Closes#16544
Release Notes:
- Added support for AWS Bedrock to the Assistant.
---------
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
Co-authored-by: Anthony <anthony@zed.dev>
Co-authored-by: Anthony Eid <hello@anthonyeid.me>
Co-authored-by: Anthony Eid <hello@anthonyeid.me>
Release Notes:
- Fix run indicators jumping when content changes
---------
Co-authored-by: Anthony Eid <hello@anthonyeid.me>
Co-authored-by: Anthony Eid <hello@anthonyeid.me>
Closes#19022
Release Notes:
- Fixes pessimal performance with the new git panel when a very large
number of files are untracked
Co-authored-by: Anthony Eid <hello@anthonyeid.me>
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
Should make it less likely that notorization fails when nathan changes
his passwords.
(though probably no less likly to fail beacuse apple forces us to resign
new agreements on the regular)
Release Notes:
- N/A
---------
Co-authored-by: Peter Tripp <peter@zed.dev>
This PR removes the dependencies on the individual model provider crates
from the `language_model` crate.
The various conversion methods for converting a `LanguageModelRequest`
into its provider-specific request type have been inlined into the
various provider modules in the `language_models` crate.
The model providers we provide via Zed's cloud offering get to stay, for
now.
Release Notes:
- N/A
Closes https://github.com/zed-industries/zed/issues/25406
### Problem
Users have been confused about requiring `alt-tab` instead of just `tab`
in cases where they don't have a completions menu open (see issue
above). When they insert a newline and are in leading whitespace, they
expect to be able to accept a prediction with just `tab`, but doing so
increasing the indentation instead.
This PR changes the behavior in so a modifier is only required if the
cursor isn't already at the right indentation level based on the
surrounding block. In this case, `tab` would increase the indentation
and the prediction would get interpolated, allowing the user to press
`tab` again to accept it.
We also updated the docs to break down this behavior:
https://github.com/zed-industries/zed/pull/25493
### Before
https://github.com/user-attachments/assets/91fe6193-dddd-43c1-8c26-0f4648bdc3fa
### After
https://github.com/user-attachments/assets/671041bf-bf22-46a3-8466-b19b3e7dd6a0
Release Notes:
- edit predictions: Do not require a modifier key when indentation is
correct according to its surrounding block
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
This function has grown a lot and it was getting really hard to
navigate. This PR splits it into smaller methods and moves it into
`Editor` with the rest of the edit prediction popovers' code.
I think there are opportunities to consolidate the many popovers we
have, but we'll do that separately.
Release Notes:
- N/A
Follow up to @0xtimsb's PR
https://github.com/zed-industries/zed/pull/22658.
- We're now changing the marked entry as we change the active buffer via
the pane tabs. If all tabs are closed, we clear all marked entries, too.
That means: if we have no open buffer, we don't have any highlighted
entry (i.e., background color) in the project panel.
- Also, now only marked entries have a different, more distinct
background color. The `is_active` state doesn't change an item's
background color anymore.
- This improves an edge case where you could have multiple entries
marked—where all of them would have a background color—and upon
unmarking one of them, that entry would continue to have a bg color.
Now, once you click or move your focus to unmark that entry, the bg
color goes away.
We discovered some new problems by doing these changes that we want to
fix:
1. If you open a project without any open buffer, focus on the project
panel, navigate with arrows to a given entry, and hit space, you will
mark and open the file in the buffer. This is all correct. If you then
hit `escape` to clear the marked entries, nothing happens to the open
buffer, and the marked styled in the project panel entry go away. This
is all correct. The wrong behavior happens if you now hit space _again_
on the active entry. That should mark it, and thus change its styles,
but it doesn't happen. You just see it upon moving to a different entry
with arrow up/down.
2. If you mark multiple entries on the project panel and then click on
an open buffer, we still see all the multiple entries marked. This feels
incorrect. We should only allow one marked entry at a time.
These fixes should happen in follow up PRs, though.
Release Notes:
- Improved the scenario where there'd be a project panel entry
highlighted/marked even if there is no open buffer.
---------
Co-authored-by: smit <0xtimsb@gmail.com>
Closes#6701 (one of the top ranking issues as of writing)
Adds the ability to specify an HTTP/HTTPS proxy to route Copilot code
completion API requests through. This should fix copilot functionality
in restricted network environments (where such a proxy is required) but
also opens up the ability to point copilot code completion requests at
your own local LLM, using e.g.:
- https://github.com/jjleng/copilot-proxy
- https://github.com/bernardo-bruning/ollama-copilot/tree/master
External MITM-proxy tools permitting, this can serve as a stop-gap to
allow local LLM code completion in Zed until a proper OpenAI-compatible
local code completions provider is implemented. With this in mind, in
this PR I've added separate `settings.json` variables to configure a
proxy server _specific to the code completions provider_ instead of
using the global `proxy` setting, to allow for cases like this where we
_only_ want to proxy e.g. the Copilot requests, but not all outgoing
traffic from the application.
