coulomb/activity-core
4
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
activity-core/workplans/ADHOC-2026-08-20.md
tegwick ea6fb0e92a
All checks were successful
CI Smoke / host-smoke (push) Successful in 0s
Details
CI Smoke / container-smoke (push) Successful in 1s
Details
fix(workplans): qualify ad-hoc identifiers with the repository prefix 
`ADHOC-YYYY-MM-DD` is unique per date but not per repository, so any two repos
opening an ad-hoc on the same day collide. The 2026-08-26 fleet projection
reset refused 9 records for exactly this reason.

Canon (work-record-types_v0.1, CUST-WP-0066) settled the form as
`{PREFIX}-WP-ADHOC-YYYY-MM-DD`, filename unchanged, and grandfathered existing
ids on the condition they are never *silently* re-derived. This is the explicit
migration that clause allows for.

The hub id is derived from the record id, so a changed id is a different
record: stale state_hub_*_id fields are dropped and fix-consistency re-derives.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 2583210@bnt-lap001
Assistant-Session: f2bff2d5-e9b2-4338-92ca-10282a927006
2026-08-28 00:28:19 +02:00

1.6 KiB
Raw Blame History

id type title domain repo status owner topic_slug created updated
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

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.