#!/usr/bin/env bash
set -euo pipefail

TMP_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")"/.. && pwd)/tmp/metric-verify"
mkdir -p "$TMP_DIR"

# 载入端口变量（由 .env 提供）
TEST_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")"/.. && pwd)"
if [[ -f "$TEST_ROOT/.env" ]]; then
  set -a; source "$TEST_ROOT/.env"; set +a
fi

PROM_BASE="http://localhost:${PROMETHEUS_PORT:-9090}/api/v1"
INSTANCE="${METRIC_TEST_INSTANCE:-172.31.0.50:9100}"
IP_ONLY="${INSTANCE%%:*}"

echo "[VERIFY:DATA] node exporter metrics present in container"
docker exec argus-metric-test-node bash -lc "curl -fsS --max-time 5 http://localhost:9100/metrics | head -n 5" > "$TMP_DIR/node_metrics_head.txt" || { echo "[ERR] cannot fetch node exporter metrics" >&2; exit 1; }
if ! grep -E "node_(exporter_build_info|time_seconds)" -q "$TMP_DIR/node_metrics_head.txt"; then
  echo "[WARN] head did not show expected lines; continuing (exporter may output later lines)"
fi
echo "[OK] node exporter endpoint reachable"

echo "[VERIFY:DATA] Prometheus has recent sample for build_info"
curl -fsS --max-time 5 --get "$PROM_BASE/query" --data-urlencode "query=node_exporter_build_info{job=\"node\",ip=\"$IP_ONLY\"}" > "$TMP_DIR/prom_ne_build_info_1.json"

python3 - "$TMP_DIR/prom_ne_build_info_1.json" <<'PY'
import json,sys,time
j=json.load(open(sys.argv[1]))
res=j.get('data',{}).get('result',[])
assert res, 'no result for node_exporter_build_info'
ts=float(res[0]['value'][0])
now=time.time()
assert now-ts<180, f"sample too old: now={now} ts={ts}"
print(int(ts))
PY
T1=$?
sleep 30
curl -fsS --max-time 5 --get "$PROM_BASE/query" --data-urlencode "query=node_exporter_build_info{job=\"node\",ip=\"$IP_ONLY\"}" > "$TMP_DIR/prom_ne_build_info_2.json"

TS1=$(python3 - "$TMP_DIR/prom_ne_build_info_1.json" <<'PY'
import json,sys
print(float(json.load(open(sys.argv[1]))['data']['result'][0]['value'][0]))
PY
)
TS2=$(python3 - "$TMP_DIR/prom_ne_build_info_2.json" <<'PY'
import json,sys
print(float(json.load(open(sys.argv[1]))['data']['result'][0]['value'][0]))
PY
)
awk -v a="$TS1" -v b="$TS2" 'BEGIN{ if (b>=a) exit 0; else exit 1 }' || { echo "[ERR] sample timestamp did not advance" >&2; exit 1; }
echo "[OK] sample timestamp advanced"
echo "[DONE] dataplane verify"

# 追加：GPU 节点端点连通性检查（启用 GPU 时）
if [[ "${ENABLE_GPU:-false}" == "true" ]]; then
  echo
  echo "[VERIFY:DATA][GPU] curl endpoints on gpu node"
  if ! docker exec argus-metric-test-gpu-node bash -lc 'curl -fsS --max-time 5 http://localhost:9100/metrics >/dev/null'; then
    echo "[ERR] gpu node 9100 not reachable" >&2; exit 1
  fi
  if ! docker exec argus-metric-test-gpu-node bash -lc 'curl -fsS --max-time 5 http://localhost:9400/metrics >/dev/null'; then
    echo "[ERR] gpu node 9400 not reachable" >&2; exit 1
  fi
  echo "[OK] gpu node endpoints reachable"
fi