mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-07-31 20:32:20 +03:00
* fix(gemini): preserve structured tool calls for antigravity * fix(gemini): parse prefixed textual tool calls * fix(antigravity): preserve textual SSE tool calls * fix(stream): normalize textual passthrough tool calls * fix(stream): normalize split textual tool calls * fix(stream): suppress malformed textual tool calls * fix(stream): suppress compact malformed tool calls * fix(stream): emit structured textual tool calls * fix(stream): suppress unknown textual tool calls * fix(stream): normalize responses textual tool calls * chore: ignore .claude/settings.local.json (per-user Claude Code permissions) * fix(opencode-go): route qwen3.x via claude messages + repair fixMissingToolResponses for Claude-shape upstreams (#2791) Integrated into release/v3.8.6 * fix: resolve npm install warnings — remove dead deps, relax engine constraint (#2792) Integrated into release/v3.8.6 * fix: register missing web-cookie validators (claude-web, gemini-web, copilot-web, t3-web) (#2793) Integrated into release/v3.8.6 * fix: Error: Unable to inspect existing database #2771 (#2795) Integrated into release/v3.8.6 * fix(oauth): repair Google loopback callback flow (#2796) Integrated into release/v3.8.6 * feat(logs): add clean history button (#2799) Integrated into release/v3.8.6 * [codex] home: restore settings-driven home layout and quota auto-refresh (#2800) Integrated into release/v3.8.6 * fix(gemini): emit signaturelessToolCallMode:text for GEMINI format models (#2801) Integrated into release/v3.8.6 * feat(modelSpecs): align opencode-go family with upstream provider limits (#2802) Integrated into release/v3.8.6 * chore: apply unit test fixes, polyfills, and environment precedence fixes * docs(agents): atualiza fluxos de release e triagem Expande os workflows de release para incluir auditoria de segurança, CHANGELOG completo por commits, quality gate obrigatório, homologação em VPS local, publicação oficial, deploy em Akamai e validação de artefatos. Reorganiza a triagem de features com arquivos permanentes por bucket, suporte a itens em andamento, regra de reclaim após 15 dias e novo tratamento para ideias viáveis catalogadas. Corrige a orientação de revisão de discussões para usar a ordem cronológica real dos comentários e respostas ao identificar a última atividade. * fix(lockout): classify Gemini Antigravity resource exhaustion as quota_exhausted * fix(reasoning): gate replay by interleaved field * docs(rule-16): permit human Co-authored-by, restrict only AI/bot trailers Rule #16 previously banned all `Co-Authored-By` trailers absolutely. That blocked the upstream-port workflows (`/port-upstream-features` and `/port-upstream-issues`), which must credit human upstream PR authors and issue reporters in OmniRoute commits. Refine the rule to ban only AI/bot-attributed trailers (Claude, GPT, Copilot, Bot; anthropic.com / openai.com / bot-owned noreply.github.com emails) while allowing standard human `Co-authored-by: Name <email>` attribution. Sync the rule across the source CLAUDE.md, the E2E shakedown doc note, and 41 i18n translations. * fix(gitlawb): add specialty validators for connection test — bypass /models probe GitLawB OpenGateway API (xiaomi-mimo compatible) does not expose a /models endpoint, causing validateOpenAILikeProvider to 404 on the initial probe and report 'Provider validation endpoint not supported'. Add specialty validators for both gitlawb and gitlawb-gmi that follow the same pattern as the existing xiaomi-mimo validator: skip GET /models, validate directly via POST /chat/completions with a minimal test message. Any 401/403 response means an invalid key; all other responses mean auth is OK. Fixes test-connection returning 404 for GitLawB providers. * test(gitlawb): add 12 unit tests for gitlawb and gitlawb-gmi specialty validators Covers success, auth failure (401/403), non-auth acceptance (400/422/429), network errors, and custom baseUrl overrides for both providers. * feat(gitlawb): serve models from static registry without API-unavailable warning GitLawB's OpenGateway API does not expose a /models endpoint per provider-path. Previously the models route fell through to the generic fallback which returned static catalog models with the misleading 'API unavailable — using local catalog' warning. Now gitlawb and gitlawb-gmi are handled as static model providers (same pattern as reka and qwen OAuth) — models are served from the provider registry without any warning, since all registered models are functional via POST /chat/completions. * refactor(gitlawb): extract shared opengateway validator factory, fix docs path in test - Extract gitlawb/gitlawb-gmi validators into buildOpengatewayValidator factory - Fix dockerignore-docs-coverage test: update stale docs/AUTO-COMBO.md -> docs/routing/AUTO-COMBO.md * fix(reasoning): guard interleaved capability lookup * feat(gitlawb): dynamic model fetch with gmi-cloud fallback Hybrid approach: - gitlawb (xiaomi-mimo): dynamic /models endpoint → 356 models - gitlawb-gmi (gmi-cloud): 404 fallback → local catalog gracefully Mimics Gitlawb/openclaude's model-routing pattern * i18n(pt-BR): complete missing translations and sync with en.json * feat(build): nix multi-OS package manager install (#2806) Integrated into release/v3.8.6 * fix(i18n): translate 144 new __MISSING__ pt-BR strings (#2816) Integrated into release/v3.8.6 * chore(docs): set coverage gate to 40/40/40/40 in CLAUDE.md Aligns the documented coverage gate with the v3.8.6 release decision (lowered from 75/75/75/70). Matches the threshold already set in package.json by the large feature PRs (planos 11-22). * fix(cli): respect PORT env var in serve command (#2845) Integrated into release/v3.8.6. * fix(deepseek-web): return 400 when client sends tools[] - chat.deepseek.com has no tool support (#2854) Integrated into release/v3.8.6. * fix(qoder): reject invalid/expired PATs returning Cosy 500 error (#2860) Integrated into release/v3.8.6. * fix(cli): register openclaw in tool-detector (#2833) (#2850) Integrated into release/v3.8.6. * fix(api): include noAuth providers in /v1/models catalog (#2798) (#2814) Integrated into release/v3.8.6. * fix(combo): resolve custom provider targets via combo name (#2778) (#2812) Integrated into release/v3.8.6. * fix(translator): strip safety_identifier in openai-responses cleanup (#2770) (#2809) Integrated into release/v3.8.6. * fix(quota): honor explicit per-connection preflight opt-out (#2831) (#2844) Integrated into release/v3.8.6. * fix(usage): un-invert GitHub Copilot Free/limited quota — limited_user_quotas is remaining (#2876) (#2881) Integrated into release/v3.8.6. * fix(nous-research): correct baseUrl to include /chat/completions (#2826) (#2835) Integrated into release/v3.8.6. * fix(opencode): qwen3.x max/plus models lack vision support (#2822) (#2836) Integrated into release/v3.8.6. * fix(translator): pass-through tool_search built-in tool type (#2766) (#2811) Integrated into release/v3.8.6. * fix(github): route