fix: separate @spaces.GPU from @app .api for ZeroGPU detection

app.py

@@ -62,22 +62,18 @@ async def health():
 
 
 # ── Core inference API ────────────────────────────────────────────────────────
-@app.api(name="analyze_defect")
-@spaces.GPU                          # GPU allocated only for this function's duration
-def analyze_defect(
-    image_path: dict,               # FileData from @gradio/client handle_file()
-    language: str = "en",
-) -> dict:
-    """
-    Primary inference endpoint.
+# ── Core inference API ────────────────────────────────────────────────────────
+@spaces.GPU
+def _gpu_inference(image: Image.Image, language: str) -> dict:
+    """Standalone GPU function — must be at module level for ZeroGPU detection."""
+    session = trace_logger.start_trace()
+    report  = run_gharscan_pipeline(image, language=language, trace_session=session)
+    trace_logger.save_trace(session)
+    return report
 
-    Accepts: image file + language preference
-    Returns: full JSON defect report
 
-    ZeroGPU note: GPU is requested here and released at function return.
-    Cold-start (~30s first call) is expected; subsequent calls are fast.
-    """
-    # ── Load image ────────────────────────────────────────────────────────────
+@app.api(name="analyze_defect")
+def analyze_defect(image_path: dict, language: str = "en") -> dict:
     try:
         img_path = image_path.get("path") or image_path.get("url")
         if img_path is None:
@@ -86,13 +82,8 @@ def analyze_defect(
     except Exception as e:
         return _error_response(f"Could not read image: {e}")
 
-    # ── Run 3-step pipeline ───────────────────────────────────────────────────
     try:
-        session = trace_logger.start_trace()
-        report  = run_gharscan_pipeline(image, language=language, trace_session=session)
-        trace_logger.save_trace(session)
-        return report
-
+        return _gpu_inference(image, language)
     except Exception as e:
         return _error_response(f"Inference failed: {e}")