We'll now prompt the user to start a new thread when the active one gets
too long.
<img width=500
src="https://github.com/user-attachments/assets/91445bc0-3e81-422f-aa4a-b8f0741f9d9a"></img>
When they click "Start New Thread", will create a new one with the
previous one added as context.
<img width=500
src="https://github.com/user-attachments/assets/c3b4223f-5bdd-4ba4-956f-5a5880d5e2c3"></img>
Instead of including the full thread text, we'll now add summarized
versions of threads to the context, allowing you to continue the
conversation even if it was near the token limit.
- Thread summaries are cached and persisted.
- A cached summary is invalidated if the thread is continued.
- We start generating the thread summary as soon as it's selected from
the picker. Most times, the summary will be ready by the time the user
sends the message.
- If the summary isn't ready by the time a message is sent, the user
message will be displayed in the thread immediately, and a "Summarizing
context..." indicator will appear. After the summaries are ready, we'll
start generating the response and show the usual "Generating..."
indicator.
Release Notes:
- N/A
---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
This PR updates the Agent Panel tooltip in the status to use "Agent
Panel" instead of "Assistant Panel".
Also changes the name we use in workspace serialization.
Release Notes:
- N/A
This PR includes design tweaks to elements involved on the "edit files"
flow: the bar that appears above the message editor, buttons on the
multibuffer hunks, adding keybindings to the "Review Changes" button,
etc.
<img
src="https://github.com/user-attachments/assets/4bff883a-c5c4-443e-8bf5-d98f535c83ce"
width="750" />
Release Notes:
- N/A
This PR makes the plus icon button not a dropdown anymore, freeing it up
to be always the new thread action. In consequence, I'm moving all of
the other items into another dropdown, which now houses "new prompt
editor", history, and settings, all of which there are keybindings for.
<img
src="https://github.com/user-attachments/assets/1d0d43da-9447-4218-8b9b-e692c0b74f61"
width="700"/>
Release Notes:
- N/A
Part of #27171
Follows-up the change in
https://github.com/zed-industries/zed/pull/22346 to consider the case
where the assistant-panel is disabled via settings (as also noted in
[this
comment](https://github.com/zed-industries/zed/pull/22346#issuecomment-2558372412),
Notably, only the explicit case is considered here. Can extend this
change to also cover the implicit case where the button is disabled if
requested.).
Currently, if the user toggles the right dock, the assistant panel will
be shown even if it is disabled via settings, because it has the highest
priority (see
https://github.com/zed-industries/zed/pull/22346#issuecomment-2564890493).
With this change, the assistant panel is no longer activated when
disabled and the dock with the next highest activation order is
activated instead.
I did not opt in to make the priority configurabe, as I agree with
https://github.com/zed-industries/zed/pull/22346#issuecomment-2564890493
that this will most likely rarely be used (the active panel is only none
on the first toggle of the dock, afterwards it remains set for the
remainder of the session).
Release Notes:
- `workspace::ToggleRightDock` will no longer open the assistant panel
when it is disabled via settings.
Also took the opportunity to rename the action to something that would
be clearer in the command palette, from `DeployPromptLibrary` to
`OpenPromptLibrary`.
Release Notes:
- N/A
---------
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
This is the core change:
https://github.com/zed-industries/zed/pull/26758/files#diff-044302c0d57147af17e68a0009fee3e8dcdfb4f32c27a915e70cfa80e987f765R1052
TODO:
- [x] Use AsyncFn instead of Fn() -> Future in GPUI spawn methods
- [x] Implement it in the whole app
- [x] Implement it in the debugger
- [x] Glance at the RPC crate, and see if those box future methods can
be switched over. Answer: It can't directly, as you can't make an
AsyncFn* into a trait object. There's ways around that, but they're all
more complex than just keeping the code as is.
- [ ] Fix platform specific code
Release Notes:
- N/A
When the user attached context in the thread, the editor model request
would fail because its tool use wouldn't be removed properly leading to
an API error.
Also, after an edit, we'd keep the old file snapshot in the context.
This would make the model think that the edits didn't apply and make it
go in a loop.
Release Notes:
- N/A
Release Notes:
- Multibuffers now use less vertical space for excerpt boundaries.
Additionally the expand up/down arrows are hidden at the start and end
of the buffers
---------
Co-authored-by: Nate Butler <iamnbutler@gmail.com>
Co-authored-by: Zed AI <claude-3.5-sonnet@zed.dev>
We decided to expose scripting as tools again. We are aware of the UX
downsides of doing so, but we want to focus on getting it working well
first, and the model seems to make better use of it as an actual tool.
In the future, the tools API might support streaming. If it doesn't and
we need to ship, we can consider reverting this.
