`tests/unit/i18n-vi-completeness.test.ts` exige paridade ESTRITA de chaves entre
en e vi — diferente do ratchet `i18n:check-ui-coverage`, que passa com 80%. As 11
chaves do seletor de perfil entraram só em en e pt-BR, e o gate de cobertura
seguiu verde, então a quebra só apareceu na matriz completa do CI.
Fecha o caminho do operador: o perfil já existia no adapter, mas só como
default de código. Agora atravessa schema Zod, normalizador do banco, API de
settings e a página dedicada do engine.
- OmniglyphConfig tipado + omniglyphConfigSchema (z.enum dos quatro perfis);
- normalizeOmniglyphConfig: nome desconhecido vindo do storage cai para o
default em vez de virar "roda com a política padrão";
- seletor na página do engine, com PATCH próprio — o perfil vive fora do mapa
`engines`, e mandá-lo junto reescreveria o mapa inteiro (o store persiste o
mapa como uma linha JSON só);
- i18n en/pt-BR descrevendo o custo medido de cada perfil, não só o nome;
- README e COMPRESSION_ENGINES.md com a regra do teto e o motivo de o default
não ser o perfil mais seguro.
Corrige de passagem um teste-irmão que ninguém via: o gate de transporte na UI
deixou de dizer "direct Anthropic" quando os wires OpenAI nativos entraram, mas
tests/unit/ui/omniglyphContextPage.test.tsx continuou afirmando a cópia antiga.
O arquivo inteiro estava excluído do vitest.config.ts como "#8618 pre-existing
failure", então a quebra passou silenciosa. Com a asserção alinhada o arquivo
fecha 3/3, e a exclusão sai — o próprio comentário mandava removê-la quando
corrigida.
A doc não nomeia OMNIGLYPH_MODELS: o gate de docs fabricadas está certo em
apontar que o OmniRoute nunca lê essa env — quem lê é o pacote.
O adapter descartava o TransformInfo inteiro, então a UI mostrava um número de
economia sem dizer de onde ele vinha — contagem do provider, estimativa ou só
diferença de bytes. O 1.4.0 expõe normalizeAccounting(), que classifica essa
evidência e resolve a semântica de cache por família: Anthropic reporta input,
cache-create e cache-read em buckets DISJUNTOS, enquanto OpenAI e xAI reportam
cached como SUBCONJUNTO do input. Somar à mão dá double-count silencioso.
O novo omniglyphTelemetry.ts não filtra por denylist — MONTA um objeto novo,
campo a campo, só com número e enum. TransformInfo mistura contadores
inofensivos com material que não pode ser persistido: bytes PNG,
imageSourceText(s), recoverable[].text, os sha8 de system/CLAUDE.md/primeira
mensagem, nomes de tags observadas e o bloco env (cwd, branch, versões). Copiar
o objeto inteiro transformaria telemetria de compressão em vazamento de prompt.
O teste de negação prova que segredo, caminho do operador, texto do system e
base64 não aparecem, e varre a allowlist exigindo que toda string seja de um
enum conhecido.
- provider threaded do chatCore e do bridge Codex WS até a engine; ausente vira
`unknown`, que faz o upstream recusar adivinhar buckets de cache;
- contabilidade propagada para o engineBreakdown do passo (o agregado do
pipeline soma todas as engines e não serviria);
- skip não emite contabilidade: zeros ali seriam indistinguíveis de "a engine
nem rodou".
O 1.4.0 trouxe perfis nomeados (coding-safe, balanced, aggressive,
passthrough), mas só transformAnthropicMessages() os resolve sozinho: os
transformadores OpenAI recebem TransformOptions cru e ignorariam o campo. Um
perfil escolhido pelo operador valeria no wire Claude e sumiria no OpenAI. O
adapter passa a mesclar o perfil com mergeCompressionProfileOptions() antes de
chamar Chat Completions e Responses.
O default segue aggressive — a política que os recibos publicados mediram.
Medido nesta base: com coding-safe/balanced, uma sessão sem histórico acumulado
para em below_min_chars e a engine não faz nada, porque os dois fixam
minCompressChars no máximo e desligam system/tools/tool-results. Como a engine é
opt-in, um default assim entregaria "ligado, 0% de ganho".
O perfil é TETO, não piso: mergeCompressionProfileOptions não deixa um override
do chamador reabrir uma lane lossy que o perfil fechou. Coberto por teste, por
ser contra-intuitivo.
Também fecha um caminho em que o OmniRoute violaria a própria política: o wire
OpenAI do pacote não tem compressSystem — honra apenas compressTools,
gptHistory, minCompressChars e reflow, e sempre troca a instrução por um
ponteiro para a imagem. Com preserveSystemPrompt ligado, imagear assim queimaria
o prefixo quente que a decisão cache-aware está protegendo, sem nada no corpo
devolvido denunciando. A engine agora pula com
skip:system_preservation_unsupported_on_wire.
O 1.4.0 introduziu escopos de segurança e passou a resolvê-los dentro de
isOmniGlyphSupportedModel() lendo process.env.OMNIGLYPH_PROFILE. Somado ao
OMNIGLYPH_MODELS que já existia, duas variáveis do ambiente do host decidiam em
silêncio o gate de TODO request do OmniRoute: passthrough desligaria a engine
inteira e OMNIGLYPH_MODELS admitiria modelos sem recibo medido, enquanto a UI
segue prometendo "Claude Fable 5 na rota direta medida".
O adapter passa a usar isOmniGlyphSupportedModelForScope() com escopo explícito
e fixa o escopo mais restrito como teto: a env só pode ESTREITAR a allowlist,
nunca alargar. Os dois wires compartilham a mesma lista no pacote desde o
1.4.0, então uma checagem cobre Anthropic e GPT.
- omniglyph ^1.3.1 -> ^1.4.0 (lock em 1.4.0);
- testes de regressão para os dois caminhos de sequestro por env;
- teste de contrato dos exports novos (escopo, perfis, accounting).
O 1.4.0 também traz, sem mudança de código aqui: correção do glyph K que era
lido como H, remoção do backtracking polinomial no secret-guard, overrides do
pnpm em pnpm-workspace.yaml e as transitivas vulneráveis resolvidas.
Roda o OmniGlyph depois da tradução para o wire real do provedor, em vez do
corpo de origem. Um cliente OpenAI roteado para Claude deixava de comprimir com
skip:source_format_not_claude porque o corpo ainda estava em formato OpenAI
quando a engine era avaliada.
- dispatch nativo por wire: Anthropic Messages, OpenAI Chat Completions e
OpenAI Responses (input[] preservado, sem achatar para messages[]);
- estágio target-wire pós-translateRequest, com guarda contra dupla compressão
no caminho Claude→OpenAI;
- preserveSystemPrompt do OmniRoute mapeado para compressSystem: false;
- imageTransportPolicy: fidelidade de bytes/dimensões separada de supportsVision;
só Anthropic/Claude tem recibo byte-preserving, o resto é fail-closed;
- contagem de tokens de data URL PNG no wire OpenAI (marcador ;base64,);
- README e i18n en/pt-BR com claims escopados ao caminho medido.
The 9 media *ExampleCard components under media-providers/components used
the masked value from useApiKey() (sk-xxxx****yyyy) as an Authorization:
Bearer header, which the gateway always rejects (AUTH_002) once
REQUIRE_API_KEY is enabled. Mirror the LlmChatCard fix (#3503): authenticate
via the dashboard session (credentials: "same-origin") and forward the
selected key's id via x-omniroute-playground-key-id instead of its secret.
buildCurl now keeps the <your-api-key> placeholder instead of the masked
value.
Adds tests/unit/bug-9935-masked-bearer.test.ts as the permanent regression
guard (asserts none of the 9 cards embed apiKey as a raw Bearer token).
Refs #9935
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
Validated in local merge-train-equivalent focused gate on release/v3.8.50 tip 9081b57146: catalog fingerprint regression + existing catalog-cache callers, 8 tests passed.
* fix(usage): read Gemini usageMetadata out of the antigravity response envelope
Port decolua/9router#59d858b: antigravity/gemini-cli wrap non-streaming
payloads in { response: {...} }, so extractUsageFromResponse only saw the
top-level usageMetadata and every non-streaming antigravity request logged
zero usage (IN 0 | OUT 0) and zeroed usage-dashboard rows. Top-level
metadata keeps priority; OpenAI/Claude branches untouched.
* chore(changelog): fragment for #10430 antigravity usage envelope
* fix(usage): surface Gemini cachedContentTokenCount as cached_tokens
Review follow-up on #10430: the Gemini branch of extractUsageFromResponse
ignored cachedContentTokenCount, so non-streaming cache-hit tokens never
reached the cached_tokens field the OpenAI/Claude/Responses branches
already populate (and the streaming path surfaces at usageTracking.ts:684).
Adds cached_tokens: usageMetadata.cachedContentTokenCount || 0, updates
the three Gemini assertions (envelope fixture already carried
cachedContentTokenCount: 7), and adds a dedicated regression test.
* chore(changelog): fragment for #10465 Gemini cached_tokens surfacing
* test(fix): refresh expired alibaba quota sample validity and onnxruntime pin for v3.8.50 base
- alibaba-free-tier-quota-fetcher.test.ts: sample quotaValidityPeriod
(2026-08-16 16:00 UTC) is in the past, making every quota entry classify
as expired/not_capable; bump to 2028-01-01 UTC so the text/merge
classification tests exercise the intended path again.
- optional-transformers-dependency.test.ts: onnxruntime-node pin assertion
updated from ~1.24.3 to ~1.27.0 to match package.json (bumped by #10403);
the regular-not-optional intent is unchanged.
---------
Co-authored-by: Rouzbeh <rqzbeh@users.noreply.github.com>
* fix(docker): real image tags + complete OMNIROUTE_BASE_PATH runtime patcher
Three docker issues fixed:
1. Images that do not exist:
- bifrost: ghcr.io/maximhq/bifrost:1.5.21 never existed (1.5.x tops at
v1.5.16, all tags carry the v prefix) -> ghcr.io/maximhq/bifrost:v1.6.11
- cliproxyapi: ghcr.io/router-for-me/* is not publicly pullable (403);
the official prebuilt image is docker.io/eceasy/cli-proxy-api, where
the pinned v6.9.7 exists -> docker.io/eceasy/cli-proxy-api:v6.9.7
- Verified still-current: redis:8.6.5-alpine (already on Redis 8 since
#9065; ioredis 5.10 is RESP2/3-compatible, no modules used) and
qdrant:v1.12.4 -- both exist, unchanged.
2. OMNIROUTE_BASE_PATH ignored on prebuilt images (root cause):
Next 16 (webpack and Turbopack) app-router renders SSR asset URLs from
assetPrefix ALONE; basePath only affects routing. The runtime patcher
(ensure-docker-base-path) rewrote basePath literals only, so a prebuilt
root-path image patched to /omniroute served the page but every
/_next/static shell reference stayed unprefixed (404 behind a subpath
proxy), the RSC flight-payload chunk refs came from client-reference
manifests baked with unprefixed paths, and the Turbopack client process
shim ships an empty env object so the client never learns the subpath.
Extended patch-standalone-base-path.mjs to also rewrite:
- assetPrefix literals (mirrors the subpath for SSR asset URLs)
- the NEXT_PUBLIC_OMNIROUTE_BASE_PATH env mirror in the inline config
- the client process.env shim (.env={}) with the two basePath keys
- every baked "/_next/static URL (manifests, media imports, .html pages)
next.config.mjs now mirrors basePath into assetPrefix so REBUILT images
bake prefixed assets too. E2E-verified on the published main-web image:
HTML under /omniroute now has 16/16 prefixed JS srcs and 82/82 prefixed
flight refs (was 13/9 + ~150 unprefixed), prefixed assets return 200.
* chore(changelog): fragment for #10482 (docker images + basepath patcher)
* chore(changelog): bullet-form fragment for #10482
* Merge branch 'release/v3.8.50' into fix/docker-compose-images-and-basepath
* test(fix): refresh expired alibaba quota sample validity and onnxruntime pin for v3.8.50 base
- alibaba-free-tier-quota-fetcher.test.ts: sample quotaValidityPeriod
(2026-08-16 16:00 UTC) is in the past, making every quota entry classify
as expired/not_capable; bump to 2028-01-01 UTC so the text/merge
classification tests exercise the intended path again.
- optional-transformers-dependency.test.ts: onnxruntime-node pin assertion
updated from ~1.24.3 to ~1.27.0 to match package.json (bumped by #10403);
the regular-not-optional intent is unchanged.
---------
Co-authored-by: Rouzbeh <rqzbeh@users.noreply.github.com>
* fix(antigravity): heal empty-projectId accounts via retryable auto-onboarding
Accounts with an empty Cloud Code projectId get a permanent 422 "Missing
Google projectId" when loadCodeAssist returns no project. The 3.8.50
bootstrap attempts to CREATE the project via onboardUser, but a single failed
attempt (transient network/upstream error) was memoized forever in
onboardAttemptedCache: every later request in the process skipped onboarding
and 422'd, even though a retry would succeed.
Replace the permanent per-token Set with a failure-backoff map: failed onboard
attempts are retried after a 5-minute backoff (bounded, self-healing), the
in-flight lock still dedupes concurrent calls, and success clears the failure
marker and memoizes the project as before. Accounts that CAN be onboarded now
heal automatically on a later request or token refresh — no user action.
Tests: the existing "does not retry" case is now framed as the backoff window;
a new case proves the account heals (retries onboarding and recovers the
project) once the backoff expires.
* chore(changelog): fragment for #10424 antigravity project autocreate
* feat(antigravity): BYOP fast-fail + manual GCP project-id override
Port decolua/9router#2934 + VansRouter 802a859:
- tryOnboardUser now returns a three-way status; a 200 onboardUser response
WITHOUT cloudaicompanionProject means Google deprecated automatic project
creation for standard-tier (personal) accounts (BYOP). Such accounts are
cached permanently (no pointless ~18s re-onboard) and the executor fails
fast with 403 GCP_PROJECT_REQUIRED + actionable 'enter your project id'
message instead of the generic 422 or a delayed 429.
- Transient onboard failures keep the existing 5-min backoff heal.
- Manual project-id override: the EditConnectionModal now stamps
providerSpecificData.isProjectIdManual when the operator enters a project
id, and tokenRefresh skips auto-discovery for flagged accounts so the
manual value is never overwritten.
* chore(changelog): cover BYOP fast-fail + manual override in #10424 fragment
* test(antigravity): expect fast 403 GCP_PROJECT_REQUIRED when loadCodeAssist finds no project (#10424)
Google now marks accounts without an onboarded project as BYOP (automatic
project creation deprecated for standard-tier accounts, #2934). The PR's
BYOP fast-fail path returns 403 gcp_project_required instead of the old
generic 422 missing_project_id; align the #2334 executor test with that
contract so CI unit-test shard 2/4 passes.
* fix(antigravity): persist isProjectIdManual, fix BYOP citation, dodge refresh-retry
Review follow-up on #10424:
1. EditConnectionModal: isProjectIdManual was set on
updates.providerSpecificData right after the project-id field, then the
OAuth path (Antigravity is always OAuth) rebuilt providerSpecificData from
connection.providerSpecificData before the request went out, discarding the
flag — tokenRefresh.ts was guarding a field never actually persisted. The
flag now lands in the single surviving antigravity merge, with a jsdom
regression test (modeled on edit-connection-modal-openai-store-toggle).
2. The '#2934' citation for the Google BYOP claim pointed at an unrelated
closed issue. Swapped for the real tracking issue #8491 (empty Google
projectId -> 422 class) across bootstrap/executor/test comments.
3. BYOP fast-fail now returns 422 instead of 403: chatCore's generic
401/403 -> refresh-and-retry path was hitting Google's OAuth token
endpoint on every request from an affected account (pointless — refreshing
cannot create a GCP project), and 422 matches the sibling
missing_project_id error the client already maps to an action-needed
prompt.
Also: eslint-disable-next-line for the pre-existing
react-hooks/set-state-in-effect baseline noise in the modal (repo
convention, same pattern as 11 other dashboard files).
* chore(ci): drop unused eslint-disable in EditConnectionModal form hydration
The react-hooks/set-state-in-effect disable added in the previous commit is
unused under the repo's pinned eslint-plugin-react-hooks (7.0.1) — the rule
does not fire on this line at that version, so the unused directive tripped
the whole-repo 'No new ESLint warnings' gate (max-warnings 0). Verified with
the lockfile-pinned plugin: lint:json is clean (0 errors, 0 warnings).
* fix(build): bound and retry the opencode-plugin npm install in prepublish
The plugin's node_modules is gitignored, so every fresh CI checkout runs a
full npm install inside @omniroute/opencode-plugin during build:cli. npm's
unbounded fetch retries turn a stalled registry CDN connection (the recurring
onnxruntime-class ETIMEDOUT flake) into a 20-30 minute hang — the DAST
'Build CLI bundle' step has been cancelled at the 30m cap repeatedly.
- Bound npm fetch: --fetch-timeout 60s, 2 retries with capped backoff — a
stalled connection now fails fast instead of hanging the job.
- Retry the install up to 3 times with a 10s pause between attempts, so
transient CDN failures recover in-build.
Net effect: the step either completes (network OK) or fails quickly with a
clear error (network down) — it can no longer eat the whole job budget.
* ci(quality): use the npm-ci-retry action on every install step
Fast Quality Gates failed on the recurring onnxruntime-node postinstall
ETIMEDOUT (Microsoft CDN 150.171.x.x) - the same transient flake that has
hit Vitest and dast-smoke today. Only the Build job used the retry action;
the other five jobs (Docs, Fast Quality Gates, Vitest, Unit Tests,
changelog) still ran a bare install and die on any CDN hiccup. Use the
existing retry action (3 attempts, exponential backoff) on every install
step for consistency.
* Merge branch 'release/v3.8.50' into fix/antigravity-project-autocreate
* test(fix): refresh expired alibaba quota sample validity and onnxruntime pin for v3.8.50 base
- alibaba-free-tier-quota-fetcher.test.ts: sample quotaValidityPeriod
(2026-08-16 16:00 UTC) is in the past, making every quota entry classify
as expired/not_capable; bump to 2028-01-01 UTC so the text/merge
classification tests exercise the intended path again.
- optional-transformers-dependency.test.ts: onnxruntime-node pin assertion
updated from ~1.24.3 to ~1.27.0 to match package.json (bumped by #10403);
the regular-not-optional intent is unchanged.
* test(fix): widen modelsDevSync lastSync wait from 200ms default to 2000ms
The truthy-spellings loop asserted each enabled case completes its first
fetch within waitFor's 200ms default timeout, which trips under CI runner
load (observed on PR 10424 shard 2/4). Match the file's other lastSync
waits (2000ms) so the sync-completion assertion is load-tolerant.
