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/eval.rs

@@ -711,9 +711,9 @@ fn print_report(
         .values()
         .flat_map(|results| {
             results.iter().map(|(example, _)| {
-                let absolute_path = example.run_directory.join("last.messages.json");
-                pathdiff::diff_paths(&absolute_path, run_dir)
-                    .unwrap_or_else(|| absolute_path.clone())
+                let absolute_path = run_dir.join(example.run_directory.join("last.messages.json"));
+                let cwd = std::env::current_dir().expect("Can't get current dir");
+                pathdiff::diff_paths(&absolute_path, cwd).unwrap_or_else(|| absolute_path.clone())
             })
         })
         .collect::<Vec<_>>();