Files
OmniRoute/@omniroute/opencode-plugin/tests/config-shim.test.ts
Diego Rodrigues de Sa e Souza a7ae9550bd Release v3.8.36 (#4854)
* chore(release): open v3.8.36 development cycle

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

---------

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

rebaseline

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

* fix db storage tuning settings (#4834)

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

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

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

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

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

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

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

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

Integrated into release/v3.8.36

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

---------

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

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

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

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

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

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

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

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

---------

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

---------

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

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

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

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

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

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

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

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

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

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

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

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

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

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

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

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

Integrated into release/v3.8.36

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

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

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

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

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

---------

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

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

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

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

---------

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

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

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

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

---------

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

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

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

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

---------

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

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

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

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

---------

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

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

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

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

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

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

---------

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

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

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

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

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

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

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

---------

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

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

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

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

---------

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

* Fix Ollama Cloud max reasoning effort (#4993)

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

Integrated into release/v3.8.36

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

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

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

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

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

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

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

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

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

---------

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

1526 lines
62 KiB
TypeScript

/**
* T-07 config-hook backward-compat shim tests.
*
* Covers `createOmniRouteConfigHook(opts, deps)`:
* - happy path: valid auth.json → mutates input.provider[id] with the
* stripped per-model shape (mirroring `@omniroute/opencode-provider`).
* - no-op paths: missing auth.json, malformed JSON, missing apiKey,
* missing baseURL, existing input.provider[id] (manual override).
* - fail-open: /v1/models error → stub `models: {}`; /api/combos error →
* models-only static catalog.
* - baseURL resolution: opts.baseURL → auth.json.baseURL fallback.
* - multi-instance: two plugins with different providerIds publish to
* their own keys without collision.
* - cache sharing: provider hook + config hook on the same Map dedupe
* fetcher invocations.
* - sibling-shape parity: emitted entries carry only
* `{name, attachment?, reasoning?, temperature?, tool_call?, limit?}`
* — never the rich ModelV2 nested capabilities tree.
*
* Mocking strategy mirrors `provider.test.ts` and `combos.test.ts`: every
* dependency (`readAuthJson`, `fetcher`, `combosFetcher`, `now`, `cache`,
* `logger`) is dependency-injected at hook construction. No global
* `fs/promises` or `fetch` monkey-patch needed.
*/
import test from "node:test";
