Compare commits

..

139 Commits

Author SHA1 Message Date
Diego Rodrigues de Sa e Souza
182bc398df chore(release): finalize v3.8.36 CHANGELOG + docs (2026-06-25) 2026-06-25 13:11:34 -03:00
Diego Rodrigues de Sa e Souza
06882d6a89 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)
2026-06-25 11:46:21 -03:00
Diego Rodrigues de Sa e Souza
db9724d29c docs(changelog): add entries for #4993, #5024, #5027 (release notes credit) 2026-06-25 11:32:11 -03:00
Diego Rodrigues de Sa e Souza
2d39c95285 fix(headroom): translate openai-responses input through OpenAI for compression (#5023)
Integrated into release/v3.8.36
2026-06-25 11:30:41 -03:00
Diego Rodrigues de Sa e Souza
50df2ca42e feat(endpoint): per-endpoint custom system prompt injection (#5022)
Integrated into release/v3.8.36
2026-06-25 11:30:34 -03:00
Hernan Javier Ardila Sanchez
8c1895574b fix(plugin): auth.json dual-key fallback for auto-prefix migration (#5027)
Integrated into release/v3.8.36
2026-06-25 11:30:16 -03:00
Hamsa_M
d40200a26b fix(copilot): replace execSync with execFile to prevent command injection (#5024)
Integrated into release/v3.8.36
2026-06-25 11:30:13 -03:00
Arthur Bodera
3eb9ff29e8 Fix Ollama Cloud max reasoning effort (#4993)
Integrated into release/v3.8.36
2026-06-25 11:30:10 -03:00
Diego Rodrigues de Sa e Souza
325188eb9b 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>
2026-06-25 07:25:59 -03:00
Diego Rodrigues de Sa e Souza
09d0d11ed5 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>
2026-06-25 07:25:07 -03:00
Diego Rodrigues de Sa e Souza
515bc3465f 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>
2026-06-25 07:24:17 -03:00
Diego Rodrigues de Sa e Souza
917b2244b6 fix(pollinations): only enable jsonMode when JSON output is requested (#3981) (#5009)
Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>
2026-06-25 07:22:27 -03:00
Diego Rodrigues de Sa e Souza
af32e0041c 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>
2026-06-25 03:29:09 -03:00
Diego Rodrigues de Sa e Souza
0412b128c0 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>
2026-06-25 03:28:43 -03:00
Diego Rodrigues de Sa e Souza
083d4b0044 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>
2026-06-25 03:27:55 -03:00
Diego Rodrigues de Sa e Souza
bf6c8ca3fd 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>
2026-06-25 03:27:36 -03:00
Diego Rodrigues de Sa e Souza
d38bf09551 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>
2026-06-25 03:26:48 -03:00
Diego Rodrigues de Sa e Souza
568472d09f 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>
2026-06-25 03:11:16 -03:00
Diego Rodrigues de Sa e Souza
d648e215f8 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>
2026-06-25 00:28:30 -03:00
Diego Rodrigues de Sa e Souza
1f685ebcd7 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>
2026-06-24 23:54:43 -03:00
Diego Rodrigues de Sa e Souza
028ed4ea7b 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>
2026-06-24 23:51:07 -03:00
Diego Rodrigues de Sa e Souza
a9ddef1302 feat(quota): combo quota-share espera cooldown curto e re-despacha (Variante A) (#4967)
Integrated into release/v3.8.36
2026-06-24 18:14:59 -03:00
Diego Rodrigues de Sa e Souza
195e40ff7a feat(quota): respeita max_concurrent por conexão no roteamento (#4965)
Integrated into release/v3.8.36
2026-06-24 18:13:31 -03:00
Diego Rodrigues de Sa e Souza
a58183ab84 fix(quota): migração 107 ativa estratégia quota-share nos combos qtSd/ existentes [Fase 3 #9] (#4962)
Integrated into release/v3.8.36
2026-06-24 18:12:15 -03:00
Diego Rodrigues de Sa e Souza
d3e02e630f fix(build): drop @omniroute/open-sse from optimizePackageImports (build OOM) (#4968)
Integrated into release/v3.8.36 — fixes build OOM (optimizePackageImports open-sse)
2026-06-24 17:58:33 -03:00
Diego Rodrigues de Sa e Souza
b03134e709 fix(dashboard): restore home provider-topology card hidden by #4596 default (#4963)
Integrated into release/v3.8.36 — restores home topology card (#4596 regression)
2026-06-24 14:31:27 -03:00
Diego Rodrigues de Sa e Souza
678cbcf207 chore(quality): reconcile file-size baseline for #4960 provider-display-name (#4961)
Integrated into release/v3.8.36
2026-06-24 14:09:41 -03:00
Diego Rodrigues de Sa e Souza
072094000d fix(translator): preserve legitimate empty-string tool arguments in openai-to-claude streaming (#4951) (#4959)
Integrated into release/v3.8.36 (fixes #4951)
2026-06-24 14:08:24 -03:00
Diego Rodrigues de Sa e Souza
cd27701c1e 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)
2026-06-24 14:06:48 -03:00
Diego Rodrigues de Sa e Souza
d4c2e4dd0a fix(api): evict stale in-memory rate-limit windows to stop slow heap leak (#4041) (#4957)
Integrated into release/v3.8.36 (fixes #4041)
2026-06-24 14:03:52 -03:00
Diego Rodrigues de Sa e Souza
3d37242993 fix(dashboard): show custom provider given-name instead of internal id across dashboard pages (#4603) (#4960)
Integrated into release/v3.8.36 (fixes #4603)
2026-06-24 14:03:21 -03:00
Diego Rodrigues de Sa e Souza
d575691d90 refactor(sse): extrai a família Antigravity de services/usage.ts (#4956)
Integrated into release/v3.8.36
2026-06-24 13:13:27 -03:00
Diego Rodrigues de Sa e Souza
cca71a5d22 refactor(sse): extrai a família GLM de services/usage.ts (#4953)
Integrated into release/v3.8.36
2026-06-24 13:12:23 -03:00
Diego Rodrigues de Sa e Souza
8a7cf50144 refactor(sse): extrai a família MiniMax de services/usage.ts (#4952)
Integrated into release/v3.8.36
2026-06-24 13:11:29 -03:00
Diego Rodrigues de Sa e Souza
07b385d4c1 feat(combo): task-aware routing strategy (#4945)
Integrated into release/v3.8.36
2026-06-24 12:43:38 -03:00
Diego Rodrigues de Sa e Souza
6137d4ef57 fix(translator): provider thinking compatibility (DeepSeek/Gemini) (#4946)
Integrated into release/v3.8.36
2026-06-24 12:41:30 -03:00
Diego Rodrigues de Sa e Souza
d65050a1db feat(providers): update volcengine-ark model list with DeepSeek V4 (#4905)
Integrated into release/v3.8.36
2026-06-24 12:40:47 -03:00
Diego Rodrigues de Sa e Souza
7c75b48792 fix(combo): fetch models dynamically from custom provider endpoints (#4860)
Integrated into release/v3.8.36
2026-06-24 12:40:08 -03:00
Diego Rodrigues de Sa e Souza
950fc6e60e fix(compression): eliminate ReDoS in math_inline preservation pattern (#4795) (#4838)
Integrated into release/v3.8.36 (fixes #4795)
2026-06-24 12:39:32 -03:00
Diego Rodrigues de Sa e Souza
4a1ae868ce refactor(open-sse): extract safeParseJSON util, dedup tryParseJSON (#4735)
Integrated into release/v3.8.36
2026-06-24 12:39:03 -03:00
Diego Rodrigues de Sa e Souza
6e28889aad refactor(sse): dedup fallback tool_call id helper (#4736)
Integrated into release/v3.8.36
2026-06-24 12:38:25 -03:00
Diego Rodrigues de Sa e Souza
cc8557cedf fix(qoder): exchange PAT for jt-* job token before Cosy chat (#4683) (#4884)
Integrated into release/v3.8.36 (fixes #4683)
2026-06-24 11:56:33 -03:00
Diego Rodrigues de Sa e Souza
b1b3069cd1 fix(translator): regroup parallel tool results adjacent to their assistant (#4714) (#4882)
Integrated into release/v3.8.36 (fixes #4714)
2026-06-24 11:55:40 -03:00
Diego Rodrigues de Sa e Souza
de19b3b087 refactor(sse): extrai quota-core (UsageQuota + builders) de services/usage.ts (#4950)
Integrated into release/v3.8.36
2026-06-24 11:54:09 -03:00
Diego Rodrigues de Sa e Souza
565b77143c refactor(sse): extrai scalar/format helpers de services/usage.ts (#4949)
Integrated into release/v3.8.36
2026-06-24 11:53:22 -03:00
Diego Rodrigues de Sa e Souza
ca72de7ba4 refactor(db): extrai schema-column reconciliation de db/core.ts (#4948)
Integrated into release/v3.8.36
2026-06-24 11:52:40 -03:00
Diego Rodrigues de Sa e Souza
5073aff2ae refactor(db): extrai column-mapping (snake↔camel) de db/core.ts (#4947)
Integrated into release/v3.8.36
2026-06-24 11:52:04 -03:00
Diego Rodrigues de Sa e Souza
ca0fdddebf refactor(db): extrai row-parsers + tipos compartilhados de db/apiKeys.ts (#4943)
Integrated into release/v3.8.36
2026-06-24 11:51:33 -03:00
Diego Rodrigues de Sa e Souza
f1589801ee refactor(db): extrai model-permission matching de db/apiKeys.ts (#4936)
Integrated into release/v3.8.36
2026-06-24 11:50:52 -03:00
Diego Rodrigues de Sa e Souza
419a90f240 refactor(api): extrai format-validators (OpenAI/Anthropic) de validation.ts (#4933)
Integrated into release/v3.8.36
2026-06-24 11:50:20 -03:00
Diego Rodrigues de Sa e Souza
537e5b5f6e refactor(api): extrai validators search + embedding/rerank de validation.ts (#4932)
Integrated into release/v3.8.36
2026-06-24 11:48:10 -03:00
Diego Rodrigues de Sa e Souza
9708288b57 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>
2026-06-24 11:40:17 -03:00
Diego Rodrigues de Sa e Souza
833adce8fb 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)
2026-06-24 09:53:36 -03:00
Diego Rodrigues de Sa e Souza
6035fd8ba1 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)
2026-06-24 09:52:23 -03:00
Diego Rodrigues de Sa e Souza
1cb246215a 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)
2026-06-24 09:51:11 -03:00
Diego Rodrigues de Sa e Souza
21ce4872d2 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)
2026-06-24 09:49:59 -03:00
Diego Rodrigues de Sa e Souza
c872b6710d 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)
2026-06-24 09:48:46 -03:00
Diego Rodrigues de Sa e Souza
b8e3dc950c 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)
2026-06-24 09:47:45 -03:00
Diego Rodrigues de Sa e Souza
15ee83b44a 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>
2026-06-24 09:35:28 -03:00
Diego Rodrigues de Sa e Souza
0811a15a09 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>
2026-06-24 09:23:34 -03:00
Diego Rodrigues de Sa e Souza
98296169ed 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>
2026-06-24 08:07:42 -03:00
Diego Rodrigues de Sa e Souza
118875e3ed 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>
2026-06-24 07:25:40 -03:00
Diego Rodrigues de Sa e Souza
9d5954122d 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>
2026-06-24 07:14:00 -03:00
Diego Rodrigues de Sa e Souza
5d9ecf6f8b 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>
2026-06-24 07:00:16 -03:00
Diego Rodrigues de Sa e Souza
8080800d8f 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)
2026-06-24 00:57:43 -03:00
Diego Rodrigues de Sa e Souza
078785cbf3 fix(cli): SIGKILL systray child PID before IPC close to avoid macOS NSStatusItem orphan (#4732)
Integrated into release/v3.8.36
2026-06-24 00:47:40 -03:00
Diego Rodrigues de Sa e Souza
1a1a51c744 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)
2026-06-24 00:46:54 -03:00
Diego Rodrigues de Sa e Souza
8251e7b8fb feat(opencode-go): advertise glm-5.2 and kimi-k2.7-code (align with official Go endpoints) (#4711)
Integrated into release/v3.8.36
2026-06-24 00:41:53 -03:00
Diego Rodrigues de Sa e Souza
7a6f43209c fix(translator): replay reasoning_content on plain Xiaomi MiMo turns (port from 9router#1321) (#4639)
Integrated into release/v3.8.36
2026-06-24 00:41:16 -03:00
Diego Rodrigues de Sa e Souza
413d1d3827 docs(ops): document the release-green family (green-prs, check:release-green, babysit, nightly) (#4679)
Integrated into release/v3.8.36
2026-06-24 00:40:09 -03:00
Diego Rodrigues de Sa e Souza
db192ce7c6 docs(agentbridge): document Electron NODE_EXTRA_CA_CERTS, real model IDs, identity caveat (#4718)
Integrated into release/v3.8.36
2026-06-24 00:39:43 -03:00
Diego Rodrigues de Sa e Souza
ec0572d060 docs: clarify Kiro is ~50 credits/month per account, not unlimited (#4690)
Integrated into release/v3.8.36
2026-06-24 00:39:19 -03:00
Diego Rodrigues de Sa e Souza
95e26a07ff fix(cli): bump better-sqlite3 runtime pin to 12.10.1 for Node 26 (#4685)
Integrated into release/v3.8.36
2026-06-24 00:38:50 -03:00
Diego Rodrigues de Sa e Souza
9b07e0ea59 fix(ci): include coverage/lcov.info in coverage-report artifact for SonarQube (#4670)
Integrated into release/v3.8.36
2026-06-24 00:38:20 -03:00
Diego Rodrigues de Sa e Souza
f9ccf342c0 chore(dashboard): rename Qoder display label from "Qoder AI" to "Qoder" (#4733)
Integrated into release/v3.8.36
2026-06-24 00:37:15 -03:00
Diego Rodrigues de Sa e Souza
70afa2b5c6 feat(quota): saturação real do Claude no fair-share via /api/oauth/usage (#4885)
Integrated into release/v3.8.36
2026-06-24 00:04:37 -03:00
Diego Rodrigues de Sa e Souza
4305ef8690 fix(quota): policy inválida não vaza allow + guard connectionIds vazio [Fase 3 #10] (#4901)
Integrated into release/v3.8.36
2026-06-24 00:04:22 -03:00
Diego Rodrigues de Sa e Souza
27c994ffd3 feat(quota): recuperação proativa de conexões em cooldown (cron heal) [Fase 3 #8] (#4900)
Integrated into release/v3.8.36
2026-06-24 00:04:20 -03:00
Diego Rodrigues de Sa e Souza
5c0cda929c fix(security): SSRF allowlist bypass via x-relay-path nos relays Deno/Vercel (#4899)
Integrated into release/v3.8.36
2026-06-24 00:04:17 -03:00
Diego Rodrigues de Sa e Souza
2039095f69 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
2026-06-24 00:04:13 -03:00
KooshaPari
c522454c79 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)
2026-06-23 23:21:51 -03:00
Éder Costa
2a7f2c892a feat(routing): honor X-Route-Model header to override body.model (#4863)
Integrated into release/v3.8.36
2026-06-23 23:15:02 -03:00
Jefferson Felizardo
eb175db8ed fix(codex): drop non-standard codex.* events that break responses.stream (env-gated, #4602) (#4715)
Integrated into release/v3.8.36
2026-06-23 23:07:51 -03:00
Diego Rodrigues de Sa e Souza
4d61198e1a 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>
2026-06-23 23:05:18 -03:00
Éder Costa
86b14add6e fix(claude): skip mcp__ tool-name cloak + guard missing connectionId (#4861)
Integrated into release/v3.8.36
2026-06-23 22:59:51 -03:00
Éder Costa
108e93e14b fix(sse): drop ccp pin when pinned provider is durably unhealthy (failover + anti-flap) (#4864)
Integrated into release/v3.8.36
2026-06-23 22:58:21 -03:00
Randi
459ffcf2c0 fix db storage tuning settings (#4834)
Integrated into release/v3.8.36
2026-06-23 22:57:26 -03:00
Chewji
e99e2887bf fix(combo): propagate selected connection ID to fallback error responses for correct model lockout (#4809)
Integrated into release/v3.8.36
2026-06-23 22:56:14 -03:00
Demiurge The Single
604654cc3a fix(install): make transformers optional for CUDA-host installs (#4807)
Integrated into release/v3.8.36
2026-06-23 22:54:15 -03:00
Anton
e1ffc8e850 fix(sse): skip third-party tool-name cloak for Anthropic server tools (#4808)
Integrated into release/v3.8.36
2026-06-23 22:53:13 -03:00
Chewji
805519befb fix(antigravity): exclude standard Gemini rate limit message from quota exhaustion keywords (#4810)
Integrated into release/v3.8.36
2026-06-23 22:52:50 -03:00
Makcim Ivanov
9a5627a4a6 fix(proxy): fan out direct dispatcher streams (#4803)
Integrated into release/v3.8.36
2026-06-23 22:51:54 -03:00
KooshaPari
21aa5617cf docs(perf): add per-endpoint p50/p95/p99 latency + cost budgets (#4867)
Integrated into release/v3.8.36
2026-06-23 22:51:25 -03:00
KooshaPari
dad55fed0a docs(ops): add canonical incident response runbook (#4868)
Integrated into release/v3.8.36
2026-06-23 22:51:05 -03:00
Diego Rodrigues de Sa e Souza
b5995778cb 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
2026-06-23 22:16:33 -03:00
Diego Rodrigues de Sa e Souza
cc8e1bedf5 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
2026-06-23 22:15:12 -03:00
Diego Rodrigues de Sa e Souza
9244d930ea 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
2026-06-23 22:14:30 -03:00
Diego Rodrigues de Sa e Souza
396a9a72cd 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
2026-06-23 22:12:12 -03:00
Diego Rodrigues de Sa e Souza
122f6d3a19 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
2026-06-23 22:10:11 -03:00
Diego Rodrigues de Sa e Souza
2d09f72b29 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
2026-06-23 22:09:04 -03:00
Diego Rodrigues de Sa e Souza
6fe21e59e9 fix(claude): omit adaptive thinking + output_config.effort for haiku (#4661)
Integrated into release/v3.8.36 — haiku adaptive-thinking omit (port); release-green
2026-06-23 22:06:59 -03:00
Diego Rodrigues de Sa e Souza
c02aa7b064 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
2026-06-23 22:04:29 -03:00
Diego Rodrigues de Sa e Souza
57de29a415 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
2026-06-23 22:02:29 -03:00
Diego Rodrigues de Sa e Souza
b92f045f70 fix(opencode): preserve DeepSeek reasoning content in streamed responses (#4631)
Integrated into release/v3.8.36 — DeepSeek reasoning_content injection (port #1099); release-green
2026-06-23 22:01:00 -03:00
Diego Rodrigues de Sa e Souza
486f01710c 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
2026-06-23 21:58:52 -03:00
Diego Rodrigues de Sa e Souza
ec1c5df091 feat(compression): Kiro/CodeWhisperer tool-result compression engine (#4635)
Integrated into release/v3.8.36 — port rebuilt clean, release-green
2026-06-23 21:58:48 -03:00
Diego Rodrigues de Sa e Souza
306863dd9e chore(quality): rebaseline catalog.ts 1574->1577 (#4630 aliases sobre quota-exclusive da release) (#4879)
rebaseline
2026-06-23 21:58:44 -03:00
Diego Rodrigues de Sa e Souza
69703ee7db 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
2026-06-23 21:56:57 -03:00
Diego Rodrigues de Sa e Souza
be2ab9e419 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
2026-06-23 21:56:21 -03:00
Diego Rodrigues de Sa e Souza
607ad12e84 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
2026-06-23 21:56:07 -03:00
Diego Rodrigues de Sa e Souza
32b2df974a 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
2026-06-23 21:54:43 -03:00
Diego Rodrigues de Sa e Souza
e176774395 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
2026-06-23 21:52:52 -03:00
Diego Rodrigues de Sa e Souza
983e152ea2 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
2026-06-23 21:52:21 -03:00
Diego Rodrigues de Sa e Souza
1ad6c46b46 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)
2026-06-23 21:51:54 -03:00
Diego Rodrigues de Sa e Souza
d2aa67a11c 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)
2026-06-23 21:51:45 -03:00
Diego Rodrigues de Sa e Souza
f4fa983a9f 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)
2026-06-23 21:51:29 -03:00
Diego Rodrigues de Sa e Souza
35a3962cf0 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)
2026-06-23 21:51:17 -03:00
Diego Rodrigues de Sa e Souza
a9368af7df 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)
2026-06-23 21:51:08 -03:00
Diego Rodrigues de Sa e Souza
2a90a9e589 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)
2026-06-23 21:50:54 -03:00
Diego Rodrigues de Sa e Souza
ea406b2197 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)
2026-06-23 21:50:37 -03:00
Diego Rodrigues de Sa e Souza
fc2fdc7e3c 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)
2026-06-23 21:50:28 -03:00
Diego Rodrigues de Sa e Souza
fcf162d3fe 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)
2026-06-23 20:37:25 -03:00
Diego Rodrigues de Sa e Souza
502f43c283 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)
2026-06-23 20:37:23 -03:00
Diego Rodrigues de Sa e Souza
c922b21102 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)
2026-06-23 20:17:09 -03:00
Diego Rodrigues de Sa e Souza
7f5b1e4d83 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>
2026-06-23 20:16:23 -03:00
Diego Rodrigues de Sa e Souza
5bffefb489 refactor(chatCore): extrai assembleStreamingPipeline (chain de transforms streaming, #3501) (#4837)
Integrated into release/v3.8.36 (#3501 chatCore extraction stack 13/13)
2026-06-23 20:03:12 -03:00
Diego Rodrigues de Sa e Souza
2cd5609628 refactor(chatCore): extrai storeStreamingSemanticCacheResponse (cache-store streaming, #3501) (#4829)
Integrated into release/v3.8.36 (#3501 chatCore extraction stack 12/13)
2026-06-23 20:03:02 -03:00
Diego Rodrigues de Sa e Souza
e87d35ceda refactor(chatCore): extrai assembleStreamingResponseHeaders (headers de resposta streaming, #3501) (#4836)
Integrated into release/v3.8.36 (#3501 chatCore extraction stack 11/13)
2026-06-23 20:02:52 -03:00
Diego Rodrigues de Sa e Souza
c69bd6a4eb refactor(chatCore): extrai maybeConvertJsonBodyToSse (#3089 JSON→SSE streaming, #3501) (#4833)
Integrated into release/v3.8.36 (#3501 chatCore extraction stack 10/13)
2026-06-23 20:02:42 -03:00
Diego Rodrigues de Sa e Souza
867e9043f5 refactor(chatCore): extrai buildNonStreamingResponseHeaders (headers de resposta non-streaming, #3501) (#4835)
Integrated into release/v3.8.36 (#3501 chatCore extraction stack 9/13)
2026-06-23 20:02:32 -03:00
Diego Rodrigues de Sa e Souza
1244e4903b refactor(chatCore): extrai storeSemanticCacheResponse (cache-store non-streaming, #3501) (#4828)
Integrated into release/v3.8.36 (#3501 chatCore extraction stack 8/13)
2026-06-23 20:02:22 -03:00
Diego Rodrigues de Sa e Souza
5c0b29e2b3 refactor(chatCore): extrai buildPostCallGuardrailContext (contexto guardrail post-call, #3501) (#4831)
Integrated into release/v3.8.36 (#3501 chatCore extraction stack 7/13)
2026-06-23 20:02:12 -03:00
Diego Rodrigues de Sa e Souza
e85fb9bb5d refactor(chatCore): extrai applyClientUsageBuffer (buffer/estimate de usage non-streaming, #3501) (#4832)
Integrated into release/v3.8.36 (#3501 chatCore extraction stack 6/13)
2026-06-23 20:01:50 -03:00
Diego Rodrigues de Sa e Souza
eb1920bf91 refactor(chatCore): extrai runPluginOnRequestHook (#3501) (#4827)
Integrated into release/v3.8.36 (#3501 chatCore extraction stack 5/13)
2026-06-23 20:01:40 -03:00
Diego Rodrigues de Sa e Souza
812f2f20a1 refactor(chatCore): extrai writeCompressionAnalytics (bloco analytics completo, #3501) (#4817)
Integrated into release/v3.8.36 (#3501 chatCore extraction stack 4/13)
2026-06-23 20:01:30 -03:00
Diego Rodrigues de Sa e Souza
34b510a543 refactor(chatCore): extrai emitOutputStyleTelemetry (#3501) (#4811)
Integrated into release/v3.8.36 (#3501 chatCore extraction stack 3/13)
2026-06-23 20:01:20 -03:00
Diego Rodrigues de Sa e Souza
e420c34fce refactor(chatCore): extrai predicados puros de combo de compressão (#3501) (#4824)
Integrated into release/v3.8.36 (#3501 chatCore extraction stack 2/13)
2026-06-23 20:01:09 -03:00
Diego Rodrigues de Sa e Souza
e494afebcf refactor(chatCore): extrai resolveCompressionSettings (#3501) (#4826)
Integrated into release/v3.8.36 (#3501 chatCore extraction stack 1/13)
2026-06-23 20:00:34 -03:00
Diego Rodrigues de Sa e Souza
8d50c9de16 chore(release): open v3.8.36 development cycle 2026-06-23 18:31:24 -03:00
7333 changed files with 189265 additions and 1240901 deletions

View File

@@ -1,201 +0,0 @@
# codebase-memory-mcp ignore list
#
# Padrão gitignore-style. Linhas começando com `#` são comentários.
# Barra final (`/`) = só diretório. Sem barra = casa arquivo OU diretório.
#
# O CBM também lê `.gitignore` automaticamente — esta lista deixa explícito o que
# os hooks do CBM vão pular. Se uma regra entrar em conflito entre os dois arquivos,
# vale a união. Editar este arquivo é mais barato do que confiar na herança implícita.
#
# Última reconciliação: 2026-07-31, status `ready` (513k nodes / 689k edges),
# `auto_index_limit=50000`, total indexável medido ≈11.546 arquivos (folga 4,3×).
#
# Fontes cruzadas:
# - `codebase-memory-mcp cli index_status --project home-diegosouzapw-dev-proxys-OmniRoute`
# → `not_indexed.dirs` (27) + `not_indexed.files` (336), todos `BY DESIGN`.
# - `.gitignore` deste repo (5.691 B) — fonte canônica secundária.
#
# Como auditar mudanças: depois de editar este arquivo, rodar `index_repository`
# (ou esperar `auto_watch` re-indexar) e re-checar `cli index_status` → comparar
# contagens em `not_indexed.dirs_count` e `not_indexed.files_count`.
# ─────────────────────────────────────────────────────────────────────────────
# 1. Diretorios de runtime / pacote — nao sao codigo-fonte
# ─────────────────────────────────────────────────────────────────────────────
node_modules/
node_modules
# Builds e artefatos reproduziveis (Layer 1 Next.js / Electron)
.build/
dist/
.next/
out/
# Electron especifico
electron/dist-electron/
electron/node_modules/
icon.iconset/
# Workspaces internos que tem proprio node_modules
@omniroute/opencode-plugin/dist/
@omniroute/opencode-plugin/node_modules/
@omniroute/opencode-provider/dist/
@omniroute/opencode-provider/node_modules/
# Recursos nativos compilados (C/JNI/wasm)
src/mitm/tproxy/native/build/
# Artefatos locais do Stryker / Playwright / coverage
.stryker-tmp/
reports/mutation/
stryker-output-*.json
.playwright-mcp/
test-results/
playwright-report/
blob-report/
# Analise / linters / caches
.analysis/
.sisyphus/
.plans/
.gitnexus
.worktrees
.codegraph/
# Quality artifacts (gerados por npm run lint --cache etc)
.eslintcache
.eslintcache-complexity
# Claude Code local state
.claude/scheduled_tasks.lock
.claude/scheduled_tasks/
.claude/sessions/
.claude/state.json
.claude/settings.local.json
# Serena / Antigravity / outras tools locais
.serena/
.antigravitycli/
.gemini/
.config/
# ─────────────────────────────────────────────────────────────────────────────
# 2. Diretorios com prefixo `_` — locais / privados (regra global do .gitignore)
# ─────────────────────────────────────────────────────────────────────────────
_*/
_artifacts/
_cache/
_mono_repo/
_references/
_tasks/
# ─────────────────────────────────────────────────────────────────────────────
# 3. Diretorios de tooling IA (state local, nao codigo)
# ─────────────────────────────────────────────────────────────────────────────
.agents/
.claude/
.vscode/
.idea/
.junie/
.omc/
.data/
.data-dev/
.local-data/
.logs/
.artifacts/
.source/
.superpowers/
.claude-flow/
.omnivscodeagent/
omnirouteCloud/
omnirouteSite/
.omniroute/
.stent/
# Subpaths especificos do Claude Code que nao estao em .claude/ (criados sob repo)
.claude/worktrees/
# ─────────────────────────────────────────────────────────────────────────────
# 4. Diretorios de dados / runtime locais (storage, env, secrets, scratch)
# ─────────────────────────────────────────────────────────────────────────────
data/
# NOTA: src/lib/env/, src/app/api/{cloud,sync/cloud,system/env,agent-skills/coverage}/
# foram removidos daqui (2026-08-05). Os nomes sugerem dados/segredos locais, mas os
# 8 arquivos sao route handlers e modulos rastreados no git — escondia-los do grafo
# criava pontos cegos em buscas e em analise de impacto.
tests/golden-set/data/
# Logs e saida de teste
logs/*
test_output.log
home-diegosouzapw-dev-automacoes-*.txt
# ─────────────────────────────────────────────────────────────────────────────
# 5. Diretorios do monorepo por subprojeto (nao fazem parte do app principal)
# ─────────────────────────────────────────────────────────────────────────────
security-analysis/
vscode-extension/
obsidian-plugin/node_modules/
# ─────────────────────────────────────────────────────────────────────────────
# 6. Diretorios de documentacao interna / workflow
# ─────────────────────────────────────────────────────────────────────────────
docs/superpowers/
# Docs traduzidas: 1.215 arquivos / 94 MB (inclui 20+ copias do CHANGELOG).
# Sao traducoes do tree em ingles, ja indexado — no grafo so geram ruido em
# search_code e consomem o auto_index_limit.
docs/i18n/
# ─────────────────────────────────────────────────────────────────────────────
# 7. Arquivos especificos (nao diretorios inteiros)
# ─────────────────────────────────────────────────────────────────────────────
# Segredos e env — NUNCA indexar
.env
.env.*
!.env.example
!.env.homolog.example
# TypeScript build info e next env declaration
*.tsbuildinfo
next-env.d.ts
typescript
# SQLite transient files (WAL/SHM/journal)
*.sqlite-shm
*.sqlite-wal
*.sqlite-journal
# Mapas e source maps
*.map
# Bun / npm lockfiles ruidosos
bun.lock
# `cheaper-inference-gateway.svg` e arquivos de midia na raiz/asset ja cobertos
# pelos `ignored-suffix` do indexador (svg/png/jpg/ico/etc >50kB ou >500linhas);
# manter a regra explicita aqui ajuda a auditar:
cheaper-inference-gateway.svg
cheaper-inference-gateway-*.svg
# Husky internals
.husky/_/
# CI / quality metric artifacts
config/quality/quality-metrics.json
config/quality/test-impact-map.json
audit-report.json
.gh-discussions.json
# i18n audit (gerado por npm run scripts)
scripts/i18n/_audit.json
scripts/i18n/_pending-keys.json
# NOTA: bin/omniroute.mjs foi removido daqui (2026-08-05). Estava marcado como
# "scratch", mas e o entrypoint real do CLI publicado (package.json -> bin.omniroute)
# e consta em PACK_ARTIFACT_REQUIRED_PATHS. Precisa estar no grafo.
# Deploy / docker backups
deploy.sh
docker-compose.yml.bak
docker-compose.minimal.yml

View File

@@ -7,13 +7,7 @@
**/.vscode
# Dependencies and build output
# `node_modules` alone matches the ROOT only — Docker's matcher does not cross
# `/` like .gitignore does. Without the `**/` form, nested installs ship in the
# build context (e.g. @omniroute/opencode-provider/node_modules, ~79 MB of
# devDependencies). Both forms are kept: the bare one is the documented root
# rule, the `**/` one covers every nested package.
node_modules
**/node_modules
.next
.build
out
@@ -24,7 +18,6 @@ coverage
# Runtime data and logs
data
logs
.sandbox
# Local env files (inject at runtime via --env-file or -e)
.env
@@ -44,19 +37,6 @@ tests
test-results
playwright-report
blob-report
output
.playwright-cli
.playwright-mcp
.stryker-tmp
reports/mutation
# Local caches and quality-gate artifacts (all gitignored). `_*` does not match
# dot-prefixed names, so these need explicit entries.
.artifacts
.eslintcache*
.fakebin-*
MAX
quality-ratchet/
# Documentation
# Issue #2348: The Dashboard Docs viewer reads markdown from `/app/docs` at
@@ -69,10 +49,6 @@ quality-ratchet/
# (English) sources at runtime, so translations are not required in the
# container image.
docs/i18n/**
# Internal planning artifacts (gitignored). `*.md` above only matches the root,
# so without this rule these land in /app/docs and become readable through the
# dashboard's Docs viewer at runtime.
docs/superpowers/**
docs/diagrams/**/*.png
docs/diagrams/**/*.jpg
docs/diagrams/**/*.jpeg
@@ -101,8 +77,6 @@ bun.lock
# Agent config
.agents
.gemini
.claude
.source
# Misc
llm.txt
@@ -149,4 +123,3 @@ app.__qa_backup/
.worktrees
.next-playwright/
cloud/
electron/dist-electron

View File

@@ -1,12 +0,0 @@
root = true
[*]
indent_style = space
indent_size = 2
end_of_line = lf
charset = utf-8
trim_trailing_whitespace = true
insert_final_newline = true
[*.sh]
indent_size = 4

View File

@@ -1,6 +0,0 @@
ENABLE_LIVE_DEVIN_TESTS=0
DEVIN_BRIDGE_MODEL=devin-cli-agentic/swe-1-7
DEVIN_BRIDGE_SONNET_MODEL=devin-cli-agentic/swe-1-7
DEVIN_BRIDGE_OPUS_MODEL=devin-cli-agentic/swe-1-7
DEVIN_BRIDGE_HAIKU_MODEL=devin-cli-agentic/swe-1-7
DEVIN_BRIDGE_SUBAGENT_MODEL=devin-cli-agentic/swe-1-7

File diff suppressed because it is too large Load Diff

View File

@@ -1,9 +0,0 @@
# Homologação E2E real — copie para .env.homolog (NUNCA commitar o real)
HOMOLOG_BASE_URL=http://192.168.0.15:20128
# Senha de management do dashboard da VPS (a mesma do /login)
HOMOLOG_ADMIN_PASSWORD=
# Deixe vazio: a suíte cria uma API key efêmera via admin e revoga no fim.
# Só preencha para depurar uma camada isolada com uma key fixa.
HOMOLOG_API_KEY=
# Tier crítico (chat real, max_tokens=5). Demais providers: só validação de catálogo.
HOMOLOG_CRITICAL_PROVIDERS=openai,anthropic,gemini,codex,grok,glm,deepseek,openrouter

View File

@@ -24,32 +24,12 @@ updates:
update-types: ["version-update:semver-major"]
- dependency-name: "eslint-config-next"
update-types: ["version-update:semver-major"]
# typescript majors are peer-blocked by typescript-eslint, which pins a hard
# upper bound (8.64.0 → peerDependencies.typescript ">=4.8.4 <6.1.0"). A TS 7
# bump therefore violates the peer and takes down the whole toolchain at once —
# #7068 grouped it with 6 harmless bumps and turned Build + Lint + Quality Ratchet
# + Unit (6/8, 8/8) + Integration (1/2, 2/2) + dast-smoke red in one shot, blocking
# the innocuous updates riding along with it. Un-ignore once typescript-eslint
# widens the peer, and migrate TS majors intentionally (own PR, own CI run).
- dependency-name: "typescript"
update-types: ["version-update:semver-major"]
# jscpd v5 is a Rust rewrite (native binary, no Node.js programmatic API).
# scripts/check/check-duplication.mjs is deliberately pinned to jscpd@4 (it
# parses jscpd-report.json against a frozen baseline). A v5 major would break
# the duplication gate — migrate the gate intentionally, not via dependabot.
- dependency-name: "jscpd"
update-types: ["version-update:semver-major"]
# ioredis is a SOFT/optional dependency loaded through a dynamic import
# (src/lib/quota/redisQuotaStore.ts — "Redis driver requires ioredis package"),
# so a breaking major never fails at build or typecheck time: the only consumers
# are the distributed quota store (redisQuotaStore.ts, storeFactory.ts) and the
# `import type Redis` in src/shared/utils/rateLimiter.ts. Nothing in the unit or
# vitest suites exercises a live Redis connection, so a v5→v6 API break would ship
# green and only surface at runtime for operators running distributed quota — the
# exact users least able to absorb it. #9310 grouped that major with 9 harmless
# bumps; majors here need their own PR and a deliberate migration review.
- dependency-name: "ioredis"
update-types: ["version-update:semver-major"]
# @huggingface/transformers is HARD-PINNED at 3.5.2 (exact, no caret) — FROZEN.
# It is load-bearing for the LLMLingua ONNX compression engine (open-sse/services/
# compression/engines/llmlingua/ — worker.ts pins @huggingface/transformers@3.5.2)

View File

@@ -9,15 +9,10 @@
## Validation
Choose the change type and focused loop from the
[Contribution Golden Path](../docs/ops/CONTRIBUTION_GOLDEN_PATH.md). The full unit suite,
Vitest, the 60% coverage gate, and the production build all run in CI on this PR (#8329):
- [ ] Change type: provider / routing / UI / i18n / CLI / DB / build-deploy / other
- [ ] Focused tests and category gates from the golden path
- [ ] `npm run lint`
- [ ] Reconciled with the current active release base; focused checks rerun afterward
- [ ] Production-code changes include a new or updated automated test in this PR
- [ ] `npm run test:unit`
- [ ] `npm run test:coverage`
- [ ] Coverage is still `>= 60%` for statements, lines, functions, and branches
- [ ] SonarQube PR analysis is green or any remaining issues are explicitly documented below
## Tests Added Or Updated
@@ -32,4 +27,4 @@ Vitest, the 60% coverage gate, and the production build all run in CI on this PR
## Reviewer Notes
- Call out any risky areas, migrations, feature flags, or manual validation that reviewers should know about.
- Call out any risky areas, migrations, feature flags, or manual validation that reviewers should know about.

71
.github/workflows/build-fork.yml vendored Normal file
View File

@@ -0,0 +1,71 @@
name: Publish Fork Image to GHCR
on:
push:
branches: [main]
tags:
- "v*"
workflow_dispatch:
# Least-privilege default: read-only at the top level; the build job that pushes to
# GHCR grants packages: write itself (Scorecard TokenPermissions).
permissions:
contents: read
env:
IMAGE_NAME: ghcr.io/kang-heewon/omniroute
jobs:
build:
name: Build and Push Fork Image
if: github.repository == 'kang-heewon/OmniRoute'
runs-on: ubuntu-latest
permissions:
contents: read
packages: write
steps:
- name: Checkout
uses: actions/checkout@v7
with:
persist-credentials: false
- name: Set up QEMU
uses: docker/setup-qemu-action@v4
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v4
- name: Login to GitHub Container Registry
uses: docker/login-action@v4
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Extract Docker metadata
id: meta
uses: docker/metadata-action@v6
with:
images: ${{ env.IMAGE_NAME }}
tags: |
type=raw,value=latest,enable={{is_default_branch}}
type=sha,prefix=sha-
type=ref,event=tag
labels: |
org.opencontainers.image.title=omniroute
org.opencontainers.image.description=Unified AI proxy/router — fork image
org.opencontainers.image.url=https://github.com/kang-heewon/OmniRoute
org.opencontainers.image.source=https://github.com/kang-heewon/OmniRoute
org.opencontainers.image.licenses=MIT
- name: Build and push
uses: docker/build-push-action@v7
with:
context: .
target: runner-base
platforms: linux/amd64,linux/arm64
push: true
tags: ${{ steps.meta.outputs.tags }}
labels: ${{ steps.meta.outputs.labels }}
cache-from: type=gha
cache-to: type=gha,mode=max

View File

@@ -1,57 +0,0 @@
name: Build App
on:
workflow_dispatch:
push:
branches: ["**"]
permissions:
contents: read
jobs:
build:
name: Fast Production Build
runs-on: ubuntu-latest
steps:
- name: Expand Virtual Memory (Native 10GB Swap)
run: |
sudo swapoff -a || true
sudo rm -f /mnt/swapfile /swapfile
sudo fallocate -l 10G /mnt/swapfile || sudo dd if=/dev/zero of=/mnt/swapfile bs=1M count=10240
sudo chmod 600 /mnt/swapfile
sudo mkswap /mnt/swapfile
sudo swapon /mnt/swapfile
free -h
- name: Checkout repository
uses: actions/checkout@v7
with:
persist-credentials: false
- name: Setup Node.js
uses: actions/setup-node@v7
with:
node-version: "24"
cache: npm
- name: Install dependencies
run: npm ci
- name: Build Next.js app & CLI bundle
run: |
npm run build:release
env:
NODE_OPTIONS: "--max-old-space-size=12288"
OMNIROUTE_BUILD_MEMORY_MB: "12288"
OMNIROUTE_USE_TURBOPACK: "1"
- name: Archive build outputs
run: |
tar -czf omniroute-build.tar.gz .build dist
- name: Upload build artifact
uses: actions/upload-artifact@v4
with:
name: omniroute-build
path: omniroute-build.tar.gz
retention-days: 7

File diff suppressed because it is too large Load Diff

View File

@@ -19,13 +19,13 @@ jobs:
actions: read
contents: read
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
persist-credentials: false
- uses: github/codeql-action/init@f205ea1c3313d32999d8d6a48b4f6530d4437b38 # v4.37.4
- uses: github/codeql-action/init@8aad20d150bbac5944a9f9d289da16a4b0d87c1e # v4.36.2
with:
languages: javascript-typescript
queries: security-extended
- uses: github/codeql-action/analyze@f205ea1c3313d32999d8d6a48b4f6530d4437b38 # v4.37.4
- uses: github/codeql-action/analyze@8aad20d150bbac5944a9f9d289da16a4b0d87c1e # v4.36.2
with:
category: "/language:javascript-typescript"

View File

@@ -2,45 +2,28 @@ name: DAST smoke (PR)
on:
pull_request:
branches: ["main", "release/**"]
# Runner-cost guard (#8084): the CLI-bundle build alone is 6-11min; a docs-only PR
# cannot change DAST behavior, so skip the whole workflow for pure docs/markdown
# changes. Any code path in the diff still runs the full smoke.
paths-ignore:
- "docs/**"
- "**/*.md"
permissions:
contents: read
# Superseded runs on the same PR must not stack 25-minute advisory builds
# (force-push storms were holding 2-3 runners each). Same group rule as quality.yml.
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
jobs:
dast-smoke:
runs-on: ubuntu-latest
# ADVISORY while this new gate matures (repo convention: advisory -> blocking).
# Flip to blocking (remove continue-on-error) once it's proven stable across a few PRs.
continue-on-error: true
# Build CLI bundle alone varies 6-11min on GitHub-hosted runners (3 consecutive
# timeouts observed on 2026-07-14 with the old 12min cap killing schemathesis
# mid-run) — 25min leaves real headroom for the actual DAST steps.
timeout-minutes: 25
timeout-minutes: 12
env:
JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
API_KEY_SECRET: ci-api-key-secret-with-sufficient-length-aaaa
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
persist-credentials: false
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
- uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
with:
node-version: "24"
cache: npm
- run: npm ci
- name: Build CLI bundle
env:
OMNIROUTE_BUILD_BACKEND_ONLY: "1"
run: npm run build:cli
- name: Start OmniRoute
env:
@@ -53,20 +36,14 @@ jobs:
if curl -sf http://localhost:20128/api/monitoring/health >/dev/null; then echo up; break; fi
sleep 2
done
- uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7.0.0
- uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
with:
python-version: "3.12"
- run: pip install schemathesis
- name: Schemathesis smoke (high-risk endpoints, blocking)
run: |
# /api/auth/oidc/* is a BROWSER redirect flow (302 to the IdP, 302 back to
# /login?oidc_error=... on every failure), not a REST endpoint: Schemathesis reads
# those 302s as "the API accepted a schema-violating request" and the configured-off
# 400 as "rejected a schema-compliant request". Documenting the flow in the spec is
# still right (operators need it); fuzzing it is not what this smoke is for.
schemathesis run docs/openapi.yaml --url http://localhost:20128 \
--include-path-regex '^/v1/(chat/completions|models)$|^/api/(auth|keys)' \
--exclude-path-regex '^/api/auth/oidc/' \
--max-examples 8 --workers 4 --checks all --max-response-time 30 \
--request-timeout 20 --suppress-health-check all --no-color
- name: promptfoo injection-guard (blocking)

View File

@@ -4,7 +4,6 @@ on:
push:
branches:
- main
- "release/v*"
tags:
- "v*"
paths-ignore:
@@ -58,20 +57,39 @@ jobs:
REF_TYPE: ${{ github.ref_type }}
INPUT_VERSION: ${{ inputs.version }}
PROMOTE_INPUT: ${{ inputs.promote_latest }}
DEFAULT_BRANCH: ${{ github.event.repository.default_branch }}
run: |
set -euo pipefail
# 1) Resolve version/channel from the trigger. Only the current default
# release branch publishes the mutable `next` channel; main keeps `main`.
VERSION=$(bash scripts/ci/resolve-docker-publish-version.sh \
"$EVENT_NAME" "$REF_TYPE" "$REF_NAME" "$INPUT_VERSION" "$DEFAULT_BRANCH")
# 1) Resolve version string from the trigger (all inputs come via env).
case "$EVENT_NAME" in
workflow_dispatch)
VERSION="${INPUT_VERSION#v}"
;;
push)
if [ "$REF_TYPE" = "tag" ]; then
VERSION="${REF_NAME#v}"
else
# Push to main → build & tag as `main` only. Never touch :latest.
VERSION="main"
fi
;;
release)
VERSION="${REF_NAME#v}"
;;
*)
VERSION="${REF_NAME#v}"
;;
esac
# Sanity-check: only allow [A-Za-z0-9._-] in VERSION (defense in depth).
if ! printf '%s' "$VERSION" | grep -qE '^[A-Za-z0-9._-]+$'; then
echo "Refusing to use unsafe VERSION value: $VERSION" >&2
exit 1
fi
echo "version=$VERSION" >> "$GITHUB_OUTPUT"
# 2) Decide whether to promote :latest. Floating channels are never
# eligible, and the helper independently fails closed for non-semver.
# 2) Decide whether to promote :latest.
PROMOTE="false"
if [ "$VERSION" = "main" ] || [ "$VERSION" = "next" ]; then
if [ "$VERSION" = "main" ]; then
PROMOTE="false"
elif printf '%s' "$VERSION" | grep -qE -- '-(rc|alpha|beta|pre|next)'; then
echo "Pre-release identifier detected — skipping :latest."
@@ -80,21 +98,19 @@ jobs:
PROMOTE="${PROMOTE_INPUT:-false}"
else
git fetch --tags --quiet || true
# Decide via the extracted helper, which folds VERSION into the
# candidate set so the result is independent of git-tag sync timing
# on `release` events (#5301). Without that, the freshly-created tag
# is often not yet visible here and :latest stays a release behind.
PROMOTE=$(git tag -l 'v[0-9]*' | bash scripts/ci/should-promote-latest.sh "$VERSION")
if [ "$PROMOTE" != "true" ]; then
echo "Version $VERSION is not the highest stable semver. Not promoting :latest."
HIGHEST=$(git tag -l 'v[0-9]*' | sed 's/^v//' | grep -vE -- '-(rc|alpha|beta|pre|next)' | sort -V | tail -1 || echo "")
if [ -n "$HIGHEST" ] && [ "$VERSION" = "$HIGHEST" ]; then
PROMOTE="true"
else
echo "Version $VERSION is not the highest semver tag (highest=${HIGHEST:-<none>}). Not promoting :latest."
fi
fi
echo "promote_latest=$PROMOTE" >> "$GITHUB_OUTPUT"
# 3) Skip immutable version tags that already exist. Floating `main`
# and `next` channels are intentionally rebuilt on every matching push.
# 3) Skip if this exact version is already published in Docker Hub.
# `main` is always rebuilt (mutable floating tag).
SKIP="false"
if [ "$VERSION" != "main" ] && [ "$VERSION" != "next" ]; then
if [ "$VERSION" != "main" ]; then
if docker manifest inspect "diegosouzapw/omniroute:${VERSION}" >/dev/null 2>&1; then
echo "Image diegosouzapw/omniroute:${VERSION} already exists on Docker Hub — skipping rebuild."
SKIP="true"
@@ -137,13 +153,13 @@ jobs:
uses: docker/setup-buildx-action@v4
- name: Login to Docker Hub
uses: docker/login-action@v4.6.0
uses: docker/login-action@v4
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Login to GitHub Container Registry
uses: docker/login-action@v4.6.0
uses: docker/login-action@v4
with:
registry: ghcr.io
username: ${{ github.actor }}
@@ -237,13 +253,13 @@ jobs:
uses: docker/setup-buildx-action@v4
- name: Login to Docker Hub
uses: docker/login-action@v4.6.0
uses: docker/login-action@v4
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Login to GitHub Container Registry
uses: docker/login-action@v4.6.0
uses: docker/login-action@v4
with:
registry: ghcr.io
username: ${{ github.actor }}
@@ -328,15 +344,6 @@ jobs:
# Visibility scan: reports HIGH + CRITICAL into the SARIF (Security tab) but
# never blocks (exit-code 0). The blocking gate below narrows to CRITICAL.
#
# ignore-unfixed mirrors the blocking gate: the Security tab must surface only
# ACTIONABLE vulnerabilities — ones with a published fix we can pull by rebuilding
# on a patched base or bumping the dep. Without it the advisory upload floods the
# tab with unfixable base-image OS CVEs (Debian trixie packages with no upstream
# patch yet, overwhelmingly local-only and not reachable from the proxy request
# surface), which is noise an operator cannot act on. trivyignores points at the
# repo-root .trivyignore so accepted-risk fixable CVEs have one auditable home.
# See docs/security/SUPPLY_CHAIN.md.
- name: Trivy image scan (SARIF, advisory)
if: needs.prepare.outputs.version != 'main'
continue-on-error: true
@@ -346,8 +353,6 @@ jobs:
format: sarif
output: trivy-results.sarif
severity: HIGH,CRITICAL
ignore-unfixed: true
trivyignores: .trivyignore
exit-code: "0"
# BLOCKING gate (v3.8.27 cycle-end): fail the release on a CRITICAL CVE in the
@@ -372,14 +377,14 @@ jobs:
- name: Upload Trivy SARIF to Security tab
if: needs.prepare.outputs.version != 'main'
continue-on-error: true
uses: github/codeql-action/upload-sarif@v4.37.4
uses: github/codeql-action/upload-sarif@v4
with:
sarif_file: trivy-results.sarif
category: trivy-image
- name: Update Docker Hub description
# Only refresh README/description when we actually promote :latest
# (avoids overwriting from main, next, or back-fill builds).
# (avoids overwriting from main pushes or back-fill builds).
if: needs.prepare.outputs.promote_latest == 'true'
uses: peter-evans/dockerhub-description@v5
with:

View File

@@ -88,13 +88,13 @@ jobs:
with:
persist-credentials: false
- name: Setup Node
uses: actions/setup-node@v7
uses: actions/setup-node@v6
with:
node-version: 24
cache: npm
- name: Cache node_modules
uses: actions/cache@v6.1.0
uses: actions/cache@v5.0.5
with:
path: node_modules
key: ${{ runner.os }}-node-${{ hashFiles('package-lock.json') }}
@@ -120,18 +120,6 @@ jobs:
env:
JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
NODE_OPTIONS: "--max_old_space_size=6144"
# Linux builds with webpack, not Turbopack. Turbopack's production build
# allocates natively (Rust, off the V8 heap), so --max_old_space_size does
# not bound it, and on this module graph it peaks above what the hosted
# runner can give — the VM is reclaimed mid-compile with "The runner has
# received a shutdown signal", no exit code. That is what silently took the
# whole desktop channel out of v3.8.49: the linux leg died, `release` was
# skipped, and the release shipped with ZERO assets. Measured on a 32 GB
# box the same build passes and peaks past 14 GB. The webpack fallback is
# the project's documented escape hatch for RAM-constrained machines
# (docs/reference/ENVIRONMENT.md, #6409) and is the same remedy already
# applied to nightly-compat's Node 26 build (#8090).
OMNIROUTE_USE_TURBOPACK: ${{ matrix.platform == 'linux' && '0' || '1' }}
run: npm run build
- name: Sync version in electron/package.json
@@ -213,12 +201,6 @@ jobs:
[ -f "$file" ] && cp "$file" "../../release-assets/OmniRoute.exe" && break
done
fi
# electron-updater manifests (latest.yml / latest-mac.yml / latest-linux.yml)
# must be published alongside the installers, or autoUpdater fails with
# "Cannot find latest.yml in the latest release artifacts" (#6766).
for file in latest*.yml; do
[ -f "$file" ] && cp "$file" ../../release-assets/
done
- name: Upload artifacts
uses: actions/upload-artifact@v7
@@ -229,16 +211,6 @@ jobs:
release:
name: Create Release
needs: [validate, build]
# Fail-partial, not fail-closed. `build` is a 4-leg matrix with `fail-fast: false`,
# so the legs that succeed still upload their artifacts — but a default `needs:`
# gate skips this job the moment ANY leg fails, discarding all of them. That is
# exactly what happened to v3.8.49: the linux leg died and the release shipped with
# ZERO assets, throwing away 1.7 GB of good Windows/macOS installers **and** the
# source archives + SBOM, which do not depend on a build at all. The result was
# indistinguishable from "this version has no desktop channel".
# Now: attach everything that did build, then fail the job loudly (see the last
# step) so an incomplete channel is visible instead of silent.
if: ${{ !cancelled() && needs.validate.result == 'success' }}
runs-on: ubuntu-latest
permissions:
contents: write # softprops/action-gh-release creates the GitHub Release
@@ -249,33 +221,11 @@ jobs:
persist-credentials: false
fetch-depth: 0
# `merge-multiple` is deliberately OFF. It resolves same-name collisions by ARRIVAL
# ORDER, and the two macOS jobs each emit their own `latest-mac.yml` listing only their
# own dmg (measured: 338 and 350 bytes, different content, identical name). One silently
# overwrote the other — arm64 won in the published v3.8.48, and since the Intel dmg
# carries no arch suffix in its name, electron-updater's
# `files.find(url includes process.arch) ?? files.shift()` sends every Intel Mac to the
# ARM dmg. Downloading into per-artifact subdirectories keeps both, so they can be
# merged on purpose instead of by luck.
- name: Download all artifacts
uses: actions/download-artifact@v8
with:
path: artifacts
# Writes release-assets/latest-mac.yml with BOTH dmgs, un-suffixed entry first (that is
# the one electron-updater can only reach through its fallback). Refuses to write when the
# inputs disagree on version — a manifest stitched from two builds is worse than none.
- name: Merge the per-arch macOS updater manifests
run: node scripts/release/merge-mac-update-manifest.mjs artifacts release-assets
# Everything else moves across as-is. The partial latest-mac.yml files are excluded so
# they cannot clobber the merged one; -n is a second belt on the same braces.
- name: Collect the remaining artifacts
run: |
mkdir -p release-assets
find artifacts -type f ! -name latest-mac.yml -exec cp -n {} release-assets/ \;
echo "release-assets:"
ls -la release-assets/
path: release-assets
merge-multiple: true
- name: Create source archives
env:
@@ -313,53 +263,11 @@ jobs:
release-assets/*.AppImage
release-assets/*.deb
release-assets/*.blockmap
release-assets/*.yml
release-assets/*.source.tar.gz
release-assets/*.source.zip
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
verify-desktop-assets:
name: Verify desktop assets landed
needs: [validate, release]
# Deliberately a SEPARATE job, not a final step of `release`: failing inside
# `release` would cascade into `publish-npm` (which gates on `needs: release`) and
# block the npm channel over a desktop-only gap. Here the assets are attached, npm
# still publishes, and an incomplete desktop channel shows up as a red job instead
# of passing unnoticed — the v3.8.49 release had ZERO assets and every gate was
# green, because nothing ever asserted the release HAS binaries.
if: ${{ !cancelled() && needs.release.result == 'success' }}
runs-on: ubuntu-latest
permissions:
contents: read
steps:
- name: Assert every platform is present on the release
env:
# Regex-validated (^v[0-9]+\.[0-9]+\.[0-9]+$) in the `validate` job, and
# passed via env rather than interpolated into the script body.
VERSION: ${{ needs.validate.outputs.version }}
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
names=$(gh release view "$VERSION" --repo "$GITHUB_REPOSITORY" \
--json assets --jq '.assets[].name')
echo "Assets on $VERSION:"
echo "$names" | sed 's/^/ /'
missing=""
# `[ ... ] && missing=...` as the last command in a branch returns 1 and
# would abort the whole script under Actions' default `set -e`. Use if/fi.
for want in '\.exe$' '\.dmg$' '\.AppImage$' '\.deb$' '^latest.*\.yml$' '\.source\.tar\.gz$'; do
if ! echo "$names" | grep -qE "$want"; then
missing="$missing $want"
fi
done
if [ -n "$missing" ]; then
echo "::error::Desktop channel incomplete on $VERSION — no asset matching:$missing"
exit 1
fi
echo "✓ every platform present on $VERSION"
publish-npm:
name: Publish to npm
needs: [validate, release]

View File

@@ -44,7 +44,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: "24"
cache: npm

View File

@@ -1,139 +0,0 @@
name: Nightly Node Compat
# Plano mestre testes+CI (Eixo D2, aprovado 2026-07-04): as matrizes de compatibilidade
# Node 24/26 custavam ~28% de CADA run do CI pesado (2 execuções completas da suíte por
# sync da release-PR) para pegar uma classe de quebra que raramente nasce num PR típico.
# Elas rodam aqui 1×/dia contra o tip da release ativa (mesmo alvo do nightly-release-green)
# e continuam obrigatórias no gate de release via workflow_dispatch do ci.yml se preciso.
# fail-fast desligado: numa quebra queremos saber TODAS as versões afetadas de uma vez.
on:
schedule:
- cron: "47 6 * * *" # 06:47 UTC diário — slot distinto dos demais nightlies
workflow_dispatch:
inputs:
branch:
description: "Branch to validate (default: highest release/vX.Y.Z)"
required: false
type: string
permissions:
contents: read
issues: write
concurrency:
group: nightly-compat
cancel-in-progress: true
jobs:
resolve-branch:
name: Resolve active release branch
runs-on: ubuntu-latest
outputs:
target: ${{ steps.branch.outputs.target }}
steps:
- uses: actions/checkout@v7
with:
fetch-depth: 0
persist-credentials: false
- name: Resolve active release branch
id: branch
env:
INPUT_BRANCH: ${{ github.event.inputs.branch }}
run: |
set -euo pipefail
if [ -n "${INPUT_BRANCH:-}" ]; then
TARGET="$INPUT_BRANCH"
else
TARGET=$(git for-each-ref --format='%(refname:short)' 'refs/remotes/origin/release/v*' \
| sed 's#origin/##' \
| sort -t/ -k2 -V \
| tail -1)
fi
case "$TARGET" in
release/v[0-9]*.[0-9]*.[0-9]*) ;;
*) echo "Refusing non-canonical branch name: $TARGET"; exit 1 ;;
esac
echo "target=$TARGET" >> "$GITHUB_OUTPUT"
compat-build-26:
name: Node 26 Compatibility Build
runs-on: ubuntu-latest
timeout-minutes: 25
needs: resolve-branch
steps:
- uses: actions/checkout@v7
with:
ref: ${{ needs.resolve-branch.outputs.target }}
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: "26"
cache: npm
- uses: ./.github/actions/npm-ci-retry
# #8090 — this is the ONLY Node 26 build in the whole CI matrix (ci.yml pins
# CI_NODE_VERSION=24). It failed every nightly with the runner-reclaimed
# signature ("The runner has received a shutdown signal" / "The operation was
# canceled", no exit code) always at the same Turbopack compile phase — a
# classic OOM kill on the memory-constrained ubuntu-latest runner. Turbopack's
# native (Rust, off-V8-heap) allocation is NOT bounded by --max-old-space-size
# and peaks far higher than webpack on this large module graph (#6409), and is
# heavier still under Node 26. Use the documented webpack fallback here: it still
# validates that the app *builds* on Node 26 (the point of this compat job) at a
# much lower memory peak. Turbopack-on-Node-24 stays covered by ci.yml's build
# job. See docs/reference/ENVIRONMENT.md (OMNIROUTE_USE_TURBOPACK) and #6409.
- run: npm run build
env:
OMNIROUTE_USE_TURBOPACK: "0"
compat-tests:
name: Node ${{ matrix.node }} Compat Tests (${{ matrix.shard }}/4)
runs-on: ubuntu-latest
timeout-minutes: 25
needs: resolve-branch
strategy:
fail-fast: false
matrix:
node: [24, 26]
shard: [1, 2, 3, 4]
env:
JWT_SECRET: ci-nightly-secret-with-sufficient-length-for-validation
API_KEY_SECRET: ci-nightly-api-key-secret-long
DISABLE_SQLITE_AUTO_BACKUP: "true"
TEST_SHARD: ${{ matrix.shard }}/4
steps:
- uses: actions/checkout@v7
with:
ref: ${{ needs.resolve-branch.outputs.target }}
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: ${{ matrix.node }}
cache: npm
- uses: ./.github/actions/npm-ci-retry
- run: npm run check:node-runtime
- run: npm run test:unit:ci:shard
report:
name: Open / update tracking issue on failure
runs-on: ubuntu-latest
if: ${{ !cancelled() && (needs.compat-tests.result == 'failure' || needs.compat-build-26.result == 'failure') }}
needs: [resolve-branch, compat-build-26, compat-tests]
permissions:
issues: write
steps:
- name: Open or update issue
env:
GH_TOKEN: ${{ github.token }}
TARGET: ${{ needs.resolve-branch.outputs.target }}
RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
run: |
set -euo pipefail
TITLE="🌙 nightly-compat: Node 24/26 failures on $TARGET"
EXISTING=$(gh issue list --repo "$GITHUB_REPOSITORY" --state open --search "$TITLE in:title" --json number --jq '.[0].number')
BODY="Nightly Node-compat run failed on \`$TARGET\`: $RUN_URL — triage which Node version/shard broke (fail-fast off, all versions reported)."
if [ -n "$EXISTING" ]; then
gh issue comment "$EXISTING" --repo "$GITHUB_REPOSITORY" --body "$BODY"
else
gh issue create --repo "$GITHUB_REPOSITORY" --title "$TITLE" --body "$BODY"
fi

