Normalize numeric pino levels correctly in the console log API so the logger transport fix does not misclassify info, warn, and error entries in file-backed logs.
Add a targeted regression test for numeric log entries.
Clear recovered provider error metadata after successful
credentialed requests in non-chat API routes as well.
Add route-level regression tests covering a Response-based
success path and a result-object success path.
Thanks @rexname (Maulana Hasanudin)! 🎉
Codex account quota policy (5h/weekly) with auto-rotation is now merged. Highlights:
- Per-account policy toggles (5h + weekly ON/OFF) in the Provider dashboard
- Accounts automatically skipped when enabled quota window reaches 90% threshold
- Auto re-eligibility when resetAt timestamp passes (no manual intervention needed)
- Side-effect free `getQuotaWindowStatus` getter design
- Safe partial merge of `codexLimitPolicy` on provider updates
Merged on top of main (v2.5.0) with no conflicts. Analytics label fix (#356) included. Thanks for the excellent quality and the 2-commit cleanup round! 🙏
Add a default-off dashboard setting that injects Codex fast service tier only when the request did not already specify one.
Also preserve service_tier through OpenAI-to-Responses translation and restore the setting at startup.
- add quota window status helper for Codex session (5h) and weekly windows
- enforce policy-based account filtering when enabled windows reach threshold
- return all-rate-limited metadata when no Codex account is eligible
- add per-account dashboard toggles for 5h and weekly policy controls
- merge codexLimitPolicy safely on provider updates to preserve partial settings
- document purpose and usage scenarios in README (EN + ID + i18n note)
- fix#355: increase STREAM_IDLE_TIMEOUT_MS from 60s to 300s to prevent
premature stream abortion for extended-thinking models (claude-opus-4-6,
o3, etc.) that can pause >60s during reasoning phases. Configurable via
STREAM_IDLE_TIMEOUT_MS env var.
- fix#350: combo health check test now bypasses REQUIRE_API_KEY=true by
sending X-Internal-Test header, recognized in chat.ts auth pipeline to
skip API key validation for internal admin-side combo tests. Also
extended test timeout from 15s to 20s. Uses OpenAI-compatible format
universally (not Claude-style).
- fix#346: filter out tools with empty function.name before forwarding
to upstream providers. Claude Code sends empty-name tool definitions
that cause '400 Invalid input[N].name: empty string' on OpenAI-compat
providers. Extends existing message/input empty-name filter.
- Add .catch() to initial and periodic sync promises (Gemini, Kilo)
- Wrap JSON.parse in try-catch for corrupted DB data (Kilo)
- Wrap response.json() in try-catch for invalid LiteLLM JSON (Kilo)
- Validate PRICING_SYNC_INTERVAL (guard against NaN/0 → tight loop) (Copilot)
- Validate and allowlist sources — reject unknown, prevent empty sync
from clearing pricing_synced data (Copilot, Kilo)
- Extract merge loop into shared iteration to reduce duplication (Gemini)
- Add data/warnings fields to MCP output schema (Copilot)
- Remove unused z import in vitest (Copilot)
- Filter non-string entries from sources array in API route (Copilot)
- Track active interval for accurate getSyncStatus().nextSync (Copilot)
* fix: tool description null sanitization, clipboard HTTP fallback fixes
T10 - Sanitize tool.description null in claude-to-openai translator
- claude-to-openai.ts: tool.description defaults to empty string when null/undefined
- claude-to-openai.ts: filter out tools with empty/missing names
- Prevents 400 validation errors on providers like NVIDIA NIM (issue #276)
T11 - Fix copy buttons to work on HTTP/non-HTTPS deployments
- Add src/shared/utils/clipboard.ts with HTTPS+HTTP (execCommand) dual fallback
- Migrate useCopyToClipboard.ts to use shared utility
- Migrate ConsoleLogViewer.tsx, RequestLoggerV2.tsx to shared utility
- Migrate HomePageClient.tsx, endpoint/page.tsx, GetStarted.tsx
- Migrate DefaultToolCard.tsx to shared utility
- Fixes copy buttons when OmniRoute runs behind HTTP proxy (issue #296)
T02 - Verified SSE [DONE] sentinel handling already correct