import assert from "node:assert/strict";
import type { Config } from "@opencode-ai/plugin";
import {
buildStaticProviderEntry,
createOmniRouteConfigHook,
createOmniRouteProviderHook,
OmniRoutePlugin,
resolveOmniRoutePluginOptions,
type OmniRouteCombosFetcher,
type OmniRouteEnrichmentEntry,
type OmniRouteEnrichmentFetcher,
type OmniRouteEnrichmentMap,
type OmniRouteFetchCache,
type OmniRouteModelsFetcher,
type OmniRouteProviderConnection,
type OmniRouteProvidersFetcher,
type OmniRouteRawCombo,
type OmniRouteRawModelEntry,
type OmniRouteReadAuthJson,
type OmniRouteStaticProviderEntry,
} from "../src/index.js";
// ────────────────────────────────────────────────────────────────────────────
// 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 },
],
};
// ────────────────────────────────────────────────────────────────────────────
// Helpers (DI stubs — mirrors patterns in provider.test.ts / combos.test.ts)
// ────────────────────────────────────────────────────────────────────────────
function stubReadAuthJson(
value: Record<string, unknown> | undefined | null
): OmniRouteReadAuthJson & { callCount: () => number } {
let n = 0;
const f: OmniRouteReadAuthJson = async () => {
n++;
return value as never;
};
return Object.assign(f, { callCount: () => n });
}
function throwingReadAuthJson(): OmniRouteReadAuthJson & { callCount: () => number } {
let n = 0;
const f: OmniRouteReadAuthJson = async () => {
n++;
throw new Error("EACCES");
};
return Object.assign(f, { callCount: () => n });
}
function stubModelsFetcher(
payload: OmniRouteRawModelEntry[]
): OmniRouteModelsFetcher & { callCount: () => number; callsBy: () => Array<[string, string]> } {
let n = 0;
const calls: Array<[string, string]> = [];
const f: OmniRouteModelsFetcher = async (baseURL, apiKey) => {
n++;
calls.push([baseURL, apiKey]);
return payload;
};
return Object.assign(f, { callCount: () => n, callsBy: () => calls });
}
function stubCombosFetcher(
payload: OmniRouteRawCombo[]
): OmniRouteCombosFetcher & { callCount: () => number; callsBy: () => Array<[string, string]> } {
let n = 0;
const calls: Array<[string, string]> = [];
const f: OmniRouteCombosFetcher = async (baseURL, apiKey) => {
n++;
calls.push([baseURL, apiKey]);
return payload;
};
return Object.assign(f, { callCount: () => n, callsBy: () => calls });
}
function throwingModelsFetcher(): OmniRouteModelsFetcher & { callCount: () => number } {
let n = 0;
const f: OmniRouteModelsFetcher = async () => {
n++;
throw new Error("ECONNREFUSED");
};
return Object.assign(f, { callCount: () => n });
}
function throwingCombosFetcher(): OmniRouteCombosFetcher & { callCount: () => number } {
let n = 0;
const f: OmniRouteCombosFetcher = async () => {
n++;
throw new Error("403 Forbidden");
};
return Object.assign(f, { callCount: () => n });
}
function stubEnrichmentFetcher(payload: OmniRouteEnrichmentMap): OmniRouteEnrichmentFetcher & {
callCount: () => number;
callsBy: () => Array<[string, string]>;
} {
let n = 0;
const calls: Array<[string, string]> = [];
const f: OmniRouteEnrichmentFetcher = async (baseURL, apiKey) => {
n++;
calls.push([baseURL, apiKey]);
return payload;
};
return Object.assign(f, { callCount: () => n, callsBy: () => calls });
}
function throwingEnrichmentFetcher(): OmniRouteEnrichmentFetcher & { callCount: () => number } {
let n = 0;
const f: OmniRouteEnrichmentFetcher = async () => {
n++;
throw new Error("ETIMEDOUT");
};
return Object.assign(f, { 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 {
// Config = Omit<SDKConfig, "plugin"> & {plugin?: ...}. We only touch the
// `provider` slot, so a partial cast is acceptable for these tests.
return { provider: initialProvider } as unknown as Config;
}
// ────────────────────────────────────────────────────────────────────────────
// 1. Happy path — valid auth.json + apiKey + baseURL → mutates input.provider
// ────────────────────────────────────────────────────────────────────────────
test("config: with valid auth.json + apiKey + baseURL → mutates input.provider[id] with stripped models block", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-test-1", baseURL: "https://or.example.com/v1" },
});
const fetcher = stubModelsFetcher([MODEL_CLAUDE, MODEL_GEMINI]);
const combosFetcher = stubCombosFetcher([COMBO_CLAUDE_TIER]);
const logger = captureWarn();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute" },
{ readAuthJson, fetcher, combosFetcher, logger }
);
const input = makeInput();
await hook(input);
const provider = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider;
const entry = provider["opencode-omniroute"];
assert.ok(entry, "input.provider['opencode-omniroute'] set");
assert.equal(entry.npm, "@ai-sdk/openai-compatible");
assert.equal(entry.name, "OmniRoute");
assert.equal(entry.options.baseURL, "https://or.example.com/v1");
assert.equal(entry.options.apiKey, "sk-test-1");
// 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["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);
assert.equal(claude.reasoning, true);
assert.equal(claude.temperature, true);
assert.equal(claude.tool_call, true);
assert.equal(claude.limit?.context, 200_000);
assert.equal(claude.limit?.output, 64_000);
assert.equal(
(claude.limit as Record<string, unknown>).input,
undefined,
"limit.input is NOT in OC's SDK schema — must not emit"
);
// Modalities — without this field OC defaults `input.image: false`
// even when `attachment: true`, blocking clipboard paste in the TUI.
assert.deepEqual(claude.modalities?.input, ["text", "image"]);
assert.deepEqual(claude.modalities?.output, ["text"]);
// Combo surfaces under bare key + LCD'd
// (gemini's reasoning=false → combo reasoning=false).
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");
assert.equal(combo.tool_call, true);
assert.equal(combo.limit?.context, 200_000, "LCD: min(200_000, 1_000_000)");
});
// ────────────────────────────────────────────────────────────────────────────
// 1b. Dual-key fallback (#5027) — auth.json stored under the BARE providerId
// (pre-auto-prefix login) must still resolve when the active providerId is
// prefixed (`opencode-omniroute`). Without the fallback the lookup misses
// the stored key and the user is forced to re-auth.
// ────────────────────────────────────────────────────────────────────────────
test("config: auth.json under bare key (pre-prefix login) resolves via dual-key fallback", async () => {
// Stored under bare `omniroute` (the key OC wrote before the auto-prefix fix),
// but the resolved providerId is now `opencode-omniroute`.
const readAuthJson = stubReadAuthJson({
omniroute: { type: "api", key: "sk-bare-1", baseURL: "https://or.example.com/v1" },
