Files
OmniRoute/tests/unit/translator-helper-branches.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

850 lines
29 KiB
TypeScript

import test from "node:test";
import assert from "node:assert/strict";
const schemaCoercion = await import("../../open-sse/translator/helpers/schemaCoercion.ts");
const openaiHelper = await import("../../open-sse/translator/helpers/openaiHelper.ts");
const claudeHelper = await import("../../open-sse/translator/helpers/claudeHelper.ts");
const geminiHelper = await import("../../open-sse/translator/helpers/geminiHelper.ts");
const toolCallHelper = await import("../../open-sse/translator/helpers/toolCallHelper.ts");
const { FORMATS } = await import("../../open-sse/translator/formats.ts");
const { translateRequest } = await import("../../open-sse/translator/index.ts");
const { cacheReasoningByKey, clearReasoningCacheAll, getReasoningCacheServiceStats } =
await import("../../open-sse/services/reasoningCache.ts");
const { clearModelsDevCapabilities, saveModelsDevCapabilities } =
await import("../../src/lib/modelsDevSync.ts");
function buildCapability(overrides = {}) {
return {
tool_call: null,
reasoning: null,
attachment: null,
structured_output: null,
temperature: null,
modalities_input: "[]",
modalities_output: "[]",
knowledge_cutoff: null,
release_date: null,
last_updated: null,
status: null,
family: null,
open_weights: null,
limit_context: null,
limit_input: null,
limit_output: null,
interleaved_field: null,
...overrides,
};
}
const originalMathRandom = Math.random;
test.afterEach(() => {
Math.random = originalMathRandom;
});
test("schemaCoercion recursively coerces schema numeric fields across object variants", () => {
const result = schemaCoercion.coerceSchemaNumericFields({
minimum: "1",
maxItems: "5",
properties: {
nested: {
minLength: "2",
items: { maximum: "7" },
},
},
patternProperties: {
"^x-": { minProperties: "1" },
},
definitions: {
one: { exclusiveMaximum: "9" },
},
$defs: {
two: { minItems: "3" },
},
dependentSchemas: {
dep: { maxProperties: "4" },
},
additionalProperties: { maximum: "8" },
unevaluatedProperties: { minimum: "0" },
prefixItems: [{ minimum: "11" }],
anyOf: [{ maximum: "12" }],
oneOf: [{ minimum: "13" }],
allOf: [{ maxLength: "14" }],
not: { minimum: "15" },
if: { minimum: "16" },
then: { maximum: "17" },
else: { minItems: "18" },
});
assert.equal((result as any).minimum, 1);
(assert as any).equal((result as any).maxItems, 5);
(assert as any).equal((result as any).properties.nested.minLength, 2);
assert.equal((result as any).properties.nested.items.maximum, 7);
assert.equal((result as any).patternProperties["^x-"].minProperties, 1);
assert.equal((result as any).definitions.one.exclusiveMaximum, 9);
assert.equal((result as any).$defs.two.minItems, 3);
assert.equal((result as any).dependentSchemas.dep.maxProperties, 4);
assert.equal((result as any).additionalProperties.maximum, 8);
assert.equal((result as any).unevaluatedProperties.minimum, 0);
assert.equal((result as any).prefixItems[0].minimum, 11);
assert.equal((result as any).anyOf[0].maximum, 12);
assert.equal((result as any).oneOf[0].minimum, 13);
assert.equal((result as any).allOf[0].maxLength, 14);
assert.equal((result as any).not.minimum, 15);
assert.equal((result as any).if.minimum, 16);
assert.equal((result as any).then.maximum, 17);
assert.equal((result as any).else.minItems, 18);
assert.equal(schemaCoercion.coerceSchemaNumericFields("unchanged"), "unchanged");
assert.deepEqual(schemaCoercion.coerceSchemaNumericFields(["2", { minimum: "3" }]), [
"2",
{ minimum: 3 },
]);
});
test("schemaCoercion sanitizes descriptions, tool schemas, tool ids and deepseek reasoning placeholders", () => {
