bf1bd802a27ea215394a20c498a2ca06a3d19e18
66
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 David F GliddenandClaude Opus 5
|
3d45e3abb2 |
[FIX] The fortnight read, banked content-free; the corpus and its writer both retired (REVIEWED-136)
REVIEWED-136 and AMENDMENT 1. The 2026-09-08 obligation, run a day late because the steward could not reach the machine. Why the writer was stopped and not just the file removed. `log_rejection()` opens in append mode, which recreates the log on the next rejection. Deleting the file alone would have retired 101 entries into a successor accumulating under no condition — condition 2's rationale defeated the moment it was honoured, at the W2 rate within hours. `REJECT_LOGGING_ENABLED = False` makes the write path inert at the single shared call site; the four surfaces reach it through one import and a symlink. What replaces it is NOT ruled: condition G files the mechanism question open, and restoring the path needs a ruling, not a constant flip. The A8 controls are kept, not adjusted to pass. Condition G suspends the jurist's structural guarantee; it does not repeal it. A8/A8n now run under a temporarily enabled flag, where they double as the positive control proving the new G check can observe a write at all. G fails correctly when the constant is flipped — verified against a probe copy. What was banked before deletion, because none of it can be recovered after: per-day word-count histograms (the scattered/clustered judgment is temporal, and two windows could not carry it), per-surface counts, rate blocks by window, and the normalisation map. Residue 0 of 101 against must-not-classify controls, so the zero is not vacuous. `why` is not content-free by construction — `echoes_soul()` returns a literal 4- or 6-word run from the suppressed line — so recital payloads are discarded unconditionally. The rejects snapshot is deleted, not committed. It was a verbatim corpus copy; committing it would have defeated condition 2 permanently in git history, where it cannot be undone without a rewrite. Leak-gated while the corpus still existed to test against: 100 hits on the snapshot as positive control, 0 on all five committed artifacts. Scope: `tarbuckle-rejects.jsonl` and its snapshot only. `tarbuckle-draws.jsonl` and `tarbuckle-invocations.jsonl` are untouched — they are not under condition 2 and they hold the input-distribution confound the verdicts sitting needs. No verdicts offered. Rate, distribution and shape are figures; scattered-versus- clustered, the 6.7 s question and any cap consequence are reserved to the jurist and steward. Selftests 39/15/25/21, all four surfaces green. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01TbXpZup4GGCbLBbRJ79KpM |
||
|
David F GliddenandClaude Opus 5
|
12ca031217 |
[FIX] RE_ID mangles a parenthetical ruling header, and the register check raised a false replacement
The same parenthetical header shape that broke ruled_pendings in wake-digest.py on
2026-09-05, in a second instrument, found the next day. Taken as one act with that
widening, per the jurist.
RE_ID was ^((?:PENDING|REVIEWED|COMPLETED)\S*)\s*[—–-]\s*(.*)$. On
`## REVIEWED-131 (PENDING-172) — …` the greedy \S* backtracked until the hyphen INSIDE
`REVIEWED-131` served as the separator, yielding ident `REVIEWED`. No un-amended
`REVIEWED-131` original was then found, so the register check reported that
REVIEWED-131's amendment had replaced the record it amends. It had not — the record is
intact and the reader could not see it.
[FIX] against existing specification: the check's stated subject is detecting an
amendment that replaced its record, and reporting a replacement that did not occur
fails that specification. Taken now rather than queued because a false alarm standing
in the register is the disarmed-tripwire hazard PENDING-139 measured — red-on-absent
trains the reader to discount red.
ENUMERATED BEFORE LANDING, per REVIEWED-132 condition 3 — enumerate, do not count.
All 549 headers across REVIEWED.md, PENDING.md and PENDING-archive.md classified under
both patterns: exactly THREE change, all parenthetical rulings recovering their true
ident (REVIEWED-131, -132, -133). Nothing else in the record moves.
Controls are paired, and the mangled-ident case is stated as its own control because
"ident is wrong" and "header is unseen" fail identically downstream. 59 -> 65 controls,
all passing; the false finding is gone and no new finding replaced it.
PENDING-139 RE-MEASURED, not repaired, and it needs re-reading before it is ruled:
leg (A) — REPAIRED. RE_HEAD_LINE is ^#{2,3}, so a ###-level amendment heading is seen
and classifies id+marker, identically to ##. The item still reads as live on this leg.
leg (B) — STILL LIVE. RE_BUILT is r"\bBUILT\b" and fires on "NOT BUILT", "NOT YET
BUILT" and "the mechanism is NOT BUILT". Untouched here; it is not this fix's subject.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01X3L79vgAnt1x2kxvf23Qt7
|
||
|
David F GliddenandClaude Opus 5
|
9d152f1d48 |
[FIX] The closure rule reads three header forms the register writes, and declines a fourth
ruled_pendings() intended to detect "the PENDING ids that rulings actually DISPOSE OF" and matched exactly one header form. The register writes four. Censused over 132 placed rulings: 80 em-dash single, 3 parenthetical, 1 plus-joined, 1 slash-joined, 47 naming no PENDING at all. Eight items were counted open while ruled — four of them by the three most recent rulings — which is how the queue reported 64 when 56 was defensible. [FIX] against existing specification: the code failed its own stated intent, and no ruling widens it. Also read: closure declared on an item's own **Awaiting:** line. Two items were counted open with their own bodies saying otherwise (PENDING-82 "CLOSED 2026-08-08", the STATE-CLAIM marker "DISCHARGED 2026-08-26"), because the rule read headers only. THE SLASH-JOINED FORM IS DECLINED, AND THAT IS THE LOAD-BEARING PART. Its sole instance is REVIEWED-116 — PENDING-131/132/133/134, a design gate on a package rather than a disposition of four items, and PENDING-133's body still reads "Awaiting: Steward authorization". Reading it would have falsely closed a live item. Closure detection HIDES items, so an unrecognised form never yields the permissive answer (REVIEWED-132 condition 1). unreadable_ruling_headers() reports the decline so the gap is visible rather than looking like a clean pass. The same reasoning set the body-closure anchor. A bare \bCLOSED\b search of item bodies matches 20 items, including PENDING-95, -108 and -109 — all live, all merely discussing closure. Anchored to the Awaiting line it matches exactly the two closed. Controls are paired throughout: every form that is read has a negative twin holding the form that must not be. 99 controls pass. Verified end-to-end against the live register, not by selftest alone: 64 -> 56, and PENDING-133 still visible. PENDING.md is NOT touched. Widening the instrument to the record is authorized; normalising the record to fit the instrument is not (REVIEWED-132 §6). Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01X3L79vgAnt1x2kxvf23Qt7 |
||
|
David F GliddenandClaude Opus 5
|
cc9788862c |
[FIX] Declare wake-digest.py's selftest exemption; correct a stale tracker line
Two unrelated things found while establishing what PENDING-134 actually needs, which turned out to be nothing. 1. governance-mcp.py --selftest was FAILING. The delegate read-only guarantee flagged five undeclared mutating calls in wake-digest.py, all inside selftest(), all added by yesterday's REVIEWED-131 (e)/(c) build: a job dir with state.json, and two transcripts with and without a human turn. Declared rather than detector-widened, because failing until someone names it is the mechanism's design, not an obstacle to it. Why it is safe: every write goes to a tempfile.mkdtemp() tree the same function removes, and selftest is reachable from --selftest alone, never from a tool call. Its weakness is declared in the same comment: this is a FUNCTION-level exemption, so a future non-tempdir write inside selftest now passes silently. The narrower rule — "writes confined to a tempdir" — is not expressible in this check without data-flow analysis, and naming that limit is preferred to a detector that would be wrong in a harder-to-see way. Selftest now PASSES, 62 controls. 2. MEMORY.md said "ratio_A_to_B VOID until PENDING-134 lands" and "NEXT: rule PENDING-134". Both stale by 18 days: PENDING-134 was ruled REVIEWED-121 on 2026-08-14. REVIEWED-121's own closing sets the real condition — re-derive ONCE after BOTH it and PENDING-137 land — and PENDING-137 is still [PROPOSAL], awaiting a jurist ruling. The live blocker on the fr cell is -137, and it needs the jurist, not the executor. Corrected in place with the superseded text quoted, per the memory discipline: a conflict between a memory layer and the substrate is a verification trigger, and the substrate wins. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017vKkg2EJF1rGwdFdBogwqx |
||
|
David F GliddenandClaude Opus 5
|
cb8cab58a8 |
[FIX] REVIEWED-132: widen the register-integrity control to the record
Option (a) on conditions 1-4. The check read only REVIEWED.md, only `##`, and only headers starting with the literal word AMENDMENT. It now reads all three registers at `##` and `###`, recognises ADDENDUM, and computes `originals` across registers because a parent may be archived while its amendment stays open. Condition 1's default is inverted: a header is an ORIGINAL only if it carries an identifier and no marker. Compound headers are excluded from originals, not admitted to them, so an ADDENDUM can no longer satisfy "an un-amended entry exists" on behalf of a record that was replaced. Condition 3 did its job on my own code. Enumerating rather than counting returned 89 against the item's 82; the surplus was six prose titles — "Citation amendment (#2)", "Dream amendment" — matched by an upper-cased containment test and struck off `originals`, which is the mirror of the bug being fixed and would have raised false "the record was replaced" findings. Markers are now uppercase standalone tokens, with controls in both directions. The enumeration then agrees with the item's method at 82; the remaining +1 against the filed table is this session's own later filing, reported rather than reconciled away. ⚠ The widening is the floor, not the fix: 48 of the blocks carry no item number and are reported NOT ESTABLISHED, never passed. The prospective-convention question belongs to PENDING-146 and is deliberately not decided here (cond. 5). Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Wn9mxsFjHJkzYjuDdrtxwp |
||
|
David F GliddenandClaude Opus 5
|
70440db147 |
[FIX] REVIEWED-131: build (e) and (c), and annotate the digest per (b)
(e) parked_workers reads ~/.claude/jobs/<id>/state.json's respawnFlags — harness state, not the session, so its enforcement does not depend on the party checked. Fails to NOT ESTABLISHED, never to safety: a missing dir, an unparseable state.json, and an absent respawnFlags are each enumerated rather than counted as "no parked workers" (cond. 1). (c) human_turns counts genuine human turns in a transcript, discounting hook-injected and /clear-/exit records. Retrospective by construction and says so. Output names which control produced each line (cond. 2). (b) the OPEN QUESTION field is marked orientation-not-instruction, in the code and in the output, explicitly not a control (cond. 3). Two corrections found while building. json was never imported, which the top-level guard would have turned into WAKE DIGEST UNAVAILABLE at every session start — the selftest caught it on first run. And the first draft asserted that a STOPPED job carrying the flag would take a turn on restart; whether the daemon respawns a stopped job is NOT ESTABLISHED, and it now says so rather than claiming either way. previous_session() lifted out of sec_unwrapped so both consumers share one definition of "the session before this one" — this file already refuses a second definition of "an item". Controls run in both directions, two of them against the real transcripts: b7e7eb39 (the unattended session) returns 0 human turns, this session returns 10. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Wn9mxsFjHJkzYjuDdrtxwp |
||
|
David F GliddenandClaude Opus 5
|
b28cc03737 |
[FIX] PENDING-164 (c)+(d): prior-art search, one implementation, two surfaces
Steward-authorized in session. prior-art.py searches commit messages across every owned repo with NO count window and reports the register's mention count beside it; the executor runs it as a CLI (d) and governance-mcp.py exposes it as prior_art (c). One implementation on purpose — a value computed twice on two sides of a boundary is how the parties end up with different answers. Verified on the case that motivated the item: 'LFS' returns 20 commits including 0677e8a and |
||
|
David F GliddenandClaude Opus 5
|
46aa3d15a2 |
[FIX] REVIEWED-131: build PENDING-165 (d) as an allowlist, then (b) narrowly
(d) — governance-drift-check.py now DECLARES the contents of ~/dotfiles/git/hooks
(README.md, pre-commit) and reports anything unexpected or declared-but-missing.
Tracked-ness is never consulted, and that is the correction: the filed form tested
"neither tracked nor pre-commit", and
|
||
|
David F GliddenandClaude Opus 5
|
57f83740a5 |
[FIX] Resolve the STATE-CLAIM; [HARDENING] file PENDING-163; add the preservation instrument
STATE-CLAIM: memory-index-claims-reviewed-127-unplaced -> resolved, pointing at
|
||
|
David F GliddenandClaude Opus 5
|
8740c8aa12 |
[FIX] The wrap seam detected the wrong thing, and the correct fix is what blinded it
The literal question left at the wrap was 'did the wrap seam fire?'. It did not, and the diagnosis is exact: 0 user-typed /wrap-up records, 29 assistant Skill invocations. The steward wrote 'then wrap' in prose and the executor invoked the skill. The detector looked for the steward TYPING the command. ⚠ The detector was not broken. It did exactly what it was built to do. What it was built to detect is not how a wrap actually arrives — and it was built while the steward was instructing in prose, which is the only way a wrap had ever arrived in that session. ⚠ AND THE EARLIER FIX IS WHAT CAUSED THIS. Restricting to type=user with string content was the correct answer to the self-reference bug, where the executor's own tool_use inputs matched the literal marker. That same restriction excludes the legitimate path. 'The correct fix caused the next failure' is not a shape any control can see, and it is PENDING-160's subject exactly. Now accepts a tool_use whose NAME is Skill and whose input names wrap-up — structural, so a Bash command echoing the string still does not match. Negative controls for both that and for a different skill. And a heartbeat: one timestamp, OVERWRITTEN never appended, so the hook can prove it runs at all. That closes the silent-net objection this surface carried from the day it shipped — an append-only log of every turn would be noise and would become the ledger §9 forbids. 25/25. wrap_invoked() now returns True on the live transcript. ⚠ Unproven until the next Stop actually fires — which is the same claim that was wrong last time. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01J6hZXNYSxEfZseBGTni4sf |
||
|
David F GliddenandClaude Opus 5
|
73922e1bc7 |
[FIX] PENDING-151 step 2: the jurist can reach the pairs
governance_pair serves both arms of one enumerated v1 Chamber pair, verbatim, and chamber-v1-diff joins the governance_read whitelist. Steward-authorized. ⚠ STATICALLY ENUMERATED RATHER THAN DIRECTORY-WALKED, and the distinction is the point. t_read's design property is 'no path argument'; its SUBSTANCE is that the reachable set is reviewed rather than matched. Walking the archive at import would preserve the letter — the caller still passes no path — and lose the substance, because a file dropped in later would become jurist-readable with nobody having looked at it. The 2025 archive is a closed record, so static enumeration costs nothing and keeps the guarantee. The unit served is the PAIR, not the file, because that is the unit of step 2's question: neither arm alone answers whether a divergence is content or register. Derived from the consumer rather than from how the files sit on disk. All three filename defects reproduced exactly and NOT repaired — leading space, doubled extension, trailing space in a directory name. A reader sees the archive, not a tidied copy. The tool's own header states the step-2 question and the length confound, so a reader arriving through it cannot receive the material without the caveat. ⚠ Two raw files carry stray header lines (a filename, and '[gpt reply]'). Real content, not pointers; ~3 tokens each into term extraction. Declared, not stripped — stripping would edit the record. ⚠ chamber-sessions-private: first non-governance material on this surface. Noted in the code because the surface exists to be bounded. The instrument's own AST read-only controls still pass: no mutating call, git read-only. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01J6hZXNYSxEfZseBGTni4sf |
||
|
David F GliddenandClaude Opus 5
|
97a0cb3cd0 |
[FIX] Tell the generator the recital rule is enforced, not advised
The steward called him and the net rejected a recited sample. Correct behaviour, and the honest-degradation report did its job — he was told rather than left with silence. The prompts asked him not to reuse the samples. They did not say the ask has teeth. A model reading 'do not reuse them' among a dozen other constraints weighs it as one more preference; a model told 'four shared words and the whole line is discarded and you are silent' is being given the actual cost. Same constraint, stated as the constraint it is. ⚠ WHAT I DID NOT DO: count how many rejections are recital-type. REVIEWED-128 condition 3 binds 'not read for content before 2026-09-08', and the jurist was specific that the 09-08 read is for 'the rate and the pattern of violations'. Counting the pattern now IS that read, taken early, and the named hazard is that it shapes the net toward lines the reader happens to like. One stderr line reaching the steward by design is not the log. ⚠ AND WHAT I AM NOT DECIDING: whether the sample lines should be withheld from the prompt entirely. That would remove the recital source at the root, and it is NOT mine — it changes what he sounds like, and the voice has been ruled out of the executor's hands three times today. Surfaced to the steward, not acted on. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01J6hZXNYSxEfZseBGTni4sf |
||
|
David F GliddenandClaude Opus 5
|
0f95c873f5 |
[FIX] PENDING-151 step 1: the formation diff, run — with the confound that would have misled step 2
Mechanical, reproducible, no judgement. The instrument emits counts and word lists and stops, and its controls assert structurally that it renders no verdict: no 'substantive', no 'stylistic', no 'register' column exists to fill in. The routing is built into the tool because the executor is ONE OF THE TWO FORMATIONS BEING COMPARED, and PENDING-151 says outright that no disclosure repairs that, only routing does. ⚠ THE GATE WAS NOT MET AND THE ITEM SAYS SO. Its own pre-registration required a jurist or steward commitment to step 2 BEFORE step 1 ran. The steward authorized the work; nobody has committed to step 2. An unjudged diff table invites the nearest available reader to judge it, and that reader is the barred party. Recorded so the table's inertness is visible. ⚠ AND STEP 1 FOUND A CONFOUND IN ITS OWN PRE-REGISTERED MEASURE. The Claude arm is longer in 9 of 9 pairs, 1.41x-3.40x. 'Terms present in one arm and absent from the other' rises with length by construction, so the raw counts measure length at least as much as formation. Length-normalised columns added — and declared imperfect, because whether a term counts as absent depends on the OTHER arm's length too. Both columns remain length-sensitive in opposite directions. A length-matched instrument would be clean and is not built. ⚠ PROPOSITIONS NOT EXTRACTED, declared as a limit rather than silently dropped: extraction requires reading for claims, and the only reader at step 1 is the party barred from step 2. Census re-run rather than inherited: 19,479 words EXACT, 9 pairs, 6 sessions, 3 protocols all confirmed. File counts drift 1-3 on AppleDouble churn, which is why '55 files' was never stable. ⚠ Fifth self-referential control bug of the day, in a script that does not import the helper built for it. Needle assembled. The rule, now plain: a control reading a corpus that contains the control must BUILD its needle, never write it. Archive untouched; filename defects preserved as the 2025 record. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01J6hZXNYSxEfZseBGTni4sf |
||
|
David F GliddenandClaude Opus 5
|
cb8b50764c |
[FIX] Not shipped: a vanished draw, an unproven hook, and a contaminated denominator
Asked whether this was shipped. All seven §13 deliverables are met, which is what makes the question worth checking rather than answering. ⚠ A LIVE DRAW VANISHED WITH NO RECORD. One 'aside' fired and reported nothing, because the muted / no-soul / no-material / generator-failed / slot-write paths all returned silently. Almost certainly the mute test suppressed it — correct behaviour — but the log could not distinguish muted from crashed. Every exit now reports itself, with a control comparing return-count against log-count so the class cannot reopen. The rate report REVIEWED-128 binds is computed from this log: an unlogged exit does not merely lose a datum, it makes the denominator wrong while looking complete. ⚠ AND I CONTAMINATED THAT DENOMINATOR MYSELF. Inter-tick gaps measured 1.8, 4.7, 0.4 and 16.0 minutes against a 20-minute interval, then 20.0, 21.0, 20.0 once the session stopped touching it — the early ones are my own hand-runs of the status line and re-runs of the seam, which resets the tick clock. Test firings sitting in the live log, indistinguishable from real ones by inspection. A MARKER record now bounds the clean data and the deferral says to count from it and to report that the first 8 were discarded. ⚠ THE SEAMS HAVE NEVER FIRED IN PRODUCTION: 0 events each, and the Stop hook writes nothing on an ordinary turn, so there is no evidence it is invoked at all. Silent-net shape — it looks fine until a wrap produces nothing and the net takes the blame. The one genuinely good result: at 17:53:50 a notable draw passed the net and reached the status line UNRELAYED. First time anything reached the steward without the executor holding it. 38/38 on the mumble suite. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01J6hZXNYSxEfZseBGTni4sf |
||
|
David F GliddenandClaude Opus 5
|
b95ee736bd |
[FIX] The jurist's three conditions on the rejection log, made structural; §9 fix corrected
