I'm parked on you

Pick an option on each card and press Done; your answer goes straight back to the session. The raiser's pick is marked. "I'm not sure" and "Take it to the engineering bridge" are real answers.

13 questions on this

In plain terms. Three calls left from the held-PR cleanup. First, whether a driver may remove only its own review hold. Second, whether engineers get alerted when Clara correctly holds back a message. Third, whether Smith's worker moves to a newer Temporal version. Each answer either lets an approved fix merge or decides a follow-up.

0 of 3 answered

1agent-harness#1859 narrows Gera's CLAUDE.md line "a hold label a BOT applied is yours to settle and lift": a driver may lift only its OWN hold, and only after the cross-reviewer gives ROOT + low/med. Lifting any other bot's hold is never auto-released and needs a person to merge. Keep that narrowing?

In plain terms. Should a driver be allowed to remove only its own 'hold for review' label, and only after the reviewer approves? The agents and Gera share one GitHub account, so 'a bot added it' can't be checked; this changes a rule Gera wrote.
Why the raiser recommends it
The session raising this recommends: Yes: a driver lifts only its own hold
GitHub can't tell an agent from Gera (every label event is gera-propflow), so 'a bot applied it' can't be checked; the reviewer's record can. Trinity graded #1859 ROOT/med.

2When the follow-up gate deliberately stops an APPROVED held message (because the lead was just contacted), should that still post to #alerts for engineering, or only post the plain-words 'not sent' note to the team?

In plain terms. Should engineers still get an alert when Clara correctly holds back a message because the lead was just texted? The property team already gets a plain-words note.
Why the raiser recommends it
The session raising this recommends: Team note only, no engineering alert
The decider split on option order (receipt f8f6d7d50). The #alerts charter (Fede, 09-03) is infra failures the team wasn't told about; since propflowai#24678 the team is told, and the gate fails open on errors, so this code is always a deliberate product stop.

3A Temporal core-SDK bug (sdk-rust#1146, unfixed upstream) wedged one Driver watcher tonight; I recovered it by hand. The decider recommends upgrading temporalio 1.30 to 1.34+ on the Smith worker (it eases the worker overload that triggers the bug), gated by a replay test against saved histories. It's infra with a non-clean rollback across ~1,300 running workflows. Go?

In plain terms. Should Smith's worker move to a newer Temporal version to make tonight's frozen-tracker bug rarer? Switching versions under about a thousand running jobs is hard to undo, so this needs Gera's OK.
Why the raiser recommends it
The session raising this recommends: Yes: upgrade, behind a replay test
Decider receipt f9a77430d: 1.33/1.34 fix the queue starvation that triggers it; the replay test already exists to extend. Raised to Gera because rolling the SDK back under running workflows isn't clean (CLAUDE.md: infra blast radius).
Why, and what was tried
Tried first, unsuccessfully: q1: not sent to the decider (changes Gera's own CLAUDE.md rule, out of plan). q3: fable-decide f8f6d7d50 NEEDS HUMAN (the reversed passes disagreed). q5: fable-decide f9a77430d resolved 'upgrade behind a replay test', escalated because rollback under running workflows is not clean (CLAUDE.md infra risk).

4f481092 is parked on this.

Pick an option above, then press Done.
PropFlow Docs