agent: Improve initial file search quality (#29317)

This PR significantly improves the quality of the initial file search
that occurs when the model doesn't yet know the full path to a file it
needs to read/edit.

Previously, the assertions in file_search often failed on main as the
model attempted to guess full file paths. On this branch, it reliably
calls `find_path` (previously `path_search`) before reading files.

After getting the model to find paths first, I noticed it would try
using `grep` instead of `path_search`. This motivated renaming
`path_search` to `find_path` (continuing the analogy to unix commands)
and adding system prompt instructions about proper tool selection.

Note: I know the command is just called `find`, but that seemed too
general.

In my eval runs, the `file_search` example improved from 40% ± 10% to
98% ± 2%. The only assertion I'm seeing occasionally fail is "glob
starts with `**` or project". We can probably add some instructions in
that regard.

Release Notes:

- N/A
This commit is contained in:
Agus Zubiaga 2025-04-23 21:24:41 -03:00 committed by GitHub
parent 2124b7ea99
commit 8b5835de17
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 107 additions and 28 deletions

View file

@ -20,6 +20,8 @@ use util::paths::PathMatcher;
pub struct GrepToolInput {
/// A regex pattern to search for in the entire project. Note that the regex
/// will be parsed by the Rust `regex` crate.
///
/// Do NOT specify a path here! This will only be matched against the code **content**.
pub regex: String,
/// A glob pattern for the paths of files to include in the search.