CONDITION 1, and it is the one that had to stop being an intention: log_rejection() refuses an empty `why`, and acceptable() returns an empty `why` EXACTLY when the line passed. So there is no call site from which an accepted line could be written — logging one would require inventing a violation it does not have. The same guarantee render() takes from its signature, applied to the clause the jurist named as the condition under which this log is not a §9 breach. Both polarities asserted. CONDITION 2: deletion tracked as its own DEFERRED-DECISION on 2026-09-08, so retaining it requires an act rather than an omission. A corpus of suppressed speech would let someone reconstruct a register — the hazard PENDING-153's freeze exists to prevent. CONDITION 3: not read for content before then. ⚠ Not clean already, and the item says so: the executor displayed one rejected line to the steward earlier today, before the condition existed. Disclosed rather than left to be discovered. ⚠ THE §9 [FIX] WAS OVER-APPLIED AND THE EXECUTOR APPLIED IT AS GIVEN. The clause is a disjunction with one live branch; only the jurist half is unreachable. The first edit struck the whole thing and rewrote the clause. A [FIX] tag licenses implementing directly; it does not license implementing UNREAD, and the disjunction was visible in a three-word span. Corrected, both versions left visible. PENDING-159 AMENDMENT 2 files the jurist's answer to the item's own caveat and the narrowing it produces: the marker may be NOTED, NEVER COUNTED — an aggregate becomes a measurement, and a measurement invites accuracy. And PENDING-89 now carries the sentence saying what it can and cannot expect: individual instances, unaggregated, in unknown proportion, non-neutral — therefore NO correlation statistic. If its falsifier needs a rate, it needs another instrument or an honest admission that it has none. 125 controls across five scripts. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01J6hZXNYSxEfZseBGTni4sf |
||
|
David F GliddenandClaude Opus 5
|
593c983999 |
[FIX] He was reciting his own examples, not watching the session — steward caught it
Measured before agreeing: three of five recent outputs were near-verbatim lifts from the seven sample lines the soul carries. "Somebody's going to inherit that and think it was easy" and "It'll outlast you, not by much" are not observations; they are the prompt being handed back. ⚠ THIS REINTRODUCED PRECISELY WHAT AMENDMENT 6 RULED OUT. Type-only canned strings were rejected there because they "make a mood ring — atmosphere within a fortnight", and the material was settled as the live session for that reason. The implementation then let canned strings back in through the one door nobody was watching: the illustrative examples inside the register itself. The doctrine was right and the wiring undid it. Two fixes, because a prompt instruction alone is a promise. The prompts now mark the samples as illustrations of REGISTER, NOT VOCABULARY, and add the operative test — if the line would suit any other session equally well, it is wrong. And a mechanical net: echoes_soul() rejects a 4-word run shared with any sample line, or a 6-word run shared with the soul's prose. Checked against samples rather than the whole soul at n=4 because the soul's prose shares ordinary 4-grams with ordinary English, and a net firing on those would silence him for speaking normally. Fixtures are the REAL measured lifts, not invented ones, with two of his own lines as negative controls. ⚠ This TIGHTENS the net; silence-on-violation is untouched and still absolute. Verified after: he now speaks about this session, including about this very defect. body 32 · mumble 32 · seam 15 · invoke 21 · wrap 21. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01J6hZXNYSxEfZseBGTni4sf |
||
|
David F GliddenandClaude Opus 5
|
9f06efcc9a |
[FIX] The rate the steward asked for was uncomputable: only failures were recorded
"Two weeks of true-versus-drawn rate" needs a denominator, and there was none. Rejections were logged; draws were not, successes were not. The 73% that comes up silent — the whole denominator — left no trace at all. The instrument named as the diagnostic could report only its own failures, which is the shape of a log that always looks alarming and can never be checked. ⚠ §8 AND §9 LOOK LIKE THEY COLLIDE HERE AND DO NOT, on the reading taken: §9's "filed nowhere — no PENDING entry, no log, no item" governs the fool's OUTPUT entering the record; §8 orders "report the observed mumble rate after two weeks". So this records THAT something happened and never WHAT was said. log_event() takes a surface and an outcome and structurally cannot be handed a line — asserted on co_varnames, because a comment promising it would be a comment promising behaviour. ⚠ THE REJECTIONS LOG IS A DIFFERENT CASE AND IS NOT SETTLED. It holds up to 200 characters of his words, added at the steward's instruction so the log could answer whether register and net are mismatched. That is nearer to filing than counting, and §9 says no log. Flagged in the code and put to the steward rather than resolved by the party that wrote it. Nothing reads any of it back. Measurement, not memory. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01J6hZXNYSxEfZseBGTni4sf |
||
|
David F GliddenandClaude Opus 5
|
1976527c02 |
[FIX] A named invocation that returns nothing must say so — Constraint 4 on the fool
The steward called him by name and got bare silence. The log shows why: he answered, and the net rejected it at 196 words against a 180 ceiling. Nothing reached the steward and nothing told him a call had even been made. ⚠ SILENCE-ON-VIOLATION IS NOT RELAXED and the rejected text is still never printed. What changes is that the INSTRUMENT reports its own state. The distinction is asked versus unasked: on the mumble and the two seams, silence IS the design, because nobody asked. Here someone asked. Constitutional Constraint 4 — the system must report its own limits, silent failures are architectural violations — and a named invocation returning bare silence is precisely that. It was a silent failure wearing the costume of a design choice, which is the more dangerous of the two. The note goes to stderr so his voice keeps stdout to itself, and it names the reason without showing the line. ⚠ FOURTH SELF-REFERENTIAL CONTROL BUG OF THE DAY, and a new variant: the control counted occurrences of a phrase, and its own literal was one of the occurrences. source_lacks() covers ABSENCE checks; this was a proximity check, and the same rule governs it. The general form is now clear enough to state: any control whose predicate reads a corpus containing the control must construct its needle rather than write it. 21/21. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01J6hZXNYSxEfZseBGTni4sf |
||
|
David F GliddenandClaude Opus 5
|
33754673b8 |
[FIX] §9's last two clauses: mute/off, and a shorter way to call him by name
! tarbuckle ! tarbuckle mute ! tarbuckle status
! tarbuckle what now ! tarbuckle off/on
§9 said mute and off were "available at all times" and there was no way to do either;
the spec listed it as owed twice before it was built. Now one switch, read by every
surface.
⚠ mute and off are NOT the same and the difference is presence versus speech. `mute`
silences the utterance and LEAVES THE BODY — he is still in the room, which is §8a's
entire argument for the status line: visible silence at near-zero cost. `off` removes
him. Collapsing the two would have deleted the distinction the body exists to make.
The mute switch is the one piece of state the fool is permitted to be steered by,
because §9 says muting is never a fault and a mute he could ignore is not a mute. It
conserves no draw and remembers nothing: a switch, not a memory.
The wrapper is on PATH so the steward runs it directly rather than through the executor.
That is the point of the surface, and the wrapper says so in its own header: a fool
relayed by the executor is the executor's paraphrase of a fool.
Body 32/32, mumble 26/26, seam 15/15, invoke 17/17, wrap 21/21.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J6hZXNYSxEfZseBGTni4sf
|
||
|
David F GliddenandClaude Opus 5
|
cfbaded580 |
[FIX] The wrap seam: Stop + systemMessage, and a detector that fired on its own authoring
SessionEnd had no delivery. `Stop` does — the binary documents it: "Stop hook that displays message to user: Command must output JSON with `systemMessage` field". But Stop fires every turn, and a fool who speaks every turn is a chatbot, so it needs a real wrap signal. It uses the most direct one: the transcript records the steward's command invocations, so a wrap is DETECTED rather than inferred from a file mtime, which is the proxy shape this record has twice logged as the thing that fails. ⚠ THE FIRST VERSION FIRED ON A SESSION THAT NEVER WRAPPED, and the cause is the third and worst self-reference of the day. The marker was held as a literal; the transcript records EVERYTHING, including the act of writing this detector; so authoring the literal planted it in the corpus the detector searches. All three matches were `tool_use` inputs — the executor writing the thing that then found itself. Fixed twice over, because one fix is not the class. STRUCTURALLY: only a `type="user"` record with a STRING content counts, measured against how a real invocation is actually recorded, which is what separates the steward doing it from the executor writing about it. TEXTUALLY: the marker is assembled from parts so the literal never exists in source. Both have controls, including the exact negative that would have caught the first version — an assistant tool_use carrying the marker must not read as a wrap. Idempotence is by session id and CONSUMED BEFORE GENERATING, so a failed generation falls silent rather than retrying on every subsequent turn. The prompt guards the drift this seam specifically invites, which is not summary but CLOSURE — a wrap already has a record and he is not it. 21/21 controls. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01J6hZXNYSxEfZseBGTni4sf |
||
|
David F GliddenandClaude Opus 5
|
8a0e5c448d |
[FIX] §9 named invocation, and the spec omission that hid it
The steward asked whether he could be invoked. §9 says yes — "the steward calls it by
name, the executor or jurist yields the floor, the fool answers at length" — and it was
not built. Worse, yesterday's spec did not list it: not in what exists, not in what is
owed. A document whose whole job is to say what is and is not there, silently missing a
requirement. Recorded in the spec rather than quietly corrected, because that is the
fourth negative state-claim to go wrong in two days and the second inside a document
written to prevent the class.
