assistant: Stream tool uses as structured data (#17322)

This PR adjusts the approach we use to encoding tool uses in the
completion response to use a structured format rather than simply
injecting it into the response stream as text.

In #17170 we would encode the tool uses as XML and insert them as text.
This would require then re-parsing the tool uses out of the buffer in
order to use them.

The approach taken in this PR is to make `stream_completion` return a
stream of `LanguageModelCompletionEvent`s. Each of these events can be
either text, or a tool use.

A new `stream_completion_text` method has been added to `LanguageModel`
for scenarios where we only care about textual content (currently,
everywhere that isn't the Assistant context editor).

Release Notes:

- N/A

crates/assistant/src/inline_assistant.rs

@@ -2344,7 +2344,7 @@ impl Codegen {
                 self.build_request(user_prompt, assistant_panel_context, edit_range.clone(), cx)?;
 
             let chunks =
-                cx.spawn(|_, cx| async move { model.stream_completion(request, &cx).await });
+                cx.spawn(|_, cx| async move { model.stream_completion_text(request, &cx).await });
             async move { Ok(chunks.await?.boxed()) }.boxed_local()
         };
         self.handle_stream(telemetry_id, edit_range, chunks, cx);