Now, tabs have arguments, `active` (default, applied also for no
arguments case) and `all` to insert the active tab only or all tabs.
Release Notes:
- N/A
This adds a pulsating effect to the assistant header in case the message
is pending.
The pulsating effect is capped between 0.2 and 1.0 and I tried (with the
help of Claude) to give it a "breathing" effect, since I found the
normal bounce a bit too much.
Also opted for setting the `alpha` on the `LabelLike` things, vs.
overwriting the color, since I think that's cleaner instead of exposing
the color and mutating that.
https://github.com/user-attachments/assets/4a94a1c5-8dc7-4c40-b30f-d92d112db7b5
Release Notes:
- N/A
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>
This PR adds the ability to revoke access tokens for the LLM service.
There is a new `revoked_access_tokens` table that contains the
identifiers (`jti`) of revoked access tokens.
To revoke an access token, insert a record into this table:
```sql
insert into revoked_access_tokens (jti) values ('1e887b9e-37f5-49e8-8feb-3274e5a86b67');
```
We now attach the `jti` as `authn.jti` to the tracing spans so that we
can associate an access token with a given request to the LLM service.
Release Notes:
- N/A
This PR adds feature-flagged access to the LLM service.
We've repurposed the `language-models` feature flag to be used for
providing access to Claude 3.5 Sonnet through the Zed provider.
The remaining RPC endpoints that were previously behind the
`language-models` feature flag are now behind a staff check.
We also put some Zed Pro related messaging behind a feature flag.
Release Notes:
- N/A
---------
Co-authored-by: Max <max@zed.dev>
On top of `editor::ScrollCursorCenter`, `editor::ScrollCursorTop`,
`editor::ScrollCursorBottom` actions, adds an
`editor::ScrollCursorCenterTopBottom` one, that allows using a single
keybinding to scroll between positions on the screen.
The implementation matches a corresponding Emacs feature: there's a
timeout (1s) that is kept after every switch, to allow continuously
changing the positions, center (initial) -> top -> bottom
Scrolling behavior is the same as the existing actions (e.g. editor will
ignore scroll to bottom, if there's not enough space above).
After 1s, next position is reset to the initial, center, one.
Release Notes:
- Added an `editor::ScrollCursorCenterTopBottom` action for toggling
scroll position with a single keybinding
---------
Co-authored-by: Alex Kladov <aleksey.kladov@gmail.com>
This PR restricts usage of the LLM service to accounts older than 30
days.
We now store the GitHub user's `created_at` timestamp to check the
GitHub account age. If this is not set—which it won't be for existing
users—then we use the `created_at` timestamp in the Zed database.
Release Notes:
- N/A
---------
Co-authored-by: Max <max@zed.dev>
Improves workflows, based on the keymaps that group actions behind a
certain symbol.
E.g.
```json5
", o k": "zed::OpenKeymap",
", o K": "zed::OpenDefaultKeymap",
// other `,`-based keymaps
```
Now, it's possible to do
```json
", ,": ["editor::HandleInput", ","]
```
and type `,` without waiting for the timeout due to `,`-based bindings.
Release Notes:
- Add an `editor::HandleInput` action to ease typing symbols that are
part of keymaps. E.g. if `, o k` keybinding is bound, `", ,":
["editor::HandleInput", ","]` would allow to type `,` without timeouts.
---------
Co-authored-by: Alex Kladov <aleksey.kladov@gmail.com>
Now, when an anthropic request is invalid or anthropic's API is down,
we'll expose that to the user instead of just returning a generic 500.
Release Notes:
- N/A
Co-authored-by: Marshall <marshall@zed.dev>
This PR makes it so Zed staff can use a separate Anthropic API key for
the LLM service.
We also added an `is_staff` column to the `usages` table so that we can
exclude staff usage from the "active users" metrics that influence the
rate limits.