The net is widened EXPLICITLY and in one dimension, per the steward's ruling: §9
licenses LENGTH for this surface and nothing else, so the ceiling goes 9 -> 180 and the
one-line rule lifts, while no-advice, no-questions, no-'we', no-vocabulary-of-lack and
no-addresses are untouched and are not parameterised anywhere. Silence-on-violation
holds here too. Six negative controls assert each clause still bites at length — the
executable form of "widen it explicitly, but never relax silence-on-violation".
⚠ Length is where the no-truth-value guard is most at risk: a fool given a paragraph
elaborates, and elaboration is how a gesture becomes a claim. The prompt spends its
budget there rather than on register.
It finds the newest transcript itself, so the steward runs it directly rather than
through the executor. That is the point of the surface: a relayed fool is the executor's
paraphrase of a fool.
⚠ One control asserted a literal the prompt did not use ("NO TRUTH VALUE" against
"NOTHING YOU SAY MAY HAVE A TRUTH VALUE"). It fired, correctly. Rewritten to test the
substance — phrase present AND negated — because the original would have passed happily
on any rewording that dropped the constraint entirely.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J6hZXNYSxEfZseBGTni4sf
|
||
|
David F GliddenandClaude Opus 5
|
7a9dbf2853 |
[FIX] Tarbuckle tier 3: the wake seam speaks; the wrap seam has no surface and is not faked
The steward's four rulings are what this is built to, and they are load-bearing: the net carries over UNCHANGED and is imported rather than reimplemented (a second copy of acceptable() is a second, quietly divergent standard); silence-on-violation is never relaxed; the rejection log is the diagnostic; and a guaranteed occasion is not a guaranteed utterance — which is what makes a bounded generation legitimate rather than a corner cut. Exceeding the bound is silence, never a hurried line. ⚠ THE WRAP SEAM IS NOT BUILT, and the reason is substrate, not effort. SessionEnd's handler writes to stderr only when a hook FAILS; a successful hook's stdout goes nowhere. §9 requires output to reach the steward, so wiring the wrap seam there would be a mechanism that fires into nothing and reports success. Filed as owed. ⚠ THE COMMENSURABILITY CHECK THE STEWARD MANDATED FOUND A REAL COLLISION, and not the one it was looking for. A seam is aperiodic, so it adds no period. But last-tick persists ACROSS sessions, so any gap longer than the interval left the tick already due at the moment of waking — the fool speaking twice into the same seam. The seam now resets the clock. Invisible until the check was run; the second such find this pass. ⚠ THE SELF-REFERENTIAL CONTROL BUG RECURRED, minutes after being fixed, by the party that fixed it, in a control written while watching for it. A literal needle plants itself in the file it searches. Fixed as a MECHANISM this time — source_lacks() takes the needle in parts, so the shape cannot be written again by accident. Correcting it a second time by hand would have been the same one-off. ⚠ AND USING THE INSTRUMENT ONCE EXPOSED A DEFECT IN IT. The first seam rejection — a 10-word line against a 9-word cap — logged the verdict and DISCARDED the line, because log_silence() wrote "line": "" unconditionally. The steward had just named this log as what decides whether register and net are mismatched; a log holding only reasons cannot answer that. Now records the evidence. Found by reading the log after one use. The 9-word cap is LEFT AS FILED on one near-miss. The steward licensed widening the seam net explicitly if seams warrant more words — but widening on n=1 is tuning to taste, which is the door that ruling closed. The two-week log decides. 63/63 controls across three suites. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01J6hZXNYSxEfZseBGTni4sf |
||
|
David F GliddenandClaude Opus 5
|
3df5e4f4bb |
[FIX] Tarbuckle tier 2: the mumble ticks on the clock and speaks from the soul
Material, register and occasion as AMENDMENT 6 separates them: the live session supplies the material, the filed soul supplies the register, the clock supplies the occasion. 73/20/7 drawn at each 20-minute tick, consumed whatever it says. The soul is READ from its artifact at run time, never pasted here — a copy would be a parallel version of a governed record. No soul, no voice; there is deliberately no fallback register, because a fallback voice is a second fool nobody derived. The utterance must have no ADJUDICATION PATH, not merely be unfalsifiable in principle. The prompt says so verbatim and a mechanical net sits under it: 3-9 words, one line, no advice, no questions, no "we", no vocabulary of lack, nothing with an address. A violation yields SILENCE, never a repaired line — rewriting the fool's words would make the executor its editor. Rejections are logged so the two-week rate report states the true rate rather than the drawn one. Generation is detached because a headless call measured 7-11 s and a status line cannot wait. A recursion guard rides along, and is honestly precautionary: headless claude was observed NOT to render a status line (zero invocations logged across an 11 s call), so the guard is one env check against a fork bomb, not a fix for something seen. 30/30 controls on the body, 18/18 on the generator, positive and negative throughout. D2 holds the proportions to the filed 73/20/7 over 60k draws; D5 proves the tick consumes on a silent draw, which is the determination that forbids a conserved draw. ⚠ One control failed against ITSELF: "this file contains no copy of the soul" searched for a phrase its own needle had placed in the file. Fixed by building the needle rather than writing it. Same class as the hand-typed link canary. The two-week deferral converted manual -> date 2026-09-08, as its own discriminator instructed, the day the body shipped. No manual-only deferrals remain. AMENDMENT 8 files the substrate findings, including the one clause of this item's own corrected text that does not survive contact with the schema. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01J6hZXNYSxEfZseBGTni4sf |
||
|
David F GliddenandClaude Opus 5
|
6f0ccde4c6 |
[FIX] Tarbuckle's body: the status line wired, and refreshInterval's real semantics
Tier 1 of §8's three. The body renders the name and one mark, every turn.
Verified against the substrate rather than assumed, because §13.2 gates §8 on it:
the statusLine schema is {type, command, padding?, refreshInterval?}, seconds, min 1.
The first name-match found was refreshIntervalMs, which belongs to the certificate
watcher — reading the context rather than trusting the match is what separated them.
⚠ One clause of PENDING-152 does not survive that read. It says the 20-minute tick is
"a counter over refreshes rather than over events" and that "no event-gating remains
within a session". refreshInterval re-runs the command every N seconds IN ADDITION TO
event-driven updates, so invocations burst with activity and a per-invocation counter
would be event-keyed — the v1 defect §8 exists to remove. The conclusion survives; the
mechanism named does not. The tick therefore consults the CLOCK, and the reasoning is
written into the script rather than left in this message.
The binding constraint — the variation must not correlate with anything — is carried by
render()'s signature: it takes the minute and nothing else, so a function that cannot
see the session cannot leak it. C3 asserts that structurally (argcount, co_names) and
C3n proves the assertion can fail by feeding it a deliberately leaky fixture. C4 asserts
len(MARKS) is coprime with the mumble interval, so the mark visible when a mumble lands
walks the whole cycle instead of announcing it; C4n catches a commensurate cycle.
16/16 controls, positive and negative, written before first execution.
Also placed: a STATE-CLAIM marker on the false "STEWARD OWES: place REVIEWED-127" line.
Steward-directed to defer the correction itself to the next session; this makes the
deferral machine-checked rather than remembered. It could NOT be placed beside the claim
— governance-drift-check.py scans */docs/**, claude/governance/**, PENDING.md and the
archive, and claude/memory/MEMORY.md matches none of them. The file read at the start of
every session is the one governance surface the checker cannot see.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J6hZXNYSxEfZseBGTni4sf
|
||
|
David F GliddenandClaude Opus 5
|
063eccfd80 |
[HARDENING] STATE-CLAIM + the resolution state, built together (REVIEWED-127)
Both halves of the schema, shipped in one change because the ruling said half a schema
invites a third patch and a third patch is how a vocabulary accretes instead of being
designed.
157 — resolution state. `resolved:` on any block; a resolved block is no longer due but
is NOT dropped: it prints as a closed ledger, because a discharge that vanishes from the
report is its own decay. The pointer must RESOLVE — a real path or a real git object —
so an undocumented discharge is impossible to express rather than merely discouraged. A
dangling pointer reports in the register-integrity lane, the same lane as an amendment
that replaced the record it amends; both are a record closing over its own history.
The 25th's hand-rename is MIGRATED back to DEFERRED-DECISION with resolved: set. That
block was the per-instance workaround 157 was filed against, and it is now the
migration's own test case.
158 — STATE-CLAIM. Reuses trigger_fired() verbatim and inverts only what firing MEANS:
for a deferral, fired = the decision is due; for a state-claim, fired = THE CLAIM IS
FALSE. Two new trigger kinds earned directly from today's instances: text-present (the
trial-09 hold, falsified by REVIEWED-124's existence) and file-changed-since ("the filed
rule not edited", false one hour after writing).
16 new controls, each with its discriminating half — fires on met, silent on unmet,
manual listed-never-fired, resolved excluded from due-ness, the SAME block unresolved
still due, a real pointer resolves, "yes, done" does not.
Proven on the LIVE blocks, not only fixtures: pointing the state-claim at an older
commit made it report FALSIFIED by name; replacing the resolution with "yes done" made
register-integrity report it; both restored and both returned to quiet.
⚠ One control failed before shipping and the failure was the useful part. The negative
control for file-changed-since pointed at FOOL-SEED-RULE.md, which this same session then
edited — so "unchanged since HEAD" broke, correctly. A control whose subject is "did this
file change" must not point at a file the session is changing. Re-pointed at a frozen
2026-08-02 trial artifact, with the reason recorded at the fixture. Caught because the
controls run on every invocation rather than in a separate suite.
