David/dotfiles
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

session 2026-08-13: fr identification pass, PENDING-135/136 filed and ruled, voice_stamp built; memory + register + KG

Browse Source
This commit is contained in:
David F Glidden
2026-08-13 21:28:46 +02:00
parent 92d5ad2547
commit e90c334bb2
6 changed files with 328 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
claude/memory/knowledge-graph.jsonl
+10
View File
@@ -641,3 +641,13 @@
{"subject": "reading the PLACED record instead of the relayed message", "predicate": "prevention", "object": "REVERSED A DECISION I HAD ALREADY MADE AND LOGGED AS A COST — third consecutive instance. I froze four documents on the relayed condition 'no document may call the artifact V4's fixture', and recorded in the ledger that 'deliberately unedited' was also 'preserving a falsehood' (CLAUDE.md L61 asserted an empty file was the designated fixture). The PLACED condition 4 reads '…may be corrected to name existing material; they may not assert a fixture that is half-done' — the opposite of my reading, resolving the exact tension I had flagged. The banked rule (quote from the FILE, never the relayed message) fired and changed the action, not merely the citation.", "valid_from": "2026-08-09", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-09-the-fixture-was-an-empty-file.md", "extracted_at": "2026-08-09"}
{"subject": "resurfacing the banked artifact before deriving", "predicate": "prevention", "object": "STOPPED A FULL RE-DERIVATION OF MEASURED GROUND. The inherited resumption point said to 'settle the baseline asymmetry BEFORE the chavruta re-run'. P7 had already run on 2026-08-07 and committed corpus/v2-stratum-tags.yaml, which measures it exactly: EN divisions median 27,833 chars vs FR spans median 969 (29x, max 198,258). It also holds three further findings the wrap never mentioned — including that the fr authoring plan INVERTS (inherited 1A:9B; §6.3 would land ~1:27 against §6.2's 1:1). Checking the artifact first converted a session of re-measurement into one act: narrow the EN anchors.", "valid_from": "2026-08-09", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-09-the-fixture-was-an-empty-file.md", "extracted_at": "2026-08-09"}
{"subject": "driving a degraded state rather than reasoning about it", "predicate": "prevention", "object": "CORRECTED THE RULING THAT AUTHORIZED THE WORK. REVIEWED-113's design gate inferred the (manifested, not-probed) cell would collapse into `silence`, flagged that as 'inference, not reading' and invited the check. Driving it raised KeyError: 'arendt' — a crash in ENGINE code, the class PENDING-126(c) had closed suite-side only, and the second engine-side instance after retrieve.py:134. The correction ran executor→ruling, which the differently-biased-checkers doctrine predicts; recorded as an instance, proving nothing general.", "valid_from": "2026-08-09", "valid_to": null, "confidence": 0.9, "source_file": "session-2026-08-09-the-fixture-was-an-empty-file.md", "extracted_at": "2026-08-09"}
{"subject": "claude-code", "predicate": "drift-pattern", "object": "control-set-drawn-from-one-source: every positive control for the nested-voice census lived in Mauss — one quotation convention (guillemets), one line structure (paragraph-per-line). The instrument was therefore blind to ASCII quotes (3 sources, incl. the two largest EN texts) and to hard-wrapped text (2 sources), and reported a CLEAN ZERO for both rather than an error. Five defects total; four escaped the controls entirely. Coverage is the whole of a control set's strength.", "valid_from": "2026-08-13", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-13-the-fence-was-never-blocked.md", "extracted_at": "2026-08-13"}
{"subject": "claude-code", "predicate": "drift-pattern", "object": "count-by-subtraction-not-enumeration: wrote bound_instances_grounded as 12 by computing 15 bound - 3 retracted, silently ignoring that instance 17 had already left the grounded set at P7. Correct is 10. Committed the SAME error PENDING-136 was filed about, inside the session that filed it — and P7's original error entered the same way. Enumerate against the actual rows; subtraction is how the error enters.", "valid_from": "2026-08-13", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-13-the-fence-was-never-blocked.md", "extracted_at": "2026-08-13"}
{"subject": "claude-code", "predicate": "drift-pattern", "object": "one-marker-over-two-dispositions, recurring: voice_stamp's first verdict vocabulary returned `boundary-crossing` for BOTH fragments of instance 8 — whose differing dispositions are the entire reason the instance is before the steward. PENDING-133's exact finding, reproduced inside the instrument built to address it. Split into crosses-opening / crosses-closing / spans-quotation. Caught only by the suite's load-bearing negative.", "valid_from": "2026-08-13", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-13-the-fence-was-never-blocked.md", "extracted_at": "2026-08-13"}
{"subject": "claude-code", "predicate": "drift-pattern", "object": "unscoped-git-add-in-dotfiles: used `git add -A` in a dotfiles commit, sweeping the steward's freshly-placed REVIEWED-119/120 and a sysupdate Brewfile line under an executor message about MCP key descriptions. /wrap-up §6.5 forbids exactly this and states why — the steward's in-progress changes belong to the steward's sweep. Amended before push. NOTE the routing gap: the rule is stated only in §6.5, which fires at WRAP, while dotfiles commits happen throughout a session.", "valid_from": "2026-08-13", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-13-the-fence-was-never-blocked.md", "extracted_at": "2026-08-13"}
{"subject": "substrate-checking a disposition clause instead of reading it as status", "predicate": "prevention", "object": "CAUGHT AN AUTHORIZED-BUT-UNEXECUTED RULING THAT HAD SAT THREE DAYS. REVIEWED-118's `**If AUTHORIZED:**` line reads like a completed act; grepping for `REVIEWED-118` in corpus/ and docs/ returned nothing and the L926 instances still stood. The /wake-up step's own rule (a disposition clause is not a status) fired and changed the wake's report from 'done' to 'the unblocked next act' — which became the session's first work.", "valid_from": "2026-08-13", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-13-the-fence-was-never-blocked.md", "extracted_at": "2026-08-13"}
{"subject": "checking a suspicious ZERO rather than accepting it", "predicate": "prevention", "object": "CONVERTED A FABRICATED MEASUREMENT INTO A REAL ONE, TWICE. The census reported 0 inline quoted spans for harrison/alexander/after-the-reply; checking found 2005 and 1348 ASCII quotes the matcher could not see (43% undercount). Then the steward's challenge to a dismissive aside about musil found the same shape structurally — musil is hard-wrapped, so a within-line matcher guaranteed ~0 before the file was opened. A clean zero is the most dangerous output an instrument can produce, because it reads as a finding.", "valid_from": "2026-08-13", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-13-the-fence-was-never-blocked.md", "extracted_at": "2026-08-13"}
{"subject": "reading the ratified schema before repeating a blocking claim", "predicate": "prevention", "object": "STOPPED A REVIEWED ENTRY FROM CARRYING A FALSE BLOCKER. PENDING-135 stated option (d) was blocked on PENDING-131 (c) — the chamber-locked studium/meta@1. Opening v2-harness §14.2 before drafting REVIEWED-119 showed the real constraint is studium/v2-gold@1's `lines: [a, b]`, which is ENGINE-SIDE and D-1. Had it gone unchecked, an authorization would have stood on a false blocking claim — the trap REVIEWED-115 pt 1 voided an authorization over.", "valid_from": "2026-08-13", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-13-the-fence-was-never-blocked.md", "extracted_at": "2026-08-13"}
{"subject": "PENDING-134", "predicate": "blocked-by", "object": "H1 — the four V0-lane governance_read keys are registered on disk (4c3758e) but NOT SERVED: governance-mcp.py builds FILES at import, so the running client holds the old eight-key map until the STEWARD restarts it. Executor half discharged 2026-08-13 (selftest 54/54; two stale key descriptions refreshed at 92d5ad2). The remaining step is a client restart, not a build.", "valid_from": "2026-08-13", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-13-the-fence-was-never-blocked.md", "extracted_at": "2026-08-13"}
{"subject": "PENDING-131 (c) sub-line addressing", "predicate": "does-not-block", "object": "the engine's citation path. chunker.py has recorded `char_range: [cstart, cend]` document offsets since Cluster A, so voice_stamp addresses sub-line extents with no schema change and no cross-repo consent. The line-granularity ceiling was an artifact of where the fence was being WRITTEN (the sidecar), not of what the engine can SEE. (c) remains real for the sidecar.", "valid_from": "2026-08-13", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-13-the-fence-was-never-blocked.md", "extracted_at": "2026-08-13"}
{"subject": "free indirect discourse", "predicate": "is-not", "object": "a provenance failure. Steward-argued 2026-08-13 and accepted: in FID there is NO second author to join to — the words are the novelist's, composed in the narrative voice. A PROVENANCE failure has a second author who can be named; a STANCE question has one author and an interpretive judgment about endorsement. Irony shows it is not a fiction matter: Arendt reporting a view to demolish it raises the identical question in non-fiction. Consequence: PENDING-131 (c) stays ONE capability, not two; the residue belongs to PENDING-134 and the synthesized tier's NLI.", "valid_from": "2026-08-13", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-13-the-fence-was-never-blocked.md", "extracted_at": "2026-08-13"}