* 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(oauth): route Zed hosted sign-in callback back to the dashboard port
Zed's native-app sign-in always redirects the browser to the loopback port
sent as native_app_port (hardcoded default 58443), where nothing listens:
the browser shows "site can't be reached" and the login looks broken even
though the token is in the URL. The manual paste fallback was broken too -
handleManualSubmit requires a ?code= param that Zed's callback
(user_id + access_token) never carries, so the flow could never complete.
- zed-hosted: derive native_app_port from the dashboard's own loopback
port so the redirect lands back on OmniRoute; remote/LAN origins keep
the old default port and the paste flow
- app root: forward ?user_id=...&access_token=... to the /callback relay
instead of dropping the query string on the /dashboard redirect
- /callback relay: recognize the Zed payload (no code param) and relay the
full URL as the exchange payload; allow postMessage to both loopback
spellings (localhost/127.0.0.1) of the same port
- OAuthModal: zed-hosted popup auto-completes on true localhost; the
manual paste path passes the full URL through to the exchange instead
of erroring with "No authorization code found"
- manual input panel: zed-hosted-specific placeholder and hint
- tests: extend the postMessage scope guard with the loopback same-port
trusted origins
* changelog: fragment for #10517
* fix(oauth): derive Zed native_app_port from server config, not browser scheme/port
resolveDashboardLoopbackPort() previously re-derived the dashboard's loopback
port from the browser-supplied redirectUri (window.location.port ||
protocol === "https:" ? "443" : "80"), which produced http://127.0.0.1:443/
native-app redirects when the dashboard was reached over HTTPS on its
implicit default port (e.g. behind a local TLS-terminating reverse proxy) -
a scheme/port mismatch, since Zed's own redirect is always plain http and
nothing serves plain HTTP on 443 in that scenario.
This code runs server-side (in the OAuth authorize API route), so once the
redirect URI's hostname is confirmed loopback it now uses the OmniRoute
process's own authoritative listening port via getRuntimePorts()
(OMNIROUTE_PORT/PORT/DASHBOARD_PORT) instead of re-deriving it from the
browser-observed scheme/port. Non-loopback (remote/LAN) redirect URIs still
return null and fall back to the manual paste flow.
Adds tests/unit/zed-hosted-loopback-port-derivation.test.ts (8 cases)
covering the port-derivation logic directly, including the HTTPS-default-port
mismatch scenario that motivated this fix, env-var precedence, IPv6 loopback,
non-loopback/remote fallback, and buildAuthUrl's native_app_port wiring.
Also rebaselines config/quality/file-size-baseline.json for OAuthModal.tsx's
own growth from this PR's earlier commit (1134->1149 gate units) - legitimate
zed-hosted callback wiring at the existing provider-switch chokepoint, not
extractable without a broader modal decomposition (tracked in #3501).
The live Zed OAuth handshake itself (root -> /callback -> OAuthModal exchange
against the real zed.dev endpoint) still needs a documented VPS smoke test
per Hard Rule #18; this fix covers the TDD-able port-derivation logic that
motivated the change.
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 <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>
Two independently-merged PRs (#10263 agentic-conversation-tracking-v4
and #10362 exclusive-managed-session-leases) each picked migration
slot 155 against different base states, landing a real collision on
release/v3.8.50 (155_agentic_conversations.sql vs
155_exclusive_connection_leases.sql; #10263 also claimed 156 via
156_conversation_turn_nodes.sql). Renumbered #10362's migration to the
next free slot (157) and updated its own regression test
(exclusive-connection-leases.test.ts) that asserted the literal
filename/slot. No retroactive guard needed: CREATE TABLE IF NOT
EXISTS is idempotent under either number.
Confirmed via check-migration-numbering.mjs (154 migrations, 0
duplicates) and the full exclusive-connection-leases test suite
(11/11 pass).
- README: 'run any supported CLI in one command' block (7 targets incl. gemini),
updated one-command setup bullet with run/configure
- CLI-INTEGRATIONS: gemini in the master table + run examples + base-URL row
(GOOGLE_GEMINI_BASE_URL → /v1beta), opt-in smoke sweep section
- REMOTE-MODE: 'launching a CLI against the remote' section (run + contexts)
- CLI-TOOLS: gemini install step in Quick Start
- ENVIRONMENT/.env.example: CLI_AIDER_BIN, CLI_GOOSE_BIN, CLI_GEMINI_BIN
- API_REFERENCE: apply endpoint row documents dryRun/422/migration contract
- smoke harness fixes proven against a live local OmniRoute: node:test treats
timeout:0 as 'time out immediately' (sized budget from the per-target cap),
and resolve on child 'exit' instead of 'close' so grandchildren holding the
stdio pipes cannot hang a target (qwen was blocked 431s past its 120s cap).
Live evidence: gemini exit=0 pass via /v1beta against localhost; all four
installed CLIs (codex/opencode/qwen/gemini) reached the upstream end-to-end
with correctly classified upstream errors (free-tier 429 / ddgw 400).
* feat(providers): add Cloudflare AI Playground as No Auth provider (closes#10389)
Reverse-engineered access to the free, anonymous Cloudflare AI Playground:
chat runs over a PartySocket WebSocket speaking Cloudflare's cf_agent RPC
protocol with zero credentials (no account, no API key, no cookies). The
WS upgrade is gated on a browser-grade TLS fingerprint, so the executor
drives a headless Chromium via Playwright and speaks the protocol from
inside the page context.
- registry entry: cloudflare-playground (alias cfp), authType none,
curated 20-model catalog (GLM 5.2, Kimi K2.7 Code, DeepSeek V4 Pro,
gpt-oss-120B, Llama 3.3 70B, Qwen2.5 Coder 32B, ...) captured from the
live getModels RPC (2026-08-15)
- executor: cf_agent frame stream -> OpenAI SSE translation, id-filtered
parser (RPC done:true frames cannot kill the stream), in-band upstream
errors mapped to HTTP 429/502, abort + timeout handling, clean errors
- noauth UI entry with reverse-engineered-endpoint notice
- tests: 12 unit tests using real captured frames (incl. the 3021
rate-limit error) + fake transport; ESLint clean; open-sse typecheck clean
* fix(providers): define __name helper in page context before evaluate
Bundlers with keepNames (esbuild/tsx, webpack) inject a __name() call into
serialized function bodies. page.evaluate(openPlaygroundSession) therefore
threw ReferenceError: __name is not defined in real browser sessions.
Define the helper on window before evaluating the session opener.
* fix(providers): sync docs counts, golden snapshots and add reasoning_content support for cloudflare-playground
* chore: remove ad-hoc cfp-shim debug script per review feedback
The standalone shim duplicated the executor's frame-parsing and transport
logic and is superseded by open-sse/executors/cloudflare-playground.ts.
Requested in PR #10442 review.
* feat(gemini-web): expose image generation through /v1/images/generations (closes#10466)
Adds a gemini-web image-generation path following the chatgpt-web precedent:
- imageRegistry: gemini-web provider entry (format gemini-web, cookie auth)
with the nano-banana-web model. The -web suffix keeps the bare
nano-banana id owned by adobe-firefly (operator decision 2026-07-31).
- gemini-web executor: new parseStreamResponseImages() extracts generated
image URLs from the StreamGenerate candidate extension block
(inner[4][0][12][7][0], url at entry[0][3][3] — string or list form),
dedupes cumulative frames, upgrades to =s2048, and deliberately skips
web-search thumbnails at [12][1]. Image mode (x_gemini_web_image_mode)
captures every StreamGenerate frame, resolves on first image, and gets
a 90s window; chat mode is byte-for-byte unchanged.
- handlers/imageGeneration/providers/geminiWeb.ts: drives the executor in
image mode with an explicit generation directive prompt (the web UI
otherwise answers with web-search images), caps n at 4, returns URLs or
b64_json (downloads the public googleusercontent asset), and surfaces
refusal text when no image was produced.
- Dispatch branch on format gemini-web in handleImageGeneration.
Tests: 21 new tests with fixtures built from the documented frame layout
(string/list url forms, cumulative-frame dedupe, web-image exclusion,
size-directive handling, refusal visibility, n-cap, b64_json, registry
wiring incl. the bare nano-banana → adobe-firefly regression guard).
Adjacent suites: gemini-web (6 files), chatgpt-web image, image handler,
route, registry, adobe-firefly, freepik, designer — all green.
ESLint clean on touched files (2 pre-existing any warnings unchanged);
tsc -p open-sse 0 errors.
* fix(media): close browser leak, surface timeout errors, and fall back accounts for gemini-web images
Addresses pre-merge review findings on #10494 (closes#10466):
- cloudflare-playground executor: close the launched browser on EVERY
non-success start() path, including the detected Cloudflare "Attention
Required" challenge branch (was leaking a Chromium process per blocked
request).
- cloudflare-playground executor: a streaming chat timeout now emits an
explicit timeout_error SSE chunk before [DONE] instead of silently
completing, so a client can no longer mistake an empty/partial timed-out
stream for a successful answer. Timeout duration is now injectable for
deterministic tests.
- gemini-web image handler + imageCredentialRetry: classify the underlying
GeminiWebExecutor's expired/blocked-session failure modes (400/500, per
its own Playwright timeout/catch-all branches) as retryable, so
executeImageWithCredentialFallback advances to the next eligible account
instead of only doing so on a plain 401.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* docs: regenerate provider counts after merging release/v3.8.50 (341 -> 342)
The previous merge commit resolved all 51 auto-generated-file conflicts by
taking release/v3.8.50's content, which still said 341 providers. Merging in
this branch's Cloudflare Playground provider brings the live catalog to 342,
so npm run check:docs-counts-sync now flags stale claims. Fix:
- docs/reference/PROVIDER_REFERENCE.md: regenerated via
`npm run gen:provider-reference`.
- README.md/AGENTS.md/llm.txt/package.json description: 341 -> 342.
- docs/diagrams/{readme-hero,promise-pillars,comparison-table,cli-terminal}.svg:
341 -> 342 in the embedded "NNN providers" text (targeted replace, matched
against the exact pattern check-docs-counts-sync.mjs validates).
check:docs-counts-sync and check:changelog-integrity are both clean after
this commit.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* docs(env): document CLOUDFLARE_PLAYGROUND_CHROME_PATH
Used by open-sse/executors/cloudflare-playground.ts but missing from
.env.example and docs/reference/ENVIRONMENT.md, caught by the
env-doc-sync gate when combined with other PRs in the release
merge-train.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: user.email <freakymustard67@gmail.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(cliproxy): read os.platform()/os.arch() at runtime in binaryManager platform detection (#10244)
detectPlatform()/detectArch() read the module's process.platform/process.arch,
which Turbopack `next build` (run only on Linux) constant-folds, pruning every
Windows/arm64 branch from the published npm artifact — so the embedded CLIProxyAPI
installer downloads the Linux ELF binary on Windows. Switch to runtime os.platform()/
os.arch() calls (the repo's established anti-fold pattern) so the Windows/ARM branches
survive any build machine. Add a regression guard mocking os.platform()/os.arch() to
win32/arm64 asserting the Windows/ARM path is reachable — RED before, GREEN after.
* fix(cliproxy): use runtime platform for binary install paths
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(cliproxy): thread runtime platform as a parameter instead of re-reading os.platform()
extractZip(), installVersion(), and rollbackVersion() each independently called
os.platform() inline in their own module scope even after #10244 switched the
detection helpers to os.platform()/os.arch(). Each independent call site is its
own opportunity for a bundler to constant-fold that particular occurrence away.
Detect the runtime platform once per orchestrating call (installVersion,
downloadRelease, rollbackVersion) and thread the already-detected value down as
an explicit parameter into extractZip and the symlink/copy decisions, instead of
re-reading the global in every helper.
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.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).
* feat(dashboard): agentic conversation tracking with live transcript view
Every agentic chat request now gets a conversation id (X-ConversationId
response header). OmniRoute detects when a follow-up request continues the
same conversation via fingerprint + bounded prefix-hash matching, with a
strict-growth invariant to prevent false merges between independent
single-shot requests that happen to share identical opening content.
Continuation detection excludes the system message from the identity
anchor, since real coding-agent CLIs commonly regenerate it every request
with live context (timestamp, cwd, git status) — without this, that
volatility alone broke every continuation check against real traffic.
- `/dashboard/logs`: new toggleable Conversation column.
- `/dashboard/logs/timeline`: requests sharing a conversation id share a
timeline lane, connected by an arrow, with a configurable lane-reuse
window.
- Request detail panel: new Full Conversation transcript above the raw SSE
event stream — Markdown rendering, per-turn timestamps, turn-relative
view, click-any-turn navigation, live auto-refresh building the
transcript in real time from the in-flight SSE chunk buffer while a
request is still streaming, auto-scroll-to-bottom as the live turn grows.
- New `/dashboard/conversations` page listing conversations with 2+ turns,
no-forking model (an edited/duplicated mid-history turn mints its own
independent conversation instead of merging), pagination, duplicate-
anchor fix.
- Configurable auto-refresh intervals on both the timeline and
conversations list pages.
- Responses API tool-call gap fix: turnsFromOpenAiMessages only handled
role-based Chat Completions messages, so bare {type:"function_call"} /
{type:"function_call_output"} / {type:"reasoning"} items (real Responses
API traffic) silently vanished from the Conversation Context panel.
- truncateForLog now counts input[] (Responses API), not just messages[]
(Chat Completions), so a truncated /v1/responses request still shows a
placeholder instead of nothing.
- RequestTimeline.tsx now reads the same debugEnabled/emailsVisible
settings RequestLoggerV2.tsx already used, instead of hardcoding both
false — the timeline view never showed SSE/stream-chunk events or
respected email-masking, regardless of the actual setting.
Migrations 147/148 (agentic_conversations, conversation_turn_nodes) — 135
and 136 are now taken upstream; 143-145 are documented KNOWN_GAPS, so this
uses the next free slot past upstream's current highest.
Test plan:
- npm run typecheck:core — clean
- npm run lint — clean
- node --import tsx/esm scripts/check/check-migration-numbering.mjs — OK, 0 collisions
- 109 unit tests across the conversation-tracking, migration-renumber, and
dashboard-wiring surface — 0 failures
* refactor(dashboard): reuse call-log artifacts for conversation transcript content
conversation_turn_nodes no longer stores turn text/tool-call content
(text_preview/block_kind/tool_name) -- it's identity-only now (id/parent/
content_hash), matching agentic_conversations' existing lightweight-index
shape. Every node's originating request is already fully captured by the
call-log pipeline artifact its last_correlation_id points at, so the
/dashboard/conversations tree view resolves each node's actual display
content on demand from there (open-sse/services/conversationTurnContent.ts),
re-running the same extractCanonicalTurns/hashTurnContent the write path
used and matching by content_hash, instead of duplicating conversation
content into a second store under a separate retention/gating policy. This
also drops the old 8000-char text_preview truncation entirely -- resolved
content is always full and untruncated.
