Closes https://github.com/zed-industries/zed/issues/37087
This PR adds an icon button to the footer of the message editor enabling
to trigger and interact with the @-mention completions menu with the
mouse. This is a first step towards making other types of context you
can add in Zed's agent panel more discoverable. Next, I want to improve
the discoverability of images and selections, given that you wouldn't
necessarily know they work in Zed without a clear way to see them. But I
think that for now, this is enough to close the issue above, which had
lots of productive comments and discussion!
<img width="500" height="540" alt="Screenshot 2025-11-11 at 10 46 3@2x"
src="https://github.com/user-attachments/assets/fd028442-6f77-4153-bea1-c0b815da4ac6"
/>
Release Notes:
- agent: Added an icon button in the agent panel that allows to trigger
the @-mention menu (for adding context) now also with the mouse.
This PR creates a dedicated function for the agent panel message
editor's placeholder text so that we can wait for the agent
initialization to capture whether they support slash commands or not. On
the one (nice) hand, this allow us to stop matching agents by name and
make this a bit more generic. On the other (bad) hand, the "/ for
commands" bit should take a little second to show up because we can only
know whether an agent supports it after it is initialized.
This is particularly relevant now that we have agents coming from
extensions and for them, we would obviously not be able to match by
name.
Release Notes:
- agent: Fixed agent panel message editor's placeholder text by making
it more accurate as to whether agents support slash commands,
particularly those coming from extensions.
Closes https://github.com/zed-industries/zed/issues/42356
This PR fixes the history view losing focus by simply always displaying
the search editor. I don't think it's too weird to not have it when it's
empty, and it also ends up matching how regular pickers work.
Release Notes:
- agent: Fixed a bug where navigating the agent panel with the keyboard
wouldn't work if you visited the history view and it was empty/had no
entries.
Closes#42178
Now it's consistent with the DateAndTime path which already does
timezone conversion.
- **Future Work**
Happy to tackle the TODO in `time_format.rs` about implementing native
Windows APIs for proper localized formatting (similar to macOS's
`CFDateFormatter`) as a follow-up.
Release Notes:
- agent: Fixed the thread history item timestamp, which was being shown
in GMT instead of in the user's local timezone on Windows.
We can always include symbols, since we either include a ResourceLink to
the symbol (when `PromptCapabilities::embedded_context = false`) or a
Resource (when `PromptCapabilities::embedded_context = true`)
Release Notes:
- Fixed an issue where symbols could not be included when using specific
ACP agents
Agents running in extensions need to have a root directory of the
extension's dir for installation and authentication, but *not* for the
conversation itself - otherwise the agent is running things like
terminal commands in the wrong dir.
Release Notes:
- Fixed Agent Server extensions having the current working directory of
the extension rather than the project
This makes it possible to do login via things like `cmd: "node", args:
["my-node-file.js", "login"]`
Also, that command will now use Zed's managed `node` instance.
Release Notes:
- ACP extensions can now run terminal login commands using relative
paths
This PR changes the loading/generating indicator when in the "waiting
for tool call confirmation" state so that's a bit more visible and
discernible as needing your attention, as opposed to a regular
generating state.
<img width="400" alt="Screenshot 2025-11-05 at 10 46@2x"
src="https://github.com/user-attachments/assets/88adbf97-20fb-49c4-9c77-b0a3a22aa14e"
/>
Release Notes:
- agent: Improved the "waiting for confirmation" state visibility so
that you more rapidly know the agent is waiting for you to act.
As discussed with @benbrandt and @mikayla-maki:
* We now tell ACP clients we support the nonstandard `terminal-auth`
`_meta` field for terminal-based authentication
* In the future, we anticipate ACP itself supporting *some* form of
terminal-based authentication, but that hasn't been designed yet or gone
through the RFD process
* For now, this unblocks terminal-based auth
Release Notes:
- Added experimental terminal-based authentication to ACP support
Noticed this whilst testing the Docker debugger. I randomly scrolled the
console off screen and was confused briefly as to why this was the case.
Release Notes:
- The debugger query console will no longer needlessly overscroll.
The button could not be clicked whenever the editor was currently not
focused. This PR fixes this and also registers the action on a more
global level, similar to how this is done for all the other agent
actions.
