platform/scripts/setup/officer-setup.sh

#!/bin/bash
set -e

# =============================================================================
# officer-setup — the platform, on a machine that is already provisioned
#
# The second half of the install. machine-setup/ brings a blank box up to a
# usable machine; this puts Officer on top of it.
#
# Run as root:  sudo scripts/setup/officer-setup.sh
# =============================================================================

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
PROGRESS_FILE="$SCRIPT_DIR/officer-setup/.setup-progress"

ONLY_STEP=""
while [[ $# -gt 0 ]]; do
  case "$1" in
    --only)
      ONLY_STEP="${2:-}"
      shift 2
      ;;
    --only=*)
      ONLY_STEP="${1#*=}"
      shift
      ;;
    -l | --list)
      grep -oP '^step "\K[^"]+' "${BASH_SOURCE[0]}"
      exit 0
      ;;
    -h | --help)
      echo "usage: officer-setup.sh [--only <step>] [--list]"
      exit 0
      ;;
    *) echo "unknown option: $1" >&2 && exit 2 ;;
  esac
done

# shellcheck source=officer-setup/lib/base.sh
source "$SCRIPT_DIR/officer-setup/lib/base.sh"
# shellcheck source=officer-setup/lib/preflight.sh
source "$SCRIPT_DIR/officer-setup/lib/preflight.sh"
# shellcheck source=officer-setup/lib/repo.sh
source "$SCRIPT_DIR/officer-setup/lib/repo.sh"
# shellcheck source=officer-setup/lib/layout.sh
source "$SCRIPT_DIR/officer-setup/lib/layout.sh"

trap 'echo ""; echo -e "${RED}╔══════════════════════════════════════════════════╗${NC}"; echo -e "${RED}║  OFFICER SETUP FAILED${NC}"; echo -e "${RED}║  Step: ${CURRENT_STEP:-unknown}${NC}"; echo -e "${RED}║  Line: $LINENO${NC}"; echo -e "${RED}║  Command: $BASH_COMMAND${NC}"; echo -e "${RED}╚══════════════════════════════════════════════════╝${NC}"' ERR

# =============================================================================
# 1. Pre-flight
# =============================================================================

echo ""
echo -e "${BOLD}╔══════════════════════════════════════════════════╗${NC}"
echo -e "${BOLD}║          Officer Setup                           ║${NC}"
echo -e "${BOLD}╚══════════════════════════════════════════════════╝${NC}"

if [[ "$EUID" -ne 0 ]]; then
  fail "Please run as root: sudo ./officer-setup.sh"
fi

# ── what machine-setup already established ──
echo ""
if load_machine_answers; then
  info "Read from machine-setup: ${MACHINE_ANSWERS}"
else
  warn "machine-setup has not run on this machine"
  echo "     That is fine if you provisioned it another way — the questions it"
  echo "     would have answered are asked below instead."
fi

# ── the account ──
#
# A remembered answer can go stale: the account it names may have been renamed or
# removed since machine-setup ran. That is a reason to ask again, not a reason to
# stop — so the remembered value is checked before it is trusted, and a bad one
# is reported and replaced rather than ending the run.
if [[ -n "$USERNAME" ]] && ! owner_exists; then
  warn "the remembered account '${USERNAME}' does not exist on this machine any more"
  USERNAME=""
fi

while [[ -z "$USERNAME" ]] || ! owner_exists; do
  echo ""
  info "Which account owns this Officer install?"
  echo "     Its files, its node_modules and its pm2 process list all belong to"
  echo "     this account rather than to root."
  echo ""
  ask_required USERNAME "Username" "${SUDO_USER:-}"
  owner_exists || warn "There is no account called '${USERNAME}' on this machine."
done

resolve_user_home

# ── where it goes ──
if [[ -z "$OFFICER_ROOT" ]]; then
  echo ""
  info "Where should Officer be installed?"
  echo "     One directory holding the app, its data, the item store and any"
  echo "     containers the app store provisions."
  echo ""
  ask_required OFFICER_ROOT "Path" "${USER_HOME}/officerdev"
fi
OFFICER_ROOT="${OFFICER_ROOT/#\~/$USER_HOME}"
[[ "$OFFICER_ROOT" == /* ]] || fail "That needs to be an absolute path — got '${OFFICER_ROOT}'"
OFFICER_ROOT="${OFFICER_ROOT%/}"

info "Account:  ${USERNAME} (home ${USER_HOME})"
info "Officer:  ${OFFICER_ROOT}"
[[ -n "$MACHINE_ROLE" ]] && info "Role:     ${MACHINE_ROLE}"