});
const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
const combosFetcher = stubCombosFetcher([]);
const logger = captureWarn();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute" }, // resolves to opencode-omniroute internally
{ readAuthJson, fetcher, combosFetcher, 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 from bare-key apiKey");
assert.equal(entry.options.apiKey, "sk-bare-1", "apiKey resolved from the bare auth.json key");
assert.equal(entry.options.baseURL, "https://or.example.com/v1");
});
test("config: prefixed key wins over bare key when both present (dual-key precedence)", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-prefixed", baseURL: "https://pref.example/v1" },
omniroute: { type: "api", key: "sk-bare", baseURL: "https://bare.example/v1" },
});
const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
const combosFetcher = stubCombosFetcher([]);
const logger = captureWarn();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute" },
{ readAuthJson, fetcher, combosFetcher, logger }
);
const input = makeInput();
await hook(input);
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.ok(entry);
assert.equal(
entry.options.apiKey,
"sk-prefixed",
"prefixed key takes precedence (looked up first)"
);
assert.equal(entry.options.baseURL, "https://pref.example/v1");
});
// ────────────────────────────────────────────────────────────────────────────
// 2. Missing auth.json → no-op, no throw, no mutation
// ────────────────────────────────────────────────────────────────────────────
test("config: missing auth.json file → no-op, no throw, no input mutation", async () => {
const readAuthJson = stubReadAuthJson(undefined);
const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
const combosFetcher = stubCombosFetcher([]);
const logger = captureWarn();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute" },
{ readAuthJson, fetcher, combosFetcher, logger }
);
const input = makeInput();
await hook(input);
assert.deepEqual((input as { provider: Record<string, unknown> }).provider, {});
assert.equal(fetcher.callCount(), 0, "no fetch on missing auth.json");
assert.equal(combosFetcher.callCount(), 0, "no combos fetch on missing auth.json");
// One breadcrumb — the missing-apiKey path.
assert.ok(
logger.entries.some((e) => String(e[0]).includes("no apiKey")),
"breadcrumb emitted"
);
});
// ────────────────────────────────────────────────────────────────────────────
// 3. Malformed auth.json → no-op + warn once
// ────────────────────────────────────────────────────────────────────────────
test("config: malformed auth.json → no-op + warn once", async () => {
// stubReadAuthJson returns `null` to signal malformed JSON (matches
// defaultReadAuthJson's contract).
const readAuthJson = stubReadAuthJson(null);
const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
const combosFetcher = stubCombosFetcher([]);
const logger = captureWarn();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute" },
{ readAuthJson, fetcher, combosFetcher, logger }
);
const input = makeInput();
await hook(input);
assert.deepEqual((input as { provider: Record<string, unknown> }).provider, {});
assert.equal(fetcher.callCount(), 0);
// First warn = "failed to parse"; second warn = "no apiKey".
assert.ok(
logger.entries.some((e) => String(e[0]).includes("failed to parse")),
"parse-failure breadcrumb emitted"
);
});
// ────────────────────────────────────────────────────────────────────────────
// 4. Existing input.provider[id] → no overwrite (respect manual override)
// ────────────────────────────────────────────────────────────────────────────
test("config: existing input.provider[id] → no overwrite (respect manual override)", async () => {
const manual = {
npm: "@ai-sdk/openai-compatible",
name: "Manual OmniRoute",
options: { baseURL: "http://manual/v1", apiKey: "manual-key" },
models: { "manual-model": { name: "manual-model" } },
};
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
});
const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
const combosFetcher = stubCombosFetcher([]);
const logger = captureWarn();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute" },
{ readAuthJson, fetcher, combosFetcher, logger }
);
const input = makeInput({ "opencode-omniroute": manual });
await hook(input);
const provider = (input as { provider: Record<string, unknown> }).provider;
assert.equal(provider["opencode-omniroute"], manual, "manual override preserved by reference");
assert.equal(fetcher.callCount(), 0, "no fetch — short-circuited before I/O");
assert.equal(readAuthJson.callCount(), 0, "no auth.json read either");
assert.ok(
logger.entries.some((e) => String(e[0]).includes("already set")),
"override breadcrumb emitted"
);
});
// ────────────────────────────────────────────────────────────────────────────
// 5. fetchers throw → warn + emit stub entry with `models: {}`
// ────────────────────────────────────────────────────────────────────────────
test("config: fetchers throw → warn + emit stub entry with models: {}", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
});
const fetcher = throwingModelsFetcher();
const combosFetcher = throwingCombosFetcher();
const logger = captureWarn();
// Opt-out of disk-cache fallback for this test — we want to assert the
// pure stub path, not the disk-cache-recovery path (covered by its own
// test below).
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute", features: { diskCache: false } },
{ readAuthJson, fetcher, combosFetcher, logger }
);
const input = makeInput();
await hook(input);
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.ok(entry, "stub provider entry published even when fetchers fail");
assert.equal(entry.npm, "@ai-sdk/openai-compatible");
assert.deepEqual(entry.models, {}, "models stub is empty object");
assert.equal(entry.options.baseURL, "https://or.example/v1");
assert.equal(entry.options.apiKey, "sk-test");
// Both warns fired.
assert.ok(
logger.entries.some((e) => String(e[0]).includes("/v1/models fetch failed")),
"models-fetch breadcrumb emitted"
);
assert.ok(
logger.entries.some((e) => String(e[0]).includes("/api/combos fetch failed")),
"combos-fetch breadcrumb emitted"
);
});
// ────────────────────────────────────────────────────────────────────────────
// 6. Combos fetcher throws → models-only catalog (no combos in models block)
// ────────────────────────────────────────────────────────────────────────────
test("config: combos fetcher throws → emit models-only catalog (no combos in models block)", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
