test: add more logging

litellm/tests/test_model_max_token_adjust.py

@@ -15,6 +15,7 @@ litellm.drop_params = True
 
 
 def test_completion_sagemaker():
+    litellm.set_verbose = True
     response = completion(
         model="sagemaker/berri-benchmarking-Llama-2-70b-chat-hf-4",
         messages=[{"content": "Hello, how are you?", "role": "user"}],

litellm/utils.py

@@ -2220,6 +2220,7 @@ def client(original_function):
                         pass  # allow call to fail normally
                     elif user_max_tokens + input_tokens > max_output_tokens:
                         user_max_tokens = max_output_tokens - input_tokens
+                    print_verbose(f"user_max_tokens: {user_max_tokens}")
                     kwargs["max_tokens"] = user_max_tokens
                 except Exception as e:
                     print_verbose(f"Error while checking max token limit: {str(e)}")