Add automation status surface

SCOPE.md

@@ -90,6 +90,9 @@ The two evaluation modes:
 - **REST admin API** (FastAPI): CRUD for ActivityDefinitions, manual trigger,
   event type registry queries.
 - **Prometheus metrics**: Temporal SDK metrics exposed for scraping.
+- **Automation status surface**: deterministic, non-LLM status reporting via
+  `make automation-status` / `scripts/automation_status.py`, using repo-owned
+  evidence sources rather than coding assistant scheduler state.
 - **Operational runbook**: `docs/runbook.md`.
 
 ---
@@ -116,6 +119,10 @@ The two evaluation modes:
   runs on Railiance infrastructure (or Docker Compose for dev).
 - **End-user task UI** — tasks land in issue-core; presentation is separate.
 - **Synchronous request-response patterns** — Temporal is async-first.
+- **Coding assistant automation infrastructure** — assistant-provided reminders,
+  heartbeats, or scheduled jobs are not the execution or evidence authority for
+  activity-core automations. Assistants may run and summarize repo-native
+  commands only.
 
 ---
 
@@ -132,6 +139,8 @@ The two evaluation modes:
   commands.
 - You are replacing scattered bespoke cron jobs and manual coordination with
   a governed, observable automation layer.
+- You need to answer "how did our automations go since Friday?" from
+  deterministic repo-native evidence before any optional LLM summary.
 
 ---