---------
Co-authored-by: Rouzbeh <rqzbeh@users.noreply.github.com>
* Sanitize test fixtures, add developer .env guidance, and add gitleaks workflow
- Replace realistic-looking AWS keys and PEM fixtures in unit tests with synthetic placeholders to avoid false positives from secret scanners.
- Add docs/DEVELOPER-ENVIRONMENT.md describing postinstall .env behavior and remediation guidance.
- Add .github/workflows/gitleaks.yml to run gitleaks on pull requests.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add gitleaks baseline and CI baseline support; update ignore and PR body\n\n- Copy gitleaks-local.json -> gitleaks-baseline.json\n- Add --baseline-path to workflow\n- Allowlist baseline in .gitleaks.toml\n- Ignore gitleaks-local.json\n- Add PR_BODY.md with scan summary\n\nCo-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* chore(security): fix gitleaks config, drop redundant baseline/CI, clean doc artifacts
- Fix the malformed .gitleaks.toml [[rules]] block: an inline [rules.allowlist]
with only paths (no regex/path at rule level) made gitleaks refuse to load the
config (`FTL Failed to load config ... both |regex| and |path| are empty`),
turning the project's blocking check-secrets ratchet into a hard failure.
Verified: check-secrets config now loads and exits 0.
- Reconcile with the existing gitleaks gate: remove the redundant
.github/workflows/gitleaks.yml and root gitleaks-baseline.json (a second,
differently-scoped scanning mechanism + an unreviewed 430-finding blanket
baseline) — the project already runs scripts/check/check-secrets.mjs as a
blocking ratchet in ci.yml/quality.yml and its .gitleaks.toml policy is to fix
real findings, not blanket-allowlist them.
- Remove the stray PR_BODY.md automation artifact from the repo root.
- Fix the duplicated <div align="center"> tag in README.md.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: OmniRoute Bot <noreply@omniroute.local>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: blarovse <312250233+blarovse@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(deps): bump nanoid, dompurify for 2 new Dependabot alerts (#189, #190)
Bumps: nanoid ^3.3.17 (was transitive, now overridden), dompurify ^3.4.13
(with monaco-editor scoped override). Closes Dependabot #189, #190.
Remaining #182-#188 (js-yaml + mermaid) already closed by #9651 merge —
awaiting Dependabot re-scan.
npm audit → 0 vulnerabilities.
* fix(repo): harden .gitignore to also ignore a _tasks symlink (/_tasks)
_tasks is a SEPARATE nested git repo (gitignored). The pattern _tasks/ (trailing
slash) ignores only a directory, not a SYMLINK named _tasks. A self-referential
_tasks symlink can slip in via git add -A and, once pulled, checkout materializes
it over the real _tasks repo (destroying plans/specs/hands-off). Anchored /_tasks
ignores the symlink too, preventing re-capture.
* Hide health-check excluded models from /v1/models catalog (#10026)
Mirror the request-time exclusion rule (provider_specific_data.excludedModels)
in the unified catalog builder: a model is hidden when its provider has
connections but none of them is eligible for it. Applied across the
PROVIDER_MODELS, synced, custom, alias-backed, and managed-fallback loops
so ghost models no longer appear as available.
Co-authored-by: ritheshcn25 <ritheshcn25@users.noreply.github.com>
* fix(models): memoize getModelsDevPricing (event loop / healthz) (#10055)
* fix(models): memoize getModelsDevPricing for /v1/models catalog
resolveCatalogPricing called getModelsDevPricing once per model while
building GET /v1/models. Each call re-scanned models_dev_pricing and
JSON.parsed every row (~10k SQL scans + multi-GB parse work), pegging
the event loop so even /healthz timed out (#9685, #10052).
Memoize the parsed map until saveModelsDevPricing / clearModelsDevPricing
and add a unit test for invalidation.
Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
* fix(db): invalidate modelsDevPricing cache on DB reset (#10055)
Copilot review fixes:
1. Register invalidateModelsDevPricingCache() with DB state reset system
so resetDbInstance() clears the process-local memo, preventing stale
pricing data from surviving across DB reset/restore operations.
2. Add test assertion verifying DB reset bypasses the memo (Copilot #10055).
The process-local memo at modelsDevSync.ts:204 caches getModelsDevPricing()
results until saveModelsDevPricing()/clearModelsDevPricing() to avoid
re-scanning all pricing rows on every /v1/models request. Without this hook,
backup restore and test DB resets would serve stale cached data from the
previous connection.
Tests: npm run test:unit:serial -- tests/unit/modelsDevSync-extended.test.ts
---------
Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
* fix(sse): keep Codex quota headers under the forwarding budget
The 768-byte cap plus priority-3 for any name that does not contain
"ratelimit" dropped x-codex-*-used-percent / reset / credits on every
stream. x-codex-turn-state (314 bytes) ate the budget. Raise the cap,
treat Codex quota headers as rate-limit priority, and do not forward
turn-state.
---------
Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@outlook.com>
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
Co-authored-by: ritheshcn25 <rithesh.chandran@snb.ca>
Co-authored-by: ritheshcn25 <ritheshcn25@users.noreply.github.com>
Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
* feat(responses): virtualize previous_response_id continuation regardless of upstream support
OmniRoute now exposes OpenAI-compatible previous_response_id/store
continuation to clients unconditionally, even when the selected upstream
provider has no native Responses-API state support. Reconstruction happens
server-side in handleChatImplementation, before any downstream validation
or provider translation: OmniRoute resolves the response id back to the
full input/output it previously produced, prepends it to the client's
delta, and forwards the full reconstructed history upstream exactly as it
does today. Client<->OmniRoute traffic shrinks to the new delta only;
OmniRoute<->provider traffic is unchanged.
Storage reuses the existing call-log pipeline artifact (already gated by
call_log_pipeline_enabled, already retained/cleaned up by the existing
call-log lifecycle) instead of duplicating conversation content into a
second store -- only a lightweight call_logs.response_id index is new.
Every lookup is scoped by api_key_id so one client can never resolve
another client's stored conversation, and any unresolvable/missing/
size-limit-omitted state fails closed with OpenAI's own
previous_response_not_found contract.
Stacked on feat/openai-responses-store-toggle (#10121).
* fix(db): re-export responsesContinuationStore from the localDb barrel
check-db-rules requires every db/ module to be re-exported (or explicitly
allowlisted as intentionally-internal) for discoverability. Missed this
when the module was first added.
* fix(db): renumber previous_response_id index migration to 154
The migration was numbered 153, but release/v3.8.50 already carries
153_radar_local_model_state.sql. The emngrating runner's collision guard
throws on two live .sql files sharing a numeric prefix, so the refreshed
merge would fail DB startup. Renumber to the next free slot (154).
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
* docs(db): sync migration count to 149 across llm.txt mirrors
The responses-continuation store adds one migration, so the docs'
migration count is now 149 (was 148). Update README/AGENTS/llm.txt and
regenerate the i18n llm.txt mirrors to keep check:docs-all green.
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
* fix(responses-continuation): respect preserve mode, drop dead export
- Un-export ResponsesContinuationState: it's never imported outside
responsesContinuationStore.ts, its own defining file. Fixes the
check:dead-code regression (410 > baseline 409).
- Scope the previous_response_id virtualization interception in chat.ts to
skip entirely when responsesPreviousResponseIdMode=preserve. The
interception ran unconditionally before target/connection selection,
ahead of applyResponsesPreviousResponseIdPolicy (chatCore.ts) -- the
existing per-target enforcement point for this setting -- so "preserve"
(the explicit, connection-independent contract for "let the upstream
resolve previous_response_id natively") was silently unreachable: the
field was already deleted and replaced with locally-reconstructed input
by the time that policy ran. This also broke Codex's own executor, which
relies on an untouched previous_response_id to delegate history
resolution upstream (see stripOrphanedCodexFunctionCallOutputs in
codex.ts). "auto" and "strip" modes are unaffected -- virtualization is
a strict improvement over their old "drop the field, hope the client
resent everything" behavior.
- Add a regression test exercising the actual chat.ts handler (not just
the policy helper in isolation): confirms mode=preserve now proceeds to
normal routing instead of the virtualization's previous_response_not_found
rejection, and that default/auto mode's existing virtualization behavior
is unchanged. Verified the test fails for the right reason against
pre-fix chat.ts.
Addresses PR review feedback.
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
Co-authored-by: hartmark <hartmark@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
* fix(routing): fallback to default model alias seeds when unmapped in database
* fix(routing): rename seed-fallback resolver; hermetic 401 regression test
Maintainer review (PR #10124):
1. Rename resolveModelAlias -> resolveModelAliasWithSeedFallback (and
resolveModelAliasOnBody -> resolveModelAliasWithSeedFallbackOnBody) to
avoid the export collision with the sync resolveModelAlias in
open-sse/services/modelDeprecation.ts and
src/shared/constants/modelSpecs.ts.
2. Regression test now reproduces the 401: alias unmapped in the (empty,
DATA_DIR-isolated) modelAliases namespace but present in the static seed
resolves to the seed target instead of passing through unmapped.
3. Test isolates DATA_DIR (temp dir + resetDbInstance) instead of reading
the operator's live DB.
* fix(models): add outputTokenLimit to CustomModelEntry
Fixes the open-sse typecheck gate regression: catalog.ts reads
model.outputTokenLimit (for max_output_tokens in custom model metadata)
but CustomModelEntry only declared inputTokenLimit — TS2551. The
field exists in the runtime model data and is already consumed; the
interface just never declared it.
* fix(db): align compression_run_telemetry cleanup cutoff with millisecond column
cleanupCompressionRunTelemetry() computed its cutoff in epoch seconds while
insertCompressionRunTelemetryRow() stamps the timestamp column with Date.now()
(epoch milliseconds). A millisecond timestamp is ~1000x larger than a seconds
cutoff, so DELETE WHERE timestamp < cutoff never matched an old row and the
retention sweep added by #6848 to bound storage.sqlite growth was inert.
This is the same defect as domain_cost_history (#9625), whose fix corrected
cleanupDomainCostHistory() ~90 lines earlier in this file and missed this
sibling call site. The stale docstring asserting a unix-epoch column is
corrected too.
The repro test seeds through the real writer to establish the stored unit, so
it also fails if the producer format diverges from the consumer again.
* docs(changelog): add fragment for the telemetry retention unit fix
* fix(db): tolerate a SQLite build without the dbstat virtual table
getDatabaseStats() queried `dbstat` once per table with no guard. `dbstat` is
compile-time optional (ENABLE_DBSTAT_VTAB) and is absent from sql.js/WASM
builds, so on those runtimes the query throws and the error propagates out of
getDatabaseStats().
Every caller dies with it. Most visibly, GET and PATCH /api/settings/database
return HTTP 500, which makes the entire database settings page unusable — users
cannot read or change page size, cache size, or vacuum settings.
The function already anticipated missing virtual-table modules: the COUNT(*)
lookup a few lines above swallows "no such module:" errors. The dbstat query
simply sat outside that guard.
Probe dbstat once per call and skip the per-table size lookups when it is
unavailable, reporting size 0. Database-level figures (total size, page count,
cache size) come from pragmas and stay accurate; only per-table byte sizes are
lost, which is the correct trade against a hard 500.
Unrelated failures (I/O errors, corruption) still propagate.
Both spellings are handled: sql.js reports "no such module: dbstat" while
better-sqlite3 can surface "no such table: dbstat".
* test(db): cover prefixed driver errors and dbstat edge cases
Review follow-up on the previous commit.
The guard is deliberately unanchored because real drivers stringify errors
with their class name attached ("SqliteError: no such table: dbstat",
"RuntimeError: ..."). Nothing pinned that, so anchoring the regex would have
passed the suite while silently breaking every real driver. Add a case for the
prefixed form; it fails if a caret is introduced.
Also cover three shapes the fake previously could not express:
- a database with no user tables, which is what a fresh install hits first
- SUM(pgsize) returning NULL for a table occupying no pages
- dbstat answering the probe but failing on a later table, which documents
that a mid-iteration fault still propagates rather than being mistaken for
an absent module
Correct the source comment: the two error spellings track the SQLite build,
not the driver package, so the earlier attribution to better-sqlite3 was
wrong.
* docs(changelog): add fragment for the dbstat availability guard
Registers the new test with Stryker alongside the sibling db suites and adds
the changelog fragment for this fix.
---------
Co-authored-by: Nick Sullivan <nick@technick.ai>
* fix(deps): bump nanoid, dompurify for 2 new Dependabot alerts (#189, #190)
Bumps: nanoid ^3.3.17 (was transitive, now overridden), dompurify ^3.4.13
(with monaco-editor scoped override). Closes Dependabot #189, #190.
Remaining #182-#188 (js-yaml + mermaid) already closed by #9651 merge —
awaiting Dependabot re-scan.
npm audit → 0 vulnerabilities.
* fix(repo): harden .gitignore to also ignore a _tasks symlink (/_tasks)
_tasks is a SEPARATE nested git repo (gitignored). The pattern _tasks/ (trailing
slash) ignores only a directory, not a SYMLINK named _tasks. A self-referential
_tasks symlink can slip in via git add -A and, once pulled, checkout materializes
it over the real _tasks repo (destroying plans/specs/hands-off). Anchored /_tasks
ignores the symlink too, preventing re-capture.
* Hide health-check excluded models from /v1/models catalog (#10026)
Mirror the request-time exclusion rule (provider_specific_data.excludedModels)
in the unified catalog builder: a model is hidden when its provider has
connections but none of them is eligible for it. Applied across the
PROVIDER_MODELS, synced, custom, alias-backed, and managed-fallback loops
so ghost models no longer appear as available.
Co-authored-by: ritheshcn25 <ritheshcn25@users.noreply.github.com>
* fix(models): memoize getModelsDevPricing (event loop / healthz) (#10055)
* fix(models): memoize getModelsDevPricing for /v1/models catalog
resolveCatalogPricing called getModelsDevPricing once per model while
building GET /v1/models. Each call re-scanned models_dev_pricing and
JSON.parsed every row (~10k SQL scans + multi-GB parse work), pegging
the event loop so even /healthz timed out (#9685, #10052).
Memoize the parsed map until saveModelsDevPricing / clearModelsDevPricing
and add a unit test for invalidation.
Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
* fix(db): invalidate modelsDevPricing cache on DB reset (#10055)
Copilot review fixes:
1. Register invalidateModelsDevPricingCache() with DB state reset system
so resetDbInstance() clears the process-local memo, preventing stale
pricing data from surviving across DB reset/restore operations.
2. Add test assertion verifying DB reset bypasses the memo (Copilot #10055).
The process-local memo at modelsDevSync.ts:204 caches getModelsDevPricing()
results until saveModelsDevPricing()/clearModelsDevPricing() to avoid
re-scanning all pricing rows on every /v1/models request. Without this hook,
backup restore and test DB resets would serve stale cached data from the
previous connection.
Tests: npm run test:unit:serial -- tests/unit/modelsDevSync-extended.test.ts
---------
Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
* fix(providers): remove invalid CodeBuddy CN glm-4.7 and add hy3 (0.0x credit)
Swap the GLM-4.7 model for the Hunyuan hy3 model in the codebuddy-cn
registry, keep the catalog at 15 models, and update the matching provider
test expectations. Regenerated the auto-generated provider reference doc.
---------
Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@outlook.com>
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
Co-authored-by: ritheshcn25 <rithesh.chandran@snb.ca>
Co-authored-by: ritheshcn25 <ritheshcn25@users.noreply.github.com>
Co-authored-by: Ravi Tharuma <25951435+RaviTharuma@users.noreply.github.com>
Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(deps): bump nanoid, dompurify for 2 new Dependabot alerts (#189, #190)
Bumps: nanoid ^3.3.17 (was transitive, now overridden), dompurify ^3.4.13
(with monaco-editor scoped override). Closes Dependabot #189, #190.
Remaining #182-#188 (js-yaml + mermaid) already closed by #9651 merge —
awaiting Dependabot re-scan.
npm audit → 0 vulnerabilities.
* fix(repo): harden .gitignore to also ignore a _tasks symlink (/_tasks)
_tasks is a SEPARATE nested git repo (gitignored). The pattern _tasks/ (trailing
slash) ignores only a directory, not a SYMLINK named _tasks. A self-referential
_tasks symlink can slip in via git add -A and, once pulled, checkout materializes
it over the real _tasks repo (destroying plans/specs/hands-off). Anchored /_tasks
ignores the symlink too, preventing re-capture.
* Hide health-check excluded models from /v1/models catalog (#10026)
Mirror the request-time exclusion rule (provider_specific_data.excludedModels)
in the unified catalog builder: a model is hidden when its provider has
connections but none of them is eligible for it. Applied across the
PROVIDER_MODELS, synced, custom, alias-backed, and managed-fallback loops
so ghost models no longer appear as available.
Co-authored-by: ritheshcn25 <ritheshcn25@users.noreply.github.com>
* fix(models): memoize getModelsDevPricing (event loop / healthz) (#10055)
* fix(models): memoize getModelsDevPricing for /v1/models catalog
resolveCatalogPricing called getModelsDevPricing once per model while
building GET /v1/models. Each call re-scanned models_dev_pricing and
JSON.parsed every row (~10k SQL scans + multi-GB parse work), pegging
the event loop so even /healthz timed out (#9685, #10052).
Memoize the parsed map until saveModelsDevPricing / clearModelsDevPricing
and add a unit test for invalidation.
Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
* fix(db): invalidate modelsDevPricing cache on DB reset (#10055)
Copilot review fixes:
1. Register invalidateModelsDevPricingCache() with DB state reset system
so resetDbInstance() clears the process-local memo, preventing stale
pricing data from surviving across DB reset/restore operations.
2. Add test assertion verifying DB reset bypasses the memo (Copilot #10055).
The process-local memo at modelsDevSync.ts:204 caches getModelsDevPricing()
results until saveModelsDevPricing()/clearModelsDevPricing() to avoid
re-scanning all pricing rows on every /v1/models request. Without this hook,
backup restore and test DB resets would serve stale cached data from the
previous connection.
Tests: npm run test:unit:serial -- tests/unit/modelsDevSync-extended.test.ts
---------
Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
* fix(models): honor MODELS_DEV_SYNC_ENABLED=0 over dashboard settings
The file header already advertised this env var but nothing read it.
When catalog/compression pin the event loop, the dashboard (same process)
cannot turn models.dev sync off. Let 0/false/off win over sqlite so an
operator can recover with env + restart. Skip getModelsDevPricing SQL
scans while the kill switch is set.
* fix(models): restore prettier formatting after base merge
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
* test(models): cover env kill switch during live settings updates
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@outlook.com>
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
Co-authored-by: ritheshcn25 <rithesh.chandran@snb.ca>
Co-authored-by: ritheshcn25 <ritheshcn25@users.noreply.github.com>
Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* feat(proxy): add non-destructive auto-disable mode for the proxy health scheduler
PROXY_AUTO_REMOVE was the only opt-in action the background proxy health
scheduler could take on a consistently failing proxy, and it deletes the row.
