This PR adds the ability to favorite models for external agents—writing
to the settings in the `agent_servers` key—as well as a handful of other
improvements:
- Make the cycling keybinding `alt-enter` work for the inline assistant
as well as previous user messages
- Better organized the keybinding files removing some outdated
agent-related keybinding definitions
- Renamed the inline assistant key context to "InlineAssistant" as
"PromptEditor" is old and confusing
- Made the keybindings to rate an inline assistant response visible in
the thumbs up/down button's tooltip
- Created a unified component for the model selector tooltip given we
had 3 different places creating the same element
- Make the "Cycle Favorited Models" row in the tooltip visible only if
there is more than one favorite models
Release Notes:
- agent: External agents also now support the favoriting model feature,
which comes with a handy keybinding to cycle through the favorite list.
Release Notes:
- Fixed spurious "no checkpoint" error in agent panel
---
## Summary
`update_last_checkpoint` would call `last_user_message()` twice - once
at the start to capture the checkpoint, and again in an async closure
after the checkpoint comparison completed. If a new user message without
a checkpoint was added between these two calls, the second call would
find the new message and fail with "no checkpoint".
## Fix
Capture the user message ID at the start and use `user_message_mut(&id)`
in the async closure to find the specific message.
cc @mikayla-maki
This PR fixes two issues with regards to markdown codeblocks rendered in
tool call input and output content display:
- the JSON code snippets weren't properly indented
- codeblocks weren't being rendered in unique containers; e.g., if you
hovered one scrollbar, all of them would also be hovered, even though
horizontal scrolling itself worked properly
Here's the end result:
https://github.com/user-attachments/assets/3d6daf64-0f88-4a16-a5a0-94998c1ba7e2
Release Notes:
- agent: Fix scrollbar and JSON indentation for tool call input/output
content's markdown codeblocks.
This PR solves my main pain point with Zed agent: I have a long list of
available models from different providers, and I switch between a few of
them depending on the context and the project. In particular, I use the
same models from different providers depending on whether I'm working on
a personal project or at my day job. Since I only care about a few
models (none of which are in "recommended") that are scattered all over
the list, switching between them is bothersome, even using search.
This change adds a new option in `settings.json`
(`agent.favorite_models`) and the UI to manipulate it directly from the
list of available models. When any models are marked as favorites, they
appear in a dedicated section at the very top of the list. Each model
has a small icon button that appears on hover and allows to toggle
whether it's marked as favorite.
I implemented this on the UI level (i.e. there's no first-party
knowledge about favorite models in the agent itself; in theory it could
return favorite models as a group but it would make it harder to
implement bespoke UI for the favorite models section and it also
wouldn't work for text threads which don't use the ACP infrastructure).
The feature is only enabled for the native agent but disabled for
external agents because we can't easily map their model IDs to settings
and there could be weird collisions between them.
https://github.com/user-attachments/assets/cf23afe4-3883-45cb-9906-f55de3ea2a97
Closes https://github.com/zed-industries/zed/issues/31507
Release Notes:
- Added the ability to mark language models as favorites and pin them to
the top of the list. This feature is available in the native Zed agent
(including text threads and the inline assistant), but not in external
agents via ACP.
---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Fixes#43165
## Problem
MCP prompts were only available in text threads, not agent threads.
Users with MCP servers that expose prompts couldn't use them in the main
agent panel.
## Solution
Added MCP prompt support to agent threads by:
- Creating `ContextServerPromptRegistry` to track MCP prompts from
context servers
- Subscribing to context server events to reload prompts when MCP
servers start/stop
- Converting MCP prompts to available commands that appear in the slash
command menu
- Integrating prompt expansion into the agent message flow
## Testing
Tested with a custom MCP server exposing `explain-code` and
`write-tests` prompts. Prompts now appear in the `/` slash command menu
in agent threads.
Release Notes:
- Added MCP prompt support to agent threads. Prompts from MCP servers
now appear in the slash command menu when typing `/` in agent threads.
---------
Co-authored-by: Agus Zubiaga <agus@zed.dev>
## Summary
This fixes a minor bug I found #44981
- Fix percent-encoded filenames appearing in agent mentions after
message submission.
- Decode file:// paths in MentionUri::parse using the existing
urlencoding crate (already used elsewhere in the codebase).
- Add tests for non-ASCII file URIs.
