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

session 2026-06-26: chamber OCR pipeline + Levi first spec-conformant graduation

Browse Source 
Session memory + MEMORY.md index (Active → 2026-06-26) + ledger + skill-harvest
register (/graduate-chamber-source proposal). Pulling thread: apply the proven
OCR→canonical pipeline to the rest of the OCR sources — Alexander Books 1–4 next.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_019pnD8uNFC9Q2dbLQa3MBDc
This commit is contained in:
David F Glidden
2026-06-26 23:51:29 +02:00
co-authored by Claude Opus 4.8
parent adb3d88596
commit 64356724f2
4 changed files with 84 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
claude/memory/skill-harvest-register.md
+8
View File
@@ -240,3 +240,11 @@ The single place proposed skills live so they don't evaporate between sessions.
| **Symmetria §3 flag: reinvent-governed-DESIGN-without-reading-the-spec** | Symmetria §3 flag (may be redundant) | Proposed PENDING-41 (consumer-hardware graceful degradation) as a *novel* architectural direction when `local-inference-spec` 43L/43M **already designed exactly it**. Steward's clasp/circles pointer caught it. Antidote: before proposing an architectural direction, grep/read the spec for the existing design. **Possibly redundant** with the KG drift `reinvented-governed-tooling-without-checking-it-exists` (this is the *design/architecture* sibling of that *tooling* flag) — steward to judge whether it needs its own entry or just widens the existing one. | Symmetria §3 | **PROPOSED (poss. redundant)** |
*(Two. The first is genuinely load-bearing — it would have saved an embarrassing afternoon of flip-flopping and is a clean, reusable diagnostic discipline. The second may just widen an existing flag; surfaced for the steward to merge-or-keep. Reinforced-not-new: the clone-test discipline [proposed 2026-06-22] — I restarted the LIVE substrate 4× today doing diagnosis that belonged on a clone; reinforces that proposal, no new entry. None created autonomously.)*
### Harvest 2026-06-26 (Chamber spec ratified + OCR pipeline + Levi first graduation)
| Skill | Kind | One-line | Origin | Status |
|---|---|---|---|---|
| **`/graduate-chamber-source`** (the `/convert-*` family the runbook already plans) | create | Codify the now-PROVEN OCR→canonical→graduation pipeline as a single governed discipline, so the next source (Alexander 1–4, then the rest) follows the sequence + gates without re-deriving them: **(1)** `normalize_ocr.py` (mechanical: pages, seam-rejoin, dict-validated de-hyphenation, verbatim word-guard, conversion record; raw→`converted_texts/` §III) → **(2)** build per-book `structure.tsv` (curatorial: offset-anchor → read page-top windows → verify each chapter opening → `insert_chapter_headings.py`, fails-loud) → **(3)** curatorial front/back-matter trim + §IV/§VI frontmatter (drop apparatus, keep epigraph) → **(4)** `verify_conversion.py` PASS → **(5)** graduate (catalogue regen) → **(6)** check/​re-point the studium-engine manifest. **Yardstick met:** the steward watched me *derive* the order + gates live this session; a skill carries it. The runbook (`known_gaps.next`) already flags "author the four /convert-* skills" — **today's Levi run is their empirical spec.** Recurs for every OCR source. | 2026-06-26 Levi graduation | **PROPOSED** |
*(One candidate, load-bearing. It realizes a pre-existing planned-skill (runbook `/convert-*` family) with a concrete proven sequence — not manufactured. Captured-elsewhere, not proposed as skills: the de-hyphenation 3-way classifier (in `normalize_ocr.py` + tool-evolution-log); "test the steward's idea against the substrate before accepting/dismissing" (already covered by the measure-before-theorizing ladder/Symmetria flags); the structure-map curatorial method (folded into the proposed skill above). None created autonomously.)*