The frontend contract is unchanged (tree API still returns
{textPreview, blockKind, toolName} per node), so the dashboard UI itself
(page.tsx, RequestLoggerDetail/RequestTimeline, sidebar, i18n) needed no
changes.
Renumbered the cherry-picked 147/148 migrations to 153/154 -- 147 now
collides with 147_api_keys_model_access_mode.sql, which landed on
release/v3.8.50 after this work was originally built.
Also includes a standalone, unrelated fix carried along from this rebase:
close isProviderModelHidden's missing function-body brace in
modelSelectModalHelpers.ts (separately landed as #10206).
Stacked on feat/responses-previous-response-id-virtualization (#3), which
is itself stacked on feat/openai-responses-store-toggle (#10121).
* fix(dashboard): resync conversation list on open so the live-text poll starts immediately
openConversation() seeded activeConversation (and therefore activeCallLogId,
which gates the live-partial-text poll effect) from whatever row snapshot the
list's own fixed-interval poll last produced. A conversation opened right
after a reply started streaming -- after that tick, before the next -- had
activeCallLogId still null, so the live-text poll never started; only a
subsequent background list-poll resync (already existed) picked it up,
which is why closing and reopening the same conversation "just worked".
loadConversations() is now a shared callback so openConversation can force
one immediately on open instead of waiting on pollSeconds.
Live-verified against omniroute-dev: opening a conversation mid-stream now
shows live reasoning on the first open.
* style: prettier formatting for conversationTurnContent.test.ts
* fix(db): close migration numbering gap left by decoupling from #3/#10262
153/154 (originally 154/155) were chosen back when this branch stacked on
top of the previous_response_id migration (153_call_logs_response_id.sql).
Decoupling removed that migration from this branch's history, leaving an
unused 153 slot that check-migration-numbering.test.ts correctly flags as
a gap.
* refactor(dashboard): split RequestTimeline/RequestLoggerDetail under the 1000-line file-size cap
Both files exceeded check-file-size's new-file cap after this PR's own
additions (RequestTimeline 1048, RequestLoggerDetail 1163). Extracted pure
non-component logic (types, constants, allocateLanes and its helpers) out
of RequestTimeline.tsx into RequestTimeline.utils.ts, and the two
self-contained presentational sub-components (PayloadSection,
ConversationContextSection + its private helper) out of
RequestLoggerDetail.tsx into RequestLoggerDetail.sections.tsx. No behavior
change; existing external imports (default exports, allocateLanes,
TimelineLog, CONVERSATION_LANE_REUSE_STORAGE_KEY) still resolve from the
original file paths.
* fix(db): renumber agentic-conversation migrations to clear 153 collision + sync migration-count docs
The refresh-merge of release/v3.8.50 exposed that the feature's three
migrations collided at slot 153 with the base's radar_local_model_state
(153) and its own call_logs_response_id. Migration runner enforces unique
numeric prefixes -> every DB init threw, red-ing Vitest, all Unit shards and
the DB-backed quality gates. Renumber the feature's pair to
155_agentic_conversations / 156_conversation_turn_nodes and move
call_logs_response_id to 154 (keeps 153_radar base-owned, preserves
agentic-before-turn_nodes ordering). Update SQL headers and the
154/156 references in feature code + tests.
Migration count is now 151 (was 148 stale in README/AGENTS/llm.txt) — sync
the doc counts to clear the docs-accuracy gate.
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
* fix(ui): drop unused CONVERSATION_LANE_REUSE_STORAGE_KEY re-export from RequestTimeline
Knip 6.32 (baseline 415) flags the public re-export of
CONVERSATION_LANE_REUSE_STORAGE_KEY from RequestTimeline.tsx as dead: no
external consumer imports it through that re-export (it is imported and
used directly from RequestTimeline.utils.ts inside the component). Removed
the unused re-export; the internal import stays. DEAD_TOTAL 416 -> 415,
back to the frozen baseline.
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
* fix(agentic-conversations): guard resolveConversationId, drop dead whole-chain export
- Wrap resolveConversationId() in try/catch in chat.ts, matching the
defensive pattern used by every other best-effort side call nearby, so a
DB hiccup in conversation tracking can't turn a working chat request into
a hard failure.
- Remove getConversationTurnTree: knip's project scope excludes tests/**,
so an export used only by tests can never register as used there. Swap
its 8 test call sites to the paginated getConversationTurnPage (already
the dashboard's canonical query) with a generous limit, collapsing to one
query path instead of keeping a second whole-chain export alive solely
for test convenience.
- Regenerate i18n llm.txt mirrors from root (pre-existing drift on this
branch, unrelated to the above, caught by the docs-sync pre-commit gate).
Addresses PR review feedback.
* fix(i18n): close requestLogger conversation-column gap, fix domain-modules count drift
- fr.json, vi.json were missing requestLogger.columns.conversation (added
in the conversation-tracking feature), failing i18n-vi-completeness.test.ts.
- docs/i18n/*/llm.txt mirrors still said 117 domain-specific files after an
earlier rebase fixed the migration count but missed this companion number,
failing check-docs-sync.mjs across all 42 locales.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(docs): restore PROXY_LOG_INCLUDE_IPS env/doc entries (env-doc-sync red)
.env.example and docs/reference/ENVIRONMENT.md were both missing the
PROXY_LOG_INCLUDE_IPS entry that src/lib/proxyLogger.ts already reads
(confirmed present at this branch's merge-base too, so this predates
the conversation-tracking work and is unrelated to it) -- the entry
was added on release/v3.8.50 after this branch's last sync and this
branch never picked it up. That gap red-lines
tests/unit/check-env-doc-sync.test.ts and
tests/unit/issue-7793-env-doc-sync-repro.test.ts (Unit Tests
fast-path 2/4 in CI). Restore both entries verbatim from the current
release/v3.8.50 tip -- no feature-code change.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: hartmark <hartmark@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* feat(api): add provider quota telemetry, adaptive routing, and status inventory
Adds a read-only OmniRoute status/inventory surface plus supporting
resilience and usage-tracking infrastructure:
- src/lib/quota/providerQuotaTelemetry.ts, providerCapabilities.ts:
provider quota state and capability signals, sourced from configured
metadata rather than invented values; unknown stays unknown.
- src/lib/resilience/adaptiveCircuit.ts, failureClassification.ts:
circuit state with lazy recovery and explicit failure classification.
- src/lib/usage/usageLedger.ts, budgetGuard.ts, modelPricingRegistry.ts:
internal usage tracking and budget allow/warn/deny decisions, kept
separate from upstream-reported quota (never conflated).
- src/lib/routing/adaptiveRouting.ts: excludes exhausted-quota and
open-circuit candidates from routing, penalizes approaching-limit.
- src/lib/omnirouteStatus.ts + src/app/api/omniroute/status,
route/preview: read-only status endpoint; never issues a live
upstream model request (asserted via liveRequestExecuted: false).
- src/lib/db/quotaPools.ts: adds ensurePool() for idempotent pool
management by automation/CLI callers, following the existing
group-demo default-group convention.
- scripts/omniroute-verify.mjs (+ omniroute:verify script): local
verification against the running gateway.
9 new unit tests, all passing. typecheck:core clean relative to base
(release/v3.8.50) -- the 2 pre-existing gateways.ts errors are tracked
separately in #9985 and untouched by this change.
* test(cli): align cli-machine-token assertions with HMAC-SHA256 64-char format
The quota-telemetry feature hardens cliToken to HMAC-SHA256(machineId, SALT)
(64-char hex, pristine machine id). Update the regression test to the new
format and mirror the production derivation in the different-machine-id check.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
Co-authored-by: desamours-hub <desamours-hub@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* feat(admission): per-target lane-aware probes for combo/fusion fan-out (#9654 Wave 2)
Combo and fusion fan out N targets without ever consulting the adaptive-admission
layer: the parent request holds one lease, but each fan-out target is dispatched
unconditionally. With virtual lanes enabled (OMNIROUTE_CHAT_VIRTUAL_LANES=1), a
connection whose lane queue is full now SKIPS additional fan-out targets instead
of piling more queued work onto an already-congested session.
Adds PerTargetAdmissionHook (admission/types.ts) + createPerTargetAdmissionHook
factory (chatAdmission.ts): strictly non-blocking (maxWaitMs 0 - skip, never
queue), a no-op when virtual lanes are off, keyed to the parent tenantKey, and
release-on-admit so the probe is a capacity gate, not a hold.
Threaded through every parallel fan-out path:
- priority/weighted executeTarget + round-robin skip chains (combo.ts)
- fusion panel before fan-out (fusion.ts), judge fallback prefers survivors
- chaos parallel panel (autoCombo/chaosEngine.ts)
- tryFusionDispatch / tryRuntimeUnitDispatch / buildBaseOptions (dispatchPrelude.ts)
- chat.ts primary + safety-net redirect call sites
Snapshot exposes virtualLanes so the no-op gate is cheap and honest.
Tests: tests/unit/combo-lane-awareness-9654.test.ts (10 tests) - factory
semantics, priority/RR skip, fusion panel drop + all-skipped 503, no-hook
backward-compat baseline.
* feat(flags): activation UX - env-wins adaptive virtual-lanes flag + env docs (#9654 Wave 2)
U7: make adaptive virtual admission lanes discoverable + activatable.
- New OMNIROUTE_CHAT_VIRTUAL_LANES feature flag (boolean/runtime/requiresRestart) in featureFlagDefinitions + en.json i18n key.
- lib/admissionVirtualLanes.ts: env-wins resolver (env > DB > default) + boot warm folding a DB-sourced override into the process-global runtime env via reloadAdaptiveAdmissionRuntime(options.env) - no process.env mutation, no open-sse changes. Env still wins; DB toggle gates at next boot.
- GET /api/settings/feature-flags special-cases the flag to report the gate true source (ccDiscoveryAliases precedent); flagPayload helper dedupes the payload shape.
- Wire the warm into instrumentation-node registerNodejs (non-fatal, DB-ready).
- Document the master switch in .env.example + ENVIRONMENT.md with the system-1/system-2 distinction; zero new env-doc-sync drift.
- 11 new tests (resolver precedence + warm); 60/60 across feature-flag suites; typecheck core clean; ESLint + doc gates green.
* feat(mcp): surface adaptive admission lane data in omniroute_get_health (#9654 Wave 2)
U8: make adaptive virtual-lane admission visible to agents via the MCP health tool. handleGetHealth now surfaces a curated adaptiveAdmission block from the health payload (which already carried the runtime snapshot but was dropping it): virtualLanes/pressure/utilization/laneCount/laneQueuedCount/laneQueuedCost, laneTenants capped at top-10 by queued cost, admitted/rejected/wouldReject counts, shutdown. Block omitted entirely when the health endpoint reports none.
isLaneFlagOn mirrors the runtime 1|true convention so a string serialization can never invert a boolean lane report. getHealthOutput schema extended with the matching optional shape; tool description updated.
4 new dispatch tests (full block, top-10 cap/order, omission, defensive coercion of string flags + malformed lane entries) - 22/22 in essentialTools.test.ts. README: Adaptive Admission Lane Data table + Skills & Tool Navigability audit (29/43 schema entries covered, 14 undocumented, tool_search keyword runtime discovery, full catalog in docs/frameworks/MCP-SERVER.md).
No new lint errors (4 pre-existing in server.ts), typecheck core clean, doc counts + fabricated-docs gates green.
* docs: add changelog entry for #9654 Wave 2 (#10039)
* fix(codeql): suppress js/insufficient-password-hash false positive in lane-key fingerprinting (#10039)
resolveSessionId sha256-hashes bearer/x-api-key/x-goog-api-key to derive a deterministic, non-reversible per-key lane-bucket ID for virtual admission lanes (#9654). This is not password storage or verification, so the rule is a false positive; suppress it inline (same house style as src/lib/sync/tokens.ts) to clear the codeqlAlerts ratchet (2 > baseline 1) that blocks #10039 and every PR against release/v3.8.50.
* docs(mcp): complete MCP server README tool reference (#10039)
The MCP server README covered only 29 of the 43 schema entries, listing the
remaining tools solely as a gap note with omniroute_tool_search as the runtime
fallback. Add tool-reference tables for the agent-skills trio, oneproxy trio,
web_fetch/web_search, tool_search, create_combo, set_routing_strategy,
pick_fastest_model, sync_pricing, and db_health_check so the README covers the
full schemas catalog, and fold the coverage note into the tool_search discovery
paragraph.
* fix(chat): drop unused correlationId from safety-net combo redirect (#10039)
handleComboChat's HandleComboChatOptions has no correlationId member and
the combo pipeline never consumes it; the property was copied from the
handleSingleModelChat options shape by accident and introduced a new
TS2353 under the open-sse workspace typecheck gate.
* fix(i18n): translate featureFlagChatVirtualLanesEnabledDescription into 42 locales (#10039)
en.json gained the flag description in this PR but the locale catalogs
were never mirrored, failing the pt-BR key-parity (#6695) and vi
completeness gates. Adds a real translation to every locale, keeping the
zh-CN/zh-TW glossary canonical terms (提供者/儀表板) and no ICU drift.
* chore(quality): ratchet open-sse-typecheck baseline down (#10039)
The Wave 2 admission refactor removed 66 baselined open-sse type errors;
re-freeze the baseline so the gate pins the new, tighter state.
* docs: resync provider reference to 341 and CLI tools to 34
The release branch gained an 11th no-auth provider (freeaiapikey registry
resync, #10233) and a 26th CLI Code tool without regenerating the
auto-generated docs, leaving every PR against release/v3.8.50 failing the
Docs Gates strict validator (code 341 vs doc 340, CLI 34 vs "33 tools").
Regenerate docs/reference/PROVIDER_REFERENCE.md and sync the provider/tool
counts across README.md, AGENTS.md, llm.txt plus 42 i18n mirrors,
package.json description, and the four diagram SVGs.
* fix(tests): align count expectations with live catalogs (pre-existing release drift)
Release/v3.8.50 currently fails five gates on its own tree; this PR inherits
them. Fix the stale expectations to match live code:
- feature-flags-settings: 48 -> 49 flags (Wave 2 adds OMNIROUTE_CHAT_VIRTUAL_LANES)
- cli-tools-schema / cli-catalog-counts: 33 -> 34 tools (zcode added; 26 code = 21 visible + 5 none)
- optional-transformers-dependency: onnxruntime-node ~1.24.3 -> ~1.27.0 (bump #10382)
- stryker.conf.json: register chatcore-header-drop-warn-dedupe-10315 test
- check-public-creds: freeze zcodeProtocol clientId false positive (client identifier, not a credential)
* fix(tests): follow release's onnxruntime-node revert to ~1.24.3
release/v3.8.50's #10543 pinned onnxruntime-node back to ~1.24.3 after
#10403's ~1.27.0 bump caused npm to nest a second native copy under
@huggingface/transformers and broke the Docker SONAME contract. This
PR's own drift-alignment commit (57b9c033) predates that revert and
still expected ~1.27.0; the 3-way merge did not flag it as a textual
conflict since only one side touched this exact line, but the merged
tree became internally inconsistent (package.json ~1.24.3 vs test
expecting ~1.27.0). Align the test with the now-canonical release
value.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(quality): dedupe stryker.conf.json chatcore-header-drop-warn-dedupe entry
The 3-way merge applied both sides' insertion of the same test-file entry
at different positions, producing a duplicate with broken indentation.
