Release Notes:
- Allow Anthropic custom models to override "temperature"
This also centralized the defaulting of "temperature" to be inside of
each model's `into_x` call instead of being sprinkled around the code.
This PR removes the `replica_id` field from the `MultiBuffer` struct.
We were only ever referencing this field to pass when constructing a
`MultiBuffer`, and never used it outside of that.
Release Notes:
- N/A
Release Notes:
- Added a new `assistant.inline_alternatives` setting to configure
additional models that will be used to perform inline assists in
parallel.
---------
Co-authored-by: Nathan <nathan@zed.dev>
Co-authored-by: Roy <roy@anthropic.com>
Co-authored-by: Adam <wolffiex@anthropic.com>
Fixes https://github.com/zed-industries/zed/issues/5291
Release Notes:
- Fixed a bug where the 'toggle comments' command didn't use the right
comment syntax in JSX and TSX elements.
---------
Co-authored-by: Conrad <conrad@zed.dev>
Co-authored-by: Conrad Irwin <conrad.irwin@gmail.com>
Co-authored-by: Kirill Bulatov <mail4score@gmail.com>
Closes https://github.com/zed-industries/zed/issues/17738
This PR is motivated by having also noticed what the issue above
mentions. Looked it further and it does seem the inline assistant had a
slightly bigger font-size even though it was using the configured UI
font-size as per https://github.com/zed-industries/zed/pull/17542. I'm
not sure why that was, technically speaking. However, I ended up
realizing that, given we're within the editor, it'd make more sense to
use the buffer font instead. With this change, the size mismatch seems
to be gone.
<img width="900" alt="Screenshot 2024-09-16 at 2 13 28 PM"
src="https://github.com/user-attachments/assets/fe2f3096-d5dd-4986-ba96-f2ca7578d84d">
Release Notes:
- N/A
This PR improves adding and working with icons by using the new
`DerivePathStr` to derive icon paths.
This means paths no longer need to be manually specified, and the
`IconName` and file name will always be consistent between icons.
This PR does not do any work to standardize icons visually, remove
unused icons, or any other such cleanup.
Release Notes:
- N/A
This is a barebones modification of the OpenAI provider code to
accommodate non-streaming completions. This is specifically for the o1
models, which do not support streaming. Tested that this is working by
running a `/workflow` with the following (arbitrarily chosen) settings:
```json
{
"language_models": {
"openai": {
"version": "1",
"available_models": [
{
"name": "o1-preview",
"display_name": "o1-preview",
"max_tokens": 128000,
"max_completion_tokens": 30000
},
{
"name": "o1-mini",
"display_name": "o1-mini",
"max_tokens": 128000,
"max_completion_tokens": 20000
}
]
}
},
}
```
Release Notes:
- Changed `low_speed_timeout_in_seconds` option to `600` for OpenAI
provider to accommodate recent o1 model release.
---------
Co-authored-by: Peter <peter@zed.dev>
Co-authored-by: Bennet <bennet@zed.dev>
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
We noticed that the `Workspace` was never released (along with the
`Project` and everything that comes along with that) when closing a
window.
After playing around with the LeakDetector and debugging with
`cx.on_release()` callbacks, we found two culprits: the inline assistant
and the outline panel.
Both held strong references to `View<Workspace>` after PR #16589 and PR
#16845.
This PR changes both references to `WeakView<Workspace>` which fixes the
leak but keeps the behaviour the same.
Release Notes:
- N/A
Co-authored-by: Bennet <bennet@zed.dev>
This PR adjusts the approach we use to encoding tool uses in the
completion response to use a structured format rather than simply
injecting it into the response stream as text.
In #17170 we would encode the tool uses as XML and insert them as text.
This would require then re-parsing the tool uses out of the buffer in
order to use them.
The approach taken in this PR is to make `stream_completion` return a
stream of `LanguageModelCompletionEvent`s. Each of these events can be
either text, or a tool use.
A new `stream_completion_text` method has been added to `LanguageModel`
for scenarios where we only care about textual content (currently,
everywhere that isn't the Assistant context editor).
Release Notes:
- N/A
This PR updates the Assistant with support for receiving tool uses from
Anthropic models and capturing them as text in the context editor.
This is just laying the foundation for tool use. We don't yet fulfill
the tool uses yet, or define any tools for the model to use.
Here's an example of what it looks like using the example `get_weather`
tool from the Anthropic docs:
<img width="644" alt="Screenshot 2024-08-30 at 1 51 13 PM"
src="https://github.com/user-attachments/assets/3614f953-0689-423c-8955-b146729ea638">
Release Notes:
- N/A
## Todo
* [x] Parse and present new XML output
* [x] Resolve new edits to buffers and anchor ranges
* [x] Surface resolution errors
* [x] Steps fail to resolve because language hasn't loaded yet
* [x] Treat empty `<symbol>` tag as None
* [x] duplicate assists when editing steps
* [x] step footer blocks can appear *below* the following message header
block
## Release Notes:
- N/A
---------
Co-authored-by: Mikayla <mikayla@zed.dev>
Co-authored-by: Peter <peter@zed.dev>
Co-authored-by: Marshall <marshall@zed.dev>
Co-authored-by: Antonio <antonio@zed.dev>
Co-authored-by: Antonio Scandurra <me@as-cii.com>
This adds a new action: `editor: toggle inline completions`.