const sanitizedOpenAI = schemaCoercion.sanitizeToolDescription({
type: "function",
function: { name: "weather", description: 42 },
});
(assert as any).equal((sanitizedOpenAI as any).function.description, "42");
const sanitizedClaude = schemaCoercion.sanitizeToolDescription({
name: "weather",
description: null,
});
assert.equal((sanitizedClaude as any).description, "");
const sanitizedGemini = schemaCoercion.sanitizeToolDescription({
functionDeclarations: [{ name: "one", description: 12 }, { name: "two" }],
});
assert.equal((sanitizedGemini as any).functionDeclarations[0].description, "12");
assert.equal((sanitizedGemini as any).functionDeclarations[1].name, "two");
assert.equal(schemaCoercion.sanitizeToolDescription("plain"), "plain");
const coercedTools = schemaCoercion.coerceToolSchemas([
{
type: "function",
function: { parameters: { minimum: "4" } },
},
{
name: "claude-style",
input_schema: { minItems: "2" },
},
{
parameters: { maximum: "9" },
},
{
functionDeclarations: [{ parameters: { minLength: "1" } }],
},
"untouched",
]);
assert.equal(coercedTools[0].function.parameters.minimum, 4);
assert.equal(coercedTools[1].input_schema.minItems, 2);
assert.equal(coercedTools[2].parameters.maximum, 9);
assert.equal(coercedTools[3].functionDeclarations[0].parameters.minLength, 1);
assert.equal(coercedTools[4], "untouched");
assert.equal(schemaCoercion.coerceToolSchemas("not-array"), "not-array");
const descriptionList = schemaCoercion.sanitizeToolDescriptions([{ description: 7 }, "raw"]);
assert.equal(descriptionList[0].description, "7");
assert.equal(descriptionList[1], "raw");
assert.equal(schemaCoercion.sanitizeToolDescriptions("raw"), "raw");
assert.equal(schemaCoercion.sanitizeToolId("call.abc:123"), "call_abc_123");
assert.match(schemaCoercion.sanitizeToolId(""), /^tool_[a-z0-9_]+$/);
assert.match(schemaCoercion.sanitizeToolId(undefined), /^tool_[a-z0-9_]+$/);
const injected = schemaCoercion.injectEmptyReasoningContentForToolCalls(
[
{ role: "assistant", tool_calls: [{ id: "call_1" }] },
{ role: "assistant", tool_calls: [{ id: "call_2" }], reasoning_content: "keep" },
{ role: "user", tool_calls: [{ id: "call_3" }] },
],
"deepseek",
"deepseek-v4-flash"
);
assert.equal(injected[0].reasoning_content, "");
assert.equal(injected[1].reasoning_content, "keep");
assert.equal(injected[2].reasoning_content, undefined);
assert.equal(
schemaCoercion.injectEmptyReasoningContentForToolCalls(
[{ role: "assistant" }],
"openai",
"gpt-4o"
)[0].reasoning_content,
undefined
);
});
test("openaiHelper filters content, normalizes tools and removes OpenAI-incompatible fields", () => {
const body = {
messages: [
{ role: "tool", content: "" },
{ role: "assistant", tool_calls: [{ id: "call_1" }], content: "" },
{
role: "assistant",
content: [
{ type: "thinking", thinking: "plan first" },
{ type: "redacted_thinking", text: "skip" },
{ type: "text", text: "visible text" },
{ type: "image_url", image_url: { url: "https://example.com/a.png" }, signature: "x" },
{ type: "tool_use", id: "call_1" },
{ type: "tool_result", tool_use_id: "call_1", text: "done", cache_control: "drop" },
],
},
{ role: "user", content: [{ type: "text", text: " " }] },
{ role: "assistant", content: [{ type: "tool_result", tool_use_id: "call_2" }] },
],
tools: [
{
name: "claude-tool",
description: "Claude style",
input_schema: { type: "object" },
},
{
functionDeclarations: [
{ name: "gemini-tool", description: "Gemini style", parameters: { type: "object" } },
],
},
{
type: "function",
function: { name: "openai-tool", parameters: { type: "object" } },
},
],
tool_choice: { type: "tool", name: "forced_tool" },