Release Notes:
- Fixed an issue where the `Expand message editor` button would not work
in agent threads if the message editor was not focused.
This PR makes it clearer that you can click on the file path to open the
corresponding file in the agent panel's "edit bar", which is the element
that shows up in the panel as soon as agent-made edits happen.
Release Notes:
- agent panel: Improved the "go to file" affordance in the edit bar.
Release Notes:
- N/A
---
Previously, agent markdown rendering used hardcoded font sizes
(TextSize::Default and TextSize::Small) which ignored the
agent_ui_font_size and agent_buffer_font_size settings. This updates the
markdown style to respect these settings.
This pull request adds support for customizing the font size of code
blocks in agent responses, making it possible to set a distinct font
size for code within the agent panel. The changes ensure that if the new
setting is not specified, the font size will fall back to the agent UI
font size, maintaining consistent appearance.
(I am a frontend developer without any Rust knowledge so this is
co-authored with Claude Code)
**Theme settings extension:**
* Added a new `agent_buffer_code_font_size` setting to
`ThemeSettingsContent`, `ThemeSettings`, and the default settings JSON,
allowing users to specify the font size for code blocks in agent
responses.
[[1]](diffhunk://#diff-a3bba02a485aba48e8e9a9d85485332378aa4fe29a0c50d11ae801ecfa0a56a4R69-R72)
[[2]](diffhunk://#diff-aed3a9217587d27844c57ac8aff4a749f1fb1fc5d54926ef5065bf85f8fd633aR118-R119)
[[3]](diffhunk://#diff-42e01d7aacb60673842554e30970b4ddbbaee7a2ec2c6f2be1c0b08b0dd89631R82-R83)
* Updated the VSCode import logic to recognize and import the new
`agent_buffer_code_font_size` setting.
**Font size application in agent UI:**
* Modified the agent UI rendering logic in `thread_view.rs` to use the
new `agent_buffer_code_font_size` for code blocks, and to fall back to
the agent UI font size if unset.
[[1]](diffhunk://#diff-f73942e8d4f8c4d4d173d57d7c58bb653c4bb6ae7079533ee501750cdca27d98L5584-R5584)
[[2]](diffhunk://#diff-f73942e8d4f8c4d4d173d57d7c58bb653c4bb6ae7079533ee501750cdca27d98L5596-R5598)
* Implemented a helper method in `ThemeSettings` to retrieve the code
block font size, with fallback logic to ensure a value is always used.
* Updated the settings application logic to propagate the new code block
font size setting throughout the theme system.
### Example Screenshots


---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Currently Zed only displays agent notifications (e.g. when the agent
completes a task) if the user has switched apps and Zed is not in the
foreground. This adds PR supports the scenario where the agent finishes
a long-running task and the user is busy coding within Zed on something
else.
Releases Note:
- If agent notifications are turned on, they will now also be displayed
when the agent panel is hidden, in complement to them showing when the
Zed window is in the background.
---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Closes#41458
Dynamically position mode selector tooltip to prevent clipping.
Position tooltip on the right when panel is docked left, otherwise on
the left. This ensures the tooltip remains visible regardless of panel
position.
**Note:** The tooltip currently vertically aligns with the bottom of the
menu rather than individual items. Would be great if it can be aligned
with the option it explains. But this doesn't seem trivial to me to
implement and not sure if it's important enough atm?
Before:
<img width="431" height="248" alt="Screenshot 2025-10-30 at 22 21 09"
src="https://github.com/user-attachments/assets/073f5440-b1bf-420b-b12f-558928b627f1"
/>
After:
<img width="632" height="158" alt="Screenshot 2025-10-30 at 17 26 52"
src="https://github.com/user-attachments/assets/e999e390-bf23-435e-9df0-3126dbc14ecb"
/>
<img width="685" height="175" alt="Screenshot 2025-10-30 at 17 27 15"
src="https://github.com/user-attachments/assets/84efca94-7920-474b-bcf8-062c7b59a812"
/>
Release Notes:
- Improved the agent panel's mode selector by preventing it to go
off-screen in case the panel is docked to the left.
Update the behavior of the `zed_actions::agent::AddSelectionToThread`
action so that, after the selecitons are added to the current thread,
the editor automatically scrolls to the cursor's position, fixing an
issue where the inserted selection's UI component could wrap the cursor
to the next line below, leaving it outside the viewable area.
