Looks like I accidentally touched a line of code in an eval fixture in
#31479, despite intentionally trying to avoid that code. Thanks
@cole-miller!
Release Notes:
- N/A
This change instructs models to wrap new file content in Markdown fences
and introduces a parser for this format. The reasons are:
1. This is the format we put a lot of effort into explaining in the
system prompt.
2. Gemini really prefers to do it.
3. It adds an option for a model to think before writing the content
The `eval_zode` pass rate for GEmini models goes from 0% to 100%. Other
models were already at 100%, this hasn't changed.
Release Notes:
- N/A
An unintended consequence of format on save is that we start (correctly)
informing the model that the file changed on disk every time the
formatter changes anything, which in turn can lead the model to things
like extra reads.
Until we have a solution in place to prevent this downside, we're going
back to not formatting on save by reverting
cb112a4012.
Release Notes:
- N/A
Open inspector with `dev: toggle inspector` from command palette or
`cmd-alt-i` on mac or `ctrl-alt-i` on linux.
https://github.com/user-attachments/assets/54c43034-d40b-414e-ba9b-190bed2e6d2f
* Picking of elements via the mouse, with scroll wheel to inspect
occluded elements.
* Temporary manipulation of the selected element.
* Layout info and JSON-based style manipulation for `Div`.
* Navigation to code that constructed the element.
Big thanks to @as-cii and @maxdeviant for sorting out how to implement
the core of an inspector.
Release Notes:
- N/A
---------
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
Co-authored-by: Federico Dionisi <code@fdionisi.me>
This change improves `eval_extract_handle_command_output` results for
all models:
Model | Pass rate before | Pass rate after
----------------------------|------------------|----------------
claude-3.7-sonnet | 0.96 | 0.98
gemini-2.5-pro | 0.35 | 0.86
gpt-4.1 | 0.81 | 1.00
Part of this improvement comes from more robust evaluation, which now
accepts multiple possible outcomes. Another part is from the prompt
adaptation: addressing common Gemini failure modes, adding a few-shot
example, and, in the final commit, auto-rewriting instructions for
clarity and conciseness.
This change still needs validation from larger end-to-end evals.
Release Notes:
- N/A
1. Add system prompt: this is how it's called from threads. Previously,
we were sending
2. Fix an issue with writing agent thought into a newly created empty
file.
Release Notes:
- N/A
---------
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
Co-authored-by: Antonio Scandurra <me@as-cii.com>
https://github.com/zed-industries/zed/issues/30972 brought up another
case where our context is not enough to track the actual source of the
issue: we get a general top-level error without inner error.
The reason for this was `.ok_or_else(|| anyhow!("failed to read HEAD
SHA"))?; ` on the top level.
The PR finally reworks the way we use anyhow to reduce such issues (or
at least make it simpler to bubble them up later in a fix).
On top of that, uses a few more anyhow methods for better readability.
* `.ok_or_else(|| anyhow!("..."))`, `map_err` and other similar error
conversion/option reporting cases are replaced with `context` and
`with_context` calls
* in addition to that, various `anyhow!("failed to do ...")` are
stripped with `.context("Doing ...")` messages instead to remove the
parasitic `failed to` text
* `anyhow::ensure!` is used instead of `if ... { return Err(...); }`
calls
* `anyhow::bail!` is used instead of `return Err(anyhow!(...));`
Release Notes:
- N/A
This eval checks that Edit Agent can create an empty file without
writing its thoughts into it. This issue is not specific to empty files,
but it's easier to reproduce with them.
For some mysterious reason, I could easily reproduce this issue roughly
90% of the time in actual Zed. However, once I extract the exact LLM
request before the failure point and generate from that, the
reproduction rate drops to 2%!
Things I've tried to make sure it's not a fluke: disabling prompt
caching, capturing the LLM request via a proxy server, running the
prompt on Claude separately from evals. Every time it was mostly giving
good outcomes, which doesn't match my actual experience in Zed.
At some point I discovered that simply adding one insignificant space or
a newline to the prompt suddenly results in an outcome I tried to
reproduce almost perfectly.
