learning-platform/infra/development/site/deploy-playbook.yml

- name: Deploy Learning Platform with Ansible
  hosts: all
  become: yes
  gather_facts: yes
  vars:
    ansible_ssh_common_args: '-o StrictHostKeyChecking=no'

  tasks:
    - name: Set destination directory
      ansible.builtin.set_fact:
        dest_dir: "/opt/learning-platform"

    - name: Ensure dependencies are installed
      ansible.builtin.package:
        name:
          - docker-ce
        state: present
      ignore_errors: yes
      register: docker_valid

    - name: Include geerlingguy.docker role conditionally
      include_role:
        name: geerlingguy.docker
      when: docker_valid is failed

    - name: Ensure target directory exists
      ansible.builtin.file:
        path: "{{ dest_dir }}"
        state: directory
        owner: root
        group: root
        mode: "0755"

    - name: Copy compose.yml to destination
      ansible.builtin.copy:
        src: compose.yml
        dest: "{{ dest_dir }}/compose.yml"

    - name: Copy pb_migrations to destination
      ansible.builtin.copy:
        src: ../../../pb_migrations
        dest: "{{ dest_dir }}/"
        mode: "0755"

    - name: Copy pb_hooks to destination
      ansible.builtin.copy:
        src: ../../../pb_hooks
        dest: "{{ dest_dir }}/"
        mode: "0755"

    - name: Create .env file for secrets
      ansible.builtin.copy:
        dest: "{{ dest_dir }}/.env"
        content: |
          ANTHROPIC_API_KEY={{ anthropic_api_key | default('') }}
          ENTRA_TENANT_ID={{ entra_tenant_id | default('') }}
          ENTRA_CLIENT_ID={{ entra_client_id | default('') }}
          ENTRA_CLIENT_SECRET={{ entra_client_secret | default('') }}
          ENTRA_ADMIN_EMAILS={{ entra_admin_emails | default('') }}
        mode: '0600'

    - name: Pull latest image
      community.docker.docker_compose_v2:
        project_src: "{{ dest_dir }}"
        state: present
        files: compose.yml
        pull: always

    - name: Start services with Docker Compose
      community.docker.docker_compose_v2:
        project_src: "{{ dest_dir }}"
        state: present
        files: compose.yml
        recreate: always

    # A failed migration aborts `pocketbase serve` and the container crash-loops
    # while `docker compose up` still reports success (issue #18). Gate the
    # deploy on PocketBase actually serving its health endpoint.
    - name: Wait for PocketBase to become healthy
      ansible.builtin.command: docker exec pocketbase-learning wget -q -O - http://127.0.0.1:8090/api/health
      register: pb_health
      until: pb_health.rc == 0
      retries: 18
      delay: 5
      changed_when: false
      ignore_errors: yes

    - name: Collect PocketBase logs for diagnosis
      ansible.builtin.command: docker logs --tail 80 pocketbase-learning
      register: pb_logs
      when: pb_health is failed
      changed_when: false
      failed_when: false

    - name: Abort deploy — PocketBase is not healthy
      ansible.builtin.fail:
        msg: |
          PocketBase did not become healthy after the deploy (health endpoint unreachable).
          Recent container logs:
          {{ pb_logs.stdout | default('') }}
          {{ pb_logs.stderr | default('') }}
      when: pb_health is failed

    # The frontend container carries the SPA + Caddy. An invalid Caddyfile
    # crash-loops it at startup while the PocketBase gate stays green — that
    # outage (issue #20) was invisible to CI because the test job swaps in
    # Caddyfile.test. Gate on the real container actually serving.
    - name: Wait for the frontend (Caddy) to become healthy
      ansible.builtin.command: docker exec learning-platform wget -q --spider http://127.0.0.1:80/
      register: fe_health
      until: fe_health.rc == 0
      retries: 18
      delay: 5
      changed_when: false
      ignore_errors: yes

    - name: Collect frontend logs for diagnosis
      ansible.builtin.command: docker logs --tail 80 learning-platform
      register: fe_logs
      when: fe_health is failed
      changed_when: false
      failed_when: false

    - name: Abort deploy — frontend is not healthy
      ansible.builtin.fail:
        msg: |
          The frontend (Caddy) container did not become healthy after the deploy.
          Recent container logs:
          {{ fe_logs.stdout | default('') }}
          {{ fe_logs.stderr | default('') }}
      when: fe_health is failed

    # Observability behind the auth perimeter: surface the end-to-end state
    # in the CI log on every deploy.
    - name: Post-deploy smoke report
      ansible.builtin.shell: |
        cd /opt/learning-platform
        echo '--- docker compose ps ---'
        docker compose ps
        echo '--- frontend -> pocketbase proxy health ---'
        docker exec learning-platform wget -q -O - http://127.0.0.1:80/api/health || echo 'PROXY HEALTH FAILED'
        echo '--- team_members auth methods (OIDC provider present?) ---'
        docker exec pocketbase-learning wget -q -O - http://127.0.0.1:8090/api/collections/team_members/auth-methods || echo 'AUTH-METHODS FAILED'
        echo '--- pocketbase logs (tail 30) ---'
        docker compose logs --tail=30 pocketbase-learning
      register: smoke_report
      changed_when: false
      failed_when: false

    - name: Show smoke report
      ansible.builtin.debug:
        msg: "{{ smoke_report.stdout_lines }}"