metadata: { remove: true },
anthropic_version: "2023-06-01",
};
const result = openaiHelper.filterToOpenAIFormat(body);
assert.equal(result.messages.length, 3);
assert.equal(result.messages[2].reasoning_content, "plan first");
assert.deepEqual(result.messages[2].content, [
{ type: "text", text: "visible text" },
{ type: "image_url", image_url: { url: "https://example.com/a.png" } },
{ type: "text", text: "[Tool Result: call_1]\ndone" },
]);
assert.equal(result.tools.length, 3);
assert.equal(result.tools[0].function.name, "claude-tool");
assert.equal(result.tools[1].function.name, "gemini-tool");
assert.equal(result.tools[2].function.name, "openai-tool");
assert.deepEqual(result.tool_choice, { type: "function", function: { name: "forced_tool" } });
assert.equal("metadata" in result, false);
assert.equal("anthropic_version" in result, false);
});
test("openaiHelper keeps unmatched tool choices and deletes empty tools arrays", () => {
const autoChoice = openaiHelper.filterToOpenAIFormat({
messages: [{ role: "assistant", content: "" }],
tools: [],
tool_choice: { type: "auto" },
});
assert.equal(autoChoice.tool_choice, "auto");
assert.equal("tools" in autoChoice, false);
const requiredChoice = openaiHelper.filterToOpenAIFormat({
messages: [{ role: "assistant", content: "" }],
tool_choice: { type: "any" },
});
assert.equal(requiredChoice.tool_choice, "required");
const untouched = { metadata: { keep: false } };
assert.deepEqual(openaiHelper.filterToOpenAIFormat(untouched), {
metadata: { keep: false },
});
});
test("claudeHelper validates content, ordering and request preparation branches", () => {
assert.equal(claudeHelper.hasValidContent({ content: " hello " }), true);
assert.equal(claudeHelper.hasValidContent({ content: [{ type: "tool_use", id: "call" }] }), true);
assert.equal(claudeHelper.hasValidContent({ content: [{ type: "text", text: " " }] }), false);
assert.deepEqual(claudeHelper.fixToolUseOrdering([{ role: "user", content: "single" }]), [
{ role: "user", content: "single" },
]);
const reordered = claudeHelper.fixToolUseOrdering([
{
role: "assistant",
content: [
{ type: "text", text: "before" },
{ type: "tool_use", id: "call_1", name: "lookup", input: {} },
{ type: "text", text: "after" },
],
},
{ role: "assistant", content: [{ type: "tool_result", tool_use_id: "call_1", content: [] }] },
]);
assert.deepEqual(reordered[0].content, [
{ type: "tool_result", tool_use_id: "call_1", content: [] },
{ type: "text", text: "before" },
{ type: "tool_use", id: "call_1", name: "lookup", input: {} },
]);
// splitMisplacedToolResults: a tool_result whose tool_use_id was already
// emitted by an earlier assistant turn is moved into the preceding user
// message. The trailing tool_use survives on the assistant side. (#2815)
const split = claudeHelper.splitMisplacedToolResults([
{ role: "user", content: [{ type: "text", text: "q" }] },
{ role: "assistant", content: [{ type: "tool_use", id: "call_x", name: "Read", input: {} }] },
{
role: "assistant",
content: [
{ type: "tool_result", tool_use_id: "call_x", content: "ok" },
{ type: "tool_use", id: "call_y", name: "Read", input: {} },
],
},
]);
assert.deepEqual(split, [
{ role: "user", content: [{ type: "text", text: "q" }] },
{ role: "assistant", content: [{ type: "tool_use", id: "call_x", name: "Read", input: {} }] },
{ role: "user", content: [{ type: "tool_result", tool_use_id: "call_x", content: "ok" }] },
{ role: "assistant", content: [{ type: "tool_use", id: "call_y", name: "Read", input: {} }] },
]);
// tool_result whose id has not been seen earlier is dropped — moving it
// would just shift the 400 to "unexpected tool_use_id".
