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
This PR increases the size of the the icon buttons within the inline
editors, both within the buffer and on the terminal. I also added
properties to make sure they always render as a square, as well as
tweaking the stop icon SVG, adding an alternative sparkle icon that fit
the same grid as the close (14x14) icon, and adding a bit more right
padding on the buffer's case so it doesn't collide with the scrollbar.
End result is that they have a bit of an easier target space area and
normalized sizes.
---
Release Notes:
- N/A
When using the inline assistant with a language such as Go that uses
tabs, if the user selects a block of text that is correctly formatted
and where the first line has no indentation, the `suggested_line_indent`
variable ends up with `IndentSize { len: 0, kind: Space }`. That's
because `suggested_line_indent` current relies on
`BufferSnapshot::suggested_indents` suggestion for the first line on the
selection, but since it is already correctly indented, there are no
suggestions and `MultiBufferSnapshot::indent_size_for_line` is used
instead.
2d96bba61f/crates/assistant/src/inline_assistant.rs (L2124-L2128)
In this patch, we also take a look at the rest of the selection and
detect tabs. If one is encountered, we assume that tabs should always be
used. I suppose this isn't perfect, especially if the original file had
a mix of spaces and tabs, however it seems better than the status quo.
I considered using `BufferSnapshot::language_indent_size_at`, but I
imagine tabs should be preserved even when a specific language isn't
being used.
See screenshot below of the original prompt with this patch.
Tests:
* New unit test
* I've also manually tested with a few other cases: selection where all
lines are indented and file that only use spaces.
Release Notes:
- Fixed 'inline_assistant: tabs are overwritten with space characters
when first line in selection has no indentation'
([#14885](https://github.com/zed-industries/zed/issues/14885)).
<img width="942" alt="image"
src="https://github.com/user-attachments/assets/f2c5d7e9-e8bc-400b-bd6f-09e4a89d22c1">
This PR mostly refines the model selector popover design by formatting
the models names' and adjusting spacing/alignment in the list-related
items. The list component changes could've been made in a separate PR
but it was also very practical to do it here as I was already
in-context. Either way, I'm happy to separate if that's better!
One thing I couldn't necessarily figure out, though, is why the order
changed (e.g., Anthropic at last ). I wonder if that was because of the
separator logic somehow? I'd love guidance here—new to Rust!
| Before | After |
|--------|--------|
| <img width="228" alt="Screenshot 2024-07-23 at 21 02 33"
src="https://github.com/user-attachments/assets/3372c6c9-08dc-4d71-9265-26f015e2dbc2">
| <img width="228" alt="Screenshot 2024-07-23 at 21 01 45"
src="https://github.com/user-attachments/assets/624cc7db-a3d9-48e3-99d7-c29829501130">
|
---
Release Notes:
- N/A
---------
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
Co-authored-by: Bennet Bo Fenner <bennet@zed.dev>
Co-authored-by: Antonio <antonio@zed.dev>
Co-authored-by: Antonio Scandurra <me@as-cii.com>
<img width="624" alt="image"
src="https://github.com/user-attachments/assets/f492b0bd-14c3-49e2-b2ff-dc78e52b0815">
- [x] Correctly set custom model token count
- [x] How to count tokens for Gemini models?
- [x] Feature flag zed.dev provider
- [x] Figure out how to configure custom models
- [ ] Update docs
Release Notes:
- Added support for quickly switching between multiple language model
providers in the assistant panel
---------
Co-authored-by: Antonio <antonio@zed.dev>
This PR updates a number of spots where we were setting all of the
`TextStyle` fields even if we were not changing the values from the
defaults.
We now use `..Default::default()`.
Release Notes:
- N/A
We will soon need `semantic_index` to be able to use
`CompletionProvider`. This is currently impossible due to a cyclic crate
dependency, because `CompletionProvider` lives in the `assistant` crate,
which depends on `semantic_index`.
This PR breaks the dependency cycle by extracting two crates out of
`assistant`: `language_model` and `completion`.
Only one piece of logic changed: [this
code](922fcaf5a6 (diff-3857b3707687a4d585f1200eec4c34a7a079eae8d303b4ce5b4fce46234ace9fR61-R69)).
* As of https://github.com/zed-industries/zed/pull/13276, whenever we
ask a given completion provider for its available models, OpenAI
providers would go and ask the global assistant settings whether the
user had configured an `available_models` setting, and if so, return
that.
* This PR changes it so that instead of eagerly asking the assistant
settings for this info (the new crate must not depend on `assistant`, or
else the dependency cycle would be back), OpenAI completion providers
now store the user-configured settings as part of their struct, and
whenever the settings change, we update the provider.
In theory, this change should not change user-visible behavior...but
since it's the only change in this large PR that's more than just moving
code around, I'm mentioning it here in case there's an unexpected
regression in practice! (cc @amtoaer in case you'd like to try out this
branch and verify that the feature is still working the way you expect.)
Release Notes:
- N/A
---------
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
Release Notes:
- Fixed a bug that caused focus to be lost when renames and inline
assists were scrolled offscreen.
---------
Co-authored-by: Nathan <nathan@zed.dev>
Note that this shouldn't have any visible user-facing behavior yet. The
feature is incomplete but we wanna merge early to avoid a long-running
branch.
Release Notes:
- N/A
---------
Co-authored-by: Nathan <nathan@zed.dev>
This PR refactors the completion providers to only process a maximum
amount of completion requests at a time.
Also started refactoring language model providers to use traits, so it's
easier to allow specifying multiple providers in the future.
Release Notes:
- N/A
Fix a minor bug when the inline assistant model spits out an empty line
with leading indentation on it. This happens sometimes with Claude 3.5
Sonnet and currently it causes the following line to have the wrong
indentation.
Release Notes:
- N/A
Release Notes:
- Now when an editor loses focus (e.g. from switching tabs) and then
gains focus again, it doesn't close the inline assist. Instead, it only
closes when you move the cursor outside of it, e.g. by clicking
somewhere else in its parent editor.
---------
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Release Notes:
- Improved UX for the inline assistant. It will now automatically wrap
when the text gets too long, and you can insert newlines using
`shift-enter`.
