session 2026-08-17 coda: PENDING-146 (Class E) + the three placed-record corrections

Wrap amended after it was written, because the thread moved.

PENDING-146 filed at steward direction: the open list's unit is the id, the
decidable unit is the ## block. Upstream of everything PENDING-142 reaches, and
worse than a wrong verdict because the verdict is right.

Corrects my own report to the steward: FOUR blocks under PENDING-131 carry a live
Awaiting (parent, ADD-1, ADD-2, ADD-4), not the two I named. The jurist ruled on
that testimony while explicitly disclosing it had not verified ADDENDUM 1; running
that one check overturned the count. The disclosure was the instrument — no
control was pointed at it.

The answer key's specification changed before the key was drafted: it must be
keyed on ## BLOCKS, not ids, recording per block whether a live Awaiting exists
and at what tag. Keyed on ids it would have reproduced the unit that caused Class
E and graded green.

Resumption point revised and superseding the wrap's: three live options, steward
stopped tired without picking. (A) Move 2, closable in one sitting, no ruling,
and it is the fence itself. (C) Move 1, the emission-side fence over all 532
spans. (B) the answer key, session-sized. Recommendation absent a preference:
(A) then (C).

KG +3: the census-of-what-I-looked-at drift pattern; the disclosed-scope-limit
prevention; and the unit-of-a-pre-registration catch.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013Y6t6qx7cpaCu5xGdD36u4

claude/memory/MEMORY.md

@@ -68,14 +68,14 @@ permalink: claude-memory/memory
 - Chamber-typography — *tracker not yet established*; moves live in per-session memories (2026-05-11 →) + `project-chamber-cruft-restoration.md` + `project-chamber-typography-mining-plan-2026-05-15.md`.
 
 ## Active Session
-> 🔑 **PULLING THREAD — THE ANSWER KEY FOR PENDING-142.** 69 filtered items, disposition **hand-read and committed BEFORE any implementation exists**, hash recorded (REVIEWED-122 cond. 1). **Cond. 10 says plainly the ruling cannot verify the census — the key is the only instrument that can.** A key written after the fix inherits the fix's reading of closure and passes by construction. ⚠ **PENDING-145 must be encoded in it**: (a)/(b)/(d) all still resolve *id → ruled*, so a key written against that model certifies the defect as correct.
+> 🔑 **PULLING THREAD — THE FENCE, and the answer key behind it.** Steward stopped 2026-08-17 tired, with three live options and no pick made. **(A) MOVE 2** — disposition the 25 line-addressable blockquote runs: **closable in ONE SITTING, needs no ruling**, and it is the fence itself rather than the scaffolding. **(C) MOVE 1** — fence the citation *at emission*, engine-side under D-1, covering all **532 spans** including sources added later; a build direction, carrying ADDENDUM 4's own control requirement (controls from **each structural class present**, `NOT ESTABLISHED` rather than zero where a class has none — four of that census's five defects escaped Mauss-only controls). **(B) THE ANSWER KEY** — session-sized, gates all of PENDING-142. *Recommendation absent a preference: (A), then (C). (B) when there is a full session.*
