Add detailed error logging to debug model loading

- Print full traceback when model loading fails
- Show error type and message
- This will help us see EXACTLY why it's falling back to DEMO MODE

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

app.py

@@ -32,17 +32,21 @@ from backend.utils.image_processing import (
 @st.cache_resource
 def load_model():
     try:
+        print("[*] Attempting to import TransformersDepthEstimator...")
         from backend.utils.transformers_depth import TransformersDepthEstimator
-        print("[*] Loading REAL AI Depth-Anything V2 BASE model...")
+        print("[*] Import successful! Loading REAL AI Depth-Anything V2 BASE model...")
         print("[*] This will download ~372MB on first run (one-time download)")
         depth_estimator = TransformersDepthEstimator(model_size="base")
         print("[+] REAL AI MODE ACTIVE - BASE MODEL!")
         print("[+] Quality: SUPERB (best available)")
         return depth_estimator, True, "BASE (372MB)"
     except Exception as e:
-        print(f"[!] Could not load AI models: {e}")
+        print(f"[!] FULL ERROR TRACEBACK:")
+        import traceback
+        traceback.print_exc()
+        print(f"[!] Error type: {type(e).__name__}")
+        print(f"[!] Error message: {str(e)}")
         print("[*] Falling back to DEMO MODE")
-        from backend.utils.demo_depth import generate_smart_depth
         return None, False, "Demo Mode"
 
 depth_estimator, USE_REAL_AI, MODEL_SIZE = load_model()