#!/usr/bin/env bash
# game-day-driver.sh — orchestrate the W5 Day 22 game-day exercise.
#
# Walks the 5 failure scenarios in sequence, captures stdout/stderr +
# exit code per scenario, writes a session report under
# docs/runbooks/game-days/<DATE>-game-day-driver.log, and prints a
# summary table at the end.
#
# v1.0.9 W5 Day 22.
#
# Scenarios (mapped to existing smoke tests) :
#   A : test_pg_failover.sh         — kill Postgres primary, RTO < 60s
#   B : test_backend_failover.sh    — kill backend-api 1, HAProxy bascule
#   C : test_redis_failover.sh      — kill Redis master, Sentinel promote
#   D : test_minio_resilience.sh    — kill 2 MinIO nodes, EC:2 reconstructs
#   E : test_rabbitmq_outage.sh     — stop RabbitMQ 60s, backend stays up
#
# Usage :
#   bash scripts/security/game-day-driver.sh                                 # all scenarios on staging (default)
#   SKIP=DE bash scripts/security/game-day-driver.sh                         # skip D + E
#   ONLY=A bash scripts/security/game-day-driver.sh                          # only A
#   INVENTORY=prod CONFIRM_PROD=1 bash scripts/security/game-day-driver.sh   # prod (gated)
#
# Required env (passed through to the underlying smoke tests) :
#   REDIS_PASS / SENTINEL_PASS for scenario C
#   MINIO_ROOT_USER / MINIO_ROOT_PASSWORD for scenario D
#
# v1.0.10 polish — production gating :
#   INVENTORY=prod must be paired with CONFIRM_PROD=1 or the script
#   refuses to run, so a stale shell-history line can't accidentally
#   kill prod Postgres on a Monday morning. The driver also runs a
#   backup-freshness pre-flight when targeting prod (most recent
#   pgBackRest backup must be < 24 h old).
#
# Exit codes :
#   0  — every selected scenario passed
#   1  — at least one scenario failed
#   2  — runner pre-flight failed (script missing, prod safety guard tripped, stale backup, etc.)
set -euo pipefail

REPO_ROOT="$(cd "$(dirname "$0")/../.." && pwd)"
TESTS_DIR="$REPO_ROOT/infra/ansible/tests"
LOGS_DIR="$REPO_ROOT/docs/runbooks/game-days"
SESSION_DATE="$(date +%Y-%m-%d-%H%M)"
SESSION_LOG="$LOGS_DIR/$SESSION_DATE-game-day-driver.log"

mkdir -p "$LOGS_DIR"
: > "$SESSION_LOG"

ONLY=${ONLY:-}
SKIP=${SKIP:-}
INVENTORY=${INVENTORY:-staging}
CONFIRM_PROD=${CONFIRM_PROD:-0}
SKIP_BACKUP_FRESHNESS=${SKIP_BACKUP_FRESHNESS:-0}

log()  { printf '[%s] %s\n' "$(date +%H:%M:%S)" "$*" | tee -a "$SESSION_LOG" >&2; }
fail() { log "FAIL: $*"; exit "${2:-2}"; }

declare -A SCENARIO_SCRIPT=(
  [A]="$TESTS_DIR/test_pg_failover.sh"
  [B]="$TESTS_DIR/test_backend_failover.sh"
  [C]="$TESTS_DIR/test_redis_failover.sh"
  [D]="$TESTS_DIR/test_minio_resilience.sh"
  [E]="$TESTS_DIR/test_rabbitmq_outage.sh"
)
declare -A SCENARIO_DESC=(
  [A]="Postgres primary failover RTO < 60s"
  [B]="HAProxy backend-api 1 fail-over"
  [C]="Redis Sentinel master promotion"
  [D]="MinIO 2-node loss EC:2 reconstruction"
  [E]="RabbitMQ outage backend stays up"
)
SCENARIOS=(A B C D E)

want() {
  local s=$1
  if [ -n "$ONLY" ] && [[ "$ONLY" != *"$s"* ]]; then return 1; fi
  if [ -n "$SKIP" ] && [[ "$SKIP" == *"$s"* ]]; then return 1; fi
  return 0
}