For a manually-maintained proxy chain (multi-proxy pool/rotation, #6365) that
is too destructive just to exclude a temporarily-dead member.
Add PROXY_AUTO_DISABLE as a sibling flag: at the same consecutive-failure
threshold it soft-disables the proxy (status "dead") instead of removing it.
"dead" is already one of the statuses the pool/rotation alive-filter excludes,
so a disabled proxy drops out of the active chain immediately with no other
code changes. The scheduler keeps probing dead proxies on its normal interval,
and the existing recovery branch (previously autoRemove-only) re-activates it
automatically once it starts answering again.
decision.ts's decideProxyHealthAction() gets an optional `autoDisable` input
(defaults to false, so existing callers are unaffected) and a "dead" status
value; scheduler.ts wires the new PROXY_AUTO_DISABLE env flag through. If both
flags are set, auto-remove wins. getProxyHealthStats() now also surfaces the
registry `status` so operators can see when a proxy was auto-disabled, and
ProxyStatusBadge now treats the full "not alive" status set (not just the
literal string "inactive") as inactive in the dashboard.
* test(proxy): assert registry status in getProxyHealthStats output
The non-destructive auto-disable change added the live registry status to the
stats object returned by getProxyHealthStats. Align the pre-existing
db-proxies-crud assertion with the intended output shape.
Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
* fix(proxy): preserve auto-disabled status in dashboard edits
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
Co-authored-by: Gi99lin <Gi99lin@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(oauth): send required CLI headers in claude-auth import bootstrap call
enrichWithBootstrap() in claudeAuthImport.ts was missing the
User-Agent and anthropic-beta headers that the two other callers of
the same /api/claude_cli/bootstrap endpoint (claudeIdentity.ts and
src/lib/oauth/providers/claude.ts) always send. Without them,
Anthropic doesn't recognize the request as coming from a CLI client
and the bootstrap call fails, silently returning a null identity
(accountUUID/organizationUUID/organizationType all null).
createConnectionFromAuthFile()'s identity-verification refusal then
gets bypassed via overwriteExisting: true (the only way imports
currently succeed, since first attempts fail with
identity_unverified because of this same bug), so every imported
Claude connection ends up with unverified identity.
Downstream, resolveAccountUUID() in claudeIdentity.ts falls back to
a hash-derived fake UUID when providerSpecificData.accountUUID is
null. That fake UUID is shape-valid but was never associated with
the real account by Anthropic, so requests carrying it get
classified as unrecognized third-party traffic and routed to the
separate extra-usage pool instead of the account's plan limits --
producing an intermittent (~50% observed) 400:
"Third-party apps now draw from your extra usage, not your plan
limits." on an otherwise perfectly valid, imported subscription
token.
Fixes the header mismatch so bootstrap succeeds and imported
connections get a real, Anthropic-recognized account identity from
the start, same as connections created via the native OAuth flow.
Fixes#10143
* fix(oauth): persist cliUserID device identity on claude-auth import
createConnectionFromAuthFile() in claudeAuthImport.ts never set
providerSpecificData.cliUserID, unlike the native OAuth setup flow in
src/lib/oauth/providers/claude.ts which always mints one. cliUserID is
read by resolveCliUserID() (open-sse/executors/claudeIdentity.ts) as
the request's device_id; when absent it falls back to a lazy-random
device id regenerated fresh every process restart (in-memory Map,
process-lifetime only), so every restart of an imported connection
presents as a brand-new device to Anthropic for the same account --
a second, independent contributor (alongside Part 1's bootstrap
header fix in this same PR) to the intermittent third-party-usage 400
on valid imported subscription tokens.
- "create new connection" branch: always mint a fresh cliUserID.
- "update existing connection" branch: preserve any already-persisted
cliUserID from existing.providerSpecificData (don't rotate a working
device identity on re-import); only mint a fresh one if absent.
Adds changelog.d/fixes/10144-claude-import-cli-user-id.md per
CONTRIBUTING.md.
Fixes#10143
* test(oauth): cover claude-auth import bootstrap headers + cliUserID persistence
Adds tests/unit/claudeAuthImport-bootstrap-headers-10144.test.ts (Rule #18
regression guard for #10143):
1. enrichWithBootstrap() sends the required CLI headers on the
/api/claude_cli/bootstrap call — a claude-cli User-Agent (now sourced
from CLAUDE_CODE_CLIENT_VERSION, matching the two working call-sites)
and anthropic-beta: oauth-2025-04-20 — and still falls back to null
identity fields on non-OK upstream responses.
2. createConnectionFromAuthFile() mints a 64-hex cliUserID device
identity on create, preserves an already-persisted cliUserID on
overwrite re-import (no rotation), and mints a fresh one when the
existing connection has none.
Also aligns the hardcoded claude-cli/1.0.0 User-Agent in the import
bootstrap with the version constant the two working call-sites
(claudeIdentity.ts, oauth/providers/claude.ts) already use.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* refactor(oauth): source claude-auth import UA from canonical constant (#10144 review nit)
Addresses the hardcoded-version nit from review: the bootstrap User-Agent was
re-typed as `claude-cli/${CLAUDE_CODE_CLIENT_VERSION}` instead of importing
getClaudeCodeUserAgent() — the single source of truth the two working
call-sites (claudeIdentity.ts, oauth/providers/claude.ts) use.
- claudeAuthImport.ts: use getClaudeCodeUserAgent("cli") for the bootstrap call
- test: import the same canonical helper instead of a local copy of the pinned
version, and assert the outbound UA byte-for-byte against it, so a future
version bump can't silently desync the wire identity.
Verified: node --import tsx/esm --test on the new test file -> 5/5 pass;
sibling claudeAuthImport.test.ts -> pass; eslint on both changed files ->
no new findings (only the pre-existing @/lib/localDb barrel-import restriction
on an untouched import line).
* test(oauth): exercise claude auth import implementation
Replace copied helper tests with real implementation coverage for bootstrap headers and persistent cliUserID behavior.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
Co-authored-by: stanleytejakusuma <stanleytejakusuma@users.noreply.github.com>
`@huggingface/transformers` 4.2.0 hard-pins `onnxruntime-node` to "1.24.3".
The production-group bump in #10403 raised the root range from "~1.24.3" to
"~1.27.0", so npm stopped deduping and nested a second copy under
`node_modules/@huggingface/transformers/node_modules/onnxruntime-node`.
Both copies ship a native `libonnxruntime.so.1` under the SAME SONAME, so
glibc binds whichever is dlopen()ed first and the other addon dies. The
Dockerfile post-build verification imports `@huggingface/transformers` and
`onnxruntime-node` in one process, so `docker build` has failed on every
commit since #10403:
Error: .../transformers/node_modules/onnxruntime-node/bin/napi-v6/linux/x64/libonnxruntime.so.1:
version `VERS_1.27.0' not found (required by .../onnxruntime-node/bin/napi-v6/linux/x64/onnxruntime_binding.node)
Restore the root range to "~1.24.3" so a single hoisted copy is resolved
again. Copying the nested native binaries into the standalone bundle is NOT
a workaround: it makes both `.so` files present, which is precisely what
triggers the SONAME clash above (verified against a real image build).
Regression guard: tests/unit/onnxruntime-single-copy.test.ts asserts the
lockfile resolves exactly one onnxruntime-node and that it matches the
version transformers pins. Confirmed failing on the pre-fix lockfile
(two copies, 1.27.0 vs 1.24.3) and passing after.
Validated with a full `docker build --target runner-base`: the post-build
verification step now passes (#19 DONE 156.9s) and the image boots healthy
(/api/monitoring/health 200, migrations 134-148 applied).
Keep the #8350 Hermes system-prompt drops, but remove hermes from the
factory obfuscate_words list so hostnames and CLI mentions stay intact.
Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
* fix(antigravity): unblock Gemini and Claude reasoning capabilities
* fix(antigravity): align two unit tests with unblocked Gemini/Claude reasoning
The PR unblocks Antigravity Gemini/Claude reasoning (removed from
REASONING_UNSUPPORTED_PATTERNS, mirroring model-capabilities-registry.test.ts).
models-catalog-combo-metadata and services-branch-hardening still asserted the
pre-PR deny contract; align them to the new verified behavior. No production
code changed.
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
Co-authored-by: Chewji9875 <Chewji9875@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
* fix(providers): add PATCH handler to provider connection route
The OpenAPI spec and the CLI (omniroute providers rotate, generated
api-commands) both use PATCH /api/providers/[id], but the route only
implemented PUT — PATCH requests returned 405 and key rotation via the
CLI silently failed while reporting success (the DB-write fallback only
catches thrown exceptions, not non-OK HTTP responses).
Add a PATCH handler delegating to the PUT handler: both apply the same
partial-update schema, so the semantics are identical.
Regression test proves the PATCH export exists and delegates into the
shared auth path; verified to fail without the fix.
* docs(changelog): note PATCH provider route fix (PR #10366)
* fix(providers): make PATCH delegation test environment-robust
The 'PATCH delegates to PUT' assertion hardcoded a 401, which only holds
when management auth is enforced (dev). In the CI unit-test env auth is not
required, so the flow falls through to 'Connection not found' (404) for an
unknown id — the test failed on the status code while the PATCH->PUT
delegation itself is correct. Assert on delegation equivalence instead:
PATCH must never 405 (the regression) and must return the same status as
PUT for the same input.
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
* test(providers): use fresh Request per handler in PATCH delegation test
The same Request was passed to both PATCH and PUT — PUT consumes the
body via request.json(), so the second call got an empty body (400
validation) vs the first (404 not-found): a false status mismatch on
bases where management auth is bypassed in the test env (release
v3.8.50). Fresh Request per invocation makes identical inputs produce
identical statuses.
---------
Co-authored-by: benzntech <benzntech@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
* fix(mcp): dynamically generate web search provider enum from registry
* test(mcp): add contract test for dynamic web search provider enum
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(mcp): restore search.ts eslint suppression, type builder maps, fix firecrawl searchType arg
The enum-dynamic refactor dropped search.ts's no-explicit-any suppression
while a new Record<string,any> map re-introduced anys, and the response
normalizer map swapped the firecrawl searchType argument with query. Type
both maps explicitly, restore the base suppression (33 pre-existing anys),
and pass searchType (not query) to normalizeFirecrawlSearchResponse.
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
---------
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
Co-authored-by: sadSanta-07 <sadSanta-07@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
* fix(api-manager): allow empty combo restrictions
Represent unrestricted Combo access explicitly as combo/* so an empty Allowed Combos list can deny every Combo without affecting direct model routes. Preserve existing keys through migration 149 and cover Dashboard, policy, routing-target, and migration behavior.
* docs: sync migration count to 149 after api-key combo-access migration
Merging release/v3.8.50 forward landed 149_api_key_combo_access.sql,
bumping the real migration count from 148 to 149. Updates README.md,
AGENTS.md, llm.txt (root + all 42 i18n mirrors, exact-copy requirement)
so the strict docs-counts-sync gate matches the live count again.
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
Co-authored-by: xz-dev <xz-dev@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
Issue #10443: when the upstream kills an SSE stream mid-generation
(antigravity/Gemini does this under its own rate enforcement), OmniRoute
closed the stream silently for OpenAI-format clients - HTTP 200, a few
content chunks, no finish_reason. The client sees a truncated turn.
resolveSilentCloseReason() only flagged that shape for Claude clients
(#7699). Extend it to OpenAI chat completions guarded on sawContent(),
and teach hasClientTerminalSseMarker() that a non-null finish_reason
chunk is a terminal marker (some providers omit data: [DONE]). Every
known OpenAI-producing path ends with one of the two, so content
forwarded without either is an upstream drop and now surfaces the
in-band 502 error chunk + [DONE] instead of a silent close.
TDD: tests/unit/silent-sse-close-openai-10443.test.ts - core case RED
before / GREEN after, plus guard cases for finish_reason-only close,
[DONE] close, empty-content (#8649 verdict preserved), and literal
finish_reason text inside model content (JSON escaping keeps the raw
bytes from matching the unescaped-field regex).
Signed-off-by: Minxi Hou <houminxi@gmail.com>
The base gemini-3.5-flash entry spread the shared GEMINI_35_FLASH_MODEL_SPEC
constant, which has supportsThinking:false because it is also spread into
several Antigravity flash-tier aliases that reject client-supplied thinking
params. That made the reasoning-routing policy resolve reasoning_effort as
"unsupported" for the base Google AI Studio model, producing a spurious
pre-provider HTTP 400 even though the model supports reasoning (it has an
effort-tier alias gemini-3.5-flash-high).
Set supportsThinking:true as an explicit override on the base
gemini-3.5-flash entry only, leaving the shared spec and the Antigravity
tier aliases unchanged.
Closes#10286
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* fix(sse): exclude search providers from credential-health scheduler sweep
The credential-health scheduler's sweep() tested every active connection
every 5 minutes with no exclusion for search providers. For providers in
SEARCH_VALIDATOR_CONFIGS (tavily-search, exa-search, serper-search,
brave-search, google-pse-search, linkup-search, searchapi-search,
youcom-search), "validation" fires a real billed upstream query
(e.g. POST api.tavily.com/search), so the periodic sweep silently burned
quota with no user-initiated search.
Exclude connections whose provider id is registered in
SEARCH_VALIDATOR_CONFIGS from the sweep's connection-selection filter.
Non-search API-key/OAuth connections remain monitored (#9180, #9289
regressions verified green).
Closes#9970
* fix(docs): drop backticks around SEARCH_VALIDATOR_CONFIGS in ENVIRONMENT.md
The env/docs sync gate (check-env-doc-sync.mjs) treats any backtick-wrapped
SHOUTY_NAME as an env var reference. SEARCH_VALIDATOR_CONFIGS is a code
export, not an env var, so wrapping it in backticks made the #9970 doc note
trip the env/docs contract check (docMissingEnv). Drop the backticks so the
gate stops classifying it as an undocumented env var.
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* feat(dashboard): add VS Code Copilot Chat home banner, remove Provider Quota home card
Announce the OmniCopilot extension right below the Kimi sponsor banner on the
dashboard home page (same size/shape, dismissible, no version gate). Also
removes the "pin Provider Quota to home" card and its now-dead settings
toggle — the widget itself, its auto-refresh setting (shared with the
standalone /dashboard/quota page), and its component tests are untouched.
* fix(dashboard): remove now-dead homeWidgets.ts (dead-code gate)
Deleting the AppearanceTab pin-to-home toggle left this file's sole export,
PIN_PROVIDER_QUOTA_TO_HOME_KEY, with zero remaining consumers, which regressed
the dead-code ratchet from 415 to 416. Removing the file restores the exact
baseline count (415).
---------
Co-authored-by: Xiangzhe <bakryun0718@proton.me>
Stage 7 of issue #10321 moves the optional ML and browser automation dependency closures out of the desktop bundle into checksummed, versioned packs installed on demand through the omniroute packs command.
- scripts/build/optionalPackStaging.mjs stages pack members under .build/optional-packs, creates release tarballs, and emits optional-packs.index.json with per-member SHA-256 checksums.
- scripts/packs provides manifest, install, remove, and verification helpers plus the packs CLI commands.
- Runtime lookup includes installed pack node_modules directories, while LLMLingua and browser executors continue to degrade gracefully when packs are absent.
The measured darwin-arm64 staging closure was about 534 MB of the 929 MB standalone node_modules tree (57%).
better-sqlite3 v13 ships Node-API prebuilds for every packaged platform
(darwin/linux/linuxmusl/win32 x x64/arm64) inside the npm tarball, so the
Electron-ABI node-gyp source rebuild in prepare-electron-standalone.mjs is
obsolete. Replace it with a fail-fast prebuild verification that mirrors
better-sqlite3 lib/binding.js selection, and strip build/deps/src so the
packaged loader can only resolve the prebuild.
Verified locally on darwin-arm64: the same darwin-arm64.node prebuild loads
under both Node 24 (NODE_MODULE_VERSION 137) and Electron 43.3.0 under
ELECTRON_RUN_AS_NODE (148); DB create/migrate/read/write/close/reopen pass
in both runtimes and cross-runtime on each other's database files.
Issue #10321 Stage 6.
* fix(chat-body-admission): process-wide budget (#10110)
Remove per-session admission lanes that multiplied the documented
"in one process" heavy/bytes bound by up to 64. All requests now admit
against ONE process-global ChatAdmissionController so the bound holds
against fake-credential sharding.
Per-request session identity survives only as a fairness scheduling key:
waiters are grouped per key and served round-robin (#9654) against the
shared budget — one connection's burst cannot starve others.
- src/shared/middleware/chatBodyAdmission.ts: delete lane map + LRU/TTL
eviction; ChatAdmissionController is now the global budget with per-key
FIFO queues + round-robin dispatchFair(). PerConnectionAdmissionController
returns the same shared controller for every session. resolveSessionId
stays as a scheduling key with honest re-scoping docs. snapshot() emits
process-wide aggregates.
- tests/unit/chat-body-admission-aggregate-10110.test.ts: new U6 suite — 6
deterministic tests (LRU-no-mint, TTL-no-mint, shared byte budget,
16 MiB config, same-session recreation, round-robin fairness). RED on
release/v3.8.50, GREEN post-fix.
- tests/unit/per-connection-admission-9654.test.ts: rewrite the tests that
encoded the defect (per-session isolation) to assert the global-budget
contract.
- docs/reference/ENVIRONMENT.md: OMNIROUTE_CHAT_ADMISSION_MAX_QUEUED_BYTES
documented as process-wide; VIRTUAL_TTL_MS/VIRTUAL_MAX_SESSIONS deprecated.
* docs(changelog): add #10322 fragment for process-wide admission budget
* ci: retrigger checks after transient npm ci network failure in shard 3/4 (ETIMEDOUT)
---------
Co-authored-by: Brandon Bennett <brandonbennett@macbookair.myfiosgateway.com>
The desktop release matrix ran the full Next.js standalone build on all four legs (windows, macos-intel, macos-arm64, linux), duplicating the platform-neutral majority of that work four times and re-exposing every leg to the hosted-runner RAM class of failure that took the linux leg out of v3.8.49.
- scripts/build/standaloneTarball.mjs: deterministic, dependency-free tar.gz writer/reader (uid/gid/mtime pinned, sorted entries, symlink + exec-bit preservation; GNU-tar interop covered by tests).
- scripts/build/standaloneManifest.mjs: byte-level manifest of .build/next (sha256 + size + symlink target per entry, plus the archive's own digest) catching artifact-transfer corruption before extraction and re-verifying the restored tree byte-for-byte, smuggling included.
- scripts/build/standaloneBundle.mjs: pack / restore / hydrate CLI over the two modules above.
- scripts/build/hydrateNativeDeps.mjs: swaps install-machine-forked native optionals (@img/sharp-*, @ngrok/ngrok-*, fsevents) from the leg's own npm ci into the restored tree, then verifies the bundled-native closure (koffi triplets, better-sqlite3 prebuilds, wreq-js, onnxruntime with its documented darwin-x64 exemption) services the leg's platform/arch before packaging starts.
