Files
OmniRoute/docs/openapi.yaml
Diego Rodrigues de Sa e Souza a7ae9550bd Release v3.8.36 (#4854)
* chore(release): open v3.8.36 development cycle

* refactor(chatCore): extrai resolveCompressionSettings (#3501) (#4826)

Integrated into release/v3.8.36 (#3501 chatCore extraction stack 1/13)

* refactor(chatCore): extrai predicados puros de combo de compressão (#3501) (#4824)

Integrated into release/v3.8.36 (#3501 chatCore extraction stack 2/13)

* refactor(chatCore): extrai emitOutputStyleTelemetry (#3501) (#4811)

Integrated into release/v3.8.36 (#3501 chatCore extraction stack 3/13)

* refactor(chatCore): extrai writeCompressionAnalytics (bloco analytics completo, #3501) (#4817)

Integrated into release/v3.8.36 (#3501 chatCore extraction stack 4/13)

* refactor(chatCore): extrai runPluginOnRequestHook (#3501) (#4827)

Integrated into release/v3.8.36 (#3501 chatCore extraction stack 5/13)

* refactor(chatCore): extrai applyClientUsageBuffer (buffer/estimate de usage non-streaming, #3501) (#4832)

Integrated into release/v3.8.36 (#3501 chatCore extraction stack 6/13)

* refactor(chatCore): extrai buildPostCallGuardrailContext (contexto guardrail post-call, #3501) (#4831)

Integrated into release/v3.8.36 (#3501 chatCore extraction stack 7/13)

* refactor(chatCore): extrai storeSemanticCacheResponse (cache-store non-streaming, #3501) (#4828)

Integrated into release/v3.8.36 (#3501 chatCore extraction stack 8/13)

* refactor(chatCore): extrai buildNonStreamingResponseHeaders (headers de resposta non-streaming, #3501) (#4835)

Integrated into release/v3.8.36 (#3501 chatCore extraction stack 9/13)

* refactor(chatCore): extrai maybeConvertJsonBodyToSse (#3089 JSON→SSE streaming, #3501) (#4833)

Integrated into release/v3.8.36 (#3501 chatCore extraction stack 10/13)

* refactor(chatCore): extrai assembleStreamingResponseHeaders (headers de resposta streaming, #3501) (#4836)

Integrated into release/v3.8.36 (#3501 chatCore extraction stack 11/13)

* refactor(chatCore): extrai storeStreamingSemanticCacheResponse (cache-store streaming, #3501) (#4829)

Integrated into release/v3.8.36 (#3501 chatCore extraction stack 12/13)

* refactor(chatCore): extrai assembleStreamingPipeline (chain de transforms streaming, #3501) (#4837)

Integrated into release/v3.8.36 (#3501 chatCore extraction stack 13/13)

* ci(quality): shift heavy validations to the PR→release fast-path (release-acceleration) (#4857)

* feat(quality): add check:test-runner-api gate (vitest-only dirs must use vitest API)

* feat(release): reusable CHANGELOG i18n-mirror sync script

* chore(ops): add prune-stale-worktrees.sh (dry-run by default)

* ci(quality): run test-runner-api + docs-all + vitest + full unit suite on PR->release fast-path

---------

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* fix(quota): cota exclusiva lista qtSd/ no /v1/models (#4806) + limite EPSILON não bloqueia (#4830)

Integrated into release/v3.8.36 — quota-exclusive qtSd/ listing (#4806) + EPSILON placeholder no longer blocks; rebuilt from stale base (3 defining commits cherry-picked clean over release tip)

* feat(sse): add Google Flow video-generation provider (#4569) (#4769)

Integrated into release/v3.8.36 — Google Flow video-generation provider (#4569), release-green validated (typecheck + 21 tests + file-size)

* fix(api): auth on compression run-telemetry + document OMNIROUTE_EVAL_CREDENTIALS (#4694, #4720) (#4796)

Integrated into release/v3.8.36 — auth on compression run-telemetry + OMNIROUTE_EVAL_CREDENTIALS doc, release-green validated (typecheck + 3 tests + env-doc-sync)

* fix(translator): strip top-level client_metadata on the OpenAI passthrough (port from 9router#1157) (#4624)

Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated)

* fix(translator): normalize `developer` role to `system` for OpenAI-format providers (#4625)

Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated)

* fix(translator): emit </think> close marker for Anthropic thinking blocks (#4633)

Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated)

* fix(translator): normalize tools to Anthropic-native shape for non-Anthropic providers (#4650)

Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated)

* fix(gemini): preserve `pattern` in antigravity tool schema sanitizer (#4651)

Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated)

* fix(perplexity): validate API keys via /v1/models endpoint (#4654)

Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated)

* fix(image): prevent compatible nodes from shadowing provider aliases (#4656)

Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated)

* fix(cli-tools): tolerate JSONC (comments, trailing commas) in tool settings (#4659)

Integrated into release/v3.8.36 — port (rebuilt from stale base; defining commit cherry-picked clean over release tip, release-green validated)

* fix(security): validate kiro region to prevent SSRF (GHSA-6mwv-4mrm-5p3m) (#4629)

Integrated into release/v3.8.36 — kiro region SSRF guard (GHSA-6mwv-4mrm-5p3m), port rebuilt clean over release tip

* fix(cli): harden the systray2 tray runtime (port of 9router#1080) (#4628)

Integrated into release/v3.8.36 — port rebuilt clean over release tip, release-green validated

* fix(test): validate anthropic-compatible connections via POST /v1/messages (#4657)

Integrated into release/v3.8.36 — anthropic-compat validation via POST /v1/messages (port 584cf66a), rebuilt clean + baseline; release-green

* fix(executors): strip params unsupported by the target provider/model (#4658)

Integrated into release/v3.8.36 — port rebuilt clean over release tip, release-green validated

* fix(claude-oauth): respect 429 backoff on usage endpoint to reduce spam (#4655)

Integrated into release/v3.8.36 — port rebuilt clean over release tip, release-green validated

* feat(api/v1): include alias-backed models in /v1/models listing (#4630)

Integrated into release/v3.8.36 — port rebuilt clean over release tip, release-green validated

* chore(quality): rebaseline catalog.ts 1574->1577 (#4630 aliases sobre quota-exclusive da release) (#4879)

rebaseline

* feat(compression): Kiro/CodeWhisperer tool-result compression engine (#4635)

Integrated into release/v3.8.36 — port rebuilt clean, release-green

* fix(security): don't trust loopback socket as local when behind reverse proxy (#4632)

Integrated into release/v3.8.36 — port rebuilt clean, release-green

* fix(opencode): preserve DeepSeek reasoning content in streamed responses (#4631)

Integrated into release/v3.8.36 — DeepSeek reasoning_content injection (port #1099); release-green

* fix(copilot,antigravity): cap maxOutputTokens at 16384 to stop "Invalid Argument" 400 (#4636)

Integrated into release/v3.8.36 — cap maxOutputTokens 16384 antigravity (port #779); release-green

* fix(dashboard): show custom vision models in LLM selector (#4653)

Integrated into release/v3.8.36 — custom vision models in LLM selector (port 5e5e78d3); release-green

* fix(claude): omit adaptive thinking + output_config.effort for haiku (#4661)

Integrated into release/v3.8.36 — haiku adaptive-thinking omit (port); release-green

* feat(provider): CodeBuddy CN (copilot.tencent.com) — full stack (#4664)

Integrated into release/v3.8.36 — CodeBuddy CN provider (port efd20be8); usage.ts import + public-creds allowlist line reconciled; release-green

* feat(combo): Fusion strategy — parallel panel + judge synthesis (16th strategy) (#4652)

Integrated into release/v3.8.36 — Fusion combo strategy (16th, port 87e5c1c6); combo.ts baseline reconciled; release-green

* feat(proxy-pool): Deno Deploy relays + group action buttons (#4643)

Integrated into release/v3.8.36 — Deno Deploy relays (port #1437); proxies.ts baseline reconciled + env docs restored; release-green

* fix(security): pin image fetch DNS resolution to prevent SSRF rebinding (GHSA-cmhj-wh2f-9cgx) (#4634)

Integrated into release/v3.8.36 — pin DNS for image fetch SSRF rebinding guard (GHSA-cmhj-wh2f-9cgx, port c7d07448); caller DNS stubs + test-file baseline reconciled; release-green

* fix(github): route Copilot Codex models to /responses (port from 9router#102) (#4626)

Integrated into release/v3.8.36 — route Copilot Codex models to /responses (port #102); release-green

* fix(copilot): never route Gemini/Claude variants to /responses (chat-completions only) (#4627)

Integrated into release/v3.8.36 — never route Gemini/Claude to /responses (port #1536); fused with #4626 codex routing via supportsResponsesEndpoint gate; release-green

* docs(ops): add canonical incident response runbook (#4868)

Integrated into release/v3.8.36

* docs(perf): add per-endpoint p50/p95/p99 latency + cost budgets (#4867)

Integrated into release/v3.8.36

* fix(proxy): fan out direct dispatcher streams (#4803)

Integrated into release/v3.8.36

* fix(antigravity): exclude standard Gemini rate limit message from quota exhaustion keywords (#4810)

Integrated into release/v3.8.36

* fix(sse): skip third-party tool-name cloak for Anthropic server tools (#4808)

Integrated into release/v3.8.36

* fix(install): make transformers optional for CUDA-host installs (#4807)

Integrated into release/v3.8.36

* fix(combo): propagate selected connection ID to fallback error responses for correct model lockout (#4809)

Integrated into release/v3.8.36

* fix db storage tuning settings (#4834)

Integrated into release/v3.8.36

* fix(sse): drop ccp pin when pinned provider is durably unhealthy (failover + anti-flap) (#4864)

Integrated into release/v3.8.36

* fix(claude): skip mcp__ tool-name cloak + guard missing connectionId (#4861)

Integrated into release/v3.8.36

* chore(quality): reconcile env-doc + file-size base-reds in release/v3.8.36 (#4886)

- env-doc-sync: document PIN_DROP_BACKOFF_LEVEL / PIN_DROP_GRACE_MS (added by the
  ccp-pin health gate #4864) in .env.example + ENVIRONMENT.md.
- file-size: rebaseline image-generation-handler.test.ts 1996 -> 2019 to its actual
  size (pre-existing drift).

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* fix(codex): drop non-standard codex.* events that break responses.stream (env-gated, #4602) (#4715)

Integrated into release/v3.8.36

* feat(routing): honor X-Route-Model header to override body.model (#4863)

Integrated into release/v3.8.36

* feat(live-ws): allow non-loopback clients via LIVE_WS_ALLOWED_HOSTS (closes #4873) (#4877)

Integrated into release/v3.8.36 (live-ws + combo-api commits; Tailscale CGNAT commit held pending opt-in/opt-out decision)

* chore(claude,codex): bump pinned CLI identity — Claude 2.1.158→2.1.187, Codex 0.132.0→0.142.0 (#4883)

Integrated into release/v3.8.36

* fix(security): SSRF allowlist bypass via x-relay-path nos relays Deno/Vercel (#4899)

Integrated into release/v3.8.36

* feat(quota): recuperação proativa de conexões em cooldown (cron heal) [Fase 3 #8] (#4900)

Integrated into release/v3.8.36

* fix(quota): policy inválida não vaza allow + guard connectionIds vazio [Fase 3 #10] (#4901)

Integrated into release/v3.8.36

* feat(quota): saturação real do Claude no fair-share via /api/oauth/usage (#4885)

Integrated into release/v3.8.36

* chore(dashboard): rename Qoder display label from "Qoder AI" to "Qoder" (#4733)

Integrated into release/v3.8.36

* fix(ci): include coverage/lcov.info in coverage-report artifact for SonarQube (#4670)

Integrated into release/v3.8.36

* fix(cli): bump better-sqlite3 runtime pin to 12.10.1 for Node 26 (#4685)

Integrated into release/v3.8.36

* docs: clarify Kiro is ~50 credits/month per account, not unlimited (#4690)

Integrated into release/v3.8.36

* docs(agentbridge): document Electron NODE_EXTRA_CA_CERTS, real model IDs, identity caveat (#4718)

Integrated into release/v3.8.36

* docs(ops): document the release-green family (green-prs, check:release-green, babysit, nightly) (#4679)

Integrated into release/v3.8.36

* fix(translator): replay reasoning_content on plain Xiaomi MiMo turns (port from 9router#1321) (#4639)

Integrated into release/v3.8.36

* feat(opencode-go): advertise glm-5.2 and kimi-k2.7-code (align with official Go endpoints) (#4711)

Integrated into release/v3.8.36

* feat(db): track API endpoint dimension on usage_history (#4676)

Integrated into release/v3.8.36 (migration renumbered 103→105; endpoint plumbed through extracted usage-stats helpers)

* fix(cli): SIGKILL systray child PID before IPC close to avoid macOS NSStatusItem orphan (#4732)

Integrated into release/v3.8.36

* feat(proxy-pool): Cloudflare Workers proxy deployer + pool integration (#4640)

Integrated into release/v3.8.36 (relay type added to RELAY_TYPES set; dropdown UX preserved + Cloudflare item added; proxies.ts file-size rebaselined 1057→1060)

* chore(quality): conserta base-red de release/v3.8.36 (gates + 7 testes + build MDX) (#4915)

A base tinha base-red sistêmica herdada de PRs de outras sessões, bloqueando
TODOS os PRs do ciclo (o TIA roda a suíte full em fail-safe p/ diffs hub).

4 Fast Quality Gates:
- test-discovery (#4877): live-server-allowlist.test.ts em tests/unit/server/
  (não-coletado) + vitest → nunca rodava. Convertido p/ node:test em tests/unit/security/.
- any-budget:t11 (#4664): 3 explicit-any em tokenRefresh.ts tipados (sem crescer file-size).
- docs-symbols (#4868): rotas inexistentes → /api/system/version e
  PUT /api/providers/{id} {isActive:false}.
- docs-all fabricated-claim (#4868 + #4718): 5 bin/*.sh reais criados (rollback,
  snapshot-data, restore-data, restore-policies, cold-start-bench) + _ops-common.sh
  (snapshot VACUUM INTO, guards de confirmação/TTY, testes de contrato); NODE_EXTRA_CA_CERTS
  (env de runtime Node) na allowlist do checker.

7 testes unit base-red (de features alheias à quota):
- oauth-providers-config (#4664): teste alinhado ao provider codebuddy-cn do registry.
- antigravity-model-aliases (#4636): maxOutputTokens esperado 32769→16384 (cap intencional).
- provider-request-capture #4091 (#4861): exemplo do teste trocado de mcp__ (que #4861
  isenta de cloak por causa dos 400s de assimetria de histórico) para um tool de terceiro
  cloakável — preserva o invariante de #4091 SEM reverter #4861.
- combo-error-response: convertido de vitest p/ node:test (era coletado pelo glob node:test
  e crashava); api/** e server/** removidos do vitest.config (config morta).

Build MDX (dast-smoke, #4679):
- docs/ops/RELEASE_GREEN.md não tinha frontmatter `title` → fumadocs-mdx rejeitava no
  webpack compile ("invalid frontmatter: title expected string"), quebrando o next build
  (e o deploy). Frontmatter title adicionado (único doc do collection sem ele).

17/17 Fast Quality Gates + suíte unit completa (17737 testes, 0 fail) + vitest verdes localmente.

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* feat(quota): saturação proativa por headers de tokens (universal) [Fase 3 #2] (#4907)

storeRateLimitHeaders só capturava os headers de REQUESTS (RPM/min), que não
refletem a pressão de TOKENS. Agora também parseia os headers de tokens (em toda
resposta, sucesso também) para throttle proativo antes do 429:
- Anthropic: anthropic-ratelimit-tokens-{limit,remaining,reset} (+ input/output), RFC3339.
- OpenAI: x-ratelimit-{limit,remaining,reset}-tokens, reset em duração (6m0s).

saturation = 1 − remaining/limit; resetAt normalizado a epoch (parse de duração
ReDoS-safe). getTokenHeaderSaturation por (provider, connectionId). fetchGeneric-
Saturation passa a usar esse sinal (complementa o oauth/usage do #1, que segue
primário p/ Claude). Fail-open, cache mantido, request-path inalterado.

16 testes novos + regressão (oauth/usage #1 8/8, signals 6/6) = 30/30;
typecheck:core + eslint limpos.

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* feat(quota): estratégia de combo "headroom" — seleção por folga de cota [Fase 3 #4] (#4908)

Nova estratégia de roteamento que escolhe a conexão com MAIS folga de plano:
headroom = 1 − max(util_5h, util_7d) (técnica do dario), via getSaturation
(melhorado p/ Claude no #1). Proativo em vez de só fill-first reativo.

- Helper PURO headroomRanking.ts (computeHeadroom + rankByHeadroom; saturação
  injetada, não-mutante, tie-break estável, fail-open).
- Orderer async em combo/quotaStrategies.ts (reusa a maquinaria reset-aware de
  expansão de conexões + concorrência limitada; seam injetável).
- Registrada como "headroom" em routingStrategies (combo-only); fill-first segue
  default — nenhuma estratégia existente tocada.
- baseline file-size combo.ts 3168->3180 (só +12L de dispatch; lógica fora do god-file).

16 testes novos + combo-strategies 15/15 = 31/31; typecheck:core + eslint +
file-size limpos.

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* feat(quota): cap per-(key,model) — quota_allocation_model_caps [Fase 3 #7] (#4927)

* feat(quota): cap per-(key,model) com tabela quota_allocation_model_caps [Fase 3 #7]

Fecha o buraco onde uma API key pode drenar o pool inteiro consumindo um único modelo.

Tabela nova: quota_allocation_model_caps(pool_id, api_key_id, model, cap_value, cap_unit)
PK composta (pool_id, api_key_id, model). cap_unit alinhado ao QuotaUnit existente.

Comportamento: keyA acima do cap para modelo M → bloqueada somente em M; ainda
permitida em qualquer outro modelo no mesmo pool. Cap <= EPSILON → ignorado (seed).

Consumo por-(key,model) usa bucket segregado no quota_consumption existente
(poolId mangled ':model:<model>') com window fixa 'hourly'; nenhuma nova tabela
ou método de store necessário.

Módulo novo: src/lib/db/quotaModelCaps.ts (getModelCap/setModelCap/deleteModelCap/listModelCaps)
enforce.ts ganha o pre-check em enforceQuotaShare + recording em recordConsumption.
EnforceInput e RecordConsumptionInput ganham model?: string (backward-compatible).
localDb.ts re-exporta os 4 helpers (Hard Rule #2).

TDD: tests/unit/quota-per-key-model.test.ts — 4 cenários (bloqueia em M, permite em M2,
sem cap → sem bloqueio, EPSILON → ignorado). Todos os gates de qualidade passam.

* feat(quota): plumba model resolvido no hot path para ativar o per-(key,model) cap [Fase 3 #7]

A tabela/enforce do commit anterior estavam INERTES: o hot path não passava `model`
ao enforce nem ao record, então nenhum model-cap disparava em produção.

Plumbagem (model resolvido = mesma var usada no log/roteamento, pós background-redirect/alias):
- chatCore.ts: enforceQuotaShare ganha `model`; scheduleQuotaShareConsumption recebe `model`.
- chatCore/quotaShareConsumption.ts: threade `model` no RecordConsumptionInput (non-streaming).
- spendRecorder.ts: recordStreamingConsumption já recebia `model` — agora o coloca no
  RecordConsumptionInput (streaming accrue por-modelo).
- embeddings.ts: enforce + record ganham `model`.

