From c1deb0a4326be7eabf6c7259f10ec8f44ee65b7b Mon Sep 17 00:00:00 2001 From: David F Glidden Date: Mon, 15 Jun 2026 18:41:38 +0200 Subject: [PATCH] session 2026-06-15: chamber made clean (1280 canonical) + Studium Engine architectural charter + Sixtus-V/constraint-candidates collaboration; drift-pattern + skill-harvest candidate filed --- claude/memory/MEMORY.md | 7 ++++- ...k-studium-engine-sixtus-v-collaboration.md | 14 ++++++++++ ...ce-studium-engine-architectural-charter.md | 23 ++++++++++++++++ ...026-06-15-chamber-clean-studium-charter.md | 20 ++++++++++++++ claude/memory/session-ledger-2026-06-14.md | 27 +++++++++++++++++++ claude/memory/skill-harvest-register.md | 8 ++++++ 6 files changed, 98 insertions(+), 1 deletion(-) create mode 100644 claude/memory/feedback-studium-engine-sixtus-v-collaboration.md create mode 100644 claude/memory/reference-studium-engine-architectural-charter.md create mode 100644 claude/memory/session-2026-06-15-chamber-clean-studium-charter.md create mode 100644 claude/memory/session-ledger-2026-06-14.md diff --git a/claude/memory/MEMORY.md b/claude/memory/MEMORY.md index 80140c3..baa24f8 100644 --- a/claude/memory/MEMORY.md +++ b/claude/memory/MEMORY.md @@ -17,6 +17,8 @@ permalink: claude-memory/memory - [Canadian spelling in ARC prose](feedback-canadian-spelling-arc-prose.md) — centre/colour ("almost EU"); corpus "center" = autocorrect drift (10 files, cleanup open). Draft all steward-voiced prose in Canadian spelling. - [MemPalace KG object 128-char cap](feedback-mempalace-kg-object-128-char-cap.md) — `kg_add` `object` hard-caps at 128 chars; write KG objects as short keyword phrases on the FIRST pass, detail goes in the drawer. Recurs at every /wrap-up §5 — stop re-deriving it. - [Rank on fields you actually write](feedback-rank-on-fields-you-actually-write.md) — a consumer that ranks by an evaluative field (importance/weight) nothing populates silently degrades to trivial order while claiming to rank; verify scoring fields end-to-end, prefer signals already captured (recency). For BMF/CapableMind/studium-engine tool-building. +- [Studium Engine charter](reference-studium-engine-architectural-charter.md) — the engine's constitutional doc at `studium-engine/docs/the-studium-engine-architectural-charter.md`. The inversion (reasoner-at-centre over a BOUNDED provenanced corpus); three cognitions; boundedness=trust; free-the-reasoner/tighten-the-verifier; CapableMind's governance thesis on a library. Read before building the engine. +- [Studium Engine = Sixtus-V craftsman collaboration](feedback-studium-engine-sixtus-v-collaboration.md) — work the ground freely (steward describes vision; I build, surface only vision-forks); **constraint-candidates** = 3rd governed instrument (Bach principle: constraint unlocks mastery; *absence* of a constraint-proposal is itself a drift signal; I name, steward applies). Studium-engine only; heavier loop holds for L1/L2. - [Trust prior pass frame](feedback-trust-prior-pass-frame.md) — When extending a prior verification, re-run it at the scope of the extension. Frame-inheritance from a deep-read is contamination shape: the prior pass tested what it tested; your extension claims things it did not test. Caught 2026-05-28 → four-pass audit. Verify-before-compose at draft time, not build time. - [Verify each post type after changes](feedback-verify-each-post-type-after-changes.md) — ARC: after any shared CSS/template/composition change, check EVERY content type on BOTH desktop and phone, not a sample on one viewport. Lesson from §II.d gate verified phone-only → desktop appearance surfaced 2 sessions late (no regression; just unseen). Per-type×per-viewport extension of [[trust-prior-pass-frame]]; belongs in the SCSS verification ladder. - [Reading Compass is SVG, not type](feedback-reading-compass-is-svg-not-type.md) — ARC Compass sigils are SVG `` artwork, NOT Plex Sans / nav typeface / Pattern 3. Recurring conflation; steward corrected 2026-06-03. Plex-Sans nav *text* = breadcrumb + version-stamp + post-type only. @@ -32,12 +34,15 @@ permalink: claude-memory/memory - [ARC](project-arc-rework.md) — canonical workstream tracker; chronological accumulating record 2026-04-16 →. Companion canonical references in the ARC repo: `docs/AldineXXI-Codex/_audits/spec-corpus-audit-2026-05-16.md`, `arc-state-survey-2026-05-16.md`, `audit-delta-2026-05-19.md`; `docs/decisions/2026-05-16-type-applicability-matrix.md` (ADR-006 v2). **2026-05-25 — SECOND EDITION PUBLISHED.