Re-enable NV-Reason-CXR for L40S GPU (48GB VRAM)

With L40S, we now have enough VRAM for all 7 tools:
- NV-Reason-CXR: ~7GB (with 4-bit quantization)
- MAIRA-2 Grounding: ~22GB
- CheXagent VQA: ~2-3GB
- Classification + Report Gen: ~2GB
- Total: ~33-34GB out of 48GB (14GB free)

This completes the full MedRAX2 medical AI assistant with:
1. NV-Reason-CXR - Clinical reasoning
2. MAIRA-2 Grounding - Visual phrase grounding
3. CheXagent VQA - Interactive Q&A
4. Classification - Pathology detection
5. Report Generation - Radiology reports
6. DICOM Processor - File handling
7. Web Browsing - Medical information

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

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

app.py

@@ -35,19 +35,18 @@ tools = []
 if device == "cuda":
     # Load GPU-based tools
 
-    # NV-Reason-CXR - Temporarily disabled (uses ~7GB VRAM)
-    # Taking up too much memory alongside MAIRA-2 (15GB), leaving no room for VQA
-    # Priority: VQA is more useful for interactive Q&A
-    # try:
-    #     from medrax.tools import NVReasonCXRTool
-    #     nv_reason_tool = NVReasonCXRTool(
-    #         device=device,
-    #         load_in_4bit=True  # Use quantization to save VRAM
-    #     )
-    #     tools.append(nv_reason_tool)
-    #     print("✓ Loaded NV-Reason-CXR tool")
-    # except Exception as e:
-    #     print(f"✗ Failed to load NV-Reason-CXR tool: {e}")
+    # NV-Reason-CXR - Re-enabled for L40S (48GB VRAM)
+    # With 48GB, we have room for all tools: MAIRA-2 (22GB) + VQA (2GB) + NV-Reason (7GB)
+    try:
+        from medrax.tools import NVReasonCXRTool
+        nv_reason_tool = NVReasonCXRTool(
+            device=device,
+            load_in_4bit=True  # Use quantization to save VRAM (~7GB)
+        )
+        tools.append(nv_reason_tool)
+        print("✓ Loaded NV-Reason-CXR tool")
+    except Exception as e:
+        print(f"✗ Failed to load NV-Reason-CXR tool: {e}")
 
     # MAIRA-2 Grounding - Re-enabled for L40S (48GB VRAM)
     try: