In #32656 I generalized the argument to change selections to allow
controling both the scroll and the nav history (and the completion
trigger).
To avoid conflicting with ongoing debugger cherry-picks I left the
argument as an `impl Into<>`, but I think it's clearer to make callers
specify what they want here.
I converted a lot of `None` arguments to `SelectionEffects::no_scroll()`
to be exactly compatible; but I think many people used none as an "i
don't care" value in which case Default::default() might be more
appropraite
Closes #ISSUE
Release Notes:
- N/A
In #32656 I generalized the argument to change selections to allow
controling both the scroll and the nav history (and the completion
trigger).
To avoid conflicting with ongoing debugger cherry-picks I left the
argument as an `impl Into<>`, but I think it's clearer to make callers
specify what they want here.
I converted a lot of `None` arguments to `SelectionEffects::no_scroll()`
to be exactly compatible; but I think many people used none as an "i
don't care" value in which case Default::default() might be more
appropraite
Closes#32354
The issue is that we render selections over the text in the agent panel,
but under the text in editor, so themes that have no alpha for the
selection background color (defaults to 0xff) will just occlude the
selected region. Making the selection render under the text in markdown
would be a significant (and complicated) refactor, as selections can
cross element boundaries (i.e. spanning code block and a header after
the code block).
The solution is to add a new highlight to themes
`element_selection_background` that defaults to the local players
selection background with an alpha of 0.25 (roughly equal to 0x3D which
is the alpha we use for selection backgrounds in default themes) if the
alpha of the local players selection is 1.0. The idea here is to give
theme authors more control over how the selections look outside of
editor, as in the agent panel specifically, the background color is
different, so while an alpha of 0.25 looks acceptable, a different color
would likely be better.
CC: @iamnbutler. Would appreciate your thoughts on this.
> Note: Before and after using Everforest theme
| Before | After |
|-------| -----|
| <img width="618" alt="Screenshot 2025-06-09 at 5 23 10 PM"
src="https://github.com/user-attachments/assets/41c7aa02-5b3f-45c6-981c-646ab9e2a1f3"
/> | <img width="618" alt="Screenshot 2025-06-09 at 5 25 03 PM"
src="https://github.com/user-attachments/assets/dfb13ffc-1559-4f01-98f1-a7aea68079b7"
/> |
Clearly, the selection in the after doesn't look _that_ great, but it is
better than the before, and this PR makes the color of the selection
configurable by the theme so that this theme author could make it a
lighter color for better contrast.
Release Notes:
- agent panel: Fixed an issue with some themes where selections inside
the agent panel would occlude the selected text completely
Co-authored-by: Antonio <me@as-cii.com>
This cleans up our settings to not include any `version` fields, as we
have an actual settings migrator now.
This PR removes `language_models > anthropic > version`,
`language_models > openai > version` and `agent > version`.
We had migration paths in the code for a long time, so in practice
almost everyone should be using the latest version of these settings.
Release Notes:
- Remove `version` fields in settings for `agent`, `language_models >
anthropic`, `language_models > openai`. Your settings will automatically
be migrated. If you're running into issues with this open an issue
[here](https://github.com/zed-industries/zed/issues)
## Description of Feature or Change
Zed currently lacks a built-in way to convert a file’s indentation style
on the fly. While it's possible to change indentation behavior via
global or language-specific settings, these changes are persistent and
broad in scope as they apply to all files or all files of a given
language. We believe this could be improved for quick one-off
adjustments to specific files.
This PR introduces two new editor commands:
`Editor::convert_indentation_to_spaces` and
`Editor::convert_indentation_to_tabs`. These commands allow users to
convert the indentation of either the entire buffer or a selection of
lines, to spaces or tabs. Indentation levels are preserved, and any
mixed whitespace lines are properly normalized.
This feature is inspired by VS Code’s "Convert Indentation to
Tabs/Spaces" commands, but offers faster execution and supports
selection-based conversion, making it more flexible for quick formatting
changes.
## Implementation Details
To enable selection-based indentation conversion, we initially
considered reusing the existing `Editor::manipulate_lines` function,
which handles selections for line-based manipulations. However, this
method was designed specifically for operations like sorting or
reversing lines, and does not allow modifications to the line contents
themselves.
To address this limitation, we refactored the method into a more
flexible version: `Editor::manipulate_generic_lines`. This new method
passes a reference to the selected text directly into a callback, giving
the callback full control over how to process and construct the
resulting lines. The callback returns a `String` containing the modified
text, as well as the number of lines before and after the
transformation. These counts are computed using `.len()` on the line
vectors during manipulation, which is more efficient than calculating
them after the fact.
