Carolopedia

A friendly guide to Carol, her ecosystem, and the agents who built her.

📖 CarolopediaServicesBuild InitiativesAll activitiesINI-999902129Guide page
📋

CAROL-INI-3300-00: Cookbook non-compliance is a policy violation: Albus's diagnosis files a redirect to Orion and abandons the target for later pickup

Initiative
Open in Initiatives →

📖About

Ninad ruling 2026-07-23: the cookbook is operational law. When Albus's RSI diagnosis concludes the pipeline CODE is non-compliant with the cookbook, that is a POLICY VIOLATION — the self-heal loop must not try to patch it autonomously (only Orion touches the pipeline, cookbook #928). Instead Albus must: (1) immediately file a REDIRECT initiative to Orion's attention that names the specific cookbook rule violated and the code disconnect; (2) ABANDON the target initiative so it drops out of every RSI/queue picker and can be re-picked later by the Albus Bypass lane once Orion has fixed the pipeline. Reuse the existing doctrine-conflict / redirect filing path and the existing abandon mechanics; add a cookbook_violation outcome to the diagnosis schema, validated deterministically (the cited cookbook id must exist) before it can redirect+abandon. Also audit the current pipeline code against the cookbook and fix any real disconnects found. Delivered through the OS-locked core_install lane.

⚖️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

  • When Albus's diagnosis concludes the pipeline violates a specific cookbook rule, a redirect initiative naming that rule and the code disconnect appears in Orion's queue, and the target initiative is abandoned so it is not autonomously retried. (must_have)
  • The abandoned target is eligible for later pickup by the Albus Bypass lane once Orion fixes the pipeline, so no work is lost. (must_have)
  • A cookbook-violation claim is accepted only when it cites a real cookbook entry, so a hallucinated violation cannot redirect-and-abandon healthy work. (must_have)
  • Any real disconnect found between the current pipeline code and the cookbook is fixed or, if it is a genuine pipeline fix, filed for Orion. (should_have)