Commit Graph

856 Commits

Author SHA1 Message Date
Diego Rodrigues de Sa e Souza
ce560ebe9d fix: resolve issues #273, #276, #277 — image routing, models route, missing-key error (#282)
Squash merge PR #282: bug fixes for #273 (Gemini image routing), #276 (Ollama Cloud models), #277 (missing apiKey error), lint fix, and all security code-scanning patches.
2026-03-10 09:48:50 -03:00
diegosouzapw
ebd1e5421b feat(kimi-coding): add Kimi Coding plan quota display (#279)
- Add getKimiUsage() with X-Msh-* device headers for Kimi API
- Parse weekly quota + rate-limit breakdown from /v1/usages endpoint
- Fix X-Msh-* headers in refreshKimiCodingToken (was missing)
- Wire kimi-coding into getUsageForProvider switch
- Add quota capability flag to providers.ts
- Remove console.warn/error (production-safe silent returns)

Co-authored-by: nyatoru <nyarutoru0002@outlook.co.th>
2026-03-10 09:04:03 -03:00
jack
5ab6a3b431 fix(validation): support elevenlabs and inworld API key checks 2026-03-10 11:20:19 +00:00
nyatoru
6e1bf4652d feat(kimi-coding): update platform and version for Kimi Coding integration 2026-03-10 14:18:57 +07:00
nyatoru
3991c96c78 feat(kimi-coding): integrate Kimi Coding API for token refresh and usage tracking 2026-03-10 14:12:37 +07:00
Diego Rodrigues de Sa e Souza
44ee62e391 feat(#248,#260): TTS provider support + friendly display names (#262)
* feat(#248,#260): TTS provider support + friendly display names

## #248 — Text to Speech endpoint expansion
- audioRegistry: add Inworld, Cartesia, PlayHT providers with correct auth/format tags
- audioSpeech handler: add handleInworldSpeech (base64 decode), handleCartesiaSpeech (X-API-Key + transcript), handlePlayHtSpeech (X-USER-ID)
- /dashboard/media: add Speech tab with voice selector, format selector, and inline <audio> player (Blob URL)
- /dashboard/playground: add Text to Speech option; detect audio/* Content-Type and render inline audio player

## #260 — Friendly provider/account display names
- src/lib/display/names.ts: new centralized helper module with getAccountDisplayName() and getProviderDisplayName()
- src/lib/usage/usageStats.ts: replace raw connectionId.slice(0,8) fallbacks with getAccountDisplayName()
- src/app/api/rate-limits/route.ts: replace raw connectionId.slice(0,8) fallback with getAccountDisplayName()

* feat(#248,#261): ElevenLabs voice presets + mobile UX fixes

## #248 — ElevenLabs/Cartesia/Deepgram/Inworld voice presets
- MediaPageClient: replace static SPEECH_VOICES with provider-aware PROVIDER_VOICE_PRESETS
  - ElevenLabs: 9 premade voices with name+type (Rachel, Domi, Bella, Antoni, Elli, Josh, Arnold, Adam, Sam)
  - Cartesia: 3 built-in voices (Barbershop Man, Friendly Reading Man, California Girl)
  - Deepgram: 5 Aura voices (Asteria, Luna, Stella, Zeus, Orion)
  - Inworld: 2 voices (Eva, Marcus)
  - default: OpenAI 6 standard voices (alloy, echo, fable, onyx, nova, shimmer)
- Voice dropdown updates automatically when model input prefix changes

## #261 — Mobile UX improvements
- DashboardLayout: add h-dvh to mobile sidebar wrapper for proper scroll containment
- Sidebar: add h-full to aside element so nav can scroll on short screens
- ProvidersPage: change all 4 section headers from flex justify-between to flex flex-wrap so actions wrap on narrow screens instead of overflowing

