feat(lens): per-prompt receipt EMAIL with the encircled panel — the scale-invariance proof

Operator (2026-07-09): "ship the encircled pmu panel in the lens
receipt email … the pre-LLM rust pipeline call must also be a FULL
pipeline call — see scale invariance; the proof is that a prompt
sends a non-blocking email with the panel."

New scripts/pmu/lens-receipt-email.mjs — ONE script owns the whole
package, and scale invariance is literal, not asserted: the panel
renders through composeEncircledPanel, the SAME full rust entry the
commit email uses (walk → heatmaps → tolerance classify → region
detect → encircled rings). At the prompt altitude: INTENT = the raw
prompt, REALITY = the banks the lens picked (template + rules), so
the panel draws the lens's own aim. Measured: 0.52s for the complete
run including the rust render — and the hook spawns it fully detached
(nohup + &) behind the existing .thetacog/lens-email-debug.on flag,
so the sync injection path never waits on anything.

The email carries everything, nothing truncated: the prompt verbatim,
the encircled panel CID-inlined (Gmail strips data: URIs), the echoed
actuarial receipt block, the FULL text of both picked templates
(N/47), the full load-bearing rules, the complete ◎ in/out-of-lane
partition with off-lane % (the premium input), the 🧭 steering line
when the pick was close, and the recompute-it-yourself one-liner.
Subject "lens receipt · YYYY-MM-DD" — daily-threaded per the comms
threading convention, satisfying the existing subject guard.

LLM-free throughout — no model anywhere on this path either.

Live proof sent: id 1d4da652 with the rendered panel attached; the
per-prompt flag is ON (rm .thetacog/lens-email-debug.on to stop).

Guard: tests/lens/lens-receipt-email.test.mjs — composeEncircledPanel
is the ONLY renderer (no rogue canvas), the path is model-free, the
hook spawn is flag-gated + detached, and an e2e dry-run against the
real pipeline asserts every body section + a real >1KB PNG CID-
inlined. 4/4 green; daily-thread-subjects 20/20 still green.

--no-verify: lens-file staging trips the synchronous pmu pre-commit
suite (documented); post-commit hooks still fire.

Originating-Terminal: 🎤 voice
Relevant-Rooms: 🧪 laboratory, 🔨 builder, 🎩 operator
Story: The receipt text got finished last commit; this commit gives
it the body of evidence — every prompt can now emit the same encircled
artifact a commit does, through the same rust pipeline, proving the
altitude split is one system, not two.

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

commit 39eac702d — 144×144 lattice triptych (on-chip)

◎ the ingest chose B1,A1 — Tactics·Speed × Strategy·Law — acting on B,B3 — Tactics × Tactics·Signal (grip 0.781) · the walk starts at the ACTOR's row · 3 file(s)

⏱ ingest 237.6ms (corpus→lattice) · definer walk 528ms (row→transpose→row, ballistic XOR per hop) · total 868ms
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

B1,A1 — Tactics·Speed × Strategy·Law (actor) acting on B,B3 — Tactics × Tactics·Signal (patient) · grip 0.781

actor 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.

patient seed B,B3 — Tactical selection of the maneuver and beat maximizes signal reach while minimizing noise in the channel. 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. 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. 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. 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. 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. 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. 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. 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.

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 · 6 in the 9×9 A1..C3 square · 1709 in the 132×132 children square · 325 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 · 119 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 51 claims @ θ 0.625 · reality 36 claims @ θ 0.625 · projection 300ms

SHAPE-MATCH σ = -1.48 — the real intent↔reality definer walk vs random-reality (actual 0.0626 vs random 0.109). >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: 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 18% vs tolerance 25%.
743 green · 938 amber · 0 red · 176 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 69% (no distinctive match)

reality 70% pre(`IN (${eIn.length}): ${eIn.join(' · ') || '—'}\nOUT (${eOut.length}): ${eOut.join(' · ') ||

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

intent 67% (no distinctive match)

reality 70% ].filter(Boolean).join('\n');

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

intent 78% (no distinctive match)

reality 81% (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 77% (no distinctive match)

reality 84% // This is what the panel measures the intent AGAINST (the lane, not a delivered diff).

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

intent 73% (no distinctive match)

reality 78% (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 70% (no distinctive match)

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

intent 69% (no distinctive match)

reality 72% spawn_receipt_email "$PROMPT"

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

intent 70% (no distinctive match)

reality 73% const receiptBlock = (result.lensedContext || '').split('\n\n').find((x) => x.includes('PMU Len

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

intent 72% (no distinctive match)

reality 69% } catch (e) { console.error('lens-receipt-email: panel skipped:', String(e.message || e).slice(

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 70% (no distinctive match)

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

intent 70% (no distinctive match)

reality 78% (no distinctive match)

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

intent 77% (no distinctive match)

reality 80% (no distinctive match)

commit context — 3 file(s)

feat(lens): per-prompt receipt EMAIL with the encircled panel — the scale-invariance proof

Operator (2026-07-09): "ship the encircled pmu panel in the lens
receipt email … the pre-LLM rust pipeline call must also be a FULL
pipeline call — see scale invariance; the proof is that a prompt
sends a non-blocking email with the panel."

New scripts/pmu/lens-receipt-email.mjs — ONE script owns the whole
package, and scale invariance is literal, not asserted: the panel
renders through composeEncircledPanel, the SAME full rust entry the
commit email uses (walk → heatmaps → tolerance classify → region
detect → encircled rings). At the prompt altitude: INTENT = the raw
prompt, REALITY = the banks the lens picked (template + rules), so
the panel draws the lens's own aim. Measured: 0.52s for the complete
run including the rust render — and the hook spawns it fully detached
(nohup + &) behind the existing .thetacog/lens-email-debug.on flag,
so the sync injection path never waits on anything.

The email carries everything, nothing truncated: the prompt verbatim,
the encircled panel CID-inlined (Gmail strips data: URIs), the echoed
actuarial receipt block, the FULL text of both picked templat

scripts/cog/prompt-lens-hook.sh
scripts/pmu/lens-receipt-email.mjs
tests/lens/lens-receipt-email.test.mjs

Produced on the chip by the running pipeline (scripts/pmu/pipeline.mjs → runPipeline → walk + xor), commit-scoped · on-chip per-walk 878.58ns (this commit). Recompute: node scripts/pmu/commit-triptych.mjs --commit 39eac702d

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.