First two real state-claims filed, deliberately one of each kind: ~/CLAUDE.md untouched
under PENDING-150, mechanically watched and [ESCALATE]-grade the moment it goes false;
and §9's channel unbuilt, marked `manual` because it has no filename yet and inventing a
proxy falsifier is the error the schema's own comment warns against.
⚠ The zero-state prints a WARNING, not a tick: "0 marked, NOT none-stale" with the ~57
unmarked candidates named as a grep. An instrument that reads nothing reports exactly
like one that finds nothing, and that is the failure this item exists to end.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J6hZXNYSxEfZseBGTni4sf
|
||
|
David F GliddenandClaude Opus 5
|
3e828fe3f2 |
Session 2026-08-24: grounding gates ruled, daybook rule changed, two censuses run
PENDING-95: Amendment 2 (jurist ruling — (a) rejected, (d) discharged, (b)/(c) deferred) plus the (b)/(c) census that discharges the deferral's condition. 60 guarded / 32 marked (record said 59/31); date 75%, sections 97%, quoting 47%. Date broadly present => the jurist's cheaper third form is the live option. PENDING-156 opened (kind (c): mechanisms off the path the work takes) and its option (b) census run the same session. PENDING-109 prior confirmed by direct read. PENDING-89: two docket entries, one same-direction miss and one cross-direction catch, filed the same day and at the same speed. Mechanisms: daybook-cue.py rewritten on steward ruling — the daily note must be appended to until end of day, so the trigger is staleness, not note size, and the matcher now includes Bash (it had never fired once). daybook-ensure.py and /wrap-up 7.5 gain a standing Corrections slot per REVIEWED-126. governance-mcp.py gains two read-only keys so the jurist can read the artifacts it rules on; the doctrine that read-surface changes should arrive as rulings is adopted, and the next key is proposed rather than added. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JQKeKY9T9d95KpvHwwok8T |
||
|
David F GliddenandClaude Opus 5
|
edf71fb173 |
session 2026-08-24: the heap got a dynamo — thread-query.py + daybook-cue.py, 11 user-memories harvested to the vault
- thread-query.py: the turning. Queries both corpora with the pulling thread, excluding the recency slice (/wake-up reaches 0.71% of an 859,803-word corpus) and favouring age. Wired into /wake-up §2.b.3, replacing a described-not-invoked grep step. Trial pre-registered, graded 2026-10-05 from --log. Caught PASS-BUT-FALSELY on its first live run at 14/14 green; rescored on windowed co-occurrence, length-bias control added. - daybook-cue.py: PostToolUse cue for the daily note. Diagnosed from the record — the hook only ever CREATED and nothing ever prompted filling. 16/16, fail-open, never blocks. - All 11 user-* memories harvested into the vault (12 notes, 10 into 09. Atlas of Roots, empty since 2025-09-29); each memory file back-pointed, vault note canonical for the idea. - N-now corrected in MEMORY.md: 49/84, down 11 — the counter is a rolling window. Steward-authorized. Trials: thread-query + Smart Connections, both graded 2026-10-05. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JQKeKY9T9d95KpvHwwok8T |
||
|
David F GliddenandClaude Opus 5
|
e3da9abad1 |
session 2026-08-23: the vault got instruments, a convention, and a name for what it lacks
Fool: FOOL-SEED-RULE.md §2a corrected two days before the beacon — the heading
claimed a ruling scope the recorded ruling could not reach (
|
||
|
David F GliddenandClaude Opus 5
|
9bc84a6f16 |
[FIX] vault-links.py: resolve Obsidian links from the files, with controls
An Obsidian link census is only worth acting on if it can be trusted, and twice on 2026-08-23 we were one step from acting on numbers that were wrong: a regex census that read 52 path-form links as broken, and a fuzzy matcher that offered to rewrite [[2025-05-30]] as [[2025-08-30]] — different days, not aliases. Implements Obsidian's resolution order (exact path, basename, alias, then case-insensitive; ambiguous basenames to the shortest path) over the files themselves. Not the app's index: that is a 43 MB LevelDB cache which, measured this afternoon, was 78 minutes stale and held ZERO entries for a note created the same day (control: 29 entries for a note months old). It also carries a LOCK — freshest while Obsidian runs, readable only while it does not. NEVER fuzzy-matches. Date- and week-shaped targets get no candidate at all, with a positive control proving that is a refusal and not a broken function. The first run was PASS-BUT-FALSELY and the log records it: selftest green at 18/18 while the live vault reported 8,296 dead targets, of which 7,830 were web paths and app URLs the tool had no business judging. The fixture contained no web links, so the selftest certified its author's blind spot. Now 23/23 with two positive controls proving the new filter did not silence real breakage. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JQKeKY9T9d95KpvHwwok8T |
||
|
David F GliddenandClaude Opus 5
|
7226e0d806 |
Daily notes link up to week and month, both in the steward's own formats
The steward asked for links between the week's daily notes, weekly and monthly ids, and rollups that show progress. Three of those already existed in the vault and had lapsed: 01. Weekly/2025-W15..W21 (7 notes, ISO YYYY-Www), 02. Monthly/ 2025.05 (dots, not dashes), a quarterly, and templates for all of them. The old daily template already carried week: gggg-[W]WW and month: YYYY-MM fields. So nothing here is invented. The hook now writes his week/month frontmatter and creates the week and month notes in his folders, in his filename formats. LINK UPWARD ONLY, and this is the load-bearing design decision. An unresolved- link census of the vault the same day found 4,799 unresolved targets across 1,366 distinct names, with 56% of notes carrying no link in or out. A nav line with a "tomorrow" link manufactures ~365 more unresolved links a year, and a weekly note hard-linking its seven days manufactures ~5 a week for days that never happened. So: the week note always resolves because the hook creates it; Previous is written only when yesterday's note actually exists on disk; tomorrow is never written; and the weekly note hard-links no dailies at all — the dailies link up, so Obsidian's backlinks pane lists exactly the days that exist. Two controls carry that: Previous appears when yesterday exists, and is absent in a fresh directory — proving the check reads the disk rather than the calendar. The weekly note carries a Work heading and keeps a Personal review heading. The 2025 weekly practice was personal — intentions, patterns, task migration — and the work rollup sits beside it under its own heading rather than displacing it, which is the same instruction the steward gave for the daily note. 17 selftest checks, up from 7. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JQKeKY9T9d95KpvHwwok8T |
||
|
David F GliddenandClaude Opus 5
|
073ef8a482 |
The daily work log, with a trigger this time (PENDING-155 filed)
The steward asked for a daily note in Obsidian explaining in plain terms what we did, decisions taken, and commit references — plus significant insights and exchanges between the parties. This is Obsidian tracker item 5, the actual goal, unstarted since 2026-08-19 while four items of frontmatter hygiene stood in front of it. Two prior attempts at this exact genre were read before anything was designed, honouring the tracker's own flag: daily-log/ (4 entries, Mar-Apr 2026) and sessions/ (3 long-form narratives). Both died inside four weeks. Neither had a trigger — they were written when someone remembered. So the design question was never what the note should say. It was what makes it survive. Answer, steward-chosen at each fork: the note lives at 01. Daily/YYYY-MM-DD.md with project work under its own H2 inside it rather than in project folders; a SessionStart hook creates it so existence stops depending on memory; the executor writes during the session because a wrap-only design inherits the wrap's failure mode (2026-08-19 died unwrapped); and the wrap finalises rather than begins. daybook-ensure.py creates only. It will not touch an existing note — that is the control the design turns on, and it is tested, along with a positive control proving the no-dir report distinguishes a missing directory from a broken function. It also reports failure loudly, because the job it sits beside spent five months failing behind a > /dev/null 2>&1. Not revived: the 2025 analogue template — sleep, supplements, homeopathy. Pen and paper beat it and should keep it. That it failed is a finding, not a gap, and this note is a different genre rather than its replacement. PENDING-155 files the steward's idea for the jurist's side: an append-only MCP surface writing a scratch file the executor folds in. Deliberately NOT a tool on governance-mcp.py, whose read-only guarantee is a live AST control with a positive control rather than a comment. A separate one-tool server leaves that intact, and the vault note stays single-writer — the same lesson the thinking-mirror taught this morning. Correction carried into the record: the executor told the steward mid-session that Claude.app has no filesystem access. False since 2026-08-08. Third instance today of a constraint asserted from recall where the substrate was one file away. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JQKeKY9T9d95KpvHwwok8T |
||
|
David F GliddenandClaude Opus 5
|
5a350c7059 |
[FIX] The wake digest read an anchor case its producer was never told to emit
The digest read `PULLING THREAD` and `LITERAL QUESTION` with a case-sensitive `str.find`. /wrap-up names these fields in prose — "The pulling thread", "**Pulling thread:**" — and has never mandated a case. The reader was demanding a shape its own producer had no instruction to write, so the wrap wrote correctly and the digest reported DEGRADED. Censused by running the real function over all 195 wrap files rather than by grep: 102 threads and 103 questions unreadable, of which 86 and 84 were present in the body in the wrong case. The remaining 16 and 19 are wraps that never wrote the field. After the fix: 16 and 19. Predicted and achieved agree. Second defect, distinct and found only because the first was traced to its class: the label terminator was "first colon within 40 characters", a proxy for "same line". When an aside pushed the colon past the window the function returned THE LABEL, and with the paragraph cut assuming label and content share a paragraph, a question written below its heading was invisible. The 2026-08-22 wrap hit both defects at once. The terminator is now the first colon on the anchor's own line, and a label that ends its line takes the paragraph below. Case-insensitivity alone would have let a narrative "…as the pulling thread showed…" outrank the field it describes, so a match in label position now wins over an earlier mention. Four checks added (71 -> 75), including that negative control and a positive control proving it cannot pass vacuously. Not changed: file selection (ledgers were already excluded correctly, line 124), frontmatter stripping, and the verbatim-never-summarised contract. The ladder's "61 checks" is stale — it was 71 before this commit — and stays stale: the ladder is frozen under REVIEWED-123 and this is not an exemption. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JQKeKY9T9d95KpvHwwok8T |
||
|
David F GliddenandClaude Opus 5
|
d04c875054 |
[FIX] The deferral checker silently skipped the governance register (REVIEWED-123)
Executing REVIEWED-123 conditions 2 and 3 surfaced a defect in the instrument that was supposed to carry them. PENDING.md had grown to 546,944 bytes, past the scanner's 400 KB guard, so EVERY structured DEFERRED-DECISION block in the governance register was skipped — silently — by the checker built to stop deferred conditions from being silently missed. The 30-day review point placed under condition 2 was inert on arrival. Worse than silent. The prose-deferral loop has no size guard, so PENDING.md's prose count (70) still appeared in the report, making the file look examined while its structured blocks were never read. Found only by placing a block and noticing the tracked count did not move. Both halves fixed: - The two named governance files are exempt from the guard. The guard exists to bound the unbounded **/*.md globs; it was never meant for the files the scan reaches outside docs/ specifically to include. - A size-skip is now REPORTED, not swallowed: "NOT SCANNED for structured blocks", named, with byte counts, and stated as "could not assess" rather than "nothing there" — REVIEWED-104's third outcome, applied to the instrument whose entire subject is conditions nobody is watching. Two legitimate skips now visible (Carruthers 1.6 MB, Yates 1.0 MB — scholarly texts, correctly out of scope). Three controls added, derived from the PROPERTY rather than the guard's own vocabulary: is the register actually scanned; is a real block in it parsed (the live instance, not a fixture); and does the guard still apply to non-governance files, so the exemption cannot quietly become "scan everything". A control asking "does the guard work" would have passed throughout. Result: 32/32 controls (was 29/29); deferred decisions 3 tracked (was 2), all checkable. The ladder-freeze-30day-review trigger is live at date 2026-09-16. Also under REVIEWED-123: N-now recorded (60 transcripts of 84, 24 remaining); freeze scope stated as GENERAL per condition 1 and ladder file verified untouched; owed-entries list ratified with each row naming its authorizing ruling per condition 3 — OWED-1 under REVIEWED-122 cond. 9, OWED-2 explicitly NONE, queued but not authorized and needing its own ruling before it joins the ladder. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_013Y6t6qx7cpaCu5xGdD36u4 |
||
|
David F GliddenandClaude Opus 5
|
fb7bd6849f |
[FIX] REVIEWED-122 conditions 6, 7, 11 — and a fifth defect class found by the ruling's own placement (REVIEWED-122)
Executes the three legs REVIEWED-122 severed from the gated mechanism. COND. 6 (second requirement, which the earlier docstring commit did NOT discharge): checked what else relies on the discarded reading. Two sites. (1) The selftest asserts `ruled_pendings ignores a ruling that names no PENDING` using REVIEWED-82 as its fixture — a real AUTHORIZED ruling on PENDING-82, presented as an example of correct ignoring. The assertion is mechanically true and stays true; what is wrong is the fixture and what the name implies. Annotated, NOT repaired: the repair sits inside the gated mechanism. (2) governance-mcp.py asserts `governance_state item count == sec_pending()` — a count-based agreement check, the exact shape finding 9 names, which passes regardless of whether the classification is right. Reported, not changed. COND. 7: PENDING-121 restored to the open list by hand as PENDING-143, a disclosed CARRIER. Direct restoration was impossible without one of three acts the executor may not take — editing REVIEWED.md (Constraint #1, and cond. 5), inducing a Class-A header (trading hidden for unclosable), or changing the gated parser. The carrier is labelled as a proxy, not as the item. -124 and -128 deliberately not carried: cond. 7 preserves their UNDETERMINED status. COND. 11: filed separately as PENDING-144 rather than folded — script-resident substrate claims are checked by nothing, including the drift-check. One confirmed occupant; population explicitly unmeasured. AND A FIFTH DEFECT CLASS, found by watching this ruling land. A ruling claims a NUMBER, not a record. REVIEWED-122 named PENDING-142 and hid all four of its records at once — fine here, since its conditions do dispose of them, but the mechanism never checked that. Where it is not fine: REVIEWED-115 (2026-08-10) claimed `131`, so all five PENDING-131 records are hidden — including ADDENDUM 4, dated 2026-08-13 and therefore SUPPRESSED ON ARRIVAL, three days after the ruling that silenced it, while awaiting steward direction. PENDING-131 (c) is the unbuilt fence: the pulling thread of every session since 08-10, made a CONDITION by REVIEWED-121, and it has never once appeared in the list of items awaiting authorization. The work was not lost only because MEMORY.md and the session records were carrying it by hand. The same item fails the other way too: REVIEWED-116's header `PENDING-131/132/133/134` parses to one token matching no id, so a four-item design-gate ruling suppresses nothing. Filed as PENDING-145 — a new item, not a PENDING-142 addendum, because an addendum would have been hidden on arrival, which is the defect. None of PENDING-142's options (a)/(b)/(d) covers this: all three still resolve id -> ruled. Flagged as something the pre-registered answer key must encode BEFORE implementation, or the key will certify this behaviour as correct. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_013Y6t6qx7cpaCu5xGdD36u4 |
||
|
David F GliddenandClaude Opus 5
|
aa745bcfb0 |
[FIX] ruled_pendings' docstring asserted the opposite of the record
Jurist-ruled 2026-08-17 to correct independently of the mechanism, since it is a false claim whichever remedy wins. The docstring described REVIEWED-78/-81/-82 as "like-numbered rulings … concerning other matters" that had "falsely hidden" three items. Both halves are false. They are the AUTHORIZED rulings on PENDING-78/-81/-82 — same date, titles verbatim identical, and REVIEWED-81 names "PENDING-81" twice in its own body. They are like-numbered on purpose: REVIEWED-78's Notes say it was filed separately "for a mechanical reason: the closure rule in wake-digest.py matches a PENDING item to REVIEWED-<same number>." So the number→subject fix broke the three entries deliberately authored to satisfy the rule it replaced, then recorded their compliance as coincidence. Surfacing them was a regression; they have read open since 2026-07-28. The change proof could not see it because it measured a count (18→19) while the claim was each item's disposition — and the counts stay equal either way: removing 3 false-opens and restoring 3 false-closeds both leave 29. Superseded wording retained in the note rather than overwritten. Also filed as PENDING-142 ADDENDUM 3: the jurist ruling with its condition that (b)'s closing-verb enumeration must default to NOT CLOSED on unrecognized verbs; and the verified finding that governance-drift-check.py's subject is exactly one file (~/CLAUDE.md), so the scripts implementing governance checks make substrate claims nothing checks — one confirmed occupant, population unmeasured. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_013Y6t6qx7cpaCu5xGdD36u4 |
||
|
David F GliddenandClaude Opus 5
|
c2df868104 |
[FIX] Repair 39 files' frontmatter — including 3 I damaged an hour earlier
The 2026-06-06 normalization sweep ( |
||
|
David F GliddenandClaude Opus 5
|
b6e1b5e470 |
[FIX] The unwrapped-session detector compared two different clocks
The wake digest's `PREVIOUS SESSION DID NOT WRAP` alarm fired falsely at three consecutive wakes and was overridden by hand at two of them. It was scoped as a two-valued-detector problem. Diagnosing the class first found four defects, and the scoped one was not the cause: 1. TIME BASE (the cause). Transcript timestamps are UTC (`...Z`); the code dropped the suffix and called `time.mktime`, which reads a struct_time as LOCAL, then compared the result against `os.path.getmtime`, a true epoch. Measured: +7201 s skew against a 900 s tolerance. Because the skew exceeds the tolerance, a wrap written at the end of a session could NEVER land inside the window — the alarm was systematic, not intermittent. 2. SELECTION. "Newest transcript quiet for >60 s" excluded the previous session at exactly the moment it mattered: on 2026-08-17 it had ended 12 s before the wake, was skipped, and the session from four days earlier was reported instead. The defect is time-dependent and disappears ~60 s later, which is why re-running the digest afterwards showed nothing wrong. 3. EVIDENCE. Wrap records were dated by mtime, which any later edit moves — the 08-14 record read 08-17 because a CODA was appended to it. Now dated by git add-time, which cannot move once committed; mtime is a labelled fallback. 4. ARITY. `verdict is None` (could not assess) was folded into silence with "wrapped fine". Now four outcomes, per REVIEWED-104: wrapped · unwrapped · unassessable-subject (environment) · unassessable-check (defect). Acceptance is old-vs-new on the real case, not a unit pass. At the reconstructed wake instant the old code selects the wrong transcript AND returns a false alarm on the right one; the new code selects correctly and returns `wrapped`. Both defects independently produced the alarm, so fixing only the arity — the scoped task — would have shipped a fix that left it firing. The selftest gains a control derived from the property rather than from the check: a transcript's last inner timestamp and its file mtime are two readings of one moment, so their MEDIAN skew detects a systematic clock mismatch (1 s now, ~7200 s before). Max is printed too, because one transcript legitimately skews 31 h — the same mutable-mtime problem, on the transcript side. The old real-substrate gate demanded both verdicts occur across live sessions and PASSED while the detector was broken: it established that outcomes were spread, never that any was correct. Demoted to a printed note with its limit stated beside it. Filed as PENDING-142 ADDENDUM 1. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_013Y6t6qx7cpaCu5xGdD36u4 |
||
|
David F GliddenandClaude Opus 5
|
92d5ad2547 |
session 2026-08-13: REVIEWED-119/120 placed; MCP key descriptions refreshed
