Fix 527 mistranslated values in the Korean locale, all verified against
the en.json source:
- Restore protected product/protocol names garbled by machine translation
(응록→ngrok, 인류/인류학→Anthropic, 쌍둥이자리→Gemini, 반중력→Antigravity,
꼬리비늘 깔때기→Tailscale Funnel, 진공→VACUUM, 우편번호→ZIP)
- Fix wrong-sense homonym translations (달리기→실행 중 for Running,
장애인→비활성화됨 for Disabled, 열쇠→키 for Key, 안타→적중 for Hits,
유물→아티팩트 for Artifacts, 건강검진→상태 확인 for Healthcheck)
- Repair translated identifiers that broke literal values (양말5→socks5,
볼록-세션-id→convex-session-id, 채팅/완료→chat/completions,
메시지/보내기→message/send JSON-RPC methods)
- Replace key-name dumps shipped as values ("Table Name", "Overview
Title", "Cli Tools Redirect Title" etc.) with real Korean translations
- Unify ngrok casing (Ngrok→ngrok) and trailing punctuation with the
English source; align terminology across fixes (공급자, 폴백, 사용자 정의)
All {placeholder} tokens, markdown, and protected terms preserved
verbatim; i18n UI coverage and ko validation gates pass.
Use getEmbeddingDimension() in resolveEmbeddingSource so sqlite-vec can
create vec_memories before the first upsert, and abort reindex batches
when ensureReady returns ready=false instead of wasting embed credits.
* fix: restore OAuth auto-refresh for gemini-cli connections
gemini-cli OAuth connections had no PROVIDERS registry entry at all, so
the token-refresh health check permanently skipped them once the access
token expired, forcing a full re-authentication instead of using the
still-valid refresh token.
Two layered gaps, both required:
1. supportsTokenRefresh()'s explicit allow-set had "gemini" but not
"gemini-cli" (the id actually stored on these connections), and its
PROVIDERS[e].tokenUrl fallback also failed since...
2. ...open-sse/config/providers registry had zero entry for "gemini-cli"
at all: no clientId/clientSecret/tokenUrl/refreshUrl, so even the
generic refresh path had nothing to refresh with.
Adds a "gemini-cli" registry entry mirroring antigravity's Google
Cloud Code OAuth shape, reusing the same well-known public Gemini CLI
client credentials already embedded (and already used, unchanged, by
the Gemini Studio API-key provider's own oauth block) via
resolvePublicCred("gemini_id"/"gemini_alt"). Adds "gemini-cli" to the
explicit refresh allow-set, the Google-refresh dispatch case, and the
15-minute non-rotating-token proactive lead alongside antigravity/agy.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
* fix: register gemini-cli in canonical provider list (provider-consistency gate)
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(gemini-cli): use ANTIGRAVITY_RUNTIME_BASE_URLS (renamed by #8013 antigravity split)
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
Co-authored-by: seanford <seanford@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
ServiceSupervisor.start(), when probeBeforeSpawn detects an already-healthy
instance on the target port, "adopts" it (marks the service running without
spawning a duplicate that would die with EADDRINUSE). This adopt path calls
setToolStatus(tool, "running") with no pid argument at all, so this.pid stays
at its constructor default of null for the rest of that supervisor's life --
only the spawn path (a genuinely new child process) ever sets a real pid.
In production this "adopt" path is common, not an edge case: any embedded
sidecar service (cliproxy, 9router, bifrost, mux) whose child process
survives a `systemctl --user restart omniroute.service` gets adopted by the
new supervisor instance on the next start(), and its pid is lost from that
point on -- even though the service is genuinely healthy and running. The
observed symptom: a service shows state "running" but pid null, and
something downstream that keys liveness tracking off pid eventually treats
it as untrustworthy/stale despite nothing actually being wrong.
Fix: resolve the real pid of the process holding the port (via `lsof -ti
:<port>`, best-effort -- a lookup failure leaves pid null rather than
blocking adoption) and record it the same way the spawn path does.
An existing test asserted pid === null on adopt. That was accurate for the
old behavior but reflected a missing resolution, not a deliberate "adopted
services never get a pid" design choice -- updated its assertion to match
the corrected behavior and added a dedicated regression test proving the
resolved pid matches the real process actually bound to the port.
* fix(sse): Gemini TPM classification, combo-cooldown-wait for auto/quota-share, and target-timeout floor
Gemini TPM/RPM 429s were misclassified as QUOTA_EXHAUSTED because
sanitizeErrorMessage() truncates to the first line, hiding Google's
metric name and retry hint on lines 2-3. Added a rawMessage field
(internal-only, never reaches the client) and classifyGeminiQuotaMetricFromText()
to classify from the untruncated text, reordered ahead of the generic
credits/daily-quota checks.
Widened comboCooldownWaitEnabled (wait out a short transient cooldown
instead of crystallizing a 429/503) from quota-share-only to also cover
auto-strategy combos, and raised the wait ceiling to 65s/130s-budget/90s-cap
to match Gemini's ~60s TPM/RPM windows.
The per-target timeout (DEFAULT_COMBO_TARGET_TIMEOUT_MS, 120s) was shorter
than the new 130s cooldown-wait budget, so a target could get cut off
mid-wait with a synthetic 524 instead of completing the retry. Added
resolveComboTargetTimeoutMsForCombo()/isComboCooldownWaitEligible() in
comboConfig.ts to raise the per-target floor to budgetMs+buffer only for
wait-eligible strategies (auto/quota-share), verified live: a 12-request
concurrent burst against a TPM-exhausted combo went from 2/12 succeeding
(10 x 524) to 12/12 succeeding with zero 503/524.
Also: liveGeminiShared.ts's sendAndValidate now fails fast on a 503
instead of retrying past it, and the health dashboard + request logger
surface TPM stats alongside RPM/RPD.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): combo-exhausted rejection logs now capture request body + attempted models
recordRejectedRequestUsage() (the fast path for combo requests that never
reach handleChatCore, e.g. all targets locked by resilience cooldown)
hardcoded provider: "-" and never passed a request body to saveCallLog(),
so /dashboard/logs entries for these failures were nearly useless for
debugging: no way to see the client's request or which models were tried.
- recordRejectedRequestUsage() now accepts requestBody and persists it
through the existing saveCallLog() artifact mechanism (same path
handleChatCore's own logging uses).
- Added summarizeComboAttemptedModels(), which reads the combo's own model
list (always available, unlike the response's combo-diagnostics headers —
a model-level resilience-lockout skip never touches the
exhaustedProviders/exhaustedConnections sets those headers are built
from) to populate a real "provider" value instead of "-".
- Wired both into the call site in src/sse/handlers/chat.ts.
NOTE: unrelated to the Gemini TPM/combo-cooldown-wait fix on this branch —
landed here per operator request, to be split into its own branch/PR.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* feat(sse): synthetic streaming keep-alive event + 5-minute Gemini cooldown-wait ceiling
Many clients enforce a first-SSE-byte timeout, which made it unsafe to wait
out a longer upstream rate-limit cooldown on a streaming request — the
client would abandon the connection before any bytes arrived. This landed
in two parts:
1. Synthetic startup "thinking" event (OpenAI chat/completions format):
the already-existing withEarlyStreamKeepalive wrapper (open-sse/utils/
earlyStreamKeepalive.ts, wired into /v1/chat/completions, /v1/messages,
/v1/responses since #2544) opens the SSE stream immediately once a
request runs past its threshold, but only ever sent empty/no-op
keepalive frames. Added a `startupFrame` option (defaults to
`keepaliveFrame` — zero behavior change unless a route opts in) so the
very first frame can carry real content instead. Wired
OPENAI_STARTUP_THINKING_FRAME (a reasoning_content delta: "OmniRoute:
got request, sending to provider") into /v1/chat/completions only —
Claude Messages and Responses API formats both require a preceding
envelope event (message_start / response.created) that a synthetic
pre-dispatch frame can't safely fabricate without risking a duplicate
envelope once the real stream arrives, so those two routes keep their
existing (safe, proven) keepalive frames unchanged.
2. Raised the "wait out a known cooldown, then retry" ceiling to 5 minutes
for both retry mechanisms, now that a client-side first-byte timeout is
no longer a risk on the (opted-in) route:
- comboCooldownWait (auto/quota-share combos, open-sse/services/combo.ts):
maxWaitMs hard clamp raised 90s -> 300s (src/lib/resilience/settings/
normalize.ts); defaults raised to maxWaitMs:90s/maxAttempts:5/
budgetMs:300s. comboConfig.ts's resolveComboTargetTimeoutMsForCombo
already derives the per-target timeout floor from budgetMs, so it
tracks the new ceiling with no further changes.
