This PR updates the `/file` command to emit its `SlashCommandEvent`s in
a way that can actually be streamed.
Previously it was buffering up all of the events and then returning them
all at once.
Note that we still don't yet support streaming in the context editor on
`main`, so there won't be any visible changes just yet.
Release Notes:
- N/A
This changes the download logic to not fetch the latest version, but to
fetch the version matching the current version of Zed.
Release Notes:
- Changed the update logic of the SSH remote server to not fetch the
latest version for a current channel, but to fetch the version matching
the current Zed version. If Zed is updated, the server is updated too.
If the server is newer than the Zed version an error will be displayed.
This fixes a debug-only panic when processing filenames. The underflow
that happens in Preview/Stable shouldn't cause any issues (other than
maybe unmarking an entry in the project panel).
/cc @notpeter
Closes #ISSUE
Release Notes:
- N/A
Release Notes:
- Changed the update process of the remote server binary to not attempt
an update if we can detect that the current binary is used by another
process.
- Changed the update process of the remote server binary to mark the
lock file as stale in case the SSH connection of the process that
created the lock file isn't open anymore.
Co-authored-by: Kirill <kirill@zed.dev>
Co-authored-by: Mikayla <mikayla@zed.dev>
Fixes#9896
Release Notes:
- Fixed an issue where clicking on an image inside the project panel
would not re-use an existing image tab
Co-authored-by: Kirill <kirill@zed.dev>
Co-authored-by: Mikayla <mikayla@zed.dev>
This restores all the init behaviour into main again. This means we
never need to call init_ui (and so we can't call it more than once).
Release Notes:
- (Nightly only) fixes a panic when using the cli to open another file
in a running zed.
This PR fixes an issue introduced in
https://github.com/zed-industries/zed/pull/18768 where the element
backgrounds colors for `ElevationIndex::ElevatedSurface` and
`ElevationIndex::Surface` were swapped.
Release Notes:
- N/A
Use `Fs` instead of `std::fs` and do entry existence checks better:
* first, check the worktree entry existence without any FS checks
* then, only for local cases, use `Fs` to check for abs_path existence
of items, in case those came from single-filed worktrees that got closed
and removed.
Remote entries do not get file existence checks, so might try opening
previously removed buffers for now.
Release Notes:
- N/A
This PR fixes a panic that could occur when trying to complete arguments
for the `/delta` slash command.
We were using `unimplemented!()` instead of providing a default no-op
implementation like we do for other slash commands that do not support
completing arguments.
Closes https://github.com/zed-industries/zed/issues/19686.
Release Notes:
- Fixed a panic that could occur when trying to complete arguments with
the `/delta` command.
This pull request does a couple of things:
- In 29c2df73e1, we introduced a safety
guard that prevents this crash from happening again in the future by
returning an error instead of panicking when the payload is too large.
- In 3e7a2e5c30, we introduced chunking
for updates coming from SSH servers (previously, we were sending the
whole changeset and initial set of paths in their entirety).
- In 122b5b4, we introduced a panic hook that sends panics to Axiom.
For posterity, this is how we figured out what the panic was:
```
kubectl logs current-pod-name --previous --namespace=production
```
Release Notes:
- N/A
---------
Co-authored-by: Thorsten <thorsten@zed.dev>
Co-authored-by: Bennet <bennet@zed.dev>
Co-authored-by: Kirill <kirill@zed.dev>
Just making just we also add the other keybinding to open the Remote
Projects dialog and capitalize every "SSH" mention for consistency. Tiny
stuff!
Release Notes:
- N/A
Before this change, we would save the working directory *on the client*
of each shell that was running in a terminal.
While it's technically right, it's wrong in all of these cases where
`working_directory` was used:
- in inline assistant
- when resolving file paths in the terminal output
- when serializing the current working dir and deserializing it on
restart
Release Notes:
- Fixed terminals opened on remote hosts failing to deserialize with an
error message after restarting Zed.
See #12673https://github.com/user-attachments/assets/94079afc-a851-4206-9c9b-4fad3542334e
TODO:
- [x] Make active indent guides work for autofolded directories
- [x] Figure out which theme colors to use
- [x] Fix horizontal scrolling
- [x] Make indent guides easier to click
- [x] Fix selected background flashing when hovering over entry/indent
guide
- [x] Docs
Release Notes:
- Added indent guides to the project panel
This snuck in when Bennet and I were debugging why our connection to the
SSH host would break. We suspected that somewhere something was logging
to STDOUT and, I guess, we changed all `println!` to `eprintln!`.
Now, two weeks later, I'm sitting here, wondering why the version check
doesn't work anymore. The server always reports a version of `""`.
Turns out we take the command's STDOUT and not STDERR, which is correct.
But it also turns out we started to print the version to STDERR, which
breaks the version check.
One-character bug & one-character fix.
Release Notes:
- N/A
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [actions/checkout](https://redirect.github.com/actions/checkout) |
action | digest | `eef6144` -> `11bd719` |
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC4xMjAuMSIsInVwZGF0ZWRJblZlciI6IjM4LjEyMC4xIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6W119-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
This PR updates the `SlashCommand` trait to use a streaming return type.
This change is just at the trait layer. The goal here is to decouple
changing the trait's API while preserving behavior on either side.
The `SlashCommandOutput` type now has two methods for converting two and
from a stream to use in cases where we're not yet doing streaming.
On the `SlashCommand` implementer side, the implements can call
`to_event_stream` to produce a stream of events based off the
`SlashCommandOutput`.
On the slash command consumer side we use
`SlashCommandOutput::from_event_stream` to convert a stream of events
back into a `SlashCommandOutput`.
The `/file` slash command has been updated to emit `SlashCommandEvent`s
directly in order for it to work properly.
Release Notes:
- N/A
---------
Co-authored-by: Max <max@zed.dev>
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [crate-ci/typos](https://redirect.github.com/crate-ci/typos) | action
| pinDigest | -> `8e6a428` |
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC4xMjAuMSIsInVwZGF0ZWRJblZlciI6IjM4LjEyMC4xIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6W119-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [anyhow](https://redirect.github.com/dtolnay/anyhow) |
workspace.dependencies | patch | `1.0.89` -> `1.0.91` |
---
### Release Notes
<details>
<summary>dtolnay/anyhow (anyhow)</summary>
###
[`v1.0.91`](https://redirect.github.com/dtolnay/anyhow/releases/tag/1.0.91)
[Compare
Source](https://redirect.github.com/dtolnay/anyhow/compare/1.0.90...1.0.91)
- Ensure OUT_DIR is left with deterministic contents after build script
execution
([#​388](https://redirect.github.com/dtolnay/anyhow/issues/388))
###
[`v1.0.90`](https://redirect.github.com/dtolnay/anyhow/releases/tag/1.0.90)
[Compare
Source](https://redirect.github.com/dtolnay/anyhow/compare/1.0.89...1.0.90)
- Documentation improvements
</details>
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC4xMjAuMSIsInVwZGF0ZWRJblZlciI6IjM4LjEyMC4xIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6W119-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
Due to leaning towards `musl` builds, unit features for `zstd` and link
it statically too for Zed.
bfe1e34f59/zstd-safe/zstd-sys/build.rs (L260)
shows that `ZSTD_SYS_USE_PKG_CONFIG` env var can be used to return this
behavior.
Release Notes:
- N/A
- Closes: https://github.com/zed-industries/zed/issues/19609
Switches us to using `-latest` tags with Anthropic models instead of
pinning to a specific date version.
See: [Anthropic Model
Docs](https://docs.anthropic.com/en/docs/about-claude/models)
This is a no-op for:
- Claude 3 Opus (`claude-3-opus-20240229`)
- Claude 3 Sonnet (`claude-3-sonnet-20240229`)
- Claude 3 Haiku (`claude-3-haiku-20240307`)
For Claude 3.5 Sonnet this will update us from
`claude-3-5-sonnet-20240620` to `claude-3-5-sonnet-20241022`. We will
also pickup any subsequent model updates automatically when Anthropic
updates the `latest` tag.
This matches the behavior for OpenAI where use `gpt-4o` as the
model_name and not `gpt-4o-2024-08-06`.
This PR adds a new `SlashCommandResult` type alias.
We're going to be changing what slash commands can return in order to
support streaming, so having this type alias in place will make that
switch a bit more neat.
Release Notes:
- N/A
This tackles an issue with us exposing unnecessary env variables in
environment which are not actually needed for tasks themselves (and may
have little utility), yet come into the way of ssh remoting.
/cc @ConradIrwin
Release Notes:
- N/A
Just polishing the UI a bit more. One drawback of this, though, is that
if you _do_ have a big nickname or server name, with this current
solution, you won't be able to see it. Ideally, we should be able to
hover over it and see it in a tooltip, but the `div` still doesn't
support that out of the box.
| Main modal | Modal header |
|--------|--------|
| <img width="1136" alt="Screenshot 2024-10-23 at 12 49 18"
src="https://github.com/user-attachments/assets/ed5f0222-faa1-49bd-b249-2f22497566d8">
| <img width="1136" alt="Screenshot 2024-10-23 at 12 49 23"
src="https://github.com/user-attachments/assets/5a464b12-99e8-4934-aa6a-c9c4c40ea4d4">
|
Release Notes:
- N/A
Improved: Documenation for (un)installing extensions automatically.
Signed-off-by: Tom Zaspel <tom@zaspel.it>
Co-authored-by: Peter Tripp <peter@zed.dev>
Hey team!
I was investigating the new node settings added in #18172, and when
trying to set the node path I noticed that the example settings in
`default.json` use the wrong key for the `node_path` - it should be
`path` instead.
See
[here](19eebcd349/crates/zed/src/main.rs (L488))
for where the setting is used.
Release Notes:
- N/A
Certain files like Rust stdlib ones can be opened by cmd-clicking on
terminal, editor contents, etc.
Those files will not belong to the current worktree, so a fake worktree,
with a single file, invisible (i.e. its dir(s) will not be shown in the
UI such as project panel), will be created on the file opening.
When the file is closed, the worktree is closed and removed along the
way, so those worktrees are considered ephemeral and their ids are not
stored in the database.
This causes issues on reopening such files when they are closed.
The PR makes Zed to fall back to opening the file by abs path when it's
not in the project metadata, but has the abs path stored in history or
in the opened items DB data.
Release Notes:
- Handle external worktree entries [re]open better
This adds the following optional setting:
```json
{
"remote_server": {
"download_on_host": false
}
}
```
Right now, it's **off by default** because I haven't tested it enough.
Release Notes:
- N/A
This PR main relevant change is removing the logic we had inserted for
keyboard nav scroll as that was unreliable; we need to figure out a
better solution still. I'm also removing the visible on hover behavior
for the scrollbar as that was making us lose the click and drag feature
the component has. Lastly, I added a bit of right-margin in the delete
icon button so that's not too crammed with the scrollbar.
Release Notes:
- N/A
This creates a `<binary_path>.lock` file and checks for it whenever
uploading a binary.
Parameters:
- Wait for other instance to finish: 10m
- Mark lockfile as stale and ignore it after: 10m
- When waiting on another process, check every 5seconds
We can tweak all of them.
Ideally we'd have a value in the lockfile, that lets us detect whether
the other process is still there, but I haven't found something stable
yet:
- We don't have a stable PID on the server side when we run multiple
commands
- The `ControlPath` is on the client side
Release Notes:
- N/A
Hello, this PR adds a new view to the LSP servers menu for
displaying an LSP server capabilities.
When I work on LSP stuff, quite often I need to check what capabilities
an LSP server has. Currently there is no built-in way for checking that
in Zed, and I have to use [`LSP
DevTools`](https://lsp-devtools.readthedocs.io) project. LSP DevTools
works OK but it works as a proxy between the client and the server, so
setting it up is not that easy in Zed. Zed already has many goodies for
LSP like tracing and RPC messages, so I thought that a simple view with
server capabilities could be useful too. Thanks!
## Some screenshots:
### Ruby LSP
### New menu entry:
Release Notes:
- N/A
Caps the size of the Supermaven states buffer to 1000 elements.
Previously, the buffer would grow unbounded so for long sessions the
number of states that the Supermaven autocomplete provider maintains can
be quite large. In practice, states that are sufficiently old are so
unlikely to be visited again that we can regenerate the completion.
Thus, we can cap the buffer to 1000 elements.
Release Notes:
- N/A
- Fixes modal closing when using the remote modal folder
- Fixes a bug with local terminals where they could open in / instead of
~
- Fixes a bug where SSH connections would continue running after their
window is closed
- Hides SSH Terminal process details from Zed UI
- Implement `cmd-o` for remote projects
- Implement LanguageServerPromptRequest for remote LSPs
Release Notes:
- N/A
The old links pointed to specific lines that were no longer the correct
lines. Let's skip pointing the reader of the docs to a specific line.
Release Notes:
- N/A
This PR removes an extra slash from the Github link to the upstream
Tree-sitter markdown grammer introduced in #19570 in the cargo-files.
Release Notes:
- N/A
This PR adds some safeguards to ensure that users do not end up with
multiple active billing subscriptions.
We now do the following:
1. When initiating a checkout, we first make sure the user does not
already have an active subscription.
2. When creating subscriptions in response to Stripe events, we ensure
that we don't already have an active subscription.
Release Notes:
- N/A
This PR makes it so that when we apply changes within a branch
buffer—currently just the edits buffer—we save the underlying buffer.
This also fixes an issue where new files created via edits were not
properly flushed to disk.
Release Notes:
- N/A
---------
Co-authored-by: Max <max@zed.dev>
A user commented on this issue to let us know they couldn't reproduce,
which would keep it open for another 6 months. Best we can do is tell
them what to do if they can't repro, which is to close the issue
themselves.
- https://github.com/zed-industries/zed/issues/10671
Release Notes:
- N/A
This contains a bunch of smallish but nasty fixes:
- Heartbeat timer was never reset after first heartbeat
- Use same return value when stderr is closed as when stdout is closed
- Always check proxy process status since it should also be done when we
get to this point (either it died and our task stopped, or our task
stopped and we dropped the process handle and it was killed on drop)
- make error messages less wrongly-specific
Release Notes:
- N/A
Co-authored-by: Bennet <bennet@zed.dev>
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [wasmtime-wasi](https://redirect.github.com/bytecodealliance/wasmtime)
| workspace.dependencies | patch | `24.0.0` -> `24.0.1` |
---
### Release Notes
<details>
<summary>bytecodealliance/wasmtime (wasmtime-wasi)</summary>
###
[`v24.0.1`](https://redirect.github.com/bytecodealliance/wasmtime/releases/tag/v24.0.1)
[Compare
Source](https://redirect.github.com/bytecodealliance/wasmtime/compare/v24.0.0...v24.0.1)
#### 24.0.1
Released 2024-10-09.
##### Fixed
- Fix a runtime crash when combining tail-calls with host imports that
capture a
stack trace or trap.
[GHSA-q8hx-mm92-4wvg](https://redirect.github.com/bytecodealliance/wasmtime/security/advisories/GHSA-q8hx-mm92-4wvg)
- Fix a race condition could lead to WebAssembly control-flow integrity
and type
safety violations.
[GHSA-7qmx-3fpx-r45m](https://redirect.github.com/bytecodealliance/wasmtime/security/advisories/GHSA-7qmx-3fpx-r45m)
</details>
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC4xMjAuMSIsInVwZGF0ZWRJblZlciI6IjM4LjEyMC4xIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6W119-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
This PR exposes the server address (or the nickname, if there is one) on
the title bar and in all modals that have the SSH header. The title bar
tooltip meta description still shows the original server address
(regardless of a nickname existing in this case), though.
<img width="600" alt="Screenshot 2024-10-22 at 10 58 36"
src="https://github.com/user-attachments/assets/64a94d9f-798b-44a4-9dee-6056886535bb">
Release Notes:
- N/A
---------
Co-authored-by: Piotr Osiewicz <24362066+osiewicz@users.noreply.github.com>
We sadly have to change the underlying protocol once again. This will
likely be the last change to the core protocol without correctly
handling older versions. From here on out, we want to get better with
version handling. To do so, we introduce the notion of a string protocol
version to be explicit of when the underlying protocol last changed.
The change also changes the return values of prompts. For now we only
allow User messages from servers to match the current behaviour. We will
change this once #19222 lands which will allow slash commands to insert
user and assistant messages.
Release Notes:
- N/A
This fixes the `ssh` proxy process not being notified when the proxy
process dies. Turns out that the server would have stdout/stderr/stdin
connected to the grand-parent ssh process connected to it and as long as
the server kept running (even once it was daemonized into the
background) the grand-parent ssh process wouldn't exit.
That in turn meant that the Zed client wasn't notified when the proxy
process died.
Release Notes:
- N/A
---------
Co-authored-by: Bennet <bennet@zed.dev>
We can't seem to generate invite links that dumps a user directly into a
specific channel, so just adding a general invite link and then pointing
them to the Windows channel name.
