Previously, you could only accept and reject all changes from a specific
file by checking that file out on a tab. Now, you can do that via the
message editor changes summary bar. The buttons appear as you hover over
the file item in the accordion.
Here's what it looks like:
<img
src="https://github.com/user-attachments/assets/8c0843d3-9bf1-4588-8b42-4cd8d0798a68"
width="500" />
Release Notes:
- agent: Enable accepting and rejecting individual file changes from
message editor.
* Adds `min_lines` to `EditorMode::AutoHeight` and use `min_lines: 4` in
agent message editor. This makes it so that clicks in the blank space
below the first line of the editor also focus it, instead of needing to
click the very first line.
* Removes the div wrapping the editor, as it was only there to set
`min_h_16()`. This also tightens up the min space given to the editor -
before it was not evenly dividing the number of lines.
* Further tightens up vertical spacing by using `gap_1` instead of
`gap_4` between editor and controls below
At 4 line min height (after on the left, before on the right):
At 5 lines, one more than min height (after on the left, before on the
right):
Release Notes:
- Agent: Fixed clicking to focus the message editor to also work for
clicks below the last line.
Some MCP servers expose tools that take absolute paths as arguments. To
interact with these, the agent needs to know the absolute path to the
project directories, not just their names. This PR changes the system
prompt to include the full path to each worktree, and updates some tool
descriptions to reflect this.
Todo:
* [x] Run evals, make sure assistant still understand how to specify
paths for tools, now that we include abs paths in the system prompt.
Release Notes:
- Improved the agent's ability to use MPC tools that require absolute
paths to files and directories in the project.
---------
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
Previously, upon getting close to reaching the context window, we'd just
suggest creating a new thread using the summary of the current one. Now,
we also suggest turning burn mode on as an alternative action to solve
the context window problem.
Release Notes:
- agent: Added a suggestion to turn burn mode on when getting close to
the context window limit.
What motivated me to refactor this component was the fact that I wanted
a new variant to allow having _two CTAs_ instead of just one. This
variant should work with either a single or multiline description. But,
given we were using a `Callout::single_line` and `Callout::multi_line`
API, I'd then need to have both `Callout::single_line_one_button` and
`Callout::single_line_two_buttons` type of variants, which just points
to a combinatorial problem.
With this refactor, the Callout now follows the same structure of the
Banner component, where it's all `Callout::new` and every method is
passed as if they were props in a React component, allowing for a more
flexible design where you can customize button styles. Also made it
slightly more robust for wrapping and removed the top border as that
should be defined by the place it is being used in.
Release Notes:
- N/A
Consolidates configuration error handling by moving the error type and
logic from assistant_context_editor to language_model::registry.
The registry now provides a single method to check for configuration
errors, making the error handling more consistent across the agent panel
and context editor.
This also now checks if the issue is that we don't have any providers,
or if we just can't find the model.
Previously, an incorrect model name showed up as having no providers,
which is very confusing.
Release Notes:
- N/A
I think we mistakenly added an early return for the review multibuffer
button if `has_pending_edit_tool_uses` is true. It is totally fine _to
access_ the review multibuffer while that's happening. It's another
thing to _accept and reject_ changes while they're still ongoing!
Release Notes:
- agent: Fixed access to the review multibuffer from the agent panel.
This is reverting a change from #32071 which caused agent following to
stop after the file was edited.
This will reintroduce the behavior that the keyboard shortcuts don't
work until the model is done generating, but we will revisit that
afterwards.
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Release Notes:
- agent: Fix a regression in agent following behavior after file edits
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
When editing a message, cancel any in-progress completion before
starting a new request to prevent overlapping model responses.
Release Notes:
- agent: Fixed previous completion not cancelling when editing a
previous message
This PR also introduces `Context::processor`, a sibling of
`Context::listener` that takes a strong pointer to entity and allows for
a return result.
Release Notes:
- N/A
Co-authored-by: Mikayla <mikayla@zed.dev>
| Before | After |
|--------|-------|
| <video
src="https://github.com/user-attachments/assets/db4dcc91-9a32-4621-be78-87fe9d80b801"
controls width="400"></video> | <video
src="https://github.com/user-attachments/assets/8ee31d6d-5150-4239-a4af-eeca112d56d5"
controls width="400"></video> |
While working on something else I found this weird behaviour in message
editor of agent panel. When model names are too long, the model selector
would expand and push the send button outside the visible area. This
change fixes the flex layout to ensure the send button always remains
accessible while properly truncating long model names.
