0.1.0

• Refactor the code to use LangGraph instead of LangChain LCEL
  (except for RAG functionality, see the get_history_aware_retriever method).
• Store all messages in the Thread model, including tool calls and their outputs.
• Allow separation of threads per assistant: assistant_id in the Thread model.
• New updateThread function from useThreadList hook.
• Improved examples:
  • Add markdown rendering to HTMX example.
  • Better Movie Recommendation example.
  • Better Tour Guide example.