BerriAI/litellm · error · MidStreamFallbackError

str(mapped_exception)

Error message

str(mapped_exception)

What it means

Router streaming fallback decision point: when a mid-stream exception occurs, the mapped exception's string is raised if the error is judged non-transient (e.g. client errors other than 429); the string form of the mapped exception becomes the surfaced error for the failing stream.

Source

Thrown at litellm/litellm_core_utils/streaming_handler.py:2381

                    status_code: Final[int | str | None] = getattr(response, "status_code", None)
                    if status_code is not None:
                        return int(status_code)
                except Exception:
                    pass
            return None

        mapped_status_code: Final = _normalize_status_code(mapped_exception)
        original_status_code: Final = _normalize_status_code(e)

        # Raise non-retriable client errors directly (skip fallback).
        # Exception: 429 (rate-limit) IS retriable/transient — allow it
        # through so the Router can switch to a different model group.
        if mapped_status_code is not None and 400 <= mapped_status_code < 500 and mapped_status_code != 429:
            raise mapped_exception
        if original_status_code is not None and 400 <= original_status_code < 500 and original_status_code != 429:
            raise mapped_exception

        raise MidStreamFallbackError(
            message=str(mapped_exception),
            model=self.model,
            llm_provider=self.custom_llm_provider or "anthropic",
            original_exception=mapped_exception,
            generated_content=self.response_uptil_now,
            is_pre_first_chunk=not self.sent_first_chunk,
        )

    @staticmethod
    def _strip_sse_data_from_chunk(chunk: str | None) -> str | None:
        """
        Strips the 'data: ' prefix from Server-Sent Events (SSE) chunks.

        Some providers like sagemaker send it as `data:`, need to handle both

        SSE messages are prefixed with 'data: ' which is part of the protocol,
        not the actual content from the LLM. This method removes that prefix
        and returns the actual content.

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Inspect the mapped exception (str(mapped_exception)) with verbose logging for the root cause.
2. Fix the underlying request or configuration issue that produced the exception.

When it happens

Trigger: Thrown at litellm/litellm_core_utils/streaming_handler.py:2381 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/b0b090ac01d49c03. Report an issue: GitHub.