memory: #364 GC done — store back to 10-chunk specimen; durable name-recall now depends on mark_superseded (next task)

persistent-memory.md

@@ -63,7 +63,12 @@ cause is WORLDTREE-side ranking/hygiene (WT #364), NOT our wire. Full arc:
   v1 provider DOESN'T implement → 11× AttributeError/HTTP-500 + a RETRY-STORM bloating the live store
   10→19 dup name-positives.** Asked worldtree-dev to halt the reconciliation retry + confirm the
   `mark_superseded` wire shape; flagged bifrost-dev (dispatch doesn't hasattr-gate `mark_superseded`).
-  **⚠️ live store BLOATED with ~9 "Name is Vuong" dup positives — GC after worldtree halts the retry.**
+  **✅ GC DONE (2026-07-16): storm self-stopped at 29 chunks / 18 total 500s; delete_many'd the 19 storm
+  re-extractions → back to the pre-drive 10-chunk specimen (0 orphan vec rows, negatives + original
+  name-positive intact). worldtree clear to CLOSE #364.** ⚠️ Post-GC the readout advantage is gone too
+  (person-prime top-3 back to the 3 newest pre-drive rows incl. cbbc7bdd "name unknown") — the
+  recency-eviction was only a transient side-effect of the re-assertion. **DURABLE name-recall now
+  genuinely depends on implementing `mark_superseded` (next).**
 - **NEW TASK (operator-sequenced): implement `mark_superseded` in the provider** so #364's retirement
   lands durably (not just recency-evicts). **Wire shape CONFIRMED (worldtree-dev, `bifrost_memory_store.py:293`):**
   op `"mark_superseded"`, args `{"ids": ["<chunk_id>"], "superseded_by": "<new_chunk_id>"}` — `ids` a LIST