This PR improves the consecutive tool call UX by allowing users to
quickly continue an interrupted with one-click. What we do here is
insert a hidden "Continue" message that will just nudge the LLM to keep
going. We're also using the opportunity to upsell the previously called
"Max Mode", now rebranded as "Burn Mode", which allows users to don't be
interrupted anymore if they ever have 25 consecutive tool calls again.
Release Notes:
- agent: Improve consecutive tool call UX by allowing users to quickly
continue an interrupted thread with one click.
---------
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
Co-authored-by: Agus Zubiaga <hi@aguz.me>
Co-authored-by: Agus Zubiaga <agus@zed.dev>
This PR adds the ability to hear a sound notification when the agent is
done generating and/or needs user input. This setting is turned off by
default and can be used together with the visual notification. The
specific sound I'm using here comes from the [Material Design 2 Sound
Library](https://m2.material.io/design/sound/sound-resources.html#).
Release Notes:
- agent: Added the ability to have a sound notification when the agent
is done generating and/or needs user input.
Addresses an issue where the agent context token meter in the panel
toolbar (showing usage like "X / Y tokens") failed to update its count
after the user cleared the current context via the context editor UI.
While the meter updated correctly when adding items, clearing them left
the display showing the old count.
The root cause was traced to the `ContextStore::clear` method in
`crates/agent/src/context_store.rs`. This method correctly cleared the
internal data structures holding the context items but neglected to call
`cx.notify()` to inform listeners of the state change. Consequently, the
UI components responsible for displaying the token count were not
triggered to re-render with the new (presumably lower) count.
This PR fixes the issue by adding the missing `cx.notify()` call to the
`ContextStore::clear` method. This ensures listeners are notified when
the context set is cleared, allowing the token meter UI to update
correctly.
Release Notes:
- Fixed an issue where the agent context token meter did not update when
the context was cleared.
This is a partial reversion of
https://github.com/zed-industries/zed/pull/30878 - having it always
scroll to bottom whenever a new message is added makes it so that when
you're scrolled up, you don't have time to read what you're trying to
read before it autoscrolls to the end.
@danilo-leal when you're back, we can pair on addressing that in a
different way!
Release Notes:
- Fixed bug where scrolling up in the agent panel didn't prevent
automatic scroll-to-end whenever a new message arrived.
This PR makes the edit tool call codeblock cards expanded by default, to
be consistent with https://github.com/zed-industries/zed/pull/30806.
Also, I am removing the collapsing behavior of Markdown codeblocks where
we'd add a gradient while capping the container's height based on an
arbitrary number of lines. Figured if they're all now initially
expanded, we could simplify how the design/code operates here
altogether.
Open for feedback, as I can see an argument where the previous Markdown
codeblock design of "collapsed but not fully; it shows a preview" should
stay as it is useful.
Release Notes:
- N/A
This PR also moves the context strip to be at the top, so it matches the
main message editor, making the arrow-up keyboard interaction to focus
on it to work the same way.
Release Notes:
- agent: Made the previous message editing UX more consistent with the
main message editor.
This is very basic support for them. There are a number of other TODOs
before this is really a first-class supported feature, so not adding any
release notes for it; for now, this PR just makes it so that if
read_file tries to read a PNG (which has come up in practice), it at
least correctly sends it to Anthropic instead of messing up.
This also lays the groundwork for future PRs for more first-class
support for images in tool calls across more image file formats and LLM
providers.
Release Notes:
- N/A
---------
Co-authored-by: Agus Zubiaga <hi@aguz.me>
Co-authored-by: Agus Zubiaga <agus@zed.dev>
The title of a (text) thread would get stuck in "Loading Summary..."
when the request to generate it failed. We now handle this case by
falling back to the default title, and letting the user manually edit
the title or retry generating it.
https://github.com/user-attachments/assets/898d26ad-d31f-4b62-9b05-519d923b1b22
Release Notes:
- agent: Handle thread title generation errors
---------
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
Closes https://github.com/zed-industries/zed/issues/30411
Rendering as markdown gives us text selection and copying for free. In
the future, we may want to explore having these commands be actual
editors, allowing you to step in, change the command, and re-run it
right from there.
Release Notes:
- agent: Made the terminal command in the tool card selectable and
copyable.
Just noticed this got lost when main was merged in #29828.
Release Notes:
- agent: Fixed the rendering of added context when editing past messages
in a thread.
This is similar to the `block_mouse_down` method added in #20649 (which
has a very similar motivation), but is more comprehensive in stopping
mouse events. Since I want to cherry-pick this to the releases, keeping
this change just to the agent panel. In a follow-up will replace
existing use of `block_mouse_down` to instead use this.
Release Notes:
- N/A
Seems that `h_full` was causing it to use the height of the overall list
item for some reason.
Closes#30002
Release Notes:
- Agent Panel: Fixed text overlap for code blocks nested in lists in
agent response.
