This PR disables `parallel_tool_calls` for the models that support it,
as the Agent currently expects at most one tool use per turn.
It was a bit of trial and error to figure this out. OpenAI's API
annoyingly will return an error if passing `parallel_tool_calls` to a
model that doesn't support it.
Release Notes:
- N/A
This adds a nix CI job to build the flake in debug mode for
aarch64-darwin and x86-linux. For now this job will only run when the
`run-nix` label is added to a PR.
The CI job doesn't push to cachix for now, so every build is a clean
build.
I also added a condition to the garbage collection step so it only runs
when the nix store is >50GB.
Release Notes:
- N/A
This makes context essentially work the same way as `read-file`,
increasing the likelihood of cache hits.
Just like with `read-file`, we'll notify the model when the user makes
an edit to one of the tracked files. In the future, we want to send a
diff instead of just a list of files, but that's an orthogonal change.
Release Notes:
- agent: Improved caching of files in context
---------
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Same as `editor::RestartLanguageServer`, now there's an
`editor::StopLanguageServer` action that stops all language servers,
related to the currently opened editor.
Opening another singleton editor with the same language or changing
selections in a multi buffer will bring the servers back up.
Release Notes:
- Added a way to temporarily stop LSP servers
---------
Co-authored-by: Michael Sloan <mgsloan@gmail.com>
This PR adds the token count to the active thread view. It doesn't
behaves quite like Assistant 1 where it updates as you type, though; it
updates after you submit the message.
<img
src="https://github.com/user-attachments/assets/82d2a180-554a-43ee-b776-3743359b609b"
width="700" />
---
Release Notes:
- agent: Add token count in the thread view
---------
Co-authored-by: Agus Zubiaga <hi@aguz.me>
Release Notes:
- Fixed a rendering bug that caused context in the agent to not wrap
properly.
---------
Co-authored-by: Conrad Irwin <conrad.irwin@gmail.com>
Co-authored-by: Zed AI <ai+claude-3.7@zed.dev>
### Context
The Anthropic API fails if a request message contains a tool use and no
`Text` segments or it only contains empty `Text` segments. These are
cases that the model itself produces, but the API doesn't support
sending them back.
#27917 fixed this by appending "Using tool..." in the thread's message,
but this causes the actual conversation to include it, so it would
appear in the UI (we would actually display a gap because we never
rendered its markdown, but "Using tool..." would show up when the thread
was restored).
### Solution
We'll now only append this placeholder when we build the request, so the
API still sees it, but the UI/Thread doesn't.
Another issue we found is that the model starts mimicking these
placeholders in later tool uses which is undesirable. So unfortunately,
we had to add logic to filter them out.
Release Notes:
- agent: Improved rendering of tool uses without text
---------
Co-authored-by: Bennet <bennet@zed.dev>
Previously the "Thinking..." step would show up as pending, even though
the user cancelled the generation:
<img width="672" alt="image"
src="https://github.com/user-attachments/assets/c9cdce0a-d827-4e23-96f5-b150465911a7"
/>
Release Notes:
- Fixed an issue where the thinking step would show up as pending even
when the generation was cancelled
This happened because of two reasons:
- `Workspace::recent_navigation_history` didn't include the current file
- The context picker added the current file to a exclude list
The latter was actually intentional because we already show the file in
the suggested context, but now that we actually have mentions, it's just
inconvenient not to have it there.
Release Notes:
- N/A
This was accidentally getting added due to increased feature
unification. We've manually excluded reqwest to go back to the desired
behavior: remote_server, doesn't depend on openssl.
Release Notes:
- N/A
Co-authored-by: Mikayla Maki <mikayla.c.maki@gmail.com>
This PR adds the `Cargo.toml` for the `workspace-hack` crate to the
ignore list for Renovate, as it is opening a number of PRs against it
that will interfere with it.
Release Notes:
- N/A
This PR adds the ability to edit previous user messages in the thread.
Release Notes:
- Agent: Added the ability to edit previous user messages
(Preview-only).
Release Notes:
- Fixed a bug where Zed sometimes added multiple redundant FS watchers
when language servers requested to watch paths. This could cause saves
and git operations to fail if Zed exceeded the file descriptor limit.
---------
Co-authored-by: Piotr <piotr@zed.dev>
Closes#27769
When adding snippet we were not respecting autoclose setting, before
creating AutocloseRegion. This leads to cursor to skip over instead of
typing that character. This PR fixes it.
Release Notes:
- Fixed certain case where typing closing bracket would skip it when
auto close setting is turned off.
