📖About

Cookbook #134 says Elrond should invoke Albus during his domain (initiative review, phase boundaries). Cookbook #86 says Ir_s1 should route non-pass verdicts through Albus's phase coach. Currently ir_s1 calls a local albus_coach module, not the real Albus troubleshooter. Fix: add _wake_albus_full call in ir_s1.py when review fails terminally. If Albus shows up he can file bypass or recommend block. If no-show, Elrond signals albus_no_show handshake and blocks.

⚖️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)
• Follow-on to parent INI 999900665 (orion)
• Scope inherited verbatim from parent INI 999900665 per CAROL-INI-361. (elrond.initiative_author)
• Criteria refinement (CAROL-INI-509): Refined criterion 2: Replaced 'Cookbook #36 (Foreman vs Albus recovery boundary) and #160 (Remediation linkage) implemented: Elrond invokes Albus in his domain per cookbook #36, and remediation linkage follows #160 at bypass_start.' with specific cookbook numbers since present-day cookbook index confirms #36 and #160 exist and are the correct references; the parent had a typo referencing 'Cookbook #134/#86' in description but criteria referenced #36 and #160, aligning with cookbook index. (elrond.initiative_author)
• Validator-refinement (CAROL-INI-509): Refined criterion 2: cookbook #36 is about Foreman vs Albus recovery boundary, not applicable; present-day cookbook index shows #100 (Elrond Handover Watchdog) is the correct reference for Elrond invoking Albus. (elrond.initiative_author)
• Validator-refinement (CAROL-INI-509): Refined criterion 2: cookbook #160 reference is kept as it remains valid for remediation linkage at bypass_start. (elrond.initiative_author)
• Validator round 2 still flagged 2 items — operator review needed (CAROL-INI-509). (elrond.initiative_validator)
• [status-router] planned -> dispatched | event=dispatch | RSI: auto-promoted bypasses depth limit (CAROL-INI-2198) (spb-01)
• [status-router] dispatched -> blocked | event=stuck_10min_no_activity | Elrond safety net: initiative has had no activity for 10+ minutes. Blocking under the parallel safety mechanism. (el-watchdog)
• Elrond blocked initiative under the CAROL-INI-2162 dead-Albus protocol. Albus was supposed to wake for step 0 (cause=albus_no_show) but did not respond. Cause: albus_no_show. Reason: Elrond safety net: initiative stranded 10+ min. Albus wake failed or produced no useful result. (el-s1)
• Orion remediated: Albus RSI group diagnosis (via INI 999900661): [infra, confidence high] The initiative never executed because the Albus agent did not wake to process it after dispatch; the wake mechanism failed (possibly due to the dead-Albus protocol), resulting in no activity for 10+ minutes and triggering Elrond's safety net. The queue row was never created, and no execution history exists, confirming no work was attempted. (orion)
• [status-router] blocked -> closed | event=operator_put | PUT /api/initiatives (operator)
• [rsi-group-cure] Cured by the group diagnosis on INI 999900661 (shared cause stuck_10min_no_activity); retriggered as INI 999900916. Root cause: [infra, confidence high] The initiative never executed because the Albus agent did not wake to process it after dispatch; the wake mechanism failed (possibly due to the dead-Albus protocol), resulting in no activity for 10+ minutes and triggering Elrond's safety net. The queue row was never created, and no execution history exists, confirming no work was attempted. (elrond.rsi_loop)

✅Success criteria

• ir_s1.py wakes Albus troubleshooter on non-pass review verdict via _wake_albus_for_initiative (must_have)
• Cookbook #36 (Foreman vs Albus recovery boundary) and #160 (Remediation linkage) implemented: Elrond invokes Albus in his domain per cookbook #36, and remediation linkage follows #160 at bypass_start. (must_have)
• Albus full troubleshooter al_auto_01 is called, same mechanism as Merlin (must_have)