#!/bin/bash
# update-cp-1.sh — controlled OS update for the k3s control-plane node.
#
# See ../CP1_UPDATE_PROCEDURE.md for the full design rationale.
#
# Usage:
#   update-cp-1.sh --dry-run           # print what would be done, touch nothing
#   update-cp-1.sh --add-swap          # Phase A only (idempotent, safe standalone)
#   update-cp-1.sh --preflight         # Phase B only
#   update-cp-1.sh --drain-stateful    # Phase C only  (cordon + batched sts moves)
#   update-cp-1.sh --apt               # Phase D only  (requires cp-1 fully drained)
#   update-cp-1.sh --reboot            # Phase E only  (requires --apt reported REBOOT_REQUIRED=yes)
#   update-cp-1.sh --finalize          # Phase F only  (uncordon + verify)
#   update-cp-1.sh --run               # all phases with a confirmation between each (or ASSUME_YES=1)
#
# Environment overrides:
#   CP1_HOST                     default 178.105.17.239
#   SWAP_SIZE_MB                 default 4096       (>=2048 required)
#   SWAP_PATH                    default /swapfile
#   DRAIN_TIMEOUT_SECONDS        default 600
#   REBOOT_MAX_WAIT_SECONDS      default 600
#   POST_UNCORDON_WAIT_SECONDS   default 180
#   STATEFUL_SETTLE_SECONDS      default 60         (pause between batched sts moves)
#   MIN_WORKER_MEM_MIB           default 500        (per-worker MemAvailable floor at preflight)
#   MIN_CP1_MEM_MIB              default 200        (cp-1 MemAvailable floor mid-drain)
#   MAX_KUBECTL_SECONDS          default 5          (kine-health guardrail)
#   SSH_OPTS                     default "-o ConnectTimeout=10 -o StrictHostKeyChecking=accept-new"
#   ASSUME_YES=1                 skip interactive confirmations in --run
#   DRY_RUN=1                    do not execute state-mutating commands; log-only
#
# Log directory contract (matches update-node.sh):
#   Every command's stdout+stderr is tee'd to /tmp/os-update-cp-1-<UTC-ts>.log on
#   the operator machine AND to /tmp/os-update-cp-1-<UTC-ts>.log on cp-1 (via the
#   ssh command wrappers). Attach both to the execution ticket at the end.
#
# NEVER touches k3s config, k3s services, containerd, or any manifest. Only
# fixes it will attempt: apt/dpkg recovery on cp-1 (see Phase D). Any other
# problem → escalate and STOP.

set -euo pipefail

# --------------------------------------------------------------------------- #
# Config
# --------------------------------------------------------------------------- #
CP1_HOST="${CP1_HOST:-178.105.17.239}"
SWAP_SIZE_MB="${SWAP_SIZE_MB:-4096}"
SWAP_PATH="${SWAP_PATH:-/swapfile}"
DRAIN_TIMEOUT_SECONDS="${DRAIN_TIMEOUT_SECONDS:-600}"
REBOOT_MAX_WAIT_SECONDS="${REBOOT_MAX_WAIT_SECONDS:-600}"
POST_UNCORDON_WAIT_SECONDS="${POST_UNCORDON_WAIT_SECONDS:-180}"
STATEFUL_SETTLE_SECONDS="${STATEFUL_SETTLE_SECONDS:-60}"
MIN_WORKER_MEM_MIB="${MIN_WORKER_MEM_MIB:-500}"
MIN_CP1_MEM_MIB="${MIN_CP1_MEM_MIB:-200}"
MAX_KUBECTL_SECONDS="${MAX_KUBECTL_SECONDS:-5}"
SSH_OPTS="${SSH_OPTS:--o ConnectTimeout=10 -o StrictHostKeyChecking=accept-new}"
DRY_RUN="${DRY_RUN:-0}"
ASSUME_YES="${ASSUME_YES:-0}"

