session 2026-07-06: MEMORY.md two-file compaction (213→17KB) + self-bounding wiring (/wrap-up §3 demote-on-promote, /wake-up §2.a load-gate); skill-harvest closures; Olson graduation-state note

claude/memory/session-2026-07-06-memory-compaction-and-olson-graduation-opened.md

@@ -0,0 +1,52 @@
+---
+name: Session 2026-07-06 — MEMORY.md two-file compaction + self-bounding wiring, then the Olson graduation opened (right, once)
+description: "Two arcs. (1) MEMORY.md 213KB→17KB via a two-file split (live index / MEMORY-reference.md history), after the steward reframed 'this recurs — what's the DURABLE fix?': root cause = role-conflation + no self-bounding + no load-integrity gate. Wired the recurrence-killers into /wrap-up §3 (demote-on-promote) + /wake-up §2.a (load-integrity gate); closed 3 long-open skill-harvest proposals. Caught a live stale-marker specimen (the /aldine-xxi/ 'RESUME ON RETURN' banner, 2mo dead — page shipped 2026-05-18). (2) Opened the graduation of Olson's *The Power to Name* (2002) — the A2 primary source for REVIEWED-49 AND a fitting chamber accession. Orientation COMPLETE + durably staged; the fidelity-critical build deliberately PAUSED for fresh attention. PULLING THREAD: finish the Olson graduation (right, once) → A2 verification off it (Ch 6) → A2 preamble, all within REVIEWED-49 execution."
+metadata:
+  node_type: memory
+  type: project
+  originSessionId: d1e67361-d1b9-4dac-a0c4-e7a0e26211c4
+---
+
+# Session 2026-07-06 — memory compaction + the Olson graduation opened
+
+Woke into the steward-set sequence (compaction FIRST, then REVIEWED-49). Both arcs advanced; the second was deliberately paused mid-build on a fittingness call.
+
+## PAST — what we did + why
+
+**Arc 1 — MEMORY.md two-file compaction + self-bounding wiring (DONE, authorized).**
+- The steward stopped the authorized compaction to ask the deeper question: *"this recurs — what's the best/durable way? something to add to wake-up/wrap-up so future selves aren't held up?"* Reframed from execute-the-task → diagnose-the-class. **Root cause named:** MEMORY.md did three jobs in one file (live index / append-only archive / stable reference), all growing, all loaded; the 2026-06-08 compress-in-place (285→157KB) attacked the *level* not the *class*, so it re-bloated to 213KB and the harness now truncates it (the wake stopped seeing the whole index).
+- **Measurement caught a would-be miss:** the two-file split alone was insufficient — the wake-critical CORE was already 23.7KB (over ceiling), because ONE tracker line (the ARC entry, line 40) was an 8KB chronological log crammed into the index. Slimmed exactly that one line (→0.6KB pointer, full log relocated); left the 13 other lean tracker lines untouched.
+- **Executed byte-safe:** line-range slices (nothing retyped) + md5 byte-conservation proof (relocated tail 56–659 and kept head both md5-identical to source) + full link-resolution canary. Canary flagged 8 unresolved links → VERIFIED all 8 pre-existing (moved verbatim), zero regressions, 7/8 resolve to real files, 1 genuinely-dead pointer predating the pass. Backup at `scratchpad/MEMORY.md.backup-2026-07-06`.
+- **Result:** `MEMORY.md` 213KB→**17KB** (91.8%); `MEMORY-reference.md` (198KB, lossless history+reference). The remaining 17KB bulk is genuinely load-bearing (Standing prefs 7.5KB + trackers 7.3KB) — NOT pruned unilaterally.
+- **The recurrence-killers, wired (steward-authorized):** `/wrap-up` §3 → **demote-on-promote** (new Active Session evicts the prior into MEMORY-reference.md, same move; trackers stay one-liners; budget check). `/wake-up` §2.a → **load-integrity gate** (harness-truncation = loud flag + trim before proceeding). Provenance notes in both skills. **Closed 3 long-open skill-harvest proposals** (compress-at-demotion 2026-06-08; deeper-reduction 2026-06-08; wake-canary truncation-half 2026-06-07) — marked BUILT in the register; the wake-canary *link-resolution* half stays PROPOSED (applied once here, not yet a standing wake step).
+- **Live stale-marker specimen caught:** the relocated `/aldine-xxi/` "Pulling thread on hold — RESUME ON RETURN / STEWARD WILL NEED THIS IMMEDIATELY" banner was **2 months dead** — substrate-verified the page shipped `content/pages/aldine-xxi.md` (`date: 2026-05-18`, rewritten `89bae96`, refined `da375a6` 2026-06-06), all three held questions answered *in the published prose* incl. the literal "§IV named territory" one (*"the synthesis is the work's own"*). Corrected both files (header→CLOSED/SUPERSEDED + evidence; removed the "parked" mention from the MEMORY.md pointer). The session's own subject, in miniature.
+
+**Arc 2 — Olson *The Power to Name* graduation OPENED (orientation done; build paused).**
+- Context: the steward has the Olson PDF on his desktop — the REVIEWED-49 **A2** primary source (verify Olson vs the 2002 text before drafting A2's preamble; citing the scout's characterization = repeat A4's error). Steward: *"probably a good addition to the chamber library ;)"* → per [[feedback-engine-sources-become-permanent-chamber-collection]] it graduates. Fitting: the book *about* the power of naming, entering the library whose classification doctrine prompted PENDING-49.
+- **Composed the two tasks:** graduate → verify A2 off the clean text (steward chose graduate-first-full-arc over a quick raw read: *"Let's do it right, once."*).
