mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-01 04:42:10 +03:00
* chore(release): open v3.8.36 development cycle * refactor(chatCore): extrai resolveCompressionSettings (#3501) (#4826) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 1/13) * refactor(chatCore): extrai predicados puros de combo de compressão (#3501) (#4824) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 2/13) * refactor(chatCore): extrai emitOutputStyleTelemetry (#3501) (#4811) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 3/13) * refactor(chatCore): extrai writeCompressionAnalytics (bloco analytics completo, #3501) (#4817) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 4/13) * refactor(chatCore): extrai runPluginOnRequestHook (#3501) (#4827) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 5/13) * refactor(chatCore): extrai applyClientUsageBuffer (buffer/estimate de usage non-streaming, #3501) (#4832) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 6/13) * refactor(chatCore): extrai buildPostCallGuardrailContext (contexto guardrail post-call, #3501) (#4831) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 7/13) * refactor(chatCore): extrai storeSemanticCacheResponse (cache-store non-streaming, #3501) (#4828) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 8/13) * refactor(chatCore): extrai buildNonStreamingResponseHeaders (headers de resposta non-streaming, #3501) (#4835) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 9/13) * refactor(chatCore): extrai maybeConvertJsonBodyToSse (#3089 JSON→SSE streaming, #3501) (#4833) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 10/13) * refactor(chatCore): extrai assembleStreamingResponseHeaders (headers de resposta streaming, #3501) (#4836) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 11/13) * refactor(chatCore): extrai storeStreamingSemanticCacheResponse (cache-store streaming, #3501) (#4829) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 12/13) * refactor(chatCore): extrai assembleStreamingPipeline (chain de transforms streaming, #3501) (#4837) Integrated into release/v3.8.36 (#3501 chatCore extraction stack 13/13) * ci(quality): shift heavy validations to the PR→release fast-path (release-acceleration) (#4857) * feat(quality): add check:test-runner-api gate (vitest-only dirs must use vitest API) * feat(release): reusable CHANGELOG i18n-mirror sync script * chore(ops): add prune-stale-worktrees.sh (dry-run by default) * ci(quality): run test-runner-api + docs-all + vitest + full unit suite on PR->release fast-path --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(quota): cota exclusiva lista qtSd/ no /v1/models (#4806) + limite EPSILON não bloqueia (#4830) Integrated into release/v3.8.36 — quota-exclusive qtSd/ listing (#4806) + EPSILON placeholder no longer blocks; rebuilt from stale base (3 defining commits cherry-picked clean over release tip) * feat(sse): add Google Flow video-generation provider (#4569) (#4769) Integrated into release/v3.8.36 — Google Flow video-generation provider (#4569), release-green validated (typecheck + 21 tests + file-size) * fix(api): auth on compression run-telemetry + document OMNIROUTE_EVAL_CREDENTIALS (#4694, #4720) (#4796) Integrated into release/v3.8.36 — auth on compression run-telemetry + OMNIROUTE_EVAL_CREDENTIALS doc, release-green validated (typecheck + 3 tests + env-doc-sync) * fix(translator): strip top-level client_metadata on the OpenAI passthrough (port from 9router#1157) (#4624) Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated) * fix(translator): normalize `developer` role to `system` for OpenAI-format providers (#4625) Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated) * fix(translator): emit </think> close marker for Anthropic thinking blocks (#4633) Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated) * fix(translator): normalize tools to Anthropic-native shape for non-Anthropic providers (#4650) Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated) * fix(gemini): preserve `pattern` in antigravity tool schema sanitizer (#4651) Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated) * fix(perplexity): validate API keys via /v1/models endpoint (#4654) Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated) * fix(image): prevent compatible nodes from shadowing provider aliases (#4656) Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated) * fix(cli-tools): tolerate JSONC (comments, trailing commas) in tool settings (#4659) Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated) * fix(security): validate kiro region to prevent SSRF (GHSA-6mwv-4mrm-5p3m) (#4629) Integrated into release/v3.8.36 — kiro region SSRF guard (GHSA-6mwv-4mrm-5p3m), port rebuilt clean over release tip * fix(cli): harden the systray2 tray runtime (port of 9router#1080) (#4628) Integrated into release/v3.8.36 — port rebuilt clean over release tip, release-green validated * fix(test): validate anthropic-compatible connections via POST /v1/messages (#4657) Integrated into release/v3.8.36 — anthropic-compat validation via POST /v1/messages (port 584cf66a), rebuilt clean + baseline; release-green * fix(executors): strip params unsupported by the target provider/model (#4658) Integrated into release/v3.8.36 — port rebuilt clean over release tip, release-green validated * fix(claude-oauth): respect 429 backoff on usage endpoint to reduce spam (#4655) Integrated into release/v3.8.36 — port rebuilt clean over release tip, release-green validated * feat(api/v1): include alias-backed models in /v1/models listing (#4630) Integrated into release/v3.8.36 — port rebuilt clean over release tip, release-green validated * chore(quality): rebaseline catalog.ts 1574->1577 (#4630 aliases sobre quota-exclusive da release) (#4879) rebaseline * feat(compression): Kiro/CodeWhisperer tool-result compression engine (#4635) Integrated into release/v3.8.36 — port rebuilt clean, release-green * fix(security): don't trust loopback socket as local when behind reverse proxy (#4632) Integrated into release/v3.8.36 — port rebuilt clean, release-green * fix(opencode): preserve DeepSeek reasoning content in streamed responses (#4631) Integrated into release/v3.8.36 — DeepSeek reasoning_content injection (port #1099); release-green * fix(copilot,antigravity): cap maxOutputTokens at 16384 to stop "Invalid Argument" 400 (#4636) Integrated into release/v3.8.36 — cap maxOutputTokens 16384 antigravity (port #779); release-green * fix(dashboard): show custom vision models in LLM selector (#4653) Integrated into release/v3.8.36 — custom vision models in LLM selector (port 5e5e78d3); release-green * fix(claude): omit adaptive thinking + output_config.effort for haiku (#4661) Integrated into release/v3.8.36 — haiku adaptive-thinking omit (port); release-green * feat(provider): CodeBuddy CN (copilot.tencent.com) — full stack (#4664) Integrated into release/v3.8.36 — CodeBuddy CN provider (port efd20be8); usage.ts import + public-creds allowlist line reconciled; release-green * feat(combo): Fusion strategy — parallel panel + judge synthesis (16th strategy) (#4652) Integrated into release/v3.8.36 — Fusion combo strategy (16th, port 87e5c1c6); combo.ts baseline reconciled; release-green * feat(proxy-pool): Deno Deploy relays + group action buttons (#4643) Integrated into release/v3.8.36 — Deno Deploy relays (port #1437); proxies.ts baseline reconciled + env docs restored; release-green * fix(security): pin image fetch DNS resolution to prevent SSRF