feat(pmu): blend-sweep frames — render every step, skip only on deterministic identity

The frame contract (operator): every blend step renders its full triptych
frame (buildTriptychInputs → renderTriptych, the canonical pipeline —
never a re-derived panel) UNLESS the state is content-hash-identical to an
already-rendered state; a cache hit is the ONLY skippable frame. frameKey
= sha256 of the triangulation texts, so re-running a sweep reuses every
frame instantly while any novel blend renders fresh (~1.2–3s measured).
--render all|last|none; frames + index.json land in docs/pmu/blend-frames/
(served next to the instrument). Measured full run: 10 fresh + 1 memo hit,
identical three-flip boundary (f=0.3 · 0.6 abstain pinch · 0.7). Guard
extended same commit: fresh-on-first, cached-on-rerun, distinct keys for
distinct blends (no false dedup).

Originating-Terminal: 🔨 builder
Relevant-Rooms: 🔨 builder, 🧭 navigator, 🧪 laboratory
Story: The operator's UX-feedback requirement made the skip rule explicit — frames may only be skipped when they deterministically fit a prior state, never for convenience. Content-hash memoization is that rule made mechanical: the filmstrip of the decision boundary is now a served artifact scrubbers and future streaming UX can walk, and the cost of honesty amortizes to zero on re-runs.

Receipt-Verified: σ=2.54 · cell=A · witness-agreement=GZIP_ONLY · lens=gzip · receipt=d9bcde27

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YQxP9rRho3RXPUBTtdvWgZ

commit 3cb651451 — 144×144 lattice triptych (on-chip)

◎ the ingest chose B2,C2 — Tactics·Deal × Operations·Loop — acting on B1,A1 — Tactics·Speed × Strategy·Law (grip 0.766) · the walk starts at the ACTOR's row · 2 file(s)

⏱ ingest 116.2ms (corpus→lattice) · definer walk 367ms (row→transpose→row, ballistic XOR per hop) · total 638ms
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) · 3% 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

B2,C2 — Tactics·Deal × Operations·Loop (actor) acting on B1,A1 — Tactics·Speed × Strategy·Law (patient) · grip 0.766

actor seed B2,C2 — Every exchange rate and deal term is validated through the iterative feedback loop and hypothesis test cycle. 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. A loop that does not learn is a treadmill. The cycle has to update its own model on the way around, or the same lap teaches nothing the previous lap did not already teach. The deal sets the exchange rate between two value substrates. Mis-priced exchange is a slow-bleed; correctly priced exchange compounds both sides, because each cycle of trade enriches the bench on both ends. Terms are the API between two organizations — every clause is a contract method that survives the handshake. Renegotiation is the breaking change; the deal is the stable interface either side can build against. Negotiation closes at the moment both parties' BATNAs cross. Push past that point and you've bought regret at retail; stop short and you've left margin on the table that the next deal will not return to you.

patient seed B1,A1 — Speed limits are constrained by the binding mandate and governance rule of law within the beat. 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. Latency is the price of a missed beat. Every hundred milliseconds of round-trip turns a parallel race into a stalemate, because the first arrival sets the rules the second arrival has to honor. Throughput compounds: doubling the rate doubles the surface area where serendipity can hit. A pipeline at twice the velocity is not twice as productive — it is exponentially more lucky. Time-to-first-byte is the only number the operator feels at the wheel. Optimize the felt latency before the raw throughput; the operator's grip on the loop is what drives the loop forward.

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) · 2% 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 · 9 in the 9×9 A1..C3 square · 1307 in the 132×132 children square · 295 cross-zone
REALITY: 0 in the 3×3 ABC corner · 8 in the 9×9 A1..C3 square · 1067 in the 132×132 children square · 176 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 40 claims @ θ 0.625 · reality 20 claims @ θ 0.6094 · projection 593ms

SHAPE-MATCH σ = -0.05 — the real intent↔reality definer walk vs random-reality (actual 0.0779 vs random 0.079). >0 = the walk distinguishes real alignment from noise; aggregate over independent walks → the divergent series.
σ_drift · noise · below zero — this read is noise, not a measurement

Most out-of-lane row: C1 · Grid — 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 9% vs tolerance 25%.
562 green · 761 amber · 0 red · 82 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 66% (no distinctive match)

reality 70% // ── THE FRAME CONTRACT (operator 2026-07-15): every step RENDERS its full triptych frame unle

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

intent 75% (no distinctive match)

reality 67% (no distinctive match)

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

intent 78% (no distinctive match)

reality 72% (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 80% tests/pmu-simulator/tape-blend-sweep.test.mjs — THE BOUNDARY MAP GUARD (operator 2026-07-15:. "

reality 72% (no distinctive match)

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

intent 73% (no distinctive match)

reality 75% (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 69% (no distinctive match)

reality 67% (no distinctive match)

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

intent 73% feat(pmu): blend-sweep frames — render every step, skip only on deterministic identity

reality 72% (no distinctive match)

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

intent 78% (no distinctive match)

reality 73% (no distinctive match)

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

intent 69% Receipt-Verified: σ=2.54 · cell=A · witness-agreement=GZIP_ONLY · lens=gzip · receipt=d9bcde27

reality 67% (no distinctive match)

C1,C1 Power flows where the grid lets it.

intent 73% Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/s

reality 67% try { row.frame = await renderFrame({ intent: from.intent, reality, negative: from.negative, la

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

intent 70% (no distinctive match)

reality 67% (no distinctive match)

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

intent 77% (no distinctive match)

reality 73% (no distinctive match)

commit context — 2 file(s)

feat(pmu): blend-sweep frames — render every step, skip only on deterministic identity

The frame contract (operator): every blend step renders its full triptych
frame (buildTriptychInputs → renderTriptych, the canonical pipeline —
never a re-derived panel) UNLESS the state is content-hash-identical to an
already-rendered state; a cache hit is the ONLY skippable frame. frameKey
= sha256 of the triangulation texts, so re-running a sweep reuses every
frame instantly while any novel blend renders fresh (~1.2–3s measured).
--render all|last|none; frames + index.json land in docs/pmu/blend-frames/
(served next to the instrument). Measured full run: 10 fresh + 1 memo hit,
identical three-flip boundary (f=0.3 · 0.6 abstain pinch · 0.7). Guard
extended same commit: fresh-on-first, cached-on-rerun, distinct keys for
distinct blends (no false dedup).

Originating-Terminal: 🔨 builder
Relevant-Rooms: 🔨 builder, 🧭 navigator, 🧪 laboratory
Story: The operator's UX-feedback requirement made the skip rule explicit — frames may only be skipped when they deterministically fit a prior state, never for convenience. Content-hash memoization is that rule made mechanical: the filmstrip of the decision

scripts/pmu/tape-blend-sweep.mjs
tests/pmu-simulator/tape-blend-sweep.test.mjs

Produced on the chip by the running pipeline (scripts/pmu/pipeline.mjs → runPipeline → walk + xor), commit-scoped · on-chip per-walk 754.81ns (this commit). Recompute: node scripts/pmu/commit-triptych.mjs --commit 3cb651451

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.