- .github/workflows/electron-release.yml: new web-build job builds the standalone once on ubuntu with webpack and uploads the bundle; legs download, restore, and hydrate it, skipping the per-leg build. The legacy per-leg build remains as a rollback path via the ELECTRON_SHARED_STANDALONE workflow_dispatch input, and legs fail closed if web-build ran and failed.
Regression tests cover archive roundtrip, byte determinism, manifest tamper/smuggle detection, forked-native swaps, and native-closure serviceability.
* fix(security): sanitize test regex and annotate CodeQL hash false-positives
tests/unit/early-sse-route-intent.test.ts built a RegExp from a hardcoded
string but only escaped `?`/`.`, missing `\` — js/incomplete-sanitization
(#816). Not exploitable (fixed literal input) but the escaping was
genuinely incomplete; now escapes backslash too.
reasoningCache.ts::buildAssistantMessageCacheKey and codexIdentity.ts's two
UUID derivation helpers hash a cache-scope/account-seed with SHA-256 to
produce a lookup key / deterministic ID — not a stored, verified password.
CodeQL's js/insufficient-password-hash overfires on any hash of a
secret-like variable, the same false-positive class already annotated at
src/lib/db/apiKeys.ts:624. Added matching lgtm/nosemgrep annotations and
inline rationale so the intent is clear to reviewers and future scans.
Refs #815#816#817#818
* fix(security): keep only the regex sanitization; drop non-functional CodeQL annotations
The lgtm[]/nosemgrep: comments in codexIdentity.ts and reasoningCache.ts use
formats GitHub Actions CodeQL does not honor, and shifting those sha256 lines
re-attributed the already-dismissed base alerts to this PR as two new CodeQL
findings. Revert those two annotation-only files to base so the existing
dismissals apply; retain the real fix (escaping backslash in the test regex),
which resolves the open js/incomplete-sanitization alert.
---------
Co-authored-by: Xiangzhe <bakryun0718@proton.me>
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* fix(deps): bump nanoid, dompurify for 2 new Dependabot alerts (#189, #190)
Bumps: nanoid ^3.3.17 (was transitive, now overridden), dompurify ^3.4.13
(with monaco-editor scoped override). Closes Dependabot #189, #190.
Remaining #182-#188 (js-yaml + mermaid) already closed by #9651 merge —
awaiting Dependabot re-scan.
npm audit → 0 vulnerabilities.
* fix(repo): harden .gitignore to also ignore a _tasks symlink (/_tasks)
_tasks is a SEPARATE nested git repo (gitignored). The pattern _tasks/ (trailing
slash) ignores only a directory, not a SYMLINK named _tasks. A self-referential
_tasks symlink can slip in via git add -A and, once pulled, checkout materializes
it over the real _tasks repo (destroying plans/specs/hands-off). Anchored /_tasks
ignores the symlink too, preventing re-capture.
* Hide health-check excluded models from /v1/models catalog (#10026)
Mirror the request-time exclusion rule (provider_specific_data.excludedModels)
in the unified catalog builder: a model is hidden when its provider has
connections but none of them is eligible for it. Applied across the
PROVIDER_MODELS, synced, custom, alias-backed, and managed-fallback loops
so ghost models no longer appear as available.
Co-authored-by: ritheshcn25 <ritheshcn25@users.noreply.github.com>
* fix(models): memoize getModelsDevPricing (event loop / healthz) (#10055)
* fix(models): memoize getModelsDevPricing for /v1/models catalog
resolveCatalogPricing called getModelsDevPricing once per model while
building GET /v1/models. Each call re-scanned models_dev_pricing and
JSON.parsed every row (~10k SQL scans + multi-GB parse work), pegging
the event loop so even /healthz timed out (#9685, #10052).
Memoize the parsed map until saveModelsDevPricing / clearModelsDevPricing
and add a unit test for invalidation.
Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
* fix(db): invalidate modelsDevPricing cache on DB reset (#10055)
Copilot review fixes:
1. Register invalidateModelsDevPricingCache() with DB state reset system
so resetDbInstance() clears the process-local memo, preventing stale
pricing data from surviving across DB reset/restore operations.
2. Add test assertion verifying DB reset bypasses the memo (Copilot #10055).
The process-local memo at modelsDevSync.ts:204 caches getModelsDevPricing()
results until saveModelsDevPricing()/clearModelsDevPricing() to avoid
re-scanning all pricing rows on every /v1/models request. Without this hook,
backup restore and test DB resets would serve stale cached data from the
previous connection.
Tests: npm run test:unit:serial -- tests/unit/modelsDevSync-extended.test.ts
---------
Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
* fix(ops): Docker HEALTHCHECK probes /healthz not deep monitoring
/api/monitoring/health does a SQLite ping and more. When the event loop
is busy the official image HEALTHCHECK (5s timeout) marks the container
Unhealthy and orchestrators restart the only replica mid-session.
* fix(ops): keep healthcheck PR scoped to the /healthz probe
Drop the stray catalog ghost-model exclusion that leaked into this branch
from main (already covered upstream). Restore catalog.ts to the release
version so the PR contains only the Docker HEALTHCHECK /healthz fix, its
tests, and the changelog entry.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@outlook.com>
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
Co-authored-by: ritheshcn25 <rithesh.chandran@snb.ca>
Co-authored-by: ritheshcn25 <ritheshcn25@users.noreply.github.com>
Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* docs(ops): recommend TCP liveness and HTTP /healthz readiness for k8s
Stock Docker HEALTHCHECK hits /api/monitoring/health (deep). Orchestrators
should not use that path for kubelet liveness. Document /healthz vs deep
health, note same-process event-loop limits, and link related issues.
* docs: add changelog fragment for #10297
---------
Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
* fix(providers): point freeaiapikey at the api. host it moved to
Every /v1 route on the freeaiapikey.com apex host answers HTTP 410 with
type "endpoint_moved", and the body names its own replacement:
"This API endpoint has moved. Please update your base_url to
https://api.freeaiapikey.com/v1 - the old endpoint on freeaiapikey.com
no longer works."
Probed 2026-08-13 with paired controls so a network fault could not be
read as an upstream verdict:
GET https://freeaiapikey.com/v1/models -> 410
GET https://freeaiapikey.com/v1/chat/completions -> 410
GET https://api.freeaiapikey.com/v1/models -> 200
GET https://api.freeaiapikey.com/v1/chat/completions -> 405 (POST-only)
GET https://api.openai.com/v1/models -> 401 (control: reachable)
GET https://<nonexistent-domain>/v1/models -> 000 (control: unreachable)
Every request through this provider therefore fails today. Repoint baseUrl
and modelsUrl at the host upstream names.
* fix(providers): resync the freeaiapikey catalog with its live model list
GET https://api.freeaiapikey.com/v1/models (200, probed 2026-08-13) serves 10
models. The registry declared 7, four of which upstream does not serve at all:
openai/gpt-5, openai/gpt-5.2-codex, Alibaba/qwen3.5, Alibaba/qwen3-vl:235b.
Seven live models were missing: openai/gpt-5.4, openai/gpt-5.5,
openai/gpt-5.6-sol, anthropic/claude-opus-4.7, anthropic/claude-opus-4.8,
anthropic/claude-sonnet-5, anthropic/claude-opus-5.
The four phantom ids are selectable in the dashboard and can only ever fail
upstream; the seven real ones are unreachable through the static catalog.
On context windows: the /v1/models response carries only id/object/created/
owned_by, so upstream publishes no window at all. The models added here
therefore declare no contextLength and inherit the entry's existing
defaultContextLength (128000) instead of a fabricated number. The two
pre-existing contextLength values are left untouched for the same reason -
this sweep neither confirms nor refutes them, and rewriting them would be
guesswork in the other direction.
* chore(changelog): name the fragment after the real PR number
* chore(changelog): substitute the PRNUM placeholder in the fragment body
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* fix(account-fallback): classify 'insufficient credits' as credits-exhausted
Command Code returns 400 'You have insufficient credits to make this
request...' when an account's billing credits run out. The phrase was
missing from CREDITS_EXHAUSTED_SIGNALS, so the error stayed unclassified
(errorType=null) and the connection was never marked credits_exhausted —
getProviderCredentials kept re-selecting the same dead account on every
request instead of rotating to a healthy one.
Add 'insufficient credits'/'insufficient credit' to the signal list
(already used by antigravity429Engine.ts) so the error classifies as
QUOTA_EXHAUSTED and the account is skipped on subsequent selections.
* fix(account-fallback): harden insufficient-credit matching and preserve chatanywhere
Add the common 'insufficient credit balance' variation to
CREDITS_EXHAUSTED_SIGNALS alongside the Command Code 'insufficient
credits'/'insufficient credit' signals, and restore the consolidated
ChatAnywhere gateway entry that the stale snapshot removal would have
deleted when merging into release/v3.8.50.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* feat(cli): refuse ephemeral container auto-config writes
Detect containerized OmniRoute and block CLI/API config writes into
throwaway homes unless a bind mount or explicit opt-in is present, and
honor compose host-profile CLI_CONFIG_HOME mounts outside the container home.
Co-authored-by: Cursor <cursoragent@cursor.com>
* chore(changelog): name fragment for #10057
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: yansigit <yansigit@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
A combo target that stalls past comboTargetTimeoutMs is aborted by
buildTargetTimeoutRunner, which swallows the resulting rejection behind its
synthetic 524. Nothing marks the account unavailable — correctly, since a stall
is not a quota/auth failure — so the #6219 eviction on the generic
markAccountUnavailable -> shouldFallback path in chat.ts never ran. The session
pin therefore survived its full TTL and every following request in that session
was handed straight back to the account that had just stalled.
Seen in production on combo "coding" [priority]: one codex account pinned for a
30-minute TTL, four consecutive requests, four 120s timeouts, "all targets
exhausted" each time, while four sibling codex accounts stayed healthy and
unused.
Classify the abort reason (new dependency-free leaf comboAbortReasons.ts) and
evict the connection-matched pin. Only a genuine per-model timeout evicts: a
client disconnect or a hedge cancellation says nothing about account health, so
those keep the pin and its prompt-cache locality. Eviction is best-effort and
never breaks the dispatch path.
The dispatch itself moves into a new seam, chatDispatch.ts, which merges the
per-model abort signal into the outgoing request, runs executeChatWithBreaker,
and owns the eviction on both the rejection and failed-result paths. Keeping
that logic out of the frozen god-file leaves chat.ts one line SHORTER than
before (1844 -> 1843).
Co-authored-by: alexey.nazarov@softmg.ru <alexey.nazarov@softmg.ru>
Co-authored-by: fenix007 <fenix007@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
containsOrMayEndWithThinkOpenTag missed the 6-char partial '<think', so an
open tag arriving as '<think' + '>' across SSE deltas leaked into content
instead of being parsed as reasoning. Derive every proper prefix from
THINK_OPEN itself so the lookahead list can never drift out of sync with
the tag again. Covered by new unit tests for the partial-suffix lookahead
and the split-delta buffering path.
* fix(usage): read Gemini usageMetadata out of the antigravity response envelope
Port decolua/9router#59d858b: antigravity/gemini-cli wrap non-streaming
payloads in { response: {...} }, so extractUsageFromResponse only saw the
top-level usageMetadata and every non-streaming antigravity request logged
zero usage (IN 0 | OUT 0) and zeroed usage-dashboard rows. Top-level
metadata keeps priority; OpenAI/Claude branches untouched.
* chore(changelog): fragment for #10430 antigravity usage envelope
* ci: re-run dast-smoke (Build CLI bundle runner timeout flake)
---------
Co-authored-by: Rouzbeh <rqzbeh@users.noreply.github.com>
* fix(antigravity): classify geo-blocked egress, exclude account, real connection probe
Google refuses the Cloud Code model API from unsupported egress locations
with 400 FAILED_PRECONDITION "User location is not supported for the API
use." Previously this surfaced as a cryptic "Antigravity upstream error
(400)", never excluded the account, and the dashboard connection test stayed
green because it only probed the (non-geo-restricted) OAuth userinfo endpoint.
- errorClassifier: new GEO_BLOCKED type + isGeoBlockedError detection
(400/403 + location-not-supported wording); non-terminal classification.
- chatCore fallback: GEO_BLOCKED marks the connection and caches a 24h
rate-limit-until exclusion so routing moves to other accounts instead of
re-selecting the same one; never bans/expires the account.
- auth: GEO_BLOCKED joins the non-terminal group (no banned/expired state).
- antigravityUpstreamError: geo refusals carry an actionable message (egress
location vs account problem, proxy-in-supported-region guidance).
- connection test: antigravity/agy now probe the REAL streamGenerateContent
surface (buildProbe), so a green tick means the model path actually works
and a geo-blocked egress shows red with a clear diagnosis.
* chore(changelog): fragment for #10420 antigravity geo-block resilience
* chore(pr): drop prettier-version drift noise, keep only real hunks
The earlier format pass (local prettier differs from the repo's pinned
version) rewrapped unrelated lines in chatCore.ts and the provider test
route. Restore the base formatting and re-apply only the GEO_BLOCKED
fallback branch and the buildProbe connection-test changes.
* fix(antigravity): strip competing-agent system prompts (429 RESOURCE_EXHAUSTED)
Port decolua/9router b566b20, generalized: Antigravity flags system prompts
advertising competing agents ('You are a Claude agent, built on Anthropic's
Claude Agent SDK.' — Zed, Claude Code, etc.) and answers with a 429 quota
error. sanitizeAntigravityGeminiRequest now strips known competitor identity
sentences from systemInstruction.parts before dispatch; surrounding
instruction text is untouched and non-matching prompts pass through without
allocation.
* chore(changelog): cover competitive prompt strip in #10420 fragment
* fix(antigravity): scope GEO_BLOCKED classification to Google AI surfaces
Address reviewer feedback: classifyProviderError is shared across every
provider, so a lookalike 'not available in your region' body from an
unrelated upstream must not receive the egress-fixable 24h exclusion
treatment. Gate GEO_BLOCKED behind isGeoBlockEligibleProvider, which
matches the surfaces that actually emit Google's regional-availability
refusal: Cloud Code / Gemini Code Assist (antigravity, agy, cloudcode*),
the Gemini Developer API (gemini, gemini-cli, vertex), plus a
registry-driven fallback on executor/format. Non-Google providers fall
through to their existing 400/403 classification (typically null for an
unclassified 400), so a permanent block still follows its own path.
* ci: re-run quality gates
Trigger a fresh CI run for the PR: the previous run's 'Vitest (fast-path)'
job failed in 'npm ci' because the onnxruntime-node postinstall could not
download its binary from the Microsoft CDN (connect ETIMEDOUT
150.171.109.118:443). No tests ran; no code changed in this commit.
* fix(antigravity): guard provider before registry lookup in geo-block gate
isGeoBlockEligibleProvider passes the raw provider (string | null | undefined)
to getRegistryEntry(provider: string), failing typecheck:core and the
ts7-diagnostics ratchet (TS2345 at errorClassifier.ts:166). Add an explicit
null guard; runtime behavior is unchanged — a falsy provider already resolved
to !entry -> false.
* ci: re-run quality gates (vitest npm ci onnxruntime CDN flake)
---------
Co-authored-by: Rouzbeh <rqzbeh@users.noreply.github.com>
* fix(guardrails): reroute zero-vision combos through the vision bridge
Named combos whose model targets all lack vision support are never
reroute-eligible: the bridge only attempts the describe path, and when
describing cannot run or fails the raw images stay in the payload and the
request dies in the combo capability filter with capability_mismatch.
getComboVisionBridgeDecision now returns a "no-vision" verdict for combos
with zero vision-capable targets, and preCall treats it as reroute-eligible
with the same credential guards as single text-only models, falling back to
describe only when no usable reroute target exists.
* chore(changelog): fragment for #10415 vision bridge combo reroute
* fix(guardrails): extend allNull stub fallback to no-vision combos
Reviewer follow-up (#10415): the allNull stub-text fallback at the end of
preCall only fired for comboVisionBridgeDecision === 'process'. In the
compound-failure case for a zero-vision combo — reroute target without
usable credentials AND every describe call failing — raw images were
preserved and the original capability_mismatch recurred, because a
no-vision combo has no target that can consume images.
Include 'no-vision' in the guard: stub text is strictly better than raw
bytes no combo target can consume. Adds a double-failure unit test.
* ci: re-run dast-smoke (Build CLI bundle runner timeout flake)
* fix(build): bound and retry the opencode-plugin npm install in prepublish
The plugin's node_modules is gitignored, so every fresh CI checkout runs a
full npm install inside @omniroute/opencode-plugin during build:cli. npm's
unbounded fetch retries turn a stalled registry CDN connection (the recurring
onnxruntime-class ETIMEDOUT flake) into a 20-30 minute hang — the DAST
'Build CLI bundle' step has been cancelled at the 30m cap repeatedly.
- Bound npm fetch: --fetch-timeout 60s, 2 retries with capped backoff — a
stalled connection now fails fast instead of hanging the job.
- Retry the install up to 3 times with a 10s pause between attempts, so
transient CDN failures recover in-build.
Net effect: the step either completes (network OK) or fails quickly with a
clear error (network down) — it can no longer eat the whole job budget.
* ci(dast): use existing npm-ci-retry action instead of bare npm ci
dast-smoke died at 'Run npm ci' with connect ETIMEDOUT to the
onnxruntime-node binary CDN (Microsoft 150.171.x.x) — the same
transient CDN flake class that has hit Vitest/Quality Gates before.
quality.yml already wraps npm ci in ./.github/actions/npm-ci-retry
(3 attempts, exponential backoff); dast-smoke was the one workflow
still using a bare install. Use the existing action for consistency.
* ci(quality): use the npm-ci-retry action on every install step
Fast Quality Gates failed on the recurring onnxruntime-node postinstall
ETIMEDOUT (Microsoft CDN 150.171.x.x) - the same transient flake that has
hit Vitest and dast-smoke today. Only the Build job used the retry action;
the other five jobs (Docs, Fast Quality Gates, Vitest, Unit Tests,
changelog) still ran a bare install and die on any CDN hiccup. Use the
existing retry action (3 attempts, exponential backoff) on every install
step for consistency.
---------
Co-authored-by: Rouzbeh <rqzbeh@users.noreply.github.com>
OpencodeExecutor and MimocodeExecutor rotated to the next account only on
HTTP 429. A network exception (timeout, connection refused/reset) on one
account instead propagated out of execute() and failed the whole request,
even when other accounts remained available.
Both executors now rotate on a network exception only when the failed
account has its own dedicated proxy (account.proxy !== null) — a dead
proxy is genuinely account-scoped, so rotating away from it is safe.
Accounts sharing the default egress (no proxy configured) trigger the
same cooldown and are skipped for the rest of the request once the shared
egress is known down, but a later account with its own dedicated proxy is
still tried normally — a throw on a proxy-less account no longer strands
a proxied account further in the rotation. This behavior is gated behind
NETWORK_ROTATION_SHARED_EGRESS_GUARD (Feature Flag, default on); disabled,
it reproduces the immediate-propagation behavior this fix started from.
