- Updated RoleDetector to use OllamaService for AI-based speaker detection - Implemented _detect_with_ollama() method with availability check - Added fallback logic: tries Ollama first, then pattern matching - Implemented role merging and deduplication across both methods - Handles Ollama unavailable gracefully with logging - Logs detection method used (AI vs pattern) - Updated main.py endpoint to await async detect_roles - Added comprehensive integration tests Requirements: 14.1, 14.4, 14.5
5.2 KiB
5.2 KiB