Carol — back to Apps ← Apps

Carolopedia

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

📖 CarolopediaServicesBuild InitiativesAll activitiesINI-999900757
📋

CAROL-INI-0139-03: Retire legacy enablement droid via shim

Initiative
Open in Initiatives →

📖About

INI-029 attempt 8 (exec 363) failed because Merlin's escalate_albus path invoked the legacy enablement droid (al-en-01) which doesn't have the new structured verdicts from CAROL-INI-137/138. CAROL-INI-110 was supposed to retire the legacy 5-droid harness but al-en-01 survived because many callers (Forge, Argus, Sage, Merlin orchestrator/planner, Merlin watcher escalation) call al_en_01.enable() inline. This initiative replaces al_en_01 with a thin shim that delegates to Albus's autonomous troubleshooter (al_auto_01); updates Merlin's watcher to call al_auto_01 directly; updates registry + Design #146 + identity cards + cookbook to reflect the single-canonical-troubleshooter design. Also adds the cookbook #46 amendment for CAROL-INI-135 auto-retry unblock that was outstanding.

⚖️Decisions

  • Follow-on to parent INI 999900670 (orion)
  • Scope inherited verbatim from parent INI 999900670 per CAROL-INI-361. (elrond.initiative_author)
  • Validator round 2 still flagged 6 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 safety net blocked initiative: no activity for 10+ minutes. Parallel mechanism (twin of handshake). (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 999900502): [procedural, confidence high] The Albus executor did not wake to process step 0 of the initiative after dispatch (albus_no_show), leaving it idle with no execution history until the Elrond safety net blocked it after 10 minutes of inactivity. This is a procedural failure consistent with a systemic pattern where Albus fails to respond to dispatch events, as confirmed by the empty execution history and the dead-Albus protocol decision. (orion)
  • Orion remediated: Albus RSI group diagnosis (via INI 999900575): [procedural, confidence high] The initiative blocked because the Albus executor never received a proper activation signal (bypass_start was never called) after dispatch. The execution history is empty and the dispatch queue status is 'cancelled', consistent with the pattern in prior diagnoses where the operator failed to invoke bypass_start on bypass-mode initiatives, leaving the initiative stranded until Elrond's 10-minute inactivity safety net triggered. (orion)
  • [status-router] blocked -> closed | event=operator_put | PUT /api/initiatives (operator)
  • [rsi-group-cure] Cured by the group diagnosis on INI 999900575 (shared cause stuck_10min_no_activity); retriggered as INI 999900877. Root cause: [procedural, confidence high] The initiative blocked because the Albus executor never received a proper activation signal (bypass_start was never called) after dispatch. The execution history is empty and the dispatch queue status is 'cancelled', consistent with the pattern in prior diagnoses where the operator failed to invoke bypass_start on bypass-mode initiatives, leaving the initiative strand (elrond.rsi_loop)

Success criteria

  • The legacy enablement module delegates to the Albus troubleshooter (al-rsi-diag-01) and returns the legacy output shape. (must_have)
  • Merlin watcher escalate_albus invokes the Albus troubleshooter directly. (must_have)
  • Execute SQL: UPDATE droids SET status='superseded', superseded_by='al-rsi-diag-01' WHERE id='al-en-01'; verify row reflects change in registry.db. (must_have)
  • Cookbook reflects the single canonical troubleshooter; documentation covers the auto-retry unblock functionality. (must_have)
  • INI-029 attempt 9 reaches Albus via the new path and the structured verdict drives routing (not escalate_orion). (must_have)