This PR includes the following adjustments:
- Add divider in the full screen view to expose what part of a
subagent's output is actually sent to the parent model
- Auto-expand the subagent card if there's only one running on a turn
- Adjust errors display within the subagent card
Release Notes:
- N/A
Before you mark this PR as ready for review, make sure that you have:
- [x] Added a solid test coverage and/or screenshots from doing manual
testing
- [x] Done a self-review taking into account security and performance
aspects
- [x] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A
## Problem
Zed's ACP config-options UI was only rebuilding selectors when the set
of config option IDs changed.
For many model switches, the IDs stay the same (`mode`, `model`,
`reasoning_effort`) while the valid values for `reasoning_effort` change
by model. As a result, the picker could show stale values (for example,
missing `xhigh` on `gpt-5.3-codex`, or showing extra `xhigh` after
switching away).
This is especially problematic for providers like Copilot that expose
multiple agents/models with different reasoning-level capabilities.
## Fix
Rebuild ACP config-option selectors on every `config_option_update`, not
only when config IDs change.
This refreshes cached picker entries whenever model-specific option
values change, even if option IDs are unchanged.
## User Impact
- Reasoning-effort picker now reflects the selected model immediately on
Claude <-> GPT transitions.
- Prevents stale or invalid effort choices in ACP sessions.
## Validation
- Manual validation: switch across models with different
reasoning-effort sets and confirm picker updates immediately.
- Local `cargo check -p agent_ui` remains blocked by unrelated
pre-existing `livekit-protocol` compile errors in this checkout.
## Files Changed
- `crates/agent_ui/src/acp/config_options.rs`
Release Notes:
- acp: Fix for config selectors not always being refreshed
---------
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
This is a staff only toggle for now, since the consequences of
activating it are not obvious and quite dire (tokens costs 6 times
more).
Also, persist thinking, thinking effort and fast mode in DbThread so the
thinking mode toggle and thinking effort are persisted.
Release Notes:
- Agent: The thinking mode toggle and thinking effort are now persisted
when selecting a thread from history.
Paving the way to remove `ExcerptId`. Done in this PR:
- Unshipped the stack trace view
- Get rid of `push_excerpts`
- Get rid of some callers of `remove_excerpts`
We still need to remove some calls to `remove_excerpts` and other APIs,
especially in `randomly_edit_excerpts` and collaboration.
Release Notes:
- The stack trace multibuffer view has been removed.
---------
Co-authored-by: Conrad Irwin <conrad.irwin@gmail.com>
The ACP monikers are left over from when we had two versions of
everything. Now that all agents, including our own, use the same UI
components, it seems silly to have all of this separation. Flattens
files and removes unneeded Acp prefixes
Release Notes:
- N/A
This has lots of benefits, but mainly allows users to uninstall agents.
Release Notes:
- N/A
---------
Co-authored-by: Anthony Eid <hello@anthonyeid.me>
Co-authored-by: cameron <cameron.studdstreet@gmail.com>
Before you mark this PR as ready for review, make sure that you have:
- [x] Added a solid test coverage and/or screenshots from doing manual
testing
- [x] Done a self-review taking into account security and performance
aspects
- [x] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A
---------
Co-authored-by: Zed Zippy <234243425+zed-zippy[bot]@users.noreply.github.com>
## Summary
Fixes RefCell borrow panic on Linux (Wayland and X11) when callbacks try
to register new callbacks.
**Root cause:** Linux GPUI backends invoked callbacks while still
holding a `RefCell` borrow on the `Callbacks` struct. If a callback
tried to register a new
callback (e.g., `on_window_should_close`), it would panic with "already
borrowed: BorrowMutError".
**Bug pattern:**
```rust
// Callback runs while borrow is held - panics if callback borrows
callbacks
if let Some(ref mut fun) = self.callbacks.borrow_mut().input {
fun(input);
}
Fix: Apply the take-call-restore pattern (already used in macOS
backend):
// Take callback out, release borrow, call, restore
let callback = self.callbacks.borrow_mut().input.take();
if let Some(mut fun) = callback {
let result = fun(input);
self.callbacks.borrow_mut().input = Some(fun);
}
Changes
- Wayland (window.rs): Fixed 6 callback invocations
- X11 (window.rs): Fixed 4 callback invocations
Test plan
- cargo check -p gpui compiles successfully
- Tested on Linux (Wayland) - no more RefCell panic
Release Notes:
- Fixed a crash on Linux when window callbacks attempted to register new
callbacks
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Following up from https://github.com/zed-industries/zed/pull/50061: when
connecting to an ACP adapter fails before any thread is active, errors
would not display in the Agent Panel. Falling back to
`handle_load_error` to show the error UI properly as it already handles
this.
