Files
OmniRoute/open-sse/services/ccBridgeTransforms.ts
Diego Rodrigues de Sa e Souza a7ae9550bd Release v3.8.36 (#4854)
* 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>
2026-06-25 13:17:40 -03:00

582 lines
22 KiB
TypeScript

/**
* CC Bridge Transforms — config-driven request body normalization for the
* Claude Code Compatible (`anthropic-compatible-cc-*`) bridge.
*
* Goal: ensure the final request body OmniRoute sends to Anthropic's
* `/v1/messages?beta=true` endpoint has classifier-correct structure
* regardless of which client (OpenCode, Cline, Cursor, Continue, raw API
* consumer) supplied the prompt.
*
* Approach: an ordered pipeline of declarative `TransformOp` entries that
* mutate the request body in place. Each op is idempotent; the executor is
* pure (no I/O); new defenses can be added through Settings UI by appending
* a new op — no new TypeScript needed.
*
* Reference implementation: ex-machina/opencode-anthropic-auth `transform.ts`
* and `cch.ts`. Ported with the same defaults (paragraph anchors, identity
* prefixes, text replacements, billing header algorithm) but generalised
* behind a discriminated-union DSL so future fingerprints are configurable.
*
* Related: OmniRoute issue #2260.
*/
import { createHash } from "node:crypto";
// ────────────────────────────────────────────────────────────────────────────
// DSL types
// ────────────────────────────────────────────────────────────────────────────
export type TransformOp =
| DropParagraphIfContainsOp
| DropParagraphIfStartsWithOp
| ReplaceTextOp
| ReplaceRegexOp
| DropBlockIfContainsOp
| PrependSystemBlockOp
| AppendSystemBlockOp
| InjectBillingHeaderOp;
export interface DropParagraphIfContainsOp {
kind: "drop_paragraph_if_contains";
needles: string[];
caseSensitive?: boolean;
}
export interface DropParagraphIfStartsWithOp {
kind: "drop_paragraph_if_starts_with";
prefixes: string[];
caseSensitive?: boolean;
}
export interface ReplaceTextOp {
kind: "replace_text";
match: string;
replacement: string;
allOccurrences?: boolean;
}
export interface ReplaceRegexOp {
kind: "replace_regex";
pattern: string;
flags?: string;
replacement: string;
}
export interface DropBlockIfContainsOp {
kind: "drop_block_if_contains";
needles: string[];
}
export interface PrependSystemBlockOp {
kind: "prepend_system_block";
text: string;
/** Skip if any earlier block already starts with this prefix. */
idempotencyKey?: string;
}
export interface AppendSystemBlockOp {
kind: "append_system_block";
text: string;
idempotencyKey?: string;
}
export interface InjectBillingHeaderOp {
kind: "inject_billing_header";
/** Anthropic billing entrypoint label (e.g. `sdk-cli`, `cli`). */
entrypoint: string;
/**
* Version suffix algorithm:
* - ex-machina: sha256(SALT + chars-at-positions + version).slice(0,3)
* - omniroute-daystamp: sha256(YYYY-MM-DD + version).slice(0,3)
*/
versionFormat: "ex-machina" | "omniroute-daystamp";
/**
* CCH attestation algorithm:
* - sha256-first-user: sha256(firstUserMessageText).slice(0,5) (ex-machina)
* - xxhash64-body: defer to body-level signRequestBody; emit "00000" here
* - static-zero: emit "00000" (relay endpoints don't validate)
*/
cchAlgo: "sha256-first-user" | "xxhash64-body" | "static-zero";
/** Override the embedded `cc_version=` value. Defaults to `2.1.137`. */
version?: string;
}
export interface CcBridgeTransformsConfig {
enabled: boolean;
pipeline: TransformOp[];
}
// ────────────────────────────────────────────────────────────────────────────
// Ported constants (ex-machina/constants.ts)
// ────────────────────────────────────────────────────────────────────────────
/** Stable salt used by ex-machina/cch.ts for the version-suffix hash. */
export const CCH_SALT = "59cf53e54c78";
/** Character positions sampled from the first user message text. */
export const CCH_POSITIONS = [4, 7, 20] as const;