Release Notes:
- N/A
This PR changes the behavior of pressing the `Esc` key on the connection
input. Now, if you hit it, the address inserted into the input won't be
erased. Effectively, escape now only cancels the connection process
instead of doing both (clearing the input _and_ cancelling the
connection).
Release Notes:
- N/A
Co-authored-by: Piotr Osiewicz <24362066+osiewicz@users.noreply.github.com>
Before this change we sometimes showed errors inline, sometimes in
alerts.
Sometimes we closed the window, someimtes we didn't.
Now they always show as prompts and we never close windows.
Co-Authored-By: Mikayla <mikayla@zed.dev>
Release Notes:
- SSH Remoting: Improve error handling
This is a fixup for #19410.
Apparently, `mdbook` requires a reference to the document from the
`SUMMARY.md`. This fixes the 404
(https://zed.dev/docs/languages/jsonnet.html) and also adds the Jsonnet
to the docs' navigation.
Release Notes:
- N/A
Closes#19181
When the keystroke was empty ("") the `ime_key` was converted from
`None` to `Some("")` when `with_simulated_ime` was called. That was
leading to not intentional behavior when an empty keystroke was combined
with `shift-up` in a keybinding `["workspace::SendKeystrokes", "shift-up
"]`.
By adding a `key.is_empty()` we make sure the `ime_key` keeps as `None`.
This was manually tested.
Release Notes:
- Fixed empty keystroke with simulated ime
Signed-off-by: Bruno Calza <brunoangelicalza@gmail.com>
This fixes problems where auto-indent wasn't working correctly for
assistant edits.
Release Notes:
- Fixed a bug where auto-indent didn't work correctly when pasting with
multiple cursors on adjacent lines
Co-authored-by: Marshall <marshall@zed.dev>
- Closes#12515
Before fix:
<img width="1506" alt="Screenshot 2024-10-17 at 09 50 19"
src="https://github.com/user-attachments/assets/250f50cb-0119-4b96-bc9b-7258aa83247c">
After fix:
<img width="1027" alt="Screenshot 2024-10-17 at 09 52 36"
src="https://github.com/user-attachments/assets/c2eb7e4a-3c03-466c-b215-7fcc22eed024">
Testing:
- Manual testing
- Added unit test
Test results, these tests fail on the main branch for my setup as well,
I have docker running but still had some failures:
```
failures:
tests::integration_tests::test_context_collaboration_with_reconnect
tests::integration_tests::test_formatting_buffer
tests::integration_tests::test_fs_operations
tests::integration_tests::test_git_branch_name
tests::integration_tests::test_git_diff_base_change
tests::integration_tests::test_git_status_sync
tests::integration_tests::test_join_after_restart
tests::integration_tests::test_join_call_after_screen_was_shared
tests::integration_tests::test_joining_channels_and_calling_multiple_users_simultaneously
tests::integration_tests::test_leaving_project
tests::integration_tests::test_leaving_worktree_while_opening_buffer
tests::integration_tests::test_local_settings
tests::integration_tests::test_lsp_hover
tests::integration_tests::test_mute_deafen
tests::integration_tests::test_open_buffer_while_getting_definition_pointing_to_it
tests::integration_tests::test_pane_split_left
tests::integration_tests::test_prettier_formatting_buffer
tests::integration_tests::test_preview_tabs
tests::integration_tests::test_project_reconnect
tests::integration_tests::test_project_search
tests::integration_tests::test_project_symbols
tests::integration_tests::test_propagate_saves_and_fs_changes
tests::integration_tests::test_references
tests::integration_tests::test_reloading_buffer_manually
tests::integration_tests::test_right_click_menu_behind_collab_panel
tests::integration_tests::test_room_location
tests::integration_tests::test_room_uniqueness
tests::integration_tests::test_server_restarts
tests::integration_tests::test_unshare_project
tests::notification_tests::test_notifications
tests::random_project_collaboration_tests::test_random_project_collaboration
tests::remote_editing_collaboration_tests::test_sharing_an_ssh_remote_project
test result: FAILED. 156 passed; 32 failed; 0 ignored; 0 measured; 0 filtered out; finished in 100.98s
```
Comments:
I do not have a ton of rust knowledge, so very open to feedback. TYSM
Release Notes:
- Fix Incorrect checkbox placement in Markdown preview
---------
Co-authored-by: Bennet Bo Fenner <bennet@zed.dev>
Before this change, `parse_block` was consuming events that it doesn't
handle. This was fine in its use in `parse_document`, but in its use in
`parse_list` this broke when there is an empty list item, causing it to
consume list end tags / list item starts / etc.
Release Notes:
- Fixed markdown preview rendering of empty list items.
Closes https://github.com/zed-industries/zed/issues/8534
Supersedes https://github.com/zed-industries/zed/pull/16349
Potential concerns:
* we do not follow up to the `/` when looking for `.editorconfig`, only
up to the worktree root.
Seems fine for most of the cases, and the rest should be solved
generically later, as the same issue exists for settings.json
* `fn language` in `AllLanguageSettings` is very hot, called very
frequently during rendering. We accumulate and parse all `.editorconfig`
file contents beforehand, but have to go over globs and match these
against the path given + merge the properties still.
This does not seem to be very bad, but needs more testing and
potentially some extra caching.
Release Notes:
- Added .editorconfig support
---------
Co-authored-by: Ulysse Buonomo <buonomo.ulysse@gmail.com>
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [swatinem/rust-cache](https://redirect.github.com/swatinem/rust-cache)
| action | digest | `23bce25` -> `82a92a6` |
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC4xMjAuMSIsInVwZGF0ZWRJblZlciI6IjM4LjEyMC4xIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6W119-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
Before this change messages could be lost on reconnect, now they will
not be.
Release Notes:
- SSH Remoting: make reconnects smoother
---------
Co-authored-by: Nathan <nathan@zed.dev>
When we insert before some text and then update that same text, we need
to preserve and concatenate the new text associated with both
operations.
Release Notes:
- N/A
This simplifies rendering of excerpt headers and footers, and removes
the need to store a `BlockDisposition` on these boundary blocks. It's a
step toward implementing "replace blocks", which we want to use in the
assistant panel.
We've also cleaned up the way heights are specified for headers and
footers and fixed some visual asymmetries between the "expand upward"
and "expand downward" buttons.
Release Notes:
- N/A
---------
Co-authored-by: Richard <richard@zed.dev>
Hi. While working on https://github.com/zed-industries/zed/pull/19230 I
noticed that some servers send a request to unregistered the
`textDocument/rename` capability. I thought it would be good to handle
that message in Zed:
```plaintext
[2024-10-18T21:25:07+02:00 WARN project::lsp_store] unhandled capability unregistration: Unregistration { id: "biome_rename", method: "textDocument/rename" }
```
So this pull request implements that. Thanks.
Release Notes:
- N/A
Fixes a bug due to the `select!` macro tossing futures that had
partially read messages, causing us to desync our message reading with
the input stream.
Release Notes:
- N/A
---------
Co-authored-by: Conrad Irwin <conrad.irwin@gmail.com>
Co-authored-by: conrad <conrad@zed.dev>
This PR removes the conditional checks around the billing-related
enforcement for LLM completions.
These were just in place to prevent executing any billing code before we
had rolled it out. Now that it is rolled out, we don't need this
conditional execution anymore.
Release Notes:
- N/A
I no longer want to have to keep my ears and eyes open for GitHub
notifications that relate to someone requesting a closed stale issue be
reopened. As a community maintainer, I can get hundreds or even
thousands of notifications a week, and a lot of those are about activity
on closed issues. If everyone following an issue did not react fast
enough (7 days) to keep an issue flagged as `stale` open, let's instruct
them to open new issues, so we are forced to see it during next triage.
Release Notes:
- N/A
This PR adds a basic documentation about the Jsonnet language support.
Release Notes:
- N/A
---------
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
Closes#19362
This pull request includes several updates to the `reqwest_client` crate
and its dependencies. The most important changes involve adding support
for SOCKS proxies, improving error handling for proxy URIs, and adding
tests for proxy functionality.
### Dependency Updates:
*
[`Cargo.toml`](diffhunk://#diff-2e9d962a08321605940b5a657135052fbcef87b5e360662bb527c96d9a615542L394-R401):
Added support for SOCKS proxies in the `reqwest` dependency by including
the `socks` feature.
### Code Improvements:
*
[`crates/reqwest_client/src/reqwest_client.rs`](diffhunk://#diff-8e036b034e987390be2f57373864b75d6983f0cf84e85c43793eb431d13538f3L47-R52):
Improved error handling when parsing proxy URIs by logging errors
instead of directly panicking.
### Testing Enhancements:
*
[`crates/reqwest_client/src/reqwest_client.rs`](diffhunk://#diff-8e036b034e987390be2f57373864b75d6983f0cf84e85c43793eb431d13538f3R274-R317):
Added tests to verify the handling of various proxy URIs, including
valid and invalid cases.
Release Notes:
- N/A
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
|
[actions/upload-artifact](https://redirect.github.com/actions/upload-artifact)
| action | digest | `604373d` -> `b4b15b8` |
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC4xMjAuMSIsInVwZGF0ZWRJblZlciI6IjM4LjEyMC4xIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6W119-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
I suspect that this might have something to do with saving files not
being possible after a while.
I want to merge this and bump nightly.
Release Notes:
- N/A
This PR adds a new `zed_urls` module to the `client` crate.
This module contains functions for constructing URLs to Zed properties,
such as zed.dev.
The URLs produced by this module will respect the server URL set via
settings or the `ZED_SERVER_URL` environment variable. This allows them
to correctly reflect the current environment (such as when testing Zed
against a local collab/zed.dev).
Release Notes:
- N/A
This PR moves the spelling check out of the `check_style` action, which
we can leave for just checking formatting.
We can't use the `crates-ci-typos` action as-is on the macOS runners due
to the absence of `wget`.
Release Notes:
- N/A
This changes the `/workflow` command so that instead of emitting edits
in separate steps, the user is presented with a single tab, with an
editable diff that they can apply to the buffer.
Todo
* Assistant panel
* [x] Show a patch title and a list of changed files in a block
decoration
* [x] Don't store resolved patches as state on Context. Resolve on
demand.
* [ ] Better presentation of patches in the panel
* [ ] Show a spinner while patch is streaming in
* Patches
* [x] Preserve leading whitespace in new text, auto-indent insertions
* [x] Ensure patch title is very short, to fit better in tab
* [x] Improve patch location resolution, prefer skipping whitespace over
skipping `}`
* [x] Ensure patch edits are auto-indented properly
* [ ] Apply `Update` edits via a diff between the old and new text, to
get fine-grained edits.
* Proposed changes editor
* [x] Show patch title in the tab
* [x] Add a toolbar with an "Apply all" button
* [x] Make `open excerpts` open the corresponding location in the base
buffer (https://github.com/zed-industries/zed/pull/18591)
* [x] Add an apply button above every hunk
(https://github.com/zed-industries/zed/pull/18592)
* [x] Expand all diff hunks by default
(https://github.com/zed-industries/zed/pull/18598)
* [x] Fix https://github.com/zed-industries/zed/issues/18589
* [x] Syntax highlighting doesn't work until the buffer is edited
(https://github.com/zed-industries/zed/pull/18648)
* [x] Disable LSP interaction in Proposed Changes editor
(https://github.com/zed-industries/zed/pull/18945)
* [x] No auto-indent? (https://github.com/zed-industries/zed/pull/18984)
* Prompt
* [ ] make sure old_text is unique
Release Notes:
- N/A
---------
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
Co-authored-by: Antonio <antonio@zed.dev>
Co-authored-by: Richard <richard@zed.dev>
Co-authored-by: Marshall <marshall@zed.dev>
Co-authored-by: Nate Butler <iamnbutler@gmail.com>
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
- Closes: https://github.com/zed-industries/zed/issues/19351
- Switch to using the official [typos GitHub Action](https://github.com/crate-ci/typos/blob/master/docs/github-action.md)
- Move the typos check into `actions/check_style`
- Move Squawk Postgres migration check out of `actions/check_style` file into ci.yml
- `actions/check_style` can now be run on stateless/linux runners (previous required self-hosted MacOS runner)
- ci.yml: Split old `style` into checks into those that can run statelessly (linux) and everything else into a new `migration` group which benefit from the full git checkout available on the MacOS runners.
- ci.yml: Move `Check unused dependencies` from style to `linux_tests`
- Add `if: github.repository_owner == 'zed-industries'` to all jobs so they won't try and run on GitHub forks.
Ran into this this morning. At least I suspect I ran into it. In any
case: we need to reset the missed hearbeats to 0 in case we got any
connection activity.
Release Notes:
- N/A
- This reverts the change I made in https://github.com/zed-industries/zed/pull/15535 which set `option_as_meta` to `true` in the default settings.
- `true` is a reasonable default for US Keyboards, but is terrible for many others which rely on `alt+<key>` for totally normal keystroke combinations.
This PR makes it so new subscriptions will have their billing cycle
anchored to the first of the month.
When someone signs up today, they will be billed starting on the first
of next month.
Release Notes:
- N/A
Co-authored-by: Antonio <antontio@zed.dev>
Co-authored-by: Richard <richard@zed.dev>
This fixes a bug that was causing most users to be unable to use the
LLMs via Zed. It was caused by not using pagination and, instead, always
querying the very first page of stripe events.
Note that we're also allowing processing events generated in the last 24
hours (before, this was only 1 hour). I did this so that we can process
the backlog of events that the aforementioned bug was skipping.
Release Notes:
- N/A
This is useful for passing a custom identity file, jump hosts, etc.
Unlike with the v1 feature, we won't support `gh`/`gcloud` ssh wrappers
(yet?). I think the right way of supporting those would be to let
extensions provide remote projects.
Closes#19118
Release Notes:
- SSH remoting: restored ability to set arguments for SSH
This PR cleans up the custom icon with indicator implementation in favor
of `IconWithIndicator`, which we already had. It seems like it isn't
super used still, but it's good to try to enforce some consistency
either way. I checked my changes against the REPL stuff (one instance
where its used) and everything's looking good so far. As far as SSH,
nothing has visually changed; we just have less code for this thing now.
<img width="800" alt="Screenshot 2024-10-17 at 2 15 47 AM"
src="https://github.com/user-attachments/assets/5c146757-501e-4242-b145-a576a8f289b5">
---
Release Notes:
- N/A
The server count was something that existed since the remote development
implementation and we just kept it there without a lot of critical
thinking. However, it doesn't feel like it's particularly useful yet,
which means that, at least for now, we could clean it up more and wait
for further feedback to add it back, if ever requested.
Release Notes:
- N/A
This PR replaces a toast for the system prompt to confirm the action of
removing a server from the remote list. The alert dialog component is
the right choice here as we want to have a modal action that forces
choice. This should make it easier to convert to a nativa alert dialog
in the future, as well as for other platforms.
<img width="800" alt="Screenshot 2024-10-17 at 3 01 41 AM"
src="https://github.com/user-attachments/assets/7bb1210a-54bf-40da-a85a-f269484825a1">
Release Notes:
- N/A
Before this, if no project paths were opened you were in a wierd UI
state where
most things didn't work because the project was ssh, but no
files/folders were open.
Release Notes:
- Fixed error handling when no project paths could be opened
This PR removes the lifetime spending limit that was added in #16780.
We had previously added this as a way to prevent runaway usage, but now
that we have a cap on free usage per month with paid access after that,
we don't need this check anymore.
Release Notes:
- N/A
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [astral-sh/setup-uv](https://redirect.github.com/astral-sh/setup-uv) |
action | pinDigest | -> `f3bcaeb` |
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC4xMjAuMSIsInVwZGF0ZWRJblZlciI6IjM4LjEyMC4xIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6W119-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
|
[tree-sitter-cpp](https://redirect.github.com/tree-sitter/tree-sitter-cpp)
| workspace.dependencies | patch | `0.23.0` -> `0.23.1` |
---
### Release Notes
<details>
<summary>tree-sitter/tree-sitter-cpp (tree-sitter-cpp)</summary>
###
[`v0.23.1`](https://redirect.github.com/tree-sitter/tree-sitter-cpp/compare/v0.23.0...v0.23.1)
[Compare
Source](https://redirect.github.com/tree-sitter/tree-sitter-cpp/compare/v0.23.0...v0.23.1)
</details>
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC4xMTQuMCIsInVwZGF0ZWRJblZlciI6IjM4LjExNC4wIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6W119-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [tree-sitter-c](https://redirect.github.com/tree-sitter/tree-sitter-c)
| workspace.dependencies | patch | `0.23.0` -> `0.23.1` |
---
### Release Notes
<details>
<summary>tree-sitter/tree-sitter-c (tree-sitter-c)</summary>
###
[`v0.23.1`](https://redirect.github.com/tree-sitter/tree-sitter-c/compare/v0.23.0...v0.23.1)
[Compare
Source](https://redirect.github.com/tree-sitter/tree-sitter-c/compare/v0.23.0...v0.23.1)
</details>
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC4xMTQuMCIsInVwZGF0ZWRJblZlciI6IjM4LjExNC4wIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6W119-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
This PR does two things. It fixes some minor inconsistencies in the
protocol. This is mostly about handling JSON RPC notifications correctly
and skipping fields when set to None.