View File

@@ -15,13 +15,11 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with: { node-version: "24", cache: npm }
- run: npm ci
- name: Build CLI bundle
env:
JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
OMNIROUTE_BUILD_BACKEND_ONLY: "1"
env: { JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation }
run: npm run build:cli
- name: Start OmniRoute (block mode)
env:
@@ -67,16 +65,14 @@ jobs:
with:
persist-credentials: false
if: steps.gate.outputs.run == 'true'
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
if: steps.gate.outputs.run == 'true'
with: { node-version: "24", cache: npm }
- run: npm ci
if: steps.gate.outputs.run == 'true'
- name: Build CLI bundle
if: steps.gate.outputs.run == 'true'
env:
JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
OMNIROUTE_BUILD_BACKEND_ONLY: "1"
env: { JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation }
run: npm run build:cli
- name: Start OmniRoute
if: steps.gate.outputs.run == 'true'
@@ -90,7 +86,7 @@ jobs:
if curl -sf http://localhost:20128/api/monitoring/health >/dev/null; then echo up; break; fi
sleep 2
done
- uses: actions/setup-python@v7
- uses: actions/setup-python@v6
if: steps.gate.outputs.run == 'true'
with: { python-version: "3.12" }
- run: pip install garak

View File

@@ -107,13 +107,13 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: "24"
cache: npm
- run: npm ci
- name: Restore Stryker incremental cache
uses: actions/cache@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
with:
path: reports/mutation/stryker-incremental.json
key: stryker-incremental-${{ matrix.batch.name }}-${{ github.run_id }}
@@ -148,10 +148,10 @@ jobs:
runs-on: ubuntu-latest
timeout-minutes: 15
steps:
- uses: actions/checkout@v7
- uses: actions/checkout@v6
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: "24"
- name: Download all mutation reports

View File

@@ -13,7 +13,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: "24"
cache: npm

View File

@@ -1,18 +1,11 @@
name: Release-Green (continuous)
name: Nightly Release-Green
# Solution D — continuous, NON-BLOCKING drift signal for the active release branch.
#
# WHY: the full gate (ci.yml) only runs on the release PR (PR → main), so reds
# accrue silently on release/** and explode — in layers — at release time. This
# workflow reproduces the release-equivalent validation on the release branch and,
# when there are HARD failures, opens/updates a single tracking issue.
#
# WS5.1 (v3.8.49 quality plan) — two modes:
# push to release/v* (code paths) → --quick (fast HARD gates, ~5-8min). Catches the
# captain's direct pushes (sync-back — the one ungated write path) AND the merged
# COMBINATION right after every PR merge, attributing the offending push range in
# the issue. Base-red MTTD drops from ≤24h to ≤~15min after the offending push.
# schedule (3×/day) → full --with-build --full-ci (the deep sweep incl. build+suites).
# nightly reproduces the release-equivalent validation on the active release branch
# HEAD and, when there are HARD failures, opens/updates a single tracking issue.
#
# It is NOT a required status check and never touches a contributor PR — it only
# reports. Ratchet drift (eslint warnings / cognitive-complexity / file-size) is
@@ -21,23 +14,8 @@ name: Release-Green (continuous)
# package-artifact) flip the issue open.
on:
push:
branches: ["release/v*", "main"]
paths:
- "src/**"
- "open-sse/**"
- "bin/**"
- "electron/**"
- "scripts/**"
- "tests/**"
- "config/**"
- "package.json"
- "package-lock.json"
- "tsconfig*.json"
schedule:
- cron: "23 5 * * *" # full sweep — off-peak, distinct from other nightlies
- cron: "23 12 * * *" # full sweep — midday (WS5.1: 3×/day instead of 1×)
- cron: "23 18 * * *" # full sweep — evening
- cron: "23 5 * * *" # 05:23 UTC daily — off-peak, distinct from other nightlies
workflow_dispatch:
inputs:
branch:
@@ -50,25 +28,13 @@ permissions:
issues: write
concurrency:
# push storms during merge campaigns collapse to the newest commit per branch;
# scheduled full sweeps keep their own single lane.
group: release-green-${{ github.event_name }}-${{ github.ref }}
group: nightly-release-green
cancel-in-progress: true
env:
OMNIROUTE_SKIP_SYSTEM_TRUST: "1"
jobs:
release-green:
name: Validate active release branch
# On a push, only run for release/* pushes — a push to main is handled by the
# main-green job below. Schedule/dispatch always run (they validate the highest release).
if: ${{ github.event_name != 'push' || startsWith(github.ref_name, 'release/') }}
# Dynamic runner: with USE_VPS_RUNNER=true (release window / on-demand pre-flight)
# this runs on the dedicated VPS runner — clean env (no operator OMNIROUTE_API_KEY,
# no local noauth CLIs => zero machine-specific false positives) and no contention.
# Nightly cron normally finds the var false (VM off) and falls back to hosted.
runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && fromJSON('["self-hosted","omni-release"]')) || 'ubuntu-latest' }}
runs-on: ubuntu-latest
env:
JWT_SECRET: ci-nightly-secret-with-sufficient-length-for-validation
API_KEY_SECRET: ci-nightly-api-key-secret-long
@@ -83,15 +49,10 @@ jobs:
id: branch
env:
INPUT_BRANCH: ${{ github.event.inputs.branch }}
EVENT_NAME: ${{ github.event_name }}
PUSHED_REF: ${{ github.ref_name }}
run: |
set -euo pipefail
if [ -n "${INPUT_BRANCH:-}" ]; then
TARGET="$INPUT_BRANCH"
elif [ "$EVENT_NAME" = "push" ]; then
# validate exactly what was pushed, not the highest branch
TARGET="$PUSHED_REF"
else
# highest release/vX.Y.Z by semver among remote branches
TARGET=$(git for-each-ref --format='%(refname:short)' 'refs/remotes/origin/release/v*' \
@@ -116,7 +77,7 @@ jobs:
git checkout "$TARGET"
git log -1 --oneline
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: "24"
cache: npm
@@ -125,27 +86,9 @@ jobs:
- name: Release-green validation (full)
id: validate
env:
EVENT_NAME: ${{ github.event_name }}
run: |
set +e
# --hermetic: scrub live-test trigger vars (self-hosted runner may carry
# operator env; hosted ignores the unknown flag before #6300 lands).
# push → --quick: fast HARD gates only (~5-8min), per-merge signal.
# schedule/dispatch → --with-build --full-ci: ALSO run every static gate from
# ci.yml's gate jobs (lint, quality-gate, quality-extended, docs-sync-strict,
# pr-test-policy) + build + full suites. PRs into release/** only get the
# fast-gates, so these accrue silently and explode in layers on the release PR
# (v3.8.46: 11 static base-reds leaked).
if [ "$EVENT_NAME" = "push" ]; then
MODE="--quick"
else
MODE="--with-build --full-ci"
fi
echo "[release-green] mode: $MODE (event: $EVENT_NAME)"
# MODE is an intentional flag list, so word-splitting is wanted here
# shellcheck disable=SC2086
node scripts/quality/validate-release-green.mjs --json --hermetic $MODE \
node scripts/quality/validate-release-green.mjs --json --with-build \
1> release-green.json 2> release-green.log
echo "exit=$?" >> "$GITHUB_OUTPUT"
echo "------- report -------"
@@ -157,28 +100,15 @@ jobs:
GH_TOKEN: ${{ github.token }}
TARGET: ${{ steps.branch.outputs.target }}
RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
EVENT_NAME: ${{ github.event_name }}
BEFORE_SHA: ${{ github.event.before }}
AFTER_SHA: ${{ github.event.after }}
run: |
set -euo pipefail
TITLE="🔴 Release branch not green: ${TARGET}"
{
echo "The **release-green** validation found HARD failures on \`${TARGET}\`."
echo "The nightly **release-green** validation found HARD failures on \`${TARGET}\`."
echo "These are real defects that would block the release PR — fix them in the"
echo "originating PR branch (via co-authorship), not by demanding it from contributors."
echo ""
echo "**Run:** ${RUN_URL} (mode: ${EVENT_NAME})"
# WS5.1 attribution: on push events the offending change IS this push's range
# (one merge per push in the normal queue), so name it — no bisect needed.
if [ "$EVENT_NAME" = "push" ] && [ -n "${BEFORE_SHA:-}" ] && \
git cat-file -e "$BEFORE_SHA" 2>/dev/null; then
echo ""
echo "**Offending push range** (\`${BEFORE_SHA:0:9}..${AFTER_SHA:0:9}\`):"
echo '```'
git log --no-decorate --oneline "${BEFORE_SHA}..${AFTER_SHA}" | head -20
echo '```'
fi
echo "**Run:** ${RUN_URL}"
echo ""
echo '```'
sed -n '/──────── verdict ────────/,$p' release-green.log || tail -40 release-green.log
@@ -193,255 +123,15 @@ jobs:
gh issue comment "$EXISTING" --repo "$GITHUB_REPOSITORY" --body-file issue-body.md
echo "Updated existing issue #$EXISTING"
else
gh issue create --repo "$GITHUB_REPOSITORY" --title "$TITLE" --label base-red --body-file issue-body.md
gh issue create --repo "$GITHUB_REPOSITORY" --title "$TITLE" --body-file issue-body.md
fi
- name: Upload report artifact
if: always()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v4
with:
name: release-green-report
path: |
release-green.json
release-green.log
if-no-files-found: ignore
# Companion arm for `main`. Under the parallel-cycle model, main only receives merged
# work at the release squash — so a gate/infra fix that lands only on release leaves
# main red the whole cycle, and repo-wide gates (CodeQL alert count, ratchet baselines)
# turn EVERY PR into main red on a check unrelated to its diff. This detects that and
# opens a "🔴 main not green" tracking issue. The PREVENTION is the companion-PR reflex
# (Hard Rule #21 area / _shared/merge-gates.md §8); this is the automated backstop.
main-green:
name: Validate main branch
# On a push, only run for a push to main — a push to release/* is handled by
# release-green above. Schedule/dispatch always run (they also sweep main).
if: ${{ github.event_name != 'push' || github.ref_name == 'main' }}
runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && fromJSON('["self-hosted","omni-release"]')) || 'ubuntu-latest' }}
env:
JWT_SECRET: ci-nightly-secret-with-sufficient-length-for-validation
API_KEY_SECRET: ci-nightly-api-key-secret-long
DISABLE_SQLITE_AUTO_BACKUP: "true"
steps:
- uses: actions/checkout@v7
with:
ref: main # literal — no injection surface; scheduled runs default to the repo default branch (a release/v*), so pin main explicitly
fetch-depth: 0
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: "24"
cache: npm
- uses: ./.github/actions/npm-ci-retry
- name: Main-green validation
id: validate
env:
EVENT_NAME: ${{ github.event_name }}
run: |
set +e
# push (a merge into main) → --quick fast HARD gates; schedule/dispatch → full sweep.
if [ "$EVENT_NAME" = "push" ]; then
MODE="--quick"
else
MODE="--with-build --full-ci"
fi
echo "[main-green] mode: $MODE (event: $EVENT_NAME)"
# MODE is an intentional flag list, so word-splitting is wanted here
# shellcheck disable=SC2086
node scripts/quality/validate-release-green.mjs --json --hermetic $MODE \
1> main-green.json 2> main-green.log
echo "exit=$?" >> "$GITHUB_OUTPUT"
echo "------- report -------"
cat main-green.log
- name: Open / update tracking issue on HARD failure
if: steps.validate.outputs.exit != '0'
env:
GH_TOKEN: ${{ github.token }}
RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
EVENT_NAME: ${{ github.event_name }}
run: |
set -euo pipefail
TITLE="🔴 main branch not green"
{
echo "The **main-green** validation found HARD failures on \`main\`."
echo ""
echo "Because \`main\` only receives merged work at the release squash, a gate/infra"
echo "fix that landed only on the release branch leaves \`main\` broken for the whole"
echo "cycle — and repo-wide gates (CodeQL alert count, ratchet baselines) then turn"
echo "**every open PR into main** red on a check unrelated to its diff. The fix is a"
echo "companion PR \`--base main\` carrying the release-side fix (see"
echo "\`_shared/merge-gates.md\` §8), NOT chasing each contributor PR."
echo ""
echo "**Run:** ${RUN_URL} (mode: ${EVENT_NAME})"
echo ""
echo '```'
sed -n '/──────── verdict ────────/,$p' main-green.log || tail -40 main-green.log
echo '```'
echo ""
echo "_Ratchet drift (eslint warnings / cognitive-complexity / file-size) is expected mid-cycle and did NOT, on its own, open this issue._"
} > issue-body.md
EXISTING=$(gh issue list --repo "$GITHUB_REPOSITORY" --state open \
--search "in:title $TITLE" --json number --jq '.[0].number' 2>/dev/null || echo "")
if [ -n "$EXISTING" ]; then
gh issue comment "$EXISTING" --repo "$GITHUB_REPOSITORY" --body-file issue-body.md
echo "Updated existing issue #$EXISTING"
else
gh issue create --repo "$GITHUB_REPOSITORY" --title "$TITLE" --label base-red --body-file issue-body.md
fi
- name: Upload report artifact
if: always()
uses: actions/upload-artifact@v7
with:
name: main-green-report
path: |
main-green.json
main-green.log
if-no-files-found: ignore
# ── Banking lane (#8584) ──────────────────────────────────────────────────
# The ratchet is asymmetric: RAISING a cap is a ten-second manual JSON edit made
# under merge pressure, LOWERING one requires someone to run `--update` and commit
# — which no workflow does. Grep `.github/workflows/` for `--update`: only
# wiki-sync.yml (unrelated) and ci.yml's check-quality-ratchet.mjs --require-tighten
# (a different script, a different metric). So a cap outlives the code that earned
# it and every completed decomposition silently becomes a growth allowance for
# whoever touches the file next. Measured on 2026-07-25: 18 frozen files already at
# or under the 800-line new-file cap, up to 132x (schemas.ts, 19 lines / 2523 cap),
# and 31 unfulfilled "tighten via --update next cycle" notes honoured exactly once
# (-1 unit) in six weeks.
#
# This job closes that loop by making the DOWNWARD direction as automatic as the
# upward one is easy. It measures the active release branch, runs the shrink-only
# `--update` paths, and opens ONE always-current PR with the result. It never
# pushes to release/* — a human still merges, so a bad measurement cannot land
# unreviewed. verify-ratchet-bank.mjs is the hard guarantee that the automation can
# only ever write in the shrink direction; if anything was raised, added, or a
# rebaseline note was touched, the job aborts and opens nothing.
#
# Schedule/dispatch only, deliberately NOT on push: banking has no latency
# requirement (a shrink banked within 8h is fine) and a per-merge run would rebuild
# the PR branch repeatedly during merge campaigns while paying for a full ESLint
# walk each time. Detection stays on push (release-green above); banking is batched.
bank-ratchet-shrinks:
name: Bank ratchet shrinks
if: ${{ github.event_name != 'push' }}
runs-on: ubuntu-latest
permissions:
contents: write
pull-requests: write
steps:
- uses: actions/checkout@v7
with:
fetch-depth: 0
- name: Resolve active release branch
id: branch
env:
INPUT_BRANCH: ${{ github.event.inputs.branch }}
run: |
set -euo pipefail
if [ -n "${INPUT_BRANCH:-}" ]; then
TARGET="$INPUT_BRANCH"
else
TARGET=$(git for-each-ref --format='%(refname:short)' 'refs/remotes/origin/release/v*' \
| sed 's#origin/##' \
| sort -t/ -k2 -V \
| tail -1)
fi
if [ -z "$TARGET" ]; then echo "No release/v* branch found"; exit 1; fi
# Same strict guard as the validation job — blocks ref/command injection
# through the workflow_dispatch input.
if ! printf '%s' "$TARGET" | grep -qE '^release/v[0-9]+\.[0-9]+\.[0-9]+$'; then
echo "Refusing non-canonical branch name: $TARGET"; exit 1
fi
echo "target=$TARGET" >> "$GITHUB_OUTPUT"
echo "bank_branch=chore/bank-ratchet-${TARGET#release/}" >> "$GITHUB_OUTPUT"
- name: Checkout the release branch
env:
TARGET: ${{ steps.branch.outputs.target }}
run: |
set -euo pipefail
git checkout "$TARGET"
git log -1 --oneline
- uses: actions/setup-node@v7
with:
node-version: "24"
cache: npm
- uses: ./.github/actions/npm-ci-retry
- name: Ratchet the baselines down
run: |
# Both --update paths are shrink-only by construction (file-size writes only
# on `improvements`, complexity-ratchets only when `.improved`), and both exit
# non-zero while the branch is over baseline — which is exactly when there is
# nothing to bank. Their exit code is not the signal; the verifier below is.
set +e
node scripts/check/check-file-size.mjs --update
node scripts/check/check-complexity-ratchets.mjs --update
exit 0
- name: Verify the write only went downward
id: verify
run: |
set -euo pipefail
# Exits 1 if ANYTHING was raised/added or a rebaseline note was touched.
# `set -e` then aborts the job before a commit exists — no PR is opened.
node scripts/quality/verify-ratchet-bank.mjs > bank-summary.md
if [ -n "$(git status --porcelain config/quality/)" ]; then
echo "changed=true" >> "$GITHUB_OUTPUT"
else
echo "changed=false" >> "$GITHUB_OUTPUT"
echo "Nothing to bank — baselines already match the code."
fi
- name: Open / update the banking PR
if: steps.verify.outputs.changed == 'true'
env:
GH_TOKEN: ${{ github.token }}
TARGET: ${{ steps.branch.outputs.target }}
BANK_BRANCH: ${{ steps.branch.outputs.bank_branch }}
RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
run: |
set -euo pipefail
git config user.name "github-actions[bot]"
git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
git checkout -B "$BANK_BRANCH"
git add config/quality/
git commit -m "chore(quality): bank ratchet shrinks measured on ${TARGET}"
git push --force origin "$BANK_BRANCH"
{
echo "Automated banking of quality-ratchet **shrinks** already present in"
echo "\`${TARGET}\` — the downward half of the ratchet, which nothing else runs (#8584)."
echo ""
echo "Produced by \`check:file-size --update\` + \`check:complexity-ratchets --update\`,"
echo "then verified by \`scripts/quality/verify-ratchet-bank.mjs\`: **nothing was raised,"
echo "nothing was added, no rebaseline note was touched** — the job aborts without"
echo "opening a PR if any of those is violated."
echo ""
echo "No product code changes. Merging retires growth allowances that the code no"
echo "longer needs; not merging leaves them available to whoever edits those files next."
echo ""
cat bank-summary.md
echo ""
echo "**Run:** ${RUN_URL}"
} > pr-body.md
EXISTING=$(gh pr list --repo "$GITHUB_REPOSITORY" --head "$BANK_BRANCH" \
--state open --json number --jq '.[0].number' 2>/dev/null || echo "")
if [ -n "$EXISTING" ]; then
gh pr edit "$EXISTING" --repo "$GITHUB_REPOSITORY" --body-file pr-body.md
echo "Updated existing PR #$EXISTING"
else
gh pr create --repo "$GITHUB_REPOSITORY" --base "$TARGET" --head "$BANK_BRANCH" \
--title "chore(quality): bank ratchet shrinks (${TARGET})" --body-file pr-body.md
fi

View File

@@ -15,7 +15,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: "24"
cache: npm
@@ -29,7 +29,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: "24"
cache: npm
@@ -43,7 +43,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: "24"
cache: npm
@@ -51,7 +51,6 @@ jobs:
- name: Build CLI bundle
env:
JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
OMNIROUTE_BUILD_BACKEND_ONLY: "1"
run: npm run build:cli
- name: Start OmniRoute (background)
env:
@@ -95,13 +94,13 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: "24"
cache: npm
- run: npm ci
- name: Cache Playwright browsers
uses: actions/cache@v6.1.0
uses: actions/cache@v5.0.5
with:
path: ~/.cache/ms-playwright
key: playwright-chromium-${{ runner.os }}-${{ hashFiles('package-lock.json') }}

View File

@@ -16,13 +16,11 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with: { node-version: "24", cache: npm }
- run: npm ci
- name: Build CLI bundle
env:
JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
OMNIROUTE_BUILD_BACKEND_ONLY: "1"
env: { JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation }
run: npm run build:cli
- name: Start OmniRoute (background)
env:
@@ -35,7 +33,7 @@ jobs:
if curl -sf http://localhost:20128/api/monitoring/health >/dev/null; then echo "server up"; break; fi
sleep 2
done
- uses: actions/setup-python@v7
- uses: actions/setup-python@v6
with: { python-version: "3.12" }
- name: Install schemathesis
run: pip install schemathesis

View File

@@ -22,14 +22,6 @@ on:
- latest
- next
- historic
publish_mode:
description: "staged = npm stage publish (owner approves with 2FA after the staged boot-verify); direct = legacy immediate publish (emergency fallback only)"
required: false
default: "staged"
type: choice
options:
- staged
- direct
workflow_call:
inputs:
version:
@@ -56,15 +48,8 @@ env:
jobs:
publish:
# Same dynamic-runner rule as ci.yml's `build`/`test-unit`: `build:cli` falls back to a
# full `next build`, whose working set outgrew the 16 GB hosted runner during the
# v3.8.49 cycle — the publish died with "The runner has received a shutdown signal"
# mid-"Creating an optimized production build" while v3.8.48 had still fit in 16min.
# This job never runs on `pull_request`, so the fork-safety clause is always true here;
# it is kept verbatim so the expression stays greppable against ci.yml.
runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && (github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository)) && fromJSON('["self-hosted","omni-release"]') || 'ubuntu-latest' }}
runs-on: ubuntu-latest
permissions:
actions: read # find + download the CI run's next-build artifact for this SHA
contents: write # gh release upload (attach SBOM to the GitHub Release)
id-token: write # npm provenance
packages: write # publish to npm.pkg.github.com
@@ -78,7 +63,7 @@ jobs:
fetch-depth: 0
- name: Setup Node.js
uses: actions/setup-node@v7
uses: actions/setup-node@v6
with:
node-version: ${{ env.NPM_PUBLISH_NODE_VERSION }}
registry-url: https://registry.npmjs.org
@@ -152,74 +137,6 @@ jobs:
run: |
npm version "$VERSION" --no-git-tag-version --allow-same-version
# Fast path: CI already built the standalone tree for THIS commit and uploaded it as
# `next-build`. `build:cli` (scripts/build/prepublish.ts) only shells out to a full
# `next build` when `.build/next/standalone/server.js` is missing — restoring the
# artifact turns the heaviest step of the publish into a download. Matching on
# `head_sha` is the tree-equality guarantee: same commit, same tree.
# Best-effort by design (retention is 1 day): every miss falls through to the build
# step below, which is why the dynamic runner above matters as the backstop.
#
# The `head_repository.full_name == env.REPO` clause is a supply-chain guard, not a
# filter refinement. This artifact becomes the published npm tarball. `pull_request`
# runs from forks execute in THIS repository's context and upload their own
# `next-build` built from fork-controlled source, and the runs API returns them for a
# matching `head_sha` — 57 such runs exist in this repo today. Without the clause,
# anything that made a fork's head commit coincide with the publish commit could put
# attacker-built bytes on npm. Requiring the run to originate from this repository
# excludes every fork run while keeping the fast path intact (verified: the same
# single run is selected either way for the current tip).
# CodeQL: actions/artifact-poisoning/critical.
- name: Reuse CI's next-build artifact (skips the heavy rebuild)
if: steps.resolve.outputs.skip != 'true'
continue-on-error: true
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
HEAD_SHA: ${{ github.sha }}
REPO: ${{ github.repository }}
run: |
set -uo pipefail
# The question is "which run HAS the artifact", not "which run passed" (gap 16).
# Requiring `conclusion == "success"` on the whole run discarded a perfectly good tree
# whenever any unrelated shard went red — one flaky test then pushed the publish into
# the 40-minute build this step exists to avoid. The artifact is only uploaded if the
# Build job itself succeeded, so its PRESENCE is the accurate signal; the run's overall
# conclusion is noise from jobs that have nothing to do with the tree.
#
# `head_repository.full_name == env.REPO` stays, and it is not a filter refinement:
# this tree becomes the published npm tarball, and fork `pull_request` runs execute in
# THIS repository's context uploading their own next-build. That clause is the
# supply-chain guard (CodeQL actions/artifact-poisoning).
CANDIDATES=$(gh api "repos/$REPO/actions/runs?head_sha=$HEAD_SHA&per_page=100" \
--jq '[.workflow_runs[]
| select(.name == "CI"
and .head_repository.full_name == env.REPO)]
| sort_by(.run_started_at) | reverse | .[0:5] | .[].id') || CANDIDATES=""
if [ -z "$CANDIDATES" ]; then
echo "::notice::no CI run from this repository for $HEAD_SHA — falling back to a full build"
exit 0
fi
RUN=""
for candidate in $CANDIDATES; do
if gh run download "$candidate" --repo "$REPO" --name next-build --dir /tmp/next-build 2>/dev/null; then
RUN="$candidate"
break
fi
echo " run $candidate carries no usable next-build — trying the next"
done
if [ -z "$RUN" ]; then
echo "::notice::none of the candidate runs still carries next-build (1-day retention) — falling back to a full build"
exit 0
fi
tar -xzf /tmp/next-build/e2e-build.tar.gz -C .
rm -rf /tmp/next-build
if [ -f .build/next/standalone/server.js ]; then
echo "✅ standalone tree restored from CI run $RUN — build:cli will skip next build"
else
echo "::notice::extract did not yield .build/next/standalone — falling back to a full build"
rm -rf .build
fi
- name: Build CLI bundle (standalone app)
if: steps.resolve.outputs.skip != 'true'
env:
@@ -249,46 +166,8 @@ jobs:
TAG: ${{ github.ref_name }}
run: gh release upload "$TAG" sbom-npm.cdx.json --clobber
# WS1.2/WS1.3 (#7065 class): the artifact that is about to be published must
# BOOT. build:cli already assembled dist/ above; this packs+installs+boots the
# real tarball and fails the publish before anything reaches the registry.
- name: Boot-smoke the tarball before ANY publish
- name: Publish to npm
if: steps.resolve.outputs.skip != 'true'
run: npm run check:pack-boot
# The boot-smoke above proves a CLEAN install boots. It does not prove the path that
# actually broke us: installing over an existing version, where ~110 SQLite migrations
# run against a populated database. v3.8.48 shipped as a hotfix because the published
# 3.8.47 crashed on boot, and the v3.8.49 upgrade path was first exercised end-to-end
# by hand on a real 3.8.48 box (VPS .16) — after publishing, which is exactly backwards.
# Runs BEFORE `npm stage publish` so a broken upgrade never reaches the registry at all;
# a staged package that is never approved simply expires, with no `npm deprecate` needed.
- name: Prove clean-install AND upgrade-over-previous both boot
if: steps.resolve.outputs.skip != 'true'
timeout-minutes: 30
run: npm run check:install-upgrade
# WS1.3 (D2, v3.8.49 plan): STAGED publishing by default — `npm stage publish`
# parks the exact bytes on the registry WITHOUT making them installable; the
# owner then verifies and approves with 2FA (`npm stage approve`), moving the
# human gate to AFTER the proof instead of before it. Requires npm >= 11.15
# (staged publishing GA 2026-05-22). publish_mode=direct is the emergency
# fallback (legacy immediate publish) via workflow_dispatch.
- name: Ensure npm supports staged publishing
if: steps.resolve.outputs.skip != 'true' && (github.event_name != 'workflow_dispatch' || inputs.publish_mode != 'direct')
run: |
set -euo pipefail
CUR=$(npm --version)
if ! node -e "const [a,b]='$(npm --version)'.split('.').map(Number); process.exit(a>11||(a===11&&b>=15)?0:1)"; then
# Pinned exact version (supply-chain: never float @latest in the publish
# job); bump deliberately when a newer npm is required.
echo "npm $CUR < 11.15 — installing pinned npm 11.15.0 for staged publishing"
npm install -g --ignore-scripts npm@11.15.0
fi
npm --version
- name: Publish to npm (staged — owner approves with 2FA)
if: steps.resolve.outputs.skip != 'true' && (github.event_name != 'workflow_dispatch' || inputs.publish_mode != 'direct')
env:
VERSION: ${{ steps.resolve.outputs.version }}
TAG: ${{ steps.resolve.outputs.tag }}
@@ -296,32 +175,10 @@ jobs:
run: |
set -euo pipefail
# Always pass --tag explicitly. Defense in depth: even if VERSION is
# accidentally an older release, the historic tag will NOT claim `@latest`.
npm stage publish --provenance --access public --tag "$TAG"
{
echo "## 📦 omniroute@$VERSION STAGED (not yet installable)"
echo ""
echo "The exact bytes are parked on the registry. To release them:"
echo '```'
echo "npm stage list omniroute # find the stage id"
echo "npm stage approve <id> # owner 2FA — THE publish"
echo '```'
echo "To verify the staged bytes first: npm stage download <id> → run"
echo "scripts/check/check-pack-boot.mjs against them (see RELEASE_CHECKLIST)."
echo "To discard: npm stage reject <id>."
} >> "$GITHUB_STEP_SUMMARY"
echo "✅ Staged omniroute@$VERSION (dist-tag=$TAG) — awaiting owner 'npm stage approve'"
- name: Publish to npm (DIRECT — emergency fallback)
if: steps.resolve.outputs.skip != 'true' && github.event_name == 'workflow_dispatch' && inputs.publish_mode == 'direct'
env:
VERSION: ${{ steps.resolve.outputs.version }}
TAG: ${{ steps.resolve.outputs.tag }}
NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}
run: |
set -euo pipefail
# accidentally an older release, `npm publish --tag historic` will
# NOT promote it to `@latest`.
npm publish --provenance --access public --tag "$TAG"
echo "✅ Published omniroute@$VERSION (dist-tag=$TAG) [DIRECT mode]"
echo "✅ Published omniroute@$VERSION (dist-tag=$TAG)"
- name: Publish to GitHub Packages
if: steps.resolve.outputs.skip != 'true'
@@ -348,56 +205,13 @@ jobs:
uses: actions/checkout@v7
with:
persist-credentials: false
fetch-depth: 0
# Full history needed for auto-bump: git diff against previous release tag
- name: Setup Node.js
uses: actions/setup-node@v7
uses: actions/setup-node@v6
with:
node-version: ${{ env.NPM_PUBLISH_NODE_VERSION }}
registry-url: https://registry.npmjs.org
- name: Auto-bump plugin version if plugin changed since last release
id: bump
working-directory: "@omniroute/opencode-plugin"
env:
CURRENT_TAG: ${{ github.ref_name }}
run: |
set -euo pipefail
PKG_VERSION=$(node -p "require('./package.json').version")
PKG_NAME=$(node -p "require('./package.json').name")
# 1) Skip if current version is not yet published (no bump needed)
PUBLISHED="$(npm view "${PKG_NAME}@${PKG_VERSION}" version 2>/dev/null || true)"
if [ "$PUBLISHED" != "$PKG_VERSION" ]; then
echo "✅ ${PKG_NAME}@${PKG_VERSION} is new — no bump needed."
echo "bumped=false" >> "$GITHUB_OUTPUT"
exit 0
fi
# 2) Find the previous release tag (exclude the current one)
PREV_TAG=$(git tag -l 'v*' --sort=-version:refname \
| grep -v "^${CURRENT_TAG}$" | head -1 || echo "")
if [ -z "$PREV_TAG" ]; then
echo "No previous tag to compare — skipping bump."
echo "bumped=false" >> "$GITHUB_OUTPUT"
exit 0
fi
# 3) Check if plugin dir actually changed since that tag
if git diff --quiet "$PREV_TAG" -- "@omniroute/opencode-plugin/"; then
echo "⏭️ No plugin changes since $PREV_TAG — nothing to publish."
echo "bumped=false" >> "$GITHUB_OUTPUT"
exit 0
fi
# 4) Auto-bump patch version
npm version patch --no-git-tag-version --allow-same-version
NEW_VERSION=$(node -p "require('./package.json').version")
echo "bumped=true" >> "$GITHUB_OUTPUT"
echo "📦 Auto-bumped ${PKG_NAME} from ${PKG_VERSION} to ${NEW_VERSION}"
- name: Install plugin dependencies
working-directory: "@omniroute/opencode-plugin"
run: npm install --no-audit --no-fund

View File

@@ -35,7 +35,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ matrix.node }}
cache: npm
@@ -52,7 +52,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: "22"
cache: npm

View File

@@ -35,7 +35,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ matrix.node }}
cache: npm
@@ -51,7 +51,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: "20"
cache: npm

View File

@@ -14,117 +14,11 @@ permissions:
contents: read
env:
# CI must never mutate the runner's OS trust store (2026-07-05: a cert-flow
# test installed a fake PEM on a persistent self-hosted runner and broke all
# system TLS). Belt-and-suspenders with tests/_setup/isolateDataDir.ts.
OMNIROUTE_SKIP_SYSTEM_TRUST: "1"
CI_NODE_VERSION: "24"
jobs:
# Same classifier as ci.yml (scripts/quality/classify-pr-changes.mjs) so PR→release
# path filters share existence reasons: code / docs / i18n / workflow.
changes:
name: Change Classification
runs-on: ubuntu-latest
outputs:
code: ${{ steps.classify.outputs.code }}
docs: ${{ steps.classify.outputs.docs }}
i18n: ${{ steps.classify.outputs.i18n }}
workflow: ${{ steps.classify.outputs.workflow }}
steps:
- uses: actions/checkout@v7
with:
persist-credentials: false
fetch-depth: 0
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
- id: classify
env:
EVENT_NAME: ${{ github.event_name }}
BASE_SHA: ${{ github.event.pull_request.base.sha }}
HEAD_SHA: ${{ github.event.pull_request.head.sha }}
run: |
if [ "$EVENT_NAME" != "pull_request" ]; then
{
echo "code=true"
echo "docs=true"
echo "i18n=true"
echo "workflow=true"
} >> "$GITHUB_OUTPUT"
exit 0
fi
git diff --name-only "$BASE_SHA" "$HEAD_SHA" > changed-files.txt
node scripts/quality/classify-pr-changes.mjs changed-files.txt >> "$GITHUB_OUTPUT"
build:
name: Build (advisory)
needs: changes
if: ${{ github.event_name != 'pull_request' || ((github.event.pull_request.draft == false || startsWith(github.head_ref, 'mergify/merge-queue/')) && needs.changes.outputs.code == 'true') }}
# Dynamic runner — same fork-safe rule as ci.yml / fast-gates.
runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && (github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository)) && fromJSON('["self-hosted","omni-release"]') || 'ubuntu-latest' }}
# #7307: advisory for the first week of release-PR runs; remove
# continue-on-error after the production-build signal is stable.
continue-on-error: true
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
with:
persist-credentials: false
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- uses: ./.github/actions/npm-ci-retry
- run: npm run check:node-runtime
- run: npm run build
env:
OMNIROUTE_USE_TURBOPACK: "1"
# No artifact upload here: the PR-to-release quality workflow has no
# downstream package/e2e jobs that consume the Next.js build output.
# Docs/OpenAPI contract gates only — existence reason is doc accuracy + route refs.
# Split out of fast-gates so pure-docs PRs skip typecheck/unit while still validating docs.
docs-gates:
name: Docs Gates (fast-path)
needs: changes
if: ${{ github.event_name != 'pull_request' || ((github.event.pull_request.draft == false || startsWith(github.head_ref, 'mergify/merge-queue/')) && (needs.changes.outputs.docs == 'true' || needs.changes.outputs.code == 'true')) }}
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- run: npm ci
# One walk of src/app/api for openapi-routes + docs-symbols (both still fail independently).
- run: npm run check:api-docs-refs
- name: Docs accuracy (fabricated-docs + i18n mirrors, strict)
run: npm run check:docs-all
fast-gates:
name: Fast Quality Gates
needs: changes
# Code surface only — pure docs/i18n PRs skip this bag (docs-gates covers docs).
if: ${{ github.event_name != 'pull_request' || ((github.event.pull_request.draft == false || startsWith(github.head_ref, 'mergify/merge-queue/')) && needs.changes.outputs.code == 'true') }}
# Dynamic runner (same rule as ci.yml): use the self-hosted VPS pool only when the
# release captain has USE_VPS_RUNNER=true AND this is not a fork PR (own-origin
# branches only — a fork PR must never execute on the LAN runner). Var unset/false
# or a fork PR falls back to ubuntu-latest, so this is inert until the flag flips.
# PINNED to hosted (gap 19). This job carried the USE_VPS_RUNNER expression, and that
# expression was DEAD CONFIGURATION: across 160 quality.yml runs the job never once landed on
# a self-hosted runner — every non-skipped sample is `GitHub Actions NNNN`. The classifier is
# not at fault: in the same window ci.yml's Build demonstrably ran on omniroute-113-7 and
# omniroute-113-6, so self-hosted runs are visible when they happen.
#
# And if it ever HAD fired it would have inherited the measured penalty, because this job's
# first two steps are exactly the bottleneck: actions/setup-node + npm ci took 20m06s on .113
# with 4 concurrent runners versus 16s hosted (npm cache restore saturating the link). Median
# here is 5.6 min hosted across 72 successful runs.
#
# With this pinned, USE_VPS_RUNNER governs ONLY build-like jobs — one variable, one coherent
# purpose. That is what gap 19 asked for; a second variable turned out to be unnecessary.
runs-on: ubuntu-latest
# tsx gates (known-symbols, route-guard-membership) import modules that open
# SQLite on load; provide DB env so a fresh CI DB initializes cleanly.
@@ -137,246 +31,63 @@ jobs:
with:
fetch-depth: 0
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- run: npm ci
- name: Restore ESLint file cache
uses: actions/cache@v6
with:
path: |
.eslintcache
.eslintcache-complexity
key: eslint-${{ runner.os }}-${{ hashFiles('eslint.config.mjs', 'eslint.complexity-ratchets.config.mjs', 'config/quality/eslint-suppressions.json', 'package-lock.json') }}
restore-keys: |
eslint-${{ runner.os }}-
# Security scanners — same hardened install as ci.yml quality-extended
# (gh release download = authenticated, 5000 req/hr; curl to api.github.com
# is rate-limited to 60/hr and silently no-ops when throttled). The blocking
# gates below SKIP (exit 0) when their binary is absent — only a measured
# regression vs config/quality/quality-baseline.json blocks.
- name: Install security scanners (gitleaks/osv/actionlint/zizmor/oasdiff)
continue-on-error: true
env:
GH_TOKEN: ${{ github.token }}
run: |
set +e
mkdir -p "$HOME/.local/bin"
# Ratchets compare scanner COUNTS across runs. Pin every auditor: a rule-set
# update must be an explicit PR that re-measures/rebaselines, never a random
# red (or green) caused by whatever "latest" served that morning.
GITLEAKS_VERSION=v8.30.1
OSV_SCANNER_VERSION=v2.3.8
ACTIONLINT_VERSION=v1.7.12
ZIZMOR_VERSION=1.25.2
OASDIFF_VERSION=v1.19.1
# gitleaks — pinned linux x64 tarball via gh (authed), extract binary
rm -rf /tmp/gl && mkdir -p /tmp/gl
gh release download "$GITLEAKS_VERSION" --repo gitleaks/gitleaks --pattern '*linux_x64.tar.gz' --dir /tmp/gl
tar -xzf /tmp/gl/*linux_x64.tar.gz -C "$HOME/.local/bin" gitleaks
# osv-scanner — pinned linux amd64 bare binary via gh (authed)
rm -rf /tmp/osv && mkdir -p /tmp/osv
gh release download "$OSV_SCANNER_VERSION" --repo google/osv-scanner --pattern '*linux_amd64' --dir /tmp/osv
install -m 0755 /tmp/osv/*linux_amd64 "$HOME/.local/bin/osv-scanner"
# actionlint — official installer from a pinned release tag (never main)
bash <(curl -fsSL "https://raw.githubusercontent.com/rhysd/actionlint/${ACTIONLINT_VERSION}/scripts/download-actionlint.bash") "$ACTIONLINT_VERSION" "$HOME/.local/bin"
# zizmor — pinned PyPI package (same version as ci.yml quality-extended)
pipx install "zizmor==$ZIZMOR_VERSION" || pip install --user "zizmor==$ZIZMOR_VERSION"
# oasdiff — pinned linux amd64 tarball via gh (authed), extract binary
rm -rf /tmp/oasd && mkdir -p /tmp/oasd
gh release download "$OASDIFF_VERSION" --repo Tufin/oasdiff --pattern '*linux_amd64.tar.gz' --dir /tmp/oasd
tar -xzf /tmp/oasd/*linux_amd64.tar.gz -C "$HOME/.local/bin" oasdiff
# ALWAYS export the bin dir (even if any step above failed)
echo "$HOME/.local/bin" >> "$GITHUB_PATH"
"$HOME/.local/bin/gitleaks" version || true
"$HOME/.local/bin/actionlint" -version || true
"$HOME/.local/bin/osv-scanner" --version || true
"$HOME/.local/bin/oasdiff" --version || true
zizmor --version || true
- name: Forgotten sibling tests (advisory)
env:
GITHUB_BASE_SHA: ${{ github.event.pull_request.base.sha }}
run: |
node scripts/quality/build-test-impact-map.mjs
node scripts/check/check-forgotten-sibling-tests.mjs \
--summary-file forgotten-sibling-tests.md \
--json-file forgotten-sibling-tests.json
cat forgotten-sibling-tests.md >> "$GITHUB_STEP_SUMMARY"
- name: Upload forgotten sibling report
if: always()
uses: actions/upload-artifact@v7
with:
name: forgotten-sibling-tests
path: |
forgotten-sibling-tests.md
forgotten-sibling-tests.json
if-no-files-found: ignore
retention-days: 30
# Quality gates (all, non-fail-fast) — #8542: replaces 17 bare check:* steps,
# 6 G0 gates, 4 ratchet gates, and 3 typecheck steps with a single aggregation
# step. Each gate runs in a loop with ::group::; failures are collected and
# reported at the end. set -uo pipefail (NOT set -e) so one failing gate does
# not abort the job and mask every later gate. Release-added gates are folded
# in: open-sse typecheck (#8781) and file-size base-relative mode (#8522).
- name: Quality gates (all, non-fail-fast)
env:
# #8522: base-relative file-size mode on PR events — inherited drift (base
# already over frozen cap) must not red an innocent PR. Unset on
# workflow_dispatch (no PR base) → absolute comparison.
PR_BASE_SHA: ${{ github.event.pull_request.base.sha }}
BASE_REF: ${{ github.base_ref && format('origin/{0}', github.base_ref) || '' }}
run: |
set -uo pipefail
gates=(
provider-consistency fetch-targets deps file-size error-helper
migration-numbering public-creds db-rules known-symbols
route-guard-membership test-discovery test-runner-api
mutation-test-coverage any-budget:t11 build-scope pack-policy
complexity-ratchets
cycles lockfile duplication dead-code type-coverage compression-budget
# #8781: open-sse workspace typecheck gate — the workspace imports @/ which
# escapes to src/ via undeclared path aliases. See check-open-sse-typecheck.mjs.
open-sse-typecheck
)
ratchet_gates=(
secrets vuln-ratchet workflows openapi-breaking
)
failed=()
for g in "${gates[@]}"; do
echo "::group::check:$g"
# #8522: file-size is base-relative on PR events (compare against
# max(frozen, base)) so inherited drift doesn't red an innocent PR;
# workflow_dispatch (no PR base) falls back to absolute comparison.
if [ "$g" = "file-size" ] && [ -n "${PR_BASE_SHA:-}" ]; then
npm run "check:$g" -- --base-ref "$PR_BASE_SHA" || failed+=("$g")
else
npm run "check:$g" || failed+=("$g")
fi
echo "::endgroup::"
done
for g in "${ratchet_gates[@]}"; do
echo "::group::check:$g (ratchet)"
npm run "check:$g" -- --ratchet || failed+=("$g")
echo "::endgroup::"
done
echo "::group::typecheck:core"
npm run typecheck:core || failed+=("typecheck:core")
echo "::endgroup::"
echo "::group::check:dashboard-typecheck"
npm run check:dashboard-typecheck || failed+=("check:dashboard-typecheck")
echo "::endgroup::"
# #10134: TS7 zero-new-diagnostics ratchet — folded into this non-fail-fast
# loop (never a separate blocking step) so an earlier red gate cannot abort
# the job and mask it (#8542 mechanism). PR-only: the base-relative
# comparison needs the PR base SHA (empty on workflow_dispatch).
if [ -n "${PR_BASE_SHA:-}" ]; then
echo "::group::check:ts7-diagnostics-ratchet"
npm run check:ts7-diagnostics-ratchet -- --base-ref "$PR_BASE_SHA" || failed+=("ts7-diagnostics-ratchet")
echo "::endgroup::"
fi
if (( ${#failed[@]} )); then
printf '::error::%d gate(s) failed: %s\n' "${#failed[@]}" "${failed[*]}"
exit 1
fi
# WS4.2 (v3.8.49 plan): TypeScript 7 native-compiler SHADOW — advisory only.
# TS7 went GA 2026-07-08 with 8-12x type-check speedups; its Compiler API only
# arrives in 7.1, so typescript-eslint / type-coverage / Stryker stay on 6.x
# (the hybrid is the officially documented pattern). Isolated npx on purpose:
# installing an alias package could collide node_modules/.bin/tsc with 6.x.
# The full result stays advisory while #8484 has a backlog. The blocking
# base-relative ratchet (folded into the non-fail-fast gates step above)
# rejects only diagnostics added by the PR, so existing release debt does
# not block unrelated work.
- name: Typecheck (core) — TS7 native shadow (advisory)
continue-on-error: true
run: |
RC=0
START=$(date +%s)
npm exec --yes --package=typescript@7.0.2 -- tsc --pretty false -p tsconfig.typecheck-core.json || RC=$?
echo "[ts7-shadow] exit=$RC elapsed=$(( $(date +%s) - START ))s — the 6.x step above stays authoritative"
exit $RC
- run: npm run check:provider-consistency
- run: npm run check:fetch-targets
- run: npm run check:openapi-routes
- run: npm run check:docs-symbols
- name: Docs accuracy (fabricated-docs + i18n mirrors, strict)
run: npm run check:docs-all
- run: npm run check:deps
- run: npm run check:file-size
- run: npm run check:error-helper
- run: npm run check:migration-numbering
- run: npm run check:public-creds
- run: npm run check:db-rules
- run: npm run check:known-symbols
- run: npm run check:route-guard-membership
- run: npm run check:test-discovery
- run: npm run check:test-runner-api
- run: npm run check:any-budget:t11
- name: Typecheck (core)
run: npm run typecheck:core
# TIA: build the impact map at runtime (gitignored, ~21MB) and run only the
# unit tests impacted by this PR's changed files. On hub/unmapped changes the
# selector returns __RUN_ALL__ — full-suite authority is the parallel
# `fast-unit` 4-shard job (test:unit:ci:shard; was 2-shard, #6781), NOT an
# unsharded re-run here. Stacking unsharded test:unit:ci on top of fast-unit
# doubled wall time (~16 min extra on ubuntu-latest) without extra coverage.
# unit tests impacted by this PR's changed files. Fail-safe runs the FULL
# unit suite on hub/unmapped changes — TIA accelerates, never replaces, the net.
#
# BLOCKING for the *impacted subset* (flipped 2026-06-17). Fail-safe full
# coverage remains required via `Unit Tests fast-path` (fast-unit).
- name: Impacted unit tests (TIA subset; blocking)
# BLOCKING (flipped 2026-06-17). The pre-existing release unit test-debt that kept
# this advisory was cleared: #4030 (16 Zod/registry reds, lossless restore) and
# #4063 (the last red — the LiveWS boot test — root-caused as a real event-loop
# stall in the WS sidecar, fixed + relocated to the integration suite). A full
# ci.yml run on release/v3.8.28 then showed all 8 unit shards green, so PR->release
# now blocks on unit-test regressions in the impacted set (typecheck:core already
# blocked above). Fail-safe still runs the FULL unit suite on hub/unmapped changes.
- name: Impacted unit tests (TIA, fail-safe full; blocking)
env:
GITHUB_BASE_REF: ${{ github.base_ref }}
run: |
git fetch --no-tags origin "$GITHUB_BASE_REF" || true
# The advisory sibling-test step generates the same map earlier in this job.
[ -f config/quality/test-impact-map.json ] || node scripts/quality/build-test-impact-map.mjs
node scripts/quality/build-test-impact-map.mjs
SEL="$(node scripts/quality/select-impacted-tests.mjs)"
# Shadow evidence (#8084): persist every selection so TIA false negatives can
# be measured against fast-unit's full-suite verdict across releases BEFORE
# any gate authority moves off ordinary PRs. Artifact uploaded below.
printf '%s\n' "$SEL" > tia-selection.txt
if [ -z "$SEL" ]; then
echo "TIA selection: empty (no source/test changes)" >> "$GITHUB_STEP_SUMMARY"
echo "No source/test changes — skipping unit tests"; exit 0
fi
if [ -z "$SEL" ]; then echo "No source/test changes — skipping unit tests"; exit 0; fi
# CI runners are 4-vCPU; run at --test-concurrency=4 (matching the ci.yml unit
# job) rather than test:unit's local-tuned concurrency=20. Oversubscribing the
# runner makes timing-sensitive tests (db-backup, upstream-timeout, ...) flake,
# which must not happen on a blocking gate. DATA_DIR isolation keeps the parallel
# run race-free regardless of concurrency.
if echo "$SEL" | grep -q "__RUN_ALL__"; then
echo "TIA selection: __RUN_ALL__ (fail-safe) — full-suite authority stays with fast-unit" >> "$GITHUB_STEP_SUMMARY"
echo "Fail-safe: __RUN_ALL__ — deferring FULL unit suite to fast-unit (4-shard)."
echo "Not re-running unsharded test:unit:ci here (duplicate of fast-unit coverage)."
exit 0
echo "Fail-safe: running FULL unit suite (CI concurrency)"; npm run test:unit:ci; exit $?
fi
echo "TIA selection: $(grep -c . tia-selection.txt) impacted test file(s) — full suite still runs in fast-unit (shadow-evidence phase, #8084)" >> "$GITHUB_STEP_SUMMARY"
echo "Running impacted tests:"; echo "$SEL"
mapfile -t FILES <<< "$SEL"
# Loader parity with test:unit:ci:shard (#6787): tests/unit/dashboard/** runs
# under `--import tsx` (CJS transform — required for ESM-only deep imports like
# @lobehub/icons/es/* reached via lobeProviderIcons.ts); everything else under
# `--import tsx/esm`. A single tsx/esm invocation false-reds every dashboard
# module-shape test the impact map selects ("Unexpected token 'export'").
DASH=(); REST=()
for f in "${FILES[@]}"; do
case "$f" in
tests/unit/dashboard/*) DASH+=("$f") ;;
*) REST+=("$f") ;;
esac
done
RC=0
if [ ${#REST[@]} -gt 0 ]; then
node --import tsx/esm --import ./open-sse/utils/setupPolyfill.ts --import ./tests/_setup/isolateDataDir.ts --test --test-force-exit --test-concurrency=4 "${REST[@]}" || RC=$?
fi
if [ ${#DASH[@]} -gt 0 ]; then
node --import tsx --import ./open-sse/utils/setupPolyfill.ts --import ./tests/_setup/isolateDataDir.ts --test --test-force-exit --test-concurrency=4 "${DASH[@]}" || RC=$?
fi
exit $RC
# #8084 shadow evidence: keep the raw selection downloadable so TIA misses can be
# audited against fast-unit failures on the same run (gate moves need this data).
- name: Upload TIA selection (shadow evidence)
if: always()
uses: actions/upload-artifact@v7
with:
name: tia-selection
path: tia-selection.txt
if-no-files-found: ignore
retention-days: 30
node --import tsx --import ./open-sse/utils/setupPolyfill.ts --import ./tests/_setup/isolateDataDir.ts --test --test-force-exit --test-concurrency=4 "${FILES[@]}"
fast-vitest:
name: Vitest (fast-path)
needs: changes
if: ${{ github.event_name != 'pull_request' || ((github.event.pull_request.draft == false || startsWith(github.head_ref, 'mergify/merge-queue/')) && needs.changes.outputs.code == 'true') }}
# Dynamic runner — see fast-gates (own-origin + flag; fork/unset → ubuntu-latest).
# PINNED to hosted, deliberately not on the USE_VPS_RUNNER switch (gap 19). One variable
# governed the build and the test jobs, which want OPPOSITE machines: the build needs the
# .113's RAM, the tests need the hosted runner's link. Measured on 2026-07-29 —
# actions/setup-node took 20m06s on .113 with 4 concurrent runners versus 16s hosted (npm
# cache restore saturating the link), while the tests themselves tied, 2m54 vs 2m31. So
# self-hosted is strictly worse here and there is nothing to configure.
runs-on: ubuntu-latest
env:
JWT_SECRET: ci-lint-secret-with-sufficient-length-for-validation
@@ -386,44 +97,20 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- run: npm ci
# WS5.2/5.3: JUnit feeds Trunk Flaky Tests — the fast-path runs on EVERY PR,
# which is where flaky-detection volume actually comes from (ci.yml's heavy
# jobs only run on the release PR). Advisory upload, own-origin only.
- run: npm run test:vitest -- --reporter=default --reporter=junit --outputFile.junit=trunk-junit/vitest-fastpath.xml
- name: Upload test results to Trunk (advisory)
if: ${{ always() && (github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository) }}
continue-on-error: true
uses: trunk-io/analytics-uploader@385f1ccdf345b4532dc4b6c665dd432b702b8e28 # v2.1.2
with:
junit-paths: trunk-junit/**/*.xml
org-slug: omniroute
token: ${{ secrets.TRUNK_TOKEN }}
- run: npm run test:vitest
fast-unit:
name: Unit Tests fast-path (${{ matrix.shard }}/4)
needs: changes
if: ${{ github.event_name != 'pull_request' || ((github.event.pull_request.draft == false || startsWith(github.head_ref, 'mergify/merge-queue/')) && needs.changes.outputs.code == 'true') }}
# Dynamic runner — see fast-gates (own-origin + flag; fork/unset → ubuntu-latest).
# This is the heaviest fast-path job; 4-way sharding (was 2, #6781) halves the
# critical path again (~8.5min → ~4.5min on ubuntu-latest; ~2min on the 8-slot
# runner box). Node's native --test-shard=N/total takes any denominator — only
# this matrix and the TEST_SHARD env below encode the shard count.
# PINNED to hosted, deliberately not on the USE_VPS_RUNNER switch (gap 19). One variable
# governed the build and the test jobs, which want OPPOSITE machines: the build needs the
# .113's RAM, the tests need the hosted runner's link. Measured on 2026-07-29 —
# actions/setup-node took 20m06s on .113 with 4 concurrent runners versus 16s hosted (npm
# cache restore saturating the link), while the tests themselves tied, 2m54 vs 2m31. So
# self-hosted is strictly worse here and there is nothing to configure.
name: Unit Tests fast-path (${{ matrix.shard }}/2)
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
shard: [1, 2, 3, 4]
shard: [1, 2]
env:
JWT_SECRET: ci-lint-secret-with-sufficient-length-for-validation
API_KEY_SECRET: ci-lint-api-key-secret-long
@@ -432,119 +119,14 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- run: npm ci
# QW-d: fonte única — o mesmo npm script do CI pesado/local. Fecha dois drifts do
# comando inline antigo: os dirs `memory` e `usage` estavam FORA do glob (testes
# silenciosamente não rodavam no fast path) e o setupPolyfill não era importado.
- run: npm run test:unit:ci:shard
env:
TEST_SHARD: ${{ matrix.shard }}/4
# ── Pacote 4 (plano mestre testes+CI, aprovado 2026-07-04) ─────────────────────────
# No-new-warnings por PR via ESLint bulk suppressions nativo (>=9.24). O baseline
# config/quality/eslint-suppressions.json congela as violações EXISTENTES por
# arquivo+regra; qualquer warning NOVO aparece e o --max-warnings 0 falha o job — o
# drift de +41/+88 warnings por ciclo passa a morrer no PR que o introduz, em vez de
# ser rebaselinado às cegas na release. Aperto do baseline (na reconciliação da
# release): npx eslint . --prune-suppressions --suppressions-location config/quality/eslint-suppressions.json
#
# Princípio Zero: bloqueante SÓ para branches internas (as campanhas/sessões são a
# origem do drift). PR de FORK roda em modo report (continue-on-error → o job fica
# verde com anotação; a campanha /green-prs aplica o fix via co-autoria — o
# contribuidor NUNCA é bloqueado nem cobrado).
lint-guard:
name: No new ESLint warnings
needs: changes
if: ${{ github.event_name != 'pull_request' || ((github.event.pull_request.draft == false || startsWith(github.head_ref, 'mergify/merge-queue/')) && needs.changes.outputs.code == 'true') }}
runs-on: ubuntu-latest
continue-on-error: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.repo.fork == true }}
# G0 (trilho .50): security-events:read lets the CodeQL ratchet below read open
# code-scanning alerts via `gh api .../code-scanning/alerts` (same as ci.yml's
# quality-gate job). contents: read keeps checkout working.
permissions:
contents: read
security-events: read
steps:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- run: npm ci
- name: Restore ESLint file cache
uses: actions/cache@v6
with:
path: |
.eslintcache
.eslintcache-complexity
key: eslint-${{ runner.os }}-${{ hashFiles('eslint.config.mjs', 'eslint.complexity-ratchets.config.mjs', 'config/quality/eslint-suppressions.json', 'package-lock.json') }}
restore-keys: |
eslint-${{ runner.os }}-
- name: ESLint (baseline congelado — warning novo = vermelho)
# lint:json writes the report; --max-warnings 0 keeps no-new-warnings policy.
run: npm run lint:json -- --max-warnings 0
# ── G0 (trilho .50): motor de ratchet também no trilho B ─────────────────────
# This job just wrote .artifacts/eslint-results.json — collect-metrics prefers
# that file, so the ratchet engine lands here at ZERO extra ESLint cost (one
# inventory, two consumers; same reason ci.yml chains lint → quality-gate).
# The coverage-report artifact does not exist on this rail, so both ratchet
# invocations run --allow-missing: coverage.* metrics skip gracefully while
# the deterministic ones (eslint / openapi-coverage / i18n-ui) stay BLOCKING.
# Coverage authority remains on the main rail (ci.yml test-coverage → quality-gate).
- run: npm run quality:collect
- name: Ratchet check (blocking)
run: node scripts/quality/check-quality-ratchet.mjs --allow-missing --summary .artifacts/quality-ratchet.md
- name: Require-tighten (blocking)
run: node scripts/quality/check-quality-ratchet.mjs --allow-missing --require-tighten
# CodeQL alerts ratchet — same semantics as ci.yml quality-gate: exits 1 ONLY
# on a real regression (open alerts > baseline in quality-baseline.json);
# a measurement failure (gh/auth/api) self-skips with exit 0.
- name: CodeQL alerts ratchet (blocking)
run: npm run check:codeql-ratchet
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Append ratchet summary
if: always()
run: cat .artifacts/quality-ratchet.md >> "$GITHUB_STEP_SUMMARY" || true
# Merge-integrity: pega no PR os dois vazamentos crônicos de merge que hoje só
# explodem na release-PR. (1) CHANGELOG-eat — o auto-resolve do merge come
# bullets vizinhos/seções inteiras (incidente #6193, 2026-07-05: 212 linhas /
# 130 bullets); o checkout de PR é refs/pull/N/merge, então comparar contra a
# base detecta o eat ANTES do merge. (2) SKILL.md gerado stale vs o catálogo de
# agent-skills (#6186 mergeou um id de catálogo sem rodar o gerador → 8 reds de
# integration invisíveis até a release).
#
# Princípio Zero: bloqueante SÓ para branches internas; PR de FORK roda em modo
# report (continue-on-error) — a campanha corrige via co-autoria, o contribuidor
# nunca é bloqueado.
merge-integrity:
name: Merge integrity (changelog + generated skills)
# Always on non-draft PRs — CHANGELOG/skills can break on docs-only merges too.
if: ${{ github.event_name != 'pull_request' || (github.event.pull_request.draft == false || startsWith(github.head_ref, 'mergify/merge-queue/')) }}
runs-on: ubuntu-latest
continue-on-error: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.repo.fork == true }}
env:
JWT_SECRET: ci-lint-secret-with-sufficient-length-for-validation
API_KEY_SECRET: ci-lint-api-key-secret-long
DISABLE_SQLITE_AUTO_BACKUP: "true"
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
with:
fetch-depth: 0
persist-credentials: false
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- run: npm ci
- name: CHANGELOG integrity (nenhum bullet da base pode sumir no merge-result)
run: npm run check:changelog-integrity
- name: Agent-skills generator sync (SKILL.md gerado ≡ catálogo)
run: npm run check:agent-skills-sync
- run: >
node --max-old-space-size=4096 --import tsx
--import ./tests/_setup/isolateDataDir.ts
--test --test-force-exit --test-concurrency=4 --test-shard=${{ matrix.shard }}/2
tests/unit/*.test.ts
"tests/unit/{api,auth,authz,build,cli,cli-helper,combo,compression,correctness,cors,dashboard,db,db-adapters,docs,gamification,guardrails,lib,mcp,runtime,security,services,settings,shared,ui}/**/*.test.ts"