It allows users to toggle inline completions on/off for the current
buffer.
That toggling is not persistent and when the editor is closed, it's
gone.
That makes it easy to disable inline completions for a single text
buffer, for example, even if you want them on for other buffers.
When toggling on/off, the toggling also overwrites any language
settings. So if you have inline completions disabled for Go buffers,
toggling them on takes precedence over those settings.
Release Notes:
- Added a new editor action to allow toggling inline completions
(Copilot, Supermaven) on and off for the current buffer, taking
precedence over any settings.
Co-authored-by: Antonio <antonio@zed.dev>
Follow-up https://github.com/zed-industries/zed/pull/16085 that fixes
the search deploy to be actually a part of the terminal-related
bindings.
Part of https://github.com/zed-industries/zed/issues/16839
Also
* fixes few other bindings to use `shift` and avoid conflicts with the
existing key bindings.
* adds terminal inline assist to the context menu and makes both the
menu and the button to dynamically adjust to `assist.enabled` settings
change
It is still unclear to me, why certain labels for certain bindings are
wrong (it's still showing `ctrl-w` for closing the terminal tab, and
`shift-insert` instead of `ctrl-shift-v` for Paste, while Insert is near
and has a `ctrl-shift-c` binding shown) but at least the keys work now.
Release notes:
- Improved Linux terminal keymap and context menu
This PR reverts #16145 and subsequent changes.
This reverts commit a515442a36.
We still have issues with our approach to indentation in Python
unfortunately, but this feels like a safer equilibrium than where we
were.
Release Notes:
- Returned to our previous prompt for inline assist transformations,
since recent changes were introducing issues.
I focused on cases where we're inserting doc comments or annotations
above symbols.
I added 5 new examples to the content generation prompt, covering
various scenarios:
1. Inserting documentation for a Rust struct
2. Writing docstrings for a Python class
3. Adding comments to a TypeScript method
4. Adding a derive attribute to a Rust struct
5. Adding a decorator to a Python class
These examples demonstrate how to handle different languages and common
tasks like adding documentation, attributes, and decorators.
To improve context integration, I've made the following changes:
1. Added a `transform_context_range` that includes 3 lines before and
after the transform range
2. Introduced `rewrite_section_prefix` and `rewrite_section_suffix` to
provide more context around the section being rewritten
3. Updated the prompt template to include this additional context in a
separate code snippet
Release Notes:
- Reduced instances of over-generation when inserting docs or
annotations above a symbol.
Release Notes:
- Adds support for Prompt Caching in Anthropic. For models that support
it this can dramatically lower cost while improving performance.
This PR is a refactor to pave the way for allowing the user to view and
edit workflow step resolutions. I've made tool calls work more like
normal streaming completions for all providers. The `use_any_tool`
method returns a stream of strings (which contain chunks of JSON). I've
also done some minor cleanup of language model providers in general,
removing the duplication around handling streaming responses.
Release Notes:
- N/A
For future reference: WIP branch of copy/pasting a mixture of images and
text: https://github.com/zed-industries/zed/tree/copy-paste-images -
we'll come back to that one after landing this one.
Release Notes:
- You can now paste images into the Assistant Panel to include them as
context. Currently works only on Mac, and with Anthropic models. Future
support is planned for more models, operating systems, and image
clipboard operations.
---------
Co-authored-by: Antonio <antonio@zed.dev>
Co-authored-by: Mikayla <mikayla@zed.dev>
Co-authored-by: Jason <jason@zed.dev>
Co-authored-by: Kyle <kylek@zed.dev>
This PR simplifies our approach to indentation in the inline assistant
in hopes of improving our experience for Python. We tell the model to
generate the correct indentation in the prompt, and always start
generating at the start of the line. This may fall down for less capable
models, but I want to get a solid experience on the best models and then
figure the rest out later.
Also: We now prefer `./assets/prompts` as an overrides directory when
stdout is a PTY, so you can do `cargo run` and then iterate prompts for
the current run inside the current working copy.
cc @trishume @dsp-ant
Release Notes:
- Zed now allows the model to control indentation when performing inline
transformation. We're hoping this improves the indentation experience in
Python and other indentation-sensitive languages, but it does require
more from the model.
---------
Co-authored-by: Mikayla <mikayla@zed.dev>
Closes https://github.com/zed-industries/zed/issues/16042
This commit modifies the behavior of inline transformations to only
accept finished transformations when the user manually saves the file.
