#!/usr/bin/env bash
# Generate the clean LLM reading version for every document, in parallel.
#
# - One doc per `claude -p` (Sonnet) via 40_reading_version.py
# - Skips docs that already have reading.md (idempotent — safe to re-run)
# - mkdir-based per-doc lock prevents two workers racing the same doc
# - WORKERS parallel workers (default 2)
#
# Run:
#   ./run_reading_parallel.sh                # all docs, 2 workers
#   WORKERS=3 ./run_reading_parallel.sh      # 3 workers
#   ./run_reading_parallel.sh DOC1 DOC2      # specific docs only
set -uo pipefail

UFO="/Users/guto/ufo"
RAW="$UFO/raw"
GEN="$UFO/scripts/synthesize/40_reading_version.py"
WORKERS="${WORKERS:-2}"

if [ "$#" -gt 0 ]; then
  DOCS=("$@")
else
  DOCS=()
  for d in "$RAW"/*--subagent; do
    [ -f "$d/_index.json" ] || continue
    DOCS+=("$(basename "$d" | sed 's/--subagent$//')")
  done
fi

echo "=== reading-version generator ==="
echo "  docs queued: ${#DOCS[@]}"
echo "  workers:     $WORKERS"
echo ""

process_one() {
  local doc_id="$1"
  local sub="$RAW/$doc_id--subagent"
  local out="$sub/reading.md"
  local log="$sub/_reading.log"
  local lock="$sub/.reading.lock"

  if [ -f "$out" ]; then
    echo "[SKIP] $doc_id (already has reading.md)"
    return 0
  fi
  if ! mkdir "$lock" 2>/dev/null; then
    echo "[LOCK] $doc_id (another worker)"
    return 0
  fi
  trap "rmdir '$lock' 2>/dev/null || true" EXIT

  local t0=$(date +%s)
  echo "[BEGIN] $doc_id"
  if python3 "$GEN" "$doc_id" > "$log" 2>&1; then
    echo "[OK]    $doc_id ($(($(date +%s) - t0))s)"
  else
    echo "[FAIL]  $doc_id ($(($(date +%s) - t0))s) — see $log"
  fi
  rmdir "$lock" 2>/dev/null || true
  trap - EXIT
}
export -f process_one
export RAW GEN

printf '%s\n' "${DOCS[@]}" | xargs -n 1 -P "$WORKERS" -I {} bash -c 'process_one "$@"' _ {}

echo ""
echo "=== Done. reading.md count: ==="
ls "$RAW"/*--subagent/reading.md 2>/dev/null | wc -l