rebinding (GHSA-cmhj-wh2f-9cgx) (#4634) Integrated into release/v3.8.36 — pin DNS for image fetch SSRF rebinding guard (GHSA-cmhj-wh2f-9cgx, port c7d07448); caller DNS stubs + test-file baseline reconciled; release-green * fix(github): route Copilot Codex models to /responses (port from 9router#102) (#4626) Integrated into release/v3.8.36 — route Copilot Codex models to /responses (port #102); release-green * fix(copilot): never route Gemini/Claude variants to /responses (chat-completions only) (#4627) Integrated into release/v3.8.36 — never route Gemini/Claude to /responses (port #1536); fused with #4626 codex routing via supportsResponsesEndpoint gate; release-green * docs(ops): add canonical incident response runbook (#4868) Integrated into release/v3.8.36 * docs(perf): add per-endpoint p50/p95/p99 latency + cost budgets (#4867) Integrated into release/v3.8.36 * fix(proxy): fan out direct dispatcher streams (#4803) Integrated into release/v3.8.36 * fix(antigravity): exclude standard Gemini rate limit message from quota exhaustion keywords (#4810) Integrated into release/v3.8.36 * fix(sse): skip third-party tool-name cloak for Anthropic server tools (#4808) Integrated into release/v3.8.36 * fix(install): make transformers optional for CUDA-host installs (#4807) Integrated into release/v3.8.36 * fix(combo): propagate selected connection ID to fallback error responses for correct model lockout (#4809) Integrated into release/v3.8.36 * fix db storage tuning settings (#4834) Integrated into release/v3.8.36 * fix(sse): drop ccp pin when pinned provider is durably unhealthy (failover + anti-flap) (#4864) Integrated into release/v3.8.36 * fix(claude): skip mcp__ tool-name cloak + guard missing connectionId (#4861) Integrated into release/v3.8.36 * chore(quality): reconcile env-doc + file-size base-reds in release/v3.8.36 (#4886) - env-doc-sync: document PIN_DROP_BACKOFF_LEVEL / PIN_DROP_GRACE_MS (added by the ccp-pin health gate #4864) in .env.example + ENVIRONMENT.md. - file-size: rebaseline image-generation-handler.test.ts 1996 -> 2019 to its actual size (pre-existing drift). Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(codex): drop non-standard codex.* events that break responses.stream (env-gated, #4602) (#4715) Integrated into release/v3.8.36 * feat(routing): honor X-Route-Model header to override body.model (#4863) Integrated into release/v3.8.36 * feat(live-ws): allow non-loopback clients via LIVE_WS_ALLOWED_HOSTS (closes #4873) (#4877) Integrated into release/v3.8.36 (live-ws + combo-api commits; Tailscale CGNAT commit held pending opt-in/opt-out decision) * chore(claude,codex): bump pinned CLI identity — Claude 2.1.158→2.1.187, Codex 0.132.0→0.142.0 (#4883) Integrated into release/v3.8.36 * fix(security): SSRF allowlist bypass via x-relay-path nos relays Deno/Vercel (#4899) Integrated into release/v3.8.36 * feat(quota): recuperação proativa de conexões em cooldown (cron heal) [Fase 3 #8] (#4900) Integrated into release/v3.8.36 * fix(quota): policy inválida não vaza allow + guard connectionIds vazio [Fase 3 #10] (#4901) Integrated into release/v3.8.36 * feat(quota): saturação real do Claude no fair-share via /api/oauth/usage (#4885) Integrated into release/v3.8.36 * chore(dashboard): rename Qoder display label from "Qoder AI" to "Qoder" (#4733) Integrated into release/v3.8.36 * fix(ci): include coverage/lcov.info in coverage-report artifact for SonarQube (#4670) Integrated into release/v3.8.36 * fix(cli): bump better-sqlite3 runtime pin to 12.10.1 for Node 26 (#4685) Integrated into release/v3.8.36 * docs: clarify Kiro is ~50 credits/month per account, not unlimited (#4690) Integrated into release/v3.8.36 * docs(agentbridge): document Electron NODE_EXTRA_CA_CERTS, real model IDs, identity caveat (#4718) Integrated into release/v3.8.36 * docs(ops): document the release-green family (green-prs, check:release-green, babysit, nightly) (#4679) Integrated into release/v3.8.36 * fix(translator): replay reasoning_content on plain Xiaomi MiMo turns (port from 9router#1321) (#4639) Integrated into release/v3.8.36 * feat(opencode-go): advertise glm-5.2 and kimi-k2.7-code (align with official Go endpoints) (#4711) Integrated into release/v3.8.36 * feat(db): track API endpoint dimension on usage_history (#4676) Integrated into release/v3.8.36 (migration renumbered 103→105; endpoint plumbed through extracted usage-stats helpers) * fix(cli): SIGKILL systray child PID before IPC close to avoid macOS NSStatusItem orphan (#4732) Integrated into release/v3.8.36 * feat(proxy-pool): Cloudflare Workers proxy deployer + pool integration (#4640) Integrated into release/v3.8.36 (relay type added to RELAY_TYPES set; dropdown UX preserved + Cloudflare item added; proxies.ts file-size rebaselined 1057→1060) * chore(quality): conserta base-red de release/v3.8.36 (gates + 7 testes + build MDX) (#4915) A base tinha base-red sistêmica herdada de PRs de outras sessões, bloqueando TODOS os PRs do ciclo (o TIA roda a suíte full em fail-safe p/ diffs hub). 4 Fast Quality Gates: - test-discovery (#4877): live-server-allowlist.test.ts em tests/unit/server/ (não-coletado) + vitest → nunca rodava. Convertido p/ node:test em tests/unit/security/. - any-budget:t11 (#4664): 3 explicit-any em tokenRefresh.ts tipados (sem crescer file-size). - docs-symbols (#4868): rotas inexistentes → /api/system/version e PUT /api/providers/{id} {isActive:false}. - docs-all fabricated-claim (#4868 + #4718): 5 bin/*.sh reais criados (rollback, snapshot-data, restore-data, restore-policies, cold-start-bench) + _ops-common.sh (snapshot VACUUM INTO, guards de confirmação/TTY, testes de contrato); NODE_EXTRA_CA_CERTS (env de runtime Node) na allowlist do checker. 7 testes unit base-red (de features alheias à quota): - oauth-providers-config (#4664): teste alinhado ao provider codebuddy-cn do registry. - antigravity-model-aliases (#4636): maxOutputTokens esperado 32769→16384 (cap intencional). - provider-request-capture #4091 (#4861): exemplo do teste trocado de mcp__ (que #4861 isenta de cloak por causa dos 400s de assimetria de histórico) para um tool de terceiro cloakável — preserva o invariante de #4091 SEM reverter #4861. - combo-error-response: convertido de vitest p/ node:test (era coletado pelo glob node:test e crashava); api/** e server/** removidos do vitest.config (config morta). Build MDX (dast-smoke, #4679): - docs/ops/RELEASE_GREEN.md não tinha frontmatter `title` → fumadocs-mdx rejeitava no webpack compile ("invalid frontmatter: title expected string"), quebrando o next build (e o deploy). Frontmatter title adicionado (único doc do collection sem ele). 17/17 Fast Quality Gates + suíte unit completa (17737 testes, 0 fail) + vitest verdes localmente. Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * feat(quota): saturação proativa por headers de tokens (universal) [Fase 3 #2] (#4907) storeRateLimitHeaders só capturava os headers de REQUESTS (RPM/min), que não refletem a pressão de TOKENS. Agora também parseia os headers de tokens (em toda resposta, sucesso também) para throttle proativo antes do 429: - Anthropic: anthropic-ratelimit-tokens-{limit,remaining,reset} (+ input/output), RFC3339. - OpenAI: x-ratelimit-{limit,remaining,reset}-tokens, reset em duração (6m0s). saturation = 1 − remaining/limit; resetAt normalizado a epoch (parse de duração ReDoS-safe). getTokenHeaderSaturation por (provider, connectionId). fetchGeneric- Saturation passa a usar esse sinal (complementa o oauth/usage do #1, que segue primário p/ Claude). Fail-open, cache mantido, request-path inalterado. 