/** Default `cc_version=` value embedded in the billing header. */
export const DEFAULT_CLAUDE_CODE_VERSION = "2.1.187";
/** Identity sentinel prepended for Claude Agent SDK callers. */
export const CLAUDE_AGENT_SDK_IDENTITY =
"You are a Claude agent, built on Anthropic's Claude Agent SDK.";
/** Paragraph anchors from ex-machina (URLs identifying third-party agents). */
export const DEFAULT_PARAGRAPH_REMOVAL_ANCHORS = [
"github.com/anomalyco/opencode",
"opencode.ai/docs",
"github.com/cline/cline",
"github.com/getcursor/cursor",
"continue.dev",
];
/** Identity paragraph prefixes that signal a third-party agent. */
export const DEFAULT_IDENTITY_PREFIXES = ["You are OpenCode"];
/** Text replacements (last entry is the v1.7.5 phrase-shape filter fix). */
export const DEFAULT_TEXT_REPLACEMENTS: Array<{ match: string; replacement: string }> = [
{ match: "if OpenCode honestly", replacement: "if the assistant honestly" },
{
match: "Here is some useful information about the environment you are running in:",
replacement: "Environment context you are running in:",
},
];
/**
* Default pipeline shipped with the PR — matches the T4-200 fixture layout
* proven against the live OmniRoute deployment (call log
* f0c2fedb-b27a-4f1d-9ee6-0c88646a6d42).
*
* Layout after pipeline (system blocks):
* [0] x-anthropic-billing-header: cc_version=…; cc_entrypoint=sdk-cli; cch=…
* [1] You are a Claude agent, built on Anthropic's Claude Agent SDK.
* [2..] sanitized caller-supplied system blocks
*/
export const DEFAULT_CC_BRIDGE_PIPELINE: TransformOp[] = [
// Sanitize caller-supplied system blocks first so dropped paragraphs do not
// accidentally contain a stale billing header from a previous pass.
{
kind: "drop_paragraph_if_contains",
needles: [...DEFAULT_PARAGRAPH_REMOVAL_ANCHORS],
},
{
kind: "drop_paragraph_if_starts_with",
prefixes: [...DEFAULT_IDENTITY_PREFIXES],
},
...DEFAULT_TEXT_REPLACEMENTS.map<ReplaceTextOp>((r) => ({
kind: "replace_text",
match: r.match,
replacement: r.replacement,
allOccurrences: true,
})),
// Then prepend the SDK identity (becomes block[1] after billing prepend).
{
kind: "prepend_system_block",
text: CLAUDE_AGENT_SDK_IDENTITY,
idempotencyKey: "claude-agent-sdk-identity",
},
// Billing header always lands at block[0] — matches T4-200 fixture layout.
{
kind: "inject_billing_header",
entrypoint: "sdk-cli",
versionFormat: "ex-machina",
cchAlgo: "sha256-first-user",
},
];
export const DEFAULT_CC_BRIDGE_TRANSFORMS_CONFIG: CcBridgeTransformsConfig = {
enabled: true,
pipeline: DEFAULT_CC_BRIDGE_PIPELINE,
};
// ────────────────────────────────────────────────────────────────────────────
// Billing header value
// ────────────────────────────────────────────────────────────────────────────
interface SystemBlock {
type: string;
text?: string;
[key: string]: unknown;
}
interface MessageContentBlock {
type?: string;
text?: string;
[key: string]: unknown;
}
interface Message {
role?: string;
content?: string | MessageContentBlock[];
[key: string]: unknown;
}
/**
* Pull the textual content of the first user message in the request.
* Returns "" when no user message has text content.
*/
export function extractFirstUserMessageText(messages: Message[]): string {
if (!Array.isArray(messages)) return "";
for (const msg of messages) {
if (msg?.role !== "user") continue;
if (typeof msg.content === "string") return msg.content;
if (Array.isArray(msg.content)) {
for (const block of msg.content) {
if (block?.type === "text" && typeof block.text === "string") {
return block.text;
}
}
}
}
return "";
}
function sha256Hex(input: string): string {
return createHash("sha256").update(input, "utf8").digest("hex");
}
function pickCharsAtPositions(text: string, positions: readonly number[]): string {
return positions.map((p) => (typeof text[p] === "string" ? text[p] : "\0")).join("");
}
/**
* Compute the `cc_version` suffix per the ex-machina algorithm.
