FabledSteward/steward/ansible/bundled/host_agent/provision.yml

---
# description: Provision a fresh host — create the steward account + managed key + passwordless sudo, then install the agent.
# steward:category: host-agent
# First-contact provisioning: bring a fresh host under Steward management, then
# install the host agent — all in one idempotent run.
#
# Run this ONCE per host with bootstrap credentials (an existing login + sudo,
# typically password auth via the "Provision host" button). It:
#   1. creates a dedicated `steward` login account,
#   2. installs Steward's managed public key into its authorized_keys,
#   3. grants it passwordless sudo,
#   4. installs/updates the host agent.
# After this, every future run (agent updates, maintenance) connects as
# `steward` with the managed key — no operator credentials needed.
#
# Extra-vars (injected by the Provision card):
#   steward_url, steward_token   — agent → Steward auth (per-host)
#   steward_pubkey               — managed public key to authorize
#   steward_user (default steward), agent_interval (default 30)
- name: Provision host for Steward + install agent
  hosts: all
  become: true
  gather_facts: false
  # steward_token is injected as a per-host inventory var (it differs per host),
  # so it must NOT be declared here — a play var would outrank the inventory var
  # and shadow it. The globals below arrive as extra-vars (highest precedence),
  # which override these defaults.
  vars:
    steward_url: ""
    steward_pubkey: ""
    steward_user: steward
    agent_interval: 30
  tasks:
    - name: Require provisioning vars
      ansible.builtin.assert:
        that:
          - steward_url | default('') | length > 0
          - steward_token | default('') | length > 0
          - steward_pubkey | default('') | length > 0
        fail_msg: "Pass steward_url, steward_token and steward_pubkey (Steward injects these)."

    # ── Managed login account ────────────────────────────────────────────────
    - name: Create the steward management account
      ansible.builtin.user:
        name: "{{ steward_user }}"
        shell: /bin/sh
        create_home: true
        state: present

    - name: Ensure ~/.ssh exists
      ansible.builtin.file:
        path: "/home/{{ steward_user }}/.ssh"
        state: directory
        owner: "{{ steward_user }}"
        group: "{{ steward_user }}"
        mode: "0700"

    - name: Authorize the managed public key (replace any prior steward-managed key)
      ansible.builtin.lineinfile:
        path: "/home/{{ steward_user }}/.ssh/authorized_keys"
        # Match on the ' steward-managed' comment so a rotated key REPLACES the
        # old one in place rather than stacking a second authorized key. Any
        # keys the operator added by hand (different comment) are left untouched.
        regexp: ' steward-managed$'
        line: "{{ steward_pubkey }}"
        create: true
        owner: "{{ steward_user }}"
        group: "{{ steward_user }}"
        mode: "0600"

    - name: Grant passwordless sudo to the steward account
      ansible.builtin.copy:
        dest: "/etc/sudoers.d/steward"
        content: "{{ steward_user }} ALL=(ALL) NOPASSWD:ALL\n"
        owner: root
        group: root
        mode: "0440"
        validate: "visudo -cf %s"

    # ── Host agent (same as install.yml) ─────────────────────────────────────
    - name: Create steward-agent system user
      ansible.builtin.user:
        name: steward-agent
        system: true
        shell: /usr/sbin/nologin
        create_home: false

    # Let the agent read the local Docker socket so it can report this host's
    # containers (the per-host docker collection path). Best-effort: skipped on
    # hosts without Docker. Restart picks up the new supplementary group.
    - name: Detect docker group
      ansible.builtin.command: getent group docker
      register: _docker_grp
      changed_when: false
      failed_when: false

    - name: Add steward-agent to the docker group
      ansible.builtin.user:
        name: steward-agent
        groups: docker
        append: true
      when: _docker_grp.rc == 0
      notify: restart steward-agent

    - name: Create agent directory
      ansible.builtin.file:
        path: /usr/local/lib/steward-agent
        state: directory
        mode: "0755"

    - name: Download agent.py
      ansible.builtin.get_url:
        url: "{{ steward_url }}/plugins/host_agent/agent.py"
        dest: /usr/local/lib/steward-agent/agent.py
        mode: "0755"
        force: true
      notify: restart steward-agent

    - name: Write agent config
      # The content carries steward_token; --diff and a failure would print it.
      no_log: true
      ansible.builtin.copy:
        dest: /etc/steward-agent.conf
        owner: root
        group: steward-agent
        mode: "0640"
        content: |
          url = {{ steward_url }}
          token = {{ steward_token }}
          interval_seconds = {{ agent_interval }}
      notify: restart steward-agent

    - name: Install systemd unit
      ansible.builtin.copy:
        dest: /etc/systemd/system/steward-agent.service
        mode: "0644"
        content: |
          [Unit]
          Description=Steward host agent
          After=network-online.target
          Wants=network-online.target

          [Service]
          Type=simple
          User=steward-agent
          Environment=STEWARD_AGENT_CONFIG=/etc/steward-agent.conf
          ExecStart=/usr/bin/env python3 /usr/local/lib/steward-agent/agent.py
          Restart=on-failure
          RestartSec=5
          NoNewPrivileges=true
          ProtectSystem=strict
          ProtectHome=true
          PrivateTmp=true

          [Install]
          WantedBy=multi-user.target
      notify: restart steward-agent

    - name: Enable and start the agent
      ansible.builtin.systemd:
        name: steward-agent
        enabled: true
        state: started
        daemon_reload: true

  handlers:
    - name: restart steward-agent
      ansible.builtin.systemd:
        name: steward-agent
        state: restarted
        daemon_reload: true