Somehow we have a regression where the auth wasn't being called, so the
model didn't exist.
Looking at the code, it is likely this was relying on some other part of
the code doing the auth, since the order wouldn't have worked before
without that happening. This new order of doing auth before checking for
available models should fix it going forward.
Release Notes:
- N/A
Extracts and cleans up GPUI's scheduler code into a new `scheduler`
crate, making it pluggable by external runtimes. This will enable
deterministic integration testing with cloud components by providing a
unified test scheduler across Zed and backend code. In Zed, it will
replace the existing GPUI scheduler for consistent async task management
across platforms.
## Changes
- **Core Implementation**: `TestScheduler` with seed-based
randomization, session tracking (`SessionId`), and foreground/background
task separation for reproducible testing.
- **Executors**: `ForegroundExecutor` (!Send, thread-local) and
`BackgroundExecutor` (Send, with blocking/timeout support) as
GPUI-compatible wrappers.
- **Clock and Timer**: Controllable `TestClock` and future-based `Timer`
for time-sensitive tests.
- **Testing APIs**: `once()`, `with_seed()`, and `many()` methods for
configurable test runs.
- **Dependencies**: Added `async-task`, `chrono`, `futures`, etc., with
updates to `Cargo.toml` and lock file.
## Benefits
- **Integration Testing**: Facilitates reliable async tests involving
cloud sessions, reducing flakiness via deterministic execution.
- **Pluggability**: Trait-based design (`Scheduler`) allows easy
integration into non-GPUI runtimes while maintaining GPUI compatibility.
- **Cleanup**: Refactors GPUI scheduler logic for clarity, correctness
(no `unwrap()`, proper error handling), and extensibility.
Follows Rust guidelines; run `./script/clippy` for verification.
- [x] Define and test a core scheduler that we think can power our cloud
code and GPUI
- [ ] Replace GPUI's scheduler
Release Notes:
- N/A
---------
Co-authored-by: Antonio Scandurra <me@as-cii.com>
This removes around 900 unnecessary clones, ranging from cloning a few
ints all the way to large data structures and images.
A lot of these were fixed using `cargo clippy --fix --workspace
--all-targets`, however it often breaks other lints and needs to be run
again. This was then followed up with some manual fixing.
I understand this is a large diff, but all the changes are pretty
trivial. Rust is doing some heavy lifting here for us. Once I get it up
to speed with main, I'd appreciate this getting merged rather sooner
than later.
Release Notes:
- N/A
This pull request should be idempotent, but lays the groundwork for
avoiding to connect to collab in order to interact with AI features
provided by Zed.
Release Notes:
- N/A
---------
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
This PR updates the Agent panel to work with the `CloudUserStore`
instead of the `UserStore`, reducing its reliance on being connected to
Collab to function.
Release Notes:
- N/A
---------
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
This introduces a new field `thinking_allowed` on `LanguageModelRequest`
which lets us control whether thinking should be enabled if the model
supports it.
We permit thinking in the Inline Assistant, Edit File tool and the Git
Commit message generator, this should make generation faster when using
a thinking model, e.g. `claude-sonnet-4-thinking`
Release Notes:
- N/A
* Updates to `zed_llm_client-0.8.5` which adds support for `retry_after`
when anthropic provides it.
* Distinguishes upstream provider errors and rate limits from errors
that originate from zed's servers
* Moves `LanguageModelCompletionError::BadInputJson` to
`LanguageModelCompletionEvent::ToolUseJsonParseError`. While arguably
this is an error case, the logic in thread is cleaner with this move.
There is also precedent for inclusion of errors in the event type -
`CompletionRequestStatus::Failed` is how cloud errors arrive.
* Updates `PROVIDER_ID` / `PROVIDER_NAME` constants to use proper types
instead of `&str`, since they can be constructed in a const fashion.
* Removes use of `CLIENT_SUPPORTS_EXA_WEB_SEARCH_PROVIDER_HEADER_NAME`
as the server no longer reads this header and just defaults to that
behavior.
Release notes for this is covered by #33275
Release Notes:
- N/A
---------
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
Co-authored-by: Richard <richard@zed.dev>
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
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 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>
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
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
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
1. The `edit_file` tool tended to use `create_or_overwrite` a bit too
often, leading to corruption of long files. This change replaces the
boolean flag with an `EditFileMode` enum, which helps Agent make a more
deliberate choice when overwriting files.
With this change, the pass rate of the new eval increased from 10% to
100%.
2. eval: Added ability to run eval on top of an existing thread. Threads
can now be loaded from JSON files in the `SerializedThread` format,
which makes it easy to use real threads as starting points for
tests/evals.
3. Don't try to restore tool cards when running in headless or eval mode
-- we don't have a window to properly do this.
Release Notes:
- N/A
This is very basic support for them. There are a number of other TODOs
before this is really a first-class supported feature, so not adding any
release notes for it; for now, this PR just makes it so that if
read_file tries to read a PNG (which has come up in practice), it at
least correctly sends it to Anthropic instead of messing up.
This also lays the groundwork for future PRs for more first-class
support for images in tool calls across more image file formats and LLM
providers.
Release Notes:
- N/A
---------
Co-authored-by: Agus Zubiaga <hi@aguz.me>
Co-authored-by: Agus Zubiaga <agus@zed.dev>
This allows us to debug the raw edits that were generated when people
report feedback, when running evals and when opening the thread as
Markdown.
Release Notes:
- Improved debug output for agent threads.
Release Notes:
- Fixed a bug that would prevent the agent from working over SSH.
---------
Co-authored-by: Nathan Sobo <nathan@zed.dev>
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Cole Miller <m@cole-miller.net>
David Kleingeld
Ben Brandt
Nathan SoboandAntonio Scandurra
tidely
Piotr Osiewicz
Kirill Bulatov
Oleksiy Syvokon
Bennet Bo Fenner
Rodrigo FreireandPedro Silveira
Umesh Yadav
Max BrunsfeldandBen Brandt
shenjack
Joseph T. Lyons
