Follow up #40736
Clean up `CodeBlockRenderer::Custom` related rendering per the previous
PR
[comment](https://github.com/zed-industries/zed/pull/40736#issuecomment-3503074893).
Additional note here:
1. The `Custom` variant in the enum `CodeBlockRenderer` will become not
useful since cleaning all code related to the custom rendering logic.
2. Need to further review the usage of code block `metadata` field in
`MarkdownTag::CodeBlock` enum.
I would like to have the team further review my note above so that we
can make sure it will be safe to clean it up and will not affect any
potential future features will be built on top of it. Thank you!
Release Notes:
- N/A
## Summary
Adds explanations for what each type of scrollbar indicator visually
represents in the editor.
## Description
This PR addresses the issue where users didn't understand what the
colored marks on the scrollbar mean. The existing documentation
explained how to toggle each type of mark on/off, but didn't explain
what they actually represent.
This adds a brief, clear explanation after each scrollbar indicator
setting describing what that indicator shows (e.g., "Git diff indicators
appear as colored marks showing lines that have been added, modified, or
deleted compared to the git HEAD").
## Fixes
Closes#31794
## Test Plan
- Documentation follows the existing style and format of
`docs/src/configuring-zed.md`
- Each explanation is concise and immediately follows the setting
description
- Language is clear and user-friendly
Release Notes:
- N/A
Since we removed the filtering step during context gathering, we want
the model to perform more targeted searches. This PR tweaks search tool
schema allowing the model to search within syntax nodes such as `impl`
blocks or methods.
This is what the query schema looks like now:
```rust
/// Search for relevant code by path, syntax hierarchy, and content.
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
pub struct SearchToolQuery {
/// 1. A glob pattern to match file paths in the codebase to search in.
pub glob: String,
/// 2. Regular expressions to match syntax nodes **by their first line** and hierarchy.
///
/// Subsequent regexes match nodes within the full content of the nodes matched by the previous regexes.
///
/// Example: Searching for a `User` class
/// ["class\s+User"]
///
/// Example: Searching for a `get_full_name` method under a `User` class
/// ["class\s+User", "def\sget_full_name"]
///
/// Skip this field to match on content alone.
#[schemars(length(max = 3))]
#[serde(default)]
pub syntax_node: Vec<String>,
/// 3. An optional regular expression to match the final content that should appear in the results.
///
/// - Content will be matched within all lines of the matched syntax nodes.
/// - If syntax node regexes are provided, this field can be skipped to include as much of the node itself as possible.
/// - If no syntax node regexes are provided, the content will be matched within the entire file.
pub content: Option<String>,
}
```
We'll need to keep refining this, but the core implementation is ready.
Release Notes:
- N/A
---------
Co-authored-by: Ben <ben@zed.dev>
Co-authored-by: Max <max@zed.dev>
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
#42021 Made clicking on an excerpt title toggle it. This PR brings back
the old behavior if a user is pressing the Alt key when clicking on an
excerpt title.
Release Notes:
- N/A
---------
Co-authored-by: Remco Smits <djsmits12@gmail.com>
This is a follow up to #41482. When running `script/bundle-mac`, it will
upload debug symbols to Sentry if you have a `$SENTRY_AUTH_TOKEN` set. I
happen to have one set, so this script was trying to generate and upload
those. Whoops! This change skips the upload entirely if you're running a
local install.
Release Notes:
- N/A
Closes#41969
This was caused because scope names weren't being truncated unlike the
other type of variable list entries.
Release Notes:
- debugger: Fix bug where minimizing the width of the variable list
would cause scope names to overlap
Co-authored-by: Remco Smits <djsmits12@gmail.com>
When rust-analyzer is still loading the cargo project it tends to error
out on most lsp requests with `content modified`. This pollutes our
logs.
Release Notes:
- N/A *or* Added/Fixed/Improved ...
Technically these should not be possible to hit, but sentry says
otherwise. Turning these into errors should give us more information
than the abort due to unwinding across ffi boundaries.
Fixes ZED-321
Release Notes:
- N/A *or* Added/Fixed/Improved ...
Second take on https://github.com/zed-industries/zed/pull/37765.
This PR adds support for styling elements (**b**, **strong**, **em**,
**i**, **ins**, **del**), but also allow you to show the styling text
inline with the current text.
This is done by appending all the up-following text into one text chunk
and merge the highlights from both of them into the already existing
chunk. If there does not exist a text chunk, we will create one and the
next iteration we will use that one to store all the information on.
