Unblock fleet waits on interrupt and scope them to the caller - #679
Merged
Conversation
wait_agents with omitted targets used the shared session store, so a parent could block on siblings and leftover workers. interrupt_agent never wrote the wait mailbox, so a wait after interrupt hung until timeout and the parent retried forever. Wait now uses this install's fleetRecords, interrupt terminalizes that mailbox immediately, nested spawn_agent records parentSessionId, and wait supports mode=all plus parent-turn abort.
Collaborator
Author
closeOne flips strip status to cancelled, which killed the soft-interrupt fallback that still required status === running. Terminalize fleetRecords on close (same owning layer as interrupt) and collect on the soft path so omitted re-waits do not re-deliver.
TheGreatAxios
added a commit
that referenced
this pull request
Aug 27, 2026
* Unblock fleet waits on interrupt and scope them to the caller wait_agents with omitted targets used the shared session store, so a parent could block on siblings and leftover workers. interrupt_agent never wrote the wait mailbox, so a wait after interrupt hung until timeout and the parent retried forever. Wait now uses this install's fleetRecords, interrupt terminalizes that mailbox immediately, nested spawn_agent records parentSessionId, and wait supports mode=all plus parent-turn abort. * Require fleetRecords on interrupt and tighten fleet wait coverage * Clarify mode=all interrupt test comment timing * Unblock fleet waits when close_agent tears a worker down closeOne flips strip status to cancelled, which killed the soft-interrupt fallback that still required status === running. Terminalize fleetRecords on close (same owning layer as interrupt) and collect on the soft path so omitted re-waits do not re-deliver.
TheGreatAxios
added a commit
that referenced
this pull request
Aug 27, 2026
* Unblock fleet waits on interrupt and scope them to the caller wait_agents with omitted targets used the shared session store, so a parent could block on siblings and leftover workers. interrupt_agent never wrote the wait mailbox, so a wait after interrupt hung until timeout and the parent retried forever. Wait now uses this install's fleetRecords, interrupt terminalizes that mailbox immediately, nested spawn_agent records parentSessionId, and wait supports mode=all plus parent-turn abort. * Require fleetRecords on interrupt and tighten fleet wait coverage * Clarify mode=all interrupt test comment timing * Unblock fleet waits when close_agent tears a worker down closeOne flips strip status to cancelled, which killed the soft-interrupt fallback that still required status === running. Terminalize fleetRecords on close (same owning layer as interrupt) and collect on the soft path so omitted re-waits do not re-deliver.
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
1 participant
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.
Summary
wait_agentswith omitted targets waits on this caller’s own uncollected fleet, not every running session in the shared store.interrupt_agentterminalizes the wait mailbox immediately (interrupted) so a parent wait cannot hang until timeout and retry forever.spawn_agentrecordsparentSessionIdsoclose_agentcan walk descendants.wait_agentsacceptsmode=alland treats a parent-turn abort like a timeout: workers keep running.Verification
bun run typecheck,bun run build, andbun run testpassmode=all, and wait abort