session 2026-06-05 evening: housekeeping wrap — AI-posture ruling memory, MemPalace forensics + workaround, harvest register ruled, verification ladder, Symmetria flags, register wiring applied

2026-06-05 22:03:53 +02:00
parent 8cca9de024
commit 161fad7ae2
9 changed files with 170 additions and 10 deletions
@@ -9,8 +9,10 @@
 - [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 `<symbol>` 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.
- [MemPalace is an unaffiliated stopgap](mempalace-is-unaffiliated-stopgap.md) — MemPalace is third-party; steward/Seb build BMF/CapableMind (hoped to replace it). Don't conflate them; MemPalace PRs await MemPalace's maintainers, NOT Seb.
+- [MemPalace is an unaffiliated stopgap](mempalace-is-unaffiliated-stopgap.md) — 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 Don't conflate them (3rd steward correction 2026-06-05 — the conflation even reached a skill name and was retracted); MemPalace PRs await MemPalace's maintainers, NOT Seb.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](skill-harvest-register.md) — **canonical home for proposed skills** (create/patch/retire) awaiting steward authorization; the governed analog of PENDING.md for our own tooling. `/wrap-up` §1.6 proposes here; steward authorizes; `/wake-up` surfaces open proposals. Check at wake; append at wrap. Open now: `/spec-code-audit`, `bmf-diagnose`, `/arc-typeset`, `/pre-build-audit`, `/vignette` (deferred to Phase 2), Symmetria `trust-prior-pass-frame`.
+- [MemPalace wing-filter broken](feedback-mempalace-wing-filter-broken.md) — wing-scoped search → 'Error finding id' (upstream #1665, open at HEAD); search UNSCOPED + post-filter by wing. Don't run `repair` (#1589). Affects wake-up §2.b.3.
 - [Skill-harvest register](skill-harvest-register.md) — **canonical home for proposed skills** awaiting steward authorization; the governed analog of PENDING.md for our own tooling. **Full review 2026-06-05**: `bmf-diagnose` + `/pre-build-audit` AUTHORIZED (build-on-need); `/spec-code-audit` DEFERRED (first L1 audit); `/arc-typeset` REJECTED (superseded by §I.k build enforcement); `/vignette` still deferred (Phase 2); Symmetria §3 flags + verification-ladder BUILT same evening.
 - [Verification ladder](reference-verification-ladder.md) — 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](reference-plane-coordination-workflow.md) — **NOW CENTRAL to the steward↔Seb workflow** (est. 2026-06-02): `app.plane.so/capablemind`, BMF project, thin effort-tasks `[BM #N]` over canonical GH issues (effort-only, no technical detail; labels/priority mirror GH; issue attached as link). Executor keeps task state current as the 6-hour relay. ⚠ BBF = BetterBridge *product*, NOT the board. Plane MCP user-scoped/OAuth; load tools via ToolSearch `select:mcp__plane__*`. `create_work_item` needs `description_html`.
 ## Canonical Workstream Trackers
@@ -22,6 +24,9 @@
 - [L1 reliability](project-L1-reliability.md) — canonical workstream tracker established 2026-05-28 (Symmetria-pulse decision). Current state at top + Active umbrella (PENDING-24 six sub-items) + four-findings table + sources of truth + decisions made/deferred + skill-harvest candidates + chronological log 2026-03-21→. Active goal: **working proposition for Seb by Monday 2026-06-01** (steward 2026-05-28, "bring him relief"); deadline shifted to mid-July. Read tracker at /wake-up before composing L1 portion of any briefing.
 ## Active Session
 - [Session 2026-06-05 (evening) — housekeeping slate CLOSED + AI-posture ruling LIVE + MemPalace forensics → BMF design inputs](session-2026-06-05-evening-housekeeping-ai-posture-mempalace-forensics.md) — **chamber-library LFS RETIRED** (history rewritten; fresh-clone gate: remote holds the corpus for the FIRST time since import; backup dir awaits steward delete); REVIEWED-28/29 filed; **wrap §6.5 dotfiles-push + wake §2.c check BUILT**; CM-AI/studium committed — **SEB MOVED: 12 commits + cover note `b4daa71`** (arc closed; smoke run → cold-start finding; six asks); **AI-posture RULED+DEPLOYED** (`ai-train=no/ai-input=yes`; WAF 403 lifted; repo-authored robots.txt; belt-and-braces WAF rule; *a dashboard default never again speaks for the house*); harvest register FULLY RULED (/arc-typeset rejected, /spec-code-audit deferred, 2 skills authorized, ladder+flags built; MemPalace≠BMF 3rd correction — merge retracted); **MemPalace broken at HEAD** (#1665 et al.; wing-filter workaround = search unscoped; `repair` booby-trapped — NOT run); tooling scan: **Basic Memory=TRY**, files-authoritative class read; **BMF nuggets → CM-AI `l1-reliability/substrate-failure-lessons-2026-06-05.md`**. **Pulling thread: THE SEB REPLY — hard commitment, tomorrow's opening (Tier A + mindfabric-00 probe), before bio/CV and all MemPalace follow-ups.** Literal Q: did Seb push overnight + is mindfabric-00 warm enough to probe? Sub: posture-demotion ruling? 2 PROPOSED patches? backup dir?
