDown": "Đang nguội sau các thay đổi gần đây", - "advancedDiagnosticsTitle": "Chẩn đoán nâng cao", - "hide": "Ẩn", - "show": "Hiện" + "noResults": "Không có kết quả" }, "webhooks": { "title": "Webhook", @@ -2918,6 +2912,7 @@ "interpreter": "Tác nhân lập trình tự trị Open Interpreter CLI", "omp": "Tác nhân lập trình Oh My Pi trên terminal", "letta": "Tác nhân Letta CLI có bộ nhớ lâu dài và khả năng dùng công cụ", + "prime-agent": "Prime Agent — bộ khung lập trình RLM tự cải tiến hỗ trợ API tương thích OpenAI", "warp": "Terminal Warp AI hỗ trợ nhà cung cấp tùy chỉnh", "agent-deck": "Trình điều phối đa tác nhân Agent Deck" }, @@ -4627,6 +4622,13 @@ "retry": "Thử lại", "allOperational": "Tất cả hệ thống đang hoạt động bình thường", "issuesDetected": "Phát hiện sự cố hệ thống", + "healthVerdictReady": "OmniRoute đã sẵn sàng", + "healthVerdictActionRequired": "Cần hành động để khôi phục hoạt động đầy đủ", + "healthVerdictCoolingDown": "Đang nguội sau các thay đổi gần đây", + "healthSubtitle": "Kiểm tra tình trạng hệ thống", + "advancedDiagnosticsTitle": "Chẩn đoán nâng cao", + "hide": "Ẩn", + "show": "Hiện", "updatedAt": "Đã cập nhật {time}", "latency": "Độ trễ", "latencyP50": "p50", diff --git a/src/shared/schemas/cliCatalog.ts b/src/shared/schemas/cliCatalog.ts index 27ab19e3c9..bcfefe1700 100644 --- a/src/shared/schemas/cliCatalog.ts +++ b/src/shared/schemas/cliCatalog.ts @@ -67,4 +67,5 @@ export const EXPECTED_CODE_COUNT = 21; // +2 (#6318): "omp" (Oh My Pi) and "letta" (Letta CLI) added as agent entries. // Note: #6318 originally also shipped duplicate "pi"/"jcode"/"codewhale" entries — // those tools were already delivered by a separate PR, so only omp+letta landed here. -export const EXPECTED_AGENT_COUNT = 8; +// +1 (#11166): "prime-agent" (PrimeIntellect-ai/prime-agent) added as an agent entry. +export const EXPECTED_AGENT_COUNT = 9; diff --git a/stryker.conf.json b/stryker.conf.json index f9317d95a0..f039eeaca8 100644 --- a/stryker.conf.json +++ b/stryker.conf.json @@ -89,7 +89,6 @@ "tests/unit/auth-terminal-status.test.ts", "tests/unit/authz/discovery-routes-local-only.test.ts", "tests/unit/authz/oauth-autoimport-local-only.test.ts", - "tests/unit/quota-exhaustion-cutoff-opencode.test.ts", "tests/unit/authz/route-guard-local-prefix.test.ts", "tests/unit/authz/route-guard-skills-collect.test.ts", "tests/unit/authz/route-guard-version-get-exemption.test.ts", @@ -308,6 +307,7 @@ "tests/unit/public-client-ids-3493.test.ts", "tests/unit/publicCreds.test.ts", "tests/unit/qoder-oauth-config.test.ts", + "tests/unit/quota-exhaustion-cutoff-opencode.test.ts", "tests/unit/quota-groups-route.test.ts", "tests/unit/quota-key-models-route.test.ts", "tests/unit/quota-policy-generalization.test.ts", diff --git a/tests/integration/qdrant-routes.test.ts b/tests/integration/qdrant-routes.test.ts index 252c6e505f..34444154d5 100644 --- a/tests/integration/qdrant-routes.test.ts +++ b/tests/integration/qdrant-routes.test.ts @@ -39,6 +39,10 @@ const qdrantEmbeddingModelsRoute = // ── Helpers ── +// Route handlers are typed against NextRequest; the management-session helper +// returns the Fetch API Request, which is structurally sufficient at runtime. +const asNextRequest = (req: Request) => req as unknown as import("next/server").NextRequest; + async function resetStorage() { core.resetDbInstance(); fs.rmSync(TEST_DATA_DIR, { recursive: true, force: true }); @@ -91,7 +95,7 @@ test.after(async () => { test("GET /api/settings/qdrant — returns settings with masked API key shape", async () => { const req = await makeAuthRequest("GET", "http://localhost/api/settings/qdrant"); - const res = await qdrantSettingsRoute.GET(req as any); + const res = await qdrantSettingsRoute.GET(asNextRequest(req)); assert.strictEqual(res.status, 200); const body = await res.json(); @@ -110,7 +114,7 @@ test("GET /api/settings/qdrant — returns settings with masked API key shape", test("GET /api/settings/qdrant — 401 without auth", async () => { await setRequireLogin(true); const req = makeUnauthRequest("GET", "http://localhost/api/settings/qdrant"); - const res = await qdrantSettingsRoute.GET(req as any); + const res = await qdrantSettingsRoute.GET(asNextRequest(req)); assert.strictEqual(res.status, 401); await setRequireLogin(false); }); @@ -126,7 +130,7 @@ test("PUT /api/settings/qdrant — updates settings and returns new masked shape embeddingModel: "openai/text-embedding-3-small", }); - const res = await