Files
OmniRoute/tests/unit/executor-codex.test.ts
Diego Rodrigues de Sa e Souza f59f8daa94 Release v3.8.6 (#2804)
* 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>
2026-05-29 12:44:29 -03:00

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/);
});
});