+- **Orientation COMPLETE + durably staged** at `chamber-library/converted_texts/traditions/critical_modernity/epistemology/`: `the-power-to-name-olson.GRADUATION-STATE.md` (the full resume note), `.STRUCTURE-MAP.md` (authoritative ch/section map from the SCAN ToC — text-layer ToC is OCR-garbage), `.RAW-ia-textlayer.txt` (92.5K-word body extraction). Findings: 278pp single-page **V-SCAN**; IA body layer CLEAN (0 U+FFFD, 0 cid, 2 line-hyphens); **path = clean IA body + recover structure from scan, NOT 278pp re-OCR** (disproportionate; body already clean; re-OCR has its own PASS-BUT-FALSELY risk). Metadata verified (Kluwer ©2002, ISBN 1-4020-0776-0). Body boundaries: DROP 1–438 (front+ToC) + Index; KEEP Preface@439 → Notes@11633. **Placement CONFIRMED by steward: `critical_modernity/epistemology/`.**
+- **Verbatim-protect hazards logged** for the cleaning pass: Dewey reformed-spelling QUOTES (speld/wil/uzed/vizual/prejudis — content, not OCR error); Olson's deliberate stylizations "Confuzion" (2.1), "Ite/arating" (ch5), "Universality ≠ Diversity" (4.x).
+- **A2 locus pinpointed: Ch 6 "Toward Eccentric Techniques"** (pp.224–240 — "Eccentric Classification", "Proposing an Eccentric Technique", "Breaching The Limit") — where Olson turns critique→proposal, so where the jurist's (a)-vs-(b) question is settled.
+
+## PRESENT — mood / disposition
+
+A high-integrity day where the executor-agency directives paid out repeatedly: challenged the framing (compaction-as-symptom, not just do-the-task); measured before asserting (the 23.7KB core finding; the 8KB ARC line); verified before claiming clean (byte-conservation + canary, not "the split looks fine"); verified a status against substrate before agreeing (the /aldine-xxi/ closure — the steward said "closed" and I *checked* rather than just concurring, matching his memory with specifics). The one genuinely load-bearing **return** was the pacing call: after a long session (memory surgery + deep Olson orientation), I named the honest-degradation risk of cramming a 92.5K-word *verbatim* graduation + a close governance read into the tail — the corpus's whole thesis forbids a rushed PASS-BUT-FALSELY. The steward chose to wrap+clear+continue, which is the fittingness call (τὸ πρόσφορον — hasten when ready, not before). No new drift patterns; the returns this session were positive disciplines held, not corrections.
+
+## FUTURE — what is pulling
+
+**PULLING THREAD (singular): finish the Olson graduation *right, once* — from the staged orientation — then the A2 verification off the clean text, then draft A2's preamble.** This is the live piece of REVIEWED-49 execution (A2's gating source). Everything needed is in `the-power-to-name-olson.GRADUATION-STATE.md`; it resumes with zero re-derivation.
+
+**ACTIONABLE RESUMPTION POINT (as of wrap — re-judge against what changed):**
+- **First move:** open `chamber-library/converted_texts/traditions/critical_modernity/epistemology/the-power-to-name-olson.GRADUATION-STATE.md` and execute its "Remaining build" list (steps 1–7): strip front-matter(1–438)+Index → clean body (PROTECT the verbatim list; fix only unambiguous doublings + LOG) → insert structure per the STRUCTURE-MAP → frontmatter+title-block per `graduation-spec.yaml` → gates (verify_conversion + verify_graduation + body_word_conservation) → graduate_to_canonical + build_catalogue → archive source (archive_sources.py → Chamber Sources) + `source_verified:` attestation. Reading-index sidecar DEFERRED (PENDING-42).
+- **Then:** REVIEWED-49 / A2 — read Ch 6 (RAW + scan cross-check every load-bearing quote) → settle (a)-vs-(b) → draft A2's preamble (default (b) unless the primary source moves it).
+- **Then, the rest of REVIEWED-49:** the A1 `retrieve.py` hot-path read (does the engine need per-work agent access in a hot path?); the frontmatter sweep (A1 freed it — proceeds on current schema); A2/A4/B = FIX; A3 = PROPOSAL (status-gate).
+- **Governance loose end:** canonical REVIEWED-49 not yet in `~/REVIEWED.md` (steward's to place; the chamber RULING doc has it).
+- **Infra:** chamber `main` 5 unpushed (skemantix down): b9a5d05, 2238b65, fd49422, db3db9b, 4c5892e. Retry push / ping Seb. Olson staging artifacts are untracked-on-disk (durable; recorded here) — not committed (graduation incomplete).
+
+**PAUSE STATEMENT:** I am about to be away — mid-graduation, by deliberate choice, with the orientation banked clean. What I want to find still pulling: the discipline that made me pause — *do the verbatim build with fresh attention, not crammed* — honored. The temptation on return will be to rush the mechanical conversion to "get to A2"; resist it. The chamber's whole reason for being is that a rushed-but-plausible text is worse than none. Graduate it as carefully as if the steward were watching each word — because the point is that he shouldn't have to.
+
+**LITERAL QUESTION for next-Claude:** When you read Olson's Ch 6, does "eccentric classification / proposing an eccentric technique" actually *license a declared personal partial scheme* (→ A2 citation strategy (a): Berman + Olson each scoped) — or is "eccentric technique" a subtler *decentering-within-the-institution* move that critiques universalism without endorsing a private scheme (→ default (b): the Chamber's move only *rhymes* with hers, attributed to no one)? The answer decides A2's preamble.
+
+**Other open horizons (ranked):** REVIEWED-49 A1 retrieve.py read + the frontmatter sweep (now unblocked); the wake-canary link-resolution half (still PROPOSED, low-urgency); the older parked set (PENDING-43 ESCALATE Loom/Mill; PENDING-27; S-cluster; L1 PENDING-5/10 likely stale-retire); the chamber untracked Alexander *Nature of Order* vol-1 conversion sitting in contemporary_voices/environmental.
+
+**State at wrap:** MEMORY.md 17KB (two-file, self-bounding wired). chamber `main` 5 unpushed (skemantix down) + Olson orientation staged untracked. studium clean/pushed. CapableMind-AI ahead 1 (steward's addee62). dotfiles committed+pushed at §6.5.

