Commit Graph
11 Commits
Author SHA1 Message Date
Oleksiy SyvokonandMarshall Bowers 6df4c537b9 agent: Less disruptive changed file notification (#31693)
When the user edits one of the tracked files, we used to notify the
agent by inserting a user message at the end of the thread. This was
causing a few problems:
- The agent would stop doing its work and start reading changed files
- The agent would write something like, "Thank you for letting me know
about these changed files."

This fix contains two parts:
1. Changing the prompt to indicate this is a service message
2. Moving the message higher in the conversation thread

This works, but it slightly hurts caching.

We may consider making these notification messages stick in history,
trading context tokens count for the cache.

This might be related to #30906

Release Notes:

- N/A

---------

Co-authored-by: Marshall Bowers <git@maxdeviant.com>
2025-06-16 18:45:24 +03:00
Oleksiy SyvokonandBen Brandt 3884de937b assistant: Partial fix for HTML entities in tools params (#32148)
This problem seems to be specific to Opus 4. Eval shows improvement from
89% to 97%.

Closes: https://github.com/zed-industries/zed/issues/32060

Release Notes:

- N/A

Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
2025-06-05 10:36:55 +00:00
Oleksiy Syvokon cb187b0b4d evals: Configurable number of max dialog turns (#31680)
Release Notes:

- N/A
2025-05-29 10:35:29 +00:00
Marshall Bowers 8faeb34367 Rename assistant_settings to agent_settings (#31513)
This PR renames the `assistant_settings` crate to `agent_settings`, as
well a number of constructs within it.

Release Notes:

- N/A
2025-05-27 15:16:55 +00:00
Oleksiy Syvokon 255d8f7cf8 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
2025-05-14 10:40:44 +03:00
Oleksiy Syvokon 8199664a5a agent: Handle attempts to use hallucinated tools (#29946)
This change:

1. Catches attempts to use missing tools. If this happens, we now send
Agent a message listing available tools, after which Agent can
gracefully recover. Prior behavior: thread would stop in a broken state.

Example of a hallucinated call and a message we send back: 

![image](https://github.com/user-attachments/assets/92a8f700-b192-4038-8c7e-0a74ca2e0146)

2. Adds evals for hallucinated tool use and imagined edits
3. Adds ability to configure a profile name in evals.



Release Notes:

- N/A
2025-05-05 19:31:11 +00:00
Antonio Scandurra 4d51602e7b Encourage editing over re-creating a file from scratch (#29870)
I also introduced a new eval to prove the encouragement actually makes a
difference.

Release Notes:

- Improved agent behavior when streaming edits, encouraging it to
editing files as opposed to creating them from scratch
2025-05-04 13:18:28 +00:00
Richard Feldman 9efc09c5a6 Add eval for open_tool (#29801)
Also have its description say it should only be used on request

Release Notes:

- N/A
2025-05-02 15:56:07 +00:00
Richard Feldman d7004030b3 Code block evals (#29619)
Add a targeted eval for code block formatting, and revise the system
prompt accordingly.

### Eval before, n=8

<img width="728" alt="eval before"
src="https://github.com/user-attachments/assets/552b6146-3d26-4eaa-86f9-9fc36c0cadf2"
/>

### Eval after prompt change, n=8 (excluding the new evals, so just
testing the prompt change)

<img width="717" alt="eval after"
src="https://github.com/user-attachments/assets/c78c7a54-4c65-470c-b135-8691584cd73e"
/>

Release Notes:

- N/A
2025-04-29 18:52:09 -04:00
Agus ZubiagaandRichard Feldman 45d3f5168a eval: New add_arg_to_trait_method example (#29297)
Release Notes:

- N/A

---------

Co-authored-by: Richard Feldman <oss@rtfeldman.com>
2025-04-23 18:46:39 +00:00
ce1a674eba eval: Fine-grained assertions (#29246)
- Support programmatic examples
([example](https://github.com/zed-industries/zed/blob/17feb260a0919e102ae4e220669c467885bf4b57/crates/eval/src/examples/file_search.rs))
- Combine data-driven example declarations into a single `.toml` file
([example](https://github.com/zed-industries/zed/blob/17feb260a0919e102ae4e220669c467885bf4b57/crates/eval/src/examples/find_and_replace_diff_card.toml))
- Run judge on individual assertions (previously called "criteria")
- Report judge and programmatic assertions in one combined table

Note: We still need to work on concept naming 

<img width=400
src="https://github.com/user-attachments/assets/fc719c93-467f-412b-8d47-68821bd8a5f5">

Release Notes:

- N/A

---------

Co-authored-by: Richard Feldman <oss@rtfeldman.com>
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Thomas Mickley-Doyle <tmickleydoyle@gmail.com>
2025-04-22 23:58:58 -03:00