diff --git a/litellm/litellm_core_utils/streaming_handler.py b/litellm/litellm_core_utils/streaming_handler.py index 6b2da11a197..41fb06c6608 100644 --- a/litellm/litellm_core_utils/streaming_handler.py +++ b/litellm/litellm_core_utils/streaming_handler.py @@ -2473,18 +2473,18 @@ class CustomStreamWrapper: self._earlier_rounds_spend = earlier def partial_response(self) -> "ModelResponse | TextCompletionResponse | None": - if not self.chunks: - return None - partial: Final = litellm.stream_chunk_builder( - chunks=self.chunks, - messages=self.messages if isinstance(self.messages, list) else None, - logging_obj=self.logging_obj, - count_prompt_tokens=self.count_prompt_tokens, + partial: Final = ( + litellm.stream_chunk_builder( + chunks=self.chunks, + messages=self.messages if isinstance(self.messages, list) else None, + logging_obj=self.logging_obj, + count_prompt_tokens=self.count_prompt_tokens, + ) + if self.chunks + else None ) - if partial is None: - return None usage: Final[object] = getattr(partial, "usage", None) - if not isinstance(usage, Usage): + if partial is None or not isinstance(usage, Usage): return None if self.model: partial.model = self.model