- sseParser.ts filters [DONE] on line 13 (no change needed)
- stream.ts uses doneSent flag to prevent duplicate sentinel
- bypassHandler.ts correctly separates streaming/non-streaming responses
Issue triage comments posted to #340, #341, #344
* feat: DB read cache + Accept header stream negotiation (T09/T01)
T09 - In-memory TTL cache for hot DB read paths
- Add src/lib/db/readCache.ts with TTL cache (5s settings/connections, 30s pricing)
- Eliminates redundant SQLite reads on concurrent requests
- Integrate invalidation in settings.ts updateSettings() and updatePricing()
- Integrate invalidation in providers.ts create/update/delete operations
- Export getCachedSettings, getCachedPricing, getCachedProviderConnections,
invalidateDbCache via localDb.ts for consumer migration
- Cache auto-busts on any write, preserving data consistency
T01 - Accept header stream negotiation
- src/sse/handlers/chat.ts: detect Accept: text/event-stream header
- Override body.stream=true when Accept header indicates streaming client
- Enables curl, httpx and SDK clients that use HTTP headers instead of JSON
body field to trigger streaming responses
- Logs Accept override at DEBUG level for observability
* fix: auto-advance quota window on expiry to prevent stale blocking (T08)
T08 - Quota Window Rolling Auto-Advance
- quotaCache.ts: add windowDurationMs field to QuotaCacheEntry interface
(optional field that callers can set when they know the window duration)
- Add advancedWindowResetAt() helper: if entry.nextResetAt is in the past,
eagerly returns { exhausted: false } so requests are unblocked immediately
- isAccountQuotaExhausted() now uses advancedWindowResetAt() instead of
the previous inline date check, and optimistically clears entry.exhausted
flag to avoid re-checking the same stale entry on the next request
Before: exhausted accounts with an expired resetAt would wait up to 5
minutes for the background refresh before accepting new requests.
After: the first request after resetAt passes will be immediately accepted
and will trigger a quota refresh on the next background tick.
* feat: manual OAuth token refresh UI (T12)
T12 - Manual Token Refresh UI
- Add POST /api/providers/[id]/refresh endpoint
- Validates connection exists and is OAuth type
- Calls getAccessToken() (same helper used in auto-refresh)
- Persists new credentials via updateProviderCredentials()
- Returns { success, expiresAt, refreshedAt } on success
- Update providers/[id]/page.tsx
- handleRefreshToken() with loading state (refreshingId)
- Pass onRefreshToken + isRefreshing props to ConnectionRow
- ConnectionRow: add optional onRefreshToken/isRefreshing props
- ConnectionRow: tokenMinsLeft state via lazy init (Date.now() in
getter fn, not in render body - satisfies react-hooks/purity)
- Token expiry badge: red 'expired' | amber '~Xm' (<30min) | hidden
- 'Token' button (amber) next to 'Retest' for OAuth connections
- Add en.json i18n: tokenRefreshed, tokenRefreshFailed
* Initial plan
* feat: integrate wildcardRouter into model alias resolution (T13)
T13 - Wildcard Model Routing
- Import resolveWildcardAlias from wildcardRouter.ts into model.ts
- In getModelInfoCore(), after exact alias check fails, try glob wildcard
alias matching (e.g., 'claude-sonnet-*' alias → 'anthropic/claude-sonnet-4')
- Returns { provider, model, extendedContext, wildcardPattern } on match
- Falls back to MODEL_TO_PROVIDERS lookup and openai default as before
* fix: clipboard cleanup and tool validation
* feat: media page UX + T04 playground uploads + T03 HuggingFace/Vertex AI
Media Page (MediaPageClient.tsx):
- Render images inline (img tags from b64_json or url)
- Show transcription as plain readable text (not raw JSON)
- Amber banner for credential errors with link to /dashboard/providers
- Detect empty transcription result and show credentials hint
- Provider credential hint below selector for non-local providers
- Extended provider/model lists: HuggingFace, Qwen TTS, Inworld, Cartesia, PlayHT, AssemblyAI
T04 - Playground File Uploads (playground/page.tsx):
- Audio file upload panel for transcription endpoint (multipart/form-data)
- Image upload panel for vision models (gpt-4o, claude-3, gemini, pixtral, llava...)