qdrantSettingsRoute.PUT(req as any); + const res = await qdrantSettingsRoute.PUT(asNextRequest(req)); assert.strictEqual(res.status, 200); const body = await res.json(); @@ -148,7 +152,7 @@ test("PUT enabled=true also activates Qdrant as the engine (memoryVectorStore=qd host: "qdrant-server", collection: "c", }); - const res = await qdrantSettingsRoute.PUT(req as any); + const res = await qdrantSettingsRoute.PUT(asNextRequest(req)); assert.strictEqual(res.status, 200); const s = (await localDb.getSettings()) as Record; @@ -161,16 +165,20 @@ test("PUT enabled=true also activates Qdrant as the engine (memoryVectorStore=qd test("PUT enabled=false resets the engine back to auto (sqlite-vec)", async () => { await qdrantSettingsRoute.PUT( - (await makeAuthRequest("PUT", "http://localhost/api/settings/qdrant", { - enabled: true, - host: "qdrant-server", - collection: "c", - })) as any + asNextRequest( + await makeAuthRequest("PUT", "http://localhost/api/settings/qdrant", { + enabled: true, + host: "qdrant-server", + collection: "c", + }) + ) ); await qdrantSettingsRoute.PUT( - (await makeAuthRequest("PUT", "http://localhost/api/settings/qdrant", { - enabled: false, - })) as any + asNextRequest( + await makeAuthRequest("PUT", "http://localhost/api/settings/qdrant", { + enabled: false, + }) + ) ); const s = (await localDb.getSettings()) as Record; @@ -185,9 +193,11 @@ test("PUT without the enabled field must not change memoryVectorStore", async () // User already on qdrant; editing only the collection must not reset the engine. await localDb.updateSettings({ memoryVectorStore: "qdrant", qdrantEnabled: true }); await qdrantSettingsRoute.PUT( - (await makeAuthRequest("PUT", "http://localhost/api/settings/qdrant", { - collection: "renamed", - })) as any + asNextRequest( + await makeAuthRequest("PUT", "http://localhost/api/settings/qdrant", { + collection: "renamed", + }) + ) ); const s = (await localDb.getSettings()) as Record; @@ -211,11 +221,13 @@ test("PUT enabled=true invalidates the memory-settings cache (retrieval sees qdr ); const res = await qdrantSettingsRoute.PUT( - (await makeAuthRequest("PUT", "http://localhost/api/settings/qdrant", { - enabled: true, - host: "qdrant-server", - collection: "c", - })) as any + asNextRequest( + await makeAuthRequest("PUT", "http://localhost/api/settings/qdrant", { + enabled: true, + host: "qdrant-server", + collection: "c", + }) + ) ); assert.strictEqual(res.status, 200); @@ -234,7 +246,7 @@ test("PUT /api/settings/qdrant — 400 invalid settings (invalid port type in st port: "not-a-number", }); - const res = await qdrantSettingsRoute.PUT(req as any); + const res = await qdrantSettingsRoute.PUT(asNextRequest(req)); assert.strictEqual(res.status, 400); const body = await res.json(); assert.ok(body.message || body.error, "should return error"); @@ -243,7 +255,7 @@ test("PUT /api/settings/qdrant — 400 invalid settings (invalid port type in st test("PUT /api/settings/qdrant — 401 without auth", async () => { await setRequireLogin(true); const req = makeUnauthRequest("PUT", "http://localhost/api/settings/qdrant", { enabled: true }); - const res = await qdrantSettingsRoute.PUT(req as any); + const res = await qdrantSettingsRoute.PUT(asNextRequest(req)); assert.strictEqual(res.status, 401); await setRequireLogin(false); }); @@ -257,7 +269,7 @@ test("GET /api/settings/qdrant/health — returns health result shape (qdrant di headers: Object.fromEntries(headers.entries()), }); - const res = await qdrantHealthRoute.GET(req as any); + const res = await qdrantHealthRoute.GET(asNextRequest(req)); assert.strictEqual(res.status, 200); const body = await res.json(); @@ -292,7 +304,7 @@ test("GET /api/settings/qdrant/health — reports named collection vector metada try { const req = await makeAuthRequest("GET", "http://localhost/api/settings/qdrant/health"); - const res = await qdrantHealthRoute.GET(req as any); + const res = await qdrantHealthRoute.GET(asNextRequest(req)); const body = await res.json(); assert.strictEqual(res.status, 200); @@ -309,7 +321,7 @@ test("GET /api/settings/qdrant/health — reports named collection vector metada test("GET /api/settings/qdrant/health — 401 without auth", async () => { await setRequireLogin(true); const req = makeUnauthRequest("GET", "http://localhost/api/settings/qdrant/health"); - const res = await qdrantHealthRoute.GET(req as any); + const res = await qdrantHealthRoute.GET(asNextRequest(req)); assert.strictEqual(res.status, 