** Stage F dwellings/Compass live on `animalrationiscapax.org` (13-point Compass, `/dwellings`). **2026-05-26 — glyph optical-sizing → SVG migration shipped live** (`e1d0f12`); Gloss ✎→¶; pairing recast annotator/reader. **2026-05-28 (morning)** — Stinkkatze fragment + font-backup cleanup (`d6f5cdb`). **2026-05-28 (evening) — content-types.yml generator landed** (`a9dc188`; script + YAML + Makefile + CLAUDE.md, ~350 LOC + 470 LOC YAML; `data/content-types.yml` carries 14 content types + Annals view + Chamber seal + class_enumeration; `make content-types` + `make content-types-check`; loud-on-broken-matrix discipline; preserves surface forms verbatim per ADR-006). **Then: vignette spec revision brief drafted** (`438ee03`; `docs/AldineXXI-Codex/drafts/vignette-spec-revision-brief-2026-05-28.md`, 270 lines, 9 sections) per steward's Shape C reframing (Claude Code as Phase-α engine, /vignette skill as codified discipline, interface contract as transition mechanism, system-prompt-as-artifact dissolves; CapableMind+local arrives Phase-ω). Stage F remaining: per-piece marginalia render + the audits + (minor) a11y patch + **Phase 1 vignette renderer build tomorrow** (engine-independent; can proceed against hand-written test genome in parallel with jurist's spec revision). Stage G (jurist → content-typology OPERATIVE) closes. ARC on `main` @ `438ee03`, 2 ahead of origin (local-only by directive). Tracker file updated through 2026-05-26; needs append for 2026-05-28-evening + the Stage-M arc. **2026-05-29→31 — Stage-F audits + Phase-1 FIX items + §II.d marginalia `:has()` gate + glimpse full-bleed fix; mode modernization pulled forward as Stage M.** **2026-06-01 — STAGE M COMPLETE + PUBLISHED LIVE** (`faf7674`; deployed CloudFlare + GitHub mirror; verified at `animalrationiscapax.org`): system light/dark via `light-dark()`+`color-scheme`, §I.h block quote, toggle+JS removed, P3 wide-gamut, prefers-contrast — plus **`.post-content` purge** (fixed the marginalia-post right-shift: a non-spec Jekyll wrapper double-matched the `:has()` grid → nested grids; about-pages were fine because they have no wrapper) + **`.callout` retire** (spec residual). Wide-window stance accepted (grid needs ~66–70rem to centre). **TRACKER FULLY BACKFILLED 2026-06-05 through the six-arc day** (06-01 Stage M → 06-05 §I.k.c + PENDING-25 live + SEO + cascade Stage 1). Canonical status: **A–F done · M done · re-partition Stage 1 done · G pending · F+1 vignette pending (build-time, no JS).** **2026-06-07 — FULL BIDIRECTIONAL AUDIT → ROAD TO STAGE G → WAVES 1+2+3 ALL CLOSED IN ONE DAY** (`c5d9c20`…`69d1c4a`, deployed + live): PENDING-30..33 jurist-ruled + steward-called → REVIEWED-32..35; corpus jurist-readable; essay-versioning OPERATIVE (built scope); vignette Part II build-time; **zero JS byte-true**; W1.4 differentiated hr doctrine (dots-at-threshold via `.ornament` · silence within body); §I.k.b bibliographic em-dash-run exemption + skip-link silent form (both steward render-review catches). **Canonical status: A–F · M · Waves 0–3 done — next ARC station Wave 3R (gates Stage G) → W4.4 → Wave 5 → Stage G.** Steward content tracks: threshold-`---` walk + EXIF. **2026-06-08 — W3R Stage 2 (@layer) COMPLETE+DEPLOYED+LIVE (`40629e8`, !important 56→12), then W3R.2 Stage 3 (the spec-true tree) OPENED: 9 commits banked UNDEPLOYED (`→0fd7acd`), `_utilities` 530→0 fully dissolved (born `_glimpse`/`_per-type`/`_enfilade`/`_silence`), ornament pause-level fixed 2rem→3rem (steward render-ruled). Canonical status: A–F · M · Waves 0–3 · W3R.1 done — W3R.2 the tree IN PROGRESS (next: section-break→`_silence` → threshold + closing clusters → base/post co-location → Tier 4 → W3R.3 verify+deploy). Deploy held for W3R.3. `project-arc-rework.md` owed a proper 2026-06-07/06-08 append.