mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-07-31 20:32:20 +03:00
* fix(gemini): preserve structured tool calls for antigravity * fix(gemini): parse prefixed textual tool calls * fix(antigravity): preserve textual SSE tool calls * fix(stream): normalize textual passthrough tool calls * fix(stream): normalize split textual tool calls * fix(stream): suppress malformed textual tool calls * fix(stream): suppress compact malformed tool calls * fix(stream): emit structured textual tool calls * fix(stream): suppress unknown textual tool calls * fix(stream): normalize responses textual tool calls * chore: ignore .claude/settings.local.json (per-user Claude Code permissions) * fix(opencode-go): route qwen3.x via claude messages + repair fixMissingToolResponses for Claude-shape upstreams (#2791) Integrated into release/v3.8.6 * fix: resolve npm install warnings — remove dead deps, relax engine constraint (#2792) Integrated into release/v3.8.6 * fix: register missing web-cookie validators (claude-web, gemini-web, copilot-web, t3-web) (#2793) Integrated into release/v3.8.6 * fix: Error: Unable to inspect existing database #2771 (#2795) Integrated into release/v3.8.6 * fix(oauth): repair Google loopback callback flow (#2796) Integrated into release/v3.8.6 * feat(logs): add clean history button (#2799) Integrated into release/v3.8.6 * [codex] home: restore settings-driven home layout and quota auto-refresh (#2800) Integrated into release/v3.8.6 * fix(gemini): emit signaturelessToolCallMode:text for GEMINI format models (#2801) Integrated into release/v3.8.6 * feat(modelSpecs): align opencode-go family with upstream provider limits (#2802) Integrated into release/v3.8.6 * chore: apply unit test fixes, polyfills, and environment precedence fixes * docs(agents): atualiza fluxos de release e triagem Expande os workflows de release para incluir auditoria de segurança, CHANGELOG completo por commits, quality gate obrigatório, homologação em VPS local, publicação oficial, deploy em Akamai e validação de artefatos. Reorganiza a triagem de features com arquivos permanentes por bucket, suporte a itens em andamento, regra de reclaim após 15 dias e novo tratamento para ideias viáveis catalogadas. Corrige a orientação de revisão de discussões para usar a ordem cronológica real dos comentários e respostas ao identificar a última atividade. * fix(lockout): classify Gemini Antigravity resource exhaustion as quota_exhausted * fix(reasoning): gate replay by interleaved field * docs(rule-16): permit human Co-authored-by, restrict only AI/bot trailers Rule #16 previously banned all `Co-Authored-By` trailers absolutely. That blocked the upstream-port workflows (`/port-upstream-features` and `/port-upstream-issues`), which must credit human upstream PR authors and issue reporters in OmniRoute commits. Refine the rule to ban only AI/bot-attributed trailers (Claude, GPT, Copilot, Bot; anthropic.com / openai.com / bot-owned noreply.github.com emails) while allowing standard human `Co-authored-by: Name <email>` attribution. Sync the rule across the source CLAUDE.md, the E2E shakedown doc note, and 41 i18n translations. * fix(gitlawb): add specialty validators for connection test — bypass /models probe GitLawB OpenGateway API (xiaomi-mimo compatible) does not expose a /models endpoint, causing validateOpenAILikeProvider to 404 on the initial probe and report 'Provider validation endpoint not supported'. Add specialty validators for both gitlawb and gitlawb-gmi that follow the same pattern as the existing xiaomi-mimo validator: skip GET /models, validate directly via POST /chat/completions with a minimal test message. Any 401/403 response means an invalid key; all other responses mean auth is OK. Fixes test-connection returning 404 for GitLawB providers. * test(gitlawb): add 12 unit tests for gitlawb and gitlawb-gmi specialty validators Covers success, auth failure (401/403), non-auth acceptance (400/422/429), network errors, and custom baseUrl overrides for both providers. * feat(gitlawb): serve models from static registry without API-unavailable warning GitLawB's OpenGateway API does not expose a /models endpoint per provider-path. Previously the models route fell through to the generic fallback which returned static catalog models with the misleading 'API unavailable — using local catalog' warning. Now gitlawb and gitlawb-gmi are handled as static model providers (same pattern as reka and qwen OAuth) — models are served from the provider registry without any warning, since all registered models are functional via POST /chat/completions. * refactor(gitlawb): extract shared opengateway validator factory, fix docs path in test - Extract gitlawb/gitlawb-gmi validators into buildOpengatewayValidator factory - Fix dockerignore-docs-coverage test: update stale docs/AUTO-COMBO.md -> docs/routing/AUTO-COMBO.md * fix(reasoning): guard interleaved capability lookup * feat(gitlawb): dynamic model fetch with gmi-cloud fallback Hybrid approach: - gitlawb (xiaomi-mimo): dynamic /models endpoint → 356 models - gitlawb-gmi (gmi-cloud): 404 fallback → local catalog gracefully Mimics Gitlawb/openclaude's model-routing pattern * i18n(pt-BR): complete missing translations and sync with en.json * feat(build): nix multi-OS package manager install (#2806) Integrated into release/v3.8.6 * fix(i18n): translate 144 new __MISSING__ pt-BR strings (#2816) Integrated into release/v3.8.6 * chore(docs): set coverage gate to 40/40/40/40 in CLAUDE.md Aligns the documented coverage gate with the v3.8.6 release decision (lowered from 75/75/75/70). Matches the threshold already set in package.json by the large feature PRs (planos 11-22). * fix(cli): respect PORT env var in serve command (#2845) Integrated into release/v3.8.6. * fix(deepseek-web): return 400 when client sends tools[] - chat.deepseek.com has no tool support (#2854) Integrated into release/v3.8.6. * fix(qoder): reject invalid/expired PATs returning Cosy 500 error (#2860) Integrated into release/v3.8.6. * fix(cli): register openclaw in tool-detector (#2833) (#2850) Integrated into release/v3.8.6. * fix(api): include noAuth providers in /v1/models catalog (#2798) (#2814) Integrated into release/v3.8.6. * fix(combo): resolve custom provider targets via combo name (#2778) (#2812) Integrated into release/v3.8.6. * fix(translator): strip safety_identifier in openai-responses cleanup (#2770) (#2809) Integrated into release/v3.8.6. * fix(quota): honor explicit per-connection preflight opt-out (#2831) (#2844) Integrated into release/v3.8.6. * fix(usage): un-invert GitHub Copilot Free/limited quota — limited_user_quotas is remaining (#2876) (#2881) Integrated into release/v3.8.6. * fix(nous-research): correct baseUrl to include /chat/completions (#2826) (#2835) Integrated into release/v3.8.6. * fix(opencode): qwen3.x max/plus models lack vision support (#2822) (#2836) Integrated into release/v3.8.6. * fix(translator): pass-through tool_search built-in tool type (#2766) (#2811) Integrated into release/v3.8.6. * fix(github): route claude-opus-4.6 via chat completions (#2821) Integrated into release/v3.8.6. * docs(oauth): add Windsurf login fix design (Phase 1 hotfix + Phase 2 Firebase OAuth) Two-phase plan to fix the broken Windsurf OAuth flow: - Phase 1: drop the dead app.devin.ai/editor/signin PKCE path, promote import-token from windsurf.com/show-auth-token as the primary path - Phase 2: port Firebase OAuth + RegisterUser flow from fendoushaonian/WindSurf-gRPC-API for full browser-based automation Spec only - no code changes yet. * docs(plan): Phase 1 windsurf login hotfix implementation plan 10 tasks covering: - TDD assertions for flowType + 410 Gone responses - Provider switch to import_token - Route handler retiring authorize/start-callback-server/poll-callback - OAuthModal UI override - i18n sync - Verification + PR steps * fix(cli): replace cli-table3 with hand-rolled formatter (#2752) (#2813) Integrated into release/v3.8.6. * fix(skills): skip interception for unregistered client-native tools (#2815) (#2817) Integrated into release/v3.8.6. * feat(sse): add RTK filters for kubectl, docker-build, composer, gh (#2824) Integrated into release/v3.8.6. * fix(geminiHelper): support rec.image content shape + warn on dropped remote URLs (refs #2807) (#2855) Integrated into release/v3.8.6. * fix(cli): allow nullable/optional apiKey in cliMitmStartSchema (#2857) Integrated into release/v3.8.6. * fix(combo): preserve