- Confirming a completion now runs the command immediately
- Hitting `enter` on a line with a command now runs it
- The output of commands gets folded away and replaced with a custom
placeholder
- Eliminated ambient context
<img width="1588" alt="image"
src="https://github.com/zed-industries/zed/assets/482957/b1927a45-52d6-4634-acc9-2ee539c1d89a">
Release Notes:
- N/A
---------
Co-authored-by: Nathan Sobo <nathan@zed.dev>
Adds the following features to the prompt manager:
- New prompt – Create a new prompt from the UI. It will only persist if
it is saved.
- Save prompt – Save a prompt by clicking the save button in the UI. A
keybinding will be added for this in the future.
- Reveal prompt - Show the selected prompt on the file system. Only
available for saved prompts.
New prompts that are saved will use the
`{slugified_title}_{ver}_{id}.md` format which all imported prompts will
move to in the near future.
Also orders prompts in alphabetical order by default.
Release Notes:
- N/A
This PR replaces an `expect` with a precondition check to avoid a panic
if the `LspAdapterDelegate` isn't set when invoking a slash command.
Release Notes:
- N/A
Moved some things around so prompts now always have front-matter to
return, either by creating a prompt with default front-matter, or
bailing earlier on importing the prompt to the library.
In the future we'll improve visibility of malformed prompts in the
`prompts` folder in the prompt manager UI.
Fixes:
- Prompts inserted with the `/prompt` command now only include their
body, not the entire file including metadata.
- Prompts with an invalid title will now show "Untitled prompt" instead
of an empty line.
Release Notes:
- N/A
This PR adds initial support for defining slash commands for the
Assistant from extensions.
Slash commands are defined in an extension's `extension.toml`:
```toml
[slash_commands.gleam-project]
description = "Returns information about the current Gleam project."
requires_argument = false
```
and then executed via the `run_slash_command` method on the `Extension`
trait:
```rs
impl Extension for GleamExtension {
// ...
fn run_slash_command(
&self,
command: SlashCommand,
_argument: Option<String>,
worktree: &zed::Worktree,
) -> Result<Option<String>, String> {
match command.name.as_str() {
"gleam-project" => Ok(Some("Yayyy".to_string())),
command => Err(format!("unknown slash command: \"{command}\"")),
}
}
}
```
Release Notes:
- N/A
This PR extracts the `SlashCommand` trait (along with the
`SlashCommandRegistry`) from the `assistant` crate.
This will allow us to register slash commands from extensions without
having to make `extension` depend on `assistant`.
Release Notes:
- N/A
This pull request replaces the static `⋯` character we used to insert
when folding a range with a custom render function that return an
`AnyElement`. We plan to use this in the assistant, but for now this
should be behavior-preserving.
Release Notes:
- N/A
---------
Co-authored-by: Nathan <nathan@zed.dev>
Co-authored-by: Conrad <conrad@zed.dev>
Builds on top of existing work from #2249, but here's a showcase:
https://github.com/zed-industries/zed/assets/53836821/4b346965-6654-496c-b379-75425d9b493f
TODO:
- [x] handle line wrapping
- [x] implement handling in multibuffer (crashes currently)
- [x] add configuration option
- [x] new theme properties? What colors to use?
- [x] Possibly support indents with different colors or background
colors
- [x] investigate edge cases (e.g. indent guides and folds continue on
empty lines even if the next indent is different)
- [x] add more tests (also test `find_active_indent_index`)
- [x] docs (will do in a follow up PR)
- [x] benchmark performance impact
Release Notes:
- Added indent guides
([#5373](https://github.com/zed-industries/zed/issues/5373))
---------
Co-authored-by: Nate Butler <1714999+iamnbutler@users.noreply.github.com>
Co-authored-by: Remco <djsmits12@gmail.com>
Restructure prompts & the prompt library.
- Prompts are now written in markdown
- The prompt manager has a picker and editable prompts
- Saving isn't wired up yet
- This also removes the "Insert active prompt" button as this concept doesn't exist anymore, and will be replaced with slash commands.
I didn't staff flag this, but if you do play around with it expect it to still be pretty rough.