This weirdness happens even outside the Zed code base and even when
using a different subscription. The result is the same: an extra newline
or space changes the model behavior significantly enough, so that the
pass rate drops from 99% to 0-3%
I have no explanation to this.
Release Notes:
- N/A
This PR makes the edit tool call codeblock cards expanded by default, to
be consistent with https://github.com/zed-industries/zed/pull/30806.
Also, I am removing the collapsing behavior of Markdown codeblocks where
we'd add a gradient while capping the container's height based on an
arbitrary number of lines. Figured if they're all now initially
expanded, we could simplify how the design/code operates here
altogether.
Open for feedback, as I can see an argument where the previous Markdown
codeblock design of "collapsed but not fully; it shows a preview" should
stay as it is useful.
Release Notes:
- N/A
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 is very basic support for them. There are a number of other TODOs
before this is really a first-class supported feature, so not adding any
release notes for it; for now, this PR just makes it so that if
read_file tries to read a PNG (which has come up in practice), it at
least correctly sends it to Anthropic instead of messing up.
This also lays the groundwork for future PRs for more first-class
support for images in tool calls across more image file formats and LLM
providers.
Release Notes:
- N/A
---------
Co-authored-by: Agus Zubiaga <hi@aguz.me>
Co-authored-by: Agus Zubiaga <agus@zed.dev>
Closes https://github.com/zed-industries/zed/issues/30411
Rendering as markdown gives us text selection and copying for free. In
the future, we may want to explore having these commands be actual
editors, allowing you to step in, change the command, and re-run it
right from there.
Release Notes:
- agent: Made the terminal command in the tool card selectable and
copyable.
This allows us to debug the raw edits that were generated when people
report feedback, when running evals and when opening the thread as
Markdown.
Release Notes:
- Improved debug output for agent threads.
- Adds a new smoke test for the use of the read_file tool by the agent
in an SSH project
- Fixes the SSH shutdown sequence to use a timer from the app's executor
instead of always using a real timer
- Changes the main executor loop for tests to advance the clock
automatically instead of panicking with `parked with nothing left to
run` when there is a delayed task
Release Notes:
- N/A
## Overview
This PR adds the minimap feature to the Zed editor, closely following
the [design from Visual Studio
Code](https://code.visualstudio.com/docs/getstarted/userinterface#_minimap).
When configured, a second instance of the editor will appear to the left
of the scrollbar. This instance is not interactive and it has a slimmed
down set of annotations, but it is otherwise just a zoomed-out version
of the main editor instance. A thumb shows the line boundaries of the
main viewport, as well as the progress through the document. Clicking on
a section of code in the minimap will jump the editor to that code.
Dragging the thumb will act like the scrollbar, moving sequentially
through the document.
## New settings
This adds a `minimap` section to the editor settings with the following
keys:
### `show`
When to show the minimap in the editor.
This setting can take three values:
1. Show the minimap if the editor's scrollbar is visible: `"auto"`
2. Always show the minimap: `"always"`
3. Never show the minimap: `"never"` (default)
### `thumb`
When to show the minimap thumb.
This setting can take two values:
1. Show the minimap thumb if the mouse is over the minimap: `"hover"`
2. Always show the minimap thumb: `"always"` (default)
### `width`
The width of the minimap in pixels.
Default: `100`
### `font_size`
The font size of the minimap in pixels.
Default: `2`
## Providing feedback
In order to keep the PR focused on development updates, please use the
discussion thread for feature suggestions and usability feedback: #26894
## Features left to add
- [x] fix scrolling performance
- [x] user settings for enable/disable, width, text size, etc.
- [x] show overview of visible lines in minimap
- [x] clicking on minimap should navigate to the corresponding section
of code
- ~[ ] more prominent highlighting in the minimap editor~
- ~[ ] override scrollbar auto setting to always when minimap is set to
always show~
Release Notes:
- Added minimap for high-level overview and quick navigation of editor
contents.
---------
Co-authored-by: MrSubidubi <dev@bahn.sh>
Co-authored-by: Kirill Bulatov <kirill@zed.dev>
This PR changes the way a horizontal margin is added in editors. It
removes the possibility to set a custom `horizontal_padding` for an
editor and utilizes the default `gutter_dimension` instead.
