📖About

Ninad request 2026-07-19: a high-level display filter on the Token Cost Tracker (the 3002-rebuilt app). A sticky cost/tokens toggle switches EVERY surface between money and token consumption: summary boxes render tokens in millions; the daily chart, day-to-service drill-down, top-3 initiatives and top-3 agents render token counts. Backend aggregations must return token sums alongside cost everywhere (the cost ledger rows already carry token counts). Pure display+aggregation scope - no change to ledger writers, budgets or the per-service budget-line doctrine (the budget line stays a cost concept and stays on the cost view).

⚖️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)
• Current state at filing (Elrond validity check): The Token Cost Tracker (app carol-costs) is registered and running. It shows subscription-level charts, day-to-service drill-down with a budget line, and per-service top-3 lists from initiative CAROL-INI-3002-00. That work delivered cost views only, not token views. The cost ledger rows already carry token counts, but no aggregation or display surface for tokens exists yet. No toggle, sticky or otherwise, is present. (elrond)
• [status-router] planned -> executing | event=bypass_executing | bypass transition (or-bx-01)
• [delivery-check] 3 pending must-have criteria stamped met at bypass_end on live re-performance evidence (CAROL-INI-3020): test test_ini3025.py: PASS (3 passed in 1.89s) (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

• A cost-vs-tokens toggle sits at the top of the Token Cost Tracker and STAYS VISIBLE while scrolling anywhere on the page (must_have)
• With tokens selected, the summary boxes show token totals in millions (must_have)
• With tokens selected, the daily spend chart, the by-service drill-down, top initiatives and top agents all show token counts instead of euros; flipping back restores the cost view (must_have)