mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-07-31 04:12:10 +03:00
* chore(release): open v3.8.36 development cycle * refactor(chatCore): extrai resolveCompressionSettings (#3501) (#4826) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 1/13) * refactor(chatCore): extrai predicados puros de combo de compressão (#3501) (#4824) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 2/13) * refactor(chatCore): extrai emitOutputStyleTelemetry (#3501) (#4811) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 3/13) * refactor(chatCore): extrai writeCompressionAnalytics (bloco analytics completo, #3501) (#4817) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 4/13) * refactor(chatCore): extrai runPluginOnRequestHook (#3501) (#4827) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 5/13) * refactor(chatCore): extrai applyClientUsageBuffer (buffer/estimate de usage non-streaming, #3501) (#4832) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 6/13) * refactor(chatCore): extrai buildPostCallGuardrailContext (contexto guardrail post-call, #3501) (#4831) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 7/13) * refactor(chatCore): extrai storeSemanticCacheResponse (cache-store non-streaming, #3501) (#4828) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 8/13) * refactor(chatCore): extrai buildNonStreamingResponseHeaders (headers de resposta non-streaming, #3501) (#4835) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 9/13) * refactor(chatCore): extrai maybeConvertJsonBodyToSse (#3089 JSON→SSE streaming, #3501) (#4833) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 10/13) * refactor(chatCore): extrai assembleStreamingResponseHeaders (headers de resposta streaming, #3501) (#4836) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 11/13) * refactor(chatCore): extrai storeStreamingSemanticCacheResponse (cache-store streaming, #3501) (#4829) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 12/13) * refactor(chatCore): extrai assembleStreamingPipeline (chain de transforms streaming, #3501) (#4837) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 13/13) * ci(quality): shift heavy validations to the PR→release fast-path (release-acceleration) (#4857) * feat(quality): add check:test-runner-api gate (vitest-only dirs must use vitest API) * feat(release): reusable CHANGELOG i18n-mirror sync script * chore(ops): add prune-stale-worktrees.sh (dry-run by default) * ci(quality): run test-runner-api + docs-all + vitest + full unit suite on PR->release fast-path --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(quota): cota exclusiva lista qtSd/ no /v1/models (#4806) + limite EPSILON não bloqueia (#4830) Integrated into release/v3.8.36 — quota-exclusive qtSd/ listing (#4806) + EPSILON placeholder no longer blocks; rebuilt from stale base (3 defining commits cherry-picked clean over release tip) * feat(sse): add Google Flow video-generation provider (#4569) (#4769) Integrated into release/v3.8.36 — Google Flow video-generation provider (#4569), release-green validated (typecheck + 21 tests + file-size) * fix(api): auth on compression run-telemetry + document OMNIROUTE_EVAL_CREDENTIALS (#4694, #4720) (#4796) Integrated into release/v3.8.36 — auth on compression run-telemetry + OMNIROUTE_EVAL_CREDENTIALS doc, release-green validated (typecheck + 3 tests + env-doc-sync) * fix(translator): strip top-level client_metadata on the OpenAI passthrough (port from 9router#1157) (#4624) Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated) * fix(translator): normalize `developer` role to `system` for OpenAI-format providers (#4625) Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated) * fix(translator): emit </think> close marker for Anthropic thinking blocks (#4633) Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated) * fix(translator): normalize tools to Anthropic-native shape for non-Anthropic providers (#4650) Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated) * fix(gemini): preserve `pattern` in antigravity tool schema sanitizer (#4651) Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated) * fix(perplexity): validate API keys via /v1/models endpoint (#4654) Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated) * fix(image): prevent compatible nodes from shadowing provider aliases (#4656) Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated) * fix(cli-tools): tolerate JSONC (comments, trailing commas) in tool settings (#4659) Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated) * fix(security): validate kiro region to prevent SSRF (GHSA-6mwv-4mrm-5p3m) (#4629) Integrated into release/v3.8.36 — kiro region SSRF guard (GHSA-6mwv-4mrm-5p3m), port rebuilt clean over release tip * fix(cli): harden the systray2 tray runtime (port of 9router#1080) (#4628) Integrated into release/v3.8.36 — port rebuilt clean over release tip, release-green validated * fix(test): validate anthropic-compatible connections via POST /v1/messages (#4657) Integrated into release/v3.8.36 — anthropic-compat validation via POST /v1/messages (port 584cf66a), rebuilt clean + baseline; release-green * fix(executors): strip params unsupported by the target provider/model (#4658) Integrated into release/v3.8.36 — port rebuilt clean over release tip, release-green validated * fix(claude-oauth): respect 429 backoff on usage endpoint to reduce spam (#4655) Integrated into release/v3.8.36 — port rebuilt clean over release tip, release-green validated * feat(api/v1): include alias-backed models in /v1/models listing (#4630) Integrated into release/v3.8.36 — port rebuilt clean over release tip, release-green validated * chore(quality): rebaseline catalog.ts 1574->1577 (#4630 aliases sobre quota-exclusive da release) (#4879) rebaseline * feat(compression): Kiro/CodeWhisperer tool-result compression engine (#4635) Integrated into release/v3.8.36 — port rebuilt clean, release-green * fix(security): don't trust loopback socket as local when behind reverse proxy (#4632) Integrated into release/v3.8.36 — port rebuilt clean, release-green * fix(opencode): preserve DeepSeek reasoning content in streamed responses (#4631) Integrated into release/v3.8.36 — DeepSeek reasoning_content injection (port #1099); release-green * fix(copilot,antigravity): cap maxOutputTokens at 16384 to stop "Invalid Argument" 400 (#4636) Integrated into release/v3.8.36 — cap maxOutputTokens 16384 antigravity (port #779); release-green * fix(dashboard): show custom vision models in LLM selector (#4653) Integrated into release/v3.8.36 — custom vision models in LLM selector (port 5e5e78d3); release-green * fix(claude): omit adaptive thinking + output_config.effort for haiku (#4661) Integrated into release/v3.8.36 — haiku adaptive-thinking omit (port); release-green * feat(provider): CodeBuddy CN (copilot.tencent.com) — full stack (#4664) Integrated into release/v3.8.36 — CodeBuddy CN provider (port efd20be8); usage.ts import + public-creds allowlist line reconciled; release-green * feat(combo): Fusion strategy — parallel panel + judge synthesis (16th strategy) (#4652) Integrated into release/v3.8.36 — Fusion combo strategy (16th, port 87e5c1c6); combo.ts baseline reconciled; release-green * feat(proxy-pool): Deno Deploy relays + group action buttons (#4643) Integrated into release/v3.8.36 — Deno Deploy relays (port #1437); proxies.ts baseline reconciled + env docs restored; release-green * fix(security): pin image fetch DNS resolution to prevent SSRF rebinding (GHSA-cmhj-wh2f-9cgx) (#4634) Integrated into release/v3.8.36 — pin DNS for image fetch SSRF rebinding guard (GHSA-cmhj-wh2f-9cgx, port c7d07448); caller DNS stubs + test-file baseline reconciled; release-green * fix(github): route Copilot Codex models to /responses (port from 