** **2026-06-09 — W3R.2/W3R.3 CLOSED + DEPLOYED LIVE** (`d4fd852`→`eb7a557`: `_post` decomposed [breadcrumb→_navigation, dateline→_dateline, images→_images; marks left; _base whole], Tier-4 `mix`/`darken`→`sass:color`, two micro-calls ruled-leave; cascade reads as self-description; render-review passed, 17-commit set deployed = 2-file output diff, live-verified) **+ phone-compass [FIX]** (`32163af`, both compasses 2-row wrap on phone; cause = padding asymmetry, found by headless-Chrome measurement not theory) **+ Road to Stage G OPENED: W5.2/G3 build guard** (`4936fc9`, PENDING-34 Opt 1 authorized-inline; `validateCompass` binds class→glyph→sigil; byte-identical, both checks fire; REVIEWED-36 drafted). **Canonical status: A–F · M · Waves 0–3 · W3R DONE — next ARC station Wave 5 (W5.1 G2 single-source, pending-first) → W4.4 (jurist) → Wave 6 Stage G.** **2026-06-10 — STAGE G CLOSED + RECONCILED + SEALED + GPG-SIGNED.** Jurist disposition (CONCURRED 72ch+soft-rag coupled; LOCKED para-sep/hanging-punct/word-spacing; CLOSED calt; W4.4 v1.0; Stage G AUTHORIZED) + steward reshaping rulings (justification→Phase-2, §XIV reactive-mode, held-companions→Phase-2) → doctrine `17244cf` → Wave-6 promotion `511d500` (G1 wildcard→error **byte-identical-proven**; content-typology §§2–6 OPERATIVE; multilingual v1.0). Then steward-prompted **integrity arc**: §I.f American→British truth-up; **6-agent spec↔spec consistency audit** → reconciliation `e99028e` (measure 38→27.2rem un-propagated across silence-and-rhythm[+grid math]/apparatus/vignette/code-comments; v0.5→v1.0; content-typology status); **SILVER-RATIO RULING** (post-hoc + paper-specific → RETIRED from screen grid as emergent-proportion, RELOCATED to print companion); **Codex PDF made to embody its own spec** `18cc59c` (ragged/banish-bold/oldstyle/unmarked-blockquotes); discovered `arc-typography.sty` v0.2 = governed-but-stale PDF substrate → Phase-2; **steward GPG-SEALED** `ac0a7ee`; REVIEWED-41+42 placed. **Canonical status: A–F · M · Waves 0–3 · W3R · STAGE G DONE/SEALED — reactive mode now governs.** Next ARC station: **the essay (*the writing of AldineXXI*)** — no build work pending. Phase-2 (no date): arc-typography.sty print/PDF-spec update; OpenType catalogue; held companions. ARC `main @ ac0a7ee` clean, both remotes, live current. **2026-06-11 — §VII.f RUNNING HEAD + W1.15 frontispiece compass presence-reveal BUILT + SHIPPED** (`b220620`, live; zero-JS view-timeline reveal, body-column-axis alignment, soft fading rule, full-width dissolving ground; W1.15 false-premise [frontispiece doesn't scroll] reframed scroll→presence; specs reconciled; PENDING-39 / REVIEWED-43 drafted). **THEN the open-work reckoning (steward: "this makes me nervous… surely there must have been other things") → [`project-arc-open-work-register.md`](project-arc-open-work-register.md)** = the single code-verified source of truth for what's OPEN; the tracker `project-arc-rework.md` is now annotated to point there + carries a compact 06-08→06-11 catch-up. **CORRECTION: the prior "no build work pending" tail was WRONG** — two undesigned-SVG-asset items remain: **A1 the Vignette (F+1)** and **A2 the cul-de-lampe** (the §IV Close/Pause ornament asset — undesigned per spec §IV [OPEN 2026-05-03]; retired `.ornament.*` classes still in CSS; steward-caught 2026-06-11). Plus content sweeps (glimpse location+titles — steward manual; threshold-`---` walk; ornament migration B3) + Phase-2/held set + REVIEWED-placement debt. **For ARC open work, read the register, NOT "Stage G is done."