litellm call id's in responses when client true

litellm/tests/test_completion.py

@@ -54,6 +54,26 @@ def test_completion_claude():
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
 
+def test_completion_with_litellm_call_id():
+    try:
+        litellm.use_client = False
+        response = completion(
+            model="gpt-3.5-turbo", messages=messages)
+        print(response)
+        if 'litellm_call_id' in response:
+            pytest.fail(f"Error occurred: litellm_call_id in response objects")
+        
+        litellm.use_client = True
+        response2 = completion(
+            model="gpt-3.5-turbo", messages=messages)
+        
+        if 'litellm_call_id' not in response2:
+            pytest.fail(f"Error occurred: litellm_call_id not in response object when use_client = True")
+        # Add any assertions here to check the response
+        print(response2)
+    except Exception as e:
+        pytest.fail(f"Error occurred: {e}")
+
 
 def test_completion_claude_stream():
     try:

litellm/utils.py

@@ -543,6 +543,11 @@ def client(original_function):
             # [OPTIONAL] ADD TO CACHE
             if litellm.caching or litellm.caching_with_models or litellm.cache != None: # user init a cache object
                 litellm.cache.add_cache(result, *args, **kwargs)
+            
+            # [OPTIONAL] Return LiteLLM call_id
+            if litellm.use_client == True:
+                result['litellm_call_id'] = litellm_call_id
+
             # LOG SUCCESS
             my_thread = threading.Thread(
                 target=handle_success, args=(args, kwargs, result, start_time, end_time)