});
const fetcher = stubModelsFetcher([MODEL_CLAUDE, MODEL_GEMINI]);
const combosFetcher = throwingCombosFetcher();
const logger = captureWarn();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute" },
{ readAuthJson, fetcher, combosFetcher, logger }
);
const input = makeInput();
await hook(input);
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.ok(entry);
const ids = Object.keys(entry.models).sort();
assert.deepEqual(ids, [
"opencode-omniroute/claude-sonnet-4-6",
"opencode-omniroute/gemini-3-flash",
]);
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"
);
});
// ────────────────────────────────────────────────────────────────────────────
// 7. baseURL from auth.json takes precedence when opts.baseURL absent
// ────────────────────────────────────────────────────────────────────────────
test("config: baseURL from auth.json takes precedence when opts.baseURL absent", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://creds.example/v1" },
});
const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
const combosFetcher = stubCombosFetcher([]);
const logger = captureWarn();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute" }, // NO opts.baseURL
{ readAuthJson, fetcher, combosFetcher, logger }
);
const input = makeInput();
await hook(input);
assert.equal(fetcher.callsBy()[0][0], "https://creds.example/v1");
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.equal(entry.options.baseURL, "https://creds.example/v1");
});
test("config: opts.baseURL wins over auth.json's stored baseURL", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://creds.example/v1" },
});
const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
const combosFetcher = stubCombosFetcher([]);
const logger = captureWarn();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute", baseURL: "https://opts.example/v1" },
{ readAuthJson, fetcher, combosFetcher, logger }
);
const input = makeInput();
await hook(input);
assert.equal(fetcher.callsBy()[0][0], "https://opts.example/v1");
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.equal(entry.options.baseURL, "https://opts.example/v1");
});
test("config: no baseURL resolvable (no opts, no auth.json baseURL) → no-op", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-test" }, // NO baseURL on the credential
});
const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
const combosFetcher = stubCombosFetcher([]);
const logger = captureWarn();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute" }, // NO opts.baseURL
{ readAuthJson, fetcher, combosFetcher, logger }
);
const input = makeInput();
await hook(input);
assert.deepEqual((input as { provider: Record<string, unknown> }).provider, {});
assert.equal(fetcher.callCount(), 0);
assert.ok(
logger.entries.some((e) => String(e[0]).includes("no baseURL")),
"no-baseURL breadcrumb emitted"
);
});
// ────────────────────────────────────────────────────────────────────────────
// 8. Multi-instance: two plugins with different providerIds publish to
// their own keys without collision.
// ────────────────────────────────────────────────────────────────────────────
test("config: multi-instance — two plugins with different providerIds publish to their own keys without collision", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute-prod": {
type: "api",
key: "sk-prod",
baseURL: "https://prod.example/v1",
},
"opencode-omniroute-preprod": {
type: "api",
key: "sk-preprod",
baseURL: "https://preprod.example/v1",
},
});
const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
const combosFetcher = stubCombosFetcher([]);
const logger = captureWarn();
const hookA = createOmniRouteConfigHook(
{ providerId: "omniroute-prod" },
{ readAuthJson, fetcher, combosFetcher, logger }
);
const hookB = createOmniRouteConfigHook(
{ providerId: "omniroute-preprod" },
{ readAuthJson, fetcher, combosFetcher, logger }
);
const input = makeInput();
await hookA(input);
await hookB(input);
const provider = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider;
assert.ok(provider["opencode-omniroute-prod"], "prod block present");
assert.ok(provider["opencode-omniroute-preprod"], "preprod block present");
assert.equal(provider["opencode-omniroute-prod"].options.apiKey, "sk-prod");
assert.equal(provider["opencode-omniroute-preprod"].options.apiKey, "sk-preprod");
assert.equal(provider["opencode-omniroute-prod"].options.baseURL, "https://prod.example/v1");
assert.equal(
provider["opencode-omniroute-preprod"].options.baseURL,
"https://preprod.example/v1"
);
assert.notEqual(
provider["opencode-omniroute-prod"],
provider["opencode-omniroute-preprod"],
"blocks are distinct references"
);
});
// ────────────────────────────────────────────────────────────────────────────
// 9. Cache sharing: provider hook + config hook on the same Map dedupe
// fetcher invocations.
// ────────────────────────────────────────────────────────────────────────────
test("config + provider share cache: second call uses cached fetch result (single fetch per TTL)", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-shared", baseURL: "https://or.example/v1" },
});
const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
const combosFetcher = stubCombosFetcher([COMBO_CLAUDE_TIER]);
const sharedCache: OmniRouteFetchCache = new Map();
const logger = captureWarn();
const configHook = createOmniRouteConfigHook(
{ providerId: "omniroute", baseURL: "https://or.example/v1", modelCacheTtl: 60_000 },
{ readAuthJson, fetcher, combosFetcher, cache: sharedCache, logger }
);
const providerHook = createOmniRouteProviderHook(
{ providerId: "omniroute", baseURL: "https://or.example/v1", modelCacheTtl: 60_000 },
{ fetcher, combosFetcher, cache: sharedCache }
);
// Simulate OC ≥1.14.49 cold start: config fires first, populates cache,
// then provider.models() reuses the cached raw results.
const input = makeInput();
await configHook(input);
assert.equal(fetcher.callCount(), 1, "config fired the only models fetch");
assert.equal(combosFetcher.callCount(), 1, "config fired the only combos fetch");
// provider hook then runs — should hit the shared cache, NOT refetch.
const apiAuth = { type: "api", key: "sk-shared" };
await providerHook.models!({} as never, { auth: apiAuth as never });
assert.equal(fetcher.callCount(), 1, "provider reused cached models");
assert.equal(combosFetcher.callCount(), 1, "provider reused cached combos");
});
test("provider → config order also dedupes (cache populated by provider, consumed by config)", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-reverse", baseURL: "https://or.example/v1" },