16 testes novos + regressão (oauth/usage #1 8/8, signals 6/6) = 30/30; typecheck:core + eslint limpos. Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * feat(quota): estratégia de combo "headroom" — seleção por folga de cota [Fase 3 #4] (#4908) Nova estratégia de roteamento que escolhe a conexão com MAIS folga de plano: headroom = 1 − max(util_5h, util_7d) (técnica do dario), via getSaturation (melhorado p/ Claude no #1). Proativo em vez de só fill-first reativo. - Helper PURO headroomRanking.ts (computeHeadroom + rankByHeadroom; saturação injetada, não-mutante, tie-break estável, fail-open). - Orderer async em combo/quotaStrategies.ts (reusa a maquinaria reset-aware de expansão de conexões + concorrência limitada; seam injetável). - Registrada como "headroom" em routingStrategies (combo-only); fill-first segue default — nenhuma estratégia existente tocada. - baseline file-size combo.ts 3168->3180 (só +12L de dispatch; lógica fora do god-file). 16 testes novos + combo-strategies 15/15 = 31/31; typecheck:core + eslint + file-size limpos. Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * feat(quota): cap per-(key,model) — quota_allocation_model_caps [Fase 3 #7] (#4927) * feat(quota): cap per-(key,model) com tabela quota_allocation_model_caps [Fase 3 #7] Fecha o buraco onde uma API key pode drenar o pool inteiro consumindo um único modelo. Tabela nova: quota_allocation_model_caps(pool_id, api_key_id, model, cap_value, cap_unit) PK composta (pool_id, api_key_id, model). cap_unit alinhado ao QuotaUnit existente. Comportamento: keyA acima do cap para modelo M → bloqueada somente em M; ainda permitida em qualquer outro modelo no mesmo pool. Cap <= EPSILON → ignorado (seed). Consumo por-(key,model) usa bucket segregado no quota_consumption existente (poolId mangled ':model:<model>') com window fixa 'hourly'; nenhuma nova tabela ou método de store necessário. Módulo novo: src/lib/db/quotaModelCaps.ts (getModelCap/setModelCap/deleteModelCap/listModelCaps) enforce.ts ganha o pre-check em enforceQuotaShare + recording em recordConsumption. EnforceInput e RecordConsumptionInput ganham model?: string (backward-compatible). localDb.ts re-exporta os 4 helpers (Hard Rule #2). TDD: tests/unit/quota-per-key-model.test.ts — 4 cenários (bloqueia em M, permite em M2, sem cap → sem bloqueio, EPSILON → ignorado). Todos os gates de qualidade passam. * feat(quota): plumba model resolvido no hot path para ativar o per-(key,model) cap [Fase 3 #7] A tabela/enforce do commit anterior estavam INERTES: o hot path não passava `model` ao enforce nem ao record, então nenhum model-cap disparava em produção. Plumbagem (model resolvido = mesma var usada no log/roteamento, pós background-redirect/alias): - chatCore.ts: enforceQuotaShare ganha `model`; scheduleQuotaShareConsumption recebe `model`. - chatCore/quotaShareConsumption.ts: threade `model` no RecordConsumptionInput (non-streaming). - spendRecorder.ts: recordStreamingConsumption já recebia `model` — agora o coloca no RecordConsumptionInput (streaming accrue por-modelo). - embeddings.ts: enforce + record ganham `model`. Namespace do cap = id do modelo RESOLVIDO (o mesmo de modelForScope/pendingScope/getUnsupportedParams), não o requestedModel cru nem o finalModelToUpstream (sem prefixo de provider). Operador configura o cap contra esse id. `model || undefined` em todos os pontos: vazio/null → check pulado (fail-safe, zero latência — só um campo no objeto). Teste de integração novo (tests/unit/quota-per-key-model-hotpath.test.ts): prova end-to-end que N consumos via scheduleQuotaShareConsumption({model}) → enforceQuotaShare({model}) bloqueia, e que outro modelo no mesmo pool ainda passa; + guard de que enforce SEM model nunca dispara model-cap. --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * feat(quota): session stickiness p/ integridade de prompt-cache [Fase 3 #5] (#4929) * feat(quota): session stickiness p/ integridade de prompt-cache [Fase 3 #5] Adiciona stickiness de sessão ao roteamento de combo: uma conversa multi-turno é roteada para a MESMA conexão enquanto ela permanecer saudável, evitando a perda do prompt-cache do provider (custo 5-10× sem stickiness, efeito conhecido no dario/clewdr). Implementação: - `open-sse/services/combo/sessionStickiness.ts` (novo, <800 linhas): mapa em memória (messageHash → connectionId) com TTL 15 min + cap 500 entradas; `applySessionStickiness` promove a conexão sticky ao índice 0 dos targets ordenados pelo strategy, guardado por `computeHeadroom > 0.15` (threshold); quando saturada (headroom ≤ 0.15), o binding é limpo e a seleção normal reage. Hash da sessão = SHA-256 dos primeiros chars da 1ª mensagem user → 16 hex chars. Seam de teste: `__setStickinessHeadroomFetcherForTests`. - `open-sse/services/combo.ts`: import + 2 pontos de integração (pré-eval-scores e pós-success), dentro do orçamento congelado de 3180 linhas. - `tests/unit/combo-session-stickiness.test.ts`: 19 testes node:test + assert/strict, todos via injeção de fetcher (zero rede/DB). Threshold 0.15: conexão a >85% de utilização está a um burst de rate-limit; o benefício de cache não compensa manter-se numa conexão degradada. Valor alinhado com a zona de soft-penalty do restante do engine de quota-share. * test(combo): isola combo-strategies da session stickiness (#5) selectedConnectionFor reusa o mesmo body, então o sticky map (#5) fixava a connection após a 1ª chamada e quebrava o round-robin tie-break do teste reset-aware. Limpa o sticky map no início da helper — a stickiness tem suíte própria (combo-session-stickiness). Sem enfraquecer asserts. --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * feat(quota): buckets multi-janela por conexão (5h/7d/per-model) [Fase 3 #3] (#4928) Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * refactor(providers): decompõe catálogo providers.ts em módulos de dados (godfile sweep, #3501) (#4917) Integrado em release/v3.8.36 (godfile sweep providers.ts, #3501) * refactor(pricing): decompõe pricing.ts em shared-tiers + DEFAULT_PRICING particionado (godfile sweep, #3501) (#4918) Integrado em release/v3.8.36 (godfile sweep pricing.ts, #3501) * refactor(api): extrai camada-folha pura de validation.ts (URL/headers/transport) (#4921) Integrado em release/v3.8.36 (validation.ts split fatia 1 — leaf layer) * refactor(api): extrai validators web-cookie + Meta AI de validation.ts (#4922) Integrado em release/v3.8.36 (validation.ts split fatia 2 — web-cookie + Meta AI) * refactor(api): extrai validators enterprise-cloud + probe compartilhado de validation.ts (#4923) Integrado em release/v3.8.36 (validation.ts split fatia 3 — enterprise-cloud + probe) * refactor(api): extrai validators áudio/speech + misc apikey de validation.ts (#4930) Integrado em release/v3.8.36 (validation.ts split fatia 4 — áudio/speech + misc apikey) * feat(quota): estratégia dedicada de quota-share (DRR + P2C in-flight + gating per-model) [Fase 3 #9] (#4939) * feat(quota): estratégia dedicada de quota-share (DRR + P2C in-flight + gating per-model) [Fase 3 #9] Estratégia interna "quota-share" isolada num módulo dedicado — NÃO toca a seleção/ fair-share genérica (decisão do dono: não mexer no que já funciona). Os combos qtSd/ (quotaCombos.ts) passam de fill-first para essa strategy; combo.ts ganha só 1 branch de dispatch que delega 100% ao módulo (nenhum case existente alterado). - quotaShareStrategy.ts: gating per-model (isBucketSaturated do #3) + DRR (quantum proporcional ao weight) + P2C sobre carga in-flight. - quotaShareInflight.ts: contador in-flight com TTL/lease de 120s — fallback do decrement-on-abort sem precisar instrumentar o combo genérico. - "quota-share" registrada como strategy INTERNA (não exposta na UI). - testes de síntese (quota-combo-balancing, quota-multiprovider) alinhados: a strategy esperada dos combos qtSd/ passa de "fill-first" para "quota-share" (alinhamento ao novo comportamento intencional, não mascaramento — os 73 testes de qtSd/ seguem verdes). * test(quota-share): alinha 2 scope-guards ao godfile sweep (base-reds que bloqueavam o CI) Dois testes de "arquivo contém X" quebraram por decomposições de godfile que outras sessões mergearam no release DURANTE a validação de #9 — NÃO são regressão de #9 (que não toca validation/oauth). Alinhados ao novo layout, asserts preservados: - proxy-bypass-scope-guard #3226: bypassProxyPatch foi extraído de validation.ts para validation/headers.ts (split #4921–#4930) → o teste lê a camada de validação. - sse-error-passthrough #3324: a windsurf authHint foi extraída de providers.ts para providers/oauth.ts → o teste lê o novo local. --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * refactor(api): extrai validators search + embedding/rerank de validation.ts (#4932) Integrated into release/v3.8.36 * refactor(api): extrai format-validators (OpenAI/Anthropic) de validation.ts (#4933) Integrated into release/v3.8.36 * refactor(db): extrai model-permission matching de db/apiKeys.ts (#4936) Integrated into release/v3.8.36 * refactor(db): extrai row-parsers + tipos compartilhados de db/apiKeys.ts (#4943) Integrated into release/v3.8.36 * refactor(db): extrai column-mapping (snake↔camel) de db/core.ts (#4947) Integrated into release/v3.8.36 * refactor(db): extrai schema-column reconciliation de db/core.ts (#4948) Integrated into release/v3.8.36 * refactor(sse): extrai scalar/format helpers de services/usage.ts (#4949) Integrated into release/v3.8.36 * refactor(sse): extrai quota-core (UsageQuota + builders) de services/usage.ts (#4950) Integrated into release/v3.8.36 * fix(translator): regroup parallel tool results adjacent to their assistant (#4714) (#4882) Integrated into release/v3.8.36 (fixes #4714) * fix(qoder): exchange PAT for jt-* job token before Cosy chat (#4683) (#4884) Integrated into release/v3.8.36 (fixes #4683) * refactor(sse): dedup fallback tool_call id helper (#4736) Integrated into release/v3.8.36 * refactor(open-sse): extract safeParseJSON util, dedup tryParseJSON (#4735) Integrated into release/v3.8.36 * fix(compression): eliminate ReDoS in math_inline preservation pattern (#4795) (#4838) Integrated into release/v3.8.36 (fixes #4795) * fix(combo): fetch models dynamically from custom provider endpoints (#4860) Integrated into release/v3.8.36 * feat(providers): update volcengine-ark model list with DeepSeek V4 (#4905) Integrated into release/v3.8.36 * fix(translator): provider thinking compatibility (DeepSeek/Gemini) (#4946) Integrated into release/v3.8.36 * feat(combo): task-aware routing strategy (#4945) Integrated into release/v3.8.36 * refactor(sse): extrai a família MiniMax de services/usage.ts (#4952) Integrated into release/v3.8.36 * refactor(sse): extrai a família GLM de services/usage.ts (#4953) Integrated into release/v3.8.36 * refactor(sse): extrai a família Antigravity de services/usage.ts (#4956) Integrated into release/v3.8.36 * fix(dashboard): show custom provider given-name instead of internal id across dashboard pages (#4603) (#4960) Integrated into release/v3.8.36 (fixes #4603) * fix(api): evict stale in-memory rate-limit windows to stop slow heap leak (#4041) (#4957) Integrated into release/v3.8.36 (fixes #4041) * fix(api): parse /v1/responses body once instead of 3-4x on the hot path (#4041) (#4958) Integrated into release/v3.8.36 (fixes #4041) * fix(translator): preserve legitimate empty-string tool arguments in openai-to-claude streaming (#4951) (#4959) Integrated into release/v3.8.36 (fixes #4951) * chore(quality): reconcile file-size baseline for #4960 provider-display-name (#4961) Integrated into release/v3.8.36 * fix(dashboard): restore home provider-topology card hidden by #4596 default (#4963) Integrated into release/v3.8.36 — restores home topology card (#4596 regression) * fix(build): drop @omniroute/open-sse from optimizePackageImports (build OOM) (#4968) Integrated into release/v3.8.36 — fixes build OOM (optimizePackageImports open-sse) * fix(quota): migração 107 ativa estratégia quota-share nos combos qtSd/ existentes [Fase 3 #9] (#4962) Integrated into release/v3.8.36 * feat(quota): respeita max_concurrent por conexão no roteamento (#4965) Integrated into release/v3.8.36 * feat(quota): combo quota-share espera cooldown curto e re-despacha (Variante A) (#4967) Integrated into release/v3.8.36 * fix(quality): resolve base-reds da release — db-rules allowlist + task-aware router precedence (#4973) Dois base-reds pré-existentes que reprovavam o CI da release v3.8.36 (Fast Quality Gates + Unit Tests fast-path), independentes de qualquer feature em voo: 1. check:db-rules / allowlist: os módulos db-internal caseMapping (#4947) e schemaColumns (#4948), extraídos de db/core.ts e importados só por ele, não estavam em INTENTIONALLY_INTERNAL. Registrados na allowlist (correção canônica — são internos legítimos, não re-exportados pelo localDb). 2. auto-strategy honra LKGP/cost (combo-routing-engine.test.ts, 2 testes): o task-aware reordering (#4945, reorderByTaskWeight) roda para strategy "auto" e era aplicado DEPOIS do router explícito (selectWithStrategy: lkgp/cost), sobrescrevendo o orderedTargets[0] que o operador escolheu. Instrumentação provou: post-filter [0]=claude (LKGP) → post-task [0]=gpt-oss. Correção: quando o auto usa router explícito, preserva o [0] dele e deixa o task-aware refinar só a cauda de fallback. gpt-oss-120b PERMANECE tool-capable (não é mudança de catálogo; o model-capabilities-registry test segue verde). Validado: 121 testes (combo-routing-engine + combo-task-aware + registry) verdes, red-check confirmado, db-rules/file-size/typecheck/lint/prettier OK. Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * feat(quota): serializa concorrência por conexão no caminho quota-share (FASE 2.1) (#4970) O gating de quota-share em selectQuotaShareTarget é fail-open: uma conexão at-cap só é despriorizada, nunca bloqueada. Com 1 conexão por conta de assinatura (caso comum), chamadas concorrentes ainda floodam a conta (→ 429 + cooldown) — provado live na .15: 3 chamadas concorrentes com max_concurrent=1 despacharam todas em 94ms. Adiciona um semáforo POR CONEXÃO em torno do dispatch quota-share: chamadas excedentes esperam na fila em vez de floodar (key qsconn:<connectionId>, cap = max_concurrent da conexão). Fail-open em fila saturada/timeout para nunca piorar disponibilidade. Gated por strategy===quota-share + kill-switch resilienceSettings.quotaShareConcurrencyLimit (default on; UI no ResilienceTab). Lógica extraível isolada no leaf puro combo/quotaShareConcurrency.ts (unit-testado: estabilidade da key, no-op sem cap, serialização real, fail-open). Settings + schema + UI espelham comboCooldownWait. Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * docs(resilience): document Quota-Share Concurrency Control (max_concurrent + serialization + cooldown-wait) (#4980) Documents the v3.8.36 quota-share concurrency layers in RESILIENCE_GUIDE.md: per-connection max_concurrent cap, the quota-share request serialization semaphore (FASE 2.1, qsconn:<connectionId>, fail-open, kill-switch), and the combo cooldown-aware retry — so operators know how to cap a subscription account's concurrency and why the routing gate alone cannot contain a single-connection flood. Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(dashboard): proxy-pool success gating, sync timestamp, opt-in Redis (#4878) (#4988) Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(sse): fail over on 400 responses carrying rate-limit text (#4976) (#4986) * fix(sse): fail over on 400 responses carrying rate-limit text (#4976) * chore(quality): rebaseline accountFallback.ts file-size for #4976 fix --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(compression): stop RTK over-truncating file-read tool results (#4559) (#4987) * fix(compression): stop RTK over-truncating file-read tool results (#4559) * chore(quality): trim #4559 comment to keep rtk/index.ts within size cap --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(sse): honor per-account proxies and fingerprint rotation in opencode executor (#4954) (#4989) * fix(sse): honor per-account proxies and fingerprint rotation in opencode executor (#4954) * chore(quality): rebaseline auth.ts file-size for #4954 (+39: synthetic no-auth providerSpecificData hydration of fingerprints/accountProxies; irreducible credential-path wiring, covered by opencode-proxy-rotation-4954.test.ts + 159 auth/noauth regression) --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(sse): soft-penalize exhausted providers in auto-combo scoring (#4540) (#4990) * fix(sse): soft-penalize exhausted providers in auto-combo scoring (#4540) * chore(quality): document STATUS_SOFT_DEPRIORITIZE_FACTOR + rebaseline combo.ts for #4540 --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(dashboard): switch to visible filter after auto-hiding failed models in test-all (#4887) (#4991) * fix(dashboard): switch to visible filter after auto-hiding failed models in OAuth provider test-all (#4887) * test(dashboard): move #4887 test into tests/unit/ui so a CI runner collects it --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(pollinations): only enable jsonMode when JSON output is requested (#3981) (#5009) Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(antigravity): default safetySettings to all-OFF for parity with native Gemini paths (#5003) (#5008) * fix(antigravity): default safetySettings to all-OFF for parity with native Gemini paths (#5003) * docs(changelog): restore #3981 pollinations entry eaten by merge --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(chatgpt-web): map advertised gpt-5.5/5.4-pro/5.2-pro slugs to prevent silent model substitution (#4665) (#5010) * fix(chatgpt-web): map advertised gpt-5.5/5.4-pro/5.2-pro slugs to prevent silent model substitution (#4665) MODEL_MAP was missing the advertised catalog ids gpt-5.5, gpt-5.5-pro, gpt-5.4-pro and gpt-5.2-pro, so MODEL_MAP[model] ?? model sent the dot-form id verbatim to the ChatGPT backend-api, which silently rejected it and served the default Plus model. Map each to its dash-form slug. gpt-4-5 is already dash-form and falls through correctly, so it is intentionally left unmapped. Extends the executor MODEL_MAP test with the four ids and adds a drift guard asserting every advertised dot-form catalog id reaches the backend in dash-form (never verbatim), guarding future catalog<->map drift. file-size: tests/unit/chatgpt-web.test.ts frozen baseline 2809->2855 (+46) for the added test cases and drift-guard test; executor source unchanged in baseline. * docs(changelog): restore #3981/#5003 entries eaten by merge --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * feat(combos): add editable per-combo description field persisted via /api/combos (#5005) (#5011) * feat(combos): add editable per-combo description field persisted via /api/combos (#5005) * docs(changelog): restore #3981/#5003/#4665 entries eaten by merge --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * Fix Ollama Cloud max reasoning effort (#4993) Integrated into release/v3.8.36 * fix(copilot): replace execSync with execFile to prevent command injection (#5024) Integrated into release/v3.8.36 * fix(plugin): auth.json dual-key fallback for auto-prefix migration (#5027) Integrated into release/v3.8.36 * feat(endpoint): per-endpoint custom system prompt injection (#5022) Integrated into release/v3.8.36 * fix(headroom): translate openai-responses input through OpenAI for compression (#5023) Integrated into release/v3.8.36 * docs(changelog): add entries for #4993, #5024, #5027 (release notes credit) * fix(api): stop /api/system/env/repair 500 on packaged install (#5006) (#5028) * fix(api): stop /api/system/env/repair 500 on packaged install — lazy createRequire in sync-env.mjs (#5006) scripts/dev/sync-env.mjs ran createRequire(import.meta.url) at module top-level. When webpack bundles it into the standalone env-repair route, import.meta.url is frozen to the build-machine path (file:///home/runner/...) and createRequire throws during module evaluation, so the whole route module fails to load and every GET returns HTTP 500 — breaking the onboarding wizard on packaged/global installs. - Move createRequire into the guarded better-sqlite3 block (only place that needs it); a bad import.meta.url now returns the safe default. - resolveRootDir() falls back to process.cwd() when fileURLToPath throws. - route.ts passes an explicit rootDir (process.cwd()) so the helper never derives the root from the frozen import.meta.url, matching the .env target used by createEnvBackup(). - Regression guard: assert sync-env.mjs has no top-level createRequire + getEnvSyncPlan(oauth) works with explicit rootDir without throwing. * docs(changelog): restore #4993/#5023/#5024/#5027 + custom-system-prompt/headroom entries eaten by release merge * chore(quality): rebaseline 3 inherited base-reds from release merge Files NOT touched by this PR — grew on release/v3.8.36 via --admin merges and inherited here through 'git merge origin/release': - open-sse/executors/base.ts 1414->1416 (#4993 Ollama Cloud max-effort) - src/lib/db/settings.ts 1149->1151 (#5023 custom system prompt) - src/app/(dashboard)/.../endpoint/EndpointPageClient.tsx 2570->2612 (custom system prompt UI) * chore(release): finalize v3.8.36 CHANGELOG + docs (2026-06-25) --------- Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> Co-authored-by: KooshaPari <42529354+KooshaPari@users.noreply.github.com> Co-authored-by: Makcim Ivanov <makcimbx@gmail.com> Co-authored-by: Chewji <126886556+Chewji9875@users.noreply.github.com> Co-authored-by: Anton <39598727+NomenAK@users.noreply.github.com> Co-authored-by: Demiurge The Single <megamen932@gmail.com> Co-authored-by: Randi <55005611+rdself@users.noreply.github.com> Co-authored-by: Éder Costa <eder.almeida.costa@gmail.com> Co-authored-by: Jefferson Felizardo <jeffer1312@gmail.com> Co-authored-by: Arthur Bodera <abodera@gmail.com> Co-authored-by: Hamsa_M <116961508+hamsa0x7@users.noreply.github.com> Co-authored-by: Hernan Javier Ardila Sanchez <hjasgr@gmail.com>
476 lines
18 KiB
TypeScript
476 lines
18 KiB
TypeScript
/**
|
|
* Auto-combo scoring, intent extraction, request-tag routing, candidate-pool
|
|
* expansion and the quota-soft execution-candidate registry — extracted from
|
|
* combo.ts (Quality Gate v2 / Fase 9, combo split D8 — reduced).