# ── is the machine actually ready ──
#
# Checked and reported together. Finding out about a missing bun three sections
# in, after a repository has been cloned and a database started, is a worse way
# to learn it.
echo ""
info "What Officer needs from this machine"

mapfile -t MISSING < <(missing_tools)
mapfile -t MISSING_OPT < <(missing_optional_tools)

for t in "${REQUIRED_TOOLS[@]}"; do
  if command -v "$t" &>/dev/null; then
    printf '     %-6s %-10s %s\n' "$t" "ok" "$(tool_why "$t")"
  else
    printf '     %-6s %-10s %s\n' "$t" "MISSING" "$(tool_why "$t")"
  fi
done
for t in "${OPTIONAL_TOOLS[@]}"; do
  if command -v "$t" &>/dev/null; then
    printf '     %-6s %-10s %s\n' "$t" "ok" "$(tool_why "$t")"
  else
    printf '     %-6s %-10s %s\n' "$t" "absent" "$(tool_why "$t") — optional"
  fi
done

if ((${#MISSING[@]} > 0)); then
  echo ""
  fail "Missing: ${MISSING[*]}. Run scripts/setup/machine-setup/machine-setup.sh first, or install them yourself."
fi

if ((${#MISSING_OPT[@]} > 0)); then
  echo ""
  warn "No Docker. Postgres will have to be one you already run, and the app"
  echo "     store cannot provision anything until Docker is installed."
fi

if [[ -f "$PROGRESS_FILE" ]]; then
  echo ""
  info "Resuming — $(wc -l <"$PROGRESS_FILE") step(s) already done, and they will be skipped"
  echo "     To start over instead:  sudo rm ${PROGRESS_FILE}"
else
  echo ""
  echo "     This can be stopped at any point and run again later. Completed"
  echo "     steps are remembered and skipped."
fi

# =============================================================================
# 2. Layout
# =============================================================================
#
# Before the repository, because the repository is cloned into it.

step "Layout"
if ! skip; then
  echo ""
  info "Layout — everything Officer owns, under one root"
  echo "     ${OFFICER_ROOT}/"
  echo "       platform/       the app"
  echo "       data/           managed homes, attachments, job logs"
  echo "       dockers/        anything the app store provisions"
  echo "       capabilities/   skills, tools, tasks, processes"
  echo ""
  echo "     Nothing here is configurable. The original asked separately for the"
  echo "     data directory and the item store, which were two answers that had"
  echo "     to agree with each other. One root now, and the rest follows."
  echo ""
  echo "     To put data/ on a bigger volume later, symlink it — that is a"
  echo "     decision about storage rather than about how Officer is laid out."

  mapfile -t WRONG_OWNER < <(layout_wrong_owner)
  if ((${#WRONG_OWNER[@]} > 0)); then
    echo ""
    warn "these exist but do not belong to ${USERNAME}:"
    printf '       %s\n' "${WRONG_OWNER[@]}"
    echo "     Everything that writes into them runs as ${USERNAME} — the platform"
    echo "     under pm2, the app store's compose files, the item store the agent"
    echo "     authors into. Left as they are, those writes fail in a way that"
    echo "     reads as a bug in the platform."
    if confirm "Give them to ${USERNAME}?"; then
      for d in "${WRONG_OWNER[@]}"; do chown -R "${USERNAME}:$(user_group)" "$d"; done
      ok "ownership corrected"
      SUMMARY+=("Layout: ownership corrected on ${#WRONG_OWNER[@]} directory(ies)")
    fi
  fi

  create_layout
  ok "layout in place under ${OFFICER_ROOT}"
  SUMMARY+=("Layout: ${OFFICER_ROOT} (data, dockers, capabilities)")
  step_ok
fi

# =============================================================================
# 3. Repository
# =============================================================================

step "Repository"
if ! skip; then
  PLATFORM_DIR="$(platform_dir)"

  echo ""
  info "Repository — where the platform's code lives"
  echo "     path:      ${PLATFORM_DIR}"

  if repo_exists; then
    echo "     remote:    $(repo_remote)"
    echo "     branch:    $(repo_branch)"
    echo "     working:   $(repo_is_dirty && echo 'has uncommitted changes' || echo 'clean')"

