This PR adds an example of rendering previews for tools using the new
Agent ToolCard style.

![CleanShot 2025-04-17 at 13 03
12@2x](https://github.com/user-attachments/assets/d4c7d266-cc32-4038-9170-f3e070fce60e)

Release Notes:

- N/A

---------

Co-authored-by: Marshall Bowers <git@maxdeviant.com>

This PR refines a bit the web search tool UI by introducing a component
(`ToolCallCardHeader`) that aims to standardize the heading element of
tool calls in the thread.

In terms of next steps, I plan to evolve this component further soon
(e.g., building a full-blown "tool call card" component), and even move
it to a place where I can re-use it in the active_thread as well without
making the `assistant_tools` a dependency of it.

Release Notes:

- N/A

Mainly removing the "You" label, which didn't add a lot of value. Still
figuring out an issue with font size Markdown rendering before merging
this PR.

Release Notes:

- N/A

WIP

Release Notes:

- N/A

Adds support for the new gemini-2.5-flash-preview-04-17

Release Notes:

- agent: Added support for gemini-2.5-flash-preview

Release Notes:

- agent: Add support for adding images as context when using Google
Gemini

https://github.com/user-attachments/assets/d6a27b05-3590-4f40-a820-f6f99f6bd581

Release Notes:

- agent: Added support for pasting images as context

---------

Co-authored-by: Danilo Leal <daniloleal09@gmail.com>

Our provider code in `language_models` filters out messages for which
`LanguageModelRequestMessage::contents_empty` returns `false`. This
doesn't seem wrong by itself, but `contents_empty` was returning `false`
for messages whose first segment didn't contain non-whitespace text even
if they contained other non-empty segments. This caused requests to fail
when a message with a tool call didn't contain any preceding text.

Release Notes:

- N/A

Release Notes:

- N/A

Release Notes:

- N/A

Cherry-picked editor: Expand selection to word under cursor before
expanding to next enclosing syntax node (#28864)

Closes #27995

For strings in any language and Markdown, `select_larger_syntax_node`
will first select the word and then expand from there if:
- The cursor is on the word.
- The selection is inside the word.

It will not select the word and will directly proceed to expand if:
- The word is already selected.
- Multiple partial words are selected.

Todo:
- [x] Tests

Release Notes:

- Fixed `select_larger_syntax_node` to first expand to the word within a
string, and then to the larger syntax node.

Co-authored-by: Smit Barmase <heysmitbarmase@gmail.com>

Cherry-picked Use buffer size for markdown preview (#29172)

Note:

This is implemented in a very hacky and one-off manner. The primary
change is to pass a rem size through the markdown render tree, and scale
all sizing (rems & pixels) based on the passed in rem size manually.
This required copying in the `CheckBox` component from `ui::CheckBox` to
make it use the manual rem scaling without modifying the `CheckBox`
implementation directly as it is used elsewhere.

A better solution is required, likely involving `window.with_rem_size`
and/or _actual_ `em` units that allow text-size-relative scaling.

Release Notes:

- Made it so Markdown preview uses the _buffer_ font size instead of the
_ui_ font size.

---------

Co-authored-by: Ben Kunkle <ben@zed.dev>
Co-authored-by: Nate Butler <nate@zed.dev>

Co-authored-by: Mikayla Maki <mikayla@zed.dev>
Co-authored-by: Ben Kunkle <ben@zed.dev>
Co-authored-by: Nate Butler <nate@zed.dev>

Release Notes:

- agent: Added support for adding rules as context.

Cherry-picked Fix ctrl-c in vim normal mode (#29167)

This was broken when we added helix keybindings because we populate the
menu's shortcut based on the "last" seen binding for an action ignoring
context.

Release Notes:

- Fix `ctrl-c` in vim normal mode

Co-authored-by: Conrad Irwin <conrad.irwin@gmail.com>

Release Notes:

- agent: Add migration to rename `find_replace_file` tool to
`edit_file`, and `regex_search` to `grep`.