**Before**
<img width="483" height="692" alt="Screenshot 2025-11-06 at 22 08 09"
src="https://github.com/user-attachments/assets/6158fd3b-066c-4abe-9f8e-bcafae85392e"
/>
**After**
<img width="868" height="300" alt="Screenshot 2025-11-06 at 22 08 21"
src="https://github.com/user-attachments/assets/4d5a7a33-d31c-4514-91c8-2b2a2ff43e0e"
/>
**Code example**
```html
<p>some text <b>bold text</b></p>
<p>some text <strong>strong text</strong></p>
<p>some text <i>italic text</i></p>
<p>some text <em>emphasized text</em></p>
<p>some text <del>delete text</del></p>
<p>some text <ins>insert text</ins></p>
<p>Some text <strong>strong text</strong> more text <b>bold text</b> more text <i>italic text</i> more text <em>emphasized text</em> more text <del>deleted text</del> more text <ins>inserted text</ins></p>
<p><a href="https://example.com">Link Text</a></p>
<p style="text-decoration: underline;">text styled from style attribute</p>
```
cc @bennetbo
**TODO**
- [x] add tests for styling nested text that should result in one merge
Release Notes:
- Markdown Preview: Added support for `HTML` styling elements
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Closes#40097
When multiple files are added sequentially to the agent panel, the
request JSON incorrectly includes "text" elements containing only
spaces. These empty elements cause the Zhipu AI API to return a "text
cannot be empty" error.
The fix filters out any "text" elements that are empty or contain only
whitespaces.
UI state when the error occurs:
<img width="300" alt="Image"
src="https://github.com/user-attachments/assets/c55e5272-3f03-42c0-b412-fa24be2b0043"
/>
Request JSON (causing the error):
```
{
"model": "glm-4.6",
"messages": [
{
"role": "system",
"content": "<<CUT>>"
},
{
"role": "user",
"content": [
{
"type": "text",
"text": "[@1.txt](zed:///agent/file?path=C%3A%5CTemp%5CTest%5C1.txt)"
},
{ "type": "text", "text": " " },
{
"type": "text",
"text": "[@2.txt](zed:///agent/file?path=C%3A%5CTemp%5CTest%5C2.txt)"
},
{ "type": "text", "text": " describe" },
```
Release Notes:
- Fixed an issue when an OpenAI request contained whitespace-only text content
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
### Summary
Restore the agent pane’s code-block horizontal scrollbar for easier
scrolling without trackpad and preserve individual scroll state across
multiple code blocks.
### Motivation
Addresses https://github.com/zed-industries/zed/issues/34224, where
agent responses with wide code snippets couldn’t be scrolled
horizontally in the panel. Previously there is no visual effect for
scrollbar to let the user move the code snippet and it was not obviously
to use trackpad or hold down `shift` while scrolling. This PR will
ensure the user being able to only use their mouse to drag the
horizontal scrollbar to show the complete line when the code overflow
the width of code block.
### Changes
- Support auto-hide horizontal scrollbar for rendering code block in
agent panel by adding scrollbar support in markdown.rs
- Add `code_block_scroll_handles` cache in
_crates/markdown/src/markdown.rs_ to give each code block a persistent
`ScrollHandle`.
- Wrap rendered code blocks with custom horizontal scrollbars that match
the vertical scrollbar styling and track hover visibility.
- Retain or clear scroll handles based on whether horizontal overflow is
enabled, preventing leaks when the markdown re-renders.
### How to Test
1. Open the agent panel, request code generation, and ensure wide
snippets show a horizontal scrollbar on hover.
3. Scroll horizontally, navigate away (e.g., change tabs or trigger a
re-render), and confirm the scroll position sticks when returning.
5. Toggle horizontal overflow styling off/on (if applicable) and verify
scrollbars appear or disappear appropriately.
### Screenshots / Demos (if UI change)
https://github.com/user-attachments/assets/e23f94d9-8fe3-42f5-8f77-81b1005a14c8
### Notes for Reviewers
- This is my first time contribution for `zed`, sorry for any code
patten inconsistency. So please let me know if you have any comments and
suggestions to make the code pattern consistent and easy to maintain.
- For now, the horizontal scrollbar is not configurable from the setting
and the style is fixed with the same design as the vertical one. I am
happy to readjust this setting to fit the needs.
- Please let me know if you think any behaviors or designs need to be
changed for the scrollbar.
- All changes live inside _crates/markdown/src/markdown.rs_; no API
surface changes.
