feat(lens): paradox-voice rulebook baked into the PMU runner — SQLite substrate + prose-lane core banks

Operator 2026-07-04: "look for the paradox voice rules and make them into
the SQLite and bake them into the PMU runner." Two legs, both landed:

SUBSTRATE — seedRules() gains a dedicated extractor for
docs/voice/paradox-voice-rulebook.md: its 13 numbered hard rules are
exactly the line-shape the CLAUDE.md noise filter drops BY DESIGN (the
glossary-slurp incident tightened it; not loosened here). Each rule is
joined across wrapped lines, compressed to one line, tagged src='voice',
and placed on the lattice by the same compression sensor — the sensor's
own placements are sane (reader-as-hero / no-technique-leak / density
landed on B3, the voice room's coordinate). 144 rules seeded, 13 voice.

RUNNER — the three prose lanes' core banks (data/pmu/lens-reef.json:
book +6, blog-content +6, comms-email +5) carry the load-bearing voice
rules; the per-prompt relevance sort makes densified banks safe. Proven
live: a book-editing prompt now injects "voice: reader-as-hero" as its
TOP rule (matched on voice/reader/land), with no-technique-leak and
show-the-loss-with-the-win riding alongside the build-book rules.

Guard (same commit): tests/lens/voice-rules-baked.test.js — extractor
still yields ≥10 named hard rules from the rulebook; seeder lands ≥10
src='voice' rows in an isolated LENS_DB; all three prose lanes keep ≥4
voice rules in their banks. 3/3 green.

Originating-Terminal: 🎤 Terminal Voice
Relevant-Rooms: 🎤 voice, 🧪 laboratory, 📐 architect
Story: The rulebook graded tonight's book kernel by hand minutes before this landed; now the same rules ride the directive lens automatically on every book, blog, and comms prompt — the grading reference became part of the instrument it grades for, one step toward the qwen-rulecheck substrate spec.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VRmFxPtHxYBiXRjiqRT54T

commit d589e44f6 — 144×144 lattice triptych (on-chip)

◎ the ingest chose C2,B — Operations·Loop × Tactics — acting on A1,A2 — Strategy·Law × Strategy·Goal (grip 0.781) · the walk starts at the ACTOR's row · 3 file(s)

⏱ ingest 361.9ms (corpus→lattice) · definer walk 618ms (row→transpose→row, ballistic XOR per hop) · total 1273ms
ingest here = commit-scoped SENSING only (this commit's message + changed files → lit anchors) — deep seed authoring lives in the reef-self-loop, off the commit path

rows = ACTOR (lens) · cols = PATIENT (object) · diagonal = self-reference; ◎ at actor-row × patient-col — every panel, same orientation. Heat above the diagonal = actors ranking ShortLex-earlier than their patients (the walk follows definers uphill in rank).
The 12 canonical lanes (rows top→bottom, cols left→right): A·Strategy · B·Tactics · C·Operations · A1·Law · A2·Goal · A3·Fund · B1·Speed · B2·Deal · B3·Signal · C1·Grid · C2·Loop · C3·Flow

PAIR LATTICE (the map we normally see)

PRE-WALK SENSE · INTENT grid — the snapshot, no point of view

the no-point-of-view snapshot — what the sensor lit before any walk; the leaf walk below is what bridges the two grids

	ABC A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N A1–C3
ABC A1–C3 A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N

PRE-WALK SENSE · REALITY grid — the snapshot, no point of view

the no-point-of-view snapshot, reality side — same sensor law

	ABC A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N A1–C3
ABC A1–C3 A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N

PRE-WALK Δ · straight comparison of the two ingested grids (green both · cyan intent-only · amber reality-only) · 5% overlap · ◎ = where the competence pixel sits in the raw overlap

good = green overlap without being a copy — near-100% is self-similarity, not alignment

	ABC A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N A1–C3
ABC A1–C3 A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N

◎ the pixel this commit belongs to

C2,B — Operations·Loop × Tactics (actor) acting on A1,A2 — Strategy·Law × Strategy·Goal (patient) · grip 0.781

actor seed C2,B — Feedback loops and hypothesis test cycles inform which tactics or leverage maneuvers are effective at each beat. Each iteration is a hypothesis tested against the ground truth of the world. Loops shorter than the feedback half-life waste the half-life; loops longer than it pay compounding interest on the wait. Cycles compound when each turn's exhaust feeds the next turn's intake. Closed loops compound; open loops decay. The closing of the loop IS the productivity, not the running of it. Iteration discipline: one commit per iteration, never bundled. Bundled iterations destroy the bisect, and the bisect is the future agent's only tool for finding which round of feedback produced which artifact. Tactics is the choice of which leverage to pull at which beat. Not what we want, but how the want lands on Tuesday: the sequence of irreversible commitments, each made before the next one's information is available. Speed of feedback dominates speed of execution. Tactics that converge fast beat tactics that compute long, because the loop closes around the world's response before the world has moved. The tactical map is a ranked list of moves where each move carries a cost-of-delay. Pick the move whose cost of doing it tomorrow exceeds the cost of doing it imperfectly today. Execution is a sequence of bets made under uncertainty. Tactics is the discipline of betting the right size on the bet whose information value pays for the loss-if-wrong.

