mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-07-26 09:52:11 +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>
493 lines
20 KiB
TypeScript
493 lines
20 KiB
TypeScript
/**
|
|
* Unit tests for the dedicated quota-share strategy (Phase 3 #9).
|
|
*
|
|
* Covers the three mechanisms of the isolated strategy module plus its
|
|
* activation wiring:
|
|
* 1. per-model bucket gating (accountBuckets.isBucketSaturated)
|
|
* 2. DRR (deficit round-robin, quantum proportional to weight)
|
|
* 3. P2C over real in-flight counters (quotaShareInflight)
|
|
* 4. fail-open behavior (no data / all saturated / empty targets)
|
|
* 5. qtSd/ combos are minted with strategy "quota-share"
|
|
*
|
|
* Runner: node:test + assert/strict (NO vitest, NO jest). Clock is injected via
|
|
* the nowMs param on every call — the tested path never reads Date.now().
|
|
*/
|
|
|
|
import { test, describe, beforeEach } from "node:test";
|
|
import assert from "node:assert/strict";
|
|
|
|
import {
|
|
selectQuotaShareTarget,
|
|
_clearDrrStateForTest,
|
|
_getDrrDeficitForTest,
|
|
} from "../../open-sse/services/combo/quotaShareStrategy.ts";
|
|
import {
|
|
incrementInflight,
|
|
decrementInflight,
|
|
getInflight,
|
|
_clearInflightForTest,
|
|
DEFAULT_LEASE_MS,
|
|
} from "../../open-sse/services/combo/quotaShareInflight.ts";
|
|
import { recordUsage, _clearBucketsForTest } from "../../src/lib/quota/accountBuckets.ts";
|
|
import { QUOTA_SHARE_STRATEGY } from "../../src/lib/quota/quotaCombos.ts";
|
|
import { INTERNAL_ROUTING_STRATEGY_VALUES } from "../../src/shared/constants/routingStrategies.ts";
|
|
import type { ResolvedComboTarget } from "../../open-sse/services/combo/types.ts";
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Helpers
|
|
// ---------------------------------------------------------------------------
|
|
|
|
const NOW = Date.UTC(2026, 5, 24, 12, 0, 0); // 2026-06-24T12:00:00.000Z
|
|
const RESET_AT = new Date(NOW + 3_600_000).toISOString(); // +1h (window still open)
|
|
|
|
function makeTarget(
|
|
executionKey: string,
|
|
connectionId: string,
|
|
weight = 100,
|
|
modelStr = "anthropic/claude-sonnet-4-5"
|
|
): ResolvedComboTarget {
|
|
return {
|
|
kind: "model",
|
|
stepId: `step-${executionKey}`,
|
|
executionKey,
|
|
modelStr,
|
|
provider: modelStr.split("/")[0],
|
|
providerId: null,
|
|
connectionId,
|
|
weight,
|
|
label: null,
|
|
};
|
|
}
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Setup — reset all module state before each case for isolation.
|
|
// ---------------------------------------------------------------------------
|
|
|
|
beforeEach(() => {
|
|
_clearBucketsForTest();
|
|
_clearDrrStateForTest();
|
|
_clearInflightForTest();
|
|
});
|
|
|
|
// ─── quotaShareInflight ─────────────────────────────────────────────────────
|
|
|
|
describe("quotaShareInflight", () => {
|
|
test("increment → getInflight returns 1", () => {
|
|
incrementInflight("conn-a", DEFAULT_LEASE_MS, NOW);
|
|
assert.equal(getInflight("conn-a", NOW), 1);
|
|
});
|
|
|
|
test("increment twice → getInflight returns 2", () => {
