BerriAI/litellm · error · AnthropicError

{e} Received Messages={messages}

Error message

{e}
Received Messages={messages}

What it means

Anthropic request transform error wrapper: while transforming OpenAI messages to Anthropic format (system extraction, tool name rewriting, content mapping) an exception occurred; it is re-raised with the full messages list attached so the offending input can be identified.

Source

Thrown at litellm/llms/anthropic/chat/transformation.py:1871

        if _name_forward_map:
            messages = self._rewrite_tool_names_in_messages(messages, _name_forward_map)
        if _name_reverse_map and isinstance(litellm_params, dict):
            litellm_params[ANTHROPIC_TOOL_NAME_REVERSE_MAP_KEY] = _name_reverse_map

        # Separate system prompt from rest of message
        anthropic_system_message_list: Final = self.translate_system_message(messages=messages)
        # Handling anthropic API Prompt Caching
        if len(anthropic_system_message_list) > 0:
            optional_params["system"] = anthropic_system_message_list
        # Format rest of message according to anthropic guidelines
        try:
            anthropic_messages = anthropic_messages_pt(
                model=model,
                messages=messages,
                llm_provider=self._resolved_provider,
            )
        except Exception as e:
            raise AnthropicError(
                status_code=400,
                message=f"{e}\nReceived Messages={messages}",
            )  # don't use verbose_logger.exception, if exception is raised

        ## Auto-strip advisor blocks from history if advisor tool is absent.
        ## Prevents Anthropic 400: advisor_tool_result in history requires advisor tool.
        _all_tools: Final = optional_params.get("tools") or []
        _has_advisor = any(isinstance(t, dict) and t.get("type") == ANTHROPIC_ADVISOR_TOOL_TYPE for t in _all_tools)
        if not _has_advisor:
            anthropic_messages = strip_advisor_blocks_from_messages(anthropic_messages)

        ## Add code_execution tool if container_upload is in messages
        _tools: Final = (
            cast(
                list[AllAnthropicToolsValues | dict] | None,
                optional_params.get("tools"),
            )
            or []

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Inspect the messages list shown in the error for malformed entries (bad roles, non-string content blocks).
2. Fix the underlying exception '{e}' reported before the message dump.

When it happens

Trigger: Thrown at litellm/llms/anthropic/chat/transformation.py:1871 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/5fee267ebec4befe. Report an issue: GitHub.