Before you mark this PR as ready for review, make sure that you have:
- [x] Added a solid test coverage and/or screenshots from doing manual
testing
- [x] Done a self-review taking into account security and performance
aspects
- [x] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- Added fallback error handling for connect failures in the Agent Panel
- Increase hit area of both the preview expansion as well as the full
screen expansion
- Add the ability to stop a subagent from the full screen view
- Fix subagent state display in the full screen view (e.g., we were
showing the green check mark even when the subagent was cancelled)
- Make card header font size consistent with the thread through a new
enum value in `LabelSize`
- Refine tooltip content and display
- Fix slight layout shift happening between the "there is no thread" and
"there is a thread" states
---
Closes #ISSUE
Before you mark this PR as ready for review, make sure that you have:
- [x] Added a solid test coverage and/or screenshots from doing manual
testing
- [x] Done a self-review taking into account security and performance
aspects
- [x] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A
Before you mark this PR as ready for review, make sure that you have:
- [x] Added a solid test coverage and/or screenshots from doing manual
testing
- [x] Done a self-review taking into account security and performance
aspects
- [x] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A
---------
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
After looking around a bit, I felt like subagent wasn't the right way to
introduce this tool to the model. And with some back and forth
verification + market research, we both agreed spawn_agent was a better
name for what this tool is doing.
It still calls the right tool if you ask for a subagent, but especially
if we move these to be running in the background, spawn will be a better
name anyway.
Release Notes:
- N/A
When there is no selection, make `cmd->` (`agent::addSelectionToThread`)
use the current line containing the cursor instead of doing nothing.
Supports both Zed Agent and Zed Assistant.
Works with multiple-cursors and a mix of selections and cursors.
Authored by Claude Opus 4.5, tested by me.
Release Notes:
- agent: Make `agent::addSelectionToThread` (`cmd->`) use the current
line of the cursor when there is no selection.
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
When a subagent title is long, the header buttons (expand/collapse,
maximize, stop) were pushed out of view because the title area grew
unconstrained.
## Fix
- Add `min_w_0()` and `overflow_hidden()` to the title container so it
can shrink below its content width
- Add `truncate()` to the title label so it shows an ellipsis when
clipped
- Add `flex_shrink_0()` to the buttons container so it never gets
squeezed out
- Add a tooltip on the title area showing the full text on hover
Release Notes:
- N/A
Release Notes:
- Added the ability to use a self-hosted OpenAI-compatible server for
edit predictions.
---------
Co-authored-by: Ben Kunkle <ben@zed.dev>
Co-authored-by: Zed Zippy <234243425+zed-zippy[bot]@users.noreply.github.com>
* Update the font weight used in the Agent Panel's editor to respect the
`buffer_font_weight` setting.
* Update the font weight used in the Command Palette to use the
`ui_font_weight` setting value, seeing as the command palette is using
the `ui_font` settings for the font family and features
* Update the font weight used in the popovers to match the
`buffer_font_weight`, as it's also using the buffer font family and
features
* Update the `LabelLike.buffer_font` method in order to correctly set
the font weight, which fixes the font weight used in the file header
when displaying a multibuffer editor
Release Notes:
- Fixed incorrect font weight in the Command Pallete input
- Fixed missing font weight the Agent Panel's buffer
- Fixed missing font weight the Hover Popover
- Fixed missing font weight in Markdown's code block and inline code
---------
Co-authored-by: Zed Zippy <234243425+zed-zippy[bot]@users.noreply.github.com>
Before you mark this PR as ready for review, make sure that you have:
- [ ] Added a solid test coverage and/or screenshots from doing manual
testing
- [ ] Done a self-review taking into account security and performance
aspects
- [ ] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A
This PR adds a button in the `git: branch diff` view that allows to
quickly and easily send the entire diff to your last used agent for a
review. What this does is automatically submits a (pre-written and
generic) prompt to the last agents you were using in the agent panel
with the whole content of your diff.
<img width="750" height="1964" alt="Screenshot 2026-02-18 at 3 35@2x"
src="https://github.com/user-attachments/assets/493d8cf4-4815-4b01-91a0-6a39ad6219fe"
/>
Release Notes:
- Added a "Review Branch" button in the `git: branch diff` view so that
the whole diff can be quickly sent for review to an agent.
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
The agent thread feedback comments event was still going through the
standard telemetry pipeline. This routes it through cloud instead, as
was just done for agent thread rated and edit prediction rated, so we
can enforce organization data and privacy settings.