Closes #ISSUE
Release Notes:
- Fix agent panel model selector layout pushing send button off screen
---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Co-authored-by: Danilo Leal <67129314+danilo-leal@users.noreply.github.com>
We were previously displaying this modal in all open Zed windows if
triggered. That was a bit annoying because I had to go to each window
individually to close it, which meant doing it multiple times. 😅
Release Notes:
- agent: Fixed the MCP configuration modal to show only in the active
window.
Previously, upon hitting the "Continue" button to restart an interrupted
thread due to consecutive tool calls reaching its limit, you wouldn't
see the loading dots and the UI would be a weird state. This PR improves
when these loading dots actually show up, including in their conditional
a check for `message.is_hidden`.
Also took advantage of the opportunity to quickly organize some of these
variables. The `render_message` function could potentially be chopped up
in more smaller pieces. Lots of things going on here.
Release Notes:
- N/A
Mostly a small tweak making sure that the indicator tooltip hit area is
bigger and the loading state is clearer (not using an indicator
anymore). Way more little improvement opportunities in this component to
do, though.
Release Notes:
- N/A
- Improved colors
- Blank out diff hunk gutter highlights in conflict regions
- Paint conflict marker highlights all the way to the gutter
Release Notes:
- Improved the highlighting of merge conflict markers in editors.
---------
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
Co-authored-by: Cole Miller <cole@zed.dev>
Bubbles up rate limit information so that we can retry after a certain
duration if needed higher up in the stack.
Also caps the number of concurrent evals running at once to also help.
Release Notes:
- N/A
This was causing a lot of work on startup, particularly due to
instantiating edit tool cards. The minor downside is that now these
threads don't open quite as fast.
Includes a few other improvements:
* On text thread rename, now immediately updates the metadata for
display in the UI instead of waiting for reload.
* On text thread rename, first renames the file before writing. Before
if the file removal failed you'd end up with a duplicate.
* Now only stores text thread file names instead of full paths. This is
more concise and allows for the app data dir changing location.
* Renames `ThreadStore::unordered_threads` to
`ThreadStore::reverse_chronological_threads` (and removes the old one
that sorted), since the recent change to use a SQL database queries them
in that order.
* Removes `ContextStore::reverse_chronological_contexts` since it was
only used in one location where it does sorting anyway - no need to sort
twice.
* `SavedContextMetadata::title` is now `SharedString` instead of
`String`.
Release Notes:
- Fixed regression in startup performance by not deserializing and
instantiating recently opened agent threads.
Closes#32205
The issue was that in some places the end of the replacement range used
anchors with `Bias::Left` instead of `Bias::Right`. Before #31872
completions were recomputed on every change and so the anchor bias
didn't matter. After that change, the end anchor didn't move as the
user's typing. Changing it to `Bias::Right` to "stick" to the character
to the right of the cursor fixes this.
Release Notes:
- Fixes incorrect auto-completion of `/files` in text threads (Preview
Only)
The `async-watch` crate doesn't seem to be maintained and we noticed
several panics coming from it, such as:
```
[bug] failed to observe change after notificaton.
zed::reliability::init_panic_hook::{{closure}}::hea8cdcb6299fad6b+154543526
std::panicking::rust_panic_with_hook::h33b18b24045abff4+127578547
std::panicking::begin_panic_handler::{{closure}}::hf8313cc2fd0126bc+127577770
std::sys::backtrace::__rust_end_short_backtrace::h57fe07c8aea5c98a+127571385
__rustc[95feac21a9532783]::rust_begin_unwind+127576909
core::panicking::panic_fmt::hd54fb667be51beea+9433328
core::option::expect_failed::h8456634a3dada3e4+9433291
assistant_tools::edit_agent::EditAgent::apply_edit_chunks::{{closure}}::habe2e1a32b267fd4+26921553
gpui::app::async_context::AsyncApp::spawn::{{closure}}::h12f5f25757f572ea+25923441
async_task::raw::RawTask<F,T,S,M>::run::h3cca0d402690ccba+25186815
<gpui::platform::linux::x11::client::X11Client as gpui::platform::linux::platform::LinuxClient>::run::h26264aefbcfbc14b+73961666
gpui::platform::linux::platform::<impl gpui::platform::Platform for P>::run::hb12dcd4abad715b5+73562509
gpui::app::Application::run::h0f936a5f855a3f9f+150676820
zed::main::ha17f9a25fe257d35+154788471
std::sys::backtrace::__rust_begin_short_backtrace::h1edd02429370b2bd+154624579
std::rt::lang_start::{{closure}}::h3d2e300f10059b0a+154264777
std::rt::lang_start_internal::h418648f91f5be3a1+127502049
main+154806636
__libc_start_main+46051972301573
_start+12358494
```
I didn't find an executor-agnostic watch crate that was well maintained
(we already tried postage and async-watch), so decided to implement it
our own version.
