spec(pmu): the full pipeline spec + harness + one-pipeline guard — close the empty-panel loop

Operator: 'set up a full harness ... one rust pipeline, we always use it, it never comes up empty, and we
never mix in the LLM call on the same call. We can't be selling risk and have empty panels.' Delivered:

(1) THE SPEC — docs/architecture/pmu-pipeline-full-spec.md: the one Rust core (pmu-onchip), the 9-stage
runPipeline (resolve→invariants→sense→sigma→binarize→project→xor→walk→claudbridge), the FORK diagnosis
(11 shared-module callers vs 42 DIRECT binary callers — that fragmentation is why panels go empty), the 3
invariants (one-pipeline · never-empty · never-LLM-mixed), the empty-panel root cause + close, and the
maintainable enforcement (ONE functional entry + an ENUMERATION guard that freezes the fork ceiling).
Emailed (id 12e5c74a).

(2) THE HARNESS — scripts/pmu/pipeline-harness.mjs: drives the REAL receipt path (dogfood), walks every
stage, and PROVES all 3 invariants — substantial commit non-empty (367g/243a/300r, 910 cloud cells, no
walk-collapse), thin commit honest direction-only, dead-ollama identical (no LLM in the decidable path),
deterministic twice. Reports the fork backlog (43). Exits non-zero on breach → callable from CI/tick/hand.

(3) THE GUARD — tests/pmu-simulator/one-pipeline.test.mjs: freezes the direct-caller ceiling at 43; a NEW
bypass turns the build red, so the fork can only shrink. Migrate commit-triptych to runPipeline first.

Originating-Terminal: 🔨 iTerm Builder
Relevant-Rooms: 🔨 builder, 🧪 laboratory, 📐 architect
Story: The empty panel is a forked pipeline; the fix is one entry, a harness that proves it never empties, and a guard that stops the fork from growing.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013BUf5M5p42Zw73VaGt33ZL

commit e15fc7fa3 — 144×144 lattice triptych (on-chip)

◎ the ingest chose A1,A3 — Strategy·Law × Strategy·Fund — acting on B3,B — Tactics·Signal × Tactics (grip 0.797) · the walk starts at the ACTOR's row · 3 file(s)

⏱ ingest 525.9ms (corpus→lattice) · definer walk 2630ms (row→transpose→row, ballistic XOR per hop) · total 3323ms
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) · 12% 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

A1,A3 — Strategy·Law × Strategy·Fund (actor) acting on B3,B — Tactics·Signal × Tactics (patient) · grip 0.797

actor seed A1,A3 — Compliance articles provide the binding mandate that oversees how capital and the dollar floor fund finance. 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. 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. 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. 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. Every dollar builds either the floor (substrate that lifts future bets) or the ceiling (cap on the next round). Allocation is which one this dollar chooses, and the choice is irreversible by the time the wire clears. Burn rate divides into substrate-building and exhaust. Substrate compounds; exhaust evaporates by quarter-end. The investor who pays for substrate is buying a different asset than the investor who pays for exhaust. Capital allocation is the irreversible vote — the bet that closes options to keep the others open. Each dollar deployed buys both the asset and the foreclosure of every alternative the dollar could have funded. The funding question is the runway question. Eighteen months at one burn rate is a different company than twelve months at a higher burn rate, even when the bank balance matches.

patient seed B3,B — Reach of a signal and the message bandwidth provide the channel for tactical maneuver choices. Signal-to-noise is the inverse cube of bandwidth — narrow the channel, the message arrives; broaden it, recipients tune out. The right channel is the one whose floor matches the message's importance. A broadcast that addresses everyone addresses no one. Precision over reach until the address is calibrated; only then does scale convert prospects into recipients rather than into unsubscribes. Repetition is the cost of being heard. Three sends to one recipient beats one send to three; the first send announces, the second send is heard, the third send is remembered. Every message carries provenance. The sender's history is half the message's weight; an unknown sender pays in attention what a known sender pays in seconds saved. 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.