Adopted release's clean version of the file.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: Brandon Bennett <brandonbennett@macbookair.myfiosgateway.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
Co-authored-by: Brandon Bennett <branben@users.noreply.github.com>
PR #10573 landed with two real defects surfaced by typecheck/tests on
the combined release tip:
- TS2322: allowedConnectionIds (string[]) was built from
compatible.map(t => t.connectionId), whose type includes null.
Filter nulls before assigning.
- applyNativeCodexTurnPin never assigned the pinned connectionId onto
a compatible candidate that didn't already carry it (e.g. an
unresolved placeholder target with connectionId: null) — the pin
was silently dropped instead of applied. Now resolves the pinned
slot's connectionId explicitly (in original order, so
allowedConnectionIds stays consistent regardless of pinned-first
reordering) before building the returned target list.
Confirmed via the existing focused suites:
tests/unit/chatgpt-web-codex-turn-pin.test.ts and
tests/unit/native-codex-turn-pin-10379.test.ts (14/14 pass),
typecheck:core clean.
* fix(providers): make upstream model sync opt-in and preserve manual overrides
(cherry picked from commit 0a84f5496896a95856e834112b3d813fa1b87d38)
* test(providers): cover upstream model sync controls
* fix(providers): fix pre-existing tests broken by opt-in model sync + sync i18n keys
The upstream model auto-fetch opt-in default flip made 3 pre-existing tests
short-circuit before reaching the paths they exercise, because their
connection fixtures never set providerSpecificData.autoFetchModels: true:
- tests/unit/provider-models-route-lan-guard.test.ts (#6939 SSRF-guard tests)
- tests/unit/openrouter-embeddings-catalog-6976.test.ts (live discovery merge/dedup)
- tests/unit/provider-models-route.test.ts (Kimi Coding auth-header test —
this was mislabeled as base/catalog drift during review, but is the same
root cause: without autoFetchModels the mocked fetch is never reached and
the route falls back to local catalog data instead)
Also syncs the 11 new providers.autoFetchModels*/overridesUpstreamModel*/
resetToUpstreamDefaults* i18n keys from en.json/zh-CN.json to the remaining
40 locale files via a narrowly-scoped ad-hoc translation script (only these
11 keys — leaves each locale's pre-existing, unrelated missing-key backlog
untouched).
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(providers): fix remaining pre-existing tests broken by opt-in model sync
Rebase surfaced that the 'Kimi Coding' CI failure flagged as possible base
drift during review was actually the same root cause as the lan-guard and
openrouter-embeddings fixes: 29 pre-existing tests in
tests/unit/provider-models-route.test.ts (of 59 total) short-circuit under
the new autoFetchModels opt-in default because their connection fixtures
never set providerSpecificData.autoFetchModels: true, so they never reach
the live-fetch/validation paths they were written to exercise (fetch mocks
never called, base-URL validation never reached, live models never merged).
Adds providerSpecificData.autoFetchModels: true to each affected fixture.
No production code or test assertions changed — same TEST-fixture-only
pattern as the lan-guard and openrouter-embeddings fixes. All 59 tests in
the file now pass (was 30/59).
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(combo): allow fill-first failover across Codex OAuth connections
applyNativeCodexTurnPin previously narrowed the target pool to the
single pinned connection, making same-provider failover impossible when
the pinned connection was rejected by pre-dispatch checks. Return all
compatible connections (same provider + model) with the pinned connection
first, so the combo engine can fall over to siblings. Also allow
pinNativeCodexTurn to update connectionId for failover recovery while
still rejecting provider/model changes.
Fixes#10379
Signed-off-by: Minxi Hou <houminxi@gmail.com>
* fix(test): replace as any with properly typed ResolvedComboTarget literal
Addresses ESLint no-explicit-any error in tests/.
Signed-off-by: Minxi Hou <houminxi@gmail.com>
---------
Signed-off-by: Minxi Hou <houminxi@gmail.com>
* fix(logging): redact client IPs and account prefixes by default
ProxyEgress and AUTH logs exposed client IPs, egress IPs, and account
prefixes at info level — a privacy leak in multi-tenant/shared-log
environments. Now redacted by default, only shown when debugMode=true.
Fixes#10348
* fix(sse): default SSE comment lines to disabled
Strict SSE clients (WorkBuddy, etc.) JSON.parse every SSE line and
crash on comment lines. Changed OMNIROUTE_SSE_COMMENTS
default from enabled to disabled. Operators can opt in with
OMNIROUTE_SSE_COMMENTS=on.
Fixes#10524
* fix(logging): gate AUTH account-prefix redaction on a narrow flag, not debugMode
The proxy-log redaction half of #10348 is superseded by an already-merged
fix (PROXY_LOG_INCLUDE_IPS, decoupled from debugMode). The remaining gap was
the chat.ts AUTH log line ("Using <provider> account: <prefix>..."), which
this PR gated on the broad `debugMode` setting. `debugMode` is a general
dashboard-visibility toggle unrelated to log privacy — coupling redaction to
it means any future, unrelated change to debugMode's default silently
changes whether account prefixes leak into logs.
Add a dedicated AUTH_LOG_INCLUDE_ACCOUNT_ID feature flag (default off,
security category) and gate the AUTH log line on it via
isFeatureFlagEnabled(), which reads the DB override synchronously on every
call (no stale in-memory cache to invalidate) and fails safe to redacted on
any lookup error.
Also update the SSE-comments tests/docs that still asserted the old
enabled-by-default behavior (tests/unit/sseHeartbeat.test.ts,
tests/unit/sse-comments-optout-9305.test.ts, docs/reference/ENVIRONMENT.md)
to match the new default-off behavior from this PR's earlier commit.
Refs #10348, #10524
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(cli): guarantee non-empty [STARTUP] Fatal log on instrumentation-hook boot throw
Refs #10171: on native Windows / WSL2 boots, an instrumentation-hook throw
during module-load or registerNodejs() leaves the HTTP listener up while
every DB-touching route 500s, with app.log staying completely empty. The
#7773/#7828 guard in ensureDbReadyForBoot only logs one specific failure
class (DB driver init). register() in src/instrumentation.ts now wraps the
boot call in a try/catch at the outermost boundary and unconditionally logs
a "[STARTUP] Fatal: instrumentation hook failed during boot:" line before
rethrowing, so app.log/stdout is never silently empty on a failed boot
regardless of platform or which step threw.
This is a partial diagnostic hardening, not the full fix for #10171 — the
platform-specific root cause on native Windows/WSL2 still needs the
reporter's raw child stderr from a real host (tracked separately, see
_tasks/pipeline/bugs/2-implementing/10171-instrumentation-hook-500-on-windows-wsl.plan.md).
* fix(cli): normalize instrumentation boot errors
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(cli): reuse shared normalizeBootError helper in instrumentation.ts
The outermost instrumentation-hook boot boundary (#10171) was inlining its
own err-instanceof-Error normalization instead of reusing the existing
normalizeBootError() helper already defined in instrumentation-node.ts for
the same purpose (#6560/#7773). Extract it into a dependency-free
src/lib/instrumentationBootError.ts so both instrumentation.ts (which also
loads under the Edge runtime) and instrumentation-node.ts can import it
statically without risking a second failing dynamic import of
instrumentation-node.ts from within the catch block.
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
Diagnosed while chasing the reused-output-index incident (see
705ac7335 / OpenClaw issue #123342): every call-log artifact showed a
wire-clean response, even for requests that actually failed, because
withEarlyStreamKeepalive injects its startup/keepalive/error frames
directly into the outer response stream, entirely outside the request
handler's own reqLogger. reqLogger.appendConvertedChunk (which
populates pipeline.streamChunks.client) never sees those bytes — only
what chatCore.ts's own SSE writer produced. The persisted artifact was
answering "what did the handler generate," not "what did the client
actually receive," which is the wrong question when diagnosing a
client-visible stream defect.
withEarlyStreamKeepalive wraps the handler's Promise from OUTSIDE its
call tree; the reqLogger it needs to feed is created deep inside
chatCore.ts, after routing/model/provider resolution, and doesn't
exist yet when the keepalive frames are written. The two sides share
no reference — only an identifier, if one is deliberately threaded
through both.
Fix: responses/route.ts now generates a correlationId before calling
handleChat, passes it as handleChat's existing (already-supported,
previously-unused-here) 4th positional arg — which chatCore.ts already
threads into trackPendingRequest's metadata as entry.correlationId,
zero changes needed there — and also into
withEarlyStreamKeepalive's options. The wrapper buffers every direct-
to-client write (startup frame, periodic ticks, in-band error frames)
via the new earlyKeepaliveByteBuffer module, keyed by that same id.
chatCore/attemptLogging.ts, which already has correlationId in scope
right where it assembles the final pipeline payload before saveCallLog,
takes the buffered bytes and prepends them into streamChunks.client in
send order. The verbatim-forwarded real response body is deliberately
NOT re-recorded here — the handler's own reqLogger already captures
that; recording it twice would duplicate it in the artifact.
The buffer is consumed exactly once per correlationId and swept on a
10-minute TTL so a request that never reaches the persist call
(aborted, detailed logging disabled, a route that doesn't opt in)
cannot leak entries forever.
Scoped to /v1/responses only, where the incident actually happened.
/v1/chat/completions and /v1/messages call withEarlyStreamKeepalive the
same way and would need the identical two-line route change to opt in;
left as a follow-up rather than bundled in sight-unseen.
Test plan:
- tests/unit/early-keepalive-byte-buffer.test.ts (new): record/take
ordering, single-consumption, per-id isolation, empty-input no-ops,
unbounded-growth cap
- tests/unit/early-stream-keepalive.test.ts: two new tests — a
correlationId records the startup frame and keepalive ticks but NOT
the forwarded body; omitting correlationId is a true no-op
- tests/unit/attempt-logging-early-keepalive-merge.test.ts (new): real
temp-DB end-to-end proof against the actual persisted call-log row —
early bytes prepended in send order, consumed exactly once, no-op
without a correlationId, gated by detailedLoggingEnabled matching the
existing streamChunks capture gate
- tests/unit/chatcore-attempt-logging.test.ts (existing): unchanged,
still passing — confirms the merge addition doesn't disturb existing
persistence behavior
- 44 passed total across the above plus earlyStreamKeepalive.test.ts,
2 pre-existing skips unrelated to this change
- tsgo --noEmit: clean on all touched files
Kiro's device poll endpoint reports progress in a `status` field (e.g.
`authorization_pending`), but `classifyKiroSocialPoll()` only inspected
`data.error`. This caused every pre-authorization poll to fall through to
the terminal `invalid_token_response` error, making social login impossible
for Kiro AI and Amazon Q via Google/GitHub.
Changes:
- Add `status` field to `KiroSocialPollData` type
- Update `classifyKiroSocialPoll()` to check `data.status` as fallback
for `data.error` when detecting pending states
- Add tests covering `status`-based pending detection and precedence
Closes#10618
* feat(resilience): scope auto-disable banned accounts to subscriptions
Prepaid API keys should stay in the routing pool after a permanent-ban
signal; subscription/OAuth accounts can still be deactivated. Default
scope remains all so existing installs do not change.
* docs(security): document auto-disable scope and log skipped prepaid keys
Keep the operator ban-detection page aligned with the new setting and
reuse the shared scope enum in the settings schema and dashboard radios.
* chore(changelog): name the auto-disable scope fragment for #10617
* docs(settings): treat free login seats as auto-disable targets
The first-cut scope is still all vs login-style auth. Copy now states
that paid subscriptions and free accounts both disable, while prepaid
API keys stay in the pool until per-account overrides exist.
* i18n: backfill autoDisableBannedScope keys across all locales
npm run i18n:sync-ui — the 6 new autoDisableBannedScope* keys landed
in en.json and vi.json but not the other 40 locales (including
pt-BR), tripping the pt-BR no-drift regression test (#6695).
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(auth): add missing state parameter to OIDC authorization URL
The OIDC login route generates a state UUID and stores it in the
oidc_state cookie, but never includes it in the authorization URL.
This causes the OIDC callback to receive state=null, failing with
'oidc_error=missing_code' because the provider has no state to echo.
Add url.searchParams.set('state', state) after setting scope, so the
state parameter is sent to the OIDC provider and returned in the
callback for proper CSRF protection.
* test(auth): add regression coverage for OIDC login state parameter
Adds a TDD regression test proving the fix in this PR: the OIDC login
route now includes the state query parameter in the authorization
redirect URL, and it matches the oidc_state cookie value set on the
same response. Modeled on tests/unit/oidc-callback.test.ts.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(auth): use originEarly for OIDC err redirects (#10224)
* test(auth): verify OIDC err redirects use proxy origin (#10224)
---------
Co-authored-by: openhands <openhands@all-hands.dev>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(cli): let setup --api-key reach the provider setup path
`bin/cli/program.mjs` declares a program-level `--api-key` (the OmniRoute server
key) and `bin/cli/commands/setup.mjs` declares its own `--api-key` (the provider
key). Commander binds the value to the program-level option, so the subcommand's
`opts.apiKey` was always `undefined` and
omniroute setup --non-interactive --add-provider \
--provider openrouter --api-key sk-...
aborted with "Provider API key is required. Pass --api-key or OMNIROUTE_API_KEY."
— naming the very flag that had just been passed. The documented headless setup
path was unusable; the only way in was `omniroute keys add`.
Fall back to the program-level value in a small exported helper. This also makes
`OMNIROUTE_API_KEY` satisfy the provider key, which the error message already
promised (that env var feeds the program-level option).
Tests cover the real Commander flag shape, the env-var path, and precedence when
both are supplied.
* chore(changelog): use the real PR number for the fragment
* fix(cli): derive machine-id token under plain Node and honor salt rotation
`getCliToken()` destructured `machineIdSync` off `await import("node-machine-id")`.
That module is CommonJS, so under plain Node its exports land on `.default` and the
destructured binding is `undefined`. Calling it threw, the bare catch blanked the
token, and every management request went out with no `x-omniroute-cli-token` header
— silently unauthenticated, 401 on every `omniroute combo` / `usage budget` call.
Resolve the binding the same way `src/lib/machineToken.ts` already does, and read
`OMNIROUTE_CLI_SALT` so the rotation documented in docs/security/CLI_TOKEN.md
actually reaches CLI processes (the salt was hardcoded). The catch now logs instead
of failing mute, per the error-handling convention in CONTRIBUTING.md.