const droppedOrphan = claudeHelper.splitMisplacedToolResults([
{ role: "user", content: [{ type: "text", text: "q" }] },
{
role: "assistant",
content: [
{ type: "tool_result", tool_use_id: "self-ref", content: "Skill not found" },
{ type: "tool_use", id: "self-ref", name: "Read", input: {} },
],
},
]);
assert.deepEqual(droppedOrphan, [
{ role: "user", content: [{ type: "text", text: "q" }] },
{ role: "assistant", content: [{ type: "tool_use", id: "self-ref", name: "Read", input: {} }] },
]);
const prepared = claudeHelper.prepareClaudeRequest(
{
system: [
{ type: "text", text: "one", cache_control: { type: "ephemeral" } },
{ type: "text", text: "two", cache_control: { type: "ephemeral" } },
],
messages: [
{ role: "user", content: [{ type: "text", text: "first question" }] },
{ role: "assistant", content: "first answer" },
{ role: "user", content: [{ type: "text", text: "follow up" }] },
{
role: "assistant",
content: [
{ type: "text", text: "before tool" },
{ type: "tool_use", id: "call_1", name: "lookup", input: {} },
{ type: "text", text: "drop after" },
{ type: "redacted_thinking", text: "keep" },
],
},
{
role: "user",
content: [
{ type: "tool_result", tool_use_id: "call_1", content: "ok" },
{ type: "tool_result", content: "drop missing id" },
],
},
{
role: "assistant",
content: [
{ type: "thinking", thinking: "old", signature: "replace" },
{ type: "tool_use", id: "call_2", name: " ", input: {} },
{ type: "text", text: "" },
],
},
],
thinking: { type: "enabled" },
tools: [
{ name: "", description: "drop me" },
{ name: "deferred", defer_loading: true, cache_control: { type: "ephemeral" } },
{ name: "kept-tool", cache_control: { type: "ephemeral" } },
],
},
"claude",
false
);
assert.deepEqual(prepared.system[0], { type: "text", text: "one" });
assert.deepEqual(prepared.system[1], {
type: "text",
text: "two",
cache_control: { type: "ephemeral", ttl: "1h" },
});
assert.equal(prepared.messages.length, 6);
assert.equal(prepared.messages[2].content.at(-1).cache_control.type, "ephemeral");
assert.equal(prepared.messages[4].content[0].type, "tool_result");
// messages[5] is the latest (and last) assistant message; Anthropic enforces
// that its thinking blocks must remain verbatim — not rewritten to
// redacted_thinking. The guard in prepareClaudeRequest preserves them.
assert.deepEqual(
prepared.messages[5].content.map((block) => block.type),
["thinking", "text"]
);
assert.equal(prepared.messages[5].content[0].thinking, "old", "thinking text preserved verbatim");
assert.equal(
prepared.messages[5].content[0].signature,
"replace",
"signature preserved verbatim"
);
assert.equal(
prepared.messages[5].content[0].data,
undefined,
"no data field on verbatim thinking"
);
assert.equal(prepared.tools.length, 2);
assert.equal(prepared.tools[0].cache_control, undefined);
assert.deepEqual(prepared.tools[1].cache_control, { type: "ephemeral", ttl: "1h" });
const preserved = claudeHelper.prepareClaudeRequest(
{
messages: [
{
role: "assistant",
content: [{ type: "text", text: "keep cache", cache_control: { type: "ephemeral" } }],
},
],
tools: [{ name: "kept", cache_control: { type: "ephemeral" } }],
},
"openai",
true
);
assert.deepEqual(preserved.messages[0].content[0].cache_control, { type: "ephemeral" });
assert.deepEqual(preserved.tools[0].cache_control, { type: "ephemeral" });
});
test("geminiHelper converts content, safely parses JSON and cleans complex schemas", () => {
assert.deepEqual(geminiHelper.convertOpenAIContentToParts("hello"), [{ text: "hello" }]);
assert.deepEqual(
geminiHelper.convertOpenAIContentToParts([
{ type: "text", text: "hello" },
{ type: "image_url", image_url: { url: "data:image/png;base64,abc" } },
{ type: "file_url", file_url: { url: "not-a-data-url" } },
]),
[{ text: "hello" }, { inlineData: { mimeType: "image/png", data: "abc" } }]
);
assert.equal(
geminiHelper.extractTextContent([
{ type: "text", text: "A" },