system messages during context handoff summary generation (#2865) Integrated into release/v3.8.6. * fix: wire CLIProxyAPI fallback settings into chatCore routing engine (#2866) Integrated into release/v3.8.6. * fix(usage): add opencode quota fetcher (#2852) (#2867) Integrated into release/v3.8.6. * feat(claude): default xhigh support for newer Opus models (#2874) Integrated into release/v3.8.6. * fix(cli): restore omniroute logs command stream (#2756) (#2810) Integrated into release/v3.8.6. * fix(combo): normalize upstream Headers for Node 24 undici interop (#2751) (#2823) Integrated into release/v3.8.6. * Rename proxy log Public IP to Client IP (#2880) Integrated into release/v3.8.6. * fix(claude): preserve max effort for supported models (#2875) Integrated into release/v3.8.6. * fix(oauth): switch windsurf provider to import_token flow The PKCE auth URL targeting app.devin.ai/editor/signin returns 404 post-rebrand. Until Phase 2 ports Firebase OAuth + RegisterUser, the only supported path is import-token via windsurf.com/show-auth-token. - windsurf.ts: drop buildAuthUrl, set flowType=import_token - generateAuthData returns supported:false + helpful error for windsurf/devin-cli - tests: assert flowType + disabled stub * fix(oauth): return 410 Gone for retired windsurf/devin-cli PKCE actions start-callback-server, authorize, and poll-callback (GET + POST) now return 410 Gone with a pointer to /import-token. The 410 short-circuit runs before auth so the response is honest about the action being permanently gone, not gated. Codex PKCE flow unchanged. Tests: 5 new assertions cover GET + POST 410 paths and a Codex regression check. * refactor(oauth): annotate retired PKCE fields in WINDSURF_CONFIG No behaviour change - comment-only update documenting that authorizeUrl, codeChallengeMethod, callbackPort, callbackPath, apiServerUrl, and exchangePath are no longer consumed. Active fields (inferenceUrl, showAuthTokenUrl, firebaseApiKey, ideName) called out separately. * fix(cli,docs): use requireCliToolsAuth in logs route + document OPENCODE quota env Post-merge contract fixes for v3.8.6: - src/app/api/cli-tools/logs/route.ts (#2810) now uses the shared requireCliToolsAuth guard (param renamed req->request) to satisfy the cli-tools-auth-hardening contract test. - Document OMNIROUTE_OPENCODE_QUOTA_URL (#2867) in docs/reference/ENVIRONMENT.md to satisfy the env/docs sync contract. * fix(dashboard): force import-token panel for windsurf/devin-cli Phase 1 hotfix: hide the 'Browser Login' tab and start in Paste API Key mode. Removes windsurf/devin-cli from PKCE_CALLBACK_SERVER_PROVIDERS so no callback server is started for them. Codex still uses the PKCE flow. The 'Get token' link continues to point at windsurf.com/show-auth-token via the existing supportsTokenPaste form copy. * fix(oauth): windsurf import-token mapTokens signature mismatch The route at `src/app/api/oauth/[provider]/[action]/route.ts` invokes `providerData.mapTokens({ accessToken: token })` (object), matching the cursor/kiro signature. The windsurf provider was declared with `mapTokens(token: string)` instead, so the entire object was stored as `accessToken`. When the connection record reached the SQLite layer it crashed with: SQLite3 can only bind numbers, strings, bigints, buffers, and null Fix by aligning windsurf's `mapTokens` signature with the route caller and the cursor/kiro convention. Also dedupe a copy-pasted second `if (action === "import-token")` block in the route handler — the second block was unreachable but identical to the first. Adds two regression tests asserting that `provider.mapTokens({ accessToken })` returns a string `accessToken` for both windsurf and devin-cli, so a future signature drift trips the gate instead of the SQLite bind error in production. * feat(compression): expand pt-BR pack with troglodita rules (15 → 49) (#2818) Integrated into release/v3.8.6 * fix(sse): repair RTK engine defaults so dedup and direct calls work (#2825) Integrated into release/v3.8.6 * fix(mcp): redirect console.log/warn to stderr in --mcp stdio mode (#2840) Integrated into release/v3.8.6 * fix(gemini-cli): prefer real project IDs over default-project (#2841) Integrated into release/v3.8.6 * fix(opencode-go): add provider limits quota fetcher (#2861) Integrated into release/v3.8.6 * Audit & add web cookie providers: fix 4 missing registry entries + DuckDuckGo (#2862) Integrated into release/v3.8.6 * fix(antigravity): harden signatureless tool history (#2878) Integrated into release/v3.8.6 * fix: provider model sync pruning and dynamic antigravity MITM proxy mappings (#2886) Integrated into release/v3.8.6 * feat(usage): per-API-key token limits scoped to model/provider/global (#2888) Integrated into release/v3.8.6 * fix(audio): build multipart body manually to preserve Content-Type (#2842) Integrated into release/v3.8.6 * refactor: remove agent skill documentation files and streamline maintenance workflows * test(stabilization): resolve unit test failures in blackbox-web, schema-coercion, translator-helper-branches, usage-service-hardening, and audio-transcription * fix(security): mitigate Socket.dev supply-chain findings + secrets opt-in + minimal build profile (#2863) (#2871) Two real security gaps closed and four cosmetic Socket.dev fingerprints removed. See docs/security/SOCKET_DEV_FINDINGS.md for the per-finding maintainer attestation. Real bugs fixed: - cloudSync: HMAC verification of `X-Cloud-Sig` + opt-in `OMNIROUTE_CLOUD_SYNC_SECRETS=true` before overwriting `accessToken` / `refreshToken` / `providerSpecificData` from a remote response. Closes the silent-credential-swap surface (a misconfigured or hostile CLOUD_URL could previously replace local tokens unverified). - Zed import: split into 2-step `/discover` + `/import` flow. `/import` now requires `confirmedAccounts: [{ service, account, fingerprint }]` and re-reads the keychain server-side to filter by fingerprint, so a tampered discover response cannot trick the endpoint into saving an unrelated token. Cosmetic Socket.dev mitigations: - runElevatedPowerShell writes the elevated payload to a per-call temp `.ps1` file (mode 0o600) and references it via `-File`. Removes the textbook `-EncodedCommand <base64utf16le>` pattern flagged as malware by Socket's AI classifier. - Maintainer attestation `SECURITY-AUDITOR-NOTE:` blocks added at every flagged call site pointing to `docs/security/SOCKET_DEV_FINDINGS.md`. Build-time hardening: - `OMNIROUTE_BUILD_PROFILE=minimal` (`npm run build:secure`) physically removes the four sensitive modules from the standalone bundle via webpack `NormalModuleReplacementPlugin`. Stubs throw `FeatureDisabledError` at runtime. Intended for the `omniroute-secure` artifact. Tests: - 24 new unit tests in `tests/unit/security/` covering the wrapper builder, HMAC verification (4 cases), credential fingerprint determinism (5 cases), confirmedAccounts validation + fingerprint filtering (6 cases), and the minimal-build stubs (5 cases). Docs: - New `docs/security/SOCKET_DEV_FINDINGS.md` — per-finding attestation. - New `socket.yml` — Socket.dev v2 config pointing at the attestation. - Updated `SECURITY.md` — supply-chain scanner section. - Updated `.env.example` — three new env vars documented. Backwards compatibility: - Cloud sync token overwrite is OFF by default. Users who relied on it must set `OMNIROUTE_CLOUD_SYNC_SECRETS=true`. Breaking change documented in CHANGELOG. - Zed import 2-step is the new default; legacy 1-step preserved behind `OMNIROUTE_ZED_IMPORT_LEGACY_ONE_STEP=true` and will be removed in v3.9. Closes #2863 * fix(security): redact public Firebase Web key from windsurf spec; doc SHA-256 cache-key rationale (#2894) Two security-scanning findings on release/v3.8.6: - Secret-scanning alert 7 (google_api_key): the windsurf login-fix design spec embedded the literal public Firebase Web API key on two lines. Firebase Web API keys are non-sensitive by design (they identify the project; access is gated by Firebase Security Rules + key restrictions), but the literal trips secret scanning. Redacted to a placeholder; the embedded default still goes through resolvePublicCred per rule #11. - Code-scanning alert 261 (js/insufficient-password-hash): tokenCacheKey() uses SHA-256 to derive an in-memory cache key from the session token, not for password-at-rest storage. Added a comment documenting why CWE-916 KDFs do not apply (false positive). * fix(ci): resolve