Second part is about improving the rendering of context server commands,
by passing on the description
of the command to the slash command UI and showing the name of the
argument as a CodeLabel.
Release Notes:
- N/A
This PR updates the location where we send the user to subscribe for
more LLM usage to the account page.
Release Notes:
- Updated the URL to the account page when subscribing to LLM usage.
Closes#18705 (comment)
This PR fixes the issue where the Zed window was not displaying
correctly on launch. Now, when Zed is closed in a maximized state, it
will reopen in a maximized state.
On macOS, when a window is created but not yet visible, calling `zoom`
or `toggle_fullscreen` will still affect the hidden window. However,
this behavior is different on Windows, so special handling is required.
Also, since #18705 hasn't been reviewed yet, I'm not sure if this PR
should be merged now or if it should wait until #18705 is reviewed
first.
Release Notes:
- N/A
Before this change we had a race condition bug: if stderr was closed
before the other two sockets, we wouldn't properly detect when the
server died, and not report or retry anything.
That's because we treated a closed stderr as a non-error.
Technically, it isn't an error (closing a connection is okay!), but
until we have a proper shutdown ceremony between all three processes, we
can treat it as an error, because that lets us to detect when the server
is gone.
On the client-side, we also always react to these errors by
reconnecting. Except when we shutdown: there we do a proper shutdown and
won't error on the proxy exit code.
So, this works, even if I wish there was a better way for the server to
communicate to the proxy that it shutdown properly. But I don't want a
fourth socket.
Release Notes:
- N/A
* uses the state that's synced, to fetch the language server name
* uses proper, canonicalized path when creating a remote ssh worktree,
otherwise `~/foo/something` stays unexpanded
Release Notes:
- N/A
This PR makes it so collab will trigger a refresh for a user's LLM token
whenever their subscription changes.
This allows us to proactively push down changes to their subscription.
In order to facilitate this, the Stripe event processing has been moved
from the `api` service to the `collab` service in order to access the
RPC server.
Release Notes:
- N/A
This restores the change from #19193 that I erroneously reverted in
#19234.
I think the bug in #19275 got in my way when testing.
With that bug fixed, the changes in here also work fine.
Release Notes:
- N/A
I've been a bit annoyed by the hover divider rule being extremely bright
compared to other divider rules in the UI. This PR updates their color
to use the regular border color from the current theme instead of the
muted (but still pretty bright) text color.
Apologies for the unsolicited PR (and please feel free to close if it
goes against some other plans / designs you already have in place :).
#### Example screenshot before:
<img width="302" alt="Screenshot 2024-10-15 at 23 29 18"
src="https://github.com/user-attachments/assets/7ea22808-8135-4a46-9457-e670225aebaa">
#### Example screenshot after:
<img width="312" alt="Screenshot 2024-10-15 at 23 28 16"
src="https://github.com/user-attachments/assets/63ac0d02-ae6d-4962-84a2-1fdb95519b15">
***
Release Notes:
- Make the divider rule in LSP hovers more muted
Release Notes:
- Added a new `editor: format selections` action that allows formatting
only the currently selected text via the primary language server.
---------
Co-authored-by: Thorsten Ball <mrnugget@gmail.com>
When the SSH command dies or the server, the channel gets dropped and
the heartbeat method went into an infinite loop causing a hang.
Oversight from yesterday. Fixed now.
Release Notes:
- N/A
Closes#19040
Addresses the problem with annoying error messages on windows (see
comment from SomeoneToIgnore on #18567)
Release Notes:
- Fixed the bug where language servers from PATH would sometimes be
prioritised over the ones from `direnv`
- Stopped running environment loading on windows as it didn't work
anyways due to `SHELL` not being set
This commit adds support for using the physical insert-button. First
click toggles insert mode and subsequent clicks toggle back and forth
between replace and insert mode.
Closes#19224
Release Notes:
- Added support for using the insert button for vim_mode.
Part of https://github.com/zed-industries/zed/issues/19239
Overall, this hardcoding approach has to stop and Zed better show some
notification/modal that proposes to select a primary language server,
when launching with the language that has no such settings.
Release Notes:
- Fixed Astro LSP interactions
Supersedes https://github.com/zed-industries/zed/pull/19166
TODO:
- [x] Update basic zed paths
- [x] update create_state_directory
- [x] Use this with `NodeRuntime`
- [x] Add server settings
- [x] Add an 'open server settings command'
- [x] Make sure it all works
Release Notes:
- Updated the actions `zed::OpenLocalSettings` and `zed::OpenLocalTasks`
to `zed::OpenProjectSettings` and `zed::OpenProjectTasks`.
---------
Co-authored-by: Conrad <conrad@zed.dev>
Co-authored-by: Richard <richard@zed.dev>
This PR refines the SSH modal UI, adjusting spacing and alignment. Via
these changes, I'm also introducing the ability for the `empty_message`
on the `List` component to receive not just a string but any element.
The custom way in which the SSH modal was designed made it feel like
this was needed for proper spacing.
<img width="700" alt="Screenshot 2024-10-16 at 1 20 54 AM"
src="https://github.com/user-attachments/assets/f2e0586b-4c9f-4497-b4cb-e90c8157512b">
Release Notes:
- N/A
This PR makes it so the Storybook loads GPUI with the default features
enabled.
This fixes a panic that would occur when trying to run any of the
stories.
Release Notes:
- N/A
Sometimes, issues are created outside of issue templates (which we don't
prefer, but we can't prevent). This updates our top-ranking issues
script such that it will add `triage` and `admin read` labels to any
issue that is missing a core label, so that we don't miss the issues
when doing the next triage.
Release Notes:
- N/A
when no result found, always display `Search all files`, which is
confused.
Release Notes:
- Fixed an issue where the project search would sometimes show "Search
all files" when there were no results.
---------
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
This does two things.
Important one: it reverts #19193, which lead to our whole process
handling breaking. When the `proxy` process was killed, it apparently
didn't close the stdout/stderr anymore, which meant we would not detect
when it died. (Watching its `status()` in the io loop also didn't work!)
We should figure out how to keep our process handling working before we
make this change in #19193, which sounds reasonable.
Second, less important thing: I think we should treat the process being
killed from a signal as non-zero, as an error.
Release Notes:
- N/A
This improves the heartbeat detection logic. We now treat any other
incoming message from the ssh remote server
as a heartbeat message, meaning that we can detect re-connects earlier.
It also changes the connection handling to await futures detached.
Co-Authored-by: Thorsten <thorsten@zed.dev>
Release Notes:
- N/A
---------
Co-authored-by: Thorsten <thorsten@zed.dev>
Co-authored-by: Antonio <antonio@zed.dev>
TL;DR: Another O(n^2) strikes.
In #19194 we received a report about a 7Mb JSON file that Zed struggles
with. Naturally this file showcased a O(n^2) in line layout; this file
has one long line.
During line layout for Mac we have to convert between UTF-16 and UTF-8
indices in the string, as CoreText works with UTF-16 and Rust strings
are UTF-8. The problem stemmed from the fact that we were re-seeking our
string converter on each glyph, which boils down to: we were reparsing
[0..curr_string_position] bytes up to full length of the string, which
is the O(n^2) in question. This PR changes this behaviour to reuse the
Index Converter if the position we're seeking to is not yet reached.
Basically, we're treating the converter as forward iterator and we try
to seek with the same iterator, if possible.
Where previously you could not even open the file in OP (within
reasonable time frame, I waited for 40 seconds before giving up), now
you can do it in.. slightly over a second. The best part is: the
experience is still not ideal. Typing in the buffer is sluggish. Still,
this is a start.
Release Notes:
- Mac: Improved performance with very long lines
This PR changes the SSH modal design so its more keyboard
navigation-friendly and adds the server nickname feature.
Release Notes:
- N/A
---------
Co-authored-by: Danilo <danilo@zed.dev>
Co-authored-by: Danilo Leal <67129314+danilo-leal@users.noreply.github.com>
This also puts the entire state of `StripeBilling` behind a `RwLock`.
When fetching the existing prices and meters, or when inserting new
ones, we acquire a write lock and hold it until the Stripe request
completes. This prevents two concurrent calls to `get_or_insert_price`
from inserting the same data twice.
Creating a new meter/price is unusual, so in practice we'll acquire a
read lock most of the time.
/cc @rtfeldman @maxdeviant
Release Notes:
- N/A
Closes#19051Closes#19182
#### How to reproduce this crash:
1. Open any file and input some ASCII characters.
2. Replace these characters with `你好`.
3. Press `backspace`.
4. Crash.
https://github.com/user-attachments/assets/ea5c5340-29a5-42c8-98c5-6e60770445a4
The issue lies with the `prefix_offset` introduced in #18858. After the
buffer is modified, this value is not always valid and may fall within a
`char boundary`, which results in a crash.
Release Notes:
- Fixed Supermaven crashing on deleting non-ASCII text
remote: Disable ControlPersist for master ssh connection
`ControlPersist=yes` combined with `ControlMaster=yes` silently forces
`ForkAfterAuthentication=yes` (even when the user has explicitly set it
to `no` - reported upstream in [0]) - and the latter makes the ssh
subprocess disappear, which makes us think that the connection died
(This is only an issue for people who have `ControlPersist=yes` in their
`ssh_config`, and perhaps the answer is "if that option breaks things,
don't use that option?" - but it's an option that makes sense _most_ of
the time, it's just in this edge-case of "creating an ssh connection
with -N and expecting the process to stay in the foreground" where it
_must_ be set to no)
I think the alternative approach is to tell people "if you want to use
persistent connections, have a separate ~/.ssh/config entry for
servername (to ssh into) and servername-no-persist (to zed into)", which
is possible, but ugh. Kind of a messy situation >.<
Tests:
- Before: Connections to my server result in "Failed to connect: ." (The
error message is attempting to show stderr, but stderr is empty)
- After: Connections to my server work reliably
[0] https://bugzilla.mindrot.org/show_bug.cgi?id=3743
Release Notes:
- N/A
- Closes#16998
This PR resolves issues with the /file and /diagnostics commands in the
assistant panel, which previously failed to display the contents of a
directory when searching for a folder instead of using the arrow button.
- Changed the format in `project.rs` (located at
`crates/project/src/project.rs`) to use `std::path::MAIN_SEPARATOR` for
cross-platform compatibility, which resolves errors encountered on
Windows that originally used the format `format!("{}/", ...)`.
Release Notes:
- N/A
Similar to e2647025ac, this adds a `regex`
option to `vim::Search` command to allow disabling regex search.
Release Notes:
- Added `regex` option to `vim::Search` command to allow disabling regex
search by default in the keymap. Example usage:
```yaml
{
"context": "VimControl && !menu",
"bindings": {
"/": ["vim::Search", { "regex": false }],
}
}
```
This will allow us to compile debug builds of the remote-server for a
different architecture than the one we are developing on.
This also adds a CI step for building our remote server with minimal
dependencies.
Release Notes:
- N/A
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [bytes](https://redirect.github.com/tokio-rs/bytes) |
workspace.dependencies | patch | `1.7.1` -> `1.7.2` |
---
### Release Notes
<details>
<summary>tokio-rs/bytes (bytes)</summary>
###
[`v1.7.2`](https://redirect.github.com/tokio-rs/bytes/blob/HEAD/CHANGELOG.md#172-September-17-2024)
[Compare
Source](https://redirect.github.com/tokio-rs/bytes/compare/v1.7.1...v1.7.2)
##### Fixed
- Fix default impl of `Buf::{get_int, get_int_le}`
([#​732](https://redirect.github.com/tokio-rs/bytes/issues/732))
##### Documented
- Fix double spaces in comments and doc comments
([#​731](https://redirect.github.com/tokio-rs/bytes/issues/731))
##### Internal changes
- Ensure BytesMut::advance reduces capacity
([#​728](https://redirect.github.com/tokio-rs/bytes/issues/728))
</details>
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC45Ny4wIiwidXBkYXRlZEluVmVyIjoiMzguMTE1LjEiLCJ0YXJnZXRCcmFuY2giOiJtYWluIiwibGFiZWxzIjpbXX0=-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
Closes#19131Closes#19039
fixes the broken auto-updater.
I had the bright idea of using streams as the most common unit of data
transfer. Unfortunately, streams are not re-usable. So HTTP redirects
that have a stream body (like our remote server and auto update
downloads), don't redirect, as they can't reuse the stream. This PR
fixes the problem and simplifies the AsyncBody implementation now that
we're not using Isahc.
Release Notes:
- N/A
This PR adjusts the billing logic to not write any records to
`billing_events` if:
- The user is staff, as we don't want to bill staff members
- Billing is disabled (we currently enable billing based on the presence
of the Stripe API key)
Release Notes:
- N/A
This PR makes the `StripeBilling` object long-lived so that we can make
better use of the cached data on it.
We now hold it on the `AppState` and spawn a background task to
initialize the cache on startup.
Release Notes:
- N/A
Co-authored-by: Richard <richard@zed.dev>
When setting a remote ssh project path starting with ~, Zed would fail
to cd into such project's directory when opening a new terminal.
Release Notes:
- N/A
---------
Co-authored-by: Thorsten Ball <mrnugget@gmail.com>
This PR adds usage-based billing for LLM interactions in the Assistant.
Release Notes:
- N/A
---------
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Antonio <antonio@zed.dev>
Co-authored-by: Richard <richard@zed.dev>
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
collab: Remove dependency on X11
I'm not sure if this is the best solution (perhaps pulling
`LanguageName` into a separate `language_types` crate would be
better...?) - but it massively reduces build time / dependencies / size
and means that the collab server no longer requires X11 libraries to be
installed.
tl;dr: `telemetry_events` requires the `language` crate, and the
language crate requires a whole ton of extra stuff. Since
telemetry_events only uses `language` for a single type definition
(`LanguageName`, aka `String`), we can cut all of these out by using the
base `String` type (This doesn't seem too terrible, given that all other
telemetry fields are using basic datatypes like String as opposed to
more strongly-typed variants).
FYI the dependency tree for "why does collab need X11 libraries??" looks
like this:
```
collab
\- telemetry_events
\- language
|- gpui
|- fuzzy
| \- gpui
|- git
| \- gpui
|- lsp
| |- gpui
| \- release_channel
| \- gpui
|- settings
| |- fs
| | \- gpui
| \- gpui
|- task
| \- gpui
\- theme
\- gpui
```
Release Notes:
- N/A
This PR adds support to the assistant for display billing-related
errors.
Pulling this out of #19081 to make it easier to cherry-pick.
Release Notes:
- N/A
Co-authored-by: Antonio <antonio@zed.dev>
Co-authored-by: Richard <richard@zed.dev>
terminal: Improve default locale handling
* Use `LANG` instead of `LC_ALL` (`LC_ALL` is the highest priority which
will override any other end-user settings; when that isn't set things
fall back to separate `LC_*` variables; and when those aren't set things
fall back to `LANG`). [0]
* Only set `LANG` for our child if necessary (if it already exists in
the parent, then the child will inherit that, no need for us to do
anything)
[0]
https://pubs.opengroup.org/onlinepubs/9699919799/basedefs/V1_chap08.html#tag_08_02
Tested cases:
- `unset LANG ; cargo run`: locale inside zed's terminal is set to
`en_US.UTF-8`
- `export LANG=en_GB.UTF-8 ; cargo run`: locale inside zed's terminal is
set to `en_GB.UTF-8`
Release Notes:
- Use the system locale in the terminal instead of forcing `en_US.UTF-8`
This fixes two things:
- Go-to-def to absolute paths (i.e. opening stdlib files) multiple times
(opening, dropping, and re-opening worktrees)
- Re-opening abs paths from the file picker history that were added
there by go-to-def
Release Notes:
- N/A
---------
Co-authored-by: Bennet <bennet@zed.dev>
Currently terminal.cursor_shape uses `underline` and `cursor_shape` uses
`underscore`.
This standardizes them so they use the same settings value.
I think `underline` is the more common term and it matches the
terminology used by VSCode, Alacritty, iTerm, etc.
Note the protobuf enum `CursorShape::CursorUnderscore` remains
unchanged.
See also:
- https://github.com/zed-industries/zed/pull/18530
- https://github.com/zed-industries/zed/pull/17572
Release Notes:
- Settings: rename one `cursor_shape` from `underscore` to `underline`
(breaking change).
This is a bit of a personal thing, but it's been bugging me for a while
now that the search options are sticky whenever I use `/` in Vim mode.
This change makes it so that the options are reset with each new `/`.
That means you can, for example, use `v` to create a visual selection,
then hit `*` to search for that (which activates a bunch of search
options), but then continue with `/` to get a normal search.