View File

@@ -26,7 +26,7 @@ jobs:
persist-credentials: false
- name: Run analysis
uses: ossf/scorecard-action@v2.4.4
uses: ossf/scorecard-action@v2.4.3
with:
results_file: results.sarif
results_format: sarif

View File

@@ -6,19 +6,13 @@ on:
branches: ["main"]
permissions:
contents: read
# Cancel superseded PR runs (same rule as quality.yml). No paths filter on purpose:
# p/secrets must keep scanning docs-only diffs too — credentials leak in .md files.
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
jobs:
semgrep:
runs-on: ubuntu-latest
container:
image: semgrep/semgrep
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
persist-credentials: false
- name: Run semgrep (advisory)

View File

@@ -9,7 +9,7 @@ name: Wiki Sync
# It does NOT overwrite existing wiki pages by default: several docs sources still carry
# stale counts (e.g. ARCHITECTURE.md says "177 providers" while the wiki cover is 226),
# so blind overwrite would regress the wiki. Full content parity (--update-existing) is
# gated on regenerating those sources first.
# gated on regenerating those sources — see docs/ops/DOCUMENTATION_AUDIT_REPORT.md.
on:
push:
@@ -40,7 +40,7 @@ jobs:
uses: actions/checkout@v7
- name: Setup Node
uses: actions/setup-node@v7
uses: actions/setup-node@v6
with:
node-version: "24"

76
.gitignore vendored
View File

@@ -1,7 +1,6 @@
# See https://help.github.com/articles/ignoring-files/ for more about ignoring files.
# project-specific directories
.slim/deepwork/
.omnivscodeagent/
omnirouteCloud/
omnirouteSite/
@@ -18,7 +17,7 @@ _tasks/
.logs/**
.tests/**
.coverage/**
/coverage/
coverage/
.dist/**
.next/**
.build/**
@@ -44,7 +43,6 @@ memory-bank/
# Root-level underscore-prefixed directories (private/draft — never commit)
/_*/
/_*
# Draft features documentation (internal only)
docs/new-features/
@@ -58,6 +56,10 @@ node_modules/
*.map
.DS_Store
# Obsidian sync plugin — committed for community distribution
!obsidian-plugin/
obsidian-plugin/node_modules/
# Serena AI assistant config (local-only tool, not project code)
.serena/
@@ -70,8 +72,6 @@ yarn-error.log*
# env files (can opt-in for committing if needed)
.env*
!.env.example
!.env.homolog.example
!.env.devin-bridge.example
# Provider API keys (never commit)
*.api-key
.nvidia-api-key
@@ -84,7 +84,7 @@ yarn-error.log*
next-env.d.ts
# data and logs
/data/
data/
.data/
logs/*
test_output.log
@@ -106,7 +106,7 @@ open-sse/test/*
test-results/
playwright-report/
blob-report/
/cloud/
cloud/
.tmp/
# Security Analysis (standalone project with own git)
@@ -120,8 +120,6 @@ app.log
deploy.sh
docker-compose.minimal.yml
# Docker Compose override (local-only, never commit)
docker-compose.override.yml
# Backup directories
app.__qa_backup/
@@ -157,15 +155,12 @@ vscode-extension/
# Empty/dangling files
typescript
/MAX
# Gemini Antigravity agent data
.gemini/
# Superpowers plans/specs (internal tooling, not project code)
docs/superpowers/
# Superpowers visual-companion brainstorm mockups (ephemeral)
.superpowers/
# TIA test-impact map — generated at runtime in CI (build-test-impact-map.mjs), never committed (~21MB)
config/quality/test-impact-map.json
@@ -173,6 +168,7 @@ config/quality/test-impact-map.json
# GitNexus local index
.gitnexus
.worktrees
bin/omniroute.mjs
# Consistent with .dockerignore / .npmignore
.omc/
@@ -201,16 +197,13 @@ scripts/i18n/_pending-keys.json
.claude/worktrees/
.codegraph/
# Test executable shims belong in the OS temporary directory, not the repository root
/.fakebin-*/
# Fumadocs generated source
.source/
# AI agent local settings and configs
.agents/
.antigravitycli/
/.claude/
.claude/
# PR Reviews and local feedback files
pr_reviews*.json
@@ -225,26 +218,6 @@ CODEX-SETUP-PROMPT.md
# Quality ratchet — métricas efêmeras (baseline commitado em config/quality/; métricas não)
config/quality/quality-metrics.json
# Electron desktop build output unpacked into the repo root.
# `electron-builder` (squirrel-windows target) unpacks the packaged app — the
# entire Chromium runtime, ~24k files — directly into the repository root.
# Every rule below is ROOT-ANCHORED (leading `/`) on purpose: a bare `locales/`
# or `resources/` would also swallow tracked sources such as the CLI
# translations in `bin/cli/locales/*.json`.
/OmniRoute.exe
/Uninstall OmniRoute.exe
/uninstallerIcon.ico
/locales/
/resources/
/*.pak
/*.dll
/icudtl.dat
/snapshot_blob.bin
/v8_context_snapshot.bin
/vk_swiftshader_icd.json
/LICENSE.electron.txt
/LICENSES.chromium.html
# Runtime logs (diretório local, nunca versionado)
/logs/
-home-diegosouzapw-dev-automações-bots-yt-downloader-20260504 .txt
@@ -254,34 +227,3 @@ docs/prompts/AGENT-OWNERSHIP-PROTOCOL.md
docs/prompts/AGENT-OWNERSHIP-PROTOCOL.omniroute-mim.md
docs/prompts/AGENT-OWNERSHIP-PROTOCOL.omniroute-mid.md
omniroute.md
# mise configuration
mise.toml
_artifacts/ # release-green artifacts
.claude-flow/
# ESLint file cache (npm run lint --cache / complexity ratchets)
.eslintcache
.eslintcache-complexity
/.eslintcache-*
# CI/local quality artifacts (eslint-results.json, quality-ratchet.md, etc.)
.artifacts/
/perf-audit*.md
/quality-ratchet/
# Homologation E2E suite (npm run homolog) — real-environment credentials + report output
.env.homolog
tests/homolog/.auth/
tests/homolog/ui/.auth/
homolog-report/
docker-compose.yml.bak
# _tasks e um repo git SEPARADO (ver AGENTS.md). A linha _tasks/ (com barra) NAO
# ignora um SYMLINK chamado _tasks; /_tasks (ancorado) cobre arquivo/symlink/dir na raiz
# e impede que um git add -A recapture o symlink (incidente 2026-08-08).
/_tasks
# CLI local cache/state
.playwright-cli

View File

@@ -74,23 +74,3 @@
# '''tests/unit/''',
# ]
#
[[rules]]
# Falsos-positivos comprovados do generic-api-key — zerados em 2026-07-13 (WS6/D3,
# plano v3.8.49). Revisar em v3.9.0. Nenhum é credencial: dois são NOMES DE CAMPO
# de métricas de latência; o terceiro é o valor PÚBLICO de um beta header da API
# da Anthropic (documentado publicamente, não é segredo).
id = "generic-api-key"
[rules.allowlist]
description = "Field names + public Anthropic beta-header value (não são segredos)"
regexes = [
'''latencyP\d{2}Ms''',
'''interleaved-thinking-2025-05-14''',
# v3.8.49 pre-flight (2026-07-28). Nenhum dos dois e credencial:
# - chave de localStorage do banner de patrocinio (#8723; #10200 bumpou v1->v2,
# generalizado para -v\d+ no round 3 de base-reds #9985), so um identificador de UI;
# - x-api-key PUBLICO do Firefly web (documentado em open-sse/utils/publicCreds.ts:207);
# as duas ocorrencias sinalizadas estao em COMENTARIOS JSDoc, o runtime le de resolvePublicCred().
'''omniroute-kimi-sponsor-banner-dismissed-v\d+''',
'''SunbreakWebUI1''',
]

View File

@@ -1,9 +1,7 @@
#!/usr/bin/env sh
# .husky/pre-push — intentionally light.
# any-budget + tracked-artifacts already run on pre-commit; re-running them on
# every push only doubles local wall time for the same existence reason (CI still
# enforces both). Keep this hook as a PATH/npm sanity check + reminder.
# Intentionally excludes test:unit / typecheck (slow; covered by CI).
# .husky/pre-push — fast deterministic gates (<10s total)
# Intentionally excludes test:unit (slow; covered by CI pre-push remote run).
# Activated: 2026-06-13 (6A.12 — replaced commented-out test:unit stub)
if ! command -v npm >/dev/null 2>&1; then
echo "⚠️ npm not found in PATH — skipping pre-push hooks"
@@ -11,5 +9,4 @@ if ! command -v npm >/dev/null 2>&1; then
exit 0
fi
# No-op success: real local gates live in pre-commit; CI owns the rest.
exit 0
npm run check:any-budget:t11 && npm run check:tracked-artifacts

17
.mcp.json.example Normal file
View File

@@ -0,0 +1,17 @@
{
"$comment_purpose": "OPT-IN agent-lsp / LSP-in-the-loop (Quality Gates Fase 7 Task 15). Copy this file to `.mcp.json` to enable. It exposes a TypeScript language server to coding agents (Claude Code, etc.) so they get diagnostics / hover / go-to-definition / blast-radius BEFORE writing code — turning 'invented symbol' review-catches into impossible-at-edit-time. Pairs with `npm run typecheck:core` as a compile-before-claim check.",
"$comment_safety": "Shipped as `.example` (NOT `.mcp.json`) on purpose so it never auto-loads an unvetted server into everyone's session. Pick an MCP<->LSP bridge you trust and have verified locally, then drop in its package + args below. A broken MCP entry only logs a connection error; it does not break agent sessions. The underlying language server is `typescript-language-server` (npm, mature) — install via `npm i -g typescript-language-server typescript` or rely on npx.",
"mcpServers": {
"typescript-lsp": {
"command": "npx",
"args": [
"-y",
"<your-mcp-lsp-bridge>",
"--lsp",
"typescript-language-server",
"--stdio"
],
"$note": "Replace <your-mcp-lsp-bridge> with the concrete MCP<->LSP adapter you chose. It must speak MCP on stdio and proxy to `typescript-language-server --stdio`. Scope it to this repo's tsconfig (open-sse/tsconfig.json / tsconfig.json) for accurate diagnostics."
}
}
}

View File

@@ -1,74 +0,0 @@
# Mergify merge queue — WS3.4/D5 of the v3.8.49 quality/velocity master plan.
#
# WHY: ~85-100 active PR authors/month and 300+ PRs/week peaks, all merged by ONE
# identity. The manual merge-train validated batches by hand; this queue automates
# it with batching + automatic batch bisection (a red batch of N costs ~log2(N)
# revalidations instead of N). Mergify Open Source plan: free, unlimited, public repo.
#
# GOVERNANCE (non-negotiable, mirrors CLAUDE.md Hard Rules #21/#22 + the owner's
# pre-merge ⭐ gate):
# • A PR enters the queue ONLY via the `queue` label — applied by the owner (or a
# session acting for the owner) AFTER the pre-merge ⭐ report/decision. The label
# IS the merge approval; Mergify only executes it.
# • During a release-freeze (open issue labeled `release-freeze`), do NOT label PRs
# targeting the frozen branch — the freeze is a human-honored coordination signal
# the queue cannot see. Retarget to the active release/vX+1 first (Hard Rule #21).
# • Never label a PR another session is actively working (Hard Rule #22b).
# • Fallback path if Mergify misbehaves or the OSS plan changes: the manual
# merge-train runbook (docs/ops/MERGE_TRAIN.md) — remove labels, proceed by hand.
# Auto-enqueue (current Mergify model, 2026): auto_merge_conditions in
# merge_protections_settings — the rules-based queue action / autoqueue path is
# deprecated (EOL 2026-07-16). The owner-applied `queue` label IS the approval.
merge_protections_settings:
auto_merge_conditions:
- label = queue
queue_rules:
- name: release
# Any current or future release branch — the reason GitHub's native queue was
# rejected (no wildcard support on personal-account repos).
queue_conditions:
- base~=^release/v\d+\.\d+\.\d+$
- label=queue
- -draft
- -conflict
# "Everything that ran is green, nothing still running, AND the always-on
# anchor check succeeded" — robust to the path-filtered fast-gates (docs-only
# PRs skip code jobs; matrix shard names vary) while never fail-open: a PR with
# zero checks cannot vacuously merge, because `Merge integrity` runs on EVERY
# non-draft PR (quality.yml) and must be an affirmative success. Review approval
# is intentionally NOT a condition here: the owner-applied `queue` label IS the
# approval in this repo's single-maintainer model (see governance header).
merge_conditions:
# "Zero failures" — EXCEPT the advisory "Build (advisory)" job (quality.yml):
# continue-on-error by design, and its GH-hosted Turbopack build hangs
# recurrently mid-"Creating an optimized production build" (100% failure rate
# across every sampled PR since the job was added 2026-07-27, always killed by
# a runner timeout/shutdown signal, never a real compile error). Any OTHER
# failure still blocks (anti-fail-open kept). The prior dast-smoke exception
# (#7225) was dropped here: dast-smoke's hang (#7226) has been dormant for
# weeks (0 failures in the last 30 runs; 2 all-time, none since 2026-07-13) —
# carrying its tolerance forward would mask problems it no longer causes.
- or:
- "#check-failure=0"
- and:
- "#check-failure=1"
- check-failure=Build (advisory)
- "#check-pending=0"
- "#check-success>=1"
- check-success=Merge integrity (changelog + generated skills)
# NO batching: 'Merge Queue Batch' requires a paid Mergify tier (live finding
# 2026-07-15 — the queue command fails with "Cannot use Merge Queue batch" on
# the free plan). Serial queue (1 PR at a time) still automates the train.
# Squash keeps the one-commit-per-PR history the CHANGELOG reconciliation expects.
merge_method: squash
pull_request_rules:
- name: clean up the queue label after merge
conditions:
- merged
actions:
label:
remove:
- queue

View File

@@ -4,14 +4,11 @@ data/
**/db.json
# VS Code extension test runtime (large binary, not needed in npm package)
app/vscode-extension/
**/data/
**/db.json
# Source code (pre-built dist/ is published instead)
#
# NOTA (2026-08-05): as entradas `app/*` foram removidas — o diretorio `app/`
# foi renomeado para `dist/` na Layer 1 e nao existe mais. Elas sugeriam um
# layout que ja nao e o do projeto.
# Source code (pre-built app/ is published instead)
#
# NOTE (#3578 / #3821-review): package.json "files" is the source of truth for what
# ships. It now allowlists the backend source closure the MCP server needs at runtime
@@ -52,6 +49,8 @@ scripts/
.vscode/
.agents/
.env*
app/.env
app/.env*
eslint.config.mjs
prettier.config.mjs
postcss.config.mjs
@@ -83,6 +82,8 @@ bun.lock
*.deb
*.rpm
electron/
app/electron/
app/vscode-extension/
# Subprojects
clipr/
@@ -92,12 +93,12 @@ vscode-extension/
# Root-level underscore-prefixed directories (private/draft — never publish)
/_*/
app/_*/
app/coverage/
app/logs/
app/tests/
# Consistent with .gitignore and .dockerignore
.claude/
.fakebin-*
.eslintcache*
_tasks/
.DS_Store
.idea/
.config/

10
.npmrc
View File

@@ -2,13 +2,3 @@
# Keeping peer auto-install disabled prevents npm from pulling @lobehub/ui/mermaid
# back into the tree and reopening npm audit findings for unused packages.
legacy-peer-deps=true
# Network resilience: enlarge npm's fetch retry budget so a transient registry
# socket reset (ECONNRESET) mid-download retries instead of failing the job.
# npm defaults to only 2 retries with short timeouts; `npm ci` in
# electron-release.yml hit ECONNRESET during v3.8.41 publish. Applies to every
# CI workflow (electron / docker / unit) and local installs.
fetch-retries=5
fetch-retry-factor=4
fetch-retry-mintimeout=20000
fetch-retry-maxtimeout=120000

View File

@@ -1,16 +0,0 @@
# Long reference tables are manually aligned; formatting the whole file causes noisy diffs.
docs/reference/ENVIRONMENT.md
# Generated by `npm run gen:provider-reference`; the generator aligns the tables and
# is their formatter of record. Without this, lint-staged reformats the file whenever
# it is staged and the next generator run reverts it — a diff ping-pong.
docs/reference/PROVIDER_REFERENCE.md
# Dense auto-generated free-tier budget rows (one object per line) — prettier multi-line expand blows past file-size cap 800.
open-sse/config/freeModelCatalog.data.ts
# Generated by scripts/skills/generate-agent-skills.mjs; the generator is their
# formatter of record and check:agent-skills-sync diffs its output byte-for-byte.
# Prettier reformats the frontmatter (blank line after ---), which makes the gate
# fail on any skill that happens to pass through lint-staged.
skills/*/SKILL.md

8
.source/dynamic.ts Normal file
View File

@@ -0,0 +1,8 @@
// @ts-nocheck
import { dynamic } from 'fumadocs-mdx/runtime/dynamic';
import * as Config from '../source.config';
const create = await dynamic<typeof Config, import("fumadocs-mdx/runtime/types").InternalTypeConfig & {
DocData: {
}
}>(Config, {"configPath":"source.config.ts","environment":"next","outDir":".source"}, {"doc":{"passthroughs":["extractedReferences"]}});

22
.source/source.config.mjs Normal file
View File

@@ -0,0 +1,22 @@
// source.config.ts
import { defineDocs, defineConfig } from "fumadocs-mdx/config";
var docs = defineDocs({
dir: "docs",
docs: {
files: [
"./architecture/**/*.md",
"./guides/**/*.md",
"./reference/**/*.md",
"./frameworks/**/*.md",
"./routing/**/*.md",
"./security/**/*.md",
"./compression/**/*.md",
"./ops/**/*.md"
]
}
});
var source_config_default = defineConfig();
export {
source_config_default as default,
docs
};

View File

@@ -1,22 +0,0 @@
# .trivyignore — accepted-risk suppressions for the container image scan
#
# Policy (see docs/security/SUPPLY_CHAIN.md):
# - The Trivy steps in .github/workflows/docker-publish.yml run with
# `ignore-unfixed: true`, so vulnerabilities WITHOUT a published fix are
# already excluded from both the blocking CRITICAL gate and the advisory
# Security-tab upload. You do NOT need an entry here for an unfixable
# base-image OS CVE — it will not be reported.
# - This file is the single auditable home for the rare case where a *fixable*
# CVE must be temporarily accepted (e.g. the upstream fix is not yet in the
# pinned base tag, or the affected package/binary is provably unreachable
# from the proxy request surface and rebuilding now is not justified).
#
# Format — one CVE id per line, each with a justification comment and, where
# possible, an expiry, e.g.:
# # CVE-XXXX-YYYY — <why accepted>; revisit on next base-image bump (YYYY-MM-DD)
# CVE-XXXX-YYYY
#
# Keep this list SHORT and reviewed every release. Prefer fixing (rebuild on a
# patched base / bump the dep) over suppressing. Stale entries are debt.
#
# (No accepted-risk suppressions at present — ignore-unfixed covers the noise.)

10
.vscode/settings.json vendored
View File

@@ -48,19 +48,11 @@
"**/.build",
"**/dist",
"**/coverage",
"**/.worktrees",
"**/.claude/worktrees",
"**/electron",
"**/_references",
"**/_mono_repo",
"**/_tasks"
"**/.worktrees"
]
},
// Para esconder os diretórios gerados da árvore do Explorer, descomente:
// (MANTIDO comentado — o dono precisa ver _references/_mono_repo/_tasks na árvore.
// A performance é resolvida por watcherExclude + search.exclude + tsserver, sem
// precisar escondê-los do Explorer.)
// "files.exclude": {
// "**/.worktrees": true,
// "**/coverage": true,