---------

Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
2026-03-09 13:43:48 -03:00
diegosouzapw
1c2f553a7c feat: features 07/09/04/06 — codex clamp, openrouter cache, quota preflight & monitor
feat(codex): clamp reasoning effort per model (feature-07)
- Add MAX_EFFORT_BY_MODEL table in CodexExecutor
- Add clampEffort() applied after effort derivation
- Logs debug when clamp is applied

feat(catalog): OpenRouter catalog with persistent cache (feature-09)
- New src/lib/catalog/openrouterCatalog.ts with TTL 24h + stale-if-error
- New GET /api/models/openrouter-catalog endpoint (authenticated)
- Reduces redundant OpenRouter API calls from dashboard

feat(quota): quota preflight with per-provider toggle (feature-04)
- New open-sse/services/quotaPreflight.ts
- Toggle: providerSpecificData.quotaPreflightEnabled (default: false)
- Extensible via registerQuotaFetcher() pattern
- Graceful degradation when no fetcher registered

feat(quota): quota session monitor with per-provider toggle (feature-06)
- New open-sse/services/quotaMonitor.ts
- Toggle: providerSpecificData.quotaMonitorEnabled (default: false)
- Adaptive polling: 60s normal / 15s critical
- Alert deduplication (5min suppression window)
- timer.unref() ensures clean process exit

feat(providers): support providerSpecificData patch in PUT /api/providers/[id]
- Partial merge of providerSpecificData (preserves existing keys)
- Schema updated to accept providerSpecificData in updateProviderConnectionSchema
2026-03-08 17:36:17 -03:00
diegosouzapw
e4a11bd6d0 feat: ACP Agents dashboard + themeCoral i18n fix
- 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)
2026-03-07 11:19:12 -03:00
diegosouzapw
ac89069671 feat: playground, CLI fingerprints, ACP support (#234, #223, #235)
- 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)
2026-03-07 10:24:43 -03:00
diegosouzapw
97a67b5d3e fix: persist lastUsedAt in provider_connections schema for round-robin (#218)
- Add last_used_at column to provider_connections CREATE TABLE schema
- Add ensureProviderConnectionsColumns migration for existing databases
- Add last_used_at to INSERT and UPDATE SQL in providers.ts
- Add last_used_at to JSON migration INSERT in core.ts
- Add zod to serverExternalPackages in next.config.mjs (#217)

Fixes #218: Round-robin routing strategy now correctly persists
the lastUsedAt timestamp, allowing rotation between accounts.

Fixes #217: zod module is now properly included in standalone/Docker
builds by declaring it as a server external package.
2026-03-05 23:22:10 -03:00
diegosouzapw
228ebf436e feat: endpoint-aware model management + fix 3 bugs (#212, #213, #200)
Bug Fixes:
- #212: Auto-generate API_KEY_SECRET at startup (like JWT_SECRET)
- #213: Circuit breaker now scoped per-model instead of per-provider
- #200: Connectivity fallback for custom providers (Ollama, LM Studio)

Features:
- #204: API Format selector (Chat Completions / Responses API) for custom models
- #205: Combo endpoint field (chat / embeddings / images) in schema
- #206: Supported Endpoints checkboxes (chat, embeddings, images, audio)
- Custom models with endpoint tags appear in /v1/embeddings and /v1/images/generations
- Model catalog includes api_format, type, and supported_endpoints metadata
- Provider detail page shows badges for non-default endpoint configurations