claude-opus-4.6 via chat completions (#2821) Integrated into release/v3.8.6. * docs(oauth): add Windsurf login fix design (Phase 1 hotfix + Phase 2 Firebase OAuth) Two-phase plan to fix the broken Windsurf OAuth flow: - Phase 1: drop the dead app.devin.ai/editor/signin PKCE path, promote import-token from windsurf.com/show-auth-token as the primary path - Phase 2: port Firebase OAuth + RegisterUser flow from fendoushaonian/WindSurf-gRPC-API for full browser-based automation Spec only - no code changes yet. * docs(plan): Phase 1 windsurf login hotfix implementation plan 10 tasks covering: - TDD assertions for flowType + 410 Gone responses - Provider switch to import_token - Route handler retiring authorize/start-callback-server/poll-callback - OAuthModal UI override - i18n sync - Verification + PR steps * fix(cli): replace cli-table3 with hand-rolled formatter (#2752) (#2813) Integrated into release/v3.8.6. * fix(skills): skip interception for unregistered client-native tools (#2815) (#2817) Integrated into release/v3.8.6. * feat(sse): add RTK filters for kubectl, docker-build, composer, gh (#2824) Integrated into release/v3.8.6. * fix(geminiHelper): support rec.image content shape + warn on dropped remote URLs (refs #2807) (#2855) Integrated into release/v3.8.6. * fix(cli): allow nullable/optional apiKey in cliMitmStartSchema (#2857) Integrated into release/v3.8.6. * fix(combo): preserve system messages during context handoff summary generation (#2865) Integrated into release/v3.8.6. * fix: wire CLIProxyAPI fallback settings into chatCore routing engine (#2866) Integrated into release/v3.8.6. * fix(usage): add opencode quota fetcher (#2852) (#2867) Integrated into release/v3.8.6. * feat(claude): default xhigh support for newer Opus models (#2874) Integrated into release/v3.8.6. * fix(cli): restore omniroute logs command stream (#2756) (#2810) Integrated into release/v3.8.6. * fix(combo): normalize upstream Headers for Node 24 undici interop (#2751) (#2823) Integrated into release/v3.8.6. * Rename proxy log Public IP to Client IP (#2880) Integrated into release/v3.8.6. * fix(claude): preserve max effort for supported models (#2875) Integrated into release/v3.8.6. * fix(oauth): switch windsurf provider to import_token flow The PKCE auth URL targeting app.devin.ai/editor/signin returns 404 post-rebrand. Until Phase 2 ports Firebase OAuth + RegisterUser, the only supported path is import-token via windsurf.com/show-auth-token. - windsurf.ts: drop buildAuthUrl, set flowType=import_token - generateAuthData returns supported:false + helpful error for windsurf/devin-cli - tests: assert flowType + disabled stub * fix(oauth): return 410 Gone for retired windsurf/devin-cli PKCE actions start-callback-server, authorize, and poll-callback (GET + POST) now return 410 Gone with a pointer to /import-token. The 410 short-circuit runs before auth so the response is honest about the action being permanently gone, not gated. Codex PKCE flow unchanged. Tests: 5 new assertions cover GET + POST 410 paths and a Codex regression check. * refactor(oauth): annotate retired PKCE fields in WINDSURF_CONFIG No behaviour change - comment-only update documenting that authorizeUrl, codeChallengeMethod, callbackPort, callbackPath, apiServerUrl, and exchangePath are no longer consumed. Active fields (inferenceUrl, showAuthTokenUrl, firebaseApiKey, ideName) called out separately. * fix(cli,docs): use requireCliToolsAuth in logs route + document OPENCODE quota env Post-merge contract fixes for v3.8.6: - src/app/api/cli-tools/logs/route.ts (#2810) now uses the shared requireCliToolsAuth guard (param renamed req->request) to satisfy the cli-tools-auth-hardening contract test. - Document OMNIROUTE_OPENCODE_QUOTA_URL (#2867) in docs/reference/ENVIRONMENT.md to satisfy the env/docs sync contract. * fix(dashboard): force import-token panel for windsurf/devin-cli Phase 1 hotfix: hide the 'Browser Login' tab and start in Paste API Key mode. Removes windsurf/devin-cli from PKCE_CALLBACK_SERVER_PROVIDERS so no callback server is started for them. Codex still uses the PKCE flow. The 'Get token' link continues to point at windsurf.com/show-auth-token via the existing supportsTokenPaste form copy. * fix(oauth): windsurf import-token mapTokens signature mismatch The route at `src/app/api/oauth/[provider]/[action]/route.ts` invokes `providerData.mapTokens({ accessToken: token })` (object), matching the cursor/kiro signature. The windsurf provider was declared with `mapTokens(token: string)` instead, so the entire object was stored as `accessToken`. When the connection record reached the SQLite layer it crashed with: SQLite3 can only bind numbers, strings, bigints, buffers, and null Fix by aligning windsurf's `mapTokens` signature with the route caller and the cursor/kiro convention. Also dedupe a copy-pasted second `if (action === "import-token")` block in the route handler — the second block was unreachable but identical to the first. Adds two regression tests asserting that `provider.mapTokens({ accessToken })` returns a string `accessToken` for both windsurf and devin-cli, so a future signature drift trips the gate instead of the SQLite bind error in production. * feat(compression): expand pt-BR pack with troglodita rules (15 → 49) (#2818) Integrated into release/v3.8.6 * fix(sse): repair RTK engine defaults so dedup and direct calls work (#2825) Integrated into release/v3.8.6 * fix(mcp): redirect console.log/warn to stderr in --mcp stdio mode (#2840) Integrated into release/v3.8.6 * fix(gemini-cli): prefer real project IDs over default-project (#2841) Integrated into release/v3.8.6 * fix(opencode-go): add provider limits quota fetcher (#2861) Integrated into release/v3.8.6 * Audit & add web cookie providers: fix 4 missing registry entries + DuckDuckGo (#2862) Integrated into release/v3.8.6 * fix(antigravity): harden signatureless tool history (#2878) Integrated into release/v3.8.6 * fix: provider model sync pruning and dynamic antigravity MITM proxy mappings (#2886) Integrated into release/v3.8.6 * feat(usage): per-API-key token limits scoped to model/provider/global (#2888) Integrated into release/v3.8.6 * fix(audio): build multipart body manually to preserve Content-Type (#2842) Integrated into release/v3.8.6 * refactor: remove agent skill documentation files and streamline maintenance workflows * test(stabilization): resolve unit test failures in blackbox-web, schema-coercion, translator-helper-branches, usage-service-hardening, and audio-transcription * fix(security): mitigate Socket.dev supply-chain findings + secrets opt-in + minimal build profile (#2863) (#2871) Two real security gaps closed and four cosmetic Socket.dev fingerprints removed. See docs/security/SOCKET_DEV_FINDINGS.md for the per-finding maintainer attestation. Real bugs fixed: - cloudSync: HMAC verification of `X-Cloud-Sig` + opt-in `OMNIROUTE_CLOUD_SYNC_SECRETS=true` before overwriting `accessToken` / `refreshToken` / `providerSpecificData` from a remote response. Closes the silent-credential-swap surface (a misconfigured or hostile CLOUD_URL could previously replace local tokens unverified). - Zed import: split into 2-step `/discover` + `/import` flow. `/import` now requires `confirmedAccounts: [{ service, account, fingerprint }]` and re-reads the keychain server-side to filter by fingerprint, so a tampered discover response cannot trick the endpoint into saving an unrelated token. Cosmetic Socket.dev mitigations: - runElevatedPowerShell writes the elevated payload to a per-call temp `.ps1` file (mode 0o600) and references it via `-File`. Removes the textbook `-EncodedCommand <base64utf16le>` pattern flagged as malware by Socket's AI classifier. - Maintainer attestation `SECURITY-AUDITOR-NOTE:` blocks added at every flagged call site pointing to `docs/security/SOCKET_DEV_FINDINGS.md`. Build-time hardening: - `OMNIROUTE_BUILD_PROFILE=minimal` (`npm run build:secure`) physically removes the four sensitive modules from the standalone bundle via webpack `NormalModuleReplacementPlugin`. Stubs throw `FeatureDisabledError` at runtime. Intended for the `omniroute-secure` artifact. Tests: - 24 new unit tests in `tests/unit/security/` covering the wrapper builder, HMAC verification (4 cases), credential fingerprint determinism (5 cases), confirmedAccounts validation + fingerprint filtering (6 cases), and the minimal-build stubs (5 cases). Docs: - New `docs/security/SOCKET_DEV_FINDINGS.md` — per-finding attestation. - New `socket.yml` — Socket.dev v2 config pointing at the attestation. - Updated `SECURITY.md` — supply-chain scanner section. - Updated `.env.example` — three new env vars documented. Backwards compatibility: - Cloud sync token overwrite is OFF by default. Users who relied on it must set `OMNIROUTE_CLOUD_SYNC_SECRETS=true`. Breaking change documented in CHANGELOG. - Zed import 2-step is the new default; legacy 1-step preserved behind `OMNIROUTE_ZED_IMPORT_LEGACY_ONE_STEP=true` and will be removed in v3.9. Closes #2863 * fix(security): redact public Firebase Web key from windsurf spec; doc SHA-256 cache-key rationale (#2894) Two security-scanning findings on release/v3.8.6: - Secret-scanning alert 7 (google_api_key): the windsurf login-fix design spec embedded the literal public Firebase Web API key on two lines. Firebase Web API keys are non-sensitive by design (they identify the project; access is gated by Firebase Security Rules + key restrictions), but the literal trips secret scanning. Redacted to a placeholder; the embedded default still goes through resolvePublicCred per rule #11. - Code-scanning alert 261 (js/insufficient-password-hash): tokenCacheKey() uses SHA-256 to derive an in-memory cache key from the session token, not for password-at-rest storage. Added a comment documenting why CWE-916 KDFs do not apply (false positive). * fix(ci): resolve release/v3.8.6 gate failures (docs-sync, any-budget, pack-artifact) (#2895) * fix(ci): resolve release/v3.8.6 gate failures (docs-sync, any-budget, pack-artifact) Three CI gates failed on release/v3.8.6 (run 26630300877): - docs-sync: CHANGELOG had a spurious "## [3.8.6-patch]" section above "## [3.8.6]", so the latest release no longer matched package.json (3.8.6) and the 41 i18n CHANGELOG mirrors were flagged as missing that section. Fold the lone #2752 entry into [3.8.6] and drop the patch heading. - any-budget:t11: open-sse/handlers/chatCore.ts regressed to 1 explicit `any` (budget 0). Type the persist callback arg as Record<string, unknown>, which matches runWithOnPersist's RefreshPersistFn contract exactly. - pack-artifact: open-sse/utils/setupPolyfill.ts ships via package.json "files" (bin/omniroute.mjs imports it at startup) but was missing from the pack policy allowlist. Allow it and add a regression test. * fix(security): redact public Firebase Web key from windsurf spec Redact the literal public Firebase Web API key (secret-scanning #7) to a placeholder, mirroring the redaction on release/v3.8.6 (PR #2894) and the windsurf fix branch. Non-sensitive public Web key; trips secret scanning. * feat(combo): Zero-Latency Combos (Hedging, Proactive Compression, Predictive TTFT) (#2868) * feat(combo): implement zero-latency combo optimizations (hedging, proactive compression, predictive TTFT) * fix(combo): fix predictive TTFT skip logic and unhandled promise rejections --------- Co-authored-by: Automation <automation@omniroute> * feat: implement automated skill workflows and update system configuration and validation schemas * test: eliminate dynamic cast warnings in cloud-sync unit test * test: isolate services-branch-hardening database directory to avoid concurrency issues * feat(providers): add 7 new web-cookie providers + research catalog + discovery tool New providers: - huggingchat: free LLM chat via huggingface.co/chat (no subscription) - phind: free dev-focused AI chat via phind.com/api/agent - poe-web: multi-model chat via poe.com GraphQL (p-b cookie) - venice-web: privacy-focused AI chat via venice.ai (session cookie) - v0-vercel-web: Vercel v0 code gen via v0.dev (session cookie) - kimi-web: Moonshot Kimi chat via kimi.moonshot.cn (session cookie) - doubao-web: ByteDance Doubao chat via doubao.com (session cookie) Additional: - Research catalog: docs/research/UNLIMITED_LLM_ACCESS.md - Discovery tool design + stub: src/lib/discovery/ + migration 073 - Unit tests: 33 tests for all 7 providers - Shared helpers consolidated in error.ts (slop cleanup) - All registered in WEB_COOKIE_PROVIDERS + providerRegistry + webSessionCredentials Closes #2885 * fix(typecheck): resolve typecheck errors in combo spec and compression modules * feat(api,oauth): add `agy` (Antigravity CLI) standalone provider with CLI token import (#2899) Add a standalone OAuth provider `agy` (Antigravity CLI) next to gemini-cli/antigravity. It reuses the antigravity inference backend (identical Google client_id + daily-cloudcode-pa.googleapis.com endpoint, executor and token-refresh) but ships its own model catalog — including the Claude models the backend exposes (claude-opus-4-6-thinking, claude-sonnet-4-6) — its own account pool, and four ways to connect: - token-file import (paste/upload the agy oauth token JSON) - auto-detect a local CLI login (~/.gemini/antigravity-cli/antigravity-oauth-token) - browser OAuth (via the shared OAuthModal Google loopback flow) - bulk / ZIP import New routes: POST /api/providers/agy-auth/{import,import-bulk,zip-extract,apply-local}. Catalog pinned from the live :fetchAvailableModels endpoint. Docs (openapi.yaml, ENVIRONMENT.md, .env.example, CHANGELOG) updated; new unit tests for registration, the token parser, and route auth-hardening. * fix(security): redact public Firebase Web key from windsurf spec (#2896) Redact the literal public Firebase Web API key (secret-scanning #7) to a placeholder. Firebase Web API keys are non-sensitive by design but the literal trips GitHub secret scanning. Mirrors the redaction landed on release/v3.8.6 (PR #2894). Embedded default still flows through resolvePublicCred (rule #11). * Pr 2871 (#2897) * fix(security): mitigate