patient seed A1,A2 — Legal binding mandates and governance rules dictate how a quarterly goal position is occupied and secured. EU AI Act Article 14 requires human-on-the-loop oversight, with the supervisor able to interrupt the system at any moment. Compliance attaches to the artifact the artifact cannot escape — provenance is a regulatory primitive, not a feature. The target is the cell coordinate the system MUST occupy by end-of-quarter. Anything that does not drive toward that coordinate is exhaust, and exhaust does not become substrate by being labelled progress. Constraints precede objectives. The cap-table, the license text, the consent envelope — each draws the inviolate line the action must respect, and the line is enforced before the optimization runs. Vision is the coordinate the lattice rotates around — the fixed bearing every iteration is measured against. Without the fixed point, motion is movement; with the fixed point, motion is convergence. A rule names what the system MAY NOT do. If the agent can do X, then 'forbid X' is not the constraint — it is wishful thinking dressed as policy. Constraints live in the gate, not in the prompt. Define the goal as a verifiable predicate, not a feeling. The system terminates when the predicate evaluates true, and the predicate is what the next agent inherits when this one hands off. Regulation is not advisory. The fine is the price tag stapled to the omitted control; insurance is the option pricing on the failure-mode the regulation already named. A goal that cannot be tested is a wish. Wishes have no termination condition, so they consume budget forever; goals have a finish line and therefore a payable price.

INTENT · leaf-walk clouds · BLUE→VIOLET by ply (◎ = the competence pixel: actor∩patient)

good = the clouds concentrate where the commit SAYS it works

	ABC A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N A1–C3
ABC A1–C3 A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N

REALITY · leaf-walk clouds · ORANGE→RED by ply (◎ = the same pixel — the shared perspective)

good = the same clouds as intent — shipped where declared

	ABC A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N A1–C3
ABC A1–C3 A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N

DELTA · graded cloud divergence (green agree · magenta declared-not-done · amber done-not-declared) · 4% agree

good = mostly green; magenta = said-not-done (chase it in the code), amber = done-not-said (chase it in the docs)

	ABC A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N A1–C3
ABC A1–C3 A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N

TOLERANCE · cloud topology (dim green in-shape · hot amber bleed · red orthogonal concentration)

red only matters above the flip — a few amber is normal bleed

	ABC A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N A1–C3
ABC A1–C3 A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N

SHORTLEX-3 PROJECTION (ABC · A1..C3 · the 132 children — candidate, pre-ratchet)

PROJECTED INTENT · the commit’s claims, head→axis_i tail→axis_j (cyan)

the three-length view — good = claims land inside their own zone

	ABC A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N A1–C3
ABC A1–C3 A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N

PROJECTED REALITY · same projection law (amber)

same projection law — good = reality occupies the zones intent does

	ABC A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N A1–C3
ABC A1–C3 A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N

STRAIGHT COMPARISON · green both · cyan intent-only · amber reality-only · 3% overlap

good = the zones agree; cross-zone scatter is the drift to read

	ABC A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N A1–C3
ABC A1–C3 A1A–O A2A–O A3A–O B1A–O B2A–O B3A–O C1A–N C2A–N C3A–N

shortlex-3 zone occupancy (lit cells per diagonal square)
INTENT: 0 in the 3×3 ABC corner · 7 in the 9×9 A1..C3 square · 1552 in the 132×132 children square · 303 cross-zone
REALITY: 0 in the 3×3 ABC corner · 3 in the 9×9 A1..C3 square · 946 in the 132×132 children square · 125 cross-zone
axes: identical 144 ShortLex names both sides (symmetric); weights asymmetric
zone 3 = candidate children, pre-ratchet (repo-derived dumps not yet past the perturbation-probe gate) · intent 45 claims @ θ 0.625 · reality 29 claims @ θ 0.625 · projection 664ms

SHAPE-MATCH σ = 1.69 — the real intent↔reality definer walk vs random-reality (actual 0.1315 vs random 0.073). >0 = the walk distinguishes real alignment from noise; aggregate over independent walks → the divergent series.
σ_drift · weak · panel story is not yet evidence

Most out-of-lane row: B1 · Speed — that lane is drifting most (read the red band in that row).

