📖About

The premise re-validation gate (CAROL-INI-2032/2090) only re-checks WATCHER HEALTH ALARMS. Old normal initiatives (e.g. INI-9, filed long ago) are never re-validated for relevance before dispatch. Build a genuine staleness/relevance check that runs on EVERY initiative at queue entry: relevance_status(initiative_id) reads the initiative intent + success criteria + age + recent decisions + recently-closed initiatives (superseded signal) via the relay, and asks the on-VM LLM (call_claude) for a CONSERVATIVE verdict — stale (clearly already-done / premise gone / superseded) vs valid vs uncertain; defaults to valid unless clearly stale. autoclose_if_stale(initiative_id) closes a stale one via Elrond's existing close path — shared.status_router.route_status(.., 'closed', actor='ds-s1', event='stale_irrelevant', ..) — NOT a parallel closure; fail-open (any error never closes and never blocks dispatch). Wire it into the dispatcher enqueue() right after the premise auto-close (CAROL-INI-2090) so queue membership now means BOTH checks passed. cookbook + regression. Then run the 3 already-queued initiatives (9/14/15) through it; they should stay open (still relevant).

⚖️Decisions

• Elrond's bypass methodology checklist (a reminder, not a gate -- you've got this): 0. File it requested_mode='bypass' (planner-vs-bypass is a deliberate choice). bypass_start REFUSES a non-bypass initiative (CAROL-INI-1846), and the dispatcher only skips the bypass lane when the mode says bypass -- a 'planner' mistag lets Merlin's pipeline grab the placeholder step and block your finished work. 1. Filed as planned status -- let the bypass claim/activate it; never file active. 2. Open the bypass (bypass_start) with your droid id + the remediation answer (remediates_initiative_id=NNN, or remediates_nothing=True). 3. Work the blocks for your work-type: template -> design -> code -> test -> review. Do the real work; record decisions on the initiative as you make them. 4. Reality is recorded for you at close -- code (files changed), each decision, and the twin-review verdict become real activities tied to this initiative and show in the Activity Tracker like a planner run (CAROL-INI-1840). No dummy rows. 5. Keep the initiative status moving; it parks in 'reviewing' and is tagged uat-pending for you at close (CAROL-INI-1836), so the stuck-watchdog leaves it alone until UAT. 6. Close runs the gates (design/architecture compliance + caller-audit). If a gate flags something pre-existing or unrelated to your change, waive it with a clear written rationale -- audit, don't skip. 7. Bypass skips the planner's auto-orchestration, NOT the standards. Same template checklist, same review, same observability as a planner run. (elrond)
• [status-router] planned -> executing | event=bypass_executing | bypass transition (or-bx-01)
• [status-router] executing -> reviewing | event=bypass_reviewing | bypass transition (or-bx-01)
• [status-router] reviewing -> closed | event=operator_signoff | Auto-accepted (CAROL-INI-1859): Orion-initiated, >2 days in reviewing with no objection. (el-srac-01)

✅Success criteria

• relevance_status runs an LLM judgment (intent + criteria + age + superseded signal) returning stale/valid/uncertain, conservative, fail-open (must_have)
• autoclose_if_stale closes a stale initiative via the status router (event=stale_irrelevant), not a parallel closure; fail-open (must_have)
• The staleness check is wired into enqueue() for every initiative, running after the premise check, so queue entry requires both (must_have)
• The 3 already-queued initiatives (9/14/15) are run through the staleness gate and the verdicts reported (must_have)