The bash tool will now truncate its output to 8192 bytes (or the last
newline before that).
We also added a global limit for any tool that produces a clearly large
output that wouldn't fit the context window.
Release Notes:
- agent: Truncate bash tool output
---------
Co-authored-by: Michael Sloan <mgsloan@gmail.com>
I found a few more cases where the UI wasn't updated immediately after
an interaction.
Release Notes:
- agent: Fixed delay after removing threads from "Past Interactions"
- agent: Fixed delay after adding/remove context via keyboard
This would cause the history view not to get refreshed immediately when
a thread was deleted
Release Notes:
- agent: Fixed a bug where the history view wouldn't refresh after
deleting a thread
#28102 introduced a bug where thread summaries wouldn't get generated
because they would get set to the default title instead of `None`.
Not adding a release note because the bug didn't make it to Preview.
Release Notes:
- N/A
Closes: https://github.com/zed-industries/zed/issues/20582
Allows users to select a specific model for each AI-powered feature:
- Agent panel
- Inline assistant
- Thread summarization
- Commit message generation
If unspecified for a given feature, it will use the `default_model`
setting.
Release Notes:
- Added support for configuring a specific model for each AI-powered
feature
---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
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>
### 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>
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
We were including the context at the end which meant it never got
cached. We'll now include it with the first message that introduced it
so it's cached as long as it doesn't change.
This is an improvement, but we probably still need to think of ways to
optimize caching for cases where files in context change.
Release Notes:
- N/A
We'll now prompt the user to start a new thread when the active one gets
too long.
<img width=500
src="https://github.com/user-attachments/assets/91445bc0-3e81-422f-aa4a-b8f0741f9d9a"></img>
When they click "Start New Thread", will create a new one with the
previous one added as context.
<img width=500
src="https://github.com/user-attachments/assets/c3b4223f-5bdd-4ba4-956f-5a5880d5e2c3"></img>
Instead of including the full thread text, we'll now add summarized
versions of threads to the context, allowing you to continue the
conversation even if it was near the token limit.
- Thread summaries are cached and persisted.
- A cached summary is invalidated if the thread is continued.
- We start generating the thread summary as soon as it's selected from
the picker. Most times, the summary will be ready by the time the user
sends the message.
- If the summary isn't ready by the time a message is sent, the user
message will be displayed in the thread immediately, and a "Summarizing
context..." indicator will appear. After the summaries are ready, we'll
start generating the response and show the usual "Generating..."
indicator.
Release Notes:
- N/A
---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
Models seem to do this ever so often and get very confused. Failing here
helps them recover.
Release Notes:
- N/A
Co-authored-by: Richard Feldman <richard@zed.dev>
Adds some guidance for the assistant on how to respond to tool results
and other interactions
Release Notes:
- N/A
Co-authored-by: Richard Feldman <richard@zed.dev>
Edit action markers look like git conflicts and can trip up tooling used
to resolve git conflicts. This PR creates them programmatically so that
they don't appear in source code.
Release Notes:
- N/A
This required adding scrollbar support to `list`. Since `list` is
virtualized, the scrollbar height will change as more items are
measured. When the user manually drags the scrollbar, we'll persist the
initial height and offset calculations accordingly to prevent the
scrollbar from moving away from the cursor as new items are measured.
We're not doing this yet, but in the future, it'd be nice to budget some
time each frame to layout unmeasured items so that the scrollbar height
is as accurate as possible.
Release Notes:
- N/A
- Add instructions in description to read before editing
- Add instructions in edit prefix to explicitly ask for reads
- Fix `connection error: delay between messages too long` by processing
chunks off a channel
Release Notes:
- N/A
Sometimes the editor model returns no search/replace blocks. This
usually happens when the architect model calls the edit tool before
reading any files. When this happens, we'll now return the raw response
from the editor model to the architect model so it can recover
accordingly.
Release Notes:
- N/A
Instead of just reporting a search match failure, we'll now indicate
whether the file is empty or exists to help the model recover better
from bad edits.
Release Notes:
- N/A
This is surprising, but the Anthropic API returns a 400 if a tool output
is an empty string because it thinks we're attaching a `tool use`
without a corresponding `tool result`, but we are not, it's just empty
(which seems totally reasonable) 🙃
Release Notes:
- N/A
Anthropic API doesn't allow `tool_use` messages without a corresponding
`tool_result`, so we'll skip those when building a request. I'll
separately investigate why we are sending request before the tool result
as that might lead to separate issues, but that might take a while and
this is currently very frustrating.
Release Notes:
- N/A
Sometimes the model produces SEARCH queries that don't match the
indentation of the source file exactly.
When we can't find an exact match, we'll now attempt to match the lines
while being more flexible about the leading whitespace as long as all
lines are consistently offset from the source, and extend the leading
whitespace in the REPLACE string accordingly.
Release Notes:
- N/A
When we failed to match a search string, we were reporting the replace
string as not found, this confuses the model and can make it go into a
doom loop. This PR fixes that improves the error output in general to
help it recover faster.
Release Notes:
- N/A
#26935 is leading to bad edits, so let's revert it for now. I'll bring
back a version of this, but it'll likely just focus on indentation
instead of making the whole search fuzzy.
Release Notes:
- N/A
When the model reads file, we'll track the version it read, and let it
know if the user makes edits to the buffer. This helps prevent edit
failures because it'll know to re-read the file before.
Release Notes:
- N/A
We'll now include the search/replace block that got applied as part of
the tool output. We think this will help the model have a better idea of
how the file changed and prevent later edit failures.
Release Notes:
- N/A
Without this, we running into the following error:
```
Running into this when running tests. Is this
dyld[45041]: Library not loaded: @rpath/WebRTC.framework/WebRTC
Referenced from: <B2EA63A5-994E-3FB0-A74B-C9C4F7E5C1EF> /Users/aguz/zed/zed/target/debug/deps/assistant_tools-522d7745dd439dfb
Reason: no LC_RPATH's found
```
Thanks Piotr!
Release Notes:
- N/A
When the user attached context in the thread, the editor model request
would fail because its tool use wouldn't be removed properly leading to
an API error.
Also, after an edit, we'd keep the old file snapshot in the context.
This would make the model think that the edits didn't apply and make it
go in a loop.
Release Notes:
- N/A
Instead of getting the whole text from the buffer, replacing with
`String::replace`, and getting a whole diff, we'll now use `SearchQuery`
to get a range, diff only that range, and apply it (all in the
background).
When we match zero strings, we'll record a "bad search", keep going and
report it to the model at the end.
Release Notes:
- N/A
---------
Co-authored-by: Max <max@zed.dev>
Adds an `debug: edit tool` action that opens a new view which will help
us debug the edit tool internals. As the edit tool runs, the log
displays:
- Instructions provided by the main model
- Response stream from the editor model
- Parsed edit blocks
- Tool output provided back to main model
The log automatically records all edit tool interactions for staff, so
if you notice something weird, you can debug it retroactively without
having to open the debug tool first. We may want to limit the number of
recorded requests later.
I have a few more ideas for it, but this seems like a good starting
point.
https://github.com/user-attachments/assets/c61f5ce8-08b1-4500-accb-db2a480eb3ab
Release Notes:
- N/A
Assertions on the parsed system prompt should use CRLF on Windows. I
didn't see it before because I was testing on my Windows VM from a
shared folder I cloned on macOS.
Release Notes:
- N/A
#26538 fixed part of the issue, but it would keep trailing carriage
returns in the old/new strings. The model is unlikely to produce those,
but we might as well support them.
Release Notes:
- N/A
Exposes a new "edit files" tool that the model can use to apply
modifications to files in the project. The main model provides
instructions and the tool uses a separate "editor" model (Claude 3.5 by
default) to generate search/replace blocks like Aider does:
````markdown
mathweb/flask/app.py
```python
<<<<<<< SEARCH
from flask import Flask
=======
import math
from flask import Flask
>>>>>>> REPLACE
```
````
The search/replace blocks are parsed and applied as they stream in. If a
block fails to parse, the tool will apply the other edits and report an
error pointing to the part of the input where it occurred. This should
allow the model to fix it.
Release Notes:
- N/A
---------
Co-authored-by: Antonio Scandurra <me@as-cii.com>
This PR makes `io.open` use our own implementation again, but instead of
the real filesystem, it will now use the project's to check file
metadata and perform read and writes using project buffers.
This also cleans up the `io.open` implementation by splitting it into
multiple methods, adds tests for various File I/O patterns, and fixes a
few bugs in read formats.
Release Notes:
- N/A
We decided to expose scripting as tools again. We are aware of the UX
downsides of doing so, but we want to focus on getting it working well
first, and the model seems to make better use of it as an actual tool.
In the future, the tools API might support streaming. If it doesn't and
we need to ship, we can consider reverting this.
Release Notes:
- N/A
This PR makes refactors the scripting functionality to be a first-class
concept of the assistant instead of a generic tool, which will allow us
to build a more customized experience.
- The tool prompt has been slightly tweaked and is now included as a
system message in all conversations. I'm getting decent results, but now
that it isn't in the tools framework, it will probably require more
refining.
- The model will now include an `<eval ...>` tag at the end of the
message with the script. We parse this tag incrementally as it streams
in so that we can indicate that we are generating a script before we see
the closing `</eval>` tag. Later, this will help us interpret the script
as it arrives also.
- Threads now hold a `ScriptSession` entity which manages the state of
all scripts (from parsing to exited) in a centralized way, and will
later collect all script operations so they can be displayed in the UI.
- `script_tool` has been renamed to `assistant_scripting`
- Script source now opens in a regular read-only buffer
Note: We still need to handle persistence properly
Release Notes:
- N/A
---------
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
If the user already binds `tab`/`alt-tab`/`alt-l` to a different action
in a conflicting context and hasn't assigned a different keybinding for
`editor::AcceptEditPrediction`, we would show broken popovers with no
bindings:
Instead, they will now see an error-variant of every popover which
includes a tooltip with a short description and buttons to open the
keymap, and open a new docs section explaining the issue in detail and
how to fix it.