Namespace do cap = id do modelo RESOLVIDO (o mesmo de modelForScope/pendingScope/getUnsupportedParams),
não o requestedModel cru nem o finalModelToUpstream (sem prefixo de provider). Operador configura
o cap contra esse id. `model || undefined` em todos os pontos: vazio/null → check pulado (fail-safe,
zero latência — só um campo no objeto).

Teste de integração novo (tests/unit/quota-per-key-model-hotpath.test.ts): prova end-to-end que
N consumos via scheduleQuotaShareConsumption({model}) → enforceQuotaShare({model}) bloqueia, e que
outro modelo no mesmo pool ainda passa; + guard de que enforce SEM model nunca dispara model-cap.

---------

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* feat(quota): session stickiness p/ integridade de prompt-cache [Fase 3 #5] (#4929)

* feat(quota): session stickiness p/ integridade de prompt-cache [Fase 3 #5]

Adiciona stickiness de sessão ao roteamento de combo: uma conversa multi-turno
é roteada para a MESMA conexão enquanto ela permanecer saudável, evitando a
perda do prompt-cache do provider (custo 5-10× sem stickiness, efeito conhecido
no dario/clewdr).

Implementação:
- `open-sse/services/combo/sessionStickiness.ts` (novo, <800 linhas):
  mapa em memória (messageHash → connectionId) com TTL 15 min + cap 500 entradas;
  `applySessionStickiness` promove a conexão sticky ao índice 0 dos targets
  ordenados pelo strategy, guardado por `computeHeadroom > 0.15` (threshold);
  quando saturada (headroom ≤ 0.15), o binding é limpo e a seleção normal reage.
  Hash da sessão = SHA-256 dos primeiros chars da 1ª mensagem user → 16 hex chars.
  Seam de teste: `__setStickinessHeadroomFetcherForTests`.
- `open-sse/services/combo.ts`: import + 2 pontos de integração (pré-eval-scores
  e pós-success), dentro do orçamento congelado de 3180 linhas.
- `tests/unit/combo-session-stickiness.test.ts`: 19 testes node:test + assert/strict,
  todos via injeção de fetcher (zero rede/DB).

Threshold 0.15: conexão a >85% de utilização está a um burst de rate-limit;
o benefício de cache não compensa manter-se numa conexão degradada. Valor
alinhado com a zona de soft-penalty do restante do engine de quota-share.

* test(combo): isola combo-strategies da session stickiness (#5)

selectedConnectionFor reusa o mesmo body, então o sticky map (#5) fixava a
connection após a 1ª chamada e quebrava o round-robin tie-break do teste
reset-aware. Limpa o sticky map no início da helper — a stickiness tem suíte
própria (combo-session-stickiness). Sem enfraquecer asserts.

---------

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* feat(quota): buckets multi-janela por conexão (5h/7d/per-model) [Fase 3 #3] (#4928)

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* refactor(providers): decompõe catálogo providers.ts em módulos de dados (godfile sweep, #3501) (#4917)

Integrado em release/v3.8.36 (godfile sweep providers.ts, #3501)

* refactor(pricing): decompõe pricing.ts em shared-tiers + DEFAULT_PRICING particionado (godfile sweep, #3501) (#4918)

Integrado em release/v3.8.36 (godfile sweep pricing.ts, #3501)

* refactor(api): extrai camada-folha pura de validation.ts (URL/headers/transport) (#4921)

Integrado em release/v3.8.36 (validation.ts split fatia 1 — leaf layer)

* refactor(api): extrai validators web-cookie + Meta AI de validation.ts (#4922)

Integrado em release/v3.8.36 (validation.ts split fatia 2 — web-cookie + Meta AI)

* refactor(api): extrai validators enterprise-cloud + probe compartilhado de validation.ts (#4923)

Integrado em release/v3.8.36 (validation.ts split fatia 3 — enterprise-cloud + probe)

* refactor(api): extrai validators áudio/speech + misc apikey de validation.ts (#4930)

Integrado em release/v3.8.36 (validation.ts split fatia 4 — áudio/speech + misc apikey)

* feat(quota): estratégia dedicada de quota-share (DRR + P2C in-flight + gating per-model) [Fase 3 #9] (#4939)

* feat(quota): estratégia dedicada de quota-share (DRR + P2C in-flight + gating per-model) [Fase 3 #9]

Estratégia interna "quota-share" isolada num módulo dedicado — NÃO toca a seleção/
fair-share genérica (decisão do dono: não mexer no que já funciona). Os combos qtSd/
(quotaCombos.ts) passam de fill-first para essa strategy; combo.ts ganha só 1 branch
de dispatch que delega 100% ao módulo (nenhum case existente alterado).

- quotaShareStrategy.ts: gating per-model (isBucketSaturated do #3) + DRR (quantum
  proporcional ao weight) + P2C sobre carga in-flight.
- quotaShareInflight.ts: contador in-flight com TTL/lease de 120s — fallback do
  decrement-on-abort sem precisar instrumentar o combo genérico.
- "quota-share" registrada como strategy INTERNA (não exposta na UI).
- testes de síntese (quota-combo-balancing, quota-multiprovider) alinhados: a strategy
  esperada dos combos qtSd/ passa de "fill-first" para "quota-share" (alinhamento ao novo
  comportamento intencional, não mascaramento — os 73 testes de qtSd/ seguem verdes).

* test(quota-share): alinha 2 scope-guards ao godfile sweep (base-reds que bloqueavam o CI)

Dois testes de "arquivo contém X" quebraram por decomposições de godfile que outras
sessões mergearam no release DURANTE a validação de #9 — NÃO são regressão de #9
(que não toca validation/oauth). Alinhados ao novo layout, asserts preservados:
- proxy-bypass-scope-guard #3226: bypassProxyPatch foi extraído de validation.ts para
  validation/headers.ts (split #4921–#4930) → o teste lê a camada de validação.
- sse-error-passthrough #3324: a windsurf authHint foi extraída de providers.ts para
  providers/oauth.ts → o teste lê o novo local.

---------

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* refactor(api): extrai validators search + embedding/rerank de validation.ts (#4932)

Integrated into release/v3.8.36

* refactor(api): extrai format-validators (OpenAI/Anthropic) de validation.ts (#4933)

Integrated into release/v3.8.36

* refactor(db): extrai model-permission matching de db/apiKeys.ts (#4936)

Integrated into release/v3.8.36

* refactor(db): extrai row-parsers + tipos compartilhados de db/apiKeys.ts (#4943)

Integrated into release/v3.8.36

* refactor(db): extrai column-mapping (snake↔camel) de db/core.ts (#4947)

Integrated into release/v3.8.36

* refactor(db): extrai schema-column reconciliation de db/core.ts (#4948)

Integrated into release/v3.8.36

* refactor(sse): extrai scalar/format helpers de services/usage.ts (#4949)

Integrated into release/v3.8.36

* refactor(sse): extrai quota-core (UsageQuota + builders) de services/usage.ts (#4950)

Integrated into release/v3.8.36

* fix(translator): regroup parallel tool results adjacent to their assistant (#4714) (#4882)

Integrated into release/v3.8.36 (fixes #4714)

* fix(qoder): exchange PAT for jt-* job token before Cosy chat (#4683) (#4884)

Integrated into release/v3.8.36 (fixes #4683)

* refactor(sse): dedup fallback tool_call id helper (#4736)

Integrated into release/v3.8.36

* refactor(open-sse): extract safeParseJSON util, dedup tryParseJSON (#4735)

Integrated into release/v3.8.36

* fix(compression): eliminate ReDoS in math_inline preservation pattern (#4795) (#4838)

Integrated into release/v3.8.36 (fixes #4795)

* fix(combo): fetch models dynamically from custom provider endpoints (#4860)

Integrated into release/v3.8.36

* feat(providers): update volcengine-ark model list with DeepSeek V4 (#4905)

Integrated into release/v3.8.36

* fix(translator): provider thinking compatibility (DeepSeek/Gemini) (#4946)

Integrated into release/v3.8.36

* feat(combo): task-aware routing strategy (#4945)

Integrated into release/v3.8.36

* refactor(sse): extrai a família MiniMax de services/usage.ts (#4952)

Integrated into release/v3.8.36

* refactor(sse): extrai a família GLM de services/usage.ts (#4953)

Integrated into release/v3.8.36

* refactor(sse): extrai a família Antigravity de services/usage.ts (#4956)

Integrated into release/v3.8.36

* fix(dashboard): show custom provider given-name instead of internal id across dashboard pages (#4603) (#4960)

Integrated into release/v3.8.36 (fixes #4603)

* fix(api): evict stale in-memory rate-limit windows to stop slow heap leak (#4041) (#4957)

Integrated into release/v3.8.36 (fixes #4041)

* fix(api): parse /v1/responses body once instead of 3-4x on the hot path (#4041) (#4958)

Integrated into release/v3.8.36 (fixes #4041)

* fix(translator): preserve legitimate empty-string tool arguments in openai-to-claude streaming (#4951) (#4959)

Integrated into release/v3.8.36 (fixes #4951)

* chore(quality): reconcile file-size baseline for #4960 provider-display-name (#4961)

Integrated into release/v3.8.36

* fix(dashboard): restore home provider-topology card hidden by #4596 default (#4963)

Integrated into release/v3.8.36 — restores home topology card (#4596 regression)

* fix(build): drop @omniroute/open-sse from optimizePackageImports (build OOM) (#4968)

Integrated into release/v3.8.36 — fixes build OOM (optimizePackageImports open-sse)

* fix(quota): migração 107 ativa estratégia quota-share nos combos qtSd/ existentes [Fase 3 #9] (#4962)

Integrated into release/v3.8.36

* feat(quota): respeita max_concurrent por conexão no roteamento (#4965)

Integrated into release/v3.8.36

* feat(quota): combo quota-share espera cooldown curto e re-despacha (Variante A) (#4967)

Integrated into release/v3.8.36

* fix(quality): resolve base-reds da release — db-rules allowlist + task-aware router precedence (#4973)

Dois base-reds pré-existentes que reprovavam o CI da release v3.8.36 (Fast
Quality Gates + Unit Tests fast-path), independentes de qualquer feature em voo:

1. check:db-rules / allowlist: os módulos db-internal caseMapping (#4947) e
   schemaColumns (#4948), extraídos de db/core.ts e importados só por ele, não
   estavam em INTENTIONALLY_INTERNAL. Registrados na allowlist (correção
   canônica — são internos legítimos, não re-exportados pelo localDb).

2. auto-strategy honra LKGP/cost (combo-routing-engine.test.ts, 2 testes): o
   task-aware reordering (#4945, reorderByTaskWeight) roda para strategy "auto" e
   era aplicado DEPOIS do router explícito (selectWithStrategy: lkgp/cost),
   sobrescrevendo o orderedTargets[0] que o operador escolheu. Instrumentação
   provou: post-filter [0]=claude (LKGP) → post-task [0]=gpt-oss. Correção: quando
   o auto usa router explícito, preserva o [0] dele e deixa o task-aware refinar
   só a cauda de fallback. gpt-oss-120b PERMANECE tool-capable (não é mudança de
   catálogo; o model-capabilities-registry test segue verde).

Validado: 121 testes (combo-routing-engine + combo-task-aware + registry) verdes,
red-check confirmado, db-rules/file-size/typecheck/lint/prettier OK.

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* feat(quota): serializa concorrência por conexão no caminho quota-share (FASE 2.1) (#4970)

O gating de quota-share em selectQuotaShareTarget é fail-open: uma conexão
at-cap só é despriorizada, nunca bloqueada. Com 1 conexão por conta de
assinatura (caso comum), chamadas concorrentes ainda floodam a conta (→ 429 +
cooldown) — provado live na .15: 3 chamadas concorrentes com max_concurrent=1
despacharam todas em 94ms.

Adiciona um semáforo POR CONEXÃO em torno do dispatch quota-share: chamadas
excedentes esperam na fila em vez de floodar (key qsconn:<connectionId>, cap =
max_concurrent da conexão). Fail-open em fila saturada/timeout para nunca
piorar disponibilidade. Gated por strategy===quota-share + kill-switch
resilienceSettings.quotaShareConcurrencyLimit (default on; UI no ResilienceTab).

Lógica extraível isolada no leaf puro combo/quotaShareConcurrency.ts
(unit-testado: estabilidade da key, no-op sem cap, serialização real,
fail-open). Settings + schema + UI espelham comboCooldownWait.

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* docs(resilience): document Quota-Share Concurrency Control (max_concurrent + serialization + cooldown-wait) (#4980)

Documents the v3.8.36 quota-share concurrency layers in RESILIENCE_GUIDE.md:
per-connection max_concurrent cap, the quota-share request serialization semaphore
(FASE 2.1, qsconn:<connectionId>, fail-open, kill-switch), and the combo
cooldown-aware retry — so operators know how to cap a subscription account's
concurrency and why the routing gate alone cannot contain a single-connection flood.

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* fix(dashboard): proxy-pool success gating, sync timestamp, opt-in Redis (#4878) (#4988)

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* fix(sse): fail over on 400 responses carrying rate-limit text (#4976) (#4986)

* fix(sse): fail over on 400 responses carrying rate-limit text (#4976)

* chore(quality): rebaseline accountFallback.ts file-size for #4976 fix

---------

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* fix(compression): stop RTK over-truncating file-read tool results (#4559) (#4987)

* fix(compression): stop RTK over-truncating file-read tool results (#4559)

* chore(quality): trim #4559 comment to keep rtk/index.ts within size cap

---------

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* fix(sse): honor per-account proxies and fingerprint rotation in opencode executor (#4954) (#4989)

* fix(sse): honor per-account proxies and fingerprint rotation in opencode executor (#4954)

* chore(quality): rebaseline auth.ts file-size for #4954 (+39: synthetic no-auth providerSpecificData hydration of fingerprints/accountProxies; irreducible credential-path wiring, covered by opencode-proxy-rotation-4954.test.ts + 159 auth/noauth regression)

---------

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* fix(sse): soft-penalize exhausted providers in auto-combo scoring (#4540) (#4990)

* fix(sse): soft-penalize exhausted providers in auto-combo scoring (#4540)

* chore(quality): document STATUS_SOFT_DEPRIORITIZE_FACTOR + rebaseline combo.ts for #4540

---------

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* fix(dashboard): switch to visible filter after auto-hiding failed models in test-all (#4887) (#4991)

* fix(dashboard): switch to visible filter after auto-hiding failed models in OAuth provider test-all (#4887)

* test(dashboard): move #4887 test into tests/unit/ui so a CI runner collects it

---------

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* fix(pollinations): only enable jsonMode when JSON output is requested (#3981) (#5009)

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* fix(antigravity): default safetySettings to all-OFF for parity with native Gemini paths (#5003) (#5008)

* fix(antigravity): default safetySettings to all-OFF for parity with native Gemini paths (#5003)

* docs(changelog): restore #3981 pollinations entry eaten by merge

---------

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* fix(chatgpt-web): map advertised gpt-5.5/5.4-pro/5.2-pro slugs to prevent silent model substitution (#4665) (#5010)

* fix(chatgpt-web): map advertised gpt-5.5/5.4-pro/5.2-pro slugs to prevent silent model substitution (#4665)

MODEL_MAP was missing the advertised catalog ids gpt-5.5, gpt-5.5-pro,
gpt-5.4-pro and gpt-5.2-pro, so MODEL_MAP[model] ?? model sent the dot-form
id verbatim to the ChatGPT backend-api, which silently rejected it and served
the default Plus model. Map each to its dash-form slug. gpt-4-5 is already
dash-form and falls through correctly, so it is intentionally left unmapped.

Extends the executor MODEL_MAP test with the four ids and adds a drift guard
asserting every advertised dot-form catalog id reaches the backend in dash-form
(never verbatim), guarding future catalog<->map drift.

file-size: tests/unit/chatgpt-web.test.ts frozen baseline 2809->2855 (+46) for
the added test cases and drift-guard test; executor source unchanged in baseline.

* docs(changelog): restore #3981/#5003 entries eaten by merge

---------

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* feat(combos): add editable per-combo description field persisted via /api/combos (#5005) (#5011)

* feat(combos): add editable per-combo description field persisted via /api/combos (#5005)

* docs(changelog): restore #3981/#5003/#4665 entries eaten by merge

---------

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* Fix Ollama Cloud max reasoning effort (#4993)

Integrated into release/v3.8.36

* fix(copilot): replace execSync with execFile to prevent command injection (#5024)

Integrated into release/v3.8.36

* fix(plugin): auth.json dual-key fallback for auto-prefix migration (#5027)

Integrated into release/v3.8.36

* feat(endpoint): per-endpoint custom system prompt injection (#5022)

Integrated into release/v3.8.36

* fix(headroom): translate openai-responses input through OpenAI for compression (#5023)

Integrated into release/v3.8.36

* docs(changelog): add entries for #4993, #5024, #5027 (release notes credit)

* fix(api): stop /api/system/env/repair 500 on packaged install (#5006) (#5028)

* fix(api): stop /api/system/env/repair 500 on packaged install — lazy createRequire in sync-env.mjs (#5006)

scripts/dev/sync-env.mjs ran createRequire(import.meta.url) at module
top-level. When webpack bundles it into the standalone env-repair route,
import.meta.url is frozen to the build-machine path (file:///home/runner/...)
and createRequire throws during module evaluation, so the whole route
module fails to load and every GET returns HTTP 500 — breaking the
onboarding wizard on packaged/global installs.

- Move createRequire into the guarded better-sqlite3 block (only place
  that needs it); a bad import.meta.url now returns the safe default.
- resolveRootDir() falls back to process.cwd() when fileURLToPath throws.
- route.ts passes an explicit rootDir (process.cwd()) so the helper never
  derives the root from the frozen import.meta.url, matching the .env
  target used by createEnvBackup().
- Regression guard: assert sync-env.mjs has no top-level createRequire +
  getEnvSyncPlan(oauth) works with explicit rootDir without throwing.

