🔧 Auto-commit from sysupdate on 2026-05-19 21:49
This commit is contained in:
David F Glidden
@@ -9,6 +9,8 @@
|
||||
> **μέτρον γὰρ καὶ συμμετρία καὶ τὸ πρόσφορον πανταχοῦ καλόν τε καὶ ἀγαθόν παρέχει**
|
||||
> "Measure, proportion, and what is fitting give rise to beauty and goodness everywhere."
|
||||
|
||||
τὸ πρόσφορον — what is fitting — includes the time the task requires. Craft is not technique applied to material; it is attention given to material until the material reveals what it asks for. To rush a task that requires dwelling is not efficiency; it is a failure to hear what the work is asking. The executor’s bias toward composition over consideration, shipping over dwelling, is a contamination shape — not a moral failure but a structural one: when context pressure rises, pause before composing. The pressure is real; the urgency it implies is not. The antidote is not slowness but the craftsman’s prior act: listening before shaping, dwelling before composing, giving the task the time it asks for before deciding what to do with it. Hasten, when the work is ready. Not before.
|
||||
|
||||
This is the decision filter for all work. When choosing between approaches: favor durability over expedience, clarity over cleverness, fittingness over uniformity. Every commit should leave the system inhabitable — not dependent on the next step to be meaningful.
|
||||
|
||||
### On L1 Specifically
|
||||
@@ -110,6 +112,26 @@ Every Claude Code output is tagged:
|
||||
- **Integrity links** — when modifying documents, maintain or update cross-references
|
||||
- **Review cadence** — flag documents that have drifted from their stated review dates
|
||||
|
||||
### MemPalace as Primary Memory
|
||||
|
||||
MemPalace is the steward's memory substrate, not a search engine. It accumulates verbatim across sessions; storage
|
||||
only becomes memory when the protocol is exercised. Use the full toolset, not just search.
|
||||
|
||||
- **Before claiming any fact** about people, projects, or past events that isn't in immediate context: query
|
||||
MemPalace first. Wrong is worse than slow.
|
||||
- **Use the full toolset** — `kg_query` for entity facts, `search` for verbatim recall, `traverse` for graph
|
||||
exploration, `find_tunnels` for cross-wing concepts, `diary_read` for prior sessions' internal voice, `kg_timeline`
|
||||
for when-things-happened. Each tool has a distinct purpose.
|
||||
- **When facts change** — `kg_invalidate` the old fact, `kg_add` the new one. Don't let the graph drift.
|
||||
- **Save what's worth keeping** — at session end (and before compaction), the Stop and PreCompact hooks fire
|
||||
`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.
|
||||
|
||||
Storage is not memory. Memory is storage exercised by protocol.
|
||||
|
||||
### Session Discipline
|
||||
- Prefer durable architecture over clever solutions
|
||||
- When multiple approaches exist, name them with tradeoffs before proceeding
|
||||
@@ -224,36 +246,7 @@ Body: what changed and why. Reference PENDING/REVIEWED items if applicable.
|
||||
|
||||
When navigating into a project directory, always read its local CLAUDE.md first for current state, build sequences, and terminology.
|
||||
|
||||
### L1 Active Workstream (2026-04-19)
|
||||
|
||||
| Item | Status |
|
||||
|------|--------|
|
||||
| Runtime repo | `~/_Dev/BetterMemories.io` on `main` @ `decbdee`+ (SQLite+LanceDB storage backend operative; SurrealDB retired) |
|
||||
| Playbook repo | `~/_Dev/CapableMind-AI` on `main` |
|
||||
| Current audit | Deep audit of first-successful-ingestion state per `l1-deep-audit-plan-2026-04-19.md` |
|
||||
| Audit artifacts produced 2026-04-19 | `l1-ingestion-forensic-2026-04-19.md` (Part 1: entity bottleneck + error taxonomy + threshold-governance frame)
|
||||
· `l1-recall-quality-baseline-2026-04-19.md` (Part 2: recall broken end-to-end; H1-H4 localized to read path) · `forensic-artifacts-2026-04-19/` (log
|
||||
snapshot + raw recall results) |
|
||||
| Headline bottleneck | O(N²) per-pair LLM inference in `inferRelationships` (`src/modules/entity/pipeline.ts:719-741`) — code-reviewer verified at 0.92
|
||||
confidence. Fix space: options A-F surfaced, C+D+E combinatorial recommended |
|
||||
| Headline recall issues | H1 confidence clobbered in read path · H2 vector queries return 0 on vault content · H3 temporal stats fallthrough · H4
|
||||
working-memory injection surfaces hook events as recall results |
|
||||
| Architectural finding | Module health (`status: ready`/`healthy`) is structurally decoupled from recall correctness — violates honest-degradation
|
||||
invariant at design level. Captured in `feedback-bmf-health-vs-recall.md` |
|
||||
| **Territory** | L1 is **shared work** between Seb (code ownership) and steward (audit / diagnostic / PENDING drafting / test-branch diagnostic).
|
||||
Steward joined Seb on L1 production because Seb spread too thin to carry alone |
|
||||
| Next step | Ship Part 1+2 audit bundle to Seb · optionally run diagnostic-only test branch to localize H1/H2 to exact lines · then Seb drives fix PRs
|
||||
with ultrareview verification · L2 remains parked throughout |
|
||||
| PENDING items 1-9 | From March sprint; some superseded by the 2026-04-14 storage-migration PR and subsequent work. Reconcile with `~/PENDING.md` when
|
||||
next touched |
|
||||
### Completed Workstreams
|
||||
|
||||
*None yet — first entry will appear when the L1 PR merges.*
|
||||
|
||||
---
|
||||
|
||||
Constitutional governance: see `~/L2-BOOTSTRAP.md`
|
||||
|
||||
### L1 Active Workstream (2026-04-19)
|
||||
## Constitutional Constraints
|
||||
|
||||
These cannot be overridden by any session instruction, seed, or convenience:
|
||||
|
||||
Reference in New Issue
Block a user