Previously we'd crash when deserializing a breakpoint whose row number
was out of bounds (could happen if the file was externally modified).
This PR fixes that code to skip such breakpoints.
An alternative would be to clip the deserialized `PointUtf16`, but I
think that would mostly result in nonsensical breakpoints.
Release Notes:
- N/A
To make DAP work over SSH we want to create the binary
at the project level (so we can wrap it in an `ssh` invocation
transparently).
This means not pushing the adapter down into the session, and resolving
more information ahead-of-time.
Co-authored-by: Anthony Eid <hello@anthonyeid.me>
Co-authored-by: Piotr <piotr@zed.dev>
Release Notes:
- N/A
---------
Co-authored-by: Anthony Eid <hello@anthonyeid.me>
Co-authored-by: Piotr <piotr@zed.dev>
Co-authored-by: Piotr Osiewicz <24362066+osiewicz@users.noreply.github.com>
Co-authored-by: Anthony <anthony@zed.dev>
This PR makes a debugger's pane layout persistent across session's that
use the same debug adapter.
Release Notes:
- N/A
---------
Co-authored-by: Piotr Osiewicz <24362066+osiewicz@users.noreply.github.com>
Co-authored-by: Cole Miller <m@cole-miller.net>
Avoids building a whole git2 repository object at the worktree layer
just to watch some additional paths.
- [x] Tidy up names of the various paths
- [x] Tests for worktrees and submodules
Release Notes:
- N/A
This PR fixes a bug when deleting a breakpoint with a (log, conditional,
hit condition) message by removing the message. All breakpoints that
contain that type of message were also deleted.
Release Notes:
- N/A
Fixes a regression introduced in
https://github.com/zed-industries/zed/pull/28377 where the pending hunks
didn't get cleared properly when staging/unstaging hunks remotely. I
didn't add new tests, because the fix was to simplify some code.
Release Notes:
- N/A
Fixes https://github.com/zed-industries/zed/issues/26039
Release Notes:
- Fixed an issue where diffs stopped updating closing and reopening them
after staging hunks.
- Fixed a bug where staging a hunk while the cursor was in a deleted
line would move the cursor erroneously.
---------
Co-authored-by: Cole Miller <m@cole-miller.net>
Co-authored-by: João Marcos <marcospb19@hotmail.com>
The debug console will now show an indicator when it's unopened and
there's unread messages.
`NewSessionModal` attempts to resolve debug configurations before using
the config to start debugging. This allows users to use zed's task
variables in the modal prompt.
I had to invert tasks_ui dependency on debugger_ui so `NewSessionModal`
could get the correct `TaskContexts` by calling tasks_ui functions. A
consequence of this workspace has a new event `ShowAttachModal` that I'm
not a big fan of. @osiewicz if you have time could you please take a
look to see if there's a way around adding the event. I'm open to pair
on it too.
Release Notes:
- N/A
This regressed in #27568, oops.
Release Notes:
- Fixed a bug causing conflicted files in the git panel to jump to the
"Tracked" section as soon as they were staged.
## Description
In https://github.com/zed-industries/zed/pull/27213 the new feature for
setting env variables for LSPs was added but env vars passed from an
instance of `ExtensionLspAdapter` are lost now. This means if an
extension returns any env variable like this:
```rust
zed::Command {
command: some_command,
args: some_args,
env: vec![("A", "value_for_a")],
}
```
The env variable `A` will never be used by `LspStore`. This commit
preserves env variables passed from an instance of
`ExtensionLspAdapter`.
After this change overwriting of env variables
happens in the following order:
```plaintext
shell <- variables from an extension <- variables from settings
```
## How to reproduce
Allow any extension to return a `zed::Command` with environment
variables to Zed. You can use [this
branch](https://github.com/zed-extensions/ruby/pull/48) for the Ruby
extension:
1. Check out the branch and install the dev version of the Ruby
extension.
2. Ensure you have the `solargraph` LSP configured and enabled for the
Ruby extension. This LSP is enabled by default in Zed and in the Ruby
extension.