The shared rotation mechanics (pickAccount/markCooldown/markSuccess) are
extracted into executors/accountRotation.ts, used by both executors —
they had independently implemented the same round-robin+cooldown
skeleton. This also fixes an identical, pre-existing bug in
MimocodeExecutor that predates this PR: its catch block called
markCooldown unconditionally on any throw, with no proxy check and no
warn log (a silent exception swallow on a path that influences the
result).
The cooldown formula for both the proxy and shared-egress cases reuses
the repo's already-established "transient, not clearly attributable"
constants (errorConfig.ts TRANSIENT_COOLDOWN_MS/COOLDOWN_MS.transientMax,
already used by accountFallback.ts for network-error classification)
instead of introducing a separate value.
MimocodeExecutor's network-error 502 body also now goes through
buildErrorBody()/sanitizeErrorMessage() instead of embedding the raw
caught error message directly (Hard Rule #12), matching the sanitization
already used on its #2101 malformed-request path.
Validated by TDD (Hard Rule #18): tests/unit/account-rotation.test.ts
covers the shared module directly; opencode-proxy-rotation-4954.test.ts
and mimocode-executor.test.ts cover the proxy-configured rotation path,
the mixed-fleet case, the shared-egress single-network-call case, and the
NETWORK_ROTATION_SHARED_EGRESS_GUARD-disabled legacy path, for each
executor. tsc, lint, and the provider golden-path gates
(check:provider-consistency, check:provider-assets,
provider-translate-path-golden.test.ts) are clean on all touched files.
Co-authored-by: Max <maxmad64@gmail.com>
* fix(sse): dedupe header-budget drop warns by drop-set fingerprint
The 768-byte forwarded-header budget drop path emitted a full warn (with
up to 20 dropped entries) on every SSE response whose headers exceeded the
budget. The dropped set is usually identical across responses from the same
upstream, so the repeats carried no new information — under Desktop
multi-stream use this buried real errors and added event-loop serialization
work.
Warn once per unique drop fingerprint (sorted dropped-header names, capped
at 1000 fingerprints) per process, then log at debug level.
Fixes#10315
* changelog: fragment for #10397
* fix(db): default debugMode to false in getSettings() defaults
Fresh installs (or installs missing the persisted debugMode key) ran in
debug mode, contradicting the documented opt-in toggle and flooding new
production installs with debug-level logs. Flip the default to false;
installs that persisted debugMode=true keep it — only the missing-key
path changes, no migration needed.
Fixes#10312
* changelog: fragment for #10372
* fix(monitoring): canonicalize provider aliases in health matrix
* fix(monitoring): canonicalize aliases in health autopilot
---------
Co-authored-by: tkgo11 <7.1800574e+07+tkgo11@users.noreply.github.com>
* fix(sse): close the synthetic keepalive reasoning item's output_item
RESPONSES_STARTUP_THINKING_FRAME (the /v1/responses early-keepalive
placeholder for slow-starting reasoning models) opened a synthetic
"rs_keepalive" reasoning item at output_index 0 and closed its nested
summary part (response.reasoning_summary_part.done), but never sent
response.output_item.done to close the item itself. The comment
claimed it was "closed within this one frame" — that was true for the
part, not the item.
Since this placeholder has no real upstream counterpart (the real
response starts an independent response.created lifecycle later and
never touches it), nothing else ever closes it. A client tracking open
items by output_index (as the Responses API spec requires — this is
exactly what OpenClaw's parser does) sees index 0 still open when the
real response's own output_item.added later reuses that same index,
and throws a collision.
Live incident (2026-08-13, reliably reproducing by 2026-08-14): traced
via a live tcpdump capture on the OmniRoute-dev container's network
namespace, correlated against the OpenClaw gateway journal and 10
separate real request/response pairs (all wire-clean on the response
side, ruling out provider corruption). The failing request's own
outbound payload confirmed a replayed reasoning item without
encrypted_content feeding a continuation call; the response wire bytes
for that exact exchange showed rs_keepalive's output_item.added at
index 0, then response.created/response.in_progress arriving *after*
it, then a second output_item.added reusing index 0 for the real
reasoning item — never preceded by an output_item.done for
rs_keepalive. Reported upstream as OpenClaw issue #123342 before the
OmniRoute-side root cause was found.
Fix: emit response.output_item.done for the synthetic item, matching
its already-buffered summary text, right after the summary part closes
and before the frame ends.
Test plan:
- tests/unit/early-stream-keepalive.test.ts: updated the frame-shape
test to assert the full 5-event closed sequence (added the missing
output_item.done and its field assertions); confirmed it fails
against pre-fix code (only 4 events) and passes after
- node --test tests/unit/early-stream-keepalive.test.ts,
tests/unit/earlyStreamKeepalive.test.ts,
tests/unit/keepalive-cleanup-8140.test.ts,
tests/unit/chat-body-admission.test.ts: 58 passed, 2 pre-existing
skips unrelated to this change (Node test runner
ReadableStream-error-simulation limitation)
- tsgo --noEmit: clean on both touched files
* fix(sse): allocate the keepalive output_index from a stack, not a literal
Follow-up to 03f8345ac. That commit patched the specific symptom (added
the missing response.output_item.done). This commit fixes the class:
RESPONSES_STARTUP_THINKING_FRAME hardcoded output_index: 0 as a literal
across five hand-written events, which is exactly how the missing-close
bug happened in the first place — nothing enforced that every open got
a matching close, so it silently didn't for months.
ResponsesOutputIndexStack (open-sse/utils/responsesOutputIndexStack.ts)
makes that structural: open() allocates the next sequential index,
close() must name the index being closed and throws if it doesn't match
the stack's top, and assertAllClosed() throws if anything is still open.
The keepalive frame now calls assertAllClosed() at module load, so a
future regression of this exact shape fails at import/boot time instead
of shipping a malformed stream to production and surfacing days later
as a live incident.
Also adds tests/helpers/assertResponsesOutputIndexLifecycle.ts: a
reusable version of the same invariant for replaying a full SSE event
sequence (not just checking one frame's own shape), mirroring what a
real client's output-index tracker enforces. Existing coverage for this
bug class (responses-reasoning-close-before-message-466.test.ts) only
asserted it by hand for one specific emitter (the real translator); nothing
generic existed for a hand-rolled synthetic frame like this keepalive to
be checked against, which is why its own test could pass while the actual
downstream contract still failed. Wired into
early-stream-keepalive.test.ts, including a test that concatenates the
keepalive frame with a plausible real subsequent response and asserts no
collision — the scenario that actually reproduced live, not just the
frame's own internal shape.
Test plan:
- tests/unit/responses-output-index-stack.test.ts (new): open/close/
assertAllClosed behavior, including the exact mismatch and
never-closed shapes this incident hit
- tests/unit/early-stream-keepalive.test.ts: existing frame-shape test
plus new collision-simulation test, both passing
- node --test across responses-output-index-stack, early-stream-keepalive,
earlyStreamKeepalive, keepalive-cleanup-8140, chat-body-admission:
65 passed, 2 pre-existing skips unrelated to this change
- tsgo --noEmit: clean on all touched files
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* fix(docker): prefix cache mount ids with Railway service scope
Railway's Dockerfile builder rejects --mount=type=cache ids that lack
the s/<service-id>- prefix (dockerfile invalid, caught at syntax
validation before any build step runs). Prefix all 7 cache mount ids
(apt-cache, apt-lists x4 RUN blocks, npm-cache x2, next-cache x1) with
the omni-route service id.
* fix(sse): remove duplicate sseCommentsEnabled import in stream.ts
Turbopack rejected the file with 'the name sseCommentsEnabled is
defined multiple times' — imported once at the top of the file and
again lower down from the same module. Broke every production build
(Docker/Railway) at the release/v3.8.50 tip, independent of the cache
mount fix in this branch. Validated by a full Docker build on Railway
completing past this step.
* fix(sse): answer tiny-budget reasoning probes with a truncated 200 (#10281)
Claude Code's /model capability check sends max_tokens: 1. Reasoning
models burn the whole probe on thinking, and some upstreams (e.g.
api.cline.bot for deepseek-v4-flash) answer the empty outcome with a
5xx "empty response content" instead of a truncated 200. The relayed
failure also marked the connection unavailable and poisoned
fallback/cooldown bookkeeping for what is only a probe.
Detect tiny-budget reasoning probes in the non-streaming providerFailure
path and synthesize a valid truncated response (200, empty content,
finish_reason "length") — the same semantics errorClassifier.ts already
grants to length-truncated empty 200s. Probes no longer poison
connection health. Refs #10281.
* chore(changelog): add fragment for reasoning-probe truncated-200 fix (#10284)
sql.js has no incremental write path, so persist() rewrites the whole image on
every save. Going through fs.writeFileSync(filePath, ...) opened the destination
with O_TRUNC, leaving the on-disk database 0 bytes and then partial for the whole
write -- a window that scales with database size and recurs on every save.
Unlike better-sqlite3 / node:sqlite, that window is not covered by SQLite's
locking protocol, so it is visible to every other process reading the same file:
a backup job, a metrics exporter, an operator running sqlite3. Those readers get
SQLITE_CORRUPT ("database disk image is malformed") while PRAGMA
integrity_check passes moments later, which makes the failure look random and
blames the reader.
Now: temp file in the same directory, fsync, rename() over the destination.
rename is atomic on POSIX and on Windows for a same-volume replace, so a reader
sees either the previous image or the new one, never a truncated one. It also
closes a total-loss window: a crash mid-write used to leave the real database
truncated, and now only leaves a stale temp file behind.
The regression guard asserts the property that separates the two implementations
without racing a timer: a reader that opened the file before a save still reads a
complete, valid image afterwards, and the published file sits on a new inode.
It fails on the previous implementation and passes on this one.
Co-authored-by: Max <maxmad64@gmail.com>
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* fix(providers): make the monsterapi deprecation from #8676 actually apply
#8676 marked MonsterAPI deprecated after its domain stopped resolving, but
wrote the flag as `isDeprecated`. Nothing reads that key. The field the
codebase consumes is `deprecated`:
src/shared/validation/providerSchema.ts declares `deprecated`
ProviderCard.tsx strikethrough + block icon + reason
ProviderTestSlideOver.tsx warning
providerOnboardingCatalog.ts Boolean(provider.deprecated), sorts last
ProviderOnboardingWizard.tsx deprecated badge
scripts/docs/gen-provider-reference.ts gates the DEPRECATED note
Zod object schemas ignore undeclared keys, so `isDeprecated` never failed
validation - it was dropped silently. The deprecation therefore had no effect
anywhere, and tests/unit/8676-monsterapi-deprecation.test.ts asserted the same
unread key, so it stayed green while guarding nothing.
The committed docs/reference/PROVIDER_REFERENCE.md is the visible proof: the
generator renders predibase (which uses `deprecated`) with a DEPRECATED note,
while monsterapi still advertised "Get API key at monsterapi.ai" - a domain
that does not resolve (probed 2026-08-13: api.monsterapi.ai and monsterapi.ai
both 000, against api.openai.com 401 as a reachability control).
Rename the key, repair the regression test to assert the consumed field and to
reject the undeclared one, and refresh the generated reference row.
* fix(providers): name the changelog fragment for PR #10234
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: pacocartones <pacocartones@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
Present xAI API-key and OAuth connections through one dashboard card while preserving the distinct backend IDs required for refresh and quota handling.
Co-locate both registry entries and include canonical and legacy connection IDs in provider fetch and batch-test flows.
* feat(providers): add local ZCode ACP backend
* test(snapshots): regenerate translate-path golden for zcode provider
The new local ZCode ACP backend (zcode://app-server/stdio) was added to the
provider catalog but the translate-path golden snapshot was not regenerated,
so the combined suite (provider-translate-path-golden.test.ts) failed on the
merged tip. Regenerate the snapshot to include the zcode translate-path entry.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* docs(env): document ZCODE_* vars for the local zcode provider
Registers the 11 ZCODE_* env vars read by the zcode executor (.env.example
+ docs/reference/ENVIRONMENT.md) so the env-doc-sync gate stays green.
Co-authored-by: Diego Souza <8016841+diegosouzapw@users.noreply.github.com>
* test(autoCombo): include zcode in the glm-family provider set
#10184's local zcode backend advertises the full GLM_SHARED_MODELS
line-up (registry/zcode, authType none) — same documented case as auggie
and devin-cli-agentic. Update auto/glm provider-set assertion to include
it.
Co-authored-by: Diego Souza <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: roomhacker <roomhacker@bezrabotnyi.com>
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
resolvePortPid shelled out to lsof alone. On a host without it, spawn
raises ENOENT, the error handler turned that into null, and the caller
could not tell 'nothing holds this port' from 'I have no way to look' -
so a service adopted on a supervisor restart kept pid: null forever,
silently, which is the regression the adopt-branch test guards against.
Probes lsof, then ss, then netstat, sharing one deadline so the whole
lookup still costs at most PID_RESOLVE_TIMEOUT_MS. Output parsing for
each is a pure exported function so the formats are unit-testable
without the binary being installed.
netstat cannot filter by port, so its parser matches the local-address
column rather than scanning the line, keeping a foreign address that
ends in the same number from being read as a listener.
Implements the secure, opt-in Video Bridge for issue #9760, including bounded FFmpeg frame extraction, capability-aware routing, telemetry, settings UI, localization, documentation, and regression coverage.
* fix(sse): let :free OpenRouter models bypass connection-wide credits_exhausted lock
A 402 from one paid OpenRouter model correctly locks the whole connection
as credits_exhausted for an hour (intentional, per #6842), but that lock
was also blocking every :free model on the same connection even though
OpenRouter bills free models separately from account credits.
Reconstructed clean against release/v3.8.50 by the maintainer: the author's
original branch predated a large auth.ts import refactor; the same delta was
re-applied onto the current tip and the TDD test still passes.
TDD: tests/unit/openrouter-free-model-credits-exhausted.test.ts
reproduces the bug (fails before the fix, passes after) and covers the
three guard cases above.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* test(mutation): register openrouter-free-model-credits-exhausted in stryker tap.testFiles
The new unit test covers src/sse/services/auth.ts, which is one of the 31
stryker-mutated modules — per check-mutation-test-coverage every covering
test must be listed in tap.testFiles or its mutant kills stop counting.
Registered the file so the blocking mutation-test-coverage gate passes.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: killmonger2317-coder <282069920+killmonger2317-coder@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(kilocode): strip unsupported response_format for DeepSeek (400 regression)
kilocode's DeepSeek V4 Flash rejects ANY response_format — both
json_schema AND json_object 400 with 'Invalid input: response_format'
(verified live 2026-08-15 via the Hindsight fact-extraction path on
kilocode/deepseek/deepseek-v4-flash). The default executor's
applyJsonSchemaFallback only covered openai-compatible-* providers and
only downgraded json_schema -> json_object, so kilocode forwarded the
unsupported format raw. Same bug class as the opencode fix#9992.
For kilocode: strip response_format entirely and inject the schema (or a
plain 'valid JSON only' instruction for json_object) into the system
prompt. openai-compatible-* keeps the existing json_schema downgrade and
json_object passthrough (they accept both).
Regression tests: kilocode json_schema is stripped + schema-injected;
kilocode json_object is stripped + JSON-only instruction; both verified
to fail without the fix (sabotage: 2 fail). All 49 executor-default-base
tests pass.
* fix(kilocode): drop as-any casts in new tests to clear the frozen ESLint baseline
The file's frozen no-explicit-any baseline is count 42; the new kilocode
strip tests added 3 net-new 'as any' casts, tripping the --max-warnings 0
lint-guard. Replace them with typed assertions that carry the same checks.
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
---------
Co-authored-by: benzntech <benzntech@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
The upstream Messages API rejects directive-style messages (empty content
array with a message-level output_config) when they sit at messages[0] —
the initial system prompt position — while accepting the form at any other
position. Measured in production: 122x 400 on the offical-claude combo in
one hour.
The mid-conversation-system passthrough (official provider + 1M-context
beta models) keeps system-role messages inside messages[], so a directive
that arrived first went upstream unchanged. relocateDirectiveOnlyMessages()
moves the whole leading run of empty system messages: directive-only ones
past the first real turn, plain empties dropped. extractSystemRoleMessages()
now folds a directive's output_config into the top-level parameter instead
of silently discarding it.
Signed-off-by: Minxi Hou <houminxi@gmail.com>
Auto combos (virtual auto/* pools via virtualFactory and pure-auto named
combos via expandAutoComboCandidatePool) expanded their candidate pool from
the provider's STATIC registry catalog, which can include models the operator
never synced or approved (e.g. openrouter/auto). The visibility filter
(getHiddenModelsByProvider) only caught models explicitly flagged isHidden,
so catalog-only models passed through and got routed upstream.
Build the credentialed pool from the models the user actually has available
(synced + custom non-hidden), falling back to the static catalog only when
the operator has no synced/custom models for that provider. Applies to every
provider uniformly (openai, kilocode, openrouter, ...), with per-connection
scoping for synced models. Provider wildcards (providerWildcard.ts) already
used the active synced catalog as the authoritative source.
Regression coverage: tests/unit/combo-auto-pool-visible-only.test.ts
Co-authored-by: herjarsa <herjarsa@users.noreply.github.com>
* feat(providers): add tencent-aistudio-web cookie provider (tasw)
* fix(sse): remove orphaned DevinDesktopExecutor import from executor index
The "devin-desktop" executor key is unused (devin-desktop provider config
resolves to executor "devin-cli"); the imported ./devin-desktop.ts file
was never present, so executors/index.ts failed to load (ERR_MODULE_NOT_FOUND)
and broke every unit test that imports the executor registry (e.g.
tests/unit/deepseek-web.test.ts). Stale base sync carried this into the branch.
Remove the dead import/registration/export.
* fix(providers): restore DevinDesktopExecutor registration in executor index
The previous commit removed the devin-desktop executor import/registration/
export from open-sse/executors/index.ts, but the devin-desktop provider
registry still resolves executor "devin-desktop" and
tests/unit/devin-providers.test.ts asserts hasSpecializedExecutor("devin-desktop")
is true. The removal broke 6 tests in that file. Restore the three lines so
the live Devin Desktop executor keeps serving the provider.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(providers): correct tencent-aistudio-web wrapper shape + provider count sync
Return {response,url,headers,transformedBody} instead of a raw fetch Response
(the executor contract every other executor in this file follows) and
re-wrap the upstream body so it uses the local Response constructor, not the
undici-patched one from globalThis.fetch.