```rust
fn manipulate_generic_lines<M>(
&mut self,
window: &mut Window,
cx: &mut Context<Self>,
mut manipulate: M,
) where
M: FnMut(&str) -> (String, usize, usize),
{
// ... Get text from buffer.text_for_range() ...
let (new_text, lines_before, lines_after) = manipulate(&text);
// ...
```
We now introduce two specialized methods:
`Editor::manipulate_mutable_lines` and
`Editor::manipulate_immutable_lines`. Each editor command selects the
appropriate method based on whether it needs to modify line contents or
simply reorder them. This distinction is important for performance: when
line contents remain unchanged, working with an immutable reference as
`&mut Vec<&str>` is both faster and more memory-efficient than using an
owned `&mut Vec<String>`.
## Demonstration
https://github.com/user-attachments/assets/e50b37ea-a128-4c2a-b252-46c3c4530d97
Release Notes:
- Added `editor::ConvertIndentationToSpaces` and
`editor::ConvertIndentationToTabs` actions to change editor indents
---------
Co-authored-by: Pedro Silveira <pedroruanosilveira@tecnico.ulisboa.pt>
This PR is in preparation for doing automatic retries for certain
errors, e.g. Overloaded. It doesn't change behavior yet (aside from some
granularity of error messages shown to the user), but rather mostly
changes some error handling to be exhaustive enum matches instead of
`anyhow` downcasts, and leaves some comments for where the behavior
change will be in a future PR.
Release Notes:
- N/A
I saw recently we added diff-fenced edit parser which improves the
overall edit performance of gemini models in this PR: #32737. The idea
is to enable it to all the models which has gemini as their id as this
will help copilot and openrouter provider as they seem to aggregate all
these models under one umbrella. I thought about adding a new method in
LanguageModel as vendor_name() which returns the underlying actual model
provider name but felt like a too early abstraction for a method to be
used at one place.
Release Notes:
- N/A
This format is enabled for Google models as they seem to prefer it.
A relevant unit eval's pass rate has increased from 0.77 to 0.98.
Diff-fenced format looks like this (markdown fences and a line hint are
optional):
```diff
<<<<<<< SEARCH line=42
...
=======
...
>>>>>>> REPLACE
```
Release Notes:
- Agent: Gemini models now use the diff-fenced format when making edits
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>
These changes help the agent edit files when `<old_text>` matches more
than one location.
First, the agent can specify an optional `<old_text line=XX>` parameter.
When this is provided and multiple matches exist, we use this hint to
identify the best match.
Second, when there is ambiguity in matches, we now return the agent a
more helpful message listing the line numbers of all possible matches.
Together, these changes should reduce the number of misplaced edits and
agent confusion.
I have ensured the LLM Worker works with these prompt changes.
Release Notes:
- Agent: Improved locating edits
Adds some jitter to avoid the issue that all requests will retry at
roughly the same time in eval where we have a lot of concurrent
requests.
Release Notes:
- N/A
#31922 made embedded terminals automatically grow to fit the content. We
since found some issues with large output which this PR addresses by:
- Only shaping / laying out lines that are visible in the viewport
(based on `window.content_mask`)
- Falling back to embedded scrolling after 1K lines. The perf fix above
actually makes it possible to handle a lot of lines, but:
- Alacrity uses a `u16` for rows internally, so we needed a limit to
prevent overflow.
- Scrolling through thousands of lines to get to the other side of a
terminal tool call isn't great UX, so we might as well set the limit
low.
- We can consider raising the limit when we make card headers sticky.
Release Notes:
- Agent: Improve handling of large terminal output
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
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 PR fixes some broken links that where found using
[lychee](https://github.com/lycheeverse/lychee/) as discussed today with
@JosephTLyons and @nathansobo at the RustNL hackathon. Using
[lychee-action](https://github.com/lycheeverse/lychee-action/) we can
scan for broken links daily to prevent issues in the future.
There are still 6 broken links that I didn't know how to fix myself.
See https://github.com/thomas-zahner/zed/actions/runs/15075808232 for
details.
## Missing images
```
Errors in ./docs/src/channels.md
[ERROR] file:///home/runner/work/zed/zed/docs/.gitbook/assets/channels-3.png | Cannot find file
[ERROR] file:///home/runner/work/zed/zed/docs/.gitbook/assets/channels-1.png | Cannot find file
[ERROR] file:///home/runner/work/zed/zed/docs/.gitbook/assets/channels-2.png | Cannot find file
```
These errors are showing up as missing images on
https://zed.dev/docs/channels
I tried to search the git history to see when or why they were deleted
but didn't find anything.