3. Make sure you don’t have `solargraph` installed in your user gemset.
4. Open any Ruby project, such as [this
one](https://github.com/vitallium/stimulus-lsp-error-zed).
5. Open a Ruby file and wait for the error message about failing to
start `solargraph`. It should look like this or something similar:
```
[2025-04-05T23:17:26+02:00 ERROR project::lsp_store] server stderr: "/Users/vslobodin/.local/share/mise/installs/ruby/3.4.1/lib/ruby/site_ruby/3.4.0/rubygems.rb:262:in 'Gem.find_spec_for_exe': can't find gem solargraph (>= 0.a) with executable solargraph (Gem::GemNotFoundException)\n\tfrom /Users/vslobodin/.local/share/mise/installs/ruby/3.4.1/lib/ruby/site_ruby/3.4.0/rubygems.rb:281:in 'Gem.activate_bin_path'\n"
```
This error occurs because the Ruby extension passes the `GEM_PATH`
environment variable to specify the location of Ruby gems. Without it,
Zed tries to spawn the `solargraph` gem in the user's gemset scope. Ruby
fails to start it because the `solargraph` gem is not installed in the
user gemset but in the extension directory. By setting the `GEM_PATH`
environment variable, Ruby searches additional locations to start the
`solargraph` LSP.
I hope I've described it correctly. Please let me know if you need more
information. Thanks!
Release Notes:
- Fixed the issue where environment variables from `ExtensionLspAdapter`
were lost
This Pull Request updates the default behavior of the substitute (`s`)
command in vim mode to only replace the next match by default, instead
of all, and replace all matches only when the `g` flag is provided,
making it more similar to NeoVim's behavior.
In order to achieve this, the following changes were introduced:
- Update `BufferSearchBar::replace_next` to be a public method, so it
can be called from `Vim::replace_command` .
- Update the `Replacement::parse` to set the `should_replace_all` field
to `false` by default, and only set it to `true` if the `'g'` flag is
present in the query.
- Add support for when the `Replacement.should_replace_all` is set to
`false` in `Vim::replace_command`, so as to have it only replace the
next occurrence instead of all occurrences in the line.
- Introduce `BufferSearchBar::select_first_match` so as to activate the
first match on the line under the cursor.
Closes#24450
Release Notes:
- Improved vim's substitute command so as to only replace the first
match by default, and replace all matches if the `'g'` flag is provided
---------
Co-authored-by: Conrad Irwin <conrad.irwin@gmail.com>
## Summary
### Actions
This PR implements actions that allow a user to "run to cursor" and
"evaluate selected text" while there's an active debug session and
exposes the functionality to the UI as well.
- Run to cursor: Can be accessed by right clicking on the gutter
- Evaluate selected text: Can be accessed by selecting text then right
clicking in the editor
### Bug fixes
I also fixed these bugs as well
- Panic when using debugger: Stop action
- Debugger actions command palette filter not working properly in all
cases
- We stopped displaying the correct label in the session's context menu
when a session was terminated
Release Notes:
- N/A
---------
Co-authored-by: Max Brunsfeld <max@zed.dev>
Co-authored-by: Remco Smits <djsmits12@gmail.com>
Adds actions so you can have customized keybindings for `insert` and
`replace` modes.
And add `shift-enter` as a default for `replace`, this will override the
default setting
`completions.lsp_insert_mode` which is set to `replace_suffix`, which
tries to "smartly"
decide whether to replace or insert based on the surrounding text.
For those who come from VSCode, if you want to mimic their behavior, you
only have to
set `completions.lsp_insert_mode` to `insert`.
If you want `tab` and `enter` to do different things, you need to remap
them, here is
an example:
```jsonc
[
// ...
{
"context": "Editor && showing_completions",
"bindings": {
"enter": "editor::ConfirmCompletionInsert",
"tab": "editor::ConfirmCompletionReplace"
}
},
]
```
Closes#24577
- [x] Make LSP completion insertion mode decision in guest's machine
(host is currently deciding it and not allowing guests to have their own
setting for it)
- [x] Add shift-enter as a hotkey for `replace` by default.
- [x] Test actions.
- [x] Respect the setting being specified per language, instead of using
the "defaults".
