activity-core/workplans/ADHOC-2026-08-20.md
tegwick 51689bf323
All checks were successful
CI Smoke / host-smoke (push) Successful in 1s
CI Smoke / container-smoke (push) Successful in 4s
chore(consistency): write back adhoc workplan hub id
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 241500@bnt-lap001
Assistant-Session: 4a77db80-b523-4a03-83c4-e3da08755c30
2026-09-21 14:13:07 +02:00

1.6 KiB

id type title domain repo status owner topic_slug created updated state_hub_workstream_id
ACTIVITY-WP-ADHOC-2026-08-20 workplan Ad hoc — activity-core opportunistic fixes 2026-08-20 infotech activity-core finished codex activity-core 2026-08-20 2026-08-20 3c871564-3da4-5980-a13e-8a6145a57619

ACTIVITY-WP-ADHOC-2026-08-20 — activity-core opportunistic fixes

Reconcile the daily TODO review sink warning

id: ACTIVITY-WP-ADHOC-2026-08-20-T01
status: done
priority: low

The projected daily-todo-md-stale-review definition still said that IssueSink defaulted to rest and that re-enabling the definition would unconditionally recreate Forgejo issues. That warning described the state before ACTIVITY-WP-0022 and contradicted the current code, deployment configuration, and weekly-sbom-staleness definition.

Correct the warning to state that ISSUE_SINK_TYPE=state-hub is the safe fleet default, rest is explicit opt-in, and State Hub progress is visibility rather than claim authority. Keep the schedule disabled so a documentation correction does not silently change production cadence, and document the operational checks needed before it is deliberately re-enabled. Add a projection test so the stale default rest claim cannot recur unnoticed.

Verification:

  • Focused regression and IssueSink tests: 7 passed.
  • Full suite: 342 passed, 1 skipped, 4 failed. The four failures are unrelated existing inconsistencies: rules boundary allowlisting, the State Hub image pin assertion, a schedule-health response double missing status_code, and the sync-service expectation omitting the returned errors count.