Implement agent library support and a demo of streaming generation with progressive rendering

We should build an example which demonstrates generating a UI incrementally using streamed output from the LLM.

I attempted this in https://github.com/google/A2UI/pull/123 but didn't get it fully working

Decisions to make:
- Should we generate the A2UI format directly, or some simplified version of it which is more optimised for streaming?
- What message order works best, especially between data model update and component updates? Perhaps the use case could not use a data model, so it's just component updates?

See https://github.com/google/A2UI/issues/470 for a request relating to this.

Review the linked pull request #123 to see the previous attempt. Examine the A2UI format and the agent library to understand the streaming mechanism. The demo likely involves modifying or creating a component in the examples directory that uses an LLM to stream updates. Determine the message order for data model vs. component updates by experimenting with the existing codebase.

Rédigé par le modèle d'indexation à partir du texte de l'issue.