Release Notes:
- N/A
---------
Co-authored-by: Max <max@zed.dev>
This PR adds a check to the LLM API token issuance to ensure that we
only issue tokens to users that have accepted the terms of service.
Release Notes:
- N/A
This PR makes it so hitting upstream rate limits from Anthropic result
in an HTTP 429 response instead of an HTTP 500.
To do this we need to surface structured errors out of the `anthropic`
crate.
Release Notes:
- N/A
This adds the requirement for users to accept the terms of service the
first time they send a message with the Cloud provider.
Once this is out and in a nightly, we need to add the check to the
server side too, to authenticate access to the models.
Demo:
https://github.com/user-attachments/assets/0edebf74-8120-4fa2-b801-bb76f04e8a17
Release Notes:
- N/A
# HTTP Client Improvements for Extension API
This PR enhances the HTTP client functionality in the Zed extension API,
providing more control over requests and allowing for streaming
responses.
## Key Changes
1. Extended `HttpRequest` struct:
- Added `method` field to specify HTTP method
- Added `headers` field for custom headers
- Added optional `body` field for request payload
2. Introduced `HttpMethod` enum for supported HTTP methods
3. Updated `HttpResponse` struct:
- Added `headers` field to access response headers
- Changed `body` type from `String` to `Vec<u8>` for binary data support
4. Added streaming support:
- New `fetch_stream` function to get a response stream
- Introduced `HttpResponseStream` resource for chunked reading
5. Updated internal implementations to support these new features
6. Modified the Gleam extension to use the new API structure
## Motivation
These changes provide extension developers with more flexibility and
control over HTTP requests. The streaming support is particularly useful
for handling large responses efficiently or ideally streaming into the
UI.
## Testing
- [x] Updated existing tests
- [ ] Added new tests for streaming functionality
## Next Steps
- Consider adding more comprehensive examples in the documentation
- Evaluate performance impact of streaming for large responses
Please review and let me know if any adjustments are needed.
Release Notes:
- N/A
---------
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
This PR removes the `llm-service` feature flag and makes it so all
completions are done via the LLM service when using the Zed provider.
Release Notes:
- N/A
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
This PR improves workflow step management and symbol matching. We've
optimized step pruning to remove any step that intersects an edit and
switched to normalized Levenshtein distance for more accurate symbol
matching.
Release Notes:
- N/A
This PR introduces a new script for iterative development of prompt
overrides in Zed.
Just `script/prompts link` and your running Zed should start using
prompts from `zed/assets/prompts`. Use `script/prompts unlink` to undo.
You can also link with `script/prompts link --worktree` to store the
prompts to a `../zed_prompts` worktree that's a sibling of your repo, in
case you don't want to mess with your working copy. Just don't forget
about it!
Key changes:
- Add new `script/prompts` for managing prompt overrides
- Rename `prompt_templates_dir` to `prompt_overrides_dir` for clarity
- Update paths to use `~/.config/zed/prompt_overrides` instead of
`~/.config/zed/prompts/templates`
- Adjust `PromptBuilder` to use the new `prompt_overrides_dir` function
These changes simplify the process of customizing prompts and provide a
more intuitive naming convention for override-related functionality.
Release Notes:
- N/A
This PR makes it so staff members will be exempt from rate limiting by
the LLM service.
This is just a temporary measure until we can tweak the rate-limiting
heuristics.
Staff members are still subject to upstream LLM provider rate limits.
Release Notes:
- N/A
Copies rust files from extension_api/wit to the OUT_DIR to allow
including them from within the crate, which is supported by
rust-analyzer. This allows rust-analyzer to deal with the included
files. It doesn't currently support files outside the crate.
Release Notes:
- N/A
This makes sure that the `vertical_scroll_margin` doesn't leave the
cursor out of screen or somewhere it shouldn't go when it's higher than
the visible lines on screen.
So we cap it to `visible_line_count / 2`, similar to nvim:
5aa1a9532c/src/nvim/window.c (L6560)Fixes#15101
Release Notes:
- Fixed `ctrl-u`/`ctrl-d` in Vim mode not working correctly when
`vertical_scroll_margin` is set to a really high value.