release/v3.8.6 gate failures (docs-sync, any-budget, pack-artifact) (#2895) * fix(ci): resolve release/v3.8.6 gate failures (docs-sync, any-budget, pack-artifact) Three CI gates failed on release/v3.8.6 (run 26630300877): - docs-sync: CHANGELOG had a spurious "## [3.8.6-patch]" section above "## [3.8.6]", so the latest release no longer matched package.json (3.8.6) and the 41 i18n CHANGELOG mirrors were flagged as missing that section. Fold the lone #2752 entry into [3.8.6] and drop the patch heading. - any-budget:t11: open-sse/handlers/chatCore.ts regressed to 1 explicit `any` (budget 0). Type the persist callback arg as Record<string, unknown>, which matches runWithOnPersist's RefreshPersistFn contract exactly. - pack-artifact: open-sse/utils/setupPolyfill.ts ships via package.json "files" (bin/omniroute.mjs imports it at startup) but was missing from the pack policy allowlist. Allow it and add a regression test. * fix(security): redact public Firebase Web key from windsurf spec Redact the literal public Firebase Web API key (secret-scanning #7) to a placeholder, mirroring the redaction on release/v3.8.6 (PR #2894) and the windsurf fix branch. Non-sensitive public Web key; trips secret scanning. * feat(combo): Zero-Latency Combos (Hedging, Proactive Compression, Predictive TTFT) (#2868) * feat(combo): implement zero-latency combo optimizations (hedging, proactive compression, predictive TTFT) * fix(combo): fix predictive TTFT skip logic and unhandled promise rejections --------- Co-authored-by: Automation <automation@omniroute> * feat: implement automated skill workflows and update system configuration and validation schemas * test: eliminate dynamic cast warnings in cloud-sync unit test * test: isolate services-branch-hardening database directory to avoid concurrency issues * feat(providers): add 7 new web-cookie providers + research catalog + discovery tool New providers: - huggingchat: free LLM chat via huggingface.co/chat (no subscription) - phind: free dev-focused AI chat via phind.com/api/agent - poe-web: multi-model chat via poe.com GraphQL (p-b cookie) - venice-web: privacy-focused AI chat via venice.ai (session cookie) - v0-vercel-web: Vercel v0 code gen via v0.dev (session cookie) - kimi-web: Moonshot Kimi chat via kimi.moonshot.cn (session cookie) - doubao-web: ByteDance Doubao chat via doubao.com (session cookie) Additional: - Research catalog: docs/research/UNLIMITED_LLM_ACCESS.md - Discovery tool design + stub: src/lib/discovery/ + migration 073 - Unit tests: 33 tests for all 7 providers - Shared helpers consolidated in error.ts (slop cleanup) - All registered in WEB_COOKIE_PROVIDERS + providerRegistry + webSessionCredentials Closes #2885 * fix(typecheck): resolve typecheck errors in combo spec and compression modules * feat(api,oauth): add `agy` (Antigravity CLI) standalone provider with CLI token import (#2899) Add a standalone OAuth provider `agy` (Antigravity CLI) next to gemini-cli/antigravity. It reuses the antigravity inference backend (identical Google client_id + daily-cloudcode-pa.googleapis.com endpoint, executor and token-refresh) but ships its own model catalog — including the Claude models the backend exposes (claude-opus-4-6-thinking, claude-sonnet-4-6) — its own account pool, and four ways to connect: - token-file import (paste/upload the agy oauth token JSON) - auto-detect a local CLI login (~/.gemini/antigravity-cli/antigravity-oauth-token) - browser OAuth (via the shared OAuthModal Google loopback flow) - bulk / ZIP import New routes: POST /api/providers/agy-auth/{import,import-bulk,zip-extract,apply-local}. Catalog pinned from the live :fetchAvailableModels endpoint. Docs (openapi.yaml, ENVIRONMENT.md, .env.example, CHANGELOG) updated; new unit tests for registration, the token parser, and route auth-hardening. * fix(security): redact public Firebase Web key from windsurf spec (#2896) Redact the literal public Firebase Web API key (secret-scanning #7) to a placeholder. Firebase Web API keys are non-sensitive by design but the literal trips GitHub secret scanning. Mirrors the redaction landed on release/v3.8.6 (PR #2894). Embedded default still flows through resolvePublicCred (rule #11). * Pr 2871 (#2897) * fix(security): mitigate Socket.dev supply-chain findings + secrets opt-in + minimal build profile (#2863) Two real security gaps closed and four cosmetic Socket.dev fingerprints removed. See docs/security/SOCKET_DEV_FINDINGS.md for the per-finding maintainer attestation. Real bugs fixed: - cloudSync: HMAC verification of `X-Cloud-Sig` + opt-in `OMNIROUTE_CLOUD_SYNC_SECRETS=true` before overwriting `accessToken` / `refreshToken` / `providerSpecificData` from a remote response. Closes the silent-credential-swap surface (a misconfigured or hostile CLOUD_URL could previously replace local tokens unverified). - Zed import: split into 2-step `/discover` + `/import` flow. `/import` now requires `confirmedAccounts: [{ service, account, fingerprint }]` and re-reads the keychain server-side to filter by fingerprint, so a tampered discover response cannot trick the endpoint into saving an unrelated token. Cosmetic Socket.dev mitigations: - runElevatedPowerShell writes the elevated payload to a per-call temp `.ps1` file (mode 0o600) and references it via `-File`. Removes the textbook `-EncodedCommand <base64utf16le>` pattern flagged as malware by Socket's AI classifier. - Maintainer attestation `SECURITY-AUDITOR-NOTE:` blocks added at every flagged call site pointing to `docs/security/SOCKET_DEV_FINDINGS.md`. Build-time hardening: - `OMNIROUTE_BUILD_PROFILE=minimal` (`npm run build:secure`) physically removes the four sensitive modules from the standalone bundle via webpack `NormalModuleReplacementPlugin`. Stubs throw `FeatureDisabledError` at runtime. Intended for the `omniroute-secure` artifact. Tests: - 24 new unit tests in `tests/unit/security/` covering the wrapper builder, HMAC verification (4 cases), credential fingerprint determinism (5 cases), confirmedAccounts validation + fingerprint filtering (6 cases), and the minimal-build stubs (5 cases). Docs: - New `docs/security/SOCKET_DEV_FINDINGS.md` — per-finding attestation. - New `socket.yml` — Socket.dev v2 config pointing at the attestation. - Updated `SECURITY.md` — supply-chain scanner section. - Updated `.env.example` — three new env vars documented. Backwards compatibility: - Cloud sync token overwrite is OFF by default. Users who relied on it must set `OMNIROUTE_CLOUD_SYNC_SECRETS=true`. Breaking change documented in CHANGELOG. - Zed import 2-step is the new default; legacy 1-step preserved behind `OMNIROUTE_ZED_IMPORT_LEGACY_ONE_STEP=true` and will be removed in v3.9. Closes #2863 * feat: implement automated skill workflows and update system configuration and validation schemas * test: eliminate dynamic cast warnings in cloud-sync unit test * test: isolate services-branch-hardening database directory to avoid concurrency issues * chore(docs): refresh generated docs collection index Update the generated Fumadocs browser collection mapping to keep documentation imports in sync with the current docs structure. * docs: update generated browser docs collection manifest Refresh the generated Fumadocs browser collection mapping so the docs site can resolve the current documentation files correctly. --------- Co-authored-by: OpenClaw <openclaw@kuzhomesrv.local> Co-authored-by: Dmitry Kuznetsov <139351986+dmitry@users.noreply.local> Co-authored-by: KuzyaBot <kuzya@local> Co-authored-by: JeferssonLemes <jeferssondev@gmail.com> Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com> Co-authored-by: Markus Hartung <mail@hartmark.se> Co-authored-by: akarray <akarray@users.noreply.github.com> Co-authored-by: Apostol Apostolov <theapoapostolov@gmail.com> Co-authored-by: Hernan Javier Ardila Sanchez <hjasgr@gmail.com> Co-authored-by: Dmitry Kuznetsov <dmitry@kuznetsov.me> Co-authored-by: Nikolay Alafuzov <alafuzov_nn@rusklimat.ru> Co-authored-by: oyi77 <oyi77@users.noreply.github.com> Co-authored-by: Ronaldo Davi <alltomatos@users.noreply.github.com> Co-authored-by: levonk <277861+levonk@users.noreply.github.com> Co-authored-by: Lenine Júnior <lenine@engrene.com.br> Co-authored-by: Annas Alghoffar <aag.annas@gmail.com> Co-authored-by: Tushar Agarwal <76201310+Tushar49@users.noreply.github.com> Co-authored-by: GreatLiu <eurasiaxz@qq.com> Co-authored-by: yuna amelia <230527278+yunaamelia@users.noreply.github.com> Co-authored-by: Randi <55005611+rdself@users.noreply.github.com> Co-authored-by: Container <78986709+disonjer@users.noreply.github.com> Co-authored-by: nickwizard <35692452+nickwizard@users.noreply.github.com> Co-authored-by: Rajvardhan Patil <rajvardhanpatil7890@gmail.com> Co-authored-by: Raxxoor <manker_lol@hotmail.com> Co-authored-by: Muhammad Mugni Hadi <mugnimaestra3@gmail.com> Co-authored-by: mi <123757457+soyelmismo@users.noreply.github.com> Co-authored-by: Automation <automation@omniroute>
