This PR updates the `Thread::is_streaming` method so that it includes
tool use in the "streaming" state.
This will prevent the streaming indicator from disappearing when we're
doing tool use.
Release Notes:
- N/A
This should be less eager in terms of invoking tools. But we should keep
iterating on it as we add more tools.
Also, this disables the Lua interpreter by default (it can still be
enabled manually from the tools icon).
Release Notes:
- N/A
---------
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
Exposes a new "edit files" tool that the model can use to apply
modifications to files in the project. The main model provides
instructions and the tool uses a separate "editor" model (Claude 3.5 by
default) to generate search/replace blocks like Aider does:
````markdown
mathweb/flask/app.py
```python
<<<<<<< SEARCH
from flask import Flask
=======
import math
from flask import Flask
>>>>>>> REPLACE
```
````
The search/replace blocks are parsed and applied as they stream in. If a
block fails to parse, the tool will apply the other edits and report an
error pointing to the part of the input where it occurred. This should
allow the model to fix it.
Release Notes:
- N/A
---------
Co-authored-by: Antonio Scandurra <me@as-cii.com>
https://github.com/user-attachments/assets/a486ff2a-4aa1-4c0d-be6c-1dea2a8d60c8
- [x] Track buffer changes in `ScriptingSession`
- [x] Show edited files in thread
Reviewing diffs and displaying line counts will be part of an upcoming
PR.
Release Notes:
- N/A
---------
Co-authored-by: Antonio Scandurra <me@as-cii.com>
This PR decouples the scripting tool from the `Tool` trait while still
allowing it to be used as a tool from the model's perspective.
This will allow us to evolve the scripting tool as more of a first-class
citizen while still retaining the ability to have the model call it as a
regular tool.
Release Notes:
- N/A
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 factors out a new `Thread::all_tools_finished` method to
encapsulate some of the boilerplate in the `ThreadEvent::ToolFinished`
event handler.
This should make this event handler easier to replicate for the eval
use-case.
Release Notes:
- N/A
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 reworks how we store tool results and refer to them later.
We now maintain a mapping of the tool uses to their corresponding
results, with separate mappings for the messages and the tool uses they
correspond to.
Release Notes:
- N/A
This PR updates the tool use flow in Assistant 2 to automatically
respond to the model with tool results when the tools have finished
running.
Release Notes:
- N/A
This PR adds a new `send_to_model` method to the `Thread` to encapsulate
more of the thread-specific capabilities.
We then call this in `MessageEditor::send_to_model`.
Release Notes:
- N/A
This PR fixes the generation of summaries for threads when tools are
being used.
Previously we were including the tool uses in the summarization request,
but this would result in invalid messages being sent to the model and
summaries not being generated.
We now exclude any tool uses or results from the model when summarizing
a thread.
Release Notes:
- N/A
This PR removes the dependents of the `language_models` crate.
The following types have been moved from `language_models` to
`language_model` to facilitate this:
- `LlmApiToken`
- `RefreshLlmTokenListener`
- `MaxMonthlySpendReachedError`
- `PaymentRequiredError`
With this change only `zed` now depends on `language_models`.
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>
This PR updates Assistant2's response streaming to work with LLM
providers that do not emit `StartMessage` events.
Now if we get a `Text` event without having received a `StartMessage`
event we will still insert an Assistant message so we can stream in the
response from the model.
Release Notes:
- N/A
This PR makes it so the pending completion is cleared when an error
occurs.
This makes it so `Thread::is_streaming()` will return `false` in the
error case (and thus hide the streaming indicator in the UI).
Release Notes:
- N/A
The context picker will now display up to 6 recent files/threads to add
as a context:
<img
src="https://github.com/user-attachments/assets/80c87bf9-70ad-4e81-ba24-7a624378b991"
width=400>
Note: We decided to use a `ContextMenu` instead of `Picker` for the
initial one since the latter didn't quite fit the design for the
"Recent" section.
Release Notes:
- N/A
---------
Co-authored-by: Danilo <danilo@zed.dev>
Co-authored-by: Piotr <piotr@zed.dev>
Co-authored-by: Nathan <nathan@zed.dev>
This PR makes it so the context is persistent in the thread, rather than
having to reattach it for each message.
This PR intentionally does not make an attempt to refresh the attached
context if it changes. That will come in a follow-up.
Release Notes:
- N/A
This PR is a small refactoring in advance of some other changes.
Previously we were storing the whole `Context` associated with each
message. However, it's likely that multiple messages may end up using
the same context.
We now store the deduped context in a separate collection and refer to
it from each message by its `ContextId`.
Release Notes:
- N/A
This PR wire up the context picker with the inline assist.
UI is not finalized.
Release Notes:
- N/A
---------
Co-authored-by: Richard <richard@zed.dev>
Co-authored-by: Agus <agus@zed.dev>
This PR factors a new `ActiveThread` view out of the `AssistantPanel` to
group together the state that pertains solely to the active view.
There was a bunch of related state on the `AssistantPanel` pertaining to
the active thread that needed to be initialized/reset together and it
makes for a clearer narrative is this state is encapsulated in its own
view.
Release Notes:
- N/A
This PR adds the ability to open past threads in Assistant 2.
There are also some mocked threads in the history for testing purposes.
Release Notes:
- N/A