This PR adds additional fields to the `Agent Tool Finished` telemetry
event:

- `model`
- `model_provider`
- `thread_id`
- `prompt_id`

Release Notes:

- N/A

Just using the color method for the Switch component added in
https://github.com/zed-industries/zed/pull/29074.

Release Notes:

- N/A

Release Notes:

- agent: Correct over-indentation in search/replace strings from model

This allows to pass, for example, `.color(SwitchColor::Accent)` to the
Switch component and have it render differently.

<img
src="https://github.com/user-attachments/assets/c60bac8a-c5ae-4693-912a-c754e5081f45"
width="550"/>

Release Notes:

- N/A

Release Notes:

- inline assistant: Fixed a bug where the default model would be used
even when a specific inline assistant model was configured

This PR renames the `regex_search` tool to `grep` because I think it
conveys more meaning to the model, the idea of searching the filesystem
with a regular expression. It's also one word and the model seems to be
using it effectively after some additional prompt tuning.

It also takes an include pattern to filter on the specific files we try
to search. I'd like to encourage the model to scope its searches more
aggressively, as in my testing, I'm only seeing it filter on file
extension.

Release Notes:

- N/A

Before, we used to debounce selection highlight because it needed to
search the whole file to show gutter line highlights, etc. This
experience felt extremely laggy.

This PR introduces a new approach where:
1. We query only visible rows without debounce. The search function
itself is async and runs in a background thread, so it's not blocking
anything. With no debounce and such a small search space, highlights
feel realtime.
2. In parallel, we also query the whole file (still debounced, like
before). Once this query resolves, it updates highlights across the
file, making scrollbar markers visible.

This hybrid way gives the feeling of realtime, while keeping the same
functionality.


https://github.com/user-attachments/assets/432b65f1-89d2-4658-ad5e-048921b06a23

P.S. I have removed the user setting for custom debounce delay, because
(one) now it doesn't really make sense to configure that, and (two) the
whole logic is based on the assumption that the fast query will resolve
before the debounced query. A static debounce time makes sure of that.
Configuring it might lead to cases where the fast query resolves after
the debounced query, and we end up only seeing visible viewport
highlights.

Release Notes:

- Improved selection highlight speed.

Release Notes:

- Made keybindings for agent panel closer to the precedence order used
on Mac. This fixes use of `enter` to add context from the menu triggered
by `@` referencing.

* Adds a fast / cheaper model to providers and defaults thread
summarization to this model. Initial motivation for this was that
https://github.com/zed-industries/zed/pull/29099 would cause these
requests to fail when used with a thinking model. It doesn't seem
correct to use a thinking model for summarization.

* Skips system prompt, context, and thinking segments.

* If tool use is happening, allows 2 tool uses + one more agent response
before summarizing.

Downside of this is that there was potential for some prefix cache reuse
before, especially for title summarization (thread summarization omitted
tool results and so would not share a prefix for those). This seems fine
as these requests should typically be fairly small. Even for full thread
summarization, skipping all tool use / context should greatly reduce the
token use.

Release Notes:

- N/A

Previously, we were including the dummy text "Here are the tool
results." whenever reporting tool call results. I'm worried this is
adding noise and confusing the model, because the user didn't actually
say anything. This inserts an empty message to be populated later. My
preference would be something less stateful, where tool results (or
batches of them requested simultaneously) would be sent to the model as
soon as they were ready, without bothering to do this message
association dance. But for now, this seems to work.

Release Notes:

- N/A

Looks like the required backend component of this was deployed.

https://github.com/zed-industries/monorepo/actions/runs/14541199197

Release Notes:

- N/A

---------

Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Agus Zubiaga <hi@aguz.me>
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
Co-authored-by: Nathan Sobo <nathan@zed.dev>

This is based on user feedback that the Agent Panel menu was only
linking to extensions as a way to add MCP servers while we also support
adding "custom" servers, too, which don't go through the extensions
flow.

Release Notes:

- N/A

* Now only does default fallback logic in the registry

* Only emits change events when there is actually a change

Release Notes:

- N/A

Now that we've established a proper eval in tree, this PR is reboots of
our agent loop back to a set of minimal tools and simpler prompts. We
should aim to get this branch feeling subjectively competitive with
what's on main and then merge it, and build from there.