Files changed: instrumentation.ts, combo.ts, validation.ts, models.ts,
schemas.ts, provider-models/route.ts, providers/[id]/page.tsx,
catalog.ts, embeddings/route.ts, images/generations/route.ts
2026-03-05 18:49:07 -03:00
diegosouzapw
21135407af feat: Introduce new A2A and MCP API routes, enhance dashboard UI, update READMEs, and add E2E tests. 2026-03-05 11:16:56 -03:00
diegosouzapw
baa0208fa9 feat: v2.0.0 - MCP server, A2A agent, proxy improvements and docs update 2026-03-05 01:16:56 -03:00
diegosouzapw
0d8f28a4a4 feat: Introduce A2A lifecycle management, add type safety to ComfyUI and stream handling, and update various handlers and translators. 2026-03-04 21:02:56 -03:00
diegosouzapw
85c6b63c8f feat: add error pages, harden DB layer and compliance module
- Add HTTP error pages (400, 401, 403, 408, 429, 500, 502, 503)
- Add maintenance, offline, and system status pages
- Harden db/core.ts, db/apiKeys.ts, db/cliToolState.ts, db/backup.ts
- Strengthen compliance/index.ts audit logging
- Improve container.ts DI registrations
- Fix dataPaths.ts and tokenHealthCheck.ts
2026-03-04 19:35:38 -03:00
diegosouzapw
052eb8d330 refactor: replace any types with generics and add Zod validation schemas
Eliminate `any` usage across the codebase by introducing proper generics,
typed interfaces (StatementLike, DbLike, PromptRow, etc.), and helper
conversion functions (toNumber, toString, parseVariables). Add
comprehensive Zod validation schemas for API endpoint inputs to enforce
runtime type safety alongside compile-time checks.
2026-03-04 18:59:27 -03:00
diegosouzapw
5ecef5c90c feat: normalize quota and combos API responses with shared contracts
Introduce `normalizeQuotaResponse` and `normalizeCombosResponse` helpers
to handle varying API response shapes (array vs wrapped object)
consistently across MCP server and advanced tools. Add optional `meta`
field to checkQuotaOutput schema and update sourceEndpoints to reflect
current API routes.
2026-03-04 08:18:09 -03:00
diegosouzapw
e18cfe1d80 feat: add Phase 3 advanced MCP tools and A2A smart routing skill
Register 8 new advanced MCP tools (simulate_route, set_budget_guard,
set_resilience_profile, test_combo, get_provider_metrics,
best_combo_for_task, explain_route, get_session_snapshot) with their
handler implementations. Add A2A smart routing skill that routes
prompts through the OmniRoute pipeline with routing explanation,
cost envelope, and resilience trace metadata.
2026-03-03 18:53:11 -03:00
diegosouzapw
7eb45b2e19 feat: add MCP server mode with --mcp flag for IDE integration
Add stdio-based MCP server support to OmniRoute CLI, enabling AI agents
in VS Code, Cursor, Claude Desktop, and Copilot to interact with
OmniRoute tools (health, combos, quota, routing). Update help text,
gitignore vscode-extension subproject, and include MCP/A2A strategy report.
2026-03-03 17:42:24 -03:00
duongvdo
0e207dc5d2 fix: proxy logic bugs and Docker build failure
- URL-encode proxy credentials to handle special characters in passwords
- Decode URL-encoded credentials during legacy proxy migration
- Fix HTTPS proxy default port (443 instead of 8080) in frontend and migration
- Add dispatcher cache invalidation when proxy config changes
- Cast proxy port to number for SQLite INTEGER column in proxy logger
- Fix redundant .replace("//", "") in migration protocol parsing
- Copy postinstall script in Dockerfile before npm install

