feat(pmu): intervene delegates out-of-lane QC to 🧪 laboratory (obvious) + gap analysis

The out-of-lane intervention now routes its QC to the laboratory room via bifurcate (rooms JSON + signed
mesh, NEVER a branch) — the SAME room spec-drift-check uses — and NAMES it obviously so it can be shored
up from the Fable end. Best-effort: no-op in a stranger's repo, delegates in ours.

+ docs/pmu/intervention-detection-gap-analysis.html — what detection/intervention do now, what spec-
building-FROM-the-lens could do (4 passes to close the 80/20), the contexts used (README-spec · commit ·
prior outcomes) vs UNUSED (reef · room goals · @guard specs · direction · annotations), and the 5 decision
forks. Thesis: spec quality is the root lever — poor spec ⇒ poor detection ⇒ poor intervention.

Guard: tests/pmu/intervene-delegates-to-room.test.mjs (laboratory · bifurcate · never a branch).

Originating-Terminal: 🔨 builder
Relevant-Rooms: 🧪 laboratory, 📐 architect, 🎩 operator
Story: Detection is only as good as the spec it measures against — the analysis sets the direction to build the spec from the lens, and the QC of that work is owned by laboratory.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YQxP9rRho3RXPUBTtdvWgZ

commit 1c3cfefef — 144×144 lattice triptych (on-chip)

◎ the ingest chose A,C1 — Strategy × Operations·Grid — acting on A1,B — Strategy·Law × Tactics (grip 0.750) · the walk starts at the ACTOR's row · 3 file(s)

⏱ ingest 185.3ms (corpus→lattice) · definer walk 220ms (row→transpose→row, ballistic XOR per hop) · total 538ms
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) · 4% 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

A,C1 — Strategy × Operations·Grid (actor) acting on A1,B — Strategy·Law × Tactics (patient) · grip 0.750

actor seed A,C1 — Framing the strategy substrate involves a long-horizon view of the infrastructure grid and topology flow routes. Power flows where the grid lets it. Choose connections before topologies; the topology is what the connections compose, and a connection added later is a topology silently rewritten. Latency is geography expressed in milliseconds. The grid IS the map of where compute meets storage meets bandwidth; the map is the territory at the scale the request actually traverses. The lattice we build today is what next year's underwriter inherits. We set the substrate that downstream pricing rides on, and that choice is paid back across every quarter we keep operating. Direction is what you keep when you forget the calendar. Multi-year posture, irreversibly chosen, defines the boundary every quarter renegotiates inside. Strategy is the bearing the rotation is measured against. Capital lives where strategy is durable. Frame the ten-year shape of the business before optimizing the ten-week sprint; the substrate decisions compound while the surface decisions decay.

patient seed A1,B — Governance rules mandate a binding article that restricts which tactics and maneuver choices are legally permissible. 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. 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.

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) · 3% 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) · ⚠ TOO MANY

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 · 2 in the 9×9 A1..C3 square · 785 in the 132×132 children square · 135 cross-zone
REALITY: 0 in the 3×3 ABC corner · 2 in the 9×9 A1..C3 square · 1530 in the 132×132 children square · 270 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 0.6406 · reality 18 claims @ θ 0.6094 · projection 873ms

SHAPE-MATCH σ = 0.69 — the real intent↔reality definer walk vs random-reality (actual 0.0477 vs random 0.031). >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=FIRED — orthogonal out-of-lane 42% vs tolerance 25%.
226 green · 318 amber · 393 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 75% <p class="mut" style="margin-top:20px">Generated by the intervention/detection audit · the QC o

reality 66% '--commit'], { cwd: REPO, encoding: 'utf8', stdio: 'pipe' });

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

intent 78% (no distinctive match)

reality 66% (no distinctive match)

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

intent 78% (no distinctive match)

reality 67% (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% Intervention & Detection — the gap, and the direction to narrow it Intervention &amp; Detection

reality 69% (no distinctive match)

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

intent 77% (no distinctive match)

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 73% (no distinctive match)

reality 72% (no distinctive match)

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

intent 78% <div class="card"><b>NOT used — the gap (all present in-repo)</b><br>

reality 69% (no distinctive match)

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

intent 73% (no distinctive match)

reality 69% (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% <h2>5 · The direction — two modes, 4 passes, human only on the forks</h2>

reality 69% (no distinctive match)

C1,C1 Power flows where the grid lets it.

intent 73% <h2>4 · The lever — why spec quality is the whole game</h2>

reality 70% (no distinctive match)

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

intent 80% (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 70% (no distinctive match)

commit context — 3 file(s)

feat(pmu): intervene delegates out-of-lane QC to 🧪 laboratory (obvious) + gap analysis

The out-of-lane intervention now routes its QC to the laboratory room via bifurcate (rooms JSON + signed
mesh, NEVER a branch) — the SAME room spec-drift-check uses — and NAMES it obviously so it can be shored
up from the Fable end. Best-effort: no-op in a stranger's repo, delegates in ours.

+ docs/pmu/intervention-detection-gap-analysis.html — what detection/intervention do now, what spec-
building-FROM-the-lens could do (4 passes to close the 80/20), the contexts used (README-spec · commit ·
prior outcomes) vs UNUSED (reef · room goals · @guard specs · direction · annotations), and the 5 decision
forks. Thesis: spec quality is the root lever — poor spec ⇒ poor detection ⇒ poor intervention.

Guard: tests/pmu/intervene-delegates-to-room.test.mjs (laboratory · bifurcate · never a branch).

Originating-Terminal: 🔨 builder
Relevant-Rooms: 🧪 laboratory, 📐 architect, 🎩 operator
Story: Detection is only as good as the spec it measures against — the analysis sets the direction to build the spec from the lens, and the QC of that work is owned by laboratory.

Co-Authored-By: Claude Opus 4.8 <no

docs/pmu/intervention-detection-gap-analysis.html
scripts/pmu/intervene.mjs
tests/pmu/intervene-delegates-to-room.test.mjs

Produced on the chip by the running pipeline (scripts/pmu/pipeline.mjs → runPipeline → walk + xor), commit-scoped · on-chip per-walk 456.68ns (this commit). Recompute: node scripts/pmu/commit-triptych.mjs --commit 1c3cfefef

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.