Let's invest in our eval and use it to drive better performance of the
agent loop. How you can help: Pick an example, and then make the outcome
faster or better. It's fine to even use your own subjective judgment, as
our evaluation criteria likely need tuning as well at this point. Focus
on making the agent work better in your own subjective experience first.
Let's focus on simple/practical improvements to make this thing work
better, then determine how we can craft our judgment criteria to lock
those improvements in.

Release Notes:

- N/A

---------

Co-authored-by: Max <max@zed.dev>
Co-authored-by: Antonio <antonio@zed.dev>
Co-authored-by: Agus <agus@zed.dev>
Co-authored-by: Richard <richard@zed.dev>
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Michael Sloan <mgsloan@gmail.com>

This PR is a follow-up to
https://github.com/zed-industries/zed/pull/29069 that fixes an issue
where the thread ID and prompt ID were not being sent up correctly.

Release Notes:

- N/A

This PR attaches the thread ID and the new prompt ID to telemetry events
for completions in the Agent panel.

Release Notes:

- N/A

---------

Co-authored-by: Mikayla Maki <mikayla.c.maki@gmail.com>

Release Notes:

- N/A

Needed after #28915

Release Notes:

- N/A

Containing everything in boxes wasn't super necessary here. Want to
still improve the switch color contrast here, but will probably do that
in a separate PR.

<img
src="https://github.com/user-attachments/assets/f826a7a8-beaf-45d0-9dc2-36dc210c418e"
width="700"/>

Release Notes:

- N/A

Related to #28490.

- Default prompts from the prompt library are now included as "user
rules" in the system prompt.
- Presence of these user rules is shown at the beginning of the thread
in the UI.
_ Now uses an `Entity<PromptStore>` instead of an `Arc<PromptStore>`.
Motivation for this is emitting a `PromptsUpdatedEvent`.
- Now disallows concurrent reloading of the system prompt. Before this
change it was possible for reloads to race.

Release Notes:

- agent: Added support for including default prompts from the Prompt
Library as "user rules" in the system prompt.

---------

Co-authored-by: Danilo Leal <daniloleal09@gmail.com>

Release Notes:

- N/A

Release Notes:

- N/A

Cherry-picked Make Copy and Trim ignore empty lines, and fix vim line
selections (#29019)

Close #28519 

Release Notes:

Update `editor: copy and trim` command:

1. Ignore empty lines in the middle:

    ```
      Line 1

      Line 2
    ```

    Will copy text to clipboard:

    ```
    Line 1

    Line 2
    ```

    Before this commit trim not performed

1. Fix select use vim line selections, trim not works

Co-authored-by: redforks <redforks@gmail.com>

This PR makes it so the thread summarization also reports the model
request usage, to prevent the case where the count would appear to jump
by 2 the next time a message was sent after summarization.

Release Notes:

- N/A

This PR adds a banner showing request usage in the Agent panel:

<img width="640" alt="Screenshot 2025-04-17 at 5 51 46 PM"
src="https://github.com/user-attachments/assets/e0eb036c-57c1-441c-bbab-7dab1c6e56d9"
/>

Only visible to users on the new billing.

Note to Joseph: Doesn't need to be cherry-picked to Preview.

Release Notes:

- N/A

---------

Co-authored-by: Nate <nate@zed.dev>

This PR updates the Agent to extract the usage information from the
response headers, if they are present.

For now we just log the information, but we'll be using this soon to
populate some UI.

Release Notes:

- N/A

This PR updates the Zeta provider to extract the usage information from
the response headers, if they are present.

For now we just log the information, but we'll need to figure out where
this needs to get threaded through to in order to display it in the UI.

Release Notes:

- N/A

This PR makes it so we use more types and constants from the
`zed_llm_client` crate to avoid duplicating information.

Also updates the current usage endpoint to use limits derived from the
`Plan`.

Release Notes:

- N/A

This PR removes the `llm` module of the `rpc` crate in favor of using
the types from the `zed_llm_client`.

Release Notes:

- N/A