fix(utils.py): move to using litellm.modify_params to enable max output token trimming fix

litellm/__init__.py

@@ -36,6 +36,7 @@ token: Optional[str] = (
 telemetry = True
 max_tokens = 256  # OpenAI Defaults
 drop_params = False
+modify_params = False
 retry = True
 api_key: Optional[str] = None
 openai_key: Optional[str] = None

litellm/utils.py

@@ -2589,7 +2589,7 @@ def client(original_function):
             if (
                 kwargs.get("max_tokens", None) is not None
                 and model is not None
-                and litellm.drop_params
+                and litellm.modify_params
                 == True  # user is okay with params being modified
                 and (
                     call_type == CallTypes.acompletion.value