Socket.dev supply-chain findings + secrets opt-in + minimal build profile (#2863) Two real security gaps closed and four cosmetic Socket.dev fingerprints removed. See docs/security/SOCKET_DEV_FINDINGS.md for the per-finding maintainer attestation. Real bugs fixed: - cloudSync: HMAC verification of `X-Cloud-Sig` + opt-in `OMNIROUTE_CLOUD_SYNC_SECRETS=true` before overwriting `accessToken` / `refreshToken` / `providerSpecificData` from a remote response. Closes the silent-credential-swap surface (a misconfigured or hostile CLOUD_URL could previously replace local tokens unverified). - Zed import: split into 2-step `/discover` + `/import` flow. `/import` now requires `confirmedAccounts: [{ service, account, fingerprint }]` and re-reads the keychain server-side to filter by fingerprint, so a tampered discover response cannot trick the endpoint into saving an unrelated token. Cosmetic Socket.dev mitigations: - runElevatedPowerShell writes the elevated payload to a per-call temp `.ps1` file (mode 0o600) and references it via `-File`. Removes the textbook `-EncodedCommand <base64utf16le>` pattern flagged as malware by Socket's AI classifier. - Maintainer attestation `SECURITY-AUDITOR-NOTE:` blocks added at every flagged call site pointing to `docs/security/SOCKET_DEV_FINDINGS.md`. Build-time hardening: - `OMNIROUTE_BUILD_PROFILE=minimal` (`npm run build:secure`) physically removes the four sensitive modules from the standalone bundle via webpack `NormalModuleReplacementPlugin`. Stubs throw `FeatureDisabledError` at runtime. Intended for the `omniroute-secure` artifact. Tests: - 24 new unit tests in `tests/unit/security/` covering the wrapper builder, HMAC verification (4 cases), credential fingerprint determinism (5 cases), confirmedAccounts validation + fingerprint filtering (6 cases), and the minimal-build stubs (5 cases). Docs: - New `docs/security/SOCKET_DEV_FINDINGS.md` — per-finding attestation. - New `socket.yml` — Socket.dev v2 config pointing at the attestation. - Updated `SECURITY.md` — supply-chain scanner section. - Updated `.env.example` — three new env vars documented. Backwards compatibility: - Cloud sync token overwrite is OFF by default. Users who relied on it must set `OMNIROUTE_CLOUD_SYNC_SECRETS=true`. Breaking change documented in CHANGELOG. - Zed import 2-step is the new default; legacy 1-step preserved behind `OMNIROUTE_ZED_IMPORT_LEGACY_ONE_STEP=true` and will be removed in v3.9. Closes #2863 * feat: implement automated skill workflows and update system configuration and validation schemas * test: eliminate dynamic cast warnings in cloud-sync unit test * test: isolate services-branch-hardening database directory to avoid concurrency issues * chore(docs): refresh generated docs collection index Update the generated Fumadocs browser collection mapping to keep documentation imports in sync with the current docs structure. * docs: update generated browser docs collection manifest Refresh the generated Fumadocs browser collection mapping so the docs site can resolve the current documentation files correctly. --------- Co-authored-by: OpenClaw <openclaw@kuzhomesrv.local> Co-authored-by: Dmitry Kuznetsov <139351986+dmitry@users.noreply.local> Co-authored-by: KuzyaBot <kuzya@local> Co-authored-by: JeferssonLemes <jeferssondev@gmail.com> Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com> Co-authored-by: Markus Hartung <mail@hartmark.se> Co-authored-by: akarray <akarray@users.noreply.github.com> Co-authored-by: Apostol Apostolov <theapoapostolov@gmail.com> Co-authored-by: Hernan Javier Ardila Sanchez <hjasgr@gmail.com> Co-authored-by: Dmitry Kuznetsov <dmitry@kuznetsov.me> Co-authored-by: Nikolay Alafuzov <alafuzov_nn@rusklimat.ru> Co-authored-by: oyi77 <oyi77@users.noreply.github.com> Co-authored-by: Ronaldo Davi <alltomatos@users.noreply.github.com> Co-authored-by: levonk <277861+levonk@users.noreply.github.com> Co-authored-by: Lenine Júnior <lenine@engrene.com.br> Co-authored-by: Annas Alghoffar <aag.annas@gmail.com> Co-authored-by: Tushar Agarwal <76201310+Tushar49@users.noreply.github.com> Co-authored-by: GreatLiu <eurasiaxz@qq.com> Co-authored-by: yuna amelia <230527278+yunaamelia@users.noreply.github.com> Co-authored-by: Randi <55005611+rdself@users.noreply.github.com> Co-authored-by: Container <78986709+disonjer@users.noreply.github.com> Co-authored-by: nickwizard <35692452+nickwizard@users.noreply.github.com> Co-authored-by: Rajvardhan Patil <rajvardhanpatil7890@gmail.com> Co-authored-by: Raxxoor <manker_lol@hotmail.com> Co-authored-by: Muhammad Mugni Hadi <mugnimaestra3@gmail.com> Co-authored-by: mi <123757457+soyelmismo@users.noreply.github.com> Co-authored-by: Automation <automation@omniroute>
815 lines
26 KiB
TypeScript
815 lines
26 KiB
TypeScript
/**
|
|
* Unit tests for the Reasoning Replay Cache (Issue #1628).
|
|
*
|
|
* Covers: memory cache, DB fallback, hit/miss counters,
|
|
* provider detection, and cleanup behavior.
|
|
*/
|
|
|
|
import { describe, it, before, after } from "node:test";
|
|
import assert from "node:assert/strict";
|
|
|
|
import { mkdtempSync } from "node:fs";
|
|
import { join } from "node:path";
|
|
import { tmpdir } from "node:os";
|
|
|
|
process.env.DATA_DIR = mkdtempSync(join(tmpdir(), "omniroute-reasoning-"));
|
|
|
|
// ──────────── Direct service import ────────────
|
|
|
|
import {
|
|
cacheReasoningFromAssistantMessage,
|
|
cacheReasoning,
|
|
cacheReasoningByKey,
|
|
cacheReasoningBatch,
|
|
deleteReasoningCacheEntry,
|
|
getReasoningCacheServiceEntries,
|
|
lookupReasoning,
|
|
recordReplay,
|
|
getReasoningCacheServiceStats,
|
|
clearReasoningCacheAll,
|
|
isDeepSeekReasoningModel,
|
|
requiresReasoningReplay,
|
|
cleanupReasoningCache,
|
|
} from "../../open-sse/services/reasoningCache.ts";
|
|
import { translateRequest } from "../../open-sse/translator/index.ts";
|
|
import { FORMATS } from "../../open-sse/translator/formats.ts";
|
|
import { ensureToolCallIds } from "../../open-sse/translator/helpers/toolCallHelper.ts";
|
|
import { getDbInstance } from "../../src/lib/db/core.ts";
|
|
import { getReasoningCache, setReasoningCache } from "../../src/lib/db/reasoningCache.ts";
|
|
import { DELETE, GET } from "../../src/app/api/cache/reasoning/route.ts";
|
|
import { updateSettings } from "../../src/lib/db/settings";
|
|
import {
|
|
clearModelsDevCapabilities,
|
|
saveModelsDevCapabilities,
|
|
} from "../../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,
|
|
};
|
|
}
|
|
|
|
before(async () => {
|
|
await updateSettings({ requireLogin: false });
|
|
});
|
|
|
|
after(async () => {
|
|
await updateSettings({ requireLogin: true });
|
|
});
|
|
|
|
describe("Reasoning Replay Cache — Service Layer", () => {
|
|
before(() => {
|
|
// Start each suite with a clean slate
|
|
clearReasoningCacheAll();
|
|
});
|
|
|
|
after(() => {
|
|
clearReasoningCacheAll();
|
|
});
|
|
|
|
it("should store and retrieve reasoning by tool_call_id", () => {
|
|
cacheReasoning(
|
|
"call_test_1",
|
|
"deepseek",
|
|
"deepseek-reasoner",
|
|
"The user wants to read the file..."