Currently, two new settings are added:
- `inline_completions.copilot.proxy`: Proxy server URL (HTTP and HTTPS
schemes supported)
- `inline_completions.copilot.proxy_no_verify`: Whether to disable
certificate verification through the proxy
Example:
```js
"features": {
"inline_completion_provider": "copilot"
},
"show_completions_on_input": true,
// New:
"inline_completions": {
"copilot": {
"proxy": "http://example.com:15432",
"proxy_no_verify": true
}
}
```
Release Notes:
- Added the ability to specify an HTTP/HTTPS proxy for Copilot.
---------
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
This PR changes the color used for `@variable` syntax highlights in the
Gruvbox themes to be less intense.
We now use the same color as `editor.foreground`.
| Language | Before | After |
| -------- |
-----------------------------------------------------------------------------------------------------------------------------------------------------
|
-----------------------------------------------------------------------------------------------------------------------------------------------------
|
| Rust | <img width="1410" alt="Screenshot 2025-02-24 at 10 08 41 AM"
src="https://github.com/user-attachments/assets/9a34964d-9fdc-4deb-ac30-4a1c9e6fb531"
/> | <img width="1410" alt="Screenshot 2025-02-24 at 10 55 18 AM"
src="https://github.com/user-attachments/assets/c245d0fd-28af-42b8-93f6-48cb14671d94"
/> |
| Python | <img width="1410" alt="Screenshot 2025-02-24 at 10 08 38 AM"
src="https://github.com/user-attachments/assets/8f8d111e-1d50-4229-a333-eb29b6ce9f4f"
/> | <img width="1410" alt="Screenshot 2025-02-24 at 10 55 20 AM"
src="https://github.com/user-attachments/assets/010b661e-dc9e-4ccb-8e52-ee10c8eb8342"
/> |
In #25333 and #25331 the highlight used for identifiers in Rust and
Python, respectively, was changed to `@variable`, which resulted in the
intense colors you see in the "Before" screenshots above.
We considered reverting the highlight query changes to those languages,
but after taking a look at our other languages, they already use similar
queries. Instead we're adjusting the theme to make these cases less
visually intense.
Release Notes:
- Gruvbox themes: Changed the color used for `@variable` syntax
highlights to be less intense.
Renamed the `FileToolInput` structure to `NowToolInput` to better
reflect its purpose, as the tool is related to time-based operations.
Release Notes:
- N/A
Signed-off-by: Nikita Pivkin <nikita.pivkin@smartforce.io>
If you looked that up via the Command Palette, we were showing an
outdated action name ("new context") which causes confusion given the
panel says "New Chat".
Release Notes:
- N/A
Closes#12236
This PR fixes an issue where the `auto_indent_on_paste` setting was not
being applied for pasting in Vim mode. It was correctly used for normal
paste behavior.
Also includes tests.
Release Notes:
- Fixed yank + paste indenting incorrectly when `auto_indent_on_paste`
is set to `false` in certain languages.
Closes#24746
This PR modifies the implementation of `copy_recursive`. Previously, we
were copying and pasting simultaneously, which caused an issue when a
user copied a folder into one of its subfolders. This resulted in new
content being created in the folder while copying, and subsequent
recursive calls to `copy_recursive` would continue this process, leading
to an infinite loop.
In this PR, the approach has been changed: we now first collect the
paths of the files to be copied, and only then perform the copy
operation.
Additionally, I have added corresponding tests. On the main branch, this
test would previously run indefinitely.
Release Notes:
- Fixed `copy_recursive` runs infinitely when copying a folder into its
subfolder.
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
This PR removes the outdated note about pinning `@vue/language-server`
to v1.8.
As of https://github.com/zed-extensions/vue/pull/1 we now use the latest
available version.
Release Notes:
- N/A
Maybe it's not a very common, but it has a place to be.
Release Notes:
- Added `LICENSE.md` and `LICENCE.md` files to license detection for
edit prediction.
---------
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
This PR is an attempt to add support for `--target-dir` argument to
`cargo` commands when executing tasks with rust.
When using VSCode I was already using this trick to not block the
current binary compilation when I was trying a specific test. As it's a
different target directory it won't block the `cargo` commands I'm using
in my terminal.
I used the task variables to achieve this but I'm not sure it's the best
option to be honest. I didn't find any examples in your docs to see if
sometimes you had specific configuration for languages and tasks.
Let me know if this solution would be a good fit and if the
implementation is ok.
If so feel free to redirect me to an example I can reproduce to write a
unit test or so... And I will also update the docs.
Example of config:
```
{
"languages": {
"Rust": {
"tasks": {
"variables": {
"RUST_TARGET_DIR": ".cargo_check"
}
}
}
}
}
```
it will run `cargo test -p XXX --target-dir .cargo-check`
Release Notes:
- Added support for `--target-dir` for Rust tasks
---------
Signed-off-by: Benjamin <5719034+bnjjj@users.noreply.github.com>
