I wanted this for CONL (https://conl.dev )'s nascent langauge server,
and it seems like most of the support was already wired up on the LSP
side, so this surfaces it into the editor.
Release Notes:
- Added support for the `insert_text_mode` field of completions from the
language server protocol.
I found a few more cases where the UI wasn't updated immediately after
an interaction.
Release Notes:
- agent: Fixed delay after removing threads from "Past Interactions"
- agent: Fixed delay after adding/remove context via keyboard
This PR fixes the `assistant: open prompt library` action in the command
palette not opening the prompt library when the Assistant Panel did not
have focus.
Fixes https://github.com/zed-industries/zed/issues/28058.
Release Notes:
- assistant: Fixed `assistant: open prompt library` not opening the
prompt library when the Assistant Panel was not focused.
This PR fixes an issue where opening the configuration view from the
model selector in the Agent (or inline assist) was not working properly.
Fixes https://github.com/zed-industries/zed/issues/28078.
Release Notes:
- Agent Beta: Fixed an issue where selecting "Configure" in the model
selector would not bring up the configuration view.
This would cause the history view not to get refreshed immediately when
a thread was deleted
Release Notes:
- agent: Fixed a bug where the history view wouldn't refresh after
deleting a thread
#28102 introduced a bug where thread summaries wouldn't get generated
because they would get set to the default title instead of `None`.
Not adding a release note because the bug didn't make it to Preview.
Release Notes:
- N/A
A "Near" block acts similarly to a "Below" block, but can (if it's
height is <= one line height) be shown on the end of the preceding line
instead of adding an entire blank line to the editor.
You can test it out by pasting this into `go_to_diagnostic_impl` and
then press `F8`
```
let buffer = self.buffer.read(cx).snapshot(cx);
let selection = self.selections.newest_anchor();
self.display_map.update(cx, |display_map, cx| {
display_map.insert_blocks(
[BlockProperties {
placement: BlockPlacement::Near(selection.start),
height: Some(1),
style: BlockStyle::Flex,
render: Arc::new(|_| {
div()
.w(px(100.))
.h(px(16.))
.bg(gpui::hsla(0., 0., 1., 0.5))
.into_any_element()
}),
priority: 0,
}],
cx,
)
});
return;
```
Release Notes:
- N/A
---------
Co-authored-by: Antonio Scandurra <me@as-cii.com>
This PR renames the `AssistantEvent` type to `AssistantEventData`, as it
no longer represents the event itself, just the data needed to construct
it.
Pulling out of https://github.com/zed-industries/zed/pull/25179.
Release Notes:
- N/A
This PR fixes a panic that could occur when opening the Agent diff from
the workspace (with the agent panel closed).
Release Notes:
- agent: Fixed a panic when running the `agent: open agent diff` command
with the Agent Panel closed.
Release Notes:
- agent: Tool call's input and output content are now rendered with
Markdown, which allows them to be selected and copied.
---------
Co-authored-by: Agus Zubiaga <hi@aguz.me>
Release Notes:
- agent: The scrollbar now automatically hides if there's no mouse
movement on the thread list.
---------
Co-authored-by: Agus Zubiaga <agus@zed.dev>
Co-authored-by: Agus Zubiaga <hi@aguz.me>
Closes: https://github.com/zed-industries/zed/issues/20582
Allows users to select a specific model for each AI-powered feature:
- Agent panel
- Inline assistant
- Thread summarization
- Commit message generation
If unspecified for a given feature, it will use the `default_model`
setting.
Release Notes:
- Added support for configuring a specific model for each AI-powered
feature
---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
This makes context essentially work the same way as `read-file`,
increasing the likelihood of cache hits.
Just like with `read-file`, we'll notify the model when the user makes
an edit to one of the tracked files. In the future, we want to send a
diff instead of just a list of files, but that's an orthogonal change.
Release Notes:
- agent: Improved caching of files in context
---------
Co-authored-by: Antonio Scandurra <me@as-cii.com>
This PR adds the token count to the active thread view. It doesn't
behaves quite like Assistant 1 where it updates as you type, though; it
updates after you submit the message.
<img
src="https://github.com/user-attachments/assets/82d2a180-554a-43ee-b776-3743359b609b"
width="700" />
---
Release Notes:
- agent: Add token count in the thread view
---------
Co-authored-by: Agus Zubiaga <hi@aguz.me>
### Context
The Anthropic API fails if a request message contains a tool use and no
`Text` segments or it only contains empty `Text` segments. These are
cases that the model itself produces, but the API doesn't support
sending them back.
