You can set `agent_font_size` as a top-level settings key. You can also
use `zed::IncreaseBufferFontSize` and `zed::DecreaseBufferFontSize` and
`zed::ResetBufferFontSize` the agent panel is focused via the standard
bindings to adjust the agent font size. In the future, it might make
sense to rename these actions to be more general since "buffer" is now a
bit of a misnomer. 🍐'd with @mikayla-maki
Release Notes:
- N/A
---------
Co-authored-by: Mikayla Maki <mikayla.c.maki@gmail.com>
WIP
- On macOS/Linux, run the command in bash instead of the user's shell
- Try to prevent the agent from running commands that expect interaction
Release Notes:
- Agent Beta: Switched to using `bash` (if available) instead of the
user's shell when calling the terminal tool.
- Agent Beta: Prevented the agent from hanging when trying to run
interactive commands.
---------
Co-authored-by: WeetHet <stas.ale66@gmail.com>
To-dos:
- [x] Expose the command to defend against cases where that's just super
long
- [x] Tackle the vertical scroll conflict with panel scroll
- [x] Reduce default font-size
Release Notes:
- N/A
---------
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
Co-authored-by: Mikayla Maki <mikayla.c.maki@gmail.com>
Co-authored-by: Agus Zubiaga <hi@aguz.me>
Bypass our terminal subsystem and just run a shell in a pty.
- [x] make sure we use the same working directory
- [x] strip control chars from the pty output (?)
- [x] tests
Release Notes:
- N/A
I am currently setting the font size corrrectly by using a custom
EditorStyle and building an element. However I need to use the same
properties as a normal editor for everything but font size.
Release Notes:
- N/A
I also introduced a new eval to prove the encouragement actually makes a
difference.
Release Notes:
- Improved agent behavior when streaming edits, encouraging it to
editing files as opposed to creating them from scratch
Nathan here: I also tacked on a bunch of UI refinement.
Release Notes:
- Introduced the ability to follow the agent around as it reads and
edits files.
---------
Co-authored-by: Nathan Sobo <nathan@zed.dev>
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Still a work in progress.
Release Notes:
- N/A
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Co-authored-by: Nathan Sobo <nathan@zed.dev>
Co-authored-by: Cole Miller <m@cole-miller.net>
Co-authored-by: Nathan Sobo <1789+nathansobo@users.noreply.github.com>
Co-authored-by: Cole Miller <53574922+cole-miller@users.noreply.github.com>
Also `now` in `write` profile
Release Notes:
- Tools for manipulating directories no longer require confirmation, and
are enabled in the Write profile
- Enabled `now` and `list_directory` tools by default in Write profile
---------
Co-authored-by: Cole Miller <m@cole-miller.net>
Co-authored-by: Cole Miller <cole@zed.dev>
Some changes in the LanguageModelRegistry caused the web search tool not
to show up, because the `DefaultModelChanged` event is not emitted at
startup anymore.
Release Notes:
- agent: Fixed an issue where the web search tool would not be available
after starting Zed (only when using zed.dev as a provider).
Refs #29733
This pull request introduces a new field to the `StreamingEditFileTool`
that lets the model create or overwrite a file in a streaming way. When
one of the `assistant.stream_edits` setting / `agent-stream-edits`
feature flag is enabled, we are going to disable the `CreateFileTool` so
that the agent model can only use `StreamingEditFileTool` for file
creation.
Release Notes:
- N/A
---------
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
Co-authored-by: Oleksiy Syvokon <oleksiy.syvokon@gmail.com>
This PR prevents any unnecessary lines from being rendered in the edit
file tool card in the case of small diffs.
I think this (hopefully) addresses the last remaining task from
https://github.com/zed-industries/zed/pull/29448.
| `main` | This PR |
| --- | --- |
| <img width="634" alt="main"
src="https://github.com/user-attachments/assets/7c06394e-957a-4d36-a484-5974687041e9"
/> | <img width="634" alt="PR"
src="https://github.com/user-attachments/assets/84206d5a-a93a-4a42-99ca-7cdebb0d91bb"
/> |
(The last empty line in the second image is an empty line present in the
file itself)
---
n the second commit I also preemtively disabled vertical overscrolling
for full mode editors which are sized by content. This is basically the
same fix as in https://github.com/zed-industries/zed/pull/28471.
Strictly speaking, this is not needed for the fix here, but I thought it
might be nice to have for the future to prevent any issues from occuring
due to overscroll.
Release Notes:
- agent: Improved rendering of small diffs for the edit file tool card.
This pull request introduces a new tool for streaming edits. The
short-term goal is for this tool to replace the existing `EditFileTool`,
but we want to get this out the door as soon as possible so that we can
start testing it.
`StreamingEditFileTool` is mutually exclusive with `EditFileTool`. It
will be enabled by default for anyone who has the `agent-stream-edits`
feature flag, as well as people that set `assistant.stream_edits` to
`true` in their settings.
### Implementation
Streaming is achieved by requesting a completion while the `edit_file`
tool gets called. We invoke the model by taking the existing
conversation with the agent and appending a prompt specifically tailored
for editing. In that prompt, we ask the model to produce a stream of
`<old_text>`/`<new_text>` tags. As the model streams text in, we
incrementally parse it and start editing as soon as we can.
### Evals
Note that, as part of this pull request, I also defined some new evals
that I used to drive the behavior of the recursive LLM call. To run
them, use this command:
```bash
cargo test --package=assistant_tools --features eval -- eval_extract_handle_command_output
```
Or comment out the `#[cfg_attr(not(feature = "eval"), ignore)]` macro.
