17 KiB
name, metadata, permalink
| name | metadata | permalink | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
claude-memory/memory |
Claude Code Memory
Standing preferences
- CapableHands standing authorization — M4 mini david@10.0.1.136 durably authorized for remote OCR/inference; don't re-ask permission to use it (steward 2026-07-01).
- Governance files are dotfiles symlinks —
~/PENDING.md/~/REVIEWED.md/~/CLAUDE.md→~/dotfiles/…; Edit/Write refuse to write through a symlink, so edit the real dotfiles path when appending PENDING/REVIEWED. - Typography palace — query via CLI — type masters (~20-21 sources) in a dedicated MemPalace at
~/.mempalace/palace-chamber-typography; querymempalace --palace <that> search "…"(CLI). For ARC typography — don't re-ask where it lives. - Fowler's rules for quotation — single quotes primary, double for nested, logical British punctuation order. Apply across all writing.
- Canadian spelling in ARC prose — centre/colour ("almost EU"); corpus "center" = autocorrect drift (10 files, cleanup open). Draft all steward-voiced prose in Canadian spelling.
- Rank on fields you actually write — 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.
- Shorter, concentrated sessions — steward preference (2026-07-13): shorter but very concentrated — ONE tightly-scoped high-leverage bite taken all the way, then wrap; hold the rest as ranked horizons.
- Constitution-as-block, then pull-based corpus — steward discipline (2026-07-14): finish the constitution as one block FIRST, THEN corpus-into-spec pulled by what each engine phase needs. Bounded question → bounded answer; don't surface N new threads; keep open-thread count LOW. Above feedback-shorter-concentrated-sessions.
- Close thoroughly — no frequent deferrals — steward directive (2026-07-16): frequent deferrals ARE how the cloud accumulated; close ALL of a block that's closable-now; distinguish closable-now vs genuinely-blocked (name the specific dependency, never a vague defer). Completeness complement to feedback-constitution-as-block-then-pull-based-corpus.
- Checkable claim surfaces bugs — insisting on a checkable claim (number, substrate-fact, discriminating test) over a soft classification repeatedly EXPOSES a real bug; the demand for verifiability is itself a defect-detector. Steward-named 2026-07-13. (Caught F-5 + the "finally" overclaim, 2026-07-17.)
- Completion is a tripwire — the feeling of "done" is the cue to verify the tail (census/gate/scan-check), not the signal to ship; the last 10% is invisible from inside the first 90%. Ninety-Ninety as a security property (steward 2026-07-06).
- Studium Engine charter — the engine's constitutional doc (
studium-engine/docs/the-studium-engine-architectural-charter.md): reasoner-at-centre over a BOUNDED provenanced corpus; three cognitions; boundedness=trust. Read before building the engine. - Studium Engine = Sixtus-V craftsman collaboration — work the ground freely (I build, surface only vision-forks); constraint-candidates = 3rd governed instrument (I name, steward applies). Studium-engine only; heavier loop for L1/L2.
- Trust prior pass frame — 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.
- MemPalace is an unaffiliated stopgap — MemPalace is third-party; steward/Seb build BMF/CapableMind (hoped to replace it). Don't conflate them (3rd steward correction 2026-06-05 — the conflation even reached a skill name and was retracted); MemPalace PRs await MemPalace's maintainers, NOT Seb.
- Skill-harvest register — canonical home for proposed skills (governed analog of PENDING.md for tooling). FULL REVIEW RULED 2026-07-19, all four strokes (⚖ block at top is authoritative): §3 consolidation BUILT · ladder batch-append + register compaction = next housekeeping slot.
/jurist-packageBUILT 2026-07-20 (proven 2×);/model-handoff= next build ·/graduate-chamber-sourcehold-condition now MET (one-door lane RULED, v2.3.0 operative). Patch BUILT 2026-07-20 (steward-authorized):/jurist-package— "trace a ruled finding's inference, not just its words" (Load-bearing disciplines; 2× jurist-caught). - Copy-paste-clean governance drafts — draft PENDING/REVIEWED placement blocks as plain fenced markdown; display formatting leaks into the placed record (REVIEWED-59 header, 07-16).
- Verification ladder — the named instruments (byte-identical compile gate, delta classification, censused-routes, fresh-clone gate, measure-toolchain-before-spec…); reach for the gate the claim's shape demands instead of re-deriving.
- Plane coordination workflow — CENTRAL to steward↔Seb (est. 2026-06-02):
app.plane.so/capablemind, thin effort-tasks[BM #N]over canonical GH issues. ⚠ BBF = BetterBridge product, NOT the board. Plane MCP OAuth (ToolSearch select:mcp__plane__*);create_work_itemneedsdescription_html. Detail in file. - Resurface banked notes before re-deriving — when an idea was already captured (runbook known_gaps, skill-harvest, prior note), READ the note before re-deriving; re-derivation drifts (page-numbers mis-recalled as provenance vs structure-scaffolding, steward re-corrected 2026-06-27). The engine's own purpose, turned on my practice.
