Fix Azure embeddings JSON parsing to prevent connection leaks and ensure proper router cooldown (#19167)

litellm/llms/azure/azure.py

@@ -664,8 +664,29 @@ class AzureChatCompletion(BaseAzureLLM, BaseLLM):
                 **data, timeout=timeout
             )
             headers = dict(raw_response.headers)
-            response = raw_response.parse()
+            
+            # Convert json.JSONDecodeError to AzureOpenAIError for two critical reasons:
+            #
+            # 1. ROUTER BEHAVIOR: The router relies on exception.status_code to determine cooldown logic:
+            #    - JSONDecodeError has no status_code → router skips cooldown evaluation
+            #    - AzureOpenAIError has status_code → router properly evaluates for cooldown
+            #
+            # 2. CONNECTION CLEANUP: When response.parse() throws JSONDecodeError, the response
+            #    body may not be fully consumed, preventing httpx from properly returning the
+            #    connection to the pool. By catching the exception and accessing raw_response.status_code,
+            #    we trigger httpx's internal cleanup logic. Without this:
+            #    - parse() fails → JSONDecodeError bubbles up → httpx never knows response was acknowledged → connection leak
+            #    This completely eliminates "Unclosed connection" warnings during high load.
+            try:
+                response = raw_response.parse()
+            except json.JSONDecodeError as json_error:
+                raise AzureOpenAIError(
+                    status_code=raw_response.status_code or 500,
+                    message=f"Failed to parse raw Azure embedding response: {str(json_error)}"
+                ) from json_error
+            
             stringified_response = response.model_dump()
+
             ## LOGGING
             logging_obj.post_call(
                 input=input,