Release Notes:
- N/A
This PR makes refactors the scripting functionality to be a first-class
concept of the assistant instead of a generic tool, which will allow us
to build a more customized experience.
- The tool prompt has been slightly tweaked and is now included as a
system message in all conversations. I'm getting decent results, but now
that it isn't in the tools framework, it will probably require more
refining.
- The model will now include an `<eval ...>` tag at the end of the
message with the script. We parse this tag incrementally as it streams
in so that we can indicate that we are generating a script before we see
the closing `</eval>` tag. Later, this will help us interpret the script
as it arrives also.
- Threads now hold a `ScriptSession` entity which manages the state of
all scripts (from parsing to exited) in a centralized way, and will
later collect all script operations so they can be displayed in the UI.
- `script_tool` has been renamed to `assistant_scripting`
- Script source now opens in a regular read-only buffer
Note: We still need to handle persistence properly
Release Notes:
- N/A
---------
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
This PR adds two new helper methods to the `Thread` for dealing with
tool use:
- `use_pending_tools` - This uses all of the tools that are pending
- The reason we aren't calling this directly in `stream_completion` is
that we still might need to have a way for users to confirm that they
want tools to be run, which would need to happen at the UI layer in the
`ActiveThread`.
- `send_tool_results_to_model` - This encapsulates inserting a new user
message that contains the tool results and sending them up to the model.
Release Notes:
- N/A
This PR decouples the `Tool` trait from the `Workspace` (and from the
UI, in general).
`Tool::run` now takes a `WeakEntity<Project>` instead of a
`WeakEntity<Workspace>` and a `Window`.
Release Notes:
- N/A
Going for a different, arguably simpler design for the Assistant 2 empty
state here. Also took the opportunity to adjust other elements like the
toolbar, message editor, and some items in the configuration page.
<img
src="https://github.com/user-attachments/assets/03fd1d48-a675-4eac-b694-bbe4eeaf06e9"
width="700px"/>
Release Notes:
- N/A
While investigating #24896, I noticed two issues:
1. The default configuration for the `zed.dev` provider was using the
wrong string for Claude 3.5 Sonnet. This meant the provider would always
result as not configured until the user selected it from the model
picker, because we couldn't deserialize that string to a valid
`anthropic::Model` enum variant.
2. When clicking on `Open New Chat`/`Start New Thread` in the provider
configuration, we would select `Claude 3.5 Haiku` by default instead of
Claude 3.5 Sonnet.
Release Notes:
- Fixed some issues that caused AI providers to sometimes be
misconfigured.
This PR fixes an issue where the thread history would only work in one
Zed window at a time.
The backing LMDB database can only be opened once per Zed instance.
However, the `ThreadStore` has one instance per Zed window.
To fix this, we need to create the `heed` environment once and store it
as a global, and then reference the same environment across all of the
`ThreadStore`s.
Release Notes:
- N/A
This Pull Request tackles the issue outline in #14287 by changing the
way `KeyBinding`s for vim mode are displayed in the command palette.
It's worth pointing out that this whole thing was pretty much
implemented by Conrad Irwin during a pairing session, I just tried to
clean up some other changes introduced for a different issue, while
improving some comments.
Here's a quick list of the changes introduced:
- Update `KeyBinding` with a new `vim_mode` field to determine whether
the keybinding should be displayed in vim mode.
- Update the way `KeyBinding` is rendered, so as to detect if the
keybinding is for vim mode, if it is, only display keys in uppercase if
they require the shift key.
- Introduce a new global state – `VimStyle(bool)` - use to determine
whether `vim_mode` should be enabled or disabled when creating a new
`KeyBinding` struct. This global state is automatically set by the `vim`
crate whenever vim mode is enabled or disabled.
- Since the app's context is now required when building a `KeyBinding` ,
update a lot of callers to correctly pass this context.
And before and after screenshots, for comparison:
| before | after |
|--------|-------|
| <img width="1050" alt="SCR-20250205-tyeq"
src="https://github.com/user-attachments/assets/e577206d-2a3d-4e06-a96f-a98899cc15c0"
/> | <img width="1050" alt="SCR-20250205-tylh"
src="https://github.com/user-attachments/assets/ebbf70a9-e838-4d32-aee5-0ffde94d65fb"
/> |
Closes#14287
Release Notes:
- Fix rendering of vim commands to preserve case sensitivity
---------
Co-authored-by: Conrad Irwin <conrad.irwin@gmail.com>
Closes https://github.com/zed-industries/zed/issues/23894
Reworks all trigger declarations from
`.trigger(element.tooltip(tooltip))` into
`.trigger_with_tooltip(element, tooltip)` , with new API disallowing
simultaneous trigger and tooltip display.