claude/memory/session-ledger-2026-07-06.md

@@ -0,0 +1,32 @@
+---
+name: session-ledger-2026-07-06
+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: d1e67361-d1b9-4dac-a0c4-e7a0e26211c4
+---
+
+# Session Ledger — 2026-07-06
+
+## Returns
+- 2026-07-06T10:5x — Steward reframed the compaction ("this recurs — what's the durable fix?"). Returned from execute-the-authorized-task toward diagnose-the-class: the recurrence is role-conflation + no self-bounding + no load-integrity gate. Named it; proposed structural fix + wiring. Steward deferred leans + authorized wiring.
+- 2026-07-06T11:0x — Measurement caught my own would-be miss: I'd have done the two-file split and declared victory, but the wake-critical CORE was already 23.7KB (over ceiling) — the split alone is insufficient. The 8KB ARC tracker line (a chronological log crammed into the index) was the real bloat. Measured before asserting; slimmed exactly the one fat line, left the 13 lean ones untouched. Kin to census-before-claiming.
+- 2026-07-06T11:1x — Executed as byte-exact line-range slices (nothing retyped) + md5 byte-conservation proof + full link-resolution canary. Canary flagged 8 unresolved links; VERIFIED all 8 pre-existing in the original (moved verbatim), zero regressions, 7/8 resolve to real files, 1 genuinely-dead pointer that predates the pass. Did not assert "clean" from the split alone — proved conservation + zero-new-breakage.
+
+## Built (this session)
+- MEMORY.md 213KB → 17KB (91.8%); MEMORY-reference.md (198KB, lossless history+reference layer). Backup at scratchpad/MEMORY.md.backup-2026-07-06.
+- Self-bounding wiring: /wrap-up §3 (demote-on-promote, two-file architecture, tracker-stays-one-liner, budget check) + /wake-up §2.a (load-integrity gate: truncation = loud flag + trim). Provenance notes added to both skills. Steward-authorized.
+
+## Open horizons
+- 2026-07-06T10:37 — Session opens on a steward-set sequence: (1) MEMORY.md compaction (AUTHORIZED 2026-07-06; 213KB/659 lines) — real memory movement, so backup→surgical→verify-links; then (2) execute REVIEWED-49. Doctrine pass DONE; A1 freed the sweep.
+- Drift flags to hold for the compaction: `careless-edit-boundary-introduces-typo-in-untouched-text`; `assert-from-grep-hit-without-reading` (recurred on a prior MEMORY split-at-N estimate). The file is INTERLEAVED — a naive split-at-first-`## Archived` was caught-and-avoided last time. Surgical only; wake-canary (every pointer + [[link]] resolves) after the move.
+
+## Confidence to recalibrate
+
+## Authorization moves
+- REVIEWED-49 received (jurist doctrine pass on PENDING-49), captured in chamber-library/docs/library-science-adoptions-RULING-2026-07-06.md. Canonical REVIEWED-49 NOT yet placed in ~/REVIEWED.md (steward's to place — grep=0).
+
+## Sub-agent dialogues
+
+## Bypasses