NODE="k3s-cp-1"
TS="$(date -u +%Y%m%dT%H%M%SZ)"
LOG_LOCAL="/tmp/os-update-cp-1-${TS}.log"
LOG_REMOTE="/tmp/os-update-cp-1-${TS}.log"

SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
HEALTH_SCRIPT="$SCRIPT_DIR/cluster-health.sh"

# --------------------------------------------------------------------------- #
# Stateful eviction ledger — order matters (idle -> active, small -> heavy).
# --------------------------------------------------------------------------- #
# The list is derived live from the cluster in preflight and stored to
# /tmp/cp1-stateful-plan-<ts>.txt. This ORDER is the authoritative fallback.
STATEFUL_ORDER=(
  "harbor:harbor-redis-0"
  "nextcloud:nextcloud-redis-replicas-0"
  "harbor:harbor-database-0"
  "stalwart:stalwart-postgres-0"
  "stalwart:stalwart-0"
)

# --------------------------------------------------------------------------- #
# Logging + safe-run helpers
# --------------------------------------------------------------------------- #
log()  { echo "[$(date -u +%Y-%m-%dT%H:%M:%SZ)] $*" | tee -a "$LOG_LOCAL"; }
die()  { log "FATAL: $*"; exit 1; }
warn() { log "WARN:  $*"; }

# run/ssh_run/kubectl_run: honour DRY_RUN — print, do not execute state changes.
run() {
  if [ "$DRY_RUN" = "1" ]; then
    log "DRY-RUN would exec: $*"
    return 0
  fi
  log "exec: $*"
  "$@" 2>&1 | tee -a "$LOG_LOCAL"
}

ssh_run() {
  local target="root@${CP1_HOST}"
  if [ "$DRY_RUN" = "1" ]; then
    log "DRY-RUN would ssh $target: $*"
    return 0
  fi
  log "ssh $target: $*"
  ssh $SSH_OPTS "$target" "$@" 2>&1 | tee -a "$LOG_LOCAL"
}

# ssh_run_stdin: pipe a heredoc through bash -s on cp-1; used for multi-line remote
# blocks (swap add, apt).
ssh_run_stdin() {
  local target="root@${CP1_HOST}"
  if [ "$DRY_RUN" = "1" ]; then
    log "DRY-RUN would ssh $target with stdin script:"
    sed 's/^/    | /' | tee -a "$LOG_LOCAL"
    return 0
  fi
  log "ssh $target (heredoc)"
  ssh $SSH_OPTS "$target" "bash -s" 2>&1 | tee -a "$LOG_LOCAL"
}

confirm() {
  local prompt="$1"
  if [ "$ASSUME_YES" = "1" ]; then
    log "confirm SKIPPED (ASSUME_YES=1): $prompt"
    return 0
  fi
  echo -n "  >>> $prompt  Continue? [y/N] "
  read -r a
  case "$a" in y|Y|yes|YES) return 0 ;; *) die "aborted by operator" ;; esac
}

# --------------------------------------------------------------------------- #
# Phase A — Add swap on cp-1 (idempotent)
# --------------------------------------------------------------------------- #
phase_add_swap() {
  log "=== Phase A: add swap on $NODE ($SWAP_SIZE_MB MiB at $SWAP_PATH) ==="
  [ "$SWAP_SIZE_MB" -ge 2048 ] || die "SWAP_SIZE_MB=$SWAP_SIZE_MB below 2048 MiB guardrail"

  cat <<REMOTE | ssh_run_stdin
set -euo pipefail
SWAP_PATH="$SWAP_PATH"
SIZE_MB="$SWAP_SIZE_MB"

# Skip if a swapfile at this path is already active.
if swapon --show=NAME 2>/dev/null | grep -qx "\$SWAP_PATH"; then
  echo "swap already on at \$SWAP_PATH — skipping"
  free -h
  exit 0
fi