});
const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
const combosFetcher = stubCombosFetcher([]);
const sharedCache: OmniRouteFetchCache = new Map();
const logger = captureWarn();
const configHook = createOmniRouteConfigHook(
{ providerId: "omniroute", baseURL: "https://or.example/v1", modelCacheTtl: 60_000 },
{ readAuthJson, fetcher, combosFetcher, cache: sharedCache, logger }
);
const providerHook = createOmniRouteProviderHook(
{ providerId: "omniroute", baseURL: "https://or.example/v1", modelCacheTtl: 60_000 },
{ fetcher, combosFetcher, cache: sharedCache }
);
await providerHook.models!({} as never, {
auth: { type: "api", key: "sk-reverse" } as never,
});
assert.equal(fetcher.callCount(), 1);
const input = makeInput();
await configHook(input);
assert.equal(fetcher.callCount(), 1, "config reused cached models");
});
// ────────────────────────────────────────────────────────────────────────────
// 10. Stripped models shape matches sibling provider spec
// (`{name, attachment, reasoning, tool_call, temperature, limit?}`).
// ────────────────────────────────────────────────────────────────────────────
test("buildStaticProviderEntry: stripped per-model shape matches sibling @omniroute/opencode-provider", () => {
const resolved = resolveOmniRoutePluginOptions({
providerId: "omniroute",
displayName: "OmniRoute",
});
const block = buildStaticProviderEntry(
[MODEL_CLAUDE, MODEL_GEMINI],
[],
resolved,
"https://or.example/v1",
"sk-test"
);
// Top-level provider entry shape — ONLY these four keys.
assert.deepEqual(Object.keys(block).sort(), ["models", "name", "npm", "options"]);
assert.equal(block.npm, "@ai-sdk/openai-compatible");
assert.equal(block.name, "OmniRoute");
assert.deepEqual(Object.keys(block.options).sort(), ["apiKey", "baseURL"]);
// Per-model entry shape — the keys OC's SDK static schema accepts
// (see @opencode-ai/sdk types.gen.d.ts). NO nested capabilities tree,
// NO providerID/api fields from ModelV2 (those belong on the dynamic
// hook path).
const allowedKeys = new Set([
"name",
"release_date",
"attachment",
"reasoning",
"temperature",
"tool_call",
"cost",
"limit",
"modalities",
"providerID",
]);
for (const [id, entry] of Object.entries(block.models)) {
for (const key of Object.keys(entry)) {
assert.ok(allowedKeys.has(key), `${id}.${key} is not in the SDK static shape`);
}
// capabilities (ModelV2-only) must NOT leak — that's the dynamic-
// hook nested shape, not the static SDK schema.
assert.equal(
(entry as Record<string, unknown>).capabilities,
undefined,
`${id} must not carry nested capabilities tree`
);
}
// Sanity: claude entry has all expected stripped fields.
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");
assert.equal(typeof claude.temperature, "boolean");
assert.equal(typeof claude.tool_call, "boolean");
assert.equal(typeof claude.limit?.context, "number");
});
test("buildStaticProviderEntry: empty fetch results → stub block with models: {}", () => {
const resolved = resolveOmniRoutePluginOptions({ providerId: "omniroute" });
const block = buildStaticProviderEntry([], [], resolved, "https://or.example/v1", "sk-test");
assert.deepEqual(block.models, {});
assert.equal(block.options.apiKey, "sk-test");
});
test("buildStaticProviderEntry: hidden combos are excluded", () => {
const resolved = resolveOmniRoutePluginOptions({ providerId: "omniroute" });
const block = buildStaticProviderEntry(
[MODEL_CLAUDE],
[{ ...COMBO_CLAUDE_TIER, isHidden: true }],
resolved,
"https://or.example/v1",
"sk-test"
);
assert.equal(block.models["opencode-omniroute/claude-tier"], undefined);
assert.ok(block.models["opencode-omniroute/claude-sonnet-4-6"]);
});
// ────────────────────────────────────────────────────────────────────────────
// Schema parity (modalities / cost / release_date / limit cleanup)
// ────────────────────────────────────────────────────────────────────────────
test("buildStaticProviderEntry: emits modalities.input from raw.input_modalities", () => {
const resolved = resolveOmniRoutePluginOptions({ providerId: "omniroute" });
const block = buildStaticProviderEntry(
[MODEL_CLAUDE, MODEL_GEMINI],
[],
resolved,
"https://or.example/v1",
"sk-test"
);
const claude = block.models["opencode-omniroute/claude-sonnet-4-6"];
assert.deepEqual(claude.modalities?.input, ["text", "image"]);
assert.deepEqual(claude.modalities?.output, ["text"]);
});
test("buildStaticProviderEntry: never emits limit.input (OC SDK rejects it)", () => {
const resolved = resolveOmniRoutePluginOptions({ providerId: "omniroute" });
const block = buildStaticProviderEntry(
[MODEL_CLAUDE],
[],
resolved,
"https://or.example/v1",
"sk-test"
);
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");
});
test("buildStaticProviderEntry: emits cost when enrichment carries pricing", () => {
const resolved = resolveOmniRoutePluginOptions({ providerId: "omniroute" });
const enrichment = new Map([
[
"claude-sonnet-4-6",
{
name: "Claude Sonnet 4.6",
providerAlias: "cc",
providerCanonical: "claude",
providerDisplayName: "Claude",
pricing: { input: 3, output: 15, cacheRead: 0.3, cacheWrite: 3.75 },
},
],
]);
const block = buildStaticProviderEntry(
[MODEL_CLAUDE],
[],
resolved,
"https://or.example/v1",
"sk-test",
enrichment
);
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);
assert.equal(claude.cost?.cache_write, 3.75);
});
test("buildStaticProviderEntry: emits release_date when raw carries it; omits when null", () => {
const resolved = resolveOmniRoutePluginOptions({ providerId: "omniroute" });
const withDate: OmniRouteRawModelEntry = {
...MODEL_CLAUDE,
id: "claude-with-date",
release_date: "2026-02-19",
};
const block = buildStaticProviderEntry(
[withDate, MODEL_GEMINI],
[],
resolved,
"https://or.example/v1",
"sk-test"
);
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)", () => {
const resolved = resolveOmniRoutePluginOptions({ providerId: "omniroute" });
const TEXT_ONLY: OmniRouteRawModelEntry = {
id: "text-only",
capabilities: { tool_calling: true, reasoning: false, vision: false, thinking: false },
context_length: 100_000,
max_output_tokens: 4_096,
input_modalities: ["text"],
output_modalities: ["text"],
};
const block = buildStaticProviderEntry(
[MODEL_CLAUDE, TEXT_ONLY],
[
{
id: "combo-mixed",
name: "Mixed Tier",
models: [
{ id: "s1", kind: "model", model: "claude-sonnet-4-6", weight: 100 },
{ id: "s2", kind: "model", model: "text-only", weight: 50 },
],
},
],
resolved,
"https://or.example/v1",
"sk-test"
);
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"]);
assert.deepEqual(combo.modalities?.output, ["text"]);
});