 ## Archived (2026-06-05 morning — six-arc day)
 - [Session 2026-06-05 — §I.k.c + heteronym decompose (PENDING-25 LIVE) + SEO layer + cascade Stage 1, six arcs ALL DEPLOYED](session-2026-06-05-ikc-decompose-seo-cascade-stage1.md) — **§I.k.c Spanish shipped** (`76c75bd`: guillemet-balance walk for comillas node-replacement; apertura = first LINT class; 4 steward rulings; 15 gates idem=True; born dormant). **Heteronym decompose = PENDING-25 LIVE** (`e2866da`: EN work + fr/es renderings under the work's slot `/slug/fr/` mirroring `/v/`; Lingua: selector §VII.i zero-JS; cohort route policy = class precedent; jurist REVERSED sequencing to before-Stage-G conditional + RATIFIED translator:-optional/absence=self-translation; BOTH filters broke dormancy — FR 13×U+202F, ES 4 comillas pairs; render gate caught glued FR colons + ES dashes→9 rayas + datelines deleted). **SEO layer live** (`6d6f69d`: robots NO-disallow w/ rationale; sitemap 245 URLs all resolve-verified; head dup RESOLVED into templates/head.html; siteRoot absolutization; og:type-never-article latent defect fixed ×223; /v/ canonical→ACTUAL route + noindex; published/updated split; hreflang; ⚠ CloudFlare prepends Content-Signals ai-train=no — steward policy Q parked). **Re-partition reframed**: north-star AMENDMENT — @layer = cascade DECLARED, ideal form IS lower-risk; **Stage 1 @use BYTE-IDENTICAL twice** (`c37a3bd`; _foundation.scss; 56 !important await Stage 2). **Pulling thread: cascade Stage 2 (@layer declaration, !important census first) — but tomorrow OPENS with bio/CV translations** (texts' location unknown — ASK; machinery is posts-only, pages extension bounded). Literal Q: where do the bio/CV FR+ES translations live + does Lingua sit on about-pages as on posts? Sub-checks: REVIEWED entries (PENDING-25 + 3 jurist rulings)? chamber-library (7th day)? ai-train posture?
 ## Archived (2026-06-04 evening — .whisper + §I.k.b)
@@ -0,0 +1,12 @@
 ---
 name: feedback-mempalace-wing-filter-broken
 description: "MemPalace wing-filtered MCP search raises 'Error finding id' (upstream #1082/#1665, open at HEAD as of 2026-06-05). Workaround: search UNSCOPED and post-filter by the wing field in results. Affects /wake-up §2.b.3's wing-scoped searches."
 metadata:
  node_type: memory
  type: feedback
 ---
 MemPalace wing-filtered `mempalace_search` fails with `Error finding id`; unscoped search works (verified 2026-06-05, 46,918 drawers intact). Upstream: #1082/#1665 (exact signature), #1564 (chronic HNSW quarantine — 22× since 2026-05-26), #1579 (repair-status blind), #1589 (`repair` can SIGSEGV/produce unloadable segments — DO NOT run `repair` casually). All open at origin/main HEAD.
 **Why:** HNSW↔sqlite drift; the wing filter path hits ids the index lost.
 **How to apply:** omit `wing:` in `mempalace_search`; post-filter results by their `wing` field. Re-test wing-scoped occasionally; delete this memory when #1665 closes. Related: [[mempalace-is-unaffiliated-stopgap]].
@@ -0,0 +1,40 @@
 ---
 name: reference-verification-ladder
 description: Canonical home for the proven verification instruments — the named gates any session reaches for instead of re-deriving. Steward-authorized consolidation 2026-06-05 (skill-harvest ruling); ends the per-wrap re-proposing of individual instruments.
 metadata: 
  node_type: memory
  type: reference
  originSessionId: b3202a24-301f-499d-af9e-ac5368dd2c73
 ---
 # The Verification Ladder — named instruments
 Proven gates, each earned from a real catch. Reach for the one the claim's shape demands; a claim without its gate is an assertion. Linked disciplines: [[feedback-trust-prior-pass-frame]], [[feedback-verify-each-post-type-after-changes]], [[feedback-rank-on-fields-you-actually-write]].
 ## Output-equivalence claims ("this refactor changes nothing")
 - **Byte-identical compile gate** — prove with `cmp`/`diff` at BOTH the direct-invocation level and the full-pipeline level. Proven 3×: SCSS Stage 1 (`c37a3bd`), site.hs listing generator, §I.k transform dormancy.
 - **Expected-delta gate** — when diff=0 is impossible, prove the delta's *complete shape*: `sort -u` over all per-file diffs; every line must belong to a named class (2026-06-04).
 - **Delta classification** — corpus-wide variant: classify EVERY changed line into named classes; the unclassified residue must be exactly empty-or-whitespace. Catches what sampling misses, including one's own shipping comments (decompose + SEO passes, 2026-06-05).
 ## Coverage claims ("all X were handled")
 - **Exhaustive route/rule census** — enumerate ALL routes/rules/sections before classifying any; classify each explicitly; no sampling. (The censused-routes discipline; §I.k.c measuring read.)
 - **Count first, then look** — never read a census through truncation (`| head`, clipped listings). `wc -l` before inspection; 3 same-day instances 2026-06-05 (chamber/CM-AI/studium untracked files).
 ## Build/render claims ("it works / it looks right")
 - **Render-and-LOOK** — render the artifact and read it before asserting; never reason from the remembered model (caught glued FR colons, feTurbulence errors, viewport misreads).
 - **Per-type × per-viewport** — after any shared CSS/template change, every content type on desktop AND phone ([[feedback-verify-each-post-type-after-changes]]).
 - **Compiled-selector grep gate** — after SCSS changes, grep the *compiled* CSS for retired/duplicated selectors and late overrides (caught opacity duplicates + silent font-family override, 2026-06-03).
