mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-01 21:02:12 +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>
280 lines
15 KiB
Markdown
280 lines
15 KiB
Markdown
---
|
||
title: "Stealth Guide"
|
||
version: 3.8.2
|
||
lastUpdated: 2026-05-13
|
||
---
|
||
|
||
# Stealth Guide
|
||
|
||
> **Source of truth:** `open-sse/utils/tlsClient.ts`, `open-sse/services/{chatgptTlsClient,claudeCodeCCH,claudeCodeFingerprint,claudeCodeObfuscation,claudeCodeCompatible,antigravityObfuscation}.ts`, `open-sse/config/cliFingerprints.ts`, `src/mitm/`
|
||
> **Last updated:** 2026-05-13 — v3.8.0
|
||
> **Audience:** Engineers maintaining provider-specific stealth integrations.
|
||
|
||
OmniRoute integrates with providers whose edges actively fingerprint non-official clients (TLS JA3/JA4, header ordering, JSON body shape, integrity tokens). This page documents the stealth surfaces OmniRoute exposes and where they are implemented.
|
||
|
||
## Legal and Ethical Notice
|
||
|
||
Stealth features exist so OmniRoute can act as a compatibility layer between user-owned official accounts (Claude Code CLI, ChatGPT Desktop/Web, Antigravity, Cursor, etc.) and OmniRoute's unified API. They are **not** for evading fraud detection, sharing credentials, or violating provider Terms of Service. The maintainers expect operators to comply with the upstream ToS they signed when creating accounts.
|
||
|
||
---
|
||
|
||
## TLS Fingerprinting Layer
|
||
|
||
### `open-sse/utils/tlsClient.ts` — wreq-js (Chrome 124)
|
||
|
||
Lazy-loaded `wreq-js` session that impersonates **Chrome 124 on macOS**. Used as a generic JA3/JA4 wrapper for upstreams behind Cloudflare. Falls back to native fetch when `wreq-js` is not installed (`available = false`).
|
||
|
||
- Singleton session: `browser: "chrome_124", os: "macos"`
|
||
- Proxy resolution (priority): `HTTPS_PROXY` → `HTTP_PROXY` → `ALL_PROXY` (also lower-case)
|
||
- Timeout: `TLS_CLIENT_TIMEOUT_MS` (inherits from `FETCH_TIMEOUT_MS`, default 600000)
|
||
- `wreq-js` Response is fetch-compatible (`headers`, `text()`, `json()`, `clone()`, `body`).
|
||
|
||
### `open-sse/services/chatgptTlsClient.ts` — tls-client-node (Firefox 148)
|
||
|
||
Dedicated TLS impersonator for `chatgpt.com`. ChatGPT's Cloudflare config pins `cf_clearance` to JA3/JA4 + HTTP/2 SETTINGS frame ordering — undici's handshake gets `cf-mitigated: challenge` even with valid cookies.