Release Notes:
- N/A
---------
Co-authored-by: Nathan Sobo <1789+nathansobo@users.noreply.github.com>
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Tasks
* [x] remove old flaps and output when editing a slash command
* [x] the completing a command name that takes args, insert a space to
prepare for typing an arg
* [x] always trigger completions when typing in a slash command
* [x] don't show line numbers
* [x] implement `prompt` command
* [x] `current-file` command
* [x] state gets corrupted on `duplicate line up` on a slash command
* [x] exclude slash command source from completion request
Next steps:
* show output token count in flap trailer
* add `/project` command that matches project ambient context
* delete ambient context
Release Notes:
- N/A
---------
Co-authored-by: Marshall <marshall@zed.dev>
Co-authored-by: Antonio Scandurra <me@as-cii.com>
This uses Jaro-Winkler similarity for now, which seemed to produce
pretty good results in my tests. We can easily swap it with something
else if needed.
Release Notes:
- N/A
### Todo
* [x] tuck the new system prompt away somehow
* for now, we're treating it as built-in, and not editable. once we have
a way to fold away default prompts, let's make it a default prompt.
* [x] when applying edits, re-parse the edit from the latest content of
the assistant buffer (to allow for manual editing of edits)
* [x] automatically adjust the indentation of edits suggested by the
assistant
* [x] fix edit row highlights persisting even when assistant messages
with edits are deleted
* ~adjust the fuzzy search to allow for small errors in the old text,
using some string similarity routine~
We decided to defer the fuzzy searching thing to a separate PR, since
it's a little bit involved, and the current functionality works well
enough to be worth landing. A couple of notes on the fuzzy searching:
* sometimes the assistant accidentally omits line breaks from the text
that it wants to replace
* when the old text has hallucinations, the new text often contains the
same hallucinations. so we'll probably need to use a more fine-grained
editing strategy where we perform a character-wise diff of the old and
new text as reported by the assistant, and then adjust that diff so that
it can be applied to the actual buffer text
Release Notes:
- Added the ability to request edits to project files using the
assistant panel.
---------
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Marshall <marshall@zed.dev>
Co-authored-by: Antonio <antonio@zed.dev>
Co-authored-by: Nathan <nathan@zed.dev>
This PR removes the `unwrap`s in the `RecentBuffersContext` when
building the message.
We can just make `build_message` return a `Result` to clean things up.
Release Notes:
- N/A
This PR adds a Prompt Library to Zed, powering custom prompts and any
default prompts we want to package with the assistant.
These are useful for:
- Creating a "default prompt" - a super prompt that includes a
collection of things you want the assistant to know in every
conversation.
- Adding single prompts to your current context to help guide the
assistant's responses.
- (In the future) dynamically adding certain prompts to the assistant
based on the current context, such as the presence of Rust code or a
specific async runtime you want to work with.
These will also be useful for populating the assistant actions typeahead
we plan to build in the near future.
## Prompt Library
The prompt library is a registry of prompts. Initially by default when
opening the assistant, the prompt manager will load any custom prompts
present in your `~/.config/zed/prompts` directory.
Checked prompts are included in your "default prompt", which can be
inserted into the assitant by running `assistant: insert default prompt`
or clicking the `Insert Default Prompt` button in the assistant panel's
more menu.
When the app starts, no prompts are set to default. You can add prompts
to the default by checking them in the Prompt Library.
I plan to improve this UX in the future, allowing your default prompts
to be remembered, and allowing creating, editing and exporting prompts
from the Library.
### Creating a custom prompt
Prompts have a simple format:
```json
{
// ~/.config/zed/prompts/no-comments.json
"title": "No comments in code",
"version": "1.0",
"author": "Nate Butler <iamnbutler@gmail.com>",
"languages": ["*"],
"prompt": "Do not add inline or doc comments to any returned code. Avoid removing existing comments unless they are no longer accurate due to changes in the code."
}
```
Ensure you properly escape your prompt string when creating a new prompt
file.
Example:
```json
{
// ...
