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
- Return unified diff from `Edit` tool so model can see the final state
- Format on save if enabled
- Provide `Write` tool
- Disable `MultiEdit` tool
- Better prompting
Release Notes:
- N/A
We'll now use the anthropic provider to get credentials for `claude` and
embed its configuration view in the panel when they are not present.
Release Notes:
- N/A
The view was cancelling the generation, but `AcpThread` already handles
that, so we removed that extra code and fixed a bug where an update from
the first user message would appear after the second one.
Release Notes:
- N/A
Co-authored-by: Danilo <danilo@zed.dev>
When a turn ends and the checkpoint is updated, `AcpThread` emits
`EntryUpdated` with the index of the user message. This was causing the
message editor to be recreated and, therefore, lose focus.
Release Notes:
- N/A
We were leaking diffs and terminals on rewind, we'll now clean them up.
This PR also introduces a refactor of how we mantain the entry view
state to use a `Vec` that's kept in sync with the thread entries.
Release Notes:
- N/A
Fixes a bug where generation wouldn't continue after interrupting the
agent, and improves CC cancellation so we don't display "[Request
interrupted by user]"
Release Notes:
- N/A
---------
Co-authored-by: Cole Miller <cole@zed.dev>
This also adds a convenient `Scrollbar:auto_hide` function so that we
don't have to handle that at the callsite.
Release Notes:
- N/A
---------
Co-authored-by: David Kleingeld <davidsk@zed.dev>
When you switched away from an ACP thread, the `AcpThreadView` entity
(and thus thread, and subprocess) was leaked. This happened because we
were using `cx.processor` for the `list` state callback, which uses a
strong reference.
This PR changes the callback so that it holds a weak reference, and adds
some tests and assertions at various levels to make sure we don't
reintroduce the leak in the future.
Release Notes:
- N/A