dotfiles/claude/memory/MEMORY.md

name, metadata, permalink

name	metadata	permalink
	node_type title type permalink originSessionId modified memory MEMORY note claude-memory/memory 22915403-bc5d-4796-9c7d-196b7c30d2f9 2026-08-06T14:55:31.323Z	claude-memory/memory

Claude Code Memory

Standing preferences

• Chamber work: ground in constitution + charter + runbook FIRST — any chamber work or talk about it begins by reading the library constitution · engine charter · conversion runbook (incl. reanchor:). Repo CLAUDE.mds are pointers, not state. Corpus claims come from a self-tested tool, never a hand grep. Enforcement mechanism owed.
• 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).
• Every canon doc's source lives in Chamber Sources — a canonical's source = whatever resolve_archived_source returns (never the master library or a path in a doc/frontmatter); read the banked source record before calling a mismatch a defect.
• Steward maps live in ~/dotfiles/maps — a map = an artifact David reads directly to orient. Write it into ~/dotfiles/maps/ and symlink to the Desktop, never straight onto the Desktop; wake-digest.py reports strays.
• 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 — PENDING/REVIEWED only. ⚠ That refusal is a tool artifact, not a permission check, and this note is the documented route past the only friction guarding the constitution (PENDING-107: no permissions key; the one hook fires on ~/CLAUDE.md and exits 0 by design; Bash isn't gated at all). ~/CLAUDE.md/~/REVIEWED.md/L2 = [ESCALATE], steward's hand — a jurist sign-off does not authorize one.
• Typography palace — query via CLI — type masters (~20-21 sources) in a dedicated MemPalace at ~/.mempalace/palace-chamber-typography; query mempalace --palace <that> search "…" (CLI). For ARC typography — don't re-ask where it lives.
• The central path — answerability, not purity — the contamination recursion is probably irresolvable, so stop certifying the parties, bind the claims. Route by claim-type: checkable → produce the check + a falsifier; judgment → disclose standpoint in one line, decide, record; undecidable → name it open. One layer of disclosure, then act — never audit the audit.
• 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 — finish the constitution as one block FIRST, then corpus-into-spec pulled by what each engine phase needs. Bounded question → bounded answer; keep open-thread count LOW.
• Close thoroughly — no frequent deferrals — frequent deferrals ARE how the cloud accumulated; close ALL of a block that's closable-now; distinguish closable-now from genuinely-blocked (name the specific dependency).
• Removing a claim ≠ removing the reliance — cutting an unsupported sentence can hide the gap rather than close it; the dependency survives, now invisible to every check. Test isn't 'is the bad sentence gone' but 'does the conclusion still need it'.
• 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.)
• Derive the rule from the consumer, not the survivor — picking between two disagreeing implementations is selection, not derivation; derive from what a CONSUMER must do. Complementary-correctness defeats sampling.
• Census by mechanism, not proxy — census by RUNNING the real pipeline, not a proxy; distrust the finite-feeling bucket that arrives when you want to feel done.
• 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. The prior pass tested what it tested; your extension claims what it did not test.
• MemPalace is an unaffiliated stopgap — third-party; steward/Seb build BMF/CapableMind. Don't conflate them. MemPalace PRs await MemPalace's maintainers, not Seb.
• Skill-harvest register — canonical home for proposed skills (governed analog of PENDING.md for tooling); /wrap-up §1.6 proposes, steward authorizes. Register compaction + ladder batch-append owed — it exceeds read caps (tripwire 2026-07-22). Built: /jurist-package, /model-handoff. Ruled/held detail in the file.
• 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: app.plane.so/capablemind, thin effort-tasks [BM #N] over canonical GH issues. ⚠ BBF = BetterBridge product, NOT the board. Detail + MCP setup 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.
• Verify-before-compose hook — chamber constitutional writes are BLOCKED by a PreToolUse hook without <!-- GROUNDED-IN: … --> + verbatim Grounding. Don't fight the block.
• Tool review after each use — review every tool we built after each run (success OR failure); iterate until reliable. PASS-BUT-FALSELY is the priority signal. Log at chamber-library/_curation/tool-evolution-log.md.
• Engine sources graduate to the permanent chamber — 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.
• 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.