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) · 9% 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 · 6% 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 · 9 in the 9×9 A1..C3 square · 1323 in the 132×132 children square · 316 cross-zone
REALITY: 2 in the 3×3 ABC corner · 4 in the 9×9 A1..C3 square · 1644 in the 132×132 children square · 241 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 112 claims @ θ 0.6406 · reality 17 claims @ θ 0.6094 · projection 1262ms

SHAPE-MATCH σ = 7.29 — the real intent↔reality definer walk vs random-reality (actual 0.2578 vs random 0.095). >0 = the walk distinguishes real alignment from noise; aggregate over independent walks → the divergent series.
σ_drift · trustworthy · clears the trust floor — the panel story counts as evidence

Most out-of-lane row: C3 · Flow — 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 24% vs tolerance 25%.
793 green · 721 amber · 0 red · 125 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 73% **`runPartial(from, opts)`** re-runs from a stage using cached vectors — the "tweak a param, wa

reality 67% const THIN = arg('--thin') || (git(['log', '-60', '--format=%h', '--', 'docs']).split('\n').fin

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

intent 70% | Subcommand | Purpose |

reality 64% // order to make sure it's lined up properly ... one rust pipeline, we always use it, it never

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

intent 78% (no distinctive match)

reality 73% !/usr/bin/env node. scripts/pmu/pipeline-harness.mjs — PROVE the one Rust pipeline: every stage

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

intent 78% (no distinctive match)

reality 73% check('determinism: same commit renders identical tolerance', twice.tol.join('/') === sub.tol.j

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

intent 77% (1) THE SPEC — docs/architecture/pmu-pipeline-full-spec.md: the one Rust core (pmu-onchip), the

reality 73% (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 70% (no distinctive match)

reality 66% const deadRun = render(SUBSTANTIAL, { deadOllama: true });

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

intent 72% (no distinctive match)

reality 70% (no distinctive match)

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

intent 73% (no distinctive match)

reality 69% `${sub.tol.join('g/')}r == ${twice.tol.join('g/')}r`);

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

intent 78% Guard: THE ONE-PIPELINE INVARIANT (operator 2026-07-06: "one rust pipeline, we always use it").

reality 72% if (/pmu-onchip/.test(src) && f !== 'pipeline.mjs') direct.push(f);

C1,C1 Power flows where the grid lets it.

intent 75% (no distinctive match)

reality 67% function render(sha, { deadOllama = false } = {}) {

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

intent 72% (no distinctive match)

reality 69% (no distinctive match)

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

intent 80% - **11** scripts import the shared `runPipeline` module.

reality 69% (no distinctive match)

commit context — 3 file(s)

spec(pmu): the full pipeline spec + harness + one-pipeline guard — close the empty-panel loop

Operator: 'set up a full harness ... one rust pipeline, we always use it, it never comes up empty, and we
never mix in the LLM call on the same call. We can't be selling risk and have empty panels.' Delivered:

(1) THE SPEC — docs/architecture/pmu-pipeline-full-spec.md: the one Rust core (pmu-onchip), the 9-stage
runPipeline (resolve→invariants→sense→sigma→binarize→project→xor→walk→claudbridge), the FORK diagnosis
(11 shared-module callers vs 42 DIRECT binary callers — that fragmentation is why panels go empty), the 3
invariants (one-pipeline · never-empty · never-LLM-mixed), the empty-panel root cause + close, and the
maintainable enforcement (ONE functional entry + an ENUMERATION guard that freezes the fork ceiling).
Emailed (id 12e5c74a).

(2) THE HARNESS — scripts/pmu/pipeline-harness.mjs: drives the REAL receipt path (dogfood), walks every
stage, and PROVES all 3 invariants — substantial commit non-empty (367g/243a/300r, 910 cloud cells, no
walk-collapse), thin commit honest direction-only, dead-ollama identical (no LLM in the decidable path),
deterministic twice. Reports the fork ba

docs/architecture/pmu-pipeline-full-spec.md
scripts/pmu/pipeline-harness.mjs
tests/pmu-simulator/one-pipeline.test.mjs

Produced on the chip by the running pipeline (scripts/pmu/pipeline.mjs → runPipeline → walk + xor), commit-scoped · on-chip per-walk 1552.97ns (this commit). Recompute: node scripts/pmu/commit-triptych.mjs --commit e15fc7fa3

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.