#!/usr/bin/env bash
# wave-guard.sh <sentinel-name> <task> [<task>...]
#
# Solves the real cause of the wave-3 loss: the sprite AUTO-SUSPENDS when idle
# ("When idle, sprites pause automatically" — /.sprite/llm.txt). Detached workers
# do NOT keep it awake; only services, live sessions, or a task lease do.
#
# Holds a sprite task lease (POST /v1/tasks, max expire 3600s) and renews it while
# workers run, so the box stays hot with no console attached. When the workers stop
# it writes the durable completion record AND releases the lease, so the sprite is
# free to suspend instead of burning money idling.
set -u
SENT="$1"; shift
TASKS=("$@")
L="$HOME/bookshelf/logs"; OUT="$L/$SENT"; LEASE="bookshelf-wave"
RENEW="${RENEW:-900}"        # renew every 15 min against a 60 min lease
GUARD_LOG="$L/wave-guard.log"

lease_hold() {
  sprite-env curl -X DELETE "/v1/tasks/$LEASE" >/dev/null 2>&1
  sprite-env curl -X POST /v1/tasks -H 'Content-Type: application/json' \
    -d "{\"name\":\"$LEASE\",\"expire\":\"3600s\"}" >/dev/null 2>&1
}
lease_release() { sprite-env curl -X DELETE "/v1/tasks/$LEASE" >/dev/null 2>&1; }
log() { echo "[$(date -Is)] $*" >> "$GUARD_LOG"; }

trap 'lease_release; log "guard exiting, lease released"; exit 0' TERM INT

log "guard start: sentinel=$SENT tasks=${TASKS[*]} renew=${RENEW}s"
lease_hold; log "lease '$LEASE' acquired (3600s)"

while pgrep -f 'run-task\.sh|run-resume\.sh' >/dev/null; do
  sleep "$RENEW"
  lease_hold
  log "lease renewed; workers still running"
done

log "workers stopped; writing $SENT"
{
  echo "=== $SENT written $(date -Is) ==="
  echo "Workers finished. The orchestrator was NOT necessarily alive for this."
  echo
  for t in "${TASKS[@]}"; do
    echo "--- $t ---"
    grep -hE 'SUCCESS|GIVING UP|WALL CLOCK|QUOTA' "$L/$t.state" 2>/dev/null | tail -3
    if [ -s "$L/$t.json" ]; then
      jq -r '"cost=$" + ((.total_cost_usd//0)|tostring) + " turns=" + ((.num_turns//0)|tostring)' "$L/$t.json" 2>/dev/null
    else
      echo "!! $t.json is 0 bytes -> worker was KILLED, not finished (hazard #3/#5)"
    fi
    echo
  done
  echo "NEXT: orchestrator must independently verify before accepting:"
  echo "  cd ~/bookshelf && ./tasks/gw assembleDebug && ./tasks/gw testDebugUnitTest"
  echo "  git status --porcelain   # boundary check: who touched what"
} > "$OUT"

lease_release; log "lease released; sprite may suspend"