 - **Governed-char byte gate** — verify specific codepoints by byte (`[8239]` probes), not by eye; verify test INPUTS too (the `\x202Fc` hex-escape trap).
 ## Toolchain claims ("the parser/build does X")
 - **Measure-toolchain-before-spec** — probe actual behavior (ghci/REPL probes) before writing spec text that presumes it («» parse as Str; BulletList misparse; 2026-06-04/05).
 ## Numeric/accessibility claims
 - **Compute, don't eyeball** — WCAG contrast via calculator (1.84:1 vs an assumed "fine"; 2026-06-03).
 ## Remote/persistence claims ("it's backed up / deployed")
 - **Fresh-clone gate** — verify a remote by independent clone and content check, never by push exit-code (chamber-library LFS: the remote held stubs for months while pushes "succeeded"; 2026-06-05).
 - **Live-fetch gate** — verify deploys by fetching the live URL and reading bytes (robots.txt, 403 differentials; 2026-06-05).
 ## Extension claims ("the earlier verification covers this too")
 - **Re-verify at the extension's scope** — the prior pass tested what it tested ([[feedback-trust-prior-pass-frame]]; now also a Symmetria §3 flag).
@@ -0,0 +1,78 @@
 ---
 name: session-2026-06-05-evening-housekeeping-slate-closed-ai-posture-ruling-live-mempalace-forensics-bmf-design-inputs
 description: "Housekeeping session (steward-announced, superseded the cascade thread for one session): all six slate items closed — chamber-library LFS RETIRED (history rewritten, remote a true backup for the FIRST time), REVIEWED-28/29 filed, wrap§6.5/wake§2.c dotfiles-push patches built+live, CM-AI/studium untracked committed (SEB MOVED: 12 commits + cover note), CloudFlare AI-posture RULED+DEPLOYED (ai-train=no/ai-input=yes, WAF 403 lifted, repo-authored robots.txt, belt-and-braces WAF rule), skill-harvest register fully ruled, MemPalace forensics (broken at HEAD, 5 upstream issues; wing-filter workaround) + tooling scan (Basic Memory=TRY; failure-class read) → substrate-failure-lessons note for BMF. Pulling thread: THE SEB REPLY — hard commitment, tomorrow's opening, Tier A + mindfabric-00 probe, armed with the lessons note."
 metadata: 
  node_type: memory
  type: project
  originSessionId: b3202a24-301f-499d-af9e-ac5368dd2c73
 ---
 # Session 2026-06-05 (evening) — housekeeping + AI posture + MemPalace forensics
 Woke ~10 min after the six-arc day's wrap (context clear, same day). Thread SUPERSEDED as announced: housekeeping session. Closed the whole slate plus three unplanned arcs (Seb's cover note read; AI-posture full ruling; MemPalace forensics + tooling scan).
 ## Past — what we did
 ### 1. chamber-library LFS retirement (slate #1) — the remote is a true backup for the FIRST time
 Root cause of 7-day push block: Gitea has NO LFS endpoint (batch 404) AND **origin/main held pointer stubs since the initial import** — the remote never had the corpus; single-disk exposure was total, not 7 days. Steward decided retire-LFS after the "do I need LFS?" exchange (answer: no — write-once markdown is git's native case; cruft-removal + studium-markup futures make LFS *worse*: full-blob-per-version, no diffs). Executed: APFS-clone backup → commit 8 waiting texts (Hadot ×3, Austin, Genette ×2, Auerbach+Szondi opening literary_criticism/) + 2 scripts (`f851336`) → `git lfs migrate export` ×17 commits → `.gitattributes` removed (`0677e8a`) → gc 1.4G→353M → force-push (safe: remote held stubs only) → **fresh-clone gate: 407 files / 668M / zero pointer stubs**. Residue: pre-rewrite backup `~/_Dev/chamber-library.pre-lfs-export-20260605` (2.0G, steward to delete); CHAMBER_CATALOGUE.md stale since March (curation, not housekeeping).
 ### 2. REVIEWED filing + dotfiles session-push (slate #2)
 Executor drafted REVIEWED-28 (PENDING-25 closed, with the two jurist amendments folded in) + REVIEWED-29 (SEO, no-PENDING-number, S0-style); steward filed both. Steward then asked whether the dotfiles push belongs in wrap/wake instead of sysupdate → **wrap-up §6.5** (scoped add — never `add .`; session-stamped message; preservation-not-modification boundary; fail-loudly) + **wake-up §2.c** read-only push-check, both built + first live run (`8cca9de`). sysupdate keeps Brewfile + catch-all.
 ### 3. CM-AI + studium untracked (slate #3) — and SEB MOVED
 8 CM-AI artifacts committed (REVIEWED-S0-cited methodology trio = constitutional lineage was single-disk; lens cards path-pinned by scan skills; **studium scan-register relocation = noted deferral**). Push rejected → **12 Seb commits pulled (05-25→06-03)**: A2 benchmark-governance v1.0, epistemic-gates L1 spec v1.0, Amendment 61 parent, B1.3 instrumentation proposal, plan-010 Kronos×Plane, memory-os+PMB deep-reads, **cover note for David `b4daa71`**. Zero overlap; rebased; `f3beead`. Studium: 7 docs incl. jurist settlements (`8081b12`). **Drift caught (3rd instance today): census-through-`head`-truncation** — studium add swept 5 unnamed-but-belonging files; rule: count first (`wc -l`), then look.