Regenerate docs/reference/PROVIDER_REFERENCE.md and sync the 339->340
provider-count claims (README, AGENTS.md, llm.txt + 42 i18n mirrors,
package.json, promise-pillars/comparison-table/cli-terminal SVGs) that this
PR's new provider invalidated.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* docs(providers): sync readme-hero.svg provider count claim (339->340)
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(providers): register tencent-aistudio-web web-session credential metadata + golden
Add the WEB_SESSION_CREDENTIAL_REQUIREMENTS entry for tencent-aistudio-web
(cookie-based, matching the executor's raw Cookie-header credential) and
regenerate the translate-path golden snapshot to include the new provider —
both were failing CI unit tests that enumerate every registered provider.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(providers): align tencent-aistudio-web test with the wrapper-shape contract
The test asserted res.status/res.json() directly against executor.execute()'s
return value, matching the pre-fix (broken) raw-Response shape. Update it to
read res.response.status/res.response.json() — the {response,url,headers,
transformedBody} contract every executor in this codebase follows.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: openhands <openhands@all-hands.dev>
Co-authored-by: MeRezaRezaei <MeRezaRezaei@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
Deploying the internal gateway was a manual build/pack/scp/npm-i/pm2-restart sequence with no record of what landed and no proof it served traffic. On 2026-08-14 that shipped a package built from a branch predating #10373: the process came up, health said 'healthy', and every request returned 502 until a human hit it.
scripts/ops/deployCanary.ts holds the policy as pure functions — refuse an artifact that is not traceable to the release line (reusing #10427), and grade the deploy on health PLUS at least one real completion. Zero probes fails: 'no probe ran' must never read as 'everything is fine', which is exactly how a broken egress path hides behind a green health check. Remote steps are argv arrays, never shell strings (Hard Rule #13), ordered so the rollback anchor is captured before the install overwrites it.
scripts/ops/deploy-canary.mjs performs the side effects, supports --dry-run, and prints the rollback command when the smoke fails.
Closes#10429
The packaged artifact stamped dist/BUILD_SHA but nothing verified the SHA belonged to the release line, so a tarball built from a feature branch installed and served traffic indistinguishably from a release build. That is how the internal gateway ended up running a build that predated #10373 and answered every request with 502 'Executor result must contain a Response' — identifying it required SSH plus grepping the compiled chunks.
scripts/build/buildProvenance.ts classifies a build SHA against the release ref (pure functions, injected git probe). A missing SHA fails even with the canary override: an unidentifiable artifact cannot be vouched for. validate-pack-artifact enforces it on real packs (skipped under --policy-only, which runs without a build); OMNIROUTE_ALLOW_CANARY_BUILD=1 records a deliberate off-release-line build instead of failing it. /api/monitoring/health now exposes system.buildSha — absent when unknown, never fabricated.
Closes#10427
Any process that opened the DB without setting DATA_DIR resolved to ~/.omniroute/storage.sqlite — the operator's live database, provider credentials included. tests/_setup/isolateDataDir.ts only covers the npm scripts; the documented single-file test command and ad-hoc probes bypassed it (one did exactly that during #10334).
resolveWritableDataDir now redirects a test-context process with no DATA_DIR to a throwaway temp dir, stable per process. Redirect rather than throw, so the documented single-file command keeps working; OMNIROUTE_ALLOW_DEFAULT_DATA_DIR=1 opts back in and records the intent.
Closes#10428
Audit of every numeric claim in the README, AGENTS.md and the README SVGs against
live code, plus a changelog/credit reconciliation over the full v3.8.50 cycle.
Corrected numbers (all measured, not estimated):
- Provider circuit breaker thresholds were scaled up in code for 500+ connection
deployments (`providerFailureThreshold`: OAuth 3 -> 10, API key 5 -> 15) but the
docs still published the pre-scale values. Fixed in AGENTS.md (now a table that
also separates the provider-level threshold from the per-connection one and lists
the provider cooldowns), in the README alt text and inside resilience-layers.svg
(visible label and aria-label).
- "40+ free forever" was unsourced. Measured from the free-tier catalog as every
provider whose free access renews or needs no key (recurring-monthly, -daily,
-uncapped, -credit, keyless; one-time signup credits and discontinued pools
excluded): 56. Updated in the README and promise-pillars.svg.
- Cycle-evolution table: v3.8.49 shipped 290 providers, not 291, and the model row
compared the v3.8.49 free-tier catalog (516) against today's full catalog. Both
columns now use the same metric - distinct documented models, 1185 -> 1202.
- Tech-stack row: 95 domain modules -> 117.
The free-forever count is now enforced by check:docs-counts so it cannot drift
again; it is derived from freeType in the live catalog, like every other gated
number.
Changelog reconciliation (`scripts/release/list-uncovered-commits.mjs`):
uncovered cycle commits drop from 149 to 62. 75 user-facing commits gained a bullet
with author attribution, the 45 ref-less direct pushes and 29 chore/ci/test/docs
commits were consolidated into rollup bullets, and the contributors table grew from
147 to 161 rows - 14 contributors who had landed work with no credit at all
(including @amartinawi, @pacocartones and @excessivechaos) are now credited.
The remaining 62 carry no PR/issue ref, which is the ceiling of ref-based coverage.
CHANGELOG.md and its i18n mirrors are added to .prettierignore: check:changelog-
integrity compares base bullets as exact strings, and Prettier normalizes markdown
emphasis inside them (*from* -> _from_), so any PR that staged the changelog turned
the merge-integrity job red. scripts/release/* is the changelog's formatter of
record, the same precedent already used for ENVIRONMENT.md and PROVIDER_REFERENCE.md.
Co-authored-by: Xiangzhe <bakryun0718@proton.me>
* docs: add rate limiting guide for free providers (429/400/401)
Community-reported troubleshooting for auto-discovered issues when
rotating through free/no-auth providers (opencode, felo-web, auggie).
Documents the verified env-var combo that eliminates
intermittent 429/400/401 failures in cron/agent automation:
OMNIROUTE_ROTATE_ON_400=true,
OMNIROUTE_CHAT_MAX_HEAVY_IN_FLIGHT=4,
OMNIROUTE_STRUCTURE_LIMIT=off
Includes root-cause breakdown (provider quota vs passthrough 401 vs
concurrency amplification), verification steps via /monitoring/health,
and escalation for hard quota exhaustion.
* docs(providers): fix fabricated env var and breaker states in rate-limit guide
Replace OMNIROUTE_STRUCTURE_LIMIT (does not exist in the codebase) with
OMNIROUTE_CHAT_ADMISSION_QUEUE_MS and document the real rate-limit knobs
(RATE_LIMIT_MAX_WAIT_MS / RATE_LIMIT_MAX_QUEUE_DEPTH / RATE_LIMIT_AUTO_ENABLE).
Correct the circuit breaker states to the actual enum (CLOSED/DEGRADED/OPEN/HALF_OPEN)
and point the health-check note at circuitBreakers.providerBreakers[].state.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: Bruno <bruno@nousresearch.com>
Co-authored-by: mrcram2021 <mrcram2021@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* fix(db): prune pre-migration backups so db_backups stops growing unbounded
createPreMigrationBackup() wrote a VACUUM INTO snapshot on every migration run
and never pruned. On a long-lived instance db_backups/ reached 48.999 files /
204 GB against a 5,3 MB live database; a second devbox showed the same shape
(5.711 files / 24 GB).
The retention policy already existed in cleanupDbBackups() but nothing on the
migration path reached it — its only callers are backup.ts and the
/api/db-backups route, neither of which runs during a migration.
migrationRunner.ts cannot import backup.ts: core.ts imports migrationRunner.ts
and backup.ts imports core.ts, so that edge would close a cycle. The policy
therefore moves to a new core-free module, backupRetention.ts, which both call
sites share — cleanupDbBackups() now delegates to it rather than duplicating it.
At the migration call site the operator's maxFiles/retentionDays are read
through the adapter already open for the run; going through getDbInstance()
would re-enter database initialization. Pruning never throws, so housekeeping
cannot fail a migration.
Closes#10421
* chore(db): declare backupRetention as an intentionally-internal db module
check:db-rules requires every src/lib/db/ module to be either re-exported by
localDb.ts or listed in INTENTIONALLY_INTERNAL. backupRetention.ts is a shared
primitive consumed only by db/backup.ts and db/migrationRunner.ts — the same
category as the migrationRunner entry — so it belongs in the allowlist rather
than in the public re-export surface.
* test(db): include backupRetention in the audited INTENTIONALLY_INTERNAL list
check-db-rules-classification.test.ts freezes the exact membership of
INTENTIONALLY_INTERNAL, so adding the 40th entry has to be reflected there too
— the gate script and this test pin the same contract from opposite sides.
---------
Co-authored-by: Xiangzhe <bakryun0718@proton.me>
i-have-adhd shipped in #10271 with en + pt-BR only; it now covers vi/ja/id as well,
matching ponytail. Every level keeps the SHARED_BOUNDARIES clause.
Adds a per-MATRIX guard (output-styles-i18n-matrix.test.ts). Every existing test is
per-style, which is how less-code stayed English-only since the 9router port without
anyone noticing. The guard fails on: a new style without pt-BR, a style losing a
translation it had, a translation missing an intensity level, a translation that dropped
the boundaries clause, and a stale KNOWN_ENGLISH_ONLY entry.
Proven by mutation, not just by passing: dropping less-code from the allowlist and
renaming the vi key both turned it red with the expected messages.
less-code stays English-only as declared debt (KNOWN_ENGLISH_ONLY + comment); the
remaining coverage work is tracked in #10426.
Makes the ProviderErrorRule `scope` field real at the persistence layer, exclusively for agentrouter (owner decision; every other provider keeps byte-identical behavior).
checkFallbackError now surfaces `ruleScope` behind the HONORS_RULE_LOCK_SCOPE_PROVIDERS allowlist, and the agentrouter 403 path consults the rules before the generic apikey-FORBIDDEN early-return. markAccountUnavailable honors scope "connection" with a temporary connection cooldown instead of a per-model lockout — guarded so a permanent state can never be downgraded to a transient retry loop — and combo now skips the exhausted account within the same request, which also stops force-reusing the just-cooled connection via allowRateLimitedConnection.
Documented in RESILIENCE_GUIDE §7 with the honest limits (disableCooling connections keep per-model behavior; the 6h model-access cooldown is clamped by mlSettings.maxCooldownMs, 30min by default; same-request skip needs targets carrying their own connectionId).
Closes#10334
* fix(ci): pin Build (advisory) to a hosted runner with memory provisioning
`Build (advisory)` has been reporting a permanent red on every PR while
producing no usable signal at all.
Measured over the last 25 quality.yml runs (2026-08-14): not one instance of
the job reached a conclusion. Every sample was either queued on the
self-hosted pool — 2 runners, omniroute-113-6/7, both permanently busy; one
job sat queued for over 2 hours and was still unclaimed — or, when it did land
on a runner, killed mid-build by this workflow's own cancel-in-progress
concurrency. All 6 sampled "failures" are exit 143 / "The runner has received
a shutdown signal" at ~3.5 min into `npm run build`. Zero OOM, zero build
errors. The job was consuming a runner the real gates compete for while
telling every PR author it was broken.
Gap 19 deliberately left USE_VPS_RUNNER governing build-like jobs, on the
premise that the build needs the .113's RAM. That premise no longer holds:
`Fast Production Build` (build.yml) runs `build:release` — a superset of this
job's `npm run build`, plus the CLI bundle — on plain ubuntu-latest and passed
24 of its last 25 runs in ~15 min. The difference is memory PROVISIONING, not
the machine: a 10 GB swapfile plus a 12 GB V8 heap. Swap is the part that
matters, because --max-old-space-size bounds only V8's JS heap and never
Turbopack's native Rust allocation (#6409).
Pins the job to ubuntu-latest and mirrors both settings from build.yml.
USE_VPS_RUNNER keeps its other consumers (ci.yml Build, nightly-release-green,
npm-publish), so the variable stays meaningful. Fork safety is strictly
improved: no PR can reach the LAN runner through this job any more.
check:workflows --ratchet: 186 zizmor findings, baseline 190, no regression.
prettier + YAML parse: clean.
* fix(ci): scope Build (advisory) to fork PRs
Follow-up to the hosted-runner pin in this same PR, after measuring what the
job is actually for.
build.yml's `Fast Production Build` triggers on `push: branches: ["**"]` and
runs `build:release` — a superset of this job's `npm run build`, plus the CLI
bundle. For an own-origin branch that push fires here, so the tree was being
built twice per PR. A fork contributor pushes to THEIR repo, so build.yml
never runs in this repo and this job is their only pre-merge build signal.
That could have argued for deleting the job, except the traffic says
otherwise: 72 of the last 100 PRs into release/** come from forks. The fork
case is the majority, not the exception. So the job earns its place — it just
should not duplicate build.yml for the own-origin 28%. Added the fork filter
to the existing `if`.
Also corrects the reliability claim in the previous commit message. Over a
wider window the job is not literally never-green: across 2026-08-13/14 it
reached `success` on roughly 10-15% of runs (13/138 on 08-14, 7/53 sampled on
08-13). Chronically unreliable, not permanently dead — the conclusion and the
fix are unchanged.
The #7307 guard in tests/unit/build/check-workflows.test.ts pinned the old
self-hosted expression, so it is realigned here: it now asserts the hosted
pin, the absence of self-hosted/USE_VPS_RUNNER in the job's DIRECTIVES (the
comment legitimately explains why the pool was abandoned, so the scan strips
comments), both memory settings, and the fork filter. Mutation-validated —
restoring self-hosted, dropping the swapfile, or flipping the fork filter each
turns it red.
check-workflows.test.ts: 32 pass, 0 fail.
check:workflows --ratchet: 186 findings, baseline 190, no regression.
---------
Co-authored-by: Xiangzhe <bakryun0718@proton.me>
#10290 moved bailian-coding-plan from the Coding Plan host to the documented
Token Plan one, but the provider/translate-path golden still pinned
coding-intl.dashscope.aliyuncs.com, so tests/unit/provider-translate-path-golden.test.ts
fails on the release tip.
Regenerates the snapshot (UPDATE_GOLDEN=1) — the diff is exactly the two
bailian-coding-plan URLs, every other provider byte-identical — and fixes the
same stale host in the endpoint matrix of
docs/providers/ALIBABA-QWEN-PROVIDER-FAMILIES.md.
This golden covers every provider's resolved URL, which is why neither the
focused tests nor typecheck caught the change: only the unit shard runs it.