|
|
);
|
|
const result = lookupReasoning("call_test_1");
|
|
assert.equal(result, "The user wants to read the file...");
|
|
assert.equal(getReasoningCache("call_test_1")?.reasoning, "The user wants to read the file...");
|
|
});
|
|
|
|
it("should fall back to SQLite when memory misses", () => {
|
|
clearReasoningCacheAll();
|
|
setReasoningCache("call_db_only", "deepseek", "deepseek-reasoner", "DB-only reasoning");
|
|
|
|
assert.equal(lookupReasoning("call_db_only"), "DB-only reasoning");
|
|
|
|
const stats = getReasoningCacheServiceStats();
|
|
assert.equal(stats.hits, 1);
|
|
assert.equal(stats.memoryEntries, 1);
|
|
assert.equal(stats.dbEntries, 1);
|
|
});
|
|
|
|
it("should return null for unknown tool_call_id", () => {
|
|
const result = lookupReasoning("call_nonexistent");
|
|
assert.equal(result, null);
|
|
});
|
|
|
|
it("should return null for empty tool_call_id", () => {
|
|
const result = lookupReasoning("");
|
|
assert.equal(result, null);
|
|
});
|
|
|
|
it("should skip caching when reasoning is empty", () => {
|
|
cacheReasoning("call_empty", "deepseek", "deepseek-chat", "");
|
|
const result = lookupReasoning("call_empty");
|
|
assert.equal(result, null);
|
|
});
|
|
|
|
it("should cache reasoning for multiple tool_call_ids (batch)", () => {
|
|
cacheReasoningBatch(
|
|
["call_batch_1", "call_batch_2", "call_batch_3"],
|
|
"deepseek",
|
|
"deepseek-reasoner",
|
|
"Batch reasoning content"
|
|
);
|
|
assert.equal(lookupReasoning("call_batch_1"), "Batch reasoning content");
|
|
assert.equal(lookupReasoning("call_batch_2"), "Batch reasoning content");
|
|
assert.equal(lookupReasoning("call_batch_3"), "Batch reasoning content");
|
|
});
|
|
|
|
it("should capture assistant reasoning for all tool_call IDs", () => {
|
|
clearReasoningCacheAll();
|
|
|
|
const cached = cacheReasoningFromAssistantMessage(
|
|
{
|
|
role: "assistant",
|
|
reasoning_content: "Captured assistant reasoning",
|
|
tool_calls: [{ id: "call_capture_1" }, { id: "call_capture_2" }],
|
|
},
|
|
"deepseek",
|
|
"deepseek-reasoner"
|
|
);
|
|
|
|
assert.equal(cached, 2);
|
|
assert.equal(lookupReasoning("call_capture_1"), "Captured assistant reasoning");
|
|
assert.equal(lookupReasoning("call_capture_2"), "Captured assistant reasoning");
|
|
});
|
|
|
|
it("should keep request message cache keys stable when tool call IDs change", () => {
|
|
clearReasoningCacheAll();
|
|
|
|
const requestId = "req_reasoning_stable";
|
|
const messageIndex = 2;
|
|
const cacheKey = `${requestId}:${messageIndex}`;
|
|
const body = {
|
|
messages: [
|
|
{
|
|
role: "assistant",
|
|
tool_calls: [
|
|
{
|
|
id: "call_before_normalization",
|
|
type: "function",
|
|
function: { name: "lookup", arguments: { city: "Seoul" } },
|
|
},
|
|
],
|
|
},
|
|
{ role: "tool", content: "Sunny" },
|
|
],
|
|
};
|
|
|
|
cacheReasoning(cacheKey, "deepseek", "deepseek-reasoner", "Stable cached reasoning");
|
|
const originalToolCallId = body.messages[0].tool_calls[0].id;
|
|
|
|
ensureToolCallIds(body, { use9CharId: true });
|
|
|
|
assert.notEqual(body.messages[0].tool_calls[0].id, originalToolCallId);
|
|
assert.equal(lookupReasoning(cacheKey), "Stable cached reasoning");
|
|
});
|
|
|
|
it("should capture provider reasoning alias when reasoning_content is absent", () => {
|
|
clearReasoningCacheAll();
|
|
|
|
const cached = cacheReasoningFromAssistantMessage(
|
|
{
|
|
role: "assistant",
|
|
reasoning: "Alias reasoning",
|
|
tool_calls: [{ id: "call_capture_alias" }],
|
|
},
|
|
"kimi",
|
|
"kimi-k2.5"
|
|
);
|
|
|
|
assert.equal(cached, 1);
|
|
assert.equal(lookupReasoning("call_capture_alias"), "Alias reasoning");
|
|
});
|
|
|
|
it("should cache assistant reasoning without tool calls by request and message index", () => {
|
|
clearReasoningCacheAll();
|
|
|
|
const cached = cacheReasoningFromAssistantMessage(
|
|
{
|
|
role: "assistant",
|
|
reasoning_content: "No tool call reasoning",
|
|
},
|
|
"deepseek",
|
|
"deepseek-reasoner",
|
|
{ requestId: "req_no_tools", messageIndex: 3 }
|
|
);
|
|
|
|
assert.equal(cached, 1);
|
|
assert.equal(lookupReasoning("request:req_no_tools:message:3"), "No tool call reasoning");
|
|
});
|
|
|
|
it("should skip assistant reasoning without tool calls when stable key context is absent", () => {
|
|
clearReasoningCacheAll();
|
|
|
|
const cached = cacheReasoningFromAssistantMessage(
|
|
{
|
|
role: "assistant",
|
|
reasoning_content: "Missing key context",
|
|
},
|
|
"deepseek",
|
|
"deepseek-reasoner"
|
|
);
|
|
|
|
assert.equal(cached, 0);
|
|
assert.equal(lookupReasoning("request:req_missing:message:0"), null);
|
|
});
|
|
|
|
it("should store arbitrary reasoning cache keys", () => {
|
|
clearReasoningCacheAll();
|
|
|
|
cacheReasoningByKey(
|
|
"request:req_direct:message:1",
|
|
"deepseek",
|
|
"deepseek-reasoner",
|
|
"Keyed plan"
|
|
);
|
|
|
|
assert.equal(lookupReasoning("request:req_direct:message:1"), "Keyed plan");
|
|
assert.equal(getReasoningCache("request:req_direct:message:1")?.reasoning, "Keyed plan");
|
|
});
|
|
|
|
it("should not overwrite if same tool_call_id is cached again", () => {
|
|
cacheReasoning("call_overwrite", "deepseek", "deepseek-chat", "First reasoning");
|
|
cacheReasoning("call_overwrite", "deepseek", "deepseek-chat", "Updated reasoning");
|
|
// Second write wins (INSERT OR REPLACE)
|
|
const result = lookupReasoning("call_overwrite");
|
|
assert.equal(result, "Updated reasoning");
|
|
});
|
|
|
|
it("should track hits and misses correctly", () => {
|
|
clearReasoningCacheAll();
|
|
|
|
cacheReasoning("call_hit_test", "deepseek", "deepseek-chat", "test reasoning");
|
|
|
|
lookupReasoning("call_hit_test"); // hit
|
|
lookupReasoning("call_hit_test"); // hit
|
|
lookupReasoning("call_miss_test"); // miss
|
|
|
|
const stats = getReasoningCacheServiceStats();
|
|
assert.ok(stats.hits >= 2, `Expected at least 2 hits, got ${stats.hits}`);
|
|