The existing test asserted `token === "" || token.length === 32`, so the blanked
token passed. Tightening it in-process is not enough either: the suite runs under
`tsx/esm`, which resolves CJS named exports and hides the bug. The regression test
therefore spawns plain `node` — the loader the CLI actually runs under.
Both new tests fail on the previous code and pass on this one.
* chore(changelog): use the real PR number for the fragment
Whisper-compatible upstreams pick the decoder from the multipart filename
against an allow-list (flac, m4a, mp3, mp4, mpeg, mpga, oga, ogg, wav,
webm) that has no `opus`, and OmniRoute forwarded the client's filename
verbatim. The same bytes transcribed as `note.ogg` and 400'd as
`note.opus`. Since /v1/audio/speech emits audio/opus for
`response_format=opus`, clients re-uploading their own voice notes hit
this on every round trip.
A `.opus` file is Opus in an Ogg container (RFC 7845), so `.ogg` is a
truthful relabel and is already on the allow-list. Rewrite the extension
in getUploadedFileName, the single choke point feeding
buildMultipartBody.
The OpenRouter STT path had the same root cause with a quieter symptom:
`.opus` matched neither its extension list nor its MIME map, so it fell
through to the "wav" default and announced Opus bytes as WAV. Map both
the extension and audio/opus to its already-supported ogg container.
Fixes#10588
* fix(xai): cap chat history at xAI 800-message limit
xAI returns 413 when messages/input exceed 800 items. Token
compression never fires on a long tool loop that still fits the
context window, so trim at the executor edge after Responses
expansion and drop orphaned tool pairs from the cut.
* chore(changelog): attach PR number to xAI 800-message fragment
* fix(xai): resolve TS2339 generic assignment in capXaiRequestHistory
Drop the T extends Record<string, unknown> generic on
capXaiRequestHistory and type it directly as
Record<string, unknown> -> Record<string, unknown>. Assigning
next.messages / next.input onto a generic T was rejected by
TypeScript even though every call site already passes/consumes a
JsonRecord (= Record<string, unknown>), so no caller relied on the
generic preserving a narrower type.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: mikolaj92 <mikolaj92@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(audio): fall back nested STT models when the prefix provider has no credentials
Bare ids such as deepgram/nova-3 prefix-match the native provider and 400
when that key is missing, even if OpenRouter lists the same model. Retry
the gateway and mention qualified catalog ids in the error.
Closes#10583
* test(audio): scope whisper-1 fallback test to a 2-provider registry
nanogpt was added to AUDIO_TRANSCRIPTION_PROVIDERS (already merged,
unrelated to this fix) with a bare "whisper-1" model id, which now
intercepts findAlternateAudioProvider's first candidate before the
qualified-alias branch this test exists to cover. Scope the test to a
local {openai, openrouter} registry subset so it deterministically
exercises the qualified `${provider}/${model}` fallback regardless of
future providers that also list a bare "whisper-1" id.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* feat(providers): complete Jina AI via OmniRoute including Omni multimodal
Dashboard and env keys share one Jina credential pool, native v5 Omni
{text}/{image}/{content} docs pass through /v1/embeddings intact, and
classify/segment/search are proxied without a third unused Jina card.
* chore(changelog): name Jina complete-provider fragment for #10581
* feat(providers): make Gemini Embedding 2 multimodal work via OmniRoute
Route gemini-embedding-2 through embedContent/batchEmbedContents so N
OpenAI input items become N vectors, pass through native multimodal
parts, and use dashboard Gemini keys (GEMINI_API_KEY only as fallback).
* fix(providers): resolve rebase fallout for Jina/Gemini embeddings
- narrow the two new no-explicit-any violations introduced by this PR
(validateJinaFoundationProvider's params + catch, search.ts's
normalizeJinaSearchResponse data param)
- cast credentials to Record<string, unknown> at the two quota-preflight
call sites in src/sse/services/auth.ts so the new JinaEnvCredentials /
GeminiEnvCredentials union members type-check without loosening the
allRateLimited narrowing used elsewhere in the same function
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
Add githubSkillTools to getAllToolDefinitions() so the searchable MCP
catalog matches TOTAL_MCP_TOOL_COUNT, which already counts them. The
GitHub skill tools were registered and counted but missing from the
catalog, so omniroute_tool_search could not surface them.
Adds regression tests at both layers: catalog aggregation and
client-visible discovery via the MCP client.
Co-authored-by: Brandon Bennett <brandonbennett@macbookair.myfiosgateway.com>
* fix(opencode): session stability, free-tier routing, and CLI defaults
- Wire generateSessionId() into opencodeHeaders so x-opencode-session
is a deterministic fingerprint instead of randomUUID() per request,
enabling upstream prompt caching across a conversation
- Thread request body through buildHeaders() so session fingerprint
has access to model, system, messages, and tools
- Default CLI header synthesis to ON (opt-out via false), align
values with 9router proven defaults (opencode/desktop/global)
- Auto-echo listing-valid model names for noAuth providers so
response.model matches /v1/models listing
- Short-circuit free-tier model resolution to opencode provider first
to prevent prefix inference misrouting when catalog is unreachable
* fix(opencode): make free-tier default flip self-consistent + add coverage
PR #10571 flipped OPENCODE_SYNTHESIZE_CLI_HEADERS to on-by-default and
changed the synthesized UA/client/project default values, but shipped
with 2 broken assertions in the existing #5997 regression test and no
coverage for the new session-fingerprinting, free-tier routing, or
noAuth echoModel logic (Hard Rule #18).
- Update tests/unit/opencode-cli-headers-synthesis-5997.test.ts to match
the new on-by-default behavior and new default values; add an explicit
opt-out coverage test so the forward-only path is still guarded.
- Fix 20 further test failures in tests/unit/opencode-executor.test.ts
and tests/unit/refactor-buildHeaders-opencode.test.ts caused by the
same default flip (pin OPENCODE_SYNTHESIZE_CLI_HEADERS=false for the
characterization suites that predate #10571; use a genuinely
CLI-looking UA where the preserved-UA test requires one).
- Fix a real bug found via TDD while adding the mandated free-tier
routing regression test: the big-pickle/*-free short-circuit in
open-sse/services/model.ts checked activeProviders?.has("opencode")
literally, but getActiveProviderSet() canonicalizes every connection's
provider id through resolveProviderAlias(), which rewrites "opencode"
to "opencode-zen" via a manual override — so an active no-auth
opencode connection could never satisfy the check. Now checks both
opencode-family candidate ids. Proven with a test that fails on the
original code and passes with the fix (both connections active with a
stale synced catalog omitting big-pickle).
- Extract the noAuth-provider echoModel aliasing in chatCore.ts into a
pure, directly-testable helper (open-sse/handlers/chatCore/noAuthEchoModel.ts),
matching the existing chatCore god-file decomposition pattern.
- Add regression tests for generateSessionId()-based x-opencode-session
fingerprinting (stable within a conversation, changes on model/message
changes), the free-tier routing short-circuit, and the noAuth echoModel
aliasing.
- Add the changelog.d/ fragment and sync docs/reference/ENVIRONMENT.md's
OPENCODE_SYNTHESIZE_CLI_HEADERS/OPENCODE_USER_AGENT/OPENCODE_CLIENT/
OPENCODE_PROJECT rows to the new defaults.
Does NOT resolve whether flipping OPENCODE_SYNTHESIZE_CLI_HEADERS's
default was the right call, and does NOT touch the separate open PR
#10357 which flips the same flag with a different literal default value
- that decision is left to the maintainer at merge time.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
GET /v1/models listed google/gemini-embedding-001 but omitted
google/gemini-embedding-2 even though that id already returns 3072-d vectors.
Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Native gemini-embedding-2 400s with a dead-end credentials error even though
openrouter/google/gemini-embedding-2 already serves 3072-d vectors.
Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(vision): preserve high detail for inline images
* fix(vision): scope high-detail image default to OpenCode clients
defaultImageDetail() was applied at prepareUpstreamBody, the shared
upstream-body prep path for every provider and format, not just the
OpenCode path the fix targets. Gate it on isOpencodeClient (the
existing User-Agent/x-opencode-* header signal already used for
bypassDefaultToolLimit at this call site) so non-OpenCode callers keep
the provider's own image detail default. Adds a regression test
covering a non-OpenCode caller against the same opencode-zen provider.
* fix(vision): document and test the global vs OpenCode-only detail scope
The OpenCode-only high-detail default in chatCore/upstreamBody.ts
(defaultImageDetail, gated on isOpencodeClient) forwards the caller's
own image_url.detail and was already correctly scoped in a prior
commit on this branch.
The internal vision-bridge describe self-loop (visionBridgeHelpers.ts)
is architecturally global: VisionBridgeGuardrail runs for every
caller/provider whenever the target model lacks vision support, and
there is no client-identity signal at that layer to gate on. Its
describe prompt explicitly asks the vision model to transcribe visible
text, so requesting "high" detail unconditionally is justified on its
own merits (OCR accuracy), independent of the OpenCode motivation.
Adds a compatibility assertion proving the Anthropic wire-format
branch of the same describe self-loop carries no `detail` field (it
has no such concept) and is therefore unaffected by this default, and
documents the split (OpenCode-only forwarding vs. global describe
default) in docs/security/GUARDRAILS.md.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: rinseaid <rinseaid@rinseaid.net>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(a2a): use a constant-time bearer compare in /api/a2a/tasks
* fix(a2a): drop new Function from tasks-auth test in favor of dynamic import
The regression test for the constant-time bearer compare loaded tokensMatch
and authenticateA2A by regex-extracting their source and eval'ing it via
new Function, which trips the repo's no-new-func/no-implied-eval ESLint
rules (error-level everywhere, including tests). Export both helpers as a
test seam from the route module (mirrors the existing
bridgeSecretMatches/authRouteInternals pattern) and import them directly
in the test instead. Also drops the now-unused eslint-disable directives.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* feat(providers): optional AI Horde API key and live image catalog
Allow a registered Horde key on the no-auth connection and send it for
chat and image jobs. List only image models that currently have workers,
and generate through Horde's native async API.
# Conflicts:
# open-sse/config/imageRegistry.ts
# src/app/(dashboard)/dashboard/providers/[id]/ProviderDetailPageClient.tsx
# src/shared/constants/providers.ts
# src/sse/services/auth.ts
* fix(providers): validate AI Horde keys against find_user
The OpenAI-compatible /v1/models probe returns 200 for any Bearer token
on oai.aihorde.net, so Check always succeeded. Use Horde's /v2/find_user
lookup instead; an empty key still counts as the optional anonymous path.
* chore(changelog): name the AI Horde fragment for #10542
* fix(images): harden AI Horde optional-key selection and outbound fetches
- Optional-key selection now honors connection health (rate-limit cooldown
and terminal/unavailable test status) before handing a stored key back,
rotating to the next healthy key or falling back to the anonymous no-auth
path instead of using an unhealthy stored key.
- Route the Horde submit/check/status/cancel and catalog calls through the
repository's bounded outbound-fetch helper (timeout, no more bare fetch())
and route R2 image downloads through the established bounded remote-image
fetch (SSRF host guard, DNS-rebinding pin, streaming byte cap, redirect
limit) instead of an unbounded fetch().
- Extend the generation deadline to cover the full request lifecycle
(catalog freshness check, submit, polling, and image download), and add a
regression test proving that exceeding the deadline issues a DELETE
cancel to Horde's API rather than only timing out locally.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: pqr <pqr@soraka.ititti.es>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(sse): clear quota_exhausted cooldown when real window recovers
The claude-token-fallback combo was not auto-returning to Sonnet/Opus
after a subscription 429 recovered. maybeClearRecoveredQuotaState()
was honoring the synthetic 1h cooldown (SUBSCRIPTION_QUOTA_COOLDOWN_MS,
persisted when no upstream reset was parseable) instead of the REAL
per-window resetAt returned by the scheduled quota poller, so the
connection stayed locked long past the actual quota reset.
Add windowStillExhaustedAfterRealReset() and use it to decide recovery
per-quota-window: a quota_exhausted connection now clears as soon as no
governing window is still exhausted with a future-or-unknown real
reset, instead of waiting out the synthetic cooldown. Falls back to the
previous synthetic-cooldown guard when the fetch has no quota object at
all (degraded/failed shape) so existing behavior is unchanged there.
Preserves the existing kimi-coding partial-refresh semantics: an
exhausted window with no parseable resetAt still blocks recovery.
* fix(sse): preserve Claude extra-usage block from general quota recovery
maybeClearRecoveredQuotaState()'s new per-window recovery check (added in
this branch) only inspected usage.quotas, so a Claude connection blocked by
the extra-usage guard (lastErrorSource: "extra_usage") could be released
just because the session/weekly quota windows looked recovered, even while
extraUsage.queued was still true. Extra-usage blocking is orthogonal to
quota-window exhaustion and must only be released by
syncClaudeExtraUsageStateIfNeeded (buildClaudeExtraUsageConnectionUpdate).
Add a guard that keeps the connection locked when lastErrorSource is
"extra_usage", the blockExtraUsage policy is still enabled, and the fresh
usage snapshot still reports extraUsage.queued === true.
Add an integration test walking the real
fetchLiveProviderLimitsWithOptions -> syncClaudeExtraUsageStateIfNeeded ->
maybeClearRecoveredQuotaState call chain with recovered quota windows but
extraUsage.queued=true, asserting the connection stays unavailable with
lastErrorSource still "extra_usage".
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(settings,auth): default debugMode to false and skip account rotation on model-unsupported 400
* fix(auth): disambiguate model-unsupported from auth-credential 400
The model-unsupported guard used MODEL_ACCESS_DENIED_PATTERNS directly,
which also matches auth-credential errors like 'invalid api key for
model X'. Add the AUTH_CREDENTIAL_ERROR_PATTERNS exclusion (same as
checkFallbackError) and use provider_model_unsupported log reason.
Addresses maintainer feedback on PR #10525
Signed-off-by: Minxi Hou <houminxi@gmail.com>
* fix(auth): narrow model-unsupported guard to avoid misclassifying account-scoped entitlement 400s
The #10460 guard reused MODEL_ACCESS_DENIED_PATTERNS directly, which also
matches ambiguous "access"/"permission" phrasing (e.g. "does not have
permission to access this model") that commonly signals an ACCOUNT-scoped
entitlement gap (PRO vs free tier) rather than a genuinely provider-wide
unsupported model — a different account of the same provider may still
have access, so those must keep rotating normally instead of being
short-circuited.
Extract isProviderModelUnsupported400() in accountFallback.ts: reuses the
same AUTH_CREDENTIAL_ERROR_PATTERNS exclusion checkFallbackError's 400
branch already applies, narrowed to a strict subset of unambiguous
"provider does not serve this model at all" phrasings. auth.ts now calls
this shared helper instead of testing the broader patterns in isolation,
and exposes the sanitized reason ("provider_model_unsupported") on the
returned result, not just in the log line.