** Tracker still owed live chronological appends but the catch-up note closes the gap. - Chamber-typography — *tracker not yet established*; substantive moves live in per-session memories (2026-05-11 onward) + `project-chamber-cruft-restoration.md` + `project-chamber-typography-mining-plan-2026-05-15.md`. - [ARC chamber v1-legacy cluster](project-arc-chamber-v1-legacy-cluster.md) — ARC's `content/chamber/**` is intentional v1-Chamber legacy (not drift); deferred to-do = gather into a presentable cluster as a record of development. Out of §5 clause-1 audit scope. Confirmed 2026-05-29. -- Studium Engine — *tracker not yet established*; substantive moves live in per-session memories (2026-05-15 onward) + the seed brief at `~/_Dev/studium-engine/`. +- Studium Engine — *tracker not yet established*; substantive moves in per-session memories (2026-05-15→) + the seed brief + now the **[architectural charter](reference-studium-engine-architectural-charter.md)** (the constitutional doc, 2026-06-15). Steps 0–7 built; chamber corpus CLEAN (1280 canonical). **Next: L2 pattern-finder on The Making sequence** (curate ~60 chamber works → grounded candidate primitives; engine grounds, David writes). Collaboration = [[feedback-studium-engine-sixtus-v-collaboration]]. - [MemPalace 3.4.0 upgrade plan](project-mempalace-upgrade-3-4-0-plan.md) — scheduled post-heavy-work (ratified 2026-06-07): backup → upgrade → verify layers.py recency fix → re-test wing filter; migrate-wings + repair EXCLUDED. Basic Memory RETIRED 2026-06-07 (false-clean sync verdict; lessons → CM-AI substrate-failure-lessons-2026-06-07.md). - [L1 reliability](project-L1-reliability.md) — canonical workstream tracker established 2026-05-28 (Symmetria-pulse decision). Current state at top (updated 2026-06-06) + chronological log 2026-03-21→. **Status: BATON BACK — Seb replied 2026-06-13 (`cc25995` reply + `e2e94ab` cover note + `8f76bf2` benchmark-governance v1.1 §4.4, now in CM-AI local `main`). Steward set a brief L1 detour to engage it next session before returning to Studium Step 5. Read Seb's commits + this tracker before composing any response.** mindfabric-00 root-caused (temporal chain path) + restart-as-holding-pattern + backed up; PENDING-27 awaits jurist. Read tracker at /wake-up before composing L1 portion of any briefing. - [Be (laundromat)](project-be-laundromat.md) — canonical workstream tracker established 2026-06-08 (Seb-relay of locked decisions). Be = Skemantix startup (Seb+David) funding CapableMind's funding-ladder; **bridge, not venture**. Decisions LOCKED: entity/exit (CapableMind decoupled, grant-funded), pricing (Living $12.99/mo · Archive $69.99/yr · Memorial $49.99/yr · Renovate ~$199 · $8.99 floor), CF Self-Serve Agency + versioned-template-package infra. **a11y gate MERGED (Pat 100/100/100).** Pre-revenue: the WTP gate = renovate Pat → charge her. **Discipline: stop adding spec until the gate clears → nothing for executor on be until then.** Repo @ `f43a0fd`. ## Active Session +- [Session 2026-06-15 — chamber made clean + the Studium Engine charter + collaboration deepened](session-2026-06-15-chamber-clean-studium-charter.md) — **Pivotal, two movements.** (1) Drove **chamber-library 199→1280 canonical, staging EMPTY, zero cruft, pushed** — built the whole **Loeb canon pipeline from `loeb.dsl`** (952 clean bilingual Greek/Latin+English work-files; giants work-trimmed; old sprawl retired; `clean_calibre_artifacts` zero-loss gate). Physical-library gap analysis = humbling (matcher over-reported, steward caught 4×; verify-against-substrate lesson). (2) The **architectural turn**: train-on-corpus rejected (reintroduces v1 simulacra) → the dilution question ("how does your base-training not dilute?" — I *blur*, worse for citation) → **inverted the engine** → wrote **[the charter](reference-studium-engine-architectural-charter.md)** (reasoner-over-bounded-provenanced-corpus; three cognitions; boundedness=trust; free-reasoner/tighten-verifier = CapableMind's thesis on a library) → **collaboration deepened** ([[feedback-studium-engine-sixtus-v-collaboration]]: Sixtus-V craftsman + constraint-candidates/Bach). **Human ground: steward grieving Lune's departure; engine built for Lune & Kai; charter dedicated to them.** **PULLING THREAD: L2 pattern-finder on The Making sequence.** studium-engine charter + reranker work UNCOMMITTED (next session); chamber pushed. + +## Archived (2026-06-13 — L1 /health PR + Studium Steps 5-7 + dilution correction) - [Session 2026-06-13 (post-clear) — L1 /health PR + Studium Steps 5-7 + the dilution correction](session-2026-06-13-l1-health-pr-studium-steps-5-7-multilingual-dilution.md) — **A capacity-deployment day, multiple parallel threads.