#!/usr/bin/env bash
# monitor-checks.sh — poll the soft-launch acceptance gate live during
# the bêta window so the operator gets a heads-up before the decision
# call instead of discovering at 18:00 UTC that one threshold is red.
#
# Acceptance gate (per docs/SOFT_LAUNCH_BETA_2026.md §"Acceptance gate") :
#   - ≥ 50 testers signed up (used_at != NULL on beta_invites)
#   - 0 P1 events in Sentry today
#   - Status page green for the last 4 h
#   - Synthetic parcours all green for 6 h
#   - Nightly k6 load test green
#   - < 3 HIGH-severity issues reported
#
# v1.0.10 Cluster 3.4.
#
# Usage :
#   DATABASE_URL=postgres://... \
#   SENTRY_AUTH_TOKEN=... \
#   STATUSPAGE_URL=https://status.veza.fr \
#   PROM_URL=https://prom.veza.fr \
#   bash scripts/soft-launch/monitor-checks.sh
#
# By default the script runs once and exits with the gate's verdict.
# Run it from cron (e.g. every 30 min) or pass LOOP=1 to keep checking
# in-place every CHECK_INTERVAL seconds (default 600 = 10 min).
#
# Optional env :
#   LOOP=1          continuous mode
#   CHECK_INTERVAL  seconds between checks in LOOP mode (default 600)
#   QUIET=1         only emit the verdict line (for cron piping)
#   THRESHOLD_TESTERS  override 50 (default), e.g. set to 100 for
#                       a stricter sub-window
#
# Exit codes :
#   0  — every gate green
#   1  — at least one gate red
#   2  — at least one gate could not be checked (collector down,
#         token wrong, etc.) — operator must verify manually
#   3  — required env / tool missing
set -euo pipefail

DATABASE_URL=${DATABASE_URL:-?}
SENTRY_AUTH_TOKEN=${SENTRY_AUTH_TOKEN:-?}
STATUSPAGE_URL=${STATUSPAGE_URL:-https://status.veza.fr}
PROM_URL=${PROM_URL:-?}
LOOP=${LOOP:-0}
CHECK_INTERVAL=${CHECK_INTERVAL:-600}
QUIET=${QUIET:-0}
THRESHOLD_TESTERS=${THRESHOLD_TESTERS:-50}

[ "$DATABASE_URL"      = "?" ] && { echo "DATABASE_URL required" >&2; exit 3; }
[ "$SENTRY_AUTH_TOKEN" = "?" ] && { echo "SENTRY_AUTH_TOKEN required (read scope sufficient)" >&2; exit 3; }
[ "$PROM_URL"          = "?" ] && { echo "PROM_URL required" >&2; exit 3; }

command -v psql >/dev/null 2>&1 || { echo "psql required" >&2; exit 3; }
command -v curl >/dev/null 2>&1 || { echo "curl required" >&2; exit 3; }
command -v jq   >/dev/null 2>&1 || { echo "jq required"   >&2; exit 3; }

# ----------------------------------------------------------------------
# Individual gate checks. Each prints "✅ <name>" / "🔴 <name>" / "⚪ <name>"
# (last for "could not check"), and sets one of GATE_*_OK to 0 / 1 / 2.
# ----------------------------------------------------------------------

GATE_TESTERS_OK=2
GATE_SENTRY_OK=2
GATE_STATUSPAGE_OK=2
GATE_SYNTHETIC_OK=2
GATE_K6_OK=2
GATE_ISSUES_OK=2

check_testers() {
  local count
  count=$(psql "$DATABASE_URL" -A -t -c "
    SELECT count(*) FROM beta_invites WHERE used_at IS NOT NULL;
  " 2>/dev/null | tr -d ' ' || echo "?")
  if [ "$count" = "?" ] || ! [[ "$count" =~ ^[0-9]+$ ]]; then
    echo "⚪ testers signed-up : check failed (psql)"
    GATE_TESTERS_OK=2
    return
  fi
  if [ "$count" -ge "$THRESHOLD_TESTERS" ]; then
    echo "✅ testers signed-up : $count / $THRESHOLD_TESTERS"
    GATE_TESTERS_OK=0
  else
    echo "🔴 testers signed-up : $count / $THRESHOLD_TESTERS"
    GATE_TESTERS_OK=1
  fi
}

check_sentry_p1() {
  # Sentry API : count of unresolved P1 issues last 24h.
  local count
  count=$(curl -s -H "Authorization: Bearer $SENTRY_AUTH_TOKEN" \
    "https://sentry.io/api/0/projects/veza/veza-backend/issues/?statsPeriod=24h&query=is:unresolved%20level:fatal" \
    2>/dev/null | jq 'length' 2>/dev/null || echo "?")
  if [ "$count" = "?" ] || ! [[ "$count" =~ ^[0-9]+$ ]]; then
    echo "⚪ Sentry P1 events 24h : check failed (auth or network)"
    GATE_SENTRY_OK=2
    return
  fi
  if [ "$count" -eq 0 ]; then
    echo "✅ Sentry P1 events 24h : 0"
    GATE_SENTRY_OK=0
  else
    echo "🔴 Sentry P1 events 24h : $count (must be 0)"
    GATE_SENTRY_OK=1
  fi
}

