BerriAI/litellm · error · ValueError

responses_api_provider_config is required to process live st

Error message

responses_api_provider_config is required to process live streaming chunks

What it means

Guard in the live responses streaming chunk processor: responses_api_provider_config is None, so provider-specific chunk transformation cannot run; the streaming path was entered without a resolved provider config.

Source

Thrown at litellm/responses/streaming_iterator.py:236

        # ``_strip_sse_data_from_chunk`` on it — doing so would incorrectly mangle
        # payloads whose actual JSON value happens to start with ``data:``.

        # Handle "[DONE]" marker
        if chunk == STREAM_SSE_DONE_STRING:
            self.finished = True
            return None

        if self.logging_obj.completion_start_time is None:
            self.logging_obj._update_completion_start_time(completion_start_time=datetime.now())

        try:
            # Parse the JSON chunk
            parsed_chunk: Final = json.loads(chunk)

            # Format as ResponsesAPIStreamingResponse
            if isinstance(parsed_chunk, dict):
                if self.responses_api_provider_config is None:
                    raise ValueError("responses_api_provider_config is required to process live streaming chunks")
                openai_responses_api_chunk: Final = self.responses_api_provider_config.transform_streaming_response(
                    model=self.model,
                    parsed_chunk=parsed_chunk,
                    logging_obj=self.logging_obj,
                )

                # Only when the SSE JSON carries a response body (delta events do not).
                # Using getattr(..., "response") alone is unsafe with Mocks: they synthesize a
                # truthy child Mock for any attribute, which breaks tests and is wrong on stream.
                if "response" in parsed_chunk:
                    response_object: Final[ResponsesAPIResponse | None] = getattr(
                        openai_responses_api_chunk, "response", None
                    )
                    if response_object is not None:
                        response: Final = ResponsesAPIRequestUtils._update_responses_api_response_id_with_model_id(
                            responses_api_response=response_object,
                            litellm_metadata=self.litellm_metadata,
                            custom_llm_provider=self.custom_llm_provider,

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Provide responses_api_provider_config when processing live streaming chunks.

When it happens

Trigger: Thrown at litellm/responses/streaming_iterator.py:236 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/a983180a12400e8b. Report an issue: GitHub.