## ./crates/assistant_tools/src/edit_agent/evals/fixtures/zode/prompt.md
There are three errors in that file. I don't fully understand how these
issues were caused historically. Technically it would be possible to
ignore the files but of course if possible we should address the issues.
Release Notes:
- N/A
---------
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
Co-authored-by: Ben Kunkle <ben@zed.dev>
Replace hardcoded 0.10 threshold with configurable parameter and set
0.05 default for most tests, with 0.2 for from_pixels_constructor
eval that produces more mismatched tags.
Release Notes:
- N/A
We run the unit evals once a day in the middle of the night, and trigger
a Slack post if it fails.
Release Notes:
- N/A
---------
Co-authored-by: Oleksiy Syvokon <oleksiy.syvokon@gmail.com>
This problem seems to be specific to Opus 4. Eval shows improvement from
89% to 97%.
Closes: https://github.com/zed-industries/zed/issues/32060
Release Notes:
- N/A
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
Based on a Slack conversation with @notpeter - this prevents secrets in
private/excluded files from being sent by the agent to third parties for
tools that don't require confirmation.
Of course, the agent can still use the terminal tool or MCP to access
these, but those require confirmation before they run (unlike these
tools).
This change doesn't seem to cause any trouble for evals:
<img width="730" alt="Screenshot 2025-06-03 at 8 48 33 PM"
src="https://github.com/user-attachments/assets/d90221be-f946-4af2-b57b-4aa047e86853"
/>
Release Notes:
- N/A
When `<old_text>` points to more than one location in a file, we used to
edit the first match, confusing the agent along the way. Now we will
return an error, asking to expand `<old_text>` selection.
Closes #ISSUE
Release Notes:
- agent: Fixed incorrect file edits when edit locations are ambiguous
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>
The terminal tool card used a fixed height and scrolling, but this meant
that it was too tall for commands that only outputted a few lines, and
the nested scrolling was undesirable.
This PR makes the card be as too as needed to fit the entire output (no
scrolling), and allows the user to collapse it to fewer lines when
applicable. Making it work the same way as the edit tool card. In fact,
both tools now use a shared UI component.
https://github.com/user-attachments/assets/1127e21d-1d41-4a4b-a99f-7cd70fccbb56
Release Notes:
- Agent: Display full terminal output
- Agent: Allow collapsing terminal output
Another batch of allocation savings. Noteworthy ones are
`find_path_tool.rs` where one clone of *all* found matches was saved and
`web_tool_search.rs` where the tooltip no longer clones the entire url
on every hover.
I'd also like to propose using `std::borrow::Cow` a lot more around the
codebase instead of Strings. There are hundreds if not 1000+ clones that
can be saved pretty regularly simply by switching to Cow. ´Cow´'s are
likely not used because they aren't compatible with futures and because
it could cause lifetime bloat. However if we use `Cow<'static, str>`
(static lifetime) for when we need to pass them into futures, we could
save a TON of allocations for `&'static str`. Additionally I often see
structs being created using `String`'s just to be deserialized
afterwards, which only requires a reference.
Release Notes:
- N/A
This PR adds a new `intent` field to completion requests to assist in
categorizing them correctly.
Release Notes:
- N/A
---------
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
Re-enables format on save for agent changes (when the user has that
enabled in settings), except differently from before:
- Now we do the format-on-save in the separate buffer the edit tool
uses, *before* the diff
- This means it never triggers separate staleness
- It has the downside that edits are now blocked on the formatter
completing, but that's true of saving in general.
Release Notes:
- N/A
---------
Co-authored-by: Agus Zubiaga <hi@aguz.me>
This pull request removes orphaned description.md files for tools that
were deleted in [PR
#29808](https://github.com/zed-industries/zed/pull/29808). These
descriptions are no longer needed as their corresponding tools no longer
exist
Closes #ISSUE
Release Notes:
- N/A
Previously disabled both scrollbars, but horizontal scrolling is still
needed when
lines exceed the viewport width. Now editors can disable a single scroll
axis, not just both.
Release Notes:
- N/A
Looks like I accidentally touched a line of code in an eval fixture in
#31479, despite intentionally trying to avoid that code. Thanks
@cole-miller!
Release Notes:
- N/A
This change instructs models to wrap new file content in Markdown fences
and introduces a parser for this format. The reasons are:
1. This is the format we put a lot of effort into explaining in the
system prompt.