# Root filesystem free space check — abort if less than 2*swap free.
avail_mb=\$(df -m --output=avail / | tail -1 | tr -d ' ')
need_mb=\$(( SIZE_MB * 2 ))
if [ "\$avail_mb" -lt "\$need_mb" ]; then
  echo "ERROR: only \${avail_mb} MiB free on /, need \${need_mb} MiB (2x swap for safety)"
  exit 1
fi

# Create swapfile. fallocate is fast; dd is the fallback.
if ! fallocate -l "\${SIZE_MB}M" "\$SWAP_PATH" 2>/dev/null; then
  dd if=/dev/zero of="\$SWAP_PATH" bs=1M count="\$SIZE_MB" status=progress
fi
chmod 600 "\$SWAP_PATH"
mkswap "\$SWAP_PATH"
swapon "\$SWAP_PATH"

# Persist via fstab (dedup).
if ! grep -q "^\$SWAP_PATH " /etc/fstab; then
  echo "\$SWAP_PATH none swap sw 0 0" >> /etc/fstab
fi

# Moderate swappiness — swap as safety net, not aggressive paging.
sysctl -w vm.swappiness=10
if [ ! -f /etc/sysctl.d/99-k3s-swap.conf ] || ! grep -q '^vm.swappiness' /etc/sysctl.d/99-k3s-swap.conf; then
  echo 'vm.swappiness=10' > /etc/sysctl.d/99-k3s-swap.conf
fi

echo "--- swap after ---"
free -h
swapon --show
sysctl vm.swappiness
REMOTE

  # Verify from operator view.
  if [ "$DRY_RUN" != "1" ]; then
    log "verifying kubelet still Ready after swap add"
    local ready
    ready=$(kubectl get node "$NODE" -o jsonpath='{.status.conditions[?(@.type=="Ready")].status}')
    [ "$ready" = "True" ] || die "kubelet on $NODE not Ready after swap add — halt"
    log "kubelet Ready=True — Phase A complete"
  fi
}

# --------------------------------------------------------------------------- #
# Guardrail probes
# --------------------------------------------------------------------------- #
kubectl_latency_s() {
  # returns integer seconds elapsed for `kubectl get nodes >/dev/null`.
  local start end
  start=$(date +%s)
  kubectl get nodes >/dev/null 2>&1 || echo "kubectl-error" >&2
  end=$(date +%s)
  echo $(( end - start ))
}

cp1_mem_available_mib() {
  # returns integer MiB `MemAvailable` on cp-1.
  ssh $SSH_OPTS "root@$CP1_HOST" "awk '/^MemAvailable:/{printf \"%d\n\", \$2/1024}' /proc/meminfo" 2>/dev/null || echo 0
}

guard_kine_healthy() {
  local s
  s=$(kubectl_latency_s)
  if [ "$s" -gt "$MAX_KUBECTL_SECONDS" ]; then
    die "kubectl get nodes took ${s}s (>${MAX_KUBECTL_SECONDS}s) — kine cascade risk, HALT"
  fi
  log "  kine ok: kubectl get nodes took ${s}s"
}

guard_cp1_memory() {
  local m
  m=$(cp1_mem_available_mib)
  if [ "$m" -lt "$MIN_CP1_MEM_MIB" ]; then
    die "cp-1 MemAvailable=${m} MiB below ${MIN_CP1_MEM_MIB} MiB floor — HALT"
  fi
  log "  cp-1 mem ok: MemAvailable=${m} MiB"
}

