Add curl command generation on embedding timeout

Co-authored-by: Mte90 <403283+Mte90@users.noreply.github.com>

Author: Copilot

ai/openai.py

@@ -136,6 +136,34 @@ def __init__(self,
             self.session.headers.update({"Authorization": f"Bearer {self.api_key}"})
         self.session.headers.update({"Content-Type": "application/json"})
 
+    def _generate_curl_command(self, url: str, headers: Dict[str, str], payload: Dict[str, Any]) -> str:
+        """
+        Generate a curl command for debugging purposes.
+        Masks the API key for security.
+        """
+        # Start with basic curl command
+        curl_parts = ["curl", "-X", "POST", f"'{url}'"]
+        
+        # Add headers
+        for key, value in headers.items():
+            if key.lower() == "authorization" and value:
+                # Mask the API key for security
+                if value.startswith("Bearer "):
+                    masked_value = f"Bearer <API_KEY_MASKED>"
+                else:
+                    masked_value = "<API_KEY_MASKED>"
+                curl_parts.append(f"-H '{key}: {masked_value}'")
+            else:
+                curl_parts.append(f"-H '{key}: {value}'")
+        
+        # Add data payload
+        payload_json = json.dumps(payload)
+        # Escape single quotes in the JSON for shell compatibility
+        payload_json_escaped = payload_json.replace("'", "'\\''")
+        curl_parts.append(f"-d '{payload_json_escaped}'")
+        
+        return " \\\n  ".join(curl_parts)
+
     def _log_request_start(self, request_id: str, file_path: str, chunk_index: int, chunk_len: int):
         _embedding_logger.debug(
             "Embedding request START",
@@ -244,7 +272,26 @@ def embed_text(self, text: str, file_path: str = "<unknown>", chunk_index: int =
             except requests.Timeout as e:
                 elapsed = time.perf_counter() - start
                 err_msg = f"Timeout after {elapsed:.2f}s: {e}"
-                _embedding_logger.error("Embedding API Timeout", extra={"request_id": request_id, "error": str(e)})
+                
+                # Generate and print curl command for debugging
+                curl_command = self._generate_curl_command(self.api_url, dict(self.session.headers), payload)
+                _embedding_logger.error(
+                    "Embedding API Timeout",
+                    extra={
+                        "request_id": request_id,
+                        "error": str(e),
+                        "elapsed_s": elapsed,
+                        "curl_command": curl_command
+                    }
+                )
+                # Also print to console for easy debugging
+                print(f"\n{'='*80}")
+                print(f"Embedding request timed out after {elapsed:.2f}s")
+                print(f"Request ID: {request_id}")
+                print(f"File: {file_path}, Chunk: {chunk_index}")
+                print(f"\nDebug with this curl command:")
+                print(curl_command)
+                print(f"{'='*80}\n")
             except requests.RequestException as e:
                 elapsed = time.perf_counter() - start
                 err_msg = f"RequestException after {elapsed:.2f}s: {e}\n{traceback.format_exc()}"