I recommend running them one at a time, because right now we don't
really have a way of orchestrating of all these evals. I think we should
invest into that effort once the new agent panel goes live.
Release Notes:
- N/A
---------
Co-authored-by: Nathan Sobo <nathan@zed.dev>
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Co-authored-by: Oleksiy Syvokon <oleksiy.syvokon@gmail.com>
⚠️ Work in progress until all of the to-dos are knocked out:
- [x] Disable soft-wrapping
- [x] Make it foldable only after a certain number of lines
- [x] Display tool status errors
- [x] Fix horizontal scroll now that we've disabled soft-wrap
- [ ] Don't render unnecessary extra lines (will be added later, on a
follow-up PR)
Release Notes:
- N/A
---------
Co-authored-by: Agus Zubiaga <hi@aguz.me>
Co-authored-by: Michael Sloan <mgsloan@gmail.com>
Adds popular examples of long-running commands to system prompt.
Unfortunately, I couldn't add an eval example as the new terminal tool
no longer works in `eval`. We can look into that tomorrow, but I'm
seeing improvements when manually testing this, so I'd like to merge it.
<img
src="https://github.com/user-attachments/assets/ac24e617-e068-466f-875d-c30e1f2465c4"
width=400></img>
Release Notes:
- agent: Discourage long-running commands
The `grep` tool used to include 4 lines of context around the match, but
the lines included would often be unhelpful. This PR improves this
behavior by using the range of the parent syntax node that contains the
full line(s) matched.
The match headers will also now include symbol breadcrumbs so that the
model can already gather code structure before/without reading files.
````md
### impl GitRepository for RealGitRepository › fn compare_checkpoints › L1278-1284
```rust
let result = git
.run(&[
"diff-tree",
"--quiet",
&left.commit_sha.to_string(),
&right.commit_sha.to_string(),
])
```
````
This positively impacts the `add_arg_to_trait_method` eval example with
better diff output, fewer tool failures, and reduced total turns.
Note: We have some plans to use a an "elision" approach where we would
combine all matches for a given file, skipping lines between them while
keeping symbol declaration lines. The theory is that this would be map
more closely to the expected input for edits. For now, this PR is a
significant improvement.
Release Notes:
- Agent: Enrich `grep` tool output with syntax information
This PR addresses the behavior of the agent's terminal tool when the
executed command is interrupted or fails after producing some output.
Currently, if the command doesn't finish successfully, any partial
output captured before the interruption/failure is discarded, and only
an error message (or a generic cancellation message) is returned to the
LLM.
This change modifies the `run_command_limited` function in the terminal
tool to catch errors when awaiting the command's status (which includes
interruptions). In the case of such an error, it now includes any
partial stdout/stderr captured up to that point within the error message
returned to the `ToolUseState`. This ensures the LLM receives the
partial context even when the command doesn't complete cleanly, framed
appropriately as part of an error/interruption message.
Closes#29101
Release Notes:
- N/A
One motivation is that the outlines returned by `read_file` for large
files list line numbers assuming an inclusive `end_line`. As a result,
when the agent uses these outlines for `read_line` calls, it would
otherwise miss the last line.
Release Notes:
- N/A
Implementing the `ToolCard` for the path_search tool. It also adds the
"jump to file" functionality if you expand the results.
Release Notes:
- N/A
---------
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
Co-authored-by: Agus Zubiaga <hi@aguz.me>
This PR removes two fields from JSON schemas (`$schema` and `title`),
which are not expected by any model provider, but were spuriously
included by our JSON schema library, `schemars`.
These added noise to requests and cost wasted input tokens.
### Old
```json
{
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "FetchToolInput",
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"description": "The URL to fetch.",
"type": "string"
}
}
}
```
### New:
```json
{
"properties": {
"url": {
"description": "The URL to fetch.",
"type": "string"
}
},
"required": [
"url"
],
"type": "object"
}
```
- N/A
This PR significantly improves the quality of the initial file search
that occurs when the model doesn't yet know the full path to a file it
needs to read/edit.
Previously, the assertions in file_search often failed on main as the
model attempted to guess full file paths. On this branch, it reliably
calls `find_path` (previously `path_search`) before reading files.
After getting the model to find paths first, I noticed it would try
using `grep` instead of `path_search`. This motivated renaming
`path_search` to `find_path` (continuing the analogy to unix commands)
and adding system prompt instructions about proper tool selection.
Note: I know the command is just called `find`, but that seemed too
general.
In my eval runs, the `file_search` example improved from 40% ± 10% to
98% ± 2%. The only assertion I'm seeing occasionally fail is "glob
starts with `**` or project". We can probably add some instructions in
that regard.
Release Notes:
- N/A
Instructs the model to include the fields that we display first in the
input object, so that e.g the user can see the path of a file while the
model generates the content.
Release Notes:
- N/A
This PR implements the `ToolCard` for the edit file tool, which allow us
to display an editor with a diff in the thread view with the changes
performed by the model.
- [x] Fix buffer sometimes displaying empty
- [x] Stop buffer from scrolling together with the thread
- [x] Fix multibuffer header sometimes appearing
- [x] Fix buffer height issue
- [x] Implement "full height" expand button
- [x] Add "Jump To File" functionality
- [x] Polish and refine styles
Release Notes:
- agent: Added diff preview cards in the thread view for edits performed
by the agent.
---------
Co-authored-by: João Marcos <marcospb19@hotmail.com>
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
Co-authored-by: Agus Zubiaga <hi@aguz.me>
Co-authored-by: Conrad Irwin <conrad.irwin@gmail.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
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
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>