-> ⚠ **ORDER IS BINDING:** key first, alone, hash recorded → then the (b) closing-verb enumeration goes for a **ruling** (it is a gate-design claim; unrecognized verb ⇒ NOT closed) → only then implement (d) framing (a)+(b). Report key-vs-implementation **in full, agreements included**.
+> ⚠ **THE KEY'S SPEC CHANGED BEFORE IT WAS DRAFTED — PENDING-146.** REVIEWED-122 cond. 1 says "per-item". **If "item" resolves to *id*, the key reproduces the very unit that caused Class E and grades green.** Key it on `##` **BLOCKS**, recording per block whether a live `Awaiting:` exists **and at what tag** (ADD-2 §5 re-tags (c) `[PROPOSAL]` inside a `[HARDENING]` row). Caught only because the key was not yet written.
-> ⚠ **REPORT AT EVERY WAKE UNTIL THE FREEZE LIFTS — N-now = 60/84 transcripts, 24 remaining** (REVIEWED-123 cond. 2). **The verification ladder is FROZEN, generally, from any source** (cond. 1) — 4 rows queued in PENDING-141's owed-entries list; OWED-4 is a *rewording*, merge on lift. 30-day review wired as `DEFERRED-DECISION date 2026-09-16`.
+> ⚠ **CLASS E (PENDING-146): the open list's unit is the `id`; the decidable unit is the `##` BLOCK.** Upstream of everything PENDING-142 reaches. Worse than a wrong verdict **because the verdict is right** — (d) reports PENDING-131 OPEN, correctly, and still hides that it carries four separate asks. **`governance_state()` shows ZERO rows for `131`.**
-> ⚠ **THE DAY'S SHAPE, SIX TIMES: a control whose SUBJECT is adjacent to its claim is not a check.** A count cited for a classification (equal both directions — 29 either way) · mtime cited as content age · git-date cited as content age (`3f9a89b` reset both) · a spread of outcomes cited as correctness · **and two of mine**, one inside my own verification.
+> ⚠ **FOUR blocks under PENDING-131 carry a live `Awaiting:`** — parent, ADD-1, ADD-2, ADD-4 — **not the two I reported.** The jurist ruled on my testimony *and disclosed it had not verified ADD-1*; running that check overturned my count. The disclosure is what made it findable.
-> ✅ **PENDING-142/143/144/145 filed; REVIEWED-122 + REVIEWED-123 received and EXECUTED**; docstring corrected (`aa745bc`); 16 trackers stamped superseded; 39 files' frontmatter repaired; wake detector rebuilt (4 defects, the scoped one was not the cause). All pushed `17669f2`.
+> ⚠ **REPORT AT EVERY WAKE — N-now = 60/84 transcripts, 24 remaining** (REVIEWED-123 cond. 2). **The ladder is FROZEN generally, from any source** (cond. 1); 4 rows queued in PENDING-141's owed-entries list, OWED-4 a *rewording* to merge on lift.
-> ⚠ **STEWARD-OWED:** three transcription errors in the placed records (`"cannot be e-run"`; unfilled `REVIEWED-<next-1>`; `"REVIEWED-123 condition 9"` where cond. 9 is REVIEWED-122's). **PENDING-131 ADDENDA 2 and 4 await action and cannot say so** — ADD-4 (08-13) was suppressed on arrival by a ruling placed 08-10, and **PENDING-131 (c), the unbuilt fence, has NEVER appeared in the open list.**
+> ✅ **Filed today: PENDING-142/143/144/145/146; REVIEWED-122 + REVIEWED-123 executed; three transcription errors in the placed records corrected by the steward.** Wake detector rebuilt (4 defects, the scoped one was not the cause); 16 trackers stamped superseded; 39 files' frontmatter repaired; deferral checker was skipping the register at 546 KB. All pushed `7f891de`.
 