# --------------------------------------------------------------------------- #
# Phase B — Preflight
# --------------------------------------------------------------------------- #
phase_preflight() {
  log "=== Phase B: preflight ==="

  log "-- cluster health"
  if [ "$DRY_RUN" != "1" ]; then
    if ! RETRY_ON_TRANSIENT=1 "$HEALTH_SCRIPT" 2>&1 | tee -a "$LOG_LOCAL"; then
      die "cluster is not healthy — refuse to start cp-1 update"
    fi
  else
    log "DRY-RUN would run: $HEALTH_SCRIPT"
  fi

  log "-- swap on cp-1"
  if [ "$DRY_RUN" != "1" ]; then
    local swap_total
    swap_total=$(ssh $SSH_OPTS "root@$CP1_HOST" "awk '/^SwapTotal:/{print \$2}' /proc/meminfo")
    [ "${swap_total:-0}" -ge $((2 * 1024 * 1024)) ] \
      || die "cp-1 SwapTotal=${swap_total} KiB below 2 GiB — run --add-swap first"
    log "  cp-1 SwapTotal=$(( swap_total / 1024 )) MiB"
  fi

  log "-- fsn1 workers Ready and have >=${MIN_WORKER_MEM_MIB} MiB MemAvailable"
  # Worker private IPs (worker-4 nbg1 excluded — cannot host fsn1 RWO PVs).
  local ips=("10.42.1.2" "10.42.1.3" "10.42.1.5" "10.42.1.7")
  local names=("k3s-worker-1" "k3s-worker-2" "k3s-worker-3" "k3s-worker-5")
  if [ "$DRY_RUN" != "1" ]; then
    for i in "${!ips[@]}"; do
      local nm="${names[$i]}"
      local ip="${ips[$i]}"
      local ready
      ready=$(kubectl get node "$nm" -o jsonpath='{.status.conditions[?(@.type=="Ready")].status}' 2>/dev/null || echo Unknown)
      [ "$ready" = "True" ] || die "worker $nm not Ready (Ready=$ready)"
      local mem
      mem=$(ssh $SSH_OPTS -J "root@$CP1_HOST" "root@$ip" \
        "awk '/^MemAvailable:/{printf \"%d\n\", \$2/1024}' /proc/meminfo" 2>/dev/null || echo 0)
      [ "$mem" -ge "$MIN_WORKER_MEM_MIB" ] \
        || die "worker $nm MemAvailable=${mem} MiB below ${MIN_WORKER_MEM_MIB} MiB — HALT"
      log "  $nm ok: MemAvailable=${mem} MiB"
    done
  fi

  log "-- kine latency probe"
  if [ "$DRY_RUN" != "1" ]; then guard_kine_healthy; fi

  log "-- k3s SQLite datastore snapshot"
  # k3s etcd-snapshot in embedded-SQLite mode copies the sqlite file to
  # /var/lib/rancher/k3s/server/db/snapshots/.
  ssh_run "k3s etcd-snapshot save --name pre-cp1-os-update-${TS}"
  ssh_run "ls -la /var/lib/rancher/k3s/server/db/snapshots/ | tail -10"

  log "-- persist eviction plan"
  if [ "$DRY_RUN" != "1" ]; then
    local plan="/tmp/cp1-stateful-plan-${TS}.txt"
    ssh $SSH_OPTS "root@$CP1_HOST" "cat > $plan" <<EOF
# cp-1 stateful eviction plan generated at $TS
# Order: idle -> active, small -> heavy. Do NOT reorder without design review.
$(for e in "${STATEFUL_ORDER[@]}"; do echo "$e"; done)
EOF
    log "  wrote $plan on cp-1"
  else
    log "DRY-RUN would write /tmp/cp1-stateful-plan-${TS}.txt with STATEFUL_ORDER"
  fi

  log "=== Phase B: preflight OK ==="
}

# --------------------------------------------------------------------------- #
# Phase C — Cordon + move stateful pods off cp-1, one at a time
# --------------------------------------------------------------------------- #
phase_drain_stateful() {
  log "=== Phase C: cordon + batched stateful move ==="

  log "-- cordon $NODE (prevents rescheduled pods from landing back on cp-1)"
  run kubectl cordon "$NODE"

  local i=0
  for entry in "${STATEFUL_ORDER[@]}"; do
    i=$((i + 1))
    local ns="${entry%%:*}"
    local pod="${entry##*:}"

    log "--- [${i}/${#STATEFUL_ORDER[@]}] moving $ns/$pod"

