Repository navigation
fix(fork): an agent's self-snooze survives its own turn completing - #4
Merged
Jefferson-Butler1 merged 1 commit intoOct 19, 2026
Merged
Conversation
Carries a fix for upstream pingdotgg#18985 as agent-self-snooze.patch: an agent that snoozed its own thread mid-turn was woken by finishing that turn. The snooze now waits for the turn to complete, like upstream's deferred self-settle.
Jefferson-Butler1
force-pushed
the
fork/agent-self-snooze
branch
from
October 19, 2026 18:08
d55166f to
1ef0155
Compare
Jefferson-Butler1
changed the base branch from
fork-maintenance
to
fork/refresh-patches-20261019
October 19, 2026 18:08
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
An agent that snoozes its own thread mid-turn gets woken by finishing that same turn (upstream #18985). A completed run wakes a snoozed thread when it finishes after
snoozedAt, and the agent's own run always does.Change
Adds
agent-self-snooze.patchto the end of the series. When the caller is the thread's own agent and a run is active,t3_thread_organizesnooze now waits for that run to complete and then snoozes, returningsnoozesWhenTurnEnds: true. This mirrors upstream's existing deferred self-settle (settleAfterRun). A failed or interrupted run, a snooze someone else set meanwhile, or a wake time that already passed leaves the thread awake. Manual snoozes are unchanged.Source commit:
b7fcd4confix/agent-self-snooze.Verification
vp test runonThreadManagementService.test.ts,runtimeLayer.test.ts,AgentAwarenessRelay.test.ts,OrchestratorMcpToolkit.integration.test.ts: 152 passed. New:snoozeAfterRunbranch cases, and a runtime test showing an own-agent snooze is deferred until the run completes, then applied.v0.1.1-nightly.20261018.3335.python3 -m unittest discover -s .fork -p '*_test.py'passes.Not checked: replay after
home-agent.patch, because the nightly series already fails on that tag (right-panel-maximize-any-width,home-agent,inbox-order,thread-links-any-environmentall conflict). Those need a refresh before any build ships; this patch may need regenerating afterhome-agent.patchis.Claude Opus 5.5 via Claude Code