- Auto-detect vision models by name heuristic
- Inject uploaded images as base64 image_url in chat messages
- Inline image rendering for image generation results
- Readable text view for transcription results with copy button
- Preview thumbnails for attached images with individual remove
T03 - HuggingFace + Vertex AI Providers:
- HuggingFace: frontend providers.ts + backend providerRegistry.ts
Uses HuggingFace Router OpenAI-compatible endpoint
- Vertex AI: frontend providers.ts + backend providerRegistry.ts
Uses gemini format with generateContent API (urlBuilder fallback)
T07 - API Key Round-Robin: VERIFIED already implemented in auth.ts
fill-first, round-robin, p2c, random, least-used, cost-optimized strategies
* feat: T05 task-aware routing + fix#302 stream override + fix#73 claude provider fallback
T05 - Task-Aware Smart Routing:
- New open-sse/services/taskAwareRouter.ts:
Detects 7 task types: coding, creative, analysis, vision, summarization,
background, chat from system/user message content and images
Configurable taskModelMap per task type, stats tracking
applyTaskAwareRouting() integrates with existing chat pipeline
- New src/app/api/settings/task-routing/route.ts:
GET/PUT/POST API for task routing config + reset-stats + detect action
Persists config via updateSettings('taskRouting')
- Integration in src/sse/handlers/chat.ts:
applyTaskAwareRouting() called after policy enforcement, before combo resolve
Logs task type detection and model overrides
Fix#302 - OpenAI SDK stream=False drops tool_calls:
- src/sse/handlers/chat.ts T01 Accept header negotiation:
Changed condition from 'body.stream !== true' to 'body.stream === undefined'
OpenAI Python SDK sends 'Accept: application/json, text/event-stream' in every
request, even stream=False — the old code was incorrectly forcing stream=true,
causing tool_calls to be dropped from non-streaming responses
Fix#73 - Claude Haiku routed to OpenAI provider instead of Antigravity:
- open-sse/services/model.ts getModelInfoCore():
Added heuristic prefix detection before the blind 'openai' fallback:
claude-* models → antigravity (Anthropic) provider
gemini-*/gemma-* models → gemini provider
Closes: #73, partially addresses #302
* fix: token counts 0 (#74), model import dup (#180), model route fallback (#73)
fix#74 - Token counts always 0 for Antigravity/Claude streaming:
- open-sse/utils/usageTracking.ts extractUsage():
Add handler for 'message_start' SSE event which carries INPUT tokens in
Antigravity/Claude streaming:
{ type: 'message_start', message: { usage: { input_tokens: N } } }
This event was completely unhandled, causing ALL input token counts to be
dropped for every Antigravity/Claude streaming request
fix#180 - Model import shows duplicates with no visual feedback:
- src/shared/components/ModelSelectModal.tsx:
Added addedModelValues prop (string[]) to receive already-added model values
Models already in the combo now shown with ✓ indicator + green highlight
Makes it visually clear which models are already added vs new
- src/app/(dashboard)/dashboard/combos/page.tsx:
Pass addedModelValues={models.map(m => m.model)} to ModelSelectModal
* Harden clipboard UX and Claude tool normalization (#360)
* Initial plan
* chore: plan updates for clipboard and translator fixes
* fix: clipboard cleanup, copy feedback, and claude tool validation
---------
Co-authored-by: openai-code-agent[bot] <242516109+Codex@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
Co-authored-by: openai-code-agent[bot] <242516109+Codex@users.noreply.github.com>
- fix(oauth): restore iFlow clientSecret default — was empty string, now uses the valid public key (#339)
- fix(mitm): compile src/mitm/*.ts to JS during prepublish so server.js exists in npm bundle (#335)
- fix(gemini-cli): graceful projectId fallback — warn + empty string instead of hard 500 error (#338)
- feat(models): add gpt5.4 to Codex; add claude-sonnet-4, claude-opus-4.6, deepseek-v3.2, minimax-m2.1, qwen3-coder-next, auto to Kiro (#334)
- fix(electron): sync electron/package.json version to 2.3.13 (#323)
- feat(scoring): add tierPriority (0.05) to ScoringWeights Zod schema and combos/auto API route