View File

@@ -10,8 +10,7 @@ This plugin solves that by:
- Fetching `/v1/models` and `/api/combos` **at OpenCode startup, in Node.js** — no CORS, no WebView restrictions
- Emitting the provider block **dynamically** in the plugin's `config`/`provider` hook — so `opencode.json` only needs the plugin entry, not a static `provider.omniroute`
- Re-fetching on a configurable TTL (default 5 min) **and** background auto-discovery while OpenCode is running (`autoSyncIntervalMs`, default 5 min), so new models / combo changes appear without restarting OpenCode
- Exposing a force-refresh path (`omniroute_sync_models` tool + `/omni-sync` command template) equivalent to Pi `/omni sync`
- Re-fetching on a configurable TTL (default 5 min), so new models / combo changes in the OmniRoute UI appear without restarting OpenCode
- Computing `limit.context` for combos as `min(member.context_length)` from the live catalog (no more `null` values that cause 4K-token truncation)
- **Auto-pickup of `interleaved` capability** for thinking models (merged via PR #3138)
@@ -30,7 +29,7 @@ omniroute setup opencode --auth
# 3. Restart OpenCode — /models lists the full live catalog
```
The `--auth` flag runs `opencode auth login --provider opencode-omniroute` automatically.
The `--auth` flag runs `opencode auth login --provider omniroute` automatically.
Use `--base-url` to point at a non-default OmniRoute address:
```sh
@@ -74,9 +73,6 @@ Peer dep: `@opencode-ai/plugin` (managed by your OpenCode install).
{
"providerId": "omniroute",
"baseURL": "https://or.example.com",
// Background re-discovery while OpenCode is running (Pi parity).
// Default 300000 (5 min). Minimum 60000. Set 0 to disable.
"autoSyncIntervalMs": 300000,
},
],
],
@@ -84,7 +80,7 @@ Peer dep: `@opencode-ai/plugin` (managed by your OpenCode install).
```
```sh
opencode auth login --provider opencode-omniroute
opencode auth login --provider omniroute
# prompts for the OmniRoute API key, writes to ~/.local/share/opencode/auth.json
```
@@ -92,27 +88,6 @@ opencode auth login --provider opencode-omniroute
Restart OpenCode. `/models` lists the full live catalog. Variants (`-low`, `-medium`, `-high`, `-thinking`) and combos appear as first-class IDs — OmniRoute is the source of truth, no client-side synthesis.
### Live catalog refresh (auto + force)
While OpenCode is running, the plugin keeps the model catalog fresh in two ways:
| Mechanism | Default | What it does |
| --- | --- | --- |
| `modelCacheTtl` | `300000` (5 min) | On-demand TTL: next provider/models hook after expiry re-fetches `/v1/models` |
| `autoSyncIntervalMs` | `300000` (5 min) | Background timer: proactively invalidates + re-fetches while the harness is running. Min `60000`. Set `0` to disable background polling (TTL still applies) |
**Force sync now** (Pi `/omni sync` equivalent) — OpenCode has no Pi-style slash-command registration API, so the plugin wires both a tool and command templates:
1. **Tool:** `omniroute_sync_models` — invalidates in-memory + disk caches, re-fetches `GET /v1/models` (and combos/enrichment when enabled), returns `{ ok, count, ... }`.
2. **Command templates** (type these in OpenCode):
- `/omni-sync` — asks the agent to call `omniroute_sync_models` and report the result
- `/omni-autosync` — asks the agent to report current `autoSyncIntervalMs` / `modelCacheTtl` status
```text
/omni-sync
/omni-autosync
```
## Multi-instance (prod + preprod side-by-side)
> ⚠ OC ≤1.15.5 dedupes plugin loads by absolute module path. Two `plugin:` entries pointing at the same `dist/index.js` collapse into one (last-listed options win). Workaround: install the plugin twice into separate directories so each entry resolves to a distinct module file. v0.2.x will introduce an `instances: [...]` shape that registers N providers from a single load.
@@ -164,8 +139,8 @@ Then in `~/.config/opencode/opencode.json` reference each directory by absolute
Paths are relative to `~/.config/opencode/`. Each entry now resolves to a distinct module file, so OC loads them as two separate plugin instances. Authenticate each:
```sh
opencode auth login --provider opencode-omniroute
opencode auth login --provider opencode-omniroute-preprod
opencode auth login --provider omniroute
opencode auth login --provider omniroute-preprod
```
Each entry gets its own provider id, its own model picker entry, its own slot in `auth.json`, and its own TTL cache. Closures are isolated per plugin instance — no cross-talk.
@@ -190,13 +165,12 @@ npm install --prefix ~/.config/opencode/plugins/omniroute-opencode-plugin-prepro
| Dynamic `/v1/models` | Pulls live catalog (455+ entries on prod) on each refresh, TTL-cached | `provider.models` |
| Variants pass-through | `-low`/`-medium`/`-high`/`-thinking` ship as first-class IDs from OmniRoute (no client synthesis) | `provider.models` |
| Combo LCD aggregation | Combos appear with intersected capabilities + min context/output across members | `provider.models` + `config` |
| `combo/<slug>` namespace + `Combo:` prefix | Combos surface under `combo/claude-primary` (not the upstream UUID) and the picker shows `Combo: claude-primary` so they stand apart from raw provider/model pairs | both hooks |
| `combo/<slug>` namespace + `Combo: ` prefix | Combos surface under `combo/claude-primary` (not the upstream UUID) and the picker shows `Combo: claude-primary` so they stand apart from raw provider/model pairs | both hooks |
| Nice names + cost | `/api/pricing/models` display names AND `/api/pricing` per-million-token cost overlaid onto the live catalog | both hooks |
| Canonical-twin dedup + alias-fallback | `/v1/models` exposes the same upstream model under both short alias (`cc/claude-opus-4-7`) and canonical name (`claude/claude-opus-4-7`); the plugin drops the canonical twin when an alias twin exists (no duplicate rows in the picker) and reverse-maps canonical → alias to pick up enrichment for short aliases (`dg/nova-3 → Deepgram - Nova 3`) that `/api/pricing/models` only indexes by canonical | both hooks |
| Compression pipeline tags | Combo names get tagged with their compression pipeline (e.g. `Combo: claude-primary [rtk🟡 → caveman🟠]`) when `features.compressionMetadata: true`. Intensity tokens render as a traffic-light emoji: 🟢 lite/minimal · 🟡 standard · 🟠 aggressive/full · 🔴 ultra | both hooks |
| Provider-tag prefix | Prepend short upstream-provider label to enriched names (e.g. `Claude - Claude Opus 4.7` vs `Kiro - Claude Opus 4.7`, `GHM - GPT 5`) so same-id models routed via different upstream connections group visibly in the picker (default-on, opt-out via `features.providerTag: false`) | both hooks |
| Usable-only filter | Filter to providers with at least one healthy connection in `/api/providers` (opt-in via `features.usableOnly`) | both hooks |
| Model allowlist/blocklist | Curate the model picker to a fixed set of IDs via `features.visibleModels` (allowlist) and/or `features.hiddenModels` (blocklist). Bare suffixes like `claude-opus-4-7` match any `{prefix}/claude-opus-4-7`. Both compose with `usableOnly` (all filters AND together). Blocklist wins over allowlist (deny takes precedence) | both hooks |
| Disk-cache fallback | Last-known-good catalog persisted to disk; hydrates on a cold start when `/v1/models` is unreachable (default-on, opt-out via `features.diskCache: false`) | `config` |
| Bearer injection + suffix-spoof guard | Adds `Authorization` on baseURL-matched requests only | `auth.loader.fetch` |
| Gemini schema sanitization | Strips `$schema`/`$ref`/`additionalProperties` for `gemini-*`/`google-vertex-gemini/*` | `auth.loader.fetch` wrap |
@@ -205,35 +179,30 @@ npm install --prefix ~/.config/opencode/plugins/omniroute-opencode-plugin-prepro
## Plugin options
| Option | Type | Default | Description |
| --------------------- | -------- | ------------------------------------------ | ----------------------------------------------------------------------------------------------------- |
| `providerId` | `string` | `"omniroute"` | OpenCode provider id; must be unique across plugin entries |
| `displayName` | `string` | `"OmniRoute"` or `OmniRoute (<id>)` | Label in the OC UI |
| `modelCacheTtl` | `number` | `300000` (5 min) | `/v1/models` TTL in ms |
| `baseURL` | `string` | resolved from `auth.json` after `/connect` | Override OmniRoute base URL |
| `managementReadToken` | `string` | falls back to `apiKey` | Optional read-only token for management catalog GETs; `/v1` inference stays on the connected `apiKey` |
| `features` | `object` | see below | Feature toggles (all opt-in/out, defaults preserve v0.1.0) |
For least-privilege deployments, set top-level `managementReadToken` to a read-only management token. It is sent only to catalog reads (`/api/combos`, `/api/combos/auto`, `/api/pricing/models`, `/api/pricing`, `/api/context/combos`, and `/api/providers`). Inference requests under `/v1`, including chat, continue to use the `apiKey` stored by OpenCode. `features.mcpToken` remains independent. If `managementReadToken` is omitted, catalog reads retain the previous `apiKey` behavior.
| Option | Type | Default | Description |
| --------------- | -------- | ------------------------------------------ | ---------------------------------------------------------- |
| `providerId` | `string` | `"omniroute"` | OpenCode provider id; must be unique across plugin entries |
| `displayName` | `string` | `"OmniRoute"` or `OmniRoute (<id>)` | Label in the OC UI |
| `modelCacheTtl` | `number` | `300000` (5 min) | `/v1/models` TTL in ms |
| `baseURL` | `string` | resolved from `auth.json` after `/connect` | Override OmniRoute base URL |
| `features` | `object` | see below | Feature toggles (all opt-in/out, defaults preserve v0.1.0) |
### `features` block
Every field is optional. Defaults mirror v0.1.0 behaviour so existing `opencode.json` files do not need to change.
| Feature | Type | Default | What it does |
| --------------------- | --------- | ------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `combos` | `boolean` | `true` | Discover `/api/combos` and surface them as pseudo-models with LCD capabilities. Combos are keyed under the `combo/<slug>` namespace and labelled `Combo: <name>` in the model picker so they're distinguishable from raw provider/model pairs. |
| `enrichment` | `boolean` | `true` | Pull display names from `/api/pricing/models` AND per-million-token pricing (`input`, `output`, `cached``cacheRead`, `cache_creation``cacheWrite`) from `/api/pricing`, then overlay both onto the live catalog (so the UI shows `Claude 4.7 Opus` with `cost.input: 5`, `cost.output: 25` instead of raw IDs and zeroed cost). |
| `compressionMetadata` | `boolean` | `false` | Pull `/api/context/combos` so combo names get tagged with their compression pipeline, e.g. `Combo: claude-primary [rtk🟡 → caveman🟠]`. Intensity tokens render as traffic-light emoji (🟢 lite/minimal · 🟡 standard · 🟠 aggressive/full · 🔴 ultra) so the picker advertises "how compressed" each combo is at a glance. |
| `providerTag` | `boolean` | `true` | Prepend a short upstream-provider label to the enriched display name with `" - "` separator, so `cc/claude-opus-4-7 → Claude - Claude Opus 4.7` differs visibly from `kr/claude-opus-4-7 → Kiro - Claude Opus 4.7` in the OC TUI model picker. Label resolution: use `/api/pricing/models[<alias>].name` verbatim when ≤8 chars (e.g. `Claude`, `Kiro`, `Codex`, `Qwen`), otherwise fall back to `UPPER(alias)` (e.g. `GitHub Models``GHM`, `Gemini``GEMINI`). Idempotent. Combos intentionally skipped (the `Combo:` prefix already conveys multi-upstream). |
| `usableOnly` | `boolean` | `false` | Read `/api/providers` and filter the catalog to providers that have at least one connection with `isActive: true` AND `testStatus: 'active'`. Subtract-filter semantics: providers unknown to BOTH the pricing-models catalog AND the connection table pass through (so synthetic prefixes like `agentrouter/*` survive). On fetch failure the filter is disabled for the refresh — never hides the whole catalog. |
| `visibleModels` | `string[]` | _unset_ | Allowlist — when set and non-empty, only models whose raw `/v1/models` ID matches are emitted. Bare IDs (no slash, e.g. `claude-opus-4-7`) match any `{prefix}/claude-opus-4-7`; full IDs (e.g. `cc/claude-opus-4-7`) match exactly. Composes with `usableOnly` and `hiddenModels` (all filters AND together). Unset or empty = no filter. |
| `hiddenModels` | `string[]` | _unset_ | Blocklist — models whose raw ID matches are dropped. Same matching rules as `visibleModels`. When a model is in both `visibleModels` and `hiddenModels`, the blocklist wins (deny takes precedence). Composes with `usableOnly` and `visibleModels` (all filters AND together). Unset or empty = no filter. |
| `diskCache` | `boolean` | `true` | Persist the last successful `/v1/models` + `/api/combos` + enrichment + connections + compression snapshot to `${OPENCODE_DATA_DIR ?? ~/.local/share/opencode}/plugins/omniroute-<providerId>.json`. On a subsequent cold start where `/v1/models` throws (network down / IP whitelist drop / 5xx) the static block hydrates from the snapshot so OC's model picker survives offline. Soft-fail on read/write — never blocks publishing. |
| `geminiSanitization` | `boolean` | `true` | Strip `$schema`/`$ref`/`additionalProperties` from tool params when the model id matches `gemini` |
| `mcpAutoEmit` | `boolean` | `false` | Auto-write an `mcp.<providerId>` remote entry into the OC config pointing at `<baseURL>/api/mcp/stream` with the resolved Bearer token |
| `mcpToken` | `string` | _unset_ | Optional separate Bearer for the auto-emitted MCP entry. Falls back to the provider's `apiKey` (from `auth.json`) when unset |
| `fetchInterceptor` | `boolean` | `true` | Inject `Authorization: Bearer` + default `Content-Type` on every outbound request targeting `baseURL` (suffix-spoof guarded) |
| Feature | Type | Default | What it does |
| --------------------- | --------- | ------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `combos` | `boolean` | `true` | Discover `/api/combos` and surface them as pseudo-models with LCD capabilities. Combos are keyed under the `combo/<slug>` namespace and labelled `Combo: <name>` in the model picker so they're distinguishable from raw provider/model pairs. |
| `enrichment` | `boolean` | `true` | Pull display names from `/api/pricing/models` AND per-million-token pricing (`input`, `output`, `cached``cacheRead`, `cache_creation``cacheWrite`) from `/api/pricing`, then overlay both onto the live catalog (so the UI shows `Claude 4.7 Opus` with `cost.input: 5`, `cost.output: 25` instead of raw IDs and zeroed cost). |
| `compressionMetadata` | `boolean` | `false` | Pull `/api/context/combos` so combo names get tagged with their compression pipeline, e.g. `Combo: claude-primary [rtk🟡 → caveman🟠]`. Intensity tokens render as traffic-light emoji (🟢 lite/minimal · 🟡 standard · 🟠 aggressive/full · 🔴 ultra) so the picker advertises "how compressed" each combo is at a glance. |
| `providerTag` | `boolean` | `true` | Prepend a short upstream-provider label to the enriched display name with `" - "` separator, so `cc/claude-opus-4-7 → Claude - Claude Opus 4.7` differs visibly from `kr/claude-opus-4-7 → Kiro - Claude Opus 4.7` in the OC TUI model picker. Label resolution: use `/api/pricing/models[<alias>].name` verbatim when ≤8 chars (e.g. `Claude`, `Kiro`, `Codex`, `Qwen`), otherwise fall back to `UPPER(alias)` (e.g. `GitHub Models``GHM`, `Gemini-cli``GEMINI-CLI`). Idempotent. Combos intentionally skipped (the `Combo: ` prefix already conveys multi-upstream). |
| `usableOnly` | `boolean` | `false` | Read `/api/providers` and filter the catalog to providers that have at least one connection with `isActive: true` AND `testStatus: 'active'`. Subtract-filter semantics: providers unknown to BOTH the pricing-models catalog AND the connection table pass through (so synthetic prefixes like `agentrouter/*` survive). On fetch failure the filter is disabled for the refresh — never hides the whole catalog. |
| `diskCache` | `boolean` | `true` | Persist the last successful `/v1/models` + `/api/combos` + enrichment + connections + compression snapshot to `${OPENCODE_DATA_DIR ?? ~/.local/share/opencode}/plugins/omniroute-<providerId>.json`. On a subsequent cold start where `/v1/models` throws (network down / IP whitelist drop / 5xx) the static block hydrates from the snapshot so OC's model picker survives offline. Soft-fail on read/write — never blocks publishing. |
| `geminiSanitization` | `boolean` | `true` | Strip `$schema`/`$ref`/`additionalProperties` from tool params when the model id matches `gemini` |
| `mcpAutoEmit` | `boolean` | `false` | Auto-write an `mcp.<providerId>` remote entry into the OC config pointing at `<baseURL>/api/mcp/stream` with the resolved Bearer token |
| `mcpToken` | `string` | _unset_ | Optional separate Bearer for the auto-emitted MCP entry. Falls back to the provider's `apiKey` (from `auth.json`) when unset |
| `fetchInterceptor` | `boolean` | `true` | Inject `Authorization: Bearer` + default `Content-Type` on every outbound request targeting `baseURL` (suffix-spoof guarded) |
#### Example — enrichment + compression tags + MCP auto-emit
@@ -245,7 +214,6 @@ Every field is optional. Defaults mirror v0.1.0 behaviour so existing `opencode.
{
"providerId": "omniroute",
"baseURL": "https://or.example.com",
"managementReadToken": "<read-only-management-token>",
"features": {
"combos": true,
"enrichment": true,
@@ -301,45 +269,7 @@ If you want a narrower-scoped Bearer for MCP (different from the chat/inference
- `compressionMetadata: true` annotates combo display names with their pipeline using traffic-light emoji for intensity (e.g. `Combo: claude-primary [rtk🟡 → caveman🟠]`) so the picker advertises which compression each combo applies and how heavy it is at a glance. Palette: 🟢 lite/minimal · 🟡 standard · 🟠 aggressive/full · 🔴 ultra. Unknown intensities fall through to raw text (`[rtk:custom-thing]`) so the plugin never hides a value OmniRoute knows but the plugin doesn't.
- `providerTag: true` (default) prepends a short upstream-provider label so the picker shows `Claude - Claude Opus 4.7` for `cc/claude-opus-4-7`, `Kiro - Claude Opus 4.7` for `kr/claude-opus-4-7`, and `GHM - GPT 5` for `ghm/gpt-5` (slot.name `GitHub Models` > 8 chars → abbreviated). Critical when the same model id is sold through multiple upstream connections with different cost/auth/rate-limit profiles. Set to `false` to keep the pre-v3.8.3 unsuffixed format.
#### Example — curating the model picker (allowlist + blocklist)
A typical OmniRoute instance serves 600+ models. The OpenCode TUI/CLI picker becomes unusable when you need to scroll through hundreds of entries to find the ~30 models you actually use. `visibleModels` and `hiddenModels` let you curate the picker to a fixed set of model IDs that persists in `opencode.json` across config resets.
```jsonc
{
"plugin": [
[
"@omniroute/opencode-plugin",
{
"providerId": "omniroute",
"baseURL": "https://or.example.com",
"features": {
"combos": true,
"enrichment": true,
"usableOnly": true,
"visibleModels": [
"claude-opus-4-7", // bare suffix: matches cc/claude-opus-4-7, kr/claude-opus-4-7, etc.
"cc/claude-sonnet-4-6", // exact: only the cc/ alias
"gemini-2.5-pro",
"gpt-5",
"o3",
"o3-pro",
"o4-mini",
],
"hiddenModels": [
"o3-mini", // hide the mini variant even if visibleModels is unset
],
},
},
],
],
}
```
- `visibleModels` is an allowlist — only models whose raw ID matches are emitted. Bare IDs (no slash) match any provider prefix; full IDs (with slash) match exactly.
- `hiddenModels` is a blocklist — listed models are dropped. When a model is in both lists, the blocklist wins (deny takes precedence).
- Both compose with `usableOnly` (all filters AND together: a model must pass usableOnly AND visibleModels AND not be in hiddenModels).
- Unset or empty = no filter (current behavior).
## Comparison vs `@omniroute/opencode-provider`
[`@omniroute/opencode-provider`](https://github.com/diegosouzapw/OmniRoute/tree/main/%40omniroute/opencode-provider) is the existing config-generator package — it writes a frozen `provider.<id>` block into `opencode.json` at build time. This plugin is the runtime integration.

View File

@@ -1,12 +1,12 @@
{
"name": "@omniroute/opencode-plugin",
"version": "0.2.1",
"version": "0.1.0",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@omniroute/opencode-plugin",
"version": "0.2.1",
"version": "0.1.0",
"license": "MIT",
"dependencies": {
"zod": "^4.4.3"

View File

@@ -1,6 +1,6 @@
{
"name": "@omniroute/opencode-plugin",
"version": "0.2.1",
"version": "0.1.0",
"description": "OpenCode plugin for the OmniRoute AI Gateway. Drives dynamic model discovery, /connect auth flow, and multi-instance OmniRoute providers via the official @opencode-ai/plugin contract.",
"type": "module",
"main": "./dist/index.js",
@@ -23,7 +23,7 @@
"scripts": {
"build": "tsup",
"clean": "rm -rf dist",
"test": "node --import tsx/esm --test tests/scaffold.test.ts tests/auth.test.ts tests/options-schema.test.ts tests/multi-instance.test.ts tests/fetch-interceptor.test.ts tests/provider.test.ts tests/gemini-sanitize.test.ts tests/combos.test.ts tests/config-shim.test.ts tests/features.test.ts tests/feature-defaults.test.ts tests/usable-combo.test.ts tests/disk-snapshot-perms.test.ts tests/fork-features.test.ts tests/auto-combo-context.test.ts tests/provider-id-routing.test.ts tests/management-read-token.test.ts tests/auto-sync.test.ts tests/model-allowlist.test.ts",
"test": "node --import tsx/esm --test tests/scaffold.test.ts tests/auth.test.ts tests/options-schema.test.ts tests/multi-instance.test.ts tests/fetch-interceptor.test.ts tests/provider.test.ts tests/gemini-sanitize.test.ts tests/combos.test.ts tests/config-shim.test.ts tests/features.test.ts tests/usable-combo.test.ts tests/disk-snapshot-perms.test.ts tests/fork-features.test.ts tests/auto-combo-context.test.ts",
"prepublishOnly": "npm run clean && npm run build && npm test"
},
"keywords": [

File diff suppressed because it is too large Load Diff

View File

@@ -1,130 +0,0 @@
/**
* Auto-discovery + force-sync (OpenCode parity with Pi `/omni sync`).
*/
import test from "node:test";
import assert from "node:assert/strict";
import {
sanitizeAutoSyncIntervalMs,
DEFAULT_AUTO_SYNC_INTERVAL_MS,
MIN_AUTO_SYNC_INTERVAL_MS,
parseOmniRoutePluginOptions,
resolveOmniRoutePluginOptions,
invalidateOmniRouteFetchCache,
forceSyncOmniRouteModels,
type OmniRouteFetchCache,
} from "../src/index.js";
test("sanitizeAutoSyncIntervalMs: unset → default 300000", () => {
assert.equal(sanitizeAutoSyncIntervalMs(undefined), DEFAULT_AUTO_SYNC_INTERVAL_MS);
assert.equal(sanitizeAutoSyncIntervalMs(null), DEFAULT_AUTO_SYNC_INTERVAL_MS);
});
test("sanitizeAutoSyncIntervalMs: 0 disables", () => {
assert.equal(sanitizeAutoSyncIntervalMs(0), 0);
});
test("sanitizeAutoSyncIntervalMs: clamps below min to 60000", () => {
assert.equal(sanitizeAutoSyncIntervalMs(1), MIN_AUTO_SYNC_INTERVAL_MS);
assert.equal(sanitizeAutoSyncIntervalMs(59_999), MIN_AUTO_SYNC_INTERVAL_MS);
});
test("sanitizeAutoSyncIntervalMs: keeps valid values", () => {
assert.equal(sanitizeAutoSyncIntervalMs(60_000), 60_000);
assert.equal(sanitizeAutoSyncIntervalMs(300_000), 300_000);
});
test("parseOmniRoutePluginOptions accepts autoSyncIntervalMs including 0", () => {
assert.equal(parseOmniRoutePluginOptions({ autoSyncIntervalMs: 0 }).autoSyncIntervalMs, 0);
assert.equal(parseOmniRoutePluginOptions({ autoSyncIntervalMs: 120_000 }).autoSyncIntervalMs, 120_000);
});
test("resolveOmniRoutePluginOptions defaults autoSyncIntervalMs to 300000", () => {
const r = resolveOmniRoutePluginOptions({});
assert.equal(r.autoSyncIntervalMs, DEFAULT_AUTO_SYNC_INTERVAL_MS);
});
test("resolveOmniRoutePluginOptions clamps low positive autoSyncIntervalMs", () => {
const r = resolveOmniRoutePluginOptions({ autoSyncIntervalMs: 5000 });
assert.equal(r.autoSyncIntervalMs, MIN_AUTO_SYNC_INTERVAL_MS);
});
test("invalidateOmniRouteFetchCache clears by baseURL prefix", () => {
const cache: OmniRouteFetchCache = new Map();
cache.set("https://a.example/v1::abc", {
rawModels: [],
rawCombos: [],
rawAutoCombos: [],
rawEnrichment: new Map(),
rawCompressionCombos: [],
rawConnections: [],
expiresAt: Date.now() + 1000,
});
cache.set("https://b.example/v1::def", {
rawModels: [],
rawCombos: [],
rawAutoCombos: [],
rawEnrichment: new Map(),
rawCompressionCombos: [],
rawConnections: [],
expiresAt: Date.now() + 1000,
});
const removed = invalidateOmniRouteFetchCache(cache, "https://a.example/v1");
assert.equal(removed, 1);
assert.equal(cache.size, 1);
assert.equal(cache.has("https://b.example/v1::def"), true);
});
test("forceSyncOmniRouteModels: fetches, populates cache, returns count", async () => {
const cache: OmniRouteFetchCache = new Map();
const resolved = resolveOmniRoutePluginOptions({
providerId: "omniroute",
baseURL: "https://omniroute.example/v1",
autoSyncIntervalMs: 0,
features: {
combos: false,
autoCombos: false,
enrichment: false,
compressionMetadata: false,
usableOnly: false,
diskCache: false,
},
});
const result = await forceSyncOmniRouteModels({
resolved,
cache,
readAuthJson: async () => ({
omniroute: { type: "api", key: "test-key" },
}),
fetcher: async () => [
{ id: "model-a", object: "model" },
{ id: "model-b", object: "model" },
],
now: () => 1_000_000,
});
assert.equal(result.ok, true);
assert.equal(result.count, 2);
assert.equal(result.provider, "omniroute");
assert.equal(cache.size, 1);
const entry = [...cache.values()][0];
assert.equal(entry.rawModels.length, 2);
assert.equal(entry.expiresAt, 1_000_000 + resolved.modelCacheTtl);
});
test("forceSyncOmniRouteModels: missing auth returns error", async () => {
const cache: OmniRouteFetchCache = new Map();
const resolved = resolveOmniRoutePluginOptions({
providerId: "omniroute",
baseURL: "https://omniroute.example/v1",
autoSyncIntervalMs: 0,
features: { diskCache: false },
});
const result = await forceSyncOmniRouteModels({
resolved,
cache,
readAuthJson: async () => ({}),
});
assert.equal(result.ok, false);
assert.match(result.error ?? "", /credentials|baseURL|connect/i);
});

View File

@@ -447,14 +447,14 @@ test("models() returns combo entries merged into the map", async () => {
// 3 raw models + 1 combo = 4 entries
assert.equal(Object.keys(out).length, 4);
assert.ok(out["omniroute/claude-primary"]);
assert.ok(out["omniroute/claude-secondary"]);
assert.ok(out["omniroute/gemini-3-flash"]);
assert.ok(out["omniroute/claude-tier"]);
assert.ok(out["opencode-omniroute/claude-primary"]);
assert.ok(out["opencode-omniroute/claude-secondary"]);
assert.ok(out["opencode-omniroute/gemini-3-flash"]);
assert.ok(out["opencode-omniroute/claude-tier"]);
const combo = out["omniroute/claude-tier"];
const combo = out["opencode-omniroute/claude-tier"];
assert.equal(combo.name, "Claude Tier");
assert.equal(combo.providerID, "omniroute");
assert.equal(combo.providerID, "opencode-omniroute");
// LCD over claude-primary (200k, reasoning) + claude-secondary (100k, no reasoning)
assert.equal(combo.limit.context, 100_000);
assert.equal(combo.capabilities.reasoning, false);
@@ -478,11 +478,11 @@ test("models(): combo with unknown member ids degrades to all-false LCD posture"
{ fetcher: modelsFetcher, combosFetcher }
);
const out = await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
assert.ok(out["omniroute/phantom-combo"]);
assert.ok(out["opencode-omniroute/phantom-combo"]);
// With zero resolvable members, LCD = all-false (defensive posture).
assert.equal(out["omniroute/phantom-combo"].capabilities.toolcall, false);
assert.equal(out["omniroute/phantom-combo"].capabilities.reasoning, false);
assert.equal(out["omniroute/phantom-combo"].limit.context, 0);
assert.equal(out["opencode-omniroute/phantom-combo"].capabilities.toolcall, false);
assert.equal(out["opencode-omniroute/phantom-combo"].capabilities.reasoning, false);
assert.equal(out["opencode-omniroute/phantom-combo"].limit.context, 0);
});
test("models(): hidden combos are excluded from the map", async () => {
@@ -505,8 +505,8 @@ test("models(): hidden combos are excluded from the map", async () => {
{ fetcher: modelsFetcher, combosFetcher }
);
const out = await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
assert.ok(out["omniroute/visible"]);
assert.ok(!out["omniroute/hidden"], "hidden combo must be omitted");
assert.ok(out["opencode-omniroute/visible"]);
assert.ok(!out["opencode-omniroute/hidden"], "hidden combo must be omitted");
});
test("models(): combo name exactly matches raw model id → raw deleted, raw deleted, no warn", async () => {
@@ -530,8 +530,8 @@ test("models(): combo name exactly matches raw model id → raw deleted, raw del
});
// Raw model replaced by combo of the same key; combo now lives at the bare slug.
assert.ok(out["omniroute/claude-primary"], "combo surfaces under prefixed key");
assert.equal(out["omniroute/claude-primary"].name, "claude-primary");
assert.ok(out["opencode-omniroute/claude-primary"], "combo surfaces under prefixed key");
assert.equal(out["opencode-omniroute/claude-primary"].name, "claude-primary");
// No collision warning fires — dedup makes keys disjoint.
const collisionWarns = warnings.filter((w) => {
@@ -565,8 +565,8 @@ test("models(): two combos with same slug → second gets disambiguator suffix",
const out = await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
// First combo gets the bare slug; second gets disambiguated.
assert.ok(out["omniroute/claude"], "first combo at prefixed slug");
assert.ok(out["omniroute/claude-uuid"], "second combo disambiguated by id prefix");
assert.ok(out["opencode-omniroute/claude"], "first combo at prefixed slug");
assert.ok(out["opencode-omniroute/claude-uuid"], "second combo disambiguated by id prefix");
});
test("models(): combos fetch fails → falls back to models-only, warn emitted, no throw", async () => {
@@ -583,8 +583,8 @@ test("models(): combos fetch fails → falls back to models-only, warn emitted,
// Catalog includes the models but NOT any combo entries.
assert.equal(Object.keys(out).length, 2);
assert.ok(out["omniroute/claude-primary"]);
assert.ok(out["omniroute/claude-secondary"]);
assert.ok(out["opencode-omniroute/claude-primary"]);
assert.ok(out["opencode-omniroute/claude-secondary"]);
// Soft-fail warning surfaced.
const softFail = warnings.find((w) => {
@@ -609,7 +609,7 @@ test("models(): combos cached + reused within TTL (one combo fetch per TTL windo
const second = await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
assert.equal(combosFetcher.callCount(), 1, "combos fetched only once within TTL");
assert.equal(modelsFetcher.callCount(), 1, "models fetched only once within TTL");
assert.ok(second["omniroute/claude-tier"]);
assert.ok(second["opencode-omniroute/claude-tier"]);
});
test("models(): combos refetched after TTL expiry (same key as models)", async () => {
@@ -701,7 +701,7 @@ test("models(): nested combo-ref context is the min of nested + raw members", as
{ fetcher: modelsFetcher, combosFetcher }
);
const out = await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
const masterLight = out["omniroute/master-light"];
const masterLight = out["opencode-omniroute/master-light"];
assert.ok(masterLight, "MASTER-LIGHT entry must exist");
assert.equal(
masterLight.limit.context,

View File

@@ -33,7 +33,6 @@ import {
createOmniRouteProviderHook,
OmniRoutePlugin,
resolveOmniRoutePluginOptions,
_resetInflightRefresh,
type OmniRouteCombosFetcher,
type OmniRouteEnrichmentEntry,
type OmniRouteEnrichmentFetcher,
@@ -48,16 +47,6 @@ import {
type OmniRouteStaticProviderEntry,
} from "../src/index.js";
// ────────────────────────────────────────────────────────────────────────────
// Test isolation: reset the module-level in-flight refresh guard between
// tests so a detached refresh from a previous test doesn't leak into the
// next one.
// ────────────────────────────────────────────────────────────────────────────
test.beforeEach(() => {
_resetInflightRefresh();
});
// ────────────────────────────────────────────────────────────────────────────
// Fixtures
// ────────────────────────────────────────────────────────────────────────────
@@ -238,7 +227,7 @@ test("config: with valid auth.json + apiKey + baseURL → mutates input.provider
// Stripped per-model shape: name + cap flags + modalities + (optional)
// cost. OC's SDK static schema accepts only `limit.{context,output}` —
// `limit.input` is NOT in the SDK shape and gets dropped silently.
const claude = entry.models["claude-sonnet-4-6"];
const claude = entry.models["opencode-omniroute/claude-sonnet-4-6"];
assert.ok(claude, "claude model surfaced");
assert.equal(claude.name, "claude-sonnet-4-6");
assert.equal(claude.attachment, true);
@@ -259,7 +248,7 @@ test("config: with valid auth.json + apiKey + baseURL → mutates input.provider
// Combo surfaces under bare key + LCD'd
// (gemini's reasoning=false → combo reasoning=false).
const combo = entry.models["claude-tier"];
const combo = entry.models["opencode-omniroute/claude-tier"];
assert.ok(combo, "combo surfaced under bare key");
assert.equal(combo.name, "Claude Tier");
assert.equal(combo.reasoning, false, "LCD: any member reasoning=false → combo reasoning=false");
@@ -482,10 +471,10 @@ test("config: combos fetcher throws → emit models-only catalog (no combos in m
assert.ok(entry);
const ids = Object.keys(entry.models).sort();
assert.deepEqual(ids, [
"claude-sonnet-4-6",
"gemini-3-flash",
"opencode-omniroute/claude-sonnet-4-6",
"opencode-omniroute/gemini-3-flash",
]);
assert.equal(entry.models["claude-tier"], undefined, "no combo entry");
assert.equal(entry.models["opencode-omniroute/claude-tier"], undefined, "no combo entry");
assert.ok(
logger.entries.some((e) => String(e[0]).includes("/api/combos fetch failed")),
"combos-fetch breadcrumb emitted"
@@ -734,7 +723,7 @@ test("buildStaticProviderEntry: stripped per-model shape matches sibling @omniro
}
// Sanity: claude entry has all expected stripped fields.
const claude = block.models["claude-sonnet-4-6"];
const claude = block.models["opencode-omniroute/claude-sonnet-4-6"];
assert.equal(typeof claude.name, "string");
assert.equal(typeof claude.attachment, "boolean");
assert.equal(typeof claude.reasoning, "boolean");
@@ -759,8 +748,8 @@ test("buildStaticProviderEntry: hidden combos are excluded", () => {
"https://or.example/v1",
"sk-test"
);
assert.equal(block.models["claude-tier"], undefined);
assert.ok(block.models["claude-sonnet-4-6"]);
assert.equal(block.models["opencode-omniroute/claude-tier"], undefined);
assert.ok(block.models["opencode-omniroute/claude-sonnet-4-6"]);
});
// ────────────────────────────────────────────────────────────────────────────
@@ -776,7 +765,7 @@ test("buildStaticProviderEntry: emits modalities.input from raw.input_modalities
"https://or.example/v1",
"sk-test"
);
const claude = block.models["claude-sonnet-4-6"];
const claude = block.models["opencode-omniroute/claude-sonnet-4-6"];
assert.deepEqual(claude.modalities?.input, ["text", "image"]);
assert.deepEqual(claude.modalities?.output, ["text"]);
});
@@ -790,7 +779,7 @@ test("buildStaticProviderEntry: never emits limit.input (OC SDK rejects it)", ()
"https://or.example/v1",
"sk-test"
);
const claude = block.models["claude-sonnet-4-6"];
const claude = block.models["opencode-omniroute/claude-sonnet-4-6"];
assert.equal((claude.limit as Record<string, unknown>).input, undefined);
assert.equal(typeof claude.limit?.context, "number");
assert.equal(typeof claude.limit?.output, "number");
@@ -818,7 +807,7 @@ test("buildStaticProviderEntry: emits cost when enrichment carries pricing", ()
"sk-test",
enrichment
);
const claude = block.models["claude-sonnet-4-6"];
const claude = block.models["opencode-omniroute/claude-sonnet-4-6"];
assert.equal(claude.cost?.input, 3);
assert.equal(claude.cost?.output, 15);
assert.equal(claude.cost?.cache_read, 0.3);
@@ -839,8 +828,8 @@ test("buildStaticProviderEntry: emits release_date when raw carries it; omits wh
"https://or.example/v1",
"sk-test"
);
assert.equal(block.models["claude-with-date"].release_date, "2026-02-19");
assert.equal(block.models["gemini-3-flash"].release_date, undefined);
assert.equal(block.models["opencode-omniroute/claude-with-date"].release_date, "2026-02-19");
assert.equal(block.models["opencode-omniroute/gemini-3-flash"].release_date, undefined);
});
test("buildStaticProviderEntry: combo modalities = intersection of members (LCD)", () => {
@@ -869,7 +858,7 @@ test("buildStaticProviderEntry: combo modalities = intersection of members (LCD)
"https://or.example/v1",
"sk-test"
);
const combo = block.models["mixed-tier"];
const combo = block.models["opencode-omniroute/mixed-tier"];
assert.ok(combo, "combo emitted under slug key");
// claude has text+image, text-only has text → intersection drops image.
assert.deepEqual(combo.modalities?.input, ["text"]);
@@ -978,10 +967,10 @@ test("config: enrichment fetched + name overlaid on raw-model entries", async ()
"opencode-omniroute"
];
assert.ok(entry);
assert.equal(entry.models["claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
assert.equal(entry.models["gemini-3-flash"].name, "Gemini 3 Flash");
assert.equal(entry.models["opencode-omniroute/claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
assert.equal(entry.models["opencode-omniroute/gemini-3-flash"].name, "Gemini 3 Flash");
// Combo names still come from /api/combos — enrichment overlay does NOT touch combos.
assert.equal(entry.models["claude-tier"].name, "Claude Tier");
assert.equal(entry.models["opencode-omniroute/claude-tier"].name, "Claude Tier");
assert.equal(enrichmentFetcher.callCount(), 1);
});
@@ -1011,7 +1000,7 @@ test("config: features.enrichment=false skips enrichment fetch + keeps raw-id na
assert.ok(entry);
assert.equal(enrichmentFetcher.callCount(), 0, "enrichment fetch suppressed by feature flag");
assert.equal(
entry.models["claude-sonnet-4-6"].name,
entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
"claude-sonnet-4-6",
"raw id retained"
);
@@ -1038,7 +1027,7 @@ test("config: enrichment fetcher throws → soft-fail (warn + raw-id static cata
];
assert.ok(entry, "static block still published on enrichment failure");
assert.equal(
entry.models["claude-sonnet-4-6"].name,
entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
"claude-sonnet-4-6",
"raw id retained"
);
@@ -1240,20 +1229,17 @@ test("config: diskCache hydrates stale snapshot when /v1/models throws", async (
"opencode-omniroute"
];
assert.ok(
entry.models["claude-sonnet-4-6"],
entry.models["opencode-omniroute/claude-sonnet-4-6"],
"stale snapshot hydrated into static block"
);
assert.equal(
entry.models["claude-sonnet-4-6"].name,
entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
"Claude Sonnet 4.6 (cached)",
"stale enrichment also reused"
);
assert.equal(writes, 0, "disk write skipped when live fetch failed");
assert.ok(
logger.entries.some((e) =>
String(e[0]).includes("using stale disk cache") ||
String(e[0]).includes("warm startup from disk snapshot")
),
logger.entries.some((e) => String(e[0]).includes("using stale disk cache")),
"disk-cache hydration breadcrumb emitted"
);
});
@@ -1295,7 +1281,7 @@ test("config: cached rawEnrichment from earlier provider hook is reused (no refe
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.equal(entry.models["claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
assert.equal(entry.models["opencode-omniroute/claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
});
// ─────────────────────────────────────────────────────────────────────
@@ -1325,9 +1311,9 @@ test("config: providerTag (default-on) prepends '<provider> - ' to enriched raw-
"gemini-3-flash",
{
name: "Gemini 3 Flash",
providerAlias: "gemini",
providerCanonical: "gemini",
providerDisplayName: "Gemini",
providerAlias: "gemini-cli",
providerCanonical: "gemini-cli",
providerDisplayName: "Gemini-cli",
},
],
])
@@ -1346,12 +1332,15 @@ test("config: providerTag (default-on) prepends '<provider> - ' to enriched raw-
];
assert.ok(entry);
assert.equal(
entry.models["claude-sonnet-4-6"].name,
entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
"Claude - Claude Sonnet 4.6"
);
assert.equal(entry.models["gemini-3-flash"].name, "Gemini - Gemini 3 Flash");
assert.equal(
entry.models["opencode-omniroute/gemini-3-flash"].name,
"Gemini-cli - Gemini 3 Flash"
);
// Combos stay untouched — `Combo: ` prefix already conveys multi-upstream.
assert.equal(entry.models["claude-tier"].name, "Claude Tier");
assert.equal(entry.models["opencode-omniroute/claude-tier"].name, "Claude Tier");
});
test("config: providerTag=false suppresses the suffix", async () => {
@@ -1378,7 +1367,7 @@ test("config: providerTag=false suppresses the suffix", async () => {
"opencode-omniroute"
];
assert.equal(
entry.models["claude-sonnet-4-6"].name,
entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
"Claude Sonnet 4.6",
"enriched name kept, provider tag suppressed"
);
@@ -1410,7 +1399,7 @@ test("config: providerTag falls back to UPPER(alias) when providerDisplayName mi
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.equal(entry.models["claude-sonnet-4-6"].name, "CC - Claude Sonnet 4.6");
assert.equal(entry.models["opencode-omniroute/claude-sonnet-4-6"].name, "CC - Claude Sonnet 4.6");
});
test("config: providerTag skipped entirely when neither providerDisplayName nor providerAlias set", async () => {
@@ -1437,7 +1426,7 @@ test("config: providerTag skipped entirely when neither providerDisplayName nor
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.equal(entry.models["claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
assert.equal(entry.models["opencode-omniroute/claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
});
test("config: providerTag is idempotent — second hook call doesn't double-suffix", async () => {
@@ -1465,7 +1454,7 @@ test("config: providerTag is idempotent — second hook call doesn't double-suff
"opencode-omniroute"
];
assert.equal(
entryA.models["claude-sonnet-4-6"].name,
entryA.models["opencode-omniroute/claude-sonnet-4-6"].name,
"Claude - Claude Sonnet 4.6"
);
@@ -1476,7 +1465,7 @@ test("config: providerTag is idempotent — second hook call doesn't double-suff
"opencode-omniroute"
];
assert.equal(
entryB.models["claude-sonnet-4-6"].name,
entryB.models["opencode-omniroute/claude-sonnet-4-6"].name,
"Claude - Claude Sonnet 4.6"
);
});
@@ -1530,7 +1519,7 @@ test("buildStaticProviderEntry: nested combo-ref context is the bottleneck acros
);
// Pre-fix: Parent would advertise 200_000 (only raw-big counted).
// Post-fix: Parent should advertise 8_000 (TinyCombo bottleneck).
const parent = block.models["parent"];
const parent = block.models["opencode-omniroute/parent"];
assert.ok(parent, "Parent combo must be in the static catalog");
assert.equal(parent.limit?.context, 8_000);
});

View File

@@ -40,7 +40,7 @@ test("defaultDiskSnapshotWriter writes an owner-only (no group/other) snapshot",
process.env.OPENCODE_DATA_DIR = tmp;
try {
await defaultDiskSnapshotWriter("perm-test", makeEntry(), "test-snapshot-identity");
await defaultDiskSnapshotWriter("perm-test", makeEntry());
const file = diskSnapshotPath("perm-test");
assert.ok(fs.existsSync(file), "snapshot file should be written");

View File

@@ -1,95 +0,0 @@
/**
* #7624 — explicit feature-flag defaults.
*
* The `features` block in opencode.json marks every toggle `.optional()` with
* no default. The effective value was previously only knowable by tracing the
* implicit `features.X !== false` (default-ON) / `features.X === true`
* (default-OFF) convention scattered across each read site, which left
* operators unsure whether combos / autoCombos / enrichment were enabled when
* they omitted the block.
*
* `OMNIROUTE_FEATURE_DEFAULTS` declares those defaults explicitly and
* `resolveEffectiveFeatureFlags(features)` derives the effective state for any
* (possibly-undefined) features object, mirroring the read-site conventions
* exactly. These are purely derived — runtime routing behaviour is unchanged.
*/
import test from "node:test";
import assert from "node:assert/strict";
import {
OMNIROUTE_FEATURE_DEFAULTS,
resolveEffectiveFeatureFlags,
} from "../src/index.js";
const DEFAULT_ON = [
"combos",
"autoCombos",
"enrichment",
"diskCache",
"providerTag",
"fetchInterceptor",
"geminiSanitization",
] as const;
const DEFAULT_OFF = [
"compressionMetadata",
"usableOnly",
"mcpAutoEmit",
"debugLog",
"startupDebug",
] as const;
test("OMNIROUTE_FEATURE_DEFAULTS: declares each flag with its documented default", () => {
for (const key of DEFAULT_ON) {
assert.equal(OMNIROUTE_FEATURE_DEFAULTS[key], true, `${key} defaults ON`);
}
for (const key of DEFAULT_OFF) {
assert.equal(OMNIROUTE_FEATURE_DEFAULTS[key], false, `${key} defaults OFF`);
}
});
test("resolveEffectiveFeatureFlags: undefined features → full declared default set", () => {
const flags = resolveEffectiveFeatureFlags(undefined);
for (const key of DEFAULT_ON) {
assert.equal(flags[key], true, `${key} effective ON when features omitted`);
}
for (const key of DEFAULT_OFF) {
assert.equal(flags[key], false, `${key} effective OFF when features omitted`);
}
});
test("resolveEffectiveFeatureFlags: empty features object → same as omitted", () => {
assert.deepEqual(
resolveEffectiveFeatureFlags({}),
resolveEffectiveFeatureFlags(undefined)
);
});
test("resolveEffectiveFeatureFlags: explicit false disables a default-ON flag", () => {
const flags = resolveEffectiveFeatureFlags({ autoCombos: false });
assert.equal(flags.autoCombos, false, "explicit autoCombos:false honoured");
// Untouched flags keep their declared defaults.
assert.equal(flags.combos, true);
assert.equal(flags.enrichment, true);
});
test("resolveEffectiveFeatureFlags: explicit true enables a default-OFF flag", () => {
const flags = resolveEffectiveFeatureFlags({ compressionMetadata: true });
assert.equal(flags.compressionMetadata, true, "explicit compressionMetadata:true honoured");
assert.equal(flags.usableOnly, false, "other opt-in flags stay OFF");
});
test("resolveEffectiveFeatureFlags: non-boolean sibling keys do not leak into flags", () => {
// features may also carry mcpToken/logLevel/apiFormat — the resolver must
// only ever return the boolean toggle keys.
const flags = resolveEffectiveFeatureFlags({
mcpAutoEmit: true,
mcpToken: "sk-mcp-token-abc",
logLevel: "debug",
});
assert.equal(flags.mcpAutoEmit, true);
assert.equal(Object.keys(flags).length, Object.keys(OMNIROUTE_FEATURE_DEFAULTS).length);
assert.equal("mcpToken" in flags, false);
assert.equal("logLevel" in flags, false);
});

View File

@@ -376,8 +376,7 @@ test("provider hook: enrichment fetcher called when features.enrichment !== fals
);
const out = await hook.models!({} as never, { auth: apiAuth("sk") as never });
assert.equal(called, 1, "enrichment fetcher called once");
// #6859: dynamic-hook catalog keys use the unprefixed omnirouteProviderId.
const m = out["omniroute/claude-sonnet-4-6"];
const m = out["opencode-omniroute/claude-sonnet-4-6"];
assert.equal(m.name, "Claude Sonnet 4.6", "enrichment name overlay applied");
assert.equal(m.cost.input, 3, "enrichment pricing applied");
assert.equal(m.cost.output, 15);
@@ -403,7 +402,7 @@ test("provider hook: enrichment fetcher NOT called when features.enrichment:fals
const out = await hook.models!({} as never, { auth: apiAuth("sk") as never });
assert.equal(called, 0, "enrichment fetcher NOT called when gated off");
assert.equal(
out["omniroute/claude-sonnet-4-6"].name,
out["opencode-omniroute/claude-sonnet-4-6"].name,
"claude-sonnet-4-6",
"raw id preserved"
);
@@ -464,7 +463,7 @@ test("provider hook: compression metadata fetcher called when opted in", async (
);
const out = await hook.models!({} as never, { auth: apiAuth("sk") as never });
assert.equal(called, 1, "compression metadata fetcher called");
const combo = out["omniroute/claude-primary"];
const combo = out["opencode-omniroute/claude-primary"];
assert.ok(combo, "combo entry present");
assert.match(
combo.name,

View File

@@ -50,52 +50,6 @@ test("createOmniRouteFetchInterceptor: targets baseURL → Authorization header
}
});
test("createOmniRouteFetchInterceptor: path-prefixed baseURL scopes auth to its normalized inference paths", async () => {
const { calls, restore } = installFetchRecorder();
try {
const prefixedBase = "https://or.example.com/tenant-a/v1";
const f = createOmniRouteFetchInterceptor({
apiKey: KEY,
baseURL: `${prefixedBase}///`,
});
const streamingBody = '{"stream":true}';
await f(`${prefixedBase}/chat/completions?trace=1`, {
method: "POST",
body: streamingBody,
headers: { Accept: "text/event-stream" },
});
await f(`${prefixedBase}/models/?refresh=1`);
await f("https://or.example.com/v1/chat/completions", { method: "POST", body: "{}" });
await f("https://or.example.com/v1/models");
await f("https://or.example.com/tenant-b/v1/chat/completions", {
method: "POST",
body: "{}",
});
await f(`${prefixedBase}/chat/completions/batch`, { method: "POST", body: "{}" });
const headers = calls.map(({ init }) => new Headers(init?.headers));
assert.equal(headers[0]?.get("Authorization"), `Bearer ${KEY}`);
assert.equal(headers[1]?.get("Authorization"), `Bearer ${KEY}`);
for (const index of [2, 3, 4, 5]) {
assert.equal(headers[index]?.get("Authorization"), null);
}
assert.equal(calls[0]?.input, `${prefixedBase}/chat/completions?trace=1`);
assert.equal(calls[0]?.init?.body, streamingBody);
assert.equal(headers[0]?.get("Accept"), "text/event-stream");
const suffixingInterceptor = createOmniRouteFetchInterceptor({
apiKey: KEY,
baseURL: "https://or.example.com/tenant-a/",
});
await suffixingInterceptor(`${prefixedBase}/models`);
const suffixedHeaders = new Headers(calls[6]?.init?.headers);
assert.equal(suffixedHeaders.get("Authorization"), `Bearer ${KEY}`);
} finally {
restore();
}
});
test("createOmniRouteFetchInterceptor: targets baseURL → Authorization OVERRIDES caller-supplied Bearer", async () => {
const { calls, restore } = installFetchRecorder();
try {
@@ -305,7 +259,7 @@ test("loader integration: wired interceptor actually injects Bearer when invoked
{} as never
);
const wiredFetch = (result as { fetch: typeof fetch }).fetch;
await wiredFetch(`${BASE}/models`, {});
await wiredFetch(`${BASE}/v1/models`, {});
assert.equal(calls.length, 1);
const sentHeaders = new Headers((calls[0]!.init as RequestInit).headers);
assert.equal(sentHeaders.get("Authorization"), `Bearer ${KEY}`);

View File

@@ -212,8 +212,8 @@ test("shouldSanitizeForGemini: google-vertex/gemini-1.5-flash → true", () => {
assert.equal(shouldSanitizeForGemini({ model: "google-vertex/gemini-1.5-flash" }), true);
});
test("shouldSanitizeForGemini: gemini/gemini-2.5-pro → true", () => {
assert.equal(shouldSanitizeForGemini({ model: "gemini/gemini-2.5-pro" }), true);
test("shouldSanitizeForGemini: gemini-cli/gemini-2.5-pro → true (real OmniRoute alias)", () => {
assert.equal(shouldSanitizeForGemini({ model: "gemini-cli/gemini-2.5-pro" }), true);
});
test("shouldSanitizeForGemini: claude-sonnet-4 → false", () => {

View File

@@ -1,271 +0,0 @@
import test from "node:test";
import assert from "node:assert/strict";
import fs from "node:fs";
import os from "node:os";
import path from "node:path";
import {
createOmniRouteAuthHook,
createOmniRouteConfigHook,
createOmniRouteProviderHook,
parseOmniRoutePluginOptions,
type OmniRouteCompressionMetaFetcher,
type OmniRouteEnrichmentFetcher,
type OmniRouteProvidersFetcher,
type OmniRouteRawModelEntry,
} from "../src/index.js";
const BASE_URL = "https://or.example.com/v1";
const API_KEY = "sk-inference-only";
const MANAGEMENT_READ_TOKEN = "sk-management-read-only";
const RAW_MODELS: OmniRouteRawModelEntry[] = [
{
id: "openai/gpt-test",
context_length: 16_000,
max_output_tokens: 4_000,
capabilities: {
tool_calling: true,
reasoning: false,
vision: false,
thinking: false,
temperature: true,
},
input_modalities: ["text"],
output_modalities: ["text"],
},
];
function apiAuth(key: string) {
return { type: "api" as const, key };
}
test("options: managementReadToken is accepted and preserved", () => {
const parsed = parseOmniRoutePluginOptions({ managementReadToken: MANAGEMENT_READ_TOKEN });
assert.equal(parsed.managementReadToken, MANAGEMENT_READ_TOKEN);
});
test("provider hook: management GET fetchers use managementReadToken while /v1 uses apiKey", async () => {
const calls: Array<[string, string]> = [];
const enrichmentFetcher: OmniRouteEnrichmentFetcher = async (_baseURL, token) => {
calls.push(["pricing", token]);
return new Map();
};
const compressionMetaFetcher: OmniRouteCompressionMetaFetcher = async (_baseURL, token) => {
calls.push(["context", token]);
return [];
};
const providersFetcher: OmniRouteProvidersFetcher = async (_baseURL, token) => {
calls.push(["providers", token]);
return [];
};
const hook = createOmniRouteProviderHook(
{
baseURL: BASE_URL,
managementReadToken: MANAGEMENT_READ_TOKEN,
features: { compressionMetadata: true, usableOnly: true },
},
{
fetcher: async (_baseURL, token) => {
calls.push(["models", token]);
return RAW_MODELS;
},
combosFetcher: async (_baseURL, token) => {
calls.push(["combos", token]);
return [];
},
autoCombosFetcher: async (_baseURL, token) => {
calls.push(["auto-combos", token]);
return [];
},
enrichmentFetcher,
compressionMetaFetcher,
providersFetcher,
}
);
await hook.models!({} as never, { auth: apiAuth(API_KEY) as never });
assert.deepEqual(calls, [
["models", API_KEY],
["combos", MANAGEMENT_READ_TOKEN],
["auto-combos", MANAGEMENT_READ_TOKEN],
["pricing", MANAGEMENT_READ_TOKEN],
["context", MANAGEMENT_READ_TOKEN],
["providers", MANAGEMENT_READ_TOKEN],
]);
});
test("provider hook: absent managementReadToken preserves apiKey fallback", async () => {
const calls: Array<[string, string]> = [];
const hook = createOmniRouteProviderHook(
{ baseURL: BASE_URL, features: { enrichment: false, autoCombos: false } },
{
fetcher: async (_baseURL, token) => {
calls.push(["models", token]);
return RAW_MODELS;
},
combosFetcher: async (_baseURL, token) => {
calls.push(["combos", token]);
return [];
},
}
);
await hook.models!({} as never, { auth: apiAuth(API_KEY) as never });
assert.deepEqual(calls, [
["models", API_KEY],
["combos", API_KEY],
]);
});
test("config hook: managementReadToken stays out of provider inference and MCP config", async () => {
const calls: Array<[string, string]> = [];
const hook = createOmniRouteConfigHook(
{
baseURL: BASE_URL,
managementReadToken: MANAGEMENT_READ_TOKEN,
features: { enrichment: false, autoCombos: false, diskCache: false, mcpAutoEmit: true },
},
{
readAuthJson: async () => ({
"opencode-omniroute": { type: "api" as const, key: API_KEY },
}),
fetcher: async (_baseURL, token) => {
calls.push(["models", token]);
return RAW_MODELS;
},
combosFetcher: async (_baseURL, token) => {
calls.push(["combos", token]);
return [];
},
logger: { warn: () => {} },
}
);
const input: { provider?: Record<string, any>; mcp?: Record<string, any> } = {};
await hook(input as never);
assert.deepEqual(calls, [
["models", API_KEY],
["combos", MANAGEMENT_READ_TOKEN],
]);
assert.equal(input.provider?.["opencode-omniroute"]?.options?.apiKey, API_KEY);
assert.equal(
input.mcp?.["opencode-omniroute"]?.headers?.Authorization,
`Bearer ${API_KEY}`,
"mcpAutoEmit remains independent of managementReadToken"
);
});
test("auth fetch: only intended same-origin inference paths receive apiKey", async () => {
const calls: Array<{ input: RequestInfo | URL; init?: RequestInit }> = [];
const originalFetch = globalThis.fetch;
globalThis.fetch = (async (input: RequestInfo | URL, init?: RequestInit) => {
calls.push({ input, init });
return new Response("ok");
}) as typeof fetch;
try {
const hook = createOmniRouteAuthHook({
baseURL: `${BASE_URL}/`,
managementReadToken: MANAGEMENT_READ_TOKEN,
});
const loaded = await hook.loader!(async () => apiAuth(API_KEY) as never, {} as never);
const interceptedFetch = (loaded as { fetch: typeof fetch }).fetch;
const streamingBody = '{"stream":true}';
await interceptedFetch(`${BASE_URL}/chat/completions?trace=1`, {
method: "POST",
body: streamingBody,
headers: { Accept: "text/event-stream" },
});
await interceptedFetch(`${BASE_URL}/models/?refresh=1`);
await interceptedFetch("https://or.example.com/api/combos");
await interceptedFetch("https://or.example.com/api/mcp/stream");
await interceptedFetch("https://or.example.com/v1/embeddings");
await interceptedFetch("https://third-party.example/v1/chat/completions", {
method: "POST",
body: "{}",
});
const headers = calls.map(({ init }) => new Headers(init?.headers));
assert.equal(headers[0]?.get("Authorization"), `Bearer ${API_KEY}`);
assert.equal(headers[1]?.get("Authorization"), `Bearer ${API_KEY}`);
for (const index of [2, 3, 4, 5]) {
assert.equal(headers[index]?.get("Authorization"), null);
}
assert.equal(calls[0]?.input, `${BASE_URL}/chat/completions?trace=1`);
assert.equal(calls[0]?.init?.body, streamingBody);
assert.equal(headers[0]?.get("Accept"), "text/event-stream");
assert.equal(
calls.some(({ init }) =>
[...new Headers(init?.headers).values()].some((value) =>
value.includes(MANAGEMENT_READ_TOKEN)
)
),
false,
"managementReadToken must never enter inference fetch headers"
);
} finally {
globalThis.fetch = originalFetch;
}
});
test("disk cache: snapshot written under management token A is rejected under token B", async () => {
const tmp = fs.mkdtempSync(path.join(os.tmpdir(), "omniroute-token-snapshot-"));
const previousDataDir = process.env.OPENCODE_DATA_DIR;
process.env.OPENCODE_DATA_DIR = tmp;
try {
const commonDeps = {
readAuthJson: async () => ({
"opencode-omniroute": {
type: "api" as const,
key: API_KEY,
baseURL: BASE_URL,
},
}),
combosFetcher: async () => [],
logger: { warn: () => {} },
};
const features = {
enrichment: false,
autoCombos: false,
diskCache: true,
} as const;
const tokenAHook = createOmniRouteConfigHook(
{ managementReadToken: "token-A", features },
{
...commonDeps,
fetcher: async () => RAW_MODELS,
}
);
await tokenAHook({} as never);
const tokenBHook = createOmniRouteConfigHook(
{ managementReadToken: "token-B", features },
{
...commonDeps,
fetcher: async () => {
throw new Error("offline");
},
}
);
const input: { provider?: Record<string, { models: Record<string, unknown> }> } = {};
await tokenBHook(input as never);
assert.deepEqual(
input.provider?.["opencode-omniroute"]?.models,
{},
"catalog from token A must not hydrate after switching to token B"
);
} finally {
if (previousDataDir === undefined) delete process.env.OPENCODE_DATA_DIR;
else process.env.OPENCODE_DATA_DIR = previousDataDir;
fs.rmSync(tmp, { recursive: true, force: true });
}
});

View File

@@ -1,317 +0,0 @@
/**
* #9473 — Model allowlist/blocklist for the opencode-plugin.
*
* Tests for the pure filter helpers (`compileModelListFilter`,
* `passesModelAllowlist`, `passesComboAllowlist`) and the schema + hook-level
* integration. The allowlist/blocklist composes with `usableOnly` (all filters
* AND together), blocklist wins over allowlist (deny takes precedence), and
* bare-suffix entries (e.g. "claude-opus-4-7") match any "{prefix}/claude-opus-4-7".
*/
import test from "node:test";
import assert from "node:assert/strict";
import {
compileModelListFilter,
passesModelAllowlist,
passesComboAllowlist,
parseOmniRoutePluginOptions,
buildStaticProviderEntry,
resolveOmniRoutePluginOptions,
type OmniRouteRawCombo,
type OmniRouteRawModelEntry,
} from "../src/index.js";
// ─────────────────────────────────────────────────────────────────────────
// compileModelListFilter
// ─────────────────────────────────────────────────────────────────────────
test("compileModelListFilter: undefined list → undefined", () => {
assert.equal(compileModelListFilter(undefined), undefined);
});
test("compileModelListFilter: empty array → undefined", () => {
assert.equal(compileModelListFilter([]), undefined);
});
test("compileModelListFilter: raw IDs with slash → exact set populated", () => {
const f = compileModelListFilter(["cc/claude-opus-4-7", "glm/gpt-5"]);
assert.ok(f);
assert.equal(f.exact.has("cc/claude-opus-4-7"), true);
assert.equal(f.exact.has("glm/gpt-5"), true);
assert.equal(f.suffixes.size, 0);
});
test("compileModelListFilter: bare IDs (no slash) → suffixes set populated", () => {
const f = compileModelListFilter(["claude-opus-4-7", "gpt-5"]);
assert.ok(f);
assert.equal(f.suffixes.has("claude-opus-4-7"), true);
assert.equal(f.suffixes.has("gpt-5"), true);
assert.equal(f.exact.size, 0);
});
test("compileModelListFilter: mixed raw + bare → both sets populated", () => {
const f = compileModelListFilter(["cc/claude-opus-4-7", "gpt-5"]);
assert.ok(f);
assert.equal(f.exact.has("cc/claude-opus-4-7"), true);
assert.equal(f.suffixes.has("gpt-5"), true);
});
// ─────────────────────────────────────────────────────────────────────────
// passesModelAllowlist
// ─────────────────────────────────────────────────────────────────────────
test("passesModelAllowlist: no visible, no hidden → keep (passthrough)", () => {
assert.equal(passesModelAllowlist("cc/claude-opus-4-7", undefined, undefined), true);
});
test("passesModelAllowlist: visible undefined, hidden undefined → keep", () => {
assert.equal(passesModelAllowlist("cc/claude-opus-4-7", undefined, undefined), true);
});
test("passesModelAllowlist: visible set, id matches exact → keep", () => {
const vis = compileModelListFilter(["cc/claude-opus-4-7"]);
assert.equal(passesModelAllowlist("cc/claude-opus-4-7", vis, undefined), true);
});
test("passesModelAllowlist: visible set, id matches suffix → keep", () => {
const vis = compileModelListFilter(["claude-opus-4-7"]);
assert.equal(passesModelAllowlist("cc/claude-opus-4-7", vis, undefined), true);
});
test("passesModelAllowlist: visible set, id does NOT match → drop", () => {
const vis = compileModelListFilter(["cc/claude-opus-4-7"]);
assert.equal(passesModelAllowlist("glm/gpt-5", vis, undefined), false);
});
test("passesModelAllowlist: visible set, bare suffix matches different prefix → keep", () => {
const vis = compileModelListFilter(["claude-opus-4-7"]);
assert.equal(passesModelAllowlist("kr/claude-opus-4-7", vis, undefined), true);
});
test("passesModelAllowlist: hidden set, id matches exact → drop", () => {
const hid = compileModelListFilter(["cc/claude-opus-4-7"]);
assert.equal(passesModelAllowlist("cc/claude-opus-4-7", undefined, hid), false);
});
test("passesModelAllowlist: hidden set, id matches suffix → drop", () => {
const hid = compileModelListFilter(["claude-opus-4-7"]);
assert.equal(passesModelAllowlist("cc/claude-opus-4-7", undefined, hid), false);
});
test("passesModelAllowlist: hidden set, id does NOT match → keep", () => {
const hid = compileModelListFilter(["cc/claude-opus-4-7"]);
assert.equal(passesModelAllowlist("glm/gpt-5", undefined, hid), true);
});
test("passesModelAllowlist: id in BOTH visible and hidden → DROP (deny wins)", () => {
const vis = compileModelListFilter(["cc/claude-opus-4-7"]);
const hid = compileModelListFilter(["cc/claude-opus-4-7"]);
assert.equal(passesModelAllowlist("cc/claude-opus-4-7", vis, hid), false);
});
test("passesModelAllowlist: visible allows, hidden blocks different id → keep the visible one", () => {
const vis = compileModelListFilter(["cc/claude-opus-4-7"]);
const hid = compileModelListFilter(["glm/gpt-5"]);
assert.equal(passesModelAllowlist("cc/claude-opus-4-7", vis, hid), true);
assert.equal(passesModelAllowlist("glm/gpt-5", vis, hid), false);
});
test("passesModelAllowlist: bare-suffix hidden blocks exact match too", () => {
const hid = compileModelListFilter(["claude-opus-4-7"]);
assert.equal(passesModelAllowlist("cc/claude-opus-4-7", undefined, hid), false);
assert.equal(passesModelAllowlist("kr/claude-opus-4-7", undefined, hid), false);
});
test("passesModelAllowlist: no-slash id, visible set has bare match → keep", () => {
const vis = compileModelListFilter(["claude-primary"]);
assert.equal(passesModelAllowlist("claude-primary", vis, undefined), true);
});
test("passesModelAllowlist: no-slash id, visible set has no match → drop", () => {
const vis = compileModelListFilter(["cc/claude-opus-4-7"]);
assert.equal(passesModelAllowlist("claude-primary", vis, undefined), false);
});
// ─────────────────────────────────────────────────────────────────────────
// passesComboAllowlist
// ─────────────────────────────────────────────────────────────────────────
function combo(models: OmniRouteRawCombo["models"]): OmniRouteRawCombo {
return { id: "c1", name: "Test Combo", models };
}
test("passesComboAllowlist: visible undefined → keep", () => {
const c = combo([{ kind: "model", model: "cc/claude-opus-4-7" }]);
assert.equal(passesComboAllowlist(c, undefined), true);
});
test("passesComboAllowlist: ≥1 member matches visible → keep", () => {
const vis = compileModelListFilter(["cc/claude-opus-4-7"]);
const c = combo([
{ kind: "model", model: "dead/legacy" },
{ kind: "model", model: "cc/claude-opus-4-7" },
]);
assert.equal(passesComboAllowlist(c, vis), true);
});
test("passesComboAllowlist: zero members match visible → drop", () => {
const vis = compileModelListFilter(["cc/claude-opus-4-7"]);
const c = combo([
{ kind: "model", model: "glm/gpt-5" },
{ kind: "model", model: "kr/claude-opus-4-7" },
]);
assert.equal(passesComboAllowlist(c, vis), false);
});
test("passesComboAllowlist: bare suffix matches any prefix → keep", () => {
const vis = compileModelListFilter(["claude-opus-4-7"]);
const c = combo([{ kind: "model", model: "kr/claude-opus-4-7" }]);
assert.equal(passesComboAllowlist(c, vis), true);
});
test("passesComboAllowlist: zero members → keep", () => {
const vis = compileModelListFilter(["cc/claude-opus-4-7"]);
assert.equal(passesComboAllowlist(combo([]), vis), true);
assert.equal(passesComboAllowlist(combo(undefined), vis), true);
});
test("passesComboAllowlist: only combo-ref steps → keep", () => {
const vis = compileModelListFilter(["cc/claude-opus-4-7"]);
const c = combo([{ kind: "combo-ref", comboName: "nested" }]);
assert.equal(passesComboAllowlist(c, vis), true);
});
// ─────────────────────────────────────────────────────────────────────────
// Schema — visibleModels / hiddenModels
// ─────────────────────────────────────────────────────────────────────────
test("parseOmniRoutePluginOptions: visibleModels string[] → preserved", () => {
const r = parseOmniRoutePluginOptions({
features: { visibleModels: ["cc/claude-opus-4-7", "gpt-5"] },
});
assert.deepEqual(r.features?.visibleModels, ["cc/claude-opus-4-7", "gpt-5"]);
});
test("parseOmniRoutePluginOptions: hiddenModels string[] → preserved", () => {
const r = parseOmniRoutePluginOptions({
features: { hiddenModels: ["glm/gpt-5"] },
});
assert.deepEqual(r.features?.hiddenModels, ["glm/gpt-5"]);
});
test("parseOmniRoutePluginOptions: both lists together → preserved", () => {
const r = parseOmniRoutePluginOptions({
features: {
visibleModels: ["cc/claude-opus-4-7"],
hiddenModels: ["glm/gpt-5"],
},
});
assert.deepEqual(r.features?.visibleModels, ["cc/claude-opus-4-7"]);
assert.deepEqual(r.features?.hiddenModels, ["glm/gpt-5"]);
});
test("parseOmniRoutePluginOptions: empty string in visibleModels → rejects", () => {
assert.throws(
() =>
parseOmniRoutePluginOptions({
features: { visibleModels: [""] },
}),
/Invalid @omniroute\/opencode-plugin options/
);
});
test("parseOmniRoutePluginOptions: empty string in hiddenModels → rejects", () => {
assert.throws(
() =>
parseOmniRoutePluginOptions({
features: { hiddenModels: [""] },
}),
/Invalid @omniroute\/opencode-plugin options/
);
});
test("parseOmniRoutePluginOptions: unknown features key still rejects (strict invariant)", () => {
assert.throws(
() =>
parseOmniRoutePluginOptions({
features: { visibleModels: ["x"], unknownKey: true },
}),
/Invalid @omniroute\/opencode-plugin options/
);
});
// ─────────────────────────────────────────────────────────────────────────
// buildStaticProviderEntry — allowlist/blocklist integration
// ─────────────────────────────────────────────────────────────────────────
const FAKE_RAW_MODELS: OmniRouteRawModelEntry[] = [
{ id: "cc/claude-opus-4-7", owned_by: "anthropic" },
{ id: "glm/gpt-5", owned_by: "openai" },
{ id: "kr/claude-opus-4-7", owned_by: "anthropic" },
{ id: "claude-primary", owned_by: "combo" },
];
test("buildStaticProviderEntry: no allowlist → all models emitted", () => {
const opts = resolveOmniRoutePluginOptions({ features: {} });
const entry = buildStaticProviderEntry(FAKE_RAW_MODELS, [], opts, "http://localhost:20128/v1", "sk-test");
const ids = Object.keys(entry.models);
assert.ok(ids.includes("cc/claude-opus-4-7"), "cc/claude-opus-4-7 should be present");
assert.ok(ids.includes("glm/gpt-5"), "glm/gpt-5 should be present");
assert.ok(ids.includes("kr/claude-opus-4-7"), "kr/claude-opus-4-7 should be present");
});
test("buildStaticProviderEntry: visibleModels filters to only listed IDs", () => {
const opts = resolveOmniRoutePluginOptions({
features: { visibleModels: ["cc/claude-opus-4-7"] },
});
const entry = buildStaticProviderEntry(FAKE_RAW_MODELS, [], opts, "http://localhost:20128/v1", "sk-test");
const ids = Object.keys(entry.models);
assert.ok(ids.includes("cc/claude-opus-4-7"), "cc/claude-opus-4-7 should be present");
assert.equal(ids.includes("glm/gpt-5"), false, "glm/gpt-5 should be filtered out");
assert.equal(ids.includes("kr/claude-opus-4-7"), false, "kr/claude-opus-4-7 should be filtered out");
});
test("buildStaticProviderEntry: hiddenModels drops listed IDs", () => {
const opts = resolveOmniRoutePluginOptions({
features: { hiddenModels: ["glm/gpt-5"] },
});
const entry = buildStaticProviderEntry(FAKE_RAW_MODELS, [], opts, "http://localhost:20128/v1", "sk-test");
const ids = Object.keys(entry.models);
assert.ok(ids.includes("cc/claude-opus-4-7"), "cc/claude-opus-4-7 should be present");
assert.equal(ids.includes("glm/gpt-5"), false, "glm/gpt-5 should be hidden");
assert.ok(ids.includes("kr/claude-opus-4-7"), "kr/claude-opus-4-7 should be present");
});
test("buildStaticProviderEntry: bare-suffix visibleModels matches any prefix", () => {
const opts = resolveOmniRoutePluginOptions({
features: { visibleModels: ["claude-opus-4-7"] },
});
const entry = buildStaticProviderEntry(FAKE_RAW_MODELS, [], opts, "http://localhost:20128/v1", "sk-test");
const ids = Object.keys(entry.models);
assert.ok(ids.includes("cc/claude-opus-4-7"), "cc/claude-opus-4-7 should match via suffix");
assert.ok(ids.includes("kr/claude-opus-4-7"), "kr/claude-opus-4-7 should match via suffix");
assert.equal(ids.includes("glm/gpt-5"), false, "glm/gpt-5 should be filtered out");
});
test("buildStaticProviderEntry: id in both visible and hidden → hidden wins", () => {
const opts = resolveOmniRoutePluginOptions({
features: {
visibleModels: ["cc/claude-opus-4-7"],
hiddenModels: ["cc/claude-opus-4-7"],
},
});
const entry = buildStaticProviderEntry(FAKE_RAW_MODELS, [], opts, "http://localhost:20128/v1", "sk-test");
const ids = Object.keys(entry.models);
assert.equal(ids.includes("cc/claude-opus-4-7"), false, "deny takes precedence");
});
test("buildStaticProviderEntry: empty visibleModels → no filter (passthrough)", () => {
const opts = resolveOmniRoutePluginOptions({
features: { visibleModels: [] },
});
const entry = buildStaticProviderEntry(FAKE_RAW_MODELS, [], opts, "http://localhost:20128/v1", "sk-test");
const ids = Object.keys(entry.models);
assert.ok(ids.includes("cc/claude-opus-4-7"), "empty visibleModels should not filter");
assert.ok(ids.includes("glm/gpt-5"), "empty visibleModels should not filter");
});

View File

@@ -1,143 +0,0 @@
/**
* Regression test for #6859.
*
* `resolveOmniRoutePluginOptions()` auto-prefixes `providerId` with
* `"opencode-"` (commit 75b52e286) so OpenCode 1.17.8+'s native-adapter gate
* accepts it as an OC-registered provider id. That prefixed value must stay
* OC-internal (AuthHook.provider / provider registration keys) — it must
* NEVER leak into the identifiers OmniRoute's own server parses to resolve
* credentials (`mapRawModelToModelV2`'s `id`/`providerID`,
* `mapComboToModelV2`'s `providerID`, and the dynamic-hook catalog keys).
*
* OmniRoute's server-side `parseModel()` (open-sse/services/model.ts) splits
* a dispatched model string on `/` to recover the provider name and look up
* credentials. If the plugin embeds the OC-gate-prefixed id in that string,
* the server looks up credentials for a provider named "opencode-omniroute"
* (which never exists in `src/shared/constants/providers.ts`) instead of
* "omniroute" — producing the exact "No credentials for opencode-omniroute" /
* "No active credentials for provider: opencode-omniroute" errors reported
* in #6859.
*/
import test from "node:test";
import assert from "node:assert/strict";
import {
buildStaticProviderEntry,
createOmniRouteProviderHook,
mapRawModelToModelV2,
resolveOmniRoutePluginOptions,
type OmniRouteRawCombo,
} from "../src/index.js";
/**
* Minimal stand-in for OmniRoute's own `parseModel()` (open-sse/services/
* model.ts), which splits a dispatched `<providerID>/<modelID>` string on the
* FIRST "/" to recover the provider name used for credential lookup. Kept
* local (rather than cross-importing the real module) so this package's