2. Gemini really prefers to do it.
3. It adds an option for a model to think before writing the content
The `eval_zode` pass rate for GEmini models goes from 0% to 100%. Other
models were already at 100%, this hasn't changed.
Release Notes:
- N/A
An unintended consequence of format on save is that we start (correctly)
informing the model that the file changed on disk every time the
formatter changes anything, which in turn can lead the model to things
like extra reads.
Until we have a solution in place to prevent this downside, we're going
back to not formatting on save by reverting
cb112a4012.
Release Notes:
- N/A
Open inspector with `dev: toggle inspector` from command palette or
`cmd-alt-i` on mac or `ctrl-alt-i` on linux.
https://github.com/user-attachments/assets/54c43034-d40b-414e-ba9b-190bed2e6d2f
* Picking of elements via the mouse, with scroll wheel to inspect
occluded elements.
* Temporary manipulation of the selected element.
* Layout info and JSON-based style manipulation for `Div`.
* Navigation to code that constructed the element.
Big thanks to @as-cii and @maxdeviant for sorting out how to implement
the core of an inspector.
Release Notes:
- N/A
---------
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
Co-authored-by: Federico Dionisi <code@fdionisi.me>
This change improves `eval_extract_handle_command_output` results for
all models:
Model | Pass rate before | Pass rate after
----------------------------|------------------|----------------
claude-3.7-sonnet | 0.96 | 0.98
gemini-2.5-pro | 0.35 | 0.86
gpt-4.1 | 0.81 | 1.00
Part of this improvement comes from more robust evaluation, which now
accepts multiple possible outcomes. Another part is from the prompt
adaptation: addressing common Gemini failure modes, adding a few-shot
example, and, in the final commit, auto-rewriting instructions for
clarity and conciseness.
This change still needs validation from larger end-to-end evals.
Release Notes:
- N/A
1. Add system prompt: this is how it's called from threads. Previously,
we were sending
2. Fix an issue with writing agent thought into a newly created empty
file.
Release Notes:
- N/A
---------
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
Co-authored-by: Antonio Scandurra <me@as-cii.com>
https://github.com/zed-industries/zed/issues/30972 brought up another
case where our context is not enough to track the actual source of the
issue: we get a general top-level error without inner error.
The reason for this was `.ok_or_else(|| anyhow!("failed to read HEAD
SHA"))?; ` on the top level.
The PR finally reworks the way we use anyhow to reduce such issues (or
at least make it simpler to bubble them up later in a fix).
On top of that, uses a few more anyhow methods for better readability.
* `.ok_or_else(|| anyhow!("..."))`, `map_err` and other similar error
conversion/option reporting cases are replaced with `context` and
`with_context` calls
* in addition to that, various `anyhow!("failed to do ...")` are
stripped with `.context("Doing ...")` messages instead to remove the
parasitic `failed to` text
* `anyhow::ensure!` is used instead of `if ... { return Err(...); }`
calls
* `anyhow::bail!` is used instead of `return Err(anyhow!(...));`
Release Notes:
- N/A
This eval checks that Edit Agent can create an empty file without
writing its thoughts into it. This issue is not specific to empty files,
but it's easier to reproduce with them.
For some mysterious reason, I could easily reproduce this issue roughly
90% of the time in actual Zed. However, once I extract the exact LLM
request before the failure point and generate from that, the
reproduction rate drops to 2%!
Things I've tried to make sure it's not a fluke: disabling prompt
caching, capturing the LLM request via a proxy server, running the
prompt on Claude separately from evals. Every time it was mostly giving
good outcomes, which doesn't match my actual experience in Zed.
At some point I discovered that simply adding one insignificant space or
a newline to the prompt suddenly results in an outcome I tried to
reproduce almost perfectly.
This weirdness happens even outside the Zed code base and even when
using a different subscription. The result is the same: an extra newline
or space changes the model behavior significantly enough, so that the
pass rate drops from 99% to 0-3%
I have no explanation to this.
Release Notes:
- N/A
This PR makes the edit tool call codeblock cards expanded by default, to
be consistent with https://github.com/zed-industries/zed/pull/30806.
Also, I am removing the collapsing behavior of Markdown codeblocks where
we'd add a gradient while capping the container's height based on an
arbitrary number of lines. Figured if they're all now initially
expanded, we could simplify how the design/code operates here
altogether.
Open for feedback, as I can see an argument where the previous Markdown
codeblock design of "collapsed but not fully; it shows a preview" should
stay as it is useful.
Release Notes:
- N/A