"prompt": "This project using the gpui crate as it's UI framework for building UI in Rust. When working in Rust files with gpui components, import it's dependencies using `use gpui::{*, prelude::*}`.\n\nWhen a struct has a `#[derive(IntoElement)]` attribute, it is a UI component that must implement `RenderOnce`. Example:\n\n```rust\n#[derive(IntoElement)]\nstruct MyComponent {\n id: ElementId,\n}\n\nimpl MyComponent {\n pub fn new(id: impl Into<ElementId>) -> Self {\n Self { id.into() }\n }\n}\n\nimpl RenderOnce for MyComponent {\n fn render(self, cx: &mut WindowContext) -> impl IntoElement {\n div().id(self.id.clone()).child(text(\"Hello, world!\"))\n }\n}\n```"
}
```
Release Notes:
- N/A
---------
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
This PR adds some ergonomic improvements when working with GPUI
`Global`s.
Two new traits have been added—`ReadGlobal` and `UpdateGlobal`—that
provide associated functions on any type that implements `Global` for
accessing and updating the global without needing to call the methods on
the `cx` directly (which generally involves qualifying the type).
I looked into adding `ObserveGlobal` as well, but this seems a bit
trickier to implement as the signatures of `cx.observe_global` vary
slightly between the different contexts.
Release Notes:
- N/A
Fix: this makes sure we have token counts for the new GPT-4o model.
See: https://github.com/zurawiki/tiktoken-rs/releases/tag/v0.5.9
Release Notes:
- Fix: Token count was missing for the new GPT-4o model.
(I believe this should go in a 0.136.x release)
This PR factors some more code related to the `RecentBuffersContext` out
of the `AssistantPanel` and into the corresponding module.
We're trying to strike a balance between keeping this code easy to
evolve as we work on the Assistant, while also having some semblance of
separation/structure.
This also adds the missing functionality of updating the remaining token
count when the `CurrentProjectContext` is enabled/disabled.
Release Notes:
- N/A
---------
Co-authored-by: Max <max@zed.dev>
This PR adds the beginnings of current project context to the Assistant.
Currently it supports reading a `Cargo.toml` file and using that to get
some basic information about the project, and its dependencies:
<img width="1264" alt="Screenshot 2024-05-14 at 6 17 03 PM"
src="https://github.com/zed-industries/zed/assets/1486634/cc8ed5ad-0ccb-45da-9c07-c96af84a14e3">
Release Notes:
- N/A
---------
Co-authored-by: Nate <nate@zed.dev>
This PR restructures the ambient context in the `assistant` crate to
make it more amenable to adding more kinds of ambient context.
Release Notes:
- N/A
Release Notes:
- Added support for interacting with Claude in the assistant panel. You
can enable it by adding the following to your `settings.json`:
```json
"assistant": {
"version": "1",
"provider": {
"name": "anthropic"
}
}
```
<img width="1637" alt="image"
src="https://github.com/zed-industries/zed/assets/482957/5aaec657-3499-42c9-9528-c83728f2a7a1">
Release Notes:
- Added a new ambient context feature that allows showing the model up
to three buffers (along with their diagnostics) that the user interacted
with recently.
---------
Co-authored-by: Nathan Sobo <nathan@zed.dev>
Part of https://github.com/zed-industries/zed/issues/8081
To avoid confusion and bugs when converting between various row `u32`'s,
use different types for each.
Further PRs should split `Point` into buffer and multi buffer variants
and make the code more readable.
Release Notes:
- N/A
---------
Co-authored-by: Piotr <piotr@zed.dev>
This PR adds a setting to allow configuring the low-speed timeout for
the Assistant when using the OpenAI provider.
The `low_speed_timeout_in_seconds` accepts a number of seconds that the
HTTP client can go below a minimum speed limit (currently set to 100
bytes/second) before it times out.
```json
{
"assistant": {
"version": "1",
"provider": { "name": "openai", "low_speed_timeout_in_seconds": 60 }
},
}
```
This should help the case where the `openai` provider is being used with
a local model that requires higher timeouts.
Issue: https://github.com/zed-industries/zed/issues/9913
Release Notes:
- Added a `low_speed_timeout_in_seconds` setting to the Assistant's
OpenAI provider
([#9913](https://github.com/zed-industries/zed/issues/9913)).
This PR updates the new assistant with a button to start a new
conversation.
Clicking on it will reset the chat and put it into a fresh state.