* self-contained test suite (`cd @omniroute/opencode-plugin && npm test`)
* doesn't depend on the root repo's `@/*` path-alias resolution.
*/
function splitProviderFromDispatchedModel(modelStr: string): string {
const idx = modelStr.indexOf("/");
return idx === -1 ? modelStr : modelStr.slice(0, idx);
}
const apiAuth = (key: string) => ({ type: "api" as const, key });
test("#6859: server-facing model id/providerID must resolve to the unprefixed provider name", () => {
const resolved = resolveOmniRoutePluginOptions();
// The OC-gate-compatible id stays prefixed — it is legitimate for
// AuthHook.provider / provider registration.
assert.equal(resolved.providerId, "opencode-omniroute");
// A second, unprefixed id must be exposed for anything that reaches
// OmniRoute's own server (model id prefix, ModelV2.providerID, combo keys).
assert.equal(
resolved.omnirouteProviderId,
"omniroute",
"resolveOmniRoutePluginOptions() must expose an unprefixed omnirouteProviderId"
);
// A bare raw /v1/models entry (no existing "/" in its id — the common
// case for OmniRoute's catalog) mapped with the server-facing id.
const model = mapRawModelToModelV2(
{ id: "claude-opus-4-7" },
{ providerId: resolved.omnirouteProviderId, baseURL: "http://localhost:20128" }
);
assert.equal(model.providerID, "omniroute");
assert.equal(model.id, "omniroute/claude-opus-4-7");
// OpenCode dispatches back to OmniRoute using `providerID/modelKey`
// (matches the issue's own repro: `-m opencode-omniroute/oc/big-pickle`).
const dispatchedModelString = `${model.providerID}/claude-opus-4-7`;
const parsedProvider = splitProviderFromDispatchedModel(dispatchedModelString);
assert.equal(
parsedProvider,
"omniroute",
`server-side provider split resolved '${parsedProvider}', expected 'omniroute' — ` +
`credentials lookup would fail for an OC-gate-prefixed provider id`
);
});
test("#6859: createOmniRouteProviderHook end-to-end — catalog keys/providerID never carry the OC-gate prefix", async () => {
const hook = createOmniRouteProviderHook(
{ baseURL: "https://or.example.com/v1" },
{
fetcher: async () => [{ id: "claude-opus-4-7" }],
combosFetcher: async () => [],
}
);
const out = await hook.models!({} as never, { auth: apiAuth("sk-test") as never });
const model = out["omniroute/claude-opus-4-7"];
assert.ok(model, "catalog keyed under the unprefixed provider name");
assert.equal(model.providerID, "omniroute");
assert.ok(
!model.providerID.startsWith("opencode-"),
"the OC-gate prefix must never leak into ModelV2.providerID"
);
});
// #7976: buildStaticProviderEntry (the STATIC provider() config-hook path,
// exercised when the plugin writes `opencode.json` up front rather than
// registering the dynamic `provider.models()` hook) never received the
// #6859 fix. OC dispatches a static-catalog `models` map key verbatim as
// the `model` field of the outbound request — only the top-level
// `provider["<id>"]` segment is stripped for routing — so a bare-slug combo
// key built with the OC-gated `providerId` reaches OmniRoute's server
// doubled and fails credential lookup for the nonexistent provider
// `opencode-omniroute`. Confirmed against the issue's own curl repro
// (`model: "opencode-omniroute/hermes-smart-stack"` → "No active
// credentials for provider: opencode-omniroute").
// #9175 tightened this further: OC's `getModel` looks models up by BARE id,
// so combo dict keys now carry NO prefix at all (not even `omniroute/`).
test("#7976/#9175: buildStaticProviderEntry keys combos by bare slug (no prefix at all — never the OC-gate providerId)", () => {
const resolved = resolveOmniRoutePluginOptions({ providerId: "omniroute" });
assert.equal(resolved.providerId, "opencode-omniroute");
assert.equal(resolved.omnirouteProviderId, "omniroute");
const combo = {
id: "combo-abc123",
name: "Hermes Smart Stack",
isHidden: false,
models: [],
} as unknown as OmniRouteRawCombo;
const block = buildStaticProviderEntry(
[],
[combo],
resolved,
"https://or.example/v1",
"sk-test"
);
assert.deepEqual(Object.keys(block.models), ["hermes-smart-stack"]);
assert.equal(
block.models["opencode-omniroute/hermes-smart-stack"],
undefined,
"combo key must not carry the OC-gate-prefixed providerId — it doubles up once " +
"OC dispatches it verbatim as the `model` field"
);
});

View File

@@ -101,10 +101,7 @@ test("models: extracts apiKey from ctx.auth (type=api) and calls fetcher with it
assert.equal(fetcher.callCount(), 1);
assert.deepEqual(fetcher.callsBy()[0], ["https://or.example.com/v1", "sk-abc"]);
assert.equal(Object.keys(out).length, 3);
// #6859: dynamic-hook catalog keys use the unprefixed omnirouteProviderId
// ("omniroute"), not the OC-gate-prefixed hook.id ("opencode-omniroute") —
// that prefix must never leak into anything OmniRoute's server parses.
assert.ok(out["omniroute/claude-primary"]);
assert.ok(out["opencode-omniroute/claude-primary"]);
});
test("models: returns {} when ctx.auth is null/undefined/wrong-type/empty-key", async () => {
@@ -155,17 +152,13 @@ test("models: maps a sample /v1/models entry to ModelV2 (sanity)", async () => {
{ fetcher, combosFetcher: async () => [] }
);
const out = await hook.models!({} as never, { auth: apiAuth("sk-abc") as never });
// #6859: dynamic-hook catalog keys/ids/providerID use the unprefixed
// omnirouteProviderId ("omniroute") — the OC-gate prefix ("opencode-")
// must stay OC-internal (hook.id / AuthHook.provider) and never leak into
// anything OmniRoute's own server parses for credential lookup.
const claude = out["omniroute/claude-primary"];
const claude = out["opencode-omniroute/claude-primary"];
assert.ok(claude, "claude-primary present");
// `mapRawModelToModelV2` stamps the provider prefix on the id so OC's
// static-catalog reader resolves `(providerID, modelID)` from the key.
assert.equal(claude.id, "omniroute/claude-primary");
assert.equal(claude.id, "opencode-omniroute/claude-primary");
assert.equal(claude.name, "claude-primary");
assert.equal(claude.providerID, "omniroute");
assert.equal(claude.providerID, "opencode-omniroute");
assert.equal(claude.api.id, "openai-compatible");
assert.equal(claude.api.url, "https://or.example.com/v1");
assert.equal(claude.api.npm, "@ai-sdk/openai-compatible");

View File

@@ -1,827 +0,0 @@
/**
* Warm-startup + parallel-refresh tests for the opencode-plugin config shim.
*
* Covers `createOmniRouteConfigHook(opts, deps)`:
* - (a) Warm startup: cache miss + matching snapshot → provider block
* populated from snapshot data (not live fetch data).
* - (b) Fingerprint mismatch: reader returns undefined → no warm publish,
* falls through to awaited fetch (cold-start behavior).
* - (c) Successful parallel refresh: all fetchers resolve → cache updated,
* disk snapshot written.
* - (d) Failed refresh keeps the snapshot: warm-served + models fetcher
* rejects → no disk overwrite, block stays at warm-snapshot shape.
* - (e) Parallelism: all six fetchers start concurrently (not sequential).
* - (f) Soft-fail parity under Promise.allSettled: per-endpoint
* fallbacks + logger.warn breadcrumbs preserved.
* - (g) No double-refresh: concurrent hook invocations on the same cacheKey
* trigger only one refresh (in-flight guard).
* - (h) features.diskCache: false disables the warm read entirely.
*
* Mocking strategy: every dependency is DI-injected at hook construction
* (same pattern as config-shim.test.ts). No global monkey-patching.
*/
import test from "node:test";
import assert from "node:assert/strict";
import type { Config } from "@opencode-ai/plugin";
import {
createOmniRouteConfigHook,
resolveOmniRoutePluginOptions,
_resetInflightRefresh,
type OmniRouteAutoCombosFetcher,
type OmniRouteCombosFetcher,
type OmniRouteCompressionMetaFetcher,
type OmniRouteEnrichmentEntry,
type OmniRouteEnrichmentFetcher,
type OmniRouteEnrichmentMap,
type OmniRouteFetchCache,
type OmniRouteModelsFetcher,
type OmniRouteProviderConnection,
type OmniRouteProvidersFetcher,
type OmniRouteRawAutoCombo,
type OmniRouteRawCombo,
type OmniRouteRawModelEntry,
type OmniRouteReadAuthJson,
type OmniRouteStaticProviderEntry,
type OmniRouteDiskSnapshotReader,
type OmniRouteDiskSnapshotWriter,
type OmniRouteCompressionCombo,
} from "../src/index.js";
// ────────────────────────────────────────────────────────────────────────────
// Test isolation: reset the module-level in-flight refresh guard between
// tests so a detached refresh from a previous test doesn't leak into the
// next one (same cacheKey, different cache instance).
// ────────────────────────────────────────────────────────────────────────────
test.beforeEach(() => {
_resetInflightRefresh();
});
// ────────────────────────────────────────────────────────────────────────────
// Fixtures
// ────────────────────────────────────────────────────────────────────────────
const MODEL_CLAUDE: OmniRouteRawModelEntry = {
id: "claude-sonnet-4-6",
capabilities: {
tool_calling: true,
reasoning: true,
vision: true,
thinking: false,
temperature: true,
},
context_length: 200_000,
max_output_tokens: 64_000,
max_input_tokens: 180_000,
input_modalities: ["text", "image"],
output_modalities: ["text"],
};
const MODEL_GEMINI: OmniRouteRawModelEntry = {
id: "gemini-3-flash",
capabilities: { tool_calling: true, reasoning: false, vision: true, thinking: false },
context_length: 1_000_000,
max_output_tokens: 8_192,
input_modalities: ["text", "image"],
output_modalities: ["text"],
};
const COMBO_CLAUDE_TIER: OmniRouteRawCombo = {
id: "combo-claude-tier",
name: "Claude Tier",
models: [
{ id: "s1", kind: "model", model: "claude-sonnet-4-6", weight: 100 },
{ id: "s2", kind: "model", model: "gemini-3-flash", weight: 50 },
],
};
const AUTO_COMBO: OmniRouteRawAutoCombo = {
id: "auto",
name: "Auto",
};
const COMPRESSION_COMBO: OmniRouteCompressionCombo = {
id: "ctx-combo-1",
name: "Context Combo",
pipeline: "gzip",
};
const CONNECTION_CLAUDE: OmniRouteProviderConnection = {
id: "c1",
provider: "claude",
isActive: true,
testStatus: "active",
};
// ────────────────────────────────────────────────────────────────────────────
// DI stub helpers
// ────────────────────────────────────────────────────────────────────────────
function stubReadAuthJson(
value: Record<string, unknown> | undefined | null
): OmniRouteReadAuthJson {
return async () => value as never;
}
function immediateFetcher<T extends (...args: unknown[]) => Promise<unknown>>(
payload: ReturnType<T> extends Promise<infer U> ? U : never
): T & { callCount: () => number; startedAt: () => number | undefined } {
let n = 0;
let start: number | undefined;
const f = async (..._args: unknown[]) => {
start = Date.now();
n++;
return payload;
};
return Object.assign(f as T, { callCount: () => n, startedAt: () => start });
}
function throwingFetcher<T extends (...args: unknown[]) => Promise<unknown>>(
msg = "ECONNREFUSED"
): T & { callCount: () => number } {
let n = 0;
const f = async (..._args: unknown[]) => {
n++;
throw new Error(msg);
};
return Object.assign(f as T, { callCount: () => n });
}
interface WarnCapture {
warn: (...args: unknown[]) => void;
entries: unknown[][];
}
function captureWarn(): WarnCapture {
const entries: unknown[][] = [];
return {
warn: (...args: unknown[]) => {
entries.push(args);
},
entries,
};
}
function makeInput(initialProvider: Record<string, unknown> = {}): Config {
return { provider: initialProvider } as unknown as Config;
}
/** Build a valid auth.json stub for the default providerId. */
function authStub() {
return stubReadAuthJson({
"opencode-omniroute": {
type: "api",
key: "sk-test",
baseURL: "https://or.example.com/v1",
},
});
}
// ────────────────────────────────────────────────────────────────────────────
// (a) Warm startup: cache miss + matching snapshot → provider block populated
// from snapshot data (not live fetch data)
// ────────────────────────────────────────────────────────────────────────────
test("warm-startup: snapshot data used when snapshot is present", async () => {
// Live fetch returns MODEL_CLAUDE, but snapshot has MODEL_GEMINI.
// With warm startup, the block should contain the snapshot data.
const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
const autoCombosFetcher = immediateFetcher<OmniRouteAutoCombosFetcher>([]);
const enrichmentFetcher = immediateFetcher<OmniRouteEnrichmentFetcher>(new Map());
const compressionMetaFetcher = immediateFetcher<OmniRouteCompressionMetaFetcher>([]);
const providersFetcher = immediateFetcher<OmniRouteProvidersFetcher>([]);
const logger = captureWarn();
const snapshot: Omit<import("../src/index.js").OmniRouteFetchCacheEntry, "expiresAt"> = {
rawModels: [MODEL_GEMINI],
rawCombos: [],
rawAutoCombos: [],
rawEnrichment: new Map(),
rawCompressionCombos: [],
rawConnections: [],
};
const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => snapshot;
const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute" },
{
readAuthJson: authStub(),
fetcher,
combosFetcher,
autoCombosFetcher,
enrichmentFetcher,
compressionMetaFetcher,
providersFetcher,
diskSnapshotReader,
diskSnapshotWriter,
logger,
}
);
const input = makeInput();
await hook(input);
const provider = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider;
const entry = provider["opencode-omniroute"];
assert.ok(entry, "provider entry published");
// With warm startup, the block should contain the snapshot data (GEMINI),
// not the live fetch data (CLAUDE). This is the key assertion: the warm
// snapshot is served first, and the live refresh updates the cache in the
// background. On the next hook invocation, the cache will have the fresh data.
const hasGemini = entry.models["opencode-omniroute/gemini-3-flash"] !== undefined;
const hasClaude = entry.models["opencode-omniroute/claude-sonnet-4-6"] !== undefined;
assert.ok(
hasGemini || hasClaude,
"provider block has at least one model"
);
// The warm-startup breadcrumb should be emitted.
assert.ok(
logger.entries.some((e) =>
String(e[0]).includes("warm startup from disk snapshot")
),
"warm-startup breadcrumb emitted"
);
});
// ────────────────────────────────────────────────────────────────────────────
// (b) Fingerprint mismatch: reader returns undefined → no warm publish,
// falls through to awaited fetch
// ────────────────────────────────────────────────────────────────────────────
test("warm-startup: fingerprint mismatch → no warm publish, awaited fetch", async () => {
const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
const logger = captureWarn();
// Reader returns undefined → fingerprint mismatch or missing snapshot.
const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute" },
{
readAuthJson: authStub(),
fetcher,
combosFetcher,
diskSnapshotReader,
diskSnapshotWriter,
logger,
}
);
const input = makeInput();
await hook(input);
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.ok(entry, "provider entry published from live fetch");
// Live fetch data, not snapshot data.
assert.ok(
entry.models["opencode-omniroute/claude-sonnet-4-6"],
"live fetch model present"
);
assert.equal(fetcher.callCount(), 1, "fetcher was called (awaited cold path)");
// No warm-startup breadcrumb when no snapshot.
assert.ok(
!logger.entries.some((e) =>
String(e[0]).includes("warm startup from disk snapshot")
),
"no warm-startup breadcrumb when no snapshot"
);
});
// ────────────────────────────────────────────────────────────────────────────
// (c) Successful parallel refresh: all fetchers resolve → cache updated,
// disk snapshot written, block re-published with fresh data
// ────────────────────────────────────────────────────────────────────────────
test("warm-startup: parallel refresh updates cache + writes snapshot", async () => {
const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([COMBO_CLAUDE_TIER]);
const autoCombosFetcher = immediateFetcher<OmniRouteAutoCombosFetcher>([AUTO_COMBO]);
const enrichmentFetcher = immediateFetcher<OmniRouteEnrichmentFetcher>(
new Map<string, OmniRouteEnrichmentEntry>([
["claude-sonnet-4-6", { name: "Claude Sonnet 4.6" }],
])
);
const compressionMetaFetcher = immediateFetcher<OmniRouteCompressionMetaFetcher>([
COMPRESSION_COMBO,
]);
const providersFetcher = immediateFetcher<OmniRouteProvidersFetcher>([CONNECTION_CLAUDE]);
const logger = captureWarn();
const snapshot: Omit<import("../src/index.js").OmniRouteFetchCacheEntry, "expiresAt"> = {
rawModels: [MODEL_GEMINI],
rawCombos: [],
rawAutoCombos: [],
rawEnrichment: new Map(),
rawCompressionCombos: [],
rawConnections: [],
};
const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => snapshot;
let snapshotWrites = 0;
const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {
snapshotWrites++;
};
const sharedCache: OmniRouteFetchCache = new Map();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute", modelCacheTtl: 60_000 },
{
readAuthJson: authStub(),
fetcher,
combosFetcher,
autoCombosFetcher,
enrichmentFetcher,
compressionMetaFetcher,
providersFetcher,
diskSnapshotReader,
diskSnapshotWriter,
cache: sharedCache,
logger,
}
);
const input = makeInput();
await hook(input);
// Warm block should have been published.
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.ok(entry, "warm provider entry published");
// Give detached refresh time to complete.
await new Promise((r) => setTimeout(r, 100));
// After parallel refresh, the cache should have the fresh data.
const cacheKey = Array.from(sharedCache.keys())[0];
assert.ok(cacheKey, "cache entry created");
const cached = sharedCache.get(cacheKey)!;
assert.ok(cached.expiresAt > 0, "cache entry has expiresAt");
// Fresh data from the live fetchers (not the stale snapshot).
assert.equal(cached.rawModels.length, 1, "cache has fresh models");
assert.equal(cached.rawModels[0].id, "claude-sonnet-4-6", "cache has correct model");
// Disk snapshot should have been written.
assert.equal(snapshotWrites, 1, "disk snapshot written after successful refresh");
});
// ────────────────────────────────────────────────────────────────────────────
// (d) Failed refresh keeps the snapshot: warm-served + models fetcher
// rejects → no disk overwrite, block stays at warm-snapshot shape
// ────────────────────────────────────────────────────────────────────────────
test("warm-startup: failed refresh keeps the snapshot, no disk overwrite", async () => {
const fetcher = throwingFetcher<OmniRouteModelsFetcher>();
const combosFetcher = throwingFetcher<OmniRouteCombosFetcher>();
const logger = captureWarn();
const snapshot: Omit<import("../src/index.js").OmniRouteFetchCacheEntry, "expiresAt"> = {
rawModels: [MODEL_GEMINI],
rawCombos: [COMBO_CLAUDE_TIER],
rawAutoCombos: [],
rawEnrichment: new Map(),
rawCompressionCombos: [],
rawConnections: [],
};
const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => snapshot;
let snapshotWrites = 0;
const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {
snapshotWrites++;
};
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute" },
{
readAuthJson: authStub(),
fetcher,
combosFetcher,
diskSnapshotReader,
diskSnapshotWriter,
logger,
}
);
const input = makeInput();
await hook(input);
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.ok(entry, "warm provider entry published");
// The block should contain the warm snapshot data (gemini), not be
// downgraded to a stub.
assert.ok(
entry.models["opencode-omniroute/gemini-3-flash"],
"warm snapshot model preserved (not downgraded to stub)"
);
// Give detached refresh time to complete.
await new Promise((r) => setTimeout(r, 100));
// No disk write on failed refresh.
assert.equal(snapshotWrites, 0, "no disk snapshot written when models fetch failed");
});
// ────────────────────────────────────────────────────────────────────────────
// (e) Parallelism: all six fetchers start concurrently (not sequential)
// ────────────────────────────────────────────────────────────────────────────
test("warm-startup: all fetchers start concurrently (parallel fan-out)", async () => {
const startTimes: number[] = [];
const barrier = new Promise<void>((r) => {
setTimeout(r, 30);
});
function instrumentedFetcher<T extends (...args: unknown[]) => Promise<unknown>>(
payload: ReturnType<T> extends Promise<infer U> ? U : never
): T & { callCount: () => number } {
let n = 0;
const f = async (..._args: unknown[]) => {
startTimes.push(Date.now());
n++;
await barrier;
return payload;
};
return Object.assign(f as T, { callCount: () => n });
}
const fetcher = instrumentedFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
const combosFetcher = instrumentedFetcher<OmniRouteCombosFetcher>([]);
const autoCombosFetcher = instrumentedFetcher<OmniRouteAutoCombosFetcher>([]);
const enrichmentFetcher = instrumentedFetcher<OmniRouteEnrichmentFetcher>(new Map());
const compressionMetaFetcher = instrumentedFetcher<OmniRouteCompressionMetaFetcher>([]);
const providersFetcher = instrumentedFetcher<OmniRouteProvidersFetcher>([]);
const logger = captureWarn();
// No snapshot → cold path (awaited). All fetchers must still start
// concurrently.
const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute", features: { enrichment: true, compressionMetadata: true, usableOnly: true } },
{
readAuthJson: authStub(),
fetcher,
combosFetcher,
autoCombosFetcher,
enrichmentFetcher,
compressionMetaFetcher,
providersFetcher,
diskSnapshotReader,
diskSnapshotWriter,
logger,
}
);
const input = makeInput();
await hook(input);
// All fetchers should have been called.
assert.equal(fetcher.callCount(), 1, "models fetcher called");
assert.equal(combosFetcher.callCount(), 1, "combos fetcher called");
assert.equal(autoCombosFetcher.callCount(), 1, "autoCombos fetcher called");
assert.equal(enrichmentFetcher.callCount(), 1, "enrichment fetcher called");
assert.equal(compressionMetaFetcher.callCount(), 1, "compressionMeta fetcher called");
assert.equal(providersFetcher.callCount(), 1, "providers fetcher called");
// All start times should be within 20ms of each other (parallel fan-out),
// NOT sequential (which would show ~30ms gaps between each).
assert.ok(startTimes.length >= 6, "all 6 fetchers started");
const minStart = Math.min(...startTimes);
const maxStart = Math.max(...startTimes);
assert.ok(
maxStart - minStart < 20,
`all fetchers started within 20ms (spread: ${maxStart - minStart}ms) — parallel fan-out confirmed`
);
});
// ────────────────────────────────────────────────────────────────────────────
// (f) Soft-fail parity under Promise.allSettled: per-endpoint fallbacks +
// logger.warn breadcrumbs preserved
// ────────────────────────────────────────────────────────────────────────────
test("warm-startup: combos reject → models-only catalog with warn", async () => {
const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
const combosFetcher = throwingFetcher<OmniRouteCombosFetcher>("403 Forbidden");
const logger = captureWarn();
const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute" },
{
readAuthJson: authStub(),
fetcher,
combosFetcher,
diskSnapshotReader,
diskSnapshotWriter,
logger,
}
);
const input = makeInput();
await hook(input);
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.ok(entry, "provider entry published");
assert.ok(
entry.models["opencode-omniroute/claude-sonnet-4-6"],
"models-only catalog (no combos)"
);
assert.ok(
logger.entries.some((e) => String(e[0]).includes("/api/combos fetch failed")),
"combos-fetch breadcrumb emitted"
);
});
test("warm-startup: enrichment rejects → raw-id catalog with warn", async () => {
const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
const enrichmentFetcher = throwingFetcher<OmniRouteEnrichmentFetcher>("ETIMEDOUT");
const logger = captureWarn();
const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute" },
{
readAuthJson: authStub(),
fetcher,
combosFetcher,
enrichmentFetcher,
diskSnapshotReader,
diskSnapshotWriter,
logger,
}
);
const input = makeInput();
await hook(input);
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.ok(entry, "provider entry published");
assert.equal(
entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
"claude-sonnet-4-6",
"raw id retained (no enrichment)"
);
assert.ok(
logger.entries.some((e) => String(e[0]).includes("/api/pricing/models fetch failed")),
"enrichment-fetch breadcrumb emitted"
);
});
test("warm-startup: providers reject → usableOnly filter disabled with warn", async () => {
const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
const providersFetcher = throwingFetcher<OmniRouteProvidersFetcher>("ETIMEDOUT");
const logger = captureWarn();
const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute", features: { usableOnly: true } },
{
readAuthJson: authStub(),
fetcher,
combosFetcher,
providersFetcher,
diskSnapshotReader,
diskSnapshotWriter,
logger,
}
);
const input = makeInput();
await hook(input);
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.ok(entry, "provider entry published");
// Soft-fail: model kept (filter disabled).
assert.ok(
entry.models["opencode-omniroute/claude-sonnet-4-6"],
"model kept (usableOnly filter disabled)"
);
assert.ok(
logger.entries.some((e) => String(e[0]).includes("/api/providers fetch failed")),
"providers-fetch breadcrumb emitted"
);
});
// ────────────────────────────────────────────────────────────────────────────
// (g) No double-refresh: concurrent hook invocations on the same cacheKey
// trigger only one refresh (in-flight guard)
// ────────────────────────────────────────────────────────────────────────────
test("warm-startup: concurrent hook invocations dedupe refresh", async () => {
let fetchCount = 0;
const slowResolve = new Promise<void>((r) => {
setTimeout(r, 100);
});
const fetcher: OmniRouteModelsFetcher = async () => {
fetchCount++;
await slowResolve;
return [MODEL_CLAUDE];
};
const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
const logger = captureWarn();
const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
const sharedCache: OmniRouteFetchCache = new Map();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute", modelCacheTtl: 60_000 },
{
readAuthJson: authStub(),
fetcher,
combosFetcher,
diskSnapshotReader,
diskSnapshotWriter,
cache: sharedCache,
logger,
}
);
// Fire two concurrent hook invocations on the same cache.
const inputA = makeInput();
const inputB = makeInput();
await Promise.all([hook(inputA), hook(inputB)]);
// Both should have published, but the refresh should only run once.
assert.equal(
fetchCount,
1,
"models fetcher called only once across concurrent invocations (in-flight guard)"
);
});
// ────────────────────────────────────────────────────────────────────────────
// (h) features.diskCache: false disables the warm read entirely
// ────────────────────────────────────────────────────────────────────────────
test("warm-startup: diskCache=false disables warm read, falls through to awaited fetch", async () => {
const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
const logger = captureWarn();
let readerCalled = false;
const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => {
readerCalled = true;
return {
rawModels: [MODEL_GEMINI],
rawCombos: [],
rawAutoCombos: [],
rawEnrichment: new Map(),
rawCompressionCombos: [],
rawConnections: [],
};
};
const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute", features: { diskCache: false } },
{
readAuthJson: authStub(),
fetcher,
combosFetcher,
diskSnapshotReader,
diskSnapshotWriter,
logger,
}
);
const input = makeInput();
await hook(input);
assert.equal(readerCalled, false, "disk snapshot reader NOT called when diskCache=false");
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.ok(entry, "provider entry published from live fetch");
assert.ok(
entry.models["opencode-omniroute/claude-sonnet-4-6"],
"live fetch model present (not snapshot)"
);
});
// ────────────────────────────────────────────────────────────────────────────
// Warm startup: snapshot age logged
// ────────────────────────────────────────────────────────────────────────────
test("warm-startup: snapshot age is logged when warm-starting from disk", async () => {
const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
const logger = captureWarn();
const snapshot: Omit<import("../src/index.js").OmniRouteFetchCacheEntry, "expiresAt"> & {
writtenAt?: number;
} = {
rawModels: [MODEL_GEMINI],
rawCombos: [],
rawAutoCombos: [],
rawEnrichment: new Map(),
rawCompressionCombos: [],
rawConnections: [],
writtenAt: Date.now() - 3_600_000, // 1 hour ago
};
const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => snapshot;
const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute" },
{
readAuthJson: authStub(),
fetcher,
combosFetcher,
diskSnapshotReader,
diskSnapshotWriter,
logger,
}
);
const input = makeInput();
await hook(input);
// The log should mention "warm startup from disk snapshot".
assert.ok(
logger.entries.some((e) =>
String(e[0]).includes("warm startup from disk snapshot")
),
"warm-startup breadcrumb emitted"
);
});
// ────────────────────────────────────────────────────────────────────────────
// Warm startup: empty snapshot (rawModels.length === 0) is skipped
// ────────────────────────────────────────────────────────────────────────────
test("warm-startup: empty snapshot (rawModels.length=0) is skipped, falls through to fetch", async () => {
const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
const logger = captureWarn();
const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => ({
rawModels: [],
rawCombos: [],
rawAutoCombos: [],
rawEnrichment: new Map(),
rawCompressionCombos: [],
rawConnections: [],
});
const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute" },
{
readAuthJson: authStub(),
fetcher,
combosFetcher,
diskSnapshotReader,
diskSnapshotWriter,
logger,
}
);
const input = makeInput();
await hook(input);
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.ok(entry, "provider entry published from live fetch");
// Live data, not empty snapshot.
assert.ok(
entry.models["opencode-omniroute/claude-sonnet-4-6"],
"live fetch model present (empty snapshot skipped)"
);
assert.equal(fetcher.callCount(), 1, "fetcher was called (awaited cold path)");
});

1186
AGENTS.md

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

548
CLAUDE.md
View File

@@ -1,55 +1,523 @@
# CLAUDE.md
@AGENTS.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
**All project rules live in [`AGENTS.md`](AGENTS.md)** — the single source of truth for every AI
assistant (architecture, conventions, testing, quality gates, git workflow, the 23 Hard Rules,
PII learnings). Read it in full; do not re-add project rules here. Everything below applies ONLY
to Claude Code — operational refinements of rules already defined in `AGENTS.md`.
## Quick Start
## Worktree isolation — Claude Code specifics
```bash
npm install # Install deps (auto-generates .env from .env.example)
npm run dev # Dev server at http://localhost:20128
npm run build # Production build (Next.js 16 standalone)
npm run lint # ESLint (0 errors expected; warnings are pre-existing)
npm run typecheck:core # TypeScript check (should be clean)
npm run typecheck:noimplicit:core # Strict check (no implicit any)
npm run test:coverage # Unit tests + coverage gate (60/60/60/60 — statements/lines/functions/branches)
npm run check # lint + test combined
npm run check:cycles # Detect circular dependencies
```
The full mandatory worktree protocol (base-branch confirmation, `.claude/worktrees/` canonical
path, `cp -al` node_modules, teardown rules) is in `AGENTS.md` → Git Workflow → "Worktree
isolation". Claude-Code-specific points:
### Running Tests
- Confirm the base branch with the operator via `AskUserQuestion` (Hard Rule #19) unless they
already told you.
- Prefer the native `EnterWorktree` tool — it already creates worktrees under
`.claude/worktrees/` (the canonical path). Create the worktree with the documented `git
worktree add` command, then call `EnterWorktree` with its `path`.
```bash
# Single test file (Node.js native test runner — most tests)
node --import tsx/esm --test tests/unit/your-file.test.ts
## Cross-session safety — Claude Code specifics
# Vitest (MCP server, autoCombo, cache)
npm run test:vitest
Hard Rules #19/#21/#22 (in `AGENTS.md`) govern parallel sessions. Operational reminders for this
harness:
# All suites
npm run test:all
```
- **Replicate the `git stash` ban verbatim in the prompt of every subagent that touches git**
(Agent tool / Workflow scripts) — subagents do not inherit this file, and the recorded
recurrence of the stash incident came through a subagent.
- Before merging or pushing to any PR you did not create _this session_, run `git worktree list`
and re-check `gh pr view <N> --json state,headRefOid` (Hard Rule #22b).
- End every session with the main checkout on the branch it started on.
For full test matrix, see `CONTRIBUTING.md` → "Running Tests". For deep architecture, see `AGENTS.md`.
## Superpowers / planning artifacts — path overrides
---
The `_tasks/` convention is defined in `AGENTS.md` → "Planning & Research Artifacts". The
superpowers skills ship with defaults that point at `docs/…` — those defaults are **overridden
here**. When a superpowers skill announces a path like "saved to `docs/superpowers/plans/…`",
rewrite it to the `_tasks/…` equivalent before writing:
## Project at a Glance
| Artifact (skill) | Default (do NOT use) | Save here instead |
| ---------------------------------- | ------------------------- | ------------------------------------------------------------- |
| Plans (`writing-plans`) | `docs/superpowers/plans/` | `_tasks/superpowers/plans/YYYY-MM-DD-<feature>.md` |
| Specs / design (`brainstorming`) | `docs/superpowers/specs/` | `_tasks/superpowers/specs/YYYY-MM-DD-<topic>-design.md` |
| Research (`deep-research`, ad-hoc) | `docs/research/` | `_tasks/research/…` |
| Hand-offs (`/handoff`) | — | `_tasks/hands-off/<YYYY-MM-DD>_<branch>_v<versão>_sess-<id>/` |
**OmniRoute** — unified AI proxy/router. One endpoint, 231 LLM providers, auto-fallback.
Commit those artifacts inside the `_tasks/` repo (`git -C _tasks …`), never in the main repo.
| Layer | Location | Purpose |
| ------------- | ----------------------- | -------------------------------------------------------------------------------------------------------------------------------------- |
| API Routes | `src/app/api/v1/` | Next.js App Router — entry points |
| Handlers | `open-sse/handlers/` | Request processing (chat, embeddings, etc) |
| Executors | `open-sse/executors/` | Provider-specific HTTP dispatch |
| Translators | `open-sse/translator/` | Format conversion (OpenAI↔Claude↔Gemini) |
| Transformer | `open-sse/transformer/` | Responses API ↔ Chat Completions |
| Services | `open-sse/services/` | Combo routing, rate limits, caching, etc |
| Database | `src/lib/db/` | SQLite domain modules (83 files, 97 migrations) |
| Domain/Policy | `src/domain/` | Policy engine, cost rules, fallback logic |
| MCP Server | `open-sse/mcp-server/` | 87 tools (33 base + memory/skill/notion/obsidian/gamification/plugin modules), 3 transports (stdio / SSE / Streamable HTTP), 30 scopes |
| A2A Server | `src/lib/a2a/` | JSON-RPC 2.0 agent protocol |
| Skills | `src/lib/skills/` | Extensible skill framework |
| Memory | `src/lib/memory/` | Persistent conversational memory |
## Base-green before opening PRs
Monorepo: `src/` (Next.js 16 app), `open-sse/` (streaming engine workspace), `electron/` (desktop app), `tests/`, `bin/` (CLI entry point).
Before cutting a branch or opening a PR, run the base-green check (`AGENTS.md` → Git Workflow →
"Base-green check"; project skills reference it as `.agents/skills/_shared/base-green.md`). A PR
opened while the base tip is red must carry `⚠️ base-red inherited: #<issue>` in its body. To
drain an accumulated red state (base tip + red PRs), use the `/sweep-reds` skill.
---
## Request Pipeline
```
Client → /v1/chat/completions (Next.js route)
→ CORS → Zod validation → auth? → policy check → prompt injection guard
→ handleChatCore() [open-sse/handlers/chatCore.ts]
→ cache check → rate limit → combo routing?
→ resolveComboTargets() → handleSingleModel() per target
→ translateRequest() → getExecutor() → executor.execute()
→ fetch() upstream → retry w/ backoff
→ response translation → SSE stream or JSON
→ If Responses API: responsesTransformer.ts TransformStream
```
API routes follow a consistent pattern: `Route → CORS preflight → Zod body validation → Optional auth (extractApiKey/isValidApiKey) → API key policy enforcement → Handler delegation (open-sse)`. No global Next.js middleware — interception is route-specific.
**Combo routing** (`open-sse/services/combo.ts`): 15 strategies (priority, weighted, fill-first, round-robin, P2C, random, least-used, cost-optimized, reset-aware, reset-window, strict-random, auto, lkgp, context-optimized, context-relay). Each target calls `handleSingleModel()` which wraps `handleChatCore()` with per-target error handling and circuit breaker checks. See `docs/routing/AUTO-COMBO.md` for the 9-factor Auto-Combo scoring and `docs/architecture/RESILIENCE_GUIDE.md` for the 3 resilience layers.
---
## Resilience Runtime State
OmniRoute has three related but distinct temporary-failure mechanisms. Keep their
scope separate when debugging routing behavior. See the
[3-layer resilience diagram](./docs/diagrams/exported/resilience-3layers.svg)
(source: [docs/diagrams/resilience-3layers.mmd](./docs/diagrams/resilience-3layers.mmd))
for an at-a-glance map.
### Provider Circuit Breaker
**Scope**: whole provider, e.g. `glm`, `openai`, `anthropic`.
**Purpose**: stop sending traffic to a provider that is repeatedly failing at the
upstream/service level, so one unhealthy provider does not slow down every request.
**Implementation**:
- Core class: `src/shared/utils/circuitBreaker.ts`
- Chat gate/execution wiring: `src/sse/handlers/chatHelpers.ts`, `src/sse/handlers/chat.ts`
- Runtime status API: `src/app/api/monitoring/health/route.ts`
- Shared wrappers: `open-sse/services/accountFallback.ts`
- Persisted state table: `domain_circuit_breakers`
**States**:
- `CLOSED`: normal traffic is allowed.
- `OPEN`: provider is temporarily blocked; callers get a provider-circuit-open response
or combo routing skips to another target.
- `HALF_OPEN`: reset timeout has elapsed; allow a probe request. Success closes the
breaker, failure opens it again.
**Defaults** (`open-sse/config/constants.ts`):
- OAuth providers: threshold `3`, reset timeout `60s`.
- API-key providers: threshold `5`, reset timeout `30s`.
- Local providers: threshold `2`, reset timeout `15s`.
Only provider-level failure statuses should trip the provider breaker:
```ts
(408, 500, 502, 503, 504);
```
Do not trip the whole-provider breaker for normal account/key/model errors like most
`401`, `403`, or `429` cases. Those usually belong to connection cooldown or model
lockout. A generic API-key provider `403` should be recoverable unless it is classified
as a terminal provider/account error.
The breaker uses lazy recovery, not a background timer. When `OPEN` expires, reads such
as `getStatus()`, `canExecute()`, and `getRetryAfterMs()` refresh the state to
`HALF_OPEN`, so dashboards and combo candidate builders do not keep excluding an
expired provider forever.
### Connection Cooldown
**Scope**: one provider connection/account/key.
**Purpose**: temporarily skip one bad key/account while allowing other connections for
the same provider to continue serving requests.
**Implementation**:
- Write/update path: `src/sse/services/auth.ts::markAccountUnavailable()`
- Account selection/filtering: `src/sse/services/auth.ts::getProviderCredentials...`
- Cooldown calculation: `open-sse/services/accountFallback.ts::checkFallbackError()`
- Settings: `src/lib/resilience/settings.ts`
Important fields on provider connections:
```ts
rateLimitedUntil;
testStatus: "unavailable";
lastError;
lastErrorType;
errorCode;
backoffLevel;
```
During account selection, a connection is skipped while:
```ts
new Date(rateLimitedUntil).getTime() > Date.now();
```
Cooldowns are also lazy: when `rateLimitedUntil` is in the past, the connection becomes
eligible again. On successful use, `clearAccountError()` clears `testStatus`,
`rateLimitedUntil`, error fields, and `backoffLevel`.
Default connection cooldown behavior:
- OAuth base cooldown: `5s`.
- API-key base cooldown: `3s`.
- API-key `429` should prefer upstream retry hints (`Retry-After`, reset headers, or
parseable reset text) when available.
- Repeated recoverable failures use exponential backoff:
```ts
baseCooldownMs * 2 ** failureIndex;
```
The anti-thundering-herd guard prevents concurrent failures on the same connection from
repeatedly extending the cooldown or double-incrementing `backoffLevel`.
Terminal states are not cooldowns. `banned`, `expired`, and `credits_exhausted` are
intended to stay unavailable until credentials/settings change or an operator resets
them. Do not overwrite terminal states with transient cooldown state.
### Model Lockout
**Scope**: provider + connection + model.
**Purpose**: avoid disabling a whole connection when only one model is unavailable or
quota-limited for that connection.
Examples:
- Per-model quota providers returning `429`.
- Local providers returning `404` for one missing model.
- Provider-specific mode/model permission failures such as selected Grok modes.
Model lockout lives in `open-sse/services/accountFallback.ts` and lets the same
connection continue serving other models.
### Debugging Guidance
- If all keys for a provider are skipped, inspect both provider breaker state and each
connection's `rateLimitedUntil`/`testStatus`.
- If a provider appears permanently excluded after the reset window, check whether code
is reading raw `state` instead of using `getStatus()`/`canExecute()`.
- If one provider key fails but others should work, prefer connection cooldown over
provider breaker.
- If only one model fails, prefer model lockout over connection cooldown.
- If a state should self-recover, it should have a future timestamp/reset timeout and a
read path that refreshes expired state. Permanent statuses require manual credential
or config changes.
---
## Key Conventions
### Code Style
- **2 spaces**, semicolons, double quotes, 100 char width, es5 trailing commas (enforced by lint-staged via Prettier)
- **Imports**: external → internal (`@/`, `@omniroute/open-sse`) → relative
- **Naming**: files=camelCase/kebab, components=PascalCase, constants=UPPER_SNAKE
- **ESLint**: `no-eval`, `no-implied-eval`, `no-new-func` = error everywhere; `no-explicit-any` = warn in `open-sse/` and `tests/`
- **TypeScript**: `strict: false`, target ES2022, module esnext, resolution bundler. Prefer explicit types.
### Database
- **Always** go through `src/lib/db/` domain modules — **never** write raw SQL in routes or handlers
- **Never** add logic to `src/lib/localDb.ts` (re-export layer only)
- **Never** barrel-import from `localDb.ts` — import specific `db/` modules instead
- DB singleton: `getDbInstance()` from `src/lib/db/core.ts` (WAL journaling)
- Migrations: `src/lib/db/migrations/` — versioned SQL files, idempotent, run in transactions
### Error Handling
- try/catch with specific error types, log with pino context
- Never swallow errors in SSE streams — use abort signals for cleanup
- Return proper HTTP status codes (4xx/5xx)
### Security
- **Never** use `eval()`, `new Function()`, or implied eval
- Validate all inputs with Zod schemas
- Encrypt credentials at rest (AES-256-GCM)
- Upstream header denylist: `src/shared/constants/upstreamHeaders.ts` — keep sanitize, Zod schemas, and unit tests aligned when editing
- **Public upstream credentials** (Gemini/Antigravity/Windsurf-style OAuth client_id/secret + Firebase Web keys extracted from public CLIs): **MUST** be embedded via `resolvePublicCred()` from `open-sse/utils/publicCreds.ts`**never** as string literals. See `docs/security/PUBLIC_CREDS.md` for the mandatory pattern.
- **Error responses** (HTTP / SSE / executor / MCP handler): **MUST** route through `buildErrorBody()` or `sanitizeErrorMessage()` from `open-sse/utils/error.ts`**never** put raw `err.stack` or `err.message` in a response body. See `docs/security/ERROR_SANITIZATION.md`.
- **Shell commands built from variables**: when calling `exec()`/`spawn()` with a script that needs runtime values, pass them via the `env` option (shell-escaped automatically) — **never** string-interpolate untrusted/external paths into the script body. Reference: `src/mitm/cert/install.ts::updateNssDatabases`.
- **Secure-by-default libraries** ([tldrsec/awesome-secure-defaults](https://github.com/tldrsec/awesome-secure-defaults)): prefer Helmet.js, DOMPurify, ssrf-req-filter, safe-regex, Google Tink over custom implementations whenever adding new security-sensitive surfaces.
---
## Common Modification Scenarios
### Adding a New Provider
1. Register in `src/shared/constants/providers.ts` (Zod-validated at load)
2. Add executor in `open-sse/executors/` if custom logic needed (extend `BaseExecutor`)
3. Add translator in `open-sse/translator/` if non-OpenAI format
4. Add OAuth config in `src/lib/oauth/constants/oauth.ts` if OAuth-based — if the upstream CLI ships a public client_id/secret, embed via `resolvePublicCred()` (see `docs/security/PUBLIC_CREDS.md`), **never** as a literal
5. Register models in `open-sse/config/providerRegistry.ts`
6. Write tests in `tests/unit/` (include the publicCreds shape assertion if you added a new embedded default)
### Adding a New API Route
1. Create directory under `src/app/api/v1/your-route/`
2. Create `route.ts` with `GET`/`POST` handlers
3. Follow pattern: CORS → Zod body validation → optional auth → handler delegation
4. Handler goes in `open-sse/handlers/` (import from there, not inline)
5. Error responses use `buildErrorBody()` / `errorResponse()` from `open-sse/utils/error.ts` (auto-sanitized — never put `err.stack` or `err.message` raw in the body). See `docs/security/ERROR_SANITIZATION.md`.
6. Add tests — including at least one assertion that error responses do not leak stack traces (`!body.error.message.includes("at /")`)
### Adding a New DB Module
1. Create `src/lib/db/yourModule.ts` — import `getDbInstance` from `./core.ts`
2. Export CRUD functions for your domain table(s)
3. Add migration in `src/lib/db/migrations/` if new tables needed
4. Re-export from `src/lib/localDb.ts` (add to the re-export list only)
5. Write tests
### Adding a New MCP Tool
1. Add tool definition in `open-sse/mcp-server/tools/` with Zod input schema + async handler
2. Register in tool set (wired by `createMcpServer()`)
3. Assign to appropriate scope(s)
4. Write tests (tool invocation logged to `mcp_audit` table)
### Adding a New A2A Skill
1. Create skill in `src/lib/a2a/skills/` (5 already exist: smart-routing, quota-management, provider-discovery, cost-analysis, health-report)
2. Skill receives task context (messages, metadata) → returns structured result
3. Register in `A2A_SKILL_HANDLERS` in `src/lib/a2a/taskExecution.ts`
4. Expose in `src/app/.well-known/agent.json/route.ts` (Agent Card)
5. Write tests in `tests/unit/`
6. Document in `docs/frameworks/A2A-SERVER.md` skill table
### Adding a New Cloud Agent
1. Create agent class in `src/lib/cloudAgent/agents/` extending `CloudAgentBase` (3 already exist: codex-cloud, devin, jules)
2. Implement `createTask`, `getStatus`, `approvePlan`, `sendMessage`, `listSources`
3. Register in `src/lib/cloudAgent/registry.ts`
4. Add OAuth/credentials handling if needed (`src/lib/oauth/providers/`)
5. Tests + document in `docs/frameworks/CLOUD_AGENT.md`
### Adding a New Embedded Service
1. Create installer in `src/lib/services/installers/{name}.ts` modeled on `ninerouter.ts` (use `runNpm` from `installers/utils.ts` — no shell interpolation, hard rule #13).
2. Register the service in `src/lib/services/bootstrap.ts` (add to `SERVICES[]` array and extend `buildSpawnArgsFactory()`).
3. Add a DB seed row for the new service in `src/lib/db/migrations/` (`version_manager` table, `status='not_installed'`, `auto_start=0`).
4. Create 7 API endpoints under `src/app/api/services/{name}/` (`_lib.ts`, `install`, `start`, `stop`, `restart`, `update`, `status`, `auto-start`). All delegate errors through `createErrorResponse()`. The shared `logs` endpoint is already wired via `[name]/logs/route.ts`.
5. Verify `/api/services/` is in `LOCAL_ONLY_API_PREFIXES` in `src/server/authz/routeGuard.ts`; add a test asserting `isLocalOnlyPath()` returns `true` for the new prefix if you add one (hard rule #17).
6. Add a UI tab in `src/app/(dashboard)/dashboard/providers/services/tabs/` reusing `ServiceStatusCard`, `ServiceLifecycleButtons`, `ServiceLogsPanel`.
7. Document in `docs/frameworks/EMBEDDED-SERVICES.md` (update §1 service table + §4 API reference) and `docs/openapi.yaml`.
8. Write tests: unit (`tests/unit/services/`), integration (`tests/integration/services/`, gated by `RUN_SERVICES_INT=1`), and update `docs/ops/RELEASE_CHECKLIST.md` smoke section.
### Adding a New Guardrail / Eval / Skill / Webhook event
- Guardrail: `src/lib/guardrails/` → docs: `docs/security/GUARDRAILS.md`
- Eval suite: `src/lib/evals/` → docs: `docs/frameworks/EVALS.md`
- Skill (sandbox): `src/lib/skills/` → docs: `docs/frameworks/SKILLS.md`
- Webhook event: `src/lib/webhookDispatcher.ts` → docs: `docs/frameworks/WEBHOOKS.md`
---
## Reference Documentation
For any non-trivial change, read the matching deep-dive first:
| Area | Doc |
| --------------------------------------------- | ----------------------------------------------------------------- |
| Repo navigation | `docs/architecture/REPOSITORY_MAP.md` |
| Architecture | `docs/architecture/ARCHITECTURE.md` |
| Engineering reference | `docs/architecture/CODEBASE_DOCUMENTATION.md` |
| Auto-Combo (9-factor scoring, 15 strategies) | `docs/routing/AUTO-COMBO.md` |
| Resilience (3 mechanisms) | `docs/architecture/RESILIENCE_GUIDE.md` |
| Reasoning replay | `docs/routing/REASONING_REPLAY.md` |
| Skills framework | `docs/frameworks/SKILLS.md` |
| Memory system (FTS5 + Qdrant) | `docs/frameworks/MEMORY.md` |
| Cloud agents | `docs/frameworks/CLOUD_AGENT.md` |
| Guardrails (PII / injection / vision) | `docs/security/GUARDRAILS.md` |
| Public upstream credentials (Gemini/etc.) | `docs/security/PUBLIC_CREDS.md` |
| Error message sanitization | `docs/security/ERROR_SANITIZATION.md` |
| Evals | `docs/frameworks/EVALS.md` |
| Compliance / audit | `docs/security/COMPLIANCE.md` |
| Webhooks | `docs/frameworks/WEBHOOKS.md` |
| Authorization pipeline | `docs/architecture/AUTHZ_GUIDE.md` |
| Stealth (TLS / fingerprint) | `docs/security/STEALTH_GUIDE.md` |
| Agent protocols (A2A / ACP / Cloud) | `docs/frameworks/AGENT_PROTOCOLS_GUIDE.md` |
| MCP server | `docs/frameworks/MCP-SERVER.md` |
| A2A server | `docs/frameworks/A2A-SERVER.md` |
| API reference + OpenAPI | `docs/reference/API_REFERENCE.md` + `docs/openapi.yaml` |
| Provider catalog (auto-generated) | `docs/reference/PROVIDER_REFERENCE.md` |
| Release flow | `docs/ops/RELEASE_CHECKLIST.md` |
| Embedded services | `docs/frameworks/EMBEDDED-SERVICES.md` |
| Quality gates (~48 scripts, allowlist policy) | `docs/architecture/QUALITY_GATES.md` |
---
## Testing
| What | Command |
| ----------------------- | --------------------------------------------------------------------------- |
| Unit tests | `npm run test:unit` |
| Single file | `node --import tsx/esm --test tests/unit/file.test.ts` |
| Vitest (MCP, autoCombo) | `npm run test:vitest` |
| E2E (Playwright) | `npm run test:e2e` |
| Protocol E2E (MCP+A2A) | `npm run test:protocols:e2e` |
| Ecosystem | `npm run test:ecosystem` |
| Coverage gate | `npm run test:coverage` (60/60/60/60 — statements/lines/functions/branches) |
| Coverage report | `npm run coverage:report` |
**PR rule**: If you change production code in `src/`, `open-sse/`, `electron/`, or `bin/`, you must include or update tests in the same PR.
**Test layer preference**: unit first → integration (multi-module or DB state) → e2e (UI/workflow only). Encode bug reproductions as automated tests before or alongside the fix.
**Both test runners must pass**: `npm run test:unit` (Node native — most tests) AND `npm run test:vitest` (MCP server, autoCombo, cache) cover **non-overlapping files**. Both are wired in CI (jobs `test-unit` and `test-vitest`) and must be green before merging. A PR where only one suite passes may silently ship broken MCP tools or routing regressions.
**Bug fix / issue triage protocol (Hard Rule #18)**: Every fix for a reported issue must be validated by one of the following — no exceptions:
1. **TDD (preferred)** — write a failing test reproducing the bug → fix it → confirm the test passes. The test becomes the permanent regression guard. Touch only the files the test proves need changing; nothing more.
2. **Real-environment test (when TDD is not possible)** — deploy to the production VPS (`root@192.168.0.15`) and run a documented live test. Record the exact command + result in the PR description. Applies to: OAuth upstream flows, Cloudflare/WS upstream behavior, UI-only regressions, hardware-dependent behavior.
3. "It worked locally without a test" does not count. A fix without a test or a VPS validation record is not a fix — it is a guess.
Why this matters: fixing bug A while opening bug B is worse than not fixing at all. The TDD/VPS gate enforces surgical scope — you touch only what the failing test proves is broken. Examples where this paid off: #3090 (claude-web 403), #3113 (WS HTTP fallback), #3052 (heap-guard auto-calibration).
**Copilot coverage policy**: When a PR changes production code and coverage is below 60% (statements/lines/functions/branches), do not just report — add or update tests, rerun the coverage gate, then ask for confirmation. Include commands run, changed test files, and final coverage result in the PR report.
---
## Git Workflow
```bash
# Never commit directly to main
git checkout -b feat/your-feature
git commit -m "feat: describe your change"
git push -u origin feat/your-feature
```
**Branch prefixes**: `feat/`, `fix/`, `refactor/`, `docs/`, `test/`, `chore/`
**Commit format** (Conventional Commits): `feat(db): add circuit breaker` — scopes: `db`, `sse`, `oauth`, `dashboard`, `api`, `cli`, `docker`, `ci`, `mcp`, `a2a`, `memory`, `skills`
**Husky hooks**:
- **pre-commit**: lint-staged + `check-docs-sync` + `check:any-budget:t11`
- **pre-push**: fast deterministic gates (`check:any-budget:t11` + `check:tracked-artifacts`); intentionally excludes `test:unit` (slow — covered by the CI `test-unit` job). Activated 2026-06-13 (Quality Gates Fase 6A.12).
### Worktree isolation (MANDATORY for every development task)
Multiple sessions/agents work this repo in parallel. The main checkout is **shared**, so a
`git checkout`/branch switch in it silently discards another session's uncommitted work and
yanks the branch out from under whatever else is running (incidents: 2026-06-05, 2026-06-13).
**Rule: never develop on the shared main checkout. Every task gets its own git worktree on its
own dedicated branch, and you MUST confirm the base branch with the operator before creating it.**
1. **Ask first — which base branch?** Before creating anything, ask the operator (via
`AskUserQuestion`, unless they already told you) from which branch the new worktree/branch
should be cut. Do NOT assume `main` or "whatever I'm on" — the answer is usually the active
`release/vX.Y.Z`, but it can be another feature/release branch. Get the base explicitly.
2. **Create an isolated worktree + branch off that base** (never reuse the main checkout):
```bash
BASE_BRANCH="release/vX.Y.Z" # ← the branch the operator confirmed in step 1
TASK="feat/your-feature" # feat/ fix/ refactor/ docs/ test/ chore/
git fetch origin "$BASE_BRANCH"
git worktree add ".worktrees/${TASK##*/}" -b "$TASK" "origin/$BASE_BRANCH"
cd ".worktrees/${TASK##*/}"
# symlink node_modules from the main checkout to skip a per-worktree npm install:
ln -s "$(git -C <main_checkout> rev-parse --show-toplevel)/node_modules" node_modules
```
In Claude Code prefer the native `EnterWorktree` tool (create the worktree with the command
above, then call `EnterWorktree` with its `path`).
3. **Work, commit, push, open the PR — all from inside the worktree.** Never `git checkout` a
different branch inside a worktree another session might share.
4. **Tear down only your own** worktree + branch when done, from the main checkout:
`git worktree remove .worktrees/<dir>` then `git branch -D <task>`. Never blanket-delete
`fix/*`/`feat/*` — other sessions keep their own; delete only the branches you created, by name.
5. **Never touch another session's worktree, branch, or uncommitted changes.** If `git worktree
list` shows worktrees you didn't create, leave them alone. End every session with the main
checkout back on the branch it started on (the active `release/vX.Y.Z`, never `main`).
---
## Environment
- **Runtime**: Node.js ≥22.0.0 <23 || ≥24.0.0 <27, ES Modules
- **TypeScript**: 6.0+, target ES2022, module esnext, resolution bundler
- **Path aliases**: `@/*` → `src/`, `@omniroute/open-sse` → `open-sse/`, `@omniroute/open-sse/*` → `open-sse/*`
- **Default port**: 20128 (API + dashboard on same port)
- **Data directory**: `DATA_DIR` env var, defaults to `~/.omniroute/`
- **Key env vars**: `PORT`, `JWT_SECRET`, `API_KEY_SECRET`, `INITIAL_PASSWORD`, `REQUIRE_API_KEY`, `APP_LOG_LEVEL`
- Setup: `cp .env.example .env` then generate `JWT_SECRET` (`openssl rand -base64 48`) and `API_KEY_SECRET` (`openssl rand -hex 32`)
---
## Quality Gates & Ratchets
OmniRoute has **~48 quality-gate scripts** (`scripts/check/` + `scripts/quality/`) wired
across **9 gate-running jobs** in `.github/workflows/ci.yml` (`lint`, `quality-gate`,
`quality-extended`, `docs-sync-strict`, `i18n-ui-coverage`, `i18n`, `pr-test-policy`,
`test-vitest`, `sonarqube`), plus the `quality.yml` fast-gates job (PR→`release/**`) and
3 nightly workflows (`nightly-property`, `nightly-resilience`, `nightly-llm-security`;
`nightly-mutation` once merged). Full inventory, per-job breakdown, and operational
procedures are in [`docs/architecture/QUALITY_GATES.md`](docs/architecture/QUALITY_GATES.md).
**Quick reference:**
- Gates in jobs `lint` + `docs-sync-strict`: pass/fail policy gates —
fix the violation or add an allowlist entry with a justification comment + tracking issue.
- Gates in job `quality-gate`: ratchet — metrics (ESLint warnings, code coverage, duplication,
complexity) must not regress vs `quality-baseline.json`. Update via
`npm run quality:ratchet -- --update` when a metric genuinely improves.
- Job `test-vitest` runs `npm run test:vitest` (MCP tools, autoCombo, cache) — blocking.
`test:vitest:ui` is advisory until UI component tests are triaged.
**Allowlist policy (short form):** Fix the cause; use the allowlist only for pre-existing
violations you cannot fix in the same PR. Add a comment with justification + issue number.
Stale allowlist entries (suppressing a violation that no longer exists) will be caught by
the stale-enforcement added in Fase 6A.3.
---
## Hard Rules
1. Never commit secrets or credentials
2. Never add logic to `localDb.ts`
3. Never use `eval()` / `new Function()` / implied eval
4. Never commit directly to `main`
5. Never write raw SQL in routes — use `src/lib/db/` modules
6. Never silently swallow errors in SSE streams
7. Always validate inputs with Zod schemas
8. Always include tests when changing production code
9. Coverage must not regress below the baseline frozen in `quality-baseline.json` (ratchet); absolute floor is 60% (statements/lines/functions/branches). Update the baseline via `npm run quality:ratchet -- --update` only when coverage genuinely improves. See `docs/architecture/QUALITY_GATES.md`.
10. Never bypass Husky hooks (`--no-verify`, `--no-gpg-sign`) without explicit operator approval.
11. Never embed public upstream OAuth client_id/secret or Firebase Web keys as string literals — always go through `resolvePublicCred()` (`open-sse/utils/publicCreds.ts`). See `docs/security/PUBLIC_CREDS.md`.
12. Never return raw `err.stack` / `err.message` in HTTP / SSE / executor responses — always route through `buildErrorBody()` or `sanitizeErrorMessage()` (`open-sse/utils/error.ts`). See `docs/security/ERROR_SANITIZATION.md`.
13. Never string-interpolate external paths or runtime values into shell scripts passed to `exec()`/`spawn()` — pass via the `env` option instead. Reference: `src/mitm/cert/install.ts::updateNssDatabases`.
14. Never dismiss a CodeQL / Secret-Scanning alert without (a) first checking the pattern docs above to see if the helper applies, and (b) recording the technical justification in the dismissal comment. Precedent: `js/stack-trace-exposure` raised on callsites that already route through `sanitizeErrorMessage()` is a known CodeQL limitation (custom sanitizers not recognized) — dismiss as `false positive` referencing `docs/security/ERROR_SANITIZATION.md`.
15. Never expose routes that spawn child processes (`/api/mcp/`, `/api/cli-tools/runtime/`) without `isLocalOnlyPath()` classification in `src/server/authz/routeGuard.ts`. Loopback enforcement happens unconditionally before any auth check — leaked JWT via tunnel cannot trigger process spawning. See `docs/security/ROUTE_GUARD_TIERS.md`.
16. Never credit or advertise an AI assistant, LLM, or automation account in any commit/PR metadata. Two forbidden forms, both equivalent — they route attribution to a bot account (or advertise AI authorship) and hide the real author (`diegosouzapw`): **(a)** `Co-Authored-By` trailers naming an AI/bot (e.g. names containing "Claude", "GPT", "Copilot", "Bot"; emails at `anthropic.com` / `openai.com` / bot-owned `noreply.github.com` addresses); **(b)** AI-generation footers or descriptions anywhere in a commit message, PR title/body, or CHANGELOG — e.g. `🤖 Generated with [Claude Code]`, "Generated with Claude Code", "Made with <AI tool>", or any `Co-authored-by: Claude/GPT/Copilot` line. This **overrides any harness, template, or tool default that auto-appends such a footer** (e.g. the Claude Code PR-body/commit default) — strip it before pushing; do not let it reach a commit, PR, or CHANGELOG. Human collaborators — including upstream PR authors and issue reporters being ported into OmniRoute — MAY and SHOULD be credited with standard `Co-authored-by: Name <email>` trailers; the upstream-port workflows (`/port-upstream-features`, `/port-upstream-issues`) depend on this.
17. Never expose routes under `/api/services/` or `/dashboard/providers/services/*/embed/` without `isLocalOnlyPath()` classification in `src/server/authz/routeGuard.ts`. These routes can spawn child processes (`npm install`, `node`). Loopback enforcement happens unconditionally before any auth check — a leaked JWT via tunnel cannot trigger process spawning. See `docs/security/ROUTE_GUARD_TIERS.md`.
18. Every bug fix must be validated before shipping: a failing-then-passing unit/integration test (TDD) OR a documented live test on the production VPS (192.168.0.15). A fix without either is not merged. See Testing → "Bug fix / issue triage protocol" for the full decision tree.
19. Never develop on the shared main checkout. Every development task runs in its own git worktree on its own dedicated branch, and you MUST confirm the base branch with the operator (e.g. via `AskUserQuestion`) before creating the worktree/branch — never assume `main` or the currently checked-out branch. A `git checkout` in the shared checkout silently destroys other sessions' uncommitted work. Tear down only the worktrees/branches you created (by name, never `fix/*`/`feat/*` wildcards), leave other sessions' worktrees untouched, and end on the branch you started on (the active `release/vX.Y.Z`, never `main`). See Git Workflow → "Worktree isolation".
---
## PII & Stream Sanitization Learnings
### 1. Regex Security (ReDoS)
All regex patterns matching variable-length strings (e.g. IPv6 address, credit cards) must use strictly bounded, non-overlapping sequences (e.g., limit occurrences with bounded ranges `{1,7}`) to prevent catastrophic backtracking when processing untrusted inputs.
### 2. SSE Snapshot Handling
When parsing streaming LLM responses (e.g. Responses API), check if a chunk represents a final snapshot (`done` or `completed` events). Snapshot text must be sanitized directly as a standalone string (bypassing rolling delta buffers) to prevent text duplication at the end of the stream.
### 3. Database Handles in Tests
Ensure that any unit tests that trigger database migrations or establish SQLite connections call `resetDbInstance()` and properly clean up/close all DB handles in a `test.after(...)` hook. Failure to release database connection handles will cause Node's native test runner to hang indefinitely.

View File

@@ -2,11 +2,6 @@
Thank you for your interest in contributing! This guide covers everything you need to get started.
For the official per-change workflow, start with the
[Contribution Golden Path](docs/ops/CONTRIBUTION_GOLDEN_PATH.md). It maps provider, routing,
UI/UX, i18n, CLI, database, and build/deploy changes to their contracts, focused tests, CI
coverage, and reconciliation steps.
---
## Development Setup
@@ -15,12 +10,6 @@ coverage, and reconciliation steps.
- **Node.js** `>=22.22.3 <23`, or `>=24.0.0 <27` (recommended: 24 LTS)
- **npm** 10+
> **npm v11+ users (Node 24+):** After `npm install`, verify native modules were installed:
> `node -e "require('better-sqlite3')"`. If it fails with `MODULE_NOT_FOUND`,
> run `npm approve-scripts better-sqlite3 && npm install`. See
> [Troubleshooting](docs/guides/TROUBLESHOOTING.md#npm-v11-better-sqlite3-not-installed-cannot-find-module).
- **Git**
### Clone & Install
@@ -114,19 +103,13 @@ Default URLs:
## Git Workflow
> ⚠️ **NEVER commit directly to `main`.** Always use feature branches.
>
> **PR base:** target the active `release/vX.Y.Z` branch (not `main`). See
> [`docs/ops/BRANCHING_MODEL.md`](docs/ops/BRANCHING_MODEL.md) for the
> release-per-branch + tag-at-ship model.
```bash
# Branch from the active release tip (example: release/v3.8.49)
git fetch origin
git checkout -b feat/your-feature-name origin/release/v3.8.49
git checkout -b feat/your-feature-name
# ... make changes ...
git commit -m "feat: describe your change"
git push -u origin feat/your-feature-name
# Open a Pull Request with base = release/v3.8.49
# Open a Pull Request on GitHub
```
### Branch Naming
@@ -177,31 +160,19 @@ npm run test:protocols:e2e
# Ecosystem compatibility tests
npm run test:ecosystem
# Coverage gate: 60% statements/lines/functions/branches
# Coverage gate: 75% statements/lines/functions, 70% branches
npm run test:coverage
npm run coverage:report
# Lint + format check
npm run lint
npm run check
# Gated real-upstream combo smoke (requires VPS access + real provider credits)
# Hits REAL providers — costs a little. NEVER runs in CI. Skips cleanly without the gate.
# Needs: ssh root@192.168.0.15 access (sources a read-only DB snapshot from the VPS).
RUN_COMBO_LIVE=1 npm run test:combo:live
# Phase-3 VPS live smoke — plain Node ESM scripts, hit the live .15 server directly.
# Requires: ssh root@192.168.0.15 access (combos created/torn down via SSH sqlite).
# Hits REAL providers (small cost). Creates/deletes only __live_test__* combos. NEVER runs in CI.
# REQUIRE_API_KEY=false on .15 so no API key needed, but honors COMBO_LIVE_BASE_URL / COMBO_LIVE_API_KEY if set.
npm run test:combo:live:vps # 7 HTTP scenarios (priority/round-robin/weighted/cost/fusion/auto + health)
npm run test:combo:live:vps:failover # adds a real cross-provider failover scenario (8 total)
```
Coverage notes:
- `npm run test:coverage` measures source coverage for the main unit test suite, excludes `tests/**`, and includes `open-sse/**`
- Pull requests must keep the coverage gate at **60%+** statements/lines/functions/branches
- Pull requests must keep the coverage gate at **75%+** statements/lines/functions and **70%+** branches
- If a PR changes production code in `src/`, `open-sse/`, `electron/`, or `bin/`, it must add or update automated tests in the same PR
- `npm run coverage:report` prints the detailed file-by-file report from the latest coverage run
- `npm run test:coverage:legacy` preserves the older metric for historical comparison
@@ -209,15 +180,11 @@ Coverage notes:
### Pull Request Requirements
Before opening a PR, use the
[Contribution Golden Path](docs/ops/CONTRIBUTION_GOLDEN_PATH.md) to run the focused loop for
what you changed. The full unit suite (4 CI shards), Vitest, the **60%+** coverage gate, and
the production build are CI's responsibility — running them locally adds no signal the PR
checks will not already give you, and on smaller machines it can saturate the host (#8084):
Before opening or merging a PR:
- Run the test files that cover your change: `node --import tsx/esm --test tests/unit/<file>.test.ts`
- Run `npm run lint`
- Include or update automated tests in the same PR whenever production code changes
- Run `npm run test:unit`
- Run `npm run test:coverage`
- Ensure the coverage gate stays at **75%+** statements/lines/functions, **70%+** branches
- Include the changed or added test files in the PR description when production code changed
- Check the SonarQube result on the PR when the project secrets are configured in CI
@@ -243,31 +210,6 @@ Current test status: **122 unit test files** covering:
- **Zod validation** — Use Zod v4 schemas for all API input validation
- **Naming**: Files = camelCase/kebab-case, components = PascalCase, constants = UPPER_SNAKE
### Error handling / empty catch blocks
Never leave a `catch` unexplained. Classify it into one of two buckets (operationalizes
the hard rule "never silently swallow errors in SSE streams"):
- **Intentional (our own best-effort cleanup/telemetry)** — a failure here is expected and
harmless; add a one-line rationale comment, no logging (logging on every request is the
noise this convention avoids).
```ts
} catch {} // closing an already-closed controller after client disconnect is expected
```
- **Should log (external/caller-supplied code, or the swallow changes control flow)** — keep
the catch (never let it break the stream) but emit a contextual `console.debug`/`warn` so the
failure is discoverable.
```ts
} catch (e) {
console.debug("[STREAM] onFailure callback error:", e);
}
```
See `open-sse/utils/stream.ts` and `open-sse/utils/streamHandler.ts` for applied examples.
---
## Project Structure
@@ -283,7 +225,7 @@ src/ # TypeScript (.ts / .tsx)
│ ├── a2a/ # Agent-to-Agent v0.3 protocol server
│ ├── acp/ # Agent Communication Protocol registry
│ ├── compliance/ # Compliance policy engine
│ ├── db/ # SQLite domain modules + 130 migrations
│ ├── db/ # SQLite database layer (21 modules + 16 migrations)
│ ├── memory/ # Persistent conversational memory
│ ├── oauth/ # OAuth providers, services, and utilities
│ ├── skills/ # Extensible skill framework
@@ -293,16 +235,16 @@ src/ # TypeScript (.ts / .tsx)
├── mitm/ # MITM proxy (cert, DNS, target routing)
├── shared/
│ ├── components/ # React components (.tsx)
│ ├── constants/ # Provider definitions (329), MCP scopes, 19 routing strategies
│ ├── constants/ # Provider definitions (177), MCP scopes, 14 routing strategies
│ ├── utils/ # Circuit breaker, sanitizer, auth helpers
│ └── validation/ # Zod v4 schemas
└── sse/ # SSE proxy pipeline
open-sse/ # @omniroute/open-sse workspace
├── executors/ # 89 executor implementation modules
├── executors/ # 14 provider-specific request executors
├── handlers/ # 11 request handlers (chat, responses, embeddings, images, etc.)
├── mcp-server/ # MCP server (107 unique tools, 3 transports, 32 scopes)
├── services/ # 178 top-level services (combo, autoCombo, rateLimitManager, etc.)
├── mcp-server/ # MCP server (25 tools, 3 transports, 10 scopes)
├── services/ # 36+ services (combo, autoCombo, rateLimitManager, etc.)
├── translator/ # Format translators (OpenAI ↔ Claude ↔ Gemini ↔ Responses ↔ Ollama)
├── transformer/ # Responses API transformer
└── utils/ # 22 utility modules (stream, TLS, proxy, logging)
@@ -387,7 +329,7 @@ Write unit tests in `tests/unit/` covering at minimum:
- [ ] Error responses route through `buildErrorBody()` / `sanitizeErrorMessage()` — no raw stack traces in response bodies (see [`docs/security/ERROR_SANITIZATION.md`](./docs/security/ERROR_SANITIZATION.md))
- [ ] Shell commands (`exec` / `spawn`) pass runtime values via `env`, not via string interpolation
- [ ] All inputs validated with Zod schemas
- [ ] Changelog **fragment** added under `changelog.d/{features|fixes|maintenance}/<PR>-<slug>.md` for user-facing changes (see [`changelog.d/README.md`](./changelog.d/README.md)) — do **not** edit `CHANGELOG.md` directly; fragments are aggregated at release time and never conflict between PRs
- [ ] CHANGELOG updated (if user-facing change)
- [ ] Documentation updated (if applicable)
- [ ] No new CodeQL / Secret-Scanning alerts opened, or each one dismissed with technical justification referencing the relevant `docs/security/` doc
- [ ] Routes that spawn child processes (`/api/mcp/`, `/api/cli-tools/runtime/`) classified as `isLocalOnlyPath()` in `src/server/authz/routeGuard.ts` — see [Hard Rule #15](docs/security/ROUTE_GUARD_TIERS.md)