Part of CLO-297
Closes https://github.com/zed-industries/zed/issues/39294
This PR implements the ability to undo the "reject all" action from the
agent panel (and the other places where this button is surfaced).
Effectively, this allows to recuperate the edits an agent has introduced
in case you either accidentally clicked the button or regretted the
decision to reject all.
https://github.com/user-attachments/assets/6f048b95-dd0a-4a45-8b4f-cd8f99d45cb3
Release Notes:
- Agent: Introduced the ability to undo the "reject all" action from
agent-made changes.
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
This PR fixes issues with subagent cancellation, prior to this we would
still show a wait indicator for subagents that were cancelled from the
parent thread. We also removed the `stop_by_user` workaround, that code
path now uses `thread.cancel` directly
Before you mark this PR as ready for review, make sure that you have:
- [x] Added a solid test coverage and/or screenshots from doing manual
testing
- [x] Done a self-review taking into account security and performance
aspects
- [x] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A
---------
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
This PR removes onboarding modals for features that were announced, at
this point, a long time ago: Git v1, Debugger, and Agent Panel v1. This
cleans up the actions list a bit when you search for "onboarding". I
left the ACP and Claude Code ones, though; they were the two more recent
ones, but we should be able to remove them soon enough, too.
Release Notes:
- N/A
Replaces a bunch of `impl FnMut` parameters with `&mut dyn FnMut` for
functions where this is the sole generic parameter.
Release Notes:
- N/A *or* Added/Fixed/Improved ...
Removes the feature flag around listing and loading existing sessions
for external agents.
Release Notes
- acp: Expose session history for all external agents that support it.
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Previously, clicking "Always allow for `cargo` commands" after running
`cargo build --release` would also silently permit `cargo run`
(arbitrary code execution), `cargo publish`, and any other cargo
subcommand. This was overly broad and did not match user intent.
Now the extracted pattern includes the subcommand when present, so the
button reads "Always allow for `cargo build` commands" and the pattern
`^cargo\s+build\b` only matches `cargo build` invocations — not `cargo
test`, `cargo run`, etc.
### How it works
- The second token is included in the pattern when it looks like a
subcommand (alphanumeric, hyphens, underscores, no leading `-`).
- When the second token is a flag (e.g. `ls -la`), only the command name
is used — the user sees "Always allow for `ls` commands".
- Single-word commands and path-like commands behave the same as before.
### Examples
| Command | Pattern | Button label |
|---|---|---|
| `cargo build --release` | `^cargo\s+build\b` | Always for `cargo
build` commands |
| `cargo test -p search` | `^cargo\s+test\b` | Always for `cargo test`
commands |
| `npm install` | `^npm\s+install\b` | Always for `npm install` commands
|
| `ls -la` | `^ls\b` | Always for `ls` commands |
| `ls` | `^ls\b` | Always for `ls` commands |
| `./script.sh` | *(rejected)* | *(no pattern button)* |
Release Notes:
- Agent: "Always allow" suggestions for terminal commands are now
subcommand-specific (e.g. "Always allow for `cargo build` commands"
instead of "Always allow for `cargo` commands").
Replace the generic folder icon next to thread entries in the workspace
sidebar with the actual agent icon (Claude, Zed Agent, Gemini, etc.) for
the active thread.
Release Notes:
- N/A
Co-authored-by: cameron <cameron.studdstreet@gmail.com>
Co-authored-by: Anthony Eid <hello@anthonyeid.me>
This PR updates the `Agent Thread Rated` event to be routed through
Cloud instead of the normal telemetry pipeline.
Closes CLO-223.
Release Notes:
- N/A
### Description
Related Discussions: #44499, #35742, #31851
Display cost multiplier for GitHub Copilot models in the model selectors
(Both in Chat Panel and Inline Assistant)
<img width="436" height="800" alt="image"
src="https://github.com/user-attachments/assets/c9ebd8fa-4d55-4be8-b3e1-f46dbf1f0145"
/>
### Some technical notes
Although this PR's primary intent is to show the cost multiplier for
GitHub Copilot models alone, I have included some necessary plumbing to
allow specifying costs for other providers in future. I have introduced
an enum called `LanguageModelCostInfo` for showing cost in different
ways for different models. Now, this enum is used in `LanguageModel`
trait to get the cost info.
For now to begin with, in `LanguageModelCostInfo`, I have specified two
ways of pricing: Request-based (1 Agent request - GitHub Copilot uses
this) and Token-based (1M Input tokens / 1M Output tokens). I had
initially thought about adding a `Free` type, especially for Ollama but
didn't do it after realizing that Ollama has paid plans. Right now, only
the Request-based pricing is implemented and used for Copilot models.
