#!/usr/bin/env bash
# Sync Wormhole AI documentation exports for offline use, MCP mirror, and RAG prep.
# See docs/04-configuration/WORMHOLE_AI_RESOURCES_LLM_PLAYBOOK.md
set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
OUT="${WORMHOLE_AI_DOCS_DIR:-$REPO_ROOT/third-party/wormhole-ai-docs}"
BASE="https://wormhole.com/docs"

CATEGORIES=(
  basics ntt connect wtt settlement executor multigov queries transfer
  typescript-sdk solidity-sdk cctp reference
)

usage() {
  echo "Usage: $0 [--dry-run] [--full-jsonl]"
  echo "  WORMHOLE_AI_DOCS_DIR  output directory (default: third-party/wormhole-ai-docs)"
  echo "  INCLUDE_FULL_JSONL=1  or pass --full-jsonl to download llms-full.jsonl (large)"
  exit "${1:-0}"
}

DRY=0
FULL=0
while [[ $# -gt 0 ]]; do
  case "$1" in
    --dry-run) DRY=1 ;;
    --full-jsonl) FULL=1 ;;
    -h|--help) usage 0 ;;
    *) echo "Unknown option: $1" >&2; usage 1 ;;
  esac
  shift
done

if [[ -n "${INCLUDE_FULL_JSONL:-}" && "$INCLUDE_FULL_JSONL" != "0" ]]; then
  FULL=1
fi

echo "Output directory: $OUT"
if [[ "$DRY" -eq 1 ]]; then
  echo "[dry-run] would mkdir, curl downloads, write manifest.json"
  exit 0
fi

mkdir -p "$OUT/categories"

fetch() {
  local url="$1"
  local dest="$2"
  echo "  GET $url -> $dest"
  curl -fsSL --connect-timeout 30 --max-time 600 -o "$dest" "$url"
}

fetch "$BASE/llms.txt" "$OUT/llms.txt"
fetch "$BASE/ai/site-index.json" "$OUT/site-index.json"

for name in "${CATEGORIES[@]}"; do
  fetch "$BASE/ai/categories/${name}.md" "$OUT/categories/${name}.md"
done

if [[ "$FULL" -eq 1 ]]; then
  fetch "$BASE/ai/llms-full.jsonl" "$OUT/llms-full.jsonl"
else
  rm -f "$OUT/llms-full.jsonl"
fi

MANIFEST="$OUT/manifest.json"
export OUT MANIFEST BASE
python3 <<'PY'
import hashlib, json, os
from datetime import datetime, timezone
from pathlib import Path

out = Path(os.environ["OUT"])
base = os.environ["BASE"]
manifest_path = Path(os.environ["MANIFEST"])
files = {}
for p in sorted(out.rglob("*")):
    if not p.is_file():
        continue
    if p.name in ("manifest.json", "README.md"):
        continue
    rel = str(p.relative_to(out)).replace("\\", "/")
    data = p.read_bytes()
    files[rel] = {
        "sha256": hashlib.sha256(data).hexdigest(),
        "bytes": len(data),
    }
doc = {
    "synced_at_utc": datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ"),
    "base_url": base,
    "files": files,
}
manifest_path.write_text(json.dumps(doc, indent=2) + "\n", encoding="utf-8")
PY

echo "Done. Manifest: $MANIFEST"