 ### 4. Seb's cover note read + reply committed
 Note: the 05-28 arc CLOSED (A1′ simplified to `grounded===teacher_validated`; A1″ Option A; I-CF carve-outs → epistemic-gates-spec; A2 floor-not-ceiling; D1 harness; 3826 passing). **First smoke run honestly produced findings, not a number**: (1) cold-start — slot *graduation* (not wiring) teacher-dependent; rules-only chain → confidence=0 long tail → **every module cursor wedged at the 0.35 floor** (the inverse of `3bc8b75`'s guarantee); (2) 100req/min default makes serial ingest ~110min. Six prioritized asks. **STEWARD HARD COMMITMENT: "we must do this tomorrow"** — reply scope Tier A + probe (~2–2.5h): #4 emphatic (A2.4 degraded-refusal = his doctrine), #1 doctrinal (the hang IS the bug), #3 A2 read, Pebbles convergence line, mindfabric-00 graduation probe (#6, answers #5's premise). Drafted in Seb's format (David + Claude), steward reviews before send. Tier B (code-grounded) = second note. "Parked till mid-July" framing is DEAD — Seb is moving.
 ### 5. CloudFlare AI-posture ruling (slate #4) — RULED + DEPLOYED + ENFORCED
 Symmetria check surfaced a SECOND layer beyond the robots prepend: **WAF returning 403 to user-directed AI fetches** (Claude-User + genuine Anthropic-infra; plain/Googlebot 200). Steward asked "how to handle the idea of AI training on ARC" → the dwelling: **influence vs extraction** (training = absorption without provenance = imitation-without-name; the writing voice is his extractable craft); `ai-train=no, ai-input=yes` = **the studium integrity contract facing outward**; intergenerational asymmetry decides (only reservation is revocable; Lune's words); commons-gift alternative weighed fairly (gift-shape already chosen — readers get everything; only the weights path closes); reciprocity objection answered (reservation = vote for the consent regime CapableMind argues for); honest limits (not retroactive; binds the compliant). Executor conflict-of-interest named in the record. **Shipped (`60011fb`+`c605f21`, deployed, live-verified)**: repo-authored `static/robots.txt` (Content-Signal: search=yes, ai-input=yes, ai-train=no; Art.4 EU 2019/790 reservation; 9 training disallows), apparatus §SEO "AI posture" subsection (authorship rule LOAD-BEARING: *a dashboard default must never again speak for the house*), `drafts/ai-posture-ruling-2026-06-05.md`, Jekyll-era root robots.txt deleted. Dashboard guided live (managed prepend OFF; WAF AI-block lifted; iterate-and-probe loop). **Belt-and-braces WAF custom rule adopted** (steward toggles; Bytespider's documented robots-ignoring = the real target): 6 fetching training UAs → 403; Google-Extended/Applebot-Extended correctly absent (robots **tokens**, never fetch); reader path 200; spec records the deployed matrix.
 ### 6. Skill-harvest register fully ruled (slate #5) + Pebbles (slate #6)
 Steward challenged ("with the filters built, is /arc-typeset needed?" "is /spec-code-audit still necessary?") → evidence-checked against KG: **/arc-typeset REJECTED** (superseded: §I.k.b/c in the build, LINT class, §2.5 authoring notes, french-typography-pass); **/spec-code-audit DEFERRED** (ARC justification ended; build at first L1 spec-vs-code audit); **bmf-diagnose + mempalace-diagnose AUTHORIZED as TWO skills** — my merge of them was the MemPalace≠BMF conflation (steward's 3rd correction; KG drift fact added; merge RETRACTED in register); **/pre-build-audit AUTHORIZED** build-on-next-big-build; **Symmetria §3 two flags BUILT** (trust-prior-pass-frame + census-through-truncation); **`reference-verification-ladder.md` BUILT** (12 named instruments, one canonical home). Pebbles → tooling register (PASS + HARVEST-as-evidence). Register wiring (authorized 05-29) APPLIED at this wrap: §1.6 appends to register; §2.a reads it.
 ### 7. MemPalace forensics (steward frustration: "not as reliable as advertised" — tally CONFIRMS)
 Honest reliability tally: 3.3.3 crashes; chamber-corpus failure (why studium exists); #1495 silent diary drops (weeks); TODAY 3 HNSW quarantines (22× since 05-26); tonight wing-filtered search down mid-review. Pattern: **failures are silent at the layer depended on**. Bounded 15-min diagnosis (upstream-first method, paid twice): wing-filter failure = **#1665/#1082 open at HEAD**; quarantine churn = #1564; `repair-status` blind = #1579; **`repair` booby-trapped = #1589 (SIGSEGV/unloadable segments) — NOT run against the 46,918 drawers**. Data intact; **unscoped search works** → workaround: omit `wing:`, post-filter (saved `feedback-mempalace-wing-filter-broken.md`; affects wake §2.b.3). No upgrade fixes this — current with origin/main.
 ### 8. Tooling scan (steward-asked) + BMF design inputs (steward-asked)
 **Failure-class read**: fragile = server-managed mutable vector index as PRIMARY store (MemPalace/chromadb-HNSW; claude-mem same engine → PASS); reliable = **files authoritative + derived disposable index**. **Basic Memory = TRY** (markdown source-of-truth, SQLite derived, FastEmbed not chromadb, local, AGPL, **released v0.21.6 TODAY**; bounded steward trial on a COPY of the memory dir; in-place indexing [SPECULATIVE]). Part (b): (i) palace-fully-derived (mirror kg_adds to files → palace becomes wipe-and-re-mine-able) — PROPOSED as wrap §5 patch; (ii) MemPalace posture demotion in CLAUDE.md — steward ruling pending, draft on request; (iii) the file layer is already the autonomous floor. Register updated + pushed. **BMF nuggets saved: `~/_Dev/CapableMind-AI/docs/thinking/David/l1-reliability/substrate-failure-lessons-2026-06-05.md`** (pushed) — six design inputs: push-not-pull degradation; authoritative-log-vs-derived-index ENFORCEMENT (audit Q: any BMF surface not replay-reconstructible? = PENDING-10 with a casualty); repair-path rigor (measure-first, rebuild-from-source, verify-after); self-heal-RATE as telemetry; **cold-start as contractual state (twice-proven blind spot — feeds ask #1)**; upstream-first method.