{ type: "image_url", image_url: { url: "https://example.com" } },
{ type: "text", text: "B" },
]),
"AB"
);
assert.equal(geminiHelper.extractTextContent({ no: "text" }), "");
assert.deepEqual(geminiHelper.tryParseJSON('{"ok":true}'), { ok: true });
assert.equal(geminiHelper.tryParseJSON("{broken"), null);
assert.equal(geminiHelper.tryParseJSON(42), 42);
assert.match(geminiHelper.generateRequestId(), /^agent-/);
assert.match(geminiHelper.generateSessionId(), /^-/);
const schema = {
type: ["null", "object"],
properties: {},
required: ["missing"],
anyOf: [{ type: "null" }, { type: "string", enum: [1, 2] }],
oneOf: [{ type: "null" }, { type: "array", items: { type: "integer", enum: [1, 2] } }],
allOf: [
{ properties: { a: { type: "string", minLength: 2 } }, required: ["a"] },
{ properties: { b: { const: "fixed" } }, required: ["b"] },
],
additionalProperties: false,
patternProperties: { "^x-": { type: "number" } },
if: { type: "string" },
then: { type: "string" },
else: { type: "string" },
default: "remove",
examples: ["remove"],
};
const cleaned = geminiHelper.cleanJSONSchemaForAntigravity(schema);
assert.equal(cleaned.type, "array");
assert.deepEqual(cleaned.required.sort(), ["a", "b"]);
assert.equal(cleaned.properties.a.minLength, undefined);
assert.deepEqual(cleaned.properties.b.enum, ["fixed"]);
assert.deepEqual(cleaned.enum, ["1", "2"]);
assert.equal(cleaned.items.type, "integer");
assert.equal(cleaned.additionalProperties, undefined);
assert.equal(cleaned.patternProperties, undefined);
assert.equal(cleaned.if, undefined);
assert.equal(cleaned.default, undefined);
assert.equal(cleaned.examples, undefined);
const placeholder = geminiHelper.cleanJSONSchemaForAntigravity({
type: "object",
properties: {},
});
assert.deepEqual(placeholder.required, ["reason"]);
assert.equal(placeholder.properties.reason.type, "string");
});
test("toolCallHelper normalizes ids, links tool responses and inserts missing tool results", () => {
let randomCalls = 0;
Math.random = () => ((randomCalls++ % 50) + 1) / 100;
const body = toolCallHelper.ensureToolCallIds(
{
messages: [
{
role: "assistant",
tool_calls: [
{ function: { name: "first", arguments: { city: "Tokyo" } } },
{ id: " ", function: { name: "second", arguments: "{}" } },
],
},
{ role: "tool", content: "first result" },
{ role: "tool", content: "second result" },
],
},
{ use9CharId: true }
);
assert.equal(body.messages[0].tool_calls[0].type, "function");
assert.equal(typeof body.messages[0].tool_calls[0].function.arguments, "string");
assert.match(body.messages[0].tool_calls[0].id, /^[a-zA-Z0-9]{9}$/);
assert.match(body.messages[1].tool_call_id, /^[a-zA-Z0-9]{9}$/);
assert.match(body.messages[2].tool_call_id, /^[a-zA-Z0-9]{9}$/);
const missingResponseFixed = toolCallHelper.fixMissingToolResponses({
messages: [
{
role: "assistant",
tool_calls: [{ id: "call_a", function: { name: "lookup", arguments: "{}" } }],
},
{ role: "user", content: "no tool result here" },
{
role: "assistant",
content: [{ type: "tool_use", id: "call_b", name: "search", input: {} }],
},
{
role: "user",
content: [{ type: "tool_result", tool_use_id: "call_b", content: "done" }],
},
],
});
assert.equal(missingResponseFixed.messages[1].role, "tool");
assert.equal(missingResponseFixed.messages[1].tool_call_id, "call_a");
assert.equal(missingResponseFixed.messages[1].content, "");
assert.deepEqual(
toolCallHelper.getToolCallIds({
role: "assistant",
tool_calls: [{ id: "call_a" }],
content: [{ type: "tool_use", id: "call_b" }],
}),
["call_a", "call_b"]
);
assert.equal(toolCallHelper.getToolCallIds({ role: "user" }).length, 0);
assert.equal(
toolCallHelper.hasToolResults({ role: "tool", tool_call_id: "call_a" }, ["call_a"]),
true
);
assert.equal(
toolCallHelper.hasToolResults(
{ role: "user", content: [{ type: "tool_result", tool_use_id: "call_b" }] },
["call_b"]
),
true
);