# v1.0.10 polish — prod safety gate. INVENTORY=prod requires
# CONFIRM_PROD=1 + an interactive type-the-word confirm. Anything else
# defaults to staging so a forgotten env-var doesn't matter.
case "$INVENTORY" in
  staging|stg|dev|local) ;;
  prod|production)
    if [ "$CONFIRM_PROD" != "1" ]; then
      cat >&2 <<EOF

================================================================
ABORTING — INVENTORY=prod without CONFIRM_PROD=1
================================================================

This script will kill production services. Each scenario triggers a
real outage in the chosen inventory : Postgres primary kill, HAProxy
backend stop, Redis master kill, MinIO node loss, RabbitMQ stop.

To run on production, you must :

  1. Announce a maintenance window 24 h ahead (status page +
     #engineering channel).
  2. Set PagerDuty to maintenance mode for the affected services.
  3. Confirm pgBackRest's last backup is < 24 h old (this script
     auto-checks if you don't pass SKIP_BACKUP_FRESHNESS=1).
  4. Re-invoke with :

       INVENTORY=prod CONFIRM_PROD=1 \\
         bash scripts/security/game-day-driver.sh

The driver will then ask for one more interactive confirmation
(type the word KILL-PROD) before the first scenario fires.
================================================================
EOF
      exit 2
    fi

    # Backup-freshness pre-flight : refuse to run if the most recent
    # pgBackRest full/diff is > 24 h old. Recovery from a stale backup
    # can extend an outage from minutes to hours, so the cost of
    # postponing the game day is much less than the cost of compounded
    # data loss if scenario A fails to recover and we have to restore
    # from yesterday-but-one.
    if [ "$SKIP_BACKUP_FRESHNESS" != "1" ]; then
      if command -v pgbackrest >/dev/null 2>&1; then
        last_backup_ts=$(pgbackrest --stanza=veza info --output=json 2>/dev/null \
          | python3 -c "
import json, sys
try:
    data = json.load(sys.stdin)
    backups = data[0]['backup'] if data else []
    if not backups: print(0); sys.exit(0)
    print(max(b['timestamp']['stop'] for b in backups))
except Exception:
    print(0)
" 2>/dev/null || echo 0)
        now_ts=$(date +%s)
        age_seconds=$(( now_ts - last_backup_ts ))
        if [ "$last_backup_ts" -eq 0 ]; then
          fail "pgBackRest backup-freshness check failed : could not parse 'pgbackrest info'. Set SKIP_BACKUP_FRESHNESS=1 to override (only after manually verifying a recent backup exists)." 2
        fi
        if [ "$age_seconds" -gt 86400 ]; then
          age_hours=$(( age_seconds / 3600 ))
          fail "pgBackRest most recent backup is ${age_hours}h old (threshold 24h). Run a backup before the game day, or set SKIP_BACKUP_FRESHNESS=1 if you've validated freshness another way." 2
        fi
        log "pre-flight : pgBackRest most recent backup is $(( age_seconds / 3600 ))h $(( (age_seconds % 3600) / 60 ))m old (< 24h threshold) — OK"
      else
        log "WARN : pgbackrest CLI not on \$PATH ; skipping backup-freshness check. Set SKIP_BACKUP_FRESHNESS=1 to silence this warning if intentional."
      fi
    fi

    # Final type-the-word confirm. Everything above can be set in env
    # by mistake ; this last step requires a human at the keyboard.
    cat >&2 <<EOF

================================================================
PROD GAME DAY — final confirmation
================================================================

  inventory : prod
  scenarios : ${SCENARIOS[*]}${ONLY:+   (filtered by ONLY=$ONLY)}${SKIP:+   (filtered by SKIP=$SKIP)}
  session   : $SESSION_LOG