Also fix DATA_DIR test-isolation ordering in
account-fallback-service.test.ts: it was assigned after the first
dynamic import of accountFallback.ts, which transitively imports
src/lib/db/core.ts (DATA_DIR is captured once at module-load time), so
the intended isolated test directory was silently never used. Move the
assignment before any transitive DB import, and add regression tests for
the 3-account rotation contract: exactly one upstream call for an
unambiguous provider-wide 400 with the combo advancing to the next
target, continued rotation for account-scoped 401/403/429 and for the
permission/entitlement 400 case that motivated this narrowing.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Signed-off-by: Minxi Hou <houminxi@gmail.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(providers): test token-backed web sessions
* fix(providers): restrict token-web-session test dispatch to validated providers
Narrow shouldUseApiKeyConnectionTest to the token-kind web-session providers
that actually have a token-aware connection validator (deepseek-web, kimi-web,
tinycms-web, copilot-m365-web, copilot-web, zai-web). WEB_SESSION_CREDENTIAL_REQUIREMENTS
marks more providers as kind: "token" than have a matching validator in
SPECIALTY_VALIDATORS (hailuo-web, microsoft-designer-web, t3-chat-web, promptql) — those
were falling through to the generic cookie-based validateWebCookieProvider probe, which
sends the stored credential as a Cookie header and treats most non-401/403 responses as
valid, so an invalid token could be reported as a healthy connection.
Add regression coverage for hailuo-web and promptql (plus microsoft-designer-web and
t3-chat-web) proving they stay off the API-key test path, and for every currently
validated token-kind provider proving they still use it.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(dashboard): count live usage_history rows in Free Tier 'used this month' (#10381)
* fix(dashboard): use an indexable UTC month-range predicate for used-this-month (#10381)
sumUsageTokensThisMonth() filtered usage_history with
substr(timestamp, 1, 7) = strftime('%Y-%m', 'now') — a substr() expression
SQLite cannot use a range index on, and fragile against any timestamp
that isn't exactly ISO-shaped. Replace with an indexable inclusive-start/
exclusive-end UTC range: timestamp >= <month start> AND timestamp <
<next month start>, matching the ISO 8601 format saveRequestUsage()
already writes.
Adds a boundary regression test: the first instant of the current month
is included, the last instant of the previous month is excluded, and a
next-month row is excluded too (covers the upper bound substr() could
never express).
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* fix(combo): surface context-overflow before compression so oversized requests fail fast with a clear error (#10225)
* fix(combo): make context-overflow deferral target-aware for native Codex passthrough (#10225)
The deferral added by the prior commit checked only operator-named
compression exclusions when deciding whether at least one target "can
compress" — it never accounted for native Codex Responses passthrough
targets, which chatCore.ts unconditionally excludes from compression
(compressionExcluded = nativeCodexPassthrough || ...). Deferring on such
a target's account let an oversized request skip both the combo preflight
AND compression, reaching fetch() uncompressed.
Thread the same request-shape facts chatCore.ts uses
(shouldUseNativeCodexPassthrough: provider/sourceFormat/endpointPath/body/
headers) down into getKnownContextOverflow so the deferral decision can
never drift from chatCore's own — a native-codex-passthrough target now
never counts as "compressible", so a pool made only of such targets keeps
the fast local 400 instead of a wasted round trip.
Adds regression coverage: the pure getKnownContextOverflow target-aware
check, an end-to-end handleComboChat proof that a native-codex-only pool
fails fast with zero dispatches, and two real handleChatCore-path tests
proving compression actually reduces the dispatched body when eligible,
and that a still-too-large-after-compression request is rejected locally
without an upstream call.
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* fix(resilience): keep combo quality and auth reasons separate and redact connection labels in terminal errors (#10314)
* fix(resilience): sanitize identifiers in error text, add explicit terminal-status policy, fix classifier ordering (#10314)
Four gaps in the prior combo-error-aggregation fix:
- formatComboOutcomes() only redacted connection identifiers in the model
label, never in the raw upstream error TEXT — a proxy echoing a
connection/account id back in its error body leaked it into the
client-facing terminal message. Redact both.
- The terminal HTTP status was still `lastStatus` — whichever target
happened to fail last, independent of the other targets' reasons. Add
resolveComboTerminalStatus(): preserve a 4xx only when every eligible
target's failure is genuinely "the request is invalid" (model-class);
a heterogeneous mix (e.g. a quality failure + a sibling's 401) now
normalizes to a 5xx-class status reflecting an infra/provider problem,
never a misleading client error borrowed from an unrelated target.
- classifyComboOutcome()'s ordering had `status === 408 || status >= 499`
checked before `status >= 500`, making the provider branch permanently
unreachable — every real 5xx (500/502/503/504) was silently mislabeled
as "timeout". Fixed to an exact match (408/499) and gave 429 its own
explicit `rate_limit` kind instead of falling into the generic "model"
(request-invalid) bucket by accident.
- Added an integration-level regression driving the real handleComboChat
wiring end-to-end (quality failure + sibling 401, and a success-after-
quality-failure case), not just the pure aggregation helpers.
Updated three pre-existing tests whose assertions encoded the OLD
last-writer-wins contract this fix intentionally supersedes (#8486 Part B
antigravity retryAfter tests, two combo-routing-engine status/message
tests) to the new, more precise contract; verified the underlying #8486
concern (wrong target's retryAfter header) is still honored under the new
status policy.
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* fix(providers): fall back to public Code Suggestions endpoint on GitLab Duo direct_access 401 (#10365)
* fix(providers): extend GitLab Duo 401 fallback to the connection-test path (#10365)
The chat-completion path (open-sse/executors/gitlab.ts) already falls back to
the public Code Suggestions completions endpoint when the direct_access
exchange is rejected with 401, but testOAuthConnection() / the dashboard
Retest button still reported the connection unhealthy on the same 401 —
even though a real chat request through that connection would have
succeeded via the fallback. Apply the identical fallback contract to the
connection-test path (first attempt and the post-refresh retry), sharing the
predicate with the executor via shouldFallbackToPublicCodeSuggestions.
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* fix(compression): add i18n support for less-code and terse-prose
Translates less-code output style to pt-BR, vi, ja, and id. Adds missing vi translation to terse-prose caveman mode. Removes less-code from English-only allowlist and updates matrix tests.
Fixes#10426
* docs(compression): add output styles coverage table
Adds the requested Output Styles matrix to the compression guide covering styles, supported languages, and intensity levels.
Fixes#10426
* fix(cli): recognize {connections} envelope from /api/providers
GET /api/providers returns {connections, total} (src/app/api/providers/
route.ts:78), but `omniroute test --all-providers` and `omniroute oauth
providers` both parsed the response as `data.providers ?? data.items ??
data` -- an object, not an array -- so `.filter` threw
"(data.providers ?? data.items ?? data).filter is not a function" on
every call. keys.mjs already had the correct fallback chain
(`data.keys || data.connections || data.items || data`); apply the same
`connections` field to both remaining call sites.
* test(cli): cover provider connections envelope
Add regression coverage for both CLI consumers of the /api/providers connections envelope.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(memory): auto-check Qdrant health on mount and stop false-red badge
The Qdrant engine card on /dashboard/memory?tab=engine showed a red
"Error" badge after every page refresh even when Qdrant was healthy:
the badge derives its state from a health check, but the mount effect
only fetched settings + embedding models — health started as null and
the render treated `health?.ok` (undefined) as a failure. Clicking
"Test connection" (which runs the same server-side /readyz check)
immediately turned it green, proving the connection was fine.
Two changes:
- Auto-run the health check on mount once settings load and Qdrant is
enabled, so a refreshed page reflects the real state (verified live:
/api/settings/qdrant/health returns ok:true in ~2ms on a healthy
compose deployment).
- While health has not been checked yet (null), render a neutral gray
"Testing..." state instead of red — red is now reserved for an
actual failed health check.
Regression test added (fails on the old code): with enabled settings
and a healthy mock, the card must hit /api/settings/qdrant/health on
mount and show statusActive, never statusError.
* chore(changelog): fragment for #10489
* Merge branch 'release/v3.8.50' into fix/qdrant-health-badge
* 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): align optional-transformers-dependency with onnxruntime ~1.24.3 pin (base #10543)
* docs(fix): sync 150-migration count and document PROXY_LOG_INCLUDE_IPS (base drift #10348/#10507)
* fix(memory): re-check Qdrant health after saving settings
save() optimistically flipped enabled and started the PUT while the mount
effect could immediately GET /api/settings/qdrant/health against the OLD
persisted settings. If that GET won, it returned not_configured/failed and -
because health was non-null - the effect never retried after the PUT
succeeded, leaving a healthy Qdrant red until a manual Test connection.
Invalidate health (generation counter + setHealth(null)) at save start and
after a successful PUT, then explicitly schedule a fresh check: setting
health to null alone is not enough, React bails on the no-op when health is
already null (the exact GET-wins ordering). Stale responses are dropped via
the sequence guard so an in-flight pre-save check can never overwrite the
post-save result. Adds a regression test covering enable ordering.
Addresses PR #10489 review finding (issuecomment-5312271806).
* fix: narrow omniglyph transform result union (merge base aa912c42a typecheck gate)
* test(compression): align contract tests with base aa912c42a merge (providerTransport shape, engine metadata)
* fix(memory): silence set-state-in-effect on Qdrant auto health-check
The health-check re-check fix (3469234) introduced an effect that calls
checkHealth() (an async fetch that eventually calls setState) directly
from a useEffect gated on loading/enabled/health. The
react-hooks/set-state-in-effect rule flags this as a potential cascading
render, matching the same pattern already accepted elsewhere in the
dashboard (FreePoolTab.tsx, ConnectionsTable.tsx) for gated async
data-fetch effects. Suppress with the established inline convention;
no behavior change.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(memory): drop unused set-state-in-effect disable (rule inert on pinned react-hooks 7.0.1)
The eslint-disable-next-line for react-hooks/set-state-in-effect is unused:
eslint-plugin-react-hooks@7.0.1 (lockfile-pinned) does not report this rule,
so the directive itself was flagged as a warning and the 'No new ESLint
warnings' CI gate failed with --max-warnings 0. The effect body only calls
checkHealth() (async fetch) with no raw setState, so no disable is needed.
* ci(quality): sync ratchet configs to release/v3.8.50 (0a74bfbde) merge
- re-freeze open-sse typecheck baseline at merged-tree live counts
(64 stale entries dropped, 11 frozen; base video/usage drift covered)
- register tests/unit/video-bridge-drilldown-route.test.ts in stryker tap.testFiles
- regenerate skills/cli-contexts/SKILL.md (contexts migrate docs from CLI closure)
---------
Co-authored-by: Rouzbeh <rqzbeh@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(sse): downgrade adaptive thinking and gate context-1m beta on model eligibility (#10119)
* fix(sse): thread resolved model into DefaultExecutor's anthropic-beta merge (#10119)
DefaultExecutor.buildHeaders() merged the client-negotiated anthropic-beta
header without ever passing the resolved target model into
mergeClientAnthropicBeta(), so the context-1m-2025-08-07 eligibility gate
added earlier in this PR could not see which model a combo/fallback had
actually routed to at this call site. buildHeaders() now accepts an
optional model parameter (mirroring BaseExecutor.buildHeaders' existing
signature and the pattern already used by grok-cli.ts/qoder.ts) and
forwards it through, so an ineligible model target (e.g. Haiku) has the
beta dropped instead of forwarded blind.
Restores a CHANGELOG bullet (PR #10366) that a prior merge auto-resolve
had dropped from this branch.
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* fix(admission): resolve adaptive latency-collapse self-lock with solo-progress and idle recovery (#10111)
* fix(admission): refresh recovery ceiling on updateConfig (#10111)
updateConfig() clamped currentLimit to the new min/maxLimit but left
recoveryCeiling pinned to the value computed at construction time, so
a raised initialLimit could never recover past the stale ceiling and
a lowered one could leave the ceiling above the new maxLimit.
Recompute recoveryCeiling from the new initialLimit on every
updateConfig call, clamped to the (possibly also new) min/maxLimit.
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* fix(usage): wire agentrouter balance quota into dashboard Quota UI (#10078)
* fix(usage): render AgentRouter wallet balance as USD in the Quota UI (#10078)
The prior fix wired AgentRouter's balance into getUsageForProvider() and
USAGE_SUPPORTED_PROVIDERS, but the actual dollar figure never reached the
Dashboard Quota UI: quotas.balance.remaining carried a synthetic two-state
percent (100/0) instead of the real dollarBalance, and the Provider Limits
renderer only formats a row as "$X.XX" when isCredits/currency/creditCount
are set, which the generic quota-parsing path never sets. A configured
balance rendered as a bare "100% left" percentage, not USD.
Shape quotas.balance.remaining as the real USD amount (clamped to 0) and add
an agentrouter branch to quotaParsing.ts that builds a credits-style row
(same buildCreditsQuota() pattern as DeepSeek/Claude extra-usage), so a
configured balance shows a currency-formatted dollar amount and an
exhausted balance always renders as exactly $0.00.
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* fix(providers): resolve combo names on /v1/audio/speech and /v1/videos/generations
`GET /v1/models` advertises combos with `owned_by: combo`, and chat, embeddings,
transcriptions (#9134) and images (#8986, #9239) all resolve those names. Speech
and video did not: both rejected a combo name at model validation, before any
resolution could happen.
POST /v1/audio/speech {"model":"my-combo","input":"hi"}
-> 400 Invalid speech model: my-combo. Use format: provider/model
POST /v1/videos/generations {"model":"my-combo","prompt":"a cube"}
-> 400 Invalid video model: my-combo. Use format: provider/model
A client picking a model out of /v1/models therefore could not tell which
entries the catalogue would actually accept, and callers ended up hardcoding
vendor ids for these two routes while using combo names everywhere else.
Both routes now mirror the images route: detect a combo name before the
provider lookup and divert to a strategy executor. The two new executors follow
imageCombo — expand targets with resolveComboTargets(), filter to targets the
route can actually serve, walk them in priority order, and return the first
success or the last failure, with 400/401/403 treated as terminal.
Two details differ from the image strategy:
Speech filters at model level rather than provider level. parseSpeechModel()
resolves a provider prefix without checking that the model behind it can speak,
so `openai/gpt-4o` would otherwise be accepted as a target and fail only once
dispatched. The filter now checks the provider's own model list, and keeps
targets from dynamic provider nodes that do not enumerate models.
Speech also returns the handler's Response untouched instead of building a JSON
body, because that route streams audio; only the ADD-only meta headers are
attached, exactly as the direct path does. The failure branch is the only place
the body is read.
successfulMediaGenerationResponse() gains optional `strategy` and
`fallbackAttempts` so the video strategy can report them the way imageCombo
does, rather than duplicating the cost calculation. Both are omitted on the
direct single-model path, where neither is meaningful.
