mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-07-31 12:22:14 +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>
498 lines
15 KiB
TypeScript
498 lines
15 KiB
TypeScript
import { CORS_HEADERS } from "./cors.ts";
|
|
import { getDefaultErrorMessage, getErrorInfo } from "../config/errorConfig.ts";
|
|
import { normalizePayloadForLog } from "@/lib/logPayloads";
|
|
import type { ModelCooldownErrorPayload } from "@/types";
|
|
|
|
/**
|
|
* Sanitize an error message to prevent stack trace exposure in API responses.
|
|
* Strips stack traces, file paths, and absolute Windows/POSIX paths from
|
|
* error messages before they reach the client.
|
|
*/
|
|
interface ErrorResponseBody {
|
|
error: {
|
|
message: string;
|
|
type?: string;
|
|
code?: string;
|
|
};
|
|
upstream_details?: Record<string, unknown> | null; // sanitized upstream provider body
|
|
}
|
|
|
|
// Length cap protects against pathological inputs even before tokenization.
|
|
const MAX_ERROR_LEN = 4096;
|
|
const SOURCE_EXT = ["ts", "tsx", "js", "jsx", "mjs", "cjs"] as const;
|
|
|
|
function looksLikeAbsolutePath(tok: string): boolean {
|
|
// POSIX: "/<...>.ts" (optionally followed by :line[:col]).
|
|
// Windows: "C:\<...>.ts" or "C:/<...>.ts".
|
|
if (tok.length < 4 || tok.length > 2048) return false;
|
|
const isPosix = tok.charCodeAt(0) === 0x2f; // '/'
|
|
const isWindows = tok.length > 2 && tok.charCodeAt(1) === 0x3a && /[A-Za-z]/.test(tok[0]);
|
|
if (!isPosix && !isWindows) return false;
|
|
const dot = tok.lastIndexOf(".");
|
|
if (dot <= 0 || dot === tok.length - 1) return false;
|
|
const ext = tok
|
|
.slice(dot + 1)
|
|
.split(":", 1)[0]
|
|
.toLowerCase();
|
|
return (SOURCE_EXT as readonly string[]).includes(ext);
|
|
}
|
|
|
|
/**
|
|
* Strip stack-trace tail and absolute source paths from error messages.
|
|
*
|
|
* Implemented via simple whitespace tokenization (linear time) instead of a
|
|
* single complex regex, so CodeQL `js/polynomial-redos` stays clean even when
|
|
* the runtime error message is attacker-controlled.
|
|
*/
|
|
export function sanitizeErrorMessage(message: unknown): string {
|
|
let str = typeof message === "string" ? message : String(message ?? "");
|
|
if (str.length > MAX_ERROR_LEN) str = str.slice(0, MAX_ERROR_LEN);
|
|
const nl = str.indexOf("\n");
|
|
const firstLine = nl >= 0 ? str.slice(0, nl) : str;
|
|
// Preserve original whitespace by splitting on captured separator.
|
|
const parts = firstLine.split(/(\s+)/);
|
|
for (let i = 0; i < parts.length; i++) {
|
|
if (looksLikeAbsolutePath(parts[i])) parts[i] = "<path>";
|
|
}
|
|
return parts.join("");
|
|
}
|
|
|
|
const BLOCKED_KEYS = /stack|trace|path|file|cwd|dir|password|secret|token|key/i;
|
|
const MAX_DEPTH = 4;
|
|
|
|
/**
|
|
* Recursively sanitize an arbitrary JSON value from an upstream provider body.
|
|
* - Strings: run through sanitizeErrorMessage (strips stacks + absolute paths).
|
|
* - Keys matching BLOCKED_KEYS are dropped (credential/path guards).
|
|
* - Depth capped at MAX_DEPTH to prevent pathological nesting.
|
|
* - Arrays capped at 32 elements.
|
|
* - Returns null for null/undefined/non-JSON-serializable values.