Co-authored-by: Bennet <bennet@zed.dev>
When setting `"vertical_scroll_margin": 99` or other high values this
can lead to a panic that crashes Zed.
Release Notes:
- vim: Fixed a possible panic that could happen when using a very high
value for `vertical_scroll_margin` that exceeded the number of visible
lines on the screen.
Co-authored-by: Bennet <bennet@zed.dev>
This makes it at least scroll again, but it doesn't scroll down to the
last element yet. We haven't figured out why yet.
Release Notes:
- N/A
Co-authored-by: Bennet <bennet@zed.dev>
Co-authored-by: Antonio <antonio@zed.dev>
We had to resort to this "hack" to get it to work, since nothing else we
tried (changing the `Pane`, changing the `ConfigurationView`, changing
the `AssistantPanel`, ...) worked.
Release Notes:
- N/A
Co-authored-by: Antonio <antonio@zed.dev>
Co-authored-by: Bennet <bennet@zed.dev>
When switching to function definitions in a new buffer the
`AutoscrollStrategy::Focused` being emitted to scroll to the found
location.
If a large value `vertical_scroll_margin` (e.g.: 99) is set, this leads
to an incorrectly calculated position and the new buffer opens in the
wrong place.
In `autoscroll_vertically()` there is a margin calculated to cap the
value of `vertical_scroll_margin` for certain AutoscrollStrategies. This
margin is being used in `AutoscrollStrategy::Fit` and
`AutoscrollStrategy::Newest` but was probably forgotten for
`AutoscrollStrategy::Focused`.
- Might fix [#15101](https://github.com/zed-industries/zed/issues/15101)
Release Notes:
- N/A
This implements #15412. Row-column parsing is changed into a regex to
support more complex patterns like the MSBuild diagnostics. Terminal
`word_regex` is also relaxed to match those suffixes.
Release Notes:
- N/A
This PR adds syntax highlighting support for `css`, `html`, `js`,
`json`, `sql`, `ts`, `yaml` and `yml` in `javascript`, `typescript` and
`tsx` languages where the contents of tagged template literals are now
highlighted.
This does not actually enable language features (like LSP support), it
only does syntax highlighting.
Before this change:
<img width="561" alt="image"
src="https://github.com/user-attachments/assets/74bace1b-5ce1-4b17-8a97-035bba152d9c">
After this change:
<img width="607" alt="image"
src="https://github.com/user-attachments/assets/f227145b-3f4a-4c27-b14f-7143bb19b4cf">
/cc @mrnugget
Release Notes:
- Added syntax highlighting for tagged template literals in
`javascript`, `typescript` and `tsx` languages for `css`, `html`, `js`,
`json`, `sql`, `ts`, `yaml` and `yml`.
([#15984](https://github.com/zed-industries/zed/issues/15984))
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>
When Anthropic releases a new version of their models, Zed AI users
should always get access to the new version even when using an old
version of zed.
Co-Authored-By: Thorsten <thorsten@zed.dev>
Release Notes:
- N/A
Co-authored-by: Thorsten <thorsten@zed.dev>
This adds an error notification that pops up when the user has an
invalid keymap, similar to what we added for settings in #15905.
Release Notes:
- Added a popup that is displayed when the keymap is invalid
This PR polishes elements around setting up LLM providers on the
Assistant panel, including:
- [x] Adding banners for promoting Zed AI and to deal with the "No
provider set up" scenario
- [x] Tweaking the error popover whenever there's no API key added
- [ ] Making configuration panel scrollable
---
Release Notes:
- N/A
---------
Co-authored-by: Thorsten Ball <mrnugget@gmail.com>
Co-authored-by: Bennet Bo Fenner <53836821+bennetbo@users.noreply.github.com>
Co-authored-by: Marshall Bowers <1486634+maxdeviant@users.noreply.github.com>
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>
This PR adjusts how we display the "mode" collab is running in on the
root endpoint.