## Screenshots
<img width="409" height="116" alt="image"
src="https://github.com/user-attachments/assets/32ef033b-6232-47c5-80c7-d5247d5dae88"
/>
- Set PAGER='' and GIT_PAGER=cat for agent/terminal commands so pager
configs (e.g. delta) don't hang tool output\n\nFixes #42943
Release Notes:
- Prevent git pager configs from hanging agent/terminal git commands by
forcing PAGER and GIT_PAGER off.
Imitating the approach of #41829. Prevents e.g. reverting a hunk and
having that excerpt yanked out from under the cursor.
Release Notes:
- git: Improved stability of excerpts when editing in the project diff.
We were defining these in multiple places and also weren't leveraging
the ids the agents were already providing.
This should make sure we use them consistently and avoid issues in the
future.
Release Notes:
- N/A
Uses the latest version of the SDK + schema crate. A bit painful because
we needed to move to `#[non_exhaustive]` on all of these structs/enums,
but will be much easier going forward.
Also, since we depend on unstable features, I am pinning the version so
we don't accidentally introduce compilation errors from other update
cycles.
Release Notes:
- N/A
Gist is we only need to block the foreground thread for reparsing if
immediate language changes are useful to the user. That is usually only
the case when they edit the buffer
Release Notes:
- Improved performance of large project searches and project diffs
Co-authored by: David Kleingeld <david@zed.dev>
It is easy for us to get the two fields out of sync causing weird
problems, there is no reason to have both here so.
Release Notes:
- N/A *or* Added/Fixed/Improved ...
Co-authored by: Antonio Scandurra <antonio@zed.dev>
This PR adds back the footer with the "Configure" button in the model
selector but only when the seeing it from the Zed agent (or inline
assistant/text threads). I had removed it a while back because seeing
the "Configure" button, which takes you to the agent panel settings
view, when clicking from an external agent didn't make much sense, given
there's nothing model-wise you can configure from Zed (at least yet) for
an external agent.
This also makes the button in the footer a bit nicer by making it full
screen and displaying a keybinding, so that you can easily do the whole
"trigger model selector → go to settings view" all with the keyboard.
<img width="400" height="870" alt="Screenshot 2025-11-21 at 10 38@2x"
src="https://github.com/user-attachments/assets/c14f2acf-b793-4bc1-ac53-8a8a53b219e6"
/>
Release Notes:
- N/A
Closes#35142
In addition to cleaning up the terminals, also stops the conversation.
Release Notes:
- Restoring a checkpoint now stops the agent conversation.
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
We were dropping the entities once we created the buffers, so the weak
entities could never be upgraded. This treats new locations we see the
same as we would for a read/write call and stores the entity so that we
can follow like we normally would.
Release Notes:
- acp: Fix following not working with certain tool calls.
- Notable change is the use of a newtype for `ReplicaId`
- Fixes `WorktreeStore::create_remote_worktree` creating a remote
worktree with the local replica id, though this is not currently used
- Fixes observing the `Agent` (that is following the agent) causing
global clocks to allocate 65535 elements
- Shrinks the size of `Global` a bit. In a local or non-collab remote
session it won't ever allocate still.
Release Notes:
- N/A *or* Added/Fixed/Improved ...
We've been considering removing workspace-hack for a couple reasons:
- Lukas ran into a situation where its build script seemed to be causing
spurious rebuilds. This seems more likely to be a cargo bug than an
issue with workspace-hack itself (given that it has an empty build
script), but we don't necessarily want to take the time to hunt that
down right now.
- Marshall mentioned hakari interacts poorly with automated crate
updates (in our case provided by rennovate) because you'd need to have
`cargo hakari generate && cargo hakari manage-deps` after their changes
and we prefer to not have actions that make commits.
Currently removing workspace-hack causes our workspace to grow from
~1700 to ~2000 crates being built (depending on platform), which is
mainly a problem when you're building the whole workspace or running
tests across the the normal and remote binaries (which is where
feature-unification nets us the most sharing). It doesn't impact
incremental times noticeably when you're just iterating on `-p zed`, and
we'll hopefully get these savings back in the future when
rust-lang/cargo#14774 (which re-implements the functionality of hakari)
is finished.