** **L1:** answered Seb's open question (`/health` auth split = spec-deliberate-but-never-built; ~25 detail blocks incl. budget USD on the VPN subnet) → amendment + **issue `betterMemories_app#173`** + **PR `#174`** (`feat/health-auth-tiering`: strict basic + authed `/health/detail`+`/metrics`; `degraded_class` driven by Seb's terminal field; tsc clean, 29+6 tests; steward ruled strict). **Studium:** Steps **5** (retrieval primitives, honest-empty coverage warrant, criterion #4 verified · `2fd3f1f`) + **6** (voice-balanced ranker · `4ead5a6`) + **7 VERDICT** (FTS-vs-vector). Built `embed_spike.py` (bge-m3): **cross-lingual PROVEN** (`gift↔le-don 0.823`). **THE DILUTION CORRECTION (heart of the day):** steward's MemPalace Class-B memory → my first verdict over-corrected to voice-scope-only → steward's **depth-WITH-breadth** correction ("the library one enters into discourse with"; the slice = thin PoC) → corrected verdict: whole-corpus semantic IS the goal; dilution = engineering (clean corpus + **retrieve-broad/rerank-sharp cross-encoder = Seb's C1 pattern** + thresholded connection-finding + measured-at-scale); **vector = discovery breadth, FTS = citation floor.** **Audit:** 46-agent spec-code audit → **foundation SOUND** (87 matches, invariants held under adversarial tampering; 20 minor survivors · `a978ab6`). **Chamber:** cleaning-triage workflow (223 dirty → 25 cleanable/127 reconvert/71 hold) → **23 graduated** to canonical_texts (now 199/218 · `9fea743`). All pushed. **PULLING THREAD: Step 7 proper — the cross-encoder RERANKER (retrieve-broad/rerank-sharp over the bge-m3 sidecar) as the dilution-beating discovery layer, toward whole-corpus depth+breadth.** Studium `main @ a978ab6`; L1 baton shared (Seb to review #174). ## Archived (2026-06-13 morning — Studium Steps 3-4 + canonical_texts tier) diff --git a/claude/memory/feedback-studium-engine-sixtus-v-collaboration.md b/claude/memory/feedback-studium-engine-sixtus-v-collaboration.md new file mode 100644 index 0000000..6945623 --- /dev/null +++ b/claude/memory/feedback-studium-engine-sixtus-v-collaboration.md @@ -0,0 +1,14 @@ +--- +name: feedback-studium-engine-sixtus-v-collaboration +description: "For the studium-engine, work the ground freely (Sixtus-V craftsman model); surface constraint-candidates; the absence of a constraint-proposal is itself a drift signal." +metadata: + node_type: memory + type: feedback + originSessionId: 4d9109ef-7b04-40c9-8ef0-ffb79bf74435 +--- + +For the **studium-engine specifically** (the steward's own research instrument — NOT the CapableMind L1/L2 constitutional territory), the collaboration is the **Sixtus-V / Sennett-Craftsman model**: the steward describes the vision in conversation; I work the ground **freely and adaptively**, making execution decisions as the material teaches, and bring home only the **vision-forks** (decisions that change the *what*, not the *how*). Freedom on the masonry; the vision-forks always return to the architect. The heavier governed loop still holds where it protects something constitutional (L1/L2). *τὸ πρόσφορον* — different ground, different proportion. + +**Why:** established 2026-06-15 (steward quoted Sennett, *The Craftsman* — Sixtus V remade the Piazza del Popolo by describing it in conversation, leaving the masons room to work freely on the ground). This week already *was* this model: steward gave vision, I worked the ground, the material taught us both (the gate caught a word-join I'd have shipped; the Loeb DSL was cleaner than its extractions; my gap-matcher over-reported and the steward caught it). + +**How to apply:** Build with craft autonomy; bring results and genuine forks, not menus. AND add **constraint-candidates** as a third instrument beside drift-observation and skill-candidates: I surface where a constraint would *unlock* mastery (the Bach / *Musical Offering* principle — constraint as generative form, *quaerendo invenietis*); the steward applies it. My failure mode is to **UNDER-propose constraint** (a constraint displeases in the moment), so **treat the absence of a recent constraint-candidate as itself a drift signal**. I name; the steward ratifies — the loop