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 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
A preparation for https://github.com/zed-industries/zed/issues/4957 that
pushes all LSP-related data out from the basic completion item, so that
it's possible to create completion items without any trace of LSP
clearly.
Release Notes:
- N/A
This PR adds a new rounded/corner border token: `rounded_md` with a
value of 6px.
I feel like I was wanting to use 6px border radius a lot but avoiding
due to it being an arbitrary value... so, not anymore! It's also cool to
have this be consistent with Tailwind v4.
Follow on to the prior renames:
- `rounded_sm` -> `rounded_xs`:
https://github.com/zed-industries/zed/pull/26221
- `rounded_md` -> `rounded_sm`:
https://github.com/zed-industries/zed/pull/26228
Release Notes:
- N/A
---------
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
This PR fixes the language model selector.
I tried to piece together the state prior to #25697 (the state it was in
at 11838cf89e) while retaining unrelated
changes that happened since then.
Release Notes:
- Fixed an issue where language models would not be authenticated until
after the model selector was opened (Preview only).
We would previously return an error if there was at least one non-UTF8
file. Now we just ignore them and only add text files. If no text files
are found we show an error.
Release Notes:
- N/A
This fixes a major performance issue in the current git beta.
This PR also removes the PopoverButton component, which was easy to
misuse.
Release Notes:
- Git Beta: Fix frame drops caused by opening the git panel
---------
Co-authored-by: Mikayla Maki <mikayla.c.maki@gmail.com>
Fine-tuning the visuals (namely, reducing font and keybinding size) and
passing `on_click` handlers to the Cancel & Regenerate actions.
Release Notes:
- N/A
This PR adds the ability for Markdown code blocks and tables to be made
horizontally scrollable.
This is a feature that the caller can opt in to.
Right now we're using it for the rendered Markdown in the Assistant 2
panel.
Release Notes:
- N/A
This PR changes how we persist threads in Assistant2 to use `serde_json`
instead of `bincode` for the representation.
This makes the format more flexible to work with (and will allow for
using things like `#[serde(default)]`) if the schema changes over time.
Note: We have to bump the LMDB database version for this, so any threads
created before now will be gone.
Release Notes:
- N/A
Closes#10167
This is take 2 on https://github.com/zed-industries/zed/pull/2341 which
was closed due to lack of migrator.
This PR contains rename of following keymap actions:
```sh
1. ["editor::GoToPrevHunk", { "center_cursor": true }] -> ["editor::GoToPreviousHunk", { "center_cursor": true }]
2. "editor::GoToPrevDiagnostic" -> "editor::GoToPreviousDiagnostic"
3. "editor::ContextMenuPrev" -> "editor::ContextMenuPrevious"
4. "search::SelectPrevMatch" -> "search::SelectPreviousMatch"
5. "file_finder::SelectPrev" -> "file_finder::SelectPrevious"
6. "menu::SelectPrev" -> "menu::SelectPrevious"
7. "editor::TabPrev" -> "editor::Backtab"
```
Release Notes:
- Renamed several keymap actions for consistency (e.g., `GoToPrevHunk` →
`GoToPreviousHunk`, `TabPrev` → `Backtab`). Your existing configured
keybindings will still work. You can click **"Backup and Update"** at
the top of your keymap file to easily update to the new actions.
Co-authored-by: Joseph T. Lyons <JosephTLyons@gmail.com>
This PR makes it so we include some textual content in the user messages
that as used to send up tool results.
I observed that when sending up the tool results with no text, it would
lead the model to start replying with no text, which would then result
in an error when attaching later tool results.
I think there's a deeper issue at play here, but for now we just include
some text to keep the model on track.
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
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
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
This PR moves the `report_assistant_event` function from the
`language_models` crate to the `language_model` crate.
This allows us to drop some dependencies on `language_models`.
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.
Closes https://github.com/zed-industries/zed/issues/25413
As the issue points out well, themes do not need to alter any in-memory
state on load: that is done via settings file load.
Originally, it was introduced in
https://github.com/zed-industries/zed/pull/4064 and
https://github.com/zed-industries/zed/pull/24857 had restored that
behavior, which seems wrong to do.
Apart from removing that part, removes unnecessary methods and
emphasizes that in-memory state is the Buffer/UI size — no need to add
`Adjusted` there as the settings file presence is already enough.
Release Notes:
- Fixed theme selector resetting the buffer size
Give the inline file crease inside of `assistant2`'s editor a
selection background when there is a selection over it
Release Notes:
- N/A
---------
Co-authored-by: Piotr <piotr@zed.dev>
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Marshall Bowers
Agus ZubiagaandMarshall Bowers
Kirill Bulatov
0x2CA
Danilo LealandMarshall Bowers
Bennet Bo Fenner
Conrad IrwinandMikayla Maki
Nate ButlerandMikayla Maki
smitandJoseph T. Lyons
Piotr Osiewicz
张小白
Mikayla MakiandNate Butler
Antonio Scandurra
João Marcos