401); await setRequireLogin(false); }); @@ -322,7 +334,7 @@ test("POST /api/settings/qdrant/search — returns ok + results array", async () topK: 5, }); - const res = await qdrantSearchRoute.POST(req as any); + const res = await qdrantSearchRoute.POST(asNextRequest(req)); assert.strictEqual(res.status, 200); const body = await res.json(); @@ -336,7 +348,7 @@ test("POST /api/settings/qdrant/search — 400 invalid body (empty query)", asyn topK: 5, }); - const res = await qdrantSearchRoute.POST(req as any); + const res = await qdrantSearchRoute.POST(asNextRequest(req)); assert.strictEqual(res.status, 400); const body = await res.json(); assert.ok(body.message || body.error, "should return error"); @@ -346,7 +358,7 @@ test("POST /api/settings/qdrant/search — 400 invalid body (empty query)", asyn test("POST /api/settings/qdrant/cleanup — returns ok + deletedCount + retentionDays", async () => { const req = await makeAuthRequest("POST", "http://localhost/api/settings/qdrant/cleanup"); - const res = await qdrantCleanupRoute.POST(req as any); + const res = await qdrantCleanupRoute.POST(asNextRequest(req)); assert.strictEqual(res.status, 200); const body = await res.json(); @@ -365,7 +377,7 @@ test("GET /api/settings/qdrant/embedding-models — returns models array", async headers: Object.fromEntries(headers.entries()), }); - const res = await qdrantEmbeddingModelsRoute.GET(req as any); + const res = await qdrantEmbeddingModelsRoute.GET(asNextRequest(req)); // 200 expected; verify shape assert.strictEqual(res.status, 200); const body = await res.json(); @@ -387,7 +399,7 @@ test("GET /api/settings/qdrant/embedding-models — lists only configured provid headers: Object.fromEntries(headers.entries()), }); - const res = await qdrantEmbeddingModelsRoute.GET(req as any); + const res = await qdrantEmbeddingModelsRoute.GET(asNextRequest(req)); assert.strictEqual(res.status, 200); const body = await res.json(); assert.ok(body.models.length > 0, "should list models for configured provider"); @@ -400,7 +412,7 @@ test("GET /api/settings/qdrant/embedding-models — lists only configured provid test("GET /api/settings/qdrant/embedding-models — 401 without auth", async () => { await setRequireLogin(true); const req = makeUnauthRequest("GET", "http://localhost/api/settings/qdrant/embedding-models"); - const res = await qdrantEmbeddingModelsRoute.GET(req as any); + const res = await qdrantEmbeddingModelsRoute.GET(asNextRequest(req)); assert.strictEqual(res.status, 401); await setRequireLogin(false); }); @@ -416,7 +428,7 @@ test("Qdrant routes — error response has no stack trace in body", async () => body: "not-valid-json{{{", }); - const res = await qdrantSettingsRoute.PUT(req as any); + const res = await qdrantSettingsRoute.PUT(asNextRequest(req)); assert.ok(res.status >= 400, "should return error status"); const body = await res.json(); diff --git a/tests/unit/8134-github-t5-fallback-filter.test.ts b/tests/unit/8134-github-t5-fallback-filter.test.ts index 6de8f13416..7f54ce4e34 100644 --- a/tests/unit/8134-github-t5-fallback-filter.test.ts +++ b/tests/unit/8134-github-t5-fallback-filter.test.ts @@ -6,8 +6,8 @@ import { getRegistryEntry } from "../../open-sse/config/providerRegistry.ts"; const { getNextFamilyFallback } = await import("../../open-sse/services/modelFamilyFallback.ts"); // Regression for #8134 — GitHub Copilot ("github", alias "gh") T5 family fallback -// returned "claude-opus-4-6" verbatim even though the github registry catalog -// (Opus 4.8 / 4.8-fast / 4.7 / 4.5) has NO 4.6 tier under any dot/hyphen +// returned "claude-opus-4-6" verbatim even though the github registry catalog at +// the time (Opus 4.8 / 4.8-fast / 4.7 / 4.5) had NO 4.6 tier under any dot/hyphen // notation. getNextFamilyFallback() resolved `supportedIds` from the provider's // registry but only used it to try notation variants of a candidate, never to // filter out a candidate that is provably absent from the catalog — so the @@ -18,35 +18,46 @@ const { getNextFamilyFallback } = await import("../../open-sse/services/modelFam // skips (continue) any family candidate that has no match in supportedIds // under ANY notation (hyphen, dot, or a dated-snapshot id with the date // suffix stripped) instead of returning it unfiltered. +// +// Fixture note: #10952 later added claude-opus-4.6 to the github registry, so +// the provably-absent tier used by the fixture moved to claude-opus-4-6-thinking +// (the ladder's first candidate after 4.6 — still absent from the catalog). -test("#8134: github claude-opus-4.8 fallback chain never returns an unsupported tier (claude-opus-4-6)", () => { +test("#8134: github claude-opus fallback chain never returns an unsupported tier (claude-opus-4-6-thinking)", () => { const github = getRegistryEntry("github"); assert.ok(github, "expected the github registry entry to resolve"); const githubIds = new Set(github.models.map((m) => m.id)); + // Fixture assumption: #10952 added claude-opus-4.6 to the github registry, so + // the original absent-tier role moved to the 4.6-thinking variant, which the + // catalog still does NOT carry under any notation. assert.ok( - !githubIds.has("claude-opus-4-6") && !githubIds.has("claude-opus-4.6"), - "fixture assumption broken: github registry now has a 4.6 tier" + !githubIds.has("claude-opus-4-6-thinking") && !githubIds.has("claude-opus-4.6-thinking"), + "fixture assumption broken: github registry now has a 4.6-thinking tier" ); + // Ladder reality: 4.8 -> 4.7 -> 4.6 -> [4-6-thinking (absent), 4-5-20251101, + // sonnet-5]. The absent 4-6-thinking must be SKIPPED — the third hop resolves + // to the dated 4.5 snapshot's undated catalog entry, never to 4-6-thinking. const tried = new Set(["github/claude-opus-4.8"]); - const first = getNextFamilyFallback("github/claude-opus-4.8", tried); - assert.ok(first, "expected a first fallback candidate"); - const firstBareId = first.replace(/^github\//, ""); - assert.ok( - githubIds.has(firstBareId), - `first fallback "${first}" is not in github's registered model catalog: ${[...githubIds].join(", ")}` - ); - - tried.add(first); - const second = getNextFamilyFallback(first, tried); - assert.ok(second, "expected a second fallback candidate (family must not be silently exhausted)"); - const secondBareId = second.replace(/^github\//, ""); - assert.ok( - githubIds.has(secondBareId), - `second fallback "${second}" is not in github's registered model catalog: ${[...githubIds].join(", ")}` - ); - assert.notEqual(secondBareId, "claude-opus-4-6"); - assert.notEqual(secondBareId, "claude-opus-4.6"); + const hops: string[] = []; + let current = "github/claude-opus-4.8"; + for (let hop = 0; hop < 3; hop++) { + const next = getNextFamilyFallback(current, tried); + assert.ok(next, `hop ${hop + 1}: family must not be silently exhausted`); + const bareId = next!.replace(/^github\//, ""); + assert.ok( + githubIds.has(bareId), + `hop ${hop + 1}: "${next}" is not in github's registered model catalog: ${[...githubIds].join(", ")}` + ); + assert.notEqual(bareId, "claude-opus-4-6-thinking"); + assert.notEqual(bareId, "claude-opus-4.6-thinking"); + tried.add(next!); + hops.push(next!); + current = next!; + } + // The skip specifically fired: the 4.6 -> next hop jumped past the absent + // 4-6-thinking tier straight to a catalogued model. + assert.equal(hops[2].replace(/^github\//, ""), "claude-opus-4.5"); }); test("#8134: getNextFamilyFallback never returns a candidate absent from the resolved provider's catalog", () => { diff --git a/tests/unit/check-db-rules-classification.test.ts b/tests/unit/check-db-rules-classification.test.ts index 5707878b8a..82ca183f0f 100644 --- a/tests/unit/check-db-rules-classification.test.ts +++ b/tests/unit/check-db-rules-classification.test.ts @@ -61,6 +61,11 @@ function hasImporter(mod: string, roots: string[]): boolean { new RegExp(`(?:import|require)\\s*\\(\\s*['""][^'"]+/db/${escaped}['"]`), // dynamic template: import(`…/db/.ts`) — bin/cli/runtime.mjs uses template literals new RegExp(`import\\s*\\(\`[^'"\`]+/db/${escaped}\\.ts\`\\)`), + // dynamic via file:// URL helper: import(projectFileUrl("…/db/.ts")) — + // bin/cli/runtime.mjs since #11238 (Windows-safe file:// dynamic imports). + new RegExp( + `import\\s*\\(\\s*projectFileUrl\\(\\s*['""][^'"]+/db/${escaped}\\.ts['"]\\s*\\)\\s*\\)` + ), // relative import within db/: from "./" or from "./" new RegExp(`from\\s+['"]\\.\\.?