|
|
incrementInflight("conn-a", DEFAULT_LEASE_MS, NOW);
|
|
incrementInflight("conn-a", DEFAULT_LEASE_MS, NOW);
|
|
assert.equal(getInflight("conn-a", NOW), 2);
|
|
});
|
|
|
|
test("decrement after increment → returns 0", () => {
|
|
incrementInflight("conn-a", DEFAULT_LEASE_MS, NOW);
|
|
decrementInflight("conn-a", NOW);
|
|
assert.equal(getInflight("conn-a", NOW), 0);
|
|
});
|
|
|
|
test("decrement below 0 is safe (floors at 0)", () => {
|
|
decrementInflight("conn-a", NOW); // no prior increment
|
|
assert.equal(getInflight("conn-a", NOW), 0);
|
|
});
|
|
|
|
test("TTL expiry: expired slot returns 0 without an explicit decrement", () => {
|
|
const leaseMs = 1_000;
|
|
incrementInflight("conn-b", leaseMs, NOW);
|
|
assert.equal(getInflight("conn-b", NOW), 1);
|
|
assert.equal(getInflight("conn-b", NOW + leaseMs + 1), 0);
|
|
});
|
|
|
|
test("empty connectionId returns 0 (fail-open)", () => {
|
|
assert.equal(getInflight("", NOW), 0);
|
|
incrementInflight("", DEFAULT_LEASE_MS, NOW); // must not throw / not store
|
|
assert.equal(getInflight("", NOW), 0);
|
|
});
|
|
});
|
|
|
|
// ─── per-model bucket gating ────────────────────────────────────────────────
|
|
|
|
describe("gating: per-model bucket saturation", () => {
|
|
test("saturated 5h window → that connection is deprioritized, the clean one wins", () => {
|
|
recordUsage("conn-sat", "5h", 100, RESET_AT, NOW);
|
|
|
|
const targets = [makeTarget("ek-sat", "conn-sat"), makeTarget("ek-ok", "conn-ok")];
|
|
const result = selectQuotaShareTarget(targets, "combo-5h", "anthropic/claude-sonnet-4-5", NOW);
|
|
|
|
assert.ok(result.target !== null, "must return a target");
|
|
assert.equal(result.target.executionKey, "ek-ok", "non-saturated target must be selected");
|
|
// Saturated target stays available as a fallback (deprioritized, not dropped).
|
|
assert.ok(
|
|
result.orderedTargets.some((t) => t.executionKey === "ek-sat"),
|
|
"saturated target must still appear in the fallback list"
|
|
);
|
|
});
|
|
|
|
test("saturated 7d window → that connection is deprioritized", () => {
|
|
recordUsage("conn-7d", "7d", 100, RESET_AT, NOW);
|
|
const targets = [makeTarget("ek-7d", "conn-7d"), makeTarget("ek-clean", "conn-clean")];
|
|
|
|
const result = selectQuotaShareTarget(targets, "combo-7d", "anthropic/claude-sonnet-4-5", NOW);
|
|
assert.equal(result.target?.executionKey, "ek-clean");
|
|
});
|
|
|
|
test("saturated per-model 7d window for the requested model → deprioritized", () => {
|
|
recordUsage("conn-pm", "7d:claude-sonnet-4-5", 100, RESET_AT, NOW);
|
|
const targets = [
|
|
makeTarget("ek-pm", "conn-pm", 100, "anthropic/claude-sonnet-4-5"),
|
|
makeTarget("ek-other", "conn-other", 100, "anthropic/claude-sonnet-4-5"),
|
|
];
|
|
|
|
const result = selectQuotaShareTarget(targets, "combo-pm", "anthropic/claude-sonnet-4-5", NOW);
|
|
assert.equal(result.target?.executionKey, "ek-other");
|
|
});
|
|
|
|
test("per-model saturation for a DIFFERENT model does NOT deprioritize", () => {
|
|
// conn-x is saturated only on 7d:claude-opus-4, but the request is for sonnet.
