📖About

Ninad 2026-08-03, exact format. One report PER AGENT per day, shaped like a report: Date; Service name; Track name; Agent name; planned budget (total); actual budget (total); status Red/Yellow/Green based on tasks completed tasks completed - Own tasks (blanket description + actual items) and Reportee tasks (blanket description + actual items); risks & issues if any + comments; tasks planned for next day - own and reportee blanket descriptions. Reportee rollup follows the reporting line (supervisor sees everything below, P.01.03.05.09). RAG definition registered in the data dictionary. NOTE: the status-report app is currently DOWN (connection refused) - per report-before-fix, first close the monitoring gap that let it be down silently, then restore and rebuild on the new format.

CORRECTION 2026-08-03: the app is NOT down - it was up and healthy the whole time (health endpoint answers ok). The recon instrument was wrong: it searched processes by the app's name, but the app runs under a bare uvicorn command line. The report-before-fix clause is therefore moot; scope is the new per-agent report format only.

⚖️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 status-report app is registered but currently down (connection refused), and the monitoring gap has not been closed yet. Related completed initiatives provide shared task-source and supervisor-rollup groundwork, but the new per-agent daily report format with RAG, planned/actual budgets, risks, and next-day plans is not yet delivered. (elrond)
• [status-router] planned -> executing | event=bypass_executing | bypass transition (or-bx-01)
• [status-router] executing -> reviewing | event=bypass_reviewing | bypass transition (or-bx-01)
• uat_comment — Ninad UAT 2026-08-03: the Agent reports tab must be a CARD per agent, each card carrying the agent's picture; clicking a card opens that agent's report for the day. Reworked in place (attempt 2). (ninad)
• [status-router] reviewing -> executing | event=bypass_executing | bypass transition (or-bx-01)
• [status-router] executing -> reviewing | event=dispatcher_transition | dispatcher state change (ds-s1)
• [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

• Status Report renders one report per agent per day with exactly: date, service, track, agent, planned budget total, actual budget total, RAG status, tasks completed (own + reportee, blanket + actual items), risks & issues + comments, next-day planned blanket tasks (own + reportee) (must_have)
• Reportee tasks roll up strictly via the registry reporting line (must_have)
• The status-report app serves the new per-agent report at its existing address (app verified UP 2026-08-03; the earlier 'down' finding was a wrong instrument) (must_have)
• Report data comes from the one shared composer (same numbers as Task Tracker) (must_have)