diegosouzapw/OmniRoute v1.4.4

Release v1.4.4

on GitHub

✨ Feature Release — Custom Provider Models in /v1/models

Compatible provider models are now saved to the customModels database, making them visible via /v1/models for all OpenAI-compatible clients.

✨ New Features

• Custom Provider Model Persistence — Compatible provider models (manual or imported) are now saved to the customModels database so they appear in /v1/models listing for clients like Cursor, Cline, Antigravity, and Claude Code (PR #122 by @nyatoru)
• Provider Models API — New /api/provider-models endpoint (GET/POST/DELETE) for managing custom model entries with full authentication
• Unified Model Deletion — New handleDeleteModel removes models from both alias configuration and customModels database
• Provider Node Prefix Resolution — getModelInfo refactored for accurate custom provider model resolution

🔒 Security

• Authentication on Provider Models API — All endpoints require API key or JWT session authentication
• URL Parameter Injection Fix — Applied encodeURIComponent to all user-controlled URL parameters
• Shared Auth Utility — Authentication logic extracted to @/shared/utils/apiAuth.ts

🔧 Improvements

• Toast Notifications — Replaced blocking alert() with non-blocking toast notifications
• Transactional Save — Database save must succeed before alias creation
• Consistent Error Handling — All model operations provide user-facing feedback