Release Notes:
- Changed `/` in Vim mode to always reset the search options in the
search bar back to regex-only. That means using `*` (in normal or visual
mode) still works with its options, but the next `/` will reset the
search options. That makes it much closer to how `/` behaves in Vim.
- The App Shortcuts in macOS System Settings does not work for Zed since the menu items titles were not set.
- Previously you could set a shortcut for `Zoom`.
- This add support for `Window->Zoom` as well.
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [wasmtime](https://redirect.github.com/bytecodealliance/wasmtime) |
workspace.dependencies | patch | `24.0.0` -> `24.0.1` |
### GitHub Vulnerability Alerts
####
[CVE-2024-47763](https://redirect.github.com/bytecodealliance/wasmtime/security/advisories/GHSA-q8hx-mm92-4wvg)
### Impact
Wasmtime's implementation of WebAssembly tail calls combined with stack
traces can result in a runtime crash in certain WebAssembly modules. The
runtime crash may be undefined behavior if Wasmtime was compiled with
Rust 1.80 or prior. The runtime crash is a deterministic process abort
when Wasmtime is compiled with Rust 1.81 and later.
[WebAssembly tail
calls](https://redirect.github.com/webassembly/tail-call) are a proposal
which relatively recently reached stage 4 in the [standardization
process](https://redirect.github.com/WebAssembly/proposals/). Wasmtime
first enabled support for tail calls by default [in Wasmtime
21.0.0](https://redirect.github.com/bytecodealliance/wasmtime/pull/8540),
although that release contained a bug where it was only on-by-default
for some configurations. In [Wasmtime
22.0.0](https://redirect.github.com/bytecodealliance/wasmtime/pull/8682)
tail calls were enabled by default for all configurations.
The specific crash happens when an exported function in a WebAssembly
module (or component) performs a `return_call` (or
`return_call_indirect` or `return_call_ref`) to an imported host
function which captures a stack trace (for example, the host function
raises a trap). In this situation, the stack-walking code previously
assumed there was always at least one WebAssembly frame on the stack but
with tail calls that is no longer true. With the tail-call proposal it's
possible to have an entry trampoline appear as if it directly called the
exit trampoline. This situation triggers an internal assert in the
stack-walking code which raises a Rust `panic!()`.
When Wasmtime is compiled with Rust versions 1.80 and prior this means
that an `extern "C"` function in Rust is raising a `panic!()`. This is
technically undefined behavior and typically manifests as a process
abort when the unwinder fails to unwind Cranelift-generated frames. When
Wasmtime is compiled with Rust versions 1.81 and later this panic
becomes a deterministic process abort.
Overall the impact of this issue is that this is a denial-of-service
vector where a malicious WebAssembly module or component can cause the
host to crash. There is no other impact at this time other than
availability of a service as the result of the crash is always a crash
and no more.
This issue was discovered by routine fuzzing performed by the Wasmtime
project via Google's OSS-Fuzz infrastructure. We have no evidence that
it has ever been exploited by an attacker in the wild.
### Patches
All versions of Wasmtime which have tail calls enabled by default have
been patched:
* 21.0.x - patched in 21.0.2
* 22.0.x - patched in 22.0.1
* 23.0.x - patched in 23.0.3
* 24.0.x - patched in 24.0.1
* 25.0.x - patched in 25.0.2
Wasmtime versions from 12.0.x (the first release with experimental tail
call support) to 20.0.x (the last release with tail-calls
off-by-default) have support for tail calls but the support is disabled
by default. These versions are not affected in their default
configurations, but users who explicitly enabled tail call support will
need to either disable tail call support or upgrade to a patched version
of Wasmtime.
### Workarounds
The main workaround for this issue is to disable tail support for tail
calls in Wasmtime, for example with
[`Config::wasm_tail_call(false)`](https://docs.rs/wasmtime/latest/wasmtime/struct.Config.html#method.wasm_tail_call).
Users are otherwise encouraged to upgrade to patched versions.
### References
* [Wasmtime's initial implementation of tail
calls](https://redirect.github.com/bytecodealliance/wasmtime/pull/6774)
* [Enabling of tail calls in
21.0.0](https://redirect.github.com/bytecodealliance/wasmtime/pull/8540)
* [Fully enabling tail calls in
22.0.0](https://redirect.github.com/bytecodealliance/wasmtime/pull/8682)
* [The WebAssembly's `tail-call`
proposal](https://redirect.github.com/webassembly/tail-call)
####
[CVE-2024-47813](https://redirect.github.com/bytecodealliance/wasmtime/security/advisories/GHSA-7qmx-3fpx-r45m)
### Impact
Under certain concurrent event orderings, a `wasmtime::Engine`'s
internal type registry was susceptible to double-unregistration bugs due
to a race condition, leading to panics and potentially type registry
corruption. That registry corruption could, following an additional and
particular sequence of concurrent events, lead to violations of
WebAssembly's control-flow integrity (CFI) and type safety. Users that
do not use `wasmtime::Engine` across multiple threads are not affected.
Users that only create new modules across threads over time are
additionally not affected.
Reproducing this bug requires creating and dropping multiple type
instances (such as `wasmtime::FuncType` or `wasmtime::ArrayType`)
concurrently on multiple threads, where all types are associated with
the same `wasmtime::Engine`. **Wasm guests cannot trigger this bug.**
See the "References" section below for a list of Wasmtime types-related
APIs that are affected.
Wasmtime maintains an internal registry of types within a
`wasmtime::Engine` and an engine is shareable across threads. Types can
be created and referenced through creation of a `wasmtime::Module`,
creation of `wasmtime::FuncType`, or a number of other APIs where the
host creates a function (see "References" below). Each of these cases
interacts with an engine to deduplicate type information and manage type
indices that are used to implement type checks in WebAssembly's
`call_indirect` function, for example. This bug is a race condition in
this management where the internal type registry could be corrupted to
trigger an assert or contain invalid state.
Wasmtime's internal representation of a type has individual types (e.g.
one-per-host-function) maintain a registration count of how many time
it's been used. Types additionally have state within an engine behind a
read-write lock such as lookup/deduplication information. The race here
is a time-of-check versus time-of-use (TOCTOU) bug where one thread
atomically decrements a type entry's registration count, observes zero
registrations, and then acquires a lock in order to unregister that
entry. However, between when this first thread observed the
zero-registration count and when it acquires that lock, another thread
could perform the following sequence of events: re-register another copy
of the type, which deduplicates to that same entry, resurrecting it and
incrementing its registration count; then drop the type and decrement
its registration count; observe that the registration count is now zero;
acquire the type registry lock; and finally unregister the type. Now,
when the original thread finally acquires the lock and unregisters the
entry, it is the second time this entry has been unregistered.
| Thread A | Thread B |
|-----------------------------------|--------------------------------|
| `acquire(type registry lock)` | |
| | `decref(E) --> 0` |
| | `block_on(type registry lock)` |
| `register(E') == incref(E) --> 1` | |
| `release(type registry lock)` | |
| `decref(E) --> 0` | |
| `acquire(type registry lock)` | |
| `unregister(E)` | |
| `release(type registry lock)` | |
| | `acquire(type registry lock)` |
| | `unregister(E)` |
This double-unregistration could then lead to a WebAssembly CFI
violation under the following conditions: a new WebAssembly module `X`
was loaded into the engine before the second, buggy unregistration
occurs; `X` defined a function type `F` that was allocated in the same
type registry slot where the original entry was allocated; the second,
buggy unregistration incorrectly unregistered `F`; another new
WebAssembly module `Y` was loaded into the engine; `Y` defined a
function type `G`, different from `F`, but which is also allocated in
the same type registry slot; a `funcref` of type `G` is created, either
by the host or by Wasm; that `funcref` is passed to a WebAssembly
instance of module `X`; that instance performs a `call_indirect` to that
`funcref`; the `call_indirect`'s dynamic type check, which preserves
CFI, could incorrectly pass in this case, because `F` and `G` were
assigned the same type registry slot. This would, ultimately, allow
calling a function with too many, too few, or wrongly-typed arguments,
violating CFI and type safety.
We were not able to reproduce this CFI violation in a vanilla Wasmtime
build, although it remains theoretically possible. However, by modifying
Wasmtime's source code to make losing the races described above more
likely (by disabling certain assertions, inserting panic catches, and
adding retry loops in a few places if we did *not* lose the race) we
were able to incorrectly get a `funcref` to pass a type check that it
should have failed, which would allow the CFI violation.
### Patches
This bug was originally introduced in Wasmtime 19's development of the
WebAssembly GC proposal. This bug affects users who are not using the GC
proposal, however, and affects Wasmtime in its default configuration
even when the GC proposal is disabled. Wasmtime users using 19.0.0 and
after are all affected by this issue. We have released the following
Wasmtime versions, all of which have a fix for this bug:
* 21.0.2
* 22.0.1
* 23.0.3
* 24.0.1
* 25.0.2
### Workarounds
If your application creates and drops Wasmtime types on multiple threads
concurrently, there are no known workarounds. Users are encouraged to
upgrade to a patched release.
### References
The following APIs create or drop types, and therefore are affected by
this race condition if performed on multiple threads concurrently and
are all associated with the same `wasmtime::Engine`:
*
[`wasmtime::FuncType::new`](https://docs.rs/wasmtime/latest/wasmtime/struct.FuncType.html#method.new)
* Also reachable from creation of
[`wasmtime::Func`](https://docs.rs/wasmtime/latest/wasmtime/struct.Func.html)
* Also reachable from
[`wasmtime::Linker::func_*`](https://docs.rs/wasmtime/latest/wasmtime/struct.Linker.html#method.func_new)
*
[`wasmtime::ArrayType::new`](https://docs.rs/wasmtime/latest/wasmtime/struct.ArrayType.html#method.new)
*
[`wasmtime::StructType::new`](https://docs.rs/wasmtime/latest/wasmtime/struct.StructType.html#method.new)
*
[`wasmtime::Func::ty`](https://docs.rs/wasmtime/latest/wasmtime/struct.Func.html#method.ty)
*
[`wasmtime::Global::ty`](https://docs.rs/wasmtime/latest/wasmtime/struct.Global.html#method.ty)
*
[`wasmtime::Table::ty`](https://docs.rs/wasmtime/latest/wasmtime/struct.Table.html#method.ty)
*
[`wasmtime::Extern::ty`](https://docs.rs/wasmtime/latest/wasmtime/struct.Extern.html#method.ty)
*
[`wasmtime::Export::ty`](https://docs.rs/wasmtime/latest/wasmtime/struct.Export.html#method.ty)
*
[`wasmtime::UnknownImportError::ty`](https://docs.rs/wasmtime/latest/wasmtime/struct.UnknownImportError.html#method.ty)
*
[`wasmtime::ImportType::ty`](https://docs.rs/wasmtime/latest/wasmtime/struct.ImportType.html#method.ty)
*
[`wasmtime::ExportType::ty`](https://docs.rs/wasmtime/latest/wasmtime/struct.ExportType.html#method.ty)
*
[`wasmtime::Val::ty`](https://docs.rs/wasmtime/latest/wasmtime/struct.Val.html#method.ty)
*
[`wasmtime::Ref::ty`](https://docs.rs/wasmtime/latest/wasmtime/struct.Ref.html#method.ty)
*
[`wasmtime::AnyRef::ty`](https://docs.rs/wasmtime/latest/wasmtime/struct.AnyRef.html#method.ty)
*
[`wasmtime::EqRef::ty`](https://docs.rs/wasmtime/latest/wasmtime/struct.EqRef.html#method.ty)
*
[`wasmtime::ArrayRef::ty`](https://docs.rs/wasmtime/latest/wasmtime/struct.ArrayRef.html#method.ty)
*
[`wasmtime::StructRef::ty`](https://docs.rs/wasmtime/latest/wasmtime/struct.StructRef.html#method.ty)
* Dropping a
[`wasmtime::FuncType`](https://docs.rs/wasmtime/latest/wasmtime/struct.FuncType.html)
* Dropping a
[`wasmtime::ArrayType`](https://docs.rs/wasmtime/latest/wasmtime/struct.ArrayType.html)
* Dropping a
[`wasmtime::StructType`](https://docs.rs/wasmtime/latest/wasmtime/struct.StructType.html)
* Dropping a
[`wasmtime::ExternType`](https://docs.rs/wasmtime/latest/wasmtime/struct.ExternType.html)
* Dropping a
[`wasmtime::GlobalType`](https://docs.rs/wasmtime/latest/wasmtime/struct.GlobalType.html)
* Dropping a
[`wasmtime::TableType`](https://docs.rs/wasmtime/latest/wasmtime/struct.TableType.html)
* Dropping a
[`wasmtime::ValType`](https://docs.rs/wasmtime/latest/wasmtime/struct.ValType.html)
* Dropping a
[`wasmtime::RefType`](https://docs.rs/wasmtime/latest/wasmtime/struct.RefType.html)
* Dropping a
[`wasmtime::HeapType`](https://docs.rs/wasmtime/latest/wasmtime/struct.HeapType.html)
* Dropping a
[`wasmtime::UnknownImportError`](https://docs.rs/wasmtime/latest/wasmtime/struct.UnknownImportError.html)
* Dropping a
[`wasmtime::Linker`](https://docs.rs/wasmtime/latest/wasmtime/struct.Linker.html)
The change which introduced this bug was
[#​7969](https://redirect.github.com/bytecodealliance/wasmtime/pull/7969)
---
### Release Notes
<details>
<summary>bytecodealliance/wasmtime (wasmtime)</summary>
###
[`v24.0.1`](https://redirect.github.com/bytecodealliance/wasmtime/releases/tag/v24.0.1)
[Compare
Source](https://redirect.github.com/bytecodealliance/wasmtime/compare/v24.0.0...v24.0.1)
#### 24.0.1
Released 2024-10-09.
##### Fixed
- Fix a runtime crash when combining tail-calls with host imports that
capture a
stack trace or trap.
[GHSA-q8hx-mm92-4wvg](https://redirect.github.com/bytecodealliance/wasmtime/security/advisories/GHSA-q8hx-mm92-4wvg)
- Fix a race condition could lead to WebAssembly control-flow integrity
and type
safety violations.
[GHSA-7qmx-3fpx-r45m](https://redirect.github.com/bytecodealliance/wasmtime/security/advisories/GHSA-7qmx-3fpx-r45m)
</details>
---
### Configuration
📅 **Schedule**: Branch creation - "" in timezone America/New_York,
Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC4xMTQuMCIsInVwZGF0ZWRJblZlciI6IjM4LjExNC4wIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6W119-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
As Zed instantly shows completion items in the completion menu, and the
resolve will cause the details to appear, flickering.
We can safely resolve the `documentation`, `additionalTextEdits` and
`command` fields, the rest should be resolved eagerly for now.
Release Notes:
- Fixed completion menu rendering
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
|
[actions/upload-artifact](https://redirect.github.com/actions/upload-artifact)
| action | digest | `5076954` -> `604373d` |
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC4xMTQuMCIsInVwZGF0ZWRJblZlciI6IjM4LjExNC4wIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6W119-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
Track the cursor offset before biasing in the Supermaven completion
provider to better determine if the text should be suggested. The
underlying issue here is due to the way anchor biasing works, the
completion provider is not able to determine if a given suggestion's
cursor location no longer exists as it is always coalesced to a correct
location (specifically, the end of the line).
This change updates that logic so the offset is stored independently of
the buffer so it can be used to represent a location that may not exist
in the buffer anymore to represent locations that have been deleted.
The net effect is that suggestions can be backspaced much more cleanly
with Supermaven.
Release Notes:
- Improves https://github.com/zed-industries/zed/issues/17981 to prevent
suggesting completions based on out-of-date cursor locations.
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [ashpd](https://redirect.github.com/bilelmoussaoui/ashpd) |
workspace.dependencies | patch | `0.9.1` -> `0.9.2` |
---
### Release Notes
<details>
<summary>bilelmoussaoui/ashpd (ashpd)</summary>
###
[`v0.9.2`](https://redirect.github.com/bilelmoussaoui/ashpd/releases/tag/0.9.2)
[Compare
Source](https://redirect.github.com/bilelmoussaoui/ashpd/compare/0.9.1...0.9.2)
#### What's Changed
- [desktop: Make trait SessionPortal
public](0d2dad594e)
- [lib: Add Pid
type](96b27e7069)
- [desktop/game_mode: Use i32 for
pid](336917a4ed)
- [desktop/device: Use Pid type for
pids](c05b3c17f8)
- [flatpak: Use Pid type for
pids](55a6ea0c9d)
- [is_sandboxed: Don't unwrap OnceCell
set](5d3cb41707)
</details>
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC4xMTQuMCIsInVwZGF0ZWRJblZlciI6IjM4LjExNC4wIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6W119-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [proc-macro2](https://redirect.github.com/dtolnay/proc-macro2) |
dependencies | patch | `1.0.86` -> `1.0.87` |
---
### Release Notes
<details>
<summary>dtolnay/proc-macro2 (proc-macro2)</summary>
###
[`v1.0.87`](https://redirect.github.com/dtolnay/proc-macro2/releases/tag/1.0.87)
[Compare
Source](https://redirect.github.com/dtolnay/proc-macro2/compare/1.0.86...1.0.87)
- Check valid punctuation character in `Punct::new`
([#​470](https://redirect.github.com/dtolnay/proc-macro2/issues/470))
</details>
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC4xMTQuMCIsInVwZGF0ZWRJblZlciI6IjM4LjExNC4wIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6W119-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [ipc-channel](https://redirect.github.com/servo/ipc-channel) |
dependencies | patch | `0.18.2` -> `0.18.3` |
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC45Ny4wIiwidXBkYXRlZEluVmVyIjoiMzguOTcuMCIsInRhcmdldEJyYW5jaCI6Im1haW4iLCJsYWJlbHMiOltdfQ==-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
|
[async-compression](https://redirect.github.com/Nullus157/async-compression)
| workspace.dependencies | patch | `0.4.12` -> `0.4.13` |
---
### Release Notes
<details>
<summary>Nullus157/async-compression (async-compression)</summary>
###
[`v0.4.13`](https://redirect.github.com/Nullus157/async-compression/blob/HEAD/CHANGELOG.md#0413---2024-10-02)
[Compare
Source](https://redirect.github.com/Nullus157/async-compression/compare/v0.4.12...v0.4.13)
##### Feature
- Update `brotli` dependency to to `7`.
