Add on_request_start() / on_request_end() hooks to Chat

Summary

ellmer recently added on_request_start() / on_request_end() hooks on Chat (tidyverse/ellmer#1052). These fire around each model request within the tool-calling loop (not just around individual tool calls), letting callers inspect or rewrite the conversation between tool rounds within a single chat()/chat_async() call — e.g. to compact turns as the context window fills up.

chatlas currently only exposes tool-level callbacks: Chat.on_tool_request() and Chat.on_tool_result() (see chatlas/_chat.py). There's no equivalent hook that fires before/after each model request in the tool loop.

Proposed behavior (mirroring ellmer)

• on_request_start(callback): callback receives the list of turns about to be sent, fired at the top of each tool-loop iteration (before the request is dispatched). Return value (if any) could allow rewriting the turns, mirroring ellmer's design.
• on_request_end(callback): callback receives the resulting turn after each model request completes.
• Should fire correctly in both sync (chat()) and async (chat_async()) paths, and work whether or not a tool loop actually runs.

References

• ellmer PR: tidyverse/ellmer#1052
• chatlas tool-level callbacks for comparison: chatlas/_chat.py (on_tool_request, on_tool_result, _on_tool_request_callbacks, _on_tool_result_callbacks)

Start in chatlas/_chat.py by reading on_tool_request(), on_tool_result(), their callback storage, and the chat() and chat_async() paths. Compare the proposed lifecycle with tidyverse/ellmer#1052, then define the start and end callback behavior for each model request, including tool-loop and no-tool cases. Done means both paths expose and invoke the hooks consistently.