Previously, transformations were automatically accepted on any save
event, including autosaves.
This was achieved by updating the `Pane` and `Workspace` structs to emit
a new `UserSavedItem` event when a manual save occurs, and modifying the
`InlineAssistant` to register and handle this new event (instead of
`editor::Saved`).
Release Notes:
- N/A
Fixes#15923
Release Notes:
- Assistant workflow steps can now be applied and reverted directly from
within the assistant panel.
---------
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Antonio <antonio@zed.dev>
This PR opens workflow step editors as preview tabs and closes them upon
exiting the step if they are still in preview mode and they weren't
already open before entering the step.
Making this work was tricky, because we often edit the buffer as part of
displaying the workflow step suggestions to create empty lines where we
can generate. We undo these edits if the transformation is not applied,
but they were causing the preview to be dismissed.
After trying a few approaches, I decided to give workspace `Item`s a
`preserve_preview` method that defaults to false. When the workspace
sees an edit event for the item, it checks if the item wants to preserve
its preview. For buffers, after editing, you can call `refresh_preview`,
which sets a preview version to the current version of the buffer. Any
edits after this version will cause preview to not be preserved.
One final issue is with async auto-indent. To ensure these async edits
don't dismiss the preview, I automatically refresh the preview version
if preview was preserved prior to performing the auto-indent. The
assumption is that these are edits created by other edits, and if we
didn't want to dismiss the preview with the originating edits, then the
auto-indent edits shouldn't dismiss it either.
Release Notes:
- N/A
---------
Co-authored-by: Jason <jason@zed.dev>
I need this to refine our prompts on the fly as I work.
Release Notes:
- Templates for prompts driving inline transformation in editors and the
terminal can now be overridden in the `~/.config/zed/prompts/templates`
directory. This is an advanced feature, and prevents you from getting
upstream changes. It's intended for use by Zed developers.
We achieved this by allowing block decorations to have a height of `0`
and superimposing the border on top of the line, as opposed to carving
out space below it.
Release Notes:
- N/A
---------
Co-authored-by: Jason <jason@zed.dev>
Release Notes:
- Improved streaming git diffs to be less jumpy during inline assistant
generation
---------
Co-authored-by: Antonio Scandurra <antonio@zed.dev>
After the changes in #15536, block decorations need to be given an
explicit height if their content doesn't consume height on its own. We
missed that inline transformation deletion decorations didn't do this,
creating weird results. This fixes the issue and prevents block
decorations from ever having a zero height. That helps avoid major
weirdness, but this still a bit of a gotcha.
We need to back port this to Preview Channel (0.147.x)
Release Notes:
- N/A
---------
Co-authored-by: Antonio <antonio@zed.dev>
This UI change is behind a `ZedPro` feature flag so that it won't be
visible until we're ready to launch that service.
Release Notes:
- N/A
---------
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
Co-authored-by: Marshall <marshall@zed.dev>
We also eliminate the `completion` crate and moved its logic into
`LanguageModelRegistry`.
Release Notes:
- N/A
---------
Co-authored-by: Nathan <nathan@zed.dev>
Supersedes https://github.com/zed-industries/zed/pull/12090fixes#5180fixes#5055
See original PR for an example of the feature at work.
This PR changes the settings interface to be backwards compatible, and
adds the `ui_font_fallbacks`, `buffer_font_fallbacks`, and
`terminal.font_fallbacks` settings.
Release Notes:
- Added support for font fallbacks via three new settings:
`ui_font_fallbacks`, `buffer_font_fallbacks`, and
`terminal.font_fallbacks`.(#5180, #5055).
---------
Co-authored-by: Junkui Zhang <364772080@qq.com>
When pressing <kbd>control</kbd> + <kbd>enter</kbd>, the AI-powered
inline transformation input displays an icon button and a token count,
which should show roughly the same numbers you'd see on your assistant
panel. At a first glance, though, the token count not being zero can be
confusing, where you'd wonder where that's coming from. That's because
the inline input uses whatever piece of context and/or information of
the currently selected assistant tab to suggest more accurate edits.
So, this PR introduces an informative piece of text to the
`ModelSelector` menu, on the inline transformation input, which delivers
exactly this bit of info, aimed at clarifying the connection between
these two methods of interacting with LLMs.
I've also took the opportunity to change the icon button's icon to one
that's a bit easier to see, still representing the affordance of "click
to configure something".
Release Notes:
- Add note about how inline edits consume context from the assistant
panel to clarify interaction with LLMs.
---------
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
Follow-up of https://github.com/zed-industries/zed/pull/14886
We do not require the branch to be up-to-date with `main` before
merging, and in 4 days some related test code got reworked so that there
were no conflicts and it slipped.
Release Notes:
- N/A
