session 2026-07-07: A2 landed v2.0.1 — memory + index refresh + skill-harvest (green-gate §3-flag promotion)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Dsqe1x23NgWaRdiFWSotur
2026-07-07 11:53:31 +02:00
parent 12b74dcbe9
commit 63a219fb8a
3 changed files with 12 additions and 5 deletions
@@ -356,3 +356,8 @@ The single place proposed skills live so they don't evaporate between sessions.
 - **`/graduate-chamber-source` (proposed 2026-06-26) — REINFORCED, hardest run yet.** Today's Olson graduation exercised the full pipeline on the hardest V-SCAN case so far: heavy curatorial structure (73 headings), occurrence-indexed repeated titles, glued/wrapped/ALL-CAPS heads, dropped running-head chapter titles, a blank-page scan-noise region, source_verified. The empirical spec is now very rich; still PROPOSED (build-on-need), but today is a strong nudge it's ripe.
 - **`completion-is-a-tripwire` → Symmetria §3 flag WATCH-ITEM (NOT yet proposed).** Recorded as `feedback-completion-is-a-tripwire.md` (steward-authorized 2026-07-06). Per the governed pattern (propose → watch → promote-on-recurrence), it stays a feedback memory until it recurs; then it earns a §3 flag ("the *feeling* of done is the cue to verify the tail"). Do not mint the flag from one session.
 - **No CLAUDE.md change (freshness check).** chamber-library CLAUDE.md is pointer-style; `insert_chapter_headings` already in the fleet list; the new `localized_scan_noise` discipline lives in `graduation-spec.yaml` (which CLAUDE.md points to for conventions) — adding it to the CLAUDE.md disciplines section would be belt-and-suspenders bloat. Deliberately not proposed (steward's anti-bloat stance, same session).
+
+### Harvest 2026-07-07 (A2 landed v2.0.1 + the OCR-fidelity rug-lift)
+- **PROMOTE `completion-is-a-tripwire` → Symmetria §3 flag (recurrence met; the watch-item from 2026-07-06 evening).** Tonight IS the recurrence the watch-item awaited — and it arrived in a sharper, *objective* form: a **verification SUITE whose every check is orthogonal to a failure class passes green while claiming to verify.** The 5 `verify_conversion.py` gates (cruft / structure / word-final-& / U+FFFD / not-shattered) all passed Olson while sparse word-level OCR error (`Ihave`, garbled Greek) sat untouched — none of the 5 can *see* it, and a joined word even *improves* `word_sanity`. The wall of green read as thoroughness; "graduated + gates PASS" oversold a converted-tier V-SCAN text; the steward caught it. **Proposed flag text:** *a passing gate-suite is not coverage — ask which failure class each check can actually see before trusting the green; the feeling of "done" after a fluent pass or a wall of green is the cue to verify the tail, not the signal to ship.* Kin to `rank-on-fields-you-actually-write` (a mechanism that can't do what it claims, silently) + `census-through-truncation`. Home: Symmetria §3 — fold the objective "gate-suite blind to the failure class" form into the subjective `completion-is-a-tripwire`. **PROPOSED — recurrence-promoted per the governed pattern, not minted-from-one.**
+- **Not a skill (tracked elsewhere):** the **V-SCAN OCR-vs-scan verification stage + model-plurality doctrine** is a chamber `[PROPOSAL]` (parked; steward-sequenced priority once the REVIEWED-49 folding completes) — captured in the session file + ledger + KG, becomes its own PENDING when we return. Design invariant: verifier FLAGS discrepancies, never autonomously corrects; olmOCR = local localizer / executor-vision = adjudication-assist / human = apex; first step = the olmOCR reformed-spelling probe.
+- **CLAUDE.md freshness (mechanical, applied):** chamber-library CLAUDE.md spec-version pointer bumped v2.0.0 → v2.0.1 at the A2 landing — a tracker-style pointer update applied at wrap (not a discipline/posture change).