# Objective
Zed on X11 could crash with `index out of bounds: the len is 0 but the
index is 0` in `WgpuAtlas::get_texture_info` right after recovering from
a lost GPU device (Sentry ZED-BVQ, Linear FR-488).
## Solution
When the device is lost, `X11Window::draw` recreates the renderer, which
clears the sprite atlas, and sets `force_render_after_recovery` so the
next frame rebuilds the scene instead of replaying the cached one. Only
the periodic refresh timer consumed that flag though. An `Expose` event
handled in the same event loop turn (a compositor repainting after the
same GPU reset, for example) requested a presentation-only frame with
`force_render: false`, so GPUI presented the previously rendered scene,
whose sprites still pointed at atlas textures that no longer exist.
We now consume the flag in `X11WindowStatePtr::refresh`, so every frame
request, Expose or timer, forces a full render after recovery. The field
is private now so a caller can't bypass it again.
## Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content adheres to Zed's UI standards
([UX/UI](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
and
[icon](https://github.com/zed-industries/zed/blob/main/crates/icons/README.md)
guidelines)
- [ ] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
---
Release Notes:
- Fixed a crash on Linux (X11) that could occur when a window was
redrawn immediately after recovering from a lost GPU device.
- [GPUI] Fixed a crash on Linux (X11) when an `Expose` event presented a
cached frame immediately after GPU device recovery.
## Objective
Related conversations can’t share an OpenAI cache key without also
sharing a thread ID. We currently derive `prompt_cache_key` directly
from `thread_id`, tying cache reuse to conversation identity.
## Solution
Add an optional `prompt_cache_key` to `LanguageModelRequest` and use it
in both OpenAI Chat Completions and Responses conversions. We still fall
back to `thread_id` when no key is supplied, so existing callers keep
their current behavior.
This lets callers share a cache key across parent and child
conversations while keeping their conversation and transport identities
separate.
## Testing
Added regression coverage for explicit keys, legacy fallback, provider
capability gating, and serialization compatibility.
## Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content adheres to Zed's UI standards
- [x] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Release Notes:
- N/A
Closes ZED-73F
# Objective
Pasting in Helix mode while the cursor was inside an expanded deleted
diff hunk could create a selection past the buffer and crash.
## Solution
Track the inserted range with before/after anchors instead of deriving
it from the clipboard text length. If the edit is rejected for
non-editable diff text, both anchors resolve to an empty valid range.
## Testing
Added a regression test for pasting inside an expanded deleted hunk and
ran the Helix paste tests.
## Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content adheres to Zed's UI standards
- [x] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
---
Release Notes:
- Fixed a crash when pasting in an expanded deleted diff hunk in Helix
mode
`ShapedLine` is nearly 3KB by value because it inlines a
`SmallVec<[DecorationRun; 32]>`. A consumer that builds wrapped lines
out of many small uniformly styled fragments only needs the shaped
glyphs plus a single decoration run it can track itself, but it ends up
moving and reallocating that mostly dead capacity constantly because
splitting and painting are only reachable through `ShapedLine`.
This moves the glyph-partitioning half of `ShapedLine::split_at` down to
a new `LineLayout::split_at`, and adds
`LineLayout::paint`/`paint_background` methods that take explicit
decoration runs. Together with the already-public `layout_line`, callers
can now hold a bare `Arc<LineLayout>` and their own decorations.
`ShapedLine::split_at` delegates to the new method and behaves the same.
## Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content adheres to Zed's UI standards
([UX/UI](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
and
[icon](https://github.com/zed-industries/zed/blob/main/crates/icons/README.md)
guidelines)
- [ ] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
---
Release Notes:
- N/A
Spinners rendered near each other (like a sidebar full of running
threads) each start rotating from the moment their element first
renders, so they spin out of phase and the group looks jittery.
This adds `Animation::repeat_synced()`, which derives the phase from a
clock shared by the whole app instead of the element's mount time, and
switches `with_rotate_animation` over to it, so every spinner with the
same period now renders the same frame at the same time. The epoch is
read off the scheduler clock at app creation, so the phase stays
deterministic under the test scheduler.
Release Notes:
- Improved loading spinners to rotate in phase with one another
Scroll events are delivered to the window under the pointer even when it
isn't focused, but we cap inactive windows at ~30fps to save energy, so
scrolling an unfocused window visibly drops frames. We now exempt
high-rate input from the cap using the existing `InputRateTracker`: a
trackpad scroll stream lifts it while events are arriving and for one
second after the last burst, then the cap resumes on its own.
## Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content adheres to Zed's UI standards
([UX/UI](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
and
[icon](https://github.com/zed-industries/zed/blob/main/crates/icons/README.md)
guidelines)
- [ ] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
---
Release Notes:
- Fixed dropped frames when scrolling unfocused windows.
# Objective
GPUI apps currently don't have a cross-platform way to react when the
system wakes from sleep.
## Solution
Add `Application::on_system_wake`, backed by platform hooks for macOS,
Windows, and Linux. The platform listeners are registered lazily once an
app installs a wake callback.
## Testing
- N/A
## Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content adheres to Zed's UI standards
([UX/UI](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
and
[icon](https://github.com/zed-industries/zed/blob/main/crates/icons/README.md)
guidelines)
- [ ] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Release Notes:
- N/A
Adds provider-side context compaction support to the Anthropic and
OpenAI API clients. Client plumbing only; not wired into the UI.
Release Notes:
- N/A
Replaces the verbose struct-literal construction of `gpui::BoxShadow`
with a builder API:
- `BoxShadow::new(offset_x, offset_y, color)` takes the required fields,
with arguments ordered to match the CSS `box-shadow` property.
- `.blur_radius(_)`, `.spread_radius(_)`, and `.inset()` set the
optional fields.
All in-tree call sites are migrated, including the Tailwind-style
`shadow_xs`..`shadow_2xl` helpers in `gpui_macros`, the `ElevationIndex`
shadows in `ui`, and various widgets across `editor`, `workspace`,
`agent_ui`, and `ai_onboarding`. The fields on `BoxShadow` remain
public, so external code using struct-literal construction continues to
work.
Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [ ] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Release Notes:
- N/A
Bumps the workspace `convert_case` dependency from 0.8 to 0.11 (already
in the tree) so the `zed` binary includes only one copy.
Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [ ] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Release Notes:
- N/A
The `nc` crate and `zed --nc <socket>` flag were added in #34577 to let
the Claude Code integration spawn the running zed binary as a
netcat-style bridge between stdio and a Unix socket for its MCP server.
That integration was removed in #37120 in favor of the external
`@agentclientprotocol/claude-agent-acp` npm package, which dropped the
only caller of `--nc`. The flag, its dispatch in `main.rs`, and the `nc`
crate itself were left behind and have been unused since.
Nothing in the Zed codebase spawns `zed --nc` anymore, so remove the
flag and delete the crate. The unrelated `--askpass` netcat bridge (in
the `askpass` crate) is unaffected.
Release Notes:
- N/A
Removes a leftover test label added by #56065
Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [ ] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Release Notes:
- N/A
Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [ ] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Release Notes:
- N/A
<img width="282" height="90" alt="CleanShot 2026-05-14 at 11 28 40@2x"
src="https://github.com/user-attachments/assets/34516022-0e26-4380-9e80-568256483309"></img>
Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [ ] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Release Notes:
- Improved diff stats by formatting large line counts with thousand
separators.
Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [x] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Bumps `mermaid-rs-renderer` to
`782b89a7da3f0e91e51f98d00a93acba679be6fb`, which picks up
[1jehuang/mermaid-rs-renderer#95](https://github.com/1jehuang/mermaid-rs-renderer/pull/95),
fixing a panic with partially typed mermaid.
Release Notes:
- Fixed a crash in markdown preview when a mermaid flowchart contained a
partially-typed parallelogram node like `A[/]` or `A[\]`.
`render_settings_item_link` was calling `cx.read_from_clipboard()`
during render so it could show a check icon next to the copy-link button
when the matching link was on the clipboard. This had two problems:
- A clipboard read per visible setting per frame is too expensive.
- On Windows, reading the clipboard pumps the system message queue. If a
queued message handler updates `App` while we're still rendering, GPUI
panics with `RefCell already borrowed` (many occurrences observed).
Track the `json_path` of the most recently copied setting locally
instead. The check icon now reflects what was copied in this session via
this UI rather than whatever is on the system clipboard.
While this removes the most common offender, the underlying
`gpui_windows` reentrancy bug still exists: `on_close` /
`on_request_frame` callbacks can be invoked while `App` is already
borrowed on Windows, and can be triggered by any other
clipboard-touching code path. We should consider a follow-up PR that
handles this at the platform layer -- either by deferring callbacks that
re-borrow `App`, or by guarding individual handlers in
`gpui_windows::events` against reentrant `borrow_mut` calls.
Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [ ] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Release Notes:
- Fixed a crash on Windows that could occur when closing the settings
window
- Improved the overall performance of the settings window
A follower could crash when following another collaborator into a
newly-opened multibuffer if the leader's recent edits hadn't yet
propagated. The follower would receive the view state with excerpt
anchors pointing into still-unobserved edits, tripping
`panic_bad_anchor`.
The fix waits for each buffer to observe the anchors timestamps before
resolving them, matching what's already done for selection and scroll
anchors. Includes a regression test in `collab` that reproduces the race
deterministically.
Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [x] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Release Notes:
- Fixed a crash in follow mode when opening multibuffers
Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [x] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
#55770 changed the npm package version spec to `package@<=1.2.3`. On
Windows this fails with `The system cannot find the file specified.`
because:
- `npm` resolves to `npm.cmd`, a batch file. Windows runs `.cmd` files
via cmd.exe, which parses the invocation and treats unquoted `<` as
input redirection.
- The single quotes our shell builder emits around args are PowerShell
string-literal syntax that PS strips during parsing. PS only re-adds
CRT-style transport quotes around native command args containing
whitespace, so `package@<=0.25.3` reaches `npm.cmd` bare and cmd.exe
fails before the batch body even runs.
Switch to npm's hyphen-range syntax (`0.0.0 - <version>`, equivalent to
`<=<version>`), which has no `<`.
Closes#55921
Release Notes:
- Fixed ACP agents failing to launch on Windows with "The system cannot
find the file specified"
The hot-exit shortcut in `save_all_internal` silently serializes dirty
buffers instead of prompting. It assumes the workspace will still be
reachable, but that's not true for `ReplaceWindow`, or for `CloseWindow`
of an empty workspace on macOS — both detach the workspace and orphan
its serialized buffers in the DB with no UI path back to them.
Only allow the shortcut when the workspace is actually recoverable
(`Quit`, `save_last_workspace`, or has visible worktrees). Otherwise
prompt.
Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [x] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Closes#55726
Release Notes:
- Fixed unsaved untitled buffers being silently lost when opening a file
or project from an empty window
Fixes a panic at `Editor::text_layout_details` when called against an
editor whose element has never been laid out (i.e., `set_style` has
never been called, so the cached `style` is still `None`).
We've seen this crash once through a helix motion. The exact production
sequence isn't clear — for the editor to receive a vim action without
ever having been drawn, the active item would have to have changed
inside the same update tick that ends with the deferred `search_submit`,
which is narrow but not impossible (since it's dispatched by the
workspace, not the editor).
Release Notes:
- Fixed a rare panic when invoking helix motions on an editor that had
not yet been laid out.
Pasting text or an image into a queued-message editor used to be a
silent no-op for text and a panic for images.
This change makes pasting into a queued message behave like typing into
one: the queued message is promoted into the main editor at the cursor
position, and the paste is then applied there.
Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [x] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Closes#55521
Release Notes:
- Fixed a crash when pasting an image into a queued message
Instead of manually handing hiding the cursor on keyboard input at the
editor level, GPUI will now take care of it.
This makes it significantly easier to handle the edge cases, and allows
delegating the cursor restoration to the platform itself in the macOS
case. On Linux and Windows, we still have to restore the cursor on
movement ourselves, but this now happens at the platform-specific level.
Bugs fixed by this change:
- No cursor when "Unsaved edits" prompt appears
- Cursor disappears when clicking a panel button if it contains a search
bar (e.g. collab panel)
### Setting rename
The `hide_mouse` setting value `"on_typing_and_movement"` has been
renamed to `"on_typing_and_action"` to better reflect what it actually
does — it hides the cursor when a keystroke resolves to an action (e.g.
cursor movement, deletion). Existing settings are migrated
automatically.
### Tested platforms
- [x] macOS
- [x] Wayland
- [x] X11
- [x] Windows
- [x] Web
Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [ ] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Release Notes:
- Renamed the `hide_mouse` setting value `on_typing_and_movement` to
`on_typing_and_action` to better describe its behavior (existing
settings are auto-migrated)
- Fixed a few situations where the mouse cursor would be incorrectly
hidden
Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [x] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Release Notes:
- N/A
We were storing a cursor hidden boolean in the window state, but that
state is actually global to the application.
Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [ ] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Release Notes:
- N/A
Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [ ] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Release Notes:
- N/A
Closes#53202
`Anchored::prepaint` computes the bounding box of its children to
determine the size used for fitting the anchored element in the window.
