Repository navigation
Require runner output once the run has exited - #34
Merged
Merged
Conversation
…ed-output-recovery
run-investigation.sh always writes the output file before it exits, so after an exit status a failed download is a transport error. Retry it in the same Sandbox and throw an infrastructure error if it stays unavailable. This drops the duplicated timeout classification and the SDK token-phase race, which is tracked upstream for #26. Co-authored-by: Cursor <cursoragent@cursor.com>
jacobprall
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When the exec stream reported an exit but downloading the output file failed, the error became empty output.
classifyRunthen reported a non-retryableagent_error, so a completed, paid investigation was thrown away.run-investigation.shalways writes the output file before it exits, so once there's an exit status the download is required. The host now retries it up to three times in the same Sandbox, so the model run isn't repeated. If it still fails, it throws an infrastructure error with the transport cause, whichinvestigateretries. Runs with no exit status (aborted or lost stream) keep best-effort reads.The original version of this PR also re-derived timeout classification inside
sandbox.tsand raced the SDK's download. That was trimmed: the classification duplicatedclassifyRun, and the SDK token-phase timeout is tracked upstream for #26.Fixes #25.