* docs(changelog): restore #4993/#5023/#5024/#5027 + custom-system-prompt/headroom entries eaten by release merge

* chore(quality): rebaseline 3 inherited base-reds from release merge

Files NOT touched by this PR — grew on release/v3.8.36 via --admin merges and
inherited here through 'git merge origin/release':
- open-sse/executors/base.ts 1414->1416 (#4993 Ollama Cloud max-effort)
- src/lib/db/settings.ts 1149->1151 (#5023 custom system prompt)
- src/app/(dashboard)/.../endpoint/EndpointPageClient.tsx 2570->2612 (custom system prompt UI)

* chore(release): finalize v3.8.36 CHANGELOG + docs (2026-06-25)

---------

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>
Co-authored-by: KooshaPari <42529354+KooshaPari@users.noreply.github.com>
Co-authored-by: Makcim Ivanov <makcimbx@gmail.com>
Co-authored-by: Chewji <126886556+Chewji9875@users.noreply.github.com>
Co-authored-by: Anton <39598727+NomenAK@users.noreply.github.com>
Co-authored-by: Demiurge The Single <megamen932@gmail.com>
Co-authored-by: Randi <55005611+rdself@users.noreply.github.com>
Co-authored-by: Éder Costa <eder.almeida.costa@gmail.com>
Co-authored-by: Jefferson Felizardo <jeffer1312@gmail.com>
Co-authored-by: Arthur Bodera <abodera@gmail.com>
Co-authored-by: Hamsa_M <116961508+hamsa0x7@users.noreply.github.com>
Co-authored-by: Hernan Javier Ardila Sanchez <hjasgr@gmail.com>
2026-06-25 13:17:40 -03:00