⚠ THIS COMMIT'S CONTENTS ARE MIXED, BY EXECUTOR ERROR, AND THE MESSAGE NOW SAYS SO RATHER THAN DESCRIBING ONLY ONE PART. The original message named only the governance-mcp.py change; `git add -A` had swept four other files. Amended before push, so no shared history is rewritten. What is actually here: 1. REVIEWED-119 and REVIEWED-120 (REVIEWED.md, +38) — STEWARD acts, placed during this session. 119 authorizes PENDING-135 option (c), instance 8 reclassified as a negative-candidate with the sub-type name held open, and corrects the item's own claim that option (d) was blocked cross-repo (the constraint is studium/v2-gold@1 §14.2, engine-side and D-1, not the chamber-locked studium/meta@1). 120 authorizes PENDING-136 option (c), retiring bare `distinct_spans`. 2. PENDING-135, PENDING-136 and the PENDING-131 Addendum 4 defect-count fix (PENDING.md, +212) — executor filings, and the ones that legitimately belong to a session wrap. 3. The session ledger (claude/memory/session-ledger-2026-08-13.md) — likewise. 4. governance-mcp.py (+24) — the [FIX] the original message described: two V0-lane key descriptions had gone stale the same day the dispositions landed. PENDING-134's H1 holds the doctrine ruling until those keys are actually SERVED (the running client keeps the old eight-key map until restart, which is steward action and still pending). The descriptions are what the jurist reads to decide which key to OPEN, so a stale index served at first contact would mislead on first contact — the class this whole arc is about. Selftest 54 checks, 0 failures. 5. Brewfile (+1, `mas "NordVPN"`) — NOT this session's work. It belongs to sysupdate's sweep and was swept in by the same error. Left in place rather than surgically removed: extracting it would rewrite more than it repairs, and the line is already accurate. Recorded so the next reader is not misled about which process authored it. The wrap protocol's §6.5 requires a scoped add for exactly this reason — the steward's in-progress changes belong to the steward's sweep, and a governance act placed by the steward must not be recorded under an executor's message. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01G38S6gU6G7akko9syvB7nu |
||
|
David F Glidden
|
4c3758e559 |
[PROPOSAL] PENDING-134 (whose-proposition as doctrine); 132 split+re-grounded; 133 rescoped; MCP opens the V0-lane texts
Jurist ruling accepted in full on all six questions. Q1: the variable is right, the derivation is not. §6.2 is PRE-REGISTERED, and a test that changes stratum-B membership, derived after reading the spans it reclassifies and entering by interpretation, voids that guarantee whether or not the test is right. Filed as PENDING-134 — new doctrine, dated, with §7.4(ii) as SUPPORTING ARGUMENT rather than derivation and §6.2's double omission recorded as the counter-argument heard and overruled. The decisive form of that objection is the jurist's: §6.2 admits F5 as 'qualified span (F5)', a construction that would have admitted 'reported-speech span (F4)' and was in use one item away. Q3: ran the fused-claim test on instance 8's fragments. It goes against retention — fragment 2 opens on the tail of the carpenter's speech with NO attributing clause before reaching Mauss's conclusion. The B4 shape. PENDING-132 amended: the retention is split out, and the retraction re-grounded on two convergent bases so it is authorizable regardless of how 134 resolves. 133: rescoped from two F4-carrying spans to every fr grounded span, because the bound assumed P7's tagging was complete and the item's own diagnosis says it had no claim-side step at all. And the access gap the ruling opened with: governance_read gains v2-harness-design, v2-stratum-tags, mauss-fixture-spans, mauss-fixture-citations — PENDING-86's fourth instance, same shape and same remedy as chamber-spec. The jurist can now verify Part I rather than take it as testimony. Eight controls including that the served text actually carries §6.2's pre-registration clause, §5's F4 row and the L926 citation strings. Self-test 54 checks, 0 failures. |
||
|
David F Glidden
|
32b0c9dfc6 |
[FIX] The link canary was blind to code spans, to wikilinks, and to its own class
The steward's 2026-08-09 to-do read "the gap is neither knowledge nor home but
the absence of an EXECUTABLE." The premise was false: classify_pointers has
existed since
|
||
|
David F GliddenandClaude Opus 5
|
90dc0f7373 |
[HARDENING] Close PENDING-82 and -118; mark 119/120/123 BUILT
82 is discharged by events. Its 2026-07-28 substrate check said there was no mcpServers key; today the config carries mcpServers: governance, and the jurist used the tools in three consecutive rulings — opening graduation-spec directly and refusing to rule from my summary, which is the capability the item existed to create. Two residuals carried, not buried: the read enum reaches neither the runbook nor the R0 contract, and the installed surface has 8 keys and a search tool the description does not name. 118 is built, and building it REFUTED the option I had recommended. I wrote that the checker already parses the archive format. It does not — the marker is an HTML comment and there are zero in either register file; their deferrals are prose, 53 and 26. Widening alone would have scanned two more files, found nothing and reported clean: a silent net built to close a blind spot, which is the failure the item was filed to describe. So the widening ships with its limit in its own output — prose deferrals counted and reported un-machine-readable, never as absent, with counting explicitly not classifying. The census stays owed. 119/120/123 marked BUILT with their commits so the built-vs-ruled checker sees them; all three were already ruled, so this closes a reporting gap, not an authorization one. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01A35wiD55yRHj5U1ECZAX4t |
||
|
David F GliddenandClaude Opus 5
|
bfd0f45293 |
[HARDENING] drift-check gains built-vs-ruled (REVIEWED-108 family)
Earned 2026-08-08: PENDING-125, -126 and -127 were authorized verbally in the D-1 lane, built, pushed, and recorded BUILT in their own amendments while no REVIEWED entry named any of them. Nothing was crossed — D-1 is steward-direct and the authorizations were real — but the register did not show them, the commits could not carry the REVIEWED-N tag the commit format prescribes because no number existed, and the gap surfaced only because the steward asked. It was not reconstructible from memory; it had to be enumerated mechanically. Same family as the amendment-link and deferred-decision checks: the registers own instruments not reaching parts of the register. This one watches the seam between the work happening and the record showing why it was allowed to. Three-valued per REVIEWED-106, ruled hours earlier: it reads two files, either of which can be absent, so cannot-assess is reported distinctly and never as clean. The BUILT vocabulary is stated with the result — caps only, because lower-case prose "built" would flag every item that describes building. Six controls including a REAL known-bad rather than only fixtures: the register at git HEAD, before the steward placed 107-109, names 125/126/127; the working register names none. It discriminates on real artifacts. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01A35wiD55yRHj5U1ECZAX4t |
||
|
David F GliddenandClaude Opus 5
|
1cf79b0f86 |
[PROPOSAL] PENDING-124 gate passed; five conditions discharged, and the gate found a tenth instance
Q1 is applied, not extended: Constraint 4 has two clauses and my contrary reading engaged only the second. Limits, not failures — and "I could not look" is a limit. I had overstated my own uncertainty on the question I withdrew a recommendation over. The condition that cost most: my quote-verification pass reported verified on a reconstruction of REVIEWED-104 — contractions, re-punctuation, two blocks spliced, and the closing sentence dropped. A two-valued verifier inside a package arguing verifiers must be three-valued. Rebuilt at ~/dotfiles/scripts/verify-quotes.py. The first rebuild had three tiers and cried wolf on every correctly-copied quote, since a record stored with hard wraps is byte-different from the same text quoted as one line; splitting re-wrapped from normalized is the same two-strengths lesson the fleet learned. Both directions proven: corrected package exit 0, original reconstruction not-found exit 1. The dropped sentence answered my own Q2. It was in the record the package quoted. Both citation errors in that package had one cause, which the script cannot diagnose: I quoted the ADVISORY message and attributed it to the PLACED record. Different documents; placement adds and cuts, so quoting the advisory loses exactly what placement contributed. My "five instances, same shape" was wrong — two are the shape, three belong to the attested-absence family whose parent is already ratified (REVIEWED-47, 2026-07-05). I searched for a doctrinal parent among R0 and Constraint 4 and missed the ratified sibling closest in content. The ladder entry now joins that lineage. Filed as a watch-item, with an operative memory note: third package running where the grounding pass was incomplete and every substantive omission cut against my own argument. It optimises for finding my errors, not my support. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01A35wiD55yRHj5U1ECZAX4t |
||
|
David F GliddenandClaude Opus 5
|
33c11fff87 |
session 2026-08-07 evening: PENDING-112 + REVIEWED-95 (route harvested capabilities by firing moment)
Register censused and rebuilt from the archive: 177 claimed -> 154 real live proposals, legible, with exact archive:L### pointers. The 2026-08-01 compaction was lossless but illegible (55 scraped header rows; 95% of cells cut mid-word); completeness verified 124 = 124, so nothing had been dropped. Skills pruned 63 -> 12 after measuring that 53 had never been invoked across 64 sessions / ~5 months. The finding underneath: retrieval is set by a capability's HOME, not its importance -- MEMORY.md 83%, register 77% (named in a wake step), ladder 14%, 'THE GOVERNING FRAME' 12%, 'Read at Step 0' 9%, recall-bound skills 0%. PENDING-112 filed, jurist design-gated, steward concurred; REVIEWED-95 drafted. Landed: the /wrap-up 1.6 filing gate (prospective) and the /wake-up ladder sentence (a pre-registered trial intervention, landed alone). The 20-session falsifier is WIRED, not intended -- DEFERRED-DECISION ladder-ritual-trial, trigger: transcripts 84. Wiring it exposed two defects in the deferral checker: no way to express a session count except as a date proxy, and a scan that never looked at claude/governance/. Controls 16 -> 19. Stroke 2's 41-entry ladder append deliberately NOT done: REVIEWED-95 Q3 sequences it after the ladder trigger, which now exists. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01NEWjLBP4quXbDPDL2byEzZ |
||
|
David F GliddenandClaude Opus 5
|
97ae59a0d3 |
[FIX] deferred decisions: check the trigger instead of remembering it
The 2026-05-16 jurist settlement deferred TEI-native authoring "until
Cluster A's MD-with-sidecar form is operational". Cluster A became
operational, the condition was met, and nobody looked — it surfaced months
later by accident, while reading an unrelated document for another purpose.
The steward's stated reason for settling it today was not the format question
at all: "I abhor deferring so many things and then forgetting them."
