memory: #364 re-verify DONE — readout passes (Sindra recalls name) but supersession 500s (mark_superseded unimpl'd); new task + retry-storm flagged
This commit is contained in:
+12
-4
@@ -55,10 +55,18 @@ cause is WORLDTREE-side ranking/hygiene (WT #364), NOT our wire. Full arc:
|
||||
`persistent-memory.d/2026-07-16-person-prime-scan-shipped.md`.
|
||||
|
||||
**Standing — awaiting two peer-initiated touchpoints (both monitored):**
|
||||
- **WT #364 re-verify** (worldtree-initiated): when the name-recall fix deploys (= `(subject,relation)`
|
||||
slot-supersession + identity-tier surfacing, shaped by our specimen), worldtree-dev sends a
|
||||
re-verify request → re-drive the same bound-Sindra turn against :8081, expect "Name is Vuong"
|
||||
to inject. **Keeping the live 10-chunk store UNTOUCHED as the re-verify target** (no cleanup).
|
||||
- **WT #364 re-verify DONE (2026-07-16, b103) — READOUT PASSES, but a real gap surfaced.** Drove 3
|
||||
"my name is Vuong" turns; person-prime turn-1 top-3 is now all name-POSITIVES (no "name unknown"; the
|
||||
true name even surfaces) → **Sindra recalls the name now**. BUT "wrong readout gone" is via **RECENCY
|
||||
EVICTION** (promotion re-upserted the positive fresh into the window), NOT supersession — the negatives
|
||||
are UNCHANGED (governance=available). **#364 calls `mark_superseded` on the consumer store, which our
|
||||
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.**
|
||||
- **NEW TASK (operator-sequenced): implement `mark_superseded` in the provider** so #364's retirement
|
||||
lands durably (not just recency-evicts) + stops the 500/retry-storm. Un-defer in the contract +
|
||||
advertise; confirm the exact wire shape with worldtree-dev first.
|
||||
- **R39 Phase-2 Arm-2 export** (brokkr-initiated): the 10-chunk contradiction specimen is frozen at
|
||||
`r39-frozen-specimen/sindra-10chunk-specimen.db` (gitignored, VACUUM INTO) — survives #364
|
||||
reconciliation; export on brokkr's Phase-2 signal. Full R39/#364 arc:
|
||||
|
||||
Reference in New Issue
Block a user