auto_rl example uses

When trying to run the auto_rl example here the calls to acompletion causes OpenRouter errors:

        response = await acompletion(
            model=INPUT_GENERATION_MODEL,
            messages=messages,
            response_format=TrainingDataset,
            temperature=1.0,
        )

This returns:

[/usr/local/lib/python3.12/dist-packages/litellm/llms/custom_httpx/llm_http_handler.py](https://localhost:8080/#) in _handle_error(self, e, provider_config)
   2402 
-> 2403         raise provider_config.get_error_class(
   2404             error_message=error_text,

OpenRouterException: {"error":{"message":"Provider returned error","code":400,"metadata":{"raw":"{\"code\":400, \"reason\":\"INVALID_REQUEST_BODY\", \"message\":\"model features structured outputs not support\", \"metadata\":{}}","provider_name":"Novita","is_byok":false}},"user_id":"user_xxx"}

I suspect this might be a litellm issue however it seems as though it's fixed there so I'm unsure what's happening. So far I haven't been able to run any of the examples on colab, it may make sense to put some instructions that lead to a happy path with the examples so that folks can get started successfully.

Start by opening and running examples/auto_rl.ipynb in the linked Colab, then inspect the acompletion call, LiteLLM version, and OpenRouter model configuration. Done means the example follows a documented happy path and clearly records any required provider or model setup.