Closes#39694
Release Notes:
- Improved the `agent: add selection to thread` action so as to
automatically scroll to the cursor's position after selections are
inserted
This ensures the thread summary is treated as a tracked mention with
accessible context.
Changes:
- Fixed `MessageEditor::insert_thread_summary()` to use proper mention
URI format
- Added test coverage to verify the fix
Release Notes:
- Fixed an issue where "New From Summary" was not properly inserting
thread summaries as contextual mentions when creating new threads.
Thread summaries are now inserted as proper mention URIs.
This PR hides the worktree root name from the path prefix displayed when
you @-mention a file or directory in the agent panel. Given the tight UI
real state we have, I believe that having the project name in there is
redundant—the project you're in is already displayed in the title bar.
Not only it was the very first word you'd see after the file's name, but
it also made the path longer than it needs to. A bit of a design clean
up here :)
(PS: We still show the project name if there are more than one in the
same workspace.)
Release Notes:
- N/A
Symbol completions in the context picker now show "SymbolName
filename.txt L123" instead of just "SymbolName". This helps distinguish
between symbols with the same name in different files.
## Motivation
I noticed that the message prompt editor only showed symbol names
without any context, making it hard to use in large projects with many
symbols sharing the same name. The inline prompt editor already includes
file context for symbol completions, so I brought that same UX
improvement to the message prompt editor. I've decided to match the
highlighting style with directory completion entries from the message
editor.
## Changes
- Extract file name from both InProject and OutsideProject symbol
locations
- Add `build_symbol_label` helper to format labels with file context
- Update test expectation for new label format
## Screenshots
Inline Prompt Editor
<img width="843" height="334" alt="Screenshot 2025-10-17 at 17 47 52"
src="https://github.com/user-attachments/assets/16752e1a-0b8c-4f58-a0b2-25ae5130f18c"
/>
Old Message Editor:
<img width="466" height="363" alt="Screenshot 2025-10-17 at 17 31 44"
src="https://github.com/user-attachments/assets/900659f3-0632-4dff-bc9a-ab2dad351964"
/>
New Message Editor:
<img width="482" height="359" alt="Screenshot 2025-10-17 at 17 31 23"
src="https://github.com/user-attachments/assets/bf382167-f88b-4f3d-ba3e-1e251a8df962"
/>
Release Notes:
- Added file names and line numbers to symbol completions in the agent
panel
After #38882 we were always including file/directory mentions as
`zed:///agent/file?path=a/b/c.rs`.
However, for most resource links (files/directories/symbols/selections)
we want to use a common format, so that ACP servers don't have to
implement custom handling for parsing `ResourceLink`s coming from Zed.
This is what it looks like now:
```
[@index.js](file:///Users/.../projects/reqwest/examples/wasm_github_fetch/index.js)
[@wasm](file:///Users/.../projects/reqwest/src/wasm)
[@Error](file:///Users/.../projects/reqwest/src/async_impl/client.rs?symbol=Error#L2661:2661)
[@error.rs (23:27)](file:///Users/.../projects/reqwest/src/error.rs#L23:27)
```
Release Notes:
- N/A
---------
Co-authored-by: Cole Miller <cole@zed.dev>
Updates to acp crate 0.7, which allows us to send information about the
client to the Agent.
In the future, we can also use the AgentInfo on the response for
internal metrics.
Release Notes:
- N/A
Previously we had `Context` and `ContextStore` in both `agent_ui` (used
to store context for the inline assistant) and `assistant_context` (used
for text threads) which is confusing.
This PR makes it so that the `assistant_context` concepts are now called
`TextThread*`, the crate was renamed to `assistant_text_thread`
Release Notes:
- N/A
Release Notes:
- agent: Improved the editing previous messages UX by focusing in the
agent panel's message editor after regenerating a prompt, instead of
moving focus to the nearest regular buffer.
Closes#39172
This refactors when we resolve UI keybindings in an effort to reduce
flickering whilst painting these: Previously, we would always resolve
these upon creating the binding. This could lead to cases where the
corresponding context was not yet available and no binding could be
resolved, even if the binding was then available on the next presented
frame. Following that, on the next rerender of whatever requested this
keybinding, the keybind for that context would then be found, we would
render that and then also win a layout shift in that process, as we went
from nothing rendered to something rendered between these frames.
