📖About

Ninad ruling (CLI-243): the blueprint service must have exactly two tracks - experimentation and industrialization - replacing the single Core track. All five existing Core work units move to blueprint-experimentation (keys unchanged); industrialization starts with no tasks by operator choice and is flagged until Sage gives it work units. Both new tracks run Claude Fable under a fresh dated operator exception (the prior Fable exception expired 2026-08-09; Ninad re-ruled in session). New tracks inherit the switched-off state so the restructure moves no money. Core is retired per the manage-service-tracks skill: tasks first, blocks, budget allocation zeroed via the budget layer (history preserved under the blueprint-core key), then the track row.

⚖️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)
• probe
• Decision 101572 ('probe') was an endpoint connectivity probe made in error - disregard it.
• Task placement (Ninad, in session): all five Core work units move to blueprint-experimentation; blueprint-industrialization deliberately starts with NO tasks and stays unfunded until Sage gives it work units - task before work, the budget follows the task.
• Blocks (4) and glossary terms (3) follow the tasks to blueprint-experimentation; keys unchanged everywhere.
• Lane (Ninad, in session): both tracks declared claude/claude-fable-5. Applied BY HAND because the lane-switch engine is DESTROYED - shared/lane_switch.py was overwritten by a byte-identical copy of its own CLI in the 2026-08-06 02:00 auto-commit (7d37f01d7); the real engine exists in git (1c6644c4e). That is CAROL-INI-3694's deliverable and is reported to Ninad, not repaired here. Dated exception recorded in the lane-exceptions store until 2026-08-20, aligned with the estate-wide Claude posture re-decision; the live ringfence table already admits every blueprint droid since the 08-06 fleet move.
• Proof call OWED: the hand declaration cannot be proven with a real call while both tracks are switched off (the spend gate refuses by design, and off outranks the exception). The proof - one real call booking claude-fable-5 against blueprint-experimentation in the ledger - is due the moment Ninad switches blueprint on, and UAT should hold this initiative to it.
• [delivery-check] 6 must-have criteria remain pending at bypass_end — delivery has no mechanical re-performance lane; UAT must grade on live evidence, not checklist silence (CAROL-INI-3020): (no detail) (orion)
• [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

• The blueprint service has exactly two tracks, blueprint-experimentation and blueprint-industrialization, both owned by Leo, and the blueprint-core track row is gone while its key history in the budget ledger is untouched (must_have)
• All five former Core work units (blueprint.roadmap_entry, milestone_notice, open_question, feedback_applied, acceptance_verdict) sit on blueprint-experimentation with keys unchanged, owner Leo, and no source_spec payer naming a stale owner (must_have)
• Both new tracks are declared on Claude Fable through a dated operator exception recorded by the lane tooling, and the Claude reservation fence covers the declaration (must_have)
• Core's budget allocation is zeroed and disabled with its recorded history preserved, and the experimentation track carries the allocation for the five tasks with the amount unchanged from Core (amount changes remain Midas's call) (must_have)
• Any blocks parented on blueprint-core are reassigned to the new tracks, and before/after reference counts for every layer match so the move changed ownership, never linkage (must_have)
• Both new tracks inherit the switched-off state (spend gate refuses them) so the restructure itself moves no money, and a money surface shows the two tracks with Core gone (must_have)