Release Notes:
- Fixed a panic that could sometimes occur when the agent performed
edits.
This changes the context server crate so that the input/output for a
request are encoded at the type level, similar to how it is done for LSP
requests.
This also makes it easier to write tests that mock context servers, e.g.
you can write something like this now when using the `test-support`
feature of the `context-server` crate:
```rust
create_fake_transport("mcp-1", cx.background_executor())
.on_request::<context_server::types::request::PromptsList>(|_params| {
PromptsListResponse {
prompts: vec![/* some prompts */],
..
}
})
```
Release Notes:
- N/A
This allows storing the profile per thread, as well as moving the logic
of which tools are enabled or not to the profile itself.
This makes it much easier to switch between profiles, means there is
less global state being changed on every profile change.
Release Notes:
- agent panel: allow saving the profile per thread
---------
Co-authored-by: Ben Kunkle <ben.kunkle@gmail.com>
Noticed while working on #31848 that we do not support pasting images as
context in the inline assistant
Release Notes:
- agent: Add support for attaching images as context from clipboard in
the inline assistant
Closes#31781
Currently we don't any warning or error if the image is not supported by
the current model in selected in the agent panel which leads for users
to think it's supported as there is no visual feedback provided by zed.
This PR adds a warning on image context pill to show warning when the
model doesn't support it.
| Before | After |
|--------|-------|
| <img width="374" alt="image"
src="https://github.com/user-attachments/assets/da659fb6-d5da-4c53-8878-7a1c4553f168"
/> | <img width="442" alt="image"
src="https://github.com/user-attachments/assets/0f23d184-6095-47e2-8f2b-0eac64a0942e"
/> |
Release Notes:
- Show warning for image context pill in agent panel when selected model
doesn't support images.
---------
Signed-off-by: Umesh Yadav <git@umesh.dev>
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
This PR is a refactor of the existing `ModelType` in
`agent_model_selector`.
In #31848 we also need to know which context we are operating in, to
check if the configured model has image support.
In order to deduplicate the logic needed, I introduced a new type called
`ModelUsageContext` which can be used throughout the agent crate
Release Notes:
- N/A
Co-authored-by: Cole Miller <m@cole-miller.net>
Release Notes:
- agent: Fixed a panic when re-editing old messages
---------
Co-authored-by: Cole Miller <m@cole-miller.net>
Co-authored-by: Cole Miller <cole@zed.dev>
Also includes a clarity refactoring to remove
`ignore_completion_provider`.
Closes#15549
Release Notes:
- Fixed completions menu closing on typing after being requested while
`show_completions_on_input: false`.
This PR introduces the "Reject All" and "Accept All" buttons in the
panel's edit bar, which appears as soon as the agent starts editing a
file. I'm also adding here a new method to the thread called
`has_pending_edit_tool_uses`, which is a more specific way of knowing,
in comparison to the `is_generating` method, whether or not the
reject/accept all actions can be triggered.
Previously, without this new method, you'd be waiting for the whole
generation to end (e.g., the agent would be generating markdown with
things like change summary) to be able to click those buttons, when the
edit was already there, ready for you. It always felt like waiting for
the whole thing was unnecessary when you really wanted to just wait for
the _edits_ to be done, as so to avoid any potential conflicting state.
<img
src="https://github.com/user-attachments/assets/0927f3a6-c9ee-46ae-8f7b-97157d39a7b5"
width="500"/>
---
Release Notes:
- agent: Added ability to reject and accept all changes from the agent
panel.
---------
Co-authored-by: Agus Zubiaga <hi@aguz.me>
These started to be used more recently, so we should also support them.