- [x] Move `insert_range` of `Completion` to the Lsp variant of
`.source`.
- [x] Fix broken default, forgotten after
https://github.com/zed-industries/zed/pull/27453#pullrequestreview-2736906628,
should be `replace_suffix` and not `insert`.
Release Notes:
- LSP completions: added actions `ConfirmCompletionInsert` and
`ConfirmCompletionReplace` that control how completions are inserted,
these override `completions.lsp_insert_mode`, by default, `shift-enter`
triggers `ConfirmCompletionReplace` which replaces the whole word.
(and any other LSP server in theory, if it exposes any LSP-ext endpoint
for the same)
Closes https://github.com/zed-industries/zed/issues/16160
* adds a way to disable tree-sitter tasks (the ones from the plugins,
enabled by default) with
```json5
"languages": {
"Rust": "tasks": {
"enabled": false
}
}
}
```
language settings
* adds a way to disable LSP tasks (the ones from the rust-analyzer
language server, enabled by default) with
```json5
"lsp": {
"rust-analyzer": {
"enable_lsp_tasks": false,
}
}
```
* adds rust-analyzer tasks into tasks modal and gutter:
<img width="1728" alt="modal"
src="https://github.com/user-attachments/assets/22b9cee1-4ffb-4c9e-b1f1-d01e80e72508"
/>
<img width="396" alt="gutter"
src="https://github.com/user-attachments/assets/bd818079-e247-4332-bdb5-1b7cb1cce768"
/>
Release Notes:
- Added tasks from rust-analyzer
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Piotr Osiewicz <piotr@zed.dev>
fixes issue where:
In a two line python file like so
```
Path()
```
If the user asks for code actions on `Path` and they select (`From
pathlib import path`)
the result they get is
```
Pathfrom pathlib import Path
Path()
```
Instead of
```
from pathlib import Path
Path()
```
This is due to a non-lsp-spec-compliant response from pyright below
```json
{"jsonrpc":"2.0","id":40,"result":[{"title":"from pathlib import Path","edit":{"changes":{"file:///Users/neb/Zed/example-project/pyright-project/main.py":[{"range":{"start":{"line":2,"character":0},"end":{"line":2,"character":4}},"newText":"Path"},{"range":{"start":{"line":2,"character":0},"end":{"line":2,"character":0}},"newText":"from pathlib import Path\n\n\n"}]}},"kind":"quickfix"}]}
```
Release Notes:
- Fixed an issue when using auto-import code actions provided by pyright
(or basedpyright) where the import would be jumbled with the scoped
import resulting in an invalid result
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Anthony Eid <hello@anthonyeid.me>
This PR adds colors to debug panel's session menu that indicate the
state of each respective session. It also adds a close button to each
entry.
green - running
yellow - stopped
red - terminated/ended
Release Notes:
- N/A
There were two bugs that caused the gdb adapter not to work properly,
one on our end and one their end.
The bug on our end was sending `stopOnEntry: null` in our launch request
when stop on entry had no value. I fixed that bug across all dap
adapters
The other bug had to do with python's "great" type system and how we
serialized our unit structs to json; mainly,
`ConfigurationDoneArguments` and `ThreadsArguments`. Gdb seems to follow
a pattern for handling requests where they pass `**args` to a function,
this errors out when the equivalent json is `"arguments": null`.
```py
@capability("supportsConfigurationDoneRequest")
@request("configurationDone", on_dap_thread=True)
def config_done(**args): ### BUG!!
...
```
Release Notes:
- N/A
I wanted this for CONL (https://conl.dev )'s nascent langauge server,
and it seems like most of the support was already wired up on the LSP
side, so this surfaces it into the editor.
Release Notes:
- Added support for the `insert_text_mode` field of completions from the
language server protocol.
Same as `editor::RestartLanguageServer`, now there's an
`editor::StopLanguageServer` action that stops all language servers,
related to the currently opened editor.
Opening another singleton editor with the same language or changing
selections in a multi buffer will bring the servers back up.
