agent: Preserve thinking blocks between requests (#29055)

Looks like the required backend component of this was deployed.

https://github.com/zed-industries/monorepo/actions/runs/14541199197

Release Notes:

- N/A

---------

Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Agus Zubiaga <hi@aguz.me>
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
Co-authored-by: Nathan Sobo <nathan@zed.dev>

crates/assistant_context_editor/src/context.rs

@@ -2373,7 +2373,7 @@ impl AssistantContext {
                                     LanguageModelCompletionEvent::Stop(reason) => {
                                         stop_reason = reason;
                                     }
-                                    LanguageModelCompletionEvent::Thinking(chunk) => {
+                                    LanguageModelCompletionEvent::Thinking { text: chunk, .. } => {
                                         if thought_process_stack.is_empty() {
                                             let start =
                                                 buffer.anchor_before(message_old_end_offset);