📖About

Raised by Ninad (2026-08-15): Clara (CEO) cannot answer 'how many tasks are there in the estate in total' - she first invented 26,568, then fell back to the 117 rows of the org ASSIGNMENT board in her reporting scope. Root cause is wiring, not the agent: the chat grounding's registry schema text describes agents/apps/services/blocks/policies/geography but says NOTHING about service_tracks or service_work_units - the estate's task registry (rule 1199: TASK = the planning record that carries a budget). The SQL generator cannot query a table it was never told exists, so it routed the question to the org task board instead. True figure tonight: 140 work units on the registry. Cure: describe service_tracks and service_work_units in the registry grounding schema with the task/track/service language of 1199, including how to count tasks estate-wide and per service/track, so EVERY agent grounded on the registry (not just Clara) answers task and track questions from the one source. No surface-local counting logic - the SQL reads the registry directly (one counter, rule 937).

⚖️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 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

• Clara's chat answers the estate-wide task total from the registry's service_work_units (grounded SQL, not guesswork), matching the live registry count (must_have)
• The registry grounding schema describes service_work_units and service_tracks including their join and the active flag, in rule-1199 task/track vocabulary (must_have)
• Track-level and service-level task questions (how many tasks on track X / service Y) generate correct registry SQL (must_have)
• A regression test asserts the schema text names both tables so a future edit cannot silently drop them (must_have)