Associate each thread with a model (#29573)

This PR makes it possible to use different LLM models in the agent
panels of two different projects, simultaneously. It also properly
restores a thread's original model when restoring it from the history,
rather than having it use the default model. As before, newly-created
threads will use the current default model.

Release Notes:

- Enabled different project windows to use different models in the agent
panel
- Enhanced the agent panel so that when revisiting old threads, their
original model will be used.

---------

Co-authored-by: Richard Feldman <oss@rtfeldman.com>

crates/agent/src/thread_store.rs

@@ -640,6 +640,14 @@ pub struct SerializedThread {
     pub detailed_summary_state: DetailedSummaryState,
     #[serde(default)]
     pub exceeded_window_error: Option<ExceededWindowError>,
+    #[serde(default)]
+    pub model: Option<SerializedLanguageModel>,
+}
+
+#[derive(Serialize, Deserialize, Debug)]
+pub struct SerializedLanguageModel {
+    pub provider: String,
+    pub model: String,
 }
 
 impl SerializedThread {
@@ -774,6 +782,7 @@ impl LegacySerializedThread {
             request_token_usage: Vec::new(),
             detailed_summary_state: DetailedSummaryState::default(),
             exceeded_window_error: None,
+            model: None,
         }
     }
 }