|
||
|
||
- Profile: `firefox_148` (must match the Firefox 148 `User-Agent` sent)
|
||
- Mode: `runtimeMode: "native"` (koffi-loaded shared library; avoids managed sidecar HTTP)
|
||
- `withRandomTLSExtensionOrder: true`
|
||
- `tlsFetchChatGpt(url, options)` supports streaming (writes body to temp file, tailed as `ReadableStream`)
|
||
- Hang detection: `raceWithTimeout` + `TlsClientHangError` triggers `resetClientCache()` so the next call respawns the binding
|
||
- Proxy resolution (priority): per-call `proxyUrl` → `OMNIROUTE_TLS_PROXY_URL` → `HTTPS_PROXY`/`HTTP_PROXY`/`ALL_PROXY` (the native binding does **not** read these envs itself; it must be threaded through)
|
||
- Errors: `TlsClientUnavailableError` (binary missing), `TlsClientHangError` (binding deadlocked)
|
||
|
||
---
|
||
|
||
## Claude Code Stealth Bundle
|
||
|
||
When `cliCompatMode` is on, OmniRoute reshapes outgoing Claude requests so they are indistinguishable from `claude-cli` traffic. Three modules collaborate:
|
||
|
||
### `claudeCodeFingerprint.ts`
|
||
|
||
Computes the 3-char `cc_version` fingerprint embedded in the billing header:
|
||
|
||
```
|
||
SHA256(SALT + msg[4] + msg[7] + msg[20] + version)[:3]
|
||
```
|
||
|
||
- `FINGERPRINT_SALT = "59cf53e54c78"` (hardcoded; matches official client)
|
||
- Inputs: chars at index 4, 7, 20 of the first user message text + version string
|
||
- Output: 3-char hex prefix
|
||
|
||
### `claudeCodeCCH.ts` (Client Content Hash)
|
||
|
||
Server-side integrity check the official Claude Code CLI computes via Bun/Zig. OmniRoute reimplements with `xxhash-wasm`:
|
||
|
||
1. Serialize body with `cch=00000;` placeholder
|
||
2. `xxhash64(bytes, seed) & 0xFFFFF`
|
||
3. Zero-padded 5-char lowercase hex
|
||
4. Replace `cch=00000;` with the computed token
|
||
|
||
Constants:
|
||
|
||
- Seed: `0x6e52736ac806831e`
|
||
- Pattern: `/\bcch=([0-9a-f]{5});/`
|
||
|
||
### `claudeCodeObfuscation.ts`
|
||
|
||
Inserts a Unicode **zero-width joiner** (`U+200D`) after the first character of "sensitive" client names so upstream filters cannot grep them. Default word list:
|
||
|
||
```
|
||
opencode, open-code, cline, roo-cline, roo_cline, cursor, windsurf,
|
||
aider, continue.dev, copilot, avante, codecompanion
|
||
```
|
||
|
||
Applied to: `system` blocks, all `messages[].content`, and `tools[].description` / `tools[].function.description`. Operator-overridable via `setSensitiveWords()`.
|
||
|
||
### `claudeCodeCompatible.ts` — `anthropic-compatible-cc-*` providers
|
||
|
||
For third-party Anthropic relays that only accept "real Claude Code" traffic:
|
||
|
||
- `CLAUDE_CODE_COMPATIBLE_USER_AGENT = "claude-cli/2.1.187 (external, sdk-cli)"`
|
||
- `CLAUDE_CODE_COMPATIBLE_STAINLESS_PACKAGE_VERSION = "0.94.0"`
|
||
- `CLAUDE_CODE_COMPATIBLE_STAINLESS_RUNTIME_VERSION = "v24.3.0"`
|
||
- `anthropic-beta = "claude-code-20250219,interleaved-thinking-2025-05-14,effort-2025-11-24"` by default
|
||
- The per-connection "Enable redact-thinking beta" toggle adds `redact-thinking-2026-02-12` when a CC Compatible upstream specifically requires redacted thinking streams
|
||
- `CONTEXT_1M_BETA_HEADER = "context-1m-2025-08-07"` (Opus/Sonnet 4.x family)
|
||
- Default path: `/v1/messages?beta=true`
|
||
|
||
Sister modules in the same bundle:
|
||
|
||
- `claudeCodeConstraints.ts` — temperature + cache-control rules
|
||
- `claudeCodeToolRemapper.ts` — tool-name remapping
|
||
- `claudeCodeExtraRemap.ts` — extra payload normalization
|
||
|
||
---
|
||
|
||
## Antigravity Stealth
|
||
|
||
### `antigravityObfuscation.ts`
|
||
|
||
Same zero-width-joiner trick as Claude Code, but with an expanded word list that also masks: `claude code`, `claude-code`, `kilo code`, `kilocode`, **`omniroute`**. Mirrors ZeroGravity's `ZEROGRAVITY_SENSITIVE_WORDS` and CLIProxyAPI's cloak system.
|
||
|
||
### `antigravityHeaderScrub.ts`
|
||
|
||
Strips Stainless SDK markers (`x-stainless-lang`, `x-stainless-package-version`, `x-stainless-os`, `x-stainless-arch`, `x-stainless-runtime`, `x-stainless-runtime-version`, `x-stainless-timeout`, `x-stainless-retry-count`, `x-stainless-helper-method`) before forwarding.