#27917 fixed this by appending "Using tool..." in the thread's message,
but this causes the actual conversation to include it, so it would
appear in the UI (we would actually display a gap because we never
rendered its markdown, but "Using tool..." would show up when the thread
was restored).
### Solution
We'll now only append this placeholder when we build the request, so the
API still sees it, but the UI/Thread doesn't.
Another issue we found is that the model starts mimicking these
placeholders in later tool uses which is undesirable. So unfortunately,
we had to add logic to filter them out.
Release Notes:
- agent: Improved rendering of tool uses without text
---------
Co-authored-by: Bennet <bennet@zed.dev>
Previously the "Thinking..." step would show up as pending, even though
the user cancelled the generation:
<img width="672" alt="image"
src="https://github.com/user-attachments/assets/c9cdce0a-d827-4e23-96f5-b150465911a7"
/>
Release Notes:
- Fixed an issue where the thinking step would show up as pending even
when the generation was cancelled
This happened because of two reasons:
- `Workspace::recent_navigation_history` didn't include the current file
- The context picker added the current file to a exclude list
The latter was actually intentional because we already show the file in
the suggested context, but now that we actually have mentions, it's just
inconvenient not to have it there.
Release Notes:
- N/A
This PR adds the ability to edit previous user messages in the thread.
Release Notes:
- Agent: Added the ability to edit previous user messages
(Preview-only).
This adds a "workspace-hack" crate, see
[mozilla's](https://hg.mozilla.org/mozilla-central/file/3a265fdc9f33e5946f0ca0a04af73acd7e6d1a39/build/workspace-hack/Cargo.toml#l7)
for a concise explanation of why this is useful. For us in practice this
means that if I were to run all the tests (`cargo nextest r
--workspace`) and then `cargo r`, all the deps from the previous cargo
command will be reused. Before this PR it would rebuild many deps due to
resolving different sets of features for them. For me this frequently
caused long rebuilds when things "should" already be cached.
To avoid manually maintaining our workspace-hack crate, we will use
[cargo hakari](https://docs.rs/cargo-hakari) to update the build files
when there's a necessary change. I've added a step to CI that checks
whether the workspace-hack crate is up to date, and instructs you to
re-run `script/update-workspace-hack` when it fails.
Finally, to make sure that people can still depend on crates in our
workspace without pulling in all the workspace deps, we use a `[patch]`
section following [hakari's
instructions](https://docs.rs/cargo-hakari/0.9.36/cargo_hakari/patch_directive/index.html)
One possible followup task would be making guppy use our
`rust-toolchain.toml` instead of having to duplicate that list in its
config, I opened an issue for that upstream: guppy-rs/guppy#481.
TODO:
- [x] Fix the extension test failure
- [x] Ensure the dev dependencies aren't being unified by Hakari into
the main dependencies
- [x] Ensure that the remote-server binary continues to not depend on
LibSSL
Release Notes:
- N/A
---------
Co-authored-by: Mikayla <mikayla@zed.dev>
Co-authored-by: Mikayla Maki <mikayla.c.maki@gmail.com>
This PR makes the command permission prompt part of the tool card and
allow users to straight away change the `always_allow_tool_actions`
setting via the "Always Allow" button from that card. If that button is
clicked, that setting is turned on, and any command that requires
permission from that point on will auto-run.
Additionally, if a bash command spans multiple lines, we show the line
count at the end of the command string. (Note: this is not perfect yet
because it can likely be not visible by default, but we didn't think
this was a major blocker for now. We'll work on improving this next).
### Thread View
<img
src="https://github.com/user-attachments/assets/00f93c39-990f-4b79-84ec-0427b997167f"
width="500"/>
### Settings View
<img
src="https://github.com/user-attachments/assets/52d32435-7c8d-4ab4-a319-6cabc007267b"
width="500"/>
Release Notes:
- N/A
---------
Co-authored-by: Thomas Mickley-Doyle <tmickleydoyle@gmail.com>
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Co-authored-by: Nathan Sobo <nathan@zed.dev>
Co-authored-by: Antonio Scandurra <me@as-cii.com>
We were including the context at the end which meant it never got
cached. We'll now include it with the first message that introduced it
so it's cached as long as it doesn't change.
This is an improvement, but we probably still need to think of ways to
optimize caching for cases where files in context change.
Release Notes:
- N/A
This PR removes an unneeded `else if` branch that was the same as the
previous branch in the conditional.
Doesn't seem necessary to run this twice.
Release Notes:
- N/A
This PR makes it so if we receive a tool use from the model without any
corresponding text, we'll insert some placeholder text to keep the
conversation in a well-structured format.
This aims to fix an error that Antonio was seeing:
Release Notes:
- N/A