9router#102) (#4626) Integrated into release/v3.8.36 — route Copilot Codex models to /responses (port #102); release-green * fix(copilot): never route Gemini/Claude variants to /responses (chat-completions only) (#4627) Integrated into release/v3.8.36 — never route Gemini/Claude to /responses (port #1536); fused with #4626 codex routing via supportsResponsesEndpoint gate; release-green * docs(ops): add canonical incident response runbook (#4868) Integrated into release/v3.8.36 * docs(perf): add per-endpoint p50/p95/p99 latency + cost budgets (#4867) Integrated into release/v3.8.36 * fix(proxy): fan out direct dispatcher streams (#4803) Integrated into release/v3.8.36 * fix(antigravity): exclude standard Gemini rate limit message from quota exhaustion keywords (#4810) Integrated into release/v3.8.36 * fix(sse): skip third-party tool-name cloak for Anthropic server tools (#4808) Integrated into release/v3.8.36 * fix(install): make transformers optional for CUDA-host installs (#4807) Integrated into release/v3.8.36 * fix(combo): propagate selected connection ID to fallback error responses for correct model lockout (#4809) Integrated into release/v3.8.36 * fix db storage tuning settings (#4834) Integrated into release/v3.8.36 * fix(sse): drop ccp pin when pinned provider is durably unhealthy (failover + anti-flap) (#4864) Integrated into release/v3.8.36 * fix(claude): skip mcp__ tool-name cloak + guard missing connectionId (#4861) Integrated into release/v3.8.36 * chore(quality): reconcile env-doc + file-size base-reds in release/v3.8.36 (#4886) - env-doc-sync: document PIN_DROP_BACKOFF_LEVEL / PIN_DROP_GRACE_MS (added by the ccp-pin health gate #4864) in .env.example + ENVIRONMENT.md. - file-size: rebaseline image-generation-handler.test.ts 1996 -> 2019 to its actual size (pre-existing drift). Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(codex): drop non-standard codex.* events that break responses.stream (env-gated, #4602) (#4715) Integrated into release/v3.8.36 * feat(routing): honor X-Route-Model header to override body.model (#4863) Integrated into release/v3.8.36 * feat(live-ws): allow non-loopback clients via LIVE_WS_ALLOWED_HOSTS (closes #4873) (#4877) Integrated into release/v3.8.36 (live-ws + combo-api commits; Tailscale CGNAT commit held pending opt-in/opt-out decision) * chore(claude,codex): bump pinned CLI identity — Claude 2.1.158→2.1.187, Codex 0.132.0→0.142.0 (#4883) Integrated into release/v3.8.36 * fix(security): SSRF allowlist bypass via x-relay-path nos relays Deno/Vercel (#4899) Integrated into release/v3.8.36 * feat(quota): recuperação proativa de conexões em cooldown (cron heal) [Fase 3 #8] (#4900) Integrated into release/v3.8.36 * fix(quota): policy inválida não vaza allow + guard connectionIds vazio [Fase 3 #10] (#4901) Integrated into release/v3.8.36 * feat(quota): saturação real do Claude no fair-share via /api/oauth/usage (#4885) Integrated into release/v3.8.36 * chore(dashboard): rename Qoder display label from "Qoder AI" to "Qoder" (#4733) Integrated into release/v3.8.36 * fix(ci): include coverage/lcov.info in coverage-report artifact for SonarQube (#4670) Integrated into release/v3.8.36 * fix(cli): bump better-sqlite3 runtime pin to 12.10.1 for Node 26 (#4685) Integrated into release/v3.8.36 * docs: clarify Kiro is ~50 credits/month per account, not unlimited (#4690) Integrated into release/v3.8.36 * docs(agentbridge): document Electron NODE_EXTRA_CA_CERTS, real model IDs, identity caveat (#4718) Integrated into release/v3.8.36 * docs(ops): document the release-green family (green-prs, check:release-green, babysit, nightly) (#4679) Integrated into release/v3.8.36 * fix(translator): replay reasoning_content on plain Xiaomi MiMo turns (port from 9router#1321) (#4639) Integrated into release/v3.8.36 * feat(opencode-go): advertise glm-5.2 and kimi-k2.7-code (align with official Go endpoints) (#4711) Integrated into release/v3.8.36 * feat(db): track API endpoint dimension on usage_history (#4676) Integrated into release/v3.8.36 (migration renumbered 103→105; endpoint plumbed through extracted usage-stats helpers) * fix(cli): SIGKILL systray child PID before IPC close to avoid macOS NSStatusItem orphan (#4732) Integrated into release/v3.8.36 * feat(proxy-pool): Cloudflare Workers proxy deployer + pool integration (#4640) Integrated into release/v3.8.36 (relay type added to RELAY_TYPES set; dropdown UX preserved + Cloudflare item added; proxies.ts file-size rebaselined 1057→1060) * chore(quality): conserta base-red de release/v3.8.36 (gates + 7 testes + build MDX) (#4915) A base tinha base-red sistêmica herdada de PRs de outras sessões, bloqueando TODOS os PRs do ciclo (o TIA roda a suíte full em fail-safe p/ diffs hub). 4 Fast Quality Gates: - test-discovery (#4877): live-server-allowlist.test.ts em tests/unit/server/ (não-coletado) + vitest → nunca rodava. Convertido p/ node:test em tests/unit/security/. - any-budget:t11 (#4664): 3 explicit-any em tokenRefresh.ts tipados (sem crescer file-size). - docs-symbols (#4868): rotas inexistentes → /api/system/version e PUT /api/providers/{id} {isActive:false}. - docs-all fabricated-claim (#4868 + #4718): 5 bin/*.sh reais criados (rollback, snapshot-data, restore-data, restore-policies, cold-start-bench) + _ops-common.sh (snapshot VACUUM INTO, guards de confirmação/TTY, testes de contrato); NODE_EXTRA_CA_CERTS (env de runtime Node) na allowlist do checker. 7 testes unit base-red (de features alheias à quota): - oauth-providers-config (#4664): teste alinhado ao provider codebuddy-cn do registry. - antigravity-model-aliases (#4636): maxOutputTokens esperado 32769→16384 (cap intencional). - provider-request-capture #4091 (#4861): exemplo do teste trocado de mcp__ (que #4861 isenta de cloak por causa dos 400s de assimetria de histórico) para um tool de terceiro cloakável — preserva o invariante de #4091 SEM reverter #4861. - combo-error-response: convertido de vitest p/ node:test (era coletado pelo glob node:test e crashava); api/** e server/** removidos do vitest.config (config morta). Build MDX (dast-smoke, #4679): - docs/ops/RELEASE_GREEN.md não tinha frontmatter `title` → fumadocs-mdx rejeitava no webpack compile ("invalid frontmatter: title expected string"), quebrando o next build (e o deploy). Frontmatter title adicionado (único doc do collection sem ele). 17/17 Fast Quality Gates + suíte unit completa (17737 testes, 0 fail) + vitest verdes localmente. Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * feat(quota): saturação proativa por headers de tokens (universal) [Fase 3 #2] (#4907) storeRateLimitHeaders só capturava os headers de REQUESTS (RPM/min), que não refletem a pressão de TOKENS. Agora também parseia os headers de tokens (em toda resposta, sucesso também) para throttle proativo antes do 429: - Anthropic: anthropic-ratelimit-tokens-{limit,remaining,reset} (+ input/output), RFC3339. - OpenAI: x-ratelimit-{limit,remaining,reset}-tokens, reset em duração (6m0s). saturation = 1 − remaining/limit; resetAt normalizado a epoch (parse de duração ReDoS-safe). getTokenHeaderSaturation por (provider, connectionId). fetchGeneric- Saturation passa a usar esse sinal (complementa o oauth/usage do #1, que segue primário p/ Claude). Fail-open, cache mantido, request-path inalterado. 16 testes novos + regressão (oauth/usage #1 8/8, signals 6/6) = 30/30; typecheck:core + eslint limpos. Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * feat(quota): estratégia de combo "headroom" — seleção por folga de cota [Fase 3 #4] (#4908) Nova estratégia de roteamento que escolhe a conexão com MAIS folga de plano: headroom = 1 − max(util_5h, util_7d) (técnica do dario), via getSaturation (melhorado p/ Claude no #1). Proativo em vez de só fill-first reativo. - Helper PURO headroomRanking.ts (computeHeadroom + rankByHeadroom; saturação injetada, não-mutante, tie-break estável, fail-open). - Orderer async em combo/quotaStrategies.ts (reusa a maquinaria reset-aware de expansão de conexões + concorrência limitada; seam injetável). - Registrada como "headroom" em routingStrategies (combo-only); fill-first segue default — nenhuma estratégia existente tocada. - baseline file-size combo.ts 3168->3180 (só +12L de dispatch; lógica fora do god-file). 16 testes novos + combo-strategies 15/15 = 31/31; typecheck:core + eslint + file-size limpos. Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * feat(quota): cap per-(key,model) — quota_allocation_model_caps [Fase 3 #7] (#4927) * feat(quota): cap per-(key,model) com tabela quota_allocation_model_caps [Fase 3 #7] Fecha o buraco onde uma API key pode drenar o pool inteiro consumindo um único modelo. Tabela nova: quota_allocation_model_caps(pool_id, api_key_id, model, cap_value, cap_unit) PK composta (pool_id, api_key_id, model). cap_unit alinhado ao QuotaUnit existente. Comportamento: keyA acima do cap para modelo M → bloqueada somente em M; ainda permitida em qualquer outro modelo no mesmo pool. Cap <= EPSILON → ignorado (seed). Consumo por-(key,model) usa bucket segregado no quota_consumption existente (poolId mangled ':model:<model>') com window fixa 'hourly'; nenhuma nova tabela ou método de store necessário. Módulo novo: src/lib/db/quotaModelCaps.ts (getModelCap/setModelCap/deleteModelCap/listModelCaps) enforce.ts ganha o pre-check em enforceQuotaShare + recording em recordConsumption. EnforceInput e RecordConsumptionInput ganham model?: string (backward-compatible). localDb.ts re-exporta os 4 helpers (Hard Rule #2). TDD: tests/unit/quota-per-key-model.test.ts — 4 cenários (bloqueia em M, permite em M2, sem cap → sem bloqueio, EPSILON → ignorado). Todos os gates de qualidade passam. * feat(quota): plumba model resolvido no hot path para ativar o per-(key,model) cap [Fase 3 #7] A tabela/enforce do commit anterior estavam INERTES: o hot path não passava `model` ao enforce nem ao record, então nenhum model-cap disparava em produção. Plumbagem (model resolvido = mesma var usada no log/roteamento, pós background-redirect/alias): - chatCore.ts: enforceQuotaShare ganha `model`; scheduleQuotaShareConsumption recebe `model`. - chatCore/quotaShareConsumption.ts: threade `model` no RecordConsumptionInput (non-streaming). - spendRecorder.ts: recordStreamingConsumption já recebia `model` — agora o coloca no RecordConsumptionInput (streaming accrue por-modelo). - embeddings.ts: enforce + record ganham `model`. Namespace do cap = id do modelo RESOLVIDO (o mesmo de modelForScope/pendingScope/getUnsupportedParams), não o requestedModel cru nem o finalModelToUpstream (sem prefixo de provider). Operador configura o cap contra esse id. `model || undefined` em todos os pontos: vazio/null → check pulado (fail-safe, zero latência — só um campo no objeto). Teste de integração novo (tests/unit/quota-per-key-model-hotpath.test.ts): prova end-to-end que N consumos via scheduleQuotaShareConsumption({model}) → enforceQuotaShare({model}) bloqueia, e que outro modelo no mesmo pool ainda passa; + guard de que enforce SEM model nunca dispara model-cap. --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * feat(quota): session stickiness p/ integridade de prompt-cache [Fase 3 #5] (#4929) * feat(quota): session stickiness p/ integridade de prompt-cache [Fase 3 #5] Adiciona stickiness de sessão ao roteamento de combo: uma conversa multi-turno é roteada para a MESMA conexão enquanto ela permanecer saudável, evitando a perda do prompt-cache do provider (custo 5-10× sem stickiness, efeito conhecido no dario/clewdr). Implementação: - `open-sse/services/combo/sessionStickiness.ts` (novo, <800 linhas): mapa em memória (messageHash → connectionId) com TTL 15 min + cap 500 entradas; `applySessionStickiness` promove a conexão sticky ao índice 0 dos targets ordenados pelo strategy, guardado por `computeHeadroom > 0.15` (threshold); quando saturada (headroom ≤ 0.15), o binding é limpo e a seleção normal reage. Hash da sessão = SHA-256 dos primeiros chars da 1ª mensagem user → 16 hex chars. Seam de teste: `__setStickinessHeadroomFetcherForTests`. - `open-sse/services/combo.ts`: import + 2 pontos de integração (pré-eval-scores e pós-success), dentro do orçamento congelado de 3180 linhas. - `tests/unit/combo-session-stickiness.test.ts`: 19 testes node:test + assert/strict, todos via injeção de fetcher (zero rede/DB). Threshold 0.15: conexão a >85% de utilização está a um burst de rate-limit; o benefício de cache não compensa manter-se numa conexão degradada. Valor alinhado com a zona de soft-penalty do restante do engine de quota-share. * test(combo): isola combo-strategies da session stickiness (#5) selectedConnectionFor reusa o mesmo body, então o sticky map (#5) fixava a connection após a 1ª chamada e quebrava o round-robin tie-break do teste reset-aware. Limpa o sticky map no início da helper — a stickiness tem suíte própria (combo-session-stickiness). Sem enfraquecer asserts. --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * feat(quota): buckets multi-janela por conexão (5h/7d/per-model) [Fase 3 #3] (#4928) Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * refactor(providers): decompõe catálogo providers.ts em módulos de dados (godfile sweep, #3501) (#4917) Integrado em release/v3.8.36 (godfile sweep providers.ts, #3501) * refactor(pricing): decompõe pricing.ts em shared-tiers + DEFAULT_PRICING particionado (godfile sweep, #3501) (#4918) Integrado em release/v3.8.36 (godfile sweep pricing.ts, #3501) * refactor(api): extrai camada-folha pura de validation.ts (URL/headers/transport) (#4921) Integrado em release/v3.8.36 (validation.ts split fatia 1 — leaf layer) * refactor(api): extrai validators web-cookie + Meta AI de validation.ts (#4922) Integrado em release/v3.8.36 (validation.ts split fatia 2 — web-cookie + Meta AI) * refactor(api): extrai validators enterprise-cloud + probe compartilhado de validation.ts (#4923) Integrado em release/v3.8.36 (validation.ts split fatia 3 — enterprise-cloud + probe) * refactor(api): extrai validators áudio/speech + misc apikey de validation.ts (#4930) Integrado em release/v3.8.36 (validation.ts split fatia 4 — áudio/speech + misc apikey) * feat(quota): estratégia dedicada de quota-share (DRR + P2C in-flight + gating per-model) [Fase 3 #9] (#4939) * feat(quota): estratégia dedicada de quota-share (DRR + P2C in-flight + gating per-model) [Fase 3 #9] Estratégia interna "quota-share" isolada num módulo dedicado — NÃO toca a seleção/ fair-share genérica (decisão do dono: não mexer no que já funciona). Os combos qtSd/ (quotaCombos.ts) passam de fill-first para essa strategy; combo.ts ganha só 1 branch de dispatch que delega 100% ao módulo (nenhum case existente alterado). - quotaShareStrategy.ts: gating per-model (isBucketSaturated do #3) + DRR (quantum proporcional ao weight) + P2C sobre carga in-flight. - quotaShareInflight.ts: contador in-flight com TTL/lease de 120s — fallback do decrement-on-abort sem precisar instrumentar o combo genérico. - "quota-share" registrada como strategy INTERNA (não exposta na UI). - testes de síntese (quota-combo-balancing, quota-multiprovider) alinhados: a strategy esperada dos combos qtSd/ passa de "fill-first" para "quota-share" (alinhamento ao novo comportamento intencional, não mascaramento — os 73 testes de qtSd/ seguem verdes). * test(quota-share): alinha 2 scope-guards ao godfile sweep (base-reds que bloqueavam o CI) Dois testes de "arquivo contém X" quebraram por decomposições de godfile que outras sessões mergearam no release DURANTE a validação de #9 — NÃO são regressão de #9 (que