Previously, this calculation manually tracked the minimum origin and
maximum bottom-right point, initializing the maximum point to `(0, 0)`.
If child bounds were in negative coordinates, the maximum point could be
clamped to `(0, 0)`, inflating the computed size.
This replaces the manual min/max accumulation with `Bounds::union`,
starting from the actual child bounds instead of sentinel values. This
computes the child bounding box correctly regardless of coordinate sign.
---
Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [x] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Release Notes:
- Fixed a bug where the context menu in the agent panel (and other
scrollable surfaces) would appear at the wrong location
#48029 introduced `set_document_path` which is frequently (we are also
working on a PR to make it less frequent) called as tabs and panes
update. Apparently, the AppKit function it uses
(`NSWindow::setRepresentedFilename`) can cause the current cursor style
to be reset, producing flicker as the cursor would change to `Arrow`
temporarily until the right cursor style is set again in the next frame.
This PR reworks how we set the cursor to use AppKit's
`resetCursorRects`, giving us a chance to re-set the cursor when the OS
decides to invalidate it.
Finally, it fixes a separate bug introduced in #50827 where moving the
mouse while typing in an editor would cause to the cursor to flicker
between `None` (hidden) -> `Arrow` -> `IBeam`. This was caused by
incorrectly resetting the cursor to `Arrow` when the last input came
from the keyboard.
Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [ ] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Release Notes:
- N/A
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
- `language_model` no longer depends on provider-specific crates such as
`anthropic` and `open_ai` (inverted dependency)
- `language_model_core` was extracted from `language_model` which
contains the types for the provider-specific crates to convert to/from.
- `gpui::SharedString` has been extracted into its own crate (still
exposed by `gpui`), so `language_model_core` and provider API crates
don't have to depend on `gpui`.
- Removes some unnecessary `&'static str` | `SharedString` -> `String`
-> `SharedString` conversions across the codebase.
- Extracts the core logic of the cloud `LanguageModelProvider` into its
own crate with simpler dependencies.
Release Notes:
- N/A
---------
Co-authored-by: John Tur <john-tur@outlook.com>
The iteration range was `(seed..num_iterations)`, which produces an
empty range whenever `seed >= num_iterations`. Changed it to
`(seed..seed + num_iterations)` so the range always runs the correct
number of iterations starting from the given seed.
Release Notes:
- N/A
Some code got added to `workspace` that prevents us from running tests
for the `edit_prediction(cli)` crates specifically without the
`test-support` feature flag.
Release Notes:
- N/A
Co-authored-by: Ben Kunkle <ben@zed.dev>
We will now properly handle `\ No newline at the end of file` after
context lines and repeated occurrences. Also, when line numbers are
present in hunk headers, we will use them to disambiguate the location
when the context is not unique enough.
Release Notes:
- N/A
Sometimes git locks are left over from crashed runs. We now assume
there's only one process of the CLI running and clean them up. If we
want to run multiple processes at the same time, we should consider our
own file-based lock, but it seems fine for an internal tool.
Release Notes:
- N/A
Follow up to https://github.com/zed-industries/zed/pull/45311. Instead
of searching for the string in the find pasteboard as soon as the pane
is focused, we will now wait until the search bar is either deployed or
`Select{Next|Prev}Match` is triggered.
Release Notes:
- N/A
Closes#17467
Release Notes:
- On macOS, buffer search now syncs with the system find pasteboard,
allowing <kbd>⌘E</kbd> and <kbd>⌘G</kbd> to work seamlessly across Zed
and other apps.
We were panicking whenever something went wrong with an example in the
CLI. This can be very disruptive when running many examples, and e.g a
single request fails. Instead, if running more than one example, errors
will now be logged alongside instructions to explore and re-run the
example by itself.
<img width="1454" height="744" alt="CleanShot 2025-12-12 at 13 32 04@2x"
src="https://github.com/user-attachments/assets/87c59e64-08b9-4461-af5b-03af5de94152"></img>
You can still opt in to stop as soon as en error occurs with the new
`--failfast` argument.