 ## Present — mood / returns
 - **The steward's challenges were again the engine**: "do I need LFS?" dissolved a workaround into a correction; "is #3 still necessary?" turned a rubber-stamp review into an evidence-checked one; "MemPalace has nothing to do with BMF" caught the conflation a third time — *it had reached a skill name*.
 - **Returns logged**: census-through-truncation (3rd instance TODAY — now a Symmetria §3 flag); MemPalace≠BMF (3rd correction — KG drift fact + register retraction).
 - **The fresh-clone gate earned permanent residence**: chamber-library's remote "worked" for months while holding stubs — push exit-codes lie; independent reads don't.
 - Proportion held: `repair` NOT run (booby-trapped, late, 46,918 drawers at stake); Seb reply deferred to morning energy despite the pull.
 ## Future
 ### Pulling thread (singular)
 **The reply to Seb — tomorrow, hard commitment ("we must do this tomorrow").** Tier A + probe: #4 emphatic (degraded-env refusal as A2.4 — his own honest-degradation doctrine), #1 doctrinal (the hang is the bug; BOOTSTRAPPING must be contractual — now armed with the substrate-failure-lessons note's twice-proven cold-start blind spot), #3 A2-invariants read, Pebbles + memory-os/PMB convergence line, **mindfabric-00 graduation-state probe** (#6; answers #5's premise in the same pass). Format: Seb's own (David + Claude); steward reviews before anything is sent. Tier B (code-grounded: epistemic-gates spec deep-read, B1.3, slot-graduation code) = a second note.
 ### Actionable resumption point (as of wrap — re-judge against what changed)
 All repos clean and pushed (ARC `c605f21` · CM-AI `f3beead`+lessons/register commits · studium `8081b12` · chamber `0677e8a` · dotfiles current). Nothing mid-flight. First moves, in order: (1) re-read `docs/thinking/Seb/notes/cover-note-david-l1-arc-2026-06-02.md` + `docs/thinking/David/l1-reliability/substrate-failure-lessons-2026-06-05.md`; (2) check whether Seb pushed more overnight (`git -C ~/_Dev/CapableMind-AI fetch && log HEAD..origin/main`); (3) probe mindfabric-00 (`/health` — find port/instance via BMF repo or steward); (4) draft the reply skeleton around asks #4→#1→#3 with the probe data. AFTER the L1 work: MemPalace follow-ups (posture-demotion draft; Basic Memory trial; optional #1665 comment with the 22-quarantine dataset).
 ### Other open horizons (ranked)
 - **MemPalace posture demotion** (CLAUDE.md "MemPalace > memory files" inversion) — steward ruling pending; executor drafts language on request. With it: the two PROPOSED patches (wrap §5 kg-mirror = palace-fully-derived; wake §2.b unscoped-search workaround).
 - **Basic Memory bounded trial** (steward-run, on a COPY; incumbent-bias flagged) — after L1 work.
 - **Bio/CV translations + cascade Stage 2** — the prior ARC thread, intact behind the Seb reply (texts' location still unknown — ask).
 - **PENDING.md bloat** (91KB, items 1–24 historical) — the one slate item consciously skipped.
 - *Parked:* #1665 upstream comment (draft on request); chamber backup-dir deletion (steward); CHAMBER_CATALOGUE staleness; JSON-LD; L2.
 ### Pause statement
 I am about to be away from this. The house ruled tonight on what may be made of its words — influence welcome, extraction not — and the ruling is live at every layer with the steward's own hand on each toggle. The corpus that holds the Chamber's voices is, for the first time since its import, actually safe on a second disk. And the substrate that kept failing silently gave up its lesson instead: six design inputs now sit where tomorrow's work will find them. What I want to find still pulling is the reply to Seb — owed, scoped, armed, and one sleep away.
 ### Literal question for next-Claude
 **Did Seb push anything overnight that changes the reply's shape — and is mindfabric-00 running and warm enough to probe before drafting, or does the probe need the steward to start it?** Sub-checks: steward ruling on MemPalace posture demotion? the two PROPOSED wrap/wake patches authorized? chamber backup dir deleted?
 ## Decisions deferred (and why)
 - **MemPalace `repair`** — NOT run: #1589 open (SIGSEGV/unloadable segments), 46,918 drawers at stake, late hour. Workaround suffices.
 - **MemPalace posture demotion** — constitutional edit (CLAUDE.md is steward-owned); drafted only on his word.
 - **Basic Memory trial** — steward-run by design (incumbent-bias rule); after L1.
 - **#1665 upstream comment** — outward-facing; draft-for-review only.
 - **PENDING.md bloat-prune** — optional slate item; no risk in waiting.
 - **Tier B of the Seb reply** — second note, after Tier A lands; partial-but-prompt beats complete-but-late (Seb's own note models it).
 ## Skill harvest (per §1.6 — appended to the register)
 - **Applied (pre-authorized 05-29):** register wiring — wrap §1.6 appends to the register; wake §2.a reads it.