Feel free to suggest changes on how to improve this design better.
Release Notes:
- Show cost multiplier for GitHub Copilot models
---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
This PR removes the `cloud-thinking-effort` feature flag to ship the
thinking effort UI for the Zed provider.
Release Notes:
- Added support for controlling thinking effort levels with supported
models using the Zed provider.
It is possible, when the agent is streaming the tool call, that we will
get a permission request on an existing terminal and we need to render
that.
When Zed controls the terminal this won't happen, but when we are just
rendering the output, it can happen and we need to show it.
Release Notes:
- agent: Fix permission options not rendering on terminal commands
Fixes#49062
Updates `crates/agent_ui/src/inline_assistant.rs` to ensure the
TerminalPanel correctly syncs the assistant_enabled
state on initialization. This fixes the issue where "Add to Agent
Thread" was missing in worktree-less windows.
## Video:
[Screencast from 2026-02-13
10-31-43.webm](https://github.com/user-attachments/assets/bee0df67-0ecf-460c-8123-a72c4790c719)
## Release Notes
- Fixed an issue where "Add to Agent Thread" was missing from the
terminal context menu in windows without open folders.
Changes the AcpThreadHistory behavior to only load the full paginated
list if we are in the history view, and only reloads the first page
otherwise. And it also updates the first page in way fewer cases to
reduce load on the agents.
Release Notes:
- N/A
This PR uses the recently introduced `CircularProgress` component to
display context window use information. It creates more space for the
message editor controls as well as simplifies the UI a little bit.
Through a tooltip, we communicate the same things we communicated before
(and more, actually, because rules use will be displayed there, too).
Note that this doesn't touch the display of split token use (for models
like GPT and whatnot).
<img width="500" height="484" alt="Screenshot 2026-02-13 at 6 16@2x"
src="https://github.com/user-attachments/assets/831cdfbf-fddd-4a11-8ac6-e9a25609aae9"
/>
Release Notes:
- Agent: Simplified context window use display by using a circular
progress component.
This PR #47407 broke thinking models for non-zed providers (Nightly
only) because we set `thinking_allowed` to `thinking_enabled`
(previously `true`)
[here](https://github.com/zed-industries/zed/blob/b671c8cdc5a73d49d158a84f386f8fecbfbae65a/crates/agent/src/thread.rs#L2400).
The value of `thinking_enabled` eventually comes from the
`LanguageModel::supports_thinking` function, which returns `false` for
all models except the ones coming from Zed.
This PR implements `thinking_enabled` for other providers.
Before you mark this PR as ready for review, make sure that you have:
- [x] Added a solid test coverage and/or screenshots from doing manual
testing
- [x] Done a self-review taking into account security and performance
aspects
- [x] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A
When the multi-workspace thread restoration feature serializes the
active thread's session ID, it includes empty threads that were never
persisted to the database (because `NativeAgent::save_thread` skips
empty threads). On restart, `AgentPanel::load()` tries to restore this
thread by calling `load_agent_thread()`, which queries the SQLite DB.
Since the empty thread was never saved, the query returns `None`, which
becomes the error: "no thread found with ID: SessionId(...)". This shows
as "Error Loading Zed Agent" / "Failed to Launch" in the UI.
**Fix:**
Before attempting to restore a serialized thread on panel load, query
the DB to verify the thread actually exists. If it doesn't, log an error
and skip restoration (the panel falls back to creating a new thread as
normal).
Closes AI-19
Release Notes:
- Fixed an "Error Loading Zed Agent" error that could appear when
opening a workspace where the previous agent thread was empty.
Closes #ISSUE
Before you mark this PR as ready for review, make sure that you have:
- [x] Added a solid test coverage and/or screenshots from doing manual
testing
- [x] Done a self-review taking into account security and performance
aspects
- [x] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- Fixed an issue where no error was shown when an LLM request exceeded
the maximum tokens supported by the model
Remove GPT-4o, GPT-4.1, GPT-4.1-mini, and o4-mini from BYOK model
options in Zed before OpenAI retires these models.
These models are being retired by OpenAI (ChatGPT workspace support ends
April 3, 2026), so they have been removed from the available models list
in Zed's BYOK provider.
Closes AI-4
Release Notes:
- Removed deprecated GPT-4o, GPT-4.1, GPT-4.1-mini, and o4-mini models
from OpenAI BYOK provider
Danilo Leal