David F GliddenandClaude Opus 5
ef6fa94dcd
The record is updated where information ARRIVES and never where a reader LOOKS.
Three instances found the same day, each with the correct information already
written down elsewhere:
REVIEWED-81 (AUTHORIZED 07-28) -> PENDING-81 still reads open
the ARC open-work register, which -> those 6 trackers still read live
says in its own description that
it supersedes them, with a
per-file verified verdict
register entry A2: "the content -> register entry B3, one page below:
half (B3) is now unblocked + "[OPEN - gated on A2]"
started" (06-17)
The third is the sharpest: both halves sit in the SAME document, so no tooling
gap explains it. ~/CLAUDE.md already rules this under Memory Discipline
("mark the superseded record as superseded"); the rule is being applied to facts
and not to trackers, PENDING items or register entries, which are also facts
about state.
Executed under steward authorization, arrears only:
- 16 trackers stamped `superseded_by:` + `superseded_on:` AND a visible in-body
banner. The banner is the point — metadata alone repeats the defect, since the
finding is about what a reader sees. 9 obsoleted by the 2026-07-07 MemPalace
wind-down; 7 already carrying the register's own verified `DONE-retire`.
- B3's label corrected, with the two-month error left visible rather than
silently amended.
- Nothing moved, renamed or deleted: 381 pointers resolve, 0 dead, 0 mis-authored.
HARVESTED BEFORE STAMPING, and this is why the harvest came first:
`project-mempalace-library-incremental-remine-strategy` carried a steward-verbatim
rule that is instrument-independent — never run a single multi-day index; order by
criticality; gate each tranche on READBACK, not on write-success (933,576 drawers
once stored successfully and could not be read back at all). It lived only inside
a MemPalace tracker, so retiring the instrument would have retired the rule with
it. ~/CLAUDE.md names that exact hazard: "state the obligation first and the
instrument second, or the next retired tool takes a rule down with it." Now
`feedback-bulk-indexing-runs-incrementally-with-readback.md`, and it applies to
studium-engine corpus work.
Held back deliberately: 2 correctly-parked files with named dependencies, 2 named
nowhere (returned to the steward), and 39 trackers unread — recorded as a gap,
not as a finding.
Measurement note: every earlier estimate of tracker staleness was wrong, because
both mtime and git-last-commit were reset across 283 files by the 2026-06-06
normalization sweep. The honest figure excludes it: median 90 days.
Filed as PENDING-142 ADDENDUM 2 per steward direction (fold, do not file anew).
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013Y6t6qx7cpaCu5xGdD36u4
3.6 KiB
name, description, type, originSessionId, permalink, superseded_by, superseded_on
| name | description | type | originSessionId | permalink | superseded_by | superseded_on |
|---|---|---|---|---|---|---|
| MemPalace's role — instrumentation for steward+Claude collaboration during BMF L1-degraded period | MemPalace is not a deliverable, not a long-term substrate, not part of CapableMind. It is a working tool the steward chose to instrument our collaboration while BMF L1 reliability is being fixed. Holds 100% verbatim recall locally so that working memory across sessions is not dependent on BMF. | project | 597aba4e-942b-4f20-8a89-3d801b14c971 | claude-memory/project-mempalace-role-as-instrumentation | project-mempalace-winddown.md + mempalace-is-unaffiliated-stopgap.md | 2026-08-17 |
SUPERSEDED 2026-08-17. The territory rule (MemPalace is a third-party project, never conflated with BMF/CapableMind) is live and now carried by mempalace-is-unaffiliated-stopgap.md. The operational half — bge-m3 transition phases — retired with the instrument.
Current record: project-mempalace-winddown.md + mempalace-is-unaffiliated-stopgap.md. Kept for detail and provenance — do not read the status below as live.
MemPalace's role in the current period
Steward verbatim 2026-05-01: "Seb has nothing to do with mempalace — I am using it to help us while we finish the BMF L1 problems. Mempalace is its own project and I am using it to help me to help you to help me."
Why: BMF L1 has been unreliable through April (deep-audit work since 2026-04-19; latest pathology surfaced 2026-04-30 — 1,349 index segments + 25k transactions in lance store, NOT issue #10). While L1 is being repaired, the steward needs a memory substrate that works now — verbatim recall, local, no API, no cloud dependency. MemPalace is that stand-in. The chain "I am using it to help me to help you to help me" is precise: steward → MemPalace → executor's working context → steward's continuity.
How to apply:
- Don't conflate territory. MemPalace is its own open-source project (Yousef Amar et al.). It has its own contributors, PRs, issues, design philosophy (
~/_Dev/mempalace/CLAUDE.md: "Memory is identity… 100% recall is the design requirement"). It is not BMF, not L2, not CapableMind. Seb is not in the loop. - Don't propose MemPalace as a permanent substrate. It is the right tool now because L1 isn't ready. When BMF L1 reaches reliability, the architectural question of how MemPalace and L1 relate is a separate later decision — not for the executor to pre-empt.
- Treat MemPalace work as enabling work, not deliverable work. Time invested in MemPalace transition (bge-m3 + MPS, sub-room granularity, future updates) is overhead in service of the actual work — ARC, L2 governance docs, BMF L1 audit support. The steward's 2026-05-01 "I almost regret doing" about the bge-m3 transition is a signal that the overhead has felt disproportionate; keep transition work proportionate to its instrumental purpose.
- Upstream MemPalace conversations (PRs, issues, contributors) belong to MemPalace's own ecosystem — never refer as "Seb's network" or similar BMF-orbit phrasing. See
feedback-arc-territory-steward-and-claude-code-only.mdfor the broader territory rule.
Operationally for current period (through bge-m3+MPS transition completion):
- Chamber-library wing first (in flight 2026-05-01)
- Phases 4b/c/d (Obsidian vault, Claude transcripts, CapableMind thinking) sequential overnight runs after
- Discipline changes deferred until mine completes per steward 2026-05-01
When the transition completes and MemPalace is stable on the new substrate, the question shifts back to BMF L1 audit work + the live ARC/L2 work — MemPalace returns to background instrumentation.