|
|
*
|
|
* Logic is unchanged (byte-identical move); the moved public symbols
|
|
* (QUOTA_SOFT_DEPRIORITIZE_FACTOR, setCandidateQuotaSoftPenalty, scoreAutoTargets,
|
|
* expandAutoComboCandidatePool) are re-exported from combo.ts for backward
|
|
* compatibility — including chatCore.ts's dynamic `import("../services/combo")`
|
|
* which reads setCandidateQuotaSoftPenalty + QUOTA_SOFT_DEPRIORITIZE_FACTOR.
|
|
*
|
|
* The _activeExecutionCandidates registry Map MUST stay a single instance, so it
|
|
* and its three mutators live together here.
|
|
*
|
|
* NOTE: buildAutoCandidates (and its two private-only helpers
|
|
* calculateTargetContextAffinity / getBootstrapLatencyMs) deliberately stay in
|
|
* combo.ts — it is the sole user of the internal reset-window helpers
|
|
* (resolveResetWindowConfig / fetchResetAwareQuotaWithCache /
|
|
* calculateResetWindowAffinity), so keeping it there avoids a combo ⇄ autoStrategy
|
|
* import cycle. This module never imports from the combo barrel.
|
|
*/
|
|
|
|
import { isRecord } from "./comboData.ts";
|
|
import type { AutoProviderCandidate, ComboLike, ResolvedComboTarget } from "./types.ts";
|
|
import { extractSessionAffinityKey } from "@/sse/services/auth";
|
|
import { DEFAULT_INTENT_CONFIG, type IntentClassifierConfig } from "../intentClassifier.ts";
|
|
import { getTaskFitness } from "../autoCombo/taskFitness.ts";
|
|
import {
|
|
calculateFactors,
|
|
calculateScore,
|
|
type ProviderCandidate,
|
|
type ScoringWeights,
|
|
} from "../autoCombo/scoring.ts";
|
|
import type { RoutingHint } from "../manifestAdapter";
|
|
import { getProviderConnections } from "../../../src/lib/db/providers";
|
|
import { getProviderModels } from "../../config/providerModels.ts";
|
|
import {
|
|
getConnectionRoutingTags,
|
|
matchesRoutingTags,
|
|
resolveRequestRoutingTags,
|
|
} from "../../../src/domain/tagRouter.ts";
|
|
|
|
// Quota Share soft-policy deprioritization factor (B17).
|
|
// When a candidate has quotaSoftPenalty === true, its auto-combo score is
|
|
// multiplied by this factor so over-quota-soft keys are de-prioritized
|
|
// without being fully blocked (that is done by "hard" policy).
|
|
// Override via QUOTA_SOFT_DEPRIORITIZE_FACTOR env var (range 0..1, default 0.7).
|
|
export const QUOTA_SOFT_DEPRIORITIZE_FACTOR = Number(
|
|
process.env.QUOTA_SOFT_DEPRIORITIZE_FACTOR ?? "0.7"
|
|
);
|
|
|
|
// #4540: Status soft-deprioritization factor.
|
|
// When the quota-preflight HARD cutoff is OFF (default), a candidate whose connection
|
|
// is in a terminal/transient unavailable status (credits_exhausted / rate_limited /
|
|
// banned / expired / future-dated unavailable) is NOT hard-blocked — instead its
|
|
// auto-combo score is multiplied by this factor so an exhausted provider ranks strictly
|
|
// below an otherwise-identical healthy one, without surfacing a misleading 429.
|
|
// Override via STATUS_SOFT_DEPRIORITIZE_FACTOR env var (range 0..1, default 0.5).
|
|
export const STATUS_SOFT_DEPRIORITIZE_FACTOR = Number(
|
|
process.env.STATUS_SOFT_DEPRIORITIZE_FACTOR ?? "0.5"
|
|
);
|
|
|
|
// G2: Module-level registry of active combo execution candidates.
|
|
// Maps executionKey → Map<stepId, candidate mutable ref>.
|
|
// Populated by buildAutoCandidates registrations; cleaned up after each execution.
|
|
// This allows chatCore.ts to mark a candidate's quotaSoftPenalty flag so that
|
|
// subsequent scoring iterations (auto-combo fallback) deprioritize it.
|
|
const _activeExecutionCandidates = new Map<string, Map<string, { quotaSoftPenalty?: boolean }>>();
|
|
|
|
/**
|
|
* Mark a specific candidate (by comboExecutionKey + stepId) with soft quota penalty.
|
|
* Called from chatCore.ts when enforceQuotaShare returns a "soft deprioritize" decision.
|
|
* The flag is read on subsequent auto-combo scoring iterations (fallback chain)
|
|
* within the same combo execution via scoreAutoTargets → QUOTA_SOFT_DEPRIORITIZE_FACTOR.
|
|
*
|
|
* Guards:
|
|
* - null executionKey or stepId → no-op (non-combo or context not available).
|
|
* - unknown executionKey → no-op (candidate not yet registered or already cleaned up).
|
|
* - Idempotent: calling twice with the same (key, stepId, true) is safe.
|
|
*/
|
|
export function setCandidateQuotaSoftPenalty(
|
|
comboExecutionKey: string | null,
|
|
comboStepId: string | null,
|
|
penalty: boolean
|
|
): void {
|
|
if (!comboExecutionKey || !comboStepId) return;
|
|
const byStep = _activeExecutionCandidates.get(comboExecutionKey);
|
|
if (!byStep) return;
|
|
const candidate = byStep.get(comboStepId);
|
|
if (candidate) {
|
|
candidate.quotaSoftPenalty = penalty;
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Register candidates for a combo execution so setCandidateQuotaSoftPenalty can
|
|
* locate them by (executionKey, stepId).
|
|
* Each candidate object is stored by reference — mutations via setCandidateQuotaSoftPenalty
|
|
* propagate back to the original candidate array used by scoreAutoTargets.
|
|
* @internal — not exported; only called within combo.ts by buildAutoCandidates callers.
|
|
*/
|
|
export function _registerExecutionCandidates(
|
|
candidates: Array<{ executionKey: string; stepId: string; quotaSoftPenalty?: boolean }>
|
|
): void {
|
|
for (const candidate of candidates) {
|
|
if (!candidate.executionKey) continue;
|
|
let byStep = _activeExecutionCandidates.get(candidate.executionKey);
|
|
if (!byStep) {
|
|
byStep = new Map();
|
|
_activeExecutionCandidates.set(candidate.executionKey, byStep);
|
|
}
|
|
byStep.set(candidate.stepId, candidate);
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Unregister all candidates for a given execution key once the execution completes.
|
|
* Prevents unbounded memory growth.
|
|
* @internal — not exported; called after each handleComboChat iteration.
