BerriAI/litellm · error · HTTPException

Redis cache not configured.

Error message

Redis cache not configured.

What it means

Polling guard on response deletion: the response_id identifies a polling response, but the proxy has no redis_usage_cache configured. Deleting a polled async response requires removing its cached state, so the operation is refused with a 500 configuration error.

Source

Thrown at litellm/proxy/response_api_endpoints/endpoints.py:820

        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 deletion
        if not redis_usage_cache:
            raise HTTPException(status_code=500, detail="Redis cache not configured.")

        polling_handler: Final = ResponsePollingHandler(redis_cache=redis_usage_cache)

        # Get state to verify access
        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")

        # Delete from cache
        success: Final = await polling_handler.delete_polling(response_id)

        if success:
            return DeleteResponseResult(id=response_id, object="response", deleted=True)
        else:
            raise HTTPException(status_code=500, detail="Failed to delete polling response")

    # Normal provider response flow

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Configure Redis in the proxy config; this endpoint requires the Redis cache backend.

When it happens

Trigger: Thrown at litellm/proxy/response_api_endpoints/endpoints.py:820 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/c10b65db9aa82861. Report an issue: GitHub.