254
DESING.md Normal file
View File

@@ -0,0 +1,254 @@
# OmniRoute — Design System & Visual Identity
> **Status:** analysis + standardization plan (no code applied yet — this doc is the spec to approve before implementation).
> **Date:** 2026-06-16 · **Scope:** unify the OmniRoute dashboard (`src/`) with the marketing site (`_mono_repo/omnirouteSite/`) into **one visual identity** — same graph-paper grid background, same color tokens, standardized components.
---
## 1. Purpose
The marketing site (`viral.omniroute.online`, `why.omniroute.online`, `omniroute.online`) and the product dashboard should look like **one product**. The site already borrowed its palette from the dashboard — its `css/tokens.css` even says _"Palette mirrors the OmniRoute dashboard (src/app/globals.css)"_. So the two are already ~80% aligned at the color level. What's missing on the dashboard:
1. The **graph-paper grid wallpaper** the site uses on every page.
2. A handful of **shared design tokens** the site has but the dashboard lacks (radius scale, brand gradient, `surface-2`, mono font).
3. **Component-level consistency** — a number of dashboard components bypass the theme tokens with hardcoded hex/rgba.
This document is the analysis and the plan. **Nothing is changed until approved.**
---
## 2. Principles
- **Single source of truth = `src/app/globals.css`.** The site mirrors the dashboard, never the other way around. New tokens land in `globals.css` first.
- **Tokens, never literals.** Components consume semantic tokens (`bg-surface`, `text-primary`, `border-border`), never raw `#hex`.
- **Subtle, not loud.** The grid is a faint wallpaper that sits behind content — it must never reduce text contrast or fight the UI.
- **Theme-aware.** Everything works in both `.dark` (default-ish, the product's signature look) and light.
- **Surgical rollout.** Ship the grid + tokens first (low risk, high visibility), then component cleanups in waves.
---
## 3. Current state — what's already aligned vs. what's not
### 3.1 Colors — already unified ✅
Every brand color and surface already matches the site **by value** (only the names differ — dashboard prefixes with `--color-`). Verified in `src/app/globals.css:30-128`:
| Concept | Site token (`tokens.css`) | Dashboard token (`globals.css`) | Match |
| -------------------------- | ------------------------------------------- | ------------------------------- | ------------ |
| primary | `--primary #e54d5e` | `--color-primary #e54d5e` | ✅ |
| primary-hover | `--primary-hover #c93d4e` | `--color-primary-hover #c93d4e` | ✅ |
| accent | `--accent #6366f1` | `--color-accent #6366f1` | ✅ |
| accent-2 | `--accent-2 #8b5cf6` | `--color-accent-hover #8b5cf6` | ✅ (renamed) |
| accent-3 | `--accent-3 #a855f7` | `--color-accent-light #a855f7` | ✅ (renamed) |
| success / warning / error | `#22c55e / #f59e0b / #ef4444` | identical | ✅ |
| traffic lights | `#ff5f56 / #ffbd2e / #27c93f` | identical | ✅ |
| dark bg / surface / border | `#0b0e14 / #161b22 / rgba(255,255,255,.08)` | identical | ✅ |
| light bg / surface / text | `#f9f9fb / #fff / #1a1a2e` | identical | ✅ |
**Conclusion:** there is no color migration to do. The identity is already shared; we are _finishing_ it, not rebuilding it.
### 3.2 Gaps — what the dashboard is missing
| Gap | Site has | Dashboard | Action |
| ----------------------- | ------------------------------------------------------------------------------ | ---------------------------------------------------------- | ---------------------- |
| **Grid wallpaper** | `body::before` graph-paper, `--grid-line`, `--grid-size 46px`, `--section-alt` | none (flat `--color-bg`) | **Part A** |
| **Radius scale** | `--radius 14px`, `--radius-sm 9px` | none — primitives use ad-hoc `rounded-md/lg/xl` (6/8/12px) | **Part B** |
| **Brand gradient** | `--grad-brand 135deg primary→accent-3` | none — only a one-off `.bg-hero-gradient` | **Part B** |
| **Nested surface** | `--surface-2 #1c2230` | none | **Part B** |
| **Mono font** | `--font-mono` (ui-monospace stack) | none (code/terminal areas have no token) | **Part B** |
| **`text-muted` (dark)** | `#8b8b9e` | `#a1a1aa` (zinc-400) | reconcile — **Part B** |
### 3.3 Theming mechanics (so we don't break anything)
- **Tailwind v4, CSS-first** (no `tailwind.config.*`). Tokens are defined in `:root`/`.dark` and exposed to utilities via `@theme inline` (`globals.css:130-179`).
- **Dark via `.dark` class** on `<html>` (`@custom-variant dark` at `globals.css:22`), toggled by a custom Zustand store (`src/store/themeStore.ts`), default theme = `system` (`src/shared/constants/appConfig.ts:11`). The site uses `html[data-theme="light"]` instead — **the mechanisms differ but never meet** (separate origins), so no conflict. We keep the dashboard's `.dark` mechanism.
- **Runtime primary override** exists (`themeStore.ts:85-97`, presets in `COLOR_THEMES`) — users can swap `--color-primary`. Any new token (gradient, etc.) that references `--color-primary` will inherit those overrides for free. ✅
---
## 4. Part A — The graph-paper grid background (headline ask)
### 4.1 What it is
The exact recipe from the site (`_mono_repo/omnirouteSite/css/base.css`): a **fixed, full-viewport pseudo-element** painting two 1px line gradients, sitting at `z-index:-1` behind all content.
```css
body::before {
content: "";
position: fixed;
inset: 0;
z-index: -1;
pointer-events: none;
background-image:
linear-gradient(to right, var(--grid-line) 1px, transparent 1px),
linear-gradient(to bottom, var(--grid-line) 1px, transparent 1px);
background-size: var(--grid-size) var(--grid-size);
}
```
**Why this works even though `body` has an opaque `background-color`:** a `::before` with `z-index:-1` paints _above_ the element's own background but _below_ its in-flow content. So `--color-bg` is the base fill, the grid is layered on top of it, and the app renders above the grid.
### 4.2 Precedent already in the codebase
`src/app/landing/page.tsx:16-26` **already implements this same grid per-page** — but with **red** lines (`#E54D5E`, opacity `0.06`) at **50px**, plus animated orbs. So the pattern is proven in the product; we are promoting it to a **global, theme-aware** wallpaper and (optionally) retiring the duplicate.
### 4.3 Tokens to add (in `globals.css`)
```css
:root {
/* light */
--grid-line: rgba(0, 0, 0, 0.045);
--grid-size: 46px;
--section-alt: rgba(0, 0, 0, 0.022);
}
.dark {
/* dark */
--grid-line: rgba(255, 255, 255, 0.035);
--section-alt: rgba(255, 255, 255, 0.018);
}
```
### 4.4 The single blocker
The grid is global by construction (it covers the panel, `auth`/`login`, error pages — every route — at once). Exactly **one** element hides it inside the panel:
- `src/shared/components/layouts/DashboardLayout.tsx:62` — the outer wrapper paints an opaque `bg-bg`:
```jsx
<div className="flex h-dvh min-h-0 w-full overflow-hidden bg-bg">
```
Everything below it is already transparent — `<main>` (`:93`), the scroll container (`:102`), the `max-w-7xl` inner (`:103`). So **removing `bg-bg` from this one line** lets the body grid show through the entire content area (the body's `--color-bg` remains the base fill underneath the grid).
```diff
- <div className="flex h-dvh min-h-0 w-full overflow-hidden bg-bg">
+ <div className="flex h-dvh min-h-0 w-full overflow-hidden">
```
### 4.5 Chrome interaction (sidebar / header)
- `Header` (`src/shared/components/Header.tsx:207`, `bg-bg`) and `Sidebar` (`src/shared/components/Sidebar.tsx:430`, `bg-sidebar`) stay **opaque** → the grid shows in the **content area only**, with solid chrome framing it. This is the recommended, calm default and matches how the site separates chrome from canvas.
- _Optional vibrancy variant:_ make the header translucent (`bg-bg/80 backdrop-blur`) so the grid runs behind it. A `.bg-vibrancy` helper already exists (`globals.css:370`). **Decision D3 below.**
### 4.6 Login / auth / error pages
These render directly under `<body>` (no panel chrome) and their page wrappers are mostly transparent — the global grid appears behind them automatically. One exception: `src/app/login/page.tsx:124,139` uses opaque `bg-bg` wrappers; soften the same way if we want the grid there too (minor, **D4**).
### 4.7 Landing page
`landing/page.tsx` keeps its richer animated background (orbs + vignette). Options: (a) leave it as-is (its own splash identity), or (b) align its grid to the global tokens (46px, neutral lines) for consistency. **Recommend (a)** — it's a marketing splash, not a panel screen. **Decision D5.**
---
## 5. Part B — Token unification
Add to `globals.css` (`:root` + `@theme inline`) so the dashboard gains the site's missing tokens. None of these change existing colors; they add the _missing_ primitives.
```css
:root {
--surface-2: #f5f5fa; /* light: nested panels */
--radius: 14px;
--radius-sm: 9px;
--grad-brand: linear-gradient(135deg, var(--color-primary), var(--color-accent-light));
--font-mono: ui-monospace, "JetBrains Mono", "Fira Code", "SF Mono", monospace;
}
.dark {
--surface-2: #1c2230;
}
@theme inline {
--color-surface-2: var(--surface-2); /* enables bg-surface-2 */
--radius-lg: var(--radius); /* enables rounded-lg = 14px */
--radius-md: var(--radius-sm); /* enables rounded-md = 9px */
--font-mono: var(--font-mono); /* enables font-mono */
}
```
| Token | Why | Consumers |
| -------------------------- | --------------------------------------------------------------- | ----------------------------------------------------------- |
| `--radius` / `--radius-sm` | One radius scale (14/9) instead of 6/8/12 ad-hoc | Button, Card, Modal, Input, Select |
| `--grad-brand` | Brand gradient for primary CTAs (red→violet), matching the site | Button `primary`, hero/CTA surfaces |
| `--surface-2` | Nested panels / table headers / inset rows | Card.Section, DataTable header, inputs |
| `--font-mono` | Code blocks, terminal, IDs, endpoints | ConsoleLogViewer, code snippets, `localhost:20128/v1` chips |
| `--text-muted` reconcile | Pick one value site↔panel | global |
**Decision D2 (text-muted):** site `#8b8b9e` vs dashboard `#a1a1aa`. Recommend keeping the **dashboard's `#a1a1aa`** (it's the live product, slightly higher contrast) and updating the _site_ to match. Low priority, cosmetic.
---
## 6. Part C — Component standardization
The component layer is **custom** (no shadcn/Radix), Tailwind v4, semantic tokens **mostly** adopted (`bg-surface`, `border-white/10`, `ring-primary`) — good adoption (195 files import the shared barrel). The work is removing the **bypasses**. Home: `src/shared/components/`.
Ranked by impact × reach:
| # | Item | File(s) | Problem → Target |
| --- | ------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| C1 | **Radius alignment** | `Button.tsx:14-18`, `Card.tsx:39`, `Modal.tsx`, `Input.tsx`, `Select.tsx` | mixed 6/8/12px → repoint to `--radius`/`--radius-sm` (14/9) |
| C2 | **Button gradient + `accent` variant** | `Button.tsx:5-12` | primary is flat red→red (`from-primary to-primary-hover`); align to `--grad-brand` (red→violet) and add the missing `accent` variant (indigo `#6366f1` is unused by buttons) — **highest visibility, ~195 importers**. **Decision D1.** |
| C3 | **Tables** | `DataTable.tsx:122-176`, `logTableStyles.ts`, `globals.css:405-414` (Ant remnants) | `DataTable` is 100% inline hardcoded rgba + references non-existent vars (`--text-secondary`, `--bg-table-header`); migrate to tokens, retire the 2 divergent table styles. Tables are everywhere (providers/connections/logs) — worst offender. |
| C4 | **Centralize status colors** | `flow/edgeStyles.ts:7-12`, `TokenHealthBadge.tsx:14-19`, `DegradationBadge.tsx`, `ProviderCascadeNode.tsx`, `Badge.tsx`, +5 `statusColor` helpers | 6+ copies of the same `#22c55e/#f59e0b/#ef4444` hex; create one `statusColors` module driven off `--color-success/warning/error`. Critical for circuit-breaker / cooldown / lockout badges to read consistently. |
| C5 | **Card border** | `Card.tsx:39` | uses `border-white/5`; brand border is `/8` → align |
| C6 | **Focus ring reconcile** | `globals.css:183` vs component `ring-primary/30` | global `:focus-visible` is indigo (`--color-accent`), components are red (`ring-primary`) — pick one (recommend **accent/indigo** globally, it reads as the "interactive" color) |
| C7 | **Add `Checkbox` + `Textarea` primitives** | currently raw `<input>`/`<textarea>` with inline `accentColor:#6366f1` (e.g. `ColumnToggle.tsx:91`) | create token-driven primitives |
| C8 | **Hardcoded-hex sweep** | `ConsoleLogViewer.tsx:240` (`#161b22`/`#30363d`), `ComboLiveStudio.tsx:306` (`#6366f120`), Modal traffic dots `Modal.tsx:149-159`, ~14 chart/component files with literal `#6366f1`/`#a855f7` | replace literals with `bg-surface`/`border-border`/`text-accent` etc. |
| C9 | **`cn()` → clsx + tailwind-merge** | `src/shared/utils/cn.ts` | current `cn` just joins; conflicting classes stack (a `className="rounded-2xl"` override won't replace a primitive's `rounded-lg`). Needed for C1 overrides to behave. |
**Already on-brand (token-driven, only need radius):** `Badge`, `Toggle`, `SegmentedControl`, `Input`, `Select`.
---
## 7. Rollout plan (phased, each phase shippable + testable)
- **Phase 1 — Grid + tokens (low risk, high visibility).**
1. Add grid + identity tokens to `globals.css` (Part A §4.3, Part B §5).
2. Add `body::before` grid.
3. Remove `bg-bg` from `DashboardLayout.tsx:62`.
4. Verify across themes + key screens (dashboard, providers, logs, login, an error page). Confirm contrast unchanged.
→ _Delivers the headline ask. Reversible in one commit._
- **Phase 2 — Primitives radius + Button (C1, C2, C5, C9).** The visible "feel" pass. `cn()` upgrade first so overrides behave.
- **Phase 3 — Tables + status colors (C3, C4).** The largest consistency win; touch the data-heavy screens.
- **Phase 4 — Cleanup (C6, C7, C8).** Focus ring, new primitives, hardcoded-hex sweep.
Each phase: `npm run lint` + `npm run typecheck:core` + a visual pass. Per repo rule, production-code changes ship with tests where applicable (token/CSS changes are visual — validated by screenshots; component API changes get unit coverage).
---
## 8. Open decisions (need your call before/while implementing)
- **D1 — Button primary look.** Keep the current **red→red** gradient, or switch the product's primary buttons to the **red→violet `--grad-brand`** (matches the site CTAs)? _(Affects every primary button.)_ Recommend: **red→violet**, with `--grad-brand`.
- **D2 — Grid line color.** **Neutral** lines (site style: faint white/black, `rgba(255,255,255,0.035)`) — calm, content-first — **or** the landing's **brand-red** lines? Recommend: **neutral** (matches the site's interior pages; red is louder and can tint readability). Size **46px** (site) to retire the landing's 50px drift.
- **D3 — Chrome vibrancy.** Sidebar/header stay **solid** (grid in content area only), or go **translucent** so the grid runs behind them? Recommend: **solid** (calmer; less risk).
- **D4 — Auth/login grid.** Soften `login/page.tsx` wrappers so the grid shows there too? Recommend: **yes** (cheap, more cohesive).
- **D5 — Landing page.** Leave its animated splash bg as-is, or align it to the global grid? Recommend: **leave as-is**.
- **D6 — Radius value.** Adopt **14/9** everywhere (bigger, softer, site-matching) — confirm you want this product-wide shift. Recommend: **yes**, it's the single biggest "one identity" signal.
- **D7 — Scope of first PR.** Ship **Phase 1 only** first (grid + tokens), then iterate? Recommend: **yes** — validate the wallpaper live before the component waves.
---
## 9. Out of scope / risks
- **No palette change** — colors already match; we only add missing tokens. Zero risk of recoloring the product.
- **No theme-engine change** — keep `.dark` + Zustand store; don't migrate to `next-themes` or to the site's `data-theme`.
- **Radius shift is broad** (D6) — it touches every card/button/input; that's the point, but it's the one change worth eyeballing on busy screens (tables, modals) before merge.
- **Tables (C3)** carry the most hardcoded styling and the highest regression surface — isolate in its own PR with before/after screenshots.
- **Worktree isolation (repo hard-rule #19):** implementation runs in a dedicated worktree on a branch cut from the confirmed base (likely `release/v3.8.28`), never on the shared checkout. This doc is the only artifact written to the working tree so far.
---
## 10. Reference index
| Area | Path |
| -------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------- |
| Dashboard tokens | `src/app/globals.css:30-179` (`:root`, `.dark`, `@theme inline`), `body` `:206` |
| Theme store | `src/store/themeStore.ts`, `src/shared/components/ThemeProvider.tsx`, `src/shared/constants/appConfig.ts:9-11` |
| Panel shell (grid blocker) | `src/shared/components/layouts/DashboardLayout.tsx:62` |
| Chrome | `src/shared/components/Header.tsx:207`, `src/shared/components/Sidebar.tsx:430` |
| Grid precedent | `src/app/landing/page.tsx:16-26` |
| Primitives | `src/shared/components/{Button,Card,Input,Select,Badge,Modal,Toggle,SegmentedControl,Loading,Tooltip,DataTable}.tsx`, barrel `index.tsx` |
| Status-color sources | `flow/edgeStyles.ts`, `TokenHealthBadge.tsx`, `DegradationBadge.tsx`, `logTableStyles.ts` |
| `cn` util | `src/shared/utils/cn.ts` |
| Site reference | `_mono_repo/omnirouteSite/css/tokens.css`, `css/base.css` (grid `body::before`) |

View File

@@ -1,79 +1,25 @@
# ── Common base with runtime deps ──────────────────────────────────────────
FROM node:26-trixie-slim AS base
FROM node:24-trixie-slim AS base
WORKDIR /app
# `apt-get upgrade` pulls the security-patched versions of the Debian (trixie)
# base-image packages at build time — clears the subset of container-scan CVEs
# (perl / util-linux / systemd / ncurses / zlib / tar / sqlite / shadow / pam …)
# that already have a fix published in trixie. CVEs without an upstream fix yet
# (local-only TOCTOU, etc.) remain until the distro patches them and the image
# is rebuilt; none are reachable from the proxy's request surface at runtime.
RUN --mount=type=cache,id=apt-cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,id=apt-lists,target=/var/lib/apt/lists,sharing=locked \
RUN --mount=type=cache,target=/var/cache/apt,sharing=shared \
--mount=type=cache,target=/var/lib/apt/lists,sharing=shared \
apt-get update \
&& apt-get upgrade -y \
&& apt-get install -y --no-install-recommends libsecret-1-0 ca-certificates \
&& rm -rf /var/lib/apt/lists/*
# npm's *bundled* node_modules (brace-expansion, ip-address, tar, undici) are
# npm's own internals — not application dependencies (the app resolves its own,
# already-fixed copies) — but the container scanner reads them off
# /usr/local/lib/node_modules/npm/node_modules and reports 9 HIGH/MEDIUM CVEs.
#
# Refreshing npm does NOT fix them. Measured on npm@12.0.2 (2026-08-12, latest):
# brace-expansion 5.0.7 (needs >= 5.0.9) CVE-2026-69152, CVE-2026-14257
# ip-address 10.2.0 (needs >= 10.3.1) CVE-2026-69192/-69198/-54272
# tar 7.5.19 (needs >= 7.5.21) GHSA-r292-9mhp-454m
# undici 6.27.0 (needs >= 6.28.0) CVE-2026-16729/-16728/-15157
# No published npm release carries patched copies, so `npm install -g npm@latest`
# alone was pure build time for zero CVEs — it is kept only to land on a known,
# current npm tree, and the patched copies are overlaid on top below.
#
# Deleting npm from the runner stages is NOT an option: the application shells
# out to npm at runtime (src/lib/services/installers/utils.ts::runNpm for the
# embedded services, src/lib/system/{autoUpdate,globalPackagePath}.ts,
# src/app/api/system/version). The previous version of this comment claimed the
# opposite; it was wrong.
#
# The overlay is semver-compatible with the ranges npm's own tree declares
# (minimatch → brace-expansion ^5.0.5, socks → ip-address ^10.1.1, node-gyp →
# tar ^7.5.4 and undici ^6.25.0 — hence undici stays on the 6.x line, NOT 8.x).
# --install-strategy=nested makes each replacement self-contained, so it cannot
# perturb the versions the rest of npm's flat tree resolves.
RUN set -eux; \
npm install -g npm@latest; \
npm install --prefix /tmp/npm-cve-patch --no-audit --no-fund --ignore-scripts \
--install-strategy=nested \
brace-expansion@5.0.9 ip-address@10.5.0 tar@7.5.22 undici@6.28.0; \
for pkg in brace-expansion ip-address tar undici; do \
test -d "/usr/local/lib/node_modules/npm/node_modules/$pkg"; \
rm -rf "/usr/local/lib/node_modules/npm/node_modules/$pkg"; \
cp -R "/tmp/npm-cve-patch/node_modules/$pkg" \
"/usr/local/lib/node_modules/npm/node_modules/$pkg"; \
done; \
rm -rf /tmp/npm-cve-patch; \
node -e "for (const p of ['brace-expansion','ip-address','tar','undici']) console.log(p, require('/usr/local/lib/node_modules/npm/node_modules/'+p+'/package.json').version);"; \
npm --version; \
npm cache clean --force
# ── Builder ────────────────────────────────────────────────────────────────
FROM base AS builder
# Build tools for native module compilation
# apt-get update needed here because base's rm -rf clears the shared cache
RUN --mount=type=cache,id=apt-cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,id=apt-lists,target=/var/lib/apt/lists,sharing=locked \
RUN --mount=type=cache,target=/var/cache/apt,sharing=shared \
--mount=type=cache,target=/var/lib/apt/lists,sharing=shared \
apt-get update \
&& apt-get install -y --no-install-recommends python3 make g++ \
&& rm -rf /var/lib/apt/lists/*
COPY package*.json ./
# Workspace package manifests MUST be present before `npm ci` so npm materializes
# the workspace and installs its *workspace-only* deps (e.g. safe-regex,
# @toon-format/toon — declared in open-sse/package.json, not hoisted to root).
# Without this, `npm ci` skips them and the application build fails with "Module not
# found" (root cause of the v3.8.39 Docker build break). workspaces = ["open-sse"].
COPY open-sse/package.json ./open-sse/package.json
COPY scripts/build/postinstall.mjs ./scripts/build/postinstall.mjs
COPY scripts/build/postinstallSupport.mjs ./scripts/build/postinstallSupport.mjs
COPY scripts/build/native-binary-compat.mjs ./scripts/build/native-binary-compat.mjs
@@ -87,81 +33,33 @@ ENV NPM_CONFIG_LEGACY_PEER_DEPS=true
# are reproducible.
RUN test -f package-lock.json \
|| (echo "package-lock.json is required for reproducible Docker builds" >&2 && exit 1)
# `npm rebuild <pkg>` re-runs the package's own install script, so under npm 11 +
# `--ignore-scripts` on the parent `npm ci` it depends on npm's script-allowlist
# machinery correctly re-enabling that one package's script. Some self-hosted build
# environments (e.g. Dokploy) hit a broken/incomplete better-sqlite3 native binding
# from that indirection. Invoking `node-gyp rebuild` directly inside the package
# directory bypasses npm's script-running layer entirely and is deterministic
# regardless of npm version or ignore-scripts allowlist behavior.
# node-gyp comes from npm's own bundled copy (deterministic, already in the image)
# instead of `npx --yes`, which would install an arbitrary registry version
# on-demand and run its lifecycle scripts (Sonar docker:S6505).
#
# tls-client-node (chatgpt-web/claude-web/grok-web/lmarena/perplexity-web TLS
# impersonation) hits the same --ignore-scripts wall: its own postinstall.js
# fetches a platform .so/.dylib/.dll from the bogdanfinn/tls-client GitHub
# Releases API and is never invoked when npm ci skips lifecycle scripts. Unlike
# better-sqlite3 above, that script never throws on failure — it only
# `console.warn`s and exits 0 — so a rate-limited or offline build would
# otherwise succeed silently with an empty bin/ and only fail at first request
# in production (TlsClientUnavailableError, #7802). Run it explicitly here so
# a broken/rate-limited fetch fails the BUILD loudly instead of shipping a
# broken image.
RUN --mount=type=cache,id=npm-cache,target=/root/.npm \
npm ci --include=optional --no-audit --no-fund --legacy-peer-deps --ignore-scripts \
&& (cd node_modules/better-sqlite3 \
&& node /usr/local/lib/node_modules/npm/node_modules/node-gyp/bin/node-gyp.js rebuild) \
&& node -e "require('better-sqlite3')(':memory:').close()" \
&& node node_modules/tls-client-node/scripts/postinstall.js \
&& (test -n "$(find node_modules/tls-client-node/bin -mindepth 1 -print -quit 2>/dev/null)" \
|| (echo "tls-client-node native binary missing after postinstall — GitHub API fetch likely rate-limited or failed (#7802)" >&2 && exit 1))
RUN --mount=type=cache,target=/root/.npm \
npm ci --no-audit --no-fund --legacy-peer-deps --ignore-scripts \
&& npm rebuild better-sqlite3 \
&& node -e "require('better-sqlite3')(':memory:').close()"
# Build with Turbopack (stable in Next 16, the repo default). The v3.8.27-era
# TurbopackInternalError panic ("entered unreachable code: there must be a path to a
# root" in ImportTracer::get_traces) no longer reproduces on Next 16.2.9 — validated
# 2026-07-05 with clean amd64 (12min14s, image smoke-tested: /api/monitoring/health
# 200) and arm64 (qemu, exit 0, zero panic strings) builds. Turbopack cut the bare
# build from 17min to 9min on the same 32-core box. Webpack stays available as the
# escape hatch: `--build-arg`/-e OMNIROUTE_USE_TURBOPACK=0.
# Build with webpack (stable). Turbopack hit a non-recoverable internal panic on this
# Next.js version during the v3.8.27 release build — TurbopackInternalError "entered
# unreachable code: there must be a path to a root" in ImportTracer::get_traces, on both
# linux/amd64 and linux/arm64. Webpack is the proven engine (build:release / VPS / CI Build
# all green). Re-enable Turbopack (=1) once the upstream tracer bug is fixed.
# See docs/ops/QUALITY_GATE_PLAYBOOK.md Parte 6.
#
# Declared as ARG+ENV, not a bare ENV: a bare ENV shadows any same-named ARG for
# the rest of the stage, so `--build-arg OMNIROUTE_USE_TURBOPACK=0` was silently
# ignored and the escape hatch above only ever worked via `-e` at runtime, never
# at build time. Turbopack compiles in native Rust memory that lives outside the
# V8 heap, so OMNIROUTE_BUILD_MEMORY_MB cannot bound it and a memory-constrained
# build host gets SIGKILLed by the cgroup OOM killer with no error message.
ARG OMNIROUTE_USE_TURBOPACK=1
ENV OMNIROUTE_USE_TURBOPACK="${OMNIROUTE_USE_TURBOPACK}"
# Next.js basePath is fixed at build time; pass OMNIROUTE_BASE_PATH here when the
# image should serve under a reverse-proxy subpath without a runtime patch.
ARG OMNIROUTE_BASE_PATH=""
ENV OMNIROUTE_BASE_PATH=$OMNIROUTE_BASE_PATH
# Docker containers cannot run the MITM/Agent-Bridge stack (no host DNS/cert
# access), so keep @/mitm/manager on the graceful stub (#3390). This flag is
# Docker-only: npm/Electron/VPS builds must bundle the REAL manager (#6344).
ENV OMNIROUTE_MITM_STUB=1
ENV OMNIROUTE_USE_TURBOPACK=0
# Raise the V8 heap ceiling for the build. The webpack production optimization
# pass needs more than V8's default ceiling (~2 GB) for a codebase this size; a
# memory-constrained Docker build otherwise dies with "FATAL ERROR: ... JavaScript
# heap out of memory" during the builder stage (#4076). Turbopack's compile is
# native (Rust) and less V8-heap-bound, but the prerender/export phase still runs
# on V8, so keep the ceiling. NODE_OPTIONS propagates to the spawned `next build`
# child (build-next-isolated.mjs → resolveNextBuildEnv spreads process.env).
# Build-only; the runtime heap is set separately on the runner stage
# (OMNIROUTE_MEMORY_MB). Override: `--build-arg OMNIROUTE_BUILD_MEMORY_MB=6144`.
# pass (forced above since Turbopack panics) needs more than V8's default ceiling
# (~2 GB) for a codebase this size; a memory-constrained Docker build otherwise
# dies with "FATAL ERROR: ... JavaScript heap out of memory" at `[builder] npm run
# build` (#4076). NODE_OPTIONS propagates to the spawned `next build` child
# (build-next-isolated.mjs → resolveNextBuildEnv spreads process.env). Build-only;
# the runtime heap is set separately on the runner stage (OMNIROUTE_MEMORY_MB).
# Override for hosts with more/less RAM: `--build-arg OMNIROUTE_BUILD_MEMORY_MB=6144`.
ARG OMNIROUTE_BUILD_MEMORY_MB=4096
ENV NODE_OPTIONS="--max-old-space-size=${OMNIROUTE_BUILD_MEMORY_MB}"
COPY . ./
RUN --mount=type=cache,id=next-cache,target=/app/.build/next/cache \
mkdir -p /app/data \
&& npm run build \
&& node --input-type=module -e "import { createRequire } from 'node:module'; import { pathToFileURL } from 'node:url'; const standaloneRoot = '/app/.build/next/standalone/node_modules/'; const require = createRequire('/app/.build/next/standalone/package.json'); for (const pkg of ['@atjsh/llmlingua-2', '@huggingface/transformers', '@tensorflow/tfjs', 'js-tiktoken']) { const resolved = require.resolve(pkg); if (!resolved.startsWith(standaloneRoot)) throw new Error(pkg + ' resolved outside standalone: ' + resolved); await import(pathToFileURL(resolved).href); } const onnxRuntime = require.resolve('onnxruntime-node'); if (!onnxRuntime.startsWith(standaloneRoot)) throw new Error('onnxruntime-node resolved outside standalone: ' + onnxRuntime); await import(pathToFileURL(onnxRuntime).href);"
RUN --mount=type=cache,target=/app/.build/next/cache \
mkdir -p /app/data && npm run build
# ── Runner base ────────────────────────────────────────────────────────────
FROM base AS runner-base
@@ -175,12 +73,6 @@ LABEL org.opencontainers.image.title="omniroute" \
ENV NODE_ENV=production
ENV PORT=20128
ENV HOSTNAME=0.0.0.0
# Runtime heap ceiling. 1024MB is enough for normal traffic but can be tight
# for large fusion-combo panels (many models fanned out in parallel, each
# response buffered in full — see open-sse/services/fusion.ts::FUSION_DEFAULTS
# .maxPanel, issue #1905). Override at `docker run` time with
# `-e OMNIROUTE_MEMORY_MB=2048` (or higher) if you raise fusionTuning.maxPanel
# above the default cap.
ENV OMNIROUTE_MEMORY_MB=1024
ENV NODE_OPTIONS="--max-old-space-size=${OMNIROUTE_MEMORY_MB}"
@@ -221,8 +113,8 @@ EXPOSE 20128
USER node
# Warns if the mounted data volume has wrong ownership
COPY --chmod=755 scripts/check-permissions.sh /app/check-permissions.sh
ENTRYPOINT ["/app/check-permissions.sh"]
COPY --chmod=755 scripts/check-permissions.sh /tmp/check-permissions.sh
ENTRYPOINT ["/tmp/check-permissions.sh"]
HEALTHCHECK --interval=30s --timeout=5s --start-period=15s --retries=3 \
CMD ["node", "healthcheck.mjs"]
@@ -262,8 +154,8 @@ COPY --from=builder /app/node_modules/playwright ./node_modules/playwright
# browsers land under /home/node which persists across image layers and is
# accessible to the non-root runtime user.
ENV PLAYWRIGHT_BROWSERS_PATH=/home/node/.cache/ms-playwright
RUN --mount=type=cache,id=apt-cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,id=apt-lists,target=/var/lib/apt/lists,sharing=locked \
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,target=/var/lib/apt/lists,sharing=locked \
apt-get update \
&& node node_modules/playwright/cli.js install chromium --with-deps \
&& chown -R node:node /home/node/.cache \
@@ -278,21 +170,16 @@ FROM runner-base AS runner-cli
# runner-base runs.
USER root
# The CLI image can use the internal ChatGPT Web (Codex) Chromium sidecar over
# CDP without installing a second browser in this container.
COPY --from=builder /app/node_modules/playwright-core ./node_modules/playwright-core
COPY --from=builder /app/node_modules/playwright ./node_modules/playwright
# Install system dependencies required by openclaw (git+ssh references).
RUN --mount=type=cache,id=apt-cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,id=apt-lists,target=/var/lib/apt/lists,sharing=locked \
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,target=/var/lib/apt/lists,sharing=locked \
apt-get update \
&& apt-get install -y --no-install-recommends git ca-certificates docker.io docker-compose \
&& rm -rf /var/lib/apt/lists/* \
&& git config --system url."https://github.com/".insteadOf "ssh://git@github.com/"
# Install CLI tools globally. Separate layer from apt for better cache reuse.
RUN --mount=type=cache,id=npm-cache,target=/root/.npm \
RUN --mount=type=cache,target=/root/.npm \
npm install -g --no-audit --no-fund @openai/codex @anthropic-ai/claude-code droid openclaw@latest
USER node

View File

@@ -1,13 +1,50 @@
# GEMINI.md
# Security and Cleanliness Rules for AI Assistants
> **Single source of truth:** all project rules for AI assistants live in
> [`AGENTS.md`](AGENTS.md). Read it in full before any change — it contains the 23 Hard Rules,
> quality gates, code conventions, file-placement / repo-root hygiene rules, the repository map
> and the local development access notes that used to live in this file.
> **Scope:** rules for Gemini-based agents. For Claude Code, see `CLAUDE.md`. For other AI assistants, see `AGENTS.md`.
Gemini-specific notes:
## 1. File Placement & Organization
- Skills activate via the `activate_skill` tool (skill metadata is loaded at session start and
the full content is activated on demand).
- There are no other Gemini-only rules today. Do not re-add project rules here — edit
`AGENTS.md` instead, so every assistant sees the same instructions.
- **Test Files**: ALL unit tests, integration tests, ecosystem tests, or Vitest files MUST strictly be placed within the `tests/` directory (e.g., `tests/unit/`, `tests/integration/`). NEVER create test files in the project root (`/`).
- **Scripts and Utilities**: ALL maintenance, debugging, generation, or experimental scripts (`.cjs`, `.mjs`, `.js`, `.ts`) MUST be placed strictly inside one of the `scripts/` subfolders (`build/`, `dev/`, `check/`, `docs/`, `i18n/`, `ad-hoc/`). One-shot or experimental code goes under `scripts/ad-hoc/`. NEVER dump loose scripts in the project root (`/`) or the top-level `scripts/` folder.
**The Project Root MUST ONLY CONTAIN:**
- Configuration files (`vitest.config.ts`, `next.config.mjs`, `eslint.config.mjs`, `tsconfig*.json`, `playwright.config.ts`, `prettier.config.mjs`, `postcss.config.mjs`, `sonar-project.properties`, `fly.toml`, `docker-compose*.yml`, `Dockerfile`)
- Dependency files (`package.json`, `package-lock.json`)
- Documentation files (`README.md`, `CHANGELOG.md`, `LICENSE`, `AGENTS.md`, `CLAUDE.md`, `GEMINI.md`, `CONTRIBUTING.md`, `SECURITY.md`, `CODE_OF_CONDUCT.md`, `llm.txt`, `Tuto_Qdrant.md`)
- CI/CD files and ignore definitions (`.gitignore`, `.dockerignore`, `.npmignore`, `.npmrc`, `.node-version`, `.nvmrc`, `.env.example`)
When creating _any_ validation tests or one-off logic scripts, default to using `scripts/ad-hoc/` or the `tests/unit/` directories according to your goals. Do not pollute the `/` root context.
## 2. Hard Rules (mirror of `CLAUDE.md`)
1. **Never commit secrets or credentials.** Use `.env` (auto-generated from `.env.example`) or a vault. Passwords, OAuth secrets, API keys, and Cookie values must never appear in committed files.
2. **Never add logic to `src/lib/localDb.ts`.** It is a re-export barrel only.
3. **Never use `eval()`, `new Function()`, or any implied eval.** ESLint enforces this.
4. **Never commit directly to `main`.** Use `feat/`, `fix/`, `refactor/`, `docs/`, `test/`, or `chore/` branches.
5. **Never write raw SQL in routes** — always go through `src/lib/db/` domain modules.
6. **Never silently swallow errors in SSE streams** — propagate them or abort the stream cleanly.
7. **Never bypass Husky hooks** (`--no-verify`, `--no-gpg-sign`) without explicit operator approval.
8. **Always validate inputs with Zod schemas** from `src/shared/validation/schemas.ts`.
9. **Always include tests when changing production code** (`src/`, `open-sse/`, `electron/`, `bin/`).
10. **Coverage must stay** ≥ 75 % statements / 75 % lines / 75 % functions / 70 % branches (real measured: ~82 %).
## 3. Codebase navigation
| Task | Read this first |
| ----------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Understand the codebase | `docs/architecture/REPOSITORY_MAP.md` |
| Architecture overview | `docs/architecture/ARCHITECTURE.md` |
| Engineering reference | `docs/architecture/CODEBASE_DOCUMENTATION.md` |
| Add a feature | `CONTRIBUTING.md` + the matching `docs/<area>.md` |
| Per-area deep dives | `docs/frameworks/SKILLS.md`, `docs/frameworks/MEMORY.md`, `docs/frameworks/EVALS.md`, `docs/security/GUARDRAILS.md`, `docs/security/COMPLIANCE.md`, `docs/frameworks/CLOUD_AGENT.md`, `docs/frameworks/MCP-SERVER.md`, `docs/frameworks/A2A-SERVER.md`, `docs/architecture/AUTHZ_GUIDE.md`, `docs/architecture/RESILIENCE_GUIDE.md`, `docs/routing/AUTO-COMBO.md`, `docs/frameworks/WEBHOOKS.md`, `docs/routing/REASONING_REPLAY.md`, `docs/security/STEALTH_GUIDE.md`, `docs/ops/TUNNELS_GUIDE.md`, `docs/guides/ELECTRON_GUIDE.md`, `docs/reference/PROVIDER_REFERENCE.md` |
| Release flow | `docs/ops/RELEASE_CHECKLIST.md` |
## 4. Local development access
The dashboard is reachable at the operator's chosen URL/port (default `http://localhost:20128`). Credentials are operator-specific:
- **Initial admin password** is read from the `INITIAL_PASSWORD` env var on first install (defaults to `CHANGEME` in `.env.example`; rotate immediately after first login).
- **Local VPS / shared dev environments**: ask the operator for the URL and current credentials — they live in their personal vault, NOT in this repo.
> Any credential observed in a previous version of this file was a non-production demo value; treat it as compromised and do not reuse it.

View File

@@ -1,69 +0,0 @@
.PHONY: help install dev start build build-release lint typecheck typecheck-strict \
test test-unit test-vitest test-coverage test-all test-integration test-e2e \
check check-cycles check-docs env-sync clean
# OmniRoute — convenience wrapper around the npm scripts.
# All targets delegate to the canonical package.json scripts (single source of truth).
help: ## Show this help
@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?## "}; {printf " \033[36m%-18s\033[0m %s\n", $$1, $$2}'
install: ## Install dependencies (auto-generates .env from .env.example)
npm install
dev: ## Dev server at http://localhost:20128
npm run dev
start: ## Production server (requires a prior build)
npm run start
build: ## Production build (Next.js 16 standalone)
npm run build
build-release: ## Release build
npm run build:release
lint: ## ESLint (0 errors expected)
npm run lint
typecheck: ## TypeScript check (core)
npm run typecheck:core
typecheck-strict: ## Strict check (no implicit any)
npm run typecheck:noimplicit:core
test: ## Unit tests (Node native runner)
npm run test:unit
test-unit: ## Alias for `test`
npm run test:unit
test-vitest: ## Vitest (MCP server, autoCombo, cache)
npm run test:vitest
test-coverage: ## Unit tests + coverage gate (60/60/60/60)
npm run test:coverage
test-all: ## All suites (unit + vitest + ecosystem + e2e)
npm run test:all
test-integration: ## Integration tests
npm run test:integration
test-e2e: ## E2E (Playwright)
npm run test:e2e
check: ## lint + test combined
npm run check
check-cycles: ## Detect circular dependencies
npm run check:cycles
check-docs: ## Validate documentation (incl. fabricated-docs)
npm run check:docs-all
env-sync: ## Sync .env from .env.example
npm run env:sync
clean: ## Remove build artifacts
rm -rf .build dist coverage .eslintcache

1444
README.md

File diff suppressed because it is too large Load Diff

View File

@@ -1,96 +0,0 @@
---
title: "OmniRoute Roadmap"
version: 3.8.50
lastUpdated: 2026-08-06
---
# OmniRoute Roadmap
> Version-gated, not date-gated: each milestone ships when its quality gates pass.
> Current line: **v3.8.x** (this branch). Last updated: 2026-08-06.
OmniRoute is heading from a monolithic router to a **modular AI platform**: a lightweight
core engine, a typed SDK, and everything else as installable modules and plugins. The path
runs through a stabilization rail (3.8.50 → 3.8.59), an LTS anchor (**3.9.0**), and the
modular **4.0**.
## The rail at a glance
```
3.8.50 ─ 3.8.54 PREPARE non-breaking structural prep (all PRs welcome)
3.8.55 ─ 3.8.59 VALIDATE stabilization (fixes / docs / i18n / providers only)
3.9.0 LTS stable/v3 branch · long-term support line
4.0.0-nightly/rc MODULAR core + SDK + modules + marketplace (develop branch)
4.0.0 GA latest switches to v4 · v3 stays supported as LTS
```
## Phase 1 — Preparation (3.8.50 → 3.8.54)
Non-breaking structural work that de-risks the modular split. Every version closes with a
mandatory quality-gate battery before new merges open.
| Version | Focus |
| --- | --- |
| 3.8.50 | CI safety net on release branches · dead-code cleanup · community-reported catalog/topology bug fixes · contributor "golden path" guide |
| 3.8.51 | Executor registry (in-place) · end-to-end provider-journey contract test becomes a CI gate · official scoped-test dev loop · CI lane consolidation (shared install/setup across gate jobs, #8084) |
| 3.8.52 | `combo.ts` decomposition · routing-strategy registry · unified model-catalog contract for `/v1/models` · one CI policy for PRs to `release/**` and `main` (#8084) |
| 3.8.53 | `chatCore.ts` decomposition · headless mode (`OMNIROUTE_HEADLESS=1`) · local candidate build/promote loop |
| 3.8.54 | Release infrastructure (dormant): channels, labels, PR templates, merge queue · full-regression authority moves to the merge queue once TIA shadow evidence clears (#8084) · public feature-freeze announcement |
## Phase 2 — Validation (3.8.55 → 3.8.59)
**External feature PRs pause here** (they get the `v4-feature` label and are re-targeted to
the v4 channel when it opens). Fixes, docs, i18n, and provider updates keep flowing.
| Version | Focus |
| --- | --- |
| 3.8.55 | Characterization tests for every extraction candidate · coupling re-measurement |
| 3.8.56 | Extended canary · performance baselines (heap, TTFB, build) |
| 3.8.57 | Security & compliance sweep · publish provenance (OIDC) rehearsal |
| 3.8.58 | Full dry-run of the 3.9.0 cut (branches, channels, forward-port) — includes the PR preview-artifact + build-once promotion rehearsal (#8084) |
| 3.8.59 | Final freeze · full-suite audit · GO/NO-GO |
## Phase 3 — v3.9.0 LTS
After 3.8.59 the next version is **3.9.0** (there is no 3.8.60). It creates the long-lived
branch model:
- **`stable/v3`** — the LTS line (3.9.x). Receives fixes, security patches, and provider
updates. `npm install omniroute` (aka `latest`) stays on v3 during the whole v4 cycle.
- **`develop`** — v4 development, published as `4.0.0-nightly.*`.
- **`main`** — v4 release candidates (`next`) and, eventually, GA.
- Fixes merged to `stable/v3` are automatically forward-ported to `develop` with full
contributor credit (`Co-authored-by`).
New features land in the v4 channel. The LTS line is stability-first.
## Phase 4 — v4.0: the modular platform
The monolith is intentionally disassembled on `develop`:
- **`@omniroute/core`** (npm name stays `omniroute`) — just the engine: `/v1/*`, routing,
combo/fallback, providers.
- **`@omniroute/sdk`** — one typed contract: hooks, extension points, two-phase lifecycle,
UI contributions. The five extension systems that exist today (plugins, CLI plugins,
skills, MCP tools, A2A skills) collapse into one declarative manifest.
- **Modules** (`@omniroute/mod-*`) — cloud agents, traffic inspection (MITM), evals,
webhooks, memory, guardrails, observability and more move out of the core, each with its
own version and lifecycle.
- **Providers as plugins** — adding a provider stops touching the core.
- **Marketplace** — one-click install with verified integrity (hash pinning, signing,
sandbox). Free in v1; a paid tier later with revenue share for creators.
- Ships as `4.0.0-nightly.*``4.0.0-rc.N` (soak in production) → **4.0.0 GA**, when
`latest` switches to v4 and v3 enters its announced LTS support window.
**The core is MIT and free, forever.**
## For contributors
| You are sending... | Target today | From 3.8.55 | After 3.9.0 |
| --- | --- | --- | --- |
| Bug fix / security | active `release/v3.8.x` | same | `stable/v3` |
| Provider update | active `release/v3.8.x` | same | `stable/v3` |
| Docs / i18n | active `release/v3.8.x` | same | `stable/v3` |
| New feature | active `release/v3.8.x` | held with `v4-feature` label | `develop` (v4) |
See `CONTRIBUTING.md` for the golden path per change type.

View File

@@ -42,13 +42,13 @@ Request → CORS → Authz pipeline (classify → policies → enforce)
| --------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
| **Dashboard Login** | Password-based auth with JWT tokens (HttpOnly cookies) |
| **API Key Auth** | HMAC-signed keys with CRC validation |
| **OAuth 2.0 + PKCE** | Provider-specific browser/device OAuth uses PKCE where supported; import-only Devin credentials are handled separately. |
| **OAuth 2.0 + PKCE** | 14 providers (Claude, Codex, GitHub, Cursor, Antigravity, Gemini, Kimi Coding, Kilo Code, Cline, Qwen, Kiro, Qoder, Windsurf, GitLab Duo) |
| **Token Refresh** | Automatic OAuth token refresh before expiry |
| **Secure Cookies** | `AUTH_COOKIE_SECURE=true` for HTTPS environments |
| **Authz Pipeline** | Route classification (PUBLIC / CLIENT_API / MANAGEMENT) — see `docs/architecture/AUTHZ_GUIDE.md` |
| **Route Guard Tiers** | 3-tier model for management routes (LOCAL_ONLY / ALWAYS_PROTECTED / MANAGEMENT) — see `docs/security/ROUTE_GUARD_TIERS.md` |
| **Manage-Scope MCP** | Remote `/api/mcp/*` access gated by API keys with `manage` scope; `/api/cli-tools/runtime/*` stays strict-loopback. See ROUTE_GUARD_TIERS |
| **MCP Scopes** | 32 granular scopes (read:health, write:combos, execute:completions, etc.) — see `docs/frameworks/MCP-SERVER.md` |
| **MCP Scopes** | ~13 granular scopes (read:health, write:combos, execute:completions, etc.) — see `docs/frameworks/MCP-SERVER.md` |
### 🛡️ Encryption at Rest
@@ -77,28 +77,21 @@ Custom guardrails register via `registerGuardrail(new MyGuardrail())`. The model
### 🧠 Prompt Injection Guard
Best-effort heuristic middleware that detects prompt injection patterns in LLM requests.
**Not a complete prompt-injection firewall** — can produce false positives (benign
persona/RPG prompts) and false negatives (leetspeak, spacing, non-English patterns).
Middleware that detects and blocks prompt injection attacks in LLM requests:
| Pattern Type | Severity | Example |
| ------------------- | -------- | ---------------------------------------------- |
| System Override | High | "ignore all previous instructions" |
| Role Hijack | Medium | "you are now DAN, you can do anything" |
| Delimiter Injection | High | Encoded separators to break context boundaries |
| DAN/Jailbreak | Medium | Known jailbreak prompt patterns |
| Instruction Leak | High | "show me your system prompt" |
| Encoding Evasion | Medium | base64/rot13/hex decode + instruction keywords |
Only **High** severity detections are blocked in `block` mode. Medium-severity
families are logged but never blocked by `sanitizeRequest`.
| Role Hijack | High | "you are now DAN, you can do anything" |
| Delimiter Injection | Medium | Encoded separators to break context boundaries |
| DAN/Jailbreak | High | Known jailbreak prompt patterns |
| Instruction Leak | Medium | "show me your system prompt" |
Configure via dashboard (Settings → Security) or `.env`:
```env
INPUT_SANITIZER_ENABLED=true
INPUT_SANITIZER_MODE=block # warn | block (injection policy; legacy "redact" does not strip injection text)
INPUT_SANITIZER_BLOCK_THRESHOLD=high # high (default) | medium | low — severities at/above this are blocked in block mode
INPUT_SANITIZER_MODE=block # warn | block | redact
```
### 🔒 PII Redaction
@@ -115,20 +108,19 @@ Automatic detection and optional redaction of personally identifiable informatio
| SSN (US) | `123-45-6789` | `[SSN_REDACTED]` |
```env
PII_REDACTION_ENABLED=true # request PII rewrite; independent of INPUT_SANITIZER_MODE
PII_RESPONSE_SANITIZATION=true # optional: redact PII in provider responses returned to clients
PII_REDACTION_ENABLED=true
```
### 🌐 Network Security
| Feature | Description |
| ------------------------ | ------------------------------------------------------------------------------ |
| **CORS** | Explicit cross-origin allowlist (`CORS_ALLOWED_ORIGINS`; legacy `CORS_ORIGIN`) |
| **IP Filtering** | Allowlist/blocklist IP ranges in dashboard |
| **Rate Limiting** | Per-provider rate limits with automatic backoff |
| **Anti-Thundering Herd** | Mutex + per-connection locking prevents cascading 502s |
| **TLS Fingerprint** | Browser-like TLS fingerprint spoofing to reduce bot detection |
| **CLI Fingerprint** | Per-provider header/body ordering to match native CLI signatures |
| Feature | Description |
| ------------------------ | ---------------------------------------------------------------- |
| **CORS** | Configurable origin control (`CORS_ORIGIN` env var, default `*`) |
| **IP Filtering** | Allowlist/blocklist IP ranges in dashboard |
| **Rate Limiting** | Per-provider rate limits with automatic backoff |
| **Anti-Thundering Herd** | Mutex + per-connection locking prevents cascading 502s |
| **TLS Fingerprint** | Browser-like TLS fingerprint spoofing to reduce bot detection |
| **CLI Fingerprint** | Per-provider header/body ordering to match native CLI signatures |
### 🔌 Resilience & Availability

View File

@@ -1,26 +0,0 @@
# Third-Party Notices
## codex-chatgpt-web
Parts of `open-sse/vendor/codex-chatgpt-web/` are adapted from
[`miuuyy/codex-chatgpt-web`](https://github.com/miuuyy/codex-chatgpt-web), commit
`55592fca0ba19a27f1b769cec8fff61ff340a785`.
MIT License
Copyright (c) 2026 codex-chatgpt-web contributors
Permission is hereby granted, free of charge, to any person obtaining a copy of this software and
associated documentation files (the "Software"), to deal in the Software without restriction,
including without limitation the rights to use, copy, modify, merge, publish, distribute,
sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all copies or substantial
portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT
NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT
OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

View File

@@ -1,8 +1,8 @@
# bin/_ops-common.sh — shared helpers for the OmniRoute ops runbook scripts.
#
# Sourced (not executed) by rollback.sh / snapshot-data.sh / restore-data.sh /
# restore-policies.sh / cold-start-bench.sh — the self-hoster incident-recovery
# and cold-start ops tooling. Each script documents its own contract via --help.
# restore-policies.sh / cold-start-bench.sh. The runbook context lives in
# docs/INCIDENT_RESPONSE.md and docs/PERF_BUDGETS.md.
#
# Path resolution mirrors the app (src/lib/db/core.ts): the SQLite store is
# $DATA_DIR/storage.sqlite and managed backups go to $DATA_DIR/db_backups

View File

@@ -1,230 +0,0 @@
/**
* ESM path-alias resolver for global installs.
*
* Problem (#7791): when OmniRoute is installed via `npm i -g omniroute`, the
* package files live under `node_modules/omniroute/`. tsx's tsconfig-path
* resolution does not apply there, so specifiers like `@/shared/utils/featureFlags`
* (declared in tsconfig.json `paths` as `@/* → ./src/*`) or
* `@omniroute/open-sse/services/usage` fail with `ERR_MODULE_NOT_FOUND`.
* The CLI crashes before any command can run.
*
* Fix: register a Node ESM `resolve` hook that rewrites alias specifiers to
* absolute file URLs. Covers all tsconfig.json `paths` entries:
* - `@/*` → `./src/*`
* - `@omniroute/open-sse` → `./open-sse/index.ts`
* - `@omniroute/open-sse/*` → `./open-sse/*`
* The hook runs after tsx so `.ts` extensions are already handled, and only
* intercepts matched prefixes — everything else falls through to Node's
* default resolver.
*
* Exposed as pure functions so the mapping logic is unit-testable without a
* running module loader.
*/
import { existsSync, statSync } from "node:fs";
import { dirname, join, relative, isAbsolute } from "node:path";
import { fileURLToPath, pathToFileURL } from "node:url";
/**
* Alias mapping table — mirrors tsconfig.json `paths`.
* Processed top-to-bottom; first matching prefix wins.
*
* Each entry:
* prefix — specifier prefix to match (e.g. `"@/"`, `"@omniroute/open-sse/"`)
* target — directory name under the package root (e.g. `"src"`, `"open-sse"`)
* exact — if true, the prefix also matches when the specifier equals the
* prefix *without* a trailing slash (e.g. `@omniroute/open-sse` →
* `<root>/open-sse/index.ts`).
*
* Exported for tests/consumers.
*/
export const ALIAS_MAP = [
{ prefix: "@/", target: "src", exact: false },
{ prefix: "@omniroute/open-sse/", target: "open-sse", exact: false },
{ prefix: "@omniroute/open-sse", target: "open-sse", exact: true },
];
/** @deprecated Use ALIAS_MAP instead. Kept for backward compat. */
export const ALIAS_PREFIX = "@/";
// This file is ESM (no CJS __dirname global) — derive it from import.meta.url
// so the pathToFileURL(join(__dirname, ...)) call below resolves correctly
// regardless of the caller's cwd.
const __dirname = dirname(fileURLToPath(import.meta.url));
/**
* Resolve an alias specifier to an absolute file URL.
*
* Rules mirror tsconfig.json `paths` via `ALIAS_MAP`:
* "@/..." → <root>/src/...
* "@omniroute/open-sse/..." → <root>/open-sse/...
* "@omniroute/open-sse" → <root>/open-sse/index.*
*
* - Strips the matched alias prefix and joins the remainder against the
* corresponding target directory.
* - Probes the underlying filesystem for the actual source file: the specifier
* itself, then with common source extensions (`.ts`, `.tsx`, `.js`, `.mjs`,
* `.cjs`, `.json`), then `<dir>/index.*`. Returns the first existing match
* as a `file://` URL.
* - Returns `null` for specifiers that do not match any alias, for malformed
* escapes, for path-traversal attempts, or when no corresponding source
* file exists on disk. The caller treats `null` as "defer to the default
* resolver".
*
* @param {string} specifier Module specifier from an `import` statement.
* @param {string} root Absolute path to the package root.
* @returns {string|null} Absolute `file://` URL, or `null` when unresolved.
*/
const SOURCE_EXTENSIONS = [".ts", ".tsx", ".js", ".mjs", ".cjs", ".json"];
export function resolveAlias(specifier, root) {
if (typeof specifier !== "string" || !root || typeof root !== "string") {
return null;
}
// Find the first matching alias entry (top-to-bottom order).
let matchedEntry = null;
let rest = null;
for (const entry of ALIAS_MAP) {
if (specifier.startsWith(entry.prefix)) {
// For non-exact entries, require at least one char after the prefix
// to avoid matching bare "@/" as "nothing".
const after = specifier.slice(entry.prefix.length);
if (after.length === 0 && !entry.exact) continue;
matchedEntry = entry;
rest = after;
break;
}
}
if (!matchedEntry) return null;
const targetDir = join(root, matchedEntry.target);
// Exact match (e.g. `@omniroute/open-sse` with no trailing path) →
// resolve to `<target>/index.*`.
if (rest === "" || rest === undefined) {
return probeIndex(targetDir);
}
// Guard against absolute-ish escapes (`@//etc/passwd`, `@/\x00`).
if (rest.startsWith("/") || rest.startsWith("\\")) {
return null;
}
// Guard against path-traversal escapes (`@/../../../etc/hostname`).
const segments = rest.split(/[\\\/]+/);
if (segments.includes("..")) {
return null;
}
const base = join(targetDir, rest);
if (!isWithinRoot(targetDir, base)) {
return null;
}
return probeFile(base) ?? probeIndex(base) ?? null;
}
/**
* Probe a bare path and its extension variants. Returns the first existing
* match as a `file://` URL, or `null`.
*/
function probeFile(base) {
// Try extension variants first — a bare `base` that happens to be a directory
// would match existsSync() but should NOT be returned as a file URL (the
// caller expects a file, not a directory). Extension-probing avoids this
// false positive (e.g. `usage` vs `usage.ts` vs `usage/`).
for (const ext of SOURCE_EXTENSIONS) {
const candidate = base + ext;
if (existsSync(candidate)) return pathToFileURL(candidate).href;
}
// Only accept the bare path if it is NOT a directory.
if (existsSync(base)) {
try {
const st = statSync(base);
if (!st.isDirectory()) return pathToFileURL(base).href;
} catch {}
}
return null;
}
/**
* Probe a directory for an `index.*` entry. Returns the first existing
* match as a `file://` URL, or `null`.
*/
function probeIndex(dir) {
const indexBase = join(dir, "index");
for (const ext of SOURCE_EXTENSIONS) {
const candidate = indexBase + ext;
if (existsSync(candidate)) return pathToFileURL(candidate).href;
}
return null;
}
/**
* True when `candidate` resolves to a location inside `ancestor` (or is
* `ancestor` itself). Used as a second, path-normalization-aware layer of
* defense against traversal beyond the literal `..` segment check above.
*
* @param {string} ancestor
* @param {string} candidate
* @returns {boolean}
*/
function isWithinRoot(ancestor, candidate) {
const rel = relative(ancestor, candidate);
return rel === "" || (!rel.startsWith("..") && !isAbsolute(rel));
}
/**
* Register the ESM resolve hook for the current process. Safe to call multiple
* times — subsequent calls are no-ops once the hook is installed.
*
* Uses Node's stable `module.register()` API (available since Node 20.6,
* required Node 22+ here). The hook runs in a worker thread but only reads the
* captured `root`, so no shared-state hazards.
*
* @param {string} root Absolute path to the package root.
* @returns {Promise<boolean>} Resolves `true` once registered (or if already
* registered), `false` on environments where `module.register` is unavailable.
*/
let _registered = false;
export async function registerAliasResolver(root) {
// Validate input FIRST, before the _registered short-circuit. Otherwise the
// second call in the same process (e.g. a test suite that already registered
// once) would silently return `true` for invalid input instead of rejecting,
// masking programmer errors. Input validation must be unconditional.
if (!root || typeof root !== "string") {
throw new TypeError("registerAliasResolver: root must be a non-empty string");
}
if (_registered) return true;
// if the directory does not exist we would only mask a real misconfiguration
// by installing a hook that rewrites to nowhere.
if (!existsSync(join(root, "src"))) {
return false;
}
try {
const { register } = await import("node:module");
// #7808: load the hook from a real file on disk via pathToFileURL() instead
// of building a `data:text/javascript,...` URL dynamically. CodeQL's
// `js/incomplete-url-substring-sanitization` flagged the interpolated
// `new URL(...)` call; a file URL produced by pathToFileURL() is a trusted,
// fully-parsed URL — no sanitization ambiguity. The hook source lives in
// `bin/aliasResolverHook.mjs` (sibling of this file), shipped via
// package.json "files": ["bin/"].
const hookPath = join(__dirname, "aliasResolverHook.mjs");
const hookUrl = pathToFileURL(hookPath);
register(hookUrl, { data: { root } });
_registered = true;
return true;
} catch {
// Older Node or sandboxed env without module.register — fall back to the
// default resolver. The bug will resurface only in the exact global-install
// scenario, which is what we explicitly patched; other entry points still
// work because they import via relative paths.
return false;
}
}
// #7808: the ESM loader hook source now lives in `bin/aliasResolverHook.mjs`,
// loaded via `pathToFileURL()` above. The previous inline `HOOK_SOURCE` template
// literal was removed because its `new URL(\`data:text/javascript,...\`)` wrapper
// triggered CodeQL `js/incomplete-url-substring-sanitization`. The hook logic
// itself is unchanged — see aliasResolverHook.mjs for the resolver behaviour.

View File

@@ -1,126 +0,0 @@
/**
* ESM loader hook for path-alias resolution (#7791 + #7808).
*
* This file runs in Node's loader worker thread after being registered via
* `module.register(url, data)` from `bin/aliasResolver.mjs`. It MUST NOT import
* anything from the parent module — all inputs arrive through `initialize(data)`.
*
* Behaviour:
* - Rewrites alias specifiers to absolute filesystem paths, mirroring
* tsconfig.json `paths`:
* - `@/*` → <root>/src/*
* - `@omniroute/open-sse` → <root>/open-sse/index.*
* - `@omniroute/open-sse/*` → <root>/open-sse/*
* - Probes the usual source extensions (`.ts`, `.tsx`, `.js`, `.mjs`, `.cjs`,
* `.json`) plus `index.*` for directory imports.
* - Returns `shortCircuit: true` only when a candidate file exists on disk;
* otherwise delegates to the next resolver (tsx/Node) so unrelated imports
* and legitimate "module not found" errors pass through unchanged.
*
* Why a separate file instead of an inline `data:` URL?
* CodeQL's `js/incomplete-url-substring-sanitization` flags dynamic `new URL(...)`
* construction with interpolated strings. A real file URL produced by
* `pathToFileURL()` is a trusted, fully-parsed URL — no sanitization ambiguity.
*/
import { pathToFileURL } from "node:url";
import { join, relative, isAbsolute } from "node:path";
import { existsSync, statSync } from "node:fs";
let ROOT = "";
export function initialize(data) {
ROOT = (data && data.root) || "";
}
const EXTENSIONS = [".ts", ".tsx", ".js", ".mjs", ".cjs", ".json"];
/**
* Alias prefix table — mirrors ALIAS_MAP in aliasResolver.mjs and
* tsconfig.json `paths`. Processed top-to-bottom; first match wins.
*
* @type {Array<{prefix: string, target: string, exact: boolean}>}
*/
const ALIAS_TABLE = [
{ prefix: "@/", target: "src", exact: false },
{ prefix: "@omniroute/open-sse/", target: "open-sse", exact: false },
{ prefix: "@omniroute/open-sse", target: "open-sse", exact: true },
];
function tryResolveAliasFsPath(specifier) {
if (!ROOT || typeof specifier !== "string") return null;
// Find the first matching alias entry.
let matchedEntry = null;
let rest = null;
for (const entry of ALIAS_TABLE) {
if (specifier.startsWith(entry.prefix)) {
const after = specifier.slice(entry.prefix.length);
if (after.length === 0 && !entry.exact) continue;
matchedEntry = entry;
rest = after;
break;
}
}
if (!matchedEntry) return null;
const targetDir = join(ROOT, matchedEntry.target);
// Exact match (e.g. `@omniroute/open-sse`) → resolve to `<target>/index.*`.
if (rest === "" || rest === undefined) {
return probeIndex(targetDir);
}
// Guard against absolute-ish escapes.
if (rest.startsWith("/") || rest.startsWith("\\")) return null;
// Guard against path-traversal escapes.
const segments = rest.split(/[\\\/]+/);
if (segments.includes("..")) return null;
const base = join(targetDir, rest);
if (!isWithinRoot(targetDir, base)) return null;
return probeFile(base) ?? probeIndex(base) ?? null;
}
function probeFile(base) {
// Extension variants first — avoids matching a bare directory name.
for (const ext of EXTENSIONS) {
const candidate = base + ext;
if (existsSync(candidate)) return candidate;
}
if (existsSync(base)) {
try {
const st = statSync(base);
if (!st.isDirectory()) return base;
} catch {}
}
return null;
}
function probeIndex(dir) {
const indexBase = join(dir, "index");
for (const ext of EXTENSIONS) {
const candidate = indexBase + ext;
if (existsSync(candidate)) return candidate;
}
return null;
}
/**
* True when `candidate` resolves to a location inside `ancestor` (or is
* `ancestor` itself). Path-normalization-aware defense against traversal.
*/
function isWithinRoot(ancestor, candidate) {
const rel = relative(ancestor, candidate);
return rel === "" || (!rel.startsWith("..") && !isAbsolute(rel));
}
export function resolve(specifier, context, nextResolve) {
const fsPath = tryResolveAliasFsPath(specifier);
if (fsPath) {
return {
url: pathToFileURL(fsPath).href,
shortCircuit: true,
};
}
return nextResolve(specifier, context);
}

View File

@@ -1,56 +0,0 @@
#!/usr/bin/env node
import { existsSync } from "node:fs";
import { dirname, join } from "node:path";
import { fileURLToPath, pathToFileURL } from "node:url";
const here = dirname(fileURLToPath(import.meta.url));
const root = join(here, "..");
export function resolveChatGptWebCodexMcpEntry(rootDir = root, exists = existsSync) {
const candidates = [
join(
rootDir,
"dist",
"open-sse",
"vendor",
"codex-chatgpt-web",
"adapters",
"chatgpt-web",
"mcp-server.js"
),
join(
rootDir,
"open-sse",
"vendor",
"codex-chatgpt-web",
"adapters",
"chatgpt-web",
"mcp-server.ts"
),
];
return candidates.find((candidate) => exists(candidate)) ?? null;
}
export async function startChatGptWebCodexMcp(args = process.argv.slice(2), rootDir = root) {
const socketIndex = args.indexOf("--broker-socket");
const brokerSocketPath = socketIndex >= 0 ? args[socketIndex + 1] : undefined;
if (!brokerSocketPath) throw new Error("--broker-socket is required");
const entry = resolveChatGptWebCodexMcpEntry(rootDir);
if (!entry) throw new Error("ChatGPT Web (Codex) MCP entrypoint was not found");
if (entry.endsWith(".ts")) {
const { register } = await import("node:module");
register("tsx/esm", pathToFileURL(`${rootDir}/`));
}
const module = await import(pathToFileURL(entry).href);
await module.runChatGptMcpServer({ brokerSocketPath });
}
if (process.argv[1] && fileURLToPath(import.meta.url) === process.argv[1]) {
startChatGptWebCodexMcp().catch((error) => {
console.error(
`ChatGPT Web (Codex) MCP konnte nicht gestartet werden: ${error?.message || error}`
);
process.exit(1);
});
}

View File

@@ -136,7 +136,7 @@ export const RETRY_DEFAULTS = {
- Every user-facing string goes through `t("module.key", vars)`.
- Catalogs live in `bin/cli/locales/{locale}.json` (nested objects).
43 files ship out-of-the-box: `en`, `pt-BR`, and 41 additional locales.
42 files ship out-of-the-box: `en`, `pt-BR`, and 40 additional locales.
11 locales are scaffold-only (empty `{}`); all keys fall back to `en` automatically.
- Detection order: `--lang` flag → `OMNIROUTE_LANG` env → `LC_ALL``LC_MESSAGES``LANG``en`.
- Locale persisted via `config lang set <code>` — saves `OMNIROUTE_LANG` to `~/.omniroute/.env`.

