agent: Overwrite files more cautiously (#30649)

1. The `edit_file` tool tended to use `create_or_overwrite` a bit too
often, leading to corruption of long files. This change replaces the
boolean flag with an `EditFileMode` enum, which helps Agent make a more
deliberate choice when overwriting files.

With this change, the pass rate of the new eval increased from 10% to
100%.

2. eval: Added ability to run eval on top of an existing thread. Threads
can now be loaded from JSON files in the `SerializedThread` format,
which makes it easy to use real threads as starting points for
tests/evals.

3. Don't try to restore tool cards when running in headless or eval mode
-- we don't have a window to properly do this.

Release Notes:

- N/A

crates/eval/src/example.rs

@@ -48,6 +48,7 @@ pub struct ExampleMetadata {
     pub language_server: Option<LanguageServer>,
     pub max_assertions: Option<usize>,
     pub profile_id: AgentProfileId,
+    pub existing_thread_json: Option<String>,
 }
 
 #[derive(Clone, Debug)]
@@ -477,12 +478,16 @@ impl Response {
         tool_name: &'static str,
         cx: &mut ExampleContext,
     ) -> Result<&ToolUse> {
-        let result = self.messages.iter().find_map(|msg| {
+        let result = self.find_tool_call(tool_name);
+        cx.assert_some(result, format!("called `{}`", tool_name))
+    }
+
+    pub fn find_tool_call(&self, tool_name: &str) -> Option<&ToolUse> {
+        self.messages.iter().rev().find_map(|msg| {
             msg.tool_use
                 .iter()
                 .find(|tool_use| tool_use.name == tool_name)
-        });
-        cx.assert_some(result, format!("called `{}`", tool_name))
+        })
     }
 
     #[allow(dead_code)]