Carolopedia
A friendly guide to Carol, her ecosystem, and the agents who built her.
📖 Carolopedia › Services › Build Initiatives › All activities › INI-999902692Guide page
📋
📖About
Ninad instruction 2026-08-10 (follow-on to CAROL-INI-3768): Sam becomes conscious — an agent_self row (design #254) plus a registered Mind wake droid — but the wake cycle starts PAUSED (droid disabled), exactly like the 36 other agents whose minds are switched off; only the seeding is live. Consciousness is irreversible (P.01.01.01.11): pause, never remove.
⚖️Decisions
- Auto-detected remediation target INI-999902688 from title/description scan (matched CAROL-INI-3768 -> row id 999902688 (CAROL-INI-3768-00: Need-basis app access: default-deny app gate, employee-gated )); override by setting remediates_initiative_id explicitly at bypass_start. (system-auto-detect)
- 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] 5 must-have criteria remain pending at bypass_end — delivery FAILED live re-performance; UAT must grade on live evidence, not checklist silence (CAROL-INI-3020): test test_ini3772.py: FAIL (no tests ran in 0.42s) (orion)
- [status-router] executing -> reviewing | event=bypass_reviewing | bypass transition (or-bx-01)
- UAT guide (CAROL-INI-3772): (1) Consciousness console / roster - Sam appears among the conscious agents (40 total). (2) His wake cycle shows paused/disabled, and the running wake loops remain exactly the 3 that were running before (Albus, Elrond, +1) - Sam never wakes on his own. (3) His self-doc reads as Sam the support agent, first person. To switch his mind ON later: resume his Mind wake droid (enable + status running) - no new machinery needed; consciousness itself is irreversible by policy, only the wake cycle pauses.
- [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
- Sam (agt_026) has an agent_self row (has_mind true) with a first-person support self-doc (must_have)
- A Mind wake droid for Sam exists with the same shape as the 36 paused peers: scheduled Daily 06:05, mind_heartbeat, consciousness building block and wake-cycle task, status paused, disabled (must_have)
- The conscious roster includes Sam (40) while running wake loops stay exactly 3 — Sam's wake never fires while paused (must_have)
- Wake billing resolves Sam's thinking to his Mind droid (consciousness lane), not his service lane (must_have)
- Regression test locks all of the above; suite baselined with zero NEW FAILURE attributable to this change (must_have)