This adds a "workspace-hack" crate, see
[mozilla's](https://hg.mozilla.org/mozilla-central/file/3a265fdc9f33e5946f0ca0a04af73acd7e6d1a39/build/workspace-hack/Cargo.toml#l7)
for a concise explanation of why this is useful. For us in practice this
means that if I were to run all the tests (`cargo nextest r
--workspace`) and then `cargo r`, all the deps from the previous cargo
command will be reused. Before this PR it would rebuild many deps due to
resolving different sets of features for them. For me this frequently
caused long rebuilds when things "should" already be cached.
To avoid manually maintaining our workspace-hack crate, we will use
[cargo hakari](https://docs.rs/cargo-hakari) to update the build files
when there's a necessary change. I've added a step to CI that checks
whether the workspace-hack crate is up to date, and instructs you to
re-run `script/update-workspace-hack` when it fails.
Finally, to make sure that people can still depend on crates in our
workspace without pulling in all the workspace deps, we use a `[patch]`
section following [hakari's
instructions](https://docs.rs/cargo-hakari/0.9.36/cargo_hakari/patch_directive/index.html)
One possible followup task would be making guppy use our
`rust-toolchain.toml` instead of having to duplicate that list in its
config, I opened an issue for that upstream: guppy-rs/guppy#481.
TODO:
- [x] Fix the extension test failure
- [x] Ensure the dev dependencies aren't being unified by Hakari into
the main dependencies
- [x] Ensure that the remote-server binary continues to not depend on
LibSSL
Release Notes:
- N/A
---------
Co-authored-by: Mikayla <mikayla@zed.dev>
Co-authored-by: Mikayla Maki <mikayla.c.maki@gmail.com>
This PR adds `completions.lsp_insert_mode` and effectively changes the
default from `"replace"` to `"replace_suffix"`, which automatically
detects whether to use the LSP `replace` range instead of `insert`
range.
`"replace_suffix"` was chosen as a default because it's more
conservative than `"replace_subsequence"`, considering that deleting
text is usually faster and less disruptive than having to rewrite a long
replaced word.
Fixes#27197Fixes#23395 (again)
Fixes#4816 (again)
Release Notes:
- Added new setting `completions.lsp_insert_mode` that changes what will
be replaced when an LSP completion is accepted. The default is
`"replace_suffix"`, but it accepts 4 values: `"insert"` for replacing
only the text before the cursor, `"replace"` for replacing the whole
text, `"replace_suffix"` that acts like `"replace"` when the text after
the cursor is a suffix of the completion, and `"replace_subsequence"`
that acts like `"replace"` when the text around your cursor is a
subsequence of the completion (similiar to a fuzzy match). Check [the
documentation](https://zed.dev/docs/configuring-zed#LSP-Insert-Mode) for
more information.
---------
Co-authored-by: João Marcos <marcospb19@hotmail.com>
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
This PR adds passing in `stop_on_entry` to debug configs in debug.json
instead of going through initialization args.
This has two benefits:
1. It's more streamlined to a user since every internal adapter supports
`stop_on_entry` for launch requests and Go's adapter supports it for
attach requests too.
2. It will allow @osiewicz `NewSesssionModal` PR to use this field for
the stop on entry checkbox.
Release Notes:
- N/A
This fixes a bug in #27568 that caused flickering in the git panel's
checkbox state when staging and unstaging entire files. The problem is
that that stage/unstage action first saves the target path (if it's open
as a buffer), and we do a targeted git status scan in response to that
filesystem event, which makes its way to the git panel and causes it to
clear its pending state before the actual stage or unstage has gone
through.
The fix is to not clear the panel's pending state for git repository
events that originated from a targeted scan (i.e. one that was triggered
by FS events for repo paths, as opposed to events inside `.git` which
cause all statuses to be recomputed).
Release Notes:
- N/A
This PR makes the command permission prompt part of the tool card and
allow users to straight away change the `always_allow_tool_actions`
setting via the "Always Allow" button from that card. If that button is
clicked, that setting is turned on, and any command that requires
permission from that point on will auto-run.
Additionally, if a bash command spans multiple lines, we show the line
count at the end of the command string. (Note: this is not perfect yet
because it can likely be not visible by default, but we didn't think
this was a major blocker for now. We'll work on improving this next).
### Thread View
<img
src="https://github.com/user-attachments/assets/00f93c39-990f-4b79-84ec-0427b997167f"
width="500"/>
### Settings View
<img
src="https://github.com/user-attachments/assets/52d32435-7c8d-4ab4-a319-6cabc007267b"
width="500"/>
Release Notes:
- N/A
---------
Co-authored-by: Thomas Mickley-Doyle <tmickleydoyle@gmail.com>
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Co-authored-by: Nathan Sobo <nathan@zed.dev>
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Marshall Bowers