BerriAI/litellm · error · HTTPException

Polling response {response_id} not found or expired

Error message

Polling response {response_id} not found or expired

What it means

Polling lookup on response retrieval: Redis is configured, but ResponsePollingHandler.get_state returned nothing for the polling response_id — the polling entry expired from the cache or never existed; surfaced as 404.

Source

Thrown at litellm/proxy/response_api_endpoints/endpoints.py:723

    )
    from litellm.proxy.response_polling.polling_handler import ResponsePollingHandler

    # Check if this is a polling ID
    if ResponsePollingHandler.is_polling_id(response_id):
        # Handle polling response
        if not redis_usage_cache:
            raise HTTPException(
                status_code=500,
                detail="Redis cache not configured. Polling requires Redis.",
            )

        polling_handler: Final = ResponsePollingHandler(redis_cache=redis_usage_cache)

        # Get current state from cache
        state: Final = await polling_handler.get_state(response_id)

        if not state:
            raise HTTPException(
                status_code=404,
                detail=f"Polling response {response_id} not found or expired",
            )

        # Return the whole state directly (OpenAI Response object format)
        # https://platform.openai.com/docs/api-reference/responses/object
        return state

    # Normal provider response flow
    data: Final = await _read_request_body(request=request)
    data["response_id"] = response_id
    processor: Final = ProxyBaseLLMRequestProcessing(data=data)
    try:
        return await processor.base_process_llm_request(
            request=request,
            fastapi_response=fastapi_response,
            user_api_key_dict=user_api_key_dict,
            route_type="aget_responses",

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Poll before the response TTL expires; re-submit the request if the stored response expired.
2. Verify the response_id matches the one returned at submission.

When it happens

Trigger: Thrown at litellm/proxy/response_api_endpoints/endpoints.py:723 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/ac92016eb3299b4b. Report an issue: GitHub.