#!/usr/bin/env bash
# One training cycle on the Spark, start to finish, unattended.
#
#   nohup bash ~/AareLC_train/tools/spark_cycle.sh v5 > ~/cycle_v5.log 2>&1 &
#   bash ~/AareLC_train/tools/spark_cycle.sh v5 --quick      # also the fast settings-A run first
#
# Steps: wait for a running pipeline batch; grow the gold set by its rule (studio `gold`
# stage: gold batches, share, floors); export the reviewed pool as dataset <tag> into this
# repo; stop vLLM; re-measure every registry model on the grown gold set so the gate and
# the comparison stand on the same frames; train the promoted recipe from the base weights;
# gate (paired bootstrap against the active model), promote on a clear win; compare every
# model on the unseen frames; push; start vLLM again.
#
# What earlier cycles taught, built in:
#   - a failed gate is a verdict, not a crash: train_run.py is called once per run;
#   - a full-resolution-mask training does not fit next to vLLM in 121 GB: vLLM is stopped
#     while it runs and started again on exit, whatever happens;
#   - torch's native JIT wants Python headers the Spark lacks: switched off, headers on CPATH;
#   - a grown gold set invalidates stored predictions: everything is re-measured first.
set -eo pipefail
TAG="${1:?usage: spark_cycle.sh <dataset tag, e.g. v5> [--quick]}"; QUICK="${2:-}"
export PATH=$HOME/bin:$PATH
export CPATH=$HOME/local/root/usr/include:$HOME/local/root/usr/include/python3.12
export TORCH_DISABLE_NATIVE_JIT=1
PY=$HOME/AareLC_studio/.venv/bin/python
STUDIO=$HOME/AareLC_studio; TRAIN=$HOME/AareLC_train; CFG=pipeline.prod.json
say() { echo "== $(date +%H:%M) $*"; }

while pgrep -f "[p]ipeline.run auto" >/dev/null; do sleep 30; done   # the reviewers' batch goes first
cd "$STUDIO"; set -a; . ~/.aaredb_env; set +a
say "gold: growing by rule"
$PY -m src.pipeline.run gold --config $CFG 2>&1 | grep -E "^gold" | cut -c1-220 || true
say "export + import into AareLC_train (dataset $TAG)"
$PY -m src.pipeline.run export --config $CFG --dest "data/pipeline_prod/dataset_$(date +%F)_$TAG" --train-repo "$TRAIN" --train-tag "$TAG" 2>&1 | grep -E "^export|dataset |committed|tagged|gold" | cut -c1-220 || true
cd "$TRAIN"
DS=$(git tag -l "dataset/*_$TAG" | tail -1); [ -n "$DS" ] || { echo "no dataset tag for $TAG"; exit 1; }
DSDIR="data/datasets/${DS#dataset/}"
say "dataset $DS: $(ls $DSDIR/images/train | wc -l) train / $(ls $DSDIR/images/val | wc -l) val; gold $(ls data/gold/labels | wc -l) frames"

vllm_back() {
  for i in 1 2 3; do
    docker start vllm >> ~/vllm_restart.log 2>&1 || true; sleep 60
    if docker ps --format "{{.Names}}" | grep -q "^vllm$"; then echo "$(date) vllm up (try $i)" >> ~/vllm_restart.log; return 0; fi
  done
  echo "$(date) vllm did NOT come back" >> ~/vllm_restart.log
}
trap vllm_back EXIT
docker stop vllm >/dev/null 2>&1 || true
say "vLLM stopped, $(free -g | awk 'NR==2{print $7}') GB available"

say "re-measuring every registry model on the $(ls data/gold/labels | wc -l) gold frames"
for d in models/registry/*/; do
  v=$(basename "$d"); [ -f "$d/weights.pt" ] || continue
  $PY tools/measure_weights.py "$d/weights.pt" --version "$v" 2>&1 | tail -n 1
done
BEAMLINE_PT=$STUDIO/models/best_yolo26n-seg-overlap-false_2026-04-12.pt   # the model before the loop lives in the studio
[ -f "$BEAMLINE_PT" ] && $PY tools/measure_weights.py "$BEAMLINE_PT" --version yolo26n-seg-overlap-false-2026-04-12 2>&1 | tail -n 1
git add models/registry data/gold && git commit -q -m "gold grown to $(ls data/gold/labels | wc -l) frames; every registry model re-measured on it" || true

run() {  # tag suffix, note, extra train_run.py args...
  local suffix="$1" note="$2"; shift 2
  local id; id=$(python3 tools/ledger.py new --dataset "$DS" --tag "$TAG-$suffix" --base models/base/yolo26n-seg.pt --note "$note")
  git add runs && git commit -q -m "run $id: exported on $DS" || true
  say "training $id"
  set +e
  $PY tools/train_run.py "$id" --device 0 --workers 8 "$@" > "runs/$id/train.log" 2>&1 < /dev/null
  local rc=$?            # 0 = gate passed (or no baseline), 2 = gate failed: both are verdicts
  set -e
  [ $rc -eq 0 ] || [ $rc -eq 2 ] || echo "!! $id ended with exit code $rc: $(grep -aiE "error|out of memory" runs/$id/train.log | tail -1 | cut -c1-160)"
  local v; v=$(python3 -c "import json;print(json.load(open('runs/$id/run.json')).get('version') or '')")
  if [ -n "$v" ] && [ -d "runs/$id/gold_predictions" ]; then mkdir -p "runs/_measure_$v" && cp -r "runs/$id/gold_predictions" "runs/_measure_$v/"; fi
  python3 -c "import json; m=json.load(open('runs/$id/metrics.json')); g=m.get('gate') or {}; b=g.get('bootstrap') or {}; print('   gate:', g.get('pass'), '| rule:', g.get('rule'), '| F1', g.get('f1_delta'), 'mask', round(g.get('mask_score',0)-g.get('mask_score_baseline',0),4), '| win F1', (b.get('f1') or {}).get('win'), 'win mask', (b.get('mask_score') or {}).get('win'))" 2>/dev/null || true
  python3 tools/ledger.py render >/dev/null 2>&1 || true
  git add runs models && git commit -q -m "run $id: $(python3 -c "import json;print(json.load(open('runs/$id/run.json'))['status'])")" || true
}
[ "$QUICK" = "--quick" ] && run recipeA "settings A (fliplr 0.5, mask_ratio 4) on dataset $TAG: quick signal, gate only, Spark" --no-promote --set fliplr=0.5 mask_ratio=4
run noflip-mask1 "promoted recipe (fliplr 0, mask_ratio 1) on dataset $TAG: candidate for the beamlines, Spark" --set fliplr=0 mask_ratio=1

say "every model on the unseen gold frames"
$PY tools/compare_unseen.py 2>&1 | cut -c1-200 || true
git add runs && git commit -q -m "unseen-frame comparison after cycle $TAG" || true
say "active model now: $(python3 -c 'import json;print(json.load(open("models/active/production.json"))["version"])')"
bash ~/sync_push.sh 2>&1 | tail -2
say "cycle $TAG done"