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-01 00:48:27 +07:00
benzntech
6ed98fb21c Merge branch 'main' of https://github.com/diegosouzapw/OmniRoute into feat/memory-optimization 2026-02-28 09:52:39 +05:30
diegosouzapw
d8bf4b1db8 chore(release): bump version to v1.6.3 2026-02-28 00:55:59 -03:00
diegosouzapw
12f7d2b484 fix: preserve database data on upgrade when old schema_migrations exists (#146)
Previously, the upgrade detection logic renamed the entire DB file when it
found a schema_migrations table (from older versions), causing data loss.
Now checks if the DB actually contains data (provider_connections) before
deciding to rename. If data exists, drops only the old migration tracking
table and lets the new CREATE TABLE IF NOT EXISTS schema take over.
2026-02-28 00:54:07 -03:00
diegosouzapw
01c1bbfe29 fix: polish split-port implementation for merge
- Add 30s timeout to API bridge proxy requests to prevent resource exhaustion
- Extract healthcheck.mjs script (replaces inline node -e in Dockerfile + compose files)
- Add unit tests for runtime port resolution (14 tests, parsePort + resolveRuntimePorts)
- Fix formatting in declare global block
2026-02-27 16:29:58 -03:00
Steven Rafferty
344e602b26 feat: enhance runtime port management and configuration
- Updated .env.example to include optional production ports for API and dashboard.
- Modified docker-compose files to utilize dynamic port configuration.
- Introduced runtime-env.mjs for centralized port resolution and environment variable management.
- Refactored run-next.mjs and run-standalone.mjs to leverage new runtime port handling.
- Enhanced route.ts and apiBridgeServer.ts to utilize dynamic ports for improved API integration.
- Updated OAuth configuration to reflect changes in port management.
2026-02-26 15:47:31 +00:00
Steven
b941515c5a Merge branch 'main' into refactor-split-ports 2026-02-26 15:17:56 +00:00
Steven Rafferty
fb597c677e feat: improve API configuration and script execution
- Added API_HOST variable to .env.example for enhanced host configuration.
- Updated package.json scripts to utilize a new run-next.mjs script for development and production.
- Introduced run-next.mjs to manage Next.js server execution with dynamic port handling.
- Enhanced route.ts files to normalize API base URLs and improve configuration checks.
- Updated apiBridgeServer.ts to use API_HOST for server initialization.
- Expanded global TypeScript definitions to include API_HOST.
2026-02-26 15:15:35 +00:00
Steven Rafferty
d0138a5037 feat: enhance port configuration and API bridge support
- Updated .env.example to include optional split ports for API and dashboard.
- Modified docker-compose files to dynamically use the configured ports.
- Introduced a new script (run-standalone.mjs) for running the server with environment-specific ports.
- Implemented an API bridge server to handle OpenAI-compatible routes when using split ports.
- Updated README and CLI tool documentation to reflect changes in port usage and configuration.
- Enhanced various components to utilize the new port configuration, ensuring backward compatibility.
2026-02-26 15:11:40 +00:00
diegosouzapw
62069dac98 fix: handle EACCES on restricted home directories (#133)
Wrap fs.mkdirSync(DATA_DIR) in try/catch so OmniRoute doesn't crash
when the user's home directory is not writable (e.g. restricted
environments, npm global install with different user).
Prints a clear warning with DATA_DIR env var recommendation.
2026-02-25 18:41:54 -03:00
diegosouzapw
bc55911d0f fix: allow multiple Codex accounts from same workspace (Team/Business)
Root cause: createProviderConnection() upsert logic for codex deduplicates
by workspaceId only (chatgpt_account_id from JWT). Two Pro Business accounts
from the same Team workspace resolve to the same workspaceId, causing the
second to silently overwrite the first.

Fix: compound uniqueness check using workspaceId + email, so different users
within the same workspace create separate connections. Includes backward-compat
fallback for old connections without email (they'll still be updated).
2026-02-25 15:32:23 -03:00
diegosouzapw
ff965234c9 fix: Claude Code OAuth redirect_uri and scope for remote deployments (#124)
- Use Anthropic's registered redirect_uri (platform.claude.com/oauth/code/callback) instead of dynamic server URL
- Add missing OAuth scopes: user:sessions:claude_code, user:mcp_servers (5 total, matching Claude CLI)
- Make redirect_uri configurable via CLAUDE_CODE_REDIRECT_URI env var
- Override redirectUri in both buildAuthUrl and exchangeToken to use config value
2026-02-24 13:56:18 -03:00
diegosouzapw
168b17adc7 fix(oauth): hardcode desktop OAuth client secrets to fix build-time inlining
Next.js inlines process.env at build time, causing clientSecret defaults to
be baked as empty strings. Desktop/CLI OAuth secrets are not confidential
per Google's documentation.

Fixes: client_secret is missing error on VPS deployment
2026-02-23 20:14:28 -03:00
nyatoru
ac3d251a1a fix(db): clear prepared statements on backup restore 2026-02-24 00:35:29 +07:00
nyatoru
7ed40c2139 fix(db): enforce stricter validation for api key model access 2026-02-24 00:14:50 +07:00
nyatoru
d2bee37e76 feat(api-manager): implement API key management with new endpoints and UI
- Add GET/PATCH endpoints for retrieving and updating API key permissions

- Move API key management from Endpoint page to dedicated API Manager page

- Add allowed_models column to database schema for model-specific access

- Implement caching layer for improved API key validation performance
2026-02-23 23:59:34 +07:00
benzntech
5a2fdacebe feat(memory): optimize RAM usage for low-memory deployments
- Add Node.js heap limit (256MB default) via OMNIROUTE_MEMORY_MB
- Convert LRU caches to byte-based limits (2-4MB)
- Reduce in-memory buffer sizes: 500→200 entries
- Add .env file loading in CLI for global npm installs
- Add PM2 ecosystem.config.js example for deployment
- Document memory tuning env vars in USER_GUIDE.md

