David/dotfiles
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

wrap 2026-07-12 evening: session record + MEMORY demote/promote + KG drift + harvest

Browse Source 
- session-2026-07-12-evening-…: full A1→schema-lock→B2→PENDING-57-keystone-ratified arc;
  pulling thread = LAND THE KEYSTONE (wire verify_body_conservation into graduation).
- MEMORY.md: demote-on-promote (A1-to-docling → reference; evening session Active).
- knowledge-graph.jsonl: +1 drift-pattern (a-check-for-one-tier-isn't-proven-for-another).
- skill-harvest-register: Doc-currency-on-wrap BUILT into both CLAUDE.md; Symmetria §3 flag proposed.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015jYS1tpR4P4NBxui4FSgfv
This commit is contained in:
David F Glidden
2026-07-12 21:15:46 +02:00
co-authored by Claude Opus 4.8
parent d9692f7418
commit 48a2aec25d
4 changed files with 67 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
claude/memory/skill-harvest-register.md
+13
View File
@@ -431,3 +431,16 @@ The single place proposed skills live so they don't evaporate between sessions.
| **check-the-register-before-a-substantial-build** | `/wake-up` §2 patch OR `/pre-build-audit` step OR Symmetria §3 flag | Before starting substantial INFRA/tool building (a converter, a pipeline, a substrate), read the **tooling-register + landscape-register + prior scans** for an existing adopt-candidate first — the studium-engine-scan-register (2026-05-27) already named Docling+Surya/OCR4all/TEI/DTS as THE substrate answer, and we hand-built ~20 bespoke tools over ~6 weeks anyway. The two-week "every breakthrough → new obstacle" feeling was the tell of reimplementing a solved domain. **Yardstick met, painfully:** the steward had to re-surface that extant tools exist ("are there no epub tools? … TEI?") — our own register carried that six weeks earlier. Kin to [[feedback-resurface-banked-notes-before-rederiving]], specialized to the build-infra decision. | `/wake-up` §2 (when the thread is a build) or `/pre-build-audit` (its natural home) or a Symmetria §3 flag (solving-at-the-wrong-level / build-a-solved-domain) | **PROPOSED** |
*(One proposal, load-bearing — the drift cost ~6 weeks and recurred at pipeline scale; a standing "check the register before building infra" reflex would have surfaced Docling at the outset. Surfaced for steward authorization; not auto-applied. The paired KG drift-patterns are already appended (solving-at-the-wrong-level · didn't-consult-our-own-tooling-register).)*
### Harvest 2026-07-12 evening (schema-lock → B2 fleet → PENDING-57 keystone ratified → doc-currency)
**BUILT this session (steward-directed — recorded, not proposed):**
- **"Doc-currency on wrap" protocol → added to BOTH `chamber-library/CLAUDE.md` and `studium-engine/CLAUDE.md`.** A standing 6-point checklist (fleet/build-state · status markers · substrate-terminology · disciplines · deprecated-verify-before-archive · tool-review) walked before ending work in each repo — the mirror of each repo's read-first session protocol, so wrapping work THERE keeps THOSE docs current (not memory). Steward's framing: "then we are always current." Institutionalizes the anti-guess/anti-reinvent/anti-ignore-a-solution-we-had discipline at the point of work. Complements `/wrap-up` §1.6's "Repo CLAUDE.md fresh?" check (which now has a repo-side counterpart).
- **chamber `CLAUDE.md` + runbook made current** — added `build_loeb_sidecar` + `verify_body_conservation` to the fleet; Loeb-DSL terminology rewritten (flatten-vs-preserve); a new **check-for-existing-tool/register-before-building** load-bearing discipline (the day's meta-lesson); schema DRAFT→LOCKED.
**PROPOSED (awaiting steward):**
| Element | Kind | One-line | Where it lands | Status |
|---|---|---|---|---|
| **Symmetria §3 flag: a check proven for one tier/case is NOT proven for another** | Symmetria §3 flag | Reusing a verification method across a boundary it wasn't demonstrated on is contamination shape — the V-TEXT k-gram coverage check FALSE-FLAGGED a clean V-DSL book (reflow ≠ born-digital). Antidote: an injection/demonstration test PER tier/case, don't reuse-and-assume. Kin to `trust-prior-pass-frame` (one level up: not "extend the same pass" but "reuse the same *instrument*"). | Symmetria §3 | **PROPOSED** |
*(One proposal, genuinely recurring-shaped — the jurist's demonstration-discipline is the human version of this flag; making it a §3 flag would make the executor reach for a per-tier demonstration before shipping a reused check. The Doc-currency protocol is BUILT, not proposed — steward directed it explicitly.)*