📖About

Ninad ruling 2026-08-03 (CLI-221), three parts. (1) NO GUESSING: which subscription pays for a piece of work is read from its TRACK, which carries the subscription label. Observed past calls are never consulted - a track's subscription can be re-tagged at any time, so historical calls carry no decision meaning. No label means the work reads UNALLOCATED; it is never filed under a subscription by fallback. This is P.01.03.07.06 applied to the surfaces: the fleet default is a migration crutch and nothing may be designed to rely on it. (2) MEASURED DEFECT: the intelligence page derives placement from observed calls, so a block with no recent calls falls into the fleet's box. It pays for none of them. (3) THE RECORD CANNOT SAY 'EXEMPT': every track must name a provider, so lanes on a FLAT subscription were given a metered provider's name. MEASURED: of 36 tracks, exactly 2 are budgeted zero, and both are mislabelled - the operator CLI lane (budget record says EXEMPT, flat Claude Max, Ninad 2026-07-30; provider label says deepseek) and the superseded media track. The track record gains a way to say flat-and-not-metered, so an exempt lane stops borrowing a metered provider's name and can never be read as spend against it. NOT A LABEL AUDIT: the labels are otherwise sound - written across 15 separate dates over two weeks, individually, and all 36 tracks carry a budget 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)
• [delivery-check] 4 pending must-have criteria stamped met at bypass_end on live re-performance evidence (CAROL-INI-3020): test test_ini3641.py: PASS (12 passed in 1.92s) (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

• (must_have)
• Work whose track names no subscription appears in a place of its own marked unallocated, and is never shown inside a subscription that is not paying for it. (must_have)
• The operator's own CLI lane reads as a flat subscription that is exempt from metering, instead of borrowing the name of a metered provider it does not use. (must_have)
• Every surface that groups work by subscription tells the same story, so the cost tracker and the budget monitor can no longer disagree with the intelligence page about who pays. (must_have)