Note: I included the docs change in this PR because it's ok to deploy
before the release, as it also applies to existing versions.
Release Notes:
- edit predictions: Improve UX when there's no keybinding for accepting
predictions
---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Co-authored-by: Danilo <danilo@zed.dev>
Closes: #25556
We were always comparing `disabled_globs` against the relative file
path, we'll now use the absolute path if the glob is also absolute.
Release Notes:
- Support absolute globs in `edit_predictions.disabled_globs`
Fixes a few state mismatches when changing providers and other settings
Release Notes:
- edit predictions: Fix mismatch between status bar settings and editor
control settings
- edit predictions: Turn off as soon as `edit_prediction_provider` is
set to `none`
---------
Co-authored-by: Danilo <danilo@zed.dev>
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Closes https://github.com/zed-industries/zed/issues/25406
### Problem
Users have been confused about requiring `alt-tab` instead of just `tab`
in cases where they don't have a completions menu open (see issue
above). When they insert a newline and are in leading whitespace, they
expect to be able to accept a prediction with just `tab`, but doing so
increasing the indentation instead.
This PR changes the behavior in so a modifier is only required if the
cursor isn't already at the right indentation level based on the
surrounding block. In this case, `tab` would increase the indentation
and the prediction would get interpolated, allowing the user to press
`tab` again to accept it.
We also updated the docs to break down this behavior:
https://github.com/zed-industries/zed/pull/25493
### Before
https://github.com/user-attachments/assets/91fe6193-dddd-43c1-8c26-0f4648bdc3fa
### After
https://github.com/user-attachments/assets/671041bf-bf22-46a3-8466-b19b3e7dd6a0
Release Notes:
- edit predictions: Do not require a modifier key when indentation is
correct according to its surrounding block
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
This function has grown a lot and it was getting really hard to
navigate. This PR splits it into smaller methods and moves it into
`Editor` with the rest of the edit prediction popovers' code.
I think there are opportunities to consolidate the many popovers we
have, but we'll do that separately.
Release Notes:
- N/A
We begin a columnar selection when we drag the mouse while holding
`alt-shift`. This PR makes it possible to start the selection and then
turn it into columnar by pressing `alt-shift`.
Fixes#5372
Release Notes:
- Support switching to columnar selection by pressing `alt-shift` while
mouse is down
If the user removes all modified keybinds in `edit_prediction_conflict`,
the preview bar above the completions menu would disappear. This PR
handles that case slightly better by still showing the 1-line preview
(which they might accept via an unmodified keybind) and hides the `|
Preview ⌥` section since it's impossible to invoke in this case.
Release Notes:
- Handle `edit_prediction_conflict` context without modified keybinds
for `AcceptEditPrediction`
Release Notes:
- Fixed a panic when displaying a whitespace-only line in the edit
prediction preview
---------
Co-authored-by: Antonio <antonio@zed.dev>
We were disabling edit predictions altogether when
`show_edit_predictions` was set to `false`. However, even in that case,
`editor::ShowEditPrediction` is supposed to let your request a
prediction manually.
Release Notes:
- Fixed `editor::ShowEditPrediction` when `show_edit_predictions` is set
to `false`.
We were reading edit prediction settings too often, causing frames to be
dropped. We'll now cache them and update them from
`update_visible_inline_completion`.
Release Notes:
- N/A
In one of the recent changes to the edit predictions status bar menu, we
lost the red dot that is displayed when the user has Zed as the provider
but hasn't accepted terms of service. Note: All the checks were still in
place, just the visual indicator was missing.
Release Notes:
- N/A
---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
- Do not accept with just `tab` in `when_holding_modifer` mode
- Fix fake cursor for jumps when destination row is outside viewport
- Use current preview state for deciding whether to show modifiers in
popovers
- Stay in preview state if ⌥ isn't released after accepting a jump
Release Notes:
- N/A
This PR adds a new `inline_completions.inline_preview` config which can
be set to `auto` (current behavior) or to `when_holding_modifier`.
When set to the latter, instead of showing edit prediction previews
inline in the buffer, we'll show it in a popover (even when there's no
LSP completion) so your isn't constantly moving as completions arrive.
https://github.com/user-attachments/assets/3615d151-3633-4ee4-98b9-66ee0aa735b8
Release Notes:
- N/A
---------
Co-authored-by: Danilo <danilo@zed.dev>
When you have an edit prediction available, you can now also accept it
with `alt-tab` (or `alt-enter` on Linux) even if you don't have an LSP
completions menu open. This is meant to lower the mental load when going
from one mode to another.
Release Notes:
- N/A
This is pretty rare but I found a case where `line_layouts` didn't have
the requested line yet, so we now skip rendering the cursor for that
period and avoid panicking.
Release Notes:
- N/A
Agus Zubiaga
