Yehowshua/ZIm
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

agent: Overwrite files more cautiously (#30649)

Browse source 
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
This commit is contained in:
Oleksiy Syvokon 2025-05-14 10:40:44 +03:00 • committed by GitHub
parent 22f76ac1a7
commit 255d8f7cf8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
18 changed files with 425 additions and 37 deletions
Download patch file Download diff file Expand all files Collapse all files

22
crates/assistant_tools/src/edit_agent/evals.rs
View file

@ -1,5 +1,9 @@
use super::*;
use crate::{ReadFileToolInput, edit_file_tool::EditFileToolInput, grep_tool::GrepToolInput};
use crate::{
ReadFileToolInput,
edit_file_tool::{EditFileMode, EditFileToolInput},
grep_tool::GrepToolInput,
};
use Role::*;
use anyhow::anyhow;
use assistant_tool::ToolRegistry;
@ -71,7 +75,7 @@ fn eval_extract_handle_command_output() {
EditFileToolInput {
display_description: edit_description.into(),
path: input_file_path.into(),
create_or_overwrite: false,
mode: EditFileMode::Edit,
},
)],
),
@ -127,7 +131,7 @@ fn eval_delete_run_git_blame() {
EditFileToolInput {
display_description: edit_description.into(),
path: input_file_path.into(),
create_or_overwrite: false,
mode: EditFileMode::Edit,
},
)],
),
@ -182,7 +186,7 @@ fn eval_translate_doc_comments() {
EditFileToolInput {
display_description: edit_description.into(),
path: input_file_path.into(),
create_or_overwrite: false,
mode: EditFileMode::Edit,
},
)],
),
@ -297,7 +301,7 @@ fn eval_use_wasi_sdk_in_compile_parser_to_wasm() {
EditFileToolInput {
display_description: edit_description.into(),
path: input_file_path.into(),
create_or_overwrite: false,
mode: EditFileMode::Edit,
},
)],
),
@ -372,7 +376,7 @@ fn eval_disable_cursor_blinking() {
EditFileToolInput {
display_description: edit_description.into(),
path: input_file_path.into(),
create_or_overwrite: false,
mode: EditFileMode::Edit,
},
)],
),
@ -566,7 +570,7 @@ fn eval_from_pixels_constructor() {
EditFileToolInput {
display_description: edit_description.into(),
path: input_file_path.into(),
create_or_overwrite: false,
mode: EditFileMode::Edit,
},
)],
),
@ -643,7 +647,7 @@ fn eval_zode() {
EditFileToolInput {
display_description: edit_description.into(),
path: input_file_path.into(),
create_or_overwrite: true,
mode: EditFileMode::Create,
},
),
],
@ -888,7 +892,7 @@ fn eval_add_overwrite_test() {
EditFileToolInput {
display_description: edit_description.into(),
path: input_file_path.into(),
create_or_overwrite: false,
mode: EditFileMode::Edit,
},
),
],