Refs #9603
Co-authored-by: Xiangzhe <bakryun0718@proton.me>
@@ -148,9 +148,26 @@ _Living section — regenerated 2026-08-12 from all cycle commits (cycle open `e
- **feat(admission) — direct pushes:** adaptive overload/pressure controls with shared admission wired across the LLM routes, plus mutation-test registration for the capability-filter suite
- **feat(agentrouter) — direct pushes:** support Claude and Codex protocols — infer the protocol from the client endpoint and honor the alternate protocol through the chat pipeline
- **feat(providers) — direct pushes:** ChatGPT Web session credential guide with a Cookie Editor fast-path (canonical chromewebstore install link) and web-session fast-path test coverage
- **feat(sse):** honor provider-rule lock scope for agentrouter (connection vs model) ([#10419](https://github.com/diegosouzapw/OmniRoute/pull/10419))
- **feat(ocr):** Vertex AI DeepSeek-OCR provider ([#10398](https://github.com/diegosouzapw/OmniRoute/pull/10398))
- **feat(providers):** derive imageToText from the OCR registry + chutes dots.ocr seed ([#10400](https://github.com/diegosouzapw/OmniRoute/pull/10400))
- **feat(bridge):** normalize images to 2048px long edge before vision describe self-call ([#10287](https://github.com/diegosouzapw/OmniRoute/pull/10287))
- **feat(sse):** restate agentrouter quota 403/400 as retryable 429 with provider-scoped error rules ([#10335](https://github.com/diegosouzapw/OmniRoute/pull/10335))
- **feat(sse):** add i-have-adhd output style to compression catalog ([#10271](https://github.com/diegosouzapw/OmniRoute/pull/10271))
- **feat(crof):** advertise reasoning effort tiers incl. max from live discovery and registry ([#10062](https://github.com/diegosouzapw/OmniRoute/pull/10062)) — thanks @excessivechaos
- **feat(open-sse):** expose provider-level circuit breaker thresholds via env vars (#10040) ([#10046](https://github.com/diegosouzapw/OmniRoute/pull/10046)) — thanks @tiangao88
- **feat(dashboard):** Kimi 15% first-top-up campaign — dedicated tracked link + discount-first banner copy ([#10240](https://github.com/diegosouzapw/OmniRoute/pull/10240))
- **providers**: honor `PATCH /api/providers/[id]` so `omniroute providers rotate` stops 405ing (the OpenAPI spec and CLI already use PATCH) (PR #10366)
- **executors**: fix internal timeout misclassified as client disconnect (499) for 7 niche executors — pass TimeoutError reason to controller.abort() (#8197 side-finding)
- test(combo): guard auto/best-free never leaks the combo name as a model (#7754)
- fix(vision-bridge): describe-model no longer returns unreachable "openai/gpt-4o-mini" when every vision-capable provider is unreachable on the instance — returns null instead and surfaces a clear error (#8430)
@@ -553,6 +570,63 @@ _Living section — regenerated 2026-08-12 from all cycle commits (cycle open `e
- **fix(i18n) — direct pushes:** restore/unescape HTML entities in UI strings, translate capability-filter messages, complete web-session guide translations and Vietnamese parity
- **fix(providers) — direct pushes:** repair the DeepAI registry import + executor
- **fix(deps) — direct pushes:** CVE-driven bumps (nanoid, dompurify, mermaid, js-yaml + transitive deps for 26 Dependabot alerts) and retained isolated-build runtime dependencies in the pack
- **fix(ci):** pin Build (advisory) to a hosted runner with memory provisioning ([#10408](https://github.com/diegosouzapw/OmniRoute/pull/10408))
- **fix(providers):** refresh the translate-path golden for the bailian Token Plan endpoint ([#10410](https://github.com/diegosouzapw/OmniRoute/pull/10410))
- **fix(sse):** surface Qwen/Alibaba personal Token Plan quota in dashboard and preflight ([#10290](https://github.com/diegosouzapw/OmniRoute/pull/10290))
- **fix(deps):** pin next to an exact version so a fresh upstream release cannot break installs ([#10340](https://github.com/diegosouzapw/OmniRoute/pull/10340))
- **fix(compression):** cap countTextTokens at 50k chars and strip base64 data URIs ([#10118](https://github.com/diegosouzapw/OmniRoute/pull/10118)) — thanks @adevwithpurpose
- **fix(ci):** clear base-reds on release/v3.8.50 (round 4) ([#10260](https://github.com/diegosouzapw/OmniRoute/pull/10260))
- **fix(mcp):** persist and re-attach Gemini thoughtSignature on the direct Claude<->Gemini path ([#9448](https://github.com/diegosouzapw/OmniRoute/pull/9448)) — thanks @Sam280903
- **fix(providers):** raise default provider probe timeout from 5s to 8s ([#9283](https://github.com/diegosouzapw/OmniRoute/pull/9283)) — thanks @Sam280903
- **fix(opencode-plugin):** stop warning when an auto combo replaces its expected /v1/models twin (#8983) ([#9042](https://github.com/diegosouzapw/OmniRoute/pull/9042)) — thanks @xiaoyaner0201
- **fix(opencode):** force CLI User-Agent when CLI identity synthesis is enabled ([#10222](https://github.com/diegosouzapw/OmniRoute/pull/10222)) — thanks @adevwithpurpose
- **fix(deepseek-web):** classify business auth rejection as 401 ([#10218](https://github.com/diegosouzapw/OmniRoute/pull/10218)) — thanks @Zartharas
- **fix(combo):** make failoverBeforeRetry actually skip the same-model retry ([#10217](https://github.com/diegosouzapw/OmniRoute/pull/10217)) — thanks @hartmark
- **fix(cli):** read the full provider catalog instead of the 6-entry fallback ([#10097](https://github.com/diegosouzapw/OmniRoute/pull/10097)) — thanks @amartinawi
- **fix(providers):** kilo-gateway authType should be optional, not apikey ([#10086](https://github.com/diegosouzapw/OmniRoute/pull/10086)) — thanks @TengSivtean
- **fix(logging):** document CHAT_LOG_MAX_BODY_KB, capture messageCount for Responses API bodies ([#10038](https://github.com/diegosouzapw/OmniRoute/pull/10038)) — thanks @hartmark
- **fix(dashboard):** expose OpenAI Responses store toggle for non-Codex connections ([#10121](https://github.com/diegosouzapw/OmniRoute/pull/10121)) — thanks @hartmark
- **fix(combo):** clear LKGP pin when its target fails, not only set it on success ([#10034](https://github.com/diegosouzapw/OmniRoute/pull/10034)) — thanks @hartmark
- **fix(responses-api):** tool call after reasoning collided on the same output_index ([#10025](https://github.com/diegosouzapw/OmniRoute/pull/10025)) — thanks @hartmark
- **fix(responses-api):** explicit function-tool declaration must win over apply_patch-is-custom fallback ([#10041](https://github.com/diegosouzapw/OmniRoute/pull/10041)) — thanks @hartmark
- **fix(kimi):** recupera limite temporario sem bloquear conta ([#10058](https://github.com/diegosouzapw/OmniRoute/pull/10058)) — thanks @bortolidiego
- **fix(sse):** apply free-tier filter to auto/best-free on chat path ([#10199](https://github.com/diegosouzapw/OmniRoute/pull/10199)) — thanks @ggdayup
- **fix(providers):** default missing cache_control.ttl to 1h on the native Claude OAuth path ([#10221](https://github.com/diegosouzapw/OmniRoute/pull/10221)) — thanks @jeff-alves
- **fix(ci):** clear base-reds on release/v3.8.50 (round 3) ([#10213](https://github.com/diegosouzapw/OmniRoute/pull/10213))
- **fix(security):** correct XML double-unescape and non-CSPRNG nonce from CodeQL sweep ([#10154](https://github.com/diegosouzapw/OmniRoute/pull/10154))
- **fix(docker):** eliminate npm-bundled CVEs from the published image ([#10182](https://github.com/diegosouzapw/OmniRoute/pull/10182))
- **fix(security):** resolve open CodeQL alerts ([#10188](https://github.com/diegosouzapw/OmniRoute/pull/10188))
- **fix(dashboard):** retarget Kimi promo CTA to the API platform aff link ([#10200](https://github.com/diegosouzapw/OmniRoute/pull/10200))
- **fix(build):** repair broken production build, red lint gate and SWR crash ([#10198](https://github.com/diegosouzapw/OmniRoute/pull/10198))
### 📝 Maintenance
@@ -698,6 +772,10 @@ _Living section — regenerated 2026-08-12 from all cycle commits (cycle open `e
- **deps (rollup):** dependency bumps and lockfile maintenance across the cycle — Dependabot groups and manual CVE-driven bumps ([#9081](https://github.com/diegosouzapw/OmniRoute/pull/9081), [#9082](https://github.com/diegosouzapw/OmniRoute/pull/9082), [#9427](https://github.com/diegosouzapw/OmniRoute/pull/9427), [#9458](https://github.com/diegosouzapw/OmniRoute/pull/9458), [#9459](https://github.com/diegosouzapw/OmniRoute/pull/9459), [#9461](https://github.com/diegosouzapw/OmniRoute/pull/9461), [#9462](https://github.com/diegosouzapw/OmniRoute/pull/9462), [#9472](https://github.com/diegosouzapw/OmniRoute/pull/9472))
- **docs/chore (rollup):** documentation, refactoring and repository-hygiene upkeep across the cycle ([#8954](https://github.com/diegosouzapw/OmniRoute/pull/8954), [#8991](https://github.com/diegosouzapw/OmniRoute/pull/8991), [#9059](https://github.com/diegosouzapw/OmniRoute/pull/9059), [#9194](https://github.com/diegosouzapw/OmniRoute/pull/9194), [#9258](https://github.com/diegosouzapw/OmniRoute/pull/9258), [#9508](https://github.com/diegosouzapw/OmniRoute/pull/9508))
- **main-branch plumbing (rollup):** work that landed on `main` between cycles and was carried into this one — the Mergify merge-queue migration and tuning (#7168, #7179, #7216, #7220, #7225), npm-publish unblock via dynamic runner + CI build reuse (#8941), CodeQL-driven e2e mock hardening (#7559), hermetic self-ref guard (#6634, #7341), coverage-baseline tightening (#7347), Dependabot alert resolutions via npm overrides (#8067, #8070), README flag/doc-link polish (#8317), and the v3.8.49 release plumbing itself (#7076)
- **deps:** bump the development group across 1 directory with 22 updates ([#10043](https://github.com/diegosouzapw/OmniRoute/pull/10043)) — thanks @app/dependabot
- **deps:** bump electron from 43.2.0 to 43.3.0 in /electron ([#10042](https://github.com/diegosouzapw/OmniRoute/pull/10042)) — thanks @app/dependabot
- **maint(release):** 45 direct pushes to the release branch with no PR ref — base-red and quality-gate repairs, i18n string completion and stream/type fixes (quality ×6, i18n ×5, deps ×3, agentrouter ×3, providers ×2, release ×2, security ×2, logging ×2)
<img src="./docs/diagrams/promise-pillars.svg" width="100%" alt="The Promise — One endpoint. 339 providers. Never stop building — OmniRoute picks the cheapest one that works. Six pillars: Never hit limits (auto-fallback across 339 providers in milliseconds, zero downtime) · Save up to 95% tokens (RTK + Caveman stacked compression cuts 15–95%, ~89% avg on tool-heavy sessions) · $0 to start (90+ free tiers, 40+ free forever — no card needed) · Every tool works (33 coding agents through one config) · One endpoint (OpenAI ↔ Claude ↔ Gemini ↔ Responses API at /v1) · Production-grade (circuit breakers, TLS stealth, MCP 105 tools, A2A, memory, guardrails, evals — 25,000+ tests)."/>
<img src="./docs/diagrams/promise-pillars.svg" width="100%" alt="The Promise — One endpoint. 341 providers. Never stop building — OmniRoute picks the cheapest one that works. Six pillars: Never hit limits (auto-fallback across 341 providers in milliseconds, zero downtime) · Save up to 95% tokens (RTK + Caveman stacked compression cuts 15–95%, ~89% avg on tool-heavy sessions) · $0 to start (90+ free tiers, 56 free forever — no card needed) · Every tool works (33 coding agents through one config) · One endpoint (OpenAI ↔ Claude ↔ Gemini ↔ Responses API at /v1) · Production-grade (circuit breakers, TLS stealth, MCP 109 tools, A2A, memory, guardrails, evals — 25,000+ tests)."/>
<br/>
<br/>
@@ -449,7 +449,7 @@ All **19** strategies — mix & match per combo step:
### 🧱 Resilience is built in (3 independent layers)
<img src="./docs/diagrams/resilience-layers.svg" width="100%" alt="OmniRoute resilience — 3 independent self-healing layers, the right layer for the right failure. Layer 1 provider circuit breaker (whole provider): trips only on 408/5xx, thresholds OAuth 3× / API-key 5× / local 2×, resets 60s/30s/15s into a HALF-OPEN probe, lazy recovery; while OPEN the combo reroutes to the next provider. Layer 2 connection cooldown (one key/account): base 5s OAuth / 3s API-key, exponential ×2 backoff with anti-thundering-herd guard, 429 honors Retry-After, success clears all error state; one cooling key is skipped while sibling keys keep serving. Layer 3 model lockout (one model): per-model 429, local 404 or mode denials lock just that model — never the whole connection. Terminal states (banned, expired, credits exhausted) are for the operator, not cooldowns."/>
<img src="./docs/diagrams/resilience-layers.svg" width="100%" alt="OmniRoute resilience — 3 independent self-healing layers, the right layer for the right failure. Layer 1 provider circuit breaker (whole provider): trips only on 408/5xx, thresholds OAuth 10× / API-key 15× / local 2×, resets 60s/30s/15s into a HALF-OPEN probe, lazy recovery; while OPEN the combo reroutes to the next provider. Layer 2 connection cooldown (one key/account): base 5s OAuth / 3s API-key, exponential ×2 backoff with anti-thundering-herd guard, 429 honors Retry-After, success clears all error state; one cooling key is skipped while sibling keys keep serving. Layer 3 model lockout (one model): per-model 429, local 404 or mode denials lock just that model — never the whole connection. Terminal states (banned, expired, credits exhausted) are for the operator, not cooldowns."/>
@@ -461,7 +461,7 @@ All **19** strategies — mix & match per combo step:
</div>
<img src="./docs/diagrams/comparison-table.svg" width="100%" alt="What sets OmniRoute apart — comparison table vs 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute: 339 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, built-in MCP server with 105 tools, A2A agent protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, Desktop/Termux/PWA, 43 i18n UI locales, 100% MIT self-hosted. OmniRoute is the only one with the full set; competitors show a mix of checks, partials and crosses. Verified from each project's docs."/>
<img src="./docs/diagrams/comparison-table.svg" width="100%" alt="What sets OmniRoute apart — comparison table vs 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute: 341 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, built-in MCP server with 109 tools, A2A agent protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, Desktop/Termux/PWA, 43 i18n UI locales, 100% MIT self-hosted. OmniRoute is the only one with the full set; competitors show a mix of checks, partials and crosses. Verified from each project's docs."/>
<sub>📊 Full methodology & per-feature detail vs 9router, OpenRouter, CLIProxyAPI & LiteLLM → [`docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md`](docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md)</sub>
@@ -513,6 +513,27 @@ Pix copia-e-cola:
<br/>
<p><strong>Developer notes:</strong> The project may generate a local <code>.env</code> file during npm install/postinstall for developer convenience. This file is intentionally ignored via <code>.gitignore</code> (see <code>.gitignore</code>) and must never be committed — if accidentally committed, rotate any exposed secrets and remove the file from history. See <a href="docs/DEVELOPER-ENVIRONMENT.md">docs/DEVELOPER-ENVIRONMENT.md</a> for guidance on managing local environment files and secrets.</p>
## 📡 OmniRoute Radar
The main free-tier headline remains **~1.53B tokens/month** from the documented,
pool-deduplicated catalog above. Temporary provider signup credits can separately lift the first
month to **~2.15B**. Radar is an optional, signed catalog overlay for people who want fresher
free-model availability between OmniRoute releases; the community catalog and every existing free
feature remain free.
Supporters can receive the live catalog and additional provider opportunities. Its separate,
mutable ceiling is **approximately 3B tokens/month at most**, depending on provider availability.
That ceiling is not a guarantee: providers can change quotas, eligibility, models, or regions at
any time.
Radar is opt-in and GET-only. The OmniRoute client does not upload prompts, traffic, provider
configuration, usage telemetry, or local announcement-dismiss state. Learn about eligibility and
the current catalog at **[radar.omniroute.online/planos](https://radar.omniroute.online/planos)**.
<br/>
<div align="center">
## ✨ What's New
@@ -538,7 +559,7 @@ Pix copia-e-cola:
- **🖼️ New endpoints** — `/v1/ocr` (Mistral OCR) and `/v1/audio/translations` (Whisper-style) round out the media surface. → [API Reference](docs/reference/API_REFERENCE.md)
- **🎨 Image / video / audio generation** — one API for media: xAI Grok Imagine & Novita AI video, ComfyUI, Freepik, Adobe Firefly, Microsoft Designer, Google Imagen, Segmind, EdgeTTS. → [API Reference](docs/reference/API_REFERENCE.md)
- **🤝 More providers & agents** — Cursor Cloud Agent, Grok Build (xAI) with browser + OAuth login, Ollama first-class card, Claude Opus 5 & Sonnet 5, Kimi official partnership (Code/Web/Moonshot), Zed, Requesty, SenseNova, Yuanbao, Agnes AI… and a refreshed **339-provider catalog**. → [Providers](docs/reference/PROVIDER_REFERENCE.md)
- **🤝 More providers & agents** — Cursor Cloud Agent, Grok Build (xAI) with browser + OAuth login, Ollama first-class card, Claude Opus 5 & Sonnet 5, Kimi official partnership (Code/Web/Moonshot), Zed, Requesty, SenseNova, Yuanbao, Agnes AI… and a refreshed **341-provider catalog**. → [Providers](docs/reference/PROVIDER_REFERENCE.md)
- **📡 Routing transparency** — every response carries an `X-OmniRoute-Decision` header naming the strategy/provider/latency that served it, a new `cache-optimized` combo strategy + Auto-Combo `cacheAffinity` factor route repeat requests back to the connection holding the cached prefix, and a read-only `/v1/auto-combo/{channel}/candidates` endpoint exposes an `auto/*` channel's live candidate pool. → [Auto-Combo](docs/routing/AUTO-COMBO.md)
- **⚡ Local performance & infra** — one-click local Redis, Cloudflare Workers / Deno Deploy relay deployers, Bifrost & Mux as supervised embedded services. → [Embedded Services](docs/frameworks/EMBEDDED-SERVICES.md)
@@ -591,7 +612,7 @@ Pix copia-e-cola:
<b>＋ also works with</b> · Kiro · Command Code · Antigravity · Windsurf · AMP · <b>any OpenAI-compatible tool</b>
> The most complete catalog of any open-source router: **339 providers**, **90+ with a free tier**, **40+ free forever**.
> The most complete catalog of any open-source router: **341 providers**, **90+ with a free tier**, **56 free forever**.
<div align="center">
@@ -683,6 +704,7 @@ Pix copia-e-cola:
<tr><td align="left" nowrap>📱 <b>Android (Termux)</b></td><td align="left" nowrap><code>pkg install nodejs && npx -y omniroute</code></td><td align="left">Runs <b>on your phone</b>, 24/7, no root</td></tr>
<tr><td align="left" nowrap>📲 <b>PWA</b></td><td align="left" nowrap>"Add to Home Screen"</td><td align="left">Fullscreen, offline, installable from browser</td></tr>
> 🎬 **Made a video about OmniRoute?** Open an [issue](https://github.com/diegosouzapw/OmniRoute/issues/new) or [discussion](https://github.com/diegosouzapw/OmniRoute/discussions) with the link — we'll feature it here.
<br/>
</div>
<div align="center">
@@ -1061,7 +1148,7 @@ same process on one port, so there is no separate CLI-only package today.
<tr><td nowrap><b>Language</b></td><td>TypeScript 6.0 — <b>100% TypeScript</b> across <code>src/</code> and <code>open-sse/</code> (zero <code>any</code> in core since v2.0)</td></tr>
@@ -242,7 +242,7 @@ function generateFishScript() {
return`# OmniRoute CLI fish completion (dynamic)
complete -c omniroute -f
set -l commands serve stop restart setup doctor status logs providers config keys models combo chat stream completion dashboard open backup restore health quota cache mcp a2a tunnel env memory skills update test
set -l commands serve stop restart setup doctor status logs providers config keys models combo chat stream completion dashboard open backup restore health quota cache mcp a2a tunnel env memory skills update test run
for cmd in $commands
complete -c omniroute -n '__fish_is_nth_token 1' -a $cmd
- **feat(cli):** container-aware auto-config — `setup-*`, `omniroute configure`, `omniroute config set` and the CLI-tool config APIs now refuse to write into a containerised OmniRoute's ephemeral home (CLI exits `2`, API returns `422` with `containerEphemeralTarget`) and point at the host-CLI or bind-mount setup instead; `--allow-container-write` / `OMNIROUTE_ALLOW_CONTAINER_CONFIG_WRITE=true` opt back in. Also fixes `CLI_CONFIG_HOME` so the Compose `host` profile's `/host-home` bind mounts are honoured instead of silently falling back to the container home. (#10057)
- feat(modality-bridge): bridge Chat and Responses video parts through a strict trusted-loopback, quota-bounded FFmpeg broker; enforce HTTPS redirects/SSRF plus format, protocol, stream, pixel, frame, 50 MiB broker/remote, 36 MiB inline, and 120-second limits; propagate caller aborts; preserve the actual successful fallback model through cache/meta/headers; expose sampled latency and honest success telemetry; and ship the localized Video settings UI (#9760)
- **feat(radar):** Persist local model display-name/enabled overrides and hide/restore tombstones, with authenticated catalog controls and feed safety precedence ([#9830](https://github.com/diegosouzapw/OmniRoute/pull/9830))
- **feat(radar):** add signed Intel insights, supporter recognition, and local Radar CLI commands ([#9923](https://github.com/diegosouzapw/OmniRoute/pull/9923))
- **feat(radar):** add a localized public news feed and dismissible dashboard launch banner, with the Radar announcement staged inactive for a separately authorized launch ([#9926](https://github.com/diegosouzapw/OmniRoute/pull/9926))
- **fix(oauth):** Claude connections created via `claude-auth/import` now send required CLI headers on the bootstrap identity call and persist a `cliUserID` device identity, fixing intermittent "Third-party apps now draw from your extra usage" 400s on otherwise valid imported subscription tokens ([#10144](https://github.com/diegosouzapw/OmniRoute/pull/10144), fixes [#10143](https://github.com/diegosouzapw/OmniRoute/issues/10143))
- **fix(cursor):** Stop truncating pending tool calls on non-composer models when a KV checkpoint arrives after text but before the `exec_mcp` frame — the KV short-circuit is now gated to the composer family where it was verified ([#10215](https://github.com/diegosouzapw/OmniRoute/issues/10215)).
