fix(budget): make the canonical .thetacog/llm-pause flag actually reach the scheduled claude -p spenders

The passive per-commit dispatches honored .thetacog/llm-pause since the 2026-06-12
token-burn incident, but the scheduled hard-claude workers (controller STAGE 1/2/7b/8
and their standalone launchd agents) called `claude -p` DIRECTLY and bypassed the flag
— so `touch .thetacog/llm-pause` did NOT stop the drain. This week's budget hit ~90%
mid-week; reserving the remainder for interactive work until the Thursday reset.

Adds the canonical early-exit to every scheduled script that spends claude:
spec-reply-execute, gcal poll-execute, cos-overnight, intervention-fire (drift→LLM),
calendar-primer-cron. One `touch .thetacog/llm-pause` now stops all of them; `rm` resumes.

The book club (bookclub-daily.sh / bookclub/*, $0 LLM) is deliberately carved OUT and
keeps running. Free/local qwen (ollama) dispatches are untouched — gemini's free tier is
exhausted so those fall back to local qwen at zero budget.

Deliverable is the guard: tests/ops/llm-pause-honored.test.js asserts each spender
early-exits on the flag AND that the book club never gains a pause exit. 14/14 green.

Originating-Terminal: 📐 architect
Relevant-Rooms: 🔨 builder, 🎩 operator, 🔒 vault
Story: Budget triage in the infra-hooks lane — the pause flag existed but leaked past the
exact scripts it was built to stop. Closing that gap at the source (script-level guard, not
agent teardown) means one flag + one test covers controller stages and standalone agents
alike, fully reversible with rm, with the book club untouched per the operator carve-out.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0177tZrfK4nEfqRKTAgSKaoN

commit d62fb01f3 — 144×144 lattice triptych (on-chip)

◎ the ingest chose A2,B3 — Strategy·Goal × Tactics·Signal — acting on A,B2 — Strategy × Tactics·Deal (grip 0.734) · the walk starts at the ACTOR's row · 6 file(s)

⏱ ingest 108.3ms (corpus→lattice) · definer walk 362ms (row→transpose→row, ballistic XOR per hop) · total 602ms
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

A2,B3 — Strategy·Goal × Tactics·Signal (actor) acting on A,B2 — Strategy × Tactics·Deal (patient) · grip 0.734

actor seed A2,B3 — Target goals prioritize the signal reach and message bandwidth required to occupy the quarterly position. 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. 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. 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. 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. 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.

patient seed A,B2 — Strategy underwrites the long-horizon substrate where deal rates and exchange terms are evaluated within the lattice. 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. 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.

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 · 7% 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 · 0 in the 9×9 A1..C3 square · 2391 in the 132×132 children square · 172 cross-zone
REALITY: 1 in the 3×3 ABC corner · 4 in the 9×9 A1..C3 square · 1674 in the 132×132 children square · 242 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 11 claims @ θ 0.5938 · reality 24 claims @ θ 0.6094 · projection 303ms

SHAPE-MATCH σ = 0.25 — the real intent↔reality definer walk vs random-reality (actual 0.0661 vs random 0.059). >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: 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 15% vs tolerance 25%.
462 green · 553 amber · 0 red · 39 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 72% (no distinctive match)

reality 70% (no distinctive match)

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

intent 72% (no distinctive match)

reality 80% (no distinctive match)

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

intent 73% (no distinctive match)

reality 78% (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 73% (no distinctive match)

reality 72% (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 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 73% (no distinctive match)

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

intent 69% (no distinctive match)

reality 72% (no distinctive match)

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

intent 75% (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 63% Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/

reality 77% (no distinctive match)

C1,C1 Power flows where the grid lets it.

intent 73% (no distinctive match)

reality 73% (no distinctive match)

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

intent 69% (no distinctive match)

reality 67% (no distinctive match)

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

intent 72% (no distinctive match)

reality 77% !/usr/bin/env bash. scripts/controller/cos-overnight.sh — STAGE: the Chief-of-Staff overnight r

commit context — 6 file(s)

fix(budget): make the canonical .thetacog/llm-pause flag actually reach the scheduled claude -p spenders

The passive per-commit dispatches honored .thetacog/llm-pause since the 2026-06-12
token-burn incident, but the scheduled hard-claude workers (controller STAGE 1/2/7b/8
and their standalone launchd agents) called `claude -p` DIRECTLY and bypassed the flag
— so `touch .thetacog/llm-pause` did NOT stop the drain. This week's budget hit ~90%
mid-week; reserving the remainder for interactive work until the Thursday reset.

Adds the canonical early-exit to every scheduled script that spends claude:
spec-reply-execute, gcal poll-execute, cos-overnight, intervention-fire (drift→LLM),
calendar-primer-cron. One `touch .thetacog/llm-pause` now stops all of them; `rm` resumes.

The book club (bookclub-daily.sh / bookclub/*, $0 LLM) is deliberately carved OUT and
keeps running. Free/local qwen (ollama) dispatches are untouched — gemini's free tier is
exhausted so those fall back to local qwen at zero budget.

Deliverable is the guard: tests/ops/llm-pause-honored.test.js asserts each spender
early-exits on the flag AND that the book club never gains a pause exit. 14/14 green.

Originating-T

scripts/calendar-primer-cron.sh
scripts/controller/cos-overnight.sh
scripts/gcal-agent/poll-execute.sh
scripts/interventions/intervention-fire.sh
scripts/spec-reply-execute.sh
tests/ops/llm-pause-honored.test.js

Produced on the chip by the running pipeline (scripts/pmu/pipeline.mjs → runPipeline → walk + xor), commit-scoped · on-chip per-walk 619.84ns (this commit). Recompute: node scripts/pmu/commit-triptych.mjs --commit d62fb01f3

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.