</details>
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC45Ny4wIiwidXBkYXRlZEluVmVyIjoiMzguOTcuMCIsInRhcmdldEJyYW5jaCI6Im1haW4iLCJsYWJlbHMiOltdfQ==-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [emojis](https://redirect.github.com/rossmacarthur/emojis) |
workspace.dependencies | patch | `0.6.3` -> `0.6.4` |
---
### Release Notes
<details>
<summary>rossmacarthur/emojis (emojis)</summary>
###
[`v0.6.4`](https://redirect.github.com/rossmacarthur/emojis/compare/0.6.3...0.6.4)
[Compare
Source](https://redirect.github.com/rossmacarthur/emojis/compare/0.6.3...0.6.4)
</details>
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC45Ny4wIiwidXBkYXRlZEluVmVyIjoiMzguOTcuMCIsInRhcmdldEJyYW5jaCI6Im1haW4iLCJsYWJlbHMiOltdfQ==-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
- Closes#18610
This PR addresses the same issue as PR #18578. After a full day of
research and testing, I believe I’ve found the best solution to resolve
this issue. With this PR, the window creation behavior on Windows
becomes more consistent with macOS:
- When `params.show` is `true`: The window is created and immediately
displayed.
- When `params.show` is `false`: The window is created but remains
hidden until the first call to `activate_window`.
As I mentioned in #18578, `winit` creates hidden windows by setting the
window's `exstyle` to `WS_EX_NOACTIVATE | WS_EX_TRANSPARENT |
WS_EX_LAYERED | WS_EX_TOOLWINDOW`, which is different from the method
used in this PR. Here, the window is created with normal parameters, but
we do not call `ShowWindow` so the window is not shown.
I'm not sure why `winit` doesn't use a smilliar approach like this PR to
create hidden windows. My guess is that `winit` is creating this hidden
window to function as a "DispatchWindow" — serving a purpose similar to
`WindowsPlatform` in `zed`. To ensure the window stays hidden even if
`ShowWindow` is called, they use the `exstyle` approach.
With the method used in this PR, my initial tests haven't revealed any
issues.
Release Notes:
- N/A
[terminal] Consider "main.cs(20,5)" to be a single clickable word
First, adding unit tests for the regexes because I'm not certain how
these regexes are _intended_ to work, and unit tests work nicely as
demonstrations of intended behaviour.
The comment string, and the regex itself, seem to imply that
"main.cs(20,5)" is supposed be a single "word" (for the purposes of
being clicked on)... but the regex doesn't actually work like that. This
PR makes it work :)
(I don't know _why_ "word with an optional `(\d+,\d+)` on the end"
doesn't match the full string, while "word with a required `(\d+,\d+)`
on the end" _does_ match the full string - aren't regexes supposed to
match as much as possible, so it should take the optional extra whenever
the extra exists? Either way, "word with a required (\d+,\d+), or word
by itself" has the correct behaviour, as demonstrated by the unit test)
Release Notes:
- N/A
Closes#7417
Release Notes:
- Added basic support for Alacritty's [vi
mode](https://github.com/alacritty/alacritty/blob/master/docs/features.md#vi-mode)
to the built-in terminal (which is using Alacritty under the hood.) The
vi mode can be activated with `ctrl-shift-space` and then supports some
basic motions to navigate through the terminal's scrollback buffer.
## Details
Leverages existing selection functionality from mouse_drag and the
ViMotion API of alacritty to add basic vi motions in the terminal.
Please note, this is only basic functionality (move, select, and yank to
system clipboard) and not a fully functional vim environment (e.g.
search, configurable keybindings, and paste). I figured this would be an
interim solution to the long term, more fleshed out, solution proposed
by @mrnugget.
Ctrl+Shift+Space to enter Vi mode while in the terminal (Same default
binding in alacritty)
* `Open Excerpts` command always opens the locations in the base buffer
* LSP features like document-highlights, go-to-def, and inlay hints work
correctly in branch buffers
* Other LSP features like completions, code actions, and rename are
disabled in branch buffers
Release Notes:
- N/A
This PR fixes some issues with our previous approach to synching LLM
usage over to Stripe.
We now have a separate LLM access price in Stripe that is a marker price
to allow us to create the initial subscription with that as its
subscription item
We then dynamically set the LLM usage price during the reconciliation
sync based on the usage for the current month.
Release Notes:
- N/A
---------
Co-authored-by: Antonio <antonio@zed.dev>
Co-authored-by: Richard <richard@zed.dev>
This PR makes the `has_llm_subscription` and
`max_monthly_spend_in_cents` fields in the `LlmTokenClaims` required.
This change will be safe to deploy in ~45 minutes.
Release Notes:
- N/A
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [actions/checkout](https://redirect.github.com/actions/checkout) |
action | digest | `692973e` -> `eef6144` |
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC4xMTQuMCIsInVwZGF0ZWRJblZlciI6IjM4LjExNC4wIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6W119-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [clap](https://redirect.github.com/clap-rs/clap) |
workspace.dependencies | patch | `4.5.19` -> `4.5.20` |
---
### Release Notes
<details>
<summary>clap-rs/clap (clap)</summary>
###
[`v4.5.20`](https://redirect.github.com/clap-rs/clap/blob/HEAD/CHANGELOG.md#4520---2024-10-08)
[Compare
Source](https://redirect.github.com/clap-rs/clap/compare/v4.5.19...v4.5.20)
##### Features
- *(unstable)* Add `CommandExt`
</details>
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC4xMTQuMCIsInVwZGF0ZWRJblZlciI6IjM4LjExNC4wIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6W119-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
|
[cloudflare/wrangler-action](https://redirect.github.com/cloudflare/wrangler-action)
| action | digest | `168bc28` -> `9681c29` |
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC4xMTQuMCIsInVwZGF0ZWRJblZlciI6IjM4LjExNC4wIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6W119-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
This PR adds a new `billing_preferences` table.
Right now there is a single preference: the maximum monthly spend for
LLM usage.
Release Notes:
- N/A
---------
Co-authored-by: Richard <richard@zed.dev>
Reworks the way tasks are stored, accessed and synchronized in the
`project`.
Now both collab and ssh remote projects use the same TaskStorage kind to
get the task context from the remote host, and worktree task templates
are synchronized along with other worktree settings.
Release Notes:
- Adds ssh support to tasks, improves collab-remote projects' tasks sync
This PR renames the `MONTHLY_SPENDING_LIMIT` constant to
`FREE_TIER_MONTHLY_SPENDING_LIMIT` to clarify it.
This will help distinguish it from the user's specified limit on their
paid monthly spending.
Release Notes:
- N/A
This PR adds a new `Cents` type that can be used to represent a monetary
value in cents.
This cuts down on the primitive obsession we were using when dealing
with money in the billing code.
Release Notes:
- N/A
Instead of wrapping the search term with `\<...\>`, enable the
`WHOLE_WORD` search option.
The advantage of the search option is that it can be toggled with one
click/key press (alt+w by default), and it doesn't require regex mode.
Release Notes:
- Vim mode's whole word search now uses the search bar's "Match whole
words" option, instead of wrapping the search term with `\<...\>`. This
allows easier toggling of whole-word search, and it also works without
enabling the regex mode.
Closes#18722
- Replace the `@escape` capture name with `@string.escape` for escape
sequences in Go, Python, Regex, Racket, Ruby, and Scheme.
- Rust
- Add syntax highlighting for escape sequences. Close#18722
- Fix the issue where `@punctuation.delimiter` is being overwritten by
`@operator`.
- Add the period (".") to `@punctuation.delimiter`.
Release Notes:
- N/A
We have a lot of data in Clickhouse. This column was used when migrating
the events dataset between analytics databases and has no purpose today.
Naive maths: 257,170,993 editor event rows * 1 byte per boolean =
257,170,993 bytes, or ~0.24 GB
I'll drop the column after deploying a new collab.
Going forward, I'd like to remove more data that we never touch, to try
to keep things more focused. We should discuss some TTL at some point.
Release Notes:
- N/A
This ensures that we only ever reconnect to a running server and not
spawn a new server with no state.
This avoids the problem of the server process crashing, `proxy`
reconnecting, starting a new server, and the user getting errors like
"unknown buffer id: ...".
Release Notes:
- N/A
---------
Co-authored-by: Bennet Bo Fenner <bennet@zed.dev>
Refactor telemetry request into separate method to make it easier to
override in a fork.
Release Notes:
- N/A
---------
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
After https://github.com/rust-lang/rust-analyzer/pull/18167 and certain
people who type and complete rapidly, it turned out that we have not
waited for `completionItem/resolve` to finish before applying the
completion results.
Release Notes:
- Fixed completion items applied improperly on fast typing
Do not always close current window in SshConnectionModal; only do so
when the window was spawned from ssh modal. Assign unique IDs to "Open
folder" buttons
Closes #ISSUE
Release Notes:
- N/A
This fixes the problem of a `Project` sometimes not being dropped when
closing the single, last window of Zed.
Turns out, it wasn't get dropped for the following reason:
1. `editor::Editor` held a reference to project
2. The macOS `input_handler` on the `Window` held a reference to that
`Editor`
3. The AppKit window (and its input handler) get dropped asynchronously
(in the code in this diff), after the window is closed.
4. After the window is closed and no `cx.update()` calls are made
anymore, `flush_effects` is not called anymore.
5. But `flush_effects` is where we dropped entities that don't have any
more references.
In short: we dropped `Editor`, which held a reference to `Project`, out
of band, `flush_effects` wasn't called anymore, and thus the `Project`
wasn't dropped.
cc @ConradIrwin @bennetbo since we talked about this.
Release Notes:
- N/A
Co-authored-by: Antonio <antonio@zed.dev>
This PR updates the telemetry events sent to collab to use
`Content-Type: application/json` instead of `Content-Type: text/plain`.
The POST bodies are JSON, so `application/json` is the correct MIME
type.
I suspect the `text/plain` is a remnant from when the events were still
going through Vercel.
Release Notes:
- N/A
This PR makes the `github_user_login` field required in the
`LlmTokenClaims`.
We previously added this in
https://github.com/zed-industries/zed/pull/16316 and made it optional
for backwards-compatibility.
It's been more than long enough for all of the previous LLM tokens to
have expired, so we can now make the field required.
Release Notes:
- N/A
This PR reworks our existing billing code in preparation for charging
based on LLM usage.
We aren't yet exercising the new billing-related code outside of
development.
There are some noteworthy changes for our existing LLM usage tracking:
- A new `monthly_usages` table has been added for tracking usage
per-user, per-model, per-month
- The per-month usage measures have been removed, in favor of the
`monthly_usages` table
- All of the per-month metrics in the Clickhouse rows have been changed
from a rolling 30-day window to a calendar month
Release Notes:
- N/A
---------
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Richard <richard@zed.dev>
Co-authored-by: Max <max@zed.dev>
This PR updates the `worktree` crate to depend on `rpc` with the
`test-support` feature flag when running tests.
This fixes an issue I was seeing locally when trying to run tests in the
`worktree` crate:
```
λ cargo test -p worktree -- test_repository_subfolder_git_status
Compiling worktree v0.1.0 (/Users/maxdeviant/projects/zed/crates/worktree)
error[E0432]: unresolved import `rpc::AnyProtoClient`
--> crates/worktree/src/worktree.rs:39:18
|
39 | use rpc::{proto, AnyProtoClient};
| ^^^^^^^^^^^^^^ no `AnyProtoClient` in the root
For more information about this error, try `rustc --explain E0432`.
error: could not compile `worktree` (lib test) due to 1 previous error
```
Release Notes:
- N/A
This does two things:
- Prevent feature unification
- Sign the remote-server binary with the same entitlements we use for
Zed because we saw this in crash report:
Crashed Thread: 4 Dispatch queue: com.apple.root.user-initiated-qos
Exception Type: EXC_BAD_ACCESS (SIGKILL (Code Signature Invalid))
Exception Codes: UNKNOWN_0x32 at 0x0000000103636644
Exception Codes: 0x0000000000000032, 0x0000000103636644
Termination Reason: Namespace CODESIGNING, Code 2 Invalid Page
VM Region Info: 0x103636644 is in 0x103634000-0x103638000; bytes after
start: 9796 bytes before end: 6587
REGION TYPE START - END [ VSIZE] PRT/MAX SHRMOD REGION DETAIL
VM_ALLOCATE 103630000-103634000 [ 16K] r--/rwx SM=ZER
---> VM_ALLOCATE 103634000-103638000 [ 16K] r-x/rwx SM=COW
VM_ALLOCATE 103638000-103640000 [ 32K] r--/rwx SM=ZER
Which sounds a lot like codesigning/jit/entitlements stuff.
Release Notes:
- N/A
Co-authored-by: Piotr <piotr@zed.dev>
Co-authored-by: Bennet <bennet@zed.dev>
As @maan2003 noted in #18473, we should warn the user if direnv call
fails
Release Notes:
- Show a notice in the activity indicator if an error occurs while
loading the shell environment
This PR drops the `cache_creation_input_tokens_this_month ` and
`cache_read_input_tokens_this_month ` columns from the `usages` table in
the LLM database.
We mistakenly added these in #18834, but these aren't necessary due to
the structure of the `usages` table. We weren't actually using these
columns anywhere.
Release Notes:
- N/A
This PR extends the LLM usage tracking to support tracking usage for
cache writes and reads for Anthropic models.
Release Notes:
- N/A
---------
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Antonio <antonio@zed.dev>
This PR adds a temporary measure to prevent deploying collab to
production, while we investigate some issues stemming from the HTTP
client change.
Release Notes:
- N/A
Previously, the connection process would be cancelled after 10 seconds,
even if the connection was established successfully but the user was
still typing in a password.
We know recognize when the user is prompted for a password, and cancel
the timeout task.
Co-Authored-by: Thorsten <thorsten@zed.dev>
Release Notes:
- N/A
---------
Co-authored-by: Thorsten <thorsten@zed.dev>
To detect connection timeouts we ping the remote server every X seconds
and attempt to reconnect if the server failed to respond.
Next up is showing some feedback in the UI to make this visible to the
user, and stop reconnecting after X amount of retries.
Release Notes:
- N/A
---------
Co-authored-by: Thorsten <thorsten@zed.dev>
Closes#18261
This makes sure that we find external formatters in the project
environment.
TODO:
- [x] Use a different type for the triplet of `(buffer_handle,
buffer_path, buffer_env)`. Something like `FormattableBuffer`.
- [x] Test this!!
Release Notes:
- Fixed external formatters not being found, even when they were
available in the `$PATH` of a project.
---------
Co-authored-by: Bennet <bennet@zed.dev>
Similar to https://github.com/zed-industries/zed/pull/18690 &
https://github.com/zed-industries/zed/pull/18695, this PR enables
required docs for `ui` and does some cleanup.
Changes:
- Enables the `deny(missing_docs)` crate-wide.
- Adds `allow(missing_docs)` on many modules until folks pick them up to
document them
- Documents some modules (all in `ui/src/styles`)
- Crate root-level organization: Traits move to `traits`, other misc
organization
- Cleaned out a bunch of unused code.
Note: I'd like to remove `utils/format_distance` but the assistant panel
uses it. To move it over to use the `time_format` crate we may need to
update it to use `time` instead of `chrono`. Needs more investigation.
Release Notes:
- N/A
This PR qualifies a call to `RangeExt::overlaps` to avoid some confusion
in rust-analyzer not being able to distinguish between
`RangeExt::overlaps` and `AnchorRangeExt::overlaps` and producing
phantom diagnostics.
We may also want to consider renaming the method on `AnchorRangeExt` to
disambiguate them.
