Commit Graph
25 Commits
Author SHA1 Message Date
Conrad IrwinandAntonio Scandurra 6ba52a3a42 Re-add history entries for native agent threads (#36500)
Closes #ISSUE

Release Notes:

- N/A

---------

Co-authored-by: Antonio Scandurra <me@as-cii.com>
2025-08-19 12:08:11 -06:00
Agus Zubiaga 8b89ea1a80 Handle auth for claude (#36442)
We'll now use the anthropic provider to get credentials for `claude` and
embed its configuration view in the panel when they are not present.

Release Notes:

- N/A
2025-08-18 20:40:59 +00:00
Bennet Bo Fenner 5591fc810e agent: Restore last used agent session on startup (#36401)
Release Notes:

- N/A
2025-08-18 10:22:00 +00:00
Marshall Bowers f17f63ec84 Remove /docs slash command (#36325)
This PR removes the `/docs` slash command.

We never fully shipped this—with it requiring explicit opt-in via a
setting—and it doesn't seem like the feature is needed in an agentic
world.

Release Notes:

- Removed the `/docs` slash command.
2025-08-16 19:00:31 +00:00
Bennet Bo FennerandAntonio Scandurra 6f3cd42411 agent2: Port Zed AI features (#36172)
Release Notes:

- N/A

---------

Co-authored-by: Antonio Scandurra <me@as-cii.com>
2025-08-15 11:17:17 +00:00
Danilo Leal cb0bc463f1 agent2: Add new "new thread" selector in the toolbar (#36133)
Release Notes:

- N/A
2025-08-13 14:45:37 -03:00
Ben BrandtandBennet Bo Fenner db497ac867 Agent2 Model Selector (#36028)
Release Notes:

- N/A

---------

Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
2025-08-13 09:01:02 +00:00
eb4b73b88e ACP champagne (#35609)
cherry pick changes from #35510 onto latest main

Release Notes:

- N/A

---------

Co-authored-by: Nathan Sobo <nathan@zed.dev>
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Lukas Wirth <lukas@zed.dev>
2025-08-06 09:01:06 +00:00
Michael Sloan 899bc8a8fd Fix edit prediction disablement with "disable_ai": true setting (#35513)
Even after #35327 edit predictions were still being queried and shown
after setting `"disable_ai": true`

Also moves `DisableAiSettings` to the `project` crate so that it gets
included in tests via existing use of `Project::init_settings(cx)`.

Release Notes:

- Fixed `"disable_ai": true` setting disabling edit predictions.
2025-08-04 15:45:11 +00:00
Ben BrandtandAgus Zubiaga f17943e4a3 Update to new agent schema (#35578)
Release Notes:

- N/A

---------

Co-authored-by: Agus Zubiaga <agus@zed.dev>
2025-08-04 13:49:41 +00:00
Kirill Bulatov 93e6b01486 Actually disable ai for now (#35327)
Closes https://github.com/zed-industries/zed/issues/35325

* removes Supermaven actions
* removes copilot-related action
* stops re-enabling edit predictions when disabled

Release Notes:

- N/A
2025-07-30 13:10:05 +00:00
Agus ZubiagaandBen Brandt c2fc70eef7 ACP over MCP server impl (#35196)
Release Notes:

- N/A

---------

Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
2025-07-28 14:14:10 +00:00
Justin Su 0e9d955e9b Hide Copilot commands when AI functionality is disabled (#35055)
Follow-up of https://github.com/zed-industries/zed/pull/34896

Related to https://github.com/zed-industries/zed/issues/31346

cc @rtfeldman

Release Notes:

- Hide copilot commands when AI functionality is disabled
2025-07-25 10:53:57 -04:00
Richard Feldman 96f9942791 Add setting to disable all AI features (#34896)
https://github.com/user-attachments/assets/674bba41-40ac-4a98-99e4-0b47f9097b6a


Release Notes:

- Added setting to disable all AI features
2025-07-22 11:32:39 -04:00
8e4555455c Claude experiment (#34577)
Release Notes:

- N/A

---------

Co-authored-by: Conrad Irwin <conrad.irwin@gmail.com>
Co-authored-by: Anthony Eid <hello@anthonyeid.me>
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
Co-authored-by: Nathan Sobo <nathan@zed.dev>
Co-authored-by: Oleksiy Syvokon <oleksiy.syvokon@gmail.com>
2025-07-17 14:25:55 +00:00
Danilo LealandAgus Zubiaga 80eed63255 agent: Add menu in the plus icon button for creating a new thread (#34143)
Release Notes:

- N/A

---------

Co-authored-by: Agus Zubiaga <agus@zed.dev>
2025-07-09 15:44:45 -03:00
Conrad Irwin 495ec7a109 ACP (#34030)
Implements an ACP client that can be used from the agent panel
2025-07-09 16:02:31 +00:00
Ben Kunkle 6cd4dbdea1 gpui: Store action documentation (#33809)
Closes #ISSUE

Adds a new `documentation` method to actions, that is extracted from doc
comments when using the `actions!` or derive macros.