/${escaped}['"]`), ]; diff --git a/tests/unit/cli-catalog-counts.test.ts b/tests/unit/cli-catalog-counts.test.ts index 186a951329..36853fdf99 100644 --- a/tests/unit/cli-catalog-counts.test.ts +++ b/tests/unit/cli-catalog-counts.test.ts @@ -41,8 +41,8 @@ test("CLI_TOOLS total code entries (including none) equals 26 (21 visible + 5 no assert.equal(codeAll.length, 26, `Expected 26 total code entries, got ${codeAll.length}`); }); -test("CLI_TOOLS total (code + agent) = 34", () => { - assert.equal(all.length, 34, `Expected 34 total entries, got ${all.length}`); +test("CLI_TOOLS total (code + agent) = 35", () => { + assert.equal(all.length, 35, `Expected 35 total entries, got ${all.length}`); }); test("All code-none entries have configType mitm OR are legacy excluded entries", () => { @@ -99,7 +99,7 @@ test("The 21 visible code entries include Qwen Code's rebuilt integration", () = } }); -test("The 8 agent entries match D15 list exactly (+ omp + letta, #6318)", () => { +test("The 9 agent entries match D15 list exactly (+ omp + letta #6318, + prime-agent #11166)", () => { const d15Agents = new Set([ "hermes-agent", "openclaw", @@ -109,6 +109,7 @@ test("The 8 agent entries match D15 list exactly (+ omp + letta, #6318)", () => "agent-deck", "omp", "letta", + "prime-agent", ]); const agentIds = new Set(agentAll.map((t) => t.id)); for (const id of d15Agents) { diff --git a/tests/unit/cli-setup-opencode.test.ts b/tests/unit/cli-setup-opencode.test.ts index ca5425e9d5..ac99ced134 100644 --- a/tests/unit/cli-setup-opencode.test.ts +++ b/tests/unit/cli-setup-opencode.test.ts @@ -74,6 +74,9 @@ describe("omniroute setup opencode", () => { // Commander turns `--base-url` into `baseUrl` — the runner must accept it. baseUrl: "http://10.0.0.5:20128", nonInteractive: true, + // These tests exercise the plugin install/merge path, not the container + // guard (#10057) — keep them hermetic on container devboxes/CI. + allowContainerWrite: true, }); assert.equal(r.exitCode, 0); @@ -99,6 +102,7 @@ describe("omniroute setup opencode", () => { configDir: CONFIG_DIR, baseUrl: "http://10.0.0.9:20128", nonInteractive: true, + allowContainerWrite: true, }); assert.equal(r.exitCode, 0); @@ -127,7 +131,11 @@ describe("omniroute setup opencode", () => { }) ); - const r = await runSetupOpenCodeCommand({ configDir: CONFIG_DIR, nonInteractive: true }); + const r = await runSetupOpenCodeCommand({ + configDir: CONFIG_DIR, + nonInteractive: true, + allowContainerWrite: true, + }); assert.equal(r.exitCode, 0); const cfg = readConfig(); @@ -140,7 +148,11 @@ describe("omniroute setup opencode", () => { it("fails with a clear error (exit 1) when the bundled plugin dist is missing", async () => { fs.rmSync(path.join(FAKE_PLUGIN_DIR, "dist"), { recursive: true, force: true }); try { - const r = await runSetupOpenCodeCommand({ configDir: CONFIG_DIR, nonInteractive: true }); + const r = await runSetupOpenCodeCommand({ + configDir: CONFIG_DIR, + nonInteractive: true, + allowContainerWrite: true, + }); assert.equal(r.exitCode, 1); } finally { makeFakePluginDist(); diff --git a/tests/unit/cli-tools-apply-opencode-jsonc.test.ts b/tests/unit/cli-tools-apply-opencode-jsonc.test.ts index f530607bc6..3abdb422b4 100644 --- a/tests/unit/cli-tools-apply-opencode-jsonc.test.ts +++ b/tests/unit/cli-tools-apply-opencode-jsonc.test.ts @@ -15,6 +15,10 @@ const originalFetch = globalThis.fetch; const originalJwtSecret = process.env.JWT_SECRET; const originalApiKeySecret = process.env.API_KEY_SECRET; const originalXdg = process.env.XDG_CONFIG_HOME; +const originalAllowContainerWrite = process.env.OMNIROUTE_ALLOW_CONTAINER_CONFIG_WRITE; +// This test exercises the apply/merge path, not the container guard (#10057) — +// keep it hermetic on container devboxes/CI. +process.env.OMNIROUTE_ALLOW_CONTAINER_CONFIG_WRITE = "1"; const testRoots = new Set(); async function createAuthCookie(): Promise { @@ -72,6 +76,9 @@ test.afterEach(async () => { else process.env.API_KEY_SECRET = originalApiKeySecret; if (originalXdg === undefined) delete process.env.XDG_CONFIG_HOME; else process.env.XDG_CONFIG_HOME = originalXdg; + if (originalAllowContainerWrite === undefined) + delete process.env.OMNIROUTE_ALLOW_CONTAINER_CONFIG_WRITE; + else process.env.OMNIROUTE_ALLOW_CONTAINER_CONFIG_WRITE = originalAllowContainerWrite; for (const root of testRoots) await fs.rm(root, { recursive: true, force: true }); testRoots.clear(); }); diff --git a/tests/unit/cli-tools-schema.test.ts b/tests/unit/cli-tools-schema.test.ts index ee2354986b..3f01c16de5 100644 --- a/tests/unit/cli-tools-schema.test.ts +++ b/tests/unit/cli-tools-schema.test.ts @@ -11,6 +11,7 @@ test("CLI_TOOLS registry contains all expected tools including rebuilt Qwen Code // (CodeWhale is the actively-maintained successor to DeepSeek TUI). // omp + letta added by #6318 (agent-category CLI integrations). // grok-build added — xAI Grok Build TUI coding