Tests mirror tests/unit/combo/image-combo.test.ts for both routes: combo not
found, no capable targets, empty combo, and targets present with no provider
connection. 16/16 pass across the three combo test files.
* fix(providers): preserve local overrides, custom models and per-target prompt rules through video combo dispatch
executeVideoCombo() diverged from the direct /v1/videos/generations route in
three ways: it dropped the ComfyUI-style local-override credential lookup for
authType:"none" targets, its capability filter only matched the built-in
video registry (skipping custom OpenAI-compatible provider nodes tagged with
the "videos" endpoint), and the route validated the prompt against the
unresolved combo name before combo targets were expanded — rejecting
prompt-optional I2V targets that never got the chance to opt out.
Extracts the shared resolution rules (resolveVideoModelTarget,
isVideoPromptOptional, resolveLocalOverrideCredentials) into
src/app/api/v1/_shared/videoModelResolution.ts so the direct route and the
combo executor apply identical rules, moves the combo-name diversion ahead of
the prompt-required check so validation runs against the real resolved
target, and adds per-target prompt validation inside the combo loop so a
missing prompt only rules out that target instead of the whole combo.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(dashboard): send periodic WS heartbeat pings to stop live-dashboard reconnect churn
The live-dashboard WS client (src/hooks/useLiveDashboard.ts) only sent a
subscribe frame on open and never emitted the protocol's { type: "ping" }
heartbeat. The server (src/server/ws/liveServer.ts) refreshes client
liveness only from inbound messages and terminates any client idle past
HEARTBEAT_TIMEOUT_MS (35s), so a healthy, connected-but-idle dashboard
client was force-terminated roughly every 35-45s, causing constant
reconnect churn (#10319).
Fix (both directions, per the analyzed plan):
- Client: start a 15s ping interval on open, cleared on close/unmount/
reconnect, so the connection stays inside the server's liveness window.
- Server (defense in depth): the outbound heartbeat pong now also bumps
client.lastActivity, so even a third-party client that never pings is
not dropped for being idle.
Regression coverage:
- tests/unit/useLiveDashboard-heartbeat.test.tsx: fast fake-timer check
that the hook emits periodic ping frames and cleans up the interval on
close/unmount (no leaked timers).
- tests/integration/live-ws-heartbeat-keepalive.test.ts: real WS-server
integration test asserting a silent-but-subscribed client stays
connected past the 35s heartbeat timeout (~50s window), converted from
the plan file's TDD RED repro.
Closes#10319
* fix(dashboard): stop renewing stale LiveWS sockets
Keep application-level heartbeat responses from refreshing server liveness, and add a regression covering silent stale sockets alongside clients that answer protocol heartbeats.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* fix(dashboard): make provider card warning indicators expose the interaction they advertise
The usage-risk indicator (subscriptionRisk) promised "click for details" in its
tooltip but was a bare <span> with no onClick/role/dialog. The connection
warning-count badge exposed neither a title tooltip (reasons) nor any click
affordance, even though the reasons already exist in
providerSpecificData.apiKeyHealth[].
Turn the risk indicator into a real <button role/aria-haspopup="dialog"> that
opens an accessible Modal reusing the existing riskNotice copy, and wrap the
warning badge in a keyboard- and pointer-interactive control that surfaces a
sanitized reasons summary (max failure count + relative last-failure time,
never raw upstream error text) and navigates to the connection detail/health
view on activation. Both indicators are now visually distinct (bare icon vs.
pill Badge).
Closes#10261
* i18n(providers): sync riskNotice.detailsTitle + warningNotice keys to all 42 locales (#10261)
Real Vietnamese translations (vi.json has a strict no-__MISSING__-marker gate);
other 41 locales carry the sync-ui __MISSING__ placeholder pending the normal
translation pass.
* test(dashboard): relocate provider warning regression test
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* fix(open-sse): stop concurrent requests colliding on dedup hash for non-OpenAI formats
computeRequestHash() in requestDedup.ts projected the prompt content from
body.messages only. The dedup site in chatCore.ts hashes the *translated*
(target-format) request body, and non-OpenAI target formats don't carry a
messages field: Gemini-translated bodies use `contents`, Responses-API
bodies use `input`. So for those formats messages was always undefined,
every prompt hashed to the same null-backed value for a given model, and
concurrent requests with different prompts joined the same in-flight
promise -- the second caller silently received the first caller's
response verbatim (#10249).
Fix: project body.messages ?? body.contents ?? body.input ?? null instead
of only body.messages, keeping the rest of the canonical hash projection
unchanged. Genuinely identical concurrent requests still dedupe (the
intended perf behavior); different prompts under Gemini/Responses-API
target formats no longer collide.
Regression test: tests/unit/request-dedup-10249.test.ts reproduces the
two collision scenarios from the plan-file (Gemini `contents`,
Responses-API `input`), confirms the OpenAI `messages` case was already
correct, and asserts identical-request dedup keeps working. Verified
RED (byte-identical hashes 0b24fd88.../dc16d5b7... pre-fix) -> GREEN
(distinct hashes, dedup preserved) against this exact diff.
* fix(open-sse): cover nested translator shapes + system fields in dedup hash (#10438)
computeRequestHash() only read top-level body.messages ?? body.contents ??
body.input, but several translated request shapes nest their prompt
content: the Antigravity Cloud Code envelope under request.contents, and
Kiro under conversationState.currentMessage.userInputMessage.content (plus
conversationState.history). Two different concurrent prompts to those
targets could hash identically and share/leak a response between callers.
Adds extractPromptContent()/extractSystemContent() helpers covering every
prompt-bearing shape produced by open-sse/translator/request/*.ts
(OpenAI/Cursor messages, Claude messages+system, Gemini contents+
systemInstruction, Responses input+instructions, Antigravity and Kiro
nesting), and folds system/instructions/systemInstruction into the
canonical hash so two requests with the same user message but a different
system prompt no longer collide either.
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* fix(sse): gate structural chat admission shedding on real heap pressure
Closes#10183, Closes#10268
3.8.49 (#9654/#9940) replaced the 3.8.48 heap-ratio shed
(heapUsed/heapLimit >= 0.75) in chatBodyAdmission.ts with an
unconditional CHAT_MAX_HEAVY_IN_FLIGHT=1 structural lease. A second
concurrent "structurally heavy" chat request (>=200 messages, >=64
tools, or >=32k estimated tokens — routine for coding-agent fan-out
like Hermes/Cursor/Claude Code) was hard-rejected with a retryable
HTTP 503 chat_admission_busy/structure_limit regardless of actual
heap pressure, even on a host with ample free RAM.
Restore the heap-conditional gate as an ADDITIONAL check layered on
top of (not a replacement for) the #9654 bounded-concurrency /
per-connection-lane protection: when heavyweight capacity is busy,
only enter the bounded-wait/shed path when a live heap-pressure probe
(heapUsed / v8 heap_size_limit >= OMNIROUTE_CHAT_ADMISSION_HEAP_SHED_RATIO,
default 0.75) confirms real pressure. A healthy heap now admits the
second heavy request immediately via a no-op lease instead of parking
or shedding it. The probe is injectable via
admitChatStructure({ heapPressureCheck }) for deterministic tests.
Regression tests:
- tests/unit/bug-10183-admission-heavy-healthy-heap.test.ts (new,
permanent): healthy-heap 2nd heavy request now admitted (was RED);
genuinely pressured heap still sheds it.
- tests/unit/probe-10268-structural-503.test.ts (promoted to
permanent): the exact reported 503 chat_admission_busy shape is
still produced under real heap pressure, and the same fan-out is
admitted on a healthy heap.
- tests/unit/chat-body-admission.test.ts,
tests/unit/chat-body-admission-queue.test.ts,
tests/unit/per-connection-admission-9654.test.ts updated to inject
heapPressureCheck: () => true where they exercise the busy/shed
path, preserving #9654/#4380 coverage.
Gates run: npm run typecheck:core (clean), eslint --suppressions-location
config/quality/eslint-suppressions.json on changed files (clean),
scripts/check/check-file-size.mjs (OK), scripts/check/check-test-discovery.mjs
(OK), focused admission suite (68/68 passing) and npm run test:unit
(in progress at commit time under heavy shared-devbox contention from
a 13-way parallel session fan-out; no admission-related failures
observed through 1873 lines of output, the sole failure seen was a
pre-existing unrelated proxy/search timeout consistent with known
load-induced flakiness, not a regression from this change).
⚠️ base-red inherited: #9985 — ESLint errors (2) from #10250
* docs(env): document OMNIROUTE_CHAT_ADMISSION_HEAP_SHED_RATIO (#10183, #10268)
* fix(sse): bound the healthy-heap admission fast path (#10437)
The #10183/#10268 fix admitted a busy heavyweight request immediately
whenever the heap was healthy, via an unconditional no-op lease with no
bound of its own -- an unlimited number of "healthy heap" requests could
pile in ahead of the heap-pressure shed path, defeating the point of
admission control.
Adds an independent, bounded healthy-heap headroom budget
(CHAT_ADMISSION_HEALTHY_HEADROOM, tryAcquireHealthyHeadroom()) that the
healthy-heap fast path draws from; once exhausted, requests fall through
to the same bounded-wait/shed path used under real heap pressure, which
is otherwise unchanged. Also fixes a pre-existing gap in
per-connection-admission-9654.test.ts's shared-budget test, which needed
an explicit heapPressureCheck override to keep exercising the #10110
invariant now that a healthy heap gets bounded headroom instead of an
outright reject.
* docs(env): document OMNIROUTE_CHAT_ADMISSION_HEALTHY_HEADROOM in .env.example
Documented in docs/reference/ENVIRONMENT.md but missing from .env.example,
caught by the env-doc-sync gate when combined with other PRs in the
release merge-train.
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* fix(antigravity): strip trailing model turn for native Gemini requests too
Newer Gemini endpoints reject a request ending on a model turn with HTTP
400 'Requests ending with a model turn are not supported' — the same
rejection class Claude hits via Vertex. transformRequest() previously
wired stripTrailingAntigravityAssistantTurn() only into the isClaude
branch, so native Gemini models routed through Antigravity kept a
trailing role:model entry and hit the 400.
Extend the guarded strip (never empties contents) to native Gemini
models too, gated by upstreamModel including "gemini". The Claude
path is untouched (byte-identical), preserving PR #6114's live
validation against Vertex Claude.
Flips tests/unit/antigravity-claude-prefill-strip.test.ts test (b),
which previously asserted the buggy pass-through, and adds (b2) for
the gemini-3-flash-agent tier.
Closes#10104
* fix(antigravity): scope Gemini trailing-turn workaround
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* fix(sse): bridge generic compatible-provider type id to concrete node id in credential lookup
getProviderSearchPool only bridged a provider string to a node id via the
node's prefix, never via the generic derived type id
(openai-compatible-chat / openai-compatible-responses / anthropic-compatible)
that resolveProviderNodeForConnection already accepts at connection-creation
time (#4421). A connection persisted under the generic type id was therefore
unreachable when the chat path resolved the concrete uuid node id, surfacing
"No active credentials for provider: openai-compatible-chat-<uuid>" even
though the key and model catalog were valid.
Closes#10085
* fix(sse): register #10085 mutation-coverage test file in stryker.conf.json
check:mutation-test-coverage --strict flagged
tests/unit/10085-compatible-generic-vs-uuid-credential.test.ts as a
covering test for src/sse/services/auth.ts that was missing from
stryker.conf.json's tap.testFiles, per the CI Fast Quality Gates run
on PR #10434.
* fix(sse): disambiguate compatible provider credential lookup
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(sse): require unambiguous type in both credential-lookup bridge directions (#10434)
getProviderSearchPool()'s generic-type<->concrete-node-id bridge (#4421,
#10085) only applied the "exactly one node of this derived type" ambiguity
guard to the concrete-id -> generic-type direction. The generic-type ->
concrete-id direction added every node sharing a derived type to the
search pool unconditionally, so a bare generic-type lookup could resolve
to a connection scoped to one specific node's baseUrl/headers even when a
second node shares the same derived type -- leaking that node's
credentials/upstream URL into an unrelated node's request.
Both directions now share the same typeIsUnambiguous gate, mirroring the
rule already enforced by selectProviderNodeForConnection() for connection
creation (src/lib/db/providerNodeSelect.ts, #4421).
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* fix(dashboard): remap Kimi Code API-key save to admitted managed id (#10096)
The unified Kimi Code card's API-key branch posted provider: "kimi-coding"
to POST /api/providers. "kimi-coding" is an OAuth-primary managed id, not
an admitted API-key/dual-auth connection id, so the backend correctly
rejected it with 400 "Invalid provider" even though key validation passed.
Add resolveApiKeySaveProviderId() in useApiKeySave.ts to remap the posted
provider id to the dedicated, admitted managed API-key id
"kimi-coding-apikey" for the API-key save flow only. The OAuth flow
(handleOAuthSuccess in ProviderDetailPageClient.tsx) never calls this hook
and keeps posting "kimi-coding" unchanged.
Regression test: tests/unit/bug-10096-kimi-coding-apikey-save.test.ts
* fix(dashboard): remap Kimi Code bulk API-key save
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* fix(proxy-subscriptions): allow local/loopback proxy-subscription fetch URLs
The subscription fetch guard (fetchGuard.ts) unconditionally blocked all
loopback/private IP ranges as SSRF protection, but the same feature already
permits loopback for the routing half (coreEndpoint.ts's
ALLOWED_LOCAL_CORE_HOSTS) — so an operator could route traffic through a
loopback core but could not fetch a proxy list from a loopback HTTP server.
Make the fetch guard local-first by reusing the existing
areLocalProviderUrlsAllowed() policy (default ON) from
outboundUrlGuardPolicy.ts: loopback/private hosts are now allowed as fetch
targets by default, while cloud-metadata/link-local (169.254.0.0/16, incl.
169.254.169.254 IMDS) and the unspecified address stay blocked
unconditionally, mirroring the provider-validation guard's "block-metadata"
mode. Callers that want the old strict behavior can pass
{ allowLocal: false }.
Closes#10158.
* fix(proxy-subscriptions): unwrap IPv4-mapped IPv6 + full fe80::/10 range (#10416)
The #10158 SSRF guard left two gaps on the IPv6 side: an IPv4-mapped IPv6
literal (::ffff:a.b.c.d) skipped IPv4 range checking entirely, and the
link-local check only matched strings literally prefixed with "fe80"
instead of the full fe80::/10 range (fe80:: - febf:ffff::), so fe90::,
febf:ffff::, etc. were wrongly allowed through.
isIpv6Blocked() now unwraps mapped IPv4 addresses (both the dotted-quad
and WHATWG-normalized hex-group forms) and re-checks them against the
IPv4 rules, and link-local detection parses the first hex group's numeric
value against the 0xfe80-0xfebf range instead of a string prefix.