- cline.ts: add decodeURIComponent before base64 decode to handle URL-encoded codes
- cline.ts: populate name = firstName+lastName || email in mapTokens
- oauth/exchange route: normalize name=email for all providers on exchange/poll/poll-callback
- Fixes: accounts showing Account #ID instead of email in providers dashboard
fix(test): security-fase01.test.mjs imports inputSanitizer.js → .ts
- The file is TypeScript-only (no compiled .js). Node was failing with
ERR_MODULE_NOT_FOUND in CI because the import path pointed to a
non-existent .js file.
fix(acp): add validateBody(jsonObjectSchema) to POST /api/acp/agents
- Satisfies check:route-validation:t06 lint rule that requires all
routes using request.json() to go through validateBody().
- Uses jsonObjectSchema (passthrough) since body shape varies between
the 'refresh' action and the custom agent creation payload.
- Manual field validation below remains unchanged.
- All 139 routes now pass the route-validation lint check.
fix(deploy-vps): add continue-on-error on SSH step + command_timeout
- SSH connection failures (host unreachable / secrets not set) no
longer mark the workflow run as failed.
- The DEPLOY_ENABLED guard still prevents the job from running when
the variable is not set to 'true'.
- Add Dashboard > Debug > Agents page: grid of 14 built-in CLI agents
with installation status, version detection, protocol badges
- Add custom agent support: users can register any CLI tool via form
- Expand registry from 5 to 14 built-in agents (aider, opencode, cline,
qwen-code, forge, amazon-q, interpreter, cursor-cli, warp)
- Add 60-second detection cache to avoid repeated execSync calls
- API: GET lists all agents, POST adds custom/refreshes, DELETE removes
- Settings schema: add customAgents array field
- Fix missing themeCoral in settings namespace for all 30 languages
- Add agents sidebar key in all 30 languages
- Add agents page i18n namespace (en + pt-BR)
- Add model playground page to dashboard (provider/model/endpoint selectors, Monaco editor, streaming, abort)
- Add CLI fingerprint matching (per-provider header/body ordering to match native CLI binaries)
- Add ACP module (CLI agent discovery, process spawner, session manager, API endpoint)
- Add playground to sidebar debug section with i18n support
- Close#192 and #200 as stale (v1.8.1, no repro info)
- Fix inverted Claude OAuth utilization (remaining, not used)
- Add hasUtilization() guard to prevent false exhaustion from empty responses
- Centralize anthropic-version into CLAUDE_CONFIG.apiVersion
- Add parseDate() for safe date validation in quota cache
- Batch background refresh with MAX_CONCURRENT_REFRESHES=5
- Move setModelUnavailable to after all accounts exhausted, not first 429
- Extract safePercentage() to shared utils (dedup)
- Use isRecord() type guard in usage API route
- Exclude binary files from Tailwind v4 source scanning
- Move setModelUnavailable from per-account loop to all-accounts-exhausted path
- Clear model unavailability on successful fallback
- Add in-memory quota cache with background refresh (5min active, 20min exhausted)
- Integrate quota cache in account selection to skip exhausted accounts
- Mark accounts as exhausted from 429 when no cached quota data exists
- Populate quota cache from dashboard usage endpoint
- Created httpTransport.ts with singleton MCP server and WebStandard
Streamable HTTP transport running inside Next.js process
- Added /api/mcp/sse route (GET+POST) for SSE transport
- Added /api/mcp/stream route (GET+POST+DELETE) for Streamable HTTP
- Added mcpTransport enum to settingsSchemas (stdio|sse|streamable-http)
- Updated /api/mcp/status to report HTTP transport state
- Added TransportSelector UI with mode buttons and connection URL display
- Routes guard against disabled MCP or wrong transport mode
- Created settingsSchemas.ts with updateSettingsSchema to avoid webpack
tree-shaking the schema from the 908-line schemas.ts barrel file
- Updated settings/route.ts import to use new dedicated file
- Fixed focusRingColor lint error in ServiceToggle
Extracted validateBody, isValidationFailure, and loginSchema from the
935-line schemas.ts barrel file into a dedicated helpers.ts module.