claude/memory/skill-harvest-register.md

@@ -39,6 +39,7 @@ The single place proposed skills live so they don't evaporate between sessions.
 - **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.
+- **MEMORY.md two-file self-bounding architecture — BUILT 2026-07-06** (steward-authorized; closes three long-open proposals below). MEMORY.md 213KB→17KB (91.8%); split into `MEMORY.md` (wake-loaded live index) + `MEMORY-reference.md` (lossless history + reference layer). **Closes:** (a) the 2026-06-08 *`/wrap-up` §3 compress-at-demotion* patch → built as the richer **demote-on-promote** rule (prior Active Session relocates to `MEMORY-reference.md` in the same move; trackers stay one-liners; budget check); (b) the 2026-06-08 *deeper MEMORY.md reduction* proposal → done (the reference-layer split it described, plus the finding that the fat 8KB ARC tracker line — not just the archive — was the real bloat); (c) the *wake-canary* (2026-06-07) → the **truncation/load-integrity half** is now a standing `/wake-up` §2.a gate (truncated load = loud flag + trim). **Still open from the wake-canary proposal:** the *link-resolution* half (every pointer + `[[link]]` resolves at every wake) was applied once as a verification instrument this pass but is NOT yet a standing wake step — remains PROPOSED. Root-cause framing: the recurrence was role-conflation (one file doing live-index + archive + reference), no self-bounding, no load-integrity gate; the compress-in-place pass of 2026-06-08 attacked the level not the class, so it re-bloated.
 
 ## Candidate patches not yet proposed (watch-list)
 
@@ -83,9 +84,9 @@ The single place proposed skills live so they don't evaporate between sessions.
 