1082 lines
35 KiB
TypeScript
1082 lines
35 KiB
TypeScript
import test from "node:test";
|
|
import assert from "node:assert/strict";
|
|
|
|
import {
|
|
CodexExecutor,
|
|
__setCodexWebSocketTransportForTesting,
|
|
encodeResponseSseEvent,
|
|
getCodexModelScope,
|
|
getCodexRateLimitKey,
|
|
getCodexResetTime,
|
|
getCodexUpstreamModel,
|
|
isCodexResponsesWebSocketRequired,
|
|
parseCodexQuotaHeaders,
|
|
} from "../../open-sse/executors/codex.ts";
|
|
import {
|
|
clearRememberedResponseFunctionCallsForTesting,
|
|
rememberResponseConversationState,
|
|
rememberResponseFunctionCalls,
|
|
} from "../../open-sse/services/responsesToolCallState.ts";
|
|
import { sanitizeReasoningEffortForProvider } from "../../open-sse/executors/base.ts";
|
|
import {
|
|
DEFAULT_THINKING_CONFIG,
|
|
setThinkingBudgetConfig,
|
|
ThinkingMode,
|
|
} from "../../open-sse/services/thinkingBudget.ts";
|
|
import { CODEX_CHAT_DEFAULT_INSTRUCTIONS } from "../../open-sse/config/codexInstructions.ts";
|
|
|
|
type MockCodexWebSocket = {
|
|
send: (data: string) => void;
|
|
close: (code?: number, reason?: string) => void;
|
|
onmessage: ((event: { data: unknown }) => void) | null;
|
|
onerror: ((event: { message?: string }) => void) | null;
|
|
onclose: (() => void) | null;
|
|
};
|
|
|
|
function getRecord(value: unknown): Record<string, unknown> {
|
|
assert.equal(typeof value, "object");
|
|
assert.notEqual(value, null);
|
|
assert.equal(Array.isArray(value), false);
|
|
return value as Record<string, unknown>;
|
|
}
|
|
|
|
test.afterEach(() => {
|
|
setThinkingBudgetConfig(DEFAULT_THINKING_CONFIG);
|
|
__setCodexWebSocketTransportForTesting(undefined);
|
|
});
|
|
|
|
async function withEnv<T>(entries: Record<string, string | undefined>, fn: () => T | Promise<T>) {
|
|
const previous = new Map();
|
|
|
|
for (const [key, value] of Object.entries(entries)) {
|
|
previous.set(key, process.env[key]);
|
|
if (value === undefined) {
|
|
delete process.env[key];
|
|
} else {
|
|
process.env[key] = value;
|
|
}
|
|
}
|
|
|
|
try {
|
|
return await fn();
|
|
} finally {
|
|
for (const [key, value] of previous.entries()) {
|
|
if (value === undefined) {
|
|
delete process.env[key];
|
|
} else {
|
|
process.env[key] = value;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
test("Codex helper functions isolate rate-limit scopes and parse quota headers", () => {
|
|
const quota = parseCodexQuotaHeaders({
|
|
"x-codex-5h-usage": "100",
|
|
"x-codex-5h-limit": "500",
|
|
"x-codex-5h-reset-at": new Date(Date.now() + 60_000).toISOString(),
|
|
"x-codex-7d-usage": "1000",
|
|
"x-codex-7d-limit": "5000",
|
|
"x-codex-7d-reset-at": new Date(Date.now() + 120_000).toISOString(),
|
|
});
|
|
|
|
assert.equal(getCodexModelScope("codex-spark-mini"), "spark");
|
|
assert.equal(getCodexModelScope("gpt-5.3-codex"), "codex");
|
|
assert.equal(getCodexModelScope("gpt-5.5-xhigh"), "codex");
|
|
assert.equal(getCodexUpstreamModel("gpt-5.5-xhigh"), "gpt-5.5");
|
|
assert.equal(getCodexUpstreamModel("gpt-5.5-medium"), "gpt-5.5");
|
|
// With mock WS transport + codexTransport=websocket, gpt-5.5 models require WS
|
|
__setCodexWebSocketTransportForTesting(
|
|
async (): Promise<MockCodexWebSocket> => ({
|
|
send() {},
|
|
close() {},
|
|
onmessage: null,
|
|
onerror: null,
|
|
onclose: null,
|
|
})
|
|
);
|
|
assert.equal(
|
|
isCodexResponsesWebSocketRequired("gpt-5.5-xhigh", {
|
|
providerSpecificData: { codexTransport: "websocket" },
|
|
}),
|
|
true
|
|
);
|
|
assert.equal(
|
|
isCodexResponsesWebSocketRequired("gpt-5.5-medium", {
|
|
providerSpecificData: { codexTransport: "websocket" },
|
|
}),
|
|
true
|
|
);
|
|
// Without codexTransport setting, defaults to HTTP (false)
|
|
assert.equal(isCodexResponsesWebSocketRequired("gpt-5.5-xhigh", {}), false);
|
|
assert.equal(isCodexResponsesWebSocketRequired("gpt-5.5-medium", {}), false);
|
|
__setCodexWebSocketTransportForTesting(undefined);
|
|
assert.equal(getCodexRateLimitKey("acct-1", "codex-spark-mini"), "acct-1:spark");
|
|
assert.equal(quota.usage5h, 100);
|
|
assert.equal(quota.limit7d, 5000);
|
|
assert.ok(getCodexResetTime(quota) >= new Date(quota.resetAt7d).getTime());
|
|
});
|
|
|
|
test("CodexExecutor.buildUrl honors /responses subpaths and compact mode", () => {
|
|
const executor = new CodexExecutor();
|
|
|
|
assert.equal(
|
|
executor.buildUrl("gpt-5.3-codex", true, 0, {}),
|
|
"https://chatgpt.com/backend-api/codex/responses"
|
|
);
|
|
assert.equal(
|
|
executor.buildUrl("gpt-5.3-codex", true, 0, { requestEndpointPath: "/responses" }),
|
|
"https://chatgpt.com/backend-api/codex/responses"
|
|
);
|
|
assert.equal(
|
|
executor.buildUrl("gpt-5.3-codex", true, 0, { requestEndpointPath: "/responses/compact" }),
|
|
"https://chatgpt.com/backend-api/codex/responses/compact"
|
|
);
|
|
});
|
|
|
|
test("CodexExecutor.buildHeaders binds workspace ids and disables SSE accept for compact responses", () => {
|
|
const executor = new CodexExecutor();
|
|
const standardHeaders = executor.buildHeaders(
|
|
{
|
|
accessToken: "codex-token",
|
|
providerSpecificData: { workspaceId: "workspace-1" },
|
|
},
|
|
true
|
|
);
|
|
const compactHeaders = executor.buildHeaders(
|
|
{
|
|
accessToken: "codex-token",
|
|
requestEndpointPath: "/responses/compact",
|
|
},
|
|
true
|
|
);
|
|
|
|
assert.equal(standardHeaders.Authorization, "Bearer codex-token");
|
|
assert.equal(standardHeaders.Accept, "text/event-stream");
|
|
assert.equal(standardHeaders["chatgpt-account-id"], "workspace-1");
|
|
assert.equal(standardHeaders.Version, "0.132.0");
|
|
assert.equal(standardHeaders["Openai-Beta"], "responses=experimental");
|
|
assert.equal(standardHeaders["X-Codex-Beta-Features"], "responses_websockets");
|
|
assert.equal(standardHeaders["User-Agent"], "codex-cli/0.132.0 (Windows 10.0.26200; x64)");
|
|
assert.equal(compactHeaders.Accept, "application/json");
|
|
});
|
|
|
|
test("CodexExecutor.buildHeaders honors safe env overrides for Version and User-Agent", async () => {
|
|
const executor = new CodexExecutor();
|
|
|
|
await withEnv(
|
|
{
|
|
CODEX_CLIENT_VERSION: "0.132.0",
|
|
CODEX_USER_AGENT: undefined,
|
|
},
|
|
() => {
|
|
const headers = executor.buildHeaders({ accessToken: "codex-token" }, true);
|
|
assert.equal(headers.Version, "0.132.0");
|
|
assert.equal(headers["User-Agent"], "codex-cli/0.132.0 (Windows 10.0.26200; x64)");
|
|
}
|
|
);
|
|
|
|
await withEnv(
|
|
{
|
|
CODEX_CLIENT_VERSION: "bad version value",
|
|
CODEX_USER_AGENT: "custom-codex/9.9.9",
|
|
},
|
|
() => {
|
|
const headers = executor.buildHeaders({ accessToken: "codex-token" }, true);
|
|
assert.equal(headers.Version, "0.132.0");
|
|
assert.equal(headers["User-Agent"], "custom-codex/9.9.9");
|
|
}
|
|
);
|
|
});
|
|
|
|
test("CodexExecutor.transformRequest injects default instructions, clamps reasoning and strips unsupported fields", () => {
|
|
const executor = new CodexExecutor();
|
|
const body = {
|
|
model: "gpt-5-mini",
|
|
messages: [{ role: "user", content: "hello" }],
|
|
tools: [{ type: "function", function: { name: "test_tool" } }],
|
|
prompt: "legacy",
|
|
stream_options: { include_usage: true },
|
|
instructions: "",
|
|
reasoning_effort: "xhigh",
|
|
service_tier: "fast",
|
|
temperature: 0.4,
|
|
user: "cursor",
|
|
};
|
|
|
|
const result = executor.transformRequest("gpt-5-mini-xhigh", body, false, {
|
|
requestEndpointPath: "/responses",
|
|
});
|
|
|
|
assert.equal(result.stream, true);
|
|
assert.equal(result.store, false);
|
|
assert.equal(result.instructions.length > 0, true);
|
|
assert.equal(result.reasoning.effort, "high");
|
|
assert.equal(result.service_tier, "priority");
|
|
assert.equal(result.messages, undefined);
|
|
assert.equal(result.prompt, undefined);
|
|
assert.equal(result.temperature, undefined);
|
|
assert.equal(result.user, undefined);
|
|
assert.equal(result.stream_options, undefined);
|
|
});
|
|
|
|
// Issue #2608: gpt-5.5 models reject residual Chat Completions fields via Codex OAuth.