|
|
*/
|
|
export function sanitizeUpstreamDetails(value: unknown, depth = 0): unknown {
|
|
if (depth > MAX_DEPTH) return "[truncated]";
|
|
if (value === null || value === undefined) return null;
|
|
if (typeof value === "string") return sanitizeErrorMessage(value);
|
|
if (typeof value === "number" || typeof value === "boolean") return value;
|
|
if (Array.isArray(value)) {
|
|
return value.slice(0, 32).map((v) => sanitizeUpstreamDetails(v, depth + 1));
|
|
}
|
|
if (typeof value === "object") {
|
|
const out: Record<string, unknown> = {};
|
|
for (const [k, v] of Object.entries(value as Record<string, unknown>)) {
|
|
if (BLOCKED_KEYS.test(k)) continue;
|
|
out[k] = sanitizeUpstreamDetails(v, depth + 1);
|
|
}
|
|
return out;
|
|
}
|
|
return null;
|
|
}
|
|
|
|
/**
|
|
* Build OpenAI-compatible error response body. Message is always sanitized
|
|
* so callers do not need to remember to strip stack traces themselves.
|
|
* Optional third argument `upstreamDetails` (raw parsed provider body) is
|
|
* sanitized by sanitizeUpstreamDetails before inclusion as `upstream_details`.
|
|
*/
|
|
export function buildErrorBody(
|
|
statusCode: number,
|
|
message: string,
|
|
upstreamDetails?: unknown
|
|
): ErrorResponseBody {
|
|
const errorInfo = getErrorInfo(statusCode);
|
|
const safeMessage = sanitizeErrorMessage(message) || getDefaultErrorMessage(statusCode);
|
|
|
|
const body: ErrorResponseBody = {
|
|
error: {
|
|
message: safeMessage,
|
|
type: errorInfo.type,
|
|
code: errorInfo.code,
|
|
},
|
|
};
|
|
|
|
if (upstreamDetails !== undefined && upstreamDetails !== null) {
|
|
const sanitized = sanitizeUpstreamDetails(upstreamDetails);
|
|
if (sanitized !== null && typeof sanitized === "object" && !Array.isArray(sanitized)) {
|
|
body.upstream_details = sanitized as Record<string, unknown>;
|
|
}
|
|
}
|
|
|
|
return body;
|
|
}
|
|
|
|
/**
|
|
* Create error Response object (for non-streaming)
|
|
* @param {number} statusCode - HTTP status code
|
|
* @param {string} message - Error message
|
|
* @returns {Response} HTTP Response object
|
|
*/
|
|
export function errorResponse(statusCode: number, message: string): Response {
|
|
return new Response(JSON.stringify(buildErrorBody(statusCode, sanitizeErrorMessage(message))), {
|
|
status: statusCode,
|
|
headers: {
|
|
"Content-Type": "application/json",
|
|
},
|
|
});
|
|
}
|
|
|
|
/**
|
|
* Write error to SSE stream (for streaming)
|
|
* @param {WritableStreamDefaultWriter} writer - Stream writer
|
|
* @param {number} statusCode - HTTP status code
|
|
* @param {string} message - Error message
|
|
*/
|
|
export async function writeStreamError(
|
|
writer: WritableStreamDefaultWriter<Uint8Array>,
|
|
statusCode: number,
|
|
message: string
|
|
): Promise<void> {
|
|
const errorBody = buildErrorBody(statusCode, sanitizeErrorMessage(message));
|
|
const encoder = new TextEncoder();
|
|
await writer.write(encoder.encode(`data: ${JSON.stringify(errorBody)}\n\n`));
|
|
}
|
|
|
|
function normalizeRetryAfterSeconds(retryAfter?: string | number | Date | null): number {
|
|
if (typeof retryAfter === "number" && Number.isFinite(retryAfter)) {
|
|
if (retryAfter > 0 && retryAfter < 1_000_000_000) {
|
|
return Math.max(Math.ceil(retryAfter), 1);
|
|
}
|
|
|
|
const retryTimeMs = new Date(retryAfter).getTime();
|
|
if (Number.isFinite(retryTimeMs)) {
|
|
return Math.max(Math.ceil((retryTimeMs - Date.now()) / 1000), 1);
|
|
}
|
|
}
|
|
|
|
if (retryAfter instanceof Date || typeof retryAfter === "string") {
|
|
const retryTimeMs = new Date(retryAfter).getTime();
|
|
if (Number.isFinite(retryTimeMs)) {
|
|
return Math.max(Math.ceil((retryTimeMs - Date.now()) / 1000), 1);
|
|
}
|
|
}
|
|
|
|
return 1;
|
|
}
|
|
|
|
/**
|
|
* Parse Antigravity error message to extract retry time
|
|
* Example: "You have exhausted your capacity on this model. Your quota will reset after 2h7m23s."