*
* `sha256(CCH_SALT + chars-at-CCH_POSITIONS(firstUserMessage) + version).slice(0, 3)`
*/
export function computeExMachinaVersionSuffix(firstUserText: string, version: string): string {
const picks = pickCharsAtPositions(firstUserText, CCH_POSITIONS);
return sha256Hex(`${CCH_SALT}${picks}${version}`).slice(0, 3);
}
/**
* Compute the `cc_version` suffix per the OmniRoute native-OAuth algorithm:
* sha256(YYYY-MM-DD + version).slice(0,3). Stable per UTC day.
*/
export function computeDaystampVersionSuffix(version: string, now: Date = new Date()): string {
const dayStamp = now.toISOString().slice(0, 10);
return sha256Hex(`${dayStamp}${version}`).slice(0, 3);
}
/**
* Compute the `cch=` attestation value per ex-machina algorithm:
* sha256(firstUserMessage).slice(0,5).
*/
export function computeCchSha256FirstUser(firstUserText: string): string {
return sha256Hex(firstUserText).slice(0, 5);
}
interface BuildBillingHeaderOptions {
entrypoint: string;
versionFormat: "ex-machina" | "omniroute-daystamp";
cchAlgo: "sha256-first-user" | "xxhash64-body" | "static-zero";
version?: string;
now?: Date;
}
/**
* Build the `x-anthropic-billing-header: …` string injected as system block[0].
*
* `xxhash64-body` and `static-zero` both emit `cch=00000` here because the
* actual body-level CCH attestation is computed later by
* `claudeCodeCCH.signRequestBody()` and replaces a 00000 placeholder in the
* serialized JSON. ex-machina's `sha256-first-user` value lives in the
* header itself.
*/
export function buildBillingHeaderValue(
messages: Message[],
options: BuildBillingHeaderOptions
): string {
const version = options.version || DEFAULT_CLAUDE_CODE_VERSION;
const firstUserText = extractFirstUserMessageText(messages);
const suffix =
options.versionFormat === "omniroute-daystamp"
? computeDaystampVersionSuffix(version, options.now)
: computeExMachinaVersionSuffix(firstUserText, version);
let cch: string;
switch (options.cchAlgo) {
case "sha256-first-user":
cch = computeCchSha256FirstUser(firstUserText);
break;
case "xxhash64-body":
case "static-zero":
default:
cch = "00000";
break;
}
return `x-anthropic-billing-header: cc_version=${version}.${suffix}; cc_entrypoint=${options.entrypoint}; cch=${cch};`;
}
// ────────────────────────────────────────────────────────────────────────────
// Body shape helpers
// ────────────────────────────────────────────────────────────────────────────
interface RequestBody {
system?: string | SystemBlock[];
messages?: Message[];
[key: string]: unknown;
}
function normalizeSystemToBlocks(system: unknown): SystemBlock[] {
if (system === null || system === undefined) return [];
if (typeof system === "string") {
return system.length > 0 ? [{ type: "text", text: system }] : [];
}
if (Array.isArray(system)) {
return system
.filter((b): b is SystemBlock => !!b && typeof b === "object")
.map((b) => ({ ...b }));
}
if (typeof system === "object") {
const block = system as SystemBlock;
return block && typeof block.text === "string" ? [{ ...block }] : [];
}
return [];
}
function isTextBlock(block: SystemBlock): block is SystemBlock & { text: string } {
return block.type === "text" && typeof block.text === "string";
}
function containsString(haystack: string, needle: string, caseSensitive: boolean): boolean {
if (caseSensitive) return haystack.includes(needle);
return haystack.toLowerCase().includes(needle.toLowerCase());
}
function startsWithString(haystack: string, prefix: string, caseSensitive: boolean): boolean {
if (caseSensitive) return haystack.startsWith(prefix);
return haystack.toLowerCase().startsWith(prefix.toLowerCase());
}
// ────────────────────────────────────────────────────────────────────────────
// Op executors
// ────────────────────────────────────────────────────────────────────────────
function applyDropParagraphIfContains(
blocks: SystemBlock[],