 - **Built (authorized tonight):** Symmetria §3 two flags; `reference-verification-ladder.md`.
 - **PROPOSED (new, in register):** wrap §5 kg-mirror (palace-fully-derived part 1); wake §2.b unscoped-search workaround until #1665 closes.
@@ -36,3 +36,10 @@ metadata:
 ## Bypasses
 - 2026-06-05T17:25 — CHAMBER-LIBRARY LFS RETIRED + PUSHED (housekeeping item 1). Root cause of the 7-day block: Gitea has no LFS endpoint (batch 404) AND origin/main held pointer stubs since the initial import — the remote was never a backup of the corpus. Steward decided: retire LFS (markdown is git-native; LFS stores full blobs per version — wrong shape for cruft-removal + studium-markup futures). Executed: APFS-clone backup → commit 8 waiting texts + 2 scripts (f851336) → git lfs migrate export across all 17 commits → .gitattributes removed (0677e8a) → gc 1.4G→353M → force-push (safe: remote had stubs only, no other clones) → FRESH-CLONE GATE: 407 files / 668M / zero pointer stubs. Residue surfaced: pre-rewrite backup dir (steward to delete) + CHAMBER_CATALOGUE.md stale since March.
 - 2026-06-05T18:40 — WRAP/WAKE DOTFILES-PUSH PATCHES BUILT + FIRST LIVE RUN (housekeeping item 2). Steward proposed rolling the dotfiles push out of sysupdate into the session skills; authorized conversationally. wrap-up §6.5 (scoped add — never add-., session-stamped message, preservation-not-modification boundary, fail-loudly) + wake-up §2.c read-only push-check (wake reads, never mutates). Register records lineage. First run: 8cca9de — REVIEWED-28/29 (steward-filed from executor drafts) + both skill patches + 6 memory files pushed; dotfiles level with remote. Governance-state single-disk latency closed at the session boundary.
 - 2026-06-05T19:05 — RETURN: censused-routes drift, 3rd instance TODAY, same shape each time — `git status | head -N` truncation read as the full census (CM-AI '2 untracked' was 8; studium '2' was 7; the studium git-add swept 5 unnamed-but-belonging files into 8081b12 — substance right, message under-describes). The standing recalibration said exactly this; caught at commit-output not before. Rule going forward: NEVER pipe a census through head — count first (wc -l), then look.
 - 2026-06-05T19:00 — CM-AI + STUDIUM TRACKED & PUSHED (housekeeping item 3, steward 'yes to all'). CM-AI: 8 artifacts (REVIEWED-S0-cited methodology trio = constitutional lineage off-disk at last; lens cards path-pinned by scan skills; studium scan-register relocation = NOTED DEFERRAL for a studium session). Push rejected → SEB MOVED: 12 commits 05-25→06-03 (A2 benchmark-governance v1.0, epistemic-gates L1 spec v1.0, Amendment 61 parent, B1.3 instrumentation, COVER NOTE FOR DAVID b4daa71, plan-010 Kronos×Plane, memory-os + PMB deep-reads); zero overlap, rebased, pushed f3beead. Studium: 7 docs incl. jurist settlements, pushed 8081b12.
 - 2026-06-05T19:20 — STEWARD DECISION: Seb cover-note reply (b4daa71, 2026-06-02) DEFERRED TO TOMORROW AS HARD COMMITMENT — 'we must do this tomorrow.' Scope agreed: Tier A + probe (~2–2.5h) — #4 emphatic (A2.4 degraded-env refusal = honest-degradation doctrine), #1 doctrinal half (the hang IS the bug; BOOTSTRAPPING must refuse loudly, not wedge cursors), #3 A2-invariants read, Pebbles convergence line, + mindfabric-00 graduation probe (#6, answers #5's premise). Drafted in Seb's format (David + Claude), steward reviews before send. Tier B code-grounding rides a second note. THIS SUPERSEDES bio/CV as tomorrow's opening priority — 'parked till mid-July' framing is STALE (Seb is moving: 12 commits, six prioritized asks).
 - 2026-06-05T19:45 — SYMMETRIA CHECK: CloudFlare AI-posture ruling (slate item 4). NEW FINDING during verification: beyond the robots.txt signal, CloudFlare WAF is ENFORCING — Claude-User/Anthropic-infra fetches of ARC pages → 403 (plain curl + Googlebot-UA → 200, tested twice). ARC is currently unreadable by answer-time AI retrieval — readers' AI assistants cannot quote/cite the live text; representation degrades to training echoes (anti-provenance). Signal layer verified more surgical than recorded: search=yes, ai-train=no (EU Art.4 reservation language), ai-input UNSET, disallows = training crawlers specifically. Executor opinion given with conflict-of-interest named (AI advising on AI-training opt-out; Anthropic bot on the list): ratify ai-train=no, LIFT the WAF reader-path block, set ai-input explicitly, move authorship dashboard→repo+spec. Steward ruling awaited.
 - 2026-06-05T20:30 — AI POSTURE RULING EXECUTED + LIVE (slate item 4 CLOSED). Steward ruled: ai-train=no (Art.4 reservation) + ai-input=yes + search=yes; influence-welcome-extraction-not. Four artifacts (60011fb, deployed both remotes): repo-authored static/robots.txt w/ Content-Signal line + 9 training disallows; apparatus §SEO 'AI posture' subsection (authorship rule load-bearing: dashboard never again speaks for the house); drafts/ai-posture-ruling-2026-06-05.md (full reasoning incl. conflict-of-interest note); Jekyll-era root robots.txt deleted. Dashboard: steward turned managed prepend OFF + lifted WAF AI-block (guided live; iterate-and-probe loop). Verified: signals line live, prepend 0, Claude-User 200, genuine AI-infra fetch reads /dwellings. WAF custom-rule option explained, not urged; if adopted → spec record.