|
|
* @param {string} message - Error message
|
|
* @returns {number|null} Retry time in milliseconds, or null if not found
|
|
*/
|
|
export function parseAntigravityRetryTime(message: unknown): number | null {
|
|
if (typeof message !== "string") return null;
|
|
|
|
// Match patterns like: 2h7m23s, 5m30s, 45s, 1h20m, etc.
|
|
const match = message.match(/reset after (\d+h)?(\d+m)?(\d+s)?/i);
|
|
if (!match) return null;
|
|
|
|
let totalMs = 0;
|
|
|
|
// Extract hours
|
|
if (match[1]) {
|
|
const hours = parseInt(match[1]);
|
|
totalMs += hours * 60 * 60 * 1000;
|
|
}
|
|
|
|
// Extract minutes
|
|
if (match[2]) {
|
|
const minutes = parseInt(match[2]);
|
|
totalMs += minutes * 60 * 1000;
|
|
}
|
|
|
|
// Extract seconds
|
|
if (match[3]) {
|
|
const seconds = parseInt(match[3]);
|
|
totalMs += seconds * 1000;
|
|
}
|
|
|
|
return totalMs > 0 ? totalMs : null;
|
|
}
|
|
|
|
/**
|
|
* Parse upstream provider error response
|
|
* @param {Response} response - Fetch response from provider
|
|
* @param {string} provider - Provider name (for Antigravity-specific parsing)
|
|
* @returns {Promise<{statusCode: number, message: string, retryAfterMs: number|null, responseBody: unknown}>}
|
|
*/
|
|
export async function parseUpstreamError(response: Response, provider: string | null = null) {
|
|
let message: unknown = "";
|
|
let retryAfterMs: number | null = null;
|
|
let responseBody: unknown = null;
|
|
let errorCode: unknown = undefined;
|
|
let errorType: unknown = undefined;
|
|
|
|
try {
|
|
const text = await response.text();
|
|
responseBody = normalizePayloadForLog(text);
|
|
|
|
// Try parse as JSON
|
|
try {
|
|
const json = JSON.parse(text);
|
|
message = json.error?.message || json.message || json.error || text;
|
|
errorCode = json.error?.code || json.code;
|
|
errorType = json.error?.type || json.type;
|
|
} catch {
|
|
message = text;
|
|
}
|
|
} catch {
|
|
message = `Upstream error: ${response.status}`;
|
|
responseBody = { _rawText: message };
|
|
}
|
|
|
|
const messageStr = typeof message === "string" ? message : JSON.stringify(message);
|
|
|
|
const retryAfterHeader = response.headers?.get?.("retry-after");
|
|
if (retryAfterHeader && !retryAfterMs) {
|
|
const retryAfterSec = Number.parseInt(retryAfterHeader, 10);
|
|
if (Number.isFinite(retryAfterSec) && retryAfterSec > 0) {
|
|
retryAfterMs = retryAfterSec * 1000;
|
|
} else {
|
|
const retryAfterDate = new Date(retryAfterHeader).getTime();
|
|
if (Number.isFinite(retryAfterDate) && retryAfterDate > Date.now()) {
|
|
retryAfterMs = retryAfterDate - Date.now();
|
|
}
|
|
}
|
|
}
|
|
|
|
// Parse Antigravity-specific retry time from error message
|
|
if (provider === "antigravity" && response.status === 429) {
|
|
retryAfterMs = parseAntigravityRetryTime(messageStr);
|
|
}
|
|
|
|
// Also parse retry time for other providers (Qwen, etc.) with "quota will reset after XhYmZs" format
|
|
if (response.status === 429 && !retryAfterMs) {
|
|
retryAfterMs = parseAntigravityRetryTime(messageStr);
|
|
}
|
|
|
|
// Generic providers: "Please retry after 20s"
|
|
if (response.status === 429 && !retryAfterMs) {
|
|
const retryMatch = messageStr.match(/retry\s+after\s+(\d+)\s*s/i);
|
|