Updated 70 API route files to import directly from helpers.ts.
Root cause: webpack on certain environments fails to resolve exports
from the bottom of large barrel files (schemas.ts), causing
'(0, O.Jb) is not a function' errors in production builds.
Fix: Split validation helpers into a small dedicated module (helpers.ts)
so webpack can correctly resolve all exports regardless of file size.
- TypeScript compiles with 0 errors
- All API routes updated to import from helpers.ts
- schemas.ts re-exports from helpers.ts for backward compatibility
- syncAndVerify now returns cloudUrl in API response for frontend to use
- EndpointPageClient uses dynamic cloudBaseUrl state instead of relying on env var
- Falls back gracefully when NEXT_PUBLIC_CLOUD_URL is not set (Docker deployments)
- Fixed setInterval in accountFallback.ts global scope for Cloudflare Workers compat
- Modified OAuth exchange route to use upsert logic at all 3 connection-save locations
- Before creating a new connection, checks for existing connections with same provider+email+authType
- If match found, calls updateProviderConnection() to refresh tokens instead of creating duplicate
- Falls back to createProviderConnection() for genuinely new connections
- Fixes: re-auth button creating new account entries instead of refreshing existing ones
Approved — adds multi-modal support with new TTS/STT/Image/Video/Music providers. Follow-up commits will add frontend pages, unit tests, and configurable local provider URLs.
- Add path traversal validation for ElevenLabs voice_id and HuggingFace
model_id URL concatenation (prevents SSRF via ../ sequences)
- Add saveCallLog usage tracking to video and music handlers for
consistent analytics with imageGeneration.ts
- Extract shared upstreamErrorResponse() and audioStreamResponse()
helpers to reduce error handling duplication in audioSpeech.ts
- Extract shared upstreamErrorResponse() and isValidPathSegment()
helpers in audioTranscription.ts
- Add explicit format: "openai" to qwen TTS and STT provider entries
- Remove unused modelId parameter from handleCoquiSpeech and
handleTortoiseSpeech
- Filter cloud video/music providers by active status in models route
(local providers with authType: "none" always listed)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add 6 TTS providers (Nvidia NIM, ElevenLabs, HuggingFace, Coqui, Tortoise,
Qwen3), 3 STT providers (Nvidia NIM, HuggingFace, Qwen3), 2 local image
providers (SD WebUI, ComfyUI), and two new modalities — Text-to-Video
(/v1/videos/generations) and Text-to-Music (/v1/music/generations).
Key design decisions:
- Format-based unified providers: local providers grouped by API format
(comfyui, sdwebui, coqui, tortoise, openai-compatible) with configurable
base URLs and expandable model lists
- Cloud providers kept separate (unique auth and API shapes)
- Local providers use authType: "none" — credential checks bypassed at both
route and handler level
- Shared ComfyUI client (comfyuiClient.ts) reused across image/video/music
- Shared registry utilities (registryUtils.ts) for model parsing and listing
- Qwen3 TTS/ASR use format: "openai" — no custom handler needed
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