Release Notes:
- N/A
- Limit status lines to 10 in case `max_parallelism` is specified with a
grater value
- Handle logging gracefully rather than writing over it when clearing
status lines
Release Notes:
- N/A
Fixes a few cases where the commit view would layout shift as the diff
loaded. This was caused by:
- Adding the commit message buffer after all the diff files
- Using the gutter dimensions from the last frame for the avatar spacing
Release Notes:
- commit view: Fix layout shift while loading commit
---------
Co-authored-by: MrSubidubi <dev@bahn.sh>
For qualified identifiers we end up requesting both the definition of
the module and the item within it, but we only want the latter. At the
moment, we can't skip the request altogether, because we can't tell them
apart from the highlights query. However, we can tell from the target
range length, because it should be small for individual definitions as
it only covers their name, not the whole body.
Release Notes:
- N/A
Sometimes machines are configured to drop outbound packets (rather than
reject connections). In these cases, curl/wget just hang causing our
download step to never complete. This PR adds a timeout of 10s for the
connection (not the whole download), so that in situations like this we
can fallback to our client-side download eventually.
Related to but doesn't fully fix:
https://github.com/zed-industries/zed/issues/43694 and
https://github.com/zed-industries/zed/issues/43718
Release Notes:
- remote: Add 10s connect timeout for server download
We have seen cases (see
https://github.com/zed-industries/zed/issues/43694) where the user's
shell initialization script includes text that ends up in the output of
the commands we use to detect the platform and shell of the remote. This
solution isn't perfect, but it should address the issue in most
situations since both commands should only output one line.
Release Notes:
- remote: Improve resiliency when initialization scripts output text
Fixes a deadlock in the background scanner that occurs on single-core
Linux devices. This happens because the background scanner would `block`
on a background thread waiting for a future, but on single-core Linux
devices there would be no other thread to pick it up. This mostly
affects SSH remoting use cases where it's common for servers to have 1
vCPU.
Closes#43884Closes#43809
Release Notes:
- Fix SSH remoting hang when connecting to 1 vCPU servers
Related to https://github.com/zed-industries/zed/pull/44109,
https://github.com/zed-industries/zed/issues/43884,
https://github.com/zed-industries/zed/issues/43809.
In the Linux dispatcher, we create one background thread per CPU, but
when a single core is available, having a single background thread
significantly hinders the perceived performance of Zed. This is
particularly helpful when SSH remoting to low-resource servers.
We may want to bump this to more than two threads actually, but I wanted
to be conservative, and this seems to make a big difference already.
Release Notes:
- N/A
#42441 moved the commit message out of the multi-buffer editor into its
own header element which looks nicer, but unfortunately can make the
view become unusable when the commit message is too long since it
doesn't scroll with the diff.
This PR maintains the metadata in its own element, but moves the commit
message back to the editor so the user can scroll past it. This does
mean that we lose markdown rendering for now, but we think this is a
good solution for the moment.
https://github.com/user-attachments/assets/d67cf22e-1a79-451a-932a-cdc8a65e43de
Release Notes:
- N/A
---------
Co-authored-by: cameron <cameron.studdstreet@gmail.com>
We currently attempt to flush all rejected predictions at once even if
we have accumulated more than
`MAX_EDIT_PREDICTION_REJECTIONS_PER_REQUEST`. Instead, we will now flush
as many as possible, and then keep the rest for the next batch.
Release Notes:
- N/A
We were allowing the client to build up to
`MAX_EDIT_PREDICTION_REJECTIONS_PER_REQUEST`. We'll now attempt to flush
the rejections when we reach half max.
Release Notes:
- N/A
At some point, rust-analyzer started including the snippet expression
for some completions in the description field, but that can look like a
bug:
<img width="1570" height="578" alt="CleanShot 2025-11-27 at 20 39 49@2x"
src="https://github.com/user-attachments/assets/5a87c9fe-c0a8-472f-8d83-3bc9e9e00bbc"></img>
In these cases, we will now inline the tab stops as an ellipsis
character:
<img width="1544" height="428" alt="CleanShot 2025-12-01 at 10 01 18@2x"
src="https://github.com/user-attachments/assets/4c550891-4545-47cd-a295-a5eb07e78e92"></img>
You may also notice that we now syntax highlight the pattern closer to
what it looks like after accepted.
Alternatively, when the tab stop isn't just one position, it gets
highlighted as a selection since that's what it would do when accepted:
<img width="1558" height="314" alt="CleanShot 2025-12-01 at 10 04 37@2x"
src="https://github.com/user-attachments/assets/ce630ab2-da22-4072-a996-7b71ba21637d"
/>
Release Notes:
- rust: Display completion tab stops inline rather than as a raw LSP
snippet expression
Without this new flag, the Sweep API will actually produce a combination
of UTF-16 and char indices, leading to incorrect edit positions.