check_statuspage() {
  local status
  status=$(curl -s "$STATUSPAGE_URL/api/v1/status" 2>/dev/null \
    | jq -r '.indicator // .status.indicator // ""' 2>/dev/null || echo "")
  case "$status" in
    none|operational)
      echo "✅ status page : $status (green)"
      GATE_STATUSPAGE_OK=0
      ;;
    minor|major|critical)
      echo "🔴 status page : $status"
      GATE_STATUSPAGE_OK=1
      ;;
    *)
      echo "⚪ status page : check failed (got '$status')"
      GATE_STATUSPAGE_OK=2
      ;;
  esac
}

check_synthetic() {
  # PromQL : sum of probe_success over the last 6h ; expect every
  # parcours at 1 (success).
  local query='probe_success{probe_kind="synthetic"} == 0'
  local resp
  resp=$(curl -s --get "$PROM_URL/api/v1/query" \
    --data-urlencode "query=$query" 2>/dev/null)
  local result_count
  result_count=$(echo "$resp" | jq '.data.result | length' 2>/dev/null || echo "?")
  if [ "$result_count" = "?" ] || ! [[ "$result_count" =~ ^[0-9]+$ ]]; then
    echo "⚪ synthetic parcours : check failed (Prometheus)"
    GATE_SYNTHETIC_OK=2
    return
  fi
  if [ "$result_count" -eq 0 ]; then
    echo "✅ synthetic parcours : all green"
    GATE_SYNTHETIC_OK=0
  else
    local failing
    failing=$(echo "$resp" | jq -r '.data.result[].metric.parcours' 2>/dev/null | tr '\n' ',' | sed 's/,$//')
    echo "🔴 synthetic parcours : $result_count failing ($failing)"
    GATE_SYNTHETIC_OK=1
  fi
}

check_k6_nightly() {
  # k6 nightly is exposed as veza_k6_nightly_last_success_timestamp_seconds
  # by the Forgejo runner workflow's textfile-collector. Reading via Prom
  # gives "is the last success < 30h old?".
  local query='time() - veza_k6_nightly_last_success_timestamp_seconds'
  local resp age
  resp=$(curl -s --get "$PROM_URL/api/v1/query" \
    --data-urlencode "query=$query" 2>/dev/null)
  age=$(echo "$resp" | jq -r '.data.result[0].value[1] // ""' 2>/dev/null)
  if [ -z "$age" ] || [ "$age" = "null" ]; then
    echo "⚪ k6 nightly : check failed (metric absent — runner offline?)"
    GATE_K6_OK=2
    return
  fi
  age_int=$(printf '%.0f' "$age" 2>/dev/null || echo 999999)
  if [ "$age_int" -lt 108000 ]; then  # 30h
    echo "✅ k6 nightly : last success $(( age_int / 3600 ))h ago"
    GATE_K6_OK=0
  else
    echo "🔴 k6 nightly : last success $(( age_int / 3600 ))h ago (> 30h)"
    GATE_K6_OK=1
  fi
}

check_high_issues() {
  # The operator-reported issues count lives in the SOFT_LAUNCH_BETA_2026.md
  # report under "Issues reported". Without an external tracker we read it
  # from a known location in the report file. Skip if file absent.
  local report
  report="$(cd "$(dirname "$0")/../.." && pwd)/docs/SOFT_LAUNCH_BETA_2026.md"
  if [ ! -f "$report" ]; then
    echo "⚪ HIGH issues count : report file not found"
    GATE_ISSUES_OK=2
    return
  fi
  local count
  count=$(grep -cE '^\| HIGH ' "$report" 2>/dev/null || echo 0)
  if [ "$count" -lt 3 ]; then
    echo "✅ HIGH-severity issues reported : $count / < 3"
    GATE_ISSUES_OK=0
  else
    echo "🔴 HIGH-severity issues reported : $count / < 3"
    GATE_ISSUES_OK=1
  fi
}

# ----------------------------------------------------------------------
# Main loop
# ----------------------------------------------------------------------

run_once() {
  if [ "$QUIET" != "1" ]; then
    echo "================================================================"
    echo "Acceptance gate check — $(date -u +'%Y-%m-%d %H:%M:%S UTC')"
    echo "----------------------------------------------------------------"
  fi

  check_testers
  check_sentry_p1
  check_statuspage
  check_synthetic
  check_k6_nightly
  check_high_issues

  if [ "$QUIET" != "1" ]; then
    echo "----------------------------------------------------------------"
  fi

  local red=0 unknown=0
  for v in "$GATE_TESTERS_OK" "$GATE_SENTRY_OK" "$GATE_STATUSPAGE_OK" \
           "$GATE_SYNTHETIC_OK" "$GATE_K6_OK" "$GATE_ISSUES_OK"; do
    case $v in
      1) red=$(( red + 1 )) ;;
      2) unknown=$(( unknown + 1 )) ;;
    esac
  done

  if [ "$red" -eq 0 ] && [ "$unknown" -eq 0 ]; then
    echo "VERDICT : ALL GATES GREEN — soft-launch is GO"
    return 0
  elif [ "$red" -gt 0 ]; then
    echo "VERDICT : $red gate(s) RED — NO-GO until resolved"
    return 1
  else
    echo "VERDICT : $unknown gate(s) UNCHECKABLE — operator must verify manually before decision call"
    return 2
  fi
}

if [ "$LOOP" != "1" ]; then
  run_once
  exit $?
fi

# Continuous mode.
while true; do
  run_once || true
  echo ""
  echo "next check in ${CHECK_INTERVAL}s — Ctrl-C to exit"
  sleep "$CHECK_INTERVAL"
done