- waitForCooldown (direct, non-combo model requests, src/sse/handlers/
chat.ts): this mechanism had NO cumulative cap before — only a
per-wait cap (maxRetryWaitMs) and a retry count (maxRetries), so
maxRetries x maxRetryWaitMs could exceed 5 minutes with no ceiling.
Added a budgetMs field (mirrors comboCooldownWait) to
WaitForCooldownSettings/CooldownAwareRetrySettings, threaded a
requestRetryBudgetLeftMs tracker through chat.ts's requestAttemptLoop
(mirrors combo.ts's comboCooldownBudgetLeftMs), and made
getCooldownAwareRetryDecision refuse to wait once the cumulative
budget is exhausted even if the single wait is under maxRetryWaitMs.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): extend the synthetic keep-alive thinking event to /v1/responses
Live incident (OpenClaw, log id 1784407081908-cbc24f): a /v1/responses
request to gemini/gemma-4-31b-it took 56s to produce a first byte and the
client disconnected (499 request_signal_aborted) — the same client-first-byte-
timeout problem the previous commit fixed for /v1/chat/completions, but
/v1/responses only had the generic bare-comment keepalive (no content), so it
wasn't covered.
Added RESPONSES_STARTUP_THINKING_FRAME: a self-contained synthetic reasoning
item (response.output_item.added -> reasoning_summary_part.added ->
reasoning_summary_text.delta -> reasoning_summary_part.done), opened AND
closed within this one frame rather than left dangling — it never carries a
response_id, so it can't collide with the real upstream response's own
independent response.created lifecycle that follows. Mirrors the abbreviated
delta+part.done close pattern open-sse/utils/stream.ts's own
emitSyntheticResponsesReasoningSummary already uses for real mid-stream
reasoning content.
Wired into src/app/api/v1/responses/route.ts via the startupFrame option
added in the previous commit.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): combo cooldown-wait vars reset every setTry, crystallizing a bogus 503 instead of waiting
Live incident (log id 1784416706646-51): a request to the "default" combo
(strategy=auto, maxSetRetries=3) hit a real Gemini TPM 429 on both gemma-4
targets, correctly classified as a short 40s rate_limit lockout — then
crystallized a 503 "all upstream accounts are inactive" in 6.9s instead of
ever reaching the cooldown-aware wait.
Root cause: `lastError`/`earliestRetryAfter`/`lastStatus` were declared with
`let` INSIDE the `for (setTry...)` loop body, so they reset to null at the
start of every set-try. When both targets lock out on setTry 0, every
subsequent setTry (1..maxSetRetries) pre-skips both targets via the
isModelLocked check with no real dispatch — so on the FINAL setTry (the only
one whose values the post-loop decision reads, since it's gated behind
`if (setTry < maxSetRetries) continue`), lastStatus was null, hitting the
"!lastStatus" branch (ALL_ACCOUNTS_INACTIVE 503) and completely bypassing the
comboCooldownWaitEnabled / earliestRetryAfter wait logic — even though a
real 429 with a known ~40s retry-after WAS observed on setTry 0.
This bug predates today's Gemini TPM work (any combo with maxSetRetries > 0
whose targets all lock out on the first pass was affected) but was masked in
existing tests: the "auto strategy (2 models...)" regression test uses
maxSetRetries: 0, so it only ever runs ONE setTry iteration and never
exercises the reset-on-retry path. It also explains why the dedicated
12-concurrent-request burst test passed cleanly — with concurrent requests,
timing variance meant some request's FINAL setTry iteration still had a live
target to dispatch to, giving lastStatus/earliestRetryAfter fresh data. A
single isolated request has no such luck.
Fix: hoist lastError/earliestRetryAfter/lastStatus to just inside
dispatchWithCooldownRetry, before the setTry loop, so they persist across
set-tries (still reset fresh on each recursive dispatchWithCooldownRetry()
call after a wait, which is correct). recordedAttempts/fallbackCount/
exhaustedProviders etc. are intentionally left per-iteration (unrelated to
this bug).
New regression test in tests/unit/combo-quota-share-cooldown-wait.test.ts
reproduces the exact live scenario (2 targets, both lock out on setTry 0,
maxSetRetries: 3) — confirmed red (503) against the pre-fix code, green
(200, waits and retries) against the fix.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* test(sse): extend live Gemini workload to Responses API + add large-context TPM test
Two additions to the live Gemini test suite, both live-verified against the
dev instance:
1. sendAndValidate() (tests/integration/liveGeminiShared.ts) now accepts an
apiFormat: "chat" | "responses" parameter, building the Responses-API
request shape (input array, max_output_tokens) and parsing its SSE events
(response.output_text.delta / response.reasoning_summary_text.delta /
response.completed) via the new readResponsesSSEStream(). Wired into two
new tests in live-gemini-workload.test.ts ([30]/[31]), mirroring the
existing Chat Completions streaming coverage. Verified live: 24/25 + 5/5
payloads succeeded end-to-end through the new code path (the one failure
was a ~300s test-client fetch timeout unrelated to the Responses API code
itself — a separate, not-yet-addressed test-harness limitation).
2. genHugeContextMessage() builds a single message large enough (~4
chars/token estimate) to approach or exceed Gemini's free-tier TPM ceiling
(16000 input tokens/min for gemma-4) by itself. Every other prompt
generator in this file tops out around 1-2k tokens — nowhere near that
ceiling — so none of the existing workload tests ever exercised a REAL TPM
429, only RPM-style rate limiting. tests/integration/gemini-large-context-tpm.test.ts
sends two ~12-13k-token requests back-to-back (comfortably exceeding
16000/min together) to exercise the full path against production Gemini:
TPM classification, the comboCooldownWait retry, and the synthetic
keep-alive frame on a genuinely slow request.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): abandoned combo target dispatch now observes its own per-target timeout, fixing a permanent "pending" dashboard leak
Live incident (dashboard log id 1784418258231-14961a, reported as "an ongoing
request even though there's already a 200"): a combo target dispatch
abandoned by comboTargetTimeoutMs (open-sse/services/combo/targetTimeoutRunner.ts)
left a permanent phantom "pending" entry in the dashboard, even after the
overall combo request had already succeeded via a different retry.
Root cause: chatCore.ts's createStreamController — and everything downstream
that depends on it (withRateLimit's Promise.race against Bottleneck,
acquireAccountSemaphore) — only ever watches clientRawRequest.signal, which
is the ORIGINAL client's request signal (set once via buildClientRawRequest
and reused unchanged across every target dispatch in a combo). It has no
connection to targetTimeoutRunner.ts's OWN AbortController
(target.modelAbortSignal), which is what actually fires when
comboTargetTimeoutMs (300s) elapses. src/sse/handlers/chat.ts's
handleSingleModel bridge between combo.ts and handleSingleModelChat received
`target.modelAbortSignal` but silently dropped it — never forwarded it
anywhere. So when a target got abandoned (e.g. stuck inside a wedged
Bottleneck rate-limiter queue, see the WEDGED force-reset log line from the
same incident), its per-target timeout fired and let the COMBO move on and
retry successfully elsewhere — but the abandoned dispatch's own promise
chain never learned it had been superseded, so it hung forever waiting on a
signal that was never going to fire, and trackPendingRequest(false) (the
finalize call) never ran.
Fix: thread target.modelAbortSignal through as a new modelAbortSignal
runtimeOption, and merge it into clientRawRequest.signal (via the existing
mergeAbortSignals helper from open-sse/executors/base.ts) right before
dispatch, so an abandoned target's own promise chain now observes its abort
and can reach its cleanup path — new resolveDispatchClientRawRequest() makes
this mechanically testable in isolation.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): combo cooldown-wait state recording, rate-limit wedge recovery, OpenAI-format SSE error frames
Five related fixes surfaced by live incidents (dashboard log ids 1784457764961-73,
1784465227489-a2cbc0, 1784504040241-6f8b9a) while validating the Gemini TPM/cooldown-wait
work on this branch against real OpenClaw traffic:
- combo.ts: the model-lockout bail-out branches in dispatchWithCooldownRetry never
recorded lastStatus, so once every target in a set hit an existing lockout the final
check crystallized a bogus ALL_ACCOUNTS_INACTIVE 503 instead of reaching the
cooldown-wait decision, even with a real 429 + short retry-after observed.
