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.

1

In plain terms. Clara sometimes tells tenants she'll personally follow up with a time, even at buildings that are supposed to run with no human backstop to make that promise true — can I fix the wording in her instructions so she stops doing that, and prove it works before asking anyone to merge it?

The full question, as raised

Clara's maintenance prompt has a self-contradiction: the always-on SCHEDULING & ACCESS block (agents/clara/lib/agent/clara-maintenance.ts:299, plus FRUSTRATED-TENANT worked examples at :349-358) instructs Clara to promise a personal follow-up/time ('I'll let you know as soon as the handyman's timing is confirmed', 'I'll confirm the time with you shortly', 'I'll page someone on-call'), while RULE 7.8 (:54-75, appended only when a property is handoffMode=autonomous, wired at :467) explicitly forbids those exact phrases because an autonomous property has no human backstop to make the promise true. The Willows (appfolio-45), the Morpheus eval bench property, IS configured handoffMode=autonomous with maintenance autonomy on (confirmed via a live propflow-prod read) — so RULE 7.8 should be firing, but Clara is still using the forbidden promise language. That's why morpheus-nightly's gen-i3-pivot-ambiguity-sink-leak-pooling scenario has failed its final checkpoint 7 of the last 9 nights (Oct 4,5,6,8,9,10,11,12; passed once on Oct 7). This is a real prompt bug, not eval noise, not a settings/wiring bug, and not a new product question — RULE 7.8's no-promise policy for autonomous properties is already agreed company doctrine; an earlier, more vivid, concrete instruction is undermining it. I checked 3 prior resolved decisions on this same morpheus/gen-i3 alert cluster (none cover this specific contradiction) before raising. Proposed fix: gate the 'YOU OWN THE FOLLOW-UP' line (:299) and the two forbidden-phrase worked examples (:349-358) behind !opts.autonomousHandoff, so an autonomous property's prompt never shows Clara language RULE 7.8 forbids a few hundred tokens later. Per the standing rule that prompt/behavior changes get verified before a PR exists, I have not written or opened anything — I'd prove the fix passes this golden scenario via morpheus-run-one's --report-only (prove-before-approve) lane, then open a PR for human review/merge (this touches live Clara behavior, so it's a human-merge PR either way).

Fix it now, prove it works, then ask to mergethe raiser's pick Hold off — I'll look at it myself I'm not sure — go find out Take it to the engineering bridge

Why, and what was tried

The session raising this recommends: Fix it now, prove it works, then ask to merge
RULE 7.8's no-promise policy for autonomous properties is already settled company doctrine; this is a bug undermining an existing rule, not a new product call, and it likely affects real autonomous-property tenants too, not just the eval.
Tried first, unsuccessfully: Read 9 nights of morpheus-nightly transcripts for this scenario, pulled the golden scenario definition and its exact judge expectation, traced the real Clara maintenance prompt file, confirmed via a live propflow-prod read that the bench property is handoffMode=autonomous with maintenance autonomy on, checked blocked outstanding + 3 prior resolved decisions on this alert cluster to avoid re-raising a settled question, and read git history on the maintenance prompt (PR #16195, Oct 4) to rule out a clean one-commit regression.

f4bd935a is parked on this.

Pick an option above, then press Done.