|
||
|
||
### ⚠️ Risk: `ANTIGRAVITY_CREDITS=always` (account-ban hot spot)
|
||
|
||
`ANTIGRAVITY_CREDITS=always` (consumed by `open-sse/executors/antigravity.ts`) routes **every** request through Antigravity AI Credit Overages (paid Google credits) instead of letting Google's free-tier quota gate things. This is documented as a feature, but it is **the single most common ToS-violation report we see** — multiple Google Ultra accounts have been banned with `403 / "service disabled for ToS violation" / insufficient_quota` after running for a few hours with `=always`.
|
||
|
||
The upstream enforcement is on **Google's side**, not anything OmniRoute can prevent. The env var name and the existing docs make it sound like a safe knob to flip; it isn't.
|
||
|
||
**Why this draws abuse detection more aggressively than free-tier-only usage:**
|
||
|
||
- Sustained automated spend on a single Google account flags differently than free-tier hits-quota-and-stops.
|
||
- Credit overages have no rate ceiling, so a misconfigured client can burn through several hundred USD in minutes and look like API-key resale or bot traffic.
|
||
- Multiple OmniRoute users hitting overage credits in parallel from the same external IP compounds the signal.
|
||
|
||
**Recommended posture:**
|
||
|
||
1. **Default to `ANTIGRAVITY_CREDITS=retry`** — overages are used only when free-tier returns 429, not on every request. This is the safer of the two non-zero modes.
|
||
2. **Spread load across providers via Auto-Combo** (`model: "auto"` or `kr/glm/etc`-combo) instead of saturating a single Antigravity account.
|
||
3. **Set per-connection RPM limits** in the Antigravity provider's edit page (Dashboard → Providers → Antigravity → connection → rate limit). 30–60 RPM is a defensible upper bound for sustained use.
|
||
4. **Use distinct upstream IPs** per Antigravity account when possible (residential proxies aimed at the same account from many users compounds the abuse signal).
|
||
5. **If banned**: appeal via `support.google.com` → "Restore Workspace/Account access" with the exact `quota_exceeded` / `service disabled` response body Google sent. Restoration is not guaranteed.
|
||
|
||
This warning is also surfaced inline in the dashboard near the Antigravity provider edit screen when `ANTIGRAVITY_CREDITS` is set to `always` (or will be in v3.8.0; tracked separately).
|
||
|
||
Touch points:
|
||
|
||
- `open-sse/executors/antigravity.ts` — reads `process.env.ANTIGRAVITY_CREDITS`
|
||
- `src/lib/oauth/providers/antigravity.ts` — credential plumbing
|
||
- Original incident report: Discussion [#1183](https://github.com/diegosouzapw/OmniRoute/discussions/1183)
|
||
|
||
---
|
||
|
||
## CLI Fingerprint Registry — `open-sse/config/cliFingerprints.ts`
|
||
|
||
Per-provider table that pins **exact** header ordering and JSON body field ordering captured from mitmproxy traces of the official CLIs. Currently registered: `codex`, `claude`, plus runtime-derived profiles in `providerHeaderProfiles.ts` for `antigravity`, `qwen`, `github`.
|
||
|
||
```ts
|
||
interface CliFingerprint {
|
||
headerOrder: string[]; // case-sensitive
|
||
bodyFieldOrder: string[]; // top-level JSON keys
|
||
userAgent?: string | (() => string);
|
||
extraHeaders?: Record<string, string>;
|
||
}
|
||
```
|
||
|
||
Toggle per provider via env (see below). When disabled, headers/body keys appear in whatever order Node/JSON gave them — easy to fingerprint.
|
||
|
||
---
|
||
|
||
## MITM Proxy (Antigravity, Linux/macOS/Windows)
|
||
|
||
For CLIs whose binaries cannot be redirected via `OPENAI_BASE_URL`, OmniRoute runs a local TLS-terminating proxy. Endpoints live under `src/app/api/cli-tools/antigravity-mitm/`.