- combo.ts/combo/types.ts: the "all credentials cooling down" pre-dispatch rejection
(buildModelCooldownBody) nests its retry hint as error.retry_after/reset_seconds, not
the top-level retryAfter every other 429 shape uses — combo's extraction only read the
latter, so earliestRetryAfter stayed null for this shape even after lastStatus was fixed.
- rateLimitManager.ts: the wedge-recovery watchdog used disconnect(), which releases the
heartbeat timer but never rejects jobs already QUEUED on that instance — orphaned
dispatches hung until the outer ~300s per-target timeout, well past real clients'
patience. Switched to stop({ dropWaitingJobs: true }), safe because the wedge condition
already requires RUNNING===0 && EXECUTING===0.
- earlyStreamKeepalive.ts: the in-band error frame emitted after committing to a 200 SSE
stream was hardcoded to Anthropic's `event: error` convention for every route, including
the OpenAI-format ones (/v1/chat/completions, /v1/responses) where that framing is
either invisible or malformed to a plain data-line parser. Added per-route
OPENAI_CHAT_ERROR_FRAME / OPENAI_RESPONSES_ERROR_FRAME and wired them in.
- chatCore.ts: persisted a synthetic clientResponse error body even when the client had
already disconnected (AbortError) before that body was ever computed — misleading the
dashboard into showing "what the client received" for a response that was never sent.
Also: RequestLoggerDetail.tsx — Provider/Client Event Stream panes lost their collapse
toggle when StreamSection replaced the collapsible PayloadSection (692d6be80, unifying
active/finished request views) without carrying the toggle over.
Each fix has a TDD regression test with a confirmed red-before-green cycle.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* test(sse): free-tier model + gemma-4 TPM-ceiling benchmark harness
Adds a live benchmark comparing free models OmniRoute exposes across
configured providers plus previously-unexercised no-auth providers
(felo-web, aihorde, opencode, duckduckgo-web — none need a connection
row, they were just never tried). Reuses liveGeminiShared.ts's SSE
parsers and CASE_BUILDERS instead of duplicating them.
Also adds a targeted TPM-stress test firing back-to-back large-context
prompts at the gemma-4-31b model across its 3 free hosts (Gemini,
NVIDIA, AI Horde) to isolate whether the documented 16k-tokens/minute
free-tier ceiling is Gemini-specific enforcement or an inherent
model property.
FORCE_TOOL_CHOICE_REQUIRED is a test-only, default-off env flag added
to liveGeminiShared.ts and live-gemini-agentic-loop.test.ts for an
earlier live A/B comparison of tool_choice: required vs unset — kept
as a reusable knob for future runs.
Co-Authored-By: Markus Hartung <markus.hartung@gmail.com>
* test(sse): benchmark for the 2026-07-22 newly-enabled provider batch
Adds NEWLY_ENABLED_MODELS to freeModelBenchmarkShared.ts (Mistral
Leanstral, OpenRouter's live "free"-tagged roster, OpenCode Zen's
current free models — refetched live from
https://opencode.ai/zen/v1/models since the static catalog had
drifted) and a dedicated workload benchmark test for them.
Co-Authored-By: Markus Hartung <markus.hartung@gmail.com>
* test(sse): sync geminiRateLimitTracker tests with e74a1722b's corrected Gemma 4 limits
e74a1722b updated geminiRateLimits.json's gemma-4-* entries from the stale
15/1500/-1 (rpm/rpd/tpm) to the real published free-tier values
16000/14400/16000, but never updated the tests asserting the old numbers.
Surfaced by running the full test:unit suite as a post-rebase sanity check.
Co-Authored-By: Markus Hartung <markus.hartream@gmail.com>
* chore(quality): file-size baseline for own-growth (#8213)
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
Co-authored-by: Markus Hartung <markus.hartream@gmail.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(logs): stop an async EPIPE becoming an uncaughtException loop
A raw process.stderr.write into a broken pipe fails asynchronously, so the
try/catch around it never sees the failure. The stream emits 'error'; with no
listener on process.stderr Node re-throws it as an uncaughtException; the
framework's handler logs that through console.error; and the patched console
writes back into the same dead stream. That closes a self-sustaining loop.
Attach an 'error' listener to process.stdout and process.stderr. Node only
converts a stream 'error' into an uncaughtException when the emitter has no
listener, so the listener alone terminates the cycle. Measured in a spawn
harness over 1.5s: 3,387 uncaught exceptions before, 0 after.
Absorb EPIPE only. Attaching a listener otherwise makes every stream error on
those streams non-fatal process-wide, so ENOSPC, EBADF and the rest are
re-raised on a fresh stack to preserve today's crash semantics. The
accompanying test asserts that in a child process, because node:test
attributes any in-process uncaughtException to the running test.
Add a test-only reset() to undo the patched console and the listeners:
test:unit:fast runs --test-isolation=none, so leaked state would reach every
subsequent test file.
Refs #8181
* fix(logs): bound interceptor disk writes and self-heal a missing log dir
Two write-path defects in the same file, both independent of the loop itself.
writeEntry appended with no rate limit, so while the loop spun it wrote
unbounded lines to disk (4.3 GB in 90 minutes in the reported incident). Apply
the same policy #1006 established in structuredLogger -- 50 writes/sec, a 5s
dedup window, a bounded tracking map -- but scoped to `error` entries only.
That scoping is deliberate: structuredLogger applies its limiter solely to
error() and fatal(), whereas writeEntry serves all five of
log/info/warn/error/debug across ~800 non-error call sites. Capping those would
silently drop routine logging from the Console Log Viewer's file. A test
asserts non-error levels stay unlimited.
ensureDir() ran once in initConsoleInterceptor and never again, so a log
directory removed while the process was alive made every later append throw
ENOENT into a bare catch -- console file-logging then stopped permanently with
nothing surfaced anywhere. Recreate the directory and retry once, and report
the failure exactly once through the unpatched stderr so it cannot recurse
through the patched console or become a flood of its own.
Refs #8181
* fix(logs): skip raw stderr writes to a stream already known dead
error() and fatal() write with a raw process.stderr.write wrapped in
try {} catch {}. The comment on that line says the raw write exists to avoid
Next.js console patching "that triggers EPIPE loops" -- but on a broken pipe
the write fails asynchronously, so the catch never sees it, and the resulting
stream error is what ignites the loop.
Skip the write when the stream is already destroyed or ended, falling through
to the file sink as before. The listener added earlier is what breaks the
cycle; this stops the ignition point firing into a dead stream in the first
place. The existing try/catch is retained for the synchronous cases it always
covered.
The #1006 suppression policy and its call sites are untouched.
Refs #8181
* fix(logs): install the stdio guard independently of console interception
initConsoleInterceptor() returns early when APP_LOG_TO_FILE=false, and when the
log directory cannot be created. The stdio 'error' listeners were installed
after that return, so in those supported configurations no listener was
attached at all.
structuredLogger's raw stderr writes still happen there, and an ordinary broken
pipe raises an async EPIPE without destroyed or writableEnded being set first,
so the guard in safeStderrWrite does not cover it either. The loop this change
exists to prevent was therefore still reachable with file logging turned off.
Extract installStdioErrorGuard() and call it before the early return. It is
idempotent and cleared by reset(). A new test asserts, in a child process, that
both listeners are present when APP_LOG_TO_FILE=false.
Also restore APP_LOG_TO_FILE and APP_LOG_FILE_PATH in the test's after() hook.
test:unit:fast runs with --test-isolation=none, so the previous top-level
mutations leaked into later test files, leaving file logging enabled against a
path this file deletes.
Refs #8181
* fix(sse): collapse single-text-part Responses-API content to a plain string
Every /v1/responses request — even the simplest single-string input —
got 500'd by AI Horde's Aphrodite-backed facade. Root cause:
normalizeResponsesInputForChat() always wraps a plain string input as
`content: [{ type: "input_text", text: value }]` (a one-element array),
and openaiResponsesToOpenAIRequest() mapped that straight through to
`content: [{ type: "text", text: value }]` on the Chat Completions side
— an array. That's spec-valid (OpenAI's own API accepts both shapes),
but strict/naive OpenAI-compatible backends like AI Horde's only
implement the plain-string form and reject the array form outright.
A single-text-part array and a plain string are semantically
identical, so collapse is safe. Real multi-part messages (text+image,
text+file) are left untouched.
Regression test: tests/unit/openai-responses-single-text-content-string.test.ts
(RED before the fix — every collapsed-content assertion failed with an
object instead of a string; GREEN after).