if (retryMatch) {
|
|
retryAfterMs = Number.parseInt(retryMatch[1], 10) * 1000;
|
|
}
|
|
}
|
|
|
|
// Cap maximum retry time at 24 hours to prevent infinite wait
|
|
const MAX_RETRY_MS = 24 * 60 * 60 * 1000;
|
|
if (retryAfterMs && retryAfterMs > MAX_RETRY_MS) {
|
|
retryAfterMs = MAX_RETRY_MS;
|
|
}
|
|
|
|
const responseHeaders: Record<string, string> | null = response.headers
|
|
? Object.fromEntries(response.headers.entries())
|
|
: null;
|
|
|
|
return {
|
|
statusCode: response.status,
|
|
message: messageStr,
|
|
errorCode,
|
|
errorType,
|
|
retryAfterMs,
|
|
responseBody,
|
|
responseHeaders,
|
|
};
|
|
}
|
|
|
|
/**
|
|
* Create error result for chatCore handler
|
|
* @param {number} statusCode - HTTP status code
|
|
* @param {string} message - Error message
|
|
* @param {number|null} retryAfterMs - Optional retry-after time in milliseconds
|
|
* @returns {{ success: false, status: number, error: string, response: Response, retryAfterMs?: number }}
|
|
*/
|
|
export function createErrorResult(
|
|
statusCode: number,
|
|
message: string,
|
|
retryAfterMs: number | null = null,
|
|
errorCode?: string,
|
|
errorType?: string,
|
|
upstreamDetails?: unknown
|
|
) {
|
|
const body = buildErrorBody(statusCode, message, upstreamDetails);
|
|
if (errorCode) {
|
|
body.error.code = errorCode;
|
|
}
|
|
if (errorType) {
|
|
body.error.type = errorType;
|
|
}
|
|
|
|
const result: {
|
|
success: false;
|
|
status: number;
|
|
error: string;
|
|
errorType?: string;
|
|
errorCode?: string;
|
|
response: Response;
|
|
retryAfterMs?: number;
|
|
} = {
|
|
success: false,
|
|
status: statusCode,
|
|
error: body.error.message,
|
|
errorType,
|
|
errorCode,
|
|
response: new Response(JSON.stringify(body), {
|
|
status: statusCode,
|
|
headers: { "Content-Type": "application/json" },
|
|
}),
|
|
};
|
|
|
|
// Add retryAfterMs if available (for Antigravity quota errors)
|
|
if (retryAfterMs) {
|
|
result.retryAfterMs = retryAfterMs;
|
|
}
|
|
|
|
return result;
|
|
}
|
|
|
|
/**
|
|
* Create unavailable response when all accounts are rate limited
|
|
* @param {number} statusCode - Original error status code
|
|
* @param {string} message - Error message (without retry info)
|
|
* @param {string} retryAfter - ISO timestamp when earliest account becomes available
|
|
* @param {string} retryAfterHuman - Human-readable retry info e.g. "reset after 30s"
|
|
* @returns {Response}
|
|
*/
|
|
export function unavailableResponse(
|
|
statusCode: number,
|
|
message: string,
|
|
retryAfter?: string | number | Date | null,
|
|
retryAfterHuman?: string
|
|
) {
|
|
const retryAfterSec = normalizeRetryAfterSeconds(retryAfter);
|
|
const msg = retryAfterHuman ? `${message} (${retryAfterHuman})` : message;
|
|
return new Response(JSON.stringify({ error: { message: msg } }), {
|
|
status: statusCode,
|
|
headers: {
|
|
"Content-Type": "application/json",
|
|
"Retry-After": String(retryAfterSec),
|
|
},
|
|
});
|
|
}
|
|
|
|
export function providerCircuitOpenResponse(
|
|
provider: string,
|
|
retryAfter?: string | number | Date | null
|
|
) {
|
|
const retryAfterSec = normalizeRetryAfterSeconds(retryAfter);
|
|
return new Response(
|
|
JSON.stringify({
|
|
error: {
|
|