    # Confirm the pod actually IS on cp-1 before touching it.
    if [ "$DRY_RUN" != "1" ]; then
      local on
      on=$(kubectl -n "$ns" get pod "$pod" -o jsonpath='{.spec.nodeName}' 2>/dev/null || echo "")
      if [ -z "$on" ]; then
        log "  $ns/$pod not found — sts may have changed; skipping"
        continue
      fi
      if [ "$on" != "$NODE" ]; then
        log "  $ns/$pod already on $on (not cp-1) — skipping"
        continue
      fi
    fi

    # Delete the pod. StatefulSet controller will re-create it; scheduler will
    # pick a fsn1 worker because cp-1 is cordoned and worker-4 is nbg1.
    run kubectl -n "$ns" delete pod "$pod" --wait=false

    if [ "$DRY_RUN" = "1" ]; then
      log "  DRY-RUN skipping wait-for-ready"
      continue
    fi

    log "  waiting for $ns/$pod to be Ready on a non-cp-1 node (max 300s)"
    local deadline=$(( $(date +%s) + 300 ))
    local new_node="" ready=""
    while [ $(date +%s) -lt $deadline ]; do
      new_node=$(kubectl -n "$ns" get pod "$pod" -o jsonpath='{.spec.nodeName}' 2>/dev/null || echo "")
      ready=$(kubectl -n "$ns" get pod "$pod" -o jsonpath='{.status.conditions[?(@.type=="Ready")].status}' 2>/dev/null || echo "")
      if [ -n "$new_node" ] && [ "$new_node" != "$NODE" ] && [ "$ready" = "True" ]; then
        log "  $ns/$pod -> $new_node OK"
        break
      fi
      sleep 5
    done
    [ "$ready" = "True" ] && [ "$new_node" != "$NODE" ] \
      || die "$ns/$pod did not reach Ready on a non-cp-1 node in 300s — HALT (leave cp-1 cordoned)"

    log "  guardrails after $ns/$pod"
    guard_kine_healthy
    guard_cp1_memory

    if [ "$i" -lt "${#STATEFUL_ORDER[@]}" ]; then
      log "  settle pause ${STATEFUL_SETTLE_SECONDS}s"
      sleep "$STATEFUL_SETTLE_SECONDS"
    fi
  done

  log "=== Phase C: all stateful pods evicted from cp-1 ==="
}

# --------------------------------------------------------------------------- #
# Phase D — Drain remaining pods + apt on cp-1
# --------------------------------------------------------------------------- #
phase_apt() {
  log "=== Phase D: drain (remaining deployments) + apt on $NODE ==="

  # Guardrail: refuse to run if any StatefulSet pod is still on cp-1.
  if [ "$DRY_RUN" != "1" ]; then
    local sts_on_cp1
    sts_on_cp1=$(kubectl get pods -A -o json --field-selector spec.nodeName=$NODE \
      | jq -r '.items[] | select(.metadata.ownerReferences[0].kind=="StatefulSet") | "\(.metadata.namespace)/\(.metadata.name)"' \
      | wc -l)
    [ "$sts_on_cp1" -eq 0 ] \
      || die "$sts_on_cp1 StatefulSet pod(s) still on cp-1 — Phase C incomplete; refuse Phase D"
  fi

  log "-- drain (timeout ${DRAIN_TIMEOUT_SECONDS}s)"
  set +e
  if [ "$DRY_RUN" = "1" ]; then
    log "DRY-RUN would run: kubectl drain $NODE --ignore-daemonsets --delete-emptydir-data --timeout=${DRAIN_TIMEOUT_SECONDS}s"
    local rc=0
  else
    kubectl drain "$NODE" \
      --ignore-daemonsets \
      --delete-emptydir-data \
      --timeout="${DRAIN_TIMEOUT_SECONDS}s" 2>&1 | tee -a "$LOG_LOCAL"
    local rc=${PIPESTATUS[0]}
  fi
  set -e

