session 2026-08-04 evening: census 02 + PENDING-95..98 + the engine tool-evolution log

Census 02 run entire on the seven instruments census 01 left uncensused. The
firing record divides by whether a human is in the invocation path. The engine
was asked a question for the first time and certified that Levi has nothing to
say about the grey zone, over ten gray zone matches in his own book.

PENDING-95..98 filed together; 96 authorized and landed same session on the
jurist's sharper wording (mine reproduced the overclaim one size down) and
kept OPEN — retrieve.py has no test at all.

Pulling thread REVISED at wrap after the steward punctured the first version:
"the sources are not golden... a cycle of engine-missing-x / source-not-golden
/ no-bounded-scope". The break was already in project-chamber-versioned-
releases, unread since 2026-07-28 — purpose choice and corpus scope are ONE
decision. Verified at wrap: 13/13 engine shas match disk. The thirteen are not
the 1,297, and the criterion is stability, not quality.

Skill harvest: 4 proposals (a /census skill, two Symmetria §3 flags, and a
/wake-up patch earned at a measured cost of ten days — a tracker marked THE
GOVERNING FRAME should be read entire, not as its MEMORY.md pointer).

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

claude/memory/knowledge-graph.jsonl

@@ -546,3 +546,12 @@
 {"subject": "the 2026-08-03 coherence_evaluated=0 lesson (verify a counter has a writer before trusting its zero)", "predicate": "prevention", "object": "Stopped a false claim about a DIFFERENT counter one day later. Investigating why recall never worked, retrieval_count/last_retrieved/recall_count/last_recalled all read 0 across 19,915 nodes. Rather than cite all four, checked each for a writer: retrieval_count has one (retrieval-tracker.ts:77) with live callers, so its zero is evidence; recall_count and last_recalled have NO writer anywhere in src/ (schema only), so their zeros mean nothing and would have been cited wrongly. A lesson banked from the coherence evaluator transferred to the retrieval counters \u2014 different subsystem, different session, same class.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-the-replay-had-never-resumed.md", "extracted_at": "2026-08-04"}
 {"subject": "L1 / mindfabric-00 replay", "predicate": "never-completes-because", "object": "minCursor is Math.min across all 11 modules (replay-coordinator.ts:300); structured and training have never processed an event (0 deferrals, 0 errors) so the floor is pinned at 0 permanently; :340 classifies every start as rebuild and :368 skips nothing. 13/13 restarts at min cursor 0, 6/6 rebuild, 0 catch-up \u2014 the resume branch has never executed. Completion is gated by uninterrupted run length (38h at the documented-healthy 17 events/min), not by rate. PENDING-94 [ESCALATE]; Seb's surface.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-the-replay-had-never-resumed.md", "extracted_at": "2026-08-04"}
 {"subject": "L1 / mindfabric-00 recall", "predicate": "has-never-returned-anything", "object": "retrieval_count = 0, last_retrieved on zero rows, across 19,915 nodes and 813,178 chains spanning April-June. Verified as a measured absence, not a blind one: writer at retrieval-tracker.ts:77, live callers in temporal/entity/vector/preference, temporal call site on the query return path guarded only by ids.length>0. The Recall canary logged FAILED 8 times vs PASSED 4. Same fact as never-completing ingestion, seen from the other end: no completed derived state to retrieve from.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-the-replay-had-never-resumed.md", "extracted_at": "2026-08-04"}
+{"subject": "claude-code", "predicate": "drift-pattern", "object": "PROBED-AN-INSTRUMENT-IN-THE-WRONG-KEY-SPACE-AND-NEARLY-CALLED-IT-INERT — queried resolve_archived_source with the ENGINE's source_id (levi-drowned-and-saved) against the CHAMBER's canonical_slug key space (the-drowned-and-the-saved-primo-levi); got None three times INCLUDING the nonsense control, which should have been the tell, and was one sentence from reporting the resolver dead. It is healthy at 349/349. Twice in one session: also read character_as_image at the YAML top level and nearly reported zero glyph maps declared (it is at promotion.character_as_image, 2 sources, 63-item census). A null from an instrument you have not positive-controlled is a fact about your instrument.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-evening-the-instruments-that-never-fired.md", "extracted_at": "2026-08-04"}
+{"subject": "claude-code", "predicate": "drift-pattern", "object": "THE-FIX-FOR-AN-OVERCLAIM-IS-AN-OVERCLAIM-CANDIDATE — replacing the engine's 'genuine silence, not a gap' with 'the index is complete and current' reproduced the same defect one size down: 'complete' is true of DOCUMENT COVERAGE and unverified of QUERY-MATCHING, and a reader without that distinction collapses the two exactly as the engine did. The repair inherits the frame that produced the original. Caught by the jurist, not by me. Re-reading a replacement as a stranger is a SEPARATE ACT from writing it.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-evening-the-instruments-that-never-fired.md", "extracted_at": "2026-08-04"}