Additionally, this PR adds doc comments to as many action definitions in
Zed as possible.

Release Notes:

- N/A *or* Added/Fixed/Improved ...
2025-07-02 21:14:33 -04:00
Michael Sloan 93b1e95a5d agent: Make AgentSettings::default_model optional (#33695)
It's already effectively optional and the the old default of gpt-4
doesn't really get used in practice

Release Notes:

- N/A
2025-07-01 00:46:01 -06:00
Michael Sloan f022a13091 Add #[serde(deny_unknown_fields)] to action structs that didn't have it (#33679)
Release Notes:

- N/A
2025-07-01 00:20:02 +00:00
Ben Brandt 6c46e1129d Cleanup remaining references to max mode (#33509)
Release Notes:

- N/A
2025-06-27 08:32:13 +00:00
Max Brunsfeld b9f81c7ce7 Restore missing initialization of text thread actions (#33422)
Fixes a regression introduced in
https://github.com/zed-industries/zed/pull/33289

Release Notes:

- Fixed a bug where some text thread actions were accidentally removed.
2025-06-25 22:48:40 +00:00
Max Brunsfeld 4cd4d28531 Move UI code from assistant_context_editor -> agent_ui (#33289)
This breaks a transitive dependency of `agent` on UI crates. I've also
found and eliminated some dead code in assistant_context_editor.

Release Notes:

- N/A
2025-06-23 22:22:01 -07:00
Michael Sloan 24c94d474e gpui: Simplify Action macros + support doc comments in actions! (#33263)
Instead of a menagerie of macros for implementing `Action`, now there
are just two:

* `actions!(editor, [MoveLeft, MoveRight])`
* `#[derive(..., Action)]` with `#[action(namespace = editor)]`

In both contexts, `///` doc comments can be provided and will be used in
`JsonSchema`.

In both contexts, parameters can provided in `#[action(...)]`:

- `namespace = some_namespace` sets the namespace. In Zed this is
required.

- `name = "ActionName"` overrides the action's name. This must not
contain "::".

- `no_json` causes the `build` method to always error and
`action_json_schema` to return `None`
and allows actions not implement `serde::Serialize` and
`schemars::JsonSchema`.

- `no_register` skips registering the action. This is useful for
implementing the `Action` trait
while not supporting invocation by name or JSON deserialization.

- `deprecated_aliases = ["editor::SomeAction"]` specifies deprecated old
names for the action.
These action names should *not* correspond to any actions that are
registered. These old names
can then still be used to refer to invoke this action. In Zed, the
keymap JSON schema will
accept these old names and provide warnings.

- `deprecated = "Message about why this action is deprecation"`
specifies a deprecation message.
In Zed, the keymap JSON schema will cause this to be displayed as a
warning. This is a new feature.

Also makes the following changes since this seems like a good time to
make breaking changes:

* In `zed.rs` tests adds a test with an explicit list of namespaces. The
rationale for this is that there is otherwise no checking of `namespace
= ...` attributes.

* `Action::debug_name` renamed to `name_for_type`, since its only
difference with `name` was that it

* `Action::name` now returns `&'static str` instead of `&str` to match
the return of `name_for_type`. This makes the action trait more limited,
but the code was already assuming that `name_for_type` is the same as
`name`, and it requires `&'static`. So really this just makes the trait
harder to misuse.

* Various action reflection methods now use `&'static str` instead of
`SharedString`.

Release Notes:

- N/A
2025-06-24 04:34:51 +00:00
Max Brunsfeld 2283ec5de2 Extract an agent_ui crate from agent (#33284)
This PR moves the UI-dependent logic in the `agent` crate into its own
crate, `agent_ui`. The remaining `agent` crate no longer depends on
`editor`, `picker`, `ui`, `workspace`, etc.

This has compile time benefits, but the main motivation is to isolate
our core agentic logic, so that we can make agents more
pluggable/configurable.

Release Notes:

- N/A
2025-06-23 18:00:28 -07:00