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
* fix(translator): Normalize tool call names from lowercase to PascalCase (#1)
* Fix: Map lowercase tool names from Antigravity (Gemini format) to Claude Code expected PascalCase
* Fix: toolNameMap in fun restoreClaudePassthroughToolUseName
* fix(translator): Normalize tool call names from lowercase to PascalCase when translating upstream responses (OpenAI, Gemini, Antigravity) to Claude Messages API format
This resolves `Error: No such tool available: read`/`bash`/`write` errors when using Claude Code CLI with third-party providers that emit lowercase tool names. The fix adds case-insensitive tool name lookups in `openai-to-claude.ts`, `gemini-to-claude.ts`, and related translators, ensuring tool names like `read`/`bash` are mapped to `Read`/`Bash` before being sent to Claude Code. Includes unit tests and comprehensive changelog notes ([#10250](https://github.com/diegosouzapw/OmniRoute/pull/10250))
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* fix(translator): Parse <tool_call> JSON and TOOL_CALL text formats fr… (#2)
* fix(translator): Parse <tool_call> JSON and TOOL_CALL text formats from model output
Some models (DeepSeek, Qwen) emit tool calls as text instead of proper
tool_calls JSON: either <tool_call>{...}</tool_call> or TOOL_CALL Name: {...}.
Extend extractXmlInvokeBlocks to handle all 3 formats in a single scan pass,
picking whichever pattern appears first. Includes unit tests for all formats.
* fix(translator): Parse text-format tool calls in gemini-to-claude translator
Extend the Gemini->Claude translator to detect <invoke>, <tool_call> JSON,
and TOOL_CALL text formats emitted inline in text parts (Antigravity/Gemini
models), converting them to proper tool_use content blocks instead of leaking
raw text to Claude Code.
* docs(changelog): Add changelog entry for text tool call parsing fix
* fix(translator): consolidate tool name casing normalization and restore thought-signature persistence (#3)
* fix(translator): sanitize tool_use.id and tool_result.tool_use_id to match Anthropic schema (#4)
Ensure tool IDs from OpenAI-compatible upstreams (which may contain dots, colons, or special characters) are sanitized to ^[a-zA-Z0-9_-]+$ in response translators and passthrough requests before reaching Claude endpoints.
* fix(responses): preserve native tools for openai-compatible Responses targets (#5)
A Responses-shaped request to a custom openai-compatible connection whose
outbound protocol is Responses took a Responses -> Chat -> Responses round
trip, so Codex custom tools lost their grammar (`exec`), namespace groups were
flattened (`collaboration`), and tool invocations failed upstream.
Gate a native Responses passthrough on the connection's configured protocol
(`apiType: "responses"` / `_omnirouteForceResponsesUpstream`) so the original
tool definitions reach a Responses-capable upstream unchanged. Chat-only
connections keep the existing downgrade.
Closes#10374
* fix(translator): add support for 'applypatch' tool name in tool call checks
* test(translator): add unit test for apply_patch and applypatch tool name remapping
* fix(translator): remove no-explicit-any lint errors in tool-use-id-sanitization test
Type the openaiToClaudeResponse/translateNonStreamingResponse return
values with narrow local shapes instead of `any`, satisfying the
repo's no-explicit-any = error rule for tests/. No behavior change —
the same 3 assertions still pass.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* test: update 9568 casing regression to match #10392's consolidated fix
restoreClaudeToolName's static casing map now normalizes known
lowercase tool names to canonical PascalCase unconditionally on the
gemini-to-claude and openai-to-claude Claude Messages API paths (not
gated behind toolNameMap), superseding the earlier per-map-only fix
that the original #9568 regression test locked in as "expected" (it
was previously labeled a known bug case). The gemini-to-openai
passthrough path is unaffected by #10392 and keeps its original
pass-through assertion.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(services): use CLIProxy executable on Windows
* fix(services): align Windows CLIProxy artifact path
---------
Co-authored-by: tkgo11 <7.1800574e+07+tkgo11@users.noreply.github.com>
Family resolves like auto/zai with no connected models logged a warn
on every call (about once a minute per poll). Keep the empty-pool
behavior; emit the warn at most once per label per 60s.
Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
* feat(oauth): add gemini-3.7-flash models with reasoning tiers for antigravity
Support gemini-3.7-flash and its thinking tiers (low/medium/high) for antigravity and agy providers.
- Define public models, pricing, modelSpecs, and CLI tool definitions
- Map tiers to live upstream id gemini-3.7-flash-tiered
- Configure defaultThinkingBudget (low: 1024, medium: 8192, high: 32768)
- Allow executor fallback on upstream 404 and 5xx errors
- Add unit tests in antigravity-model-aliases.test.ts
* fix(oauth): expose gemini-3.7-flash as one callable antigravity/agy model
Upstream (fetchAvailableModels on daily-cloudcode-pa) only accepts the single
upstream id gemini-3.7-flash-tiered; the high/medium/low suffixed tier ids
404. Registering all four as distinct public model ids violates the base
#3696 uniqueness invariant (no two ANTIGRAVITY_PUBLIC_MODELS entries may
resolve to the same upstream id). Collapse to the single live gemini-3.7-flash
public model (aliased to gemini-3.7-flash-tiered) and drop the tiered specs,
pricing, free-catalog and CLI entries accordingly, keeping the leading public
model order (Gemini 3.6 tiers first) intact.
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
---------
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
Co-authored-by: Chewji9875 <Chewji9875@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(api): scale pool usage snapshot limits by member count (summed budget)
---------
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>
* remove: drop sunset MiMoCode provider from model catalog
* remove: drop sunset MiMoCode provider from model catalog (shared.ts)
Remove unused imports, types, and comments from shared.ts.
* remove: MiMoCode provider (Xiaomi sunset) — executor, registry, no-auth config, icon, tests
* refactor(providers): finish MiMoCode removal — sweep remaining no-auth references
Drop the leftover mimocode entries from the no-auth provider controls, the
translate-path snapshot, the eslint suppressions, and the #3061 auth-loop
test. Re-point the fingerprint-pin (#6696) and proxy-noauth (#6272) tests at
opencode, which exercises the same fingerprint path, so the removal does not
break runtime behavior.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* docs(providers): reconcile provider/executor counts after MiMoCode sunset
The base's parallel doc-count sync (#10433) pinned 340 providers / 101
executors. With mimocode removed, live code has 339 providers and 100
executors; refresh the user-facing counts (package.json description,
llm.txt, README/AGENTS, i18n llm.txt, provider reference, diagrams) so the
check-docs-counts STRICT gate stays green.
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
* test(providers): fix orphaned mimocode references after MiMoCode sunset
The sunset removed mimocode/mcode from the free-onboarding candidates and
from FINGERPRINT_PROVIDERS, but two tests still referenced them:
- free-provider-onboarding-setup: the mimocode->theoldllm substitution
introduced duplicate 'opencode' rows (impossible given the request-set
dedupe) and the wrong display name; align expectations with the actual
{opencode, theoldllm} dedupe behavior and 'The Old LLM (Free)' name.
- combo-system-prompt-templates-5501: resolveTargetFingerprint tested with
provider 'mcode', which is no longer a fingerprint provider; point it at
the remaining fingerprint provider 'opencode'.
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
---------
Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
Co-authored-by: Tushar49 <Tushar49@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
* feat(quota): Phase 2 adapters, reset timers, analytics, and dashboard API
* feat(routing): add quota-aware provider scheduling (opt-in)
* fix(db): rename migration to 148_provider_quota_state.sql
* fix(quota): harden quota state route, isolate phase2 tests, slim env diff
- route: requireManagementAuth + Zod body validation + buildErrorBody
sanitization (Hard Rule #12); fix clearProviderQuotaState -> clearProviderQuota
- .env.example/ENVIRONMENT.md: drop ~20 foreign vars, keep only
OMNIROUTE_QUOTA_AWARE_ROUTING (migration 148)
- tests/unit/quota-phase2.test.ts: DATA_DIR mkdtemp + resetDbInstance teardown
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* chore(ci): fix docs-sync + eslint-suppression drift for quota branch
CI gates flagged on PR #10126 head 43335f07:
- migration counts in README/AGENTS/llm.txt were stale (145 -> 146)
- regenerate docs/reference/PROVIDER_REFERENCE.md (gen-provider-reference)
- sync root llm.txt body into all 42 i18n mirrors (headers preserved)
- prune eslint suppressions that no longer occur
--no-verify: pre-commit docs-sync was failing on a pre-existing
release-base artifact (changelog 3.8.49 vs package 3.8.50) — fixed by
the changelog entry in the prior commit; re-verify in CI.
* chore(skills): regenerate agent skills (add omni-settings)
Merge-integrity CI gate flagged a missing generated skill. Regenerated
with check:agent-skills-sync --apply: +omni-settings, 45 unchanged.
* fix(ci): resolve Fast Quality Gates regressions on quota branch
- check-migration-numbering: migration 148 (provider_quota_state) landed
on this branch, so the KNOWN_GAPS allowlist entry is stale — remove it
(stale-enforcement 6A.3: 'REMOVA a entrada')
- open-sse/utils/stream.ts: duplicate sseCommentsEnabled import from a
bad merge (lines 31 + 77) — TS2300 duplicate identifier; drop the
duplicate so the open-sse typecheck gate is back within baseline
* docs: sync migration count to 149 after release merge
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
* test(migrations): align 148 gap assertion after 148_provider_quota_state.sql landed
The phase-2 branch added 148_provider_quota_state.sql, and 148 was already
removed from KNOWN_GAPS in scripts/check/check-migration-numbering.mjs. The
frozen-allowlists assertion still expected 148 to be a gap, so it failed.
Flip the assertion to match the allowlist (same pattern as 143/147).
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
---------
Co-authored-by: benzntech <benzntech@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
* perf(logging): offload call-log artifacts to a worker
* test(call-log): raise drain wait timeout for cold worker spawn
The first cold spawn of the worker_threads artifact worker can take ~2.4s
before queued artifact writes start draining, so a 2s wait in
call-log-save-drain.test.ts flakes on cold runs. Raise it to 10s.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: xz-dev <xz-dev@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(adobe-firefly): open browser sign-in and resolve provider slug in /login
POST /api/providers/[id]/login passed the connection DB id to
inAppLoginService.startLogin, but that service looks up the provider by
slug in TOKEN_EXTRACTION_CONFIGS. The lookup always missed and returned
"No extraction config" without launching a browser — so the VibeProxy
"Sign in" button for Adobe Firefly (and every other web-cookie provider)
never opened a browser.
Adobe Firefly additionally had no extraction config because its IMS JWT
is never in cookies/localStorage — it only rides on the Authorization:
Bearer header of firefly-3p.ff.adobe.io XHRs.
- Resolve the provider slug from the connection row and pass the slug
(not the DB id) to inAppLoginService.startLogin.
- Add open-sse/services/adobeFireflyBrowserLogin.ts: a Playwright
service that launches a visible browser at firefly.adobe.com and
intercepts firefly-3p requests to capture the IMS JWT + sherlockToken
cookie. Wire it into the /login route for the adobe-firefly slug.
- Fix latent bug: updateProviderConnection reads camelCase keys
(apiKey, providerSpecificData), so the previous snake_case call never
persisted extracted credentials.
* fix(adobe-firefly): open browser sign-in and resolve provider slug in /login
POST /api/providers/[id]/login passed the connection DB id to
inAppLoginService.startLogin, but TOKEN_EXTRACTION_CONFIGS is keyed by
provider slug — so browser login never launched for web-cookie providers.
Adobe Firefly also cannot use cookie extraction: the IMS JWT only appears
on Authorization headers to firefly-3p.ff.adobe.io. Add a dedicated
Playwright interceptor and persist credentials with camelCase keys that
updateProviderConnection actually reads.
* fix(adobe-firefly): use system Chrome/Edge CDP for browser sign-in
Playwright is not available inside the pkg-packaged VibeProxyServices.exe,
so import('playwright') always failed with 'Playwright not installed' and
never opened a window. Launch Chrome/Edge with --remote-debugging-port and
capture the firefly-3p Authorization Bearer via pure CDP WebSocket instead.
* fix(adobe-firefly): live x-arp-session-id / Arkose wire (stop 408 under load)
Browser generate-async requires x-arp-session-id as base64({sid,ark,ftr}) with a
real Arkose blob (sherlockToken). JWT alone frequently returns colligo HTTP 408
system under load while credits still work.
- Match live ftr magic __UDF43-m4_31ck + Arkose pk in synthetic ARP fallback
- Ranked extract of sherlockToken / x-arp from Cookie, HAR, fetch() paste, and
space-joined JWT+ARP (PasswordBox newline collapse)
- Reuse one ARP for storage upload + generate-async
- Clearer 408 errors when browser ARP is missing vs stale
- Unit suite 42/42
* fix(adobe-firefly): durable session ARP rebuild and aux_sid false-positive
Rebuild x-arp-session-id from forterToken/arkose/ff_session_guid instead of
ranking long Cookie pairs (e.g. aux_sid=…) as opaque ARP, which caused colligo
HTTP 408. Cache IMS JWT + cookie sessions, rotate ARP on 408 retries, and keep
Playwright warm-up opt-in only (headless Forter is rejected).
Also expand synthetic ARP shape with bfp/fpjs to match live successful captures.
* fix(adobe-firefly): durable session, off-screen Chrome recovery, browser sign-in
Rebuild x-arp-session-id from Cookie pieces (sid/ark/forter) so aux_sid is never
sent as ARP. Sticky ARP + submit spacing reduce mid-batch colligo 408 thrash.
Add optional managed Chrome warm (off-screen headed by default; Forter rejects
headless) and POST /api/providers/{id}/login browser sign-in that returns JWT+Cookie
after a fresh SSO. Visible sign-in resets off-screen window placement and clears
prior Adobe session when adding another account.
* fix(adobe-firefly): renew sessions through durable CDP
* fix(adobe-firefly): isolate browser sessions per account
* fix(adobe-firefly): make account login fresh and deterministic
* chore(adobe-firefly): remove obsolete browser fallback
* docs(adobe-firefly): document renewal controls
---------
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
The per-session drill-down cache now tracks decoded bytes per entry and
evicts least-recently-used entries until an aggregate maxTotalBytes
budget fits (route sets 256 MiB); an entry larger than the whole budget
is rejected. Prevents the previous worst case of 64 x 32 MiB (~2 GiB)
pinned in memory.
The fusion result's availability, partial and failure fields now reach
DescribedVideo.fusion, the guardrail meta (audioFusionRuns/Partials/
FailureCodes), the result-cache metadata and bridge stats. Audio
transcript validation moved inside the fusion's audio branch, so an
invalid audioTranscript records failures.audio and keeps the visual
description instead of failing the whole video.