não toca validation/oauth). Alinhados ao novo layout, asserts preservados: - proxy-bypass-scope-guard #3226: bypassProxyPatch foi extraído de validation.ts para validation/headers.ts (split #4921–#4930) → o teste lê a camada de validação. - sse-error-passthrough #3324: a windsurf authHint foi extraída de providers.ts para providers/oauth.ts → o teste lê o novo local. --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * refactor(api): extrai validators search + embedding/rerank de validation.ts (#4932) Integrated into release/v3.8.36 * refactor(api): extrai format-validators (OpenAI/Anthropic) de validation.ts (#4933) Integrated into release/v3.8.36 * refactor(db): extrai model-permission matching de db/apiKeys.ts (#4936) Integrated into release/v3.8.36 * refactor(db): extrai row-parsers + tipos compartilhados de db/apiKeys.ts (#4943) Integrated into release/v3.8.36 * refactor(db): extrai column-mapping (snake↔camel) de db/core.ts (#4947) Integrated into release/v3.8.36 * refactor(db): extrai schema-column reconciliation de db/core.ts (#4948) Integrated into release/v3.8.36 * refactor(sse): extrai scalar/format helpers de services/usage.ts (#4949) Integrated into release/v3.8.36 * refactor(sse): extrai quota-core (UsageQuota + builders) de services/usage.ts (#4950) Integrated into release/v3.8.36 * fix(translator): regroup parallel tool results adjacent to their assistant (#4714) (#4882) Integrated into release/v3.8.36 (fixes #4714) * fix(qoder): exchange PAT for jt-* job token before Cosy chat (#4683) (#4884) Integrated into release/v3.8.36 (fixes #4683) * refactor(sse): dedup fallback tool_call id helper (#4736) Integrated into release/v3.8.36 * refactor(open-sse): extract safeParseJSON util, dedup tryParseJSON (#4735) Integrated into release/v3.8.36 * fix(compression): eliminate ReDoS in math_inline preservation pattern (#4795) (#4838) Integrated into release/v3.8.36 (fixes #4795) * fix(combo): fetch models dynamically from custom provider endpoints (#4860) Integrated into release/v3.8.36 * feat(providers): update volcengine-ark model list with DeepSeek V4 (#4905) Integrated into release/v3.8.36 * fix(translator): provider thinking compatibility (DeepSeek/Gemini) (#4946) Integrated into release/v3.8.36 * feat(combo): task-aware routing strategy (#4945) Integrated into release/v3.8.36 * refactor(sse): extrai a família MiniMax de services/usage.ts (#4952) Integrated into release/v3.8.36 * refactor(sse): extrai a família GLM de services/usage.ts (#4953) Integrated into release/v3.8.36 * refactor(sse): extrai a família Antigravity de services/usage.ts (#4956) Integrated into release/v3.8.36 * fix(dashboard): show custom provider given-name instead of internal id across dashboard pages (#4603) (#4960) Integrated into release/v3.8.36 (fixes #4603) * fix(api): evict stale in-memory rate-limit windows to stop slow heap leak (#4041) (#4957) Integrated into release/v3.8.36 (fixes #4041) * fix(api): parse /v1/responses body once instead of 3-4x on the hot path (#4041) (#4958) Integrated into release/v3.8.36 (fixes #4041) * fix(translator): preserve legitimate empty-string tool arguments in openai-to-claude streaming (#4951) (#4959) Integrated into release/v3.8.36 (fixes #4951) * chore(quality): reconcile file-size baseline for #4960 provider-display-name (#4961) Integrated into release/v3.8.36 * fix(dashboard): restore home provider-topology card hidden by #4596 default (#4963) Integrated into release/v3.8.36 — restores home topology card (#4596 regression) * fix(build): drop @omniroute/open-sse from optimizePackageImports (build OOM) (#4968) Integrated into release/v3.8.36 — fixes build OOM (optimizePackageImports open-sse) * fix(quota): migração 107 ativa estratégia quota-share nos combos qtSd/ existentes [Fase 3 #9] (#4962) Integrated into release/v3.8.36 * feat(quota): respeita max_concurrent por conexão no roteamento (#4965) Integrated into release/v3.8.36 * feat(quota): combo quota-share espera cooldown curto e re-despacha (Variante A) (#4967) Integrated into release/v3.8.36 * fix(quality): resolve base-reds da release — db-rules allowlist + task-aware router precedence (#4973) Dois base-reds pré-existentes que reprovavam o CI da release v3.8.36 (Fast Quality Gates + Unit Tests fast-path), independentes de qualquer feature em voo: 1. check:db-rules / allowlist: os módulos db-internal caseMapping (#4947) e schemaColumns (#4948), extraídos de db/core.ts e importados só por ele, não estavam em INTENTIONALLY_INTERNAL. Registrados na allowlist (correção canônica — são internos legítimos, não re-exportados pelo localDb). 2. auto-strategy honra LKGP/cost (combo-routing-engine.test.ts, 2 testes): o task-aware reordering (#4945, reorderByTaskWeight) roda para strategy "auto" e era aplicado DEPOIS do router explícito (selectWithStrategy: lkgp/cost), sobrescrevendo o orderedTargets[0] que o operador escolheu. Instrumentação provou: post-filter [0]=claude (LKGP) → post-task [0]=gpt-oss. Correção: quando o auto usa router explícito, preserva o [0] dele e deixa o task-aware refinar só a cauda de fallback. gpt-oss-120b PERMANECE tool-capable (não é mudança de catálogo; o model-capabilities-registry test segue verde). Validado: 121 testes (combo-routing-engine + combo-task-aware + registry) verdes, red-check confirmado, db-rules/file-size/typecheck/lint/prettier OK. Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * feat(quota): serializa concorrência por conexão no caminho quota-share (FASE 2.1) (#4970) O gating de quota-share em selectQuotaShareTarget é fail-open: uma conexão at-cap só é despriorizada, nunca bloqueada. Com 1 conexão por conta de assinatura (caso comum), chamadas concorrentes ainda floodam a conta (→ 429 + cooldown) — provado live na .15: 3 chamadas concorrentes com max_concurrent=1 despacharam todas em 94ms. Adiciona um semáforo POR CONEXÃO em torno do dispatch quota-share: chamadas excedentes esperam na fila em vez de floodar (key qsconn:<connectionId>, cap = max_concurrent da conexão). Fail-open em fila saturada/timeout para nunca piorar disponibilidade. Gated por strategy===quota-share + kill-switch resilienceSettings.quotaShareConcurrencyLimit (default on; UI no ResilienceTab). Lógica extraível isolada no leaf puro combo/quotaShareConcurrency.ts (unit-testado: estabilidade da key, no-op sem cap, serialização real, fail-open). Settings + schema + UI espelham comboCooldownWait. Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * docs(resilience): document Quota-Share Concurrency Control (max_concurrent + serialization + cooldown-wait) (#4980) Documents the v3.8.36 quota-share concurrency layers in RESILIENCE_GUIDE.md: per-connection max_concurrent cap, the quota-share request serialization semaphore (FASE 2.1, qsconn:<connectionId>, fail-open, kill-switch), and the combo cooldown-aware retry — so operators know how to cap a subscription account's concurrency and why the routing gate alone cannot contain a single-connection flood. Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(dashboard): proxy-pool success gating, sync timestamp, opt-in Redis (#4878) (#4988) Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(sse): fail over on 400 responses carrying rate-limit text (#4976) (#4986) * fix(sse): fail over on 400 responses carrying rate-limit text (#4976) * chore(quality): rebaseline accountFallback.ts file-size for #4976 fix --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(compression): stop RTK over-truncating file-read tool results (#4559) (#4987) * fix(compression): stop RTK over-truncating file-read tool results (#4559) * chore(quality): trim #4559 comment to keep rtk/index.ts within size cap --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(sse): honor per-account proxies and fingerprint rotation in opencode executor (#4954) (#4989) * fix(sse): honor per-account proxies and fingerprint rotation in opencode executor (#4954) * chore(quality): rebaseline auth.ts file-size for #4954 (+39: synthetic no-auth providerSpecificData hydration of fingerprints/accountProxies; irreducible credential-path wiring, covered by opencode-proxy-rotation-4954.test.ts + 159 auth/noauth regression) --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(sse): soft-penalize exhausted providers in auto-combo scoring (#4540) (#4990) * fix(sse): soft-penalize exhausted providers in auto-combo scoring (#4540) * chore(quality): document STATUS_SOFT_DEPRIORITIZE_FACTOR + rebaseline combo.ts for #4540 --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(dashboard): switch to visible filter after auto-hiding failed models in test-all (#4887) (#4991) * fix(dashboard): switch to visible filter after auto-hiding failed models in OAuth provider test-all (#4887) * test(dashboard): move #4887 test into tests/unit/ui so a CI runner collects it --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(pollinations): only enable jsonMode when JSON output is requested (#3981) (#5009) Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(antigravity): default safetySettings to all-OFF for parity with native Gemini paths (#5003) (#5008) * fix(antigravity): default safetySettings to all-OFF for parity with native Gemini paths (#5003) * docs(changelog): restore #3981 pollinations entry eaten by merge --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(chatgpt-web): map advertised gpt-5.5/5.4-pro/5.2-pro slugs to prevent silent model substitution (#4665) (#5010) * fix(chatgpt-web): map advertised gpt-5.5/5.4-pro/5.2-pro slugs to prevent silent model substitution (#4665) MODEL_MAP was missing the advertised catalog ids gpt-5.5, gpt-5.5-pro, gpt-5.4-pro and gpt-5.2-pro, so MODEL_MAP[model] ?? model sent the dot-form id verbatim to the ChatGPT backend-api, which silently rejected it and served the default Plus model. Map each to its dash-form slug. gpt-4-5 is already dash-form and falls through correctly, so it is intentionally left unmapped. Extends the executor MODEL_MAP test with the four ids and adds a drift guard asserting every advertised dot-form catalog id reaches the backend in dash-form (never verbatim), guarding future catalog<->map drift. file-size: tests/unit/chatgpt-web.test.ts frozen baseline 2809->2855 (+46) for the added test cases and drift-guard test; executor source unchanged in baseline. * docs(changelog): restore #3981/#5003 entries eaten by merge --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * feat(combos): add editable per-combo description field persisted via /api/combos (#5005) (#5011) * feat(combos): add editable per-combo description field persisted via /api/combos (#5005) * docs(changelog): restore #3981/#5003/#4665 entries eaten by merge --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * Fix Ollama Cloud max reasoning effort (#4993) Integrated into release/v3.8.36 * fix(copilot): replace execSync with execFile to prevent command injection (#5024) Integrated into release/v3.8.36 * fix(plugin): auth.json dual-key fallback for auto-prefix migration (#5027) Integrated into release/v3.8.36 * feat(endpoint): per-endpoint custom system prompt injection (#5022) Integrated into release/v3.8.36 * fix(headroom): translate openai-responses input through OpenAI for compression (#5023) Integrated into release/v3.8.36 * docs(changelog): add entries for #4993, #5024, #5027 (release notes credit) * fix(api): stop /api/system/env/repair 500 on packaged install (#5006) (#5028) * fix(api): stop /api/system/env/repair 500 on packaged install — lazy createRequire in sync-env.mjs (#5006) scripts/dev/sync-env.mjs ran createRequire(import.meta.url) at module top-level. When webpack bundles it into the standalone env-repair route, import.meta.url is frozen to the build-machine path (file:///home/runner/...) and createRequire throws during module evaluation, so the whole route module fails to load and every GET returns HTTP 500 — breaking the onboarding wizard on packaged/global installs. - Move createRequire into the guarded better-sqlite3 block (only place that needs it); a bad import.meta.url now returns the safe default. - resolveRootDir() falls back to process.cwd() when fileURLToPath throws. - route.ts passes an explicit rootDir (process.cwd()) so the helper never derives the root from the frozen import.meta.url, matching the .env target used by createEnvBackup(). - Regression guard: assert sync-env.mjs has no top-level createRequire + getEnvSyncPlan(oauth) works with explicit rootDir without throwing. * docs(changelog): restore #4993/#5023/#5024/#5027 + custom-system-prompt/headroom entries eaten by release merge * chore(quality): rebaseline 3 inherited base-reds from release merge Files NOT touched by this PR — grew on release/v3.8.36 via --admin merges and inherited here through 'git merge origin/release': - open-sse/executors/base.ts 1414->1416 (#4993 Ollama Cloud max-effort) - src/lib/db/settings.ts 1149->1151 (#5023 custom system prompt) - src/app/(dashboard)/.../endpoint/EndpointPageClient.tsx 2570->2612 (custom system prompt UI) * chore(release): finalize v3.8.36 CHANGELOG + docs (2026-06-25) --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> Co-authored-by: KooshaPari <42529354+KooshaPari@users.noreply.github.com> Co-authored-by: Makcim Ivanov <makcimbx@gmail.com> Co-authored-by: Chewji <126886556+Chewji9875@users.noreply.github.com> Co-authored-by: Anton <39598727+NomenAK@users.noreply.github.com> Co-authored-by: Demiurge The Single <megamen932@gmail.com> Co-authored-by: Randi <55005611+rdself@users.noreply.github.com> Co-authored-by: Éder Costa <eder.almeida.costa@gmail.com> Co-authored-by: Jefferson Felizardo <jeffer1312@gmail.com> Co-authored-by: Arthur Bodera <abodera@gmail.com> Co-authored-by: Hamsa_M <116961508+hamsa0x7@users.noreply.github.com> Co-authored-by: Hernan Javier Ardila Sanchez <hjasgr@gmail.com>
604 lines
23 KiB
TypeScript
604 lines
23 KiB
TypeScript
// @ts-nocheck
|
|
import "./setupPolyfill.ts";
|
|
import { AsyncLocalStorage } from "node:async_hooks";
|
|
import { fetch as undiciFetch } from "undici";
|
|
import {
|
|
buildVercelRelayHeaders,
|
|
createProxyDispatcher,
|
|
getDefaultDispatcher,
|
|
getRetryDispatcher,
|
|
isRelayType,
|
|
normalizeProxyUrl,
|
|
proxyConfigToUrl,
|
|
proxyUrlForLogs,
|
|
} from "./proxyDispatcher.ts";
|
|
import tlsClient from "./tlsClient.ts";
|
|
import { isProxyReachable } from "@/lib/proxyHealth";
|
|
import {
|
|
isControlPlaneProxyDirectFallbackEnabled,
|
|
isFeatureFlagEnabled,
|
|
} from "@/shared/utils/featureFlags";
|
|
import { findWorkingProxy } from "./proxyFallback.ts";
|
|
|
|
function isTlsFingerprintEnabled() {
|
|
return process.env.ENABLE_TLS_FINGERPRINT === "true";
|
|
}
|
|
|
|
/** Per-request tracking of whether TLS fingerprint was used */
|
|
type TlsFingerprintStore = { used: boolean };
|
|
const tlsFingerprintContext = new AsyncLocalStorage<TlsFingerprintStore>();
|
|
|
|
type FetchWithDispatcherOptions = RequestInit & { dispatcher?: unknown };
|
|
type FetchWithDispatcher = (
|
|
input: RequestInfo | URL,
|
|
init?: FetchWithDispatcherOptions
|
|
) => Promise<Response>;
|
|
|
|
/**
|
|
* Flatten a fetch error's `cause` chain (and any Happy-Eyeballs `AggregateError`
|
|
* sub-errors) into a single diagnostic line: code/syscall/errno/address:port + a
|
|
* truncated message. undici/native both reject with a bare `TypeError: fetch failed`
|
|
* whose real reason hides in `.cause`; surfacing it is what makes dispatcher-failure
|
|
* bursts (#4252) diagnosable. Never includes a stack trace (Rule #12). Pure + testable.