|
|
// The non-passthrough path must strip ALL non-Responses-API fields using an allowlist.
|
|
test("CodexExecutor.transformRequest non-passthrough allowlist strips all residual Chat Completions fields (#2608)", () => {
|
|
const executor = new CodexExecutor();
|
|
const body = {
|
|
model: "gpt-5.5",
|
|
messages: [{ role: "user", content: "hello" }],
|
|
instructions: "",
|
|
// All of these are Chat Completions fields that must be stripped:
|
|
temperature: 0.7,
|
|
top_p: 0.9,
|
|
frequency_penalty: 0.5,
|
|
presence_penalty: 0.3,
|
|
logprobs: true,
|
|
top_logprobs: 3,
|
|
n: 2,
|
|
seed: 42,
|
|
stop: ["\n"],
|
|
response_format: { type: "json_object" },
|
|
logit_bias: { "123": 1 },
|
|
function_call: "auto",
|
|
functions: [{ name: "test", parameters: {} }],
|
|
max_completion_tokens: 1000,
|
|
parallel_tool_calls: true,
|
|
user: "cursor-user",
|
|
metadata: { key: "value" },
|
|
stream_options: { include_usage: true },
|
|
safety_identifier: "safe-1",
|
|
suffix: "end",
|
|
// Custom/arbitrary fields that could be injected by middleware
|
|
custom_field: "should be stripped",
|
|
_internal_marker: true,
|
|
};
|
|
|
|
const result = executor.transformRequest("gpt-5.5", body, false, {
|
|
requestEndpointPath: "/responses",
|
|
});
|
|
|
|
// Allowed Responses API fields should survive
|
|
assert.equal(result.model, "gpt-5.5");
|
|
assert.ok(Array.isArray(result.input));
|
|
assert.equal(typeof result.instructions, "string");
|
|
assert.equal(result.store, false);
|
|
assert.equal(result.stream, true);
|
|
|
|
// All Chat Completions fields must be stripped
|
|
assert.equal(result.temperature, undefined, "temperature should be stripped");
|
|
assert.equal(result.top_p, undefined, "top_p should be stripped");
|
|
assert.equal(result.frequency_penalty, undefined, "frequency_penalty should be stripped");
|
|
assert.equal(result.presence_penalty, undefined, "presence_penalty should be stripped");
|
|
assert.equal(result.logprobs, undefined, "logprobs should be stripped");
|
|
assert.equal(result.top_logprobs, undefined, "top_logprobs should be stripped");
|
|
assert.equal(result.n, undefined, "n should be stripped");
|
|
assert.equal(result.seed, undefined, "seed should be stripped");
|
|
assert.equal(result.stop, undefined, "stop should be stripped");
|
|
assert.equal(result.response_format, undefined, "response_format should be stripped");
|
|
assert.equal(result.logit_bias, undefined, "logit_bias should be stripped");
|
|
assert.equal(result.function_call, undefined, "function_call should be stripped");
|
|
assert.equal(result.functions, undefined, "functions should be stripped");
|
|
assert.equal(result.max_completion_tokens, undefined, "max_completion_tokens should be stripped");
|
|
assert.equal(result.parallel_tool_calls, undefined, "parallel_tool_calls should be stripped");
|
|
assert.equal(result.user, undefined, "user should be stripped");
|
|
assert.equal(result.metadata, undefined, "metadata should be stripped");
|
|
assert.equal(result.stream_options, undefined, "stream_options should be stripped");
|
|
assert.equal(result.safety_identifier, undefined, "safety_identifier should be stripped");
|
|
assert.equal(result.suffix, undefined, "suffix should be stripped");
|
|
assert.equal(result.custom_field, undefined, "arbitrary custom fields should be stripped");
|
|
assert.equal(result._internal_marker, undefined, "internal markers should be stripped");
|
|
});
|
|
|
|
test("CodexExecutor.transformRequest normalizes max reasoning_effort to xhigh", () => {
|
|
const executor = new CodexExecutor();
|
|
const result = executor.transformRequest(
|
|
"gpt-5.5",
|
|
{
|
|
model: "gpt-5.5",
|
|
input: [],
|
|
reasoning_effort: "max",
|
|
},
|
|
false,
|
|
{
|
|
requestEndpointPath: "/responses",
|
|
}
|
|
);
|
|
|
|
assert.equal(result.reasoning.effort, "xhigh");
|
|
assert.equal(result.reasoning_effort, undefined);
|
|
});
|
|
|
|
test("CodexExecutor.transformRequest sends neutral instructions for bare chat requests", () => {
|
|
const executor = new CodexExecutor();
|
|
const body = {
|
|
model: "gpt-5.5-medium",
|
|
input: [
|
|
{
|
|
type: "message",
|
|
role: "user",
|
|
content: [
|
|
{
|
|
type: "input_text",
|
|
text: "Calculate 79530+41475, and reply with the result only.",
|
|
},
|
|
],
|
|
},
|
|
],
|
|
instructions: "",
|
|
stream: false,
|
|
};
|
|
|
|
const result = executor.transformRequest("gpt-5.5-medium", body, false, {
|
|
requestEndpointPath: "/responses",
|
|
});
|
|
|
|
assert.equal(result.instructions, CODEX_CHAT_DEFAULT_INSTRUCTIONS);
|
|
assert.equal(result.stream, true);
|
|
assert.equal(result.model, "gpt-5.5");
|
|
assert.equal(result.input.length, 1);
|
|
assert.equal(result.tools, undefined);
|
|
});
|
|
|
|
test("CodexExecutor.transformRequest preserves compact requests and native passthrough semantics", () => {
|
|
const executor = new CodexExecutor();
|
|
const body = {
|
|
_nativeCodexPassthrough: true,
|
|
instructions: "keep this",
|
|
stream: false,
|
|
};
|
|
const result = executor.transformRequest("gpt-5.3-codex", body, false, {
|
|
requestEndpointPath: "/responses/compact",
|
|
providerSpecificData: {
|
|
requestDefaults: { serviceTier: "priority" },
|
|
},
|
|
});
|
|
|
|
assert.equal(result._nativeCodexPassthrough, undefined);
|
|
assert.equal(result.stream, undefined);
|
|
assert.equal(result.service_tier, "priority");
|
|
assert.equal(result.reasoning.effort, "medium");
|
|
assert.equal(result.store, undefined);
|
|
assert.equal(result.instructions, "keep this");
|
|
});
|
|
|
|
test("CodexExecutor.transformRequest applies flex request default service tier", () => {
|
|
const executor = new CodexExecutor();
|
|
const result = executor.transformRequest("gpt-5.5", { input: "hello" }, false, {
|
|
requestEndpointPath: "/responses",
|
|
providerSpecificData: {
|
|
requestDefaults: { serviceTier: "flex" },
|
|
},
|
|
});
|
|
|
|
assert.equal(result.service_tier, "flex");
|
|
});
|
|
|
|
test("CodexExecutor.transformRequest preserves store-enabled responses state when explicitly enabled", () => {
|
|
const executor = new CodexExecutor();
|
|
const body = {
|
|
_nativeCodexPassthrough: true,
|
|
_omnirouteResponsesStore: true,
|
|
instructions: "keep this",
|
|
previous_response_id: "resp_prev_123",
|
|
stream: false,
|
|
};
|
|
|
|
const result = executor.transformRequest("gpt-5.3-codex", body, false, {
|
|
requestEndpointPath: "/responses",
|
|
providerSpecificData: {
|
|
openaiStoreEnabled: true,
|
|
requestDefaults: { serviceTier: "priority" },
|
|
},
|
|
});
|
|
|
|
assert.equal(result._omnirouteResponsesStore, undefined);
|
|
assert.equal(result.store, true);
|
|
assert.equal(result.previous_response_id, "resp_prev_123");
|
|
});
|
|
test("CodexExecutor.transformRequest strips store from compact requests even when store is enabled", () => {
|
|
const executor = new CodexExecutor();
|
|
const body = {
|
|
_nativeCodexPassthrough: true,
|
|
_omnirouteResponsesStore: true,
|
|
instructions: "keep this",
|
|
store: true,
|
|
stream: false,
|
|
};
|
|
|
|