  if [ "$rc" -ne 0 ]; then
    log "drain FAILED (rc=$rc). Never force. Uncordoning."
    run kubectl uncordon "$NODE"
    die "drain failed on $NODE — investigate PDB / orphan pods; do NOT proceed"
  fi

  log "-- apt on cp-1"
  cat <<'REMOTE' | ssh_run_stdin
set -euo pipefail
export DEBIAN_FRONTEND=noninteractive
APT_OPTS='-y -o Dpkg::Options::=--force-confdef -o Dpkg::Options::=--force-confold'

# Rollback references (Phase-A didn't need this, but Phase D does).
uname -r > /root/pre-apt-kernel
dpkg-query -W -f='${Package}\t${Version}\n' > /root/pre-apt-packages.tsv
echo "pre-apt kernel: $(cat /root/pre-apt-kernel)"

# Recover from any half-finished dpkg state before touching apt.
if dpkg --audit | grep -qE .; then
  echo "dpkg audit reported issues, running dpkg --configure -a"
  dpkg --configure -a || true
fi

apt-get update

if ! apt-get $APT_OPTS upgrade; then
  echo "upgrade failed, attempting apt-get -f install"
  apt-get $APT_OPTS -f install
  apt-get $APT_OPTS upgrade
fi

apt-get $APT_OPTS dist-upgrade
apt-get $APT_OPTS autoremove --purge
apt-get clean

if [ -f /var/run/reboot-required ]; then
  echo "REBOOT_REQUIRED=yes"
  echo "REBOOT_REASON<<EOF"
  cat /var/run/reboot-required.pkgs 2>/dev/null || echo "(no package list)"
  echo "EOF"
else
  echo "REBOOT_REQUIRED=no"
fi
REMOTE

  log "=== Phase D: apt complete (check REBOOT_REQUIRED in the log) ==="
}

# --------------------------------------------------------------------------- #
# Phase E — Reboot cp-1 and wait for api-server /livez
# --------------------------------------------------------------------------- #
phase_reboot() {
  log "=== Phase E: reboot $NODE ==="

  # Tell cp-1 to reboot. The ssh command will hang up mid-command — that's fine.
  if [ "$DRY_RUN" != "1" ]; then
    log "issuing 'systemctl reboot' on $NODE (ssh will drop; expected)"
    ssh $SSH_OPTS "root@$CP1_HOST" 'systemctl reboot' 2>&1 | tee -a "$LOG_LOCAL" || true
    log "waiting 15s for ssh to fully drop before polling api-server"
    sleep 15
  else
    log "DRY-RUN would ssh root@$CP1_HOST 'systemctl reboot'"
  fi

  log "-- poll api-server /livez (timeout ${REBOOT_MAX_WAIT_SECONDS}s)"
  if [ "$DRY_RUN" != "1" ]; then
    local deadline=$(( $(date +%s) + REBOOT_MAX_WAIT_SECONDS ))
    local code=000
    while [ $(date +%s) -lt $deadline ]; do
      code=$(curl -sk -o /dev/null -w '%{http_code}' "https://$CP1_HOST:6443/livez" 2>/dev/null || echo 000)
      if [ "$code" = "200" ]; then
        log "  api-server /livez=200 (elapsed $(( REBOOT_MAX_WAIT_SECONDS - (deadline - $(date +%s)) ))s)"
        break
      fi
      sleep 5
    done
    [ "$code" = "200" ] || die "api-server did not return within ${REBOOT_MAX_WAIT_SECONDS}s — escalate; check 'hcloud server describe k3s-cp-1' and Hetzner console"
  fi