This change is made to ensure that no issues with soft-wrapping occurs
for any editor that has a `horizontal_margin` set (see #26893 for more
context on the implications here`. Furthermore, it ensures that the text
actually renders properly when scrolling horizontally and is not
cut-off.
### Horizontal padding:
| `main` | This PR |
| --- | --- |
| 
| 
|
### Editor horizontally scrolled:
| `main` | This PR |
| --- | --- |
| 
| 
|
Notice the difference at the horizontal borders.
The margin added for the `edit_file_tool` was 4 pixels. The `descent`,
whilst not exactly, is roughly the same here and also scales with the
font size nicely. Furthermore, it seems that the
`gutter_dimensions.margin` should be present anyway, given the following
comment
0b00256f58/crates/editor/src/element.rs (L6887-L6889)
so ensuring this property is actually set and not 0 seems to be
reasonable given the circumstances.
Please note though that this will apply to all editors in the app.
Again, this seems like it should be the case anyway, just wanted to
mention this again.
Should the fix like this not be wanted, I can change this here so that
the `horizontal_margin` is better accounted for when soft-wrapping in an
editor. Feel free to let me know in this case.
Release Notes:
- N/A
Release Notes:
- Fixed a bug that would prevent the agent from working over SSH.
---------
Co-authored-by: Nathan Sobo <nathan@zed.dev>
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Cole Miller <m@cole-miller.net>
This PR removes all of the feature flag checks related to the Agent.
Tried to do this in the least invasive way possible; we can follow up
with a full removal.
Release Notes:
- N/A
This improves the new eval scenario by ~80% (`0.29` vs `0.525`) without
decreasing performance in the other evals.
Release Notes:
- Improved the performance of the `edit_file` tool.
Release Notes:
- Fixed a bug that would cause rejecting a hunk from the agent to delete
the file if the agent had decided to rewrite that file from scratch.
You can set `agent_font_size` as a top-level settings key. You can also
use `zed::IncreaseBufferFontSize` and `zed::DecreaseBufferFontSize` and
`zed::ResetBufferFontSize` the agent panel is focused via the standard
bindings to adjust the agent font size. In the future, it might make
sense to rename these actions to be more general since "buffer" is now a
bit of a misnomer. 🍐'd with @mikayla-maki
Release Notes:
- N/A
---------
Co-authored-by: Mikayla Maki <mikayla.c.maki@gmail.com>
WIP
- On macOS/Linux, run the command in bash instead of the user's shell
- Try to prevent the agent from running commands that expect interaction
Release Notes:
- Agent Beta: Switched to using `bash` (if available) instead of the
user's shell when calling the terminal tool.
- Agent Beta: Prevented the agent from hanging when trying to run
interactive commands.
---------
Co-authored-by: WeetHet <stas.ale66@gmail.com>
To-dos:
- [x] Expose the command to defend against cases where that's just super
long
- [x] Tackle the vertical scroll conflict with panel scroll
- [x] Reduce default font-size
Release Notes:
- N/A
---------
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
Co-authored-by: Mikayla Maki <mikayla.c.maki@gmail.com>
Co-authored-by: Agus Zubiaga <hi@aguz.me>
Bypass our terminal subsystem and just run a shell in a pty.
- [x] make sure we use the same working directory
- [x] strip control chars from the pty output (?)
- [x] tests
Release Notes:
- N/A
I am currently setting the font size corrrectly by using a custom
EditorStyle and building an element. However I need to use the same
properties as a normal editor for everything but font size.
Release Notes:
- N/A
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
Nathan here: I also tacked on a bunch of UI refinement.
Release Notes:
- Introduced the ability to follow the agent around as it reads and
edits files.
---------
Co-authored-by: Nathan Sobo <nathan@zed.dev>
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Still a work in progress.
Release Notes:
- N/A
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Co-authored-by: Nathan Sobo <nathan@zed.dev>
Co-authored-by: Cole Miller <m@cole-miller.net>
Co-authored-by: Nathan Sobo <1789+nathansobo@users.noreply.github.com>
Co-authored-by: Cole Miller <53574922+cole-miller@users.noreply.github.com>