|
||
|
||
| Method | Endpoint | Purpose |
|
||
| ------ | --------------------------------------- | ------------------------------------------------ |
|
||
| GET | `/api/cli-tools/antigravity-mitm` | Status — running, pid, dnsConfigured, certExists |
|
||
| POST | `/api/cli-tools/antigravity-mitm` | Start MITM (requires `apiKey` + `sudoPassword`) |
|
||
| DELETE | `/api/cli-tools/antigravity-mitm` | Stop MITM |
|
||
| GET | `/api/cli-tools/antigravity-mitm/alias` | List model aliases |
|
||
| PUT | `/api/cli-tools/antigravity-mitm/alias` | Save model aliases for a tool |
|
||
|
||
Target intercepted host: **`daily-cloudcode-pa.googleapis.com`** (Antigravity's upstream).
|
||
|
||
### Start sequence (`src/mitm/manager.ts::startMitm`)
|
||
|
||
1. Generate self-signed cert via `selfsigned` (RSA-2048, SHA-256, 1y) — `cert/generate.ts`
|
||
2. Install cert to system trust store — `cert/install.ts`
|
||
3. Add hosts entry `127.0.0.1 daily-cloudcode-pa.googleapis.com` — `dns/dnsConfig.ts`
|
||
4. Spawn `src/mitm/server.cjs` with `ROUTER_API_KEY` + `MITM_LOCAL_PORT` (default `443`)
|
||
5. Persist PID to `<DATA_DIR>/mitm/.mitm.pid`
|
||
|
||
### Linux dynamic trust-store detection — `cert/install.ts`
|
||
|
||
`getLinuxCertConfig()` walks a priority list and picks the first existing directory:
|
||
|
||
| Distro family | Directory | Update command |
|
||
| ------------------------ | ------------------------------------------- | ------------------------ |
|
||
| Debian / Ubuntu | `/usr/local/share/ca-certificates` | `update-ca-certificates` |
|
||
| Arch / CachyOS / Manjaro | `/etc/ca-certificates/trust-source/anchors` | `update-ca-trust` |
|
||
| Fedora / RHEL / CentOS | `/etc/pki/ca-trust/source/anchors` | `update-ca-trust` |
|
||
| openSUSE | `/etc/pki/trust/anchors` | `update-ca-certificates` |
|
||
|
||
Cert filename: `omniroute-mitm.crt`. Fingerprint match via `getCertFingerprint()` (SHA-1 of DER).
|
||
|
||
Additionally, `updateNssDatabases()` installs into per-user NSS DBs when `certutil` is available: `~/.pki/nssdb`, `~/snap/chromium/.../nssdb`, all Firefox profiles (including snap), under the nickname **`OmniRoute MITM Root CA`**.
|
||
|
||
### macOS / Windows
|
||
|
||
- **macOS:** `security add-trusted-cert -d -r trustRoot -k /Library/Keychains/System.keychain`
|
||
- **Windows:** elevated PowerShell → `certutil -addstore Root`
|
||
|
||
### Auth
|
||
|
||
All MITM endpoints require management auth (`requireCliToolsAuth`). The sudo password is cached in module scope (never `globalThis`) and cleared on `stopMitm()`.
|
||
|
||
---
|
||
|
||
## User-Agent Overrides — env vars (`.env.example` section 12)
|
||
|
||
| Variable | Default |
|
||
| ------------------------ | --------------------------------------------- |
|
||
| `CLAUDE_USER_AGENT` | `claude-cli/2.1.187 (external, cli)` |
|
||
| `CODEX_USER_AGENT` | `codex-cli/0.142.0 (Windows 10.0.26200; x64)` |
|
||
| `GITHUB_USER_AGENT` | `GitHubCopilotChat/0.45.1` |
|
||
| `ANTIGRAVITY_USER_AGENT` | `antigravity/2.0.1 darwin/arm64` |
|
||
| `KIRO_USER_AGENT` | `AWS-SDK-JS/3.0.0 kiro-ide/1.0.0` |
|
||
| `QODER_USER_AGENT` | `Qoder-Cli` |
|
||
| `QWEN_USER_AGENT` | `QwenCode/0.15.9 (linux; x64)` |
|
||
| `CURSOR_USER_AGENT` | `Cursor/3.3` |
|
||
| `GEMINI_CLI_USER_AGENT` | `google-api-nodejs-client/10.3.0` |
|
||
|
||
Consumed by `open-sse/executors/base.ts::buildHeaders()` via dynamic lookup. **Bump these when providers release new CLI versions** — stale UA strings start getting rejected as outdated clients.