Each scenario triggers a real outage. Type the literal phrase
KILL-PROD (any other input aborts) to proceed :
EOF
    read -r confirm_phrase
    if [ "$confirm_phrase" != "KILL-PROD" ]; then
      fail "operator did not confirm KILL-PROD ($confirm_phrase) — aborting" 2
    fi
    ;;
  *)
    fail "INVENTORY=$INVENTORY not recognised — must be one of staging|prod" 2
    ;;
esac

# Pre-flight : every selected scenario script must exist + be executable.
for s in "${SCENARIOS[@]}"; do
  if want "$s"; then
    script="${SCENARIO_SCRIPT[$s]}"
    if [ ! -x "$script" ]; then
      fail "scenario $s : script $script not found or not executable" 2
    fi
  fi
done

declare -A SCENARIO_RESULT
declare -A SCENARIO_DURATION

log "================================================================"
log "Game day session : $SESSION_DATE"
log "Inventory        : $INVENTORY"
log "Session log      : $SESSION_LOG"
log "Scenarios run    : ${SCENARIOS[*]}"
[ -n "$ONLY" ] && log "ONLY filter      : $ONLY"
[ -n "$SKIP" ] && log "SKIP filter      : $SKIP"
log "================================================================"

for s in "${SCENARIOS[@]}"; do
  if ! want "$s"; then
    SCENARIO_RESULT[$s]="SKIPPED"
    SCENARIO_DURATION[$s]="-"
    continue
  fi

  log ""
  log "── scenario $s : ${SCENARIO_DESC[$s]} ──────────────────────────"
  t0=$(date +%s)
  set +e
  "${SCENARIO_SCRIPT[$s]}" 2>&1 | tee -a "$SESSION_LOG"
  rc=${PIPESTATUS[0]}
  set -e
  elapsed=$(( $(date +%s) - t0 ))
  SCENARIO_DURATION[$s]="${elapsed}s"
  if [ "$rc" -eq 0 ]; then
    SCENARIO_RESULT[$s]="PASS"
    log "scenario $s : PASS in ${elapsed}s"
  else
    SCENARIO_RESULT[$s]="FAIL (exit $rc)"
    log "scenario $s : FAIL (exit $rc) after ${elapsed}s"
  fi
done

log ""
log "================================================================"
log "Session summary"
log "----------------------------------------------------------------"
printf '%-3s | %-12s | %-8s | %s\n' "ID" "result" "duration" "scenario" | tee -a "$SESSION_LOG" >&2
printf '%-3s-+-%-12s-+-%-8s-+-%s\n' "---" "------------" "--------" "$(printf '%.0s-' {1..50})" | tee -a "$SESSION_LOG" >&2
overall=0
for s in "${SCENARIOS[@]}"; do
  result=${SCENARIO_RESULT[$s]}
  duration=${SCENARIO_DURATION[$s]}
  printf '%-3s | %-12s | %-8s | %s\n' "$s" "$result" "$duration" "${SCENARIO_DESC[$s]}" \
    | tee -a "$SESSION_LOG" >&2
  if [[ "$result" == "FAIL"* ]]; then overall=1; fi
done
log "================================================================"
log ""
log "Operator next steps :"
log "  1. Open the runbook template :"
log "       docs/runbooks/game-days/$SESSION_DATE.md"
log "     (copy from docs/runbooks/game-days/TEMPLATE.md if missing)"
log "  2. For each scenario, fill : timestamp, action, observation,"
log "     runbook used, gap discovered."
log "  3. File one PR per gap that needs a code or runbook fix."
log ""

if [ "$overall" -eq 0 ]; then
  log "PASS : every selected scenario passed."
else
  log "FAIL : at least one scenario failed — review $SESSION_LOG."
fi

exit "$overall"