Closes#34224
### Release Notes:
- AI: Show horizontal scroll-bars in wide markdown elements
Closes#40576
This PR makes Conda activation configurable and transparent by adding a
`terminal.detect_venv.on.conda_manager` setting (`"auto" | "conda" |
"mamba" | "micromamba"`, default `"auto"`), updating Python environment
activation to honor this preference (or the detected manager executable)
and fall back to `conda` when necessary.
The preference is passed via `ZED_CONDA_MANAGER` from the terminal
settings, and the activation command is built accordingly (with proper
quoting for paths). Changes span
`zed/crates/terminal/src/terminal_settings.rs` (new `CondaManager` and
setting), `zed/crates/project/src/terminals.rs` (inject env var),
`zed/crates/languages/src/python.rs` (activation logic), and
`zed/assets/settings/default.json` (document the setting). Default
behavior remains unchanged for most users while enabling explicit
selection of `mamba` or `micromamba`.
Release Notes:
- Added: terminal.detect_venv.on.conda_manager setting to choose the
Conda manager (auto, conda, mamba, micromamba). Default: auto.
- Changed: Python Conda environment activation now respects the
configured manager, otherwise uses the detected environment manager
executable, and falls back to conda.
- Reliability: Activation commands quote manager paths to handle spaces
across platforms.
- Compatibility: No breaking changes; non-Conda environments are
unaffected; remote terminals are supported.
---------
Co-authored-by: Lukas Wirth <me@lukaswirth.dev>
Co-authored-by: Lukas Wirth <lukas@zed.dev>
Supersedes https://github.com/zed-industries/zed/pull/39910
At some point, these two (`index_for_x` and `closest_index_for_x`)
methods where separated out and some code paths used one, while other
code paths took the other. That said, their behavior is almost
identical:
- `index_for_x` computes the index behind the pixel offset, and returns
`None` if there's an overshoot
- `closest_index_for_x` computes the nearest index to the pixel offset,
taking into account whether the offset is over halfway through or not.
If there's an overshoot, it returns the length of the line.
Given these two behaviors, `closest_index_for_x` seems to be a more
useful API than `index_for_x`, and indeed the display map and other core
editor features use it extensively. So this PR is an experiment in
simply replacing one behavior with the other.
Release Notes:
- Improved the accuracy of mouse selections in Markdown
Release Notes:
- N/A
---
https://github.com/user-attachments/assets/d46b77ae-88ba-43da-93ad-3656a7fecaf9
The system menu is only support for macOS, so here just modify the macOS
platform special code.
The Windows, Linux used `ApplicationMenu`, I have already added
`checked` option to Zed's ContextMenu.
Then later when this PR merged, we can improve "View" menu to show check
state to panels (Project Panel, Outline Panel, ...).
* Fix a panic that happened because we lost the
`ContextRetrievalStarted` debug message, so we didn't assign `t0`.
* Write the edit prediction response log file as a markdown file
containing the text, not a JSON file. We mostly always want the text
content.
Release Notes:
- N/A
If we are in a remote session with the remote dropped, this path is very
much reachable if the call to this function got queued up in a task.
Fixes ZED-124
Release Notes:
- N/A *or* Added/Fixed/Improved ...
Previously, staging a large file in the git panel would block the UI
items until that operation finished. This is due to the fact that
staging is a git op that is locked globally by git (per repo) meaning
only one op that is modifying the git index can run at any one time. In
order to make the UI snappy while letting any pending git staging jobs
to finish in the background, we track their progress via `PendingOps`
indexed by git entry path. We have already had a concept of pending
operations however they existed at the UI layer in the `GitPanel`
abstraction. This PR moves and augments `PendingOps` into the model
`Repository` in `git_store` which seems like a more natural place for
tracking running git jobs/operations. Thanks to this, pending ops are
now stored in a `SumTree` indexed by git entry path part of the
`Repository` snapshot, which makes for efficient access from the UI.
Release Notes:
- Improved UI responsiveness when staging/unstaging large files in the
git panel
* Allow expressing alternative possible context fetches in `Expected
Context` section
* Allow marking a subset of lines as "required" in `Expected Context`.
We still need to improve how we display the results. I've removed the
context pass/fail pretty printing for now, because it would need to be
rethought to work with the new structure, but for now I think we should
focus on getting basic predictions to run. But this is progress toward a
better structure for eval examples.
Release Notes:
- N/A
---------
Co-authored-by: Oleksiy Syvokon <oleksiy.syvokon@gmail.com>
Co-authored-by: Ben Kunkle <ben@zed.dev>
Co-authored-by: Agus Zubiaga <agus@zed.dev>
