#!/usr/bin/env bash
# install_phase.sh — multi-agent-mux-update, the part that changes the tree (Issue #72, decision 5).
#
#   install_phase.sh run <workspace> <monitor_was_running 0|1> <tmpdir>
#   install_phase.sh restore <workspace> [--skip-registry]
#
# update.sh copies this file outside the workspace and execs the copy (same
# pid and start time, so its .mam/update-in-progress marker stays live). From
# here on the tree is being replaced, so this calls no lib.sh or lib_py: it runs
# the installer in place, and on failure restores .mam/update-backup/ and starts
# the monitor again with the restored (old, whole) tree's start_watchdog. On
# success phase 2 is the NEW tree's post_update.sh, in a child process. It ends
# by removing the backup and the marker (only its own: pid + lstart).
# Must run on macOS bash 3.2.
set -uo pipefail

MODE="${1:-}"
WS="${2:-}"
[ -n "$MODE" ] && [ -d "$WS" ] || { echo "usage: $0 run|restore <workspace> ..." >&2; exit 2; }
BK="$WS/.mam/update-backup"

set_state() { printf '%s\n' "$1" > "$BK/state.tmp" && mv -f "$BK/state.tmp" "$BK/state"; }

# Puts back every backed-up item, removes the ones that did not exist before,
# then (unless --skip-registry) the registry: the DB from the backup, its
# -wal/-shm removed (macOS keeps them after close).
restore() {
  local rel n
  [ -f "$BK/items" ] || { echo "ERROR: $BK/items is missing" >&2; return 1; }
  while IFS= read -r rel; do
    [ -n "$rel" ] || continue
    rm -rf "${WS:?}/$rel" || return 1
    grep -Fqx -- "$rel" "$BK/absent" 2>/dev/null && continue
    mkdir -p "$(dirname "$WS/$rel")" && cp -pPR "$BK/files/$rel" "$WS/$rel" || return 1
  done < "$BK/items"
  [ "${1:-}" = "--skip-registry" ] && return 0
  for n in agent-sessions.yaml agent-sessions.yaml.bak agent-sessions.db; do
    rm -f "$WS/.mam/$n" || return 1
    if [ -f "$BK/registry/$n" ]; then
      cp -p "$BK/registry/$n" "$WS/.mam/$n" || return 1
    fi
  done
  rm -f "$WS/.mam/agent-sessions.db-wal" "$WS/.mam/agent-sessions.db-shm"
}

release_marker() {
  local m="$WS/.mam/update-in-progress" pid lstart cur
  [ -f "$m" ] || return 0
  pid="$(grep '^pid=' "$m" | head -n 1 | cut -d= -f2-)"
  lstart="$(grep '^lstart=' "$m" | head -n 1 | cut -d= -f2-)"
  cur="$(ps -p $$ -o lstart= 2>/dev/null | tr -s ' ' | sed 's/^ *//;s/ *$//')"
  if [ "$pid" = "$$" ] && [ "$lstart" = "$cur" ]; then
    rm -f "$m"
  fi
}

restart_old_monitor() {
  [ "$1" = "1" ] || return 0
  if [ "${MAM_NO_SUBSCRIBER_DAEMON:-0}" = "1" ]; then
    echo "monitor: not restarted (MAM_NO_SUBSCRIBER_DAEMON=1)"
    return 0
  fi
  local pid
  if pid="$(bash -c 'source "$1/.agents/skills/lib.sh" && start_watchdog update "$1"' _ "$WS")"; then
    echo "monitor: restarted (PID $pid)"
  else
    echo "ERROR: could not restart the monitor daemon" >&2
  fi
}

case "$MODE" in
  restore)
    restore "${3:-}"
    exit $?
    ;;
  run) ;;
  *) echo "usage: $0 run|restore <workspace> ..." >&2; exit 2 ;;
esac

MON="${3:-0}"
TMPD="${4:-}"
trap '[ -z "$TMPD" ] || rm -rf "$TMPD"' EXIT

set_state installing || { echo "ERROR: cannot write $BK/state" >&2; release_marker; exit 1; }
URL="${MAM_INSTALLER_URL:-https://git.godopu.com/tmpl/multi-agent-mux/raw/branch/main/deploy/install.sh}"
echo "install: $URL"
irc=0
if command -v curl >/dev/null 2>&1; then
  curl -fsSL "$URL" | bash -s -- "$WS" || irc=$?
elif command -v wget >/dev/null 2>&1; then
  wget -qO- "$URL" | bash -s -- "$WS" || irc=$?
else
  echo "ERROR: neither curl nor wget is available to fetch the installer" >&2
  irc=1
fi

if [ "$irc" -ne 0 ]; then
  echo "ERROR: the install failed (rc $irc); rolling back" >&2
  if restore; then
    rm -rf "$BK"
    echo "rolled back: the workspace is at the version it had before the update"
    restart_old_monitor "$MON"
  else
    echo "ERROR: the rollback failed; the backup is kept at $BK (the next update restores it)" >&2
  fi
  release_marker
  exit 1
fi
set_state installed

POST="$WS/.agents/skills/multi-agent-mux-update/scripts/post_update.sh"
prc=0
if [ -f "$POST" ]; then
  bash "$POST" --monitor "$MON" || prc=$?
else
  echo "ERROR: the installed version has no $POST; the registry converts on its next write and the monitor was not restarted" >&2
  prc=1
fi
rm -rf "$BK"
release_marker
[ "$prc" -eq 0 ] && echo "Update complete."
exit "$prc"