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"
# shellcheck source=officer-setup/lib/postgres.sh
source "$SCRIPT_DIR/officer-setup/lib/postgres.sh"
# shellcheck source=officer-setup/lib/env.sh
source "$SCRIPT_DIR/officer-setup/lib/env.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

# =============================================================================
# 5. Database
# =============================================================================
#
# POSTGRES_URL is set here and written by the environment section below.

step "Database"
if ! skip; then
  echo ""
  info "Database — Postgres, the only one Officer has"
  echo "     It holds the account, passkeys, settings, dashboards, email"
  echo "     accounts and the job queue. Nothing else in the platform is a"
  echo "     database."
  echo ""
  # One network for everything Officer provisions. Created before the compose
  # file references it, since it is declared external there.
  if ensure_docker_network; then
    ok "docker network '${OFFICER_NETWORK}' created"
    SUMMARY+=("Docker network: ${OFFICER_NETWORK} created")
  elif docker_network_exists; then
    echo "     network:       ${OFFICER_NETWORK} (already there)"
  fi

  echo "     compose file:  $(pg_compose_exists && echo "$(pg_compose_file)" || echo 'not written yet')"
  echo "     container:     $(pg_container_running && echo "${PG_CONTAINER} running" || echo 'not running')"
  echo "     port ${PG_PORT}:    $(pg_port_in_use && echo 'something is listening' || echo 'free')"

  POSTGRES_URL=""

  # An existing compose file means this ran before. Reuse its password rather
  # than minting a new one, which would leave the container and the URL
  # disagreeing about the credential.
  if pg_compose_exists && PG_EXISTING_PASSWORD="$(pg_password_from_env_file)"; then
    POSTGRES_URL="$(pg_url "$PG_EXISTING_PASSWORD")"
    echo ""
    echo "     already provisioned here — reusing the password from $(pg_env_file)"
    pg_container_running || {
      info "     starting it"
      pg_compose_up >/dev/null 2>&1 || true
    }
    if pg_wait_ready; then
      ok "postgres answering on 127.0.0.1:${PG_PORT}"
      SUMMARY+=("Database: existing Postgres at ${PG_CONTAINER}")
    else
      warn "the container is not answering — check: docker logs ${PG_CONTAINER}"
      ERRORS+=("Database: provisioned but not answering")
    fi

  else
    echo ""
    info "Which Postgres should Officer use?"
    echo ""
    echo "     [1] provision one here"
    echo "         ${PG_IMAGE} in $(pg_service_dir), bound to 127.0.0.1 only."
    echo "         Docker publishes ports by writing iptables rules beneath ufw,"
    echo "         so a database published to every interface is reachable from"
    echo "         the internet whatever the firewall says. Loopback is all the"
    echo "         platform needs — it runs on this machine."
    echo ""
    echo "     [2] use one you already run"
    echo "         Give the connection URL. Nothing is provisioned."
    echo ""

    DB_PICK=""
    while [[ -z "$DB_PICK" ]]; do
      if ! read -rp "  Which one? (1/2) [1]: " DB_CHOICE; then
        echo ""
        fail "No answer."
      fi
      case "${DB_CHOICE:-1}" in
        1)
          if ! command -v docker &>/dev/null; then
            warn "Docker is not installed, so there is nothing to provision into."
            continue
          fi
          if pg_port_in_use; then
            warn "something is already listening on ${PG_PORT} — provisioning here would fail to bind"
            echo "     If that is a Postgres you already run, pick 2 and give its URL."
            continue
          fi
          DB_PICK=provision
          ;;
        2) DB_PICK=existing ;;
        *) warn "Pick 1 or 2." ;;
      esac
    done

    if [[ "$DB_PICK" == provision ]]; then
      PG_PASSWORD="$(openssl rand -base64 32 | tr -d '/+=' | head -c 32)"
      write_pg_compose "$PG_PASSWORD"
      ok "compose written to $(pg_compose_file)"
      if pg_compose_up && pg_wait_ready; then
        POSTGRES_URL="$(pg_url "$PG_PASSWORD")"
        ok "postgres answering on 127.0.0.1:${PG_PORT}, database '${PG_DATABASE}'"
        SUMMARY+=("Database: provisioned at $(pg_service_dir)")
      else
        warn "the container did not come up — check: docker logs ${PG_CONTAINER}"
        ERRORS+=("Database: container did not start")
        SUMMARY+=("Database: provisioning FAILED")
      fi
    else
      echo ""
      ask_required POSTGRES_URL "Connection URL" "postgresql://user:password@host:5432/officer"
      if pg_url_works "$POSTGRES_URL"; then
        ok "reachable"
        SUMMARY+=("Database: existing, ${POSTGRES_URL%%:*}://…")
      else
        # Not fatal. The URL may be right and the database not started yet, and
        # refusing to continue over that would be worse than saying so.
        warn "could not connect with that URL"
        echo "     Kept anyway — check it before running the schema step."
        ERRORS+=("Database: the given URL did not answer")
        SUMMARY+=("Database: existing URL kept, did not answer")
      fi
    fi
  fi
  step_ok
fi

