This PR adds the ability to hear a sound notification when the agent is
done generating and/or needs user input. This setting is turned off by
default and can be used together with the visual notification. The
specific sound I'm using here comes from the [Material Design 2 Sound
Library](https://m2.material.io/design/sound/sound-resources.html#).
Release Notes:
- agent: Added the ability to have a sound notification when the agent
is done generating and/or needs user input.
Fixes#14612
This was a feature I dearly missed from VSCode, so adding this helped me
migrate to Zed without disrupting my workflow. I found that `4.0` was a
nice goldilocks multiplier and felt close/the same as the speed in
VSCode.
Release Notes:
- Added faster scrolling in the editor while holding opt/alt
Follow up to https://github.com/zed-industries/zed/pull/30140 and
https://github.com/zed-industries/zed/pull/31236
This PR introduces an inline code action indicator that shows up at the
start of a buffer line when there's enough space. If space is tight, it
adjusts to lines above or below instead. It also adjusts when cursor is
near indicator.
The indicator won't appear if there's no space within about 8 rows in
either direction, and it also stays hidden for folded ranges. It also
won't show up in case there is not space in multi buffer excerpt. These
cases account for very little because practically all languages do have
indents.
https://github.com/user-attachments/assets/1363ee8a-3178-4665-89a7-c86c733f2885
This PR also sets the existing `toolbar.code_actions` setting to `false`
in favor of this.
Release Notes:
- Added code action indicator which shows up inline at the start of the
row. This can be disabled by setting `inline_code_actions` to `false`.
Don't hard wrap interactively; instead, soft wrap in `Bounded` mode
(editor width or 72 chars, whichever is smaller), and then hard wrap
before sending the commit message to git.
This also makes the soft wrap mode and width for commit messages
configurable in language settings.
Previously we didn't support soft wrap modes other than `EditorWidth` in
auto-height editors; I tried to add support for this by analogy with
code that was already there, and it seems to work pretty well.
Closes#27508
Release Notes:
- Fixed confusing wrapping behavior in commit message editors.
Closes https://github.com/blopker/codebook/issues/79
Recently, the setting `diagnostics_max_severity` was changed from `null`
to `warning`in this PR: https://github.com/zed-industries/zed/pull/30316
This change has caused the various spell checking extensions to not work
as expected by default, most of which use the `hint` diagnostic. This
goes against user expectations when installing one of these extensions.
Without `hint` as the default, extension authors will either need to
change the diagnostic levels, or instruct users to add
`diagnostics_max_severity` to their settings as an additional step,
neither of which is a great user experience.
This PR sets the default `hint`, which is closer to the original
behavior before the aforementioned PR.
Release Notes:
- Changed `diagnostics_max_severity` to `hint` instead of `warning` by
default
---------
Co-authored-by: Kirill Bulatov <kirill@zed.dev>
Closes https://github.com/zed-industries/zed/issues/20016
Use `"read_ssh_config": false` to disable the new behavior.
Release Notes:
- Added a way to import ssh host names from the ssh config
---------
Co-authored-by: Cole Miller <m@cole-miller.net>
Designed to pair with #30444 to enable enterprises to make it harder to
sign into the collab server and perhaps accidentally end up sending code
to Zed.
Release Notes:
- N/A
Co-authored-by: Mikayla Maki <mikayla@zed.dev>
- Add docs for `hover_popover_delay`.
- Set `hover_popover_delay` to `300` from `350` which matches [VSCode's
hover
delay](ed48873ba2/src/vs/editor/common/config/editorOptions.ts (L2219)).
Release Notes:
- Added `hover_popover_delay` to settings which determines time to wait
in milliseconds before showing the informational hover box.
