📖About

Clara owns 10 apps but her service-scoped chat grounding (CAROL-INI-3366) only wires 4 sources (registry structure, sst, carolopedia, roadmap). So she cannot answer questions from the data behind the rest — e.g. 'which agent did the most tasks today', which lives in Carol's Org task board (org_tasks.agent_tasks). This wires every app Clara owns that has a queryable data source into her grounding, adds the org task board + activity ledger + data dictionary, and resolves agt_NNN ids to names on results. Read-only, fail-open, kill-switch intact.

⚖️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): Clara's service-scoped chat has grounding wired for registry structure, SST, Carolopedia, and roadmap only. Carol's Org task board, activity ledger, Data Dictionary, and other registry-backed apps are not yet integrated. The kill-switch and fail-open behavior are already in place from the prior grounding (CAROL-INI-3366). (elrond)
• [status-router] planned -> executing | event=bypass_executing | bypass transition (or-bx-01)
• Grounding maps each owned app dir_name to a LIST of (db,schema) sources so one app can back several data sources. Carols Org now grounds on the agent-task board (org_tasks.agent_tasks) + the per-run activity ledger (heartbeat_runs.agent_activities) in addition to the registry; Data Dictionary grounds on data_dictionary. Added an agt_NNN to name resolver on result rows. who did the most today is steered to the activity ledger (task board is mostly planned rows). (orion)
• [delivery-check] 3 must-have criteria remain pending at bypass_end — delivery FAILED live re-performance; UAT must grade on live evidence, not checklist silence (CAROL-INI-3020): test test_ini3372.py: FAIL (no tests ran in 0.20s) (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 'which agent did the most tasks today' from Carol's Org task board, naming the top agent(s) with a count, using agent names not raw agt_NNN ids. (must_have)
• Every app Clara owns that has a queryable data source is wired into her grounding (Carol's Org task board + activity ledger, Data Dictionary definitions, and her registry-backed apps), not just registry/sst/carolopedia/roadmap. (must_have)
• Grounding remains read-only, fail-open, with the CAROL_CHAT_GROUNDING_OFF kill-switch intact, and a regression test proves the new org-tasks wiring and the agt_NNN to name resolution. (must_have)