Also adds a deeper AI Horde load-test suite (sequential/concurrent/
cross-model/sustained-throughput/new-capable-model-candidates) that
surfaced this bug via real live traffic after Behemoth-X-123B was
temporarily added to the "default" combo for evaluation.
Co-Authored-By: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): unsupportedParams provider-level fallback for aihorde's live-discovered models
Real OpenClaw traffic against the newly-added Behemoth-X-123B combo
target kept 500ing on every attempt even after the Responses-API
content-array fix landed. The pipeline artifact showed why: `tools`
was still present, unstripped, in the request actually sent to AI
Horde's Aphrodite backend.
Root cause: `unsupportedParams: ["tools", "tool_choice",
"parallel_tool_calls"]` was only declared on the 3 models statically
listed in the aihorde registry entry (Cydonia-24B, Skyfall-31B,
google/gemma-4-31b). AI Horde uses `passthroughModels: true` — its
live worker roster changes constantly — so Behemoth-X-123B, like every
other dynamically-discovered aihorde model, had no model-specific
unsupportedParams entry, and getUnsupportedParams() returned [] for
it. But "the workers run raw text-completion backends" (no tool
calling) is true of every model AI Horde serves, not just the 3
catalogued ones.
Adds a provider-level `unsupportedParams` fallback on RegistryEntry,
checked by getUnsupportedParams() after the per-model lookup misses.
Set on the aihorde entry so it covers its entire live-discovered
roster, present and future, without needing a static per-model catalog
entry for each one.
Regression test: tests/unit/aihorde-tools-unsupported-provider-fallback.test.ts
(RED before the fix — Behemoth-X and deepseek-v4-flash both returned
[] instead of the stripped param list; GREEN after, with a control
case confirming the fallback doesn't leak to unrelated providers).
Co-Authored-By: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): flatten leftover tool-call history when stripping unsupported tools
Third bug in the same AI Horde/Behemoth-X saga: even after tools/
tool_choice were correctly stripped from the live request (previous
fix), real combo traffic still 500'd. The conversation history itself
carried a prior turn's role:"assistant" tool_calls and role:"tool"
result messages, left over from before the combo failed over from a
tool-capable model (Gemini) to a non-tool-capable one (AI Horde). Its
raw completion backend doesn't understand those message shapes at all,
independent of whether live `tools` is present — confirmed by
reproducing with a role:"tool" message and NO tools param at all.
flattenToolHistory() (open-sse/utils/flattenToolHistory.ts) already
existed for exactly this, fully unit-tested — it just had zero call
sites anywhere in the request pipeline. Extracts the unsupported-params
strip into a small testable module
(open-sse/handlers/chatCore/unsupportedParamsStrip.ts, following the
existing chatCore god-file decomposition pattern e.g.
executorClientHeaders.ts) that now also flattens tool-call history
whenever "tools" was among the stripped params.
Regression test: tests/unit/chatcore-unsupported-params-strip.test.ts
(RED before the fix — the flattening test failed with the raw
tool_calls array still present; GREEN after). All 434 existing
chatcore-*.test.ts tests still pass.
Co-Authored-By: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): gate tool-history flattening on unsupported, not on stripped-this-request
The previous commit's flattening only fired when "tools" was actually
present-and-stripped on THIS request. A second live reproduction
against AI Horde had no live `tools` param at all — only stale
tool_calls/tool-result messages inherited from before a combo
failover — and still 500'd, because that condition never triggered.
A model that can't do tool calling can't do it whether or not the
current request happens to carry a `tools` array. Gate on the
unsupported-params list itself (unsupported.includes("tools")) instead
of the subset that was actually present-and-deleted this time.
Regression test added to the same file (RED before — the no-live-tools
case left tool_calls/role:"tool" untouched; GREEN after). All 435
chatcore-*.test.ts still pass.
Co-Authored-By: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): skip tool-incapable combo targets, error clearly on direct requests
Two complementary fixes for a model that structurally can't do tool
calling at all (e.g. AI Horde's raw completion backends) rather than
silently degrading — following up on the earlier strip/flatten fix,
which stopped the crashes but let a tool-incapable target still get
selected and return a 200 that narrates a fake tool call in prose
instead of erroring or being skipped.
1. Root cause, combo routing: getResolvedModelCapabilities()'s
`supportsTools` resolution only checked per-model registry entries,
synced capabilities, and static specs — none of which exist for a
dynamically-discovered model (AI Horde's passthroughModels roster
changes as workers come and go). It fell through to
heuristicToolCalling(), which optimistically defaults to `true` for
any unrecognized model (TOOL_CALLING_UNSUPPORTED_PATTERNS is empty).
Added a provider-level fallback reusing the same unsupportedParams
signal the request-time strip already relies on. This makes the
EXISTING filterTargetsByRequestCompatibility (comboStructure.ts) —
which already correctly excludes non-tool-capable targets when a
request requires tools — actually work for these models; no combo.ts
changes were needed, it was only ever fed bad capability data.
2. Direct/pinned requests: filterTargetsByRequestCompatibility only
protects combo routing. A direct request naming an exact
tool-incapable model has no other target to fail over to — added
checkToolCallingRequiredButUnsupported (chatCore/toolCallingRequiredCheck.ts),
gated on isCombo: false, returning a clear 400 instead of a 200 that
silently can't do what was asked.
Regression tests (both RED before, GREEN after):
- tests/unit/model-capabilities-provider-unsupported-tools.test.ts
- tests/unit/chatcore-tool-calling-required-check.test.ts
All 463 chatcore-*/model-capabilities-*.test.ts and 31 combo
compatibility-filter tests still pass.
Co-Authored-By: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): correct handleChatCore return shape for the tool-calling-blocked error
handleChatCore's documented contract is `{ success, response, status,
error }`, not a raw Response — returning `new Response(...)` directly
(copied from a different early-return whose surrounding context turned
out not to share this function's top-level contract) produced "No
response is returned from route handler ... Expected a Response object
but received 'undefined'" and a bare 500 with an empty body, caught
immediately when verifying the previous commit live.
Uses createErrorResult() (already used by the adjacent
translation-failure branch a few lines up) instead of hand-building the
Response, matching the same pattern already established in this
function for early error returns.
Co-Authored-By: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): scope Responses single-text-content collapse to providers that need it
The single-text-part content array -> plain string collapse (added for AI
Horde's Aphrodite facade, which 500s on the array form) was applied
unconditionally to every provider, silently breaking the standard OpenAI
array-shaped content contract that other providers and existing tests
depend on. Added RegistryEntry.requiresPlainStringContent, gated the
collapse on it (true only for aihorde), and threaded modelInfo.provider
through responsesHandler -> responsesApiHelper -> the translator so the
real /v1/responses call site can identify the provider.
Co-Authored-By: Markus Hartung <markus.hartream@gmail.com>
---------
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
Co-authored-by: Markus Hartung <markus.hartream@gmail.com>
Live AGY model discovery (isDiscoverableAgyModelId + filterUserCallableAntigravityModels)
composing with the #8013 antigravity discovery rewrite. Reconstructed onto the current
release tip (branch was ~977 commits behind); updated the test to the renamed version-cache
API (seedAntigravityVersionCache -> seedAntigravityIde/CliVersionCache) after the fusion.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
Final catalog dedupe pass drops a generic/untyped chat-like sibling row
when a typed non-chat specialty row (audio/video/moderation/...) exists
for the same public id — closing the #4424 follow-up (whisper-1, tts-1,
omni-moderation-latest, elevenlabs/*, veo-free/*). Pure, I/O-free,
order-preserving; also removes a stray raw NUL byte that was embedded in
the dedupe key template literal (which made git render the file binary).
Restores test coverage for relative-order preservation across distinct
ids and for two distinct id-less entries never being grouped, keeping the
suite's assertion count at parity with the pre-fix baseline.
Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
* fix(windows): add windowsHide to all child process spawns (#8131)
On Windows, child processes spawned without windowsHide: true cause
transient conhost.exe/cmd console windows to flash open. Audited all
spawn/exec/execFile/execSync/execFileSync call sites and added
windowsHide: true where missing.
Files patched:
- src/mitm/manager.ts (MITM server spawn)
- src/mitm/systemCommands.ts (sudo/system command spawn)
- src/mitm/inspector/systemProxyConfig.ts (execFile wrapper)
- src/shared/services/cliRuntime.ts (CLI spawn + npm execFileSync)
- src/lib/plugins/loader.ts (plugin host spawn)
- src/lib/providerModels/cursorAgent.ts (cursor binary spawn)
- src/lib/cloudflaredTunnel.ts (cloudflared spawn)
Unix-only call sites (shell: /bin/bash, which) are unaffected.
electron/main.js already had windowsHide: true.