Release Notes:
- N/A
This PR adds a bit more metadata for assistant logging.
Release Notes:
- Assistant: Added `language_name` and `model_provider` fields to
telemetry events.
---------
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
Co-authored-by: Max <max@zed.dev>
This PR makes the `report_assistant_event` method take an
`AssistantEvent` struct instead of all of the struct fields as
individual parameters.
Release Notes:
- N/A
Release Notes:
- Added Runnable for C main function
This tags can then be used in tasks, for example:
```json
[
{
"label": "Run ${ZED_STEM}",
"command": "gcc",
"args": [
"$ZED_FILE",
"-o",
"${ZED_DIRNAME}/${ZED_STEM}.out",
"&&",
"${ZED_DIRNAME}/${ZED_STEM}.out"
],
"tags": ["c-main"]
}
]
```
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [parking](https://redirect.github.com/smol-rs/parking) | dependencies
| patch | `2.2.0` -> `2.2.1` |
---
### Release Notes
<details>
<summary>smol-rs/parking (parking)</summary>
###
[`v2.2.1`](https://redirect.github.com/smol-rs/parking/blob/HEAD/CHANGELOG.md#Version-221)
[Compare
Source](https://redirect.github.com/smol-rs/parking/compare/v2.2.0...v2.2.1)
- Specify the reason for using `parking` in the docs.
([#​25](https://redirect.github.com/smol-rs/parking/issues/25))
</details>
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC45Ny4wIiwidXBkYXRlZEluVmVyIjoiMzguOTcuMCIsInRhcmdldEJyYW5jaCI6Im1haW4iLCJsYWJlbHMiOltdfQ==-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
Release Notes:
- Fixed tab switcher icons not respecting the `tabs.git_status` setting.
Fixes an issue mentioned in
https://github.com/zed-industries/zed/pull/17115#issuecomment-2378966170
- file icons in the tab switcher weren't colored according to git
status, even if `tabs.git_status` was set to true.
I used a similar approach I saw in other places of the project to get
the project entry and its git status, but maybe we could move the
coloring logic entirely to `tab_icon()`? Wouldn't this break anything?
---------
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
Taffy maintains a mapping of NodeId <-> Context anyways (and does the
lookup), so it's redundant for us to store it separately. Tl;dr: we get
rid of one map and one map lookup per layout request.
Release Notes:
- N/A
Again. https://github.com/zed-industries/zed/pull/4070
Let's see how it goes this time around. The only thing that might've
been related to that revert on our Slack was about crashing in collab
panel.
Release Notes:
- N/A
This PR streamlines the branch creation from the branch selector when
searching for a branch that does not exist.
The branch selector will show the available branches, as it does today:
<img width="576" alt="Screenshot 2024-10-03 at 4 01 25 PM"
src="https://github.com/user-attachments/assets/e1904f5b-4aad-4f88-901d-ab9422ec18bb">
When entering the name of a branch that does not exist, the picker will
be populated with an entry to create a new branch:
<img width="570" alt="Screenshot 2024-10-03 at 4 01 37 PM"
src="https://github.com/user-attachments/assets/07f8d12c-9422-4fd8-a6dc-ae450e297a13">
Selecting that entry will create the branch and switch to it.
Release Notes:
- Streamlined creating a new branch from the branch selector.
This PR updates the color swatches added in #18665 to use a predefined
`rounding` value instead of a literal value.
The underlying values are the same, but we don't want to diverge from
our design system.
Release Notes:
- N/A
Closes#11991
Release Notes:
- Added support for color swatches for language server completions.
<img width="502" alt="Screenshot 2024-10-02 at 19 02 22"
src="https://github.com/user-attachments/assets/57e85492-3760-461a-9b17-a846dc40576b">
<img width="534" alt="Screenshot 2024-10-02 at 19 02 48"
src="https://github.com/user-attachments/assets/713ac41c-16f0-4ad3-9103-d2c9b3fa8b2e">
This implementation is mostly a port of the VSCode version of the
ColorExtractor. It seems reasonable the we should support _at least_
what VSCode does for detecting color swatches from LSP completions.
This implementation could definitely be better perf-wise by writing a
dedicated color parser. I also think it would be neat if, in the future,
Zed handled _more_ color formats — especially wide-gamut colors.
There are a few differences to the regexes in the VSCode implementation
but mainly so simplify the implementation :
- The hex vs rgb/hsl regexes were split into two parts
- The rgb/hsl regexes allow 3 or 4 color components whether hsla/rgba or
not and the parsing implementation accepts/rejects colors as needed
---------
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
This PR extracts the Protocol Buffers support into an extension.
Release Notes:
- Removed built-in support for Protocol Buffers, in favor of making it
available as an extension. The Protocol Buffers extension will be
suggested for download when you open a `.proto` file.
This PR does some spring cleaning on the `theme` crate:
- Removed two unused stories and the story dep
- Removed the `one` theme family (from the `theme` crate, not the app),
this is now `zed_default_themes`.
- This will hopefully remove some confusion caused by this theme we
started in rust but didn't end up using
- Removed `theme::prelude` (it just re-exported scale colors, which we
don't use outside `theme`)
- Removed completely unused `zed_pro` themes (we started on these during
the gpui2 port and didn't finish them.)
Release Notes:
- N/A
---------
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [python](https://redirect.github.com/containerbase/python-prebuild) |
dependencies | patch | `3.12.6` -> `3.12.7` |
---
### Release Notes
<details>
<summary>containerbase/python-prebuild (python)</summary>
###
[`v3.12.7`](https://redirect.github.com/containerbase/python-prebuild/releases/tag/3.12.7)
[Compare
Source](https://redirect.github.com/containerbase/python-prebuild/compare/3.12.6...3.12.7)
##### Bug Fixes
- **deps:** update dependency python to v3.12.7
</details>
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC45Ny4wIiwidXBkYXRlZEluVmVyIjoiMzguOTcuMCIsInRhcmdldEJyYW5jaCI6Im1haW4iLCJsYWJlbHMiOltdfQ==-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [serde_json](https://redirect.github.com/serde-rs/json) | dependencies
| patch | `1.0.127` -> `1.0.128` |
| [serde_json](https://redirect.github.com/serde-rs/json) |
workspace.dependencies | patch | `1.0.127` -> `1.0.128` |
---
### Release Notes
<details>
<summary>serde-rs/json (serde_json)</summary>
###
[`v1.0.128`](https://redirect.github.com/serde-rs/json/releases/tag/1.0.128)
[Compare
Source](https://redirect.github.com/serde-rs/json/compare/1.0.127...1.0.128)
- Support serializing maps containing 128-bit integer keys to
serde_json::Value
([#​1188](https://redirect.github.com/serde-rs/json/issues/1188),
thanks [@​Mrreadiness](https://redirect.github.com/Mrreadiness))
</details>
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about these
updates again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC45Ny4wIiwidXBkYXRlZEluVmVyIjoiMzguOTcuMCIsInRhcmdldEJyYW5jaCI6Im1haW4iLCJsYWJlbHMiOltdfQ==-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
This PR enables required documentation for the `theme` crate starts on
documenting it.
The end goal is to have all meaningful documentation in the crate filled
out – However I'm not sure that just adding `#![deny(missing_docs)]` to
the whole crate is the right approach.
I don't know that having 200+ "The color of the _ color" field docs is
useful however–In the short term I've excluded some of the modules that
contain structs with a ton of fields (`colors, `status`, etc.) until we
decide what the right solution here is.
Next steps are to clean up the crate, removing unused modules or those
with low usage in favor of other approaches.
Changes in this PR:
- Enable the `deny(missing_docs)` lint for the `theme` crate
- Start documenting a subset of the crate.
- Enable `#![allow(missing_docs)]` for some modules.
Release Notes:
- N/A
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [thiserror](https://redirect.github.com/dtolnay/thiserror) |
workspace.dependencies | patch | `1.0.63` -> `1.0.64` |
---
### Release Notes
<details>
<summary>dtolnay/thiserror (thiserror)</summary>
###
[`v1.0.64`](https://redirect.github.com/dtolnay/thiserror/releases/tag/1.0.64)
[Compare
Source](https://redirect.github.com/dtolnay/thiserror/compare/1.0.63...1.0.64)
- Exclude derived impls from coverage instrumentation
([#​322](https://redirect.github.com/dtolnay/thiserror/issues/322),
thanks [@​oxalica](https://redirect.github.com/oxalica))
</details>
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC45Ny4wIiwidXBkYXRlZEluVmVyIjoiMzguOTcuMCIsInRhcmdldEJyYW5jaCI6Im1haW4iLCJsYWJlbHMiOltdfQ==-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
The indicator turns yellow when ssh client is trying to reconnect. Note
that the state tracking is probably not ideal (we'll see how it pans out
once we start dog-fooding), but at the very least "green=good" should be
a decent mental model for now.
Release Notes:
- N/A
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [clap](https://redirect.github.com/clap-rs/clap) |
workspace.dependencies | patch | `4.5.18` -> `4.5.19` |
---
### Release Notes
<details>
<summary>clap-rs/clap (clap)</summary>
###
[`v4.5.19`](https://redirect.github.com/clap-rs/clap/blob/HEAD/CHANGELOG.md#4519---2024-10-01)
[Compare
Source](https://redirect.github.com/clap-rs/clap/compare/v4.5.18...v4.5.19)
##### Internal
- Update dependencies
</details>
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC45Ny4wIiwidXBkYXRlZEluVmVyIjoiMzguOTcuMCIsInRhcmdldEJyYW5jaCI6Im1haW4iLCJsYWJlbHMiOltdfQ==-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
This PR reverts the changes to the Clickhouse event rows that were
included in https://github.com/zed-industries/zed/pull/18414.
The changes don't seem to be correct, as they make the row structs
differ from the underlying table schema.
Release Notes:
- N/A
REplace isahc with ureq everywhere gpui is used.
This should allow us to make http requests without libssl; and avoid a
long-tail of panics caused by ishac.
Release Notes:
- (potentially breaking change) updated our http client
---------
Co-authored-by: Mikayla <mikayla@zed.dev>
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
|
[cloudflare/wrangler-action](https://redirect.github.com/cloudflare/wrangler-action)
| action | digest | `f84a562` -> `168bc28` |
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC45Ny4wIiwidXBkYXRlZEluVmVyIjoiMzguOTcuMCIsInRhcmdldEJyYW5jaCI6Im1haW4iLCJsYWJlbHMiOltdfQ==-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
This PR does not change how things work for settings, but lays the
ground work for the future functionality.
After this change, Zed is prepared to sync more than just
`settings.json` files from local worktree and user config.
* ssh tasks
Part of this work is to streamline the task sync mechanism.
Instead of having an extra set of requests to fetch the task contents
from the server (as remote-via-collab does now and does not cover all
sync cases), we want to reuse the existing mechanism for synchronizing
user and local settings.
* editorconfig
Part of the task is to sync .editorconfig file changes to everyone which
involves sending and storing those configs.
Both ssh (and remove-over-collab) .zed/tasks.json and .editorconfig
files behave similar to .zed/settings.json local files: they belong to a
certain path in a certain worktree; may update over time, changing Zed's
functionality; can be merged hierarchically.
Settings sync follows the same "config file changed -> send to watchers
-> parse and merge locally and on watchers" path that's needed for both
new kinds of files, ergo the messaging layer is extended to send more
types of settings for future watch & parse and merge impls to follow.
Release Notes:
- N/A
This PR fixes an issue where the proposed changes editor would not have
any syntax highlighting until a modification was made.
When creating the branch buffer we reparse the buffer to rebuild the
syntax map.
Release Notes:
- N/A
Closes#17771
Reverts zed-industries/zed#17496
This PR turns out to need more work than I thought when I merged it.
Release Notes:
- Linux: Fix a bug where the cursor would be the wrong size on Wayland
This PR mostly makes all of the search bar icon buttons all squared and
adjusts the spacing between them, as well as the additional input that
appears when you toggle the "Replace all" action.
<img width="900" alt="Screenshot 2024-10-02 at 6 08 30 PM"
src="https://github.com/user-attachments/assets/86d50a3b-94bd-4c6a-822e-5f7f7b2e2707">
---
Release Notes:
- N/A
I noticed a few places where we were storing `&'static str`s in
`static`s instead of `const`s.
This PR updates them to use `const`.
Release Notes:
- N/A
- Closes: #18335
Update linux.md with a workaround for the
```
crypto/fips/fips.c:154: OpenSSL internal error: FATAL FIPS SELFTEST FAILURE
```
error when using bundled libssl and libcrypto.
Co-authored-by: Peter Tripp <peter@zed.dev>
This PR adds a note to the docs encouraging folks to fork the
`zed-industries/extensions` repo to a personal GitHub account rather
than a GitHub organization, as this makes life easier for everyone.
Release Notes:
- N/A
This PR adds a description constant in most of the slash command files
so that both the editor _and_ footer pickers use the same string. In
terms of copywriting, I did some tweaking to reduce the longer ones a
bit. Also standardized them all to use sentence case, as opposed to each
instance using a different convention. The editor picker needs more
work, though, given the arguments and descriptions are being cut at the
moment. This should happen in a follow-up!
<img width="900" alt="Screenshot 2024-10-01 at 7 25 19 PM"
src="https://github.com/user-attachments/assets/e8759eff-0de9-4a4d-a026-366d85507b3c">
---
Release Notes:
- N/A
---------
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
Additionally, mark context menu entry as disabled when the action would
fail (untitled buffer, collab sessions).
Supersedes #18584
Release Notes:
- Fixed "Reveal in Finder/File Manager", "Copy Path", "Copy Relative
Path" and "Copy file location" actions not working with multibuffers.
We introduced a memory leak in #18572, which meant that `Drop` was never
called on `SshRemoteConnection`, meaning that the ssh process kept
running
Co-Authored-by: Thorsten <thorsten@zed.dev>
Release Notes:
- N/A
---------
Co-authored-by: Thorsten <thorsten@zed.dev>
Fixed [Configuring
Languages](https://zed.dev/docs/configuring-languages) docs using
boolean value for `format_on_save` option although it accepts string
values of `"on"` or `"off"`
Details:
The documentation on [configuring
languages](https://zed.dev/docs/configuring-languages) states the use of
boolean values for the `format_on_save` option although the
[configuration
reference](https://zed.dev/docs/configuring-zed#format-on-save) only
allows the usage of string values `"on"` or `"off"`. In fact using
boolean values will not work and won't translate to `on` or `off`
Release Notes:
- N/A
Also, fix visual bug when pressing escape with a non-empty selection in
a deleted text block.
Release Notes:
- N/A
Co-authored-by: Antonio <antonio@zed.dev>
Closes#18531
This PR limits the range of values that can be set for `FontWeight`.
Since any value less than 1.0 or greater than 999.9 causes Zed to crash
on Windows, I’ve restricted `FontWeight` to this range.
I could apply this constraint only on Windows, but considering the
documentation at https://zed.dev/docs/configuring-zed#buffer-font-weight
indicates that `FontWeight` should be between 100 and 900, I thought it
might be a good idea to apply this restriction in the settings.
Release Notes:
- Changed `ui_font_weight` and `buffer_font_weight` settings to require
values to be between `100` and `950` (inclusive).
---------
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
This PR makes it so the proposed changes editor works with the workspace
navigation history.
This allows for easily navigating back to the proposed changes editor
after opening one of the excerpts into the base buffer.
Release Notes:
- N/A
This PR reverts the changes introduced via #18164. As shown in the video
below, once you `hide` the app, there is essentially no way to bring it
back. I must emphasize that the window logic on Windows is entirely
different from macOS. On macOS, when you `hide` an app, its icon always
remains visible in the dock, and you can always bring the hidden app
back by clicking that icon. However, on Windows, there is no such
mechanism—the app is literally hidden.
I think the `hide` feature should be macOS-only.
https://github.com/user-attachments/assets/65c8a007-eedb-4444-9499-787b50f2d1e9
Release Notes:
- N/A
This restructures the code in `remote` so that it's easier to replace
the current SSH connection with a new one in case of
disconnects/reconnects.
Right now, it successfully reconnects, BUT we're still missing the big
piece on the server-side: keeping the server process alive and
reconnecting to the same process that keeps the project-state.
Release Notes:
- N/A
---------
Co-authored-by: Bennet <bennet@zed.dev>
Closes #14089, #14416, #15970, #17230, #18485
Release Notes:
- Fixed some cases where Linux X11 mouse scrolling doesn't work at all
(#14089, ##15970, #17230)
- Fixed handling of switching between Linux X11 devices used for
scrolling (#14416, #18485)
Change details:
Also includes the commit from PR #18317 so I don't have to deal with
merge conflicts.
* Now uses valuator info from slave pointers rather than master. This
hopefully fixes remaining cases where scrolling is fully
broken. https://github.com/zed-industries/zed/issues/14089,
https://github.com/zed-industries/zed/issues/15970,
https://github.com/zed-industries/zed/issues/17230
* Per-device recording of "last scroll position" used to calculate
deltas. This meant that swithing scroll devices would cause a sudden
jump of scroll position, often to the beginning or end of the
file (https://github.com/zed-industries/zed/issues/14416).
