- Fix model_pricing table references (model_id -> model, display_name -> model)
- Fix price columns (output_price_per_1k -> output_price_per_million)
- Add price conversion (per_million / 1000 = per_1k) in all API responses
- Add whereNotNull('model') filters to exclude invalid entries
- Add getModelDisplayName() helper method to all controllers
- Fix AccountController to use gateway_users budget fields directly
- Remove Budget model dependencies from AccountController
- Add custom Scramble server URL configuration for API docs
- Create ScrambleServiceProvider to set correct /api prefix
- Add migration to rename user_id to gateway_user_id in llm_requests
- Add custom ApiGuard for gateway_users authentication
- Update all API controllers: AccountController, ModelController, PricingController, ProviderController
All API endpoints now working correctly:
- GET /api/account
- GET /api/models
- GET /api/pricing
- GET /api/providers/{provider}
Core Features:
- Multi-provider support (OpenAI, Anthropic, DeepSeek, Gemini, Mistral)
- Provider service architecture with abstract base class
- Dynamic model discovery from provider APIs
- Encrypted per-user provider credentials storage
Admin Interface:
- Complete admin panel with Livewire components
- User management with CRUD operations
- API key management with testing capabilities
- Budget system with limits and reset schedules
- Usage logs with filtering and CSV export
- Model pricing management with cost calculator
- Dashboard with Chart.js visualizations
Database Schema:
- MariaDB migrations for all tables
- User provider credentials (encrypted)
- LLM request logging
- Budget tracking and rate limiting
- Model pricing configuration
API Implementation:
- OpenAI-compatible endpoints
- Budget checking middleware
- Rate limit enforcement
- Request logging jobs
- Cost calculation service
Testing:
- Unit tests for all provider services
- Provider factory tests
- Cost calculator tests
Documentation:
- Admin user seeder
- Model pricing seeder
- Configuration files