|
|
recordUsage("conn-x", "7d:claude-opus-4", 100, RESET_AT, NOW);
|
|
const targets = [makeTarget("ek-x", "conn-x", 100, "anthropic/claude-sonnet-4-5")];
|
|
|
|
const result = selectQuotaShareTarget(
|
|
targets,
|
|
"combo-other-model",
|
|
"anthropic/claude-sonnet-4-5",
|
|
NOW
|
|
);
|
|
assert.equal(
|
|
result.target?.executionKey,
|
|
"ek-x",
|
|
"must not be gated by an unrelated model window"
|
|
);
|
|
});
|
|
|
|
test("fail-open: all targets saturated → all eligible again, still returns a target", () => {
|
|
recordUsage("conn-1", "5h", 100, RESET_AT, NOW);
|
|
recordUsage("conn-2", "5h", 100, RESET_AT, NOW);
|
|
const targets = [makeTarget("ek-1", "conn-1"), makeTarget("ek-2", "conn-2")];
|
|
|
|
const result = selectQuotaShareTarget(targets, "combo-fo", "anthropic/claude-sonnet-4-5", NOW);
|
|
assert.ok(result.target !== null, "must not return null when everything is saturated");
|
|
assert.equal(result.orderedTargets.length, 2, "both targets remain dispatchable");
|
|
});
|
|
|
|
test("empty targets → returns null (fail-open, no crash)", () => {
|
|
const result = selectQuotaShareTarget([], "combo-empty", "anthropic/claude-sonnet-4-5", NOW);
|
|
assert.equal(result.target, null);
|
|
assert.deepEqual(result.orderedTargets, []);
|
|
});
|
|
|
|
test("no buckets recorded at all → fail-open, first/healthy target selected", () => {
|
|
const targets = [makeTarget("ek-a", "conn-a"), makeTarget("ek-b", "conn-b")];
|
|
const result = selectQuotaShareTarget(
|
|
targets,
|
|
"combo-nodata",
|
|
"anthropic/claude-sonnet-4-5",
|
|
NOW
|
|
);
|
|
assert.ok(result.target !== null);
|
|
assert.equal(result.orderedTargets.length, 2);
|
|
});
|
|
});
|
|
|
|
// ─── DRR ─────────────────────────────────────────────────────────────────────
|
|
|
|
describe("DRR: deficit round robin", () => {
|
|
test("equal weight: two connections alternate across consecutive calls", () => {
|
|
const t1 = makeTarget("ek-1", "conn-1", 100);
|
|
const t2 = makeTarget("ek-2", "conn-2", 100);
|
|
|
|
const r1 = selectQuotaShareTarget([t1, t2], "combo-drr", "anthropic/claude-sonnet-4-5", NOW);
|
|
const r2 = selectQuotaShareTarget([t1, t2], "combo-drr", "anthropic/claude-sonnet-4-5", NOW);
|
|
|
|
const selected = [r1.target?.executionKey, r2.target?.executionKey];
|
|
assert.ok(selected.includes("ek-1"), "ek-1 must be selected at some point");
|
|
assert.ok(selected.includes("ek-2"), "ek-2 must be selected at some point");
|
|
});
|
|
|
|
test("higher weight connection receives proportionally more selections (2:1)", () => {
|
|
const t1 = makeTarget("ek-heavy", "conn-heavy", 200); // 2x weight
|
|
const t2 = makeTarget("ek-light", "conn-light", 100); // 1x weight
|
|
|
|
const counts: Record<string, number> = { "ek-heavy": 0, "ek-light": 0 };
|
|
for (let i = 0; i < 30; i++) {
|
|
const r = selectQuotaShareTarget(
|
|
[t1, t2],
|
|
"combo-weighted",
|
|
"anthropic/claude-sonnet-4-5",
|
|
NOW
|
|
);
|
|
if (r.target) counts[r.target.executionKey]++;
|
|
// Simulate the request settling (as a real caller's finally handler would),
|
|
// so the P2C in-flight tie-break sees equal load and the DRR weighting shows.
|
|
r.decrementInflight();
|
|
}
|
|
assert.ok(
|
|
counts["ek-heavy"] > counts["ek-light"],
|
|
`heavy (${counts["ek-heavy"]}) should be selected more than light (${counts["ek-light"]})`
|
|
);
|
|
// Roughly 2:1 — heavy should be at least ~1.5x light over 30 rounds.
|
|
assert.ok(
|
|
counts["ek-heavy"] >= counts["ek-light"] * 1.5,
|
|
`heavy/light ratio should be ~2:1, got ${counts["ek-heavy"]}:${counts["ek-light"]}`
|
|
);
|
|
});
|
|
|
|
test("DRR state is isolated per comboName", () => {
|
|
const t = makeTarget("ek-shared", "conn-shared", 100);
|
|
selectQuotaShareTarget([t], "combo-A", "anthropic/claude-sonnet-4-5", NOW);
|
|
|
|
const deficitA = _getDrrDeficitForTest("combo-A", "ek-shared");
|
|
const deficitB = _getDrrDeficitForTest("combo-B", "ek-shared");
|
|
assert.equal(deficitB, 0, "combo-B deficit must remain 0 (isolated)");
|
|
assert.equal(deficitA, 0, "the selected target's deficit must be reset to 0");
|
|
});
|
|
|
|
test("single eligible target is returned unchanged", () => {
|
|
const t = makeTarget("ek-solo", "conn-solo", 100);
|
|
const result = selectQuotaShareTarget([t], "combo-solo", "anthropic/claude-sonnet-4-5", NOW);
|
|
assert.equal(result.target?.executionKey, "ek-solo");
|
|
assert.equal(result.orderedTargets.length, 1);
|
|
});
|
|
});
|
|
|
|
// ─── P2C in-flight ────────────────────────────────────────────────────────────
|
|
|
|
describe("P2C in-flight", () => {
|
|
test("between two candidates, the one with fewer in-flight wins over the DRR pick", () => {
|
|
const t1 = makeTarget("ek-busy", "conn-busy", 100);
|
|
const t2 = makeTarget("ek-free", "conn-free", 100);
|
|
|
|
// Pre-load conn-busy with active in-flight requests.
