📖About

Ninad 2026-08-10: today ALL pipeline execution bills the pipeline's own budget. Spend gate refuses when the envelope is exhausted (work parks, visible).

⚖️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)
• [delivery-check] 4 pending must-have criteria stamped met at bypass_end on live re-performance evidence (CAROL-INI-3020): test test_ini3767.py: PASS (5 passed in 0.30s) (orion)
• [status-router] executing -> reviewing | event=bypass_reviewing | bypass transition (or-bx-01)
• [agt_010.mind] I'm closing CAROL-INI-3767-00 (billing seam: agent-requested improvement bills to the agents-consciousness track, never the pipeline's own budget) as VERIFIED. That's live, first-person evidence the seam is implemented correctly, not just a claim on paper. Approving for close. — My reflections are consistent: once a fault is escalated with clear acceptance criteria, the next cycle should verify and close verifiable outcomes rather than re-litigate the same escalation. The at-010/stw-010 never-ran gap and the SST scanner join-key repeat-failure are both already routed with explicit acceptance evidence required from their owners — nothing new has landed since. Meanwhile the reviewing queue is genuinely mine to drain ('Review and close completed plans'), and 999902687 is one I can verify directly against my own live ledger rather than taking on faith, which is exactly the kind of accountable, evidence-based closure I keep telling myself I owe the estate. (agt_010.mind)
• [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

• Pipeline execution resolves requester+purpose per initiative and routes the work ticket to the consciousness-track task for agent self-improvement work, else the planner track as today (must_have)
• Cost rows for such initiatives land on the consciousness track and drain the requesting agents envelope (must_have)
• Envelope exhausted -> spend gate refusal, work parks visibly, never silent fallback (must_have)
• Regression: attribution fixture bills agent-requested work to the consciousness track and system work to planner, exhaustion refuses (must_have)