op: DropParagraphIfContainsOp
): SystemBlock[] {
const caseSensitive = op.caseSensitive !== false;
const needles = op.needles || [];
if (needles.length === 0) return blocks;
return blocks.map((block) => {
if (!isTextBlock(block)) return block;
const paragraphs = block.text.split(/\n\n+/);
const filtered = paragraphs.filter(
(p) => !needles.some((n) => containsString(p, n, caseSensitive))
);
return { ...block, text: filtered.join("\n\n") };
});
}
function applyDropParagraphIfStartsWith(
blocks: SystemBlock[],
op: DropParagraphIfStartsWithOp
): SystemBlock[] {
const caseSensitive = op.caseSensitive !== false;
const prefixes = op.prefixes || [];
if (prefixes.length === 0) return blocks;
return blocks.map((block) => {
if (!isTextBlock(block)) return block;
const paragraphs = block.text.split(/\n\n+/);
const filtered = paragraphs.filter(
(p) => !prefixes.some((prefix) => startsWithString(p.trimStart(), prefix, caseSensitive))
);
return { ...block, text: filtered.join("\n\n") };
});
}
function applyReplaceText(blocks: SystemBlock[], op: ReplaceTextOp): SystemBlock[] {
if (!op.match) return blocks;
return blocks.map((block) => {
if (!isTextBlock(block)) return block;
if (!block.text.includes(op.match)) return block;
let next = block.text;
if (op.allOccurrences) {
next = next.split(op.match).join(op.replacement);
} else {
next = next.replace(op.match, op.replacement);
}
return { ...block, text: next };
});
}
function applyReplaceRegex(blocks: SystemBlock[], op: ReplaceRegexOp): SystemBlock[] {
if (!op.pattern) return blocks;
let regex: RegExp;
try {
regex = new RegExp(op.pattern, op.flags ?? "u");
} catch {
return blocks;
}
return blocks.map((block) => {
if (!isTextBlock(block)) return block;
return { ...block, text: block.text.replace(regex, op.replacement) };
});
}
function applyDropBlockIfContains(blocks: SystemBlock[], op: DropBlockIfContainsOp): SystemBlock[] {
const needles = op.needles || [];
if (needles.length === 0) return blocks;
return blocks.filter((block) => {
if (!isTextBlock(block)) return true;
return !needles.some((n) => block.text.includes(n));
});
}
function applyPrependSystemBlock(blocks: SystemBlock[], op: PrependSystemBlockOp): SystemBlock[] {
if (!op.text) return blocks;
// Idempotency: skip if any text block already starts with idempotencyKey (when
// set) or with op.text itself (default). Scans ALL blocks, not just the first.
const prefix = op.idempotencyKey ?? op.text;
const alreadyPresent = blocks.some((b) => isTextBlock(b) && b.text.startsWith(prefix));
if (alreadyPresent) return blocks;
return [{ type: "text", text: op.text }, ...blocks];
}
function applyAppendSystemBlock(blocks: SystemBlock[], op: AppendSystemBlockOp): SystemBlock[] {
if (!op.text) return blocks;
// Idempotency: skip if any text block already starts with idempotencyKey (when
// set) or is an exact match of op.text (default). Scans ALL blocks.
const prefix = op.idempotencyKey;
const alreadyPresent = prefix
? blocks.some((b) => isTextBlock(b) && b.text.startsWith(prefix))
: blocks.some((b) => isTextBlock(b) && b.text === op.text);
if (alreadyPresent) return blocks;
return [...blocks, { type: "text", text: op.text }];
}
function applyInjectBillingHeader(
body: RequestBody,
blocks: SystemBlock[],
op: InjectBillingHeaderOp
): SystemBlock[] {
// No user message → no billing header (ex-machina parity, transform.ts:340).
const messages = Array.isArray(body.messages) ? body.messages : [];
const hasUser = messages.some((m) => m?.role === "user");
if (!hasUser) return blocks;
const headerValue = buildBillingHeaderValue(messages, {
entrypoint: op.entrypoint,
versionFormat: op.versionFormat,
cchAlgo: op.cchAlgo,
version: op.version,
});
// Idempotency: replace any existing billing header block (ex-machina + native
// OAuth path both rebuild on retry; see executors/base.ts issue #1712).