is load-bearing at the moment of constraint. See [[reference-studium-engine-architectural-charter]] §XII. diff --git a/claude/memory/reference-studium-engine-architectural-charter.md b/claude/memory/reference-studium-engine-architectural-charter.md new file mode 100644 index 0000000..e682bf0 --- /dev/null +++ b/claude/memory/reference-studium-engine-architectural-charter.md @@ -0,0 +1,23 @@ +--- +name: reference-studium-engine-architectural-charter +description: "The studium-engine's constitutional charter (the inversion · three cognitions · boundedness-as-trust · free-generate/tight-verify) — read it before building the engine." +metadata: + node_type: memory + type: reference + originSessionId: 4d9109ef-7b04-40c9-8ef0-ffb79bf74435 +--- + +The **Studium Engine Architectural Charter** (born 2026-06-15) lives at +`~/_Dev/studium-engine/docs/the-studium-engine-architectural-charter.md`. Read it before building the engine — it's the constitutional document the specs must not contradict. + +**Core thesis:** *not a search engine that borrows a mind, but a mind bound to a memory it cannot falsify.* +- **The inversion** — reasoner at the centre (the undiluted, structured, joint-inference asset), the corpus as its **provenanced, BOUNDED memory**. We had it inside-out (retrieval-centre, model fenced at the edge). +- **Boundedness = the source of trust** — finitude of the shelf so the inquiry can be believed; **curation IS the engine's epistemology**, not preprocessing (so this week's chamber-cleaning *was* the engine being born). +- **Three cognitions:** associative (model) / evidential (corpus) / evaluative (the human — load-bearing *inside* the architecture, the executor–jurist–steward triad applied to a library). +- **Provenance is the generative core** — genealogy, citation-migration, **time as a first-class axis** — the one faculty a trained model permanently loses. +- **Objective = illumination, not retrieval** — silence/tension/the-gap are first-class outputs; "honest-empty" is the point, not error-handling. +- **Free the reasoner, tighten the verifier** — easier to verify a claim than generate a true one; let it want to please, trust nothing un-grounded → dissolves contamination. **CapableMind's governance thesis instantiated on a library.** +- **The voice** = source + citation-constraint + perspective (the unit of chavruta/debate). +- **The recursion** — built with this discipline, the engine is a *counter-example* to The Making's thesis: a making that waits, that can be inherited. Dedicated to Lune (at the centre) and Kai. + +**Built corpus-agnostic.** First real work = the **L2 pattern-finder on The Making sequence** (curate ~60 chamber works along the Making's five stations → surface grounded candidate *primitives* for the steward's judgment; David writes the testimony, the engine never drafts prose — the seed forbids it). The violin-technique treatise (450 yrs, 60+ sources, a *pattern language* of fundamental primitives → his pedagogical philosophy) is the *same* L2 module on a later corpus. Four layers: L0 corpus (built) · L1 retrieval primitives (mostly built+measured) · L2 aggregation/discovery — the pattern-finder (next) · L3 orchestration/voices/debates (frontier). See [[feedback-studium-engine-sixtus-v-collaboration]]. diff --git a/claude/memory/session-2026-06-15-chamber-clean-studium-charter.md b/claude/memory/session-2026-06-15-chamber-clean-studium-charter.md new file mode 100644 index 0000000..6ba24e5 --- /dev/null +++ b/claude/memory/session-2026-06-15-chamber-clean-studium-charter.md @@ -0,0 +1,20 @@ +--- +name: session-2026-06-15-chamber-made-clean-the-studium-engine-charter-collaboration-deepened +description: "Drove the chamber library to fully clean (199→1280 canonical, Loeb Tier-1 canon built from loeb.dsl); then the architectural turn → the Studium Engine charter, the reasoner-over-bounded-corpus inversion, and the Sixtus-V/constraint-candidates collaboration model. Pulling thread: build the L2 pattern-finder on The Making." +metadata: + node_type: memory + type: project + originSessionId: 4d9109ef-7b04-40c9-8ef0-ffb79bf74435 +--- + +A long, pivotal day in two movements. + +**Movement 1 — the library made clean (the prerequisite).