- **fix(responses):** repair corrupted SSE deltas for non-ASCII streams by keeping a single stream-aware `TextDecoder` (`{ stream: true }`) across `transform()` calls instead of recreating it per chunk and decoding without the `stream` flag. When a multi-byte UTF-8 character (CJK/emoji) was split across two TCP chunks — common in Chinese streaming text — the per-chunk decoder truncated it to `U+FFFD`, corrupting every delta while the rebuilt `*.done` snapshot stayed internally identical ([#10223](https://github.com/diegosouzapw/OmniRoute/issues/10223))
- **fix(providers):** FreeAIAPIKey now targets `api.freeaiapikey.com`, the host upstream names in its `410 endpoint_moved` response — every request through the provider was failing — and its catalog is resynced to the 10 models the live `/v1/models` actually serves ([#10233](https://github.com/diegosouzapw/OmniRoute/pull/10233))
- **fix(providers):** MonsterAPI's deprecation now actually applies — the flag was written as `isDeprecated`, a key no consumer or schema reads, so the provider kept rendering as healthy in the dashboard, the onboarding wizard and the generated provider reference ([#10234](https://github.com/diegosouzapw/OmniRoute/pull/10234))
- **fix(providers):** preserve validator HTTP status codes in API-key and web connection-test results so callers can distinguish authentication, rate-limit, and upstream failures ([#10272](https://github.com/diegosouzapw/OmniRoute/pull/10272)) — thanks @Zartharas
- **fix(sse):** tiny-budget reasoning probes (e.g. Claude Code's `/model` check sends `max_tokens: 1`) are answered with a valid truncated 200 instead of relaying the upstream 5xx "empty response content" — which previously also marked the connection unavailable and poisoned fallback/cooldown bookkeeping for a request that is only a probe ([#10281](https://github.com/diegosouzapw/OmniRoute/issues/10281)) — thanks @harkaranbrar7
- **fix(build):** stop Turbopack from dead-code-eliminating the Windows Tailscale branches of `src/lib/tailscaleTunnel.ts` in the published build (#10293). The release `dist` is bundled on a Linux runner, and the bundler constant-folds `process.platform`, pruning every non-Linux branch — the Windows installers shipped with no `where` lookup, an always-injected `--socket`, and a lost `net start Tailscale`/windows-default-binary path. The module now reads the platform at runtime via `os.platform()` (a function call a bundler cannot fold), so the Windows branches survive on any build machine; a vitest regression test mocking `os.platform()` → `win32` guards the anti-fold invariant (RED before, GREEN after).
- **fix(chat-body-admission):** restore a single process-wide admission budget — heavyweight leases and queued bytes are now bounded once for the whole process instead of per session, so one session can no longer mint extra capacity or starve others; per-session fairness is preserved via round-robin dispatch ([#10110](https://github.com/diegosouzapw/OmniRoute/issues/10110))
- **fix(providers):** validate Z.ai web Local Storage sessions against the authenticated user-settings endpoint and preserve exact upstream status codes ([#10329](https://github.com/diegosouzapw/OmniRoute/pull/10329)) — thanks @Zartharas
- **fix(db):** `getSettings()` defaults `debugMode` to `false` — fresh installs no longer run in debug mode (persisted `debugMode: true` is preserved) ([#10372](https://github.com/diegosouzapw/OmniRoute/pull/10372) — thanks @lamchun1110)
- **fix(executors):** OpencodeExecutor and MimocodeExecutor now rotate to the next account on network exceptions (timeout, connection refused/reset) when the failed account has a dedicated proxy, not only on 429 — a throw on one account no longer fails the whole request when other accounts remain. Accounts sharing the default egress (no proxy) fail fast instead of retrying the same outage against every account. The shared rotation mechanics (`pickAccount`/`markCooldown`/`markSuccess`) are now extracted into `accountRotation.ts`, fixing an identical unconditional-cooldown gap that pre-dated this PR in MimocodeExecutor ([#10393](https://github.com/diegosouzapw/OmniRoute/pull/10393))
- **fix(sse):** the header-budget drop warning fires once per unique dropped-header set instead of on every SSE response (warn-storm fix) ([#10397](https://github.com/diegosouzapw/OmniRoute/pull/10397) — thanks @lamchun1110)
- **fix(guardrails):** Vision Bridge now reroutes whole requests for named combos whose targets have zero vision-capable models (previously such image requests died with `capability_mismatch` when the describe path could not run), and when the fallback describe path also fails for every image the request degrades to explicit `(unavailable)` stub text instead of preserving images the combo cannot consume ([#10415](https://github.com/diegosouzapw/OmniRoute/pull/10415)) — thanks @rqzbeh
- **fix(antigravity):** geo-blocked egress (Google "User location is not supported") is now classified (scoped to the Google AI surfaces that emit it: Cloud Code/Gemini Code Assist, Gemini API, Vertex), cached as a 24h per-account exclusion so routing continues with other accounts, and surfaced with an actionable message; the dashboard connection test now probes the real `streamGenerateContent` model surface instead of the non-geo-restricted OAuth userinfo endpoint ([#10420](https://github.com/diegosouzapw/OmniRoute/pull/10420)) — thanks @rqzbeh
- **fix(antigravity):** strip competing-agent identity sentences from system prompts (e.g. "You are a Claude agent, built on Anthropic's Claude Agent SDK.") that Antigravity flags and answers with 429 RESOURCE_EXHAUSTED (port of decolua/9router b566b20) ([#10420](https://github.com/diegosouzapw/OmniRoute/pull/10420)) — thanks @rqzbeh
- **fix(antigravity):** accounts with an empty Cloud Code `projectId` now heal themselves — failed auto-onboarding (`onboardUser`) attempts are retried after a short backoff instead of being memoized forever, so the missing Google project is created without user action on a later request or token refresh ([#10424](https://github.com/diegosouzapw/OmniRoute/pull/10424)) — thanks @rqzbeh
- **fix(antigravity):** Google deprecated automatic project creation for standard-tier (personal) accounts — when `onboardUser` completes without a project id the account now fails fast with a clear `403 GCP_PROJECT_REQUIRED` message (no more generic 422 or delayed 429 RESOURCE_EXHAUSTED), and a manual GCP Project ID override is available in the connection editor so operators can enter their own project id ([#10424](https://github.com/diegosouzapw/OmniRoute/pull/10424)) — thanks @rqzbeh
- **fix(usage):** read Gemini `usageMetadata` out of the antigravity `{ response: {...} }` envelope so non-streaming requests log real token usage instead of `IN 0 | OUT 0` (port of decolua/9router#59d858b) ([#10430](https://github.com/diegosouzapw/OmniRoute/pull/10430)) — thanks @rqzbeh
- **fix(usage):** surface Gemini `cachedContentTokenCount` into `cached_tokens` for non-streaming requests so cache-hit accounting matches the OpenAI/Claude/Responses branches and the streaming path (follow-up to the #10430 envelope fix) ([#10465](https://github.com/diegosouzapw/OmniRoute/pull/10465)) — thanks @rqzbeh
- **fix(docker):** point the bifrost sidecar at the real `ghcr.io/maximhq/bifrost:v1.6.11` tag and the cliproxyapi sidecar at the official `docker.io/eceasy/cli-proxy-api:v6.9.7` image (the previously pinned tags never existed), and complete the runtime `OMNIROUTE_BASE_PATH` subpath patch for Next 16 standalone (assetPrefix + client env + baked asset URLs) so prebuilt images respect the webpath env var ([#10482](https://github.com/diegosouzapw/OmniRoute/pull/10482))
- **fix(providers):** allow token-backed web sessions stored with `authType: "cookie"` to refresh their token through the provider update API ([#10518](https://github.com/diegosouzapw/OmniRoute/pull/10518)) — thanks @Zartharas
- **fix(cli):** ignore the operating system `HOSTNAME` when choosing the server bind address on Linux and macOS, preventing startup failures when the shell hostname differs from `os.hostname()`; use `OMNIROUTE_SERVER_HOST` for explicit non-Windows configuration while preserving the legacy `HOSTNAME` fallback on Windows ([#10557](https://github.com/diegosouzapw/OmniRoute/pull/10557), closes [#10492](https://github.com/diegosouzapw/OmniRoute/issues/10492)) — thanks @redzrush101
- fix(dashboard): media mini-playgrounds authenticate via session instead of sending the masked API key as Bearer, fixing 401s under REQUIRE_API_KEY (#9935)
- **fix(api-manager):** Allowed Combos can now be restricted to zero entries: **All** is stored explicitly as `combo/*`, while **Restrict** with no selection saves an empty allowlist that denies Combo routes without blocking direct models. Existing keys are migrated to preserve their previous allow-all behavior.
- fix(ci): make `Build (advisory)` produce a signal again — pinned to a hosted runner with the swap/heap provisioning `Fast Production Build` proves sufficient, and scoped to fork PRs, which are the only ones `build.yml` cannot cover (72 of the last 100 PRs into `release/**`)
- **fix(api):** hash API keys in the `/v1/models` catalog cache Map key so heap dumps cannot leak bearer tokens (`src/app/api/v1/models/catalogCache.ts`)
- **fix(db):** the `compression_run_telemetry` retention sweep now actually deletes expired rows. Its cutoff was computed in epoch seconds while the column stores epoch milliseconds, so `WHERE timestamp < cutoff` never matched and the table added by #6848 to bound `storage.sqlite` growth was unbounded in practice. Same unit mismatch as #9625, which corrected the sibling `domain_cost_history` sweep and missed this call site
- **fix(db):** database settings API no longer returns HTTP 500 on SQLite builds compiled without the optional `dbstat` virtual table (sql.js/WASM); per-table sizes degrade to 0 instead of failing the whole stats call
- **fix(ops):** Docker HEALTHCHECK probes lightweight `/healthz` instead of `/api/monitoring/health` so a busy event loop does not mark the container Unhealthy (`scripts/dev/healthcheck.mjs`)
- **fix(sse):** keep Codex/Anthropic quota headers under the upstream forwarding budget; drop `x-codex-turn-state` and raise the 768-byte cap (`open-sse/handlers/chatCore/responseHeaders.ts`)
- **fix(models):** honor `MODELS_DEV_SYNC_ENABLED=0` as a hard kill switch over the dashboard setting so a wedged `/healthz` / UI can be recovered without HTTP (`src/lib/modelsDevSync.ts`)
- **fix(db):** the sql.js fallback now publishes the database atomically — temp file in the same directory, `fsync`, then `rename()` — instead of rewriting it in place with `writeFileSync`. sql.js has no incremental write path, so every save rewrote the whole image through an `O_TRUNC` open: for the duration of the write the on-disk database was 0 bytes and then partial, a window that scales with database size and recurs on every save. Unlike better-sqlite3 / node:sqlite, that window is not covered by SQLite's locking protocol, so it was visible to every OTHER process reading the same file (a backup job, a metrics exporter, an operator running `sqlite3`), which got `SQLITE_CORRUPT` — "database disk image is malformed" — while `PRAGMA integrity_check` passed moments later. It also closes a total-loss window: a crash mid-write used to leave the real database truncated, and now only leaves a stale temp file
- **chore(release):** resync the v3.8.50 provider and CLI catalogs, register the existing ChatCore mutation-coverage test, and document the local ZCode handshake identifier so the release quality gates reflect the current tree without changing ratchet baselines.
- **chore(release):** synchronize migration-count documentation and document the opt-in `PROXY_LOG_INCLUDE_IPS` logging flag so the v3.8.50 quality gates match the release tree.
This page explains the project's local `.env` behavior and how to handle environment files and secrets when developing OmniRoute.
## .env postinstall behavior
The project may generate a local `.env` file during `npm install` / `postinstall` for developer convenience. This file is intended only for local development and testing and must never be committed to version control.
Key points:
- The repository's `.gitignore` already ignores `.env*` files (see the `.gitignore` entry). Do not remove or alter that rule unless you deliberately intend to commit a specific example file and have a documented process for it.
- If a real secret is accidentally committed to the repo, rotate/revoke the credential immediately and remove it from the repository history (for example, using `git filter-repo` or an equivalent remediation workflow). Contact the security/contact owner if you need help.
- For CI and production, use the CI secrets or a secrets manager (GitHub Actions Secrets, Azure Key Vault, HashiCorp Vault, etc.) rather than committing secrets to files.
## Recommended local workflow
- Keep `.env` in your local workspace only. Use `.env.example` (already tracked) to document required variables and acceptable example values.
- When running tests locally that require secret-like values, prefer synthetic placeholders or runtime-generated ephemeral keys rather than real credentials.
- Add a short comment in tests that use placeholders so reviewers understand the fixture is synthetic.
## Scanner notes
- Some compiled or binary assets (e.g., embedded base64 WASM blobs) can contain ASCII substrings that look like credentials and may trigger text-based secret scanners. If these assets are legitimate, either mark them in the scanner's allowlist or exclude the directories in the scanner config.
## If you find a leak
1. Rotate/revoke the key immediately.
2. Remove the secret from the history and force-push a cleaned branch if necessary.
3. Notify maintainers and follow your org's incident response checklist.
| `memory/reindex.ts` | `runReindexBatch()` — processes memories with `needs_reindex=1` in background; called by `POST /api/memory/reindex` and lazy-backfill path. (plan 21) |
| `monitoring/` | Health checks, metrics emission |
**Activation:** set `BIFROST_BASE_URL=http://bifrost:8080` in `.env.example`. The existing sidecar proxy route at [`src/app/api/v1/relay/chat/completions/bifrost/route.ts`](../../src/app/api/v1/relay/chat/completions/bifrost/route.ts) (added in PR #4381) will pick this up automatically.
<svgviewBox="0 0 1200 350"xmlns="http://www.w3.org/2000/svg"role="img"aria-label="Animated terminal demoing the OmniRoute CLI: omniroute providers list (339 providers registered, anthropic, codex, glm, kimi shown active), omniroute combo list (always-on priority, cost-saver, fusion-panel, context-relay) and omniroute health (healthy, 18412 requests in 24h, p95 412ms, circuit breakers 24 closed, 1 half-open, 0 open), cycling over the 80+ command surface: providers, oauth, keys, combo, nodes, models, cache, compression, cost, usage, quota, health, resilience, telemetry, logs, audit, mcp, a2a, cloud, memory, skills, eval, doctor, repl, tunnel, backup, sync, webhooks, policy, pricing, translator, simulate and more.">
<svgviewBox="0 0 1200 350"xmlns="http://www.w3.org/2000/svg"role="img"aria-label="Animated terminal demoing the OmniRoute CLI: omniroute providers list (341 providers registered, anthropic, codex, glm, kimi shown active), omniroute combo list (always-on priority, cost-saver, fusion-panel, context-relay) and omniroute health (healthy, 18412 requests in 24h, p95 412ms, circuit breakers 24 closed, 1 half-open, 0 open), cycling over the 80+ command surface: providers, oauth, keys, combo, nodes, models, cache, compression, cost, usage, quota, health, resilience, telemetry, logs, audit, mcp, a2a, cloud, memory, skills, eval, doctor, repl, tunnel, backup, sync, webhooks, policy, pricing, translator, simulate and more.">
<desc>Compact animated terminal cycling three real OmniRoute CLI commands with a typewriter effect and a scrolling subcommand ticker; the first frame shows the completed providers-list screen.</desc>
<svgviewBox="0 0 1200 780"xmlns="http://www.w3.org/2000/svg"role="img"aria-label="Comparison table: OmniRoute versus 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute is the only one with the full set: 339 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, a built-in MCP server with 105 tools, A2A protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, desktop/Termux/PWA, 43 UI locales and 100% MIT self-hosted. 9router has free providers, RTK compression and translation but no MCP, A2A, memory, guardrails, cloud agents or stealth. OpenRouter is a hosted SaaS with 400+ models, guardrails and a hosted MCP but is not self-hosted and lacks A2A, memory, cloud agents and stealth. CLIProxyAPI is a light OAuth proxy with two routing strategies. LiteLLM has 100+ providers, A2A and extensive guardrails but no memory, compression, free tier, stealth or cloud agents.">
<svgviewBox="0 0 1200 780"xmlns="http://www.w3.org/2000/svg"role="img"aria-label="Comparison table: OmniRoute versus 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute is the only one with the full set: 341 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, a built-in MCP server with 109 tools, A2A protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, desktop/Termux/PWA, 43 UI locales and 100% MIT self-hosted. 9router has free providers, RTK compression and translation but no MCP, A2A, memory, guardrails, cloud agents or stealth. OpenRouter is a hosted SaaS with 400+ models, guardrails and a hosted MCP but is not self-hosted and lacks A2A, memory, cloud agents and stealth. CLIProxyAPI is a light OAuth proxy with two routing strategies. LiteLLM has 100+ providers, A2A and extensive guardrails but no memory, compression, free tier, stealth or cloud agents.">
<desc>Static-header comparison table where each capability row fades in top to bottom; the OmniRoute column is highlighted and shows a check or a leading value in every row, while competitors show a mix of checks, partials and crosses.</desc>
<defs>
<patternid="gC"width="32"height="32"patternUnits="userSpaceOnUse"><pathd="M 32 0 L 0 0 0 32"fill="none"stroke="#ffffff"stroke-opacity="0.05"stroke-width="1"/></pattern>
<svgviewBox="0 0 1200 540"xmlns="http://www.w3.org/2000/svg"role="img"aria-label="The OmniRoute promise: one endpoint, 339 providers — never stop building, OmniRoute picks the cheapest one that works. Six pillars. Never hit limits: auto-fallback across 339 providers in milliseconds, quota out means the next provider takes over with zero downtime. Save up to 95 percent of tokens: RTK plus Caveman stacked compression cuts 15 to 95 percent of eligible tokens, about 89 percent average on tool-heavy sessions. Zero dollars to start: 90+ providers with a free tier, 40+ free forever — Qoder, Pollinations, Cloudflare, SiliconFlow — no card needed. Every tool works: 33 coding agents including Claude Code, Codex, Cursor, Cline, Copilot and Antigravity through one config. One endpoint: OpenAI, Claude, Gemini and Responses API translation — point any tool at /v1 and it just works. Production-grade: circuit breakers, TLS stealth, MCP with 105 tools, A2A, memory, guardrails, evals — 25,000+ tests.">
<svgviewBox="0 0 1200 540"xmlns="http://www.w3.org/2000/svg"role="img"aria-label="The OmniRoute promise: one endpoint, 341 providers — never stop building, OmniRoute picks the cheapest one that works. Six pillars. Never hit limits: auto-fallback across 341 providers in milliseconds, quota out means the next provider takes over with zero downtime. Save up to 95 percent of tokens: RTK plus Caveman stacked compression cuts 15 to 95 percent of eligible tokens, about 89 percent average on tool-heavy sessions. Zero dollars to start: 90+ providers with a free tier, 56 free forever — Qoder, Pollinations, Cloudflare, SiliconFlow — no card needed. Every tool works: 33 coding agents including Claude Code, Codex, Cursor, Cline, Copilot and Antigravity through one config. One endpoint: OpenAI, Claude, Gemini and Responses API translation — point any tool at /v1 and it just works. Production-grade: circuit breakers, TLS stealth, MCP with 109 tools, A2A, memory, guardrails, evals — 25,000+ tests.">
<desc>Animated promise card: six pillar tiles fade in in reading order, then a soft colored border highlight sweeps from tile to tile in a continuous cycle.</desc>
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