|
|
*/
|
|
export function describeFetchCause(err: unknown): string {
|
|
const parts: string[] = [];
|
|
const seen = new Set<unknown>();
|
|
let cur: unknown = err;
|
|
for (let depth = 0; cur && depth < 5 && !seen.has(cur); depth++) {
|
|
seen.add(cur);
|
|
const e = cur as Record<string, unknown>;
|
|
const seg = [
|
|
typeof e.name === "string" && e.name !== "Error" ? e.name : null,
|
|
typeof e.message === "string" ? e.message.slice(0, 160) : null,
|
|
e.code != null ? `code=${String(e.code)}` : null,
|
|
e.syscall != null ? `syscall=${String(e.syscall)}` : null,
|
|
e.errno != null ? `errno=${String(e.errno)}` : null,
|
|
e.address != null
|
|
? `address=${String(e.address)}${e.port != null ? `:${String(e.port)}` : ""}`
|
|
: null,
|
|
]
|
|
.filter(Boolean)
|
|
.join(" ");
|
|
if (seg) parts.push(seg);
|
|
if (Array.isArray(e.errors)) {
|
|
for (const sub of (e.errors as unknown[]).slice(0, 4)) {
|
|
const s = (sub ?? {}) as Record<string, unknown>;
|
|
const subSeg = [
|
|
s.code != null ? `code=${String(s.code)}` : null,
|
|
s.syscall != null ? `syscall=${String(s.syscall)}` : null,
|
|
s.address != null
|
|
? `address=${String(s.address)}${s.port != null ? `:${String(s.port)}` : ""}`
|
|
: null,
|
|
]
|
|
.filter(Boolean)
|
|
.join(" ");
|
|
if (subSeg) parts.push(`↳ ${subSeg}`);
|
|
else if (typeof s.message === "string") parts.push(`↳ ${s.message.slice(0, 80)}`);
|
|
}
|
|
}
|
|
cur = e.cause;
|
|
}
|
|
return parts.join(" | ") || String(err);
|
|
}
|
|
|
|
/** Injectable dependencies for testability (Approach B DI). */
|
|
export type ProxyFetchDeps = {
|
|
undiciFetch?: FetchWithDispatcher;
|
|
nativeFetch?: (input: RequestInfo | URL, init?: RequestInit) => Promise<Response>;
|
|
};
|
|
|
|
type PatchState = {
|
|
originalFetch: typeof globalThis.fetch;
|
|
proxyContext: AsyncLocalStorage<unknown>;
|
|
isPatched: boolean;
|
|
};
|
|
|
|
const isCloud = typeof caches !== "undefined" && typeof caches === "object";
|
|
const PATCH_STATE_KEY = Symbol.for("omniroute.proxyFetch.state");
|
|
|
|
function getPatchState(): PatchState {
|
|
const scopedGlobal = globalThis as typeof globalThis & {
|
|
[PATCH_STATE_KEY]?: PatchState;
|
|
};
|
|
|
|
if (!scopedGlobal[PATCH_STATE_KEY]) {
|
|
scopedGlobal[PATCH_STATE_KEY] = {
|
|
originalFetch: globalThis.fetch,
|
|
proxyContext: new AsyncLocalStorage(),
|
|
isPatched: false,
|
|
};
|
|
}
|
|
return scopedGlobal[PATCH_STATE_KEY];
|
|
}
|
|
|
|
const patchState = getPatchState();
|
|
const originalFetch = patchState.originalFetch;
|
|
const originalFetchWithDispatcher = originalFetch as FetchWithDispatcher;
|
|
const proxyContext = patchState.proxyContext;
|
|
|
|
function noProxyMatch(targetUrl) {
|
|
const noProxy = process.env.NO_PROXY || process.env.no_proxy;
|
|
if (!noProxy) return false;
|
|
|
|
let target;
|
|
try {
|
|
target = new URL(targetUrl);
|
|
} catch {
|
|
return false;
|
|
}
|
|
|
|
const hostname = target.hostname.toLowerCase();
|
|
const port = target.port || (target.protocol === "https:" ? "443" : "80");
|
|
const patterns = noProxy
|
|
.split(",")
|
|
.map((p) => p.trim().toLowerCase())
|
|
.filter(Boolean);
|
|
|
|
return patterns.some((pattern) => {
|
|
if (pattern === "*") return true;
|
|
|
|
const [patternHost, patternPort] = pattern.split(":");
|
|
if (patternPort && patternPort !== port) return false;
|
|
|
|
if (!patternHost) return false;
|
|
|
|
// Support wildcard matching (e.g. 192.168.* or *.local).
|
|
// Uses a linear glob scan instead of dynamic RegExp to avoid ReDoS.
|
|
if (patternHost.includes("*")) {
|
|
const parts = patternHost.split("*");
|
|
let pos = 0;
|
|
let ok = hostname.startsWith(parts[0]);
|
|
if (ok) {
|
|
pos = parts[0].length;
|
|
for (let i = 1; i < parts.length && ok; i++) {
|
|
const seg = parts[i];
|
|
if (i === parts.length - 1) {
|
|
ok = seg === "" || (hostname.endsWith(seg) && hostname.length - seg.length >= pos);
|
|
} else {
|
|
const idx = seg ? hostname.indexOf(seg, pos) : pos;
|
|
if (idx === -1) {
|
|
ok = false;
|
|
} else {
|
|
pos = idx + seg.length;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
if (ok) return true;
|
|
}
|
|
|
|
if (patternHost.startsWith(".")) {
|
|
return hostname.endsWith(patternHost) || hostname === patternHost.slice(1);
|
|
}
|
|
return hostname === patternHost || hostname.endsWith(`.${patternHost}`);
|
|
});
|
|
}
|
|
|
|
function isLocalAddress(hostname: string): boolean {
|
|
const host = hostname
|
|
.replace(/^\[/, "")
|
|
.replace(/\]$/, "")
|
|
.replace(/^::ffff:/i, "");
|
|
if (host === "localhost" || host === "0.0.0.0" || host === "127.0.0.1" || host === "::1") {
|
|
return true;
|
|
}
|
|
if (host.endsWith(".local") || host.endsWith(".lan") || host.endsWith(".internal")) return true;
|
|
// RFC1918 + loopback + link-local (169.254, incl. cloud metadata 169.254.169.254)
|
|
// + CGNAT (100.64/10). 127/8 covers all loopback, not just 127.0.0.1.
|
|
if (host.startsWith("192.168.")) return true;
|
|
if (host.startsWith("10.")) return true;
|
|
if (host.startsWith("127.")) return true;
|
|
if (host.startsWith("169.254.")) return true;
|
|
if (/^172\.(1[6-9]|2\d|3[0-1])\./.test(host)) return true;
|
|
if (/^100\.(6[4-9]|[7-9]\d|1[01]\d|12[0-7])\./.test(host)) return true;
|
|
// IPv6 ULA (fc00::/7 → fc/fd prefix) and link-local (fe80::/10)
|
|
if (/^f[cd][0-9a-f]*:/i.test(host) || host.startsWith("fe80:")) return true;
|
|
return false;
|
|
}
|
|
|
|
function resolveEnvProxyUrl(targetUrl) {
|
|
if (noProxyMatch(targetUrl)) return null;
|
|
|
|
let protocol;
|
|
try {
|
|
protocol = new URL(targetUrl).protocol;
|
|
} catch {
|
|
return null;
|
|
}
|
|
|
|
const proxyUrl =
|
|
protocol === "https:"
|
|
? process.env.HTTPS_PROXY ||
|
|
process.env.https_proxy ||
|
|
process.env.ALL_PROXY ||
|
|
process.env.all_proxy
|
|
: process.env.HTTP_PROXY ||
|
|
process.env.http_proxy ||
|
|
process.env.ALL_PROXY ||
|
|
process.env.all_proxy;
|
|
|
|
if (!proxyUrl) return null;
|
|
return normalizeProxyUrl(proxyUrl, "environment proxy");
|
|
}
|
|
|
|
export function resolveProxyForRequest(targetUrl) {
|
|
let target;
|
|
try {
|
|
target = new URL(targetUrl);
|
|
} catch {
|
|
target = null;
|
|
}
|
|
|
|
// Always bypass proxy for local/LAN addresses
|
|
if (target && isLocalAddress(target.hostname.toLowerCase())) {
|
|
return { source: "direct", proxyUrl: null };
|
|
}
|
|
|
|
const contextProxy = proxyContext.getStore();
|
|
if (contextProxy) {
|
|
return { source: "context", proxyUrl: proxyConfigToUrl(contextProxy) };
|
|
}
|
|
|
|
const envProxyUrl = resolveEnvProxyUrl(targetUrl);
|
|
if (envProxyUrl) {
|
|
return { source: "env", proxyUrl: envProxyUrl };
|
|
}
|
|
|
|
return { source: "direct", proxyUrl: null };
|
|
}
|
|
|
|
function getTargetUrl(input) {
|
|
if (typeof input === "string") return input;
|
|
if (input && typeof input.url === "string") return input.url;
|
|
return String(input);
|
|
}
|
|
|
|
export async function runWithProxyContext(
|
|
proxyConfig,
|
|
fn,
|
|
opts?: { directFallbackOnUnreachable?: boolean }
|
|
) {
|
|
if (typeof fn !== "function") {
|
|
throw new TypeError("runWithProxyContext requires a callback function");
|
|
}
|
|
|
|
// Inherit existing context if no specific proxyConfig is provided
|
|
const currentContext = proxyContext.getStore();
|
|
const effectiveProxyConfig = proxyConfig || currentContext || null;
|
|
|
|
const resolvedProxyUrl = effectiveProxyConfig ? proxyConfigToUrl(effectiveProxyConfig) : null;
|
|
|
|
// The caller must opt in, and the runtime feature flag must also be enabled.
|
|
// This fallback changes egress IP, so upgrades must not silently turn it on.
|
|
const directFallbackOnUnreachable =
|
|
opts?.directFallbackOnUnreachable === true && isControlPlaneProxyDirectFallbackEnabled();
|
|
// Run fn with the proxy context cleared so the request egresses directly.
|
|
const runDirect = () => proxyContext.run(null, fn);
|
|
|
|
// T14: Proxy Fast-Fail
|
|
// Perform a short TCP reachability check before issuing upstream requests.