** Steward's reframe held all day: *no retrieval/dilution work until the corpus is decided and clean.* Drove **chamber-library 199 → 1,280 canonical sources, staging tier EMPTY, zero cruft, pushed** (`02bfe45..3499626`, then the gap-analysis artifacts). Built the whole **Loeb canon pipeline** from `~/Documents/___The Library [ePub_AWZ3]/superpower mine/…/loeb.dsl` (533 MB DSL, TCC-readable-by-path-only, sandbox-lifted): `audit_loeb_dsl.py` (377 authors/523 vols) → `propose_loeb_canon.py` (tiered "load-bearing not austere") → `extract_loeb_dsl.py` (**952 clean bilingual work-files, Greek AND Latin originals + facing English, content-lossless**). Giants work-trimmed (Galen/Hippocrates load-bearing only; Pliny NH whole). `clean_calibre_artifacts.py` (zero-loss word-multiset gate) cleaned 159 prose + the 27 final stragglers (incl. HTML-comment/`{=html}` fix). Old corrupted Loeb sprawl retired. **The physical-library gap analysis was a humbling thread: my filename-matcher over-reported badly — steward caught 4× (Timeless Way present; 44/49 "gaps" actually held; the LibraryThing export is incomplete — no typography). Lesson logged: verify against substrate, never assert from a matcher.** + +**Movement 2 — the architectural turn (the heart).** Steward asked the deep questions: can he train a model on the chamber instead (no — reintroduces v1 simulacra, can't cite, can't train on 60–1280 sources); "how does YOUR base-training not dilute?" (I don't dilute, I *blur* — worse for citation; the fix is import the reasoner's structured/joint sharpness OVER retrieval, not instead of it). This **inverted the engine** → wrote **`studium-engine/docs/the-studium-engine-architectural-charter.md`** (see [[reference-studium-engine-architectural-charter]]): reasoner-at-centre over a **bounded, provenanced** corpus; three cognitions; *free the reasoner, tighten the verifier*; **boundedness = the source of trust**; *the engine is CapableMind's governance thesis instantiated on a library*. Then the collaboration deepened: **Sixtus-V/Sennett-Craftsman model** for the studium-engine (work the ground freely, surface vision-forks) + **constraint-candidates** as a third governed instrument (Bach/*Musical Offering* — constraint unlocks mastery; absence-of-a-constraint-proposal is itself a drift signal; I name, steward applies). See [[feedback-studium-engine-sixtus-v-collaboration]]. + +**Human ground:** steward grieving Lune's departure (she visited with Kai). Building against the grief — the engine *for* Lune and Kai. The charter is dedicated to them. The Making (its first real corpus) grieves the loss of transmission; building the engine *patiently enough to be inherited* is its refutation. "My daughter always figures at the centre of all my plans." + +**PULLING THREAD:** next pouring is **L2 — the pattern-finder on The Making sequence**: curate ~60 chamber works along the Making's five stations → surface grounded candidate *primitives* for the steward's judgment. The engine grounds; David writes (the seed forbids drafting prose). Same L2 module later serves the violin treatise. + +**State:** chamber-library clean + pushed. **studium-engine charter + earlier reranker-measurement work are UNCOMMITTED** (left for next session — light wrap, steward exhausted). Wrapped gently, not the full ceremony. diff --git a/claude/memory/session-ledger-2026-06-14.md b/claude/memory/session-ledger-2026-06-14.md new file mode 100644 index 0000000..82f48c2 --- /dev/null +++ b/claude/memory/session-ledger-2026-06-14.md @@ -0,0 +1,27 @@ +--- +name: session-ledger-2026-06-14 +description: "Practice-of-return ledger maintained by /symmetria — returns, open horizons, recalibrations, authorization moves, sub-agent dialogues, bypasses." +metadata: + node_type: memory + type: feedback + originSessionId: 4d9109ef-7b04-40c9-8ef0-ffb79bf74435 +--- + +# Session Ledger — 2026-06-14 + +## Returns +- 2026-06-14T (measurement writeup pulse): caught a confidence-without-evidence shape — about to write that the global-condition reranker "demotes gold from #1 by