message: `Provider ${provider} circuit breaker is open`,
|
|
type: "server_error",
|
|
code: "provider_circuit_open",
|
|
provider,
|
|
retry_after: retryAfterSec,
|
|
},
|
|
}),
|
|
{
|
|
status: 503,
|
|
headers: {
|
|
"Content-Type": "application/json",
|
|
"Retry-After": String(retryAfterSec),
|
|
"X-OmniRoute-Provider-Breaker": "open",
|
|
},
|
|
}
|
|
);
|
|
}
|
|
|
|
export function buildModelCooldownBody({
|
|
model,
|
|
retryAfterSec,
|
|
}: {
|
|
model?: string | null;
|
|
retryAfterSec: number;
|
|
}): ModelCooldownErrorPayload {
|
|
const resolvedModel = typeof model === "string" && model.trim().length > 0 ? model.trim() : null;
|
|
|
|
return {
|
|
error: {
|
|
message: resolvedModel
|
|
? `All credentials for model ${resolvedModel} are cooling down`
|
|
: "All credentials for the requested model are cooling down",
|
|
type: "rate_limit_error",
|
|
code: "model_cooldown",
|
|
...(resolvedModel ? { model: resolvedModel } : {}),
|
|
reset_seconds: Math.max(Math.ceil(retryAfterSec), 1),
|
|
},
|
|
};
|
|
}
|
|
|
|
export function modelCooldownResponse({
|
|
model,
|
|
retryAfter,
|
|
}: {
|
|
model?: string | null;
|
|
retryAfter?: string | number | Date | null;
|
|
}) {
|
|
const retryAfterSec = normalizeRetryAfterSeconds(retryAfter);
|
|
return new Response(
|
|
JSON.stringify(
|
|
buildModelCooldownBody({
|
|
model,
|
|
retryAfterSec,
|
|
})
|
|
),
|
|
{
|
|
status: 429,
|
|
headers: {
|
|
"Content-Type": "application/json",
|
|
"Retry-After": String(retryAfterSec),
|
|
},
|
|
}
|
|
);
|
|
}
|
|
|
|
/**
|
|
* Build an executor-style error result (response + url + headers + transformedBody).
|
|
* Shared by web-cookie executors that return the `{ response, url, headers, transformedBody }` shape.
|
|
*/
|
|
export function makeExecutorErrorResult(
|
|
status: number,
|
|
message: string,
|
|
body: unknown,
|
|
url: string
|
|
) {
|
|
return {
|
|
response: new Response(
|
|
JSON.stringify({
|
|
error: {
|
|
message: sanitizeErrorMessage(message),
|
|
type: "upstream_error",
|
|
code: `HTTP_${status}`,
|
|
},
|
|
}),
|
|
{ status, headers: { "Content-Type": "application/json" } }
|
|
),
|
|
url,
|
|
headers: {} as Record<string, string>,
|
|
transformedBody: body,
|
|
};
|
|
}
|
|
|
|
/**
|
|
* Normalize a cookie string: strip a leading "Cookie:" prefix if present.
|
|
*/
|
|
export function normalizeCookie(raw: string): string {
|
|
return raw?.startsWith("Cookie:") ? raw.slice(7).trim() : raw || "";
|
|
}
|
|
|
|
/**
|
|
* Format provider error with context
|
|
* @param {Error} error - Original error
|
|
* @param {string} provider - Provider name
|
|
* @param {string} model - Model name
|
|
* @param {number|string} statusCode - HTTP status code or error code
|
|
* @returns {string} Formatted error message
|
|
*/
|
|
export function formatProviderError(
|
|
error: { code?: string | number; message?: string } | Error,
|
|
provider: string,
|
|
model: string,
|
|
statusCode?: string | number | null
|
|
): string {
|
|
const providerCode = "code" in error ? error.code : undefined;
|
|
const code = statusCode || providerCode || "FETCH_FAILED";
|
|
const message = error.message || "Unknown error";
|
|
return `[${code}]: ${message}`;
|
|
}
|