With these changes, this now happens less often, because we only look
for the keybinding once the context can actually be resolved in the
window.
| Before | After |
| --- | --- |
|
https://github.com/user-attachments/assets/adebf8ac-217d-4c7f-ae5a-bab3aa0b0ee8
|
https://github.com/user-attachments/assets/70a82b4b-488f-4a9f-94d7-b6d0a49aada9
|
Also reduced cloning in the keymap editor in this process, since that
requiered changing due to this anyway.
Release Notes:
- Fixed some cases where keybinds would appear with a slight delay,
causing a flicker in the process
Closes https://github.com/zed-industries/zed/issues/40047
Closes https://github.com/zed-industries/zed/issues/24798
Closes https://github.com/zed-industries/zed/issues/24788
Before, each editor, even if it's the same buffer split in 2, was
querying for inlay hints separately, and storing the whole inlay hint
twice, in `Editor`'s `display_map` and its `inlay_hint_cache` fields.
Now, instead of `inlay_hint_cache`, each editor maintains a minimal set
of metadata (which area was queried by what task) instead, and all LSP
inlay hint data had been moved into `LspStore`, both local and remote
flavors store the data.
This allows Zed, as long as a buffer is open, to reuse the inlay hint
data similar to how document colors and code lens are now stored and
reused.
Unlike other reused LSP data, inlay hints data is the first one that's
possible to query by document ranges and previous version had issue with
caching and invalidating such ranges already queried for.
The new version re-approaches this by chunking the file into row ranges,
which are queried based on the editors' visible area.
Among the corresponding refactoring, one notable difference in inlays
display are multi buffers: buffers in them are not
[registered](https://microsoft.github.io/language-server-protocol/specifications/lsp/3.17/specification/#textDocument_didOpen)
in the language server until a caret/selection is placed inside their
excerpts inside the multi buffer.
New inlays code does not query language servers for unregistered
buffers, as servers usually respond with empty responses or errors in
such cases.
Release Notes:
- Reworked inlay hints to be less error-prone
---------
Co-authored-by: Lukas Wirth <lukas@zed.dev>
Co-authored-by: dino <dinojoaocosta@gmail.com>
Co-authored-by: Lukas Wirth <me@lukaswirth.dev>
Re-applies https://github.com/zed-industries/zed/pull/30840
This PR re-applies the initial
[PR](https://github.com/zed-industries/zed/pull/30840). As it was closed
because it was hard to land, because of the many conflicts. This PR
re-applies the changes for it.
In several cases we were creating multiple display_map
snapshots within the same root-level function call.
Creating a display_map snapshot is quite slow, and in some
cases we were creating the snapshot multiple times.
Release Notes:
- N/A
`MultiBuffer::anchor_in_excerpt` currently just wraps the given text
anchor in a multibuffer anchor. This allows one to get a multibuffer
anchor that points outside its excerpt which is basically never what one
wants. This PR now does a bounds check and returns `None` if the given
text anchor is not within the bounds of the excerpt.
Release Notes:
- N/A *or* Added/Fixed/Improved ...
Co-authored-by: Kirill Bulatov <kirill@zed.dev>
Moves the Codex warning into the thread so that we can render it nicer,
as well as provide an option to open the folder in WSL.
Release Notes:
- N/A
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Making all triggers have the same style when the picker is open
(including changing the icon when the picker opens on top of the
trigger). Also removed the footer from the ACP model selector given
there's nothing to consider when that's the case; users can only
configure LLM providers when using Zed's built-in agent.
Release Notes:
- N/A
We were clearing the message editor too early. We only want to clear the
message editor if we are going to short circuit and return early before
submitting.
Otherwise, the agents that can handle this themselves won't have the
ability to do so.
Release Notes:
- acp: Fix /logout not working for some agents
Previously, if a tool call's output was just text, it would be collapsed
with no way to open it.
Now we track the collapsed cards instead of the expanded ones to allow
all tool calls to be expanded by default, and only collapse the ones
required by settings changes
Release Notes:
- acp: Fix tool call markdown output unintentionally being collapsed by
default