📖About

Ninad ruling 2026-08-09: any action an agent takes must follow the pipeline approach so it is filed, reviewed and auditable. A registered WHITELIST names the tasks a conscious agent may perform directly on its own authority; it starts EMPTY and only the operator widens it. Register the policy, create the whitelist store in the registry (empty), and wire the wake deliberation so an action outside the whitelist is routed as a filing request/escalation, never performed directly.

⚖️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)
• [orion] Whitelist gates only work-DOING actions (dispatching droids, enqueueing builds). Asking actions — escalate, wake a peer, wish, post a decision, request a filing — stay free: they are how work is routed INTO the pipeline, and gating them would leave a refused agent no way to ask. Whitelist is fail-closed (unreadable = empty) and read live at every wake; refusal is visible on the wake record, never a silent fallback. — Ninad ruling 2026-08-09: actions follow the pipeline for audit purposes; whitelist born empty. Policy P.01.03.01.09; enforcement in the Mind action layer. (orion)
• [delivery-check] 4 pending must-have criteria stamped met at bypass_end on live re-performance evidence (CAROL-INI-3020): test test_ini3747.py: PASS (7 passed in 0.36s) (orion)
• [status-router] executing -> reviewing | event=bypass_reviewing | bypass transition (or-bx-01)
• [status-router] reviewing -> blocked | event=reviewer_verdict | bypass twin reviewer verdict != pass (CAROL-INI-2039) (orion)
• [status-router] blocked -> reviewing | event=operator_reopen | Operator revive after rework in place (doctrine 2947): twin review re-run post evidence recording, verdict PASS (or-rv-01, 10 checks 0 failing). Awaiting UAT. (orion)
• [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

• A policy is registered in the policy register: every agent action follows the pipeline approach for audit purposes; the whitelist is the only exception and Themis/operator govern it (must_have)
• A whitelist store of self-performable tasks for conscious agents exists in the registry, starts empty, and is read (not hardcoded) by the wake (must_have)
• Wake deliberation instructions carry the directive: an action not on the whitelist routes through the pipeline (filing request / escalation), never performed directly (must_have)
• Regression test asserts: policy registered, whitelist empty at birth, wake instructions name the policy (must_have)