Release Notes:
- agent: Added support for `AGENT.md` and `AGENTS.md` as rules file
names.
Users were giving feedback about the sound notification being
annoying/unnecessary if Zed is in the foreground, which I agree! So,
this PR changes it so that it only plays if that is not the case.
Release Notes:
- agent: Improved sound notification behavior by making it play only if
Zed is in the background.
This code path is not really an error, as it can happen due to normal,
albeit uncommon, actions. Like, for example, this scenario:
1. Create a thread X in Zed instance A
2. Open Zed instance B
3. Delete the thread X in instance A
4. Close instance B. This will write non-existing thread id X to
`agent-navigation-history.json`
5. Open Zed instance C. It won't be able to load the thread X.
Another way to get into this state is by running Zed with LMDB and
SQLite thread storages side-by-side.
In any case, this is not severe enough for an error.
Closes #ISSUE
Release Notes:
- N/A
The core change here is the following:
```rust
fn write_to_pty(&self, input: impl Into<Vec<u8>>);
// into
fn write_to_pty(&self, input: impl Into<Cow<'static, [u8]>>);
```
This matches the trait bounds that's used by the Alacritty crate. We are
now allowed to effectively pass `&'static str` instead of always needing
a `String`.
The main benefit comes from making the `to_esc_str` function return a
`Cow<'static, str>` instead of `String`. We save an allocation in the
following instances:
- When the user presses any special key that isn't alphanumerical (in
the terminal)
- When the uses presses any key while a modifier is active (in the
terminal)
- When focusing/un-focusing the terminal
- When completing or undoing a terminal transaction
- When starting a terminal assist
This basically saves us an allocation on **every key** press in the
terminal.
NOTE: This same optimization can be done for **nearly all** keypresses
in the entirety of Zed by changing the signature of the `Keystroke`
struct in gpui. If the Zed team is interested in a PR for it, let me
know.
Release Notes:
- N/A
When reaching the consecutive tool call limit, the agent gets blocked
and without a notification, you wouldn't know that. This PR adds the
ability to be notified when that happens, and you can use either sound
_and_ toast, or just one of them.
Release Notes:
- agent: Added support for getting notified (via toast and/or sound)
when reaching the consecutive tool call limit.
Release Notes:
- Fixed an issue that prevented `git::Restore` keybindings from working
in editors for buffers that had previously been modified by the agent.
Co-authored-by: Anthony Eid <hello@anthonyeid.me>
Also adds reuse of the markdown documentation cache even when
completions are re-queried, so that markdown documentation doesn't
flicker when `is_incomplete: true` (completions provided by rust
analyzer always set this)
Release Notes:
- Added support for filtering language server completions instead of
re-querying.
Previously, LMDB was used for storing threads, but it consumed excessive
disk space and was capped at 1GB.
This change migrates thread storage to an SQLite database. Thread JSON
objects are now compressed using zstd.
I considered training a custom zstd dictionary and storing it in a
separate table. However, the additional complexity outweighed the modest
space savings (up to 20%). I ended up using the default dictionary
stored with data.
Threads can be exported relatively easily from outside the application:
```
$ sqlite3 threads.db "SELECT hex(data) FROM threads LIMIT 5;" |
xxd -r -p |
zstd -d |
fx
```
Benchmarks:
- Original heed database: 200MB
- Sqlite uncompressed: 51MB
- sqlite compressed (this PR): 4.0MB
- sqlite compressed with a trained dictionary: 3.8MB
Release Notes:
- Migrated thread storage to SQLite with compression
This PR adds a Danger check to remind engineers that any changes to our
various prompts need to be verified against the LLM Worker.
When changes to the prompt files are detected, we will fail the PR with
a message:
<img width="929" alt="Screenshot 2025-05-30 at 8 40 58 AM"
src="https://github.com/user-attachments/assets/79afab4e-e799-45f1-a90e-0fd7c9a73706"
/>
Once the corresponding changes have been made (or no changes to the LLM
Worker have been determined to be necessary), including the indicated
attestation message will convert the errors into informational messages:
<img width="926" alt="Screenshot 2025-05-30 at 8 41 52 AM"
src="https://github.com/user-attachments/assets/ff51c17a-7a76-46a7-b468-a7d864d480c3"
/>
Release Notes:
- N/A