* Re-queries device metadata when devices change, so that newly
plugged in devices will work, and re-use of device-ids don't use old
metadata with a new device.
* xinput 2 documentation describes support for multiple master
devices. I believe this implementation will support that, since now it
just uses `DeviceInfo` from slave devices. The concept of master
devices is only used in registering for events.
* Uses popcount+bit masking to resolve axis indexes, instead of
iterating bit indices.
---------
Co-authored-by: Thorsten Ball <mrnugget@gmail.com>
Closes#17605
Watches for target paths if file watched is a symlink in Linux.
This will check if the generated `notify::Event` has any paths matching
the `root_path` and if the file is a symlink it will also check if the
path matches the `target_root_path` (the path that the symlink is
pointing to)
Release Notes:
- Added file watching for symlinks
Release Notes:
- N/A
---
We may only want to set the height of an image to limit the size and
make the width adaptive.
In HTML, we will only set width or height, and the other side will adapt
and maintain the original image ratio.
I changed this because I had a logo image that only to be limited in
height, and then I found that setting the height of the `img` alone
would not display correctly.
I also tried to set `ObjectFit` in this Demo, but it seems that none of
them can achieve the same effect as "After".
## Before
<img width="809" alt="before 2024-09-18 164029"
src="https://github.com/user-attachments/assets/7ba559ed-e53b-43e6-a072-93c8ba5b14ee">
## After
<img width="749" alt="after 2024-09-18 172003"
src="https://github.com/user-attachments/assets/51ee2eba-76b3-400a-abbf-de0e9c4021e2">
**Clipboard Behavior on Windows Under This PR:**
| User Action | Zed’s Behavior |
| ------------------- |
-------------------------------------------------- |
| Paste PNG | Worked |
| Paste JPEG | Worked |
| Paste WebP | Worked, but not in the way you expect (see Issue section
below) |
| Paste GIF | Partially worked (see Issue section below) |
| Paste SVG | Partially worked (see Issue section below) |
| Paste BMP | Worked, but not in the way you expect (see Issue section
below) |
| Paste TIFF | Worked, but not in the way you expect (see Issue section
below) |
| Paste Files | Worked, same behavior as macOS |
| Copy image in Zed | Not tested, as I couldn’t find a way to copy
images |
---
**Differences Between the Windows and macOS Clipboard**
The clipboard functionality on Windows differs significantly from macOS.
On macOS, there can be multiple items in the clipboard, whereas, on
Windows, the clipboard holds only a single item. You can retrieve
different formats from the clipboard, but they are all just different
representations of the same item.
For example, when you copy a JPG image from Microsoft Word, the
clipboard will contain data in several formats:
- Microsoft Office proprietary data
- JPG format data
- PNG format data
- SVG format data
Please note that these formats all represent the same image, just in
different formats. This is due to compatibility concerns on Windows, as
various applications support different formats. Ideally, multiple
formats should be placed on the clipboard to support more software.
However, in general, supporting PNG will cover 99% of software, like
Chrome, which only supports PNG and BMP formats.
Additionally, since the clipboard on Windows only contains a single
item, special handling is required when copying multiple objects, such
as text and images. For instance, if you copy both text and an image
simultaneously in Microsoft Word, Microsoft places the following data on
the clipboard:
- Microsoft Office proprietary data containing a lot of content such as
text fonts, sizes, italics, positioning, image size, content, etc.
- RTF data representing the above content in RTF format
- HTML data representing the content in HTML format
- Plain text data
Therefore, for the current `ClipboardItem` implementation, if there are
multiple `ClipboardEntry` objects to be placed on the clipboard, RTF or
HTML formats are required. This PR does not support this scenario, and
only supports copying or pasting a single item from the clipboard.
---
**Known Issues**
- **WebP, BMP, TIFF**: These formats are not explicitly supported in
this PR. However, as mentioned earlier, in most cases, there are
corresponding PNG format data on the clipboard. This PR retrieves data
via PNG format, so users copying images in these formats from other
sources will still see the images displayed correctly.
- **GIF**: In this PR, GIFs are displayed, but for GIF images with
multiple frames, the image will not animate and will freeze on a single
frame. Since I observed the same behavior on macOS, I believe this is
not an issue with this PR.
- **SVG**: In this PR, only the top-left corner of the SVG image is
displayed. Again, I observed the same behavior on macOS, so I believe
this issue is not specific to this PR.
---
I hope this provides a clearer understanding. Any feedback or
suggestions on how to improve this are welcome.
Release Notes:
- N/A
- Add `script/build-docker`
- Add `script/install-cmake`
- Add `script/install-mold`
- Improve `script/linux`
- Add missing dependencies: `jq`, `git`, `tar`, `gzip` as required.
- Add check for mold
- Fix Redhat 8.x derivatives (RHEL, Centos, Almalinux, Rocky, Oracle, Amazon)
- Fix perl libs to be Fedora only
- Install the best `libstdc++` available on apt distros
- ArchLinux: run `pacman -Syu` to update repos before installing.
- Should work on Raspbian (untested)
This make it possible to test builds on other distros using docker:
```
./script/build-docker amazonlinux:2023
```
This makes it possible to have multiple Dockerfiles, each with their own
`.dockerignore`. Previously any docker builds would always include
anything inside `.dockerignore`. I believe this feature may require
`export DOCKER_BUILDKIT=1` but we use that in CI already.
This is a follow-up to #18530 thanks to this comment here:
https://github.com/zed-industries/zed/pull/18530#issuecomment-2382870564
In short: it fixes the `blinking` setting and the `cursor_shape` setting
as it relates to blinking.
Turns out our `blinking` setting was always the wrong value when using
`terminal_controlled` and the terminal _would_ control the blinking.
Example script to test with:
```bash
echo -e "0 normal \x1b[\x30 q"; sleep 2
echo -e "1 blink block \x1b[\x31 q"; sleep 2
echo -e "2 solid block \x1b[\x32 q"; sleep 2
echo -e "3 blink under \x1b[\x33 q"; sleep 2
echo -e "4 solid under \x1b[\x34 q"; sleep 2
echo -e "5 blink vert \x1b[\x35 q"; sleep 2
echo -e "6 solid vert \x1b[\x36 q"; sleep 2
echo -e "0 normal \x1b[\x30 q"; sleep 2
echo -e "color \x1b]12;#00ff00\x1b\\"; sleep 2
echo -e "reset \x1b]112\x1b\\ \x1b[\x30 q"
```
Before the changes in here, this script would set the cursor shape and
the blinking, but the blinking boolean would always be wrong.
This change here makes sure that it works consistently:
- `terminal.cursor_shape` only controls the *default* shape of the
terminal, not the blinking.
- `terminal.blinking = on` means that it's *always* blinking, regardless
of what terminal programs want
- `terminal.blinking = off` means that it's *never* blinking, regardless
of what terminal programs want
- `terminal.blinking = terminal_controlled (default)` means that it's
blinking depending on what terminal programs want. when a terminal
program resets the cursor to default, it sets it back to
`terminal.cursor_shape` if that is set.
Release Notes:
- Fixed the behavior of `{"terminal": {"blinking":
"[on|off|terminal_controlled]"}` to work correctly and to work correctly
when custom `cursor_shape` is set.
- `terminal.cursor_shape` only controls the *default* shape of the
terminal, not the blinking.
- `terminal.blinking = on` means that it's *always* blinking, regardless
of what terminal programs want
- `terminal.blinking = off` means that it's *never* blinking, regardless
of what terminal programs want
- `terminal.blinking = terminal_controlled (default)` means that it's
blinking depending on what terminal programs want. when a terminal
program resets the cursor to default, it sets it back to
`terminal.cursor_shape` if that is set.
Demo:
https://github.com/user-attachments/assets/b3fbeafd-ad58-41c8-9c07-1f03bc31771f
Co-authored-by: Bennet <bennet@zed.dev>
I've been running with direct direnv loading for a while now and haven't
experienced any significant issues other than #18473. Making it default
would make direnv integration more reliable and consistent. I've also
updated the docs a bit to ensure that they represent current status of
direnv integration
Release Notes:
- Made direnv integration use direct (`direnv export json`) mode by
default instead of relying on a shell hook, improving consistency and
reliability of direnv detection
This fixes something that I felt was off for a while. Previously, when
you'd click on the titlebar to move the window, the titlebar would only
change its background once the moving starts, but not on mouse-down.
That felt really off, since the moving is down with mouse-down and move,
so I think giving the user feedback about the mouse-down event makes
more sense.
I know there's a subjectivity to this change, so I'm ready to hear other
opinions, but for now I want to go with this.
Release Notes:
- N/A
This builds on top of @Yevgen's #15840 and combines it with the settings
names introduced in #17572.
Closes#4731.
Release Notes:
- Added a setting for the terminal's default cursor shape. The setting
is `{"terminal": {"cursor_shape": "block"}}``. Possible values: `block`,
`bar`, `hollow`, `underline`.
Demo:
https://github.com/user-attachments/assets/96ed28c2-c222-436b-80cb-7cd63eeb47dd
Closes#18393
Release Notes:
- Added a `ZED_RC_TOOLKIT_PATH` env variable so `winresource` crate can fetch the RC executable path correctly on some configurations
This is a partial revert of e6c1c51b37, which removed the middle-click
pasting on linux (both x11 & wayland). It also restores the
`middle_click_paste` option behavior which became unexistent.
Release Notes:
- Restore Linux middle-click pasting.
I made a few tree-sitter queries for improving the highlighting of C++.
There is one query that I'm not totally certain about and would
appreciate some feedback on it, the one that concerns attributes.
Many editor only highlight the identifier as a keyword (This is the
behavior implemented in this commit), while others, for example the
tree-sitter plugin for neovim, tags the entire attribute for
highlighting (double brackets included). I don't know which one is
preferable. Here are screenshots of the two versions:
Release Notes:
- Fixed C++ attributes identifiers being wrongly highlighed through the
tag "variable"
- C++ attribute identifiers (nodiscard,deprecated, noreturn, etc.. ) are
now highlighted through the tag "keyword"
- Changed C++ primitives types (void, bool, int, size_t, etc.. ) to no
longer be highlighted with the tag "keyword", they can now be
highlighted by the tag "type.primitive".
- Added a tag "concept" for highlighting C++ concept identifiers. (This
tag name has been chosen to be the same than the one returned by
clangd's semantic tokens)
Allows to split log view, and opens it split on the right, same as the
syntax tree view.
Release Notes:
- Improved language server log panel split ergonomics
Once again aping after what winit does - since we always want to have
the whole window blurred there is apparently no need to specify a blur
region at all. Rounded corners would be the exception, but that is not
possible with the current protocol (it is planned for the vendor-neutral
version though!)
This eliminates the problem where only a fixed region of the window
would get blurred if the window was resized to be larger than at launch.
Also a drive-by comment grammar fix 😉
Release Notes:
- Fixed blur region handling on Plasma/Wayland
PHP heredoc strings make it easy to define string literals over multiple
lines:
```php
$someString = <<<EOT
multiline
text
EOT;
```
That `EOT` identifier can be anything else, and it is actually being
used in Sublime Text and VS Code to inject syntax highlighting for
another language in said string, depending on the identifier. For
instance, if the identifier is SQL, SQL syntax highlighting will be
applied to the contents of the string. Likewise if the identifier is CSS
or JS.
```php
$someString = <<<SQL
SELECT *
FROM my_table
SQL;
```
This PR changes the PHP extension so that it supports that feature too.
Release Notes:
- php: Added syntax highlighting inside heredoc strings
Before this we we would stop loading the environment if the call to
direnv failed, which is not necessary in any way
cc @mrnugget
Release Notes:
- Fixed the environment not loading if `direnv` mode is set to `direct`
and `.envrc` is not allowed
If specifying a formatter in the settings like this:
"languages": {
"foo": {
"formatter": {
"external": {
"command": "/path/to/foo-formatter"
}
}
}
}
Zed will show an error like this:
Invalid user settings file
data did not match any variant of untagged enum SingleOrVec
This is because the arguments are not optional. The error is hard to
understand, so let's make the arguments actually optional, which makes
the above settings snippet valid.
Release Notes:
- Make external formatter arguments optional
We are going to use this in the multi-buffer to produce a summary for an
`Excerpt` that contains a `Range<Anchor>`.
Release Notes:
- N/A
Co-authored-by: Nathan <nathan@zed.dev>
We are now using the `view release notes locally` action when clicking
on the update toast - the endpoint for this action does not currently
return anything for valid for these channels, as we don't have support
yet for diffing between these builds, so for now, [continue to do what
the `view release notes` action did and just send the user to the commit
view on
GitHub](caffb2733f/crates/auto_update/src/auto_update.rs (L255-L260)).
It is a bit counterintuitive to send the user to the browser when using
the "local" action, but this is just a patch in the interim.
If we make adjustments to our channels to keep the nightly tag stable
and add some sort of unique suffix, like a timestamp, we can then adjust
things to return these in the request body and show them in the editor.
Release Notes:
- N/A
Closes https://github.com/zed-industries/zed/issues/17527
I think we are ok to switch to using the local action now. There are a
few things we don't support, like media, but we don't include media
directly too often, and I think this might help push the community to
maybe add support for it. That being said, I updated the markdown coming
back from the endpoint to include links to the web version of the
release notes, so they can always hop over to that version, if they
would like.
https://github.com/user-attachments/assets/b4d207a7-1640-48f1-91d0-94537f74116c
All forming of the Markdown happens in the endpoint, so if someone with
a better eye wants to update this, you can do that here:
0e5923e3e7/src/pages/api/release_notes/v2/%5Bchannel_type%5D/%5Bversion%5D.ts (L50-L62)
Release Notes:
- Changed the `view the release notes` button in the update toast to
trigger the local release notes action.
I have just recently discovered this keybinding myself out of talking to
folks, ha. The tooltip here might ease the discovery for other folks in
the future.
<img width="700" alt="Screenshot 2024-09-27 at 11 04 28 PM"
src="https://github.com/user-attachments/assets/844d3b55-15af-47f7-a8db-5c8832ceba29">
---
Release Notes:
- N/A
Fixes https://github.com/zed-industries/zed/issues/18405
In https://github.com/zed-industries/zed/pull/18313, we introduced a
problem where git addition highlights might spuriously return when
undoing certain changes. It turned out, there were already some cases
where git hunk highlighting was incorrect when editing at the boundaries
of expanded diff hunks.
In this PR, I've introduced a test helper method for more rigorously
(and readably) testing the editor's git state. You can assert about the
entire state of an editor's diff decorations using a formatted diff:
```rust
cx.assert_diff_hunks(
r#"
- use some::mod1;
use some::mod2;
const A: u32 = 42;
- const B: u32 = 42;
const C: u32 = 42;
fn main() {
- println!("hello");
+ //println!("hello");
println!("world");
+ //
+ //
}
fn another() {
println!("another");
+ println!("another");
}
- fn another2() {
println!("another2");
}
"#
.unindent(),
);
```
This will assert about the editor's actual row highlights, not just the
editor's internal hunk-tracking state.
I rewrote all of our editor diff tests to use these more high-level
assertions, and it caught the new bug, as well as some pre-existing bugs
in the highlighting of added content.
The problem was how we *remove* highlighted rows. Previously, it relied
on supplying exactly the same range as one that we had previously
highlighted. I've added a `remove_highlighted_rows(ranges)` APIs which
is much simpler - it clears out any row ranges that intersect the given
ranges (which is all that we need for the Git diff use case).
Release Notes:
- N/A
Reverts #13857. Hiding tooltips for selected buttons prevents tooltips
like "Close x dock" from showing up, see #14938 for an example.
The intention of the original PR was to hide the "Show application menu"
tooltip, while the context menu is open.
In order to fix this without breaking other UI elements, we track the
state of the context menu using `PopoverMenuHandle` now, which allows us
to prevent the tooltip from showing up while the context menu is open.
Closes#14938
Release Notes:
- Fixed an issue where some tooltips would not show up
Fixes some missing shortcuts from Tooltips like the project search,
buffer search, quick action bar, ....
https://github.com/user-attachments/assets/d3a0160a-8d6e-4ddc-bf82-1fabeca42d59
This should hopefully help new users learn and discover some nice
keyboard shortcuts
Release Notes:
- Display keyboard shortcuts inside tooltips in the project search,
buffer search etc.
Closes#6822
Updates #5142
Release Notes:
- Added new fold actions to toggle folds (`cmd-k cmd-l`), fold every
fold (`cmd-k cmd-0`) unfold every fold (`cmd-k cmd-j`) to fold
recursively (`cmd-k cmd-[`) and unfold recursively (`cmd-k cmd-]`).
- vim: Added `za` to toggle fold under cursor.
- vim: Added `zO`/`zC`/`zA` to open, close and toggle folds recursively
(and fixed `zc` to not recurse into selections).