|
|
// Skip for edge-relay types (vercel / deno): proxyConfigToUrl returns
|
|
// "https://<host>" which is the relay endpoint itself, not an HTTP proxy —
|
|
// the actual routing is handled via x-relay-* headers below.
|
|
const isVercelRelay = isRelayType((effectiveProxyConfig as { type?: string })?.type);
|
|
if (resolvedProxyUrl && !isVercelRelay) {
|
|
const reachable = await isProxyReachable(resolvedProxyUrl);
|
|
if (!reachable) {
|
|
const proxyLabel = proxyUrlForLogs(resolvedProxyUrl);
|
|
if (directFallbackOnUnreachable) {
|
|
console.warn(
|
|
`[ProxyFetch] Proxy unreachable (${proxyLabel}); using a direct connection for this request.`
|
|
);
|
|
return runDirect();
|
|
}
|
|
const err = new Error(`[Proxy Fast-Fail] Proxy unreachable: ${proxyLabel}`) as Error & {
|
|
code?: string;
|
|
statusCode?: number;
|
|
};
|
|
err.code = "PROXY_UNREACHABLE";
|
|
err.statusCode = 503;
|
|
throw err;
|
|
}
|
|
}
|
|
|
|
// Fail-closed family check: when the proxy URL carries a ?family=ipv6|ipv4 marker
|
|
// (set for HOSTNAME proxies by proxyConfigToUrl), verify the hostname actually has a
|
|
// record in that family before egressing. Refuse early rather than silently fall back
|
|
// to the other family. No-op for IP literals (their family is intrinsic).
|
|
if (resolvedProxyUrl && !isVercelRelay) {
|
|
try {
|
|
const u = new URL(resolvedProxyUrl);
|
|
const fam = u.searchParams.get("family");
|
|
if (fam === "ipv6" || fam === "ipv4") {
|
|
const { assertHostnameSupportsFamily } = await import("./proxyFamilyResolve.ts");
|
|
await assertHostnameSupportsFamily(u.hostname, fam === "ipv6" ? 6 : 4);
|
|
}
|
|
} catch (familyErr) {
|
|
if (directFallbackOnUnreachable) {
|
|
console.warn(
|
|
`[ProxyFetch] Proxy family pre-check failed (${proxyUrlForLogs(resolvedProxyUrl)}); using a direct connection for this request.`
|
|
);
|
|
return runDirect();
|
|
}
|
|
const e = familyErr as Error & { code?: string; statusCode?: number };
|
|
e.code = e.code || "PROXY_FAMILY_UNAVAILABLE";
|
|
e.statusCode = e.statusCode || 503;
|
|
throw e;
|
|
}
|
|
}
|
|
|
|
return proxyContext.run(effectiveProxyConfig, async () => {
|
|
if (resolvedProxyUrl && effectiveProxyConfig !== currentContext) {
|
|
console.log(
|
|
`[ProxyFetch] Applied request proxy context: ${proxyUrlForLogs(resolvedProxyUrl)}`
|
|
);
|
|
}
|
|
return fn();
|
|
});
|
|
}
|
|
|
|
/**
|
|
* Like {@link runWithProxyContext}, but if the assigned proxy is unreachable or fails
|
|
* its pre-checks the request can degrade to a DIRECT connection instead of throwing.
|
|
*
|
|
* For control-plane flows — OAuth code/token exchange, connection tests, token refresh —
|
|
* where a dead pinned proxy must not block reaching the upstream (it otherwise surfaces
|
|
* as a generic "Internal server error"). Data-plane chat keeps strict pinning via
|
|
* runWithProxyContext so per-account egress-IP isolation is preserved.
|
|
*
|
|
* This remains disabled unless OMNIROUTE_CONTROL_PLANE_PROXY_DIRECT_FALLBACK is enabled
|
|
* from Feature Flags or the environment.
|
|
*/
|
|
export async function runWithProxyContextOrDirect(proxyConfig, fn) {
|
|
return runWithProxyContext(proxyConfig, fn, { directFallbackOnUnreachable: true });
|
|
}
|
|
|
|
async function patchedFetch(
|
|
input: RequestInfo | URL,
|
|
options: FetchWithDispatcherOptions = {},
|
|
deps: ProxyFetchDeps = {}
|
|
) {
|
|
if (options?.dispatcher) {
|
|
// When a dispatcher is present, we MUST use the undici library fetch
|
|
// to ensure version compatibility. Node 22 built-in fetch (undici v6)
|
|
// is incompatible with undici v8 dispatchers (missing onRequestStart, etc.)
|
|
const _undiciDispatcher =
|
|
deps.undiciFetch ?? (undiciFetch as unknown as (...args: unknown[]) => Promise<Response>);
|
|
return _undiciDispatcher(input, options);
|
|
}
|
|
|
|
const targetUrl = getTargetUrl(input);
|
|
let resolved;
|
|
try {
|
|
resolved = resolveProxyForRequest(targetUrl);
|
|
} catch (error) {
|
|
const message = error instanceof Error ? error.message : String(error);
|
|
console.error(`[ProxyFetch] Proxy configuration error: ${message}`);
|
|
throw error;
|
|
}
|
|
const { source, proxyUrl } = resolved;
|
|
|
|
if (!proxyUrl) {
|
|
// TLS fingerprint spoofing for direct connections (no proxy configured)
|
|
if (isTlsFingerprintEnabled() && tlsClient.available) {
|
|
try {
|
|
const store = tlsFingerprintContext.getStore();
|
|
if (store) store.used = true;
|
|
return await tlsClient.fetch(targetUrl, {
|
|
...options,
|
|
headers: options.headers,
|
|
signal: options.signal ?? undefined,
|
|
});
|
|
} catch (error) {
|
|
const message = error instanceof Error ? error.message : String(error);
|
|
console.warn(
|
|
`[ProxyFetch] TLS fingerprint failed, falling back to native fetch: ${message}`
|
|
);
|
|
const store = tlsFingerprintContext.getStore();
|
|
if (store) store.used = false;
|
|
}
|
|
}
|
|
// Direct connection (no proxy) — use undici with custom dispatcher for timeout control.
|
|
// Falls back to original native fetch if dispatcher initialization fails (#1054).
|
|
// Retries once on transient dispatcher errors before falling back (fix: proxyfetch-undici-retry).
|
|
//
|
|
// ReadableStream/Blob body guard: if the body is non-replayable, skip the retry because
|
|
// the first attempt drains the stream; a second attempt would silently send an empty body.
|
|
// ReadableStream check: cast through unknown to avoid explicit-any budget (T11).
|
|
const _bodyUnknown = options.body as unknown;
|
|
const bodyIsStream =
|
|
_bodyUnknown !== null &&
|
|
_bodyUnknown !== undefined &&
|
|
typeof _bodyUnknown === "object" &&
|
|
(typeof (_bodyUnknown as Record<string, unknown>).getReader === "function" || // ReadableStream
|
|
typeof (_bodyUnknown as Record<string, unknown>).stream === "function"); // Blob
|
|
const maxAttempts = bodyIsStream ? 1 : 2;
|
|
const _undiciDirect =
|
|
deps.undiciFetch ?? (undiciFetch as unknown as (...args: unknown[]) => Promise<Response>);
|
|
const _nativeFallback =
|
|
(deps.nativeFetch as FetchWithDispatcher | undefined) ?? originalFetchWithDispatcher;
|
|
let lastDispatcherError: unknown = null;
|
|
for (let attempt = 0; attempt < maxAttempts; attempt++) {
|
|
try {
|
|
return await _undiciDirect(input, {
|
|
...options,
|
|
// #4252: first attempt uses the pooled keep-alive dispatcher; a retry
|
|
// (after a transient socket error) uses the no-keep-alive dispatcher so
|
|
// it opens a FRESH socket instead of grabbing another stale pooled one
|
|
// — the burst pattern was the retry re-hitting a dead pooled socket and
|
|
// then falling through to native fetch (which also pools) → 502.
|
|
dispatcher: attempt === 0 ? getDefaultDispatcher() : getRetryDispatcher(),
|
|
});
|
|
} catch (dispatcherError) {
|
|
const msg =
|
|
dispatcherError instanceof Error ? dispatcherError.message : String(dispatcherError);
|
|
// CAUTION: Do NOT fallback to native fetch if the error is a version mismatch (invalid onRequestStart)
|
|
// because the native fetch will definitely fail with the undici v8 dispatcher.
