📖About

Observed 2026-08-14/15 (CLI-255): the operator re-homed two filings to their raising agent via the identity-correction lane (3746). Within seconds of each PUT, Elrond's Initiative Reviewer opened a phase-2 review and returned verdict review_incomplete with EMPTY comments, and the bypass contract's up-or-out hold moved both initiatives to blocked - one of them two minutes after a clean close (twin PASS, review blocks with evidence on the record), the other while still planned with no build yet to review. Both holds were operator-revived the same night; decisions on 3745 and 3836 carry the trail. Two defects to cure: (1) an operator identity correction is a RECORD event, not a work event - it must not trigger a re-grade; (2) a reviewer verdict with no findings must be unauditable, never a block - the estate's own law says a verdict must be able to bite BOTH ways. Scope: the reviewer's trigger conditions and the empty-verdict guard; nothing else in the review chain.

⚖️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)
• [delivery-check] 3 pending must-have criteria stamped met at bypass_end on live re-performance evidence (CAROL-INI-3020): test test_ini3859.py: PASS (3 passed in 0.44s) (orion)
• [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

• An operator identity-correction PUT (new_requester/new_owner only) triggers NO reviewer re-grade: proven by re-performing the correction on a test filing and observing zero new review rows. (must_have)
• A reviewer verdict with no findings/comments is recorded as unauditable and never produces a hold or a status change - the block path requires at least one named finding. (must_have)
• The two false holds from 2026-08-14 are cited in the fix's regression test, which replays both trigger shapes (post-close correction, pre-build correction) and asserts no block results. (must_have)