 **Memory-index (MEMORY.md) — the archive pass + the durable fixes:**
 - **DONE 2026-06-08 (steward-authorized, live): compress-in-place archive pass.** 90 archived-session bullets compressed to one-line pointers (detail preserved in the session files), **285KB→157KB**, all 239 pointers preserved, every load-bearing section byte-identical; backup `/tmp/MEMORY.md.bak`. ⚠ A naive split-at-first-`## Archived` was **caught-and-avoided** — the file is INTERLEAVED (archived blocks scattered among load-bearing reference sections: Pending work / Feedback / Drift patterns / ARC project state / CapableMind L1 / Personal Context / Reference Files). Surgical compression of only archived bullets is the correct tool for an interleaved index.
-- **[PATCH proposal] `/wrap-up` §3 — compress at demotion.** When demoting Active Session → Archived, compress the entry to a one-liner in the *same move* (it's already in the session file). Prevents index re-bloat at the source — without it the index re-grows ~4–5KB/session and this pass recurs.
-- **[PROPOSAL] deeper MEMORY.md reduction (only if 157KB still trips "only part loaded").** The load-bearing REFERENCE sections (steward profile / project states / ARC project state / CapableMind L1 / Reference Files) are large but largely STABLE — candidate to move to a consult-on-demand `MEMORY-reference.md`, leaving the wake-loaded MEMORY.md = standing prefs + trackers + Active Session + recent. Riskier (real memory, not duplication); its own focused pass, not a tail-of-session move.
-- **[reminder] the wake-canary** (PROPOSED 2026-06-07, above) still awaits authorization — the paired guardrail (every MEMORY.md pointer + `[[link]]` resolves at wake); should cover MEMORY.md + any future archive/reference split files.
+- **[PATCH proposal] `/wrap-up` §3 — compress at demotion.** When demoting Active Session → Archived, compress the entry to a one-liner in the *same move* (it's already in the session file). Prevents index re-bloat at the source — without it the index re-grows ~4–5KB/session and this pass recurs. **→ BUILT 2026-07-06** as demote-on-promote in the two-file architecture (see built-log). CLOSED.
+- **[PROPOSAL] deeper MEMORY.md reduction (only if 157KB still trips "only part loaded").** The load-bearing REFERENCE sections (steward profile / project states / ARC project state / CapableMind L1 / Reference Files) are large but largely STABLE — candidate to move to a consult-on-demand `MEMORY-reference.md`, leaving the wake-loaded MEMORY.md = standing prefs + trackers + Active Session + recent. Riskier (real memory, not duplication); its own focused pass, not a tail-of-session move. **→ BUILT 2026-07-06** (its own focused pass, exactly as advised — backup + full read + byte-exact split + link canary). The predicted reference sections all moved to `MEMORY-reference.md`; the pass also found the fat 8KB ARC tracker line was itself a bloat source. CLOSED.
+- **[reminder] the wake-canary** (PROPOSED 2026-06-07, above) still awaits authorization — the paired guardrail (every MEMORY.md pointer + `[[link]]` resolves at wake); should cover MEMORY.md + any future archive/reference split files. **→ PARTIALLY BUILT 2026-07-06:** the *truncation/load-integrity* half is now a standing `/wake-up` §2.a gate. The *link-resolution* half was applied once (this pass, as a verification instrument — caught that all 8 unresolved links were pre-existing) but is NOT yet a standing wake step. **STILL OPEN:** wire link-resolution as a recurring wake check (covering MEMORY.md + MEMORY-reference.md); low-urgency (cheap, but the split introduced no new breakage, so no active pain).
 
 ## New proposals (2026-06-09 — the headless-Chrome measurement harness, awaiting steward)
 
@@ -339,3 +340,11 @@ The single place proposed skills live so they don't evaporate between sessions.
 | **CLAUDE.md staleness canary (git tripwire)** | create (small) OR git hook | If the `scripts/` set or `graduation-spec.yaml` changed but `CLAUDE.md` didn't since, flag "may be stale." Bounded, low-false-positive — the two most CLAUDE.md-relevant change classes. **Prompts; never auto-writes** (a bot rewriting the disciplines is the automation-of-recognition risk — the loop stays load-bearing). Sibling of the proposed **wake-canary** (MEMORY.md pointer-resolution). | git pre-commit / a `/repo-doc-canary` | **PROPOSED (optional; pairs with the wake-canary)** |
 
 *(Two proposals + two docs built. The freshness mechanism is the load-bearing one — it answers the steward's live question and applies this whole session's thesis [storage isn't memory; a protocol that exercises it is] to our own orientation docs. Not manufactured: the docs were just built, so the "how do they stay true" question is real and now. The count-vs-event correction is the substantive contribution — a raw threshold would institutionalize decorative maintenance.)*
+
+### Harvest 2026-07-06 (MEMORY.md two-file compaction + Olson graduation opened)
+
+| Element | Kind | One-line | Where it lands | Status |
+|---|---|---|---|---|
+| **memory/index restructure = byte-exact slice + md5-conservation + link-canary** | verification-ladder entry | When restructuring a memory index or any lossless-relocation of prose between files, do it as **line-range slices (never retype)** + prove **byte-conservation** (md5 each moved slice == source slice) + a **link-resolution canary** (every `](file.md)` and `[[wikilink]]` resolves; distinguish pre-existing-broken from new-broken by grepping the original). Today's MEMORY.md 213→17KB split: proved the 198KB relocated tail md5-identical to source, and verified all 8 canary-flagged links were pre-existing (0 regressions) rather than asserting "the split looks fine." Kin to the byte-identical compile gate, generalized to prose-file moves. | `reference-verification-ladder.md` | **PROPOSED** |
+
+*Also this session (recorded, not new proposals): the self-bounding wiring (`/wrap-up §3` demote-on-promote + `/wake-up §2.a` load-integrity gate) was BUILT + authorized live — see the built-log entry above. `/graduate-chamber-source` (still PROPOSED, build-on-packaged-driver) gained another reinforcing instance — the Olson orientation walked the graduation pipeline manually again; the GRADUATION-STATE.md note is effectively its per-book empirical spec.*