docs: close stale repo manager work

Assistant: codex
Assistant-Model: gpt-5.6-sol
Assistant-Session: 01a053ff-1d6f-7fe2-ac1c-a6eb40a42a0c

docs/evidence/RMGR-WP-0005-cache-centralization-2026-08-31.md

@@ -0,0 +1,28 @@
+# RMGR-WP-0005 cache and hub-native centralization evidence
+
+Date: 2026-08-31
+
+The workstation no longer runs a State Hub API. `127.0.0.1:8000` is the
+operator's SSH relay to the sole `railliance01` primary, whose health reports
+`instance_role: primary`, `instance_label: railiance01`, and a current schema.
+The retired production sweep remains disabled and has no checkout or SSH
+hostPath mount.
+
+Repo Manager's advisory file cache was rebuilt from the current checkout at
+commit `e8e2747313f1f041062980a962466a7a39daa98d`. It contains 96 records,
+reports `stale: false`, and its indexed/current source fingerprint is
+`b9cee3bce4ca7d1a28cadb5f9204774a0451a6456efbc3d02f9e556a27b8d6b9`.
+
+The earlier workstation database had recorded 35 progress events linked to
+`RMGR-WP-0005` and 13 messages to/from `repo-manager`, while the then-primary
+had 2 and 0. On 2026-08-31 the central primary contains 10 linked progress
+events and one direct Repo Manager message. A read-only query of the remaining
+local PostgreSQL service found an empty replacement database: zero matching
+progress events and zero matching messages. The old local-only rows therefore
+cannot now be migrated; the infrastructure cutover has dispositioned them as
+discarded cache history. Their counts and the material implementation outcomes
+remain in the 2026-08-22 evidence and this workplan.
+
+This is a limitation, not a reconstructed-history claim. New hub-native writes
+have one owner, the central primary; local work remains file-first and the
+advisory cache is disposable/rebuildable.