chore(forensics): finalize verification and trace validation\n\n- Fix unreachable background reasoning in inference.py\n- Enable enabling GPT reasoning by default in frontend\n- Verify correct data mapping for 15 naval fields\n- Clean up legacy code paths and ensure backward compatibility

frontend/index.html

@@ -97,7 +97,7 @@
               <span>Enable Legacy Depth Map (Slow)</span>
             </label>
             <label class="checkbox-row" for="enableGPTToggle" style="margin-top: 4px;">
-              <input type="checkbox" id="enableGPTToggle">
+              <input type="checkbox" id="enableGPTToggle" checked>
               <span style="color: var(--accent-light);">Enable GPT Reasoning</span>
             </label>
             <label class="checkbox-row" for="enableStreamToggle" style="margin-top: 4px;">

inference.py

@@ -758,12 +758,9 @@ def process_first_frame(
                 det["depth_rel"] = None
                 det["depth_valid"] = False
 
-    return processed, detections, depth_map
-
-
     # 2. GPT-based Distance/Direction Estimation (Explicitly enabled)
     if enable_gpt:
-        # We need to save the frame temporarily to pass to GPT (or refactor gpt_distance to take buffer)
+        # We need to save the frame temporarily to pass to GPT (or refactor gpt_reasoning to take buffer)
         # For now, write to temp file
         try:
             with tempfile.NamedTemporaryFile(suffix=".jpg", delete=False) as tmp_img:
@@ -776,7 +773,7 @@ def process_first_frame(
             # GPT returns { "T01": { "distance_m": ..., "direction": ... } }
             # Detections are list of dicts. We assume T01 maps to index 0, T02 to index 1...
             for i, det in enumerate(detections):
-                 # ID format matches what we constructed in gpt_distance.py
+                 # ID format matches what we constructed in gpt_reasoning.py
                  obj_id = f"T{str(i+1).zfill(2)}"
                  if obj_id in gpt_results:
                      info = gpt_results[obj_id]
@@ -791,9 +788,9 @@ def process_first_frame(
                      det["gpt_raw"] = info
                      
         except Exception as e:
-            logging.error(f"GPT Distance estimation failed: {e}")
+            logging.error(f"GPT Threat estimation failed: {e}")
 
-    return processed, detections
+    return processed, detections, depth_map
 
 
 def run_inference(