- Verify-before-compose hook — chamber-library constitutional writes (spec · graduation-spec · amendment/FOR-JURIST/JURIST-PACKAGE) are BLOCKED by a PreToolUse hook unless they carry
<!-- GROUNDED-IN: … -->+ a Grounding section quoting the ratified sections. The action-time enforcement the prose lessons (feedback-resurface-banked-notes-before-rederiving) lacked; don't fight the block. Steward-directed 2026-07-17 after the re-derived-from-training failure recurred on #2. - Tool review after each use — steward directive (2026-06-16): review every tool we built after each run (success OR failure), capture what it taught, iterate until reliable; PASS-BUT-FALSELY is the priority signal. Log at
chamber-library/_curation/tool-evolution-log.md. Proven same day (audit_cruft hardening → 160 hidden-dirty files surfaced). - Engine sources graduate to the permanent chamber — steward policy (2026-06-28): any work added for the engine ALSO becomes permanent chamber collection unless expressly stated; take it ALL the way (clean→verify→graduate→catalogue→sidecar); never leave staged. The chamber accumulates. ⇒ all ~30 Making sources graduate in.
- Notes are part of the work — steward directive (2026-06-28): footnotes/endnotes are integral — KEEP+CONVERT them (
<sup><a>→[^N]), never drop on graduation. (Caught dropping Taylor's endnotes — wrong.) - The maturation of the chamber — a dialogue — the pivotal 2026-06-28 exchange on the chamber's telos (fidelity-without-trust; reading-is-unsolvable-is-the-feature; L2/engine=answerable-not-pure). Companion to project-studium-engine-telos-chamber-of-voices.
Canonical Workstream Trackers
Read the tracker for any active workstream at /wake-up before composing the briefing. Append substantive moves at /wrap-up. Per feedback-canonical-workstream-tracker-discipline.md.
- MemPalace wind-down — DONE (steward 2026-07-07):
palace-memorywound down, wake/wrap rewired to the files layer; KG exported (knowledge-graph.jsonl). Typography palace KEPT (separate instance). - ARC open-work register — the single code-verified source of truth for what is OPEN on ARC (post-Stage-G, built 2026-06-11). Read THIS for remaining ARC work (A1 Vignette, A2 cul-de-lampe, content sweeps, Phase-2/held set, REVIEWED-placement debt), not the chronological tracker.
- ARC — canonical ARC workstream tracker (chronological record 2026-04-16 →). Status: STAGE G DONE/SEALED (GPG
ac0a7ee, 2026-06-10) — reactive mode governs. Open work → project-arc-open-work-register (A1 Vignette · A2 cul-de-lampe · content sweeps · Phase-2 held set). Chronological detail in the tracker file. - 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. - Studium engine telos — the chamber of voices — the ultimate goal, above the build plan: David's childhood chamber of hero-voices → discourse with his library + voices conversing, this time accountably (v1 was eloquent/unaccountable; same ambition built grounded/citable). Why verbatim fidelity is load-bearing.
- Studium = CM's unfettered sandbox — Studium/chamber are personal projects Seb now sees as fundamental to CM; experiment freely on the library/engine without risking CM's runtime, breakthroughs transfer back (V2 verifier = live example). Steward-framed 2026-07-08.
- Making sequence source set — COMPLETE against the ReadingList as of 2026-06-18 (reconciliation-verified); census of what's sourced where, sourced≠ingested (only Pos I in manifest), the Handke-German decision (original is source), the Levi drop-cap gate (RESOLVED STALE 2026-07-19 — initials present). Read before any Making/studium source work.
- Source library — link + dedupe — steward's master ebook library =
~/Documents/___The Library [ePub_AWZ3]/(2190 ebooks, messy nested). GOAL: link chamber↔sources (provenance index) + dedupe; real link needs EPUB/PDF internal metadata + edition-identity, not filenames. Detail + seed in file. - Character-as-image hazard — some EPUBs render diacritics/non-Latin script as INLINE IMAGES; the standard image-drop SILENTLY MUTILATES them (PASS-BUT-FALSELY). Tripwire = audit_cruft md_image count; INSPECT before dropping; character-bearing images = CONTENT (map→Unicode). (Alter's Psalms parked pending a glyph-map.)
- Sidecar typology — protocol-dependent reading-indexes — TWO layers:
.meta.jsonstructural sidecar = PROTOCOL-NEUTRAL (the graduated bar); reading-indexes (rich YAML) = PROTOCOL-DEPENDENT, probably PLURAL — don't design the schema yet; settle corpus to gold, let protocols declare themselves. Steward 2026-06-29. - Studium Engine — no tracker file yet; moves in per-session memories + the architectural charter. Steps 0–7 built; corpus CLEAN; V1
verify-quoteBUILT +fidelity_equivalence@2GOVERNING (2026-07-19; @1 frozen; dash refused/evidence-gated; Greek/Latin census owed → @3). Stage-1 rebuild plan (studium-engine/docs/stage-1-rebuild-plan-2026-07-05.md): V0+N0 ruled · V1 done → V2→V4 / N1→N3. Collaboration = feedback-studium-engine-sixtus-v-collaboration. - L1 reliability — canonical L1 tracker (est. 2026-05-28). Latest: N6 deploy #175 live+holds; CapableHands-as-BMF-clasp = PRIORITY (PENDING-41). L1 behind the Studium/chamber focus. Read the tracker before L1 work.
