This allows us to just pull requests that have the latest EP request
schema with the `predicted` boolean on events in the edit history.
Release Notes:
- N/A
This PR updates the `Edit Prediction Rated` event to be routed through
Cloud instead of the normal telemetry pipeline.
Closes CLO-224.
Release Notes:
- N/A
---------
Co-authored-by: Tom <tom@zed.dev>
This allows us to switch the prompt format without client-side changes.
If we want to experiment with prompt formats or models other than the
currently-deployed one, we can use the raw endpoint, and do prompt
construction and output processing on the client.
This also adds an optional environment parameter to the raw endpoint, so
that we can use that endpoint in the new scheme where we're deploying to
separate environments for different zeta prompt versions.
Release Notes:
- N/A
This also fixes the isolated whitespace change metric, which is not
takes cursor position into account (it's okay to insert a newline if it
has a cursor on it)
Release Notes:
- N/A
### Summary
Adds accept/reject tracking for Mercury edit predictions.
### Changes
Sends events to https://api-feedback.inceptionlabs.ai/feedback when:
Accept — user presses Tab
Reject — user presses Escape
Ignore — prediction dismissed implicitly (typing, cursor move, etc.)
Added `discard_explicit` method to the delegate trait to distinguish
explicit vs implicit dismissal. Updated `reject_prediction` and
`reject_current_prediction` methods with an `explicit` bool parameter to
thread this through to the Mercury feedback logic. Other providers are
unaffected—they use the default implementation.
Feedback is fire-and-forget in a background thread, only sent for
predictions that were shown.
### Data Collected
- Request ID (returned from Inception API)
- User action (either accept/reject/ignore)
- Client Zed version (to track updates made to Zed client which could
potentially affect nextedit implementation)
Release Notes:
- N/A
---------
Co-authored-by: Ben Kunkle <ben@zed.dev>
Previously, Ollama would not show up as available until you opened some
UI that prompted connecting to Ollama, like the agent panel or the edit
prediction settings.
Release Notes:
- N/A
Closes#48097
Release Notes:
- Fixed Copilot instances not being cleared up after their window is
closed.
- Copilot edit prediction provider now respects `disable_ai` setting.
* [x] capture and store teacher model's predicted cursor position
* [x] provide cursor position to student during distillation
* [x] eval cursor positions
* [x] parse and apply cursor position predictions at runtime
Release Notes:
- N/A
Closes #ISSUE
Measure the model reversing user edits programatically, for a more
robust and consistent measurement than LLM-as-judge
Release Notes:
- N/A *or* Added/Fixed/Improved ...
Fixes an issue where edits would be shown like this:
<img width="1262" height="1072" alt="image"
src="https://github.com/user-attachments/assets/f3ec865a-4bf2-423c-8465-62a54a21a882"
/>
When they should be like this:
<img width="1260" height="388" alt="image"
src="https://github.com/user-attachments/assets/ac555a25-f222-48aa-b922-0ae5b9f4e260"
/>
Release Notes:
- N/A *or* Added/Fixed/Improved ...
This PR adds a new `needs_llm_token_refresh` helper method for checking
if the LLM token needs to be refreshed.
We were duplicating the check for the `x-zed-expired-token` header in a
number of spots, and it will be gaining an additional case soon.
Release Notes:
- N/A
Users had trouble signing in due to us relying on the Copilot::global
being set, which was never the case. We've decided to use a dedicated
LSP instance just for handling auth of Copilot Chat and other goodies.
That instance is subscribed to by local Copilot instances for projects.
When the Auth instance changes it's state, local instances are prompted
to re-check their own sign in status.
Closes#47352
Co-authored-by: dino <dinojoaocosta@gmail.com>
Release Notes:
- Fixed authentication issues with Copilot.
---------
Co-authored-by: dino <dinojoaocosta@gmail.com>
Co-authored-by: Zed Zippy <234243425+zed-zippy[bot]@users.noreply.github.com>
Oleksiy Syvokon