-- [Session 2026-08-17 — the instruments audited themselves and lost](session-2026-08-17-the-instruments-audited-themselves-and-lost.md) — a tooling day that became a governance day; every instrument examined was wrong and two of the wrongs were made by the hand fixing the others. **LITERAL Q: across the last ~10 sessions, when a defect in the executor's own instrument was found, WHO found it — a mechanism firing unbidden, the executor re-checking, the jurist, or the steward?** Count them: mostly-executor means the practice works and the mechanisms are decorative; mostly-jurist/steward means every "verified" between reviews does less work than it appears to.
+- [Session 2026-08-17 — the instruments audited themselves and lost](session-2026-08-17-the-instruments-audited-themselves-and-lost.md) — every instrument examined was wrong; two of the wrongs were made by the hand fixing the others. **Read the CODA for the revised resumption point.** **LITERAL Q: across the last ~10 sessions, when a defect in the executor's own instrument was found, WHO found it — a mechanism firing unbidden, the executor re-checking, the jurist, or the steward?** Mostly-executor ⇒ the practice works and the mechanisms are decorative; mostly-jurist/steward ⇒ every "verified" between reviews does less work than it appears to.
 
 ## 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](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).

claude/memory/knowledge-graph.jsonl

@@ -669,3 +669,6 @@
 {"subject": "the honest-degradation banner", "predicate": "prevention", "object": "CAUGHT ITS OWN AUTHOR'S REGRESSION IN-SESSION. Repairing 39 files' frontmatter moved 20 April-May wrap records' mtimes to today; sec_pause picked `newest wrap` by mtime and promoted an April session to Last wrap, losing both the pulling thread and the open question. Nothing in the repair's own verification would have caught it — the repair's checks were about frontmatter, and they all passed. The DEGRADED section fired instead ('no PULLING THREAD anchor in the last wrap'), which is Constitutional Constraint 4 built in 2026-07-28 for a different reason and paying out here. A mechanism that reports its own limits caught a defect no purpose-built control was pointed at.", "valid_from": "2026-08-17", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-17-the-instruments-audited-themselves-and-lost.md", "extracted_at": "2026-08-17"}
 {"subject": "reading the PLACED record instead of the relayed message", "predicate": "prevention", "object": "FIFTH CONSECUTIVE FIRING, AND IT CHANGED THE WORK BOTH TIMES ON 2026-08-17. The relayed REVIEWED-122 gave the ruling; the placed entry carried five conditions, two SEVERED legs authorized ahead of the mechanism, and a binding ORDER (answer key first, alone, hash recorded, before any implementation). The relayed REVIEWED-123 read as a ladder hold for the S2 batch; the placed entry ruled the freeze GENERAL — from any source, whatever its authorization — which is what made queueing today's two earned entries to the owed list correct rather than a violation.", "valid_from": "2026-08-17", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-17-the-instruments-audited-themselves-and-lost.md", "extracted_at": "2026-08-17"}
 {"subject": "declaring a confound against one's own favourable evidence", "predicate": "prevention", "object": "STOPPED A FLATTERING n=2 FROM STANDING UNQUALIFIED. The jurist offered a discriminator for real-vs-manufactured authorization boundaries, with the executor's 2026-08-17 refusal as its POSITIVE instance. The two cases differ in a variable the discriminator does not name: on 08-17 PENDING-141 was in MEMORY.md's Active Session block, bold, flagged 'do not execute', and read at that session's wake; on 08-01 no equivalent prompt existed. So the positive instance may record an INDEX that named the instrument rather than an executor that found it — the discriminator would then measure the memory layer while appearing to measure judgment. Filed by the party the evidence flatters, into the record, before anyone asked.", "valid_from": "2026-08-17", "valid_to": null, "confidence": 0.9, "source_file": "session-2026-08-17-the-instruments-audited-themselves-and-lost.md", "extracted_at": "2026-08-17"}
+{"subject": "claude-code", "predicate": "drift-pattern", "object": "REPORTED A CENSUS OF THE THINGS IT HAD LOOKED AT, NOT OF THE THINGS THAT QUALIFY. Told the steward 'PENDING-131 ADDENDA 2 and 4 await steward action'; four of the five blocks carry a live **Awaiting:** — the parent, ADDENDUM 1, ADDENDUM 2 and ADDENDUM 4. The two I quoted were the two I had opened while investigating something else. The jurist then ruled on that testimony, explicitly disclosing it had not verified ADDENDUM 1, and running that one check overturned the count. Seventh instance in one day of a subject adjacent to the claim, and the third of them mine.", "valid_from": "2026-08-17", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-17-the-instruments-audited-themselves-and-lost.md", "extracted_at": "2026-08-17"}
+{"subject": "a jurist naming the check it did NOT run", "predicate": "prevention", "object": "CORRECTED THE EXECUTOR'S COUNT WHERE NO CONTROL EXISTED. The jurist wrote 'I did not read Addendum 1 or Addendum 2 §1 — the executor named 2 and 4, and I've taken that as testimony rather than verifying', and separately that it had not re-run governance_state(). Both disclosures were actionable by the party that COULD check: ADDENDUM 1 carries a live Awaiting (count wrong by half), and governance_state() shows ZERO rows for 131 rather than a collapsed row. Neither gap had an instrument pointed at it; the disclosure was the instrument. Constraint 6's weak form doing real work because the position was stated rather than assumed.", "valid_from": "2026-08-17", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-17-the-instruments-audited-themselves-and-lost.md", "extracted_at": "2026-08-17"}
+{"subject": "an answer key's UNIT", "predicate": "drift-pattern-good-direction", "object": "WAS CORRECTED BEFORE THE KEY EXISTED, WHICH IS THE ONLY MOMENT IT COULD BE. REVIEWED-122 cond. 1 requires a hand-read per-ITEM key over 69 filtered items as the acceptance check for PENDING-142. If 'item' resolves to the id — which is how every existing instrument resolves it — the key reproduces the exact unit that caused Class E and grades green by construction. Caught only because the key had not yet been drafted; the fix is to key on ## BLOCKS and record per block whether a live Awaiting exists and at what tag. A pre-registration is only protective if its unit is right, and its unit is the last thing anyone checks.", "valid_from": "2026-08-17", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-17-the-instruments-audited-themselves-and-lost.md", "extracted_at": "2026-08-17"}