This PR renames a number of constructs in the `agent` crate from the
"Assistant" terminology to "Agent".
Not comprehensive, but it's a start.
Release Notes:
- N/A
Release Notes:
- Fixed a bug that would prevent the agent from working over SSH.
---------
Co-authored-by: Nathan Sobo <nathan@zed.dev>
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Cole Miller <m@cole-miller.net>
Right now `agent: open active thread as markdown` will always panic when
you try to use it over collab or when SSH remoting. This PR makes it log
an error instead (we should follow up by restoring full remote support).
Release Notes:
- Prevented `agent: open active thread as markdown` from panicking when
used in a non-local project.
Adds a new `agent.model_parameters` setting that allows the user to
specify a custom temperature for a provider AND/OR model:
```json5
"model_parameters": [
// To set parameters for all requests to OpenAI models:
{
"provider": "openai",
"temperature": 0.5
},
// To set parameters for all requests in general:
{
"temperature": 0
},
// To set parameters for a specific provider and model:
{
"provider": "zed.dev",
"model": "claude-3-7-sonnet-latest",
"temperature": 1.0
}
],
```
Release Notes:
- agent: Allow customizing temperature by provider/model
---------
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
Closes #ISSUE
Release Notes:
- Agent Beta: Fixed a bug causing "Restore Checkpoint" buttons in the
agent panel not to be rendered.
Co-authored-by: Antonio Scandurra <me@as-cii.com>
You can set `agent_font_size` as a top-level settings key. You can also
use `zed::IncreaseBufferFontSize` and `zed::DecreaseBufferFontSize` and
`zed::ResetBufferFontSize` the agent panel is focused via the standard
bindings to adjust the agent font size. In the future, it might make
sense to rename these actions to be more general since "buffer" is now a
bit of a misnomer. 🍐'd with @mikayla-maki
Release Notes:
- N/A
---------
Co-authored-by: Mikayla Maki <mikayla.c.maki@gmail.com>
Because we instantiated `ContextServerManager` both in `agent` and
`assistant-context-editor`, and these two entities track the running MCP
servers separately, we were effectively running every MCP server twice.
This PR moves the `ContextServerManager` into the project crate (now
called `ContextServerStore`). The store can be accessed via a project
instance. This ensures that we only instantiate one `ContextServerStore`
per project.
Also, this PR adds a bunch of tests to ensure that the
`ContextServerStore` behaves correctly (Previously there were none).
Closes#28714Closes#29530
Release Notes:
- N/A
This change:
1. Catches attempts to use missing tools. If this happens, we now send
Agent a message listing available tools, after which Agent can
gracefully recover. Prior behavior: thread would stop in a broken state.
Example of a hallucinated call and a message we send back:
2. Adds evals for hallucinated tool use and imagined edits
3. Adds ability to configure a profile name in evals.
Release Notes:
- N/A
Otherwise the panel keeps scrolling as the new token comes in and it is
almost impossible to keep the scroll position in the right place.
Also, if the user is editing, it is likely that the current generated
tokens will need to be regenerated anyway, so we may as well stop the
current progress.
Release Notes:
- Agent Beta: Stop generating tokens if previous messages are edited.
This is purely a cosmetic change, renamed `@rules` to `@rule` which
unifies the @mention experience (for files, threads etc. we also use
`@file`, `@thread` not `@files`, `@thread`). Would also make sense to
rename the rules picker to rule picker, but i do not wanna introduce
conflicts just for the purpose of re-naming.
Release Notes:
- N/A
Enables reviewing agent edits from single-file editors in addition to
the multibuffer experience we already had.
https://github.com/user-attachments/assets/a2c287f0-51d6-43a1-8537-821498b91983
This feature can be turned off by setting `assistant.single_file_review:
false`.
Release Notes:
- agent: Review edits in single-file editors
This sets us up to display queue position information to the user, once
our language model backend is updated to support request queuing.
The JSON returned by the LLM backend will need to look like this:
```json
{"queue": {"status": "queued", "position": 1}}
{"queue": {"status": "started"}}
{"event": {"THE_UPSTREAM_MODEL_PROVIDER_EVENT": "..."}}
```
Release Notes:
- N/A
---------
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
Closes #ISSUE
Co-authored-by: Bennet <bennet@zed.dev>
Release Notes:
- Added support for context `@mentions` in the inline prompt editor and
when editing past messages in the agent panel.
---------
Co-authored-by: Bennet Bo Fenner <bennet@zed.dev>
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
Release Notes:
- agent: Support adding/removing context when editing existing message
---------
Co-authored-by: Cole Miller <m@cole-miller.net>
Co-authored-by: Cole Miller <cole@zed.dev>
Richard FeldmanandDanilo Leal
Marshall Bowers
Mani Rash Ahmadi
Max Brunsfeld
Tristan Hume
Michael Sloan
Cole Miller
Antonio Scandurra
Nate ButlerandMarshall Bowers
Bennet Bo Fenner
Oleksiy Syvokon
