[Fix] Active task sandbox closes after a provider error - #984
Merged
mrubens merged 2 commits intoAug 2, 2026
Conversation
Contributor
Author
|
No new code issues found. See task
Reviewed bddc026 |
Contributor
Author
|
Fixed the scheduler-owned completion race. A completed snapshot/standby handoff now returns |
mrubens
marked this pull request as ready for review
August 2, 2026 03:43
mrubens
requested review from
brunobergher,
daniel-lxs and
mrubens
as code owners
August 2, 2026 03:43
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What changed
waiting_for_prompt, preserve the visible error, and accept follow-up prompts without restarting the sandbox.Why this change was made
A provider error could immediately close the task and discard an otherwise healthy working environment. Model-turn failure and sandbox lifecycle should be independent so users can recover without losing workspace state.
Impact
Provider errors no longer force active task sandboxes to close or sleep immediately. Users can send a follow-up in the same task, inactive sessions retain their workspace through the normal idle lifecycle, and a completed retention handoff cannot be overwritten by a stale failed result.