* project search button in the status bar
```jsonc
"search": {
"button": false
},
```
* project diagnostics button in the status bar
```jsonc
"diagnostics": {
"button": false
}
```
* project name and host buttons in the title bar
```jsonc
"title_bar": {
"show_project_items": false
}
```
* git branch button in the title bar
```jsonc
"title_bar": {
"show_branch_name": false
}
```
Before:
<img width="1728" alt="before"
src="https://github.com/user-attachments/assets/4b13b431-3ac1-43b3-8ac7-469e5a9ccf7e"
/>
After:
<img width="1728" alt="after"
src="https://github.com/user-attachments/assets/baf2765a-e27b-47a3-8897-89152b7a7c95"
/>
Release Notes:
- Added more settings to hide buttons from Zed UI
Release Notes:
- Fixed a race condition that sometimes prevented a system-installed
`node` binary from being detected.
- Fixed a bug where the `node.path` setting was not respected when
invoking npm.
* Adds a `diagnostics_max_severity: null` editor settings that has
previous hardcoded default, `warning`
* Make inline diagnostics to inherit this setting by default (can be
overridden with its own max_severity setting)
* Allows to toggle diagnostics in the editor menu and via new action,
`editor::ToggleDiagnostics`
Closes https://github.com/zed-industries/zed/issues/4686
Release Notes:
- N/A *or* Added/Fixed/Improved ...
## 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 conflicts for space with breakpoints, and seems borderline in terms
of utility.
We could consider bringing it back in a way that is closer to the
cursor, or be content with our right-click menu discovery.
Release Notes:
- Remove the code actions indicator from the gutter. It is still
available from the right click menu, or with the keyboard shortcut.
Adds a new `agent.model_parameters` setting that allows the user to
specify a custom temperature for a provider AND/OR model:
```json5
"model_parameters": [
// To set parameters for all requests to OpenAI models:
{
"provider": "openai",
"temperature": 0.5
},
// To set parameters for all requests in general:
{
"temperature": 0
},
// To set parameters for a specific provider and model:
{
"provider": "zed.dev",
"model": "claude-3-7-sonnet-latest",
"temperature": 1.0
}
],
```
Release Notes:
- agent: Allow customizing temperature by provider/model
---------
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
Supersedes: https://github.com/zed-industries/zed/pull/29936
Thanks for your contribution @imumesh18, but we had a slightly different
take on it :)
Release Notes:
- N/A
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
- Languages now define their preferred debuggers in `config.toml`.
- `LanguageRegistry` now exposes language config even for languages that
are not yet loaded. This necessitated extension registry changes (we now
deserialize config.toml of all language entries when loading new
extension index), but it should be backwards compatible with the old
format. /cc @maxdeviant
Release Notes:
- N/A
---------
Co-authored-by: Anthony Eid <hello@anthonyeid.me>
Co-authored-by: Remco Smits <djsmits12@gmail.com>
Co-authored-by: Anthony <anthony@zed.dev>
Closes #ISSUE
Release Notes:
- Agent Beta: Renamed the top-level `assistant` settings key to `agent`.
A migration for existing settings files is included.
- Agent Beta: Moved the `assistant::ToggleFocus`,
`assistant::ToggleModelSelector`, and `assistant::OpenRulesLibrary`
actions to the `agent` namespace. Existing keymaps that mention these
actions by their old names will continue to work.
---------
Co-authored-by: Max <max@zed.dev>
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>
Completely subjective, but I just like it better.
Release Notes:
- N/A
---------
Co-authored-by: Danilo Leal <67129314+danilo-leal@users.noreply.github.com>
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Kinda feel like the way that makes the most sense to sort profiles in
the dropdown is by relevance/impact. "Write" is the default profile and
contains all built-in tools turned on by default, thus it should be the
first. "Ask" contains read-only tools, one step down from Write. And
"Manual" is totally empty, the least "powerful" profile, thus the last.
Release Notes:
- N/A
Closes#29836
The agent diff toolbar item was causing the editor toolbar to show even
when all the other elements were disabled via settings.
This PR fixes this by setting the location to
`ToolbarItemLocation::Hidden` in the states where it shouldn't show.
It also adds a new a `toolbar.agent_review` setting to hide the agent
review buttons altogether. However, if the other toolbar elements are
hidden and the file isn't under review, the editor toolbar will still be
hidden. So you only need to set this to `false` if you don't want them
to show up even under agent review.