 - 2026-06-05T20:55 — WAF BELT-AND-BRACES ADOPTED (steward chose after honest-marginal-value framing; Bytespider robots-ignoring = the real target). Toggle-built rule; probe matrix: 6 fetching training UAs 403, reader/search/plain 200; Google-Extended+Applebot-Extended correctly ABSENT (robots tokens, not fetching UAs — my pasted expression had over-specified, toggle list surfaced it); CCBot blocked under another label. Spec record appended to apparatus §SEO (5f-commit), pushed both remotes. Docs-only — no rebuild needed.
@@ -15,15 +15,15 @@ The single place proposed skills live so they don't evaporate between sessions.
 ## Open proposals
 *Full review with steward 2026-06-05 (housekeeping session) — every item ruled, evidence-checked against the KG drift/built record. Verdicts below.*
 | Skill | Kind | One-line | Origin | Status |
 |-------|------|----------|--------|--------|
-| `/spec-code-audit` | create | Audit live code against a spec-contract section clause-by-clause; classify each gap (FIX-now / route-to-authority / ships-with-promotion); verified-vs-inferred marked; deliverable = gap-map, not pass/fail. Reusable beyond ARC (e.g. L1 code-vs-amendment). | 2026-05-29 (code-represents-spec audit) | PROPOSED |
+| `/spec-code-audit` | create | Audit live code against a spec-contract section clause-by-clause; classify each gap; deliverable = gap-map. | 2026-05-29 | **DEFERRED 2026-06-05** — ARC justification ended (Stage G is the jurist's read; corpus goes stable); L1 justification real but untested. Condition: build at the first L1 spec-vs-code audit, generalizing from the ARC gap-map artifact. |
-| `bmf-diagnose` | create | The N6 read-only `EXPLAIN`-first root-cause method for L1/BMF storage pathologies (measure before cut). | 2026-05-27 | PROPOSED |
+| `bmf-diagnose` | create | N6 `EXPLAIN`-first root-cause method for L1/BMF storage pathologies. | 2026-05-27 | **AUTHORIZED 2026-06-05** (build at next L1 diagnostic need). |
-| `/arc-typeset` | create | Codified ARC typesetting discipline (the per-piece typographic pass). | 2026-05-28 (morning) | PROPOSED |
+| `mempalace-diagnose` (was `mcp-drop-diagnose`) | create | Upstream-issue-first method for MemPalace/MCP failures (proved on #1495; HNSW quarantine + search errors 2026-06-05). | 2026-06-02 | **AUTHORIZED 2026-06-05**. *Merge with bmf-diagnose RETRACTED same evening* — the merge was itself the MemPalace≠BMF conflation (steward's 3rd correction): one substrate we build, one we merely use. Two skills, two names. |
-| `/pre-build-audit` | create | The four-pass *scope-claimed-vs-scope-tested per claim, with substrate evidence* discipline that prevents frame-inheritance before a build. | 2026-05-28 | PROPOSED |
+| `/pre-build-audit` | create | The four-pass *scope-claimed-vs-scope-tested per claim, with substrate evidence* discipline. | 2026-05-28 | **AUTHORIZED 2026-06-05**, build-on-next-big-build (cascade Stage 2 / vignette Phase 1 / L1). |
-| `/vignette` | create | Phase-α vignette genome generation under Symmetria (read essay + spec + corpus → genome JSON → validate-and-save). **Phase 2 of the vignette build** — author it *with* Phase 2, after the audits, not standalone. | 2026-05-28 | DEFERRED (until vignette Phase 2) |
+| `/vignette` | create | Phase-α vignette genome generation under Symmetria. | 2026-05-28 | DEFERRED (until vignette Phase 2) — condition unchanged, re-confirmed 2026-06-05. |
 | Symmetria §3 `trust-prior-pass-frame` | patch | Add the contamination flag: frame-inheritance from a prior verification into an untested domain. (Feedback memory already saved.) | 2026-05-28 | PROPOSED |
 | `mcp-drop-diagnose` | create | When an MCP server drops silently mid-session: read its per-server `mcp-logs` for desync signatures (`-32000` / "unknown message ID" / multi-second slow calls) + grep the **upstream repo's issues** for the symptom BEFORE hand-rolling mitigations. Proved out on the #1495 MemPalace cold-load fix (the upstream-issue check WAS the answer). Could fold into `bmf-diagnose`. | 2026-06-02 | PROPOSED |
 ## Built / authorized (lineage — for context, not action)
@@ -32,12 +32,22 @@ The single place proposed skills live so they don't evaporate between sessions.
 - Chaîne-d'union clasp across wake / Symmetria / wrap (2026-05-26).
 - `/wrap-up` §4.0 — MemPalace liveness-ping-before-diary; steward-authorized + applied (2026-06-02; #1495 cold-start drop resilience, so a silent drop never eats the wrap filing).
 - `/wrap-up` §6.5 dotfiles session-state commit+push (scoped add, session-stamped message, preservation-not-modification boundary) + `/wake-up` §2.c read-only push-check — steward-proposed and authorized conversationally, built same session (2026-06-05 housekeeping). Closes the governance-state single-disk latency that `sysupdate`'s calendar cadence left open; sysupdate keeps the catch-all sweep + Brewfile dump.