+{"subject": "the tool-evolution-log discipline (review after every use)", "predicate": "prevention", "object": "Its ABSENCE explained a whole class. Census 02 found the firing record divides by whether a human is in the invocation path: audit_cruft/verify_conversion/apply_char_glyphs are exemplary because a curator invokes them; resolve_archived_source runs on EVERY graduation, is healthy at 349/349, and has zero entries because nobody invokes it; verify-before-compose fired twice with evidence surviving only in harness transcripts. The recording is attached to the HUMAN, not the instrument — so a record vanishes exactly when a tool is automated, which is when it starts running often enough to matter.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-evening-the-instruments-that-never-fired.md", "extracted_at": "2026-08-04"}
+{"subject": "the census pre-registration method (predict, then look)", "predicate": "prevention", "object": "Second census, second inverted prediction, and the discipline caught the reversal both times. Census 01 predicted weakness in the newest instruments and found it in the oldest (decay, not construction). Census 02 predicted FIRED-UNRECORDED dominant and was wrong about WHY — the skew is by human-in-the-loop, not by age or quality. Grading predictions written BEFORE the look is what converted two comfortable misses into the actual findings.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-evening-the-instruments-that-never-fired.md", "extracted_at": "2026-08-04"}
+{"subject": "studium-engine retrieval", "predicate": "has-property", "object": "Conjunctive bare-token FTS5 with no semantic layer: gray 51 hits, gray zone 10, 'levi the gray zone' 0, 'what does levi mean by the gray zone' 0. Recall collapses as a question lengthens, so natural-language questions return certified silence by default. No vector table; embed/rerank stayed spikes. PENDING-97.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-evening-the-instruments-that-never-fired.md", "extracted_at": "2026-08-04"}
+{"subject": "the studium engine's consuming end", "predicate": "was-first-exercised-on", "object": "2026-08-04 — the corpus was indexed 2026-07-19 (5,685 drawers, 13 sources) and no question was asked of it until this session. It ran, and certified that Levi has nothing to say about the grey zone over ten gray zone matches. Ingestion-elaborate / consumption-never-exercised is the same shape as L1's retrieval_count = 0.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-evening-the-instruments-that-never-fired.md", "extracted_at": "2026-08-04"}
+{"subject": "the chamber-versioned-releases frame", "predicate": "prevention", "object": "Broke a deadlock the executor had walked straight into. I recommended 'stop building, go use the library'; the steward punctured it — 'the sources are not golden... it's a cycle of engine-missing-x / source-not-golden / no-bounded-scope'. The break was already written in his own tracker, unread since 2026-07-28: you never re-gate 1,297 files for a version, you re-gate the bounded voice-set the chosen purpose needs, which makes the corpus job and the purpose choice ONE decision, not sequential ones. A banked reframe dissolved a paralysis that neither party could argue their way out of in the moment.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-evening-the-instruments-that-never-fired.md", "extracted_at": "2026-08-04"}
+{"subject": "claude-code", "predicate": "drift-pattern", "object": "RECOMMENDED-USE-WITHOUT-CHECKING-WHETHER-THE-SUBSTRATE-COULD-BEAR-IT — proposed a session of asking the corpus real questions without first checking whether the corpus was trustworthy enough for the answers to mean anything. The steward supplied the objection (sources not golden) and the check I should have run first: 13/13 engine shas match disk (so the thirteen ARE usable) and musil carries a stale voice-purity sidecar off by 6 (so one is named-defective). Both facts were one command away and would have shaped the recommendation instead of rescuing it afterwards.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-evening-the-instruments-that-never-fired.md", "extracted_at": "2026-08-04"}
+{"subject": "studium-engine corpus (the thirteen)", "predicate": "has-property", "object": "A de-facto bounded voice-set: Levi, Arendt, Weil x2, Musil, Mauss, Alexander, Harrison + the steward's own five after-the-reply essays. All 13 manifest shas verified matching the canonical files on disk 2026-08-04. NOT the 1,297-file corpus (of which only 11 pass current graduation) — that number does not bound V1. One named defect inside the set: musil-the-man-without-qualities has a stale chamber-side voice-purity sidecar (boundaries derived at 5,032 lines, canonical now 5,038; the whose-words layer, not the citation layer), HELD not migrated.", "valid_from": "2026-08-04", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-04-evening-the-instruments-that-never-fired.md", "extracted_at": "2026-08-04"}