#!/usr/bin/env bash
# run_melee_bitbrain_ab.sh — drive the melee A/B (see measure_melee_bitbrain_ab.nim).
#
# Builds ONE frozen ModularBot (from `git archive HEAD`), then runs one process
# per arm in parallel; each process owns its own Tank Royale server on an
# ephemeral port. Output: <outdir>/<arm>/run<N>.json (+ .bot.stdout.log).
#
#   common_libs/tests/run_melee_bitbrain_ab.sh [outdir]
#
# Env: MELEE_RUNS (default 16), MELEE_ROUNDS (default 7), MELEE_ARMS (space list).
# Kills its own process groups on EXIT/INT/TERM (setsid per arm).
set -euo pipefail

HERE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
REPO="$(cd "$HERE/../.." && pwd)"
OUTDIR="${1:-/tmp/melee_bitbrain_ab}"
RUNS="${MELEE_RUNS:-16}"
ROUNDS="${MELEE_ROUNDS:-7}"
ARMS_STR="${MELEE_ARMS:-pattern bb_round bb_ret bb_learn}"
BIN="$HERE/measure_melee_bitbrain_ab"

[[ -x "$BIN" ]] || { echo "ERROR: build the runner first: nim c --path:common_libs $HERE/measure_melee_bitbrain_ab.nim" >&2; exit 1; }
mkdir -p "$OUTDIR"

echo "[driver] building frozen ModularBot…"
"$BIN" --outdir "$OUTDIR" --build-only

read -r -a ARMS <<< "$ARMS_STR"
PIDS=()
cleanup() {
  local rc=$?
  trap - EXIT INT TERM
  for p in "${PIDS[@]:-}"; do
    [[ -n "$p" ]] || continue
    kill -TERM -- "-$p" 2>/dev/null || true
  done
  sleep 1
  for p in "${PIDS[@]:-}"; do
    [[ -n "$p" ]] || continue
    kill -KILL -- "-$p" 2>/dev/null || true
  done
  # backstop: anything from this run's process group that outlived the runner
  pkill -f "[m]easure_melee_bitbrain_ab.*$OUTDIR" 2>/dev/null || true
  exit "$rc"
}
trap cleanup EXIT INT TERM

for arm in "${ARMS[@]}"; do
  echo "[driver] launching arm $arm (runs=$RUNS rounds=$ROUNDS)"
  setsid "$BIN" --outdir "$OUTDIR" --arm "$arm" \
      --run-start 1 --run-count "$RUNS" --rounds "$ROUNDS" \
      > "$OUTDIR/$arm.driver.log" 2>&1 &
  PIDS+=("$!")
  sleep 3   # stagger so concurrent servers do not race for the same free port
done

echo "[driver] all arms launched; waiting…"
FAIL=0
for p in "${PIDS[@]}"; do
  wait "$p" || FAIL=$((FAIL + 1))
done
PIDS=()
echo "[driver] done (failed arm processes: $FAIL)"
exit "$FAIL"