// ────────────────────────────────────────────────────────────────────────────
// Integration: OmniRoutePlugin factory now exposes config hook
// ────────────────────────────────────────────────────────────────────────────
test("OmniRoutePlugin factory exposes config hook alongside auth + provider", async () => {
const hooks = await OmniRoutePlugin({} as never, { providerId: "omniroute" });
assert.equal(typeof hooks.config, "function", "config hook present");
assert.ok(hooks.auth, "auth hook present");
assert.ok(hooks.provider, "provider hook present");
});
// ────────────────────────────────────────────────────────────────────────────
// Edge cases / robustness
// ────────────────────────────────────────────────────────────────────────────
test("config: auth.json entry of wrong type (oauth) → no-op", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "oauth", refresh: "r", access: "a", expires: 0 },
});
const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
const combosFetcher = stubCombosFetcher([]);
const logger = captureWarn();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute", baseURL: "https://or.example/v1" },
{ readAuthJson, fetcher, combosFetcher, logger }
);
const input = makeInput();
await hook(input);
assert.deepEqual((input as { provider: Record<string, unknown> }).provider, {});
assert.equal(fetcher.callCount(), 0);
});
test("config: readAuthJson throws → treat as missing file (silent fallback)", async () => {
const readAuthJson = throwingReadAuthJson();
const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
const combosFetcher = stubCombosFetcher([]);
const logger = captureWarn();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute", baseURL: "https://or.example/v1" },
{ readAuthJson, fetcher, combosFetcher, logger }
);
const input = makeInput();
await hook(input);
assert.deepEqual((input as { provider: Record<string, unknown> }).provider, {});
assert.equal(readAuthJson.callCount(), 1);
assert.equal(fetcher.callCount(), 0);
});
test("config: initialises input.provider when undefined", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk", baseURL: "https://or.example/v1" },
});
const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
const combosFetcher = stubCombosFetcher([]);
const logger = captureWarn();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute" },
{ readAuthJson, fetcher, combosFetcher, logger }
);
// input with NO provider field at all
const input = {} as Config;
await hook(input);
const provider = (input as { provider?: Record<string, unknown> }).provider;
assert.ok(provider, "provider bag initialised");
assert.ok(provider!["opencode-omniroute"]);
});
// ────────────────────────────────────────────────────────────────────────────
// Enrichment overlay — eager fetch on config-hook so OC ≤1.15.5 TUI sees
// human display names instead of raw provider/model ids.
// ────────────────────────────────────────────────────────────────────────────
test("config: enrichment fetched + name overlaid on raw-model entries", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
});
const fetcher = stubModelsFetcher([MODEL_CLAUDE, MODEL_GEMINI]);
const combosFetcher = stubCombosFetcher([COMBO_CLAUDE_TIER]);
const enrichmentFetcher = stubEnrichmentFetcher(
new Map<string, OmniRouteEnrichmentEntry>([
["claude-sonnet-4-6", { name: "Claude Sonnet 4.6" }],
["gemini-3-flash", { name: "Gemini 3 Flash" }],
])
);
const logger = captureWarn();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute" },
{ readAuthJson, fetcher, combosFetcher, enrichmentFetcher, logger }
);
const input = makeInput();
await hook(input);
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.ok(entry);
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["opencode-omniroute/claude-tier"].name, "Claude Tier");
assert.equal(enrichmentFetcher.callCount(), 1);
});
test("config: features.enrichment=false skips enrichment fetch + keeps raw-id names", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
});
const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
const combosFetcher = stubCombosFetcher([]);
const enrichmentFetcher = stubEnrichmentFetcher(
new Map<string, OmniRouteEnrichmentEntry>([
["claude-sonnet-4-6", { name: "Claude Sonnet 4.6" }],
])
);
const logger = captureWarn();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute", features: { enrichment: false } },
{ readAuthJson, fetcher, combosFetcher, enrichmentFetcher, logger }
);
const input = makeInput();
await hook(input);
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.ok(entry);
assert.equal(enrichmentFetcher.callCount(), 0, "enrichment fetch suppressed by feature flag");
assert.equal(
entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
"claude-sonnet-4-6",
"raw id retained"
);
});
test("config: enrichment fetcher throws → soft-fail (warn + raw-id static catalog)", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
});
const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
const combosFetcher = stubCombosFetcher([]);
const enrichmentFetcher = throwingEnrichmentFetcher();
const logger = captureWarn();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute" },
{ readAuthJson, fetcher, combosFetcher, enrichmentFetcher, logger }
);
const input = makeInput();
await hook(input);
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.ok(entry, "static block still published on enrichment failure");
assert.equal(
entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
"claude-sonnet-4-6",
"raw id retained"
);
assert.equal(enrichmentFetcher.callCount(), 1);
assert.ok(
logger.entries.some((e) => String(e[0]).includes("/api/pricing/models fetch failed")),
"enrichment-fetch breadcrumb emitted"
);
});
function stubProvidersFetcher(payload: OmniRouteProviderConnection[]): OmniRouteProvidersFetcher & {
callCount: () => number;
} {
let n = 0;
const f: OmniRouteProvidersFetcher = async () => {
n++;
return payload;
};
return Object.assign(f, { callCount: () => n });
}
function throwingProvidersFetcher(): OmniRouteProvidersFetcher & { callCount: () => number } {
let n = 0;
const f: OmniRouteProvidersFetcher = async () => {
n++;
throw new Error("ETIMEDOUT");
};
return Object.assign(f, { callCount: () => n });
}
const MODEL_CC_OPUS: OmniRouteRawModelEntry = {
id: "cc/claude-opus-4-7",
capabilities: { tool_calling: true, reasoning: true, temperature: true },
context_length: 200_000,
};
const MODEL_NV_LLAMA: OmniRouteRawModelEntry = {
id: "nvidia/llama-3-70b",
capabilities: { tool_calling: true, temperature: true },
context_length: 128_000,
};
test("config: usableOnly=false → no filter (existing behavior)", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
