Integrate Ollama into role detection with fallback to pattern matching

- 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

backend/main.py

@@ -62,7 +62,7 @@ app = FastAPI(
 # Configure CORS
 app.add_middleware(
     CORSMiddleware,
-    allow_origins=["http://localhost:5173", "http://localhost:3000"],
+    allow_origins=["http://localhost:5173", "http://localhost:5174", "http://localhost:3000"],
     allow_credentials=True,
     allow_methods=["*"],
     allow_headers=["*"],
@@ -111,6 +111,8 @@ async def detect_roles(request: RoleDetectionRequest):
     """
     Analyzes text and returns detected speaker roles.
     
+    Uses AI-based detection (Ollama) first, then falls back to pattern matching.
+    
     Supports two pattern types:
     - Colon pattern: "RoleName:" at line start
     - Bracket pattern: "[RoleName]" preceding dialogue
@@ -120,7 +122,7 @@ async def detect_roles(request: RoleDetectionRequest):
     logger.info(f"Role detection requested for text of length {len(request.text)}")
     
     try:
-        roles = role_detector.detect_roles(request.text)
+        roles = await role_detector.detect_roles(request.text)
         logger.info(f"Detected {len(roles)} roles: {[r['label'] for r in roles]}")
         return RolesResponse(roles=roles)
     except Exception as e: