session 2026-08-06 evening: the parse fix landed + REVIEWED-87..94 placed + PENDING-108..111 filed
Governance: the register could not answer 'how many rulings do I owe' (23, not the digest's 26). Seven decisions that existed only in a narrative are now placed, five of them reconstructions carrying provenance lines. PENDING-99/-105/-106 closed (106 by split). PENDING-108/-109/-110/-111 filed. Engine: retrieve.py accepts a sentence (27b79ca). 26 crashes -> 0, MISLOCATED 0, FALSE-POSITIVE 0, HIT 0/22 — the engine now grounds nothing honestly, and 0/22 is recorded as the number to beat. PENDING-111 + jurist package: fidelity_equivalence@3 erases Alexander's invariant rating, found by the steward reading his printed copy. Relayed for ruling. Next session step 0, steward-directed: the MEMORY.md trim (19.9 KB vs <17.1 KB target; relocation not deletion), then N1. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AB3Kryoy6b1pm2Nz1DYdLh
This commit is contained in:
co-authored by
Claude Opus 5
parent
3dff1a93d9
commit
02a72d017e
@@ -579,3 +579,13 @@
|
||||
{"subject": "the never-delete-on-failure rule in the drainer", "predicate": "prevention", "object": "A data-safety rule produced a DIAGNOSTIC finding it was not written for. Built so a failed POST never unlinks a queued observation, plus a halt after 10 consecutive failures. On the first full run it self-stopped at 50/10,535 \u2014 and that halt is HOW the entity-pipeline finding surfaced (relationships=31556ms against a 30s budget, cursor held). A safety valve doubled as an instrument.", "valid_from": "2026-08-06", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-06-the-note-that-said-it-could-not-happen.md", "extracted_at": "2026-08-06"}
|
||||
{"subject": "BMF (bettermemories, localhost:3011)", "predicate": "operational-state", "object": "STOPPED AND DISABLED 2026-08-06 16:47 \u2014 launchctl bootout + disable on BOTH com.capablemind.bettermemories AND com.capablemind.bmf (the latter carries unconditional KeepAlive:true and would fight for port 3011 if loaded). disable persists across reboot, closing the RunAtLoad door the 08-04 kill left open. Verified: port closed, no agents loaded. Plists backed up, NOT edited. Revert: bmf-stop-and-keep-stopped.sh --revert. 10,485 observations preserved at ~/.capablemind/hook-queue-parked-2026-08-06 \u2014 do NOT resume draining until the entity pipeline is healthy.", "valid_from": "2026-08-06", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-06-the-note-that-said-it-could-not-happen.md", "extracted_at": "2026-08-06"}
|
||||
{"subject": "BMF (bettermemories, localhost:3011)", "predicate": "operational-state", "object": "down and staying down (2026-08-04 decision)", "valid_from": "2026-08-04", "valid_to": "2026-08-06", "confidence": 1.0, "source_file": "session-2026-08-06-the-note-that-said-it-could-not-happen.md", "extracted_at": "2026-08-06"}
|
||||
{"subject": "claude-code", "predicate": "drift-pattern", "object": "READ-A-DATE-OUT-OF-AN-EXTERNAL-IDENTIFIER-AND-ANCHORED-OUR-TIMELINE-TO-IT. Wrote 'reconstructed eight days later' three times; INC-2026-07-28-01 is the UK AI Security Institute's INCIDENT id, not our filing date. Actual: same day. Jurist-caught. The correction made the finding WORSE (one day sufficed to lose four things permanently), which is the tell that the wrong number was doing argumentative work.", "valid_from": "2026-08-06", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-06-evening-the-asterisk-that-carried-meaning.md", "extracted_at": "2026-08-06"}
|
||||
{"subject": "claude-code", "predicate": "drift-pattern", "object": "MEASURED-THE-ARTIFACT-CORRECTLY-AND-MISREAD-WHAT-IT-WAS-FOR. Steward-named 2026-08-06. Counted 253 Alexander patterns accurately, then read a USAGE note ('32 selected patterns') as a bibliographic claim about extent. Same shape as asserting a fleet-wide causal story from n=5 and as '3 bare headings' when the count was 33. The measurement is right; the purpose-reading is wrong.", "valid_from": "2026-08-06", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-06-evening-the-asterisk-that-carried-meaning.md", "extracted_at": "2026-08-06"}
|
||||
{"subject": "claude-code", "predicate": "drift-pattern", "object": "ASSERTED-A-CONSEQUENCE-FROM-A-FIELD-NAME-BEFORE-READING-ITS-CONSUMER. Claimed a stale `sidecar: none-yet` would make N1 skip Harrison and Alexander. False — chunker.load_sidecar() reads the file directly and ignores the manifest field. The true finding was different and better (a DISARMED TRIPWIRE in ingest_gate:142). Reading the consumer produced it; guessing from the name would have shipped the wrong claim.", "valid_from": "2026-08-06", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-06-evening-the-asterisk-that-carried-meaning.md", "extracted_at": "2026-08-06"}
|
||||
{"subject": "the positive-control-before-any-absence-claim rule", "predicate": "prevention", "object": "Stopped a false absence claim about our own governance record. Before writing 'corpus_findings does not exist', ran the control: the key appears in ZERO files fleet-wide — so it was never a convention rather than a stale pointer, which is a different and more accurate finding. Same rule then resolved a containment MISS (G4) as a comment-prefix artifact rather than a misquote.", "valid_from": "2026-08-06", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-06-evening-the-asterisk-that-carried-meaning.md", "extracted_at": "2026-08-06"}
|
||||
{"subject": "the verbatim-containment prover", "predicate": "prevention", "object": "Caught a suspect quotation in a jurist package for a SECOND distinct failure class. First use (2026-08-05) caught a compression wearing quotation marks. Here it flagged G4, and the positive control showed the fault was the checker's normalizer leaving '#' comment prefixes — instrument artifact, not misquote. An instrument that can distinguish its own failure from the author's is doing more than checking.", "valid_from": "2026-08-06", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-06-evening-the-asterisk-that-carried-meaning.md", "extracted_at": "2026-08-06"}
|
||||
{"subject": "read-the-gate's-decision-code-before-designing-its-consumer", "predicate": "prevention", "object": "Transferred from PENDING-69 (chamber) to the engine manifest. Reading ingest_gate.py:134-143 before editing `sidecar:` converted a wrong claim ('N1 would skip two sources') into the real one: the files exist and validate, so the stale value is a DISARMED TRIPWIRE — harmless today, silent if a sidecar is ever deleted. Census-01's decay-not-construction finding, instantiated.", "valid_from": "2026-08-06", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-06-evening-the-asterisk-that-carried-meaning.md", "extracted_at": "2026-08-06"}
|
||||
{"subject": "engine/retrieve.py", "predicate": "state", "object": "Parse fix landed 2026-08-06 (27b79ca): _match_expr phrase-quotes each term, punctuation inert, semantics measured unchanged over all 27 chavruta items. 26 crashes -> 0. HIT 0/22, MISLOCATED 0, FALSE-POSITIVE 0. 0/22 is the recorded number to beat. First test floor: tests/test_retrieve.py (21 checks), tests/chavruta_harness.py.", "valid_from": "2026-08-06", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-06-evening-the-asterisk-that-carried-meaning.md", "extracted_at": "2026-08-06"}
|
||||
{"subject": "the embedding arm (measure-rerank-voicescoped.json)", "predicate": "measurement", "object": "recall@20 = 22/22 voice-scoped on the SAME 22 scoreable chavruta items where FTS conjunction scores 0/22 (id-sets verified identical, 2026-08-06). The capability was measured in June and never landed — no vector table. V2 is the gate that makes surfacing it safe; landing it first is the answer-more direction.", "valid_from": "2026-08-06", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-06-evening-the-asterisk-that-carried-meaning.md", "extracted_at": "2026-08-06"}
|
||||
{"subject": "fidelity_equivalence@3", "predicate": "defect", "object": "_MARKUP_EMPHASIS = re.compile(r'[_*]') strips EVERY asterisk including backslash-escaped literals, erasing Alexander's confidence rating (81 two-star / 114 one-star / 54 none across A Pattern Language). The ruling authorized excluding DELIMITERS; the implementation excludes CHARACTERS. fidelity.py already states the correct principle for the sibling footnote class one line above. PENDING-111 + jurist package 2026-08-06; @3 governs until ruled.", "valid_from": "2026-08-06", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-06-evening-the-asterisk-that-carried-meaning.md", "extracted_at": "2026-08-06"}
|
||||
{"subject": "difference of formation (differently-biased-checkers doctrine)", "predicate": "evidence-for", "object": "2026-08-06: of seven corrections, instruments caught four, the jurist one, the steward two — and BOTH of the steward's came from reading a PHYSICAL COPY of A Pattern Language (the asterisk rating; the 32-vs-253 usage note). Neither was reachable by any instrument in the engine; the passage defining the notation is withheld paratext the engine structurally cannot read. Recorded per the doctrine's own requirement that evidence be logged when observed, not only when sought.", "valid_from": "2026-08-06", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-06-evening-the-asterisk-that-carried-meaning.md", "extracted_at": "2026-08-06"}
|
||||
|
||||
Reference in New Issue
Block a user