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
`ActiveThread` and `MessageEditor` only make sense when `active_view` is
`Thread`, so we moved them in there. This will make it easier to work on
new agent threads.
Release Notes:
- N/A
---------
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Conrad Irwin <conrad.irwin@gmail.com>
Co-authored-by: Smit Barmase <heysmitbarmase@gmail.com>
#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
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
https://github.com/zed-industries/zed/pull/31668 renamed
`CompletionMode::Max` to `CompletionMode::Burn` which is a good change,
but this broke the deserialization for threads whose completion mode was
stored in LMDB. This adds a deserialization alias so that both values
work.
We could make a full new `SerializedThread` version which migrates this
value, but that seems overkill for this single change, we can batch that
with more changes later. Also, people in nightly already have some v1
threads with `burn` stored, so it wouldn't quite work for everybody.
Release Notes:
- N/A
The title of a (text) thread would get stuck in "Loading Summary..."
when the request to generate it failed. We now handle this case by
falling back to the default title, and letting the user manually edit
the title or retry generating it.
https://github.com/user-attachments/assets/898d26ad-d31f-4b62-9b05-519d923b1b22
Release Notes:
- agent: Handle thread title generation errors
---------
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
- Try to preserve previously selected item on update
- Do not clear list items while updating to avoid a frame with no items
rendered
Release Notes:
- agent: Preserve previously selected item in Thread History on update
---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
We were still using entry indexes to scroll, but the list now includes
the separators as items, so the indexes need to be translated
Release Notes:
- agent: Fix autoscrolling to history entry when navigating via keyboard
Fixes an issue introduced by #29959 which caused the message editor to
overflow from the agent panel bounds, making the bottom buttons
invisible when the editor was expanded (cmd+esc).
Fixing this required changing the base structure of the agent panel, but
things seem to work as expected:
https://github.com/user-attachments/assets/fc4c97fb-f7cb-4f54-a268-c30fbcb1649f
Release Notes:
- agent: Fix message editor's button positions when expanded
Turns out `naive_local` doesn't actually offset a `DateTime<Utc>` to the
local timezone before creating a `NaiveDate`.
Release Notes:
- agent: Use correct timezone for thread history separators
Adds a new `agent.model_parameters` setting that allows the user to
specify a custom temperature for a provider AND/OR model:
```json5
"model_parameters": [
// To set parameters for all requests to OpenAI models:
{
"provider": "openai",
"temperature": 0.5
},
// To set parameters for all requests in general:
{
"temperature": 0
},
// To set parameters for a specific provider and model:
{
"provider": "zed.dev",
"model": "claude-3-7-sonnet-latest",
"temperature": 1.0
}
],
```
Release Notes:
- agent: Allow customizing temperature by provider/model
---------
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
Closes#29836
The agent diff toolbar item was causing the editor toolbar to show even
when all the other elements were disabled via settings.
This PR fixes this by setting the location to
`ToolbarItemLocation::Hidden` in the states where it shouldn't show.
It also adds a new a `toolbar.agent_review` setting to hide the agent
review buttons altogether. However, if the other toolbar elements are
hidden and the file isn't under review, the editor toolbar will still be
hidden. So you only need to set this to `false` if you don't want them
to show up even under agent review.
Release Notes:
- N/A
Enables reviewing agent edits from single-file editors in addition to
the multibuffer experience we already had.
https://github.com/user-attachments/assets/a2c287f0-51d6-43a1-8537-821498b91983
This feature can be turned off by setting `assistant.single_file_review:
false`.
Release Notes:
- agent: Review edits in single-file editors
Adds popular examples of long-running commands to system prompt.
Unfortunately, I couldn't add an eval example as the new terminal tool
no longer works in `eval`. We can look into that tomorrow, but I'm
seeing improvements when manually testing this, so I'd like to merge it.
<img
src="https://github.com/user-attachments/assets/ac24e617-e068-466f-875d-c30e1f2465c4"
width=400></img>
Release Notes:
- agent: Discourage long-running commands
The `grep` tool used to include 4 lines of context around the match, but
the lines included would often be unhelpful. This PR improves this
behavior by using the range of the parent syntax node that contains the
full line(s) matched.
The match headers will also now include symbol breadcrumbs so that the
model can already gather code structure before/without reading files.
````md
### impl GitRepository for RealGitRepository › fn compare_checkpoints › L1278-1284
```rust
let result = git
.run(&[
"diff-tree",
"--quiet",
&left.commit_sha.to_string(),
&right.commit_sha.to_string(),
])
```
````
This positively impacts the `add_arg_to_trait_method` eval example with
better diff output, fewer tool failures, and reduced total turns.
Note: We have some plans to use a an "elision" approach where we would
combine all matches for a given file, skipping lines between them while
keeping symbol declaration lines. The theory is that this would be map
more closely to the expected input for edits. For now, this PR is a
significant improvement.
Release Notes:
- Agent: Enrich `grep` tool output with syntax information
#29354 introduced a bug where we would append tool uses to the last
assistant message even if it was from a previous request.
Release Notes:
- N/A
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
We used to insert empty user messages into the `Thread::messages` `Vec`
when tools finished running and then we would attach the results when
creating the request. This approach was very easy to mess up during
state handling, leading to empty user messages displayed in the
conversation and API failures.
Instead, we will no longer insert actual user messages for tool results
to the `Thread`, and will only do this on the fly when creating the
model request. This simplifies a lot of code and show fix the mentioned
errors.
Release Notes:
- agent: Improve reliability of LLM requests when including tool results
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Co-authored-by: Oleksiy Syvokon <oleksiy.syvokon@gmail.com>
This PR significantly improves the quality of the initial file search
that occurs when the model doesn't yet know the full path to a file it
needs to read/edit.
Previously, the assertions in file_search often failed on main as the
model attempted to guess full file paths. On this branch, it reliably
calls `find_path` (previously `path_search`) before reading files.
After getting the model to find paths first, I noticed it would try
using `grep` instead of `path_search`. This motivated renaming
`path_search` to `find_path` (continuing the analogy to unix commands)
and adding system prompt instructions about proper tool selection.
Note: I know the command is just called `find`, but that seemed too
general.
In my eval runs, the `file_search` example improved from 40% ± 10% to
98% ± 2%. The only assertion I'm seeing occasionally fail is "glob
starts with `**` or project". We can probably add some instructions in
that regard.
Release Notes:
- N/A
Instructs the model to include the fields that we display first in the
input object, so that e.g the user can see the path of a file while the
model generates the content.
Release Notes:
- N/A
Agus Zubiaga