* fix(windows): cover remaining spawn sites missed by #8131 windowsHide sweep
Extends the #8131 windowsHide audit to the three call sites the original
sweep missed: ServiceSupervisor.start() and processManager.startProcess()
(both spawn() embedded-service child processes), and
installers/utils.ts::buildNpmExecOptions() (the execFile() options runNpm()
uses to install services). All three now always set windowsHide: true so
no transient conhost.exe/cmd console window flashes open on Windows.
The two spawn() options objects are factored into small, pure, exported
builder functions (buildServiceSpawnOptions, buildCliproxyapiSpawnOptions)
so the regression test can assert on the constructed options directly,
since both call sites use a bare named `import { spawn } from
"node:child_process"` that ESM live-binding semantics make unmockable
without --experimental-test-module-mocks (not currently enabled repo-wide).
Bumps config/quality/file-size-baseline.json for cloudflaredTunnel.ts
934->935 (the PR's own +1 windowsHide line at the existing spawn options
object).
Co-Authored-By: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: Austin Liu <austinliu@Austins-MacBook-Air-3.local>
Co-authored-by: Probe Test <probe@example.com>
Co-authored-by: Dingding-leo <Dingding-leo@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(combos): expose synced reasoning-effort variants in Combo Builder model picker (#8072)
Synced reasoning-effort aliases (e.g. GLM-5.2-high, GLM-5.2-medium)
appear in the catalog and Playground but were missing from the Combo
Builder's inline model picker. buildModelOptions() added base synced
records but never ran appendSyncedEffortVariants().
Convert synced models with non-empty supportedThinkingEfforts into
catalog-shaped entries, run the shared appendSyncedEffortVariants
utility (preserving its effort normalization, provider exclusions,
suffix-collision handling, and naming behavior), and add any new
variant ids to the builder model map. Variants inherit the base
model's endpoints, context length, output limit, and thinking support.
* fix(combos): correct baseId derivation for synced effort variants (#8072)
appendSyncedEffortVariants sets a variant's own root field to
${baseRoot}-${tier} (still tier-suffixed), not the true base model id.
buildModelOptions() was deriving baseId from variant.root, so the lookup
into modelMap never matched and every <model>-<tier> variant silently
fell back to bare defaults instead of inheriting contextLength,
outputTokenLimit, supportedEndpoints, and supportsThinking from its
base model.
Track each variant's true base raw id directly while iterating tiers
during catalogShaped construction instead of re-deriving it from
variant.root.
Adds a regression test seeding a synced model with
supportedThinkingEfforts via replaceSyncedAvailableModelsForConnection
and asserting the resulting <model>-<tier> variants both appear and
inherit the base entry's metadata through getComboBuilderOptions().
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: Austin Liu <austinliu@Austins-MacBook-Air-3.local>
Co-authored-by: Probe Test <probe@example.com>
Co-authored-by: Dingding-leo <Dingding-leo@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(security): decouple request PII redaction from injection mode
PII_REDACTION_ENABLED now rewrites request PII independently of
INPUT_SANITIZER_MODE, so the enterprise recipe (MODE=block + PII on)
actually redacts. Also cover Responses API string input/prompt shapes
and correct docs that claimed MODE=redact strips injection text.
Refs: #8092#8093#8094#8096#8097
* test(security): drop no-explicit-any in sanitizer unit tests
Unblocks CI lint/quality ratchet on the PII redaction PR by typing
chat-like payloads instead of casting to any.
---------
Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Recognize Google RESOURCE_EXHAUSTED responses that include a billing-period reset window while preserving transient rate-limit classification for generic exhaustion messages.
Fixes#8060
persistOAuthConnection gated its whole dedup step behind if(tokenData.email).
The matcher (findExistingOAuthConnectionMatch) already matches by explicit
connectionId first, but it was never reached when the payload had no top-level
email. GitHub Copilot's device-code flow keeps identity under
providerSpecificData.githubEmail, so tokenData.email is undefined — a refresh
(which passes the existing connectionId) skipped the match and fell through to
createProviderConnection, producing a duplicate connection.
- Widen the gate to if(connectionId || tokenData.email) so an explicit
connectionId is honored regardless of email.
- Guard the matcher's email branch with if(!tokenData.email) return false, so a
widened gate can't false-match an email-less connection via
safeEqual(undefined, undefined).
Fixes#8059.
Point dashboard provider cards at current Baidu developer landings instead of the deprecated yiyan nag page and the 301ing wenxinworkshop path.
Co-authored-by: LandLord64 <ulofeuduokhai@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
One-shot 提供商->提供者 normalization across src/i18n/messages/zh-CN.json
(679 substitutions) and bin/cli/locales/zh-CN.json (54), mirroring #8024's
zh-TW pass. Adds a versioned terminology glossary
(scripts/i18n/glossary/zh-CN.json), a protected-names list
(scripts/i18n/glossary/protected-terms.json), and a pure-function
consistency check (scripts/i18n/check-glossary-consistency.mjs,
npm run i18n:check-glossary) wired into CI as the i18n-glossary-zhcn job.
zh-CN added to the visual-QA harness default locales. Complements the
existing parity (check-ui-keys-coverage.mjs) and ICU (validate_translation.py)
gates without replacing them.
* fix(providers): add missing poe registry baseUrl entry (#8082)
The built-in poe provider (passthroughModels:true, NAMED_OPENAI_STYLE_PROVIDERS)
had no open-sse/config/providers/ REGISTRY entry, so model discovery's
getRegistryEntry("poe")?.baseUrl resolved to undefined and GET
/api/providers/[id]/models always failed with {"error":"No base URL
configured for provider"} even though credentials and inference worked fine
(the validation/inference path already had a hardcoded https://api.poe.com/v1
fallback). Adds a real REGISTRY entry mirroring moonshot/byteplus, and points
the audioMiscProviders.ts hardcoded fallback at the same POE_DEFAULT_BASE_URL
constant so both paths agree going forward.
* test: regenerate provider translate-path golden for poe (#8082)
src/domain/quotaCache.ts kept its quota state (cache Map, refreshingSet,
refreshTimer, tickRunning) in bare module-scope variables. In a Next.js 16
`output: "standalone"` build, code reachable only from instrumentation-node.ts
(providerLimitsSyncScheduler's write path) and code reachable from an
API-route/SSE-handler chunk (auth.ts::evaluateQuotaLimitPolicy()'s read path)
can be compiled into separate server chunks, each independently instantiating
this module's top-level state. A quota renewal written by the sync scheduler
was invisible to the routing read path, leaving accounts stuck exhausted until
a full process restart.
Anchors all quota-cache state on a single globalThis-held object, following
the same pattern already used in src/lib/credentialHealth/cache.ts and
src/lib/db/core.ts, and the identical fix already shipped for this exact
failure mode in src/lib/pricingSync.ts (#6325 / commit de9d748dac).
Regression test: tests/unit/repro-8065-quota-cache-cross-instance.test.ts
imports the module twice under distinct query-string specifiers to force two
separate module instances, proving a write from one instance is now visible
to a read from the other.
The Codex Responses-over-WebSocket bridge bypassed the whole prompt-compression
pipeline (and its analytics writes) that the HTTP/SSE path (chatCore.ts) runs on
every request, via two gaps:
1. prepare() in codex-responses-ws/route.ts never called anything from
open-sse/services/compression/* — it authenticated, injected memory, applied
reasoning-routing, then went straight to executor.transformRequest().
2. scripts/dev/responses-ws-proxy.mjs memoized the upstream connection in
ensureUpstream() and only called the internal "prepare" action on the FIRST
response.create of a WS session — every subsequent turn on a reused
connection bypassed prepare() (and therefore compression) entirely.
Fix: a new compression.ts module wires the core compression pipeline (settings
resolution -> selectCompressionStrategy -> applyCompressionAsync ->
compression_analytics/compression_engine_breakdown writes, reusing
adaptBodyForCompression's existing Responses-API input[] adapter) into
prepare(); responses-ws-proxy.mjs now re-runs prepare() (via a new shared
runPrepare() helper) for every logical response.create turn on a reused
connection, not just the first, without recreating the upstream socket.
Regression test: tests/unit/responses-ws-proxy-compression-parity.test.ts
proves the reused-connection bypass by execution (RED: 1 prepare call for 2
turns; GREEN after the fix: 2 prepare calls for 2 turns).