|
|
*/
|
|
export function _unregisterExecutionCandidates(executionKeys: string[]): void {
|
|
for (const key of executionKeys) {
|
|
_activeExecutionCandidates.delete(key);
|
|
}
|
|
}
|
|
|
|
function toTextContent(content: unknown): string {
|
|
if (typeof content === "string") return content;
|
|
if (!Array.isArray(content)) return "";
|
|
return content
|
|
.map((part) => {
|
|
if (!isRecord(part)) return "";
|
|
if (typeof part.text === "string") return part.text;
|
|
return "";
|
|
})
|
|
.join("\n");
|
|
}
|
|
|
|
export function extractPromptForIntent(body: Record<string, unknown> | null | undefined): string {
|
|
if (!body || typeof body !== "object") return "";
|
|
|
|
const fromMessages = Array.isArray(body.messages)
|
|
? [...body.messages].reverse().find((m) => isRecord(m) && m.role === "user")
|
|
: null;
|
|
if (isRecord(fromMessages)) return toTextContent(fromMessages.content);
|
|
|
|
if (typeof body.input === "string") return body.input;
|
|
if (Array.isArray(body.input)) {
|
|
const text = body.input
|
|
.map((item) => {
|
|
if (!isRecord(item)) return "";
|
|
if (typeof item.content === "string") return item.content;
|
|
if (typeof item.text === "string") return item.text;
|
|
return "";
|
|
})
|
|
.filter(Boolean)
|
|
.join("\n");
|
|
if (text) return text;
|
|
}
|
|
|
|
if (typeof body.prompt === "string") return body.prompt;
|
|
return "";
|
|
}
|
|
|
|
export function mapIntentToTaskType(intent: string): "coding" | "analysis" | "default" {
|
|
switch (intent) {
|
|
case "code":
|
|
return "coding";
|
|
case "reasoning":
|
|
return "analysis";
|
|
case "simple":
|
|
return "default";
|
|
case "medium":
|
|
default:
|
|
return "default";
|
|
}
|
|
}
|
|
|
|
function toStringArray(input: unknown): string[] {
|
|
if (Array.isArray(input)) {
|
|
return input.map((v) => (typeof v === "string" ? v.trim() : "")).filter(Boolean);
|
|
}
|
|
if (typeof input === "string") {
|
|
return input
|
|
.split(",")
|
|
.map((v) => v.trim())
|
|
.filter(Boolean);
|
|
}
|
|
return [];
|
|
}
|
|
|
|
export function getIntentConfig(
|
|
settings: Record<string, unknown> | null | undefined,
|
|
combo: ComboLike
|
|
): IntentClassifierConfig {
|
|
const resolvedSettings = settings || {};
|
|
const comboAutoConfig = combo?.autoConfig || {};
|
|
const comboConfigAuto = isRecord(combo?.config?.auto) ? combo.config.auto : {};
|
|
const comboIntentConfig =
|
|
(isRecord(comboAutoConfig.intentConfig) && comboAutoConfig.intentConfig) ||
|
|
(isRecord(comboConfigAuto.intentConfig) && comboConfigAuto.intentConfig) ||
|
|
(isRecord(combo?.config?.intentConfig) && combo.config.intentConfig) ||
|
|
{};
|
|
|
|
return {
|
|
...DEFAULT_INTENT_CONFIG,
|
|
...comboIntentConfig,
|
|
...(typeof resolvedSettings.intentDetectionEnabled === "boolean"
|
|
? { enabled: resolvedSettings.intentDetectionEnabled }
|
|
: {}),
|
|
...(Number.isFinite(Number(resolvedSettings.intentSimpleMaxWords))
|
|
? { simpleMaxWords: Number(resolvedSettings.intentSimpleMaxWords) }
|
|
: {}),
|
|
...(toStringArray(resolvedSettings.intentExtraCodeKeywords).length > 0
|
|
? { extraCodeKeywords: toStringArray(resolvedSettings.intentExtraCodeKeywords) }
|
|
: {}),
|
|
...(toStringArray(resolvedSettings.intentExtraReasoningKeywords).length > 0
|
|
? { extraReasoningKeywords: toStringArray(resolvedSettings.intentExtraReasoningKeywords) }
|
|
: {}),
|
|
...(toStringArray(resolvedSettings.intentExtraSimpleKeywords).length > 0
|
|
? { extraSimpleKeywords: toStringArray(resolvedSettings.intentExtraSimpleKeywords) }
|
|
: {}),
|
|
};
|
|
}
|
|
|
|
export async function applyRequestTagRouting(
|
|
targets: ResolvedComboTarget[],
|
|
body: Record<string, unknown> | null | undefined,
|
|
log: { info?: (...args: unknown[]) => void; warn?: (...args: unknown[]) => void }
|
|
): Promise<ResolvedComboTarget[]> {
|
|
const { tags, matchMode } = resolveRequestRoutingTags(body);
|
|
if (tags.length === 0 || targets.length === 0) {
|
|
return targets;
|
|
}
|
|
|
|
const providerIds = Array.from(
|
|
new Set(targets.map((target) => target.providerId || target.provider))
|
|
).filter(
|
|
(providerId): providerId is string => typeof providerId === "string" && providerId.length > 0
|
|
);
|
|
const providerConnections = new Map<string, Array<Record<string, unknown>>>();
|
|
|
|
await Promise.all(
|
|
providerIds.map(async (providerId) => {
|
|
try {
|
|
const connections = await getProviderConnections({ provider: providerId, isActive: true });
|
|
providerConnections.set(
|
|
providerId,
|
|
Array.isArray(connections) ? (connections as Array<Record<string, unknown>>) : []
|
|
);
|
|
} catch (error) {
|
|
log.warn?.(
|
|
"COMBO",
|
|
`Tag routing failed to load connections for provider=${providerId}: ${error instanceof Error ? error.message : String(error)}`
|
|
);
|
|
providerConnections.set(providerId, []);
|
|
}
|
|
})
|
|
);
|
|
|
|
const filteredTargets = targets.reduce<ResolvedComboTarget[]>((acc, target) => {
|
|
const providerKey = target.providerId || target.provider;
|
|
const candidateConnections =
|
|
providerConnections.get(providerKey)?.filter((connection) => {
|
|
const connectionId =
|
|
typeof connection.id === "string" && connection.id.trim().length > 0
|
|
? connection.id
|
|
: null;
|
|
if (!connectionId) return false;
|
|
if (target.connectionId) {
|
|
return connectionId === target.connectionId;
|
|
}
|
|
return true;
|
|
}) || [];
|
|
|
|
const matchedConnectionIds = candidateConnections
|
|
.filter((connection) =>
|
|
matchesRoutingTags(
|
|
getConnectionRoutingTags(connection.providerSpecificData),
|
|
tags,
|
|
matchMode
|
|
)
|
|
)
|
|
.map((connection) => connection.id)
|
|
.filter((connectionId): connectionId is string => typeof connectionId === "string");
|
|
|
|
if (matchedConnectionIds.length === 0) {
|
|
return acc;
|
|
}
|
|
|
|
if (target.connectionId) {
|
|
acc.push(target);
|
|
return acc;
|
|
}
|
|
|
|
// #3266: when a step already carries an account allowlist, intersect it with
|
|
// the tag-matched connections (most-restrictive wins). An empty intersection
|
|
// means no connection satisfies both constraints, so the target is dropped —
|
|
// the same outcome the `matchedConnectionIds.length === 0` guard above yields.