Release Notes:
- N/A
Closes#39614
The `ShellKind` struct is built on Windows' side, meaning that when
connecting to remotes, we fall back to PowerShell construction, even if
the shell program we are spawning is a unix program.
This broke tasks creation since we are using the shell kind to construct
args:
d04ac864b8/crates/project/src/terminals.rs (L149)
In normal terminals this only affected activation scripts (only place
where shell kind is used)
I don't have a Windows machine to test it, so I would appreciate any
help with testing!
Release Notes:
- Fixed an issue where tasks could not be executed in Windows WSL
---------
Signed-off-by: Marco Mihai Condrache <52580954+marcocondrache@users.noreply.github.com>
This only affects `codex-acp` for now.
Not using the PTY in display-only terminals means they don't display the
login prompt (or spurious `%`s) at the end of terminal output
renderings.
Release Notes:
- N/A
Codex needs (and future projects are anticipated to need as well) a
concept of display-only terminals. This refactors terminals to decouple
the PTY part from the display part, so that we can render terminal
changes based on a series of events - regardless of whether they're
being driven from a PTY inside Zed or from an outside source (e.g.
`codex-acp`).
Release Notes:
- N/A
When sourcing the project environment for the terminal tool, we will now
do so by spawning the shell specified by the users `terminal.shell`
setting (or as usual fall back to the login shell).
Closes#37687
Release Notes:
- N/A
Also skips indexing files that don't have a suffix that indicates a
known language, and skips when the language doesn't have an outline
grammar.
Release Notes:
- N/A
---------
Co-authored-by: Agus <agus@zed.dev>
Closes#38620
`Url::from_file_path` and `Url::from_directory_path` assume the path
style of the target they were compiled for, so we can't use them in
general. So, switch from `file://` to encoding the absolute path (for
mentions that have one) as a query parameter, which works no matter the
platforms. We'll still parse the old `file://` mention URIs for
compatibility with thread history.
Release Notes:
- windows: Fixed a crash when using `@mentions` in agent threads when
remoting from Windows to Linux or WSL.
- Map path lookup and internal failures to acp::Error
- Return INVALID_PARAMS for reads beyond EOF
Release Notes:
- acp: Return more informative error types from `read_text_file` to
agents
The previous validation was too strict and didn't permit reading empty
files.
Addresses: https://github.com/google-gemini/gemini-cli/issues/9280
Release Notes:
- acp: Fix `read_text_file` returning errors for empty files
Closes https://github.com/zed-industries/zed/issues/38690Closes#37353
### Background
On Windows, paths are normally separated by `\`, unlike mac and linux
where they are separated by `/`. When editing code in a project that
uses a different path style than your local system (e.g. remoting from
Windows to Linux, using WSL, and collaboration between windows and unix
users), the correct separator for a path may differ from the "native"
separator.
Previously, to work around this, Zed converted paths' separators in
numerous places. This was applied to both absolute and relative paths,
leading to incorrect conversions in some cases.
### Solution
Many code paths in Zed use paths that are *relative* to either a
worktree root or a git repository. This PR introduces a dedicated type
for these paths called `RelPath`, which stores the path in the same way
regardless of host platform, and offers `Path`-like manipulation APIs.
RelPath supports *displaying* the path using either separator, so that
we can display paths in a style that is determined at runtime based on
the current project.
The representation of absolute paths is left untouched, for now.
Absolute paths are different from relative paths because (except in
contexts where we know that the path refers to the local filesystem)
they should generally be treated as opaque strings. Currently we use a
mix of types for these paths (std::path::Path, String, SanitizedPath).
Release Notes:
- N/A
---------
Co-authored-by: Cole Miller <cole@zed.dev>
Co-authored-by: Piotr Osiewicz <24362066+osiewicz@users.noreply.github.com>
Co-authored-by: Peter Tripp <petertripp@gmail.com>
Co-authored-by: Smit Barmase <heysmitbarmase@gmail.com>
Co-authored-by: Lukas Wirth <me@lukaswirth.dev>
We were incorrectly handling the line number as well as stripping out
line breaks when returning portions of files.
It also makes sure following is updated even when we load a snapshot
from cache, which wasn't the case before.
We also are able to load the text via a range in the snapshot, rather
than allocating a string for the entire file and then another after
iterating over lines in the file.
Release Notes:
- acp: Fix incorrect behavior when ACP agents requested to read portions
of files.