Windows console-window close delivers CTRL_CLOSE_EVENT, which Node/libuv maps
to a JS-visible SIGHUP event. initGracefulShutdown() only listened for
SIGTERM/SIGINT, so closing the window never ran cleanup() (WAL checkpoint +
closeDbInstance()), leaving storage.sqlite's WAL un-checkpointed for the next
launch.
Separately, process.kill(pid, "SIGTERM") on win32 unconditionally
force-terminates the target process instead of delivering an interceptable
signal. The CLI's own stop paths (ServerSupervisor.stop() and
runStopCommand()) sent it immediately on every stop, racing and beating the
child's own async graceful shutdown before the WAL checkpoint could run.
Fix:
- src/lib/gracefulShutdown.ts: register a SIGHUP handler alongside
SIGTERM/SIGINT.
- src/shared/platform/windowsProcess.ts (new): stopProcessGracefully() skips
the immediate SIGTERM on win32 (letting the target's own CTRL_C/CTRL_CLOSE
handling run) and polls before escalating to SIGKILL; unchanged immediate
SIGTERM behavior on POSIX.
- bin/cli/runtime/processSupervisor.mjs and bin/cli/commands/stop.mjs: use
stopProcessGracefully() instead of an unconditional process.kill(SIGTERM).
Regression tests: tests/unit/graceful-shutdown-sighup-8045.test.ts (reuses
the RED probe from the triage analysis) and
tests/unit/windows-process-stop-8045.test.ts.
checkRunnable() built the healthcheck spawn's minimalEnv.PATH from the
caller's PATH only, never merging in this Node's own bin dir the way
locateCommand's known-path search already does. npm-installed CLIs like
codex are `#!/usr/bin/env node` shebang scripts, so when the server is
launched with a minimal PATH (systemd/docker/PM2/Electron) lacking
node's dir, the healthcheck spawn fails even though the binary was
correctly located, and the tool shows as undetected.
Extracted the merge into a new buildHealthcheckPath() helper
(cliRuntimeHealthcheckPath.ts) to keep cliRuntime.ts within its frozen
file-size ceiling.
getDbInstance()'s probe-then-reopen pattern (written for per-open-handle
drivers like better-sqlite3/node:sqlite) was calling .close() on a
throwaway probe connection before opening the "real" connection right
after. For sql.js, openSqliteDatabase()'s fallback path always returns
the SAME module-global cached singleton for a given filePath, so closing
"the probe" closed the ONLY connection that file would ever get until
process restart — every subsequent query threw sql.js's raw "Database
closed" string, matching the reported crash-loop on every boot once
storage.sqlite already exists and both sync drivers are unavailable.
Adds closeProbeIfSafe() (src/lib/db/core.ts) and uses it at every
probe-close site in getDbInstance()/captureCriticalDbState() — it skips
the close for sql.js-backed adapters and lets the same live adapter flow
through, while still closing real per-handle drivers normally.
Also makes sqljsAdapter.ts's gracefulClose() remove its 3 process-level
listeners (beforeExit/SIGINT/SIGTERM) so a closed adapter's closure (raw
sql.js Database + buffers) can actually be garbage collected instead of
being pinned forever — addresses the compounding-OOM sub-finding as a
consequence of the same defect.
Regression test: tests/unit/db-sqljs-close-poison-7494.test.ts
* chore(ci): add .mergify.yml to main — Mergify only reads config from the default branch (#7168)
* feat(vnc-session): persistent noVNC browser login for web cookie/token providers
## Why (the headless-install problem)
OmniRoute's web cookie/token providers (ChatGPT Web, Gemini Web, Claude
Web, DeepSeek Web, …) need a live browser session, but the gateway normally
runs **headless** — as a systemd service, inside Docker, or on a VPS with no
display. There is no desktop for the operator to log into the provider in.
Today the operator has to obtain the session cookie/token *out of band* (open a
real browser elsewhere, export cookies, paste them into the connection row). That
is fiddly, breaks on every provider UI change, and is a non-starter on a
headless box where you can't open a browser at all.
This PR adds an **on-demand interactive login**: OmniRoute boots a
containerized browser that exposes a noVNC web UI at the host. The operator
opens that URL in *their own* browser, logs in normally, and OmniRoute then
harvests the resulting cookies / localStorage back into the provider's
`provider_connections` row over the DevTools Protocol. No display required on
the host — the headless server renders the login into a container and the human
just drives it through a web page.
## How we ran into this
- The shipped `dist/` bundle has **no App Router source**, so the only visible
seam was `dist/server-ws.mjs`'s `http.createServer` monkeypatch. That seam
is **dead**: Next's standalone `startServer` creates its own http server in a
way that bypasses the override, so a route registered there never fires
(debug logs confirmed: zero requests reached it). The real seam is the Next
**App Router** (`src/app/api/...`), which lives in the dev tree, not `dist/`.
- **Chromium ≥130 forces the remote-debugging port onto `127.0.0.1`** and
ignores `--remote-debugging-address=0.0.0.0`. A plain published port can't
reach it, so cookie harvest needs an in-container TCP bridge to republish the
loopback CDP onto `0.0.0.0`. We shipped that bridge, but the cleaner
default is **Firefox** (`jlesage/firefox`): its debugger binds `0.0.0.0` out
of the box, so harvest works with no bridge at all.
- The CDP harvester **hung forever** on the first tries: the message handler was
defined but never attached to the socket, so every `send()` promise stayed
pending. We replaced Playwright's `connectOverCDP` (which stalls through the
bridge) with a **raw `ws` client** and wired the handler — now resolves.
## What
New management API (scoped like the other admin endpoints via
`requireManagementAuth`):
| Method | Path | Purpose |
| --- | --- | --- |
| GET | `/api/vnc-session` | list active sessions + supported providers |
| GET | `/api/vnc-session/:provider` | session state |
| POST | `/api/vnc-session/:provider/start` | boot browser container → returns `vncUrl` |
| POST | `/api/vnc-session/:provider/harvest` | persist cookies into the provider row |
| POST | `/api/vnc-session/:provider/touch` | defer idle auto-stop |
| DELETE | `/api/vnc-session/:provider` | stop + remove the container |
## Implementation
- `src/lib/vncSession/manifest.ts` — provider → login URL + cookie/token map + config
- `src/lib/vncSession/harvest.ts` — raw-CDP cookie/localStorage harvester (`ws`)
- `src/lib/vncSession/service.ts` — docker lifecycle, port allocation, idle sweep, DB write
- `src/app/api/vnc-session/**` — App Router routes
- `src/lib/gracefulShutdown.ts` — tears down running login containers on exit
## Browser image choice
Default is **`jlesage/firefox`** (0.0.0.0-friendly CDP, no bridge). The
Chromium image + in-container bridge lives under `docker/vnc-browser/chromium`,
selectable via `OMNIROUTE_VNC_IMAGE`. See `docker/vnc-browser/README.md`.
## Config (env)
`OMNIROUTE_VNC_IMAGE`, `OMNIROUTE_VNC_CONTAINER_VNC_PORT`,
`OMNIROUTE_VNC_CONTAINER_CDP_PORT`, `OMNIROUTE_VNC_PROFILE_DIR`,
`OMNIROUTE_VNC_IDLE_MS`, `OMNIROUTE_VNC_MAX_MS`, `OMNIROUTE_VNC_MAX_SESSIONS`,
`OMNIROUTE_DOCKER_BIN` — all documented in the docker README.
## Tests
`tests/unit/vnc-session.test.ts` — manifest lookup + credential mapping
(cookie / token / whole-jar). All passing via the Node test runner.
## Notes
- Docker is the only external dependency; if the `docker` CLI is missing, `start`
throws a clear error and shutdown is a no-op.
- No secrets are returned by any endpoint — only session metadata + ports.
Co-authored-by: Sora <138304505+Capslockb@users.noreply.github.com>
Co-authored-by: Bernardo <138304505+Capslockb@users.noreply.github.com>
* refactor(vnc-session): derive provider credentials from shared contract
* fix(vnc-session): harden CDP harvesting and credential filtering
* refactor(vnc-session): scope lifecycle to provider connections
* fix(vnc-session): sanitize and scope management routes
* fix(vnc-session): use canonical provider list in API
* test(vnc-session): align coverage with canonical manifest
* docs(vnc-session): align browser setup with current implementation
* fix(security): loopback-gate /api/vnc-session (Hard Rule #15/#17)
The new /api/vnc-session/* routes spawn Docker containers via
child_process.spawn (src/lib/vncSession/service.ts) but were never
registered in LOCAL_ONLY_API_PREFIXES or SPAWN_CAPABLE_PREFIXES, so
they were reachable from non-loopback callers (any manage-scope API
key or dashboard session over a tunnel) - the same CVE class
(GHSA-fhh6-4qxv-rpqj) those constants exist to close.