assert.equal(toolCallHelper.hasToolResults({ role: "user", content: [] }, []), false);
assert.deepEqual(toolCallHelper.fixMissingToolResponses({ messages: null }), { messages: null });
});
test("fixMissingToolResponses inserts Claude tool_result block when assistant uses Claude shape", () => {
const fixed = toolCallHelper.fixMissingToolResponses({
messages: [
{ role: "user", content: [{ type: "text", text: "do it" }] },
{
role: "assistant",
content: [
{ type: "tool_use", id: "tool_a", name: "bash", input: { cmd: "ls" } },
{ type: "tool_use", id: "tool_b", name: "bash", input: { cmd: "pwd" } },
],
},
{ role: "user", content: [{ type: "text", text: "continue" }] },
],
});
assert.equal(fixed.messages.length, 4);
const inserted = fixed.messages[2];
assert.equal(inserted.role, "user");
assert.ok(Array.isArray(inserted.content));
assert.equal(inserted.content.length, 2);
assert.equal(inserted.content[0].type, "tool_result");
assert.equal(inserted.content[0].tool_use_id, "tool_a");
assert.equal(inserted.content[0].content, "");
assert.equal(inserted.content[1].tool_use_id, "tool_b");
});
test("fixMissingToolResponses keeps OpenAI role:tool when assistant uses OpenAI tool_calls", () => {
const fixed = toolCallHelper.fixMissingToolResponses({
messages: [
{
role: "assistant",
tool_calls: [
{ id: "call_a", type: "function", function: { name: "lookup", arguments: "{}" } },
{ id: "call_b", type: "function", function: { name: "search", arguments: "{}" } },
],
},
{ role: "user", content: "no tool result here" },
],
});
assert.equal(fixed.messages.length, 4);
assert.equal(fixed.messages[1].role, "tool");
assert.equal(fixed.messages[1].tool_call_id, "call_a");
assert.equal(fixed.messages[2].role, "tool");
assert.equal(fixed.messages[2].tool_call_id, "call_b");
});
test("translateRequest replays cached reasoning-only messages when interleaved field is reasoning_content", () => {
clearReasoningCacheAll();
clearModelsDevCapabilities();
saveModelsDevCapabilities({
deepseek: {
"deepseek-v4-flash": buildCapability({
interleaved_field: "reasoning_content",
reasoning: true,
tool_call: true,
}),
},
});
cacheReasoningByKey(
"request:req_reasoning_only:message:0",
"deepseek",
"deepseek-v4-flash",
"cached reasoning only"
);
const result = translateRequest(
FORMATS.OPENAI,
FORMATS.OPENAI,
"deepseek-v4-flash",
{
_reasoningCacheRequestId: "req_reasoning_only",
messages: [
{ role: "user", content: "solve this" },
{ role: "assistant", content: "answer", reasoning_content: "" },
],
},
false,
null,
"deepseek"
);
assert.equal(result.messages[1].reasoning_content, "cached reasoning only");
assert.equal(getReasoningCacheServiceStats().replays, 1);
clearModelsDevCapabilities();
clearReasoningCacheAll();
});
test("translateRequest does not replay reasoning-only messages for non-DeepSeek models", () => {
clearReasoningCacheAll();
cacheReasoningByKey(
"request:req_kimi_reasoning_only:message:0",
"kimi",
"kimi-k2.5",
"cached kimi reasoning"
);
const result = translateRequest(
FORMATS.OPENAI,
FORMATS.OPENAI,
"kimi-k2.5",
{
_reasoningCacheRequestId: "req_kimi_reasoning_only",
messages: [
{ role: "user", content: "solve this" },
{ role: "assistant", content: "answer", reasoning_content: "" },
],
},
false,
null,
"kimi"
);
assert.equal(result.messages[1].reasoning_content, undefined);
assert.equal(getReasoningCacheServiceStats().replays, 0);
clearReasoningCacheAll();
});
test("translateRequest injects thinking block into Claude-format messages for Kimi K2 reasoning models", () => {
clearReasoningCacheAll();
clearModelsDevCapabilities();
saveModelsDevCapabilities({
"kimi-coding": {
"kimi-k2.5": buildCapability({
interleaved_field: "reasoning_content",
reasoning: true,
tool_call: true,
}),
},
});
cacheReasoningByKey(
"toolu_kimi_claude",
"kimi-coding",
"kimi-k2.5",
"cached thinking for Kimi tool call"
);
// Claude-format request: assistant has tool_use in content[] but NO thinking block
