Basic Memory retired + MemPalace 3.4.0 upgrade plan saved + Brewfile line dropped

Trial verdict (criteria pre-registered in 3f9a89b): false-clean sync report
disqualifies — index stale for same-session writes while status says 'No
changes'. Lessons 7-13 compiled to CM-AI substrate-failure-lessons-2026-06-07
(6cb3fe9). CLAUDE.md conflict-precedence amendment made by steward same
evening. Upgrade plan: backup-first, palliatives acknowledged, migrate-wings
and repair excluded.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
David F Glidden
2026-06-07 20:45:56 +02:00
co-authored by Claude Opus 4.8
parent 16184027b5
commit 960b256146
4 changed files with 52 additions and 3 deletions
+1 -2
View File
@@ -127,8 +127,7 @@ Every Claude Code output is tagged:
`diary_write`. If a hook fails or you notice something load-bearing mid-session, write manually.
- **"Let me check"** — when the answer matters and isn't immediate, say so and query. The cheapness of querying is
the point.
- **MemPalace > memory files when they conflict** — memory files are point-in-time snapshots; MemPalace is
maintained continuously across sessions.
- **A conflict between MemPalace and memory files is a verification trigger, not a precedence call** — neither layer wins automatically. Files are point-in-time snapshots; MemPalace is continuously maintained but carries a known silent-drift class (HNSW↔sqlite divergence, #1665/#1589, no safe repair path). On conflict: verify against the primary substrate (code, git, the document itself) before acting, then correct whichever layer was wrong (kg_invalidate/kg_add, or the file edit). Treat MemPalace as witness, not notary.
Storage is not memory. Memory is storage exercised by protocol.