Commit Graph
5 Commits
Author SHA1 Message Date
8366cd0b52 agent: Render diffs for the edit file tool (#29234)
This PR implements the `ToolCard` for the edit file tool, which allow us
to display an editor with a diff in the thread view with the changes
performed by the model.

- [x] Fix buffer sometimes displaying empty
- [x] Stop buffer from scrolling together with the thread
- [x] Fix multibuffer header sometimes appearing
- [x] Fix buffer height issue
- [x] Implement "full height" expand button
- [x] Add "Jump To File" functionality
- [x] Polish and refine styles

Release Notes:

- agent: Added diff preview cards in the thread view for edits performed
by the agent.

---------

Co-authored-by: João Marcos <marcospb19@hotmail.com>
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
Co-authored-by: Agus Zubiaga <hi@aguz.me>
Co-authored-by: Conrad Irwin <conrad.irwin@gmail.com>
2025-04-23 15:43:33 -03:00
Antonio Scandurra 55ea481707 Restore file to original content when rejecting file recreated by agent (#29264)
Release Notes:

- Fixed a bug that could sometimes cause a file to be deleted when
rejecting an agent change.
2025-04-23 09:42:43 +00:00
bab28560ef Systematically optimize agentic editing performance (#28961)
Now that we've established a proper eval in tree, this PR is reboots of
our agent loop back to a set of minimal tools and simpler prompts. We
should aim to get this branch feeling subjectively competitive with
what's on main and then merge it, and build from there.

Let's invest in our eval and use it to drive better performance of the
agent loop. How you can help: Pick an example, and then make the outcome
faster or better. It's fine to even use your own subjective judgment, as
our evaluation criteria likely need tuning as well at this point. Focus
on making the agent work better in your own subjective experience first.
Let's focus on simple/practical improvements to make this thing work
better, then determine how we can craft our judgment criteria to lock
those improvements in.

Release Notes:

- N/A

---------

Co-authored-by: Max <max@zed.dev>
Co-authored-by: Antonio <antonio@zed.dev>
Co-authored-by: Agus <agus@zed.dev>
Co-authored-by: Richard <richard@zed.dev>
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Michael Sloan <mgsloan@gmail.com>
2025-04-19 02:47:59 +00:00
Bennet Bo Fenner 5e094553fa agent: Return ToolResult from run inside Tool (#28763)
This is just a refactor which adds no functionality.
We now return a `ToolResult` from `Tool > run(...)`. For now this just
wraps the output task in a struct. We'll use this to implement custom
rendering of tools, see #28621.

Release Notes:

- N/A
2025-04-15 14:28:09 +00:00
Richard Feldman b794919842 Add contents_tool (#28738)
This is a combination of the "read file" and "list directory contents"
tools as part of a push to reduce our quantity of builtin tools by
combining some of them.

The functionality is all there for this tool, although there's room for
improvement on the visuals side: it currently always shows the same icon
and always says "Read" - so you can't tell at a glance when it's reading
a directory vs an individual file. Changing this will require a change
to the `Tool` trait, which can be in a separate PR. (FYI @danilo-leal!)

<img width="606" alt="Screenshot 2025-04-14 at 11 56 27 PM"
src="https://github.com/user-attachments/assets/bded72af-6476-4469-97c6-2f344629b0e4"
/>

Release Notes:

- Added `contents` tool
2025-04-15 00:54:25 -04:00