# =============================================================================
# 6. Environment
# =============================================================================

step "Environment"
if ! skip; then
  echo ""
  info "Environment — $(env_file)"

  # Read back before anything is asked. The two secrets below are kept, never
  # reminted, and everything else becomes the default for its question.
  ENV_JWT_SECRET="$(env_get JWT_SECRET)"
  ENV_VAULT_STORE_KEY="$(env_get VAULT_STORE_KEY)"
  ENV_PORT="$(env_get PORT)"
  ENV_PUBLIC_URL="$(env_get PUBLIC_URL)"
  ENV_MAIL_TRANSPORT="$(env_get MAIL_TRANSPORT)"
  ENV_DISCORD_WEBHOOK="$(env_get DISCORD_BUG_REPORT_WEBHOOK)"
  ENV_BROWSER_RELAY_PORT="$(env_get BROWSER_RELAY_PORT)"

  if env_exists; then
    echo "     exists — its values are the defaults below, and the two secrets are kept"
  else
    echo "     does not exist yet"
  fi

  # ── the secrets ──
  if [[ -n "$ENV_JWT_SECRET" ]]; then
    echo "     JWT_SECRET:      kept (regenerating it logs everybody out)"
  else
    ENV_JWT_SECRET="$(generate_secret)"
    echo "     JWT_SECRET:      generated"
  fi

  if [[ -n "$ENV_VAULT_STORE_KEY" ]]; then
    echo "     VAULT_STORE_KEY: kept"
  else
    ENV_VAULT_STORE_KEY="$(generate_secret)"
    echo "     VAULT_STORE_KEY: generated"
    echo ""
    warn "back up VAULT_STORE_KEY somewhere safe, now."
    echo "     It encrypts every upstream credential the platform stores, and the"
    echo "     wallet's seed on top of your passphrase. Lose it and those are gone"
    echo "     — the passphrase does not help, because it opens the inner envelope"
    echo "     and this is the outer one."
  fi

  # ── what is asked ──
  echo ""
  ask_required ENV_PORT "Port Officer listens on" "${ENV_PORT:-9000}"
  ENV_BROWSER_RELAY_PORT="${ENV_BROWSER_RELAY_PORT:-18792}"

  echo ""
  echo "     PUBLIC_URL is where Officer is reached from a browser. Allowed"
  echo "     origins are derived from it, and passkeys are bound to its host —"
  echo "     so it has to be the address you actually use, not localhost, unless"
  echo "     localhost is genuinely it."
  ask_required ENV_PUBLIC_URL "Public URL" "${ENV_PUBLIC_URL:-http://localhost:${ENV_PORT}}"

  # ── origin checking, decided by the machine rather than by a default ──
  #
  # ALLOW_ANY_ORIGIN defaults to ON inside the platform, which CLAUDE.md says is
  # only defensible because the tailnet is the perimeter. So the value is written
  # explicitly here, from whether this machine actually has one.
  if tailnet_present; then
    ENV_ALLOW_ANY_ORIGIN="true"
    ORIGIN_WHY="tailscale0 is up, so the tailnet is the perimeter"
  else
    ENV_ALLOW_ANY_ORIGIN="false"
    ORIGIN_WHY="no tailnet on this machine, so origin checking is left ON"
  fi
  echo ""
  echo "     ALLOW_ANY_ORIGIN=${ENV_ALLOW_ANY_ORIGIN} — ${ORIGIN_WHY}"

  echo ""
  ENV_MAIL_TRANSPORT="${ENV_MAIL_TRANSPORT:-}"
  read -rp "  Mail transport, blank for none [${ENV_MAIL_TRANSPORT}]: " REPLY_MAIL || true
  ENV_MAIL_TRANSPORT="${REPLY_MAIL:-$ENV_MAIL_TRANSPORT}"

  echo ""
  echo "     to write:"
  echo "       PORT=${ENV_PORT}   BROWSER_RELAY_PORT=${ENV_BROWSER_RELAY_PORT}"
  echo "       PUBLIC_URL=${ENV_PUBLIC_URL}"
  echo "       ALLOW_ANY_ORIGIN=${ENV_ALLOW_ANY_ORIGIN}"
  echo "       DATA_PATH=${OFFICER_ROOT}/data"
  echo "       OFFICER_ITEMS_DIR=${OFFICER_ROOT}/capabilities"
  echo "       HOME_DIR=${USER_HOME}"
  echo "       POSTGRES_URL=${POSTGRES_URL%%:*}://…"
  echo "       JWT_SECRET, VAULT_STORE_KEY — not shown"
  echo ""

  if confirm "Write it?"; then
    write_env
    ok "written, 0600, owned by ${USERNAME}"
    [[ -f "$(env_file).before-officer-setup" ]] && echo "     previous kept as $(env_file).before-officer-setup"
    SUMMARY+=("Environment: $(env_file)")
  else
    warn "skipped by request"
    SUMMARY+=("Environment: SKIPPED by request")
  fi
  step_ok
fi

# =============================================================================
# NOT BUILT YET
# =============================================================================
#   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 ""