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>
Also `now` in `write` profile
Release Notes:
- Tools for manipulating directories no longer require confirmation, and
are enabled in the Write profile
- Enabled `now` and `list_directory` tools by default in Write profile
---------
Co-authored-by: Cole Miller <m@cole-miller.net>
Co-authored-by: Cole Miller <cole@zed.dev>
Some changes in the LanguageModelRegistry caused the web search tool not
to show up, because the `DefaultModelChanged` event is not emitted at
startup anymore.
Release Notes:
- agent: Fixed an issue where the web search tool would not be available
after starting Zed (only when using zed.dev as a provider).
Refs #29733
This pull request introduces a new field to the `StreamingEditFileTool`
that lets the model create or overwrite a file in a streaming way. When
one of the `assistant.stream_edits` setting / `agent-stream-edits`
feature flag is enabled, we are going to disable the `CreateFileTool` so
that the agent model can only use `StreamingEditFileTool` for file
creation.
Release Notes:
- N/A
---------
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
Co-authored-by: Oleksiy Syvokon <oleksiy.syvokon@gmail.com>
This PR prevents any unnecessary lines from being rendered in the edit
file tool card in the case of small diffs.
I think this (hopefully) addresses the last remaining task from
https://github.com/zed-industries/zed/pull/29448.
| `main` | This PR |
| --- | --- |
| <img width="634" alt="main"
src="https://github.com/user-attachments/assets/7c06394e-957a-4d36-a484-5974687041e9"
/> | <img width="634" alt="PR"
src="https://github.com/user-attachments/assets/84206d5a-a93a-4a42-99ca-7cdebb0d91bb"
/> |
(The last empty line in the second image is an empty line present in the
file itself)
---
n the second commit I also preemtively disabled vertical overscrolling
for full mode editors which are sized by content. This is basically the
same fix as in https://github.com/zed-industries/zed/pull/28471.
Strictly speaking, this is not needed for the fix here, but I thought it
might be nice to have for the future to prevent any issues from occuring
due to overscroll.
Release Notes:
- agent: Improved rendering of small diffs for the edit file tool card.
This pull request introduces a new tool for streaming edits. The
short-term goal is for this tool to replace the existing `EditFileTool`,
but we want to get this out the door as soon as possible so that we can
start testing it.
`StreamingEditFileTool` is mutually exclusive with `EditFileTool`. It
will be enabled by default for anyone who has the `agent-stream-edits`
feature flag, as well as people that set `assistant.stream_edits` to
`true` in their settings.
### Implementation
Streaming is achieved by requesting a completion while the `edit_file`
tool gets called. We invoke the model by taking the existing
conversation with the agent and appending a prompt specifically tailored
for editing. In that prompt, we ask the model to produce a stream of
`<old_text>`/`<new_text>` tags. As the model streams text in, we
incrementally parse it and start editing as soon as we can.
### Evals
Note that, as part of this pull request, I also defined some new evals
that I used to drive the behavior of the recursive LLM call. To run
them, use this command:
```bash
cargo test --package=assistant_tools --features eval -- eval_extract_handle_command_output
```
Or comment out the `#[cfg_attr(not(feature = "eval"), ignore)]` macro.
I recommend running them one at a time, because right now we don't
really have a way of orchestrating of all these evals. I think we should
invest into that effort once the new agent panel goes live.
Release Notes:
- N/A
---------
Co-authored-by: Nathan Sobo <nathan@zed.dev>
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Co-authored-by: Oleksiy Syvokon <oleksiy.syvokon@gmail.com>
⚠️ Work in progress until all of the to-dos are knocked out:
- [x] Disable soft-wrapping
- [x] Make it foldable only after a certain number of lines
- [x] Display tool status errors
- [x] Fix horizontal scroll now that we've disabled soft-wrap
- [ ] Don't render unnecessary extra lines (will be added later, on a
follow-up PR)
Release Notes:
- N/A
---------
Co-authored-by: Agus Zubiaga <hi@aguz.me>
Co-authored-by: Michael Sloan <mgsloan@gmail.com>
Adds popular examples of long-running commands to system prompt.
Unfortunately, I couldn't add an eval example as the new terminal tool
no longer works in `eval`. We can look into that tomorrow, but I'm
seeing improvements when manually testing this, so I'd like to merge it.
<img
src="https://github.com/user-attachments/assets/ac24e617-e068-466f-875d-c30e1f2465c4"
width=400></img>
Release Notes:
- agent: Discourage long-running commands
The `grep` tool used to include 4 lines of context around the match, but
the lines included would often be unhelpful. This PR improves this
behavior by using the range of the parent syntax node that contains the
full line(s) matched.
The match headers will also now include symbol breadcrumbs so that the
model can already gather code structure before/without reading files.
````md
### impl GitRepository for RealGitRepository › fn compare_checkpoints › L1278-1284
```rust
let result = git
.run(&[
"diff-tree",
"--quiet",
&left.commit_sha.to_string(),
&right.commit_sha.to_string(),
])
```
````
This positively impacts the `add_arg_to_trait_method` eval example with
better diff output, fewer tool failures, and reduced total turns.
Note: We have some plans to use a an "elision" approach where we would
combine all matches for a given file, skipping lines between them while
keeping symbol declaration lines. The theory is that this would be map
more closely to the expected input for edits. For now, this PR is a
significant improvement.
Release Notes:
- Agent: Enrich `grep` tool output with syntax information
This PR addresses the behavior of the agent's terminal tool when the
executed command is interrupted or fails after producing some output.
Currently, if the command doesn't finish successfully, any partial
output captured before the interruption/failure is discarded, and only
an error message (or a generic cancellation message) is returned to the
LLM.
This change modifies the `run_command_limited` function in the terminal
tool to catch errors when awaiting the command's status (which includes
interruptions). In the case of such an error, it now includes any
partial stdout/stderr captured up to that point within the error message
returned to the `ToolUseState`. This ensures the LLM receives the
partial context even when the command doesn't complete cleanly, framed
appropriately as part of an error/interruption message.
Closes#29101
Release Notes:
- N/A
One motivation is that the outlines returned by `read_file` for large
files list line numbers assuming an inclusive `end_line`. As a result,
when the agent uses these outlines for `read_line` calls, it would
otherwise miss the last line.
Release Notes:
- N/A