Register VNC_ROUTE_PREFIX (already exported but unused in
manifest.ts) in both prefix lists, and add a regression test
asserting isLocalOnlyPath()/isLocalOnlyBypassableByManageScope()
correctly classify the new prefix.
Co-authored-by: CAPSLOCKB <138304505+Capslockb@users.noreply.github.com>
Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: Diego Rodrigues de Sa e Souza <8016841+diegosouzapw@users.noreply.github.com>
Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@gmail.com>
Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouzapw@users.noreply.github.com>
* chore(dashboard): reframe Kimi partnership as "Open Source Friends"
Kimi (Moonshot AI) asked to frame the collaboration under an "Open Source
Friends" narrative instead of "Official Sponsor". Adopt "Supported by our
Open Source Friends" — it keeps the backing/support signal and the friendship
warmth — with Kimi as the founding friend, listed first. The substance is
unchanged: affiliate links, the transparency note, first-in-list placement and
the banner display window all stay exactly as they were. Only the label moves.
- README: section header "Sponsors" -> "Supported by our Open Source Friends";
badge "Official Supporter" -> "Founding Friend"; thank-you and support-line
copy reworded; official K3 banner (public/sponsors/kimi-k3-banner.png) added
full-width at the top of the section, linked with aff=omniroute.
- ProviderCard: badge/tooltip fallback strings -> founding-friend wording.
- i18n: kimiSponsorBanner.title, kimiOfficialSupporterBadge and
kimiOfficialSupporterTooltip updated across all 43 locales (en + 42
translations), dropping the sponsor framing in every language.
- Test providerCardKimiPartnerAccent aligned to the new "Founding Friend" badge.
* docs(readme): add Sponsors honor-roll for financial backers
Credit the project's GitHub Sponsors just below the Open Source Friends
section. The two public sponsors (Professor Igor Morais Vasconcelos, longtao)
are named with avatar links; the one sponsor who chose private visibility on
GitHub Sponsors is credited anonymously, without exposing their identity.
* docs(readme): generalize private-sponsor credit to 'and others'
* feat(media): Adobe Firefly image + video generation provider
Add unofficial adobe-firefly media provider with full OpenAI-compatible
image and video generation: Nano Banana / GPT Image families, Sora 2,
Veo 3.1 (standard/fast/reference), and Kling 3.0.
Supports browser session cookies (auto IMS token exchange) or direct
IMS access tokens, async submit-and-poll against Firefly 3P endpoints,
aspect-ratio and resolution controls, and multi-account web-session UX.
Chat completions are intentionally rejected (media-only surface).
Includes unit coverage for registry wiring, payload builders, auth
resolution, and mocked generate happy-paths.
* fix(adobe-firefly): clio auth, discovery fallback, credits balance
Root-cause 401 invalid token against live firefly.adobe.com captures:
generate/discovery use x-api-key + IMS client_id clio-playground-web
(not projectx_webapp). Align headers/origin, dual cookie to IMS exchange
(clio first, Express fallback), BKS poll rewrite for /jobs/result.
Models: parse POST /v2/models/discovery + static fallback catalog from
adobe/get_models.txt; expand image/video registries.
Limits: GET firefly.adobe.io/v1/credits/balance (SunbreakWebUI1) with
total/remaining + free/plan detail quotas. Clarify cookie vs JWT UX.
Unit tests: 27/27 pass.
* fix(adobe-firefly): reject guest tokens from page-only cookies
Live repro with firefly.adobe.com Cookie export: IMS check with
guest_allowed=true returns account_type=guest (no AdobeID). That token
fails generate (401 invalid token) and credits/balance (403
ErrMismatchOauthToken). guest_allowed=false needs adobelogin.com IMS
session cookies which are not present in a page-only Cookie paste.
- Detect/reject guest JWTs; clear error tells user to paste Bearer JWT
- Prefer user JWT from HAR/mixed paste; improve credential extraction
- Update web-cookie + credential UX to recommend Authorization Bearer
Unit tests 29/29.
* fix(adobe-firefly): production auth, Limits, and 408 load handling
Live validation against firefly.adobe.com + packaged VibeProxy:
Auth / credentials
- Prefer IMS user JWT (Bearer from firefly-3p); reject guest tokens from
page-only cookies with an actionable error
- Extract JWT from Bearer, access_token=, IMS sessionStorage tokenValue,
and mixed HAR pastes; prefer non-guest tokens
- Strip JWT from Cookie header (undici Headers.append crash on mixed paste)
- Keep sherlockToken → x-arp-session-id + sanitized Cookie for generate
Limits
- credits/balance → Record quotas (firefly_total / free / plan) so
providerLimits caches them (arrays were ignored)
- Allowlist adobe-firefly + firefly in USAGE_SUPPORTED + APIKEY limits
- Live: 10000 plan credits parsed end-to-end after refresh
Generate
- Browser-shaped gpt-image body (size auto, no extra top-level size)
- Exponential 408 "system under load" retries (8 attempts) with clear
client message that 408 is Adobe capacity, not invalid token
- Live: generate returns proper 408 under load; balance/models stay 200
Tests: adobe-firefly unit suite 33/33 pass.
* fix(adobe-firefly): match live capture headers; add gpt-image-2
- Do not send firefly.adobe.com Cookie to firefly-3p (wrong-origin; soft 408)
- Lift sherlockToken only into x-arp-session-id
- Poll headers match status_check.txt (Bearer + accept, no x-api-key)
- Catalog gpt-image-2 alias → upstream modelVersion "2" (GPT Image 2)
- Shorter 408 retry budget so clients fail fast with clear message
- Unit suite 34/34
* fix(adobe-firefly): always send x-arp-session-id on generate (fixes 408)
Root cause of Bearer JWT → HTTP 408 colligo "system under load":
submit only set x-arp-session-id when sherlockToken was present in a
cookie paste. JWT-only credentials never sent the header, and Adobe
soft-blocks those requests with instant 408 (x-colligo-timeout:0.0).
A/B against a real user IMS token:
- det nonce + synthetic ARP → 200
- random nonce + synthetic ARP → 200
- det nonce without ARP → 408
Match adobe2api / GPT2Image-Pro:
- buildAdobeSubmitNonce = sha256(user_id + prompt[:256])
- buildAdobeArpSessionId = base64({sid, ftr}) synthetic session
- buildAdobeSubmitHeaders always sets both headers
Live adobeFireflyGenerateImage end-to-end: submit + poll → S3 presigned URL.
* fix(adobe-firefly): drop literal cred fallbacks + type-clean tests
Addresses pre-merge review feedback on #8006:
- Removes the `|| "literal"` fallback after resolvePublicCred() in
adobeFireflyApiKey()/adobeFireflyExpressClientId()/adobeFireflyBalanceApiKey()
(open-sse/services/adobeFireflyClient.ts). resolvePublicCred() already
always returns the decoded embedded default, so the literal fallback
was dead code that reproduced the exact env-or-literal anti-pattern
docs/security/PUBLIC_CREDS.md documents as BAD (Hard Rule #11).
- Replaces the 11 `@typescript-eslint/no-explicit-any` casts in
tests/unit/adobe-firefly.test.ts with concrete types
(Record<string, unknown>, Headers, Error-narrowing on the
assert.rejects predicate), matching the pattern already used
elsewhere in this suite. `no-explicit-any` is a hard ESLint error
under tests/ in this repo.
- Freezes file-size baseline entries for the new
open-sse/services/adobeFireflyClient.ts (1958 LOC, new-file cap 800,
mirrors the qoderCli.ts precedent for a legitimately large new
provider client), open-sse/config/imageRegistry.ts (800->821, new
adobe-firefly registry entry) and the +3 LOC growth in
src/lib/usage/providerLimits.ts (1000->1003).
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@gmail.com>
Co-authored-by: artickc <artickc@users.noreply.github.com>
* feat(sse): add HyperAgent (hyperagent.com) unofficial web provider
Reverse-engineered from live SPA captures (hyperagent/*.txt):
Chat:
- Cookie session auth (full Cookie header)
- New thread via GET /threads/new (or POST /api/threads)
- POST /api/threads/{id}/chat with SPA feature flags + content
- SSE parse of text/session_start/session_end/done events
- Multi-turn sticky threadId + sessionId cache (history prefix + last assistant)
Models:
- Hardcoded catalog from SPA pricing map
- Pretty display names (Claude Fable 5) while wire modelId stays fable etc.