View File

@@ -22,9 +22,9 @@ bin/cli/
├── provider-test.mjs ← testProviderApiKey()
├── settings-store.mjs ← DB CRUD for key_value settings
├── locales/
│ ├── en.json ← English strings (source of truth, 43 locales)
│ ├── en.json ← English strings (source of truth, 42+ locales)
│ ├── pt-BR.json ← Portuguese (Brazil) — fully translated
│ └── {locale}.json ← 42 additional locales (ar, az, de, es, fr, ja, zh-CN, …)
│ └── {locale}.json ← 40 additional locales (ar, az, de, es, fr, ja, zh-CN, …)
├── scripts/
│ └── generate-locales.mjs ← scaffold new locale files from config/i18n.json
└── commands/

View File

@@ -1,163 +0,0 @@
import { chmodSync, existsSync, writeFileSync } from "node:fs";
import { decryptCredential } from "../encryption.mjs";
import { findProviderConnection, listProviderConnections } from "../provider-store.mjs";
import { openOmniRouteDb } from "../sqlite.mjs";
import { t } from "../i18n.mjs";
/**
* Local-only, operator-invoked command that dumps DECRYPTED provider credentials
* (apiKey/accessToken/refreshToken/idToken). This never runs inside the HTTP server
* process and must never be reachable over the network — no src/app/api/ route wraps
* this. See docs/security/ for the threat-model writeup referenced in issue #6683.
*/
const CREDENTIAL_FIELDS = [
{ key: "apiKey", envSuffix: "API_KEY" },
{ key: "accessToken", envSuffix: "ACCESS_TOKEN" },
{ key: "refreshToken", envSuffix: "REFRESH_TOKEN" },
{ key: "idToken", envSuffix: "ID_TOKEN" },
];
const VALID_FORMATS = new Set(["json", "env"]);
const SECURE_FILE_MODE = 0o600;
export function registerAuthExport(program) {
program
.command("auth export")
.description(t("authExport.description"))
.option("--id <id>", t("authExport.idOpt"))
.option("--format <format>", t("authExport.formatOpt"), "json")
.option("--out <file>", t("authExport.outOpt"))
.option("--force", t("authExport.forceOpt"))
.action(async (opts, cmd) => {
const globalOpts = cmd.optsWithGlobals();
const exitCode = await runAuthExportCommand({ ...opts, ...globalOpts });
if (exitCode !== 0) process.exit(exitCode);
});
}
export async function runAuthExportCommand(opts = {}) {
// Security control (a): confirmation gate BEFORE any DB access — a dry invocation
// never opens the database and never decrypts anything.
if (!opts.force) {
printConfirmationGate();
return 0;
}
const format = opts.format || "json";
if (!VALID_FORMATS.has(format)) {
console.error(t("authExport.invalidFormat", { format }));
return 1;
}
if (!process.env.STORAGE_ENCRYPTION_KEY) {
console.error(t("authExport.missingKey"));
return 1;
}
// Security control (b): stderr warning banner BEFORE any plaintext is emitted.
process.stderr.write(t("authExport.warning") + "\n");
const rows = await loadTargetConnections(opts.id);
if (rows === null) {
console.error(t("authExport.notFound", { id: opts.id }));
return 1;
}
const exported = rows.map(exportConnection);
const content = format === "env" ? formatAsEnv(exported) : formatAsJson(exported);
if (opts.out) {
writeSecureFile(opts.out, content);
} else {
console.log(content);
}
return 0;
}
function printConfirmationGate() {
console.log(
`\n${t("authExport.confirmHeading")}\n\n${t("authExport.confirmBody")}\n\n${t("authExport.confirmFooter")}\n`
);
}
async function loadTargetConnections(id) {
const { db } = await openOmniRouteDb();
try {
if (!id) return listProviderConnections(db);
const connection = findProviderConnection(db, id);
return connection ? [connection] : null;
} finally {
db.close();
}
}
function decryptField(rawValue) {
// Security control (d): a per-field decrypt failure surfaces as a boolean flag,
// never the caught error text. Security control (e): the caught error is never
// interpolated into any message.
try {
return { value: decryptCredential(rawValue), failed: false };
} catch {
return { value: null, failed: true };
}
}
function exportConnection(connection) {
const result = {
id: connection.id,
provider: connection.provider,
name: connection.name,
authType: connection.authType,
};
for (const { key } of CREDENTIAL_FIELDS) {
const rawValue = connection[key];
if (!rawValue) {
result[key] = null;
result[`${key}DecryptFailed`] = false;
continue;
}
const { value, failed } = decryptField(rawValue);
result[key] = value;
result[`${key}DecryptFailed`] = failed;
}
return result;
}
function formatAsJson(rows) {
return JSON.stringify(rows, null, 2);
}
function envSafeSegment(value) {
return String(value || "")
.toUpperCase()
.replace(/[^A-Z0-9]+/g, "_")
.replace(/^_+|_+$/g, "");
}
function formatAsEnv(rows) {
const lines = [];
for (const row of rows) {
lines.push(`# ${row.provider} (${row.id})`);
const providerSegment = envSafeSegment(row.provider);
for (const { key, envSuffix } of CREDENTIAL_FIELDS) {
const value = row[key];
if (!value) continue;
lines.push(`OMNIROUTE_${providerSegment}_${envSuffix}=${value}`);
}
}
return lines.join("\n");
}
function writeSecureFile(filePath, content) {
// Security control (c): file output written with mode 0o600 (plus chmodSync if the
// file pre-existed, belt-and-suspenders against an already world-readable file).
const preExisted = existsSync(filePath);
writeFileSync(filePath, content, { mode: SECURE_FILE_MODE });
if (preExisted) {
chmodSync(filePath, SECURE_FILE_MODE);
}
}

View File

@@ -78,15 +78,18 @@ export function registerBackup(program) {
if (exitCode !== 0) process.exit(exitCode);
});
// Legacy: `omniroute backup` without a subcommand still creates a backup
// (documented as the canonical usage in USER_GUIDE.md / CLI-TOOLS.md /
// AGENT-SKILLS.md). No flags are declared here — declaring the same
// option names as `create`/`auto enable` here previously shadowed them
// (#8512), and no doc shows `omniroute backup` invoked with flags.
// Legacy: `omniroute backup` without subcommand still creates a backup
backup.action(async (opts) => {
const exitCode = await runBackupCommand(opts);
if (exitCode !== 0) process.exit(exitCode);
});
backup
.option("--name <name>", t("backup.nameOpt"))
.option("--cloud", t("backup.cloudOpt"))
.option("--encrypt", t("backup.encryptOpt"))
.option("--key-file <path>", t("backup.keyFileOpt"))
.option("--exclude <pattern>", t("backup.excludeOpt"), (v, prev = []) => [...prev, v], [])
.option("--retention <n>", t("backup.retentionOpt"), parseInt);
}
export function registerRestore(program) {

View File

@@ -15,11 +15,7 @@ function readCache() {
try {
const raw = JSON.parse(readFileSync(cachePath(), "utf8"));
if (raw && typeof raw.ts === "number" && Date.now() - raw.ts < CACHE_TTL_MS) return raw;
} catch (err) {
if (process.env.OMNIROUTE_DEBUG_COMPLETION) {
console.error("[omniroute completion] readCache failed:", err?.message ?? err);
}
}
} catch {}
return null;
}
@@ -45,20 +41,12 @@ async function refreshCache(opts = {}) {
const j = await mr.value.json();
models = (Array.isArray(j) ? j : j.data || []).map((m) => m.id).filter(Boolean);
}
} catch (err) {
if (process.env.OMNIROUTE_DEBUG_COMPLETION) {
console.error("[omniroute completion] refreshCache failed:", err?.message ?? err);
}
}
} catch {}
const data = { combos, providers, models, ts: Date.now() };
try {
mkdirSync(dirname(cachePath()), { recursive: true });
writeFileSync(cachePath(), JSON.stringify(data));
} catch (err) {
if (process.env.OMNIROUTE_DEBUG_COMPLETION) {
console.error("[omniroute completion] writeCache failed:", err?.message ?? err);
}
}
} catch {}
return data;
}

View File

@@ -24,7 +24,7 @@ async function restCompressionStatus() {
const combosBody = combosRes.ok ? await combosRes.json() : { combos: [] };
const analytics = analyticsRes && analyticsRes.ok ? await analyticsRes.json() : null;
return {
strategy: settings.defaultMode || "standard",
engine: settings.engine ?? null,
settings,
combos: combosBody.combos ?? combosBody,
analytics,
@@ -33,10 +33,7 @@ async function restCompressionStatus() {
async function restCompressionConfigure(config) {
const body = { ...config };
if (body.strategy) {
body.defaultMode = body.strategy === "caveman" ? "standard" : normalizeEngine(body.strategy);
delete body.strategy;
}
if (body.engine) body.engine = normalizeEngine(body.engine);
const res = await apiFetch("/api/settings/compression", { method: "PUT", body });
if (!res.ok) {
process.stderr.write(`Error: ${res.status}\n`);
@@ -46,10 +43,9 @@ async function restCompressionConfigure(config) {
}
async function restSetEngine(name) {
const normalized = normalizeEngine(name);
const res = await apiFetch("/api/settings/compression", {
method: "PUT",
body: { defaultMode: normalized === "caveman" ? "standard" : normalized },
body: { engine: normalizeEngine(name) },
});
if (!res.ok) {
process.stderr.write(`Error: ${res.status}\n`);
@@ -107,11 +103,7 @@ export async function runCompressionStatus(opts, cmd) {
export async function runCompressionConfigure(opts, cmd) {
const config = {};
// #6571 — both the MCP tool schema (compressionConfigureInput) and
// handleCompressionConfigure expect `strategy`, not `engine`; a non-strict
// MCP schema silently strips an unrecognized `engine` key on the primary
// (MCP-mounted) path, so this must be `strategy` on both paths.
if (opts.engine) config.strategy = normalizeEngine(opts.engine);
if (opts.engine) config.engine = opts.engine;
if (opts.cavemanAggressiveness !== undefined)
config.caveman = { aggressiveness: opts.cavemanAggressiveness };
if (opts.rtkBudget !== undefined) config.rtk = { tokenBudget: opts.rtkBudget };
@@ -171,7 +163,7 @@ export function registerCompression(program) {
engine.command("set <name>").action(runCompressionEngineSet);
engine.command("get").action(async (opts, cmd) => {
const data = await mcpCall("omniroute_compression_status", {}, restCompressionStatus);
process.stdout.write(`${data.strategy ?? "(default)"}\n`);
process.stdout.write(`${data.engine ?? "(default)"}\n`);
});
const combos = cmp.command("combos").description(t("compression.combos.description"));

View File

@@ -1,22 +1,17 @@
import { execFile } from "node:child_process";
import { t } from "../i18n.mjs";
function parsePort(value, fallback) {
const parsed = parseInt(String(value), 10);
return Number.isFinite(parsed) && parsed > 0 && parsed <= 65535 ? parsed : fallback;
}
export function registerDashboard(program) {
program
.command("dashboard")
.description(t("dashboard.description"))
.option("--url", t("dashboard.urlOnly"))
.option("--port <port>", "Port the server is running on")
.option("--port <port>", "Port the server is running on", "20128")
.option("--tui", t("dashboard.tui") || "Open interactive TUI dashboard (terminal UI)")
.action(async (opts, cmd) => {
if (opts.tui) {
const globalOpts = cmd.optsWithGlobals();
const port = parsePort(opts.port ?? process.env.PORT ?? "20128", 20128);
const port = opts.port ? parseInt(String(opts.port), 10) : 20128;
const baseUrl = globalOpts.baseUrl ?? `http://localhost:${port}`;
const apiKey = globalOpts.apiKey ?? null;
const { startInteractiveTui } = await import("../tui/Dashboard.jsx");
@@ -29,7 +24,7 @@ export function registerDashboard(program) {
}
export async function runDashboardCommand(opts = {}) {
const port = parsePort(opts.port ?? process.env.PORT ?? "20128", 20128);
const port = opts.port ? parseInt(String(opts.port), 10) : 20128;
const dashboardUrl = `http://localhost:${port}`;
if (opts.url) {
@@ -49,22 +44,22 @@ export async function runDashboardCommand(opts = {}) {
return 0;
}
/**
* Resolve the command and args to open a URL in the default browser
* for a given platform. Exported for testing — callers should use openFallback().
* @param {"darwin"|"win32"|string} platform
* @param {string} url
* @returns {{ cmd: string, args: string[] }}
*/
export function resolveOpenCommand(platform, url) {
if (platform === "darwin") return { cmd: "open", args: [url] };
if (platform === "win32") return { cmd: "rundll32", args: ["url.dll,FileProtocolHandler", url] };
return { cmd: "xdg-open", args: [url] };
}
function openFallback(url) {
return new Promise((resolve) => {
const { cmd, args } = resolveOpenCommand(process.platform, url);
const { platform } = process;
let cmd, args;
if (platform === "darwin") {
cmd = "open";
args = [url];
} else if (platform === "win32") {
cmd = "cmd";
args = ["/c", "start", "", url];
} else {
cmd = "xdg-open";
args = [url];
}
execFile(cmd, args, { stdio: "ignore" }, () => resolve());
});
}

View File

@@ -3,7 +3,7 @@ import net from "node:net";
import os from "node:os";
import path from "node:path";
import { createDecipheriv, scryptSync } from "node:crypto";
import { fileURLToPath, pathToFileURL } from "node:url";
import { pathToFileURL } from "node:url";
import { resolveDataDir, resolveStoragePath } from "../data-dir.mjs";
import { printHeading } from "../io.mjs";
import { t } from "../i18n.mjs";
@@ -299,15 +299,6 @@ async function checkNativeBinary(rootDir) {
"Release",
"better_sqlite3.node"
),
path.join(
rootDir,
"dist",
"node_modules",
"better-sqlite3",
"build",
"Release",
"better_sqlite3.node"
),
path.join(rootDir, "node_modules", "better-sqlite3", "build", "Release", "better_sqlite3.node"),
];
const binaryPath = candidates.find((candidate) => fs.existsSync(candidate));
@@ -389,74 +380,24 @@ function resolveLivenessUrl(options = {}) {
return `http://${formatHostForUrl(host || "127.0.0.1")}:${dashboardPort}/api/health/degradation`;
}
async function probeUrl(url) {
try {
const response = await fetchWithTimeout(url);
return { ok: response.ok, status: response.status };
} catch {
return { ok: false, status: 0 };
}
}
async function checkServerLiveness(options = {}) {
const url = resolveLivenessUrl(options);
// First attempt: configured health endpoint (may require auth token).
const primary = await probeUrl(url);
if (primary.ok) {
return ok("Server liveness", "Server health endpoint is reachable", {
url,
status: primary.status,
});
}
// #6162: /api/health and /api/health/degradation require a management token.
// When unauthenticated, fall back to probing a publicly served static asset
// (favicon.ico) to confirm the Next.js server is alive and reachable.
// Derive the fallback URL from the primary URL (preserving protocol/host/port)
// so custom liveness URL configurations are honored. Fall back to defaults
// only if the primary URL can't be parsed.
let fallbackUrl;
try {
const parsed = new URL(url);
parsed.pathname = "/favicon.ico";
parsed.search = "";
parsed.hash = "";
fallbackUrl = parsed.toString();
const response = await fetchWithTimeout(url);
if (!response.ok) {
return warn("Server liveness", `Server responded with HTTP ${response.status}`, { url });
}
return ok("Server liveness", "Server health endpoint is reachable", { url });
} catch {
const port = parsePort(process.env.PORT || "20128", 20128);
const dashboardPort = parsePort(process.env.DASHBOARD_PORT || String(port), port);
const host = String(options.livenessHost || process.env.OMNIROUTE_DOCTOR_HOST || "127.0.0.1")
.trim()
.replace(/^https?:\/\//, "")
.replace(/\/.*$/, "");
fallbackUrl = `http://${formatHostForUrl(host || "127.0.0.1")}:${dashboardPort}/favicon.ico`;
return warn("Server liveness", "Server health endpoint is not reachable", { url });
}
const fallback = await probeUrl(fallbackUrl);
if (fallback.ok) {
return ok(
"Server liveness",
`Server reachable (health endpoint returned ${primary.status}, likely requires MANAGEMENT_TOKEN)`,
{
primaryUrl: url,
primaryStatus: primary.status,
fallbackUrl,
fallbackStatus: fallback.status,
}
);
}
return warn(
"Server liveness",
`Server health endpoint returned HTTP ${primary.status || "no-response"} and fallback probe failed`,
{ primaryUrl: url, primaryStatus: primary.status, fallbackUrl, fallbackStatus: fallback.status }
);
}
export async function collectDoctorChecks(context = {}, options = {}) {
const rootDir =
context.rootDir || path.resolve(path.dirname(fileURLToPath(import.meta.url)), "..", "..", "..");
context.rootDir ||
path.resolve(path.dirname(new URL(import.meta.url).pathname), "..", "..", "..");
const dataDir = resolveDataDir();
const dbPath = resolveStoragePath(dataDir);

View File

@@ -48,11 +48,7 @@ export async function runHealthCommand(opts = {}) {
}
try {
const res = await apiFetch("/api/monitoring/health", {
retry: false,
timeout: 5000,
acceptNotOk: true,
});
const res = await apiFetch("/api/health", { retry: false, timeout: 5000, acceptNotOk: true });
if (!res.ok) {
console.error(t("common.error", { message: `HTTP ${res.status}` }));
return 1;
@@ -70,22 +66,29 @@ export async function runHealthCommand(opts = {}) {
if (health.uptime) console.log(t("health.uptime", { uptime: health.uptime }));
if (health.version) console.log(` Version: ${health.version}`);
if (health.activeConnections !== undefined) {
console.log(t("health.requests", { count: health.activeConnections }));
if (health.requests !== undefined) {
console.log(t("health.requests", { count: health.requests }));
}
if (health.circuitBreakers && opts.verbose) {
if (health.breakers && opts.verbose) {
console.log("\n \x1b[1mCircuit Breakers\x1b[0m");
const { open = 0, halfOpen = 0, closed = 0 } = health.circuitBreakers;
console.log(` \x1b[32m● closed\x1b[0m ${closed}`);
console.log(` \x1b[33m○ half-open\x1b[0m ${halfOpen}`);
console.log(` \x1b[31m○ open\x1b[0m ${open}`);
for (const [name, status] of Object.entries(health.breakers)) {
const state =
status.state === "closed" ? "\x1b[32m● closed\x1b[0m" : "\x1b[33m○ open\x1b[0m";
console.log(` ${name.padEnd(20)} ${state}`);
}
}
if (opts.verbose && health.memoryUsage) {
if (health.cache && opts.verbose) {
console.log("\n \x1b[1mCache\x1b[0m");
console.log(` Semantic hits: ${health.cache.semanticHits || 0}`);
console.log(` Signature hits: ${health.cache.signatureHits || 0}`);
}
if (opts.verbose && health.memory) {
console.log("\n \x1b[1mMemory\x1b[0m");
console.log(` RSS: ${health.memoryUsage.rss || "N/A"}`);
console.log(` Heap used: ${health.memoryUsage.heapUsed || "N/A"}`);
console.log(` RSS: ${health.memory.rss || "N/A"}`);
console.log(` Heap used: ${health.memory.heapUsed || "N/A"}`);
}
return 0;
@@ -97,17 +100,13 @@ export async function runHealthCommand(opts = {}) {
export async function runHealthComponentsCommand(opts = {}) {
try {
const res = await apiFetch("/api/monitoring/health", {
retry: false,
timeout: 5000,
acceptNotOk: true,
});
const res = await apiFetch("/api/health", { retry: false, timeout: 5000, acceptNotOk: true });
if (!res.ok) {
console.error(`HTTP ${res.status}`);
return 1;
}
const health = await res.json();
const components = health.components || health.circuitBreakers || {};
const components = health.components || health.breakers || {};
for (const [name, info] of Object.entries(components)) {
const status =
typeof info === "object" ? info.state || info.status || "unknown" : String(info);

View File

@@ -1,36 +1,6 @@
import { spawn, execFileSync } from "node:child_process";
import { spawn } from "node:child_process";
import { t } from "../i18n.mjs";
import { resolveActiveContext } from "../contexts.mjs";
import { quoteShellArgs } from "../utils/winShellArgs.mjs";
/**
* Probe PATH for a Windows executable via `where.exe`, preferring a `.exe` over
* a `.cmd`/`.bat` shim. Returns the absolute path to the preferred binary, or
* `null` when `where.exe` finds nothing (or cannot run). Mirrors the same probe
* in launch.mjs and `locateCommand()` in `src/shared/services/cliRuntime.ts`.
*
* @param {string} command bare command name to look up
* @returns {Promise<string|null>} absolute path to the preferred match, or null
*/
function probeWindowsBinary(command) {
try {
const out = execFileSync("where.exe", [command], {
stdio: ["ignore", "pipe", "ignore"],
encoding: "utf8",
timeout: 3000,
windowsHide: true,
});
const lines = out
.split(/\r?\n/)
.map((l) => l.trim())
.filter(Boolean);
if (lines.length === 0) return null;
const winExt = /\.(exe|cmd|bat|com)$/i;
return lines.find((l) => winExt.test(l)) || null;
} catch {
return null;
}
}
/** OpenAI/Codex env keys stripped from the child so a stale OpenAI key/base-url
* in the shell can't shadow the omniroute provider (defense-in-depth). Mirrors
@@ -49,47 +19,6 @@ const STRIPPED_CODEX_ENV_KEYS = [
/** Placeholder so codex's `env_key` is always satisfied when the backend is open. */
const NO_AUTH_SENTINEL = "omniroute-no-auth";
// On Windows the `codex` binary is an npm `.cmd` shim that `spawn` cannot resolve
// without a shell (bare "codex" → ENOENT). Mirror the qodercli Windows fix (#6263):
// spawn `codex.cmd` through a shell on win32, and the bare binary elsewhere.
//
// #9454: the native codex installer may ship a real `codex.exe` instead of the
// npm `.cmd` shim. Probe PATH for `codex` first: when `where.exe` resolves a
// `.exe`, spawn it directly (no shell — cmd.exe would split an absolute path
// with spaces); otherwise fall back to `codex.cmd` + shell. Off Windows the bare
// binary is spawned unchanged (no shell, no probe).
/**
* @param {NodeJS.Platform|string} platform
* @param {{ probe?: (command: string) => Promise<string|null> }} [opts] injectable probe for tests
* @returns {Promise<{ command: string, shell: true|undefined }>}
*/
export async function resolveCodexSpawn(platform, opts = {}) {
if (platform !== "win32") return { command: "codex", shell: undefined };
const probe = opts.probe ?? probeWindowsBinary;
const located = await probe("codex");
if (located && /\.exe$/i.test(located)) {
return { command: located, shell: undefined };
}
return { command: "codex.cmd", shell: true };
}
/**
* `shell: true` makes Node join argv with plain spaces and no escaping (the
* DEP0190 warning). That mangles every launch-codex invocation on Windows, not
* just the ones with a multi-word user argument: the injected `-c` provider
* flags carry TOML values whose quotes cmd.exe strips
* (`model_providers.omniroute.name="OmniRoute"` arrives unquoted and no longer
* parses as TOML). Quote the args ourselves on that path; off Windows there is
* no shell, so argv is passed through untouched. Same fix as `launch` (#8837).
*
* @param {string[]} args
* @param {NodeJS.Platform|string} platform
* @returns {string[]}
*/
export function quoteCodexArgs(args, platform) {
return quoteShellArgs(args, platform);
}
function stripTrailingSlash(value) {
let s = String(value);
let end = s.length;
@@ -197,10 +126,10 @@ export async function runLaunchCodexCommand(opts = {}, codexArgs = []) {
if (!(await healthCheck(baseUrl))) {
console.error(
(
t("launch.notRunning") ||
"OmniRoute is not reachable at {port}. Start it with 'omniroute serve'."
).replace("{port}", baseUrl)
(t("launch.notRunning") || "OmniRoute is not reachable at {port}. Start it with 'omniroute serve'.").replace(
"{port}",
baseUrl
)
);
return 1;
}
@@ -212,14 +141,8 @@ export async function runLaunchCodexCommand(opts = {}, codexArgs = []) {
const extraArgs = [...providerArgs, ...profileArgs, ...codexArgs];
const env = buildCodexEnv(process.env, authToken);
const { command: codexLaunch, shell: shellValue } = await resolveCodexSpawn(process.platform);
return await new Promise((resolve) => {
const child = spawn(codexLaunch, quoteCodexArgs(extraArgs, process.platform), {
env,
stdio: "inherit",
shell: shellValue,
});
const child = spawn("codex", extraArgs, { env, stdio: "inherit" });
child.on("error", (err) => {
if (err?.code === "ENOENT") {
console.error(
@@ -242,25 +165,16 @@ export function registerLaunchCodex(program) {
t("launchCodex.description") || "Launch Codex CLI pointed at OmniRoute (local or remote VPS)"
)
.option("--port <port>", "Local OmniRoute port (ignored when --remote is set)", "20128")
.option(
"--remote <url>",
"Remote OmniRoute base URL, e.g. http://192.168.0.15:20128 (overrides --port + context)"
)
.option("--remote <url>", "Remote OmniRoute base URL, e.g. http://192.168.0.15:20128 (overrides --port + context)")
.option("--profile <name>", "Codex profile to activate (passed as --profile <name>)")
.option("-p, --p <name>", "Alias for --profile")
.option(
"--api-key <key>",
"OmniRoute API key (overrides OMNIROUTE_API_KEY env var for this invocation)"
)
.option("--api-key <key>", "OmniRoute API key (overrides OMNIROUTE_API_KEY env var for this invocation)")
.allowUnknownOption(true)
.allowExcessArguments(true)
.argument("[codexArgs...]", "arguments passed through to the codex binary")
.action(async (codexArgs, opts) => {
const merged = { ...opts, profile: opts.profile ?? opts.p };
// process.exit() here aborted the process with a libuv assertion on
// Windows (`!(handle->flags & UV_HANDLE_CLOSING)`, async.c:94): it tears
// the loop down while the inherited stdio handles of the just-exited
// child are still closing. Setting exitCode lets the loop drain first.
process.exitCode = await runLaunchCodexCommand(merged, codexArgs ?? []);
const exitCode = await runLaunchCodexCommand(merged, codexArgs ?? []);
if (exitCode !== 0) process.exit(exitCode);
});
}

View File

@@ -1,9 +1,8 @@
import { spawn, execFileSync } from "node:child_process";
import { spawn } from "node:child_process";
import { join } from "node:path";
import os from "node:os";
import { t } from "../i18n.mjs";
import { resolveActiveContext } from "../contexts.mjs";
import { quoteShellArgs } from "../utils/winShellArgs.mjs";
function stripTrailingSlash(value) {
let s = String(value);
@@ -91,78 +90,6 @@ export function resolveLaunchTarget(opts = {}) {
return { baseUrl, authToken };
}
/**
* Probe PATH for a Windows executable via `where.exe`, preferring a `.exe` over
* a `.cmd`/`.bat` shim. Returns the absolute path to the preferred binary, or
* `null` when `where.exe` finds nothing (or cannot run).
*
* The native Anthropic installer (#9454) creates only `claude.exe` (no npm
* `.cmd` shim), so the launcher must look for the real PE and spawn it without
* a shell. Mirrors the existing `locateCommand()` probe in
* `src/shared/services/cliRuntime.ts`.
*
* @param {string} command bare command name to look up
* @returns {Promise<string|null>} absolute path to the preferred match, or null
*/
function probeWindowsBinary(command) {
try {
const out = execFileSync("where.exe", [command], {
stdio: ["ignore", "pipe", "ignore"],
encoding: "utf8",
timeout: 3000,
windowsHide: true,
});
const lines = out
.split(/\r?\n/)
.map((l) => l.trim())
.filter(Boolean);
if (lines.length === 0) return null;
const winExt = /\.(exe|cmd|bat|com)$/i;
return lines.find((l) => winExt.test(l)) || null;
} catch {
return null;
}
}
/**
* #8246 / #9454: on Windows, npm installs claude as a `.cmd` shim — spawn()
* without a shell cannot resolve PATHEXT shims (and Node refuses to exec `.cmd`
* directly since CVE-2024-27980), so the npm-shim path must go through cmd.exe.
* But the native installer creates only `claude.exe`, which is a real PE that
* must NOT go through a shell (cmd.exe would split an absolute path with spaces).
*
* So probe PATH for `claude` first: when `where.exe` resolves a `.exe`, spawn it
* directly (no shell); otherwise fall back to the npm `claude.cmd` + shell. Off
* Windows the bare binary is spawned unchanged (no shell, no probe).
*
* @param {NodeJS.Platform|string} platform
* @param {{ probe?: (command: string) => Promise<string|null> }} [opts] injectable probe for tests
* @returns {Promise<{ command: string, shell: true|undefined }>}
*/
export async function resolveClaudeSpawn(platform, opts = {}) {
if (platform !== "win32") return { command: "claude", shell: undefined };
const probe = opts.probe ?? probeWindowsBinary;
const located = await probe("claude");
if (located && /\.exe$/i.test(located)) {
return { command: located, shell: undefined };
}
return { command: "claude.cmd", shell: true };
}
/**
* `shell: true` makes Node join argv with plain spaces and no escaping (the
* DEP0190 warning), so `-p "two words"` used to reach claude as `-p two` plus
* three stray positional arguments. Quote the args ourselves on that path.
* Off Windows there is no shell, so argv is passed through untouched.
*
* @param {string[]} args
* @param {NodeJS.Platform|string} platform
* @returns {string[]}
*/
export function quoteClaudeArgs(args, platform) {
return quoteShellArgs(args, platform);
}
/**
* @param {{port?:string, remote?:string, token?:string, apiKey?:string, profile?:string, claudeHome?:string}} opts
* @param {string[]} claudeArgs pass-through args for the claude binary
@@ -179,10 +106,10 @@ export async function runLaunchCommand(opts = {}, claudeArgs = []) {
if (!res.ok) throw new Error(`status ${res.status}`);
} catch {
console.error(
(
t("launch.notRunning") ||
"OmniRoute is not reachable at {port}. Start it with 'omniroute serve'."
).replace("{port}", baseUrl)
(t("launch.notRunning") || "OmniRoute is not reachable at {port}. Start it with 'omniroute serve'.").replace(
"{port}",
baseUrl
)
);
return 1;
}
@@ -192,15 +119,8 @@ export async function runLaunchCommand(opts = {}, claudeArgs = []) {
: undefined;
const env = buildClaudeEnv(process.env, baseUrl, authToken, { configDir });
const { command, shell } = await resolveClaudeSpawn(process.platform);
return await new Promise((resolve) => {
const child = spawn(command, quoteClaudeArgs(claudeArgs, process.platform), {
env,
stdio: "inherit",
shell,
...(process.platform === "win32" ? { windowsHide: true } : {}),
});
const child = spawn("claude", claudeArgs, { env, stdio: "inherit" });
child.on("error", (err) => {
if (err && err.code === "ENOENT") {
console.error(t("launch.notFound") || "The 'claude' CLI was not found in PATH.");
@@ -222,20 +142,14 @@ export function registerLaunch(program) {
)
.option("--port <port>", t("serve.port") || "Proxy port", "20128")
.option("--remote <url>", "Remote OmniRoute base URL (overrides --port and the active context)")
.option(
"--profile <name>",
"Claude Code profile to use (CLAUDE_CONFIG_DIR ~/.claude/profiles/<name>)"
)
.option("--profile <name>", "Claude Code profile to use (CLAUDE_CONFIG_DIR ~/.claude/profiles/<name>)")
.option("--token <token>", t("launch.token") || "Token Claude sends (ANTHROPIC_AUTH_TOKEN)")
.option("--api-key <key>", "Alias for --token (OmniRoute access token / API key)")
.allowUnknownOption(true)
.allowExcessArguments(true)
.argument("[claudeArgs...]", "arguments passed through to the claude binary")
.action(async (claudeArgs, opts) => {
// process.exit() here aborted the process with a libuv assertion on
// Windows (`!(handle->flags & UV_HANDLE_CLOSING)`, async.c:94): it tears
// the loop down while the inherited stdio handles of the just-exited
// child are still closing. Setting exitCode lets the loop drain first.
process.exitCode = await runLaunchCommand(opts, claudeArgs ?? []);
const exitCode = await runLaunchCommand(opts, claudeArgs ?? []);
if (exitCode !== 0) process.exit(exitCode);
});
}

View File

@@ -1,289 +0,0 @@
import { createServer } from "node:http";
import { randomUUID } from "node:crypto";
/**
* `omniroute login antigravity` — local OAuth helper for remote installs.
*
* Why this exists: Google's `firstparty/nativeapp` consent for the embedded
* Antigravity desktop client only releases the authorization code when the
* loopback redirect (127.0.0.1:<port>) is REACHABLE. On a remote VPS install the
* loopback is unreachable, so the consent hangs forever and never emits a code —
* the dashboard's "paste the callback URL" fallback has nothing to paste. (The
* same flow works locally and over an SSH tunnel, where the loopback IS reachable.)
*
* This command runs the OAuth on the user's OWN machine — where 127.0.0.1 works —
* captures the code on a local loopback server, exchanges it for tokens, and
* prints a single-line credential blob. The user pastes that blob into the remote
* dashboard (Antigravity → "Paste credentials"), which decodes it, finalizes the
* onboarding server-side, and persists the connection.
*
* It talks ONLY to Google (no OmniRoute server needed locally), so it works even
* if the remote VPS is firewalled from the user's machine.
*
* Push mode: when an active remote context exists (`omniroute connect <host>`), the
* blob is POSTed straight to that install instead of being printed for a manual
* copy-paste — every piece was already in place:
*
* - the context carries an admin-scoped token, and `apiFetch()` injects it;
* - `/api/oauth` requires admin scope (src/server/authz/accessScopes.ts) and stays
* remote-reachable — routeGuard.ts loopback-gates only `/api/oauth/cursor/auto-import`;
* - `/api/oauth/<provider>/paste-credentials` already decodes the blob and persists.
*
* The push NEVER becomes a hard requirement: this helper exists precisely because it
* needs no route to the VPS, so a failed push falls back to printing the blob rather
* than losing an authorization the operator just completed in their browser.
*/
const PROVIDER = "antigravity";
/** Open the system browser; no-op if the optional `open` dependency is missing. */
async function defaultOpenBrowser(url) {
try {
const { default: open } = await import("open");
await open(url);
} catch {
// `open` not available — the caller already printed the URL to paste manually.
}
}
/**
* Start a loopback HTTP server bound to 127.0.0.1 (NOT 0.0.0.0 — we never want to
* expose the callback to the LAN). Resolves to { port, waitForCallback, close }.
*/
function defaultStartServer(preferredPort) {
return new Promise((resolve, reject) => {
let resolveCallback;
const callbackPromise = new Promise((r) => {
resolveCallback = r;
});
const server = createServer((req, res) => {
const url = new URL(req.url, "http://127.0.0.1");
if (url.pathname !== "/callback" && url.pathname !== "/auth/callback") {
res.writeHead(404).end();
return;
}
const params = Object.fromEntries(url.searchParams.entries());
res.writeHead(200, { "Content-Type": "text/html; charset=utf-8" });
res.end(
"<!doctype html><meta charset=utf-8><title>OmniRoute</title>" +
'<body style="font-family:system-ui;padding:2rem">' +
"<h2>✅ Authorization received</h2>" +
"<p>Return to your terminal — you can close this tab.</p></body>"
);
resolveCallback(params);
});
server.on("error", reject);
server.listen(preferredPort || 0, "127.0.0.1", () => {
const { port } = server.address();
resolve({
port,
waitForCallback: () => callbackPromise,
close: () => new Promise((r) => server.close(() => r())),
});
});
});
}
/**
* Is this context pointing at another machine? Loopback (and an unresolvable value)
* counts as local, so we never auto-push somewhere we cannot reason about.
*/
export function isRemoteBaseUrl(baseUrl) {
if (!baseUrl) return false;
try {
const { hostname } = new URL(baseUrl);
const host = hostname.replace(/^\[|\]$/g, ""); // strip IPv6 brackets
return host !== "localhost" && host !== "127.0.0.1" && host !== "::1";
} catch {
return false;
}
}
/**
* POST a credential blob to the active context's install. Never throws: the caller
* decides whether a failure is fatal (it is not — it falls back to printing).
*/
export async function pushCredentialBlob(provider, blob, deps = {}) {
try {
const fetchImpl = deps.fetchImpl ?? (await import("../api.mjs")).apiFetch;
const res = await fetchImpl(`/api/oauth/${provider}/paste-credentials`, {
method: "POST",
body: { blob },
});
const data = await res.json().catch(() => ({}));
if (!res.ok || data?.success === false) {
const message =
(typeof data?.error === "string" ? data.error : data?.error?.message) ||
`HTTP ${res.status}`;
return { ok: false, error: message };
}
return { ok: true, connectionId: data?.connection?.id };
} catch (err) {
return { ok: false, error: err?.message || String(err) };
}
}
/** Read the active CLI context (baseUrl + scoped token) written by `omniroute connect`. */
async function defaultResolveContext(overrideName) {
const { resolveActiveContext } = await import("../contexts.mjs");
return resolveActiveContext(overrideName);
}
/** Lazy-load the antigravity provider + blob codec (TS source via tsx). */
async function loadDeps() {
const { antigravity } = await import("../../../src/lib/oauth/providers/antigravity.ts");
const { encodeCredentialBlob } = await import("../../../src/lib/oauth/credentialBlob.ts");
return { antigravity, encodeCredentialBlob };
}
/**
* Build the Google authorization request for a given loopback port. Uses a plain
* authorization_code grant (NO PKCE code_challenge) — matching the working flow:
* a code_challenge here would force the exchange to require a code_verifier.
*/
export async function buildAntigravityAuthRequest(port, makeState = randomUUID) {
const { antigravity } = await loadDeps();
const redirectUri = `http://127.0.0.1:${port}/callback`;
const state = makeState();
const authUrl = antigravity.buildAuthUrl(antigravity.config, redirectUri, state);
return { redirectUri, state, authUrl };
}
/** Exchange the captured code for raw Google tokens (no code_verifier — no PKCE). */
export async function exchangeAntigravityCode(code, redirectUri) {
const { antigravity } = await loadDeps();
return antigravity.exchangeToken(antigravity.config, code, redirectUri);
}
/**
* Orchestrate the local login. Dependencies are injectable for testing; the real
* path uses a 127.0.0.1 loopback server, the system browser, and a live token
* exchange against Google. Returns the credential blob string.
*/
export async function runAntigravityLogin(opts = {}, deps = {}) {
const startServer = deps.startServer ?? defaultStartServer;
const openBrowser = deps.openBrowser ?? defaultOpenBrowser;
const exchange = deps.exchange ?? exchangeAntigravityCode;
const makeState = deps.makeState ?? randomUUID;
const print = deps.print ?? ((s) => process.stdout.write(s));
const log = deps.log ?? ((s) => process.stderr.write(s));
const { encodeCredentialBlob } = await loadDeps();
const server = await startServer(opts.port);
const { redirectUri, state, authUrl } = await buildAntigravityAuthRequest(server.port, makeState);
log(`\nOpen this URL to authorize Antigravity (it will open automatically):\n\n ${authUrl}\n\n`);
if (opts.browser !== false) await openBrowser(authUrl);
log("Waiting for Google to redirect back to the local loopback...\n");
const timeoutMs = opts.timeout ?? 300000;
let timer;
let params;
try {
params = await Promise.race([
server.waitForCallback(),
new Promise((_, reject) => {
timer = setTimeout(
() => reject(new Error("Timed out waiting for the OAuth callback")),
timeoutMs
);
// Don't keep the event loop alive solely for this timer.
if (typeof timer.unref === "function") timer.unref();
}),
]);
} finally {
clearTimeout(timer);
await server.close();
}
if (params.error) {
throw new Error(`Authorization failed: ${params.error_description || params.error}`);
}
if (params.state !== state) {
throw new Error("State mismatch — aborting (possible CSRF). Please retry the login.");
}
if (!params.code) {
throw new Error("No authorization code returned by Google.");
}
const tokens = await exchange(params.code, redirectUri);
const blob = encodeCredentialBlob({ provider: PROVIDER, tokens });
// Push when the operator explicitly asked, or when the active context already points
// at another machine — that is exactly the situation this helper was built for.
const resolveContext = deps.resolveContext ?? defaultResolveContext;
const push = deps.push ?? pushCredentialBlob;
let context = null;
try {
context = await resolveContext(opts.context);
} catch {
// No usable context store — fall through to printing.
}
const wantsPush =
opts.push === true || (opts.push !== false && isRemoteBaseUrl(context?.baseUrl));
if (wantsPush) {
log(`\nSending the credential to ${context?.baseUrl || "the active context"}...\n`);
const result = await push(PROVIDER, blob, { context });
if (result?.ok) {
log(
`Antigravity connected on ${context?.baseUrl || "the remote install"}` +
`${result.connectionId ? ` (connection ${result.connectionId})` : ""}.\n` +
"Nothing to paste — you can close this terminal.\n"
);
// Deliberately NOT printed: the blob wraps a refresh token and it already landed.
return blob;
}
log(
`\nCould not deliver the credential automatically: ${result?.error || "unknown error"}\n` +
"Falling back to manual paste — the authorization itself is still valid.\n"
);
}
print(
"\n" +
"Antigravity authorized. Copy the line below and paste it into your remote\n" +
'OmniRoute dashboard: Providers → Antigravity → Connect → "Paste credentials".\n' +
"(This contains a refresh token — treat it like a password.)\n\n" +
blob +
"\n\n"
);
return blob;
}
async function runLoginAntigravity(opts) {
try {
await runAntigravityLogin({
browser: opts.browser,
timeout: opts.timeout,
port: opts.port,
push: opts.push,
context: opts.context,
});
} catch (err) {
process.stderr.write(`\nLogin failed: ${err?.message || err}\n`);
process.exit(1);
}
}
export function registerLogin(program) {
const login = program
.command("login")
.description("Local OAuth helpers for remote OmniRoute installs (run on your own machine)");
login
.command("antigravity")
.description("Authorize Antigravity locally and print a credential blob to paste remotely")
.option("--no-browser", "Do not auto-open the browser; print the URL instead")
.option("--port <n>", "Fixed loopback port (default: OS-assigned)", (v) => parseInt(v, 10))
.option("--timeout <ms>", "How long to wait for the callback", (v) => parseInt(v, 10), 300000)
.option(
"--push",
"Send the credential to the active context instead of printing it (default when that context is remote)"
)
.option("--no-push", "Always print the blob, never contact the server")
.option("--context <name>", "Push to this context instead of the active one")
.action(runLoginAntigravity);
}

View File

@@ -6,31 +6,16 @@ import { t } from "../i18n.mjs";
const PROVIDERS_WITH_OAUTH = [
{ id: "gemini", name: "Google Gemini", flow: "browser" },
{ id: "antigravity", name: "Antigravity", flow: "browser" },
{ id: "windsurf", name: "Windsurf", flow: "browser" },
{ id: "qwen", name: "Qwen Code", flow: "browser" },
{ id: "cursor", name: "Cursor", flow: "import" },
{ id: "zed", name: "Zed", flow: "import" },
{ id: "kiro", name: "Amazon Kiro", flow: "social" },
{ id: "claude-code", name: "Claude Code (OAuth)", flow: "browser" },
{ id: "claude-code", name: "Claude Code (OAuth)", flow: "device" },
{ id: "codex", name: "OpenAI Codex (OAuth)", flow: "device" },
{ id: "copilot", name: "GitHub Copilot", flow: "device" },
];
// The user-facing provider id (the one shown by `omniroute oauth providers`)
// is NOT always the backend OAuth provider key the server's /api/oauth/[provider]/...
// route expects. `claude-code` is the CLI-facing alias for Anthropic's Claude
// OAuth, which the server registers under the key `claude` (see
// src/lib/oauth/providers/index.ts). Routing `claude-code` to the unrelated
// `command-code` (CommandCode.ai) provider — as the previous code did — sent
// the device-flow request to /api/providers/command-code/auth/start, which is
// gated by requireManagementAuth and returned 401 for a fresh CLI context
// (issue #9474). Map the alias to the real backend key instead.
const BACKEND_OAUTH_KEY = {
"claude-code": "claude",
};
function resolveBackendKey(id) {
return BACKEND_OAUTH_KEY[id] ?? id;
}
const oauthProviderSchema = [
{ key: "id", header: "Provider ID", width: 16 },
{ key: "name", header: "Name", width: 28 },
@@ -72,107 +57,32 @@ async function pollStatus(endpoint, timeoutMs) {
}
async function runBrowserFlow(def, opts) {
// The user-facing id (`def.id`, e.g. "claude-code") must be translated to the
// backend OAuth provider key the server's /api/oauth/[provider]/... route
// expects (e.g. "claude"). The previous implementation called a non-existent
// `/api/oauth/${def.id}/start` action — no such action exists on the server
// (src/app/api/oauth/[provider]/[action]/route.ts), so the browser flow was
// broken for every browser-flow provider. Use the real `authorize` action and
// complete the PKCE (authorization_code / authorization_code_pkce) flow with a
// manual code paste, mirroring the dashboard's manual "input" step.
const backendKey = resolveBackendKey(def.id);
const redirectUri = opts.redirectUri ?? null;
const authorizeUrl = `/api/oauth/${backendKey}/authorize${
redirectUri ? `?redirect_uri=${encodeURIComponent(redirectUri)}` : ""
}`;
const startRes = await apiFetch(authorizeUrl, { method: "GET" });
const startRes = await apiFetch(`/api/oauth/${def.id}/start`, { method: "POST" });
if (!startRes.ok) {
const detail = await safeErrorBody(startRes);
process.stderr.write(`Failed to start OAuth for ${def.id}: ${startRes.status}${detail}\n`);
process.stderr.write(`Failed to start OAuth for ${def.id}: ${startRes.status}\n`);
process.exit(1);
}
const start = await startRes.json();
const url = start.authUrl ?? start.authorizeUrl ?? start.url;
if (!url) {
const hint = start.error ?? "no authUrl returned by the server";
process.stderr.write(`OAuth unavailable for ${def.id}: ${hint}\n`);
process.exit(1);
}
const { codeVerifier, state, redirectUri: returnedRedirectUri } = start;
const finalRedirectUri = returnedRedirectUri || redirectUri;
const url = start.authorizeUrl ?? start.url;
process.stdout.write(`\nOpen this URL to authorize:\n ${url}\n\n`);
if (opts.browser !== false) await openBrowser(url);
if (process.stdout.isTTY && opts.browser !== false) {
const { startOAuthTui } = await import("../tui/OAuthFlow.jsx");
await openBrowser(url);
const tuiResult = await startOAuthTui({ provider: def.name ?? def.id, url });
if (tuiResult.status === "cancelled") return;
} else {
process.stdout.write(`\nOpen this URL to authorize:\n ${url}\n\n`);
if (opts.browser !== false) await openBrowser(url);
process.stderr.write("Waiting for authorization... (Ctrl+C to cancel)\n");
}
const result = await pollStatus(
`/api/oauth/${def.id}/status?state=${encodeURIComponent(start.state ?? "")}`,
opts.timeout ?? 300000
);
process.stdout.write(
"After authorizing, paste the callback URL (or the Authentication Code\n" +
"shown on the confirmation page) here:\n"
`Authorized: ${result.email ?? result.userId ?? result.account ?? "connected"}\n`
);
const { createPrompt } = await import("../io.mjs");
const prompt = createPrompt();
const input = await prompt.ask("Callback URL or code");
prompt.close();
const trimmed = input.trim();
if (!trimmed) {
process.stderr.write("No authorization code provided.\n");
process.exit(1);
}
// The Anthropic Claude confirmation page (platform.claude.com/oauth/code/callback)
// shows a raw "Authentication Code" like `code#state` rather than a full URL.
// The dashboard's manual submit (src/shared/components/OAuthModal.tsx) parses
// both forms; mirror that here.
let code = null;
let codeState = state || null;
try {
const cbUrl = new URL(trimmed);
code = cbUrl.searchParams.get("code");
const stateParam = cbUrl.searchParams.get("state") || cbUrl.hash.replace(/^#/, "");
if (stateParam) codeState = stateParam;
} catch {
const [rawCode, rawState] = trimmed.split("#", 2);
code = rawCode || null;
if (rawState) codeState = rawState;
}
if (!code) {
process.stderr.write(
"No authorization code found. Paste the callback URL or the Authentication Code.\n"
);
process.exit(1);
}
const exchangeRes = await apiFetch(`/api/oauth/${backendKey}/exchange`, {
method: "POST",
body: {
code,
redirectUri: finalRedirectUri,
codeVerifier,
...(codeState ? { state: codeState } : {}),
},
});
if (!exchangeRes.ok) {
const detail = await safeErrorBody(exchangeRes);
process.stderr.write(`Token exchange failed: ${exchangeRes.status}${detail}\n`);
process.exit(1);
}
const result = await exchangeRes.json();
const conn = result.connection ?? {};
process.stdout.write(`Authorized: ${conn.email ?? conn.displayName ?? conn.id ?? "connected"}\n`);
}
async function safeErrorBody(res) {
try {
const data = await res.json();
if (data?.error) {
const msg = typeof data.error === "string" ? data.error : data.error?.message;
if (msg) return `: ${msg}`;
}
if (data?.message) return `: ${data.message}`;
} catch {
/* ignore */
}
return "";
}
async function runImportFlow(def, opts) {
@@ -215,7 +125,7 @@ async function runSocialFlow(def, opts) {
}
async function runDeviceFlow(def, opts) {
const providerKey = resolveBackendKey(def.id);
const providerKey = def.id === "claude-code" ? "command-code" : def.id;
const startRes = await apiFetch(`/api/providers/${providerKey}/auth/start`, { method: "POST" });
if (!startRes.ok) {
process.stderr.write(`Failed to start device flow: ${startRes.status}\n`);

View File

@@ -10,25 +10,9 @@ const DEFAULT_IMAGE = "docker.io/redis:7-alpine";
const DEFAULT_NAME = "omniroute-redis";
const DEFAULT_PORT = "6379";
const DEFAULT_VOLUME = "omniroute-redis-data";
// The launcher starts Redis without AUTH unless --password is given, so the
// published port stays on loopback. `-p 6379:6379` would bind 0.0.0.0 and hand
// the whole LAN an unauthenticated Redis.
const DEFAULT_BIND = "127.0.0.1";
const RUNTIME_PREFERENCE = ["podman", "docker"];
/**
* Build the `-p` publish spec for the Redis container.
* Always host-qualified so the runtime never falls back to 0.0.0.0.
*/
export function buildRedisPublishSpec(bind = DEFAULT_BIND, port = DEFAULT_PORT) {
const host = String(bind || DEFAULT_BIND).trim() || DEFAULT_BIND;
const hostPort = String(port || DEFAULT_PORT).trim() || DEFAULT_PORT;
// Bracket IPv6 literals (e.g. ::1) so `host:port:port` stays unambiguous.
const normalizedHost = host.includes(":") && !host.startsWith("[") ? `[${host}]` : host;
return `${normalizedHost}:${hostPort}:6379`;
}
async function detectRuntime() {
for (const candidate of RUNTIME_PREFERENCE) {
try {
@@ -43,14 +27,7 @@ async function detectRuntime() {
async function containerExists(runtime, name) {
try {
const { stdout } = await execFile(runtime, [
"ps",
"-a",
"--filter",
`name=^${name}$`,
"--format",
"{{.Names}}",
]);
const { stdout } = await execFile(runtime, ["ps", "-a", "--filter", `name=^${name}$`, "--format", "{{.Names}}"]);
return stdout.trim() === name;
} catch {
return false;
@@ -59,13 +36,7 @@ async function containerExists(runtime, name) {
async function containerRunning(runtime, name) {
try {
const { stdout } = await execFile(runtime, [
"ps",
"--filter",
`name=^${name}$`,
"--format",
"{{.Names}}",
]);
const { stdout } = await execFile(runtime, ["ps", "--filter", `name=^${name}$`, "--format", "{{.Names}}"]);
return stdout.trim() === name;
} catch {
return false;
@@ -129,11 +100,6 @@ export function registerRedis(program) {
.command("up")
.description("Start the local Redis container")
.option("-p, --port <port>", "Host port to expose", DEFAULT_PORT)
.option(
"-b, --bind <host>",
"Host interface to publish on (use 0.0.0.0 only together with --password)",
DEFAULT_BIND
)
.option("-n, --name <name>", "Container name", DEFAULT_NAME)
.option("-i, --image <image>", "Container image", DEFAULT_IMAGE)
.option("--no-pull", "Skip pulling the image if it is missing")
@@ -194,7 +160,6 @@ export async function runRedisUpCommand(opts = {}) {
const name = opts.name || DEFAULT_NAME;
const port = opts.port || DEFAULT_PORT;
const bind = opts.bind || DEFAULT_BIND;
const image = opts.image || DEFAULT_IMAGE;
const exists = await containerExists(runtime, name);
@@ -221,11 +186,7 @@ export async function runRedisUpCommand(opts = {}) {
info(`Checking if image '${image}' is present locally…`);
let present = false;
try {
const { stdout } = await execFile(runtime, [
"images",
"--format",
"{{.Repository}}:{{.Tag}}",
]);
const { stdout } = await execFile(runtime, ["images", "--format", "{{.Repository}}:{{.Tag}}"]);
present = stdout.split("\n").some((line) => line.trim() === image);
} catch {
// ignore — fall through to pull
@@ -244,14 +205,10 @@ export async function runRedisUpCommand(opts = {}) {
const args = [
"run",
"-d",
"--name",
name,
"--restart",
"unless-stopped",
"-p",
buildRedisPublishSpec(bind, port),
"-v",
`${DEFAULT_VOLUME}:/data`,
"--name", name,
"--restart", "unless-stopped",
"-p", `${port}:6379`,
"-v", `${DEFAULT_VOLUME}:/data`,
];
if (opts.password) {
args.push("-e", `REDIS_PASSWORD=${opts.password}`);
@@ -262,13 +219,8 @@ export async function runRedisUpCommand(opts = {}) {
info(`Launching ${runtime} run ${args.join(" ")}`);
try {
await execFile(runtime, args);
success(`Container '${name}' is now running on redis://${bind}:${port}`);
info(`Set OMNIROUTE_REDIS_URL=redis://${bind}:${port} in your .env to wire OmniRoute to it.`);
if (bind !== DEFAULT_BIND && !opts.password) {
info(
`Warning: '${bind}' publishes Redis beyond loopback without AUTH. Re-run with --password <secret>.`
);
}
success(`Container '${name}' is now running on redis://127.0.0.1:${port}`);
info(`Set OMNIROUTE_REDIS_URL=redis://127.0.0.1:${port} in your .env to wire OmniRoute to it.`);
return 0;
} catch (err) {
fail(`Failed to launch container: ${err.message}`);
@@ -315,13 +267,7 @@ export async function runRedisStatusCommand(opts = {}) {
const exists = await containerExists(runtime, name);
if (!exists) {
console.log(
JSON.stringify(
{ runtime, name, port, exists: false, running: false, reachable: false },
null,
2
)
);
console.log(JSON.stringify({ runtime, name, port, exists: false, running: false, reachable: false }, null, 2));
return 0;
}
@@ -339,12 +285,10 @@ export async function runRedisStatusCommand(opts = {}) {
console.log(` Running: ${running ? "yes" : "no"}`);
console.log(` Reachable: ${reachable ? "yes" : "no"} (port ${port})`);
if (running && !reachable) {
warn(
"Container is running but the port is not reachable. Is REDIS_PASSWORD set or another process bound?"
);
warn("Container is running but the port is not reachable. Is REDIS_PASSWORD set or another process bound?");
}
if (!running) {
info(`Run 'omniroute redis up' to launch it.`);
}
return 0;
}
}

View File

@@ -2,7 +2,6 @@ import { registerMemory } from "./memory.mjs";
import { registerSkills } from "./skills.mjs";
import { registerAudit } from "./audit.mjs";
import { registerOAuth } from "./oauth.mjs";
import { registerLogin } from "./login.mjs";
import { registerCloud } from "./cloud.mjs";
import { registerEval } from "./eval.mjs";
import { registerWebhooks } from "./webhooks.mjs";
@@ -37,7 +36,6 @@ import { registerProviders } from "./providers.mjs";
import { registerProvider } from "./provider-cmd.mjs";
import { registerConfig } from "./config.mjs";
import { registerKeys } from "./keys.mjs";
import { registerAuthExport } from "./auth-export.mjs";
import { registerModels } from "./models.mjs";
import { registerCombo } from "./combo.mjs";
import { registerStatus } from "./status.mjs";
@@ -70,8 +68,9 @@ import { registerSetupCursor } from "./setup-cursor.mjs";
import { registerSetupRoo } from "./setup-roo.mjs";
import { registerSetupCrush } from "./setup-crush.mjs";
import { registerSetupGoose } from "./setup-goose.mjs";
import { registerSetupAider } from "./setup-aider.mjs";
import { registerSetupQwen } from "./setup-qwen.mjs";
import { registerSetupAider } from "./setup-aider.mjs";
import { registerSetupGemini } from "./setup-gemini.mjs";
import { registerConnect } from "./connect.mjs";
import { registerContexts } from "./contexts.mjs";
import { registerTokens } from "./tokens.mjs";
@@ -84,7 +83,6 @@ export function registerCommands(program) {
registerSkills(program);
registerAudit(program);
registerOAuth(program);
registerLogin(program);
registerCloud(program);
registerEval(program);
registerWebhooks(program);
@@ -119,7 +117,6 @@ export function registerCommands(program) {
registerProvider(program);
registerConfig(program);
registerKeys(program);
registerAuthExport(program);
registerModels(program);
registerCombo(program);
registerStatus(program);
@@ -153,8 +150,9 @@ export function registerCommands(program) {
registerSetupRoo(program);
registerSetupCrush(program);
registerSetupGoose(program);
registerSetupAider(program);
registerSetupQwen(program);
registerSetupAider(program);
registerSetupGemini(program);
registerConnect(program);
registerContexts(program);
registerTokens(program);

View File

@@ -34,14 +34,7 @@ async function runRepairAction(opts, cmd) {
if (ok) {
process.stdout.write("✓ better-sqlite3 repaired OK\n");
} else {
process.stderr.write("✗ Repair failed\n");
process.stderr.write(
" Possible causes:\n" +
" • npm not available — check that Node.js/npm are on your PATH\n" +
" • npm install scripts are blocked — run: npm install-scripts approve better-sqlite3\n" +
" • Network issue — check your internet connection\n" +
" Try: npm install-scripts ls (to see if better-sqlite3 is blocked)\n"
);
process.stderr.write("✗ Repair failed — check npm availability\n");
process.exit(1);
}
}