assert.ok(stats.misses >= 1, `Expected at least 1 miss, got ${stats.misses}`);
|
|
});
|
|
|
|
it("should track replays", () => {
|
|
clearReasoningCacheAll();
|
|
|
|
recordReplay();
|
|
recordReplay();
|
|
recordReplay();
|
|
|
|
const stats = getReasoningCacheServiceStats();
|
|
assert.ok(stats.replays >= 3, `Expected at least 3 replays, got ${stats.replays}`);
|
|
});
|
|
|
|
it("should report correct stats structure", () => {
|
|
clearReasoningCacheAll();
|
|
|
|
cacheReasoning("call_stat_1", "deepseek", "deepseek-reasoner", "Reasoning A");
|
|
cacheReasoning("call_stat_2", "kimi", "kimi-k2.5", "Reasoning B from Kimi");
|
|
|
|
const stats = getReasoningCacheServiceStats();
|
|
|
|
assert.equal(typeof stats.memoryEntries, "number");
|
|
assert.equal(typeof stats.dbEntries, "number");
|
|
assert.equal(typeof stats.totalEntries, "number");
|
|
assert.equal(typeof stats.totalChars, "number");
|
|
assert.equal(typeof stats.hits, "number");
|
|
assert.equal(typeof stats.misses, "number");
|
|
assert.equal(typeof stats.replays, "number");
|
|
assert.equal(typeof stats.replayRate, "string");
|
|
assert.ok(stats.replayRate.endsWith("%"));
|
|
assert.equal(typeof stats.byProvider, "object");
|
|
assert.equal(typeof stats.byModel, "object");
|
|
assert.equal(stats.dbEntries, 2);
|
|
assert.equal(stats.byProvider.deepseek.entries, 1);
|
|
assert.equal(stats.byProvider.kimi.entries, 1);
|
|
});
|
|
|
|
it("should list persisted entries for the dashboard API", () => {
|
|
clearReasoningCacheAll();
|
|
|
|
cacheReasoning("call_entry_1", "deepseek", "deepseek-reasoner", "Entry reasoning A");
|
|
cacheReasoning("call_entry_2", "kimi", "kimi-k2.5", "Entry reasoning B");
|
|
|
|
const deepseekEntries = getReasoningCacheServiceEntries({ provider: "deepseek" }) as Array<{
|
|
toolCallId: string;
|
|
expiresAt: string;
|
|
}>;
|
|
|
|
assert.equal(deepseekEntries.length, 1);
|
|
assert.equal(deepseekEntries[0].toolCallId, "call_entry_1");
|
|
assert.doesNotThrow(() => new Date(deepseekEntries[0].expiresAt).toISOString());
|
|
});
|
|
|
|
it("should clear all entries", () => {
|
|
cacheReasoning("call_clear_1", "deepseek", "deepseek-chat", "Will be cleared");
|
|
cacheReasoning("call_clear_2", "deepseek", "deepseek-chat", "Also cleared");
|
|
|
|
const count = clearReasoningCacheAll();
|
|
assert.ok(count >= 0);
|
|
|
|
assert.equal(lookupReasoning("call_clear_1"), null);
|
|
assert.equal(lookupReasoning("call_clear_2"), null);
|
|
});
|
|
|
|
it("should delete one entry by tool_call_id", () => {
|
|
clearReasoningCacheAll();
|
|
|
|
cacheReasoning("call_delete_1", "deepseek", "deepseek-chat", "Delete me");
|
|
cacheReasoning("call_delete_2", "deepseek", "deepseek-chat", "Keep me");
|
|
|
|
assert.equal(deleteReasoningCacheEntry("call_delete_1"), 1);
|
|
assert.equal(lookupReasoning("call_delete_1"), null);
|
|
assert.equal(lookupReasoning("call_delete_2"), "Keep me");
|
|
});
|
|
|
|
it("should clear entries by provider only", () => {
|
|
clearReasoningCacheAll();
|
|
|
|
cacheReasoning("call_provider_ds", "deepseek", "deepseek-chat", "DeepSeek reasoning");
|
|
cacheReasoning("call_provider_kimi", "kimi", "kimi-k2.5", "Kimi reasoning");
|
|
|
|
assert.equal(clearReasoningCacheAll("deepseek"), 1);
|
|
assert.equal(lookupReasoning("call_provider_ds"), null);
|
|
assert.equal(lookupReasoning("call_provider_kimi"), "Kimi reasoning");
|
|
});
|
|
|
|
it("should cleanup expired reasoning (no-op when nothing expired)", () => {
|
|
cacheReasoning("call_cleanup_test", "deepseek", "deepseek-chat", "Not expired yet");
|
|
const cleaned = cleanupReasoningCache();
|
|
assert.equal(typeof cleaned, "number");
|
|
// Entry should still be available since TTL is 2 hours
|
|
assert.equal(lookupReasoning("call_cleanup_test"), "Not expired yet");
|
|
});
|
|
|
|
it("should not return expired SQLite entries and cleanup should prune them", () => {
|
|
clearReasoningCacheAll();
|
|
setReasoningCache("call_expired", "deepseek", "deepseek-chat", "Expired reasoning", -1_000);
|
|
|
|
assert.equal(lookupReasoning("call_expired"), null);
|
|
assert.equal(cleanupReasoningCache(), 1);
|
|
assert.equal(getReasoningCacheServiceStats().dbEntries, 0);
|
|
});
|
|
|
|
it("should read and prune legacy ISO expires_at rows", () => {
|
|
clearReasoningCacheAll();
|
|
|
|
const db = getDbInstance();
|
|
const futureIso = new Date(Date.now() + 60_000).toISOString();
|
|
const expiredIso = new Date(Date.now() - 60_000).toISOString();
|
|
db.prepare(
|
|
`INSERT INTO reasoning_cache
|
|
(tool_call_id, provider, model, reasoning, char_count, created_at, expires_at)
|
|
VALUES (?, ?, ?, ?, ?, datetime('now'), ?)`
|
|
).run(
|
|
"call_legacy_iso_active",
|
|
"deepseek",
|
|
"deepseek-chat",
|
|
"Legacy ISO reasoning",
|
|
"Legacy ISO reasoning".length,
|
|
futureIso
|
|
);
|
|
db.prepare(
|
|
`INSERT INTO reasoning_cache
|
|
(tool_call_id, provider, model, reasoning, char_count, created_at, expires_at)
|
|
VALUES (?, ?, ?, ?, ?, datetime('now'), ?)`
|
|
).run(
|
|
"call_legacy_iso_expired",
|
|
"deepseek",
|
|
"deepseek-chat",
|
|
"Expired legacy ISO reasoning",
|
|
"Expired legacy ISO reasoning".length,
|
|
expiredIso
|
|
);
|
|
|
|
assert.equal(lookupReasoning("call_legacy_iso_active"), "Legacy ISO reasoning");
|
|
assert.equal(lookupReasoning("call_legacy_iso_expired"), null);
|
|
const entries = getReasoningCacheServiceEntries({ provider: "deepseek" }) as Array<{
|
|
toolCallId: string;
|
|
expiresAt: string;
|
|
}>;
|
|
assert.equal(
|
|
entries.some((entry) => entry.expiresAt === futureIso),
|
|
true
|
|
);
|
|
assert.equal(cleanupReasoningCache(), 1);
|
|
});
|
|
});
|
|
|
|
describe("Reasoning Replay Cache — Provider Detection", () => {
|
|
it("should detect deepseek as requiring replay", () => {
|
|
assert.equal(requiresReasoningReplay({ provider: "deepseek", model: "deepseek-chat" }), true);
|
|
});
|
|
|
|
it("should detect opencode-go as requiring replay", () => {