• Chamber as versioned releases — THE GOVERNING FRAME for all library work. Realize the 2000-year Chamber as versioned releases with soft borders, each serving a PURPOSE. Scope every library bite through this. Open decision: which purpose anchors V1 — see the facet formalism in studium-engine/docs/parallel-tracks-…2026-08-03.md.
• The Chamber touchstone — the why — seven questions to test work against when lost in the trees. Read at Step 0 of any chamber work, before constitution/charter/runbook. Holds no state; does not decay.
• The Chamber vision is NOT in one place — it lives in seven sources across two repos + memory (census in file). A single home would become an eighth unless it supersedes or points.
• MemPalace wind-down — DONE (steward 2026-07-07): palace-memory wound 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 (2026-06-18, reconciliation-verified). Sourced ≠ ingested; the Handke-German decision; Levi drop-cap gate RESOLVED STALE. 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 — EPUBs rendering diacritics as inline images are SILENTLY MUTILATED by image-drop. Mechanism built (apply_char_glyphs.py, REVIEWED-70/v2.5.0), wired as a born-digital precondition; per-source glyph-maps still owed. VIEW the glyph; map to SOURCE form.
• Sidecar typology — protocol-dependent reading-indexes — TWO layers: .meta.json structural 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 + docs/tool-evolution-log.md (built 2026-08-04 — organ reviews; read its §0: the discipline is attached to the human, so an automatically-invoked organ leaves no entry). Steps 0–7 built; corpus CLEAN; V1 verify-quote + fidelity_equivalence@3 GOVERNING (ratified 2026-08-05, REVIEWED-87 — @2/@1 frozen; @3 = @2 + markup-delimiter exclusion, on ENGINE grounds + functional analogy, NOT chamber alignment. Greek/Latin census still owed and is a SEPARATE bump). ⚠ Quoted tier accepts 6/17 of real human citation (was 3/17) — the residual is elision/truncation/nested-quotes, not corpus defects; PENDING-99. ⚠ The consuming end was first exercised 2026-08-04 and does not answer: bare FTS tokens are conjunctive, no semantic layer, no test on retrieve.py at all (PENDING-97; silence now discloses its blindness, PENDING-96 landed-but-open). Stage-1 rebuild plan: V1 done → V2→V4 / N1→N3.
• Instrument censuses — have our gates ever fired? — ~/dotfiles/claude/governance/fool/: census 01 (does each gate have a real negative instance? → decay, not construction, is the failure mode) + census 02 (has it ever fired at all? → the record divides by whether a human invokes it). Both pre-registered before the look; both had prediction 5 invert. Read before trusting any gate's silence.
• L1 reliability — canonical L1 tracker. BLOCKED ON SEB (PENDING-94) — nothing moves until he rules; BMF is down and staying down. The replay has never resumed, only restarted: minCursor is a minimum over all 11 modules and two never participate ⇒ every start rebuilds from seq 0 (13/13, 0 catch-up). Completion is gated by uninterrupted run length, not rate — which is why ANALYZE/B1.1/N6 were all real and all changed nothing. Recall never worked either (retrieval_count = 0 across the whole April–June graph). Yesterday's "ingest mystery solved" was corrected 2026-08-04. Read the tracker before ANY L1 work — walked past once on 2026-08-03.
• 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

⛔ NEXT = the chamber PARSE FIX — decided jointly with the steward at the 2026-08-06 wrap, not defaulted into. Make engine/retrieve.py accept a sentence; 26 of 27 real questions currently crash. Bounded, and it carries its own regression test (27 audited queries with known answers). ⚠ Inherited constraint, load-bearing: the fix must NOT make the engine answer more. Every obvious fix (strip punctuation, tokenize, add semantics) trades loud failure for plausible-but-wrong — the incident's exact behaviour. Read studium-engine/docs/chavruta-retrieval-measurement-2026-08-06.md §2 and §4 first: PENDING-97's filed description of the bug is wrong (you never reach conjunction; the query dies at parse). ⏳ Not my thread — do not confuse waiting with working: the Seb package (agreed: when it can be done well; no external clock — three measured L1 write-path findings are ready for it) · the L2 design note (every constitutional bound ships with a demonstrated negative instance, or it is documentation) — wants dwelling, deliberately not composed fast. REVIEWED-87 still drafted-not-placed while engine/fidelity.py:12 cites it as ratified. Q4 census + PENDING-104 brief need dates, not "later."

• Session 2026-08-06 — the note that said it could not happen — Both constitutional items CLOSED, not filed. Constraint #1 reworded by the steward's hand after the executor declined a jurist authorization it did not hold — the tested case, and it held. The 08-04 "BMF stays down" decision had not held: the tracker's "⚠ No KeepAlive" note is inverted (plist unchanged since 03-07: KeepAlive{SuccessfulExit:false}+RunAtLoad:true) — a crash restarts it; only a clean stop leaves it down — so the 08-04 kill resurrected it, and the false note is why nobody re-checked for two days. Now bootout+disabled, both agents; prompt tax 3.11→0.22 s. Chavruta measured: 26/27 real questions CRASH, 0 empties; prediction pre-registered, graded wrong on mechanism. Three L1 write-path findings ready for Seb. Steward reframed the incident pass — he wanted the design transfer, not a repo audit. ⚠ Five same-class executor errors, three caught only by the steward.

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.)