const headerPrefix = "x-anthropic-billing-header:";
const filtered = blocks.filter((b) => !(isTextBlock(b) && b.text.startsWith(headerPrefix)));
return [{ type: "text", text: headerValue }, ...filtered];
}
// ────────────────────────────────────────────────────────────────────────────
// Pipeline executor
// ────────────────────────────────────────────────────────────────────────────
export interface ApplyPipelineResult {
body: RequestBody;
appliedOpKinds: string[];
}
/**
* Run the configured transform pipeline against a request body.
*
* The body is mutated in place (its `system` field is replaced); returned for
* chaining. `appliedOpKinds` lists the ops that ran (omitting no-ops when
* config is disabled). When `config.enabled === false`, the body is returned
* unchanged and `appliedOpKinds` is empty.
*/
export function applyCcBridgeTransformPipeline(
body: RequestBody,
config: CcBridgeTransformsConfig = getCcBridgeTransformsConfig()
): ApplyPipelineResult {
if (!body || typeof body !== "object") {
return { body, appliedOpKinds: [] };
}
if (!config.enabled || !Array.isArray(config.pipeline) || config.pipeline.length === 0) {
return { body, appliedOpKinds: [] };
}
let blocks = normalizeSystemToBlocks(body.system);
const appliedOpKinds: string[] = [];
for (const op of config.pipeline) {
switch (op.kind) {
case "drop_paragraph_if_contains":
blocks = applyDropParagraphIfContains(blocks, op);
break;
case "drop_paragraph_if_starts_with":
blocks = applyDropParagraphIfStartsWith(blocks, op);
break;
case "replace_text":
blocks = applyReplaceText(blocks, op);
break;
case "replace_regex":
blocks = applyReplaceRegex(blocks, op);
break;
case "drop_block_if_contains":
blocks = applyDropBlockIfContains(blocks, op);
break;
case "prepend_system_block":
blocks = applyPrependSystemBlock(blocks, op);
break;
case "append_system_block":
blocks = applyAppendSystemBlock(blocks, op);
break;
case "inject_billing_header":
blocks = applyInjectBillingHeader(body, blocks, op);
break;
default: {
// Unknown op kind — skip silently to keep forward compatibility.
continue;
}
}
appliedOpKinds.push(op.kind);
}
// Drop empty text blocks left behind by paragraph removal (matches
// ex-machina sanitizeSystemText trim semantics).
blocks = blocks.filter((b) => !isTextBlock(b) || b.text.length > 0);
body.system = blocks;
return { body, appliedOpKinds };
}
// ────────────────────────────────────────────────────────────────────────────
// Runtime singleton (mirrors cliFingerprints `_cliCompatProviders` pattern).
// ────────────────────────────────────────────────────────────────────────────
let _runtimeConfig: CcBridgeTransformsConfig = DEFAULT_CC_BRIDGE_TRANSFORMS_CONFIG;
/**
* Replace the active CC bridge transforms config. Called from
* `runtimeSettings.applyCcBridgeTransformsSection()` when the Settings UI
* saves a new pipeline.
*/
export function setCcBridgeTransformsConfig(config: CcBridgeTransformsConfig | null): void {
if (!config) {
_runtimeConfig = DEFAULT_CC_BRIDGE_TRANSFORMS_CONFIG;
return;
}
_runtimeConfig = {
enabled: config.enabled !== false,
pipeline: Array.isArray(config.pipeline) ? config.pipeline : DEFAULT_CC_BRIDGE_PIPELINE,
};
}
/**
* Read the currently active config (defaults to DEFAULT_CC_BRIDGE_PIPELINE).
*/
export function getCcBridgeTransformsConfig(): CcBridgeTransformsConfig {
return _runtimeConfig;
}
/**
* Reset to defaults — exposed for tests and the Settings UI "Reset" button.
*/
export function resetCcBridgeTransformsConfig(): void {
_runtimeConfig = DEFAULT_CC_BRIDGE_TRANSFORMS_CONFIG;
}