Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [x] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Closes #ISSUE
Release Notes:
- N/A
This PR upgrades the workspace's app state to a strong pointer. It's an
app-global concern, and it should only die when the app dies. When the
app dies the process exits, so the cyclic reference problem isn't an
issue.
Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [x] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Release Notes:
- N/A
Closes#52115
## Context
Removes the third party edit prediction integration for Sweep AI ahead
of their servers shutting down.
This PR will not affect those who are already use or plan to use their
open weighted models. The code removed by this PR was required for
integrating with their proprietary API.
## Self-Review Checklist
<!-- Check before requesting review: -->
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [x] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Release Notes:
- Removed support for using the Sweep AI edit prediction provider
through their proprietary API, as the servers are shutting down
https://discord.com/channels/1100625416022138902/1100625417272045639/1480644297903575142,
https://x.com/wwzeng1/status/2033302698360180949
Swaps the `arrayvec` dependency for `heapless`, as the `heapless`
library allows changing the type used for the `len` field, which
`arrayvec` hard-codes to `usize`. This means that, for all the
`ArrayVec`s in Zed, we can save 7 bytes on 64 bit platforms by just
storing the length as a `u8`.
I have not benchmarked this change locally, as I don't know what
benchmarking tools are in this project.
As a small bit of context, I wrote the PR to `heapless` to add this
`LenT` generic after seeing a PR on the `arrayvec` crate that seems to
be dead now. Once I saw some of Zed's blog posts about the `rope` crate
and noticed the usage of `arrayvec`, I thought this might be a welcome
change.
Release Notes:
- N/A
---------
Co-authored-by: Piotr Osiewicz <24362066+osiewicz@users.noreply.github.com>
## Context
We're seeing issues where large edits (think generated, agentically or
otherwise) or edits in files with very large lines cause ep requests to
fail until they are flushed from the history due to the request body
exceeding the endpoint size limit. These edits are large enough they
would be omitted from the final prompt anyway due to budgeting so it is
safe to drop them client side.
## How to Review
<!-- Help reviewers focus their attention:
- For small PRs: note what to focus on (e.g., "error handling in
foo.rs")
- For large PRs (>400 LOC): provide a guided tour — numbered list of
files/commits to read in order. (The `large-pr` label is applied
automatically.)
- See the review process guidelines for comment conventions -->
## Self-Review Checklist
<!-- Check before requesting review: -->
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [x] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Release Notes:
- Fixed an issue where large changes to buffers, or edits in buffers
with extremely long lines would cause edit prediction requests to fail
All of the important changes are in
[`db.rs`](https://github.com/zed-industries/zed/pull/51809/changes#diff-2f644eab943bfa58feec29256281a3d9e8d4d7784cd34783e845af8beb15b16d).
Consider reading the commit log in order to review this work.
The DB crate's macro and API was changed to fix flakiness observed in
the MultiWorkspace tests when run locally. This flakiness was caused by
a shared `static LazyLock`, that caused concurrent test runs to interact
with the same underlying in-memory database. This flakiness wasn't
possible on CI due to it's usage of `cargo nextest`, whose
process-per-test approach masked this problem.
Essentially, I've changed the `static_connection` macro to remove the
static database variable and redone the internal model. Now, all
database types are thin wrappers around a generic `AppDatabase`. The
`AppDatabase` collects all of the individual table's migrations via the
`inventory` crate, and so only runs the migrations once on startup,
rather than a dozen times on startup.
The new API requires a `cx` so that we can replace the database returned
at runtime, rather than relying exclusively on a process-global
thread-local. However, we are still using a `static LazyLock` so that we
only need to take an `&App`, instead of an `&mut App`. These databases
types are `Clone + Send + Sync`, so you can easily capture-and-move the
database into background tasks and other places that don't have a `cx`.
For tests that require database isolation, it is now possible to set
their own database in init. See
[`workspace::init_test`](https://github.com/zed-industries/zed/pull/51809/changes#diff-041673bbd1947a35d45945636c0055429dfc8b5985faf93f8a8a960c9ad31e28R13610),
for the flakiness fix.
Best part, this change should be entirely compiler driven, so the Zed
agent was able to make the app-wide refactor easily.