});
const fetcher = stubModelsFetcher([MODEL_CC_OPUS, MODEL_NV_LLAMA]);
const combosFetcher = stubCombosFetcher([]);
const providersFetcher = stubProvidersFetcher([
{ id: "c1", provider: "claude", isActive: true, testStatus: "active" },
]);
const enrichmentFetcher = stubEnrichmentFetcher(
new Map<string, OmniRouteEnrichmentEntry>([
["cc/claude-opus-4-7", { name: "Claude Opus 4.7" }],
["nvidia/llama-3-70b", { name: "Llama 3 70B" }],
])
);
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute", baseURL: "https://or.example/v1" },
{ readAuthJson, fetcher, combosFetcher, enrichmentFetcher, providersFetcher }
);
const input = makeInput();
await hook(input);
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.ok(entry.models["cc/claude-opus-4-7"], "claude kept");
assert.ok(entry.models["nvidia/llama-3-70b"], "nvidia kept (filter off)");
assert.equal(providersFetcher.callCount(), 0, "providers fetch not called when feature off");
});
test("config: usableOnly=true → drops models for non-usable providers, keeps usable + unknown", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
});
const fetcher = stubModelsFetcher([
MODEL_CC_OPUS,
MODEL_NV_LLAMA,
// Unknown prefix not in pricing-models nor connections — must pass through.
{
id: "agentrouter/synthetic-1",
capabilities: { temperature: true },
context_length: 100_000,
},
]);
const combosFetcher = stubCombosFetcher([]);
const providersFetcher = stubProvidersFetcher([
// Claude is usable.
{ id: "c1", provider: "claude", isActive: true, testStatus: "active" },
// Nvidia provisioned but errored → not usable.
{ id: "c2", provider: "nvidia", isActive: true, testStatus: "error" },
]);
const enrichmentFetcher = stubEnrichmentFetcher(
new Map<string, OmniRouteEnrichmentEntry>([
[
"cc/claude-opus-4-7",
{ name: "Claude Opus 4.7", providerAlias: "cc", providerCanonical: "claude" },
],
[
"nvidia/llama-3-70b",
{ name: "Llama 3 70B", providerAlias: "nvidia", providerCanonical: "nvidia" },
],
])
);
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute", baseURL: "https://or.example/v1", features: { usableOnly: true } },
{ readAuthJson, fetcher, combosFetcher, enrichmentFetcher, providersFetcher }
);
const input = makeInput();
await hook(input);
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.ok(entry.models["cc/claude-opus-4-7"], "claude kept (active)");
assert.equal(entry.models["nvidia/llama-3-70b"], undefined, "nvidia dropped (error status)");
assert.ok(entry.models["agentrouter/synthetic-1"], "unknown prefix kept (subtract-filter)");
assert.equal(providersFetcher.callCount(), 1);
});
test("config: usableOnly=true + providers fetch fails → soft-fail keeps everything", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
});
const fetcher = stubModelsFetcher([MODEL_CC_OPUS, MODEL_NV_LLAMA]);
const combosFetcher = stubCombosFetcher([]);
const providersFetcher = throwingProvidersFetcher();
const enrichmentFetcher = stubEnrichmentFetcher(
new Map<string, OmniRouteEnrichmentEntry>([
["cc/claude-opus-4-7", { name: "Claude Opus 4.7" }],
["nvidia/llama-3-70b", { name: "Llama 3 70B" }],
])
);
const logger = captureWarn();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute", baseURL: "https://or.example/v1", features: { usableOnly: true } },
{ readAuthJson, fetcher, combosFetcher, enrichmentFetcher, providersFetcher, logger }
);
const input = makeInput();
await hook(input);
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.ok(entry.models["cc/claude-opus-4-7"]);
assert.ok(entry.models["nvidia/llama-3-70b"], "soft-fail keeps both");
assert.ok(
logger.entries.some((e) => String(e[0]).includes("/api/providers fetch failed")),
"providers-fetch breadcrumb emitted"
);
});
test("config: diskCache hydrates stale snapshot when /v1/models throws", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
});
const fetcher = throwingModelsFetcher();
const combosFetcher = stubCombosFetcher([]);
const logger = captureWarn();
// Disk reader returns a stale snapshot — emulates the last-known-good
// catalog written on a healthy refresh.
const diskSnapshotReader: typeof import("../src/index.js").defaultDiskSnapshotReader =
async () => ({
rawModels: [MODEL_CLAUDE],
rawCombos: [],
rawEnrichment: new Map([["claude-sonnet-4-6", { name: "Claude Sonnet 4.6 (cached)" }]]),
rawCompressionCombos: [],
rawConnections: [],
});
let writes = 0;
const diskSnapshotWriter: typeof import("../src/index.js").defaultDiskSnapshotWriter =
async () => {
writes++;
};
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute", features: { diskCache: true } },
{
readAuthJson,
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.models["opencode-omniroute/claude-sonnet-4-6"],
"stale snapshot hydrated into static block"
);
assert.equal(
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")),
"disk-cache hydration breadcrumb emitted"
);
});
test("config: cached rawEnrichment from earlier provider hook is reused (no refetch)", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-shared", baseURL: "https://or.example/v1" },
});
const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
const combosFetcher = stubCombosFetcher([]);
const enrichmentFetcher = stubEnrichmentFetcher(
new Map<string, OmniRouteEnrichmentEntry>([
["claude-sonnet-4-6", { name: "Claude Sonnet 4.6" }],
])
);
const sharedCache: OmniRouteFetchCache = new Map();
const logger = captureWarn();
const providerHook = createOmniRouteProviderHook(
{ providerId: "omniroute", baseURL: "https://or.example/v1", modelCacheTtl: 60_000 },
{ fetcher, combosFetcher, enrichmentFetcher, cache: sharedCache }
);
const configHook = createOmniRouteConfigHook(
{ providerId: "omniroute", baseURL: "https://or.example/v1", modelCacheTtl: 60_000 },
{ readAuthJson, fetcher, combosFetcher, enrichmentFetcher, cache: sharedCache, logger }
);
// Provider hook fires first (e.g. eager cache warm-up), populates rawEnrichment.
await providerHook.models!({} as never, {
auth: { type: "api", key: "sk-shared" } as never,
});
assert.equal(enrichmentFetcher.callCount(), 1);
// Config hook then fires — must reuse cached enrichment, not refetch.
const input = makeInput();
await configHook(input);
assert.equal(enrichmentFetcher.callCount(), 1, "config reused cached enrichment");
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.equal(entry.models["opencode-omniroute/claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
});
// ─────────────────────────────────────────────────────────────────────
// Provider-tag suffix (Option E) — append upstream provider label to