claude/memory/session-2026-08-17-the-instruments-audited-themselves-and-lost.md

@@ -181,3 +181,49 @@ jurist, or the steward?** Count them. If the answer is mostly *the executor re-c
 practice is working and the mechanisms are decorative. If it is mostly *jurist or steward*, then
 every "verified" the executor reports between reviews is doing less work than it appears to, and
 the honest response is fewer claims rather than better ones.
+
+## CODA — after the wrap: Class E, and a count I had understated by half
+
+*Three post-wrap acts, captured because the session was ending and the thread moved.*
+
+**1. The three transcription errors in the placed records were corrected by the steward and pushed**
+(`bbfcc08`): `"cannot be e-run"` → `re-run`; the unfilled `REVIEWED-<next-1>` → `REVIEWED-122`;
+`"REVIEWED-123 condition 9"` → `REVIEWED-122 condition 9`. Verified 3 insertions / 3 deletions, no
+other line touched, and **120 REVIEWED headings still at column 0** — the real risk, not the typos.
+
+**2. PENDING-146 filed** (`7f891de`) at steward direction: **Class E — the open list's unit is the
+`id`; the decidable unit is the `##` block.** Upstream of everything PENDING-142 addresses, and
+reached by none of its options. The consequence is worse than a wrong verdict **because the verdict
+is right**: PENDING-131 *is* open, (d) would say so correctly, and would still conceal that it
+carries several asks filed days apart at different authorization classes.
+
+⚠ **AND IT CORRECTS ME.** I reported "ADDENDA 2 and 4 await steward action." **Four blocks carry a
+live `Awaiting:`** — the parent, ADDENDUM 1, ADDENDUM 2 and ADDENDUM 4. The jurist ruled on my
+testimony and **explicitly disclosed it had not verified ADDENDUM 1**; I ran that check and it
+overturned my count. *The disclosure is what made the gap findable.* Second disclosed gap also
+closed: `governance_state()` shows **zero** rows for `131` — not a collapsed row.
+
+**3. ⚠ THE ANSWER KEY'S SPECIFICATION CHANGED BEFORE IT WAS DRAFTED.** REVIEWED-122 cond. 1 says
+"per-item". **If "item" resolves to *id*, the key reproduces the very unit that caused Class E and
+grades green.** It must be keyed on `##` **blocks**, recording per block whether a live `Awaiting:`
+exists **and at what tag** — ADDENDUM 2 §5 re-tags (c) as `[PROPOSAL]` inside a row displaying
+`[HARDENING]`. Condition 1 was one word from certifying the defect. Caught in time only because the
+key had not been written yet.
+
+**REVISED RESUMPTION POINT (supersedes the block above; steward stopped here, tired — 2026-08-17):**
+```
+The thread still points at the answer key, but tomorrow has a cheaper, higher-value opening
+and the steward asked to stop rather than choose. Both are live; pick at the wake.
+
+A. MOVE 2 — the bounded one. Disposition the 25 line-addressable blockquote runs. Closable in
+   ONE SITTING, needs no ruling, and it is the fence: the thing the chamber is FOR, not the
+   scaffolding. PENDING-146 body carries it; PENDING-131 ADDENDUM 4 has the detail.
+B. THE ANSWER KEY — now specified as BLOCKS not ids (above). Still the gate on all of
+   PENDING-142. Session-sized, not slot-sized.
+C. MOVE 1 — the real unblocker: fence the citation at emission, engine-side under D-1, all 532
+   spans including later sources. A build direction, with ADDENDUM 4's own control requirement:
+   controls from EACH structural class present, reporting NOT ESTABLISHED rather than zero for
+   any class lacking one. Four of that census's five defects escaped Mauss-only controls.
+
+Recommendation if the steward has no preference: (A), then (C). (B) when there is a full session.
+```

claude/memory/session-ledger-2026-08-17.md

@@ -48,6 +48,12 @@ metadata:
   while the prose-count loop (no guard) kept reporting the file and made it look examined. Found only
   because the tracked count did not move after I placed a block.
 
+- **2026-08-17T~18:50 — I understated a count by half, and a disclosed limit caught it.** I reported
+  "PENDING-131 ADDENDA 2 and 4 await steward action." **Four blocks carry a live `Awaiting:`** —
+  parent, ADD-1, ADD-2, ADD-4. The jurist ruled on my testimony and *named the check it had not
+  run* (ADD-1); running it overturned my number. Seventh instance of the day's shape: my census's
+  subject was *the addenda I had looked at*, not *the blocks carrying awaits*.
+
 ## What held
 
 - The wake read every claim it reported against the substrate rather than relaying the digest:
@@ -62,6 +68,10 @@ metadata:
   catch the stamping defect — but it bounded it to 3 files and made the git-diff proof possible.
 
 
+- **A disclosed scope-limit did the work no control did.** The jurist could not verify ADDENDUM 1
+  and said so plainly instead of glossing. That sentence is the entire reason the count was
+  corrected — differently-positioned readers paying out because the position was *stated*.
+
 ## Open horizons
 
 - **Steward direction: tooling, not governance, today.** Three candidates, `wrap_inside` fix