Before you mark this PR as ready for review, make sure that you have:
- [x] Added a solid test coverage and/or screenshots from doing manual
testing
- [x] Done a self-review taking into account security and performance
aspects
- [x] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A
---------
Co-authored-by: Anthony Eid <hello@anthonyeid.me>
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
V0316 differences from V0306:
- Use `<|marker_N|><|marker_N|>` instead of `NO_EDITS`
- All intermediate markers are now emitted (should be more friendly to
speculative decoding)
- No newline padding around marker tags
- No git conflict markers; we now use SeedCoder's EOS tag instead
V0317 is like V0316, but marker numbers are relative to the cursor block
(`<|marker-2|> ... -1 ... -0 ... +1 ... <|marker+2|>`)
Release Notes:
- N/A
## Summary
This PR enables token usage reporting in streaming responses for
OpenAI-compatible APIs (OpenAI, xAI/Grok, OpenRouter, etc).
## Problem
Currently, the token counter UI in the Agent Panel doesn't display usage
for some OpenAI-compatible providers because they don't return usage
data during streaming by default. According to OpenAI's API
documentation, the `stream_options.include_usage` parameter must be set
to `true` to receive usage statistics in streaming responses.
## Solution
- Added StreamOptions struct with `include_usage` field to the open_ai
crate
- Added `stream_options` field to the Request struct
- Automatically set `stream_options: { include_usage: true }` when
`stream: true`
- Updated edit_prediction requests with `stream_options: None`
(non-streaming)
## Testing
Tested with xAI Grok models - token counter now correctly shows usage
after sending a message.
## References
- [OpenAI Chat Completions API -
stream_options](https://platform.openai.com/docs/api-reference/chat/create#chat-create-stream_options)
- [xAI API Documentation](https://docs.x.ai/api)
Closes #ISSUE
Before you mark this PR as ready for review, make sure that you have:
- [ ] Added a solid test coverage and/or screenshots from doing manual
testing
- [ ] Done a self-review taking into account security and performance
aspects
- [ ] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A *or* Added/Fixed/Improved ...
Co-authored-by: Oleksiy <oleksiy@zed.dev>
Closes #ISSUE
Before you mark this PR as ready for review, make sure that you have:
- [ ] Added a solid test coverage and/or screenshots from doing manual
testing
- [ ] Done a self-review taking into account security and performance
aspects
- [ ] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A *or* Added/Fixed/Improved ...
The edit prediction, web search and completions endpoints in Cloud all
use tokens called LlmApiToken. These were independently created, cached,
and refreshed in three places: the cloud language model provider, the
edit prediction store, and the cloud web search provider. Each held its
own LlmApiToken instance, meaning three separate requests to get these
tokens at startup / login and three redundant refreshes whenever the
server signaled a token update was needed.
We already had a global singleton reacting to the refresh signals:
RefreshLlmTokenListener. It now holds a single LlmApiToken that all
three services use, performs the refresh itself, and emits
RefreshLlmTokenEvent only after the token is fresh. That event is used
by the language model provider to re-fetch models after a refresh. The
singleton is accessed only through `LlmApiToken::global()`.
I have tested this manually, and it token acquisition and usage appear
to be working fine.
Edit: I've tested it with a long running session, and refresh seems to
be working fine too.
Release Notes:
- N/A
---------
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
BufferEvent::Edited had no way to distinguish local edits from remote
(collaboration) edits. This caused edit prediction behavior to fire on
the guest's editor when the host made document changes.
Release Notes:
- Fixed edit predictions triggering on collaboration guests when the
host edits the document.
---------
Co-authored-by: Ben Kunkle <ben@zed.dev>
Closes #ISSUE
Before you mark this PR as ready for review, make sure that you have:
- [ ] Added a solid test coverage and/or screenshots from doing manual
testing
- [ ] Done a self-review taking into account security and performance
aspects
- [ ] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A *or* Added/Fixed/Improved ...
Previously we didn't distinguish between an empty `.related_files[]` and
a case where context collection hadn't run yet. As a result, context
retrieval was always attempted for examples with empty `related_files`.
Release Notes:
- N/A
Closes #ISSUE
Before you mark this PR as ready for review, make sure that you have:
- [ ] Added a solid test coverage and/or screenshots from doing manual
testing
- [ ] Done a self-review taking into account security and performance
aspects
- [ ] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A *or* Added/Fixed/Improved ...
Emit client-side organization changed events through
`RefreshLlmTokenListener` so it produces the same `RefreshLlmTokenEvent`
used for server-pushed `UserUpdated` messages.
This keeps token refresh fan-out in one place.
Closes CLO-383.
Release Notes:
- N/A
---------
Co-authored-by: Tom Houlé <tom@tomhoule.com>
Closes #ISSUE
Before you mark this PR as ready for review, make sure that you have:
- [ ] Added a solid test coverage and/or screenshots from doing manual
testing
- [ ] Done a self-review taking into account security and performance
aspects
- [ ] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A *or* Added/Fixed/Improved ...