Release Notes:
- N/A
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>
Follow-up of https://github.com/zed-industries/zed/pull/29706
Instead of doing `cargo check` manually, use rust-analyzer's flycheck:
at the cost of more sophisticated check command configuration, we keep
much less code in Zed, and get a proper progress report.
User-facing UI does not change except `diagnostics_fetch_command` and
`env` settings removed from the diagnostics settings.
Release Notes:
- N/A
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>
Adjusts the way `cargo` and `rust-analyzer` diagnostics are fetched into
Zed.
Nothing is changed for defaults: in this mode, Zed does nothing but
reports file updates, which trigger rust-analyzers'
mechanisms:
* generating internal diagnostics, which it is able to produce on the
fly, without blocking cargo lock.
Unfortunately, there are not that many diagnostics in r-a, and some of
them have false-positives compared to rustc ones
* running `cargo check --workspace --all-targets` on each file save,
taking the cargo lock
For large projects like Zed, this might take a while, reducing the
ability to choose how to work with the project: e.g. it's impossible to
save multiple times without long diagnostics refreshes (may happen
automatically on e.g. focus loss), save the project and run it instantly
without waiting for cargo check to finish, etc.
In addition, it's relatively tricky to reconfigure r-a to run a
different command, with different arguments and maybe different env
vars: that would require a language server restart (and a large project
reindex) and fiddling with multiple JSON fields.
The new mode aims to separate out cargo diagnostics into its own loop so
that all Zed diagnostics features are supported still.
For that, an extra mode was introduced:
```jsonc
"rust": {
// When enabled, Zed runs `cargo check --message-format=json`-based commands and
// collect cargo diagnostics instead of rust-analyzer.
"fetch_cargo_diagnostics": false,
// A command override for fetching the cargo diagnostics.
// First argument is the command, followed by the arguments.
"diagnostics_fetch_command": [
"cargo",
"check",
"--quiet",
"--workspace",
"--message-format=json",
"--all-targets",
"--keep-going"
],
// Extra environment variables to pass to the diagnostics fetch command.
"env": {}
}
```
which calls to cargo, parses its output and mixes in with the existing
diagnostics:
https://github.com/user-attachments/assets/e986f955-b452-4995-8aac-3049683dd22c
Release Notes:
- Added a way to get diagnostics from cargo and rust-analyzer without
mutually locking each other
- Added `ctrl-r` binding to refresh diagnostics in the project
diagnostics editor context
Closes#27073
Currently, when searching for a file with Ctrl+P, and the first file
found is the active one, file_finder skips focus to the second file
automatically. This PR adds a setting to disable this and make the first
file always the focused one.
Default setting is still skipping the active file.
Release Notes:
- Added the `skip_focus_for_active_in_search` setting for the file
finder, which allows turning off the default behavior of skipping focus
on the active file while searching in the file finder.
---------
Co-authored-by: Smit Barmase <heysmitbarmase@gmail.com>
This new default profile is one that doesn't use any tools; it's
completely "naked" and it shouldn't lean into trying to read things from
the current project at hand. Better suited for general topic chats with
the LLM.
PS: Still expecting some wordsmithing here before merging.
Release Notes:
- agent: Added a new default profile called "Manual" that doesn't
include any tools, for general topic chats with the LLM.
Release Notes:
- git: Add a `git_panel.sort_by_path` setting to mix untracked/tracked
files in the diff list.
- git: Remove the "•" placeholder for "Tracked". The commit button says
"Commit Tracked" still by default, and this was misinterpreted to mean
"partially staged". Hovering over the button will show you which files
are tracked (in addition to the yellow square-with-a-dot-in-it).
- Increase the default value of `expand_excerpt_lines` from 3 to 5. This
makes it faster to see more context in the git diff view.
---------
Co-authored-by: Birk Skyum <birk.skyum@pm.me>
Co-authored-by: Peter Tripp <peter@zed.dev>
Added `snippet_sort_order`, which determines how snippets are sorted
relative to other completion items. It can have the values `top`,
`bottom`, or `inline`, with `inline` being the default.