|
|
assert.equal(requiresReasoningReplay({ provider: "opencode-go", model: "some-model" }), true);
|
|
});
|
|
|
|
it("should not replay legacy deepseek-r1 even under replay providers", () => {
|
|
assert.equal(requiresReasoningReplay({ provider: "siliconflow", model: "deepseek-r1" }), false);
|
|
});
|
|
|
|
it("should not replay deepseek-r1 model pattern", () => {
|
|
assert.equal(
|
|
requiresReasoningReplay({ provider: "unknown-provider", model: "deepseek-r1" }),
|
|
false
|
|
);
|
|
});
|
|
|
|
it("should detect deepseek-reasoner model pattern", () => {
|
|
assert.equal(
|
|
requiresReasoningReplay({ provider: "unknown-provider", model: "deepseek-reasoner" }),
|
|
false
|
|
);
|
|
});
|
|
|
|
it("should detect DeepSeek V4 model pattern", () => {
|
|
assert.equal(
|
|
requiresReasoningReplay({ provider: "unknown-provider", model: "deepseek/v4-pro" }),
|
|
true
|
|
);
|
|
});
|
|
|
|
it("should detect DeepSeek V4 thinking mode explicitly", () => {
|
|
assert.equal(
|
|
isDeepSeekReasoningModel({
|
|
provider: "unknown-provider",
|
|
model: "deepseek-v4.flash",
|
|
thinkingEnabled: true,
|
|
}),
|
|
true
|
|
);
|
|
});
|
|
|
|
it("should NOT detect DeepSeek V4 when thinking mode is disabled", () => {
|
|
assert.equal(
|
|
isDeepSeekReasoningModel({
|
|
provider: "unknown-provider",
|
|
model: "deepseek-v4.flash",
|
|
thinkingEnabled: false,
|
|
}),
|
|
false
|
|
);
|
|
});
|
|
|
|
it("should detect kimi-k2 model pattern", () => {
|
|
assert.equal(
|
|
requiresReasoningReplay({ provider: "unknown-provider", model: "kimi-k2.5" }),
|
|
true
|
|
);
|
|
});
|
|
|
|
it("should detect qwq model pattern", () => {
|
|
assert.equal(
|
|
requiresReasoningReplay({ provider: "unknown-provider", model: "qwq-32b-preview" }),
|
|
true
|
|
);
|
|
});
|
|
|
|
it("should detect qwen-thinking model pattern", () => {
|
|
assert.equal(
|
|
requiresReasoningReplay({ provider: "unknown-provider", model: "qwen3-thinking-235b" }),
|
|
true
|
|
);
|
|
});
|
|
|
|
it("should detect GLM thinking model pattern", () => {
|
|
assert.equal(requiresReasoningReplay({ provider: "glm", model: "glm-5-thinking" }), true);
|
|
});
|
|
|
|
it("should detect xiaomi-mimo provider", () => {
|
|
// MiMo enforces reasoning_content echo on subsequent turns; without
|
|
// replay the upstream returns 400 "Param Incorrect: The reasoning_content
|
|
// in the thinking mode must be passed back to the API."
|
|
assert.equal(
|
|
requiresReasoningReplay({ provider: "xiaomi-mimo", model: "mimo-v2.5-pro" }),
|
|
true
|
|
);
|
|
assert.equal(requiresReasoningReplay({ provider: "XIAOMI-MIMO", model: "mimo-v2.5" }), true);
|
|
});
|
|
|
|
it("should detect mimo-v* model pattern under any provider id", () => {
|
|
assert.equal(
|
|
requiresReasoningReplay({ provider: "unknown-provider", model: "mimo-v2.5-pro" }),
|
|
true
|
|
);
|
|
assert.equal(requiresReasoningReplay({ provider: "unknown-provider", model: "mimo-v3" }), true);
|
|
assert.equal(
|
|
requiresReasoningReplay({ provider: "unknown-provider", model: "MimoV2.5-pro" }),
|
|
true
|
|
);
|
|
});
|
|
|
|
it("should NOT detect a generic openai model", () => {
|
|
assert.equal(requiresReasoningReplay({ provider: "openai", model: "gpt-4o" }), false);
|
|
});
|
|
|
|
it("should NOT detect claude as requiring replay", () => {
|
|
assert.equal(requiresReasoningReplay({ provider: "anthropic", model: "claude-opus-4" }), false);
|
|
});
|
|
});
|
|
|
|
describe("Reasoning Replay Cache — Translator Replay", () => {
|
|
before(() => {
|
|
clearReasoningCacheAll();
|
|
clearModelsDevCapabilities();
|
|
});
|
|
|
|
after(() => {
|
|
clearReasoningCacheAll();
|
|
clearModelsDevCapabilities();
|
|
});
|
|
|
|
function translateWithToolHistory(provider: string, model: string, callId: string) {
|
|
return translateRequest(
|
|
FORMATS.OPENAI,
|
|
FORMATS.OPENAI,
|
|
model,
|
|
{
|
|
messages: [
|
|
{ role: "user", content: "use a tool" },
|
|
{
|
|
role: "assistant",
|
|
content: null,
|
|
tool_calls: [
|
|
{ id: callId, type: "function", function: { name: "read_file", arguments: "{}" } },
|
|
],
|
|
},
|
|
{ role: "tool", tool_call_id: callId, content: "tool result" },
|
|
],
|
|
},
|
|
false,
|
|
null,
|
|
provider
|
|
);
|
|
}
|
|
|
|
it("should inject cached reasoning for DeepSeek instead of empty fallback", () => {
|
|
clearReasoningCacheAll();
|
|
clearModelsDevCapabilities();
|
|
saveModelsDevCapabilities({
|
|
deepseek: {
|
|
"deepseek-reasoner": buildCapability({
|
|
interleaved_field: "reasoning_content",
|
|
reasoning: true,
|
|
tool_call: true,
|
|
}),
|
|
},
|
|
});
|
|
cacheReasoning("call_translate_ds", "deepseek", "deepseek-reasoner", "DeepSeek cached plan");
|
|
|
|
const translated = translateWithToolHistory(
|
|
"deepseek",
|
|
"deepseek-reasoner",
|
|
"call_translate_ds"
|
|
);
|
|
|
|
assert.equal(translated.messages[1].reasoning_content, "DeepSeek cached plan");
|
|
assert.equal(getReasoningCacheServiceStats().replays, 1);
|
|
});
|
|
|
|
it("should preserve client-provided reasoning content", () => {
|
|
clearReasoningCacheAll();
|
|
clearModelsDevCapabilities();
|
|
saveModelsDevCapabilities({
|
|
deepseek: {
|
|
"deepseek-reasoner": buildCapability({
|
|
interleaved_field: "reasoning_content",
|
|
reasoning: true,
|
|
tool_call: true,
|
|
}),
|
|
},
|
|
});
|
|
cacheReasoning("call_preserve", "deepseek", "deepseek-reasoner", "Cached reasoning");
|
|
|
|
const translated = translateRequest(
|
|
FORMATS.OPENAI,
|
|
FORMATS.OPENAI,
|
|
"deepseek-reasoner",
|
|
{
|
|
messages: [
|
|
{ role: "user", content: "use a tool" },
|
|
{
|
|
role: "assistant",
|
|
content: null,
|
|
reasoning_content: "Client reasoning",
|
|
tool_calls: [
|
|
{
|
|
id: "call_preserve",
|
|
type: "function",
|
|
function: { name: "tool", arguments: "{}" },
|
|
},
|
|
],
|
|
},
|
|
],
|
|
},
|
|
false,
|
|
null,
|
|
"deepseek"
|
|
);
|
|
|
|
assert.equal(translated.messages[1].reasoning_content, "Client reasoning");