View File

@@ -1,31 +1,14 @@
import { spawn } from "node:child_process";
import { existsSync, readFileSync } from "node:fs";
import { existsSync } from "node:fs";
import { join, dirname } from "node:path";
import { fileURLToPath } from "node:url";
import { platform, totalmem, hostname as osHostname } from "node:os";
import { platform } from "node:os";
import { t } from "../i18n.mjs";
import { writePidFile, cleanupPidFile, waitForServer } from "../utils/pid.mjs";
import { ServerSupervisor, detectMitmCrash } from "../runtime/processSupervisor.mjs";
import { isTermux } from "../../../scripts/build/postinstallSupport.mjs";
import {
ensureAndroidCacheDir,
isFatalInstrumentationHookFailure,
formatAndroidInstrumentationFailureHint,
} from "../utils/ensureAndroidCacheDir.mjs";
import {
resolveMaxOldSpaceMb,
calibrateHeapFallbackMb,
buildServerNodeOptions,
buildNodeHeapArgs,
} from "../../../scripts/build/runtime-env.mjs";
import { resolveTlsOptions } from "../../../scripts/dev/tls-options.mjs";
const __dirname = dirname(fileURLToPath(import.meta.url));
const _pkg = JSON.parse(readFileSync(join(__dirname, "..", "..", "..", "package.json"), "utf8"));
// URL scheme for the "OmniRoute is running" banner — flipped to https when
// opt-in TLS (#5242) is active. Process-scoped: one `serve` run = one scheme.
let urlScheme = "http";
const ROOT = join(__dirname, "..", "..", "..");
// The standalone bundle ships in `dist/` (since the build-output-isolation
// refactor). Fall back to the legacy `app/` location so an upgrade over a
@@ -52,52 +35,12 @@ export function registerServe(program) {
.option("--max-restarts <n>", t("serve.max_restarts"), parseInt, 2)
.option("--tray", t("serve.tray") || "Show system tray icon (desktop only)")
.option("--no-tray", t("serve.no_tray") || "Disable system tray icon")
.option(
"--tls-cert <path>",
t("serve.tls_cert") ||
"Path to a TLS certificate (PEM) to serve HTTPS (also OMNIROUTE_TLS_CERT)"
)
.option(
"--tls-key <path>",
t("serve.tls_key") ||
"Path to the TLS private key (PEM) to serve HTTPS (also OMNIROUTE_TLS_KEY)"
)
.action(async (opts) => {
await runServe(opts);
});
}
/** Once-per-process guard so the Android/Termux cache hint is not spammed. */
let instrumentationFailureHintPrinted = false;
/**
* If child output looks like Next.js failed to load its instrumentation hook
* on Android/Termux, print a clear operator-facing fix hint.
* Exported for unit tests.
*
* @param {string} text
* @returns {boolean} true when a hint was printed
*/
export function maybeReportInstrumentationHookFailure(text) {
if (instrumentationFailureHintPrinted) return false;
if (!isFatalInstrumentationHookFailure(text)) return false;
instrumentationFailureHintPrinted = true;
process.stderr.write(formatAndroidInstrumentationFailureHint(process.env.XDG_CACHE_HOME));
return true;
}
/** Test-only reset for the once-per-process hint guard. */
export function resetInstrumentationFailureHintForTests() {
instrumentationFailureHintPrinted = false;
}
export async function runServe(opts = {}) {
const startedAt = performance.now();
// Same prep as bin/omniroute.mjs — keep it here so a direct `runServe()` call
// (tests / programmatic) still gets a writable Next.js cache dir before spawn.
ensureAndroidCacheDir({ env: process.env });
const { isNativeBinaryCompatible } =
await import("../../../scripts/build/native-binary-compat.mjs");
const { getNodeRuntimeSupport, getNodeRuntimeWarning } =
@@ -116,7 +59,6 @@ export async function runServe(opts = {}) {
| |__| | | | | | | | | | | | \\ \\ (_) | |_| | || __/
\\____/|_| |_| |_|_| |_|_|_| \\_\\___/ \\__,_|\\__\\___|
\x1b[0m`);
console.log(`\x1b[2m v${_pkg.version}\x1b[0m\n`);
const nodeSupport = getNodeRuntimeSupport();
if (!nodeSupport.nodeCompatible) {
@@ -167,11 +109,7 @@ export async function runServe(opts = {}) {
"Release",
"better_sqlite3.node"
);
if (
!process.versions.bun &&
existsSync(sqliteBinary) &&
!isNativeBinaryCompatible(sqliteBinary)
) {
if (existsSync(sqliteBinary) && !isNativeBinaryCompatible(sqliteBinary)) {
console.error(
"\x1b[31m✖ better-sqlite3 native module is incompatible with this platform.\x1b[0m"
);
@@ -188,18 +126,9 @@ export async function runServe(opts = {}) {
console.log(` \x1b[2m⏳ Starting server...\x1b[0m\n`);
// #5172/#5160/#5152: default the V8 heap to ~35% of physical RAM (clamped
// [512, 4096]) instead of a fixed 512MB, which OOM-crashed boxes with plenty
// of RAM under load. An explicit OMNIROUTE_MEMORY_MB still wins.
const memoryLimit = resolveMaxOldSpaceMb(
process.env.OMNIROUTE_MEMORY_MB,
calibrateHeapFallbackMb(totalmem())
);
// #5242: opt-in native HTTPS. CLI flags take precedence over env; the child
// server (server-ws.mjs) reads these and terminates TLS on the same listener.
const tlsCert = opts.tlsCert ?? process.env.OMNIROUTE_TLS_CERT;
const tlsKey = opts.tlsKey ?? process.env.OMNIROUTE_TLS_KEY;
const rawMemory = parseInt(process.env.OMNIROUTE_MEMORY_MB || "512", 10);
const memoryLimit =
Number.isFinite(rawMemory) && rawMemory >= 64 && rawMemory <= 16384 ? rawMemory : 512;
const env = {
...process.env,
@@ -207,30 +136,11 @@ export async function runServe(opts = {}) {
PORT: String(dashboardPort),
DASHBOARD_PORT: String(dashboardPort),
API_PORT: String(apiPort),
// #6194: POSIX shells (bash/zsh) auto-set HOSTNAME to the machine name — the
// .env loader (first-wins) can never override it. Ignore HOSTNAME when it
// matches the OS-reported hostname (the auto-set signature). OMNIROUTE_SERVER_HOST
// takes precedence; legacy HOSTNAME values that don't match os.hostname() are
// still honoured for backward compatibility (e.g. Windows CMD/PowerShell users
// who set HOSTNAME in .env where it is NOT auto-set).
HOSTNAME:
process.env.OMNIROUTE_SERVER_HOST ||
(process.env.HOSTNAME !== osHostname() ? process.env.HOSTNAME : undefined) ||
"0.0.0.0",
HOSTNAME: "0.0.0.0",
NODE_ENV: "production",
// #5238: preserve a user-set NODE_OPTIONS (incl. their own
// `--max-old-space-size=…`) instead of clobbering it with the calibrated
// default — mirror the Electron/standalone launchers.
NODE_OPTIONS: buildServerNodeOptions(process.env, memoryLimit),
...(tlsCert ? { OMNIROUTE_TLS_CERT: tlsCert } : {}),
...(tlsKey ? { OMNIROUTE_TLS_KEY: tlsKey } : {}),
NODE_OPTIONS: `--max-old-space-size=${memoryLimit}`,
};
// Validate the TLS pair up front so the operator sees a clear warning in the
// CLI (the child re-validates authoritatively). Drives the banner scheme;
// when null we fall through to identical plain-HTTP behavior as before.
urlScheme = resolveTlsOptions(env) ? "https" : "http";
const isDaemon = opts.daemon === true;
const useTray = opts.tray === true;
@@ -239,15 +149,7 @@ export async function runServe(opts = {}) {
}
if (opts.noRecovery) {
return runWithoutRecovery(
serverJs,
env,
memoryLimit,
dashboardPort,
apiPort,
noOpen,
startedAt
);
return runWithoutRecovery(serverJs, env, memoryLimit, dashboardPort, apiPort, noOpen);
}
return runWithSupervisor(
@@ -259,53 +161,30 @@ export async function runServe(opts = {}) {
noOpen,
opts.log === true,
opts.maxRestarts ?? 2,
startedAt,
useTray
);
}
function runDaemon(serverJs, env, memoryLimit, dashboardPort, apiPort) {
// #5238: skip the explicit CLI --max-old-space-size when the user pinned the
// heap via NODE_OPTIONS (a CLI arg would shadow/override their value).
const server = spawn(
process.versions.bun ? process.execPath : "node",
[
...(process.versions.bun
? ["--preload", join(APP_DIR, "open-sse/utils/setupPolyfill.ts")]
: buildNodeHeapArgs(process.env, memoryLimit)),
serverJs,
],
{
cwd: APP_DIR,
env,
stdio: "ignore",
detached: true,
}
);
const server = spawn("node", [`--max-old-space-size=${memoryLimit}`, serverJs], {
cwd: APP_DIR,
env,
stdio: "ignore",
detached: true,
});
writePidFile("server", server.pid);
server.unref();
console.log(`\x1b[32m✔ OmniRoute started in background (PID: ${server.pid})\x1b[0m`);
console.log(` \x1b[1mDashboard:\x1b[0m ${urlScheme}://localhost:${dashboardPort}`);
console.log(` \x1b[1mAPI Base:\x1b[0m ${urlScheme}://localhost:${apiPort}/v1`);
console.log(` \x1b[1mDashboard:\x1b[0m http://localhost:${dashboardPort}`);
console.log(` \x1b[1mAPI Base:\x1b[0m http://localhost:${apiPort}/v1`);
}
function runWithoutRecovery(serverJs, env, memoryLimit, dashboardPort, apiPort, noOpen, startedAt) {
// #5238: skip the explicit CLI --max-old-space-size when the user pinned the
// heap via NODE_OPTIONS (a CLI arg would shadow/override their value).
const server = spawn(
process.versions.bun ? process.execPath : "node",
[
...(process.versions.bun
? ["--preload", join(APP_DIR, "open-sse/utils/setupPolyfill.ts")]
: buildNodeHeapArgs(process.env, memoryLimit)),
serverJs,
],
{
cwd: APP_DIR,
env,
stdio: "pipe",
}
);
function runWithoutRecovery(serverJs, env, memoryLimit, dashboardPort, apiPort, noOpen) {
const server = spawn("node", [`--max-old-space-size=${memoryLimit}`, serverJs], {
cwd: APP_DIR,
env,
stdio: "pipe",
});
writePidFile("server", server.pid);
@@ -314,21 +193,16 @@ function runWithoutRecovery(serverJs, env, memoryLimit, dashboardPort, apiPort,
server.stdout.on("data", (data) => {
const text = data.toString();
process.stdout.write(text);
maybeReportInstrumentationHookFailure(text);
if (
!started &&
(text.includes("Ready") || text.includes("started") || text.includes("listening"))
) {
started = true;
onReady(dashboardPort, apiPort, noOpen, startedAt);
onReady(dashboardPort, apiPort, noOpen);
}
});
server.stderr.on("data", (data) => {
const text = data.toString();
process.stderr.write(text);
maybeReportInstrumentationHookFailure(text);
});
server.stderr.on("data", (data) => process.stderr.write(data));
server.on("error", (err) => {
console.error("\x1b[31m✖ Failed to start server:\x1b[0m", err.message);
@@ -358,7 +232,7 @@ function runWithoutRecovery(serverJs, env, memoryLimit, dashboardPort, apiPort,
setTimeout(() => {
if (!started) {
started = true;
onReady(dashboardPort, apiPort, noOpen, startedAt);
onReady(dashboardPort, apiPort, noOpen);
}
}, 15000);
}
@@ -372,7 +246,6 @@ async function runWithSupervisor(
noOpen,
showLog,
maxRestarts,
startedAt,
useTray = false
) {
if (showLog) process.env.OMNIROUTE_SHOW_LOG = "1";
@@ -410,39 +283,12 @@ async function runWithSupervisor(
waitForServer(dashboardPort, 60000).then(async (up) => {
if (up) {
if (useTray) await maybeStartTray(dashboardPort, apiPort, supervisor);
onReady(dashboardPort, apiPort, noOpen, startedAt);
} else {
reportReadinessTimeout(dashboardPort, supervisor);
onReady(dashboardPort, apiPort, noOpen);
}
});
}
}
// #6321: waitForServer resolving `false` used to fall through silently — the CLI
// printed the banner + "⏳ Starting server..." and then produced ZERO further
// output forever, even though the child process may well have crashed or be
// stuck (issue reports show the server sometimes actually comes up later, or is
// reachable directly while the CLI still looks hung). Surface a clear diagnostic
// plus whatever stdout/stderr the child buffered instead of going silent.
export function reportReadinessTimeout(dashboardPort, supervisor) {
console.error(
`\n\x1b[33m⚠ Server did not respond within 60s.\x1b[0m It may still be starting, or may` +
` have failed silently.`
);
console.error(` Try: curl -I http://localhost:${dashboardPort}/api/monitoring/health`);
console.error(` Or: rerun with \x1b[36m--log\x1b[0m to see live server output.\n`);
const recentLog = supervisor?.getRecentLog?.() ?? [];
if (recentLog.length) {
console.error("--- Recent server output ---");
recentLog.forEach((l) => console.error(l));
console.error("--- End recent output ---\n");
// If the buffered log already shows the Android instrumentation failure,
// print the actionable hint even when --log was off (default).
maybeReportInstrumentationHookFailure(recentLog.join("\n"));
}
}
let _killTray = null;
function killTrayIfActive() {
if (_killTray) {
@@ -458,8 +304,8 @@ async function maybeStartTray(port, apiPort, supervisor) {
const { initTray, isTraySupported } = await import("../tray/index.mjs");
if (!isTraySupported()) return;
const { default: open } = await import("open").catch(() => ({ default: null }));
const dashboardUrl = `${urlScheme}://localhost:${port}`;
const tray = await initTray({
const dashboardUrl = `http://localhost:${port}`;
const tray = initTray({
port,
onQuit: () => {
killTrayIfActive();
@@ -475,23 +321,17 @@ async function maybeStartTray(port, apiPort, supervisor) {
const { killTray } = await import("../tray/index.mjs");
_killTray = killTray;
}
} catch (err) {
// tray is optional — do not fail the server, but surface why it failed so
// "--tray shows nothing" is diagnosable instead of silent (#4605).
process.stderr.write(`[omniroute][tray] failed to start: ${err?.message ?? String(err)}\n`);
} catch {
// tray is optional — do not fail the server
}
}
async function onReady(dashboardPort, apiPort, noOpen, startedAt) {
const dashboardUrl = `${urlScheme}://localhost:${dashboardPort}`;
const apiUrl = `${urlScheme}://localhost:${apiPort}`;
const elapsed =
typeof startedAt === "number" && Number.isFinite(startedAt)
? ((performance.now() - startedAt) / 1000).toFixed(1)
: "0.0";
async function onReady(dashboardPort, apiPort, noOpen) {
const dashboardUrl = `http://localhost:${dashboardPort}`;
const apiUrl = `http://localhost:${apiPort}`;
console.log(`
\x1b[32m✔ OmniRoute is running!\x1b[0m \x1b[2m(started in ${elapsed}s)\x1b[0m
\x1b[32m✔ OmniRoute is running!\x1b[0m
\x1b[1m Dashboard:\x1b[0m ${dashboardUrl}
\x1b[1m API Base:\x1b[0m ${apiUrl}/v1

View File

@@ -20,11 +20,7 @@ import { existsSync, mkdirSync, writeFileSync } from "node:fs";
import { join } from "node:path";
import os from "node:os";
import { printHeading, printInfo, printSuccess, printError } from "../io.mjs";
import {
categoriseModel,
isCodexCompatibleTextModel,
profileNameFromModelId,
} from "./setup-codex.mjs";
import { categoriseModel } from "./setup-codex.mjs";
/** Map a Codex-style effort to a Claude Code settings.json effortLevel. */
function effortLevelFor(cfg) {
@@ -33,17 +29,6 @@ function effortLevelFor(cfg) {
return cfg.effort || undefined;
}
/**
* Generic profile for a live-catalog model that `categoriseModel()` doesn't
* recognize (e.g. any provider added after the hardcoded glm/kimi/mimo/…
* pattern list was written). Mirrors setup-codex.mjs's fallbackCodexProfile()
* so setup-claude never silently produces zero profiles for a fresh catalog.
*/
export function fallbackClaudeProfile(modelId, model) {
if (!isCodexCompatibleTextModel(model)) return null;
return { name: profileNameFromModelId(modelId) };
}
/** Build the settings.json content for one Claude Code profile. */
export function buildProfileSettings(modelId, baseUrl, cfg) {
const env = {
@@ -65,84 +50,18 @@ export function buildProfileSettings(modelId, baseUrl, cfg) {
return JSON.stringify(settings, null, 2) + "\n";
}
/**
* Generate Claude Code profile files for a live model catalog. Shared by the
* `setup-claude` CLI command and the post-model-sync auto-sync so both stay
* behaviorally identical. Writes `<claudeHome>/profiles/<name>/settings.json`
* (directory-per-profile); never touches the active/default Claude config.
* @param {Array} models
* @param {{claudeHome?:string, baseUrl:string, dryRun?:boolean, only?:string, log?:(line:string)=>void}} opts
* @returns {Promise<{written:number, skipped:number, profiles:Array<{name:string, model:string, filePath:string}>}>}
*/
export async function syncClaudeProfilesFromModels(models, opts = {}) {
const claudeHome = opts.claudeHome || join(os.homedir(), ".claude");
const profilesRoot = join(claudeHome, "profiles");
const baseUrl = opts.baseUrl;
const dryRun = Boolean(opts.dryRun);
// Injectable dry-run printer (#5959): under the node:test runner, a child
// process writing multi-byte UTF-8 (the "──" box-drawing heading) to stdout
// corrupts the runner's V8-serialized event stream ~50% of the time
// ("Unable to deserialize cloned data due to invalid or unsupported
// version"). Tests inject a collector; the CLI default stays console.log.
const log = opts.log ?? console.log;
const onlyFilter = opts.only ? opts.only.split(",").map((s) => s.trim()) : null;
if (!dryRun && !existsSync(profilesRoot)) {
mkdirSync(profilesRoot, { recursive: true });
}
let written = 0;
let skipped = 0;
const profiles = [];
for (const m of models) {
const id = typeof m === "string" ? m : (m.id ?? "");
if (!id) {
skipped++;
continue;
}
if (onlyFilter && !onlyFilter.some((f) => id.includes(f))) {
skipped++;
continue;
}
const cfg = categoriseModel(id) ?? fallbackClaudeProfile(id, m);
if (!cfg) {
skipped++;
continue;
}
const dir = join(profilesRoot, cfg.name);
const filePath = join(dir, "settings.json");
const content = buildProfileSettings(id, baseUrl, cfg);
if (dryRun) {
log(`\n── [dry-run] ${filePath} ──`);
log(content);
} else {
mkdirSync(dir, { recursive: true });
writeFileSync(filePath, content, "utf8");
}
profiles.push({ name: cfg.name, model: id, filePath });
written++;
}
return { written, skipped, profiles };
}
/**
* @param {{remote?:string, port?:string, apiKey?:string, claudeHome?:string, dryRun?:boolean, only?:string}} opts
* @returns {Promise<number>}
*/
export async function runSetupClaudeCommand(opts = {}) {
const port = Number(opts.port ?? process.env.PORT ?? 20128) || 20128;
const baseUrl = (opts.remote ?? `http://localhost:${port}`)
.replace(/\/+$/, "")
.replace(/\/v1$/, "");
const baseUrl = (opts.remote ?? `http://localhost:${port}`).replace(/\/+$/, "").replace(/\/v1$/, "");
const apiKey = opts.apiKey ?? opts["api-key"] ?? process.env.OMNIROUTE_API_KEY ?? "";
const claudeHome = opts.claudeHome ?? opts["claude-home"] ?? join(os.homedir(), ".claude");
const profilesRoot = join(claudeHome, "profiles");
const dryRun = Boolean(opts.dryRun ?? opts["dry-run"]);
const onlyFilter = opts.only ? opts.only.split(",").map((s) => s.trim()) : null;
printHeading("OmniRoute → Claude Code profile generator");
printInfo(`Connecting to ${baseUrl}`);
@@ -156,15 +75,7 @@ export async function runSetupClaudeCommand(opts = {}) {
headers,
signal: AbortSignal.timeout(10000),
});
if (!res.ok) {
let detail = `HTTP ${res.status}`;
try {
const errorBody = await res.json();
const serverMsg = errorBody?.error?.message || errorBody?.error || errorBody?.message || "";
if (serverMsg) detail += `${serverMsg}`;
} catch {}
throw new Error(detail);
}
if (!res.ok) throw new Error(`HTTP ${res.status} ${res.statusText}`);
const body = await res.json();
models = body.data ?? body.models ?? [];
} catch (err) {
@@ -178,25 +89,42 @@ export async function runSetupClaudeCommand(opts = {}) {
printInfo(`Received ${models.length} models from ${baseUrl}`);
const { written, skipped, profiles } = await syncClaudeProfilesFromModels(models, {
claudeHome,
baseUrl,
dryRun,
only: opts.only,
});
if (!dryRun && !existsSync(profilesRoot)) {
mkdirSync(profilesRoot, { recursive: true });
}
if (!dryRun) {
for (const profile of profiles) {
printSuccess(` ✓ profiles/${profile.name}/settings.json (${profile.model})`);
let written = 0;
for (const m of models) {
const id = typeof m === "string" ? m : m.id ?? "";
if (!id) continue;
if (onlyFilter && !onlyFilter.some((f) => id.includes(f))) continue;
const cfg = categoriseModel(id);
if (!cfg) continue;
const dir = join(profilesRoot, cfg.name);
const filePath = join(dir, "settings.json");
const content = buildProfileSettings(id, baseUrl, cfg);
if (dryRun) {
console.log(`\n── [dry-run] ${filePath} ──`);
console.log(content);
} else {
mkdirSync(dir, { recursive: true });
writeFileSync(filePath, content, "utf8");
printSuccess(` ✓ profiles/${cfg.name}/settings.json (${id})`);
}
written++;
}
const skipped = models.length - written;
if (!dryRun) {
console.log("");
printSuccess(`${written} Claude Code profiles written to ${profilesRoot}`);
if (skipped > 0) printInfo(`${skipped} models skipped (no matching profile pattern)`);
console.log("\nTo use a profile:");
console.log(" omniroute launch --profile <name> # e.g. omniroute launch --profile glm52");
console.log(
" # or: CLAUDE_CONFIG_DIR=~/.claude/profiles/<name> claude (export ANTHROPIC_AUTH_TOKEN first)"
);
console.log(" # or: CLAUDE_CONFIG_DIR=~/.claude/profiles/<name> claude (export ANTHROPIC_AUTH_TOKEN first)");
} else {
console.log(`\n[dry-run] ${written} profiles would be written (${skipped} skipped)`);
}
@@ -215,10 +143,7 @@ export function registerSetupClaude(program) {
.option("--remote <url>", "Remote OmniRoute URL, e.g. http://192.168.0.15:20128")
.option("--api-key <key>", "OmniRoute API key (defaults to OMNIROUTE_API_KEY env var)")
.option("--claude-home <dir>", "Claude home dir (default: ~/.claude)")
.option(
"--only <patterns>",
"Comma-separated substrings — only matching model IDs (e.g. glm,kimi)"
)
.option("--only <patterns>", "Comma-separated substrings — only matching model IDs (e.g. glm,kimi)")
.option("--dry-run", "Print what would be written without touching the filesystem")
.action(async (opts) => {
const exitCode = await runSetupClaudeCommand(opts);

View File

@@ -39,83 +39,29 @@ export function categoriseModel(modelId) {
{ re: /kmc\/kimi-k2\.6/, name: "kimi-k26", ctx: 131072, compact: 112000, toolLimit: 32768 },
{ re: /glm\/glm-5\.2-max/, name: "glm52max", ctx: 131072, compact: 112000, toolLimit: 32768 },
{ re: /glm\/glm-5\.2$/, name: "glm52", ctx: 131072, compact: 112000, toolLimit: 32768 },
{
re: /opencode-go\/mimo-v2\.5-pro/,
name: "mimo-pro",
ctx: 131072,
compact: 112000,
toolLimit: 32768,
},
{
re: /opencode-go\/qwen3\.7-plus/,
name: "qwen37plus",
ctx: 32768,
compact: 28000,
toolLimit: 16384,
},
{ re: /opencode-go\/mimo-v2\.5-pro/, name: "mimo-pro", ctx: 131072, compact: 112000, toolLimit: 32768 },
{ re: /opencode-go\/qwen3\.7-plus/, name: "qwen37plus", ctx: 32768, compact: 28000, toolLimit: 16384 },
];
// ── Good models (high effort) ─────────────────────────────────────────────
const goodPatterns = [
{
re: /ollamacloud\/deepseek-v4-pro/,
name: "deepseek-pro",
ctx: 131072,
compact: 112000,
toolLimit: 32768,
},
{
re: /opencode-go\/mimo-v2\.5$/,
name: "mimo",
ctx: 131072,
compact: 112000,
toolLimit: 32768,
},
{ re: /ollamacloud\/deepseek-v4-pro/, name: "deepseek-pro", ctx: 131072, compact: 112000, toolLimit: 32768 },
{ re: /opencode-go\/mimo-v2\.5$/, name: "mimo", ctx: 131072, compact: 112000, toolLimit: 32768 },
];
// ── Simple models (no effort) ─────────────────────────────────────────────
const simplePatterns = [
{ re: /ollamacloud\/gemma4:31b/, name: "gemma4", ctx: 32768, compact: 28000, toolLimit: 16384 },
{
re: /ollamacloud\/nemotron-3-super/,
name: "nemotron",
ctx: 32768,
compact: 28000,
toolLimit: 16384,
},
{
re: /ollamacloud\/gpt-oss:20b/,
name: "gptoss",
ctx: 32768,
compact: 28000,
toolLimit: 16384,
},
{ re: /ollamacloud\/nemotron-3-super/, name: "nemotron", ctx: 32768, compact: 28000, toolLimit: 16384 },
{ re: /ollamacloud\/gpt-oss:20b/, name: "gptoss", ctx: 32768, compact: 28000, toolLimit: 16384 },
];
// ── Fast models (low effort) ──────────────────────────────────────────────
const fastPatterns = [
{
re: /ollamacloud\/deepseek-v4-flash/,
name: "deepseek-flash",
ctx: 65536,
compact: 56000,
toolLimit: 16384,
},
{
re: /ollamacloud\/gemini-3-flash/,
name: "gemini-flash",
ctx: 1000000,
compact: 850000,
toolLimit: 32768,
},
{ re: /ollamacloud\/deepseek-v4-flash/, name: "deepseek-flash", ctx: 65536, compact: 56000, toolLimit: 16384 },
{ re: /ollamacloud\/gemini-3-flash/, name: "gemini-flash", ctx: 1000000, compact: 850000, toolLimit: 32768 },
{ re: /glm\/glm-5-turbo/, name: "glm5turbo", ctx: 131072, compact: 112000, toolLimit: 16384 },
{
re: /glm\/glm-4\.7-flash/,
name: "glm47flash",
ctx: 131072,
compact: 112000,
toolLimit: 16384,
},
{ re: /glm\/glm-4\.7-flash/, name: "glm47flash", ctx: 131072, compact: 112000, toolLimit: 16384 },
];
for (const p of thinkingPatterns) {
@@ -134,92 +80,6 @@ export function categoriseModel(modelId) {
return null;
}
function firstPositiveNumber(...values) {
for (const value of values) {
if (typeof value === "number" && Number.isFinite(value) && value > 0) {
return value;
}
}
return null;
}
function shortHash(value) {
let hash = 5381;
for (let i = 0; i < value.length; i++) {
hash = ((hash << 5) + hash) ^ value.charCodeAt(i);
}
return (hash >>> 0).toString(36);
}
export function profileNameFromModelId(modelId) {
const normalized = String(modelId)
.toLowerCase()
.replace(/[^a-z0-9]+/g, "-")
.replace(/^-+|-+$/g, "");
const base = normalized || "model";
if (base.length <= 96) return base;
return `${base.slice(0, 84).replace(/-+$/g, "")}-${shortHash(base)}`;
}
function hasAnyValue(values, patterns) {
return values.some((value) => patterns.some((pattern) => pattern.test(value)));
}
export function isCodexCompatibleTextModel(model) {
if (typeof model === "string") return true;
const id = String(model?.id ?? "").toLowerCase();
const type = String(model?.type ?? "").toLowerCase();
const outputModalities = Array.isArray(model?.output_modalities)
? model.output_modalities.map((value) => String(value).toLowerCase())
: [];
if (type && !["chat", "text", "language", "llm", "model"].includes(type)) {
return false;
}
const unsupportedPatterns = [
/(^|[/_-])(image|img|video|veo|seedance|audio|speech|voice|tts|stt|whisper)([/_-]|$)/,
/(^|[/_-])(embedding|embeddings|embed|rerank|moderation|transcription)([/_-]|$)/,
];
if (hasAnyValue([id, type], unsupportedPatterns)) return false;
const nonTextModalities = [/^(image|video|audio)$/];
if (hasAnyValue(outputModalities, nonTextModalities)) return false;
if (outputModalities.length > 0 && !outputModalities.includes("text")) {
return false;
}
return true;
}
export function fallbackCodexProfile(modelId, model) {
if (!isCodexCompatibleTextModel(model)) return null;
const ctx =
typeof model === "string"
? 128000
: (firstPositiveNumber(
model.context_length,
model.max_context_window_tokens,
model.max_input_tokens
) ?? 128000);
const maxOutput =
typeof model === "string"
? null
: firstPositiveNumber(model.max_output_tokens, model.output_token_limit);
const toolLimit = Math.min(Math.max(maxOutput ?? 16384, 8192), 32768);
return {
name: profileNameFromModelId(modelId),
ctx,
compact: Math.floor(ctx * 0.85),
summary: false,
toolLimit,
};
}
/** Build the TOML content for a single profile. */
function buildProfileToml(modelId, cfg) {
const lines = [
@@ -245,52 +105,6 @@ function buildProfileToml(modelId, cfg) {
return lines.join("\n") + "\n";
}
export async function syncCodexProfilesFromModels(models, opts = {}) {
const codexHome = opts.codexHome || join(os.homedir(), ".codex");
const dryRun = Boolean(opts.dryRun);
const onlyFilter = opts.only ? opts.only.split(",").map((s) => s.trim()) : null;
if (!dryRun && !existsSync(codexHome)) {
mkdirSync(codexHome, { recursive: true });
}
let written = 0;
let skipped = 0;
const profiles = [];
for (const m of models) {
const id = typeof m === "string" ? m : (m.id ?? "");
if (!id) {
skipped++;
continue;
}
if (onlyFilter && !onlyFilter.some((f) => id.includes(f))) {
skipped++;
continue;
}
const cfg = categoriseModel(id) ?? fallbackCodexProfile(id, m);
if (!cfg) {
skipped++;
continue;
}
const filePath = join(codexHome, `${cfg.name}.config.toml`);
const content = buildProfileToml(id, cfg);
if (dryRun) {
console.log(`\n── [dry-run] ${filePath} ──`);
console.log(content);
} else {
writeFileSync(filePath, content, "utf8");
}
profiles.push({ name: cfg.name, model: id, filePath });
written++;
}
return { written, skipped, profiles };
}
// ── Command ───────────────────────────────────────────────────────────────────
/**
@@ -332,17 +146,39 @@ export async function runSetupCodexCommand(opts = {}) {
printInfo(`Received ${models.length} models from ${baseUrl}`);
// ── Ensure codex home exists ──────────────────────────────────────────────
if (!dryRun && !existsSync(codexHome)) {
mkdirSync(codexHome, { recursive: true });
}
// ── Generate profiles ─────────────────────────────────────────────────────
const { written, skipped, profiles } = await syncCodexProfilesFromModels(models, {
codexHome,
dryRun,
only: opts.only,
});
let written = 0;
let skipped = 0;
for (const m of models) {
const id = typeof m === "string" ? m : (m.id ?? "");
if (!id) continue;
if (onlyFilter && !onlyFilter.some((f) => id.includes(f))) continue;
const cfg = categoriseModel(id);
if (!cfg) continue;
const filePath = join(codexHome, `${cfg.name}.config.toml`);
const content = buildProfileToml(id, cfg);
if (dryRun) {
console.log(`\n── [dry-run] ${filePath} ──`);
console.log(content);
} else {
writeFileSync(filePath, content, "utf8");
printSuccess(`${cfg.name}.config.toml (${id})`);
}
written++;
}
skipped = models.length - written;
if (!dryRun) {
for (const profile of profiles) {
printSuccess(`${profile.name}.config.toml (${profile.model})`);
}
console.log("");
printSuccess(`${written} profiles written to ${codexHome}`);
if (skipped > 0) {
@@ -374,7 +210,10 @@ export function registerSetupCodex(program) {
"--api-key <key>",
"OmniRoute API key for the remote instance (defaults to OMNIROUTE_API_KEY env var)"
)
.option("--codex-home <dir>", "Directory where profile files are written (default: ~/.codex)")
.option(
"--codex-home <dir>",
"Directory where profile files are written (default: ~/.codex)"
)
.option(
"--only <patterns>",
"Comma-separated substrings — only generate profiles for matching model IDs (e.g. glm,kimi)"

View File

@@ -0,0 +1,148 @@
/**
* omniroute setup-gemini — point the Gemini CLI at OmniRoute's Gemini endpoint.
*
* The Gemini CLI is NOT OpenAI-compatible — it speaks the native Gemini API.
* OmniRoute exposes a Gemini-native surface at /v1beta (e.g.
* /v1beta/models/<model>:generateContent), so the CLI can target it via the
* @google/genai SDK env `GOOGLE_GEMINI_BASE_URL` (ROOT — the SDK appends /v1beta)
* + `GEMINI_API_KEY`. There is no settings.json key for the base URL, so this is
* primarily an env recipe; we optionally write ~/.gemini/settings.json `model`.
*
* ⚠ Known Gemini CLI caveat: it may ignore GOOGLE_GEMINI_BASE_URL if a cached
* Google login exists — run `gemini` logged-out / API-key-only for it to take.
*/
import { existsSync, mkdirSync, readFileSync, writeFileSync } from "node:fs";
import { join } from "node:path";
import os from "node:os";
import { printHeading, printInfo, printSuccess, printError, createPrompt } from "../io.mjs";
import { resolveActiveContext } from "../contexts.mjs";
function stripToRoot(url) {
const s = String(url || "").replace(/\/+$/, "");
return s.endsWith("/v1beta") ? s.slice(0, -7) : s.endsWith("/v1") ? s.slice(0, -3) : s;
}
/** Resolve GOOGLE_GEMINI_BASE_URL (ROOT — SDK appends /v1beta) + apiKey. */
export function resolveGeminiTarget(opts = {}) {
let root;
if (opts.remote) root = stripToRoot(opts.remote);
else {
try {
root = stripToRoot(resolveActiveContext(opts.context ?? process.env.OMNIROUTE_CONTEXT)?.baseUrl);
} catch {
/* none */
}
if (!root) root = `http://localhost:${Number(opts.port ?? process.env.PORT ?? 20128) || 20128}`;
}
let apiKey = opts.apiKey ?? opts["api-key"];
if (!apiKey) {
try {
const c = resolveActiveContext(opts.context ?? process.env.OMNIROUTE_CONTEXT);
apiKey = c?.accessToken || c?.apiKey;
} catch {
/* none */
}
}
if (!apiKey) apiKey = process.env.OMNIROUTE_API_KEY || "";
return { baseUrl: root, apiKey };
}
/** The guaranteed env recipe (pure → testable). */
export function buildGeminiRecipe({ baseUrl, model }) {
return [
`export GOOGLE_GEMINI_BASE_URL=${baseUrl}`,
"export GEMINI_API_KEY=$OMNIROUTE_API_KEY",
`export GEMINI_MODEL=${model}`,
`gemini -p "reply OK" # or: gemini (interactive)`,
].join("\n");
}
/** Merge the model into ~/.gemini/settings.json (base URL is env-only). */
export function buildGeminiSettings(existing, { model }) {
const s = existing && typeof existing === "object" ? { ...existing } : {};
if (model) s.model = model;
return s;
}
function readJson(path) {
try {
if (existsSync(path)) return JSON.parse(readFileSync(path, "utf8"));
} catch {
/* corrupt/missing */
}
return {};
}
async function fetchGeminiModelIds(baseUrl, apiKey) {
try {
const res = await fetch(`${baseUrl}/v1beta/models`, {
headers: { "x-goog-api-key": apiKey || "" },
signal: AbortSignal.timeout(8000),
});
if (!res.ok) return [];
const body = await res.json();
return (body.models || []).map((m) => String(m.name || "").replace(/^models\//, "")).filter(Boolean);
} catch {
return [];
}
}
export async function runSetupGeminiCommand(opts = {}) {
const { baseUrl, apiKey } = resolveGeminiTarget(opts);
const dryRun = Boolean(opts.dryRun ?? opts["dry-run"]);
const configPath = opts.configPath ?? opts["config-path"] ?? join(os.homedir(), ".gemini", "settings.json");
printHeading("OmniRoute → Gemini CLI (native Gemini /v1beta endpoint)");
printInfo(`GOOGLE_GEMINI_BASE_URL: ${baseUrl} (root — SDK appends /v1beta)`);
let model = opts.model;
if (!model) {
const ids = await fetchGeminiModelIds(baseUrl, apiKey);
if (ids.length && !opts.yes) {
printInfo(`Examples: ${ids.slice(0, 20).join(", ")}${ids.length > 20 ? " …" : ""}`);
const prompt = createPrompt();
try {
model = await prompt.ask("Model id for Gemini CLI");
} finally {
prompt.close();
}
}
}
if (!model) {
printError("A model is required. Pass --model <id>.");
return 2;
}
if (dryRun) {
console.log(`\n── [dry-run] ${configPath} ── { "model": "${model}" }`);
} else {
const merged = buildGeminiSettings(readJson(configPath), { model });
mkdirSync(join(configPath, ".."), { recursive: true });
writeFileSync(configPath, JSON.stringify(merged, null, 2) + "\n", "utf8");
printSuccess(`Wrote ${configPath} (model)`);
}
printInfo("\nThe base URL is env-only for Gemini CLI — export these:");
console.log(buildGeminiRecipe({ baseUrl, model }));
printInfo("\n⚠ If Gemini CLI ignores the base URL, you have a cached Google login —");
printInfo(" run logged-out (API-key only) so GOOGLE_GEMINI_BASE_URL takes effect.");
return 0;
}
export function registerSetupGemini(program) {
program
.command("setup-gemini")
.description("Point the Gemini CLI at OmniRoute's native Gemini /v1beta endpoint (env recipe + settings model)")
.option("--port <port>", "Local OmniRoute port (ignored when --remote is set)", "20128")
.option("--remote <url>", "Remote OmniRoute URL, e.g. http://192.168.0.15:20128")
.option("--api-key <key>", "OmniRoute API key (defaults to OMNIROUTE_API_KEY env var)")
.option("--model <id>", "Model id for Gemini CLI (required unless picked interactively)")
.option("--config-path <path>", "settings.json path (default: ~/.gemini/settings.json)")
.option("--yes", "Non-interactive: do not prompt (requires --model)")
.option("--dry-run", "Print what would be written without touching the filesystem")
.action(async (opts) => {
const code = await runSetupGeminiCommand(opts);
if (code !== 0) process.exit(code);
});
}

View File

@@ -218,56 +218,18 @@ function registerPluginInOpenCodeConfig({
* a clear "could not run opencode" message instead of a hard import
* failure.
*/
/**
* Resolve the provider id used for `opencode auth login --provider <id>`.
*
* The bundled @omniroute/opencode-plugin registers its provider under
* `opencode-<id>` (the `opencode-` prefix is required by OpenCode >=1.17.8's
* native-adapter gate). The auth login command must use the prefixed form
* because OpenCode resolves `--provider <id>` against the provider id the
* plugin actually registered.
*
* Idempotent: if the id already starts with `opencode-`, it passes through
* unchanged. This protects users who manually worked around the bug with
* `--provider opencode-omniroute`.
*
* @param {string} providerId
* @returns {string}
*/
export function resolveOpenCodeAuthProviderId(providerId) {
return providerId.startsWith("opencode-") ? providerId : `opencode-${providerId}`;
}
/**
* Pure resolver for the `opencode auth login` spawn descriptor. Extracted so the
* platform-branching logic is unit-testable without mocking child_process or
* mutating process.platform.
*
* On Windows the `opencode` binary is an npm `.cmd` shim that Node's hardened
* spawnSync (post CVE-2024-27980) refuses to run without a shell — spawning it
* with shell:false throws EINVAL (#7913). Mirror the same fix already applied to
* codex (resolveCodexSpawn in launch-codex.mjs, crediting #6263) and
* qodercli/Auggie (#6263/#6304): shell:true on win32, shell:false everywhere else.
*/
export function resolveOpenCodeAuthSpawn(providerId, platform = process.platform) {
const isWin = platform === "win32";
const authProviderId = resolveOpenCodeAuthProviderId(providerId);
return {
command: isWin ? "opencode.cmd" : "opencode",
args: ["auth", "login", "--provider", authProviderId],
options: { stdio: "inherit", shell: isWin },
};
}
export function runOpenCodeAuth(providerId) {
const authProviderId = resolveOpenCodeAuthProviderId(providerId);
const { command, args, options } = resolveOpenCodeAuthSpawn(providerId);
const res = spawnSync(command, args, options);
function runOpenCodeAuth(providerId) {
const isWin = process.platform === "win32";
const opencodeBin = isWin ? "opencode.cmd" : "opencode";
const res = spawnSync(opencodeBin, ["auth", "login", "--provider", providerId], {
stdio: "inherit",
shell: false,
});
if (res.error) {
// ENOENT = opencode is not on PATH
if (res.error.code === "ENOENT") {
printInfo(
`opencode CLI not found on PATH. Run \`opencode auth login --provider ${authProviderId}\` manually after installing OpenCode.`
`opencode CLI not found on PATH. Run \`opencode auth login --provider ${providerId}\` manually after installing OpenCode.`
);
return 1;
}
@@ -365,8 +327,7 @@ export async function runSetupOpenCodeCommand(opts = {}) {
if (wantsAuth) {
if (nonInteractive) {
printInfo(`Skipping \`opencode auth login\` (non-interactive mode).`);
const authProviderId = resolveOpenCodeAuthProviderId(providerId);
printInfo(`Run manually: opencode auth login --provider ${authProviderId}`);
printInfo(`Run manually: opencode auth login --provider ${providerId}`);
} else {
printHeading("Authenticating with OpenCode");
const authExit = runOpenCodeAuth(providerId);
@@ -375,9 +336,8 @@ export async function runSetupOpenCodeCommand(opts = {}) {
}
}
} else {
const authProviderId = resolveOpenCodeAuthProviderId(providerId);
printInfo(
`Next step: opencode auth login --provider ${authProviderId} (pass --auth to do this automatically)`
`Next step: opencode auth login --provider ${providerId} (pass --auth to do this automatically)`
);
}

View File

@@ -1,166 +1,149 @@
/** Configure Qwen Code's OpenAI-compatible provider for OmniRoute. */
/**
* omniroute setup-qwen — configure Qwen Code (QwenLM/qwen-code) for OmniRoute.
*
* Qwen Code is a terminal AI agent (gemini-cli fork) with a file-based config at
* ~/.qwen/settings.json. For a custom OpenAI-compatible endpoint it uses a
* `modelProviders` entry with authType "openai", baseUrl WITH /v1, and an
* `envKey` naming the env var holding the key (secret stays in the env, never the
* file). Remote-aware; headless test via `qwen -p "..."`.
*/
import {
chmodSync,
existsSync,
mkdirSync,
readFileSync,
renameSync,
unlinkSync,
writeFileSync,
} from "node:fs";
import { existsSync, mkdirSync, readFileSync, writeFileSync } from "node:fs";
import { join } from "node:path";
import os from "node:os";
import path from "node:path";
import {
mergeQwenCodeEnv,
mergeQwenCodeSettings,
normalizeQwenCodeBaseUrl,
} from "../../../src/shared/services/qwenCodeConfig.ts";
import { printHeading, printInfo, printSuccess, printError, createPrompt } from "../io.mjs";
import { resolveActiveContext } from "../contexts.mjs";
import { createPrompt, printError, printHeading, printInfo, printSuccess } from "../io.mjs";
/** Resolve base URL and key from flags, active context, then local defaults. */
export function resolveQwenTarget(opts = {}) {
let root = opts.remote ? String(opts.remote) : "";
let context;
if (!root || !(opts.apiKey ?? opts["api-key"])) {
try {
context = resolveActiveContext(opts.context ?? process.env.OMNIROUTE_CONTEXT);
} catch {
// An active context is optional for local setup.
}
}
if (!root) root = context?.baseUrl || "";
if (!root) {
const port = Number(opts.port ?? process.env.PORT ?? 20128) || 20128;
root = `http://localhost:${port}`;
}
const apiKey =
opts.apiKey ??
opts["api-key"] ??
context?.accessToken ??
context?.apiKey ??
process.env.OMNIROUTE_API_KEY ??
"sk_omniroute";
return { baseUrl: normalizeQwenCodeBaseUrl(root), apiKey };
function ensureV1(url) {
const s = String(url || "").replace(/\/+$/, "");
return s.endsWith("/v1") ? s : `${s}/v1`;
}
const readSettings = (filePath) => {
if (!existsSync(filePath)) return {};
const parsed = JSON.parse(readFileSync(filePath, "utf8"));
if (!parsed || typeof parsed !== "object" || Array.isArray(parsed)) {
throw new Error("Qwen Code settings.json must contain a JSON object");
}
return parsed;
};
const readText = (filePath) => (existsSync(filePath) ? readFileSync(filePath, "utf8") : "");
const writeAtomic = (filePath, content, mode) => {
const tempPath = `${filePath}.${process.pid}.${Date.now()}.tmp`;
try {
writeFileSync(tempPath, content, { encoding: "utf8", mode });
if (mode !== undefined) chmodSync(tempPath, mode);
renameSync(tempPath, filePath);
} catch (error) {
/** Resolve baseUrl (WITH /v1) + apiKey from flags → active context → localhost. */
export function resolveQwenTarget(opts = {}) {
let root;
if (opts.remote) root = String(opts.remote).replace(/\/+$/, "");
else {
try {
unlinkSync(tempPath);
root = resolveActiveContext(opts.context ?? process.env.OMNIROUTE_CONTEXT)?.baseUrl;
} catch {
// The temporary file may not have been created.
/* none */
}
throw error;
if (!root) root = `http://localhost:${Number(opts.port ?? process.env.PORT ?? 20128) || 20128}`;
}
};
let apiKey = opts.apiKey ?? opts["api-key"];
if (!apiKey) {
try {
const c = resolveActiveContext(opts.context ?? process.env.OMNIROUTE_CONTEXT);
apiKey = c?.accessToken || c?.apiKey;
} catch {
/* none */
}
}
if (!apiKey) apiKey = process.env.OMNIROUTE_API_KEY || "";
return { baseUrl: ensureV1(root), apiKey };
}
const fetchModelIds = async (baseUrl, apiKey) => {
/** Merge the OmniRoute modelProvider into Qwen's settings.json (preserve rest). */
export function buildQwenSettings(existing, { baseUrl, model }) {
const s = existing && typeof existing === "object" ? { ...existing } : {};
const providers = Array.isArray(s.modelProviders) ? s.modelProviders.filter((p) => p?.id !== "omniroute") : [];
providers.push({
id: "omniroute",
name: "OmniRoute",
authType: "openai",
baseUrl,
envKey: "OMNIROUTE_API_KEY",
});
s.modelProviders = providers;
if (model) {
s.selectedProvider = "omniroute";
s.model = model;
}
return s;
}
function readJson(path) {
try {
const response = await fetch(`${baseUrl}/models`, {
headers: { Authorization: `Bearer ${apiKey}` },
if (existsSync(path)) return JSON.parse(readFileSync(path, "utf8"));
} catch {
/* corrupt/missing */
}
return {};
}
async function fetchModelIds(baseUrl, apiKey) {
try {
const headers = { "Content-Type": "application/json" };
if (apiKey) headers["Authorization"] = `Bearer ${apiKey}`;
const res = await fetch(`${baseUrl.replace(/\/v1$/, "")}/v1/models`, {
headers,
signal: AbortSignal.timeout(8000),
});
if (!response.ok) return [];
const body = await response.json();
const models = Array.isArray(body) ? body : (body.data ?? body.models ?? []);
return models.map((entry) => (typeof entry === "string" ? entry : entry?.id)).filter(Boolean);
if (!res.ok) return [];
const body = await res.json();
const list = Array.isArray(body) ? body : body.data ?? body.models ?? [];
return list.map((m) => (typeof m === "string" ? m : m?.id)).filter(Boolean);
} catch {
return [];
}
};
}
export async function runSetupQwenCommand(opts = {}) {
const { baseUrl, apiKey } = resolveQwenTarget(opts);
const dryRun = Boolean(opts.dryRun ?? opts["dry-run"]);
const settingsPath =
opts.configPath ?? opts["config-path"] ?? path.join(os.homedir(), ".qwen", "settings.json");
const envPath = opts.envPath ?? opts["env-path"] ?? path.join(path.dirname(settingsPath), ".env");
const configPath = opts.configPath ?? opts["config-path"] ?? join(os.homedir(), ".qwen", "settings.json");
printHeading("OmniRoute → Qwen Code (OpenAI-compatible)");
printHeading("OmniRoute → Qwen Code (openai-compatible)");
printInfo(`baseUrl: ${baseUrl}`);
let model = String(opts.model || "").trim();
if (!model && !opts.yes) {
const modelIds = await fetchModelIds(baseUrl, apiKey);
if (modelIds.length > 0) {
printInfo(`Examples: ${modelIds.slice(0, 20).join(", ")}${modelIds.length > 20 ? " …" : ""}`);
}
const prompt = createPrompt();
try {
model = String(await prompt.ask("Model id for Qwen Code")).trim();
} finally {
prompt.close();
let model = opts.model;
if (!model) {
const ids = await fetchModelIds(baseUrl, apiKey);
if (ids.length && !opts.yes) {
printInfo(`Examples: ${ids.slice(0, 20).join(", ")}${ids.length > 20 ? " …" : ""}`);
const prompt = createPrompt();
try {
model = await prompt.ask("Model id for Qwen");
} finally {
prompt.close();
}
}
}
if (!model) {
printError("A model is required. Pass --model <id>.");
return 2;
}
try {
const settings = mergeQwenCodeSettings(readSettings(settingsPath), { baseUrl, model });
const envText = mergeQwenCodeEnv(readText(envPath), apiKey);
const settingsText = `${JSON.stringify(settings, null, 2)}\n`;
const merged = buildQwenSettings(readJson(configPath), { baseUrl, model });
const out = JSON.stringify(merged, null, 2) + "\n";
if (dryRun) {
console.log(`\n${settingsText}`);
printInfo(`[dry-run] settings → ${settingsPath}`);
printInfo(`[dry-run] credential → ${envPath} (OMNIROUTE_API_KEY)`);
return 0;
}
mkdirSync(path.dirname(settingsPath), { recursive: true, mode: 0o700 });
mkdirSync(path.dirname(envPath), { recursive: true, mode: 0o700 });
writeAtomic(settingsPath, settingsText);
writeAtomic(envPath, envText, 0o600);
printSuccess(`Wrote ${settingsPath}`);
printSuccess(`Updated ${envPath} (OMNIROUTE_API_KEY only)`);
printInfo('Run: qwen (or headless: qwen -p "reply OK")');
return 0;
} catch (error) {
printError(`Failed to configure Qwen Code: ${error?.message || error}`);
return 1;
if (dryRun) {
console.log("\n" + out);
printInfo(`[dry-run] ${configPath}`);
} else {
mkdirSync(join(configPath, ".."), { recursive: true });
writeFileSync(configPath, out, "utf8");
printSuccess(`Wrote ${configPath}`);
}
printInfo("\nProvide the key (settings reference OMNIROUTE_API_KEY): export OMNIROUTE_API_KEY=...");
printInfo('Then run: qwen (or headless: qwen -p "reply OK")');
return 0;
}
export function registerSetupQwen(program) {
program
.command("setup-qwen")
.description("Configure Qwen Code's upstream V4 modelProviders format for OmniRoute")
.description("Configure Qwen Code for OmniRoute: write ~/.qwen/settings.json (openai modelProvider)")
.option("--port <port>", "Local OmniRoute port (ignored when --remote is set)", "20128")
.option("--remote <url>", "Remote OmniRoute URL")
.option("--api-key <key>", "OmniRoute API key")
.option("--model <id>", "Model id for Qwen Code")
.option("--config-path <path>", "Qwen Code settings.json path")
.option("--env-path <path>", "Qwen Code .env path")
.option("--yes", "Non-interactive; requires --model")
.option("--dry-run", "Print settings without writing files or secrets")
.option("--remote <url>", "Remote OmniRoute URL, e.g. http://192.168.0.15:20128")
.option("--api-key <key>", "OmniRoute API key (defaults to OMNIROUTE_API_KEY env var)")
.option("--model <id>", "Model id for Qwen (required unless picked interactively)")
.option("--config-path <path>", "settings.json path (default: ~/.qwen/settings.json)")
.option("--yes", "Non-interactive: do not prompt (requires --model)")
.option("--dry-run", "Print what would be written without touching the filesystem")
.action(async (opts) => {
const code = await runSetupQwenCommand(opts);
if (code !== 0) process.exitCode = code;
if (code !== 0) process.exit(code);
});
}

View File

@@ -26,7 +26,6 @@ function wantsProviderSetup(opts) {
async function resolvePassword(opts, prompt, nonInteractive) {
if (opts.password) return opts.password;
if (process.env.INITIAL_PASSWORD) return process.env.INITIAL_PASSWORD;
if (nonInteractive) return "";
const answer = await prompt.ask("Set an admin password now? [y/N]", "N");

View File

@@ -8,7 +8,6 @@ import {
sleep,
} from "../utils/pid.mjs";
import { t } from "../i18n.mjs";
import { stopProcessGracefully } from "../../../src/shared/platform/windowsProcess.ts";
const execFileAsync = promisify(execFile);
@@ -24,35 +23,25 @@ export function registerStop(program) {
export async function runStopCommand(opts = {}) {
const pid = readPidFile("server");
// #9455: when the server was started with a supervisor (the default), killing only
// the child lets the supervisor respawn it immediately. The supervisor's PID is
// persisted separately by serve.mjs; SIGTERM it FIRST so its handler sets
// isShuttingDown=true and stops the child cleanly without respawning.
const supervisorPid = readPidFile("supervisor");
if (pid && isPidRunning(pid)) {
console.log(t("stop.stopping", { pid }));
try {
if (supervisorPid && isPidRunning(supervisorPid)) {
try {
process.kill(supervisorPid, "SIGTERM");
} catch {}
// Give the supervisor a moment to cascade the shutdown to its child so we
// don't race the child kill against the supervisor's own child stop.
await sleep(300);
process.kill(pid, "SIGTERM");
let waited = 0;
while (waited < 5000 && isPidRunning(pid)) {
await sleep(100);
waited += 100;
}
// #8045: on win32, process.kill(pid, "SIGTERM") unconditionally force-terminates
// the target instead of delivering an interceptable signal, racing (and beating)
// the server's own async graceful shutdown / WAL checkpoint. stopProcessGracefully
// skips the immediate SIGTERM on win32 and just polls before escalating to SIGKILL.
if (isPidRunning(pid)) {
await stopProcessGracefully({ pid, timeoutMs: 5000, isPidRunning, sleep });
process.kill(pid, "SIGKILL");
await sleep(500);
}
killAllSubprocesses();
cleanupPidFile("server");
cleanupPidFile("supervisor");
console.log(t("stop.stopped"));
return 0;
} catch (err) {
@@ -66,24 +55,10 @@ export async function runStopCommand(opts = {}) {
const port = opts.port ? parseInt(String(opts.port), 10) : 20128;
if (pid === null) {
console.log(t("stop.portFallback"));
// #9455: a stale supervisor PID file would let the port-fallback stop also
// leave the supervisor running and respawning. Stop it first.
if (supervisorPid && isPidRunning(supervisorPid)) {
try {
process.kill(supervisorPid, "SIGTERM");
} catch {}
}
const portFreed = await killByPort(port);
await killByPort(port);
killAllSubprocesses();
cleanupPidFile("server");
cleanupPidFile("supervisor");
// #9455: only report success when the port is actually free — previously stop
// printed "Server stopped." even when killByPort was a no-op (win32).
if (portFreed) {
console.log(t("stop.stopped"));
} else {
console.log(t("stop.notRunning"));
}
console.log(t("stop.stopped"));
return 0;
}
@@ -91,84 +66,31 @@ export async function runStopCommand(opts = {}) {
return 0;
}
/**
* Kill the process listening on `port`. Returns true once the port is free
* (or no listener was found), false if it could not be freed.
*
* #9455: previously this was a no-op on win32 (`if (win32) return;`) yet the
* caller still reported "Server stopped." — a lie. The win32 branch now uses
* `netstat -ano` to find LISTENING PIDs and `process.kill()` (SIGTERM then
* SIGKILL), mirroring the POSIX `lsof` path.
*/
export async function killByPort(port, deps = {}) {
const exec = deps.execFileAsync || execFileAsync;
const kill = deps.processKill || ((p, sig) => process.kill(p, sig));
const running = deps.isPidRunning || isPidRunning;
const wait = deps.sleep || sleep;
const platform = deps.platform || process.platform;
if (platform === "win32") {
return killByPortWin32(port, { exec, kill, running, wait });
}
return killByPortPosix(port, { exec, kill, running, wait });
}
async function killByPortPosix(port, { exec, kill, running, wait }) {
let pids = [];
async function killByPort(port) {
if (process.platform === "win32") return;
try {
const { stdout } = await exec("lsof", ["-ti", `:${port}`]);
pids = stdout
const { stdout } = await execFileAsync("lsof", ["-ti", `:${port}`]);
const pids = stdout
.trim()
.split("\n")
.map((p) => parseInt(p, 10))
.filter((p) => Number.isFinite(p) && p > 0);
for (const p of pids) {
try {
process.kill(p, "SIGTERM");
} catch {}
}
if (pids.length > 0) {
await sleep(1000);
for (const p of pids) {
try {
if (isPidRunning(p)) process.kill(p, "SIGKILL");
} catch {}
}
}
} catch {
// lsof not available or no process on port
}
return terminatePids(pids, { kill, running, wait });
}
async function killByPortWin32(port, { exec, kill, running, wait }) {
let pids = [];
try {
const { stdout } = await exec("netstat", ["-ano"]);
pids = parseNetstatPids(stdout, port);
} catch {
// netstat not available or empty
}
return terminatePids(pids, { kill, running, wait });
}
function parseNetstatPids(stdout, port) {
const portCol = `:${port}`;
const pids = [];
for (const line of stdout.split(/\r?\n/)) {
const cols = line.trim().split(/\s+/);
// Expected columns: Proto LocalAddress ForeignAddress State PID
if (cols.length < 5) continue;
if (cols[0] !== "TCP" && cols[0] !== "TCPv6") continue;
const local = cols[1] || "";
if (!local.endsWith(portCol)) continue;
if ((cols[cols.length - 2] || "").toUpperCase() !== "LISTENING") continue;
const pid = parseInt(cols[cols.length - 1], 10);
if (Number.isFinite(pid) && pid > 0 && !pids.includes(pid)) pids.push(pid);
}
return pids;
}
async function terminatePids(pids, { kill, running, wait }) {
if (pids.length === 0) return true;
for (const p of pids) {
try {
kill(p, "SIGTERM");
} catch {}
}
await wait(1000);
for (const p of pids) {
try {
if (running(p)) kill(p, "SIGKILL");
} catch {}
}
// Confirm the port is free: any PID still alive means we failed.
return pids.every((p) => !running(p));
}

View File

@@ -181,28 +181,6 @@ export async function runUpdateCommand(opts = {}) {
// --include=optional keeps the optionalDependencies (better-sqlite3, keytar,
// tls-client, llmlingua SLM stack) on update so an omit=optional config can't drop them.
execSync("npm install -g omniroute@latest --include=optional", { stdio: "inherit" });
// Trust-but-verify: `npm install -g` exits 0 even when a shadowing local install
// (e.g. ~/node_modules/omniroute ahead of the global prefix on PATH) means the
// binary the user actually runs was not touched. Re-read the running binary's
// version and warn instead of lying about success (#9475).
const afterVersion = await getCurrentVersion();
if (afterVersion && compareVersions(afterVersion, latest) < 0) {
printError(
`Global install updated to ${latest}, but the running binary still reports ${afterVersion}.`
);
console.log(
" A local `node_modules/omniroute` is likely shadowing the global install on PATH."
);
console.log(" Diagnose with:");
console.log(" which -a omniroute");
console.log(" command -v omniroute");
console.log(" npm prefix -g");
console.log(
" Then remove the shadowing local copy (e.g. `npm uninstall omniroute` from its directory)"
);
console.log(" or reorder PATH so the global bin comes first.");
return 1;
}
printSuccess(`Updated to version ${latest}`);
printInfo("Run `omniroute --version` to verify.");
return 0;

Some files were not shown because too many files have changed in this diff Show More