const result = executor.transformRequest("gpt-5.3-codex", body, false, {
|
|
requestEndpointPath: "/responses/compact",
|
|
providerSpecificData: {
|
|
openaiStoreEnabled: true,
|
|
requestDefaults: { serviceTier: "priority" },
|
|
},
|
|
});
|
|
|
|
assert.equal(result._omnirouteResponsesStore, undefined);
|
|
assert.equal(result.store, undefined);
|
|
assert.equal(result.stream, undefined);
|
|
assert.equal(result.instructions, "keep this");
|
|
});
|
|
|
|
test("CodexExecutor.transformRequest strips raw internal assistant commentary without dropping useful Responses items", () => {
|
|
const executor = new CodexExecutor();
|
|
const body = {
|
|
_nativeCodexPassthrough: true,
|
|
input: [
|
|
{
|
|
type: "message",
|
|
role: "user",
|
|
content: [{ type: "input_text", text: "Use the tool result." }],
|
|
},
|
|
{
|
|
type: "message",
|
|
role: "assistant",
|
|
phase: "commentary",
|
|
content: [{ type: "output_text", text: "Need maybe inspect tool output first." }],
|
|
},
|
|
{
|
|
type: "message",
|
|
role: "assistant",
|
|
phase: "final",
|
|
content: [{ type: "output_text", text: "Visible final assistant answer." }],
|
|
},
|
|
{
|
|
type: "message",
|
|
role: "assistant",
|
|
phase: "final_answer",
|
|
content: [{ type: "output_text", text: "Visible final_answer assistant answer." }],
|
|
},
|
|
{
|
|
type: "message",
|
|
role: "assistant",
|
|
content: [{ type: "output_text", text: "Visible assistant history without phase." }],
|
|
},
|
|
{
|
|
type: "reasoning",
|
|
summary: [{ type: "summary_text", text: "formal reasoning item" }],
|
|
},
|
|
{
|
|
type: "function_call",
|
|
call_id: "call_keep_123",
|
|
name: "workspace_read_file",
|
|
arguments: '{"path":"README.md"}',
|
|
},
|
|
{
|
|
type: "function_call_output",
|
|
call_id: "call_keep_123",
|
|
output: '{"ok":true}',
|
|
},
|
|
],
|
|
stream: false,
|
|
};
|
|
|
|
const result = executor.transformRequest("gpt-5.5-low", body, false, {
|
|
requestEndpointPath: "/responses",
|
|
});
|
|
|
|
assert.equal(
|
|
result.input.some((item) => JSON.stringify(item).includes("Need maybe inspect tool output")),
|
|
false
|
|
);
|
|
assert.equal(
|
|
result.input.some((item) => JSON.stringify(item).includes("Visible final assistant answer")),
|
|
true
|
|
);
|
|
assert.equal(
|
|
result.input.some((item) =>
|
|
JSON.stringify(item).includes("Visible final_answer assistant answer")
|
|
),
|
|
true
|
|
);
|
|
assert.equal(
|
|
result.input.some((item) =>
|
|
JSON.stringify(item).includes("Visible assistant history without phase")
|
|
),
|
|
true
|
|
);
|
|
assert.equal(
|
|
result.input.some((item) => item.type === "reasoning"),
|
|
true
|
|
);
|
|
assert.equal(
|
|
result.input.some((item) => item.type === "function_call"),
|
|
true
|
|
);
|
|
assert.equal(
|
|
result.input.some((item) => item.type === "function_call_output"),
|
|
true
|
|
);
|
|
});
|
|
|
|
test("CodexExecutor.transformRequest strips internal assistant commentary before mapping messages to input", () => {
|
|
const executor = new CodexExecutor();
|
|
const result = executor.transformRequest(
|
|
"gpt-5.5-low",
|
|
{
|
|
_nativeCodexPassthrough: true,
|
|
messages: [
|
|
{ role: "user", content: "Continue." },
|
|
{
|
|
role: "assistant",
|
|
phase: "commentary",
|
|
content: "Need maybe update PR body first.",
|
|
},
|
|
{
|
|
role: "assistant",
|
|
phase: "final",
|
|
content: "Visible final assistant answer.",
|
|
},
|
|
],
|
|
stream: false,
|
|
},
|
|
false,
|
|
{ requestEndpointPath: "/responses" }
|
|
);
|
|
|
|
assert.equal(
|
|
result.input.some((item) => JSON.stringify(item).includes("Need maybe update PR body")),
|
|
false
|
|
);
|
|
assert.equal(
|
|
result.input.some((item) => JSON.stringify(item).includes("Visible final assistant answer")),
|
|
true
|
|
);
|
|
assert.equal(result.messages, undefined);
|
|
});
|
|
|
|
test("CodexExecutor.transformRequest does not locally replay previous_response_id tool follow-ups", () => {
|
|
const executor = new CodexExecutor();
|
|
const body = {
|
|
_nativeCodexPassthrough: true,
|
|
previous_response_id: "resp_prev_tool_123",
|
|
input: [
|
|
{
|
|
type: "function_call_output",
|
|
call_id: "call_tool_123",
|
|
output: '{"ok":true}',
|
|
},
|
|
],
|
|
stream: false,
|
|
};
|
|
|
|
const result = executor.transformRequest("gpt-5.5-low", body, false, {
|
|
requestEndpointPath: "/responses",
|
|
});
|
|
|
|
assert.equal(result.previous_response_id, "resp_prev_tool_123");
|
|
assert.equal(result.store, false);
|
|
assert.equal(result.input.length, 1);
|
|
assert.deepEqual(result.input[0], {
|
|
type: "function_call_output",
|
|
call_id: "call_tool_123",
|
|
output: '{"ok":true}',
|
|
});
|
|
});
|
|
test("CodexExecutor.transformRequest applies per-connection reasoning and service tier defaults", () => {
|
|
const executor = new CodexExecutor();
|
|
const result = executor.transformRequest(
|
|
"gpt-5.3-codex",
|
|
{ model: "gpt-5.3-codex", input: [] },
|
|
false,
|
|
{
|
|
providerSpecificData: {
|
|
requestDefaults: {
|
|
reasoningEffort: "high",
|
|
serviceTier: "priority",
|
|
},
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.equal(result.reasoning.effort, "high");
|
|
assert.equal(result.service_tier, "priority");
|
|
});
|
|
|
|
test("CodexExecutor.transformRequest keeps explicit request values ahead of connection defaults", () => {
|
|
const executor = new CodexExecutor();
|
|
const result = executor.transformRequest(
|
|
"gpt-5.3-codex",
|
|
{
|
|
model: "gpt-5.3-codex",
|
|
input: [],
|
|
reasoning_effort: "none",
|
|
service_tier: "standard",
|
|
},
|
|
false,
|
|
{
|
|
providerSpecificData: {
|
|
requestDefaults: {
|
|
reasoningEffort: "high",
|
|
serviceTier: "priority",
|
|
},
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.equal(result.reasoning.effort, "none");
|
|
assert.equal(result.service_tier, "standard");
|
|
});
|
|
|
|
test("CodexExecutor.transformRequest lets model suffix beat connection reasoning defaults", () => {
|
|
const executor = new CodexExecutor();
|
|
const result = executor.transformRequest(
|
|
"gpt-5.3-codex-high",
|
|
{ model: "gpt-5.3-codex-high", input: [] },
|
|
false,
|
|
{
|
|
providerSpecificData: {
|
|
requestDefaults: {
|
|
reasoningEffort: "low",
|
|
},
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.equal(result.model, "gpt-5.3-codex");
|
|
assert.equal(result.reasoning.effort, "high");
|
|
});
|
|
|
|
test("CodexExecutor.transformRequest keeps gpt-5.5 as the model and applies xhigh reasoning", () => {
|
|
const executor = new CodexExecutor();
|
|
const result = executor.transformRequest(
|
|
"gpt-5.5-xhigh",
|
|
{ model: "gpt-5.5-xhigh", input: [] },
|
|
false,
|
|
{}
|
|
);
|
|
|
|
assert.equal(result.model, "gpt-5.5");
|
|
assert.equal(result.reasoning.effort, "xhigh");
|
|
});
|
|
|
|
test("CodexExecutor.transformRequest keeps GPT 5.3 Codex reasoning in Responses shape", () => {
|
|
const executor = new CodexExecutor();
|
|
const transformed = executor.transformRequest(
|
|
"gpt-5.3-codex",
|
|
{
|
|
model: "gpt-5.3-codex",
|
|
input: [],
|
|
reasoning_effort: "high",
|
|
},
|
|
true,
|
|
{
|
|
