This PR reworks how we store enabled tools in the `ToolWorkingSet`.
We now track them based on which tools are explicitly enabled, rather
than by the tools that have been disabled.
Also fixed an issue where switching profiles wouldn't properly set the
right tools.
Release Notes:
- N/A
This PR renames the variants of the `Extension` enum with delimiters
between the version number components so that it's clearer which version
of the extension API they refer to.
Release Notes:
- N/A
This PR removes the dependency on the `ui` crate from the
`assistant_tool` and `context_server` crates.
These crates were only depending on it for `IconName`, which can now be
depended on from `icons` directly.
Release Notes:
- N/A
This PR removes the dependency on the `ui` crate from the
`language_model` crate.
We were only depending on it to import `IconName`—which now lives in
`icons`—and some re-exported GPUI items.
Release Notes:
- N/A
This PR adds a new `icons` crate and moves the `IconName` into it.
We have a number of crates that are taking a dependency on `ui` just so
they can talk about icons, which is not ideal.
Release Notes:
- N/A
This PR makes the "Inline Assist" quick action in the quick action bar
work by dispatching the `InlineAssist` action.
This fixes an issue where the button was not working with Assistant 2.
Release Notes:
- N/A
This PR updates the ordering of the agent profiles in the tool selector
to respect the order they are defined in in the settings instead of
sorting them alphabetically.
This gives the user more control, and allows them to order the profiles
as they desire.
Release Notes:
- N/A
This PR moves the definitions of the built-in agent profiles into the
default `settings.json`.
It also changes the behavior of how this setting is treated when merging
settings such that the set of profiles will be merged. This is so users
don't clobber the built-in profiles when adding profiles of their own.
Release Notes:
- N/A
This PR makes `App::get_name` return an `Option` instead of panicking if
the name is not set.
We'll let the caller be responsible for dealing with the absence of a
name.
Release Notes:
- N/A
This PR gives each context server entry in the configuration view a
unique element ID.
This fixes some issues where the disclosures and switches weren't
working properly due to element ID collisions.
Release Notes:
- N/A
This PR fixes an issues where the commands returned from context server
extensions were being used as-is instead of interpreting them relative
to the extension's work dir.
Release Notes:
- Fixed an issue with context server paths not being interpreted
relative to the extension's work dir.
---------
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Thomas Mickley-Doyle <tmickleydoyle@gmail.com>
This PR adds the initial concept of agent profiles to Assistant 2.
Right now these are just collections of tools that can quickly be
enabled together:
https://github.com/user-attachments/assets/7c7f9cc8-a5e5-492f-96f7-79697bbf3d72
There are currently two profiles:
- `Read-only` - Consists only of tools that do not perform writes.
- `Code Writer` - Consists of all tools for writing code, with the
exception of the `lua-interpreter`.
Release Notes:
- N/A
This PR adds fallback colors for the `version_control.<variant>` theme
properties.
This fixes the colors when themes do not provide the properties.
Related to https://github.com/zed-industries/zed/pull/26951.
Release Notes:
- Added fallback colors for the `version_control.<variant>` theme
properties.
This PR adds the ability to open the extensions view via the `zed:
extensions` action with a pre-selected filter.
The "Install Themes" and "Install Icon Themes" buttons in their
respective selectors take advantage of this to set the filter when
opening the view:
https://github.com/user-attachments/assets/2e345c0f-418a-47b6-811e-cabae6c616d1
Release Notes:
- N/A
This PR makes it so the tool selector will stay open when toggling tools
instead of closing after each selection:
https://github.com/user-attachments/assets/eb987785-cfb5-4b07-8d63-510fbd9d9bf1
This involved making a change to `ContextMenu` to allow it to rebuild
its menu items after each confirmation in order for them to reflect
their selected/unselected status. I intend to clean up the `ContextMenu`
API a bit at a later point, but that is out of scope for this PR.
Release Notes:
- N/A
This PR makes the account age-related fields required in
`LlmTokenClaims`.
We've also removed the account age check from the LLM token issuance
endpoint, instead having it solely be enforced in the `POST /completion`
endpoint.