|
|
const tagMatched = Array.from(new Set(matchedConnectionIds));
|
|
const stepAllow = Array.isArray(target.allowedConnectionIds)
|
|
? target.allowedConnectionIds.filter(
|
|
(id): id is string => typeof id === "string" && id.length > 0
|
|
)
|
|
: null;
|
|
const effectiveAllow =
|
|
stepAllow && stepAllow.length > 0
|
|
? tagMatched.filter((id) => stepAllow.includes(id))
|
|
: tagMatched;
|
|
|
|
if (effectiveAllow.length === 0) {
|
|
return acc;
|
|
}
|
|
|
|
acc.push({
|
|
...target,
|
|
allowedConnectionIds: effectiveAllow,
|
|
});
|
|
return acc;
|
|
}, []);
|
|
|
|
if (filteredTargets.length === 0) {
|
|
log.info?.(
|
|
"COMBO",
|
|
`Tag routing matched 0/${targets.length} targets for [${tags.join(", ")}] (${matchMode}); falling back to the full target set`
|
|
);
|
|
return targets;
|
|
}
|
|
|
|
log.info?.(
|
|
"COMBO",
|
|
`Tag routing matched ${filteredTargets.length}/${targets.length} targets for [${tags.join(", ")}] (${matchMode})`
|
|
);
|
|
return filteredTargets;
|
|
}
|
|
|
|
export function scoreAutoTargets(
|
|
targets: ResolvedComboTarget[],
|
|
candidates: AutoProviderCandidate[],
|
|
taskType: string | null,
|
|
weights: ScoringWeights,
|
|
manifestHint?: RoutingHint | null
|
|
) {
|
|
const targetByExecutionKey = new Map(targets.map((target) => [target.executionKey, target]));
|
|
const activeCandidates = candidates.filter((candidate) => candidate.quotaCutoffBlocked !== true);
|
|
|
|
return activeCandidates
|
|
.map((candidate) => {
|
|
const baseTarget =
|
|
targetByExecutionKey.get(candidate.executionKey) ||
|
|
targets.find(
|
|
(target) =>
|
|
target.stepId === candidate.stepId ||
|
|
(target.provider === candidate.provider && target.modelStr === candidate.modelStr)
|
|
);
|
|
if (!baseTarget) return null;
|
|
|
|
const target: ResolvedComboTarget = {
|
|
...baseTarget,
|
|
stepId: candidate.stepId,
|
|
executionKey: candidate.executionKey,
|
|
modelStr: candidate.modelStr,
|
|
provider: candidate.provider,
|
|
connectionId: candidate.connectionId ?? baseTarget.connectionId,
|
|
};
|
|
const factors = calculateFactors(
|
|
candidate as ProviderCandidate,
|
|
activeCandidates,
|
|
taskType ?? "general",
|
|
getTaskFitness,
|
|
manifestHint ?? undefined
|
|
);
|
|
let score = calculateScore(factors, weights);
|
|
// B17: Quota Share soft-policy deprioritization
|
|
if ("quotaSoftPenalty" in candidate && candidate.quotaSoftPenalty === true) {
|
|
score *= QUOTA_SOFT_DEPRIORITIZE_FACTOR;
|
|
}
|
|
// #4540: terminal/transient connection status soft penalty (no hard block).
|
|
// A no-fetcher exhausted provider keeps quotaRemaining=100, so without this its
|
|
// score would tie a healthy provider's. The penalty pushes it strictly below.
|
|
if ("statusPenalty" in candidate && candidate.statusPenalty === true) {
|
|
score *= STATUS_SOFT_DEPRIORITIZE_FACTOR;
|
|
}
|
|
return {
|
|
target,
|
|
score,
|
|
};
|
|
})
|
|
.filter((entry): entry is { target: ResolvedComboTarget; score: number } => entry !== null)
|
|
.sort((a, b) => b.score - a.score);
|
|
}
|
|
|
|
/**
|
|
* For an auto-combo WITHOUT an explicit `candidatePool`, broaden the eligible
|
|
* targets to every model of every active provider connection so the router has
|
|
* the full pool to score over. Already-present `modelStr`s are not duplicated.
|
|
*
|
|
* Best-effort: if loading active connections or provider models throws, the
|
|
* explicitly-resolved targets are returned unchanged (the combo still runs).
|
|
* Exported for unit testing. Mutates and returns `eligibleTargets`.
|
|
*/
|
|
export async function expandAutoComboCandidatePool(
|
|
eligibleTargets: ResolvedComboTarget[],
|
|
combo: { autoConfig?: unknown; config?: unknown } | null | undefined
|
|
): Promise<ResolvedComboTarget[]> {
|
|
const localAutoConfig =
|
|
(combo?.autoConfig as Record<string, unknown> | undefined) ||
|
|
(isRecord((combo?.config as Record<string, unknown>)?.auto)
|
|
? ((combo?.config as Record<string, unknown>).auto as Record<string, unknown>)
|
|
: null) ||
|
|
(combo?.config as Record<string, unknown> | undefined) ||
|
|
{};
|
|
|
|
if (Array.isArray(localAutoConfig?.candidatePool) && localAutoConfig.candidatePool.length > 0)
|
|
return eligibleTargets;
|
|
|
|
try {
|
|
const allConnections = await getProviderConnections({ isActive: true });
|
|
const providerIds = [
|
|
...new Set(
|
|
(allConnections as Array<{ provider?: unknown }>)
|
|
.map((c) => c.provider)
|
|
.filter((p): p is string => typeof p === "string" && p.length > 0)
|
|
),
|
|
];
|
|
for (const providerId of providerIds) {
|
|
const providerModels = getProviderModels(providerId);
|
|
for (const model of providerModels) {
|
|
const modelStr = `${providerId}/${model.id}`;
|
|
if (!eligibleTargets.some((t) => t.modelStr === modelStr)) {
|
|
eligibleTargets.push({
|
|
kind: "model",
|
|
stepId: modelStr,
|
|
executionKey: modelStr,
|
|
provider: providerId,
|
|
providerId: providerId,
|
|
modelStr,
|
|
weight: 1,
|
|
connectionId: null,
|
|
label: null,
|
|
});
|
|
}
|
|
}
|
|
}
|
|
} catch {
|
|
// Best-effort candidate expansion only: if loading active connections or
|
|
// provider models fails, fall back to the explicitly-resolved targets
|
|
// rather than aborting the combo. The push above is the only mutation,
|
|
// so a throw leaves eligibleTargets exactly as explicit resolution built it.
|
|
}
|
|
|
|
return eligibleTargets;
|
|
}
|
|
|
|
/**
|
|
* Derive a STABLE per-conversation session key for combo context-cache pinning when
|
|
* the client did not provide an explicit session id (#3825).
|
|
*
|
|
* Most OpenAI-compatible clients send no session id, so the server-side pin added by
|
|
* #3399 (gated on `relayOptions?.sessionId`) never engaged → combos rotated every turn,
|
|
* causing upstream prompt-cache misses, cold high-reasoning starts and intermittent
|
|
* 504s. We reuse `extractSessionAffinityKey(body)` (the same conversation fingerprint
|
|
* used for codex failover affinity), which hashes the first user/system message — stable
|
|
* across turns of the same conversation and identical on turn 2 of a continued chat.
|
|
*
|
|
* Returns null when no stable fingerprint is available (e.g. empty body), in which case
|
|
* the caller falls back to NO pinning — preserving prior behavior rather than guessing.
|
|
*/
|
|
export function deriveComboSessionKey(body: Record<string, unknown>): string | null {
|
|
try {
|
|
return extractSessionAffinityKey(body) ?? null;
|
|
} catch {
|
|
return null;
|
|
}
|
|
}
|