  log "-- wait for kubelet Ready on $NODE (max 300s)"
  if [ "$DRY_RUN" != "1" ]; then
    local deadline=$(( $(date +%s) + 300 ))
    local ready=Unknown
    while [ $(date +%s) -lt $deadline ]; do
      ready=$(kubectl get node "$NODE" -o jsonpath='{.status.conditions[?(@.type=="Ready")].status}' 2>/dev/null || echo Unknown)
      [ "$ready" = "True" ] && break
      sleep 5
    done
    [ "$ready" = "True" ] || die "kubelet on $NODE never returned Ready — escalate (do NOT change k3s config)"
    log "  kubelet Ready=True"
  fi

  log "=== Phase E: cp-1 is back ==="
}

# --------------------------------------------------------------------------- #
# Phase F — Uncordon + verify + finalize
# --------------------------------------------------------------------------- #
phase_finalize() {
  log "=== Phase F: uncordon + verify ==="

  run kubectl uncordon "$NODE"

  log "-- settle wait ${POST_UNCORDON_WAIT_SECONDS}s"
  [ "$DRY_RUN" = "1" ] || sleep "$POST_UNCORDON_WAIT_SECONDS"

  log "-- cluster health"
  if [ "$DRY_RUN" != "1" ]; then
    if ! RETRY_ON_TRANSIENT=1 "$HEALTH_SCRIPT" 2>&1 | tee -a "$LOG_LOCAL"; then
      die "cluster health failed after cp-1 update — escalate, do NOT touch k3s"
    fi
  fi

  log "-- apt history summary (audit)"
  ssh_run 'zgrep -h "Commandline\|Install\|Upgrade\|Remove" /var/log/apt/history.log* 2>/dev/null | tail -60'

  log "-- old snapshots (>30d) — listing only, review manually"
  ssh_run 'find /var/lib/rancher/k3s/server/db/snapshots/ -type f -mtime +30 -name "pre-*" -print 2>/dev/null || true'

  log "=== cp-1 OS update complete — attach $LOG_LOCAL to the execution ticket ==="
}

# --------------------------------------------------------------------------- #
# --run — orchestrate all phases with confirmations
# --------------------------------------------------------------------------- #
phase_run_all() {
  log "=== full cp-1 update run (log: $LOG_LOCAL) ==="

  confirm "Phase A (add swap) — proceed?"
  phase_add_swap

  confirm "Phase B (preflight) — proceed?"
  phase_preflight

  confirm "Phase C (cordon + batched stateful move) — proceed?"
  phase_drain_stateful

  confirm "Phase D (drain remaining + apt) — proceed?"
  phase_apt

  confirm "Phase E (reboot cp-1; api-server unavailable ~90-180s) — proceed?"
  phase_reboot

  confirm "Phase F (uncordon + verify) — proceed?"
  phase_finalize

  log "=== FULL RUN COMPLETE ==="
}

# --------------------------------------------------------------------------- #
# Arg parse
# --------------------------------------------------------------------------- #
usage() { grep -E '^# ' "$0" | sed 's/^# \{0,1\}//'; exit 2; }

[ $# -ge 1 ] || usage

# Init the local log file up front so tee always has a target.
: > "$LOG_LOCAL"
log "update-cp-1.sh started (DRY_RUN=$DRY_RUN)"
log "log file: $LOG_LOCAL"

case "$1" in
  --dry-run)
    DRY_RUN=1
    export DRY_RUN
    log "DRY_RUN=1 — walking Phases A..F without touching state"
    phase_add_swap
    phase_preflight
    phase_drain_stateful
    phase_apt
    phase_reboot
    phase_finalize
    ;;
  --add-swap)       phase_add_swap ;;
  --preflight)      phase_preflight ;;
  --drain-stateful) phase_drain_stateful ;;
  --apt)            phase_apt ;;
  --reboot)         phase_reboot ;;
  --finalize)       phase_finalize ;;
  --run)            phase_run_all ;;
  -h|--help)        usage ;;
  *)                echo "unknown arg: $1" >&2; usage ;;
esac