// enriched model names so the picker can differentiate `cc/claude-opus-4-7`
// (Anthropic) from `kr/claude-opus-4-7` (Kiro) etc.
// ─────────────────────────────────────────────────────────────────────
test("config: providerTag (default-on) prepends '<provider> - ' to enriched raw-model names", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
});
const fetcher = stubModelsFetcher([MODEL_CLAUDE, MODEL_GEMINI]);
const combosFetcher = stubCombosFetcher([COMBO_CLAUDE_TIER]);
const enrichmentFetcher = stubEnrichmentFetcher(
new Map<string, OmniRouteEnrichmentEntry>([
[
"claude-sonnet-4-6",
{
name: "Claude Sonnet 4.6",
providerAlias: "cc",
providerCanonical: "claude",
providerDisplayName: "Claude",
},
],
[
"gemini-3-flash",
{
name: "Gemini 3 Flash",
providerAlias: "gemini-cli",
providerCanonical: "gemini-cli",
providerDisplayName: "Gemini-cli",
},
],
])
);
const logger = captureWarn();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute" },
{ readAuthJson, fetcher, combosFetcher, enrichmentFetcher, logger }
);
const input = makeInput();
await hook(input);
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.ok(entry);
assert.equal(
entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
"Claude - Claude Sonnet 4.6"
);
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["opencode-omniroute/claude-tier"].name, "Claude Tier");
});
test("config: providerTag=false suppresses the suffix", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
});
const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
const combosFetcher = stubCombosFetcher([]);
const enrichmentFetcher = stubEnrichmentFetcher(
new Map<string, OmniRouteEnrichmentEntry>([
["claude-sonnet-4-6", { name: "Claude Sonnet 4.6", providerDisplayName: "Claude" }],
])
);
const logger = captureWarn();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute", features: { providerTag: false } },
{ readAuthJson, fetcher, combosFetcher, enrichmentFetcher, logger }
);
const input = makeInput();
await hook(input);
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.equal(
entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
"Claude Sonnet 4.6",
"enriched name kept, provider tag suppressed"
);
});
test("config: providerTag falls back to UPPER(alias) when providerDisplayName missing", async () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
});
const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
const combosFetcher = stubCombosFetcher([]);
// Enrichment has the friendly name but NO providerDisplayName — e.g.
// a slot OmniRoute hasn't curated a human label for yet. We still
// have the alias though, so the prefix uses UPPER(alias) = "CC".
const enrichmentFetcher = stubEnrichmentFetcher(
new Map<string, OmniRouteEnrichmentEntry>([
["claude-sonnet-4-6", { name: "Claude Sonnet 4.6", providerAlias: "cc" }],
])
);
const logger = captureWarn();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute" },
{ readAuthJson, fetcher, combosFetcher, enrichmentFetcher, logger }
);
const input = makeInput();
await hook(input);
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
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 () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
});
const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
const combosFetcher = stubCombosFetcher([]);
// No metadata at all — defensive case, e.g. legacy enrichment payload.
const enrichmentFetcher = stubEnrichmentFetcher(
new Map<string, OmniRouteEnrichmentEntry>([
["claude-sonnet-4-6", { name: "Claude Sonnet 4.6" }],
])
);
const logger = captureWarn();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute" },
{ readAuthJson, fetcher, combosFetcher, enrichmentFetcher, logger }
);
const input = makeInput();
await hook(input);
const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
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 () => {
const readAuthJson = stubReadAuthJson({
"opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
});
const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
const combosFetcher = stubCombosFetcher([]);
const enrichmentFetcher = stubEnrichmentFetcher(
new Map<string, OmniRouteEnrichmentEntry>([
["claude-sonnet-4-6", { name: "Claude Sonnet 4.6", providerDisplayName: "Claude" }],
])
);
const logger = captureWarn();
const sharedCache = new Map();
const hook = createOmniRouteConfigHook(
{ providerId: "omniroute", modelCacheTtl: 60_000 },
{ readAuthJson, fetcher, combosFetcher, enrichmentFetcher, cache: sharedCache, logger }
);
const inputA = makeInput();
await hook(inputA);
const entryA = (inputA as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.equal(
entryA.models["opencode-omniroute/claude-sonnet-4-6"].name,
"Claude - Claude Sonnet 4.6"
);
// Second invocation (cache hit) — name must still be single-suffixed.
const inputB = makeInput();
await hook(inputB);
const entryB = (inputB as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
"opencode-omniroute"
];
assert.equal(
entryB.models["opencode-omniroute/claude-sonnet-4-6"].name,
"Claude - Claude Sonnet 4.6"
);
});
// ────────────────────────────────────────────────────────────────────────────
// T-NN: nested combo-ref resolution in the static catalog
// (mirrors the dynamic-catalog fix in combos.test.ts)
// ────────────────────────────────────────────────────────────────────────────
test("buildStaticProviderEntry: nested combo-ref context is the bottleneck across the graph", () => {
const resolved = resolveOmniRoutePluginOptions({ providerId: "omniroute" });
const rawModels: OmniRouteRawModelEntry[] = [
{
id: "raw-big",
context_length: 200_000,
max_output_tokens: 64_000,
capabilities: { tool_calling: true, reasoning: true, vision: false, temperature: true },
input_modalities: ["text"],
output_modalities: ["text"],
},
{
id: "raw-tiny",
context_length: 8_000,
max_output_tokens: 4_000,
capabilities: { tool_calling: false, reasoning: false, vision: false, temperature: true },
input_modalities: ["text"],
output_modalities: ["text"],
},
];
const rawCombos: OmniRouteRawCombo[] = [
{
id: "tiny-combo",
name: "TinyCombo",
models: [{ id: "m1", kind: "model", model: "raw-tiny", weight: 100 }],
},
{
id: "parent",
name: "Parent",
models: [
{ id: "p1", kind: "model", model: "raw-big", weight: 50 },
{ id: "p2", kind: "combo-ref", comboName: "TinyCombo", weight: 50 },
],
},
];
const block = buildStaticProviderEntry(
rawModels,
rawCombos,
resolved,
"https://or.example/v1",
"sk-test"
);
// Pre-fix: Parent would advertise 200_000 (only raw-big counted).
// Post-fix: Parent should advertise 8_000 (TinyCombo bottleneck).
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);
});