    # Reported, never silently corrected. Repointing somebody's remote is a
    # decision about where their work goes, and this script is not entitled to
    # make it quietly.
    if [[ -n "$(repo_remote)" && "$(repo_remote)" != "$OFFICER_REPO" ]]; then
      echo ""
      warn "this checkout points somewhere other than ${OFFICER_REPO}"
      echo "     Left alone. To move it:"
      echo "       git -C ${PLATFORM_DIR} remote set-url origin ${OFFICER_REPO}"
    fi

    if repo_is_dirty; then
      echo ""
      echo "     not pulling — there are uncommitted changes here, and a pull"
      echo "     would either fail or bury them"
      SUMMARY+=("Repository: present at ${PLATFORM_DIR}, left alone (uncommitted changes)")
    elif confirm "Pull the latest changes?"; then
      if pull_repo; then
        ok "up to date on $(repo_branch)"
        SUMMARY+=("Repository: pulled, on $(repo_branch)")
      else
        # --ff-only, so this means the branch has diverged rather than that the
        # network failed. Saying which matters.
        warn "could not fast-forward — the local branch has diverged from the remote"
        ERRORS+=("Repository: pull refused, branch diverged")
        SUMMARY+=("Repository: present, pull refused (diverged)")
      fi
    else
      SUMMARY+=("Repository: present at ${PLATFORM_DIR}")
    fi

  else
    echo "     nothing there yet"
    echo ""
    info "Clone from ${OFFICER_REPO}?"
    echo "     Cloned as ${USERNAME}, not as root — a repository owned by root is"
    echo "     one you cannot pull, commit in, or install into."

    CLONE_URL="$OFFICER_REPO"

    if confirm "Clone it now?"; then
      if clone_repo "$CLONE_URL"; then
        ok "cloned to ${PLATFORM_DIR} on $(repo_branch)"
        SUMMARY+=("Repository: cloned from ${CLONE_URL}")
      else
        # GIT_TERMINAL_PROMPT=0 in clone_repo means this is a real failure rather
        # than a prompt nobody answered.
        fail "could not clone ${CLONE_URL} — nothing below can run without it."
      fi
    else
      fail "Nothing below can run without the repository."
    fi
  fi
  step_ok
fi

# =============================================================================
# 4. Dependencies
# =============================================================================

step "Dependencies"
if ! skip; then
  echo ""
  info "Dependencies — bun install, as ${USERNAME}"
  echo "     node_modules: $(deps_installed && echo present || echo 'not there')"
  echo "     node-pty:     $(node_pty_built && echo built || echo 'not built')"
  echo ""
  echo "     The lockfile is frozen: bun resolves from bun.lock and nothing else,"
  echo "     so a package.json that disagrees with it fails rather than quietly"
  echo "     picking newer versions. That friction is deliberate."
  echo ""
  echo "     node-pty has no Linux prebuild, so this compiles it from source"
  echo "     every time — which is what build-essential and python3 are for."

  if deps_installed && node_pty_built; then
    ok "already installed, and node-pty is built"
    SUMMARY+=("Dependencies: already installed")
  elif confirm "Install them?"; then
    if install_deps; then
      if node_pty_built; then
        ok "installed, node-pty built"
        SUMMARY+=("Dependencies: installed")
      else
        # The install can succeed while the native module does not get built —
        # bun skips a dependency's lifecycle scripts unless it trusts the
        # package. Worth naming, because the symptom is a terminal that never
        # comes up rather than an install error.
        warn "installed, but node-pty has no built module at node_modules/node-pty/build/Release/"
        echo "     The terminal sidecar cannot start without it. Try:"
        echo "       cd $(platform_dir) && bun install --force"
        ERRORS+=("Dependencies: node-pty not built")
        SUMMARY+=("Dependencies: installed, node-pty NOT built")
      fi
    else
      warn "bun install failed"
      echo "     If it complained about the lockfile, package.json and bun.lock"
      echo "     disagree — that is the frozen lockfile doing its job, and it"
      echo "     wants a human to look at the diff."
      ERRORS+=("Dependencies: bun install failed")
      SUMMARY+=("Dependencies: FAILED")
    fi
  else
    warn "skipped by request"
    SUMMARY+=("Dependencies: SKIPPED by request")
  fi
  step_ok
fi

# =============================================================================
# NOT BUILT YET
# =============================================================================
#   4  Database       Postgres in docker, or one you already run
#   5  Environment    .env
#   6  Schema         db:push
#   7  Build          gen:index
#   8  Services       pm2 startOrRestart · save · startup
#   9  Verify         are the processes actually up

echo ""
echo -e "${BOLD}  Pre-flight complete.${NC} The remaining sections are not built yet."
echo ""