This change will be safe to deploy at ~8:01PM EDT.
Release Notes:
- N/A
This PR defers the account age check to the `POST /completion` endpoint
instead of doing it when an LLM token is generated.
This will allow us to lift the account age restriction for using Edit
Prediction.
Note: We're still temporarily performing the account age check when
issuing the LLM token until this change is deployed and the LLM tokens
have had a chance to cycle.
Release Notes:
- N/A
This PR cleans up the LLM token creation a bit.
We now pass in the entire list of feature flags to the
`LlmTokenClaims::create` method to prevent having a bunch of confusable
`bool` parameters.
Release Notes:
- N/A
This PR refactors the constructors for the various Git hosting providers
to facilitate adding support for more self-hosted variants.
Release Notes:
- N/A
This PR removes the `migration_checks` job as a required check.
This was not required before, and we shouldn't make it required, as
there are cases where we need to bypass it, as is the case in
https://github.com/zed-industries/zed/pull/26832.
Release Notes:
- N/A
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 PR updates the `ToolWorkingSet` to reduce the amount of locking we
need to do.
A number of the methods have had corresponding versions moved to the
`ToolWorkingSetState` so that we can take out the lock once and do a
number of operations without needing to continually acquire and release
the lock.
Release Notes:
- N/A
This PR adds a new `ExtensionEvents` event bus that can be used to
listen for extension-related events throughout the app.
Today you need to have a handle to the `ExtensionStore` (which entails
depending on `extension_host`) in order to listen for extension events.
With this change subscribers only need to depend on `extension`, which
has a leaner dependency graph.
Release Notes:
- N/A
This PR refactors the `ContextMenu::render` method to extract a couple
smaller methods from it.
The existing `render` method was suffering from its size, with some of
the `match` arms not being able to be formatted with `rustfmt`.
Release Notes:
- N/A
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
This PR fixes some language links in the docs.
The Shell Script page wasn't being linked from `SUMMARY.md`, so no page
was being generated.
There were also some differences in the language lists in the sidebar
and on the top-level languages page.
Release Notes:
- N/A
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 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
This PR updates the `ExtensionBuilder` to require that grammar names are
written in snake_case.
The grammar names are used to construct identifiers, so we need them to
be valid C identifiers.
Release Notes:
- N/A
This PR removes a number of `.unwrap`s in the Bedrock provider.
We must not `.unwrap` in situations where it is not provably safe to do
so, which it was not in any of these cases.
Release Notes:
- Fixed some potential panics in the AWS Bedrock model provider.
This PR finishes up the support for generating commit messages using an
LLM.
We're shelling out to `git diff` to get the diff text, as it seemed more
efficient than attempting to reconstruct the diff ourselves from our
internal Git state.
https://github.com/user-attachments/assets/9bcf30a7-7a08-4f49-a753-72a5d954bddd
Release Notes:
- Git Beta: Added support for generating commit messages using a
language model.
---------
Co-authored-by: Conrad Irwin <conrad.irwin@gmail.com>
This PR adds support for capabilities for the extension process API.
In order to use the process API, an extension must declare which
commands it wants to use, with arguments:
```toml
[[capabilities]]
kind = "process:exec"
command = "echo"
args = ["hello!"]
```
A `*` can be used to denote a single wildcard in the argument list:
```toml
[[capabilities]]
kind = "process:exec"
command = "echo"
args = ["*"]
```
And `**` can be used to denote a wildcard for the remaining arguments:
```toml
[[capabilities]]
kind = "process:exec"
command = "ls"
args = ["-a", "**"]
```
Release Notes:
- N/A
---------
Co-authored-by: Conrad Irwin <conrad.irwin@gmail.com>
This PR adds two new tools to Assistant 2:
- `list-worktrees` - Lists the worktrees in a project
- `read-file` - Reads a file at the given path in the project
I don't see `list-worktrees` sticking around long-term, as when we have
tools for listing files those will include the worktree IDs along with
the path, but making this tool available allows the model to utilize
`read-file` when it otherwise wouldn't be able to.
Release Notes:
- N/A
Marshall Bowers
