This pull request will print all the used tools and their failure rates.
The objective goal should be to minimize that failure rate.
@tmickleydoyle: this also changes the telemetry event to report
`tool_metrics` as opposed to `tool_use_counts`. Ideally I'd love to be
able to plot failure rates by tool and hopefully see that percentage go
down. Can we do that with the data we're tracking with this pull
request?
Release Notes:
- N/A
Closes#27845
This is also how VSCode tackles this issue. I think this should be
applicable to even more popovers across the editor and context menu, but
it can be addressed later.
Release Notes:
- Fixed the signature popover not hiding on editor scroll.
Closes#29117
This makes `window_min_size` work by using the `WM_GETMINMAXINFO` window
message.
Release Notes:
- N/A
---------
Co-authored-by: 张小白 <364772080@qq.com>
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
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>
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.
Closes#28944
Release Notes:
- linux: Fixed incorrect config directory being used when Zed is
installed via Flatpak
Signed-off-by: Marko Kungla <marko.kungla@gmail.com>
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
This PR adds a new `PlatformKeyboardLayout` trait with two methods:
`id(&self) -> &str` and `name(&self) -> &str`. The `id()` method returns
a unique identifier for the keyboard layout, while `name()` provides a
human-readable name. This distinction is especially important on
Windows, where the `id` and `name` can be quite different. For example,
the French layout has an `id` of `0000040C`, which is not
human-readable, whereas the `name` would simply be `French`. Currently,
the existing `keyboard_layout()` method returns what's essentially the
same as `id()` in this new design.
This PR implements the `name()` method for both Windows and macOS. On
Linux, for now, `name()` still returns the same value as `id()`.
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>
For some reason `SIGTTIN` sometimes gets sent to the process group,
causing it to stop when run from a terminal. This solves that issue by
putting the shell in a new session + progress group.
This allows removal of a workaround of using `exit 0;` to restore
handling of ctrl-c after exit. In testing this appears to no longer be
necessary.
Closes#27716
Release Notes:
- Fixed Zed sometimes becoming a stopped background process when run
from a terminal.
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>
Closes#29000
When buffer search is already deployed:
1. If find dialog is enabled, change it to find-and-replace dialog and
focuses to it
2. If find-and-replace is enabled, focuses to it
Release Notes:
- Fixed an issue where invoking `DeployReplace` while the Find dialog
was open did not switch to the Find & Replace dialog.
- Fixed an issue where invoking `DeployReplace` while the Find & Replace
dialog was already open did not focus it.
This fixes the panic that happened in debug builds in Wayland when
focusing/defocusing window in the edit mode:
```
"Thread "main" panicked with "CursorStyle::None should be handled separately in the client" at crates/gpui/src/platform/linux/wayland.rs:40:17"
```
Full log:
[stacktrace.txt](https://github.com/user-attachments/files/19814411/stacktrace.txt)
@smitbarmase, you seem to have worked on this code. Tagging you for
visibility :)
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>
This PR adjusts the upgrade from a Zed Pro trial to Zed Pro to do so by
ending the trial period early.
This will transition the subscription to `active` and bill the user
without needing to send them through a Stripe Checkout flow.
Release Notes:
- N/A
This PR adds an indicator for edit predictions usage in the edit
predictions menu:
| Free | Zed Pro / Trial |
|
---------------------------------------------------------------------------------------------------------------------------------------------------
|
---------------------------------------------------------------------------------------------------------------------------------------------------
|
| <img width="235" alt="Screenshot 2025-04-18 at 9 53 47 AM"
src="https://github.com/user-attachments/assets/6da001d2-ef9c-49df-86be-03d4c615d45c"
/> | <img width="237" alt="Screenshot 2025-04-18 at 9 54 33 AM"
src="https://github.com/user-attachments/assets/31f5df04-a8e1-43ec-8af7-ebe501516abe"
/> |
Only visible to users on the new billing.
Release Notes:
- N/A
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
When using 'c' with line-wise motions like j/k, operate like cc to fix
indentation issues.
Closes#28933
Release Notes:
- `c j` and `c k` now respect indentation
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