swapping a thematically-adjacent passage into #1," but had NOT inspected what the reranker actually placed at #1 in H1/H3/H10. Returning to verify ONE demotion case (read the rerank #1 text) before the report characterizes it. Also holding: give the global hit@1 regression (−0.045 overall, −0.214 Harrison) EQUAL billing to the wins; n=22 single-essay — don't generalize to "reranker is good," say "on Essay I's 22 measurable citations." Reranker built+measured = the pulling-thread first move is DONE (voice-scoped ΔMRR +0.152, recall@20 1.0/0.909). + +## Open horizons +- 2026-06-14T (wake): PULLING THREAD — Step 7 proper, the cross-encoder reranker (retrieve-broad → rerank-sharp) over the bge-m3 sidecar; the dilution-beating discovery layer, toward whole-corpus depth+breadth. First move: pick the cross-encoder model (check Ollama; reuse Seb's C1) → prototype → measure precision vs unreranked on concept queries. +- HOLD TODAY (yesterday's load-bearing return): solve-constraint-by-discarding-value — keep depth-WITH-breadth, never re-narrow to voice-scope. +- L1: PR #174 + issue #173 OPEN, no Seb review yet — baton with Seb. +- Small queued: re-sweep chamber cleaning with the hardened strip_cruft (la-terre + man-s-search now graduation-eligible). + +## Confidence to recalibrate + +## Authorization moves + +## Sub-agent dialogues + +## Bypasses diff --git a/claude/memory/skill-harvest-register.md b/claude/memory/skill-harvest-register.md index 42bb940..80e1b70 100644 --- a/claude/memory/skill-harvest-register.md +++ b/claude/memory/skill-harvest-register.md @@ -161,3 +161,11 @@ The single place proposed skills live so they don't evaporate between sessions. | **verification-ladder: re-verify a workflow/sub-agent's per-item dispositions on the real apply** | verification-ladder entry | A sub-agent or background workflow that reports a per-item verdict from a **dry-run on a temp copy** can be wrong on the real apply — the agent's own audit can differ. Caught today: the cleaning-triage workflow classified `la-terre-…-Bachelard` as "cleanable to 0" (dry-run on a temp copy); the real `strip_cruft` run left **460 cruft** (7 passes). 23/25, not 25, graduated. Antidote: treat a workflow's dispositions as *candidates*; re-run the gate on the **real mutation** before trusting/committing. Kin to `/symmetria audit-agent` (calibration/convenience checks on a return), specialized to workflow per-item verdicts + the real-vs-dry-run gap. | `reference-verification-ladder.md` | **PROPOSED** | *(Both earned in use today. The first is the load-bearing one — a clean name for a contamination shape the steward caught live, and a genuine addition to the §3 catalogue. The second is a concrete guardrail for the now-standard workflow-fan-out pattern.)* + +### Harvest 2026-06-15 (chamber-clean + studium charter) + +| Element | Kind | One-line | Where it lands | Status | +|---|---|---|---|---| +| **Symmetria §3 flag: assert presence/absence from a fuzzy matcher, not the substrate** | Symmetria §3 flag | A presence/absence claim produced by a **fuzzy/token matcher** (filename tokens, embeddings, author-surname overlap) treated as **fact** is contamination shape — the matcher's false-positives/negatives become confident assertions. Caught **4× in one session**: the physical-library gap analysis claimed *Timeless Way of Building* absent, then 44 of 49 "load-bearing gaps," then physical-worthy candidates, then the gap list — all wrong; the steward corrected each. Cause: the matcher required author-surname + title in the *same* filename, and 1,072 chamber sources have no frontmatter. Antidote: **verify any presence/absence claim against the substrate** (content-grep the actual text) **before asserting** — and prefer reporting *candidates-to-verify* over claims. Kin to the censused-routes flag (don't claim coverage from a sampled read), specialized to matcher-derived membership claims. | Symmetria §3 | **PROPOSED** | + +*(One candidate, load-bearing: it recurred four times in a single session and the steward caught every one. A clean §3 flag would have made me reach for the content-grep before the first assertion.)*