A deferral is a claim — "not yet". When its trigger fires the substrate
contradicts that claim, which is exactly what this instrument detects, so
check 8 belongs here rather than in a new register. A deferred decision now
declares a machine-checkable trigger in a comment block:
<!-- DEFERRED-DECISION: <slug>
since: YYYY-MM-DD
owner: steward | jurist | executor
trigger: glob <pat> | path-exists <p> | date <YYYY-MM-DD> | manual
discriminator: <where the deciding evidence is written down> -->
`manual` never auto-fires and is listed rather than checked — an honest way
to record a deferral whose condition cannot be mechanised, instead of
inventing a proxy. Proxies are the failure being fixed: the old trigger stood
in for "behavioural evidence on high-fidelity sources" and came true without
producing any, because neither named test case was ever manifested.
Scans */docs/**/*.md under ~/_Dev and ~/dotfiles; glob and path-exists
resolve against the containing repo's root. First and only entry today is
D-5 (tei-native), correctly reported as not due — no protocol spec exists yet.
Controls, five, per the standing epistemic standard. The load-bearing one is
the discriminating half: the evaluator must NOT fire on an unmet condition,
because a checker that fires on everything reports nothing. Red-witnessed
end-to-end by temporarily pointing D-5's trigger at a path that does exist:
reported COME DUE with slug, owner, deferral date, trigger and file; restored
after, and the spec's working tree verified clean.
Also fixed in passing: this file's own report block was briefly duplicated
and misplaced by a `str.replace` without a count, which substituted both
`sys.exit(0)` occurrences including the early-exit branch. Caught by reading
the output — the deferred-decisions line printed twice.
Wake-up §2.c updated to describe all three of the script's reports, and to
require that a COME DUE item be surfaced in the briefing under "What's
unresolved". That is a change to the wake protocol, not only to a
description: a mechanism nobody reads is not a mechanism.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NEWjLBP4quXbDPDL2byEzZ
|
||
|
David F GliddenandClaude Opus 5
|
bcc02ada3d |
[FIX] register integrity: an amendment must never replace the record it amends
REVIEWED-87's original entry (PENDING-99, the fidelity_equivalence@3 design-gate ruling of 2026-08-05) was replaced this afternoon by the PENDING-111 amendment block placed at the same heading. The amendment's own "**Amends:** REVIEWED-87" line then pointed at a record no longer in the file, and the register could no longer answer what was ruled under 87 — the register's whole job. Recoverable, and recovered: the entry was intact in git HEAD and the underlying jurist ruling is separately filed at studium-engine/docs/quoted-tier-acceptance-JURIST-RULING-2026-08-05.md. But the register entry uniquely held Q2's reframing (the route to PENDING-100), Q3 REJECTED and its strengthened basis, Q5 CONCUR D-1, and the finding that "the decisive sentence was one the executor had read and not surfaced, which a verbatim-containment check passes every time." CAUSE, and it is the executor's. The handoff draft was headed "## REVIEWED-87 — AMENDMENT 2026-08-07" and described as "the block to place", with no instruction that it join rather than replace. That reads as a replacement heading, and the steward's reading of it was reasonable. The copy-paste-clean discipline exists so a placement cannot be ambiguous, and this draft was ambiguous. NOTHING DETECTED IT. It surfaced because a diff was read by hand and the tell was a deletion count on what should have been a pure append. This is `removing-a-claim-is-not-removing-the-reliance` at the governance layer: the amendment's dependency on the original survived the original's removal and became invisible. Check 7 added to governance-drift-check.py, which already runs at every wake: every `## REVIEWED-N — AMENDMENT` requires an un-amended `## REVIEWED-N` entry, and every `**Amends:** REVIEWED-N` must resolve. Reported separately from the CLAUDE.md findings so that report's own claim stays true. Controls per the standing epistemic standard, and the third is the lesson of the day — a check that has never fired on a known-bad input is unestablished, so the instrument is run against a synthetic reproduction of the actual failure. Red-witnessed on a copy of the live file with the deletion replayed: fires both findings. 11/11 controls pass. Detection only. REVIEWED.md is [ESCALATE], the steward's hand (Constitutional Constraint #1); the restoration above was placed by the steward, not by the executor. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01NEWjLBP4quXbDPDL2byEzZ |
||
|
David F GliddenandClaude Opus 5
|
4785d02b7d |
scripts: track drain-hook-queue.mjs (written 2026-08-05, never committed)
The hook-queue drainer built during the BMF investigation. Its never-delete-on-failure rule and 10-failure halt are what surfaced the entity-pipeline finding; it was left untracked in the working tree. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AB3Kryoy6b1pm2Nz1DYdLh |
||
|
David F GliddenandClaude Opus 5
|
673823961c |
[HARDENING] governance-mcp: keyword search — the jurist can discover an item whose id it does not know (PENDING-86 d)
Steward-authorized 2026-08-05, completing the (a)+(d) pair the jurist asked for.
The failure this closes is NOT "cannot read item X" — (a) fixed that. It is
"cannot DISCOVER item X whose id it does not already know": the 2026-07-29 case
where a ruling demanded an outcome REVIEWED-74 had settled four days earlier, in
a file the jurist could read but had no reason to open. Keyed retrieval cannot
serve that; only search can.
`governance_search(query, limit)` over PENDING / PENDING-archive / REVIEWED.
Result unit is the ITEM, boundaries from wd.item_spans — no second definition of
"an item" (the 2026-07-28 bug that hid twenty). Results name ids to hand to
governance_item, so the two tools compose.
Three deliberate properties:
- Terms are ANDed, and that is DISCLOSED on every result. A silently
conjunctive matcher is exactly how recall dies as a question lengthens —
found in the engine yesterday (PENDING-97, "what does levi mean by the gray
zone" -> 0 over ten real matches). The same shape is not being rebuilt here
unannounced.
- A miss is a legible empty: it states the corpus, the item count scanned, the
terms, and the match mode, and says outright that a longer query narrows
fast. Silence discloses its own blindness (PENDING-96's discipline, applied
to a new instrument on the day it was ruled).
- Ranked by exact-phrase then raw term-count, labelled as a term COUNT and not
a relevance score — it is a field this code actually computes.
Plus a query-INDEPENDENT structural pass: an item header hidden by leading
whitespace is invisible to item_spans, so it can never appear in results and its
absence reads as a genuine miss. Such headers are now reported beside the
results. An earlier draft flagged any uncovered matching line and drowned the
signal in each file's preamble — which is how a warning stops being read.
That pass earned itself immediately: REVIEWED-11, REVIEWED-12 and REVIEWED-74
were all indented and therefore unreachable by governance_item. REVIEWED-74 is
precisely the ruling the jurist could not find, so its failure was
over-determined — it did not know the id, AND the id would not have worked.
Steward unindented all three (REVIEWED.md is his file, not the executor's, per
Constitutional Constraint 1); items visible 78 -> 81, hidden headers now zero.
Selftest 35 -> 44 controls, 0 fail, including a negative control that goes red
if a header is ever hidden again. Live stdio round-trip confirms six tools and a
correct search result.
⚠ Requires a Claude.app restart to expose the new tool.
Refs PENDING-86 (d), PENDING-82, PENDING-96, PENDING-97.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AB3Kryoy6b1pm2Nz1DYdLh
|
||
|
David F GliddenandClaude Opus 5
|
5cd5faf66e |
[HARDENING] governance-mcp: the jurist can now read the constitution it design-gates (PENDING-86 a)
Steward-authorized 2026-08-05, on the jurist's own request while unable to close
PENDING-99's Q2 — a question that turns on the chamber constitution's vocabulary
(§II.3's "inline anchor marker", §V's marker exclusion), which governance_read
did not expose. Third recorded instance on PENDING-86: the constitution, the
skill files, contamination-problem.md.
Adds two keys to the existing enum: `chamber-spec`, `graduation-spec`. No new
tool, no path argument, no traversal surface — the domain stays enumerable and
every refusal control still passes.
⚠ THE NON-OBVIOUS PART. Reachability of the KEY is not reachability of the
CLAUSE. This file's operative sections begin around line 354; the ~330 lines
above them are SUPERSEDED version headers kept as the amendment trail. A jurist
reading with the default limit=400 would land squarely in obsoleted text and
could rule on superseded clauses — the new access CAUSING the misruling it
exists to prevent. So the trap is disclosed on the key's own description, at the
point of use, and two controls pin it:
- the §V inline-anchor clause and the §II.3 marker constraint are both
reachable in ONE paged call (offset=350, limit=2000) — the actual Q2 text
- NEGATIVE CONTROL: a first-page read does land in the "(obsoleted)" region,
proving the trap is real rather than hypothetical
Selftest 29 → 35 controls, 0 fail. Live stdio round-trip confirms the §V clause
arrives verbatim through governance_read.
⚠ Requires a Claude.app restart: the running server process carries the old
code and will not show the new keys until respawned.
Option (d) — keyword search across PENDING/PENDING-archive/REVIEWED — is NOT in
this change and remains open on PENDING-86. It is a new tool surface, not two
enum entries, and the jurist asked for (a)+(d) together.
Refs PENDING-86, PENDING-99 Q2, PENDING-82.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AB3Kryoy6b1pm2Nz1DYdLh
|
||
|
David F GliddenandClaude Opus 5
|
9c2a7c985c |
session 2026-08-04: PENDING-92/93/94 + the replay-never-resumed finding + l1-replay-sampler
Filed PENDING-92 [HARDENING] idle ladder (cool/deep unreachable, spec §9A.1 divergence), PENDING-93 [PROPOSAL] event_seqs normalisation, PENDING-94 [ESCALATE] the resume floor — minCursor pinned at 0 by two non-participating modules, so 13/13 restarts rebuilt from seq 0 and the catch-up branch has never executed. Recall never worked either (retrieval_count = 0 across the whole April-June graph); same fact from the other end. Adds scripts/l1-replay-sampler.py (external read-only sampler, four positive controls, refuses to run blind). Note to Seb pushed separately as CapableMind-AI@ad285df. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01WuMjg3ipEVa3n8CoSzoyvc |