From 4271f7352ea0d8cabcf510af658ac2d8ea523a99 Mon Sep 17 00:00:00 2001 From: Swapna Lekkala Date: Thu, 11 Sep 2025 16:10:23 -0700 Subject: [PATCH] minor fix --- .../providers/utils/inference/openai_compat.py | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/llama_stack/providers/utils/inference/openai_compat.py b/llama_stack/providers/utils/inference/openai_compat.py index e5f01d601..b596ba276 100644 --- a/llama_stack/providers/utils/inference/openai_compat.py +++ b/llama_stack/providers/utils/inference/openai_compat.py @@ -1417,10 +1417,9 @@ class OpenAIChatCompletionToLlamaStackMixin: if stream: return OpenAIChatCompletionToLlamaStackMixin._process_stream_response(self, model, outstanding_responses) - response = await OpenAIChatCompletionToLlamaStackMixin._process_non_stream_response( + return await OpenAIChatCompletionToLlamaStackMixin._process_non_stream_response( self, model, outstanding_responses ) - return response async def _process_stream_response( self, @@ -1512,11 +1511,9 @@ class OpenAIChatCompletionToLlamaStackMixin: ) choices.append(choice) - usage = None - if total_tokens > 0: - usage = OpenAIChatCompletionUsage( - prompt_tokens=total_prompt_tokens, completion_tokens=total_completion_tokens, total_tokens=total_tokens - ) + usage = OpenAIChatCompletionUsage( + prompt_tokens=total_prompt_tokens, completion_tokens=total_completion_tokens, total_tokens=total_tokens + ) return OpenAIChatCompletion( id=f"chatcmpl-{uuid.uuid4()}",