This PR restructures the subcommands in `zeta-cli`, so that the
prediction engine (currently `zeta1` vs `zeta2`) is no longer the
highest order subcommand. Instead, there is just one layer of
subcommands: `eval`, `predict`, `context`, etc. Within these commands,
there are flags for using `zeta1`, `zeta2`, and now `sweep`.
Release Notes:
- N/A
---------
Co-authored-by: Ben Kunkle <ben@zed.dev>
Co-authored-by: Agus <agus@zed.dev>
Closes #ISSUE
The model often uses the wrong closing tag, or has spaces around the
closing tag name. This PR makes it so that opening tags are treated as
authoritative and any closing tag with the name `new_text` `old_text` or
`edits` is accepted based on depth. This has the additional benefit that
the parsing is more robust with contents that contain `new_text`
`old_text` or `edits. I.e. the following test passes
```rust
#[test]
fn test_extract_xml_edits_with_conflicting_content() {
let input = indoc! {r#"
<edits path="component.tsx">
<old_text>
<new_text></new_text>
</old_text>
<new_text>
<old_text></old_text>
</new_text>
</edits>
"#};
let result = extract_xml_replacements(input).unwrap();
assert_eq!(result.file_path, "component.tsx");
assert_eq!(result.replacements.len(), 1);
assert_eq!(result.replacements[0].0, "<new_text></new_text>");
assert_eq!(result.replacements[0].1, "<old_text></old_text>");
}
```
Release Notes:
- N/A *or* Added/Fixed/Improved ...
This prompt is for a fine-tuned model. It has the following changes,
compared to `minimal`:
- No instructions at all, except for one sentence at the beginning of
the prompt.
- Output is a simplified unified diff -- hunk headers have no line
counts (e.g., `@@ -20 +20 @@`)
- Qwen's FIM tokens are used where possible (`<|file_sep|>`,
`<|fim_prefix|>`, `<|fim_suffix|>`, etc.)
To evaluate this model:
```
ZED_ZETA2_MODEL=zeta2-exp [usual zeta-cli eval params ...] --prompt-format minimal-qwen
```
This will point to the most recent Baseten deployment of zeta2-exp
(which may change in the future, so the prompt-format may get out of
sync).
Release Notes:
- N/A
This PR improves Zeta2's matching of `old_text`/`new_text` pairs, using
similar code to what we use in the edit agent. For right now, we've
duplicated the code, as opposed to trying to generalize it.
Release Notes:
- N/A
---------
Co-authored-by: Max <max@zed.dev>
Co-authored-by: Michael <michael@zed.dev>
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Agus <agus@zed.dev>
1. Add `--prompt-format=minimal` that matches single-sentence
instructions used in fine-tuned models (specifically, in `1028-*` and
`1029-*` models)
2. Use separate configs for agentic context search model and edit
prediction model. This is useful when running a fine-tuned EP model, but
we still want to run vanilla model for context retrieval.
3. `zeta2-exp` is a symlink to the same-named Baseten deployment. This
model can be redeployed and updated without having to update the
deployment id.
4. Print scores as a compact table
Release Notes:
- N/A
---------
Co-authored-by: Piotr Osiewicz <piotr@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>
- Improves the determinism of the search step for better cache
reusability
- Adds a `--cache force` mode that refuses to make any requests or
searches that aren't cached
- The structure of the `zeta-*` directories under `target` has been
rethought for convenience
Release Notes:
- N/A
---------
Co-authored-by: Agus <agus@zed.dev>
Closes #ISSUE
Improves error reporting for various failure modes of zeta2, including
failing to parse the `<old_text>`/`<new_text>` pattern, and the contents
of `<old_text>` failing to match.
Additionally, makes it so that evals are checked out into a worktree
with the _repo_ name instead of the _example_ name, in order to make
sure that the eval name has no influence on the models prediction. The
repo name worktrees are still namespaced by the example name like
`{example_name}/{repo_name}` to ensure evals pointing to the same repo
do not conflict.
Release Notes:
- N/A *or* Added/Fixed/Improved ...
---------
Co-authored-by: Agus <agus@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>
I wanted to be able to work offline, so I made it a little bit more
convenient to point zeta2 at ollama.
* For zeta2, don't require that request ids be UUIDs
* Add an env var `ZED_ZETA2_OLLAMA` that sets the edit prediction URL
and model id to work w/ ollama.
Release Notes:
- N/A
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>
* Fix a panic that happened because we lost the
`ContextRetrievalStarted` debug message, so we didn't assign `t0`.
* Write the edit prediction response log file as a markdown file
containing the text, not a JSON file. We mostly always want the text
content.
Release Notes:
- N/A
This PR adds a `zeta zeta2 predict` subcommand that takes an edit
prediction example markdown file as an argument, and performs zeta2's
prediction, showing the retrieved context and the predicted edit.
* [x] Apply uncommitted diff to get repo into the right state.
* [x] Apply edits in edit history
* [x] Display predicted edits as unified diff, regardless of model
output format
Release Notes:
- N/A
---------
Co-authored-by: Agus Zubiaga <agus@zed.dev>
Co-authored-by: Piotr Osiewicz <24362066+osiewicz@users.noreply.github.com>
Co-authored-by: Ben Kunkle <ben.kunkle@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>
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
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
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>
This PR adds support for browser debugging in SSH and WSL projects. We
use the vscode-js-debug-companion extension, repackaged as a standalone
CLI (https://github.com/zed-industries/js-debug-companion-cli).
Closes#38878
Release Notes:
- debugger: Browser debugging is now supported in SSH and WSL projects.
---------
Co-authored-by: Nia <nia@zed.dev>
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>
Also skips indexing files that don't have a suffix that indicates a
known language, and skips when the language doesn't have an outline
grammar.
Release Notes:
- N/A
---------
Co-authored-by: Agus <agus@zed.dev>
Closes https://github.com/zed-industries/zed/issues/38690Closes#37353
### Background
On Windows, paths are normally separated by `\`, unlike mac and linux
where they are separated by `/`. When editing code in a project that
uses a different path style than your local system (e.g. remoting from
Windows to Linux, using WSL, and collaboration between windows and unix
users), the correct separator for a path may differ from the "native"
separator.
Previously, to work around this, Zed converted paths' separators in
numerous places. This was applied to both absolute and relative paths,
leading to incorrect conversions in some cases.
### Solution
Many code paths in Zed use paths that are *relative* to either a
worktree root or a git repository. This PR introduces a dedicated type
for these paths called `RelPath`, which stores the path in the same way
regardless of host platform, and offers `Path`-like manipulation APIs.
RelPath supports *displaying* the path using either separator, so that
we can display paths in a style that is determined at runtime based on
the current project.
The representation of absolute paths is left untouched, for now.
Absolute paths are different from relative paths because (except in
contexts where we know that the path refers to the local filesystem)
they should generally be treated as opaque strings. Currently we use a
mix of types for these paths (std::path::Path, String, SanitizedPath).
Release Notes:
- N/A
---------
Co-authored-by: Cole Miller <cole@zed.dev>
Co-authored-by: Piotr Osiewicz <24362066+osiewicz@users.noreply.github.com>
Co-authored-by: Peter Tripp <petertripp@gmail.com>
Co-authored-by: Smit Barmase <heysmitbarmase@gmail.com>
Co-authored-by: Lukas Wirth <me@lukaswirth.dev>
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
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>