// This simulates the scenario that causes infinite loops
const result = translateRequest(
FORMATS.OPENAI,
FORMATS.CLAUDE,
"kimi-k2.5",
{
thinking: { type: "enabled", budget_tokens: 2000 },
messages: [
{ role: "user", content: "read the file" },
{
role: "assistant",
content: [
{
type: "tool_use",
id: "toolu_kimi_claude",
name: "read_file",
input: { path: "test.ts" },
},
],
},
{ role: "tool", tool_call_id: "toolu_kimi_claude", content: "file data" },
],
},
false,
null,
"kimi-coding"
);
const assistantMsg = result.messages.find((m) => m.role === "assistant");
assert.ok(assistantMsg, "assistant message should exist");
assert.ok(Array.isArray(assistantMsg.content), "content should be array");
// Should have a thinking block injected before tool_use
const thinkingBlock = assistantMsg.content.find((b) => b?.type === "thinking");
assert.ok(thinkingBlock, "thinking block should be injected");
assert.equal(
thinkingBlock.thinking,
"cached thinking for Kimi tool call",
"should use cached reasoning"
);
// Thinking block should appear before tool_use
const thinkingIdx = assistantMsg.content.indexOf(thinkingBlock);
const toolUseIdx = assistantMsg.content.findIndex((b) => b?.type === "tool_use");
assert.ok(thinkingIdx < toolUseIdx, "thinking block should be before tool_use");
assert.equal(getReasoningCacheServiceStats().replays, 1);
clearModelsDevCapabilities();
clearReasoningCacheAll();
});
test("translateRequest injects placeholder thinking block for Claude-format Kimi K2 on cache miss", () => {
clearReasoningCacheAll();
clearModelsDevCapabilities();
saveModelsDevCapabilities({
"kimi-coding": {
"kimi-k2.6": buildCapability({
interleaved_field: "reasoning_content",
reasoning: true,
tool_call: true,
}),
},
});
// No cache seeded - should fall back to placeholder
const result = translateRequest(
FORMATS.OPENAI,
FORMATS.CLAUDE,
"kimi-k2.6",
{
thinking: { type: "enabled", budget_tokens: 2000 },
messages: [
{ role: "user", content: "do it" },
{
role: "assistant",
content: [
{ type: "tool_use", id: "toolu_miss", name: "bash", input: { command: "ls" } },
],
},
{ role: "tool", tool_call_id: "toolu_miss", content: "output" },
],
},
false,
null,
"kimi-coding"
);
const assistantMsg = result.messages.find((m) => m.role === "assistant");
assert.ok(assistantMsg, "assistant message should exist");
const thinkingBlock =
Array.isArray(assistantMsg.content) &&
assistantMsg.content.find((b) => b?.type === "thinking");
assert.ok(thinkingBlock, "thinking block should be injected on cache miss");
// Must be non-empty for kimi-coding
assert.ok(
thinkingBlock.thinking && thinkingBlock.thinking.length > 0,
"placeholder must be non-empty"
);
clearModelsDevCapabilities();
clearReasoningCacheAll();
});
test("translateRequest does NOT inject duplicate thinking for Claude-format messages with existing thinking block", () => {
clearReasoningCacheAll();
clearModelsDevCapabilities();
saveModelsDevCapabilities({
"kimi-coding": {
"kimi-k2.5": buildCapability({
interleaved_field: "reasoning_content",
reasoning: true,
tool_call: true,
}),
},
});
const result = translateRequest(
FORMATS.OPENAI,
FORMATS.CLAUDE,
"kimi-k2.5",
{
messages: [
{ role: "user", content: "hi" },
{
role: "assistant",
content: [
{ type: "thinking", thinking: "I already have this" },
{ type: "tool_use", id: "toolu_existing", name: "read", input: {} },
],
},
{ role: "tool", tool_call_id: "toolu_existing", content: "data" },
],
},
false,
null,
"kimi-coding"
);
const assistantMsg = result.messages.find((m) => m.role === "assistant");
const thinkingBlocks =
Array.isArray(assistantMsg.content) &&
assistantMsg.content.filter((b) => b?.type === "thinking");
assert.equal(
thinkingBlocks?.length,
1,
"should have exactly one thinking block (no duplicate)"
);
assert.equal(
thinkingBlocks[0].thinking,
"I already have this",
"original thinking should be preserved"
);
clearModelsDevCapabilities();
clearReasoningCacheAll();
});