Is there any way from the llm_node hook to get which provider and model was used from within the configured FallbackAdapter? I want to set up some custom logging and I would like to know what was the model that generated the response, but I did not find any way to do that.

self.session.llm.provider

returns

livekit

and the model is

FallbackAdapter

You will get logs generated by the fallback adapter, https://github.com/livekit/agents/blob/main/livekit-agents/livekit/agents/llm/fallback_adapter.py, but the provider / model are not available in the llm_node

That's a pity, I think this is a valid use case, so we can log externally what happened!