Closes #ISSUE
Before you mark this PR as ready for review, make sure that you have:
- [ ] Added a solid test coverage and/or screenshots from doing manual
testing
- [ ] Done a self-review taking into account security and performance
aspects
- [ ] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A *or* Added/Fixed/Improved ...
Closes #ISSUE
Before you mark this PR as ready for review, make sure that you have:
- [ ] Added a solid test coverage and/or screenshots from doing manual
testing
- [ ] Done a self-review taking into account security and performance
aspects
- [ ] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A *or* Added/Fixed/Improved ...
Co-authored-by: Agus <agus@zed.dev>
When a diagnostic-triggered prediction returns no edits, don't fall back
to requesting another diagnostic prediction. This was causing an
infinite loop that burned through the API rate limit until hitting 429
errors.
Release Notes:
- N/A
When multiple `queue_prediction_refresh` calls land in the same
synchronous frame, all spawned tasks would read the same throttle state
and each send an identical cloud request.
Now the second task would see that the first request has been sent and
would quit.
Release Notes:
- N/A
This is already expected on the cloud side. This lets us know under
which organization the user is logged in when requesting an llm_api
token.
Closes CLO-337
Release Notes:
- N/A
Closes #ISSUE
Before you mark this PR as ready for review, make sure that you have:
- [ ] Added a solid test coverage and/or screenshots from doing manual
testing
- [ ] Done a self-review taking into account security and performance
aspects
- [ ] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A *or* Added/Fixed/Improved ...
Closes #ISSUE
Before you mark this PR as ready for review, make sure that you have:
- [ ] Added a solid test coverage and/or screenshots from doing manual
testing
- [ ] Done a self-review taking into account security and performance
aspects
- [ ] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- Added support for providing an API key to OpenAI-compatible edit
prediction providers
Closes #ISSUE
Before you mark this PR as ready for review, make sure that you have:
- [ ] Added a solid test coverage and/or screenshots from doing manual
testing
- [ ] Done a self-review taking into account security and performance
aspects
- [ ] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A *or* Added/Fixed/Improved ...
---------
Co-authored-by: Max <max@zed.dev>
Closes #ISSUE
Before you mark this PR as ready for review, make sure that you have:
- [ ] Added a solid test coverage and/or screenshots from doing manual
testing
- [ ] Done a self-review taking into account security and performance
aspects
- [ ] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A *or* Added/Fixed/Improved ...
Closes #ISSUE
Before you mark this PR as ready for review, make sure that you have:
- [ ] Added a solid test coverage and/or screenshots from doing manual
testing
- [ ] Done a self-review taking into account security and performance
aspects
- [ ] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A *or* Added/Fixed/Improved ...
Co-authored-by: Max <max@zed.dev>
Previously, we were not computing excerpt regions correctly for EP
examples captured from prod. This PR fixes that, and also simplifies the
data flow in the EP CLI. Examples either come from a concise spec (like
the markdown evals), or are collected from prod. Either way, we compute
from them a `ZetaPromptInput`, and the downstream steps like
prompt-formatting and scoring are derived from that.
Release Notes:
- N/A
---------
Co-authored-by: Ben Kunkle <ben@zed.dev>
This will not affect how Zeta 2 behaves in production until we update
Cloud to pull in the changes to the `zeta_prompt` crate. But from some
early testing, it seems to improve behavior, not worsen it, even though
the editable region size differs from the currently-deployed model's
training data.
Release Notes:
- N/A
---------
Co-authored-by: Oleksiy Syvokon <oleksiy.syvokon@gmail.com>
Co-authored-by: Ben Kunkle <ben@zed.dev>
Co-authored-by: Zed Zippy <234243425+zed-zippy[bot]@users.noreply.github.com>
The `unreachable()` assumption at `queue_prediction_refresh` could be
violated by an async race condition:
1. `request_prediction_internal` spawns an async task
2. The task awaits a prediction request
3. If the prediction returns `None`, it calls `queue_prediction_refresh`
4. Between the time the prediction was initiated (when the provider was
an EP-store provider) and when the async callback runs, the user can
change their edit prediction provider setting to a non-EP-store provider
5. `queue_prediction_refresh` re-reads the settings and hits the
`unreachable!()
Release Notes:
- N/A
Release Notes:
- Added the ability to use a self-hosted OpenAI-compatible server for
edit predictions.
---------
Co-authored-by: Ben Kunkle <ben@zed.dev>
Co-authored-by: Zed Zippy <234243425+zed-zippy[bot]@users.noreply.github.com>
Ben Kunkle