|
|
if (msg.includes("onRequestStart")) {
|
|
console.error(
|
|
`[ProxyFetch] Fatal version mismatch: Dispatcher (v8) vs Fetch (v6/native). Hardware upgrade or SOCKS5 config isolation required. Error: ${msg}`
|
|
);
|
|
throw dispatcherError;
|
|
}
|
|
// Only retry/fallback for connection/dispatcher errors, not HTTP errors.
|
|
// Prefer the .code property when available (more stable across undici
|
|
// versions than message-string matching); fall back to substring match
|
|
// for errors that lack a structured code.
|
|
const errCode = (dispatcherError as { code?: unknown })?.code;
|
|
if (
|
|
msg.includes("fetch failed") ||
|
|
errCode === "ECONNREFUSED" ||
|
|
msg.includes("ECONNREFUSED") ||
|
|
(typeof errCode === "string" && errCode.startsWith("UND_ERR")) ||
|
|
msg.includes("UND_ERR")
|
|
) {
|
|
if (attempt === 0 && maxAttempts > 1) {
|
|
// First failure — retry once with a short jittered delay before giving up.
|
|
lastDispatcherError = dispatcherError;
|
|
await new Promise((r) => setTimeout(r, 25 + Math.random() * 50));
|
|
continue;
|
|
}
|
|
// All attempts exhausted — try proxy fallback before native fetch
|
|
if (source === "direct" && isFeatureFlagEnabled("PROXY_AUTO_SELECT_ENABLED")) {
|
|
let targetHostname = "";
|
|
try {
|
|
targetHostname = new URL(targetUrl).hostname;
|
|
} catch {
|
|
// ignore
|
|
}
|
|
if (targetHostname) {
|
|
const fallbackProxyUrl = await findWorkingProxy(targetHostname, targetUrl);
|
|
if (fallbackProxyUrl) {
|
|
try {
|
|
const dispatcher = createProxyDispatcher(fallbackProxyUrl);
|
|
return await _undiciDirect(input, { ...options, dispatcher });
|
|
} catch {
|
|
// Proxy also failed — fall through to native fetch
|
|
}
|
|
}
|
|
}
|
|
}
|
|
// Preserve original phrase intact for monitoring: "Undici dispatcher failed, falling back to native fetch"
|
|
// #4252: append the flattened err.cause (code/syscall/errno/address) — the bare
|
|
// "fetch failed" message hides what actually broke, making bursts undiagnosable.
|
|
console.warn(
|
|
`[ProxyFetch] Undici dispatcher failed, falling back to native fetch (after retry): ${describeFetchCause(dispatcherError)}`
|
|
);
|
|
try {
|
|
return await _nativeFallback(input, options);
|
|
} catch (nativeError) {
|
|
// #4252: both the undici dispatcher AND native fetch failed. Surface BOTH
|
|
// causes (server log) and tag the propagated error so the combo executor sees
|
|
// a diagnosable failure IMMEDIATELY instead of a bare "fetch failed" — the
|
|
// latter left jobs sitting until the 30s semaphore queue timeout, which then
|
|
// tripped the circuit breaker.
|
|
const detail = `dispatcher=[${describeFetchCause(dispatcherError)}] native=[${describeFetchCause(nativeError)}]`;
|
|
console.warn(`[ProxyFetch] native fetch fallback ALSO failed: ${detail}`);
|
|
if (nativeError instanceof Error) {
|
|
(nativeError as Error & { proxyFetchDetail?: string }).proxyFetchDetail = detail;
|
|
}
|
|
throw nativeError;
|
|
}
|
|
}
|
|
throw dispatcherError;
|
|
}
|
|
}
|
|
// Should not be reached, but satisfy TypeScript control-flow.
|
|
throw lastDispatcherError;
|
|
}
|
|
|
|
// Edge relay (vercel / deno): instead of routing through an HTTP proxy
|
|
// dispatcher, we send x-relay-* headers to the edge function which forwards
|
|
// the request upstream. Both backends share the same envelope shape.
|
|
const contextProxy = proxyContext.getStore();
|
|
if (
|
|
contextProxy &&
|
|
typeof contextProxy === "object" &&
|
|
isRelayType((contextProxy as { type?: string }).type)
|
|
) {
|
|
const vc = contextProxy as { type?: string; host?: string; relayAuth?: string };
|
|
if (!vc.relayAuth) {
|
|
// Generic message without internal labels — this throw can bubble up to
|
|
// catch blocks that put error.message in response bodies (combo per-model
|
|
// timeout, executor catch-all). Don't leak "[ProxyFetch]" diagnostics.
|
|
const label = vc.type === "vercel" ? "Vercel relay" : `${vc.type || "Edge"} relay`;
|
|
throw new Error(`${label} configuration error: missing relayAuth`);
|
|
}
|
|
const targetUrl = getTargetUrl(input);
|
|
const relayHeaders = buildVercelRelayHeaders(targetUrl, vc.relayAuth);
|
|
const mergedHeaders = new Headers(options?.headers);
|
|
for (const [k, v] of Object.entries(relayHeaders)) mergedHeaders.set(k, v);
|
|
// Pass host through proxyUrlForLogs so the same redaction policy applies
|
|
// to relay routing logs (the rest of this module already follows that rule).
|
|
const hostForLogs = proxyUrlForLogs(vc.host ? `https://${vc.host}` : "");
|
|
if (process.env.OMNIROUTE_PROXY_FETCH_DEBUG === "true") {
|
|
console.debug(`[ProxyFetch] Routing via ${vc.type || "edge"} relay: ${hostForLogs}`);
|
|
}
|
|
return await originalFetch(`https://${vc.host}`, {
|
|
...options,
|
|
headers: mergedHeaders,
|
|
duplex: "half",
|
|
});
|
|
}
|
|
|
|
try {
|
|
const dispatcher = createProxyDispatcher(proxyUrl);
|
|
const _undiciProxy =
|
|
deps.undiciFetch ?? (undiciFetch as unknown as (...args: unknown[]) => Promise<Response>);
|
|
return await _undiciProxy(input, {
|
|
...options,
|
|
dispatcher,
|
|
});
|
|
} catch (error) {
|
|
const message = error instanceof Error ? error.message : String(error);
|
|
console.error(`[ProxyFetch] Proxy request failed (${source}, fail-closed): ${message}`);
|
|
throw error;
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Named export for proxyFetch — identical to the patched globalThis.fetch but
|
|
* accepts an optional ProxyFetchDeps for unit test dependency injection.
|
|
* Production code should use globalThis.fetch (or the default export) instead.
|
|
*/
|
|
export async function proxyFetch(
|
|
input: RequestInfo | URL,
|
|
options: RequestInit = {},
|
|
deps: ProxyFetchDeps = {}
|
|
): Promise<Response> {
|
|
return patchedFetch(input, options as FetchWithDispatcherOptions, deps);
|
|
}
|
|
|
|
if (!isCloud && !patchState.isPatched) {
|
|
globalThis.fetch = patchedFetch;
|
|
patchState.isPatched = true;
|
|
}
|
|
|
|
/**
|
|
* Run a function with TLS fingerprint tracking context.
|
|
* After fn completes, returns { result, tlsFingerprintUsed }.
|
|
*/
|
|
export async function runWithTlsTracking(fn) {
|
|
const store = { used: false };
|
|
const result = await tlsFingerprintContext.run(store, fn);
|
|
return { result, tlsFingerprintUsed: store.used };
|
|
}
|
|
|
|
/** Check if TLS fingerprint is enabled and available */
|
|
export function isTlsFingerprintActive() {
|
|
return isTlsFingerprintEnabled() && tlsClient.available;
|
|
}
|
|
|
|
/**
|
|
* Get the original unpatched global fetch function (Node.js native fetch
|
|
* before the proxy/TLS fingerprint patch was applied).
|
|
* Use this to bypass the patched fetch for specific requests when the
|
|
* proxy dispatcher has compatibility issues with a particular endpoint.
|
|
*/
|
|
export function getOriginalFetch(): typeof globalThis.fetch {
|
|
return originalFetch;
|
|
}
|
|
|
|
export default isCloud ? originalFetch : patchedFetch;
|