The current conversation will be serialized and written to
`~/.config/zed/conversations`.
Release Notes:
- N/A
This is a crate only addition of a new version of the AssistantPanel.
We'll be putting this behind a feature flag while we iron out the new
experience.
Release Notes:
- N/A
---------
Co-authored-by: Nathan Sobo <nathan@zed.dev>
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Conrad Irwin <conrad@zed.dev>
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
Co-authored-by: Antonio Scandurra <antonio@zed.dev>
Co-authored-by: Nate Butler <nate@zed.dev>
Co-authored-by: Nate Butler <iamnbutler@gmail.com>
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Max <max@zed.dev>
This pull request introduces the new
`ElementContext::request_autoscroll(bounds)` and
`ElementContext::take_autoscroll()` methods in GPUI. These new APIs
enable container elements such as `List` to change their scroll position
if one of their children requested an autoscroll. We plan to use this in
the revamped assistant.
As a drive-by, we also:
- Renamed `Element::before_layout` to `Element::request_layout`
- Renamed `Element::after_layout` to `Element::prepaint`
- Introduced a new `List::splice_focusable` method to splice focusable
elements into the list, which enables rendering offscreen elements that
are focused.
Release Notes:
- N/A
---------
Co-authored-by: Nathan <nathan@zed.dev>
This fixes when the workspace is not actually available for a
`.read(cx)`.
Release Notes:
- Fix a panic when quoting a selection before the assistant panel has
been started
Co-authored-by: Conrad Irwin <conrad@zed.dev>
New list (used tasks are above the separator line, sorted by the usage
recency), then all language tasks, then project-local and global tasks
are listed.
Note that there are two test tasks (for `test_name_1` and `test_name_2`
functions) that are created from the same task template:
<img width="563" alt="Screenshot 2024-04-10 at 01 00 46"
src="https://github.com/zed-industries/zed/assets/2690773/7455a82f-2af2-47bf-99bd-d9c5a36e64ab">
Tasks are deduplicated by labels, with the used tasks left in case of
the conflict with the new tasks from the template:
<img width="555" alt="Screenshot 2024-04-10 at 01 01 06"
src="https://github.com/zed-industries/zed/assets/2690773/8f5a249e-abec-46ef-a991-08c6d0348648">
Regular recent tasks can be now removed too:
<img width="565" alt="Screenshot 2024-04-10 at 01 00 55"
src="https://github.com/zed-industries/zed/assets/2690773/0976b8fe-b5d7-4d2a-953d-1d8b1f216192">
When the caret is in the place where no function symbol could be
retrieved, no cargo tests for function are listed in tasks:
<img width="556" alt="image"
src="https://github.com/zed-industries/zed/assets/2690773/df30feba-fe27-4645-8be9-02afc70f02da">
Part of https://github.com/zed-industries/zed/issues/10132
Reworks the task code to simplify it and enable proper task labels.
* removes `trait Task`, renames `Definition` into `TaskTemplate` and use
that instead of `Arc<dyn Task>` everywhere
* implement more generic `TaskId` generation that depends on the
`TaskContext` and `TaskTemplate`
* remove `TaskId` out of the template and only create it after
"resolving" the template into the `ResolvedTask`: this way, task
templates, task state (`TaskContext`) and task "result" (resolved state)
are clearly separated and are not mixed
* implement the logic for filtering out non-related language tasks and
tasks that have non-resolved Zed task variables
* rework Zed template-vs-resolved-task display in modal: now all reruns
and recently used tasks are resolved tasks with "fixed" context (unless
configured otherwise in the task json) that are always shown, and Zed
can add on top tasks with different context that are derived from the
same template as the used, resolved tasks
* sort the tasks list better, showing more specific and least recently
used tasks higher
* shows a separator between used and unused tasks, allow removing the
used tasks same as the oneshot ones
* remote the Oneshot task source as redundant: all oneshot tasks are now
stored in the inventory's history
* when reusing the tasks as query in the modal, paste the expanded task
label now, show trimmed resolved label in the modal
* adjusts Rust and Elixir task labels to be more descriptive and closer
to bash scripts
Release Notes:
- Improved task modal ordering, run and deletion capabilities