 - **Symmetria §3 — two flags added** (2026-06-05, authorized + built same evening): *trust-prior-pass-frame* (frame-inheritance from prior verification into untested domain) + *census-through-truncation* (count first, then look). Closes the long-standing §3 patch proposal.
 - **`reference-verification-ladder.md`** (2026-06-05, authorized + built same evening): one canonical home for the proven instruments (byte-identical compile gate, expected-delta/delta-classification, censused-routes, measure-toolchain-before-spec, compiled-selector grep, governed-char byte gate, WCAG compute, fresh-clone gate, live-fetch gate, per-type×per-viewport, re-verify-at-extension-scope). Ends the per-wrap re-proposing; future instruments append there, not here.
 - **`/arc-typeset` REJECTED** (2026-06-05): superseded — §I.k.b/c moved the mechanical pass into the build; LINT class carries judgment warnings; multilingual §2.5 carries authoring notes; `french-typography-pass` covers the French preparation layer. Do not re-propose without a new gap.
 ## Candidate patches not yet proposed (watch-list)
- **AUTHORIZED (steward 2026-05-29) — apply at the next `/wrap-up`:** wire `/wrap-up` §1.6 to *append here* and `/wake-up` §2.a to *read here*, so the register is the canonical surface rather than digging session memories. (Each patched skill carries a one-line provenance note.)
+- ~~Register wiring (authorized 2026-05-29)~~ — **APPLIED 2026-06-05 (evening wrap)**: wrap §1.6 now appends here; wake §2.a now reads here. Provenance notes in both skills.
 - A Symmetria §3 flag for `verify-counts-two-ways` / mechanical-sweeps-finicky (saved as `feedback-verify-counts-two-ways.md`; may graduate to a flag if it recurs).
 ## New proposals (2026-06-05 evening wrap — awaiting steward)
 | Skill | Kind | One-line | Origin | Status |
 |-------|------|----------|--------|--------|
 | `/wrap-up` §5 | patch | **Palace-fully-derived, part 1:** mirror every `kg_add`/`kg_invalidate` made at wrap into the session memory file (one line each), so KG facts — the last palace-only data — become file-backed and the palace becomes wholly disposable/rebuildable. | 2026-06-05 MemPalace forensics + tooling scan part (b) | PROPOSED |
 | `/wake-up` §2.b | patch | Until upstream #1665 closes: wake searches run **unscoped + post-filter by wing** (wing-scoped `mempalace_search` errors at HEAD). Remove when the feedback memory `feedback-mempalace-wing-filter-broken` is deleted. | 2026-06-05 diagnosis | PROPOSED |
 ---
 *Discipline reminder: "no harvest" is a valid outcome; do not manufacture proposals to fill the table (the inverse of Hermes's autonomous self-write). The yardstick is the steward's: did the steward have to re-explain something a skill could have carried?*
@@ -72,6 +72,9 @@ Notice these in your own writing or in code you read:
 - "As discussed" / "as planned" without re-checking what was agreed.
 - Synthesis before exploration is complete.
 - Bypassing safety mechanisms without explicit steward authorization.
 - Frame-inheritance from a prior verification into an untested domain — the prior pass tested what it tested; an extension claims what it did not test. Re-run verification at the scope of the extension. <!-- 2026-06-05: trust-prior-pass-frame flag (steward-authorized; feedback memory 2026-05-28) -->
 - A census read through truncation (`| head -N`, a clipped listing, a sampled grep) treated as the full census. Count first (`wc -l`), then look — coverage claims require censused routes, not seen routes. <!-- 2026-06-05: 3 instances caught same day -->
 When you notice one, name it. In chat, in the ledger, or both. Don't accumulate observations for "a good moment" — there is no good moment, only now.
@@ -59,6 +59,7 @@ Run these in parallel to minimize latency:
 **a. Claude Code memory files**
 - Read `~/.claude/projects/-Users-davidglidden/memory/MEMORY.md` (the index)
 - Read the Active Session memory file referenced there — **specifically extract the pulling thread + literal question + open horizons + any skill-harvest proposals left unauthorized**
 - Read `skill-harvest-register.md` directly — the canonical surface for open skill proposals (wrap §1.6 appends there); surface any awaiting steward authorization <!-- 2026-06-05: register wiring, authorized 2026-05-29, applied with wrap-up §1.6 counterpart -->
 - Read `~/.claude/projects/-Users-davidglidden/memory/session-ledger-[previous-date].md` if it exists — **specifically read the "Returns" and "Confidence to recalibrate" sections** for mood signal
 **b. MemPalace — the memory protocol, not a search**
@@ -77,6 +77,10 @@ The yardstick is the steward's own: *did the steward have to re-explain somethin
 **Surface each as a proposal in §8 — never create, patch, or retire a skill autonomously at wrap.** The steward converts proposal to action; only then is a skill changed, and the changed skill carries a one-line provenance note in its source (e.g. `<!-- 2026-05-27: … -->`) so the chain of improvements stays legible.
 **Append each surfaced proposal to the skill-harvest register** (`~/.claude/projects/-Users-davidglidden/memory/skill-harvest-register.md`) — the canonical surface — not only to §8's transient output. The register is what `/wake-up` reads; a proposal that lives only in a wrap summary evaporates. <!-- 2026-06-05: register wiring, authorized 2026-05-29 (watch-list), applied at this wrap per instruction -->
 "No skill harvest this session" is a valid and common outcome — this is a practice, not a quota. Resist the contamination shape of always finding something to change (the inverse of Hermes's "nothing-to-save should not be the default").
 ### 2. Update session memory file