|
|
incrementInflight("conn-busy", DEFAULT_LEASE_MS, NOW);
|
|
incrementInflight("conn-busy", DEFAULT_LEASE_MS, NOW);
|
|
|
|
const result = selectQuotaShareTarget(
|
|
[t1, t2],
|
|
"combo-p2c",
|
|
"anthropic/claude-sonnet-4-5",
|
|
NOW
|
|
);
|
|
assert.equal(
|
|
result.target?.executionKey,
|
|
"ek-free",
|
|
"the target with the lower in-flight load must win the P2C tie-break"
|
|
);
|
|
});
|
|
|
|
test("decrementInflight() releases the in-flight load", () => {
|
|
const t = makeTarget("ek-dec", "conn-dec", 100);
|
|
const result = selectQuotaShareTarget([t], "combo-dec", "anthropic/claude-sonnet-4-5", NOW);
|
|
assert.equal(getInflight("conn-dec", NOW), 1, "in-flight should be 1 after a dispatch");
|
|
result.decrementInflight();
|
|
assert.equal(getInflight("conn-dec", NOW), 0, "in-flight should be 0 after the decrement");
|
|
});
|
|
|
|
test("decrementInflight() is idempotent (safe to call more than once)", () => {
|
|
const t = makeTarget("ek-idem", "conn-idem", 100);
|
|
const result = selectQuotaShareTarget([t], "combo-idem", "anthropic/claude-sonnet-4-5", NOW);
|
|
result.decrementInflight();
|
|
result.decrementInflight(); // must not go negative or throw
|
|
assert.equal(getInflight("conn-idem", NOW), 0);
|
|
});
|
|
|
|
test("TTL releases in-flight automatically when decrement is never called (abort fallback)", () => {
|
|
const t = makeTarget("ek-ttl", "conn-ttl", 100);
|
|
const result = selectQuotaShareTarget([t], "combo-ttl", "anthropic/claude-sonnet-4-5", NOW);
|
|
// Simulate an aborted request: do NOT call result.decrementInflight().
|
|
assert.equal(getInflight("conn-ttl", NOW), 1);
|
|
assert.equal(
|
|
getInflight("conn-ttl", NOW + DEFAULT_LEASE_MS + 1),
|
|
0,
|
|
"the slot must auto-expire after the lease, preventing a permanent leak"
|
|
);
|
|
// The returned callback must remain referenced to satisfy the contract.
|
|
assert.equal(typeof result.decrementInflight, "function");
|
|
});
|
|
});
|
|
|
|
// ─── gating: per-connection concurrency cap (maxConcurrent) ─────────────────
|
|
|
|
describe("gating: per-connection maxConcurrent", () => {
|
|
// DISCRIMINATING scenario: the at-cap connection has the LOWEST absolute
|
|
// in-flight load, so without concurrency gating the existing P2C tie-break
|
|
// would pick it. Only a real per-connection cap gate demotes it. This is what
|
|
// separates "gating works" from "P2C already happened to pick the free one".
|
|
test("at-cap connection with the LOWEST absolute load is still demoted (P2C alone would pick it)", () => {
|
|
// conn-tight: cap=1, in-flight=1 → AT cap, but lowest absolute load.
|
|
// conn-roomy: cap=10, in-flight=3 → below cap, but higher absolute load.
