Implement repository pattern and chat service orchestration
Repositories (Data Access Layer):
- BaseRepository: Generic CRUD operations with async support
- UserRepository: User management, Azure AD integration
- ConversationRepository: Conversation CRUD, archiving, search
- MessageRepository: Message creation, retrieval, search
- TokenUsageRepository: Usage tracking, cost calculation, analytics
Chat Service (Business Logic):
- Complete conversation lifecycle management
- Message sending with OpenAI integration
- Multi-turn conversation support via previous_response_id
- Automatic token usage tracking
- Cost calculation per message
- Permission checks for user access
- Conversation archiving and deletion
- Token usage analytics and reporting
Key Features:
- Repository pattern for clean data access
- Async/await throughout for performance
- Proper error handling and logging
- Permission verification for user actions
- Citation validation from OpenAI responses
- Automatic cost tracking per message
- File search results stored in message metadata
Integration Points:
- OpenAIService for AI responses
- All SQLAlchemy models
- Token cost calculation from settings
- Multi-turn conversations via last_response_id
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
29e6c2e442