|
||
|
||
## CLI Compatibility Mode Toggles (`.env.example` section 13)
|
||
|
||
| Variable | Effect |
|
||
| -------------------------- | ------------------------------- |
|
||
| `CLI_COMPAT_CODEX=1` | Codex fingerprint |
|
||
| `CLI_COMPAT_CLAUDE=1` | claude-cli fingerprint |
|
||
| `CLI_COMPAT_GITHUB=1` | GitHub Copilot Chat fingerprint |
|
||
| `CLI_COMPAT_ANTIGRAVITY=1` | Antigravity fingerprint |
|
||
| `CLI_COMPAT_KIRO=1` | Kiro |
|
||
| `CLI_COMPAT_CURSOR=1` | Cursor |
|
||
| `CLI_COMPAT_KIMI_CODING=1` | Kimi Coding |
|
||
| `CLI_COMPAT_KILOCODE=1` | KiloCode |
|
||
| `CLI_COMPAT_CLINE=1` | Cline |
|
||
| `CLI_COMPAT_QWEN=1` | Qwen Code |
|
||
| `CLI_COMPAT_ALL=1` | Enable all of the above |
|
||
|
||
The provider IP is **always preserved** — the toggle only reshapes the request wire image, it does not switch IP egress.
|
||
|
||
---
|
||
|
||
## Inbound Header Sanitization
|
||
|
||
OmniRoute scrubs inbound client headers before forwarding so a request that arrives from Cursor doesn't leak `User-Agent: Cursor/X.Y.Z` to a Claude upstream. See `src/shared/constants/upstreamHeaders.ts` for the denylist, kept in lockstep with the Zod schemas and unit tests.
|
||
|
||
---
|
||
|
||
## Updating Fingerprints When a Provider Rotates
|
||
|
||
1. Capture official CLI traffic with `mitmproxy` (TLS interception + dump)
|
||
2. Extract JA3/JA4 and the literal header order
|
||
3. Update the relevant `CLI_FINGERPRINTS[...]` entry
|
||
4. Bump matching `*_USER_AGENT` default in `.env.example`
|
||
5. If TLS handshake itself changed: update `chatgptTlsClient.ts::CHATGPT_PROFILE` or wreq-js `browser:` option
|
||
6. Run `chatgptTlsClient.test.ts` and a manual canary against the live provider
|
||
7. Ship in a patch release; document in `CHANGELOG.md`
|
||
|
||
---
|
||
|
||
## Tests
|
||
|
||
- `open-sse/services/__tests__/chatgptTlsClient.test.ts` — proxy resolution priority, abort handling, hang recovery
|
||
- `tests/unit/anthropic-cache-fingerprint.test.ts` — fingerprint determinism
|
||
- `tests/unit/chatgpt-web.test.ts` — end-to-end stealth path for ChatGPT
|
||
|
||
---
|
||
|
||
## See Also
|
||
|
||
- [RESILIENCE_GUIDE.md](../architecture/RESILIENCE_GUIDE.md) — what happens when a stealth path gets a `403`
|
||
- [TROUBLESHOOTING.md](../guides/TROUBLESHOOTING.md)
|
||
- [ENVIRONMENT.md](../reference/ENVIRONMENT.md) — full env reference
|
||
- [CLI-TOOLS.md](../reference/CLI-TOOLS.md) — operator view of the MITM workflow
|