6691 lines
186 KiB
YAML
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
openapi: 3.1.0
info:
title: OmniRoute API
version: 3.8.36
description: |
OmniRoute is a local-first AI API proxy router. It provides an OpenAI-compatible
endpoint that routes requests to multiple AI providers with load balancing,
failover, and usage tracking.
## Base URLs
- **Local**: `http://localhost:20128`
## Authentication
All proxy endpoints require a Bearer token (API key managed via the dashboard).
Management endpoints are protected when `requireLogin` is enabled.
contact:
name: OmniRoute
license:
name: MIT
servers:
- url: http://localhost:20128
description: Local development
tags:
- name: Playground
description: Playground Studio — preset management and prompt improvement
- name: Memory
description: Conversational memory management — CRUD, engine status, playground preview, summarization, reindex, and Qdrant settings (plan 21 — v3.8.6). All routes require management auth.
- name: Chat
description: OpenAI-compatible chat completions
- name: Messages
description: Anthropic-compatible messages
- name: Responses
description: OpenAI Responses API
- name: Embeddings
description: Text embedding generation
- name: Images
description: Image generation
- name: Audio
description: Audio speech and transcription
- name: Moderations
description: Content moderation
- name: Rerank
description: Document reranking
- name: Models
description: Available model listing
- name: Providers
description: Provider connection management
- name: Provider Nodes
description: Provider node configuration
- name: API Keys
description: API key management
- name: Combos
description: Routing combo management
- name: Settings
description: Application settings
- name: Compression
description: Prompt compression, RTK filters, Caveman rules, and compression combos
- name: Usage
description: Usage analytics and logs
- name: Translator
description: Format translation debug & testing
- name: CLI Tools
description: CLI tool configuration management
- name: Embedded Services
description: >-
Install, start, stop, and monitor locally-running embedded services (9Router, CLIProxyAPI).
All routes are LOCAL_ONLY — accessible from loopback only (hard rule #17).
- name: OAuth
description: OAuth flows for provider authentication
- name: System
description: System management (restart, shutdown, backup)
- name: Pricing
description: Model pricing configuration
- name: Cloud
description: Cloud worker authentication and sync
- name: Fallback
description: Fallback chain management
- name: Telemetry
description: Telemetry and token health monitoring
- name: Agent Skills
description: >-
Agent Skills catalog — 42 SKILL.md files (22 REST API + 20 CLI) for external agents,
MCP clients, and A2A orchestrators to discover OmniRoute capabilities.
- name: AgentBridge
description: >-
MITM proxy manager for 9 IDE agents (Antigravity, Kiro, Copilot, Codex, Cursor, Zed,
Claude Code, Open Code, Trae). Controls server lifecycle, DNS/model mappings, bypass list,
and cert management. All routes are LOCAL_ONLY + SPAWN_CAPABLE (hard rules #15, #17).
See docs/frameworks/AGENTBRIDGE.md.
- name: Traffic Inspector
description: >-
LLM-aware HTTPS traffic debugger with 4 capture modes (AgentBridge, Custom Hosts,
HTTP_PROXY :8080, System-wide). Provides real-time WebSocket stream, session recording,
HAR export, SSE merge, and conversation normalization.
All routes are LOCAL_ONLY + SPAWN_CAPABLE (hard rules #15, #17).
See docs/frameworks/TRAFFIC_INSPECTOR.md.
paths:
# --- Playground + Search Tools (plans 17+18) ---
/api/playground/improve-prompt:
post:
tags:
- Playground
summary: Improve prompt via LLM
description: |
Rewrites the supplied system prompt and/or user prompt using a meta-prompt
(inspired by Anthropic Console Prompt Improver). Internally calls
`/v1/chat/completions` with the model specified in the request body.
Quota is consumed from the caller's account.
security:
- BearerAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- model
properties:
system:
type: string
maxLength: 50000
description: System prompt to improve (at least one of system/prompt required)
prompt:
type: string
maxLength: 50000
description: User prompt to improve
model:
type: string
description: Model to use for the improvement call (e.g. openai/gpt-4o)
tone:
type: string
enum:
- concise
- detailed
default: concise
responses:
"200":
description: Improved prompt(s)
content:
application/json:
schema:
type: object
properties:
improvedSystem:
type: string
improvedPrompt:
type: string
tokensIn:
type: integer
tokensOut:
type: integer
"400":
$ref: "#/components/responses/BadRequest"
"401":
$ref: "#/components/responses/Unauthorized"
/api/playground/presets:
get:
tags:
- Playground
summary: List playground presets
description: Returns all saved playground presets ordered by creation date (newest first).
security:
- BearerAuth: []
responses:
"200":
description: Preset list
content:
application/json:
schema:
type: object
properties:
presets:
type: array
items:
$ref: "#/components/schemas/PlaygroundPreset"
"401":
$ref: "#/components/responses/Unauthorized"
post:
tags:
- Playground
summary: Create playground preset
description: Saves the current playground configuration as a named preset in the database.
security:
- BearerAuth: []
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/PlaygroundPresetCreate"
responses:
"201":
description: Created preset
content:
application/json:
schema:
$ref: "#/components/schemas/PlaygroundPreset"
"400":
$ref: "#/components/responses/BadRequest"
"401":
$ref: "#/components/responses/Unauthorized"
/api/playground/presets/{id}:
parameters:
- name: id
in: path
required: true
schema:
type: string
format: uuid
get:
tags:
- Playground
summary: Get playground preset
security:
- BearerAuth: []
responses:
"200":
description: Preset found
content:
application/json:
schema:
$ref: "#/components/schemas/PlaygroundPreset"
"401":
$ref: "#/components/responses/Unauthorized"
"404":
description: Preset not found
put:
tags:
- Playground
summary: Update playground preset
security:
- BearerAuth: []
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/PlaygroundPresetCreate"
responses:
"200":
description: Updated preset
content:
application/json:
schema:
$ref: "#/components/schemas/PlaygroundPreset"
"400":
$ref: "#/components/responses/BadRequest"
"401":
$ref: "#/components/responses/Unauthorized"
"404":
description: Preset not found
delete:
tags:
- Playground
summary: Delete playground preset
security:
- BearerAuth: []
responses:
"204":
description: Deleted
"401":
$ref: "#/components/responses/Unauthorized"
"404":
description: Preset not found
# --- Memory Engine (plan 21) ---
/api/memory:
get:
tags:
- Memory
summary: List memory entries
security:
- ManagementSessionAuth: []
parameters:
- name: apiKeyId
in: query
schema:
type: string
- name: type
in: query
schema:
type: string
enum:
- factual
- episodic
- procedural
- semantic
- name: sessionId
in: query
schema:
type: string
- name: q
in: query
schema:
type: string
- name: limit
in: query
schema:
type: integer
minimum: 1
maximum: 200
default: 50
- name: page
in: query
schema:
type: integer
minimum: 1
default: 1
- name: offset
in: query
schema:
type: integer
minimum: 0
responses:
"200":
description: Paginated list of memories with stats
content:
application/json:
schema:
type: object
properties:
data:
type: array
items:
$ref: "#/components/schemas/MemoryEntry"
total:
type: integer
totalPages:
type: integer
stats:
type: object
properties:
total:
type: integer
tokensUsed:
type: integer
hitRate:
type: number
cacheStats:
type: object
properties:
hits:
type: integer
misses:
type: integer
"401":
$ref: "#/components/responses/Unauthorized"
post:
tags:
- Memory
summary: Create a memory entry
security:
- ManagementSessionAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- content
- key
properties:
content:
type: string
minLength: 1
key:
type: string
minLength: 1
type:
type: string
enum:
- factual
- episodic
- procedural
- semantic
default: factual
sessionId:
type: string
nullable: true
apiKeyId:
type: string
metadata:
type: object
additionalProperties: true
expiresAt:
type: string
format: date-time
nullable: true
responses:
"201":
description: Created memory entry
content:
application/json:
schema:
$ref: "#/components/schemas/MemoryEntry"
"400":
description: Validation error
"401":
$ref: "#/components/responses/Unauthorized"
/api/memory/{id}:
parameters:
- name: id
in: path
required: true
schema:
type: string
description: Memory UUID
get:
tags:
- Memory
summary: Get a single memory entry
security:
- ManagementSessionAuth: []
responses:
"200":
description: Memory entry
content:
application/json:
schema:
$ref: "#/components/schemas/MemoryEntry"
"401":
$ref: "#/components/responses/Unauthorized"
"404":
description: Memory not found
put:
tags:
- Memory
summary: Update a memory entry
description: Update `type`, `key`, `content`, and/or `metadata` of an existing memory. If an embedding source is available, the vector in `vec_memories` is also regenerated. Corresponds to `MemoryUpdatePutSchema`.
security:
- ManagementSessionAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
type:
type: string
enum:
- factual
- episodic
- procedural
- semantic
key:
type: string
minLength: 1
content:
type: string
minLength: 1
metadata:
type: object
additionalProperties: true
additionalProperties: false
responses:
"200":
description: Updated memory entry
content:
application/json:
schema:
$ref: "#/components/schemas/MemoryEntry"
"400":
description: Validation error
"401":
$ref: "#/components/responses/Unauthorized"
"404":
description: Memory not found
delete:
tags:
- Memory
summary: Delete a memory entry
description: Deletes the SQLite row, removes the vector from `vec_memories`, and best-effort deletes the point from Qdrant.
security:
- ManagementSessionAuth: []
responses:
"200":
description: Deleted
content:
application/json:
schema:
type: object
properties:
success:
type: boolean
"401":
$ref: "#/components/responses/Unauthorized"
"404":
description: Memory not found
/api/memory/health:
get:
tags:
- Memory
summary: Memory store health check
description: Round-trip create→list→delete to verify the store is alive.
security:
- ManagementSessionAuth: []
responses:
"200":
description: Health result
content:
application/json:
schema:
type: object
properties:
working:
type: boolean
latencyMs:
type: number
error:
type: string
nullable: true
"401":
$ref: "#/components/responses/Unauthorized"
/api/memory/retrieve-preview:
post:
tags:
- Memory
summary: Dry-run memory retrieval (Playground)
description: Simulates `retrieveMemories()` for a given query and returns the ranked results with score, tier, and token count. Does NOT modify any memory. Corresponds to `RetrievePreviewSchema`.
security:
- ManagementSessionAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- query
properties:
query:
type: string
minLength: 1
strategy:
type: string
enum:
- exact
- semantic
- hybrid
default: hybrid
maxTokens:
type: integer
minimum: 1
maximum: 16000
default: 2000
apiKeyId:
type: string
description: Optional — tests global pool when omitted
limit:
type: integer
minimum: 1
maximum: 100
default: 20
additionalProperties: false
responses:
"200":
description: Preview results
content:
application/json:
schema:
type: object
properties:
memories:
type: array
items:
type: object
properties:
id:
type: string
type:
type: string
enum:
- factual
- episodic
- procedural
- semantic
key:
type: string
content:
type: string
score:
type: number
tokens:
type: integer
tier:
type: string
enum:
- fts5
- vector
- hybrid-rrf
- qdrant
vecScore:
type: number
nullable: true
ftsScore:
type: number
nullable: true
resolution:
type: object
properties:
embeddingSource:
type: string
enum:
- remote
- static
- transformers
nullable: true
embeddingModel:
type: string
nullable: true
vectorStore:
type: string
enum:
- sqlite-vec
- qdrant
- none
strategyUsed:
type: string
enum:
- exact
- semantic
- hybrid
rerankApplied:
type: boolean
fallbackReason:
type: string
nullable: true
totalTokensUsed:
type: integer
budgetMaxTokens:
type: integer
"400":
description: Validation error
"401":
$ref: "#/components/responses/Unauthorized"
/api/memory/embedding-providers:
get:
tags:
- Memory
summary: List embedding providers
description: Returns all providers that have embedding-capable models, indicating which have an active API key configured.
security:
- ManagementSessionAuth: []
responses:
"200":
description: Provider list
content:
application/json:
schema:
type: object
properties:
providers:
type: array
items:
type: object
properties:
provider:
type: string
hasKey:
type: boolean
models:
type: array
items:
type: object
properties:
id:
type: string
description: "Format: provider/model"
name:
type: string
dimensions:
type: integer
nullable: true
"401":
$ref: "#/components/responses/Unauthorized"
/api/memory/engine-status:
get:
tags:
- Memory
summary: Memory engine status
description: Returns the full engine status including keyword tier availability, embedding resolution, vector store statistics (sqlite-vec), Qdrant health, and rerank configuration. Corresponds to `MemoryEngineStatusSchema`.
security:
- ManagementSessionAuth: []
responses:
"200":
description: Engine status
content:
application/json:
schema:
type: object
properties:
keyword:
type: object
properties:
available:
type: boolean
backend:
type: string
enum:
- FTS5
embedding:
type: object
properties:
source:
type: string
enum:
- remote
- static
- transformers
nullable: true
model:
type: string
nullable: true
dimensions:
type: integer
nullable: true
available:
type: boolean
reason:
type: string
cacheStats:
type: object
properties:
hits:
type: integer
misses:
type: integer
size:
type: integer
vectorStore:
type: object
properties:
backend:
type: string
enum:
- sqlite-vec
- qdrant
- none
available:
type: boolean
rowCount:
type: integer
needsReindex:
type: integer
reason:
type: string
qdrant:
type: object
properties:
enabled:
type: boolean
healthy:
type: boolean
nullable: true
latencyMs:
type: number
nullable: true
error:
type: string
nullable: true
rerank:
type: object
properties:
enabled:
type: boolean
provider:
type: string
nullable: true
model:
type: string
nullable: true
available:
type: boolean
reason:
type: string
"401":
$ref: "#/components/responses/Unauthorized"
/api/memory/summarize:
post:
tags:
- Memory
summary: Compact old memories
description: "Manually triggers memory compaction for memories older than `olderThanDays`. Use `dryRun: true` to preview candidates. Corresponds to `MemorySummarizeSchema`."
security:
- ManagementSessionAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
olderThanDays:
type: integer
minimum: 1
maximum: 365
default: 30
apiKeyId:
type: string
description: Optional — compacts all keys when omitted
dryRun:
type: boolean
default: false
additionalProperties: false
responses:
"200":
description: Summarization result
content:
application/json:
schema:
type: object
properties:
candidates:
type: integer
tokensSaved:
type: integer
dryRun:
type: boolean
"400":
description: Validation error
"401":
$ref: "#/components/responses/Unauthorized"
/api/memory/reindex:
post:
tags:
- Memory
summary: Trigger vector reindex
description: "Starts background reindexing of memories with `needs_reindex = 1`. Use `force: true` to regenerate ALL vectors regardless of index status. Corresponds to `MemoryReindexSchema`."
security:
- ManagementSessionAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
force:
type: boolean
default: false
description: When true, marks all memories needs_reindex=1 before running.
additionalProperties: false
responses:
"200":
description: Reindex started
content:
application/json:
schema:
type: object
properties:
started:
type: boolean
pending:
type: integer
description: Memories still pending after this batch
"400":
description: Validation error
"401":
$ref: "#/components/responses/Unauthorized"
/api/settings/memory:
get:
tags:
- Memory
- Settings
summary: Get memory settings
description: Returns the extended memory settings including 7 new fields added in plan 21 (embeddingSource, embeddingProviderModel, transformersEnabled, staticEnabled, rerankEnabled, rerankProviderModel, vectorStore).
security:
- ManagementSessionAuth: []
responses:
"200":
description: Extended memory settings
content:
application/json:
schema:
$ref: "#/components/schemas/MemorySettingsExtended"
"401":
$ref: "#/components/responses/Unauthorized"
put:
tags:
- Memory
- Settings
summary: Update memory settings
description: "Update any subset of the extended memory settings. All fields are optional; only provided fields are updated. Schema: `MemorySettingsExtendedSchema`."
security:
- ManagementSessionAuth: []
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/MemorySettingsExtended"
responses:
"200":
description: Updated memory settings
content:
application/json:
schema:
$ref: "#/components/schemas/MemorySettingsExtended"
"400":
description: Validation error
"401":
$ref: "#/components/responses/Unauthorized"
/api/settings/qdrant:
get:
tags:
- Memory
- Settings
summary: Get Qdrant settings
description: Returns current Qdrant configuration. The `apiKey` field is never returned raw — use `hasApiKey` / `apiKeyMasked` instead.
security:
- ManagementSessionAuth: []
responses:
"200":
description: Qdrant settings
content:
application/json:
schema:
$ref: "#/components/schemas/QdrantSettings"
"401":
$ref: "#/components/responses/Unauthorized"
put:
tags:
- Memory
- Settings
summary: Update Qdrant settings
description: 'Update Qdrant configuration. Pass `apiKey: ""` to remove the stored key. Schema: `QdrantSettingsUpdateSchema`.'
security:
- ManagementSessionAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
enabled:
type: boolean
host:
type: string
port:
type: integer
minimum: 1
maximum: 65535
collection:
type: string
minLength: 1
embeddingModel:
type: string
minLength: 1
apiKey:
type: string
description: Empty string removes the key
additionalProperties: false
responses:
"200":
description: Updated Qdrant settings
content:
application/json:
schema:
$ref: "#/components/schemas/QdrantSettings"
"400":
description: Validation error
"401":
$ref: "#/components/responses/Unauthorized"
/api/settings/qdrant/health:
get:
tags:
- Memory
summary: Qdrant health probe
description: Performs a liveness check against the configured Qdrant instance. Returns latency and any connection error (sanitized — no stack traces).
security:
- ManagementSessionAuth: []
responses:
"200":
description: Health result
content:
application/json:
schema:
$ref: "#/components/schemas/QdrantHealthResult"
"401":
$ref: "#/components/responses/Unauthorized"
/api/settings/qdrant/search:
post:
tags:
- Memory
summary: Qdrant semantic search test
description: "Performs a test semantic search against the Qdrant collection. Useful for validating that the integration works end-to-end. Schema: `QdrantSearchSchema`."
security:
- ManagementSessionAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- query
properties:
query:
type: string
minLength: 1
topK:
type: integer
minimum: 1
maximum: 50
default: 5
additionalProperties: false
responses:
"200":
description: Search results
content:
application/json:
schema:
type: object
properties:
results:
type: array
items:
type: object
"400":
description: Validation error
"401":
$ref: "#/components/responses/Unauthorized"
"503":
description: Qdrant unavailable (structured error, no stack trace)
/api/settings/qdrant/cleanup:
post:
tags:
- Memory
summary: Clean up expired Qdrant points
description: Removes Qdrant points for memories that have expired or exceeded the configured retention window.
security:
- ManagementSessionAuth: []
responses:
"200":
description: Cleanup result
content:
application/json:
schema:
type: object
properties:
deleted:
type: integer
checked:
type: integer
"401":
$ref: "#/components/responses/Unauthorized"
"503":
description: Qdrant unavailable (structured error, no stack trace)
/api/settings/qdrant/embedding-models:
get:
tags:
- Memory
summary: List Qdrant embedding models
description: Returns the list of embedding models available for use with Qdrant.
security:
- ManagementSessionAuth: []
responses:
"200":
description: Embedding models list
content:
application/json:
schema:
type: object
properties:
models:
type: array
items:
type: string
"401":
$ref: "#/components/responses/Unauthorized"
# ─── Proxy Endpoints ──────────────────────────────────────────
/api/v1/chat/completions:
post:
tags: [Chat]
summary: Create chat completion
description: OpenAI-compatible chat completions endpoint. Routes to configured providers.
security:
- BearerAuth: []
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/ChatCompletionRequest"
responses:
"200":
description: Chat completion response (or SSE stream)
headers:
X-OmniRoute-Response-Cost:
schema:
type: string
description: Request cost in USD, fixed 10 decimals (e.g. `0.0001234500`; `0.0000000000` for free/unpriced).
X-OmniRoute-Tokens-In:
schema:
type: string
description: Input (prompt) token count.
X-OmniRoute-Tokens-Out:
schema:
type: string
description: Output (completion) token count.
X-OmniRoute-Model:
schema:
type: string
description: Resolved model.
X-OmniRoute-Provider:
schema:
type: string
description: Resolved provider alias.
X-OmniRoute-Latency-Ms:
schema:
type: string
description: Handler latency in milliseconds.
X-OmniRoute-Cache-Hit:
schema:
type: string
enum: ["true", "false"]
description: Whether the response was served from cache.
X-OmniRoute-Fallback-Attempts:
schema:
type: string
description: Number of fallback attempts (only present when > 0).
X-OmniRoute-Request-Id:
schema:
type: string
description: Request correlation id (present when known).
X-OmniRoute-Version:
schema:
type: string
description: OmniRoute build version (always present).
X-OmniRoute-Cost-Saved:
schema:
type: string
description: >-
On a semantic-cache HIT, the original (would-have-been) cost in USD that
the cache avoided (fixed 10 decimals). Present only on cache hits;
X-OmniRoute-Response-Cost is 0 for the same response (incremental cost).
content:
application/json:
schema:
$ref: "#/components/schemas/ChatCompletionResponse"
text/event-stream:
schema:
type: string
"401":
$ref: "#/components/responses/Unauthorized"
"502":
description: All upstream providers failed
/api/v1/ws:
get:
tags: [Chat]
summary: Chat completion over WebSocket (handshake + upgrade)
description: >-
OpenAI-compatible chat over a WebSocket connection. `GET` with
`?handshake=1` returns the connection descriptor (auth path, message
protocol and live-event channels) as JSON; a plain `GET` without an
Upgrade returns `426 Upgrade Required`. After upgrading, the client
exchanges JSON frames — `{type:"request", id, payload:{model, messages}}`
to start a completion and `{type:"cancel", id}` to abort it. A separate
live channel (default port `LIVE_WS_PORT=20129`, path `/live`) streams
dashboard events on the `requests`, `combo` and `credentials` topics with
a 15s heartbeat. Requires an API key.
security:
- BearerAuth: []
parameters:
- name: handshake
in: query
description: Set to `1` to receive the JSON connection descriptor instead of upgrading.
required: false
schema:
type: string
enum: ["1"]
responses:
"101":
description: WebSocket upgrade successful
"200":
description: Handshake descriptor (auth path, message protocol, live channels)
"401":
description: WebSocket auth required (no credential supplied)
"403":
description: Invalid WebSocket credential
"426":
description: Upgrade Required — connect via WebSocket or use `?handshake=1`
/api/v1/providers/{provider}/chat/completions:
post:
tags: [Chat]
summary: Create chat completion (provider-specific)
description: Routes to a specific provider by name.
security:
- BearerAuth: []
parameters:
- name: provider
in: path
required: true
schema:
type: string
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/ChatCompletionRequest"
responses:
"200":
description: Chat completion response
"401":
$ref: "#/components/responses/Unauthorized"
/api/v1/api/chat:
post:
tags: [Chat]
summary: Ollama-compatible chat endpoint
description: Provides compatibility with Ollama's /api/chat format.
security:
- BearerAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Chat response (JSON or streaming)
/api/v1/messages:
post:
tags: [Messages]
summary: Create message (Anthropic-compatible)