`assertValidEngine()` valida id, apply, compress, getConfigSchema e
validateConfig — não exige `metadata`. Uma engine registrada sem esse campo é,
portanto, um registro legal. Mas `canRunAtCompressionStage` lia
`engine.metadata.executionStages` sem guarda, então essa engine legal derrubava o
pipeline inteiro com `TypeError: Cannot read properties of undefined` em vez de
falhar aberto, que é o contrato da compressão.
Metadata ausente é o mesmo caso de "não declarou executionStages" e passa a cair
no mesmo fallback documentado: só pre-translation.
Isso destravava também `tests/unit/compression/pipeline-circuit-breaker.test.ts`,
que registra uma engine de teste sem metadata e vinha 8/9 na base — agora 9/9. O
teste novo torna o contrato explícito, em vez de deixá-lo dependendo de uma
reprodução incidental noutro arquivo.
The five output styles (terse-prose, less-code, ponytail, i-have-adhd,
terse-cjk) shipped in Phase 4 but COMPRESSION_GUIDE.md had zero mention of
them. Add the catalog table with per-style language coverage, the injection
contract (catalog order, single marker, shared boundaries once), the config
shape and back-compat note, plus an 'Adding an Output Style' recipe in
EXTENDING_COMPRESSION.md covering the matrix guard and translation floor.
Refs #10426
Co-authored-by: Xiangzhe <bakryun0718@proton.me>
Adds docs/guides/VSCODE-COPILOT.md covering the OmniCopilot extension: install
from either store, connection setup, what the picker actually shows and why,
the dashboard-in-a-tab mode, and a troubleshooting table.
Documents two contracts that existed in code but nowhere in the docs:
- The ?prefix= query parameter on GET /v1/models, with the warning that
"canonical" omits providers whose alias already is the canonical id — so
"alias" is the safe direction for a de-duplicated list.
- MODELS_CATALOG_PREFIX_MODE in .env.example and ENVIRONMENT.md, matching how
ARENA_ELO_SYNC_ENABLED and PII_REDACTION_ENABLED are already documented.
The fabricated-docs gate cannot see this flag being read, because
resolveFeatureFlag() indexes process.env by key rather than naming it; added
an allowlist entry explaining that, in the style of the existing entries.
Co-authored-by: Xiangzhe <bakryun0718@proton.me>
* fix(providers): validate bailian-coding-plan against the Token Plan host
The catalog entry is the personal Alibaba Token Plan, but the region map still
resolved the retired Coding Plan hosts. #10290 moved only the open-sse registry
(inference) to token-plan.ap-southeast-1.maas.aliyuncs.com, leaving the dashboard's
key validation pointed at coding-intl.dashscope.aliyuncs.com.
That host rejects Token Plan keys with 401, and validateBailianCodingPlanProvider
maps 401/403 to "Invalid API key" — so adding a working key failed at the modal
while the same key served inference fine. Verified live 2026-08-18 with a valid
key: legacy host 401 invalid_api_key, Token Plan host 429 quota (auth OK).
- point both regions of ALIBABA_PROVIDER_ENDPOINTS at the Token Plan hosts,
matching what docs/providers/ALIBABA-QWEN-PROVIDER-FAMILIES.md already stated
- keep the retired hosts recognized as presets, so connections saved with the old
URL still follow the region selector instead of being pinned to a dead host
- keep image/video generation on the DashScope AIGC hosts, which the Token Plan
host does not serve
- probe with a model this plan actually serves (qwen3-coder-plus was Coding Plan)
* test(providers): compare parsed hostnames in the legacy-host guard
CodeQL flags URL .includes() checks as js/incomplete-url-substring-sanitization.
The guard is an assertion, not a sanitizer, but comparing new URL().hostname is
strictly more precise anyway — same coverage, no substring pattern.
---------
Co-authored-by: Xiangzhe <bakryun0718@proton.me>
The model ships only as `qwen3.8-max-preview` across every provider that serves it (bailian-coding-plan, qoder, qwen-cloud-token-plan, qwen-web), so the bare `qwen3.8-max` missed MODEL_SPECS: the chatCore context preflight fell back to contextManager's `default: 128000` and rejected prompts with `context_length_exceeded` despite the model's real 1M window, and the unknown id would have reached the upstream verbatim.
Both symptoms share one cause, so the alias goes in BUILT_IN_ALIASES, which resolveLifecycle() applies before the preflight and before dispatch.
Merged with the inherited OmniGlyph base-red (#9985) documented: its two failing compression tests were reproduced on the pure base tip aa912c42a7, with no commit from this branch.
Three independent, already-approved provider PRs (#10542 aihorde,
#10494 gemini-web image, #10594 freepik/magnific) boarded together in
the 2026-08-18 merge-train each add a small, additive registry entry
to open-sse/config/imageRegistry.ts. None crosses the 1000-line cap
alone; combined they push it from 996 to 1019. Owner-authorized
blanket rebaseline approval for this merge batch.
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>
@@ -167,6 +167,7 @@ _Living section — regenerated 2026-08-12 from all cycle commits (cycle open `e
### 🐛 Bug Fixes
- **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)
<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,
@@ -546,7 +548,7 @@ the current catalog at **[radar.omniroute.online/planos](https://radar.omniroute
- **🗜️ Compression hardening** — default-on inflation guard, Caveman packs for DE / FR / JA + Chinese (wényán), RTK filters for Gradle & .NET. → [Compression](docs/compression/COMPRESSION_ENGINES.md)
- **⚖️ Quota-Share routing** — split a shared account's quota fairly across pooled keys, work-conserving so idle slices are lent out. → [Resilience Guide](docs/architecture/RESILIENCE_GUIDE.md)
**Launch any supported CLI through OmniRoute in one command** — no config files written,
credentials injected per process, Qwen/Gemini get a throwaway isolated home:
```bash
omniroute run claude --model openai/gpt-5.4 # Claude Code
omniroute run codex --model glm/glm-5.2 # OpenAI Codex CLI
omniroute run aider --model glm/glm-5.2 -- --message "reply OK"
omniroute run goose --model glm/glm-5.2
omniroute run opencode --model glm/glm-5.2 -- run "reply OK"
omniroute run qwen --model glm/glm-5.2 -- -p "reply OK"
omniroute run gemini --model glm/glm-5.2 -- --skip-trust -p "reply OK"
# Or pick provider+model interactively and write the tool's own config:
omniroute configure codex # also: claude opencode qwen aider goose cline continue kilo
```
Every command honors the active remote context (`omniroute connect <host>`), `--dry-run`
previews the exact env/args without executing, and `--api-key-env NAME` keeps secrets out
of your shell history. → [CLI Integrations](docs/guides/CLI-INTEGRATIONS.md)
<br/>
<div align="center">
## 🌐 340 AI Providers — 90+ Free
@@ -702,6 +726,7 @@ the current catalog at **[radar.omniroute.online/planos](https://radar.omniroute
<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">
@@ -1080,7 +1172,7 @@ 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>
- **feat(admission):** add lane-aware admission probes for combo/fusion/chaos fan-out (fail-open, queueing disabled), an env-wins `OMNIROUTE_CHAT_VIRTUAL_LANES` activation flag applied at boot, and adaptive-lane visibility in the `omniroute_get_health` MCP tool (related to #9654)
- **docs(mcp):** complete the MCP server README tool reference so the `schemas/` catalog is fully covered (agent-skills, oneproxy, web, tool-search, combo/routing, pricing and DB-health tools were previously only discoverable via `omniroute_tool_search`)
- **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(providers): add **Cloudflare AI Playground** as a No Auth provider (`cloudflare-playground`, alias `cfp`) — free anonymous chat over the reverse-engineered `cf_agent` WebSocket protocol (PartySocket transport, no account/API key/cookies) with GLM 5.2, Kimi K2.7 Code, DeepSeek V4 Pro, gpt-oss-120B, Llama 3.3 70B, Qwen2.5 Coder 32B and 14 more curated models. The executor drives a headless Chromium via Playwright (the WS upgrade is TLS-fingerprint-gated), translates the `cf_agent` frame stream into OpenAI SSE, and surfaces upstream rate limits (3021) as HTTP 429. Fixes #10389
- **feat(providers):** AI Horde accepts an optional registered API key and advertises only live image models that currently have workers ([#10542](https://github.com/diegosouzapw/OmniRoute/pull/10542))
- **fix(providers):** AI Horde Check validates keys via `/v2/find_user` instead of the unauthenticated OpenAI models list ([#10542](https://github.com/diegosouzapw/OmniRoute/pull/10542))
- **feat(providers):** complete Jina AI as one credential pool — dashboard `jina-ai` / `jina-reader` share a token, `JINA_AI_API_KEY` is a real fallback, Test probes `GET https://api.jina.ai/v1/models` (embeddings fallback hits `jina-embeddings-v5-omni-small`), embed/rerank logs keep `connection_id`, catalog adds `jina-reranker-v3.5`, Omni v5 multimodal `{text}`/`{image}`/`{content}` docs pass through intact, and OmniRoute proxies classify / segment / `jina-search` (`s.jina.ai`). Reader stays a separate `r.jina.ai` card with an explicit label. Gemini Embedding 2 (`gemini/gemini-embedding-2`, alias `google/gemini-embedding-2`) uses dashboard `gemini` keys (or `GEMINI_API_KEY` / `GOOGLE_API_KEY` only when none exist), forwards native multimodal parts, and maps N OpenAI `input` items to N `:batchEmbedContents` vectors instead of one aggregated `:embedContent`. ([#10581](https://github.com/diegosouzapw/OmniRoute/pull/10581))
- **feat(settings):** add `autoDisableBannedScope` so permanent-ban auto-disable can target subscription/OAuth accounts only, leaving prepaid API keys in the routing pool ([#10617](https://github.com/diegosouzapw/OmniRoute/pull/10617))
- 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(api):** add `GET`/`POST``/v1/multimodal-embeddings` as an alias of `/v1/embeddings` so Jina-compatible clients do not receive HTTP 404 `unknown_route` — thanks @RaviTharuma
- **Passthrough streaming:** stop leaking upstream SSE control lines (`id:`/`event:`/`retry:`/`:` comments) to plain OpenAI Chat-Completions-format clients, while preserving `event:` framing for OpenAI Responses API and Claude Messages API passthrough ([#10017](https://github.com/diegosouzapw/OmniRoute/issues/10017)).
- Fix: wire AgentRouter's existing console balance fetcher into the Dashboard Quota UI (visibility gate + provider-limits data path + background sync) so its wallet balance renders instead of falling back to "Usage API not implemented" (#10078)
- Fix: AgentRouter's dollar balance now renders as a currency-formatted "$X.XX" credits row in the Dashboard Quota UI instead of a bare percentage, and an exhausted wallet always shows exactly $0.00 (#10078)
- fix(dashboard): remap unified Kimi Code card API-key save to the admitted `kimi-coding-apikey` connection id, fixing 400 "Invalid provider" on Save (#10096)
- **fix(admission):** stop the adaptive latency-gradient collapse from permanently locking out ordinary requests — individually valid requests now make solo progress when the system is idle and normal pressure, and the collapsed limit actively recovers on sustained idle windows instead of being stuck; the critical-pressure fuse still wins over solo progress (#10111)
- fix(sse): downgrade client-supplied `thinking:{type:"adaptive"}` to `enabled` and gate the `context-1m-2025-08-07` beta on model eligibility when a combo/fallback re-routes a request to a non-adaptive/non-1M model like claude-haiku-4-5 (avoids "adaptive thinking is not supported on this model" and "long context beta is not yet available" 400s, #10119)
- **fix(logging):** move call-log artifact serialization and filesystem writes to a bounded singleton worker to keep request handling responsive (#10123)
- **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(sse): gate structural chat admission shedding on real heap pressure instead of unconditional capacity, with a bounded headroom budget so a healthy heap can no longer bypass admission control indefinitely (#10183, #10268)
- **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(combo):** defer the known-context-overflow hard rejection for compressible requests so compression runs before the final context gate, instead of a raw-body estimate 400'ing generic Responses clients targeting a large model before OmniRoute can shrink it ([#10225](https://github.com/diegosouzapw/OmniRoute/issues/10225))
- **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(cliproxy):** read platform/arch at runtime via `os.platform()`/`os.arch()` in `binaryManager` so the embedded installer selects the Windows/ARM assets even when the release bundle is built on a Linux runner (fixes #10244)
- **fix(translator):** Text-format tool calls emitted inline by some models are now converted to proper `tool_use` blocks. Certain models (DeepSeek, Qwen) return tool invocations as `<tool_call>{"name":"Bash","arguments":{…}}</tool_call>` or `TOOL_CALL Read: {"file_path":"…"}` inside the text stream instead of the structured `tool_calls` field. Both formats leaked through the Claude translators as plain text, so Claude Code rendered the raw block and stalled instead of executing the tool. `extractXmlInvokeBlocks` (previously `<invoke>`-only) now scans for all three shapes in a single pass and emits `content_block_start`/`input_json_delta`/`content_block_stop` events, in both `openai-to-claude` and `gemini-to-claude` (Antigravity) paths ([#10251](https://github.com/diegosouzapw/OmniRoute/pull/10251))
- **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(ops):** Docker HEALTHCHECK defaults to the lightweight `/healthz` lifecycle probe instead of the heavy `/api/monitoring/health` path, with an `OMNIROUTE_HEALTHCHECK_PATH` opt-in override ([#10311](https://github.com/diegosouzapw/OmniRoute/pull/10311))
- **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(translator):** Consolidate tool-name casing normalization into a single `restoreClaudeToolName` helper reused across every response path (`openai-to-claude`, `gemini-to-claude`, `stream` passthrough, xAI and Antigravity handlers), replacing six hand-copied 7-entry casing maps. The shared helper resolves via the request-side `toolNameMap` first (preserving declared PascalCase and MCP/alias names), then the complete `TOOL_RENAME_MAP` (which already covers `glob`/`grep`/`task`/`todowrite`/`skill`/`askuserquestion`/etc.), then the `#7926` TitleCase→lowercase fallback for map-less clients. This closes the coverage gap that left `TodoWrite` and other tools failing with `Error: No such tool available: todowrite`, fixes a `ReferenceError` in `remapToolNamesInResponse`, and preserves the Gemini thought-signature persistence (`#8979`) and OpenAI→Claude `toolNameMap` restoration that must not regress ([#10374](https://github.com/diegosouzapw/OmniRoute/issues/10374))
- **fix(responses):** preserve native tool definitions for custom OpenAI-compatible providers when using the Responses API (`/v1/responses`). When `apiType` is set to `"responses"` (or `_omnirouteForceResponsesUpstream` is enabled), OmniRoute passes native tool shapes (`custom` with lark grammars, `namespace`, `local_shell`) directly upstream without running a lossy Responses→Chat→Responses conversion ([#10374](https://github.com/diegosouzapw/OmniRoute/issues/10374))
- **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
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.