session 2026-08-02: Constraint 6 amendment verified; REVIEWED-85 FIX lane + batch 1; v1 Chamber archive evidence (ADDENDUM-1) + jurist ruling; wake-digest ID fix; PENDING-89 opened, -10/-86 amended

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WuMjg3ipEVa3n8CoSzoyvc

claude/memory/session-ledger-2026-08-02.md

@@ -5,7 +5,7 @@ metadata:
   node_type: memory
   type: feedback
   originSessionId: 9256a5b3-c56b-4564-8ff2-8dc9d93ef97a
-  modified: 2026-08-02T09:13:01.192Z
+  modified: 2026-08-02T10:25:57.625Z
 ---
 
 # Session Ledger — 2026-08-02
@@ -23,6 +23,21 @@ metadata:
 - **12:35 — the missing v1 GPT prompts are unrecoverable, and the reason is the finding.** GPT ran the protocols as **custom GPTs**: the June 14 transcript pastes only the submitted text (*"I convene a session of the shadow protocol for the following:"*), and the June 12 design conversation states the intent outright. The instruction lived in the custom-GPT configuration and never entered a conversation, so no export can hold it. Consequence for the comparison: Claude received the protocol **in-conversation**, GPT received it at **system level** — a third bundle difference after prompt text and GPT-authored compression, and one that *strengthens* the Ethics-II self-exemption (system-level "No softening" still produced an exemption for the venue).
 - **12:35 — vault/repo version-history conflict, resolved against the vault.** Vault `chamber-prompts/README.md`: "v1.0 (December 2024)". Repo `prompts/deprecated/README.md` **and** the v1 file's own header: **June 14, 2025**. Two independent repo records against one vault record. Surfaced, not corrected — the vault is steward-held and read-only for me.
 
+- **13:10 — "permanently unrecoverable" from a bounded search.** I searched the repo, `03. Schemas & Protocols`, and the ChatGPT exports, found no v1 GPT prompt, and stated it was *destroyed*. The steward pointed at `99. Archives—Previous Iterations`, which holds three of them. Seen routes reported as censused routes — the ladder has an instrument for exactly this and it did not fire.
+- **14:05 — "the M4 is down," said three times, was wrong.** This machine is on `192.168.1.52`; the M4 is `10.0.1.136`. Different subnet, not a dead host. **Self-caught** — the first bounded-conclusion error of the day I found without the steward handing it to me.
+- **15:30 — the bounded-change proof caught my own docstring.** I wrote that the wake-digest fix "can only ever surface MORE items, never fewer." It corrects in *both* directions: 3 falsely-hidden items surfaced, 2 genuinely-ruled items correctly stopped being shown. A comment promising behaviour the code does not deliver, in the file whose purpose is to stop governance hiding from the steward.
+- **16:20 — a containment control that leaks by construction, twice in five minutes.** Both controls I built for the Q3 negation were substrings of the sentence doing the negating. The instrument refused certification both times and was right to. **Substring containment cannot verify a negation** — the affirmative always appears inside its own denial. Documented in the script; polarity must be established by reading and reported as uncovered.
+- **17:05 — nearly called Seb's PENDING-10 citation a miscitation.** The substrate showed the steward himself framed the replay-contract audit question as PENDING-10's, twice, in June cover notes. Seb was echoing faithfully. The real defect was ours: the extension never got written back into the item.
+
+## What held
+
+*Instruments that fired prospectively — banked-lesson → what it caught → what it would have cost.*
+
+- **The containment checker, built ~11:00 for the doctrine package, then discharged a gate it was not built for.** It caught a fabricated terminal period inside a blockquote in my own jurist package (read past twice), and then satisfied REVIEWED-85's stated precondition — the jurist could not read the skill files, so the §1.6/§2.a quotes its ruling rested on needed mechanical verification. 7/7, 5/5 controls absent. **Transfer between failure classes: built for quotation fidelity, cleared an authorization precondition.** Without it, REVIEWED-85 lands with an undischarged condition.
+- **The wake's substrate-check rule** (*a disposition clause is not a status*) caught at 10:44 that REVIEWED-85 was already placed — three minutes after a wrap that called it the blocker. Cost avoided: reporting an authorized item as blocked, for the second day running.
+- **Pre-registering the divergence criterion before opening any archive file** caught that *reference* was the wrong term — the v1 protocols mandate invented bibliography, so counting citations would have compared two fiction generators and inflated the result enormously. Cost avoided: a doctrine looking strong for a bogus reason.
+- **Reading the protocols before the data**, at the steward's insistence. Every substantive correction to the archive reading came from the instruments and the record, not from re-reading the outputs.
+
 ## Open horizons
 
 - **The Fool's false-positive control has never been run.** Until a *sound* document is run, the model's finding-rate cannot be distinguished from a production-rate — and trial 02's apparent restraint was an artifact of a disabled reasoning mode, not evidence of restraint.