BerriAI/litellm · error · HTTPException

Redis cache not configured. Polling requires Redis.

Error message

Redis cache not configured. Polling requires Redis.

What it means

Polling guard on the response retrieval endpoint: the response_id is a polling ID, but redis_usage_cache is None on the proxy server — asynchronous response polling stores state in Redis, so without Redis configured the polling feature cannot work; surfaced as a 500 configuration error.

Source

Thrown at litellm/proxy/response_api_endpoints/endpoints.py:712

        llm_router,
        proxy_config,
        proxy_logging_obj,
        redis_usage_cache,
        select_data_generator,
        user_api_base,
        user_max_tokens,
        user_model,
        user_request_timeout,
        user_temperature,
        version,
    )
    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

View on GitHub (pinned to 77b7c6c40c)

Solutions

  1. Configure Redis (redis_host/redis_port/redis_password or REDIS_URL) in the proxy config to enable response polling.
Defensive patterns

Strategy: validation

When it happens

Trigger: Thrown at litellm/proxy/response_api_endpoints/endpoints.py:712 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/e6b54d9746e7e076. Report an issue: GitHub.