#!/bin/bash
# Sampler for the digest-vs-transcription contention measurement (the "named
# test" in STATE.md). Writes one CSV row every 2 s.
#
# It samples the SAME TWO SIGNALS `controller/digestYield.ts` reads, through the
# endpoints that expose them — `GET /api/workers` (built from the same
# `summary()` call, so `busy` and `device` are exactly what the yield sees) and
# `GET /api/jobs/active` — beside the card's own view. That is what lets a run be
# declared VOID rather than quietly believed: if `gpu_worker_busy` was 0
# throughout, the cell measured nothing.
#
# It also samples the two things that make such a run LIE:
#   - swap_used_kb / mem_avail_kb / psi_mem_full_avg10 — a run that swaps
#     measures the swap. This is not hypothetical; see
#     aborted-run-2026-07-30.csv, where swap went 9.6 -> 18.4 GB of 19 and the
#     editor died mid-request.
#   - temp_c / power_w / sclk_hz — an RX 6600 throttles over 2-3 GPU-hours, and
#     a throttled second cell would look like a regression in the first.
#
# Usage: ./sample-contention.sh out.csv     (Ctrl-C to stop; assumes card1)
OUT="$1"; CARD=/sys/class/drm/card1/device; HW=$CARD/hwmon/hwmon2
echo "ts,gpu_busy_pct,vram_used,temp_c,power_w,sclk_hz,mem_avail_kb,swap_used_kb,psi_mem_full_avg10,loadavg1,ollama_models,gpu_worker_busy,cpu_workers_busy,active_jobs,digest_jobs" > "$OUT"
while true; do
  ts=$(date -u +%Y-%m-%dT%H:%M:%SZ)
  gpu=$(cat $CARD/gpu_busy_percent 2>/dev/null||echo -1)
  vram=$(cat $CARD/mem_info_vram_used 2>/dev/null||echo -1)
  temp=$(( $(cat $HW/temp1_input 2>/dev/null||echo 0) / 1000 ))
  pw=$(( $(cat $HW/power1_average 2>/dev/null||echo 0) / 1000000 ))
  sclk=$(cat $HW/freq1_input 2>/dev/null||echo 0)
  memav=$(awk '/MemAvailable/{print $2}' /proc/meminfo)
  swt=$(awk '/SwapTotal/{print $2}' /proc/meminfo); swf=$(awk '/SwapFree/{print $2}' /proc/meminfo)
  swu=$((swt-swf))
  psi=$(awk -F'[= ]' '/^full/{print $3}' /proc/pressure/memory)
  la=$(awk '{print $1}' /proc/loadavg)
  om=$(curl -s --max-time 2 localhost:11434/api/ps | jq -r '[.models[]?.name]|join(";")' 2>/dev/null)
  w=$(curl -s --max-time 8 localhost:3001/api/workers)
  gb=$(echo "$w" | jq -r '[.workers[]?|select(.kind=="local" and ((.device // "")|ascii_downcase)!="cpu")|select(.busy)]|length' 2>/dev/null||echo -1)
  cb=$(echo "$w" | jq -r '[.workers[]?|select(.kind=="local" and ((.device // "")|ascii_downcase)=="cpu")|select(.busy)]|length' 2>/dev/null||echo -1)
  aj=$(curl -s --max-time 8 localhost:3001/api/jobs/active)
  n=$(echo "$aj" | jq -r '[.jobs[]?|select(.status=="running")]|length' 2>/dev/null||echo -1)
  dj=$(echo "$aj" | jq -r '[.jobs[]?|select(.status=="running" and (.kind|test("digest")))]|length' 2>/dev/null||echo -1)
  echo "$ts,$gpu,$vram,$temp,$pw,$sclk,$memav,$swu,$psi,$la,$om,$gb,$cb,$n,$dj" >> "$OUT"
  sleep 2
done