agent (ported from upstream decolua/9router#2571). + // prime-agent added by #11166 (PrimeIntellect-ai/prime-agent, agent category). const expected = [ "claude", "codex", @@ -46,6 +47,7 @@ test("CLI_TOOLS registry contains all expected tools including rebuilt Qwen Code "grok-build", "qwen", "zcode", + "prime-agent", ]; for (const id of expected) { assert.ok(id in CLI_TOOLS, `Missing tool: ${id}`); diff --git a/tests/unit/cli-tools.test.ts b/tests/unit/cli-tools.test.ts index 123c98e600..4523da96de 100644 --- a/tests/unit/cli-tools.test.ts +++ b/tests/unit/cli-tools.test.ts @@ -106,7 +106,9 @@ test("CLI fingerprint preserves Codex executor User-Agent and maps legacy Copilo { model: "gpt-4o", messages: [] } ); - assert.equal(copilot.headers["User-Agent"], "GitHubCopilotChat/0.54.0"); + // #10952 bumped GITHUB_COPILOT_CLI_VERSION 0.54.0 -> 1.0.81-6; the fingerprint + // pin tracks the advertised upstream CLI version. + assert.equal(copilot.headers["User-Agent"], "GitHubCopilotChat/1.0.81-6"); }); test("CLI fingerprint keeps legacy Copilot settings functional without exposing duplicate UI toggles", () => { diff --git a/tests/unit/cli/setup-qwen.test.ts b/tests/unit/cli/setup-qwen.test.ts index e8086961de..b6140c76d4 100644 --- a/tests/unit/cli/setup-qwen.test.ts +++ b/tests/unit/cli/setup-qwen.test.ts @@ -42,6 +42,9 @@ test("setup-qwen writes current V4 settings and only its dedicated env key", asy configPath: settingsPath, envPath, yes: true, + // These tests exercise the merge/write logic, not the container guard + // (#10057) — keep them hermetic on container devboxes/CI. + allowContainerWrite: true, }); assert.equal(code, 0); @@ -76,6 +79,8 @@ test("setup-qwen does not overwrite an invalid settings file", async () => { model: "model-id", configPath: settingsPath, yes: true, + // See above — hermetic regardless of container detection (#10057). + allowContainerWrite: true, }); assert.equal(code, 1); assert.equal(await fs.readFile(settingsPath, "utf8"), "{ invalid JSON"); diff --git a/tests/unit/db-core-init.test.ts b/tests/unit/db-core-init.test.ts index bb0cd512e5..15ab1b576b 100644 --- a/tests/unit/db-core-init.test.ts +++ b/tests/unit/db-core-init.test.ts @@ -497,7 +497,13 @@ test( } ); -test("build phase uses an in-memory database without creating sqlite files", serial, async () => { +test("build phase returns the no-op stub without creating sqlite files", serial, async () => { + // Contract changed by #10060 (via #10952): the build phase no longer opens a + // real in-memory SQLite with migrations — loading the native better-sqlite3 + // addon aborts the Next.js build worker on exit (node:: + // RemoveEnvironmentCleanupHook). getDbInstance() now returns a no-op stub + // (pinned by tests/unit/build/10060-build-sqlite-stub.test.ts); queries are + // harmless no-ops and no file is touched. const dataDir = makeTempDir("omniroute-db-build-"); try { @@ -510,13 +516,15 @@ test("build phase uses an in-memory database without creating sqlite files", ser const core = await importFresh("src/lib/db/core.ts"); const db = core.getDbInstance(); - assert.ok( + assert.notEqual(db.driver, "better-sqlite3"); + assert.equal( db .prepare("SELECT name FROM sqlite_master WHERE type = 'table' AND name = ?") - .get("provider_connections") + .get("provider_connections"), + undefined, + "the build stub must answer queries with no-ops, never a real table scan" ); assert.equal(fs.existsSync(path.join(dataDir, "storage.sqlite")), false); - assert.equal(db.pragma("journal_mode", { simple: true }), "memory"); core.resetDbInstance(); } diff --git a/tests/unit/effort-tiers-loop-catalog-e2e.test.ts b/tests/unit/effort-tiers-loop-catalog-e2e.test.ts index f2fe6f89c6..4e6b5c2663 100644 --- a/tests/unit/effort-tiers-loop-catalog-e2e.test.ts +++ b/tests/unit/effort-tiers-loop-catalog-e2e.test.ts @@ -4,7 +4,7 @@ * response (/api/v1/models), including the learned-only variant entry. * Never "fix" this test by injecting the same string on both sides. */ -import { test, after, beforeEach } from "node:test"; +import { test } from "node:test"; import assert from "node:assert/strict"; import fs from "node:fs"; import os from "node:os"; diff --git a/tests/unit/models-catalog-combo-metadata.test.ts b/tests/unit/models-catalog-combo-metadata.test.ts index b4fc629bad..c80253c314 100644 --- a/tests/unit/models-catalog-combo-metadata.test.ts +++ b/tests/unit/models-catalog-combo-metadata.test.ts @@ -98,7 +98,11 @@ test("single-target Codex combo advertises a larger model context override", asy assert.equal(response.status, 200); assert.equal(direct?.context_length, contextWindow); assert.equal(combo?.context_length, contextWindow); - assert.equal(combo?.max_input_tokens, 272000); + // #11179 raised the static codex catalog cap to maxInputTokens=872000 (the real + // usable window; the old 272000 was just the first pricing tier). The input cap + // can never exceed the total window, so with the 500K override it clamps to it: + // min(872000, 500000) = 500000. + assert.equal(combo?.max_input_tokens, 500000); } finally { contextOverrides.removeModelContextOverride("codex", modelId); } diff --git a/tests/unit/provider-models-route-codex.test.ts b/tests/unit/provider-models-route-codex.test.ts index 0a3ad6f757..0d4587218d 100644 --- a/tests/unit/provider-models-route-codex.test.ts +++ b/tests/unit/provider-models-route-codex.test.ts @@ -181,10 +181,11 @@ test("provider models route merges live Codex models with the local catalog then // merge conservatively — the smaller of live vs. pinned wins, never the // larger, so a stale/inflated live number can never make OmniRoute promise // more context than the account can actually serve (#7012). Here the pinned - // GPT-5.6 Codex contract (272000/128000, see GPT_5_6_CODEX_CAPABILITIES) + // GPT-5.6 Codex contract (872000/128000, see GPT_5_6_CODEX_CAPABILITIES — raised + // from the old 272K pricing tier to the real usable window by #11179) // is smaller than the live payload's 999999/999999, so the pinned value wins. assert.equal(liveModel?.name, "GPT 5.6 Sol Live"); - assert.equal(liveModel?.inputTokenLimit, 272000); + assert.equal(liveModel?.inputTokenLimit, 872000); assert.equal(liveModel?.outputTokenLimit, 128000); assert.equal(liveModel?.apiFormat, "responses"); assert.deepEqual(liveModel?.supportedEndpoints, ["responses"]); diff --git a/tests/unit/search-route.test.ts b/tests/unit/search-route.test.ts index 9f3c67eca1..bdcfde1892 100644 --- a/tests/unit/search-route.test.ts +++ b/tests/unit/search-route.test.ts @@ -420,25 +420,24 @@ test("v1 search POST preserves stored SearXNG baseUrl for authless providers", a } }); -test("v1 search POST returns 400 when auto-select finds no configured provider (searxng-search is now fallbackOnly)", async () => { +test("v1 search POST falls back to duckduckgo-free when no provider is configured (#11097)", async () => { + // Contract changed by PR #11097 ("fix(search): fall back to duckduckgo-free when + // no search provider is configured"): zero-credential /v1/search no longer returns + // 400 — it promotes the fallback-only duckduckgo-free provider so out-of-the-box + // search works. This test pins the NEW contract. const originalFetch = globalThis.fetch; let capturedUrl = ""; + // DuckDuckGo lite HTML shape: result link + snippet cell (see + // open-sse/services/freeWebSearch.ts parseDuckDuckGoLite). + const liteHtml = ` + Auto-selected DuckDuckGo result + Fallback free search snippet + `; + globalThis.fetch = async (url) => { capturedUrl = String(url); - return new Response( - JSON.stringify({ - results: [ - { - title: "Auto-selected SearXNG result", - url: "https://searx.example/auto", - content: "Auto-selected self-hosted response", - engines: ["duckduckgo"], - }, - ], - }), - { status: 200, headers: { "content-type": "application/json" } } - ); + return new Response(liteHtml, { status: 200, headers: { "content-type": "text/html" } }); }; try { @@ -454,14 +453,15 @@ test("v1 search POST returns 400 when auto-select finds no configured provider ( ); const body = (await response.json()) as any; - assert.equal(response.status, 400); - assert.equal(capturedUrl, "", "fallback-only SearXNG must not receive an upstream request"); - assert.ok(body.error?.message || body.error); - assert.match( - String(body.error?.message ?? body.error), - /provider|configured/i, - "the response must explain that no provider was selected" + assert.equal(response.status, 200); + assert.equal( + capturedUrl, + "https://lite.duckduckgo.com/lite/", + "the fallback must call the DuckDuckGo lite endpoint" ); + assert.equal(body.provider, "duckduckgo-free"); + assert.equal(body.results[0].title, "Auto-selected DuckDuckGo result"); + assert.equal(body.results[0].url, "https://example.com/auto-result"); } finally { globalThis.fetch = originalFetch; } diff --git a/tests/unit/usage-service-hardening.test.ts