- 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)
- Skip tools with defer_loading=true when assigning cache_control
(Anthropic API rejects the combination with 400)
- Delete stale schemas.js that shadowed the .ts source, causing
missing cloudSyncActionSchema export
Fixes#215
- 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
- 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
- Added mcpEnabled/a2aEnabled boolean fields to updateSettingsSchema
- Rewrote ServiceToggle as clickable on/off switch with status indicator
- Toggle persists state via PATCH /api/settings
- Both services default to disabled (OFF)
- Renamed sidebar 'Endpoint' to 'Endpoints', removed standalone MCP/A2A entries
- Created tabbed layout with SegmentedControl: Endpoint Proxy | MCP | A2A | API Endpoints
- Added inline ServiceToggle (online/offline status) for MCP and A2A tabs
- Created ApiEndpointsTab placeholder with Coming Soon badge
- Updated i18n in en.json and pt.json with new endpoints namespace
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
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.
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.
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.
Code Quality Improvements:
- Export COLOR_THEMES from themeStore.ts for reuse (DRY)
- Add coral preset to color list (fixes default inconsistency)
- Sync local customThemeColor state reactively via Zustand subscribe
- Add hex color validation with visual feedback (red border + disabled button)
- Remove dead /themes route from Header.tsx (page doesn't exist)
- Add CSS color-mix() fallback for older browsers
- Add themeCoral i18n key to all 30 locale files
- 24 unit tests for parseModelFromRegistry, getAllModelsFromRegistry, buildAuthHeaders
- Integration tests for video/music registries
- Media Playground dashboard page (Image/Video/Music tabs with model selector)
- Sidebar navigation entry for Media page
- i18n translations (EN + PT-BR)
- Fix Record<string, any> → Record<string, unknown> in registryUtils.ts
- Update /resolve-issues workflow to wait for user validation before commit/release
- Add collapsible '16 Real Pain Points' section to all 30 READMEs
- Fix 5 files bypassing dataPaths.ts with hardcoded os.homedir() (closes#156)
- Add per-provider User-Agent env var overrides in base executor (closes#155)
- Sync .env and .env.example with 9 provider UA defaults
- Update CHANGELOG.md for v1.7.0
- 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>
Adds a Copilot configuration generator to the CLI Tools dashboard page.
Users can select models and generate the chatLanguageModels.json config
block for VS Code GitHub Copilot with the Azure vendor pattern.
Features:
- Bulk model selection from /v1/models (includes combos, custom, aliased)
- Search/filter for large model lists
- Configurable maxInputTokens, maxOutputTokens, toolCalling, vision
- One-click copy to clipboard
- Persistent model selection via localStorage
- Version compatibility warning (VS Code >= 1.109, Copilot >= v0.37)
Feedback from @alpgul applied:
- Use /v1/models instead of /api/models/alias (includes combo definitions)
- Use window.location.origin for URL (no port duplication in Docker)
Also: added electron/dist-electron/ to .gitignore (build artifact)
The 'no password' auth bypass check was meant for fresh installs only,
but it also fired after onboarding was complete if the password row
was missing from the database (e.g. after DB migration in v1.6.3).
Fix: Added !settings.setupComplete guard so the bypass only applies
before onboarding is done. Once setupComplete=true, auth is always
required regardless of whether the password key exists in the DB.
Files changed:
- src/proxy.ts (dashboard middleware)
- src/shared/utils/apiAuth.ts (isAuthRequired)
- Add electron/ directory with main process, preload script, and types
- Add system tray integration and window management
- Add IPC communication for app info, external links, server controls
- Add useElectron React hooks for Next.js integration
- Add build scripts for Windows, macOS, and Linux
- Add development scripts for running Electron with Next.js
Ref: #149
Adds split-port runtime support: API and dashboard can run on separate ports.
- PORT remains canonical/base
- API_PORT optionally overrides API listener
- DASHBOARD_PORT optionally overrides dashboard listener
- API bridge server proxies OpenAI-compatible routes with 30s timeout
- Centralized port resolution in src/lib/runtime/ports.ts
- Unit tests for runtime port resolution (14 tests)
- Healthcheck extracted into scripts/healthcheck.mjs
- 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.
The Zod updateSettingsSchema was missing fallbackStrategy,
wildcardAliases, and stickyRoundRobinLimit fields. Since
.passthrough() was removed in a previous cleanup, these unknown
keys were silently stripped during validation, so the PATCH
/api/settings call never actually persisted these values.
- Added ApiKeyMetadata interface to replace 'any' types in apiKeyPolicy.ts
- Added error logging in catch blocks for getApiKeyMetadata() and checkBudget()
- Fixed claude-sonnet-4-6-thinking → claude-sonnet-4-6 mismatch in usage.ts importantModels
Follow-up fixes for merged PRs #131 and #128
isModelAllowedForKey() existed in src/lib/db/apiKeys.ts but was never
called anywhere. API keys with allowedModels restrictions could access
any model through any endpoint.
Changes:
- Add shared enforceApiKeyPolicy() middleware (model restriction + budget)
- Wire it into chat handler (replacing inline budget-only check)
- Wire it into all /v1/* endpoints: embeddings, images/generations,
audio/speech, audio/transcriptions, moderations, rerank
- Wire it into provider-specific endpoints: /v1/providers/[provider]/embeddings,
/v1/providers/[provider]/images/generations
The middleware checks:
1. Model restriction — if key has allowedModels, verify the model is permitted
2. Budget limit — if key has budget configured, verify it hasn't been exceeded
Fixes#130
- Combo cards now resolve UUID-based provider IDs to user-defined names using providerNodes
- API key names shown in full instead of masked (Op***w → OpenAI-Prod-Key); key IDs remain masked
- Logs/Analytics: OAI-compatible and ANT-compatible providers now show user-defined names from providerNodes instead of generic OAI-COMPAT labels
- All views (combo cards, combos form modal, logs table, quick filters, dropdowns, analytics) updated consistently
When accessing OmniRoute via LAN IP (192.168.x), the OAuth popup
callback can't resolve localhost back to the VPS. Now shows manual
paste input with warning banner instead of waiting indefinitely.
- Connection tests now route through configured proxy (key → combo → provider → global → direct)
- Compatible providers show friendly labels (OAI-COMPAT, ANT-COMPAT) in request logger
- 26 new unit tests for error classification, token expiry, and display labels
- Version bump to 1.3.1