Estimated RAM reduction: ~60-70% (from ~512MB+ to ~150-200MB)
2026-02-23 14:16:47 +05:30
Diego Rodrigues de Sa e Souza
90d2dcac97 Merge pull request #115 from benzntech/feat/enhance-kilocode-provider
feat(kilocode): add custom models endpoint and expanded model list
2026-02-23 03:44:32 -03:00
benzntech
5668e16fbf feat(kilocode): add custom models endpoint and expanded model list
- Add modelsUrl field to RegistryEntry interface for custom models endpoints
- Configure kilocode provider with dedicated models URL (https://api.kilo.ai/api/openrouter/models)
- Expand kilocode model list from 8 to 26 models including free options:
  - openrouter/free (Free Models Router)
  - stepfun/step-3.5-flash:free
  - arcee-ai/trinity-large-preview:free
  - Additional Qwen, DeepSeek, Llama, Mistral, Grok, and Kimi models
- Update validateOpenAILikeProvider to accept custom modelsUrl parameter
- Fix models URL derivation for base URLs ending with /chat/completions
- Add kilocode config to PROVIDER_MODELS_CONFIG
2026-02-23 10:31:56 +05:30
nyatoru
f0a0c97b5e feat(tokenHealthCheck): add request coalescing to shouldHideLogs 2026-02-23 06:36:39 +07:00
nyatoru
4b137d8e72 feat(settings): add toggle to hide health check logs with caching 2026-02-23 06:21:53 +07:00
nyatoru
b26cc2a82e feat(codex): enhance base64 decoding for UTF-8 compatibility in JWT parsing 2026-02-23 01:32:48 +07:00
nyatoru
0610909116 feat(codex): add workspace binding via chatgpt-account-id header 2026-02-23 01:11:53 +07:00
nyatoru
3b70e9f786 chore(qwen): remove debug console log from mapTokens 2026-02-22 20:23:37 +07:00
diegosouzapw
28c7e0d62f Fix OAuth client_secret issues (#103) & Codex Business quotas (#101) 2026-02-21 18:24:56 -03:00
diegosouzapw
03965bf768 fix(db): remove OAuth fallback overwrite when email is missing to natively support multiple accounts 2026-02-21 13:04:06 -03:00
diegosouzapw
f0513683e5 fix(qwen): extract email from id_token to allow multiple accounts 2026-02-21 12:22:56 -03:00
diegosouzapw
340dcf9515 feat(core): api key protection, provider blocking, windows fix, ui and docs 2026-02-21 09:05:59 -03:00
Adarsh
1bd5d552c1 fix: extract email from id_token for Codex OAuth to allow multiple accounts (#97)
- Parse JWT id_token to extract email in mapTokens function
- Allows database to distinguish between different Codex accounts
- Fixes issue where adding 3rd+ Codex account would update existing connection instead of creating new one
2026-02-21 07:00:37 -03:00
diegosouzapw
1e332babd6 feat(logs): add Logs Dashboard with real-time Console Viewer
- Consolidated 4-tab Logs page: Request Logs, Proxy Logs, Audit Logs, Console
- Terminal-style Console Log Viewer with level filter, search, auto-scroll
- Console interceptor captures all console.log/warn/error to JSON log file
- Integrated in Next.js instrumentation.ts for both dev and prod
- Log rotation by size + retention-based cleanup
- Fixed pino logger file transport (pino/file targets only)
- Moved initAuditLog() to instrumentation.ts for proper initialization
- Bumped version to 1.0.3
- Updated CHANGELOG, all 8 README translations, and .env.example
2026-02-19 04:38:04 -03:00
diegosouzapw
5a645973eb fix(ui): correct Quick Start API key link to /dashboard/endpoint
- HomePageClient.tsx: 'Settings → API Keys' → 'Endpoint → Registered Keys'
- docs/page.tsx: same fix in Quick Start step 2
- Also includes user's manual fixes: bodySizeGuard, container imports, migrationRunner ESM compat
2026-02-18 16:40:33 -03:00