|
|
assert.equal(getReasoningCacheServiceStats().replays, 0);
|
|
});
|
|
|
|
it("should inject cached reasoning for Qwen and GLM thinking models", () => {
|
|
clearReasoningCacheAll();
|
|
clearModelsDevCapabilities();
|
|
saveModelsDevCapabilities({
|
|
qwen: {
|
|
"qwen3-thinking-235b": buildCapability({
|
|
interleaved_field: "reasoning_content",
|
|
reasoning: true,
|
|
tool_call: true,
|
|
}),
|
|
},
|
|
glm: {
|
|
"glm-5-thinking": buildCapability({
|
|
interleaved_field: "reasoning_content",
|
|
reasoning: true,
|
|
tool_call: true,
|
|
}),
|
|
},
|
|
});
|
|
cacheReasoning("call_qwen_think", "qwen", "qwen3-thinking-235b", "Qwen cached plan");
|
|
cacheReasoning("call_glm_think", "glm", "glm-5-thinking", "GLM cached plan");
|
|
|
|
const qwen = translateWithToolHistory("qwen", "qwen3-thinking-235b", "call_qwen_think");
|
|
const glm = translateWithToolHistory("glm", "glm-5-thinking", "call_glm_think");
|
|
|
|
assert.equal(qwen.messages[1].reasoning_content, "Qwen cached plan");
|
|
assert.equal(glm.messages[1].reasoning_content, "GLM cached plan");
|
|
assert.equal(getReasoningCacheServiceStats().replays, 2);
|
|
});
|
|
|
|
it("should not inject reasoning_content for generic non-reasoning providers", () => {
|
|
clearReasoningCacheAll();
|
|
clearModelsDevCapabilities();
|
|
cacheReasoning("call_openai", "openai", "gpt-4o", "Should not replay");
|
|
|
|
const translated = translateWithToolHistory("openai", "gpt-4o", "call_openai");
|
|
|
|
assert.equal(translated.messages[1].reasoning_content, undefined);
|
|
assert.equal(getReasoningCacheServiceStats().replays, 0);
|
|
});
|
|
|
|
it("should support the full capture then replay flow", () => {
|
|
clearReasoningCacheAll();
|
|
clearModelsDevCapabilities();
|
|
saveModelsDevCapabilities({
|
|
deepseek: {
|
|
"deepseek-reasoner": buildCapability({
|
|
interleaved_field: "reasoning_content",
|
|
reasoning: true,
|
|
tool_call: true,
|
|
}),
|
|
},
|
|
});
|
|
|
|
const captured = cacheReasoningFromAssistantMessage(
|
|
{
|
|
role: "assistant",
|
|
reasoning_content: "Full flow cached plan",
|
|
tool_calls: [{ id: "call_full_flow", type: "function" }],
|
|
},
|
|
"deepseek",
|
|
"deepseek-reasoner"
|
|
);
|
|
|
|
const translated = translateWithToolHistory("deepseek", "deepseek-reasoner", "call_full_flow");
|
|
|
|
assert.equal(captured, 1);
|
|
assert.equal(translated.messages[1].reasoning_content, "Full flow cached plan");
|
|
assert.equal(getReasoningCacheServiceStats().replays, 1);
|
|
});
|
|
|
|
it("should strip reasoning_content when model has no interleaved replay signal", () => {
|
|
clearReasoningCacheAll();
|
|
clearModelsDevCapabilities();
|
|
|
|
const translated = translateRequest(
|
|
FORMATS.OPENAI,
|
|
FORMATS.OPENAI,
|
|
"deepseek-reasoner",
|
|
{
|
|
messages: [
|
|
{ role: "user", content: "hello" },
|
|
{
|
|
role: "assistant",
|
|
content: "ok",
|
|
reasoning_content: "should be stripped",
|
|
},
|
|
],
|
|
},
|
|
false,
|
|
null,
|
|
"deepseek"
|
|
);
|
|
|
|
assert.equal(translated.messages[1].reasoning_content, undefined);
|
|
});
|
|
|
|
it("should not inject reasoning_content when interleaved field is reasoning_details", () => {
|
|
clearReasoningCacheAll();
|
|
clearModelsDevCapabilities();
|
|
saveModelsDevCapabilities({
|
|
testprovider: {
|
|
"test-reasoning-details": buildCapability({
|
|
interleaved_field: "reasoning_details",
|
|
reasoning: true,
|
|
tool_call: true,
|
|
}),
|
|
},
|
|
});
|
|
cacheReasoning("call_details", "testprovider", "test-reasoning-details", "cached");
|
|
|
|
const translated = translateWithToolHistory(
|
|
"testprovider",
|
|
"test-reasoning-details",
|
|
"call_details"
|
|
);
|
|
|
|
assert.equal(translated.messages[1].reasoning_content, undefined);
|
|
});
|
|
});
|
|
|
|
describe("Reasoning Replay Cache — API Route", () => {
|
|
before(() => {
|
|
clearReasoningCacheAll();
|
|
});
|
|
|
|
after(() => {
|
|
clearReasoningCacheAll();
|
|
});
|
|
|
|
it("should return stats and entries from GET", async () => {
|
|
clearReasoningCacheAll();
|
|
cacheReasoning("call_api_get", "deepseek", "deepseek-reasoner", "API visible reasoning");
|
|
|
|
const response = await GET(
|
|
new Request("http://localhost/api/cache/reasoning?provider=deepseek") as never
|
|
);
|
|
const body = await response.json();
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.stats.dbEntries, 1);
|
|
assert.equal(body.entries.length, 1);
|
|
assert.equal(body.entries[0].toolCallId, "call_api_get");
|
|
});
|
|
|
|
it("should delete a single entry by toolCallId", async () => {
|
|
clearReasoningCacheAll();
|
|
cacheReasoning("call_api_delete_1", "deepseek", "deepseek-reasoner", "Delete API");
|
|
cacheReasoning("call_api_delete_2", "deepseek", "deepseek-reasoner", "Keep API");
|
|
|
|
const response = await DELETE(
|
|
new Request("http://localhost/api/cache/reasoning?toolCallId=call_api_delete_1") as never
|
|
);
|
|
const body = await response.json();
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.scope, "toolCallId");
|
|
assert.equal(body.cleared, 1);
|
|
assert.equal(lookupReasoning("call_api_delete_1"), null);
|
|
assert.equal(lookupReasoning("call_api_delete_2"), "Keep API");
|
|
});
|
|
|
|
it("should delete entries by provider", async () => {
|
|
clearReasoningCacheAll();
|
|
cacheReasoning("call_api_provider_ds", "deepseek", "deepseek-reasoner", "Delete provider");
|
|
cacheReasoning("call_api_provider_kimi", "kimi", "kimi-k2.5", "Keep provider");
|
|
|
|
const response = await DELETE(
|
|
new Request("http://localhost/api/cache/reasoning?provider=deepseek") as never
|
|
);
|
|
const body = await response.json();
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.scope, "provider");
|
|
assert.equal(body.cleared, 1);
|
|
assert.equal(lookupReasoning("call_api_provider_ds"), null);
|
|
assert.equal(lookupReasoning("call_api_provider_kimi"), "Keep provider");
|
|
});
|
|
});
|