#!/usr/bin/env bash
# service-worker.sh <task-name> <prompt-file> <sentinel-name>
#
# Runs ONE worker under the sprite service supervisor instead of `setsid nohup`.
#
# WHY THIS EXISTS (wave-4 post-mortem, second failure):
# `setsid nohup ./tasks/run-task.sh ...` does NOT reliably outlive the orchestrator.
# On 09-06 at 19:04 the orchestrator's session was torn down and the detached worker
# AND its wave-guard died with it -- no reboot (uptime was continuous), so this was a
# teardown kill, not the hazard-#5 suspend. `setsid` did not save it.
#
# /.sprite/llm.txt: services are "long-running processes that persist across reboots"
# and "services and sessions keep sprites alive". A service therefore fixes BOTH
# failure modes at once -- it survives orchestrator teardown AND holds the box awake --
# which makes the task-lease guard redundant.
#
# IDEMPOTENCE MATTERS HERE: the supervisor restarts services. Without the sentinel
# guard below, a finished wave would be re-run on every restart and burn quota
# redoing completed work.
set -u
NAME="$1"; PROMPT="$2"; SENT="$3"
L="$HOME/bookshelf/logs"; DONE="$L/$SENT"
SVC="${SVC_NAME:-bookshelf-worker}"

log() { echo "[$(date -Is)] service-worker: $*" >> "$L/service-worker.log"; }

# Already finished -> do not re-run. Idle briefly so a restart loop stays slow.
if [ -f "$DONE" ]; then
  log "$SENT already exists; nothing to do (service can be deleted)"
  sleep 300
  exit 0
fi

log "starting worker $NAME (prompt=$PROMPT, sentinel=$SENT)"
"$HOME/bookshelf/tasks/run-task.sh" "$NAME" "$PROMPT"
rc=$?
log "worker $NAME exited rc=$rc; writing $SENT"

{
  echo "=== $SENT written $(date -Is) ==="
  echo "Worker finished under the service supervisor. The orchestrator was NOT"
  echo "necessarily alive for this. run-task.sh exit code: $rc"
  echo
  echo "--- $NAME ---"
  grep -hE 'SUCCESS|GIVING UP|WALL CLOCK|QUOTA' "$L/$NAME.state" 2>/dev/null | tail -5
  if [ -s "$L/$NAME.json" ]; then
    jq -r '"cost=$" + ((.total_cost_usd//0)|tostring) + " turns=" + ((.num_turns//0)|tostring)' "$L/$NAME.json" 2>/dev/null
    jq -r '"is_error=" + ((.is_error//false)|tostring)' "$L/$NAME.json" 2>/dev/null
  else
    echo "!! $NAME.json is 0 bytes -> worker was KILLED, not finished (hazard #3)"
  fi
  echo
  echo "NEXT: orchestrator must independently verify before accepting:"
  echo "  cd ~/bookshelf && ./tasks/gw assembleDebug && ./tasks/gw testDebugUnitTest"
  echo "  git status --porcelain   # what did the worker actually touch?"
} > "$DONE"
sync

# Sentinel is durable now, so it is safe to stop ourselves. This lets the sprite
# suspend instead of idling hot on the owner's dime.
log "stopping service $SVC so the sprite can suspend"
sprite-env services stop "$SVC" >/dev/null 2>&1
sleep 60