requestEndpointPath: "/responses",
|
|
}
|
|
);
|
|
const sanitized = sanitizeReasoningEffortForProvider(
|
|
transformed,
|
|
"codex",
|
|
"gpt-5.3-codex",
|
|
null
|
|
) as Record<string, unknown>;
|
|
const reasoning = getRecord(sanitized.reasoning);
|
|
|
|
assert.equal(sanitized.model, "gpt-5.3-codex");
|
|
assert.equal(reasoning.effort, "high");
|
|
assert.equal(sanitized.reasoning_effort, undefined);
|
|
});
|
|
|
|
test("CodexExecutor.transformRequest keeps GPT 5.4 Mini reasoning downgrade in Responses shape", () => {
|
|
const executor = new CodexExecutor();
|
|
const transformed = executor.transformRequest(
|
|
"gpt-5.4-mini",
|
|
{
|
|
model: "gpt-5.4-mini",
|
|
input: [],
|
|
reasoning: { effort: "xhigh", summary: "auto" },
|
|
},
|
|
true,
|
|
{
|
|
requestEndpointPath: "/responses",
|
|
}
|
|
);
|
|
const sanitized = sanitizeReasoningEffortForProvider(
|
|
transformed,
|
|
"codex",
|
|
"gpt-5.4-mini",
|
|
null
|
|
) as Record<string, unknown>;
|
|
const reasoning = getRecord(sanitized.reasoning);
|
|
|
|
assert.equal(sanitized.model, "gpt-5.4-mini");
|
|
assert.equal(reasoning.effort, "high");
|
|
assert.equal(reasoning.summary, "auto");
|
|
assert.equal(sanitized.reasoning_effort, undefined);
|
|
});
|
|
|
|
test("CodexExecutor.transformRequest merges Codex installation metadata", () => {
|
|
const executor = new CodexExecutor();
|
|
const result = executor.transformRequest(
|
|
"gpt-5.5",
|
|
{
|
|
model: "gpt-5.5",
|
|
input: [],
|
|
client_metadata: { existing: "keep" },
|
|
},
|
|
true,
|
|
{
|
|
providerSpecificData: {
|
|
codexClientIdentity: {
|
|
sessionId: "session-1",
|
|
turnId: "turn-1",
|
|
windowId: "session-1:0",
|
|
installationId: "11111111-1111-4111-a111-111111111111",
|
|
},
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.deepEqual(result.client_metadata, {
|
|
existing: "keep",
|
|
"x-codex-installation-id": "11111111-1111-4111-a111-111111111111",
|
|
});
|
|
});
|
|
|
|
test("CodexExecutor.transformRequest omits client metadata for compact requests", () => {
|
|
const executor = new CodexExecutor();
|
|
const result = executor.transformRequest(
|
|
"gpt-5.5",
|
|
{
|
|
model: "gpt-5.5",
|
|
input: [],
|
|
client_metadata: { existing: "drop" },
|
|
_nativeCodexPassthrough: true,
|
|
},
|
|
false,
|
|
{
|
|
requestEndpointPath: "/responses/compact",
|
|
providerSpecificData: {
|
|
codexClientIdentity: {
|
|
sessionId: "session-1",
|
|
turnId: "turn-1",
|
|
windowId: "session-1:0",
|
|
installationId: "11111111-1111-4111-a111-111111111111",
|
|
},
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.equal(result.client_metadata, undefined);
|
|
});
|
|
|
|
test("CodexExecutor.execute falls back to HTTP when websocket transport is unavailable", async () => {
|
|
__setCodexWebSocketTransportForTesting(null);
|
|
const executor = new CodexExecutor();
|
|
const originalFetch = globalThis.fetch;
|
|
|
|
globalThis.fetch = async () =>
|
|
new Response(JSON.stringify({ id: "resp_http_fallback", object: "response" }), {
|
|
status: 200,
|
|
headers: { "Content-Type": "application/json" },
|
|
});
|
|
|
|
try {
|
|
const result = await executor.execute({
|
|
model: "gpt-5.5-xhigh",
|
|
body: { model: "gpt-5.5-xhigh", input: [{ role: "user", content: "hello" }] },
|
|
stream: true,
|
|
credentials: {
|
|
accessToken: "codex-token",
|
|
providerSpecificData: { codexTransport: "websocket" },
|
|
},
|
|
});
|
|
|
|
// When WS transport is unavailable, isCodexResponsesWebSocketRequired returns false
|
|
// and the executor falls back to HTTP via super.execute()
|
|
assert.equal(result.response.status, 200);
|
|
assert.equal(getRecord(result.transformedBody).model, "gpt-5.5");
|
|
} finally {
|
|
globalThis.fetch = originalFetch;
|
|
}
|
|
});
|
|
|
|
test("CodexExecutor.execute adds CLI-like session identity headers without changing response flow", async () => {
|
|
const executor = new CodexExecutor();
|
|
const originalFetch = globalThis.fetch;
|
|
let capturedBody: Record<string, unknown> | null = null;
|
|
let capturedHeaders: Headers | null = null;
|
|
|
|
globalThis.fetch = async (_url, init) => {
|
|
capturedHeaders = new Headers(init?.headers as HeadersInit);
|
|
capturedBody = JSON.parse(String(init?.body || "{}"));
|
|
return new Response(JSON.stringify({ id: "resp_identity", object: "response" }), {
|
|
status: 200,
|
|
headers: { "Content-Type": "application/json" },
|
|
});
|
|
};
|
|
|
|
try {
|
|
const result = await executor.execute({
|
|
model: "gpt-5.5",
|
|
body: {
|
|
model: "gpt-5.5",
|
|
session_id: "conversation-1",
|
|
input: [{ role: "user", content: "hello" }],
|
|
},
|
|
stream: true,
|
|
credentials: {
|
|
accessToken: "codex-token",
|
|
providerSpecificData: { workspaceId: "workspace-1" },
|
|
},
|
|
});
|
|
|
|
assert.equal(result.response.status, 200);
|
|
assert.equal(capturedHeaders?.get("session_id"), "conversation-1");
|
|
assert.equal(capturedHeaders?.get("x-client-request-id"), "conversation-1");
|
|
assert.equal(capturedHeaders?.get("x-codex-window-id"), "conversation-1:0");
|
|
const turnMetadata = JSON.parse(capturedHeaders?.get("x-codex-turn-metadata") || "{}");
|
|
assert.equal(turnMetadata.session_id, "conversation-1");
|
|
assert.equal(turnMetadata.thread_source, "user");
|
|
assert.equal(turnMetadata.sandbox, "none");
|
|
assert.equal(typeof turnMetadata.turn_id, "string");
|
|
assert.equal(capturedBody?.prompt_cache_key, "conversation-1");
|
|
assert.equal(
|
|
(capturedBody?.client_metadata as Record<string, unknown>)?.["x-codex-installation-id"],
|
|
"7f06a8ee-2981-4c81-a4ca-e443b5400a63"
|
|
);
|
|
} finally {
|
|
globalThis.fetch = originalFetch;
|
|
}
|
|
});
|
|
|
|
test("CodexExecutor.execute skips identity headers for unsafe session ids", async () => {
|
|
const executor = new CodexExecutor();
|
|
const originalFetch = globalThis.fetch;
|
|
let capturedHeaders: Headers | null = null;
|
|
|
|
globalThis.fetch = async (_url, init) => {
|
|
capturedHeaders = new Headers(init?.headers as HeadersInit);
|
|
return new Response(JSON.stringify({ id: "resp_identity", object: "response" }), {
|
|
status: 200,
|
|
headers: { "Content-Type": "application/json" },
|
|
});
|
|
};
|
|
|
|
try {
|
|
await executor.execute({
|
|
model: "gpt-5.5",
|
|
body: {
|
|
model: "gpt-5.5",
|
|
session_id: "bad\r\nheader",
|
|
input: [{ role: "user", content: "hello" }],
|
|
},
|
|
stream: true,
|
|
credentials: { accessToken: "codex-token" },
|
|
});
|
|
|
|
assert.equal(capturedHeaders?.get("x-client-request-id"), null);
|
|
assert.equal(capturedHeaders?.get("x-codex-window-id"), null);
|
|
assert.equal(capturedHeaders?.get("x-codex-turn-metadata"), null);
|
|
} finally {
|
|
globalThis.fetch = originalFetch;
|
|
}
|
|
});
|
|
|
|
test("CodexExecutor.transformRequest preserves namespace MCP tools and hosted tool types", () => {
|
|
// Regression: PR #1581 đã vô tình xoá nhánh `namespace` + whitelist hosted tools
|
|
// trong normalizeCodexTools, khiến MCP tool group (vd. mcp__atlassian__) bị strip
|
|
// trước khi forward lên Codex Responses API. Test này khoá lại hành vi đúng.