|
|
incrementInflight("conn-tight", DEFAULT_LEASE_MS, NOW);
|
|
incrementInflight("conn-roomy", DEFAULT_LEASE_MS, NOW);
|
|
incrementInflight("conn-roomy", DEFAULT_LEASE_MS, NOW);
|
|
incrementInflight("conn-roomy", DEFAULT_LEASE_MS, NOW);
|
|
|
|
const targets = [
|
|
makeTarget("ek-tight", "conn-tight", 100),
|
|
makeTarget("ek-roomy", "conn-roomy", 100),
|
|
];
|
|
const maxConcurrentByConnection = new Map<string, number | null>([
|
|
["conn-tight", 1],
|
|
["conn-roomy", 10],
|
|
]);
|
|
|
|
const gated = selectQuotaShareTarget(
|
|
targets,
|
|
"combo-cap-lowest",
|
|
"anthropic/claude-sonnet-4-5",
|
|
NOW,
|
|
{ maxConcurrentByConnection }
|
|
);
|
|
assert.equal(
|
|
gated.target?.executionKey,
|
|
"ek-roomy",
|
|
"the below-cap connection must win even though it has MORE absolute in-flight load"
|
|
);
|
|
// The at-cap connection is NOT dropped — it stays as a last-resort fallback.
|
|
assert.ok(
|
|
gated.orderedTargets.some((t) => t.executionKey === "ek-tight"),
|
|
"the capped connection must still appear in the fallback list (never hard-blocked)"
|
|
);
|
|
});
|
|
|
|
test("a connection BELOW its maxConcurrent is NOT deprioritized", () => {
|
|
// conn-a has maxConcurrent=3 and only 1 in-flight → still has room, fully eligible.
|
|
incrementInflight("conn-a", DEFAULT_LEASE_MS, NOW);
|
|
const targets = [makeTarget("ek-a", "conn-a")];
|
|
const maxConcurrentByConnection = new Map<string, number | null>([["conn-a", 3]]);
|
|
|
|
const result = selectQuotaShareTarget(
|
|
targets,
|
|
"combo-below",
|
|
"anthropic/claude-sonnet-4-5",
|
|
NOW,
|
|
{ maxConcurrentByConnection }
|
|
);
|
|
assert.equal(result.target?.executionKey, "ek-a", "below-cap connection must remain selected");
|
|
});
|
|
|
|
test("fail-open: ALL connections at their cap → all stay eligible, still returns a target", () => {
|
|
incrementInflight("conn-1", DEFAULT_LEASE_MS, NOW);
|
|
incrementInflight("conn-2", DEFAULT_LEASE_MS, NOW);
|
|
const targets = [makeTarget("ek-1", "conn-1"), makeTarget("ek-2", "conn-2")];
|
|
const maxConcurrentByConnection = new Map<string, number | null>([
|
|
["conn-1", 1],
|
|
["conn-2", 1],
|
|
]);
|
|
|
|
const result = selectQuotaShareTarget(
|
|
targets,
|
|
"combo-allcap",
|
|
"anthropic/claude-sonnet-4-5",
|
|
NOW,
|
|
{ maxConcurrentByConnection }
|
|
);
|
|
assert.ok(result.target !== null, "must never hard-block: a target is still returned");
|
|
assert.equal(result.orderedTargets.length, 2, "both targets remain dispatchable");
|
|
});
|
|
|
|
// DISCRIMINATING: the only candidate is at its cap with HIGH load while
|
|
// another candidate is under-cap with LOWER load — so this overlaps with P2C.
|
|
// Here we force the opposite: the under-cap winner has HIGHER absolute load so
|
|
// P2C alone would NOT pick it; the gate must.
|
|
test("at-cap target with high weight is demoted below an under-cap, higher-load target", () => {
|
|
// conn-cap: cap=2, in-flight=2 → AT cap. weight 900 (DRR would crown it).
|
|
// conn-free: cap=50, in-flight=5 → below cap, but MORE absolute load than cap.