Release Notes:
- Added a way to temporarily stop LSP servers
---------
Co-authored-by: Michael Sloan <mgsloan@gmail.com>
Release Notes:
- Fixed a bug where Zed sometimes added multiple redundant FS watchers
when language servers requested to watch paths. This could cause saves
and git operations to fail if Zed exceeded the file descriptor limit.
---------
Co-authored-by: Piotr <piotr@zed.dev>
This adds a "workspace-hack" crate, see
[mozilla's](https://hg.mozilla.org/mozilla-central/file/3a265fdc9f33e5946f0ca0a04af73acd7e6d1a39/build/workspace-hack/Cargo.toml#l7)
for a concise explanation of why this is useful. For us in practice this
means that if I were to run all the tests (`cargo nextest r
--workspace`) and then `cargo r`, all the deps from the previous cargo
command will be reused. Before this PR it would rebuild many deps due to
resolving different sets of features for them. For me this frequently
caused long rebuilds when things "should" already be cached.
To avoid manually maintaining our workspace-hack crate, we will use
[cargo hakari](https://docs.rs/cargo-hakari) to update the build files
when there's a necessary change. I've added a step to CI that checks
whether the workspace-hack crate is up to date, and instructs you to
re-run `script/update-workspace-hack` when it fails.
Finally, to make sure that people can still depend on crates in our
workspace without pulling in all the workspace deps, we use a `[patch]`
section following [hakari's
instructions](https://docs.rs/cargo-hakari/0.9.36/cargo_hakari/patch_directive/index.html)
One possible followup task would be making guppy use our
`rust-toolchain.toml` instead of having to duplicate that list in its
config, I opened an issue for that upstream: guppy-rs/guppy#481.
TODO:
- [x] Fix the extension test failure
- [x] Ensure the dev dependencies aren't being unified by Hakari into
the main dependencies
- [x] Ensure that the remote-server binary continues to not depend on
LibSSL
Release Notes:
- N/A
---------
Co-authored-by: Mikayla <mikayla@zed.dev>
Co-authored-by: Mikayla Maki <mikayla.c.maki@gmail.com>
This PR adds `completions.lsp_insert_mode` and effectively changes the
default from `"replace"` to `"replace_suffix"`, which automatically
detects whether to use the LSP `replace` range instead of `insert`
range.
`"replace_suffix"` was chosen as a default because it's more
conservative than `"replace_subsequence"`, considering that deleting
text is usually faster and less disruptive than having to rewrite a long
replaced word.
Fixes#27197Fixes#23395 (again)
Fixes#4816 (again)
Release Notes:
- Added new setting `completions.lsp_insert_mode` that changes what will
be replaced when an LSP completion is accepted. The default is
`"replace_suffix"`, but it accepts 4 values: `"insert"` for replacing
only the text before the cursor, `"replace"` for replacing the whole
text, `"replace_suffix"` that acts like `"replace"` when the text after
the cursor is a suffix of the completion, and `"replace_subsequence"`
that acts like `"replace"` when the text around your cursor is a
subsequence of the completion (similiar to a fuzzy match). Check [the
documentation](https://zed.dev/docs/configuring-zed#LSP-Insert-Mode) for
more information.
---------
Co-authored-by: João Marcos <marcospb19@hotmail.com>
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
This PR adds passing in `stop_on_entry` to debug configs in debug.json
instead of going through initialization args.
This has two benefits:
1. It's more streamlined to a user since every internal adapter supports
`stop_on_entry` for launch requests and Go's adapter supports it for
attach requests too.
2. It will allow @osiewicz `NewSesssionModal` PR to use this field for
the stop on entry checkbox.
Release Notes:
- N/A
This fixes a bug in #27568 that caused flickering in the git panel's
checkbox state when staging and unstaging entire files. The problem is
that that stage/unstage action first saves the target path (if it's open
as a buffer), and we do a targeted git status scan in response to that
filesystem event, which makes its way to the git panel and causes it to
clear its pending state before the actual stage or unstage has gone
through.
The fix is to not clear the panel's pending state for git repository
events that originated from a targeted scan (i.e. one that was triggered
by FS events for repo paths, as opposed to events inside `.git` which
cause all statuses to be recomputed).
Release Notes:
- N/A