This mimics VS Code’s setting:
https://code.visualstudio.com/docs/editing/intellisense#_snippets-in-suggestions
Release Notes:
- Added support for `snippet_sort_order` to control snippet sorting
behavior in code completion menus.
This PR significantly improves the quality of the initial file search
that occurs when the model doesn't yet know the full path to a file it
needs to read/edit.
Previously, the assertions in file_search often failed on main as the
model attempted to guess full file paths. On this branch, it reliably
calls `find_path` (previously `path_search`) before reading files.
After getting the model to find paths first, I noticed it would try
using `grep` instead of `path_search`. This motivated renaming
`path_search` to `find_path` (continuing the analogy to unix commands)
and adding system prompt instructions about proper tool selection.
Note: I know the command is just called `find`, but that seemed too
general.
In my eval runs, the `file_search` example improved from 40% ± 10% to
98% ± 2%. The only assertion I'm seeing occasionally fail is "glob
starts with `**` or project". We can probably add some instructions in
that regard.
Release Notes:
- N/A
Closes#4495
Release Notes:
- vim: add cursor shape settings for each vim mode
---
Add cursor shape settings for each vim mode to enable users to specify
them.
Example of `settings.json`:
```json
{
"vim_mode": true,
"vim": {
"cursor_shape": {
"normal": "hollow",
"insert": "bar",
"replace": "block",
"visual": "underline"
}
}
}
```
After this change is applied,
- The cursor shape specified by the user for each mode is used.
- In insert mode, the `vim > cursor_shape > insert` setting takes
precedence over the primary `cursor_shape` setting.
- If `vim > cursor_shape > insert` is not set, the primary
`cursor_shape` will be used in insert mode.
- The cursor shape will remain unchanged before and after this update
when the user does not set the `vim > cursor_shape` setting.
Video:
[screen-record.webm](https://github.com/user-attachments/assets/b87461a1-6b3a-4a77-a607-a340f106def5)
This PR renames the `regex_search` tool to `grep` because I think it
conveys more meaning to the model, the idea of searching the filesystem
with a regular expression. It's also one word and the model seems to be
using it effectively after some additional prompt tuning.
It also takes an include pattern to filter on the specific files we try
to search. I'd like to encourage the model to scope its searches more
aggressively, as in my testing, I'm only seeing it filter on file
extension.
Release Notes:
- N/A
Before, we used to debounce selection highlight because it needed to
search the whole file to show gutter line highlights, etc. This
experience felt extremely laggy.
This PR introduces a new approach where:
1. We query only visible rows without debounce. The search function
itself is async and runs in a background thread, so it's not blocking
anything. With no debounce and such a small search space, highlights
feel realtime.
2. In parallel, we also query the whole file (still debounced, like
before). Once this query resolves, it updates highlights across the
file, making scrollbar markers visible.
This hybrid way gives the feeling of realtime, while keeping the same
functionality.
https://github.com/user-attachments/assets/432b65f1-89d2-4658-ad5e-048921b06a23
P.S. I have removed the user setting for custom debounce delay, because
(one) now it doesn't really make sense to configure that, and (two) the
whole logic is based on the assumption that the fast query will resolve
before the debounced query. A static debounce time makes sure of that.
Configuring it might lead to cases where the fast query resolves after
the debounced query, and we end up only seeing visible viewport
highlights.
Release Notes:
- Improved selection highlight speed.
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>
Staff only for now. We'll work on making this usable for non zed.dev
users later
Release Notes:
- N/A
---------
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
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
Release Notes:
- agent: Replace `bash` tool with `terminal` tool which uses the current
shell
---------
Co-authored-by: Bennet <bennet@zed.dev>
Co-authored-by: Antonio <antonio@zed.dev>
Having a separate rename tool seems to make the agent more likely to use
it compared to having it be part of the code actions tool.
Release Notes:
- Added code action tool and rename tool.