|
|
incrementInflight("conn-cap", DEFAULT_LEASE_MS, NOW);
|
|
incrementInflight("conn-cap", DEFAULT_LEASE_MS, NOW);
|
|
for (let i = 0; i < 5; i++) incrementInflight("conn-free", DEFAULT_LEASE_MS, NOW);
|
|
|
|
const targets = [makeTarget("ek-cap", "conn-cap", 900), makeTarget("ek-free", "conn-free", 1)];
|
|
const maxConcurrentByConnection = new Map<string, number | null>([
|
|
["conn-cap", 2],
|
|
["conn-free", 50],
|
|
]);
|
|
|
|
const result = selectQuotaShareTarget(
|
|
targets,
|
|
"combo-cap-vs-load",
|
|
"anthropic/claude-sonnet-4-5",
|
|
NOW,
|
|
{ maxConcurrentByConnection }
|
|
);
|
|
assert.equal(
|
|
result.target?.executionKey,
|
|
"ek-free",
|
|
"concurrency gating must demote the at-cap target even though it has lower absolute load and higher DRR weight"
|
|
);
|
|
});
|
|
|
|
test("maxConcurrent null / 0 / missing is treated as 'no limit' (never gates)", () => {
|
|
// conn-null is heavily loaded (3 in-flight) but has null cap; conn-light has
|
|
// a positive cap but is well below it. With "null = no limit", conn-null must
|
|
// NOT be gated — so the lower-load conn-light wins purely by P2C, and BOTH
|
|
// remain dispatchable (nothing was demoted to the saturated tail).
|
|
incrementInflight("conn-null", DEFAULT_LEASE_MS, NOW);
|
|
incrementInflight("conn-null", DEFAULT_LEASE_MS, NOW);
|
|
incrementInflight("conn-null", DEFAULT_LEASE_MS, NOW);
|
|
const targets = [makeTarget("ek-null", "conn-null"), makeTarget("ek-light", "conn-light")];
|
|
const maxConcurrentByConnection = new Map<string, number | null>([
|
|
["conn-null", null],
|
|
["conn-light", 10],
|
|
]);
|
|
|
|
const result = selectQuotaShareTarget(
|
|
targets,
|
|
"combo-nolimit",
|
|
"anthropic/claude-sonnet-4-5",
|
|
NOW,
|
|
{ maxConcurrentByConnection }
|
|
);
|
|
assert.ok(result.target !== null);
|
|
assert.equal(result.orderedTargets.length, 2, "no connection gated when cap is null");
|
|
|
|
// And a 0 cap must behave identically to null (no gating): a single 0-cap
|
|
// connection at high load must still be selectable.
|
|
incrementInflight("conn-zero", DEFAULT_LEASE_MS, NOW);
|
|
incrementInflight("conn-zero", DEFAULT_LEASE_MS, NOW);
|
|
const zeroResult = selectQuotaShareTarget(
|
|
[makeTarget("ek-zero", "conn-zero")],
|
|
"combo-zero",
|
|
"anthropic/claude-sonnet-4-5",
|
|
NOW,
|
|
{ maxConcurrentByConnection: new Map<string, number | null>([["conn-zero", 0]]) }
|
|
);
|
|
assert.equal(zeroResult.target?.executionKey, "ek-zero", "0 cap means no limit, not block");
|
|
});
|
|
|
|
test("no options passed → behaves exactly as before (backward compatible)", () => {
|
|
// Heavily loaded connection but no maxConcurrent info at all → no gating.
|
|
incrementInflight("conn-x", DEFAULT_LEASE_MS, NOW);
|
|
incrementInflight("conn-x", DEFAULT_LEASE_MS, NOW);
|
|
const targets = [makeTarget("ek-x", "conn-x")];
|
|
const result = selectQuotaShareTarget(
|
|
targets,
|
|
"combo-compat",
|
|
"anthropic/claude-sonnet-4-5",
|
|
NOW
|
|
);
|
|
assert.equal(result.target?.executionKey, "ek-x");
|
|
assert.equal(result.orderedTargets.length, 1);
|
|
});
|
|
});
|
|
|
|
// ─── activation wiring ──────────────────────────────────────────────────────
|
|
|
|
describe("activation: qtSd/ combos use strategy 'quota-share'", () => {
|
|
test("QUOTA_SHARE_STRATEGY constant equals 'quota-share'", () => {
|
|
assert.equal(
|
|
QUOTA_SHARE_STRATEGY,
|
|
"quota-share",
|
|
"quotaCombos must mint qtSd/ combos with the 'quota-share' strategy"
|
|
);
|
|
});
|
|
|
|
test("'quota-share' is registered as an INTERNAL routing strategy", () => {
|
|
assert.ok(
|
|
(INTERNAL_ROUTING_STRATEGY_VALUES as readonly string[]).includes("quota-share"),
|
|
"'quota-share' must be in the internal (non-UI) routing strategy list"
|
|
);
|
|
});
|
|
});
|