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>
Adds an action to open the notes for the currently selected channel in
the collab panel, which is mapped to `alt-enter` in all platforms.
Release Notes:
- collab: Add `collab_panel::OpenSelectedChannelNotes` action
(`alt-enter` by default)
We'll now perform all searches from the context model concurrently, and
combine queries for the same glob into one reducing the total number of
project searches.
For better readability, the debug context view now displays each
top-level regex alternation individually, grouped by its corresponding
glob:
<img width="1592" height="672" alt="CleanShot 2025-10-29 at 19 56 03@2x"
src="https://github.com/user-attachments/assets/f6e8408e-09d6-4e27-ba11-a739a772aa12"
/>
Release Notes:
- N/A
I noticed we had some typos that were getting through CI, but it looks
like the new version of `typos` catches them. So I updated it and fixed
them.
Release Notes:
- N/A
Adds a way to submit feedback about a zeta2 prediction from the
inspector. The telemetry event includes:
- project snapshot (git + unsaved buffer state)
- the full request and response
- user feedback kind and text
Release Notes:
- N/A
Instead of producing multiple code blocks for each edit history event,
we now produce a continuous unified diff.
Release Notes:
- N/A
---------
Co-authored-by: Oleksiy Syvokon <oleksiy.syvokon@gmail.com>
Adds a new `NumberedLines` format which is similar to `MarkedExcerpt`
but each line is prefixed with its line number.
Also fixes a bug where contagious snippets wouldn't get merged.
Release Notes:
- N/A
---------
Co-authored-by: Michael Sloan <mgsloan@gmail.com>
Co-authored-by: Michael <michael@zed.dev>
Retrieval stats will now use polars to build a big data frame for
references with the cartesian product of LSP declarations and retrieved
declaration candidates (with all their score components) and rebuilds
the stats summary on top of it.
This data frame is written to a `.parquet` file, which we can load into
advanced analytics tools (such as Metabase), so we can explore our
scoring distributions and find ways to improve retrieval, and then train
the decision tree.
Release Notes:
- N/A
Gathering LSP declarations in zeta_cli can take a really long time for
big repos and has to be started from scratch if interrupted.
Instead of writing the cache file once we have walked the whole
worktree, we'll now do so incrementally as we complete each file. On
subsequent runs, we'll load as many valid declarations as has been
previously written to the cache, and then continue to request the rest
from the LSP which will append to the existing file as it makes
progress. If the last cache entry is incomplete, we'll truncate the
cache file to the end of the last valid line and continue from there, so
we can just `ctrl-c` without breaking resumability.
Release Notes:
- N/A
Plans and displays the prompt locally before the response arrives.
Helpful while debugging prompt planning.
Release Notes:
- N/A
---------
Co-authored-by: Michael Sloan <mgsloan@gmail.com>
The new cloud endpoint returns structured edits, but they may include
more of the input excerpt than what we want to display in the preview,
so we compute a smaller diff on the client side against the snapshot.
Release Notes:
- N/A
Nowadays, people don't expect @-mentioning a directory to include the
contents of all files within it. Doing so makes it very likely to
consume an undesirable amount of tokens.
By default, we'll now only include the path of the directory and let the
model decide how much to read via tools. We'll still include the
contents if no tools are available (e.g. "Minimal" profile is selected).
Release Notes:
- Agent Panel: Do not include the content of @-mentioned directories
when tools are available
The edit prediction debug tools has been renamed to zeta2 inspector
because it's now zeta specific. It will now always display the last
prediction request context, prompt, and model response.
Release Notes:
- N/A
---------
Co-authored-by: Bennet <bennet@zed.dev>
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Creates a new `EditPredictionProvider` for zeta2, that requests
completions from a new cloud endpoint including context from the new
`edit_prediction_context` crate. This is not ready for use, but it
allows us to iterate.
Release Notes:
- N/A
---------
Co-authored-by: Michael Sloan <michael@zed.dev>
Co-authored-by: Bennet <bennet@zed.dev>
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Adds a `dev: open edit prediction context` action that opens a new
workspace pane that displays the excerpts and snippets that would be
included in the edit prediction request.
Release Notes:
- N/A
---------
Co-authored-by: Bennet <bennet@zed.dev>
It appears that in macOS, the `AcpConnection._wait_task` doesn't always
get dropped when quitting the app. In these cases, the subprocess would
be kept alive because we move the `child` into it.
Instead, we will now explicitly kill it when `AcpConnection` is dropped.
It's ok to do this because when the connection is dropped, the thread is
also dropped, so there's no need to report the exit status to it.
Closes#37741
Release Notes:
- Claude Code: Fix subprocess leak on app quit
The `PromptCapabilities` introduced in previous PRs were only getting
set on the main message editor and not for the editors in user messages.
This caused a bug where mentions would disappear after resending the
message, and for the completion provider to be limited to files.
Release Notes:
- N/A
The loading diff animation can be jarring for external agents because
they stream the diff at the same time the tool call is pushed, so it's
only displayed while we're asynchronously calculating the diff. We'll
now only show it for the native agent.
Also, we'll now only update the diff when it changes, which avoids
unnecessarily hiding it for a few frames.
Release Notes:
- N/A
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
The completion provider was already limiting the mention kinds according
to `acp::PromptCapabilities`. However, it was still using
`ContentBlock::EmbeddedResource` when
`acp::PromptCapabilities::embedded_context` was `false`. We will now use
`ResourceLink` in that case making it more complaint with the
specification.
Release Notes:
- N/A
This PR adds a temporary workaround to supress "Aborted" errors from
Gemini when cancelling generation. This won't be needed once
https://github.com/google-gemini/gemini-cli/pull/6656 is generally
available.
Release Notes:
- N/A
Agus Zubiaga