It's minor, but it does make things a bit cleaner.
Release Notes:
- N/A
This prevents users from accessing other models, such as OpenAI's GPT-4
or Google's Gemini-Pro.
Staff members can still access all models.
Co-authored-by: Thorsten <thorsten@zed.dev>
Release Notes:
- N/A
---------
Co-authored-by: Thorsten <thorsten@zed.dev>
Release Notes:
- Fixed a (potential) small error in erf estimation. Technically, the
error is negligible.
I am not sure where the current calculation for erf come from and if it
is intended or a simple mistake. However it looks slightly different
from the official calculation, notably
[this](https://en.wikipedia.org/wiki/Error_function#Approximation_with_elementary_functions)
from Wikipedia.
I will add a comment if it is intended.
This will help us as we hit issues with the /workflow and step
resolution. We can override the baked-in prompts and make tweaks, then
import our refinements back into the source tree when we're ready.
Release Notes:
- N/A
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.
<img width="862" alt="image"
src="https://github.com/user-attachments/assets/ae8c479d-d9f9-4c46-bb1a-be411ab07876">
Release Notes:
- Added additional context about available to kernel sessions
- Fixed bug in kernelspec launch choosing first available kernel
matching the language rather than selected name
---------
Co-authored-by: Jason <jason@zed.dev>
This PR removes the unused `ignore_checksum_mismatch` parameter to
`run_database_migrations`.
We were always passing `false`, which meant the behavior didn't need to
be parameterized.
Release Notes:
- N/A
This PR puts the initial infrastructure for the LLM service's database
in place.
The LLM service will be using a separate Postgres database, with its own
set of migrations.
Currently we only connect to the database in development, as we don't
yet have the database setup for the staging/production environments.
Release Notes:
- N/A
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>
This PR updates the LLM service to authorize access to language model
providers based on the requester's country.
We detect the country using Cloudflare's
[`CF-IPCountry`](https://developers.cloudflare.com/fundamentals/reference/http-request-headers/#cf-ipcountry)
header.
The country code is then checked against the list of supported countries
for the given LLM provider. Countries that are not supported will
receive an `HTTP 451: Unavailable For Legal Reasons` response.
Release Notes:
- N/A
- [x] OpenAI
- [ ] ~Google~ Moved into a separate branch at:
https://github.com/zed-industries/zed/tree/tool-calls-in-google-ai I've
ran into issues with having the API digest our schema without tripping
over itself - the function call parameters are malformed and whatnot. We
can resume from that branch if needed.
- [x] Ollama
- [x] Cloud
- [ ] ~Copilot Chat (?)~
Release Notes:
- Added tool calling capabilities to OpenAI and Ollama models.
Release Notes:
- Improved streaming git diffs to be less jumpy during inline assistant
generation
---------
Co-authored-by: Antonio Scandurra <antonio@zed.dev>
Adds a "Use Supermaven" and "Use Copilot" menu item to the signed out
menus for each of the autocomplete providers to make it easier to switch
between them without having to update your local settings json.
<img width="222" alt="image"
src="https://github.com/user-attachments/assets/6f760f4e-5527-4971-bdaf-383bc99649bd">
Release Notes:
- Added menu items to quickly switch between Supermaven and Copilot
inline completions when the provider is not configured
We changed the following for the model selector:
- Fixed displaying checkmarks for selected models when using models with
the same name from different providers
- We now show the icon for the active model instead of displaying the
provider name in the trigger of the model selector
- Only display the footer when the language models feature flag is zed,
so that we don't release the hint for Zed Pro to preview tomorrow
<img width="253" alt="image"
src="https://github.com/user-attachments/assets/f95ccfb6-c0cf-43d4-9637-e2823100a427">
Release Notes:
- N/A
---------
Co-authored-by: Thorsten <thorsten@zed.dev>