|
|
const executor = new CodexExecutor();
|
|
const result = executor.transformRequest(
|
|
"gpt-5.4",
|
|
{
|
|
model: "gpt-5.4",
|
|
input: [],
|
|
tools: [
|
|
{ type: "function", name: "exec_command", parameters: { type: "object" } },
|
|
{
|
|
type: "namespace",
|
|
name: "mcp__atlassian__",
|
|
description: "Tools in the mcp__atlassian__ namespace.",
|
|
tools: [
|
|
{ type: "function", name: "jira_get_issue", parameters: { type: "object" } },
|
|
{ type: "function", name: "jira_search", parameters: { type: "object" } },
|
|
],
|
|
},
|
|
{ type: "image_generation", output_format: "png" },
|
|
{ type: "web_search" },
|
|
{ type: "unknown_hosted_tool" },
|
|
],
|
|
tool_choice: { type: "function", name: "jira_get_issue" },
|
|
},
|
|
false,
|
|
{}
|
|
);
|
|
|
|
const types = (result.tools as Array<Record<string, unknown>>).map((tool) => tool.type);
|
|
assert.deepEqual(types, ["function", "namespace", "image_generation", "web_search"]);
|
|
|
|
const namespaceTool = (result.tools as Array<Record<string, unknown>>).find(
|
|
(tool) => tool.type === "namespace"
|
|
);
|
|
assert.equal((namespaceTool as { name: string }).name, "mcp__atlassian__");
|
|
assert.equal(((namespaceTool as { tools: unknown[] }).tools ?? []).length, 2);
|
|
|
|
// tool_choice trỏ vào sub-tool của namespace phải được giữ nguyên (không bị xoá
|
|
// do tên nằm trong namespace.tools[*].name đã được đăng ký vào validToolNames).
|
|
assert.deepEqual(result.tool_choice, { type: "function", name: "jira_get_issue" });
|
|
});
|
|
|
|
test("CodexExecutor maps Codex websocket error events to response.failed SSE", () => {
|
|
const raw = JSON.stringify({
|
|
type: "error",
|
|
status_code: 429,
|
|
error: {
|
|
type: "usage_limit_reached",
|
|
message: "The usage limit has been reached",
|
|
},
|
|
});
|
|
|
|
const result = encodeResponseSseEvent(raw);
|
|
assert.equal(result.terminal, true);
|
|
assert.match(result.sse, /^event: response\.failed/m);
|
|
|
|
const dataLine = result.sse.split("\n").find((line) => line.startsWith("data: "));
|
|
assert.ok(dataLine);
|
|
const payload = JSON.parse(dataLine.slice("data: ".length));
|
|
assert.equal(payload.type, "response.failed");
|
|
assert.equal(payload.response.status, "failed");
|
|
assert.equal(payload.response.error.code, "usage_limit_reached");
|
|
assert.equal(payload.response.error.status_code, 429);
|
|
});
|
|
|
|
test("CodexExecutor.transformRequest does not apply connection reasoning defaults when Thinking Budget is not passthrough", () => {
|
|
const executor = new CodexExecutor();
|
|
setThinkingBudgetConfig({ mode: ThinkingMode.AUTO });
|
|
|
|
const noDefaults = executor.transformRequest(
|
|
"gpt-5.3-codex",
|
|
{ model: "gpt-5.3-codex", input: [] },
|
|
false,
|
|
{
|
|
providerSpecificData: {
|
|
requestDefaults: {
|
|
reasoningEffort: "high",
|
|
},
|
|
},
|
|
}
|
|
);
|
|
const explicit = executor.transformRequest(
|
|
"gpt-5.3-codex",
|
|
{ model: "gpt-5.3-codex", input: [], reasoning_effort: "high" },
|
|
false,
|
|
{
|
|
providerSpecificData: {
|
|
requestDefaults: {
|
|
reasoningEffort: "low",
|
|
},
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.equal(noDefaults.reasoning, undefined);
|
|
assert.equal(explicit.reasoning.effort, "high");
|
|
});
|
|
|
|
test("CodexExecutor.refreshCredentials refreshes OAuth tokens and returns null without a refresh token", async () => {
|
|
const executor = new CodexExecutor();
|
|
const originalFetch = globalThis.fetch;
|
|
globalThis.fetch = async (url) => {
|
|
assert.match(String(url), /auth\.openai\.com\/oauth\/token$/);
|
|
return new Response(
|
|
JSON.stringify({
|
|
access_token: "new-token",
|
|
refresh_token: "new-refresh",
|
|
expires_in: 3600,
|
|
}),
|
|
{ status: 200, headers: { "Content-Type": "application/json" } }
|
|
);
|
|
};
|
|
|
|
try {
|
|
assert.equal(await executor.refreshCredentials({}, null), null);
|
|
const refreshed = await executor.refreshCredentials({ refreshToken: "refresh-me" }, null);
|
|
assert.deepEqual(refreshed, {
|
|
accessToken: "new-token",
|
|
refreshToken: "new-refresh",
|
|
expiresIn: 3600,
|
|
});
|
|
} finally {
|
|
globalThis.fetch = originalFetch;
|
|
}
|
|
});
|
|
|
|
test("CodexExecutor.refreshCredentials returns null for unrecoverable errors to preserve original credentials", async () => {
|
|
// Source intentionally returns null (not an error object) so that base.ts does
|
|
// not spread stale error fields onto activeCredentials. The upstream 401/403
|
|
// drives the proper re-auth / mark-expired path instead.
|
|
// Source: open-sse/executors/codex.ts — refreshCredentials(), lines ~1205-1216.
|
|
const executor = new CodexExecutor();
|
|
const originalFetch = globalThis.fetch;
|
|
globalThis.fetch = async () =>
|
|
new Response(
|
|
JSON.stringify({ error: "invalid_grant", error_description: "Refresh token expired" }),
|
|
{ status: 400, headers: { "Content-Type": "application/json" } }
|
|
);
|
|
|
|
try {
|
|
const result = await executor.refreshCredentials({ refreshToken: "dead-token" }, null);
|
|
assert.equal(result, null, "should return null to leave original credentials untouched");
|
|
} finally {
|
|
globalThis.fetch = originalFetch;
|
|
}
|
|
});
|
|
|
|
test("CodexExecutor maps usage_limit_reached websocket failures without explicit status to 429", () => {
|
|
const raw = JSON.stringify({
|
|
type: "response.failed",
|
|
response: {
|
|
id: "resp_usage_limit",
|
|
status: "failed",
|
|
error: {
|
|
code: "usage_limit_reached",
|
|
message: "Your weekly usage limit has been reached",
|
|
},
|
|
},
|
|
});
|
|
|
|
const result = encodeResponseSseEvent(raw);
|
|
assert.equal(result.terminal, true);
|
|
|
|
const dataLine = result.sse.split("\n").find((line) => line.startsWith("data: "));
|
|
assert.ok(dataLine);
|
|
const payload = JSON.parse(dataLine.slice("data: ".length));
|
|
assert.equal(payload.type, "response.failed");
|
|
assert.equal(payload.response.id, "resp_usage_limit");
|
|
assert.equal(payload.response.error.code, "usage_limit_reached");
|
|
assert.equal(payload.response.error.status_code, 429);
|
|
});
|
|
|
|
test("Codex internal websocket bridge secret comparison handles mismatched lengths safely", async () => {
|
|
const { bridgeSecretMatches } =
|
|
await import("../../src/app/api/internal/codex-responses-ws/route.ts");
|
|
|
|
assert.equal(bridgeSecretMatches("bridge-secret", "bridge-secret"), true);
|
|
assert.equal(bridgeSecretMatches("bridge-secret", "bridge-secret-extra"), false);
|
|
assert.equal(bridgeSecretMatches("bridge-secret", ""), false);
|
|
});
|
|
|
|
test("Codex internal websocket bridge rejects non-object JSON payloads", async () => {
|
|
await withEnv({ OMNIROUTE_WS_BRIDGE_SECRET: "bridge-secret" }, async () => {
|
|
const { POST } = await import("../../src/app/api/internal/codex-responses-ws/route.ts");
|
|
|
|
const response = await POST(
|
|
new Request("http://omniroute.local/api/internal/codex-responses-ws", {
|
|
method: "POST",
|
|
headers: {
|
|
"content-type": "application/json",
|
|
"x-omniroute-ws-bridge-secret": "bridge-secret",
|
|
},
|
|
body: JSON.stringify(["invalid"]),
|
|
})
|
|
);
|
|
const body = await response.json();
|
|
|
|
assert.equal(response.status, 400);
|
|
assert.equal(body.error.code, "invalid_json");
|
|
assert.match(body.error.message, /JSON object/);
|
|
});
|
|
});
|