description: Anthropic Messages API endpoint. Routes to Claude providers.
security:
- BearerAuth: []
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/MessagesRequest"
responses:
"200":
description: >-
Message response (or SSE stream). Non-streaming success responses
carry the `X-OmniRoute-*` cost-telemetry headers (see
`POST /api/v1/chat/completions`), including `X-OmniRoute-Request-Id`
and `X-OmniRoute-Version`.
"401":
$ref: "#/components/responses/Unauthorized"
/api/v1/messages/count_tokens:
post:
tags: [Messages]
summary: Count tokens for a message
security:
- BearerAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Token count
/api/v1/responses:
post:
tags: [Responses]
summary: Create response (OpenAI Responses API)
description: OpenAI Responses API endpoint.
security:
- BearerAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: >-
Response object or SSE stream. Non-streaming success responses carry
the `X-OmniRoute-*` cost-telemetry headers (see
`POST /api/v1/chat/completions`), including `X-OmniRoute-Request-Id`
and `X-OmniRoute-Version`.
"401":
$ref: "#/components/responses/Unauthorized"
/api/v1/embeddings:
post:
tags: [Embeddings]
summary: Create embeddings
security:
- BearerAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
required: [input, model]
properties:
input:
oneOf:
- type: string
- type: array
items:
type: string
model:
type: string
responses:
"200":
description: >-
Embedding vectors. Success responses carry the `X-OmniRoute-*`
cost-telemetry headers (see `POST /api/v1/chat/completions`); media
cost is computed per modality when pricing is available, otherwise
`0` (fail-open).
/api/v1/providers/{provider}/embeddings:
post:
tags: [Embeddings]
summary: Create embeddings (provider-specific)
security:
- BearerAuth: []
parameters:
- name: provider
in: path
required: true
schema:
type: string
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Embedding vectors
/api/v1/images/generations:
post:
tags: [Images]
summary: Generate images
security:
- BearerAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
required: [prompt]
properties:
prompt:
type: string
model:
type: string
n:
type: integer
default: 1
size:
type: string
default: 1024x1024
responses:
"200":
description: >-
Generated images. Success responses carry the `X-OmniRoute-*`
cost-telemetry headers (see `POST /api/v1/chat/completions`); image
cost is computed per image when pricing is available, otherwise `0`
(fail-open).
/api/v1/providers/{provider}/images/generations:
post:
tags: [Images]
summary: Generate images (provider-specific)
security:
- BearerAuth: []
parameters:
- name: provider
in: path
required: true
schema:
type: string
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Generated images
/api/v1/audio/speech:
post:
tags: [Audio]
summary: Generate speech audio
description: Text-to-speech endpoint. Routes to configured TTS providers.
security:
- BearerAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
required: [input]
properties:
input:
type: string
model:
type: string
voice:
type: string
responses:
"200":
description: >-
Audio data. Success responses carry the `X-OmniRoute-*`
cost-telemetry headers (see `POST /api/v1/chat/completions`); speech
cost is computed per character when pricing is available, otherwise
`0` (fail-open).
/api/v1/audio/transcriptions:
post:
tags: [Audio]
summary: Transcribe audio
description: Audio-to-text transcription endpoint.
security:
- BearerAuth: []
requestBody:
required: true
content:
multipart/form-data:
schema:
type: object
required: [file]
properties:
file:
type: string
format: binary
model:
type: string
responses:
"200":
description: >-
Transcription result. Success responses carry the `X-OmniRoute-*`
cost-telemetry headers (see `POST /api/v1/chat/completions`);
transcription cost is computed per second when pricing is available,
otherwise `0` (fail-open).
/api/v1/moderations:
post:
tags: [Moderations]
summary: Create moderation
description: Content moderation endpoint. Routes to configured moderation providers.
security:
- BearerAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
required: [input]
properties:
input:
oneOf:
- type: string
- type: array
items:
type: string
responses:
"200":
description: >-
Moderation result. Success responses carry the `X-OmniRoute-*`
cost-telemetry headers (see `POST /api/v1/chat/completions`);
moderations are always cost `0` (free).
/api/v1/rerank:
post:
tags: [Rerank]
summary: Rerank documents
description: Document reranking endpoint.
security:
- BearerAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
required: [query, documents]
properties:
query:
type: string
documents:
type: array
items:
type: string
model:
type: string
responses:
"200":
description: >-
Reranked documents. Success responses carry the `X-OmniRoute-*`
cost-telemetry headers (see `POST /api/v1/chat/completions`); rerank
cost is computed per search-unit when pricing is available,
otherwise `0` (fail-open).
/api/v1:
get:
tags: [System]
summary: API v1 root endpoint
description: Returns basic API info and status.
security:
- BearerAuth: []
responses:
"200":
description: API info
/api/v1/models:
get:
tags: [Models]
summary: List available models
description: Returns all models available across configured providers.
security:
- BearerAuth: []
responses:
"200":
description: Model list
content:
application/json:
schema:
type: object
properties:
object:
type: string
example: list
data:
type: array
items:
$ref: "#/components/schemas/Model"
/api/v1/providers/{provider}/models:
get:
tags: [Models]
summary: List models for a specific provider
description: Returns only models for the selected provider with provider prefix removed from each model id.
security:
- BearerAuth: []
parameters:
- in: path
name: provider
required: true
schema:
type: string
description: Provider id or alias (for example `openai`, `claude`, `cc`).
responses:
"200":
description: Provider-scoped model list
content:
application/json:
schema:
type: object
properties:
object:
type: string
example: list
data:
type: array
items:
$ref: "#/components/schemas/Model"
"400":
description: Unknown provider
/api/models:
get:
tags: [Models]
summary: List models (management)
responses:
"200":
description: Internal model list with aliases
/api/models/alias:
post:
tags: [Models]
summary: Create or update a model alias
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Alias created/updated
/api/models/catalog:
get:
tags: [Models]
summary: Get full model catalog
responses:
"200":
description: Complete catalog with all providers
# ─── Management Endpoints ──────────────────────────────────────
/api/providers:
get:
tags: [Providers]
summary: List provider connections
responses:
"200":
description: Provider connection list
content:
application/json:
schema:
type: object
properties:
connections:
type: array
items:
$ref: "#/components/schemas/ProviderConnection"
post:
tags: [Providers]
summary: Create provider connection
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/ProviderConnectionCreate"
responses:
"201":
description: Created provider connection
/api/providers/{id}:
get:
tags: [Providers]
summary: Get provider connection
parameters:
- $ref: "#/components/parameters/ResourceId"
responses:
"200":
description: Provider connection details
"404":
description: Provider not found
patch:
tags: [Providers]
summary: Update provider connection
parameters:
- $ref: "#/components/parameters/ResourceId"
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/ProviderConnectionCreate"
responses:
"200":
description: Updated provider
delete:
tags: [Providers]
summary: Delete provider connection
parameters:
- $ref: "#/components/parameters/ResourceId"
responses:
"200":
description: Provider deleted
/api/providers/{id}/test:
post:
tags: [Providers]
summary: Test provider connection
parameters:
- $ref: "#/components/parameters/ResourceId"
responses:
"200":
description: Test result
/api/providers/{id}/models:
get:
tags: [Providers]
summary: List models for a provider
parameters:
- $ref: "#/components/parameters/ResourceId"
responses:
"200":
description: Provider model list
/api/providers/test-batch:
post:
tags: [Providers]
summary: Test multiple providers at once
responses:
"200":
description: Batch test results
/api/providers/validate:
post:
tags: [Providers]
summary: Validate provider credentials
responses:
"200":
description: Validation result
/api/providers/client:
get:
tags: [Providers]
summary: Get client-side provider info
responses:
"200":
description: Provider info for frontend
/api/providers/agy-auth/import:
post:
tags: [Providers]
summary: Import an Antigravity CLI (agy) token file as an `agy` connection
responses:
"200":
description: Created or updated provider connection
/api/providers/agy-auth/import-bulk:
post:
tags: [Providers]
summary: Bulk-import multiple Antigravity CLI (agy) token files (up to 50)
responses:
"200":
description: Per-entry import results (success/failed counts)
/api/providers/agy-auth/zip-extract:
post:
tags: [Providers]
summary: Extract `.json` token files from an uploaded ZIP for agy bulk import
responses:
"200":
description: Extracted token-file entries
/api/providers/agy-auth/apply-local:
post:
tags: [Providers]
summary: Auto-detect and import the local Antigravity CLI (agy) login from disk
responses:
"200":
description: Created or updated provider connection
"404":
description: No local agy login found
/api/provider-nodes:
get:
tags: [Provider Nodes]
summary: List provider nodes
responses:
"200":
description: Provider node list
post:
tags: [Provider Nodes]
summary: Create provider node
responses:
"201":
description: Created node
/api/provider-nodes/{id}:
patch:
tags: [Provider Nodes]
summary: Update provider node
parameters:
- $ref: "#/components/parameters/ResourceId"
responses:
"200":
description: Updated node
delete:
tags: [Provider Nodes]
summary: Delete provider node
parameters:
- $ref: "#/components/parameters/ResourceId"
responses:
"200":
description: Node deleted
/api/provider-nodes/validate:
post:
tags: [Provider Nodes]
summary: Validate a provider node
responses:
"200":
description: Validation result
/api/provider-models:
get:
tags: [Provider Nodes]
summary: List provider models
responses:
"200":
description: Provider model list
/api/keys:
get:
tags: [API Keys]
summary: List API keys
responses:
"200":
description: API key list
content:
application/json:
schema:
type: object
properties:
keys:
type: array
items:
$ref: "#/components/schemas/ApiKey"
"401":
description: Authentication required
post:
tags: [API Keys]
summary: Create API key
requestBody:
required: true
content:
application/json:
schema:
type: object
required: [label]
properties:
label:
type: string
responses:
"201":
description: Created API key (includes full key value)
"401":
description: Authentication required
/api/keys/{id}:
get:
tags: [API Keys]
summary: Get API key
parameters:
- $ref: "#/components/parameters/ResourceId"
responses:
"200":
description: API key metadata
"401":
description: Authentication required
"404":
description: Key not found
patch:
tags: [API Keys]
summary: Update API key
parameters:
- $ref: "#/components/parameters/ResourceId"
requestBody:
required: true
content:
application/json:
schema:
type: object
additionalProperties: true
responses:
"200":
description: API key settings updated
"400":
description: Invalid update request
"401":
description: Authentication required
"404":
description: Key not found
delete:
tags: [API Keys]
summary: Delete API key
parameters:
- $ref: "#/components/parameters/ResourceId"
responses:
"200":
description: Key deleted
"401":
description: Authentication required
"404":
description: Key not found
/api/combos:
get:
tags: [Combos]
summary: List routing combos
responses:
"200":
description: Combo list
post:
tags: [Combos]
summary: Create routing combo
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/ComboCreate"
responses:
"201":
description: Created combo
/api/combos/{id}:
patch:
tags: [Combos]
summary: Update combo
parameters:
- $ref: "#/components/parameters/ResourceId"
responses:
"200":
description: Updated combo
delete:
tags: [Combos]
summary: Delete combo
parameters:
- $ref: "#/components/parameters/ResourceId"
responses:
"200":
description: Combo deleted
/api/combos/metrics:
get:
tags: [Combos]
summary: Get combo metrics
responses:
"200":
description: Metrics for combos
/api/combos/test:
post:
tags: [Combos]
summary: Test a combo configuration
responses:
"200":
description: Test result
/api/settings:
get:
tags: [Settings]
summary: Get application settings
responses:
"200":
description: Current settings
patch:
tags: [Settings]
summary: Update settings
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Updated settings
/api/settings/purge-request-history:
post:
tags: [Settings]
summary: Clear request log history
description: Deletes `call_logs`, legacy `request_detail_logs`, and local request artifact files under `DATA_DIR/call_logs`.
security:
- ManagementSessionAuth: []
responses:
"200":
description: Request history cleared
content:
application/json:
schema:
type: object
properties:
deleted:
type: integer
deletedArtifacts:
type: integer
deletedDetailedLogs:
type: integer
errors:
type: integer
"401":
description: Unauthorized
"500":
description: Cleanup failed or reported errors
content:
application/json:
schema:
type: object
properties:
deleted:
type: integer
deletedArtifacts:
type: integer
deletedDetailedLogs:
type: integer
errors:
type: integer
error:
type: object
/api/settings/compression:
get:
tags: [Compression]
summary: Get global compression settings
security:
- ManagementSessionAuth: []
responses:
"200":
description: Current compression settings
put:
tags: [Compression]
summary: Update global compression settings
security:
- ManagementSessionAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
enabled:
type: boolean
defaultMode:
type: string
enum: [off, lite, standard, aggressive, ultra, rtk, stacked]
autoTriggerMode:
type: string
enum: [off, lite, standard, aggressive, ultra, rtk, stacked]
autoTriggerTokens:
type: integer
minimum: 0
rtkConfig:
type: object
additionalProperties: true
stackedPipeline:
type: array
items:
type: object
responses:
"200":
description: Updated compression settings
/api/settings/compression/mcp-accessibility:
get:
tags: [Compression]
summary: Get the MCP tool-output accessibility (trimming) config
security:
- ManagementSessionAuth: []
responses:
"200":
description: Current mcpAccessibility config
put:
tags: [Compression]
summary: Update the MCP tool-output accessibility (trimming) config
description: >-
Partial-merge update. Numeric floors (e.g. a maxTextChars below the truncation-tail
reserve) are folded back to the safe defaults server-side, so the response reflects the
effective config.
security:
- ManagementSessionAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
enabled:
type: boolean
maxTextChars:
type: integer
minimum: 1
collapseThreshold:
type: integer
minimum: 1
collapseKeepHead:
type: integer
minimum: 0
collapseKeepTail:
type: integer
minimum: 0
minLengthToProcess:
type: integer
minimum: 1
responses:
"200":
description: Updated mcpAccessibility config (numeric floors applied)
/api/compression/preview:
post:
tags: [Compression]
summary: Preview compression for a message payload
security:
- BearerAuth: []
- ManagementSessionAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
required: [messages, mode]
properties:
mode:
type: string
enum: [off, lite, standard, aggressive, ultra, rtk, stacked]
messages:
type: array
items:
type: object
required: [role, content]
properties:
role:
type: string
content:
oneOf:
- type: string
- type: array
items: {}
config:
type: object
additionalProperties: true
responses:
"200":
description: Compression preview with diff, validation, and stats
/api/compression/language-packs:
get:
tags: [Compression]
summary: List Caveman compression language packs
security:
- BearerAuth: []
- ManagementSessionAuth: []
responses:
"200":
description: Available languages and rule-pack metadata
/api/compression/rules:
get:
tags: [Compression]
summary: List Caveman compression rule metadata
security:
- BearerAuth: []
- ManagementSessionAuth: []
responses:
"200":
description: Caveman rule metadata
/api/context/rtk/config:
get:
tags: [Compression]
summary: Get RTK compression settings
security:
- ManagementSessionAuth: []
responses:
"200":
description: Current RTK config
put:
tags: [Compression]
summary: Update RTK compression settings
security:
- ManagementSessionAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
enabled:
type: boolean
intensity:
type: string
enum: [minimal, standard, aggressive]
customFiltersEnabled:
type: boolean
trustProjectFilters:
type: boolean
rawOutputRetention:
type: string
enum: [never, failures, always]
rawOutputMaxBytes:
type: integer
responses:
"200":
description: Updated RTK config
/api/context/rtk/filters:
get:
tags: [Compression]
summary: List RTK filters and load diagnostics
security:
- ManagementSessionAuth: []
responses:
"200":
description: RTK filter catalog and diagnostics
/api/context/rtk/test:
post:
tags: [Compression]
summary: Run RTK compression preview for text
security:
- ManagementSessionAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
required: [text]
properties:
text:
type: string
command:
type: string
config:
type: object
additionalProperties: true
responses:
"200":
description: Detection and RTK compression result
/api/context/rtk/raw-output/{id}:
get:
tags: [Compression]
summary: Read retained redacted RTK raw output
security:
- ManagementSessionAuth: []
parameters:
- in: path
name: id
required: true
schema:
type: string
pattern: "^[a-f0-9]{24}$"
responses:
"200":
description: Raw output text
"404":
description: Raw output not found
/api/settings/payload-rules:
get:
tags: [Settings]
summary: Get payload rules configuration
description: |
Returns the current payload rules used to mutate outgoing request payloads before they
are sent upstream.
Requires a dashboard management session cookie when management auth is enabled.
security:
- ManagementSessionAuth: []
responses:
"200":
description: Current payload rules configuration
content:
application/json:
schema:
$ref: "#/components/schemas/PayloadRulesConfig"
"401":
$ref: "#/components/responses/ManagementAuthenticationRequired"
"403":
$ref: "#/components/responses/ManagementInvalidToken"
"500":
description: Failed to read payload rules configuration
content:
application/json:
schema:
$ref: "#/components/schemas/ApiErrorResponse"
put:
tags: [Settings]
summary: Update payload rules configuration
description: |
Persists and hot reloads payload rules. The legacy input field `default-raw` is accepted
on writes and normalized to `defaultRaw` in responses/runtime state.
Requires a dashboard management session cookie when management auth is enabled.
security:
- ManagementSessionAuth: []
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/UpdatePayloadRulesRequest"
responses:
"200":
description: Updated payload rules configuration
content:
application/json:
schema:
$ref: "#/components/schemas/PayloadRulesConfig"
"400":
$ref: "#/components/responses/ValidationError"
"401":
$ref: "#/components/responses/ManagementAuthenticationRequired"
"403":
$ref: "#/components/responses/ManagementInvalidToken"
"500":
description: Failed to update payload rules configuration
content:
application/json:
schema:
$ref: "#/components/schemas/ApiErrorResponse"
/api/settings/combo-defaults:
get:
tags: [Settings]
summary: Get combo default settings
responses:
"200":
description: Default combo settings
/api/settings/proxy:
get:
tags: [Settings]
summary: Get proxy settings
responses:
"200":
description: Current proxy settings
patch:
tags: [Settings]
summary: Update proxy settings
responses:
"200":
description: Updated proxy settings
/api/settings/proxy/test:
post:
tags: [Settings]
summary: Test proxy connection
responses:
"200":
description: Test result
/api/settings/require-login:
post:
tags: [Settings]
summary: Toggle login requirement
responses:
"200":
description: Updated
/api/settings/ip-filter:
get:
tags: [Settings]
summary: Get IP filter configuration
description: Returns the current IP filter settings including blacklist, whitelist, and temp bans.
responses:
"200":
description: IP filter configuration
put:
tags: [Settings]
summary: Update IP filter configuration
description: |
Configure IP filtering with blacklist/whitelist modes, add/remove individual IPs, and manage temp bans.
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
enabled:
type: boolean
mode:
type: string
enum: [blacklist, whitelist]
blacklist:
type: array
items:
type: string
whitelist:
type: array
items:
type: string
addBlacklist:
type: string
removeBlacklist:
type: string
addWhitelist:
type: string
removeWhitelist:
type: string
tempBan:
type: object
properties:
ip:
type: string
durationMs:
type: integer
reason:
type: string
removeBan:
type: string
responses:
"200":
description: Updated IP filter configuration
/api/settings/system-prompt:
get:
tags: [Settings]
summary: Get system prompt configuration
description: Returns the current system prompt injection settings.
responses:
"200":
description: System prompt configuration
put:
tags: [Settings]
summary: Update system prompt configuration
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
prompt:
type: string
enabled:
type: boolean
responses:
"200":
description: Updated system prompt configuration
/api/settings/thinking-budget:
get:
tags: [Settings]
summary: Get thinking budget configuration
description: Returns the current thinking/reasoning budget settings for AI models.
responses:
"200":
description: Thinking budget configuration
put:
tags: [Settings]
summary: Update thinking budget configuration
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
mode:
type: string
description: Thinking mode (e.g., auto, manual, disabled)
customBudget:
type: integer
minimum: 0
maximum: 131072
effortLevel:
type: string
enum: [none, low, medium, high]
responses:
"200":
description: Updated thinking budget configuration
/api/rate-limit:
get:
tags: [Settings]
summary: Get rate limit configuration
responses:
"200":
description: Rate limit settings
post:
tags: [Settings]
summary: Update rate limit configuration
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Updated rate limit settings
/api/tags:
get:
tags: [System]
summary: List Ollama-compatible model tags
description: Returns models in Ollama /api/tags format for Ollama client compatibility
responses:
"200":
description: Ollama model tags
# ─── Usage & Analytics ─────────────────────────────────────────
/api/usage/analytics:
get:
tags: [Usage]
summary: Get usage analytics
parameters:
- name: period
in: query
schema:
type: string
enum: [day, week, month]
default: day
responses:
"200":
description: Usage analytics data
/api/usage/call-logs:
get:
tags: [Usage]
summary: Get call logs
parameters:
- name: limit
in: query
schema:
type: integer
default: 50
- name: offset
in: query
schema:
type: integer
default: 0
responses:
"200":
description: Paginated call logs
/api/usage/call-logs/{id}:
get:
tags: [Usage]
summary: Get a specific call log
parameters:
- $ref: "#/components/parameters/ResourceId"
responses:
"200":
description: Call log detail
/api/usage/{connectionId}:
get:
tags: [Usage]
summary: Get usage for a specific connection
parameters:
- name: connectionId
in: path
required: true
schema:
type: string
responses:
"200":
description: Connection usage data
/api/usage/history:
get:
tags: [Usage]
summary: Get usage history
responses:
"200":
description: Historical usage data
/api/usage/logs:
get:
tags: [Usage]
summary: Get usage logs
responses:
"200":
description: Usage log entries
/api/usage/proxy-logs:
get:
tags: [Usage]
summary: Get proxy logs
responses:
"200":
description: Proxy log entries
/api/usage/request-logs:
get:
tags: [Usage]
summary: Get request logs
responses:
"200":
description: Request log entries
/api/usage/budget:
get:
tags: [Usage]
summary: Get usage budget status
description: Returns current budget limits and consumption.
responses:
"200":
description: Budget status
post:
tags: [Usage]
summary: Configure usage budget
description: Set or update budget limits for usage tracking.
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Updated budget configuration