Three-colour tolerance (out-of-lane = reality fires where intent is weak, in orthogonal blocks): green=in-lane agreement · amber=a few out-of-lane (tolerated) · red=armed — orthogonal out-of-lane 3% vs tolerance 25%.
834 green · 853 amber · 0 red · 123 XOR-friction cells.

Both axes = the 144 ShortLex anchors, cell=row⊕col, on the chip. INTENT=docs+rules · REALITY=code · DELTA=friction.

tile dump — what the SimHash matched on the diagonal (inspect the sensor; tap to expand)

A,A The lattice we build today is what next year's underwriter inherits.

intent 67% (no distinctive match)

reality 78% (no distinctive match)

B,B Tactics is the choice of which leverage to pull at which beat.

intent 67% (no distinctive match)

reality 72% (no distinctive match)

C,C Operations is the loop that runs whether anyone watches.

intent 78% (no distinctive match)

reality 86% (no distinctive match)

A1,A1 EU AI Act Article 14 requires human-on-the-loop oversight, with the supervisor able to interrupt the system at

intent 81% (no distinctive match)

reality 80% (no distinctive match)

A2,A2 The target is the cell coordinate the system MUST occupy by end-of-quarter.

intent 75% (no distinctive match)

reality 83% (no distinctive match)

A3,A3 Every dollar builds either the floor (substrate that lifts future bets) or the ceiling (cap on the next round)

intent 67% (no distinctive match)

reality 72% (no distinctive match)

B1,B1 Latency is the price of a missed beat.

intent 75% Operator 2026-07-04: "look for the paradox voice rules and make them into the SQLite and bake t

reality 73% (no distinctive match)

B2,B2 The deal sets the exchange rate between two value substrates.

intent 70% (no distinctive match)

reality 75% (no distinctive match)

B3,B3 Signal-to-noise is the inverse cube of bandwidth — narrow the channel, the message arrives; broaden it, recipi

intent 73% (no distinctive match)

reality 75% // wrapped lines, compressed to one rule-line, tagged src='voice', and placed on the lattice by

C1,C1 Power flows where the grid lets it.

intent 73% (no distinctive match)

reality 75% (no distinctive match)

C2,C2 Each iteration is a hypothesis tested against the ground truth of the world.

intent 69% (no distinctive match)

reality 72% (no distinctive match)

C3,C3 Flow is the rate at which committed work crosses the finish line.

intent 77% feat(lens): paradox-voice rulebook baked into the PMU runner — SQLite substrate + prose-lane co

reality 78% (no distinctive match)

commit context — 3 file(s)

feat(lens): paradox-voice rulebook baked into the PMU runner — SQLite substrate + prose-lane core banks

Operator 2026-07-04: "look for the paradox voice rules and make them into
the SQLite and bake them into the PMU runner." Two legs, both landed:

SUBSTRATE — seedRules() gains a dedicated extractor for
docs/voice/paradox-voice-rulebook.md: its 13 numbered hard rules are
exactly the line-shape the CLAUDE.md noise filter drops BY DESIGN (the
glossary-slurp incident tightened it; not loosened here). Each rule is
joined across wrapped lines, compressed to one line, tagged src='voice',
and placed on the lattice by the same compression sensor — the sensor's
own placements are sane (reader-as-hero / no-technique-leak / density
landed on B3, the voice room's coordinate). 144 rules seeded, 13 voice.

RUNNER — the three prose lanes' core banks (data/pmu/lens-reef.json:
book +6, blog-content +6, comms-email +5) carry the load-bearing voice
rules; the per-prompt relevance sort makes densified banks safe. Proven
live: a book-editing prompt now injects "voice: reader-as-hero" as its
TOP rule (matched on voice/reader/land), with no-technique-leak and
show-the-loss-with-the-win riding alongside 

data/pmu/lens-reef.json
scripts/pmu/prompt-lens.mjs
tests/lens/voice-rules-baked.test.js

Produced on the chip by the running pipeline (scripts/pmu/pipeline.mjs → runPipeline → walk + xor), commit-scoped · on-chip per-walk 1450.89ns (this commit). Recompute: node scripts/pmu/commit-triptych.mjs --commit d589e44f6

Commit artifacts (open on a computer — Gmail mobile won't follow file:// links; the inline images above are the phone-viewable form): reef grid · this triptych · the HDL — all three are also attached to this email.