- vim: Added `zR`/`zM` to open/close all folds in the buffer.
Users of our http_client crate knew they were interacting with isahc as
they set its extensions on the request. This change adds our own
equivalents for their APIs in preparation for changing the default http
client.
Release Notes:
- N/A
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [clap](https://redirect.github.com/clap-rs/clap) |
workspace.dependencies | patch | `4.5.17` -> `4.5.18` |
---
### Release Notes
<details>
<summary>clap-rs/clap (clap)</summary>
###
[`v4.5.18`](https://redirect.github.com/clap-rs/clap/blob/HEAD/CHANGELOG.md#4518---2024-09-20)
[Compare
Source](https://redirect.github.com/clap-rs/clap/compare/v4.5.17...v4.5.18)
##### Features
- *(builder)* Expose `Arg::get_display_order` and
`Command::get_display_order`
</details>
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC44MC4wIiwidXBkYXRlZEluVmVyIjoiMzguODAuMCIsInRhcmdldEJyYW5jaCI6Im1haW4iLCJsYWJlbHMiOltdfQ==-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [cargo_toml](https://lib.rs/cargo_toml)
([source](https://gitlab.com/lib.rs/cargo_toml)) |
workspace.dependencies | patch | `0.20.4` -> `0.20.5` |
---
### Release Notes
<details>
<summary>lib.rs/cargo_toml (cargo_toml)</summary>
###
[`v0.20.5`](https://gitlab.com/lib.rs/cargo_toml/compare/v0.20.4...v0.20.5)
[Compare
Source](https://gitlab.com/lib.rs/cargo_toml/compare/v0.20.4...v0.20.5)
</details>
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC44MC4wIiwidXBkYXRlZEluVmVyIjoiMzguODAuMCIsInRhcmdldEJyYW5jaCI6Im1haW4iLCJsYWJlbHMiOltdfQ==-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [actions/setup-node](https://redirect.github.com/actions/setup-node) |
action | digest | `1e60f62` -> `0a44ba7` |
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC44MC4wIiwidXBkYXRlZEluVmVyIjoiMzguODAuMCIsInRhcmdldEJyYW5jaCI6Im1haW4iLCJsYWJlbHMiOltdfQ==-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [async-trait](https://redirect.github.com/dtolnay/async-trait) |
workspace.dependencies | patch | `0.1.82` -> `0.1.83` |
---
### Release Notes
<details>
<summary>dtolnay/async-trait (async-trait)</summary>
###
[`v0.1.83`](https://redirect.github.com/dtolnay/async-trait/releases/tag/0.1.83)
[Compare
Source](https://redirect.github.com/dtolnay/async-trait/compare/0.1.82...0.1.83)
- Prevent needless_arbitrary_self_type lint being produced in generated
code
([#​278](https://redirect.github.com/dtolnay/async-trait/issues/278))
</details>
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC44MC4wIiwidXBkYXRlZEluVmVyIjoiMzguODAuMCIsInRhcmdldEJyYW5jaCI6Im1haW4iLCJsYWJlbHMiOltdfQ==-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
I was inspecting how Zed did the layout in the editor, specifically for
the gutter, and noticed that `em_width * X` is being used as the 'width
of X consecutive characters'. Howevever, that math didn't work for me,
because em_width doesn't account for the space between characters, so
you can't just multiply it by a character count.
One place this is actually noticeable is in the logic for
`min_width_for_number_on_gutter`, where we try to reserve 4 characters
of line number space. However, once you actually hit 4 characters, the
actual width is bigger, causing things to resize. This seems clearly
counter to the intent of the code.
It seems the more correct logic is to use `em_advance` which accounts
for the space between the characters. I am leaving the rest of the uses
of `em_width` for generic padding. It is also possible that
`column_pixels()` would be the more correct fix here, but it wasn't
straightforward to use that due to it residing EditorElement source
file.
On my MacBook this increases the width of the gutter by 6 pixels when
there are <999 lines in the file, otherwise it's identical.
It might be worth doing some more general audit of some of the other
uses of em_width as a concept. (e.g. `git_blame_entries_width`)
https://github.com/user-attachments/assets/f2a28cd5-9bb6-4109-bf41-1838e56a75f9
Release Notes:
- Fix a slight gutter flicker when going over 999 lines
This is not an ideal solution to
https://github.com/fasterthanlime/zed-diags-readme, but current status
quo is not great either; we were just going through all of the language
servers and notifying them, whereas we should ideally do it based on a
glob.
/cc @fasterthanlime
Release Notes:
- N/A
Before this change, `use_on_type_format` would only have an effect when
defined on a global level in our settings.
But our default.json settings would also document that it's used in
language settings, i.e.:
```json
{
"languages": {
"C": {
"use_on_type_format": false
},
"C++": {
"use_on_type_format": false
}
}
}
```
But this did **not** work.
With the change, it now works globally and per-language.
Release Notes:
- Fixed `use_on_type_format` setting not working when defined inside
`"languages"` in the settings. This change will now change the default
behavior for C, C++, and Markdown, by turning language server's
`OnTypeFormatting` completions off by default.
Co-authored-by: Bennet <bennet@zed.dev>
This should fix the `unregistered setting type
workspace::workspace_settings::WorkspaceSettings` panic that came from
inside `restorable_workspace_locations`.
We tracked it down to a possible scenario (we can't recreate it though)
in which `app.on_reopen` is called before the app has finished
launching.
In any case, this check makes sense, because we only want to restore a
workspace in case the whole app has launched with a UI.
Release Notes:
- N/A
Co-authored-by: Bennet <bennet@zed.dev>
Closes#18119
Release Notes:
- Fixed the cursor shape in the editor not changing back to default when
`{"cursor_shape": "..."}` setting is removed. (Does not apply to Vim
mode.)
This PR adds some more functionality to the Proposed Changes Editor
view, which we'll be using in
https://github.com/zed-industries/zed/pull/18240 for allowing the
assistant to propose changes to a set of buffers.
* Add an `Apply All` button, and fully implement applying of changes to
the base buffer
* Make the proposed changes editor searchable
* Fix a bug in branch buffers' diff state management
Release Notes:
- N/A
Todo:
* [x] Tooltips for hunk buttons
* [x] Buttons to go to next and previous hunk
* [x] Ellipsis button that opens a context menu with `Revert all`
/cc @iamnbutler @danilo-leal for design 👀
Release Notes:
- Changed the behavior of the git gutter so that diff hunk are expanded
immediately when clicking the gutter, and hunk controls are displayed
above the hunk.
---------
Co-authored-by: Marshall <marshall@zed.dev>
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
| [actions/stale](https://redirect.github.com/actions/stale) | action |
pinDigest | -> `28ca103` |
---
### Configuration
📅 **Schedule**: Branch creation - "after 3pm on Wednesday" in timezone
America/New_York, Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
Release Notes:
- N/A
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzOC44MC4wIiwidXBkYXRlZEluVmVyIjoiMzguODAuMCIsInRhcmdldEJyYW5jaCI6Im1haW4iLCJsYWJlbHMiOltdfQ==-->
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
Fixes an issue where evals were hitting "too many open files" errors
because we were adding (and detaching) new directory watches for each
project. Now we add those watches globally/at the worktree level, and we
store the tasks so they stop watching on drop.
Release Notes:
- N/A
---------
Co-authored-by: Max <max@zed.dev>
Co-authored-by: Piotr <piotr@zed.dev>
Co-authored-by: Piotr Osiewicz <24362066+osiewicz@users.noreply.github.com>
2024-09-25 15:21:00 -04:00
743 changed files with 33584 additions and 27570 deletions
We're working to clean up our issue tracker by closing older issues that might not be relevant anymore. Are you able to reproduce this issue in the latest version of Zed? If so, please let us know by commenting on this issue and we will keep it open; otherwise, we'll close it in 10 days. Feel free to open a new issue if you're seeing this message after the issue has been closed.
We're working to clean up our issue tracker by closing older issues that might not be relevant anymore. If you are able to reproduce this issue in the latest version of Zed, please let us know by commenting on this issue, and we will keep it open. If you can't reproduce it, feel free to close the issue yourself. Otherwise, we'll close it in 7 days.
Thanks for your help!
close-issue-message:"This issue was closed due to inactivity; feel free to open a new issue if you're still experiencing this problem!"
close-issue-message:"This issue was closed due to inactivity. If you're still experiencing this problem, please open a new issue with a link to this issue."
# We will increase `days-before-stale` to 365 on or after Jan 24th,
# 2024. This date marks one year since migrating issues from
# 'community' to 'zed' repository. The migration added activity to all
# issues, preventing 365 days from working until then.
@@ -50,6 +50,9 @@ And here's the section to rewrite based on that prompt again for reference:
{{#ifdiagnostic_errors}}
{{#eachdiagnostic_errors}}
Below are the diagnostic errors visible to the user. If the user requests problems to be fixed, use this information, but do not try to fix these errors if the user hasn't asked you to.
The user of a code editor wants to make a change to their codebase.
You must describe the change using the following XML structure:
Your task is to guide the user through code changes using a series of steps. Each step should describe a high-level change, which can consist of multiple edits to distinct locations in the codebase.
## Output Example
Provide output as XML, with the following format:
<step>
Update the Person struct to store an age
```rust
struct Person {
// existing fields...
age: u8,
height: f32,
// existing fields...
}
impl Person {
fn age(&self) -> u8 {
self.age
}
}
```
<edit>
<path>src/person.rs</path>
<operation>insert_before</operation>
<search>height: f32,</search>
<description>Add the age field</description>
</edit>
<edit>
<path>src/person.rs</path>
<operation>insert_after</operation>
<search>impl Person {</search>
<description>Add the age getter</description>
</edit>
</step>
## Output Format
First, each `<step>` must contain a written description of the change that should be made. The description should begin with a high-level overview, and can contain markdown code blocks as well. The description should be self-contained and actionable.
After the description, each `<step>` must contain one or more `<edit>` tags, each of which refer to a specific range in a source file. Each `<edit>` tag must contain the following child tags:
### `<path>` (required)
This tag contains the path to the file that will be changed. It can be an existing path, or a path that should be created.
### `<search>` (optional)
This tag contains a search string to locate in the source file, e.g. `pub fn baz() {`. If not provided, the new content will be inserted at the top of the file. Make sure to produce a string that exists in the source file and that isn't ambiguous. When there's ambiguity, add more lines to the search to eliminate it.
### `<description>` (required)
This tag contains a single-line description of the edit that should be made at the given location.
### `<operation>` (required)
This tag indicates what type of change should be made, relative to the given location. It can be one of the following:
- `update`: Rewrites the specified string entirely based on the given description.
- `create`: Creates a new file with the given path based on the provided description.
- `insert_before`: Inserts new text based on the given description before the specified search string.
- `insert_after`: Inserts new text based on the given description after the specified search string.
- `delete`: Deletes the specified string from the containing file.
- <patch> - A group of related code changes.
Child tags:
- <title> (required) - A high-level description of the changes. This should be as short
as possible, possibly using common abbreviations.
- <edit> (1 or more) - An edit to make at a particular range within a file.
Includes the following child tags:
- <path> (required) - The path to the file that will be changed.
- <description> (optional) - An arbitrarily-long comment that describes the purpose
of this edit.
- <old_text> (optional) - An excerpt from the file's current contents that uniquely
identifies a range within the file where the edit should occur. If this tag is not
specified, then the entire file will be used as the range.
- <new_text> (required) - The new text to insert into the file.
- <operation> (required) - The type of change that should occur at the given range
of the file. Must be one of the following values:
- `update`: Replaces the entire range with the new text.
- `insert_before`: Inserts the new text before the range.
- `insert_after`: Inserts new text after the range.
- `create`: Creates a new file with the given path and the new text.
- `delete`: Deletes the specified range from the file.
<guidelines>
- There's no need to describe *what* to do, just *where* to do it.
- Only reference locations that actually exist (unless you're creating a file).
- If creating a file, assume any subsequent updates are included at the time of creation.
- Don't create and then update a file. Always create new files in one hot.
- Prefer multiple edits to smaller regions, as opposed to one big edit to a larger region.
- Don't produce edits that intersect each other. In that case, merge them into a bigger edit.
- Never nest an edit with another edit. Never include CDATA. All edits are leaf nodes.
- Descriptions are required for all edits except delete.
- When generating multiple edits, ensure the descriptions are specific to each individual operation.
- Avoid referring to the search string in the description. Focus on the change to be made, not the location where it's made. That's implicit with the `search` string you provide.
- Don't generate multiple edits at the same location. Instead, combine them together in a single edit with a succinct combined description.
- Never provide multiple edits whose ranges intersect each other. Instead, merge them into one edit.
- Prefer multiple edits to smaller, disjoint ranges, rather than one edit to a larger range.
- There's no need to escape angle brackets within XML tags.
- Always ensure imports are added if you're referencing symbols that are not in scope.
</guidelines>
@@ -124,189 +72,137 @@ Update all shapes to store their origin as an (x, y) tuple and implement Display
<message role="assistant">
We'll need to update both the rectangle and circle modules.
<step>
Add origin fields to both shape types.
```rust
struct Rectangle {
// existing fields ...
origin: (f64, f64),
}
```
```rust
struct Circle {
// existing fields ...
origin: (f64, f64),
}
```
<patch>
<title>Add origins and display impls to shapes</title>
<edit>
<path>src/shapes/rectangle.rs</path>
<description>Add the origin field to Rectangle struct</description>
<operation>insert_after</operation>
<old_text>
pub struct Rectangle {
</old_text>
<new_text>
origin: (f64, f64),
</new_text>
</edit>
<edit>
<path>src/shapes/rectangle.rs</path>
<operation>insert_before</operation>
<search>
width: f64,
height: f64,
</search>
<description>Add the origin field to Rectangle</description>
<description>Update the Rectangle's new function to take an origin parameter</description>
<description>Remove email parameter from new method</description>
</edit>
</step>
</message>
</example>
You should think step by step. When possible, produce smaller, coherent logical steps as opposed to one big step that combines lots of heterogeneous edits.
Your task is to map a step from a workflow to locations in source code where code needs to be changed to fulfill that step.
Given a workflow containing background context plus a series of <step> tags, you will resolve *one* of these step tags to resolve to one or more locations in the code.
With each location, you will produce a brief, one-line description of the changes to be made.
<guidelines>
- There's no need to describe *what* to do, just *where* to do it.
- Only reference locations that actually exist (unless you're creating a file).
- If creating a file, assume any subsequent updates are included at the time of creation.
- Don't create and then update a file. Always create new files in shot.
- Prefer updating symbols lower in the syntax tree if possible.
- Never include suggestions on a parent symbol and one of its children in the same suggestions block.
- Never nest an operation with another operation or include CDATA or other content. All suggestions are leaf nodes.
- Descriptions are required for all suggestions except delete.
- When generating multiple suggestions, ensure the descriptions are specific to each individual operation.
- Avoid referring to the location in the description. Focus on the change to be made, not the location where it's made. That's implicit with the symbol you provide.
- Don't generate multiple suggestions at the same location. Instead, combine them together in a single operation with a succinct combined description.
- To add imports respond with a suggestion where the `"symbol"` key is set to `"#imports"`
</guidelines>
</overview>
<examples>
<example>
<workflow_context>
<message role="user">
```rs src/rectangle.rs
struct Rectangle {
width: f64,
height: f64,
}
impl Rectangle {
fn new(width: f64, height: f64) -> Self {
Rectangle { width, height }
}
}
```
We need to add methods to calculate the area and perimeter of the rectangle. Can you help with that?
</message>
<message role="assistant">
Sure, I can help with that!
<step>Add new methods 'calculate_area' and 'calculate_perimeter' to the Rectangle struct</step>
<step>Implement the 'Display' trait for the Rectangle struct</step>
</message>
</workflow_context>
<step_to_resolve>
Add new methods 'calculate_area' and 'calculate_perimeter' to the Rectangle struct
</step_to_resolve>
<incorrect_output reason="NEVER append multiple children at the same location.">
{
"title": "Add Rectangle methods",
"suggestions": [
{
"kind": "AppendChild",
"path": "src/shapes.rs",
"symbol": "impl Rectangle",
"description": "Add calculate_area method"
},
{
"kind": "AppendChild",
"path": "src/shapes.rs",
"symbol": "impl Rectangle",
"description": "Add calculate_perimeter method"
}
]
}
</incorrect_output>
<correct_output>
{
"title": "Add Rectangle methods",
"suggestions": [
{
"kind": "AppendChild",
"path": "src/shapes.rs",
"symbol": "impl Rectangle",
"description": "Add calculate area and perimeter methods"
}
]
}
</correct_output>
<step_to_resolve>
Implement the 'Display' trait for the Rectangle struct
</step_to_resolve>
<output>
{
"title": "Implement Display for Rectangle",
"suggestions": [
{
"kind": "InsertSiblingAfter",
"path": "src/shapes.rs",
"symbol": "impl Rectangle",
"description": "Implement Display trait for Rectangle"
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
