Make `LLMUserAggregator` push the `LLMSetToolsFrame`s, in case a speech-to-speech service that needs to handle the frame itself—like `OpenAIRealtimeLLMService`—is downstream. As far as I can tell, pushing `LLMSetToolsFrame` should otherwise have no unwanted side effects.
Push `TranscriptionFrame`s upstream, to be handled by the user context aggregator. This will require at least a couple of other changes:
- Updating examples to put transcript processors upstream from `OpenAIRealtimeLLMService`
- Maybe figuring out a way to preserve backward compatibility with existing pipelines that put transcript processors downstream from `OpenAIRealtimeLLMService`
- Updating `OpenAIRealtimeLLMService` to ignore new received context frames, since the upstream user context aggregator will generate those after each newly-added user message; hopefully nobody was reliant on the old behavior of resetting the conversation upon receiving a new context!