All existing `.trigger(` calls were replaced, except 2 not applicable
(in dock.rs and pane.rs), 15 left as ones without tooltips, and 2
unchanged places in `inline_completion_button.rs`, where
0f7bb2e9fd/crates/inline_completion_button/src/inline_completion_button.rs (L311-L319)
`with_animation` does not allow us to simply use the same approach.
Release Notes:
- Fixed hover tooltips appearing after related element is pressed
---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
## Context
While looking through the client crate, I noticed that some of the old
functions and variables were still using gpui::model name that was
deprecated during the gpui3 transition. This PR renames those instances
of model to entity to be more inline with gpui3.
In addition, I also renamed `model` to `entity` in cases found by the
below search terms given by @someone13574
- model = cx.
- model: Entity
- model: &Entity
- OpenedModelHandle
- model.update
- model.upgrade
- model = .*\.root (regex)
- parent_model
- model = cx.new
- cx.spawn(move |model
Release Notes:
- N/A
This PR unships tool use from Assistant1.
This was only ever partially implemented, and was never released to end
users.
Assistant2 will support tool use.
Release Notes:
- N/A
This PR does some somewhat light UI adjustment to the Assistant 2
settings view. The Prompt Library section should feature the default
prompts in the future, so that's why it's been separated that way.
<img width="800" alt="Screenshot 2025-01-29 at 2 59 59 PM"
src="https://github.com/user-attachments/assets/7b033bde-51ab-44d5-9e53-3f72b8ff5f51"
/>
Release Notes:
- N/A
This PR adds really tiny visual adjustments to the assistant 2. I guess
the most note-worthy thing here is that I separated the `title` for
History views into two just because I wanted to render the `/` smaller
and lighter. 😬
Release Notes:
- N/A
This PR changes the `ThreadStore` constructor to not block on reloading
the threads before we finish initializing it.
This allows us to make the constructor synchronous instead of
asynchronous.
Release Notes:
- N/A
This PR fixes an issues where clicking the "Open Configuration" button
wasn't opening the configuration.
We needed to change how the action was dispatched after #22632.
Release Notes:
- N/A
This PR adds some logging so we can debug the issues some folks have
been having with Assistant2 not getting initialized properly.
All the logs are prefixed with `[assistant2-debug]` so they're easier to
pick out of the logs, as well as find them later to clean up once we've
diagnosed the issue.
Release Notes:
- N/A
There's still a bit more work to do on this, but this PR is compiling
(with warnings) after eliminating the key types. When the tasks below
are complete, this will be the new narrative for GPUI:
- `Entity<T>` - This replaces `View<T>`/`Model<T>`. It represents a unit
of state, and if `T` implements `Render`, then `Entity<T>` implements
`Element`.
- `&mut App` This replaces `AppContext` and represents the app.
- `&mut Context<T>` This replaces `ModelContext` and derefs to `App`. It
is provided by the framework when updating an entity.
- `&mut Window` Broken out of `&mut WindowContext` which no longer
exists. Every method that once took `&mut WindowContext` now takes `&mut
Window, &mut App` and every method that took `&mut ViewContext<T>` now
takes `&mut Window, &mut Context<T>`
Not pictured here are the two other failed attempts. It's been quite a
month!
Tasks:
- [x] Remove `View`, `ViewContext`, `WindowContext` and thread through
`Window`
- [x] [@cole-miller @mikayla-maki] Redraw window when entities change
- [x] [@cole-miller @mikayla-maki] Get examples and Zed running
- [x] [@cole-miller @mikayla-maki] Fix Zed rendering
- [x] [@mikayla-maki] Fix todo! macros and comments
- [x] Fix a bug where the editor would not be redrawn because of view
caching
- [x] remove publicness window.notify() and replace with
`AppContext::notify`
- [x] remove `observe_new_window_models`, replace with
`observe_new_models` with an optional window
- [x] Fix a bug where the project panel would not be redrawn because of
the wrong refresh() call being used
- [x] Fix the tests
- [x] Fix warnings by eliminating `Window` params or using `_`
- [x] Fix conflicts
- [x] Simplify generic code where possible
- [x] Rename types
- [ ] Update docs
### issues post merge
- [x] Issues switching between normal and insert mode
- [x] Assistant re-rendering failure
- [x] Vim test failures
- [x] Mac build issue
Release Notes:
- N/A
---------
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Cole Miller <cole@zed.dev>
Co-authored-by: Mikayla <mikayla@zed.dev>
Co-authored-by: Joseph <joseph@zed.dev>
Co-authored-by: max <max@zed.dev>
Co-authored-by: Michael Sloan <michael@zed.dev>
Co-authored-by: Mikayla Maki <mikaylamaki@Mikaylas-MacBook-Pro.local>
Co-authored-by: Mikayla <mikayla.c.maki@gmail.com>
Co-authored-by: joão <joao@zed.dev>