# ─── Pricing ───────────────────────────────────────────────────
/api/pricing:
get:
tags: [Pricing]
summary: Get model pricing
responses:
"200":
description: Current pricing configuration
post:
tags: [Pricing]
summary: Set model pricing
responses:
"200":
description: Updated pricing
/api/pricing/defaults:
get:
tags: [Pricing]
summary: Get default pricing
responses:
"200":
description: Default pricing data
/api/pricing/models:
get:
tags: [Pricing]
summary: Get pricing per model
description: Returns pricing information organized by model.
responses:
"200":
description: Per-model pricing data
# ─── Translator ────────────────────────────────────────────────
/api/translator/detect:
post:
tags: [Translator]
summary: Detect request format
description: Detects the API format of a request body (OpenAI, Claude, Gemini, etc.)
requestBody:
required: true
content:
application/json:
schema:
type: object
required: [body]
properties:
body:
type: object
responses:
"200":
description: Detected format
/api/translator/translate:
post:
tags: [Translator]
summary: Translate between formats
description: Converts a request between API formats (e.g. Claude → OpenAI)
requestBody:
required: true
content:
application/json:
schema:
type: object
required: [sourceFormat, targetFormat, body]
properties:
step:
type: string
sourceFormat:
type: string
targetFormat:
type: string
provider:
type: string
body:
type: object
responses:
"200":
description: Translated request
/api/translator/send:
post:
tags: [Translator]
summary: Send translated request to provider
requestBody:
required: true
content:
application/json:
schema:
type: object
required: [provider, body]
properties:
provider:
type: string
body:
type: object
responses:
"200":
description: Provider response (may be SSE stream)
/api/translator/history:
get:
tags: [Translator]
summary: Get translation history
description: Returns recent translation events for the Live Monitor
responses:
"200":
description: Translation history entries
# ─── CLI Remote Mode ───────────────────────────────────────────
/api/cli/connect:
post:
tags: [CLI Remote Mode]
summary: Exchange the management password for a scoped CLI access token
description: >
Remote-mode bootstrap. Public (password-gated) route: verifies the
management password with brute-force lockout, then mints an `oma_`
access token. The plaintext token is returned once.
requestBody:
required: true
content:
application/json:
schema:
type: object
required: [password]
properties:
password: { type: string }
name: { type: string }
scope: { type: string, enum: [read, write, admin] }
expiresInDays: { type: integer, minimum: 1, maximum: 3650 }
responses:
"200":
description: Token minted (token returned once)
"401":
description: Invalid password
"429":
description: Too many failed attempts
/api/cli/whoami:
get:
tags: [CLI Remote Mode]
summary: Report the current credential (scope, name, expiry)
responses:
"200":
description: Authenticated; access-token details when applicable
"401":
description: Authentication required
/api/cli/tokens:
get:
tags: [CLI Remote Mode]
summary: List access tokens (masked) — admin scope
responses:
"200":
description: Masked token list
"403":
description: Insufficient scope
post:
tags: [CLI Remote Mode]
summary: Create a scoped access token — admin scope
requestBody:
required: true
content:
application/json:
schema:
type: object
required: [name]
properties:
name: { type: string }
scope: { type: string, enum: [read, write, admin] }
expiresInDays: { type: integer, minimum: 1, maximum: 3650 }
responses:
"200":
description: Token created (token returned once)
"403":
description: Insufficient scope
/api/cli/tokens/{id}:
delete:
tags: [CLI Remote Mode]
summary: Revoke an access token by id or display prefix — admin scope
parameters:
- name: id
in: path
required: true
schema: { type: string }
responses:
"200":
description: Token revoked
"403":
description: Insufficient scope
"404":
description: Token not found or already revoked
# ─── CLI Tools ─────────────────────────────────────────────────
/api/cli-tools/backups:
get:
tags: [CLI Tools]
summary: List CLI tool backups
responses:
"200":
description: Backup list
post:
tags: [CLI Tools]
summary: Create CLI tool backup
responses:
"200":
description: Backup created
/api/cli-tools/runtime/{toolId}:
get:
tags: [CLI Tools]
summary: Get runtime status for a CLI tool
parameters:
- name: toolId
in: path
required: true
schema:
type: string
responses:
"200":
description: Runtime status
/api/cli-tools/guide-settings/{toolId}:
get:
tags: [CLI Tools]
summary: Get guide settings for a tool
parameters:
- name: toolId
in: path
required: true
schema:
type: string
responses:
"200":
description: Guide settings
/api/cli-tools/antigravity-mitm:
get:
tags: [CLI Tools]
summary: Get Antigravity MITM proxy settings
responses:
"200":
description: MITM proxy configuration
post:
tags: [CLI Tools]
summary: Update Antigravity MITM proxy settings
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Updated MITM proxy configuration
delete:
tags: [CLI Tools]
summary: Reset Antigravity MITM proxy settings
responses:
"200":
description: MITM proxy settings reset
/api/cli-tools/antigravity-mitm/alias:
get:
tags: [CLI Tools]
summary: Get Antigravity MITM alias configuration
responses:
"200":
description: Alias configuration
put:
tags: [CLI Tools]
summary: Update Antigravity MITM alias configuration
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Updated alias configuration
/api/cli-tools/claude-settings:
get:
tags: [CLI Tools]
summary: Get Claude CLI settings
responses:
"200":
description: Claude CLI configuration
post:
tags: [CLI Tools]
summary: Apply Claude CLI settings
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Claude CLI settings applied
delete:
tags: [CLI Tools]
summary: Reset Claude CLI settings
responses:
"200":
description: Claude CLI settings reset
/api/cli-tools/cline-settings:
get:
tags: [CLI Tools]
summary: Get Cline CLI settings
responses:
"200":
description: Cline CLI configuration
post:
tags: [CLI Tools]
summary: Apply Cline CLI settings
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Cline CLI settings applied
delete:
tags: [CLI Tools]
summary: Reset Cline CLI settings
responses:
"200":
description: Cline CLI settings reset
/api/cli-tools/codex-profiles:
get:
tags: [CLI Tools]
summary: Get Codex profiles
responses:
"200":
description: Codex profile list
post:
tags: [CLI Tools]
summary: Create Codex profile
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Profile created
put:
tags: [CLI Tools]
summary: Update Codex profile
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Profile updated
delete:
tags: [CLI Tools]
summary: Delete Codex profile
responses:
"200":
description: Profile deleted
/api/cli-tools/codex-settings:
get:
tags: [CLI Tools]
summary: Get Codex CLI settings
responses:
"200":
description: Codex CLI configuration
post:
tags: [CLI Tools]
summary: Apply Codex CLI settings
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Codex CLI settings applied
delete:
tags: [CLI Tools]
summary: Reset Codex CLI settings
responses:
"200":
description: Codex CLI settings reset
/api/cli-tools/droid-settings:
get:
tags: [CLI Tools]
summary: Get Droid CLI settings
responses:
"200":
description: Droid CLI configuration
post:
tags: [CLI Tools]
summary: Apply Droid CLI settings
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Droid CLI settings applied
delete:
tags: [CLI Tools]
summary: Reset Droid CLI settings
responses:
"200":
description: Droid CLI settings reset
/api/cli-tools/kilo-settings:
get:
tags: [CLI Tools]
summary: Get Kilo CLI settings
responses:
"200":
description: Kilo CLI configuration
post:
tags: [CLI Tools]
summary: Apply Kilo CLI settings
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Kilo CLI settings applied
delete:
tags: [CLI Tools]
summary: Reset Kilo CLI settings
responses:
"200":
description: Kilo CLI settings reset
/api/cli-tools/openclaw-settings:
get:
tags: [CLI Tools]
summary: Get OpenClaw CLI settings
responses:
"200":
description: OpenClaw CLI configuration
post:
tags: [CLI Tools]
summary: Apply OpenClaw CLI settings
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: OpenClaw CLI settings applied
delete:
tags: [CLI Tools]
summary: Reset OpenClaw CLI settings
responses:
"200":
description: OpenClaw CLI settings reset
# ─── Embedded Services ─────────────────────────────────────────
# All routes LOCAL_ONLY (loopback only) — hard rule #17.
# See docs/frameworks/EMBEDDED-SERVICES.md for full reference.
/api/services/9router/install:
post:
tags: [Embedded Services]
summary: Install 9Router from npm
description: >-
Installs the `9router` npm package under DATA_DIR/services/9router/.
Uses execFile (no shell interpolation — hard rule #13).
**LOCAL_ONLY** — loopback only.
requestBody:
required: false
content:
application/json:
schema:
type: object
properties:
version:
type: string
default: latest
description: npm version tag or semver to install
responses:
"200":
description: Install succeeded
content:
application/json:
schema:
type: object
properties:
ok:
type: boolean
installedVersion:
type: string
path:
type: string
"400":
description: Invalid request body
"500":
description: npm install failed
/api/services/9router/start:
post:
tags: [Embedded Services]
summary: Start 9Router
description: >-
Spawns the 9Router process. Idempotent if already running.
**LOCAL_ONLY** — loopback only.
responses:
"200":
description: Service started (or already running)
content:
application/json:
schema:
$ref: "#/components/schemas/ServiceStatus"
"409":
description: 9Router is not installed
"503":
description: Start failed
/api/services/9router/stop:
post:
tags: [Embedded Services]
summary: Stop 9Router
description: >-
Gracefully stops 9Router (SIGTERM → 15 s → SIGKILL). Idempotent.
**LOCAL_ONLY** — loopback only.
responses:
"200":
description: Service stopped
content:
application/json:
schema:
$ref: "#/components/schemas/ServiceStatus"
"503":
description: Stop failed
/api/services/9router/restart:
post:
tags: [Embedded Services]
summary: Restart 9Router
description: >-
Equivalent to stop() then start() under the operation lock.
**LOCAL_ONLY** — loopback only.
responses:
"200":
description: Service restarted
content:
application/json:
schema:
$ref: "#/components/schemas/ServiceStatus"
/api/services/9router/update:
post:
tags: [Embedded Services]
summary: Update 9Router to a newer npm version
description: >-
Stops the service (if running), installs the newer npm version, then restarts.
**LOCAL_ONLY** — loopback only.
requestBody:
required: false
content:
application/json:
schema:
type: object
properties:
version:
type: string
default: latest
responses:
"200":
description: Update succeeded
content:
application/json:
schema:
type: object
properties:
ok:
type: boolean
previousVersion:
type: string
installedVersion:
type: string
"400":
description: Invalid request body
"500":
description: Update failed
/api/services/9router/rotate-key:
post:
tags: [Embedded Services]
summary: Rotate the 9Router API key
description: >-
Generates a new API key, encrypts it at-rest, and restarts the service to
apply it. The plaintext key is never returned.
**LOCAL_ONLY** — loopback only.
responses:
"200":
description: Key rotated
content:
application/json:
schema:
type: object
properties:
keyRotated:
type: boolean
restarted:
type: boolean
"500":
description: Rotation failed
/api/services/9router/status:
get:
tags: [Embedded Services]
summary: Get 9Router status
description: >-
Returns combined live supervisor state and DB metadata.
**LOCAL_ONLY** — loopback only.
responses:
"200":
description: Status response
content:
application/json:
schema:
$ref: "#/components/schemas/ServiceStatusExtended"
"500":
description: Status read failed
/api/services/9router/auto-start:
post:
tags: [Embedded Services]
summary: Toggle 9Router auto-start
description: >-
When enabled, 9Router starts automatically on the next OmniRoute boot.
**LOCAL_ONLY** — loopback only.
requestBody:
required: true
content:
application/json:
schema:
type: object
required: [enabled]
properties:
enabled:
type: boolean
responses:
"200":
description: Auto-start flag updated
content:
application/json:
schema:
type: object
properties:
autoStart:
type: boolean
"400":
description: Invalid request body
/api/services/cliproxy/install:
post:
tags: [Embedded Services]
summary: Install CLIProxyAPI from npm
description: >-
Installs the CLIProxyAPI package under DATA_DIR/services/cliproxy/.
**LOCAL_ONLY** — loopback only.
requestBody:
required: false
content:
application/json:
schema:
type: object
properties:
version:
type: string
default: latest
responses:
"200":
description: Install succeeded
content:
application/json:
schema:
type: object
properties:
ok:
type: boolean
installedVersion:
type: string
"400":
description: Invalid request body
"500":
description: npm install failed
/api/services/cliproxy/start:
post:
tags: [Embedded Services]
summary: Start CLIProxyAPI
description: >-
Spawns the CLIProxyAPI process. Idempotent if already running.
**LOCAL_ONLY** — loopback only.
responses:
"200":
description: Service started
content:
application/json:
schema:
$ref: "#/components/schemas/ServiceStatus"
"409":
description: CLIProxyAPI is not installed
"503":
description: Start failed
/api/services/cliproxy/stop:
post:
tags: [Embedded Services]
summary: Stop CLIProxyAPI
description: >-
Gracefully stops CLIProxyAPI. Idempotent.
**LOCAL_ONLY** — loopback only.
responses:
"200":
description: Service stopped
content:
application/json:
schema:
$ref: "#/components/schemas/ServiceStatus"
/api/services/cliproxy/restart:
post:
tags: [Embedded Services]
summary: Restart CLIProxyAPI
description: >-
stop() then start() under the operation lock.
**LOCAL_ONLY** — loopback only.
responses:
"200":
description: Service restarted
content:
application/json:
schema:
$ref: "#/components/schemas/ServiceStatus"
/api/services/cliproxy/update:
post:
tags: [Embedded Services]
summary: Update CLIProxyAPI to a newer npm version
description: >-
Stops, installs newer version, restarts.
**LOCAL_ONLY** — loopback only.
requestBody:
required: false
content:
application/json:
schema:
type: object
properties:
version:
type: string
default: latest
responses:
"200":
description: Update succeeded
content:
application/json:
schema:
type: object
properties:
ok:
type: boolean
installedVersion:
type: string
"500":
description: Update failed
/api/services/cliproxy/status:
get:
tags: [Embedded Services]
summary: Get CLIProxyAPI status
description: >-
Returns live supervisor state and DB metadata (no apiKeyMasked — CLIProxyAPI
does not use an injected API key).
**LOCAL_ONLY** — loopback only.
responses:
"200":
description: Status response
content:
application/json:
schema:
$ref: "#/components/schemas/ServiceStatus"
/api/services/cliproxy/auto-start:
post:
tags: [Embedded Services]
summary: Toggle CLIProxyAPI auto-start
description: >-
When enabled, CLIProxyAPI starts automatically on the next OmniRoute boot.
**LOCAL_ONLY** — loopback only.
requestBody:
required: true
content:
application/json:
schema:
type: object
required: [enabled]
properties:
enabled:
type: boolean
responses:
"200":
description: Auto-start flag updated
content:
application/json:
schema:
type: object
properties:
autoStart:
type: boolean
"400":
description: Invalid request body
/api/services/{name}/logs:
get:
tags: [Embedded Services]
summary: Stream service logs via SSE
description: >-
Returns a Server-Sent Events stream from the service's in-memory ring buffer
(5 MB, circular). Sends a `snapshot` event with historical lines first, then
live `log` events, plus a `heartbeat` every 15 s.
**LOCAL_ONLY** — loopback only.
parameters:
- name: name
in: path
required: true
schema:
type: string
enum: [9router, cliproxy]
- name: tail
in: query
schema:
type: integer
default: 200
maximum: 1000
description: Number of historical lines to include in the initial snapshot
- name: filter
in: query
schema:
type: string
maxLength: 200
description: >-
Case-insensitive substring filter applied to log lines.
No regex — ReDoS-safe by design.
responses:
"200":
description: SSE log stream
content:
text/event-stream:
schema:
type: string
description: >-
Events: `snapshot` (LogLine[]), `log` (LogLine), `heartbeat` ({})
"400":
description: filter parameter exceeds maximum length
"404":
description: Service not found
# ─── OAuth ─────────────────────────────────────────────────────
/api/oauth/{provider}/{action}:
get:
tags: [OAuth]
summary: OAuth flow handler
description: Handles OAuth authorization and callback for providers
parameters:
- name: provider
in: path
required: true
schema:
type: string
- name: action
in: path
required: true
schema:
type: string
enum: [authorize, callback, refresh, status]
responses:
"200":
description: OAuth flow response
"302":
description: Redirect to provider auth page
/api/oauth/cursor/auto-import:
get:
tags: [OAuth]
summary: Auto-import Cursor OAuth credentials
description: Automatically detects and imports Cursor credentials from local config.
responses:
"200":
description: Import result
/api/oauth/cursor/import:
get:
tags: [OAuth]
summary: Get Cursor import status
responses:
"200":
description: Current import status
post:
tags: [OAuth]
summary: Import Cursor OAuth credentials
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Credentials imported
/api/oauth/kiro/auto-import:
get:
tags: [OAuth]
summary: Auto-import Kiro OAuth credentials
description: Automatically detects and imports Kiro credentials from local config.
responses:
"200":
description: Import result
/api/oauth/kiro/import:
get:
tags: [OAuth]
summary: Get Kiro import status
responses:
"200":
description: Current import status
post:
tags: [OAuth]
summary: Import Kiro OAuth credentials
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Credentials imported
/api/oauth/kiro/social-authorize:
get:
tags: [OAuth]
summary: Initiate Kiro social OAuth authorization
description: Starts the social OAuth flow for Kiro.
responses:
"302":
description: Redirect to OAuth provider
/api/oauth/kiro/social-exchange:
post:
tags: [OAuth]
summary: Exchange Kiro social OAuth token
description: Exchanges the authorization code for access tokens.
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Token exchange result
# ─── Cloud ─────────────────────────────────────────────────────
/api/cloud/auth:
post:
tags: [Cloud]
summary: Authenticate with cloud worker
description: Authenticates with the OmniRoute cloud worker for remote access.
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Authentication result
/api/cloud/credentials/update:
put:
tags: [Cloud]
summary: Update cloud worker credentials
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Credentials updated
/api/cloud/model/resolve:
post:
tags: [Cloud]
summary: Resolve model via cloud
description: Resolves a model request through the cloud worker.
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Resolved model info
/api/cloud/models/alias:
get:
tags: [Cloud]
summary: Get cloud model aliases
responses:
"200":
description: Cloud model alias list
put:
tags: [Cloud]
summary: Update cloud model alias
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Alias updated
# ─── Fallback ──────────────────────────────────────────────────
/api/fallback/chains:
get:
tags: [Fallback]
summary: List fallback chains
description: Returns all registered fallback chains for model routing.
responses:
"200":
description: Fallback chain list
post:
tags: [Fallback]
summary: Create fallback chain
description: Registers a fallback routing chain for a model.
requestBody:
required: true
content:
application/json:
schema:
type: object
required: [model, chain]
properties:
model:
type: string
chain:
type: array
items:
type: object
properties:
provider:
type: string
priority:
type: integer
enabled:
type: boolean
responses:
"200":
description: Fallback chain created
delete:
tags: [Fallback]
summary: Delete fallback chain
requestBody:
required: true
content:
application/json:
schema:
type: object
required: [model]
properties:
model:
type: string
responses:
"200":
description: Fallback chain deleted
# ─── System ────────────────────────────────────────────────────
/api/auth/login:
post:
tags: [System]
summary: Authenticate user
requestBody:
required: true
content:
application/json:
schema:
type: object
required: [password]
properties:
password:
type: string
minLength: 1
responses:
"200":
description: JWT token returned
"400":
description: Invalid login request
"401":
description: Invalid password
"403":
description: Password setup required
"429":
description: Too many failed attempts
/api/auth/logout:
post:
tags: [System]
summary: Log out
responses:
"200":
description: Session cleared
/api/init:
get:
tags: [System]
summary: Initialize application
responses:
"200":
description: Init status
/api/restart:
post:
tags: [System]
summary: Restart the application
responses:
"200":
description: Restart initiated
/api/shutdown:
post:
tags: [System]
summary: Shutdown the application
x-always-protected: true
responses:
"200":
description: Shutdown initiated
/api/db-backups:
get:
tags: [System]
summary: List database backups
responses:
"200":
description: Backup list
post:
tags: [System]
summary: Create database backup
responses:
"200":
description: Backup created
patch:
tags: [System]
summary: Save database backup retention settings
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
keepLatest:
type: integer
minimum: 1
maximum: 200
retentionDays:
type: integer
minimum: 0
maximum: 3650
responses:
"200":
description: Backup retention settings saved
/api/storage/health:
get:
tags: [System]
summary: Check storage health
responses:
"200":
description: Storage health status
/api/sync/cloud:
post:
tags: [System]
summary: Sync with cloud
responses:
"200":
description: Sync result
/api/sync/initialize:
post:
tags: [System]
summary: Initialize cloud sync
responses:
"200":
description: Sync initialized
# ─── Resilience & Monitoring ────────────────────────────────────
/api/resilience:
get:
tags: [System]
summary: Get resilience configuration
responses:
"200":
description: Request queue, connection cooldown, provider breaker, and wait settings
patch:
tags: [System]
summary: Update resilience configuration
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Updated resilience configuration
/api/resilience/reset:
post:
tags: [System]
summary: Reset circuit breakers
responses:
"200":
description: Circuit breakers reset
/api/monitoring/health:
get:
tags: [System]
summary: System health check
description: Returns system health including uptime, memory, circuit breakers, rate limits
responses:
"200":
description: Health status
/api/rate-limits:
get:
tags: [System]
summary: Get per-account rate limit status
responses:
"200":
description: Rate limit status by account
/api/sessions:
get:
tags: [System]
summary: Get active sessions
responses:
"200":
description: Active session list
/api/cache:
get:
tags: [System]
summary: Get cache statistics
responses:
"200":
description: Semantic cache and idempotency stats
delete:
tags: [System]
summary: Clear all caches
responses:
"200":
description: Caches cleared
/api/cache/stats:
get:
tags: [System]
summary: Get detailed cache statistics
description: Returns detailed statistics for all cache layers.
responses:
"200":
description: Detailed cache stats
delete:
tags: [System]
summary: Clear cache statistics
responses:
"200":
description: Cache stats cleared
# ─── Telemetry & Token Health ───────────────────────────────────
/api/telemetry/summary:
get:
tags: [Telemetry]
summary: Get telemetry summary
description: Returns aggregated telemetry data including request metrics and performance stats.
responses:
"200":
description: Telemetry summary data
/api/token-health:
get:
tags: [Telemetry]
summary: Get token health status
description: Returns health status of OAuth tokens across all providers.
responses:
"200":
description: Token health status
# ─── Evals & Policies ──────────────────────────────────────────
/api/evals:
get:
tags: [System]
summary: List eval suites
responses:
"200":
description: Eval suite list
post:
tags: [System]
summary: Run evaluation
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Eval results
/api/evals/{suiteId}:
get:
tags: [System]
summary: Get eval suite details
parameters:
- name: suiteId
in: path
required: true
schema:
type: string
responses:
"200":
description: Eval suite details
/api/policies:
get:
tags: [System]
summary: List routing policies
responses:
"200":
description: Policy list
post:
tags: [System]
summary: Create routing policy
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"201":
description: Created policy
delete:
tags: [System]
summary: Delete routing policy
responses:
"200":
description: Policy deleted
/api/compliance/audit-log:
get:
tags: [System]
summary: Get compliance audit log
description: >
Returns paginated audit log entries. Use `level=high` to filter to
high-level actions only (powers the Activity feed). Use `level=all`
(default) for full compliance table.
security:
- bearerAuth: []
parameters:
- name: level
in: query
schema:
type: string
enum: [high, all]
default: all
description: "high = Activity feed events only; all = all audit events"
- name: action
in: query
schema:
type: string
description: Filter by exact action string (e.g. "provider.added")
- name: actor
in: query
schema:
type: string
description: Filter by actor identifier
- name: limit
in: query
schema:
type: integer
default: 50
maximum: 500
- name: offset
in: query
schema:
type: integer
default: 0
responses:
"200":
description: Audit log entries
"401":
description: Unauthorized
"500":
description: Internal server error
# ─── Quota Sharing (Group B, plan 22) ────────────────────────────
/api/quota/pools:
get:
tags: [Quota]
summary: List quota pools
security:
- bearerAuth: []
responses:
"200":
description: Array of QuotaPool objects
content:
application/json:
schema:
type: array
items:
$ref: "#/components/schemas/QuotaPool"
"401":
description: Unauthorized
"500":
description: Internal server error
post:
tags: [Quota]
summary: Create quota pool
security:
- bearerAuth: []
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/PoolCreate"
responses:
"201":
description: Pool created
content:
application/json:
schema:
$ref: "#/components/schemas/QuotaPool"
"400":
description: Validation error (Zod)
"401":
description: Unauthorized
"500":
description: Internal server error
/api/quota/pools/{id}:
get:
tags: [Quota]
summary: Get quota pool by ID
security:
- bearerAuth: []
parameters:
- name: id
in: path
required: true
schema:
type: string
responses:
"200":
description: QuotaPool object
content:
application/json:
schema:
$ref: "#/components/schemas/QuotaPool"
"401":
description: Unauthorized
"404":
description: Pool not found
"500":
description: Internal server error
patch:
tags: [Quota]
summary: Update quota pool (name or allocations)
security:
- bearerAuth: []
parameters:
- name: id
in: path
required: true
schema:
type: string
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/PoolUpdate"
responses:
"200":
description: Updated pool
"400":
description: Validation error
"401":
description: Unauthorized
"404":
description: Pool not found
"500":
description: Internal server error
delete:
tags: [Quota]
summary: Delete quota pool
security:
- bearerAuth: []
parameters:
- name: id
in: path
required: true
schema:
type: string
responses:
"204":
description: Deleted
"401":
description: Unauthorized
"404":
description: Pool not found
"500":
description: Internal server error
/api/quota/pools/{id}/usage:
get:
tags: [Quota]
summary: Get pool usage snapshot (per-key consumption + burn rate)
security:
- bearerAuth: []
parameters:
- name: id
in: path
required: true
schema:
type: string
responses:
"200":
description: PoolUsageSnapshot
content:
application/json:
schema:
$ref: "#/components/schemas/PoolUsageSnapshot"
"401":
description: Unauthorized
"404":
description: Pool not found
"500":
description: Internal server error
/api/quota/plans:
get:
tags: [Quota]
summary: List resolved provider plans (catalog + manual overrides)
security:
- bearerAuth: []
responses:
"200":
description: Array of ProviderPlan
"401":
description: Unauthorized
"500":
description: Internal server error
/api/quota/plans/{connectionId}:
get:
tags: [Quota]
summary: Get resolved plan for a connection
security:
- bearerAuth: []
parameters:
- name: connectionId
in: path
required: true
schema:
type: string
responses:
"200":
description: ProviderPlan (source = auto | manual)
"401":
description: Unauthorized
"404":
description: Connection not found
"500":
description: Internal server error
put:
tags: [Quota]
summary: Upsert manual plan override for a connection
security:
- bearerAuth: []
parameters:
- name: connectionId
in: path
required: true
schema:
type: string
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/PlanUpsert"
responses:
"200":
description: Updated plan
"400":
description: Validation error (Zod)
"401":
description: Unauthorized
"500":
description: Internal server error
delete:
tags: [Quota]
summary: Delete manual plan override (reverts to catalog/auto)
security:
- bearerAuth: []
parameters:
- name: connectionId
in: path
required: true
schema:
type: string
responses:
"204":
description: Override deleted
"401":
description: Unauthorized
"404":
description: Override not found
"500":
description: Internal server error
/api/quota/preview:
get:
tags: [Quota]
summary: Dry-run quota enforcement check (preview only, no consumption recorded)
security:
- bearerAuth: []
parameters:
- name: apiKeyId
in: query
required: true
schema:
type: string
- name: poolId
in: query
required: true
schema:
type: string
- name: estimatedTokens
in: query
schema:
type: number
- name: estimatedUsd
in: query
schema:
type: number
- name: estimatedRequests
in: query
schema:
type: integer
responses:
"200":
description: EnforceDecision (allow/block + reason)
"400":
description: Validation error (Zod)
"401":
description: Unauthorized
"500":
description: Internal server error
/api/settings/quota-store:
get:
tags: [Settings]
summary: Get current quota store driver settings
description: Redis URL is masked in the response (shows only scheme+host).
security:
- bearerAuth: []
responses:
"200":
description: QuotaStoreSettings (driver + masked redisUrl)
"401":
description: Unauthorized
"500":
description: Internal server error
put:
tags: [Settings]
summary: Update quota store driver settings
security:
- bearerAuth: []
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/QuotaStoreSettings"
responses:
"200":
description: Settings updated
"400":
description: Validation error (Zod) — e.g. driver=redis without valid URL
"401":
description: Unauthorized
"500":
description: Internal server error
# ─── v1beta (Gemini-Compatible) ─────────────────────────────────
/api/v1beta/models:
get:
tags: [Models]
summary: List models (Gemini format)
description: Returns models in Gemini v1beta format for native SDK compatibility
security:
- BearerAuth: []
responses:
"200":
description: Model list in Gemini format
/api/v1beta/models/{path}:
post:
tags: [Models]
summary: Gemini generateContent
description: Gemini-compatible generateContent endpoint
security:
- BearerAuth: []
parameters:
- name: path
in: path
required: true
schema:
type: string
requestBody:
required: true
content:
application/json:
schema:
type: object
responses:
"200":
description: Generated content
# ─── AgentBridge ──────────────────────────────────────────────
/api/tools/agent-bridge/agents:
get:
tags: [AgentBridge]
summary: List all 9 IDE agents with current state
description: >-
Returns the state (dns_enabled, cert_trusted, setup_completed, last_started_at,
last_error) for all 9 configured IDE agents. LOCAL_ONLY.
responses:
"200":
description: Array of agent state rows
content:
application/json:
schema:
type: array
items:
$ref: "#/components/schemas/AgentBridgeAgentState"
"403":
description: Loopback-only — request came from a non-loopback address
/api/tools/agent-bridge/state:
get:
tags: [AgentBridge]
summary: Get global AgentBridge server state
description: Returns running status, port, cert info, and intercepted request count.
responses:
"200":
description: Server state
content:
application/json:
schema:
$ref: "#/components/schemas/AgentBridgeServerState"
/api/tools/agent-bridge/server:
post:
tags: [AgentBridge]
summary: Control AgentBridge MITM server
description: Start, stop, restart, trust-cert, or regenerate-cert. SPAWN_CAPABLE.
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/AgentBridgeServerAction"
responses:
"200":
description: Action executed
"400":
description: Invalid action
"409":
description: Port 443 conflict
/api/tools/agent-bridge/agents/{agentId}/dns:
post:
tags: [AgentBridge]
summary: Enable or disable DNS for one agent
description: Adds or removes /etc/hosts entries for the agent's host list. SPAWN_CAPABLE.
parameters:
- name: agentId
in: path
required: true
schema:
$ref: "#/components/schemas/AgentId"
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/AgentBridgeDnsAction"
responses:
"200":
description: DNS updated
"400":
description: Validation error
/api/tools/agent-bridge/agents/{agentId}/mappings:
get:
tags: [AgentBridge]
summary: Get model mappings for one agent
parameters:
- name: agentId
in: path
required: true
schema:
$ref: "#/components/schemas/AgentId"
responses:
"200":
description: Array of source→target model mappings
content:
application/json:
schema:
type: array
items:
$ref: "#/components/schemas/AgentBridgeMappingRow"
put:
tags: [AgentBridge]
summary: Update model mappings for one agent
parameters:
- name: agentId
in: path
required: true
schema:
$ref: "#/components/schemas/AgentId"
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/AgentBridgeMappingPut"
responses:
"200":
description: Mappings updated
/api/tools/agent-bridge/bypass:
get:
tags: [AgentBridge]
summary: List bypass patterns (hosts never decrypted)
responses:
"200":
description: Bypass patterns
content:
application/json:
schema:
type: array
items:
$ref: "#/components/schemas/AgentBridgeBypassRow"
put:
tags: [AgentBridge]
summary: Update user bypass patterns
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/AgentBridgeBypassUpsert"
responses:
"200":
description: Patterns updated
/api/tools/agent-bridge/cert:
post:
tags: [AgentBridge]
summary: Download or regenerate the AgentBridge CA certificate
requestBody:
required: true
content:
application/json:
schema:
type: object
required: [action]
properties:
action:
type: string
enum: [download, regenerate]
responses:
"200":
description: CA certificate PEM (download) or regeneration confirmation
/api/tools/agent-bridge/upstream-ca:
get:
tags: [AgentBridge]
summary: Get configured upstream CA cert path
responses:
"200":
description: Upstream CA configuration
content:
application/json:
schema:
type: object
properties:
path:
type: string
nullable: true
post:
tags: [AgentBridge]
summary: Set upstream CA cert path for corporate TLS environments
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/AgentBridgeUpstreamCaPost"
responses:
"200":
description: Upstream CA configured
"400":
description: Path does not exist or is not readable
# ─── Traffic Inspector ─────────────────────────────────────────
/api/tools/traffic-inspector/requests:
get:
tags: [Traffic Inspector]
summary: List intercepted requests (filterable)
parameters:
- name: profile
in: query
schema:
type: string
enum: [llm, custom, all]
- name: host
in: query
schema:
type: string
- name: agent
in: query
schema:
$ref: "#/components/schemas/AgentId"
- name: status
in: query
schema:
type: string
enum: ["2xx", "3xx", "4xx", "5xx", error]
- name: source
in: query
schema:
$ref: "#/components/schemas/CaptureSource"
- name: sessionId
in: query
schema:
type: string
format: uuid
responses:
"200":
description: Array of intercepted requests
content:
application/json:
schema:
type: array
items:
$ref: "#/components/schemas/InterceptedRequest"
delete:
tags: [Traffic Inspector]
summary: Clear the in-memory traffic buffer
responses:
"204":
description: Buffer cleared
/api/tools/traffic-inspector/requests/{id}:
get:
tags: [Traffic Inspector]
summary: Get a single intercepted request by ID
parameters:
- name: id
in: path
required: true
schema:
type: string
format: uuid
responses:
"200":
description: Intercepted request details
content:
application/json:
schema:
$ref: "#/components/schemas/InterceptedRequest"
"404":
description: Request not found in buffer
/api/tools/traffic-inspector/requests/{id}/replay:
post:
tags: [Traffic Inspector]
summary: Replay a captured request through OmniRoute router
description: Re-executes the original request body against /v1/chat/completions. Consumes quota.
parameters:
- name: id
in: path
required: true
schema:
type: string
format: uuid
responses:
"200":
description: Replay response (streaming or JSON)
"404":
description: Request not found
/api/tools/traffic-inspector/requests/{id}/annotation:
put:
tags: [Traffic Inspector]
summary: Save or update annotation on a request
parameters:
- name: id
in: path
required: true
schema:
type: string
format: uuid
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/InspectorAnnotationPut"
responses:
"200":
description: Annotation saved
/api/tools/traffic-inspector/ws:
get:
tags: [Traffic Inspector]
summary: Live WebSocket stream of intercepted requests
description: >-
Upgrade to WebSocket. On connect, server sends `{type:"snapshot", data:[...]}`.
Subsequent events: `{type:"new", data:{...}}`, `{type:"update", data:{...}}`,
`{type:"clear"}`. LOCAL_ONLY.
responses:
"101":
description: WebSocket upgrade successful
"403":
description: Non-loopback origin rejected
/api/tools/traffic-inspector/export.har:
get:
tags: [Traffic Inspector]
summary: Export current filtered request list as HAR 1.2
parameters:
- name: profile
in: query
schema:
type: string
enum: [llm, custom, all]
- name: sessionId
in: query
schema:
type: string
format: uuid
responses:
"200":
description: HAR file (JSON)
content:
application/json:
schema:
type: object
description: HAR 1.2 format
/api/tools/traffic-inspector/hosts:
get:
tags: [Traffic Inspector]
summary: List custom capture hosts
responses:
"200":
description: Custom hosts list
content:
application/json:
schema:
type: array
items:
$ref: "#/components/schemas/InspectorCustomHost"
post:
tags: [Traffic Inspector]
summary: Add a custom capture host (edits /etc/hosts)
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/InspectorCustomHostCreate"
responses:
"201":
description: Host added
"409":
description: Host already exists
/api/tools/traffic-inspector/hosts/{host}:
delete:
tags: [Traffic Inspector]
summary: Remove a custom capture host
parameters:
- name: host
in: path
required: true
schema:
type: string
responses:
"204":
description: Host removed
patch:
tags: [Traffic Inspector]
summary: Toggle enabled state of a custom host
parameters:
- name: host
in: path
required: true
schema:
type: string
requestBody:
required: true
content:
application/json:
schema:
type: object
required: [enabled]
properties:
enabled:
type: boolean
responses:
"200":
description: Host updated
/api/tools/traffic-inspector/capture-modes:
get:
tags: [Traffic Inspector]
summary: Get state of all 4 capture modes
responses:
"200":
description: Capture modes state
content:
application/json:
schema:
$ref: "#/components/schemas/InspectorCaptureModesState"
/api/tools/traffic-inspector/capture-modes/http-proxy:
post:
tags: [Traffic Inspector]
summary: Start or stop the HTTP_PROXY listener (port 8080)
description: SPAWN_CAPABLE — spawns a net.Server listener.
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/InspectorCaptureModeAction"
responses:
"200":
description: Action executed
"409":
description: Port conflict (EADDRINUSE) when starting
/api/tools/traffic-inspector/capture-modes/system-proxy:
post:
tags: [Traffic Inspector]
summary: Apply or revert system-wide proxy settings
description: SPAWN_CAPABLE — executes networksetup/gsettings/netsh. Requires admin.
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/InspectorSystemProxyAction"
responses:
"200":
description: System proxy updated
"500":
description: OS command failed (permission error)
/api/tools/traffic-inspector/capture-modes/tls-intercept:
post:
tags: [Traffic Inspector]
summary: Toggle TLS body decryption in HTTP_PROXY mode
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/InspectorTlsInterceptToggle"
responses:
"200":
description: TLS intercept mode updated
/api/tools/traffic-inspector/sessions:
get:
tags: [Traffic Inspector]
summary: List all saved recording sessions
responses:
"200":
description: Sessions list
content:
application/json:
schema:
type: array
items:
$ref: "#/components/schemas/InspectorSession"
post:
tags: [Traffic Inspector]
summary: Start a new recording session
requestBody:
required: false
content:
application/json:
schema:
$ref: "#/components/schemas/InspectorSessionStart"
responses:
"201":
description: Session started
content:
application/json:
schema:
$ref: "#/components/schemas/InspectorSession"
/api/tools/traffic-inspector/sessions/{id}:
get:
tags: [Traffic Inspector]
summary: Get session snapshot (all captured requests)
parameters:
- name: id
in: path
required: true
schema:
type: string
format: uuid
responses:
"200":
description: Session with embedded requests
"404":
description: Session not found
patch:
tags: [Traffic Inspector]
summary: Stop or rename a recording session
parameters:
- name: id
in: path
required: true
schema:
type: string
format: uuid
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/InspectorSessionPatch"
responses:
"200":
description: Session updated
delete:
tags: [Traffic Inspector]
summary: Delete a recording session
parameters:
- name: id
in: path
required: true
schema:
type: string
format: uuid
responses:
"204":
description: Session deleted
/api/tools/traffic-inspector/sessions/{id}/export.har:
get:
tags: [Traffic Inspector]
summary: Export a recorded session as HAR 1.2
parameters:
- name: id
in: path
required: true
schema:
type: string
format: uuid
responses:
"200":
description: HAR file for this session
content:
application/json:
schema:
type: object
description: HAR 1.2 format
"404":
description: Session not found
/api/tools/traffic-inspector/internal/ingest:
post:
tags: [Traffic Inspector]
summary: Internal ingest endpoint for server.cjs passthrough path
description: >-
Accepts a serialized InterceptedRequest from the CJS MITM server for requests
that do not go through TypeScript handlers (e.g., passthrough hosts). Requires
INSPECTOR_INTERNAL_INGEST_TOKEN header. LOCAL_ONLY.
security: []
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/InterceptedRequest"
responses:
"204":
description: Ingested
"401":
description: Invalid or missing ingest token
# ─── OpenAPI Spec ──────────────────────────────────────────────
/api/openapi/spec:
get:
tags: [System]
summary: Get OpenAPI specification catalog
description: >-
Returns a structured JSON catalog parsed from this `openapi.yaml`,
including info, servers, tags, schemas, and a flat list of endpoints
(method, path, tags, summary, security, parameters, responses).
Used by the in-app API explorer.
responses:
"200":
description: Parsed OpenAPI catalog
content:
application/json:
schema:
type: object
properties:
info:
type: object
servers:
type: array
items:
type: object
tags:
type: array
items:
type: object
endpoints:
type: array
items:
type: object
properties:
method:
type: string
path:
type: string
tags:
type: array
items:
type: string
summary:
type: string
description:
type: string
security:
type: boolean
parameters:
type: array
items:
type: object
requestBody:
type: boolean
responses:
type: array
items:
type: string
schemas:
type: array
items:
type: string
"404":
description: openapi.yaml file not found on disk
"500":
description: Failed to parse OpenAPI spec
# ─── Agent Skills Catalog ────────────────────────────────────────────────────
/api/agent-skills:
get:
tags: [Agent Skills]
summary: List agent skills catalog
description: |
Returns the full 42-entry Agent Skills catalog with optional filtering.
Skills describe how to use OmniRoute's REST API and CLI — they are structured
SKILL.md documentation files discoverable by external agents, MCP clients, and
A2A orchestrators. No authentication required.
parameters:
- name: category
in: query
required: false
schema:
type: string
enum: [api, cli]
description: Filter by category (api = REST API skills, cli = CLI skills)
- name: area
in: query
required: false
schema:
type: string
description: Filter by area slug (e.g. "providers", "models", "cli-serve")
responses:
"200":
description: Catalog list
content:
application/json:
schema:
type: object
required: [skills, count, coverage]
properties:
skills:
type: array
items:
$ref: "#/components/schemas/AgentSkill"
count:
type: integer
coverage:
$ref: "#/components/schemas/SkillCoverage"
"400":
$ref: "#/components/responses/BadRequest"
"500":
$ref: "#/components/responses/InternalError"
/api/agent-skills/{id}:
get:
tags: [Agent Skills]
summary: Get a single agent skill
description: |
Returns metadata for a single agent skill by its canonical ID
(e.g. `omni-providers`, `cli-serve`). No authentication required.
parameters:
- name: id
in: path
required: true
schema:
type: string
pattern: "^[a-z][a-z0-9-]*$"
description: Canonical skill ID
example: omni-providers
responses:
"200":
description: Agent skill metadata
content:
application/json:
schema:
$ref: "#/components/schemas/AgentSkill"
"400":
$ref: "#/components/responses/BadRequest"
"404":
$ref: "#/components/responses/NotFound"
"500":
$ref: "#/components/responses/InternalError"
/api/agent-skills/{id}/raw:
get:
tags: [Agent Skills]
summary: Get raw SKILL.md content
description: |
Returns the SKILL.md content for a skill as `text/markdown`.
Resolution order: local filesystem `skills/{id}/SKILL.md` → GitHub raw URL (1-hour cache).
No authentication required.
parameters:
- name: id
in: path
required: true
schema:
type: string
pattern: "^[a-z][a-z0-9-]*$"
description: Canonical skill ID
example: omni-providers
responses:
"200":
description: SKILL.md content as Markdown
headers:
X-Skill-Source:
schema:
type: string
enum: [filesystem, github, generated]
description: Where the content was loaded from
X-Skill-Fetched-At:
schema:
type: string
format: date-time
description: ISO timestamp of when the content was fetched
Cache-Control:
schema:
type: string
description: "public, max-age=3600"
content:
text/markdown:
schema:
type: string
"400":
$ref: "#/components/responses/BadRequest"
"404":
$ref: "#/components/responses/NotFound"
"502":
description: Upstream GitHub fetch failed
content:
application/json:
schema:
$ref: "#/components/schemas/ErrorResponse"
"500":
$ref: "#/components/responses/InternalError"
/api/agent-skills/coverage:
get:
tags: [Agent Skills]
summary: Get SKILL.md coverage stats
description: |
Returns how many of the 22 API skills and 20 CLI skills have SKILL.md
files on the local filesystem vs the catalog totals. No authentication required.
responses:
"200":
description: Coverage stats
content:
application/json:
schema:
$ref: "#/components/schemas/SkillCoverage"
"500":
$ref: "#/components/responses/InternalError"
/api/agent-skills/generate:
post:
tags: [Agent Skills]
summary: Trigger SKILL.md generator
description: |
Runs the Agent Skills generator which writes `skills/{id}/SKILL.md` for
all 42 catalog entries (or a subset via `onlyIds`). Preserves
`<!-- skill:custom-start --> ... <!-- skill:custom-end -->` blocks.
**Requires management authentication.**
security:
- BearerAuth: []
- ManagementSessionAuth: []
requestBody:
required: false
content:
application/json:
schema:
type: object
properties:
dryRun:
type: boolean
default: true
description: "If true, reports what would be generated without writing files"
prune:
type: boolean
default: false
description: "If true, deletes skill directories not in the catalog"
onlyIds:
type: array
items:
type: string
description: "If provided, only regenerate these skill IDs"
responses:
"200":
description: Generator report
content:
application/json:
schema:
type: object
required: [generated, unchanged, pruned, orphansDetected, errors]
properties:
generated:
type: array
items:
type: string
description: IDs that got new/updated SKILL.md
unchanged:
type: array
items:
type: string
description: IDs whose content was already up to date
pruned:
type: array
items:
type: string
description: IDs whose directories were deleted (prune mode)
orphansDetected:
type: array
items:
type: string
description: Directories found in skills/ not in the catalog
errors:
type: array
items:
type: object
required: [id, error]
properties:
id:
type: string
error:
type: string
"400":
$ref: "#/components/responses/BadRequest"
"401":
$ref: "#/components/responses/Unauthorized"
"500":
$ref: "#/components/responses/InternalError"
"503":
description: Generator module not available
components:
securitySchemes:
BearerAuth:
type: http
scheme: bearer
description: API key obtained from the OmniRoute dashboard
ManagementSessionAuth:
type: apiKey
in: cookie
name: auth_token
description: Dashboard management session cookie for protected management routes
parameters:
ResourceId:
name: id
in: path
required: true
schema:
type: string
responses:
Unauthorized:
description: Missing or invalid API key
content:
application/json:
schema:
type: object
properties:
error:
type: string
example: Unauthorized
ManagementAuthenticationRequired:
description: Authentication required for management routes
content:
application/json:
schema:
$ref: "#/components/schemas/ApiErrorResponse"
example:
error:
message: Authentication required
type: invalid_request
requestId: 3f9f6f5a-509a-4b35-b0a7-2d2d99d73a01
ManagementInvalidToken:
description: Bearer tokens are not accepted for management routes
content:
application/json:
schema:
$ref: "#/components/schemas/ApiErrorResponse"
example:
error:
message: Invalid management token
type: invalid_request
requestId: 1b6a6ff8-d60c-4900-8d0a-25f81749f0a3
ValidationError:
description: Request body failed validation
content:
application/json:
schema:
$ref: "#/components/schemas/ValidationErrorResponse"
BadRequest:
description: The request was malformed or failed validation
content:
application/json:
schema:
$ref: "#/components/schemas/ApiErrorResponse"
example:
error:
message: Invalid request
type: invalid_request_error
requestId: 8c2b1d44-7a3e-4c91-9b0f-1e2d3c4b5a60
NotFound:
description: The requested resource was not found
content:
application/json:
schema:
$ref: "#/components/schemas/ApiErrorResponse"
example:
error:
message: Resource not found
type: not_found_error
requestId: 4d5e6f70-1a2b-3c4d-5e6f-7a8b9c0d1e2f
InternalError:
description: An unexpected server error occurred
content:
application/json:
schema:
$ref: "#/components/schemas/ApiErrorResponse"
example:
error:
message: Internal server error
type: api_error
requestId: 0a1b2c3d-4e5f-6a7b-8c9d-0e1f2a3b4c5d
schemas:
PlaygroundPreset:
type: object
required:
- id
- name
- endpoint
- model
- params
- created_at
properties:
id:
type: string
format: uuid
name:
type: string
maxLength: 100
endpoint:
type: string
description: Playground endpoint key (e.g. "chat.completions")
model:
type: string
system:
type: string
nullable: true
params:
type: object
additionalProperties: true
description: Serialized parameter values (temperature, max_tokens, etc.)
created_at:
type: string
format: date-time
PlaygroundPresetCreate:
type: object
required:
- name
- endpoint
- model
properties:
name:
type: string
minLength: 1
maxLength: 100
endpoint:
type: string
minLength: 1
model:
type: string
minLength: 1
system:
type: string
nullable: true
params:
type: object
additionalProperties: true
default: {}
MemoryEntry:
type: object
description: A single persisted memory entry
properties:
id:
type: string
description: UUID
apiKeyId:
type: string
sessionId:
type: string
nullable: true
type:
type: string
enum:
- factual
- episodic
- procedural
- semantic
key:
type: string
description: Stable upsert key (e.g. preference:i_prefer_python)
content:
type: string
metadata:
type: object
additionalProperties: true
createdAt:
type: string
format: date-time
updatedAt:
type: string
format: date-time
expiresAt:
type: string
format: date-time
nullable: true
needsReindex:
type: integer
description: 1 if the vector for this memory is stale or missing
MemorySettingsExtended:
type: object
description: Extended memory settings including 7 new fields from plan 21. All fields are optional for PUT (patch semantics).
properties:
enabled:
type: boolean
maxTokens:
type: integer
minimum: 0
maximum: 16000
retentionDays:
type: integer
minimum: 1
maximum: 365
strategy:
type: string
enum:
- recent
- semantic
- hybrid
skillsEnabled:
type: boolean
embeddingSource:
type: string
enum:
- remote
- static
- transformers
- auto
description: Which embedding source to use. "auto" = remote > static > transformers.
embeddingProviderModel:
type: string
nullable: true
description: Embedding provider/model in "provider/model" format (e.g. openai/text-embedding-3-small).
transformersEnabled:
type: boolean
description: Opt-in for Transformers.js local MiniLM model (~400MB RAM)
staticEnabled:
type: boolean
description: Opt-in for static potion-base-8M local model
rerankEnabled:
type: boolean
description: Enable reranking step (+200-500ms/req)
rerankProviderModel:
type: string
nullable: true
description: Rerank provider/model in "provider/model" format
vectorStore:
type: string
enum:
- sqlite-vec
- qdrant
- auto
description: Which vector backend to use
QdrantSettings:
type: object
description: Qdrant vector database configuration (read shape — no raw apiKey)
properties:
enabled:
type: boolean
host:
type: string
port:
type: integer
minimum: 1
maximum: 65535
collection:
type: string
embeddingModel:
type: string
hasApiKey:
type: boolean
apiKeyMasked:
type: string
nullable: true
description: First 4 chars of the configured API key, or null
QdrantHealthResult:
type: object
description: Result of a Qdrant liveness probe
properties:
ok:
type: boolean
latencyMs:
type: number
error:
type: string
nullable: true
description: Sanitized error message (no stack traces)
AgentSkill:
type: object
description: >-
Single entry in the Agent Skills catalog. Describes one OmniRoute REST API surface
(category: api) or CLI subcommand group (category: cli) with a canonical ID and a
link to its SKILL.md documentation file.
required: [id, name, description, category, area, rawUrl, githubUrl]
properties:
id:
type: string
pattern: "^[a-z][a-z0-9-]*$"
description: Canonical skill ID (e.g. "omni-providers", "cli-serve")
example: omni-providers
name:
type: string
minLength: 1
maxLength: 100
description: Human-readable skill name
example: Provider Management
description:
type: string
minLength: 1
maxLength: 2000
description: One-paragraph description of what the skill covers
category:
type: string
enum: [api, cli]
description: "api = REST API skill; cli = CLI subcommand skill"
area:
type: string
minLength: 1
maxLength: 50
description: Functional area slug (e.g. "providers", "combos-routing", "cli-serve")
example: providers
endpoints:
type: array
items:
type: string
description: REST API endpoints (present for api-category skills only)
example: ["POST /api/providers", "GET /api/providers/:id"]
cliCommands:
type: array
items:
type: string
description: CLI subcommand names (present for cli-category skills only)
example: ["providers list", "providers test", "providers rotate"]
icon:
type: string
description: Material symbol icon name for dashboard display
isEntry:
type: boolean
description: Whether this is a recommended starting point
isNew:
type: boolean
description: Whether this skill was added in a recent release
rawUrl:
type: string
format: uri
description: GitHub raw URL of the SKILL.md file
example: "https://raw.githubusercontent.com/diegosouzapw/OmniRoute/refs/heads/main/skills/omni-providers/SKILL.md"
githubUrl:
type: string
format: uri
description: GitHub blob URL for viewing the SKILL.md in the browser
example: "https://github.com/diegosouzapw/OmniRoute/blob/main/skills/omni-providers/SKILL.md"
SkillCoverage:
type: object
description: >-
Coverage statistics for the Agent Skills catalog: how many of the 22 REST API
skills and 20 CLI skills have generated SKILL.md files on the local filesystem.
required: [api, cli, totalSkills, generatedAt]
properties:
api:
type: object
required: [have, total]
properties:
have:
type: integer
minimum: 0
maximum: 22
description: Number of API skills with SKILL.md on disk
total:
type: integer
enum: [22]
description: Canonical API skill count (always 22)
cli:
type: object
required: [have, total]
properties:
have:
type: integer
minimum: 0
maximum: 20
description: Number of CLI skills with SKILL.md on disk
total:
type: integer
enum: [20]
description: Canonical CLI skill count (always 20)
totalSkills:
type: integer
minimum: 0
maximum: 42
description: Sum of api.have + cli.have
generatedAt:
type: string
format: date-time
description: ISO datetime when coverage was last computed
ErrorResponse:
type: object
description: Standard error response body
required: [error]
properties:
error:
type: object
required: [message]
properties:
message:
type: string
description: Human-readable error message (never includes stack traces)
code:
type: string
description: Machine-readable error code
# ─── AgentBridge Schemas ────────────────────────────────────────
AgentId:
type: string
enum:
- antigravity
- kiro
- copilot
- codex
- cursor
- zed
- claude-code
- open-code
- trae
description: One of the 9 supported IDE agents
AgentBridgeAgentState:
type: object
description: Per-agent MITM state
properties:
agent_id:
$ref: "#/components/schemas/AgentId"
dns_enabled:
type: boolean
cert_trusted:
type: boolean
setup_completed:
type: boolean
last_started_at:
type: string
format: date-time
nullable: true
last_error:
type: string
nullable: true
AgentBridgeServerState:
type: object
description: Global AgentBridge MITM server state
properties:
running:
type: boolean
port:
type: integer
example: 443
certReady:
type: boolean
interceptedCount:
type: integer
activeConnections:
type: integer
lastStartedAt:
type: string
format: date-time
nullable: true
AgentBridgeServerAction:
type: object
required: [action]
properties:
action:
type: string
enum: [start, stop, restart, trust-cert, regenerate-cert]
AgentBridgeDnsAction:
type: object
required: [enabled]
properties:
enabled:
type: boolean
AgentBridgeMappingRow:
type: object
properties:
agent_id:
$ref: "#/components/schemas/AgentId"
source_model:
type: string
example: gpt-4o
target_model:
type: string
example: claude-sonnet-4.7
updated_at:
type: string
format: date-time
AgentBridgeMappingPut:
type: object
required: [mappings]
properties:
mappings:
type: array
items:
type: object
required: [source, target]
properties:
source:
type: string
example: gpt-4o
target:
type: string
example: claude-sonnet-4.7
AgentBridgeBypassRow:
type: object
properties:
pattern:
type: string
example: "*.bank.*"
source:
type: string
enum: [default, user]
created_at:
type: string
format: date-time
AgentBridgeBypassUpsert:
type: object
required: [patterns]
properties:
patterns:
type: array
items:
type: string
example: ["*.bank.*", "*.gov.*"]
AgentBridgeUpstreamCaPost:
type: object
required: [path]
properties:
path:
type: string
description: Absolute path to a PEM file for corporate upstream CA
example: "/etc/ssl/certs/corporate-ca.pem"
# ─── Traffic Inspector Schemas ──────────────────────────────────
CaptureSource:
type: string
enum: [agent-bridge, custom-host, http-proxy, system-proxy]
DetectedKind:
type: string
enum: [llm, app, unknown]
InterceptedRequest:
type: object
description: A single intercepted HTTP request captured by the Traffic Inspector
required:
[
id,
source,
timestamp,
method,
host,
path,
requestHeaders,
requestSize,
responseHeaders,
responseSize,
status,
]
properties:
id:
type: string
format: uuid
source:
$ref: "#/components/schemas/CaptureSource"
agent:
$ref: "#/components/schemas/AgentId"
timestamp:
type: string
format: date-time
method:
type: string
example: POST
host:
type: string
example: api.githubcopilot.com
path:
type: string
example: /v1/chat/completions
requestHeaders:
type: object
additionalProperties:
type: string
requestBody:
type: string
nullable: true
description: Masked (secrets replaced with ***)
requestSize:
type: integer
responseHeaders:
type: object
additionalProperties:
type: string
responseBody:
type: string
nullable: true
responseSize:
type: integer
status:
oneOf:
- type: integer
- type: string
enum: [in-flight, error]
proxyLatencyMs:
type: number
nullable: true
upstreamLatencyMs:
type: number
nullable: true
totalLatencyMs:
type: number
nullable: true
error:
type: string
nullable: true
description: Sanitized error message (no stack traces)
sourceModel:
type: string
nullable: true
mappedModel:
type: string
nullable: true
detectedKind:
$ref: "#/components/schemas/DetectedKind"
contextKey:
type: string
nullable: true
description: 12-char SHA-256 hex of the system prompt (for conversation grouping)
example: a3f9c2b1d5e4
annotation:
type: string
nullable: true
sessionId:
type: string
format: uuid
nullable: true
note:
type: string
nullable: true
description: Informational note (e.g. TLS tunnel metadata)
InspectorCustomHost:
type: object
properties:
host:
type: string
example: api.openai.com
enabled:
type: boolean
label:
type: string
nullable: true
kind:
type: string
enum: [llm, app, custom]
added_at:
type: string
format: date-time
last_seen_at:
type: string
format: date-time
nullable: true
InspectorCustomHostCreate:
type: object
required: [host]
properties:
host:
type: string
minLength: 1
example: my-internal-llm.company.com
enabled:
type: boolean
default: true
label:
type: string
nullable: true
kind:
type: string
enum: [llm, app, custom]
default: custom
InspectorCaptureModesState:
type: object
properties:
agentBridge:
type: object
properties:
active:
type: boolean
customHosts:
type: object
properties:
active:
type: boolean
count:
type: integer
httpProxy:
type: object
properties:
active:
type: boolean
port:
type: integer
example: 8080
systemProxy:
type: object
properties:
active:
type: boolean
guardMinutes:
type: integer
InspectorCaptureModeAction:
type: object
required: [action]
properties:
action:
type: string
enum: [start, stop]
InspectorSystemProxyAction:
type: object
required: [action]
properties:
action:
type: string
enum: [apply, revert]
port:
type: integer
minimum: 1
maximum: 65535
example: 8080
guardMinutes:
type: integer
minimum: 1
example: 30
InspectorTlsInterceptToggle:
type: object
required: [enabled]
properties:
enabled:
type: boolean
InspectorAnnotationPut:
type: object
required: [annotation]
properties:
annotation:
type: string
maxLength: 10000
InspectorSession:
type: object
properties:
id:
type: string
format: uuid
name:
type: string
nullable: true
started_at:
type: string
format: date-time
ended_at:
type: string
format: date-time
nullable: true
request_count:
type: integer
profile:
type: string
enum: [llm, custom, all]
nullable: true
InspectorSessionStart:
type: object
properties:
name:
type: string
example: "Antigravity test run #1"
InspectorSessionPatch:
type: object
required: [action]
properties:
action:
type: string
enum: [stop, rename]
name:
type: string
QuotaPool:
type: object
description: A quota sharing pool — binds a provider connection to allocation rules.
required: [id, connectionId, name, createdAt, allocations]
properties:
id:
type: string
connectionId:
type: string
name:
type: string
createdAt:
type: string
format: date-time
allocations:
type: array
items:
$ref: "#/components/schemas/PoolAllocation"
PoolAllocation:
type: object
required: [apiKeyId, weight, policy]
properties:
apiKeyId:
type: string
weight:
type: number
minimum: 0
maximum: 100
description: Share percentage (0100)
capValue:
type: number
nullable: true
description: Absolute cap value (optional)
capUnit:
type: string
enum: [percent, requests, tokens, usd]
nullable: true
policy:
type: string
enum: [hard, soft, burst]
PoolCreate:
type: object
required: [connectionId, name]
properties:
connectionId:
type: string
name:
type: string
maxLength: 120
allocations:
type: array
items:
$ref: "#/components/schemas/PoolAllocation"
default: []
PoolUpdate:
type: object
properties:
name:
type: string
maxLength: 120
allocations:
type: array
items:
$ref: "#/components/schemas/PoolAllocation"
PoolUsageSnapshot:
type: object
required: [poolId, generatedAt, dimensions]
properties:
poolId:
type: string
generatedAt:
type: string
format: date-time
dimensions:
type: array
items:
type: object
properties:
unit:
type: string
enum: [percent, requests, tokens, usd]
window:
type: string
enum: ["5h", hourly, daily, weekly, monthly]
limit:
type: number
consumedTotal:
type: number
perKey:
type: array
items:
type: object
properties:
apiKeyId:
type: string
consumed:
type: number
fairShare:
type: number
deficit:
type: number
description: "Negative = surplus; positive = over-allocation"
borrowing:
type: boolean
burnRate:
type: object
nullable: true
properties:
tokensPerSecond:
type: number
timeToExhaustionMs:
type: number
nullable: true
QuotaDimension:
type: object
required: [unit, window, limit]
properties:
unit:
type: string
enum: [percent, requests, tokens, usd]
window:
type: string
enum: ["5h", hourly, daily, weekly, monthly]
limit:
type: number
minimum: 0
PlanUpsert:
type: object
required: [dimensions]
properties:
dimensions:
type: array
minItems: 1
items:
$ref: "#/components/schemas/QuotaDimension"
QuotaStoreSettings:
type: object
required: [driver]
properties:
driver:
type: string
enum: [sqlite, redis]
redisUrl:
type: string
format: uri
nullable: true
description: Redis connection URL (write-only; masked in GET responses)
ServiceStatus:
type: object
description: Live supervisor state for an embedded service
properties:
tool:
type: string
example: 9router
state:
type: string
enum: [not_installed, stopped, starting, running, stopping, error]
pid:
type: integer
nullable: true
port:
type: integer
example: 20130
health:
type: string
enum: [unknown, healthy, degraded]
startedAt:
type: string
format: date-time
nullable: true
lastError:
type: string
nullable: true
ServiceStatusExtended:
allOf:
- $ref: "#/components/schemas/ServiceStatus"
- type: object
description: >-
Extended status including version metadata and (for 9Router) API key preview.
properties:
installedVersion:
type: string
nullable: true
latestVersion:
type: string
nullable: true
updateAvailable:
type: boolean
apiKeyMasked:
type: string
nullable: true
description: >-
Masked API key preview (e.g. "nr_****abcd").
Present only for services that use an injected API key (9Router).
autoStart:
type: boolean
providerExpose:
type: boolean
description: >-
Whether models from this service are exposed as a routing provider.
9Router only.
ApiErrorResponse:
type: object
properties:
error:
type: object
properties:
message:
type: string
type:
type: string
details:
description: Optional additional error details
requestId:
type: string
format: uuid
ValidationErrorResponse:
type: object
properties:
error:
type: object
required: [message, details]
properties:
message:
type: string
example: Invalid request
details:
type: array
items:
type: object
required: [field, message]
properties:
field:
type: string
message:
type: string
PayloadRuleModelSpec:
type: object
additionalProperties: false
required: [name]
properties:
name:
type: string
minLength: 1
protocol:
type: string
minLength: 1
PayloadMutationRule:
type: object
additionalProperties: false
required: [models, params]
properties:
models:
type: array
minItems: 1
items:
$ref: "#/components/schemas/PayloadRuleModelSpec"
params:
type: object
minProperties: 1
additionalProperties: true
PayloadFilterRule:
type: object
additionalProperties: false
required: [models, params]
properties:
models:
type: array
minItems: 1
items:
$ref: "#/components/schemas/PayloadRuleModelSpec"
params:
type: array
minItems: 1
items:
type: string
minLength: 1
PayloadRulesConfig:
type: object
additionalProperties: false
required: [default, override, filter, defaultRaw]
properties:
default:
type: array
items:
$ref: "#/components/schemas/PayloadMutationRule"
override:
type: array
items:
$ref: "#/components/schemas/PayloadMutationRule"
filter:
type: array
items:
$ref: "#/components/schemas/PayloadFilterRule"
defaultRaw:
type: array
items:
$ref: "#/components/schemas/PayloadMutationRule"
UpdatePayloadRulesRequest:
type: object
additionalProperties: false
description: At least one payload-rules section must be present in the request body.
properties:
default:
type: array
items:
$ref: "#/components/schemas/PayloadMutationRule"
override:
type: array
items:
$ref: "#/components/schemas/PayloadMutationRule"
filter:
type: array
items:
$ref: "#/components/schemas/PayloadFilterRule"
defaultRaw:
type: array
items:
$ref: "#/components/schemas/PayloadMutationRule"
default-raw:
type: array
items:
$ref: "#/components/schemas/PayloadMutationRule"
anyOf:
- required: [default]
- required: [override]
- required: [filter]
- required: [defaultRaw]
- required: [default-raw]
ChatCompletionRequest:
type: object
required: [model, messages]
properties:
model:
type: string
example: gpt-4o
messages:
type: array
items:
type: object
required: [role]
properties:
role:
type: string
description: >-
Message role. The proxy accepts any non-empty string; common values
include system, user, assistant, tool, function, and developer.
example: user
content:
description: >-
Message content. May be a plain string, an array of content parts
for multimodal inputs (text, image, audio, etc.), or null when the
message only carries tool/function calls.
oneOf:
- type: string
- type: array
items:
type: object
- type: "null"
name:
type: string
tool_call_id:
type: string
tool_calls:
type: array
items:
type: object
function_call:
type: object
stream:
type: boolean
default: false
temperature:
type: number
minimum: 0
maximum: 2
max_tokens:
type: integer
top_p:
type: number
minimum: 0
maximum: 1
n:
type: integer
minimum: 1
default: 1
stop:
description: Up to 4 stop sequences (string or array of strings).
oneOf:
- type: string
- type: array
items:
type: string
maxItems: 4
frequency_penalty:
type: number
minimum: -2
maximum: 2
presence_penalty:
type: number
minimum: -2
maximum: 2
seed:
type: integer
logprobs:
type: boolean
top_logprobs:
type: integer
minimum: 0
maximum: 20
response_format:
type: object
description: Output format constraint (e.g. JSON mode or JSON Schema).
properties:
type:
type: string
example: json_object
tools:
type: array
description: Tool definitions available to the model.
items:
type: object
tool_choice:
description: Controls which tool (if any) is invoked by the model.
oneOf:
- type: string
example: auto
- type: object
parallel_tool_calls:
type: boolean
default: true
service_tier:
type: string
example: auto
user:
type: string
description: Stable end-user identifier for abuse monitoring.
ChatCompletionResponse:
type: object
properties:
id:
type: string
object:
type: string
example: chat.completion
choices:
type: array
items:
type: object
properties:
index:
type: integer
message:
type: object
properties:
role:
type: string
content:
type: string
finish_reason:
type: string
usage:
type: object
properties:
prompt_tokens:
type: integer
completion_tokens:
type: integer
total_tokens:
type: integer
MessagesRequest:
type: object
required: [model, messages, max_tokens]
properties:
model:
type: string
example: claude-sonnet-4-5-20250514
messages:
type: array
items:
type: object
required: [role, content]
properties:
role:
type: string
enum: [user, assistant]
content:
type: string
max_tokens:
type: integer
stream:
type: boolean
default: false
system:
type: string
Model:
type: object
properties:
id:
type: string
object:
type: string
example: model
owned_by:
type: string
ProviderConnection:
type: object
properties:
id:
type: string
provider:
type: string
name:
type: string
url:
type: string
isActive:
type: boolean
maxConcurrent:
type: integer
nullable: true
minimum: 0
priority:
type: integer
testStatus:
type: string
enum: [active, error, untested]
createdAt:
type: string
format: date-time
ProviderConnectionCreate:
type: object
required: [provider, url]
properties:
provider:
type: string
example: openai
name:
type: string
url:
type: string
apiKey:
type: string
isActive:
type: boolean
default: true
maxConcurrent:
type: integer
nullable: true
minimum: 0
ApiKey:
type: object
properties:
id:
type: string
label:
type: string
keyPreview:
type: string
description: Last 4 characters of the key
isActive:
type: boolean
createdAt:
type: string
format: date-time
ComboCreate:
type: object
required: [name, model]
properties:
name:
type: string
model:
type: string
strategy:
type: string
enum:
- priority
- weighted
- round-robin
- context-relay
- fill-first
- p2c
- random
- least-used
- cost-optimized
- reset-aware
- strict-random
- auto
- lkgp
- context-optimized
default: priority
nodes:
type: array
items:
type: object
properties:
connectionId:
type: string
weight:
type: integer
priority:
type: integer