- /v1/models exposes pretty name; chat uses modelId
Limits:
- GET /api/settings/billing/usage → creditBlocks initialUsd/remainingUsd/usedUsd
- USD Credits quota for Limits page
Tests: 15/15 unit/executor-hyperagent
* fix(sse): HyperAgent execution mode + fable-latest wire model (no plan mode)
* fix(sse): document HyperAgent env vars + regenerate golden snapshot
Addresses pre-merge review feedback on #7994:
- Documents HYPERAGENT_USAGE_URL in .env.example and ENVIRONMENT.md
(OMNIROUTE_DATA_DIR was already documented via the sibling PromptQL
provider) so check-env-doc-sync.test.ts passes.
- Regenerates the provider-translate-path golden snapshot to include
the new hyperagent/ha registry entries.
- Swaps the local toNumber() helper in usage/hyperagent.ts for the
canonical @/shared/utils/numeric import (#7879 no-restricted-syntax
rule landed on the release branch after this PR was opened).
- Freezes file-size baseline entries for the new
open-sse/executors/hyperagent.ts (937 LOC, new-file cap 800) and the
+3 LOC growth in src/lib/usage/providerLimits.ts (1000->1003), both
irreducible to this PR's own provider-registration wiring.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@gmail.com>
* fix(embeddings): support secure multimodal inputs
Closes#7956
* fix(embeddings): translate multimodal inputs and harden URL/base64 bounds
Reject oversize base64 before format validation to avoid Zod stack overflows,
translate canonical items to Jina modality-keyed and Gemini embedContent
contracts, and fetch HTTPS media server-side with DNS pinning before provider
submission.
Closes#7956
* fix(embeddings): pin DNS only for embedding media fetches
Default remote-image fetch keeps the previous globalThis.fetch path so
image-generation tests and callers stay mockable. Multimodal embeddings
still opt into undici DNS pinning for URL media.
* fix(embeddings): close 2 SSRF/DoS gaps in secure multimodal input (#7978)
Closes two gaps in the multimodal embedding input hardening from #7956:
1. `createPinnedFetch()` (the connection-pinning mechanism that closes the
DNS-rebinding TOCTOU window, GHSA-cmhj-wh2f-9cgx) had zero test coverage
anywhere in the repo. Writing that test surfaced a real regression: its
custom `connect.lookup` only implemented the single-address callback
form `(err, address, family)`. Node's autoSelectFamily/Happy Eyeballs
(on by default since Node 18) calls `lookup` with `{ all: true }` and
requires the array form `(err, addresses[])` — the mismatch threw
`ERR_INVALID_IP_ADDRESS` on every real pinned fetch, silently breaking
all URL-sourced multimodal embedding requests in production. Fixed by
branching on `options.all`.
2. The documented "16 MiB decoded per request" cap was enforced by the Zod
schema only for base64-sourced items; URL-sourced items were excluded,
and all up-to-32 items were fetched concurrently via `Promise.all` —
allowing ~256 MiB in memory at once (16x the documented bound). Fixed by
resolving items sequentially with a running byte budget shared across
base64 and fetched-URL sources, rejecting once the aggregate is
exhausted instead of after over-fetching.
Adds tests/unit/remote-image-fetch-pin-dns-connection.test.ts (real
loopback-server pinning tests) and a new aggregate-cap test in
tests/unit/embeddings-multimodal-7956.test.ts; both were verified to fail
against the pre-fix code before the corresponding fix was applied.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@gmail.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(grok-cli): require full auth.json on OAuth paste import (#7610)
The Grok Build paste path told operators to paste only the JWT "key"
field, which creates connections with refresh_token=null that can never
auto-refresh. Require the full ~/.grok/auth.json object (with
refresh_token) in OAuthModal, and reject bare JWT pastes with a clear
error.
* fix(grok-cli): add behavioral test coverage for auth.json paste-import (#7610)
Replace the source-regex-only test for the OAuth paste-import path with a
real behavioral suite (bare JWT rejected, auth.json missing refresh_token
rejected, multi-entry auth.json accepted, valid auth.json POSTed) using the
existing grok-device-oauth-modal.test.tsx jsdom harness. Extract
parseGrokCliPasteToken() into its own src/lib/oauth/utils/grokCliAuthJson.ts
module so it is directly unit-testable and to keep OAuthModal.tsx's frozen
file-size gate from growing (bump 1080->1100, justified in
file-size-baseline.json, mirroring the existing extraction precedent on
this file). Also fixes two pre-existing "JWT Token" label assertions that
this PR's own tab rename ("Import auth.json") had left stale.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com>
Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@gmail.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* Add Responses tool-output compression engine
* fix: enable Codex Responses stacked steps
* fix(compression): share Codex tokenizer and rebase UI
* fix(compression): sync MCP engine selection
* fix(compression): i18n parity for codex-responses mode + rebaseline
The codex-responses compression engine already imports the shared
countTextTokens/resolveTokenizerEncoding from tiktokenCounter.ts (no
duplicate encoder) and CompressionSettingsTab.tsx already threads the
new mode through the existing useTranslations()/labelKey pattern - both
pre-existing on this branch tip after rebasing onto release/v3.8.49.
What was missing after the rebase: the new compressionModeCodexResponses
/ compressionModeCodexResponsesDesc keys existed only in en.json. Filled
en-fallback into all 42 locales via scripts/i18n/fill-missing-from-en.mjs
and added real pt-BR/vi translations. Also rebaselined the three files
whose own growth (new codex-responses mode wiring) crossed the frozen
file-size caps: open-sse/mcp-server/schemas/tools.ts, open-sse/services/
compression/strategySelector.ts, and src/lib/db/compression.ts.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@gmail.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* feat: provider tab account search + mirrored top pagination (#7937)
Two client-side UI improvements to the provider connections/accounts list
(all data already loaded in memory; PAGE_SIZE=50):
- Mirror the pagination bar ABOVE the list (previously bottom-only) in both
the flat/untagged branch and the tagged/grouped branch.
- Add a case-insensitive substring account search input (id/tag/name/email)
to the left of the status filter pills, searching across ALL accounts
(not just the current page), resetting pagination to page 0 on change.
- Add pagination to the tagged/grouped view, which previously had none.
New pure helper `connectionsSearchFilter.ts` keeps the substring matcher
testable and out of the already-large ConnectionsListPanel.tsx.
Closes#7937
* i18n(vi): add providers.accountSearchPlaceholder for locale parity (#7937)
Complete the translation catalogs for the 40 locales covered by this PR and rebase them onto the current release/v3.8.49 tip.
Translate the 9 Kimi sponsor and preset keys introduced by #8039. Leave en.json, vi.json, and zh-TW.json untouched so #8024 remains authoritative for Traditional Chinese.
The UI-key coverage gate reports 100% for all 40 touched locales with no missing keys or placeholders.
Co-authored-by: nguyenha935 <208228297+nguyenha935@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* feat: narrow mcp:connect scope + per-key HTTP tool-scope binding (#7895)
Adds MCP_CONNECT_SCOPE ("mcp:connect"), a narrow additive API-key scope
(kept out of MANAGEMENT_API_KEY_SCOPES, same precedent as SELF_USAGE_SCOPE)
that authorizes ONLY the /api/mcp/ LOCAL_ONLY route-guard carve-out --
remote MCP-only callers no longer need broad manage/admin scope just to
reach the transport routes. Scoped strictly to /api/mcp/; every other
LOCAL_ONLY bypass prefix still requires hasManageScope() unchanged.
Also resolves the caller's real api_keys.scopes over HTTP/SSE
(httpAuthContext.ts::resolveMcpCallerAuthInfo) and passes it to the MCP
SDK's transport.handleRequest(req, { authInfo }), so extra.authInfo.scopes
reaching tool calls reflects the Bearer key's own scopes instead of the
OMNIROUTE_MCP_SCOPES env fallback -- scopeEnforcement.ts already prioritized
authInfo, it was simply unfed over HTTP. Does not flip the
OMNIROUTE_MCP_ENFORCE_SCOPES default; stdio is unaffected (no per-caller
identity, stays on the meta/env fallback chain).
Closes#7895
* test(mcp): register mcp-connect-scope test in stryker tap.testFiles (#7895)