- Be (laundromat) — canonical Be tracker (est. 2026-06-08). Be = Skemantix startup (Seb+David) funding CapableMind's ladder; bridge, not venture. Decisions LOCKED (entity/pricing/infra in file); a11y gate MERGED. Pre-revenue WTP gate = renovate Pat → charge her; discipline: no new spec until it clears → nothing for executor on be. Repo @
f43a0fd.
Active Session
- Session 2026-07-20 — /jurist-package BUILT · PENDING-67 + F2 RULED · v2.3.0 OPERATIVE — The whole one-door/lane/F2 arc closed to an OPERATIVE constitution in one day (chamber
51ce3dd→33f795c, both remotes; engine untouched). (1)/jurist-packageskill BUILT (dotfiles canonical + symlink; grounded in the 2 proven exemplars, not recall; carries self-containment law · GROUNDED-IN gate · invariant skeleton · consequence-trace-one-level-deeper · copy-paste-clean REVIEWED draft; absorbs/spec-amendment). (2) PENDING-67 package = its first exercise → RULED (REVIEWED-67): born-digital EPUB off Docling; my "no new constitutional text" lean OVERRULED — III.1 eligibility rule IS constitutional (§V forbids the acts but is silent on who must demonstrate compliance, when, by what evidence — the gap PENDING-56 fell through; A3 legibility); Q5 DISCHARGED by a performed check = verified-zero (no EPUB-via-Docling in canon ever). (3) F2 diagnose-before-fixing OVERTURNED its premise: the injector already pairs all 10 Eichmann footnotes (pandoc emits 10 native[^N]); the pilot's "0 reciprocity / 2,180 refs" wasaudit_footnotes' HEURISTIC under-count, inherited into a jurist ruling — [challenge-the-framing], NOT built. Widened to all 48 (29 no-reciprocal-fn · 10 pairs-all [blocker = verify-guard benign delta] · 6 partial-gap · 3 no-source). F2 RULED: §5 withdrawn; Q2 SPLITS (de-glued number = provisional FIX; URL-fragment exclusion = PRINCIPLED markup-token class rule, never a per-file allow-list); Q4 verify-guard first proven at HIGH pair-count; datum-not-ledger GRADUATES to constitutional. §3 catches resolved (Montaigne reciprocal = different edition; 29-bucket relabel validated — Taruskin/Russell/Don-Quixote are one-directional). (4) v2.3.0 FOLD → CUT → OPERATIVE (REVIEWED-68): three ruled designs folded atomically; placement ruling corrections applied (the vacuity reversal — my draft reversed the very Q2 finding it landed; converter-worse→lexical content; curation-bearing second-pilot condition RESTORED aspromotion.scale_applicationowed; omnibus values out; datum-not-ledger→§VII not §Trust-Attestation); v2.2.0 frozen byte-identical, bounded-diff PROVEN (8 removed = the four intended edits, 145 added). PULLING THREAD: the verify-guard benign-delta fix (test-first, proven at HIGH pair-count — Zibaldone 3,797) → then Eichmann through the now-ruled ordered born-digital lane toward graduation (turns the arc's constitution into a verified Making source). LITERAL Q: is the "URL-fragment/link-target = markup, not body word" exclusion class determinable PURELY from the injected EPUB's own markup (the anchors inject_epub_footnotes touched — it knows which hrefs it converted), or does it need the reference comparison? Read the injector'sconverted_markersallow-list + the end-to-end verify's word-multiset comparison FIRST; "purely from the injector's touched-set" would be the clean converter-agnostic fix. Read the session file at wake.
Historical reference → MEMORY-reference.md
Older archived-session pointers and the stable reference layer (steward profile · project-state detail · L1/L2/Chamber inventories · legacy pending-work · reference-file list) live in MEMORY-reference.md — consult on demand; not loaded at wake. Recent cross-session trajectory comes from the Active Session entry above + the recent session-*.md files (wake §2.b.1; the MemPalace handoffs glance was retired 2026-07-07 with the wind-down).
Index discipline (self-bounding — keep this file lean)
Wake-loaded live index; hard budget well under the harness load ceiling. Keep to: Standing preferences · Canonical Trackers as one-line pointers (chronological detail lives in the linked tracker files, not here) · Active Session · these pointers. Rotation + budget-breach handling are wired into /wrap-up (demote prior Active Session on promote) and /wake-up (truncated load = flag + trim). Back up before restructuring. (Compacted 2026-07-17: entries re-slimmed to tight one-liners, 20.5→<17.1KB.)