refactor (untested)

process_meeting.py

@@ -38,14 +38,8 @@ Examples:
   # Adjust frame extraction quality (lower = smaller files)
   python process_meeting.py samples/meeting.mkv --run-whisper --embed-images --embed-quality 60 --scene-detection
 
-  # Hybrid approach: OpenCV + OCR (extracts text from frames)
-  python process_meeting.py samples/meeting.mkv --run-whisper --use-hybrid --scene-detection
-
-  # Hybrid + LLM cleanup (best for code formatting)
-  python process_meeting.py samples/meeting.mkv --run-whisper --use-hybrid --hybrid-llm-cleanup --scene-detection
-
   # Iterate on scene threshold (reuse whisper transcript)
-  python process_meeting.py samples/meeting.mkv --embed-images --scene-detection --scene-threshold 5 --skip-cache-frames --skip-cache-analysis
+  python process_meeting.py samples/meeting.mkv --embed-images --scene-detection --scene-threshold 5 --skip-cache-frames
         """
     )
 
@@ -123,45 +117,6 @@ Examples:
         default=15.0
     )
 
-    # Analysis options
-    parser.add_argument(
-        '--ocr-engine',
-        choices=['tesseract', 'easyocr', 'paddleocr'],
-        help='OCR engine to use (default: tesseract)',
-        default='tesseract'
-    )
-    parser.add_argument(
-        '--use-vision',
-        action='store_true',
-        help='Use local vision model (Ollama) instead of OCR for better context understanding'
-    )
-    parser.add_argument(
-        '--use-hybrid',
-        action='store_true',
-        help='Use hybrid approach: OpenCV text detection + OCR (more accurate than vision models)'
-    )
-    parser.add_argument(
-        '--hybrid-llm-cleanup',
-        action='store_true',
-        help='Use LLM to clean up OCR output and preserve code formatting (requires --use-hybrid)'
-    )
-    parser.add_argument(
-        '--hybrid-llm-model',
-        help='LLM model for cleanup (default: llama3.2:3b)',
-        default='llama3.2:3b'
-    )
-    parser.add_argument(
-        '--vision-model',
-        help='Vision model to use with Ollama (default: llava:13b)',
-        default='llava:13b'
-    )
-    parser.add_argument(
-        '--vision-context',
-        choices=['meeting', 'dashboard', 'code', 'console'],
-        help='Context hint for vision analysis (default: meeting)',
-        default='meeting'
-    )
-
     # Processing options
     parser.add_argument(
         '--no-cache',
@@ -171,27 +126,17 @@ Examples:
     parser.add_argument(
         '--skip-cache-frames',
         action='store_true',
-        help='Skip cached frames, re-extract from video (but keep whisper/analysis cache)'
+        help='Skip cached frames, re-extract from video (but keep whisper cache)'
     )
     parser.add_argument(
         '--skip-cache-whisper',
         action='store_true',
-        help='Skip cached whisper transcript, re-run transcription (but keep frames/analysis cache)'
-    )
-    parser.add_argument(
-        '--skip-cache-analysis',
-        action='store_true',
-        help='Skip cached analysis, re-run OCR/vision (but keep frames/whisper cache)'
-    )
-    parser.add_argument(
-        '--no-deduplicate',
-        action='store_true',
-        help='Disable text deduplication'
+        help='Skip cached whisper transcript, re-run transcription (but keep frames cache)'
     )
     parser.add_argument(
         '--extract-only',
         action='store_true',
-        help='Only extract frames and analyze, skip transcript merging'
+        help='Only extract frames + transcript, skip the enhanced-transcript merge'
     )
     parser.add_argument(
         '--format',
@@ -202,7 +147,8 @@ Examples:
     parser.add_argument(
         '--embed-images',
         action='store_true',
-        help='Skip OCR/vision analysis and reference frame files directly (faster, lets LLM analyze images)'
+        help='Reference extracted frames in the transcript for the LLM to read '
+             '(now the default behavior; flag kept for compatibility)'
     )
     parser.add_argument(
         '--embed-quality',