b/tests/unit/usage-service-hardening.test.ts index d503cfef3e..6f9cbb6589 100644 --- a/tests/unit/usage-service-hardening.test.ts +++ b/tests/unit/usage-service-hardening.test.ts @@ -72,10 +72,12 @@ test("usage service covers GitHub free-plan parsing, auth denial and unsupported assert.equal(freeUsage.quotas.completions.used, 0); assert.equal(freeUsage.quotas.completions.remainingPercentage, 100); assert.equal(calls[0].headers.Authorization, "token gho-free"); - assert.equal(calls[0].headers["User-Agent"], "GitHubCopilotChat/0.54.0"); - assert.equal(calls[0].headers["Editor-Version"], "vscode/1.126.0"); - assert.equal(calls[0].headers["Editor-Plugin-Version"], "copilot-chat/0.54.0"); - assert.equal(calls[0].headers["X-GitHub-Api-Version"], "2026-06-01"); + // #10952 re-based the Copilot wire identity on the live-captured CLI 1.0.81-6 + // (copilot-developer-cli integration id; API version 2026-08-01). + assert.equal(calls[0].headers["User-Agent"], "GitHubCopilotChat/1.0.81-6"); + assert.equal(calls[0].headers["Editor-Version"], "copilot/1.0.81-6"); + assert.equal(calls[0].headers["Editor-Plugin-Version"], "copilot-chat/1.0.81-6"); + assert.equal(calls[0].headers["X-GitHub-Api-Version"], "2026-08-01"); globalThis.fetch = async () => new Response("forbidden", { status: 403 }); const forbidden: any = await usageService.getUsageForProvider({ diff --git a/tests/unit/vscode-token-routes-gpt56.test.ts b/tests/unit/vscode-token-routes-gpt56.test.ts index 64daae58c4..c68a85a6b7 100644 --- a/tests/unit/vscode-token-routes-gpt56.test.ts +++ b/tests/unit/vscode-token-routes-gpt56.test.ts @@ -128,9 +128,11 @@ test("vscode raw models route exposes native GPT-5.6 IDs and effort tiers", asyn assert.equal(typeof defaultModel.created, "number"); assert.equal(defaultModel.owned_by, "codex"); assert.equal(defaultModel.name, "Codex GPT 5.6 Sol"); - assert.equal(defaultModel.context_length, 272000); + // #11179: codex static catalog advertises the usable 872K window (max_context_window), + // not the old 272K pricing tier. + assert.equal(defaultModel.context_length, 872000); assert.equal(defaultModel.max_output_tokens, 128000); - assert.equal(defaultModel.max_input_tokens, 272000); + assert.equal(defaultModel.max_input_tokens, 872000); assert.deepEqual(defaultModel.capabilities, { vision: true, tool_calling: true, diff --git a/tests/unit/vscode-token-routes.test.ts b/tests/unit/vscode-token-routes.test.ts index 5a292b4600..d66118b3f2 100644 --- a/tests/unit/vscode-token-routes.test.ts +++ b/tests/unit/vscode-token-routes.test.ts @@ -255,7 +255,9 @@ test("vscode combos route resolves combo names through Ollama api/show", async ( assert.equal(body.model, "show-combo"); assert.equal(body.modelfile, "FROM show-combo"); assert.equal(body.details.family, "show-combo"); - assert.equal(body.model_info.context_length, 272000); + // #11179: codex static catalog advertises the usable 872K window (max_context_window), + // not the old 272K pricing tier. + assert.equal(body.model_info.context_length, 872000); assert.deepEqual(body.supportsReasoningEffort, ["none", "low", "medium", "high", "xhigh"]); assert.equal(body.model_info.capabilities.reasoning, true); }); @@ -290,7 +292,8 @@ test("vscode tokenized combos root route exposes importable combo metadata", asy assert.equal(response.status, 200); assert.ok(combo, "expected balanced-load in combo root response"); assert.equal(combo.url.includes("/responses#models.ai.azure.com"), true); - assert.equal(combo.maxInputTokens, 272000); + // #11179: codex static catalog maxInputTokens is now the usable 872K window. + assert.equal(combo.maxInputTokens, 872000); assert.equal(combo.toolCalling, true); assert.deepEqual(combo.supportsReasoningEffort, ["none", "low", "medium", "high", "xhigh"]); }); @@ -1073,7 +1076,9 @@ test("vscode tokenized api/show route exposes explicit reasoning effort metadata assert.equal(body.configurationSchema?.properties?.reasoningEffort?.default, "low"); assert.equal(body.model_info["general.basename"], "Codex GPT 5.6 Sol (Default)"); assert.equal(body.model_info["general.architecture"], "codex"); - assert.equal(body.model_info["codex.context_length"], 272000); + // #11179: codex static catalog advertises the usable 872K window (max_context_window), + // not the old 272K pricing tier. + assert.equal(body.model_info["codex.context_length"], 872000); assert.deepEqual(body.model_info.supports_reasoning_effort, [ "low", "medium",