Release Notes:
- N/A
Adds a `trigger` field to the zeta1/zeta2 prediction requests so that we
can distinguish between editor, diagnostic, and zeta-cli requests.
Release Notes:
- N/A
Many prediction requests end up being rejected early without ever being
set as the current prediction. Before this change, those cases weren’t
reported as rejections because the `request_prediction_with_*` functions
simply returned `Ok(None)`.
With this update, whenever we get a successful response from the
provider, we will return at least the `id`, allowing it to be properly
reported. The request now also includes a “reject reason,” since the
different variants carry distinct implications for prediction quality.
All of these scenarios are now covered by tests. While adding them, I
also found and fixed a bug where some cancelled predictions were
incorrectly being set as the current one.
Release Notes:
- N/A
---------
Co-authored-by: MrSubidubi <dev@bahn.sh>
Fixes an issue where the terminal cursor wouldn't always be displayed in
the default `blink: "terminal_controlled"` mode unless the terminal
requested cursor blinking.
Release Notes:
- N/A
We'll now add panels to the workspace as soon as they're ready rather
than waiting for all the rest to complete. We should strive to make all
panels fast, but given that their load tasks are fallible and do IO,
this approach seems more resilient.
Additionally, we'll now start loading the agent panel at the same time
as the rest.
Release Notes:
- workspace: Add panels as soon as they are ready
When no predictions are available for the current buffer, we will now
attempt to predict at the closest diagnostic from the cursor location
that wasn't included in the last prediction request. This enables a
commonly desired kind of far-away jump without requiring explicit model
support.
Release Notes:
- N/A
We weren't reporting predictions that were generated but never made it
out of the provider, such as predictions that failed to interpolate, and
those that are cancelled because another request completes before it.
Release Notes:
- N/A
---------
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Ben Kunkle <ben@zed.dev>
Adds a `--repeat` flag to the zeta eval that runs each example as many
times as specified. Also makes the output nicer in a few ways.
Release Notes:
- N/A
---------
Co-authored-by: Ben Kunkle <ben@zed.dev>
Co-authored-by: Michael <michael@zed.dev>
We'll now cache LLM responses at the request level (by hash of
URL+contents) for both context and prediction. This way we don't need to
worry about mistakenly using the cache when we change the prompt or its
components.
Release Notes:
- N/A
---------
Co-authored-by: Oleksiy Syvokon <oleksiy.syvokon@gmail.com>
Extract some of the improvements from to the unified diff prompt from
https://github.com/zed-industries/zed/pull/42171 and adds some other
about how context work to improve the reliability of predictions.
We also now strip the `<|user_cursor|>` marker if it appears in the
output rather than failing.
Release Notes:
- N/A
---------
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Since we removed the filtering step during context gathering, we want
the model to perform more targeted searches. This PR tweaks search tool
schema allowing the model to search within syntax nodes such as `impl`
blocks or methods.
This is what the query schema looks like now:
```rust
/// Search for relevant code by path, syntax hierarchy, and content.
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
pub struct SearchToolQuery {
/// 1. A glob pattern to match file paths in the codebase to search in.
pub glob: String,
/// 2. Regular expressions to match syntax nodes **by their first line** and hierarchy.
///
/// Subsequent regexes match nodes within the full content of the nodes matched by the previous regexes.
///
/// Example: Searching for a `User` class
/// ["class\s+User"]
///
/// Example: Searching for a `get_full_name` method under a `User` class
/// ["class\s+User", "def\sget_full_name"]
///
/// Skip this field to match on content alone.
#[schemars(length(max = 3))]
#[serde(default)]
pub syntax_node: Vec<String>,
/// 3. An optional regular expression to match the final content that should appear in the results.
///
/// - Content will be matched within all lines of the matched syntax nodes.
/// - If syntax node regexes are provided, this field can be skipped to include as much of the node itself as possible.
/// - If no syntax node regexes are provided, the content will be matched within the entire file.
pub content: Option<String>,
}
```
We'll need to keep refining this, but the core implementation is ready.
Release Notes:
- N/A
---------
Co-authored-by: Ben <ben@zed.dev>
Co-authored-by: Max <max@zed.dev>
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Adds a `convert-example` subcommand to the zeta cli that converts eval
examples from/to `json`, `toml`, and `md` formats.
Release Notes:
- N/A
---------
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Agus Zubiaga