ansible/inventory/group_vars/synology_nas/vars.yml

@@ -0,0 +1,8 @@
+---
+# DSM's own python3 is 3.8; plays/configure-synology-python.yml installs this.
+ansible_python_interpreter: /var/packages/Python3.9/target/usr/bin/python3.9
+# DSM offers no sftp/scp.
+ansible_ssh_transfer_method: piped
+
+# claude-bot is a DSM administrator here; its password is unknown.
+ssh_ca_claude_sudo_all: true

ansible/inventory/pve_hosts.yml

@@ -8,8 +8,6 @@
 #   pve_cluster (jupiter/neptune/saturn)  run Talos on bare metal; no SSH at all
 #   authentik_db / authentik_app          authentik runs in-cluster (CNPG)
 #   grafana                               runs in-cluster
-#   synology_nas (nas-1)                  powered off; Garage and the PBS client
-#                                         it hosted are gone with it
 # Their hosts no longer resolve, except the three that resolve to Talos nodes.
 
 [netbird_server]
@@ -25,6 +23,11 @@ proxy-2.renner.uno ansible_host=proxy-2.nb.renner.uno ansible_user=root
 [edge_host]
 edge-1.iot.renner.uno ansible_user=root
 
+# Synology NAS (DSM): nas-1 RS1221+ on site, nas-2 DS1522+ off site.
+[synology_nas]
+nas-1.renner.uno ansible_user=root
+nas-2.renner.uno ansible_user=root
+
 # Capability groups. Membership states which hardware a host physically has,
 # and each service playbook targets the group for its own concern. No flags and
 # no `when:` on the roles -- moving a stick to another box is a one-line change
@@ -70,6 +73,8 @@ proxy-1.renner.uno
 proxy-2.renner.uno
 netbird.renner.uno
 edge-1.iot.renner.uno
+nas-1.renner.uno
+nas-2.renner.uno
 
 # Hosts whose admin logins accept only ssh_admin_authorized_keys (break-glass);
 # everything else needs a CA certificate. Members must be in [ssh_ca].

ansible/plays/configure-synology-python.yml

@@ -0,0 +1,19 @@
+---
+# Ansible needs Python >= 3.9 on the target; DSM ships 3.8. Synology's
+# Python3.9 package installs beside it. raw, because the modules cannot run
+# before it is there; raw is skipped in check mode.
+- name: Install Python 3.9 on the Synology NAS
+  hosts: synology_nas
+  become: true
+  gather_facts: false
+  tasks:
+    - name: Install the Python3.9 package
+      ansible.builtin.raw: >-
+        if [ -x {{ ansible_python_interpreter }} ]; then echo present;
+        else /usr/syno/bin/synopkg install_from_server Python3.9; fi
+      register: synology_python_install
+      changed_when: "'present' not in synology_python_install.stdout"
+
+    - name: Check the interpreter exists
+      ansible.builtin.raw: test -x {{ ansible_python_interpreter }}
+      changed_when: false

ansible/roles/common/tasks/main.yml

@@ -8,12 +8,11 @@
   lineinfile:
     path: /etc/hosts
     regexp: '^127\.0\.1\.1\s+{{ inventory_hostname }}'
-    line: "{{ ansible_default_ipv4.address }} {{ inventory_hostname }} {{ inventory_hostname_short | default(inventory_hostname.split('.')[0]) }}"
+    line: "{{ ansible_facts['default_ipv4']['address'] }} {{ inventory_hostname }} {{ inventory_hostname_short | default(inventory_hostname.split('.')[0]) }}"
     state: present
   when:
-    - ansible_virtualization_type is defined
-    - ansible_virtualization_type == 'lxc'
-    - ansible_default_ipv4.address is defined
+    - ansible_facts['virtualization_type'] == 'lxc'
+    - ansible_facts['default_ipv4']['address'] is defined
 
 # -------------------------------------------------------
 # 1. Install Common Packages
@@ -64,8 +63,8 @@
     enabled: no
     masked: yes
   when:
-    - ansible_virtualization_type is defined
-    - ansible_virtualization_type in ['kvm', 'lxc']
+    - ansible_facts['virtualization_role'] == 'guest'
+    - ansible_facts['virtualization_type'] in ['kvm', 'lxc']
   ignore_errors: yes
 
 # -------------------------------------------------------

ansible/roles/crowdsec-edge-bouncer/defaults/main.yml

@@ -15,6 +15,8 @@
 # amd64 asset for exactly this tag.
 crowdsec_bouncer_version: v0.0.36
 crowdsec_bouncer_sha256: f86e4b72693549d99f40a9402abefb894108f047a3fbe6e72fada25ee17ce88b
+# Controller cache for the release archive; it outlives /tmp cleanups.
+crowdsec_bouncer_download_dir: "{{ lookup('ansible.builtin.env', 'HOME') }}/.cache/ansible/crowdsec"
 
 # The LAPI over the public path these hosts already serve, see
 # kubernetes/infrastructure/crowdsec/lapi-ingress.yaml. The proxies cannot

ansible/roles/crowdsec-edge-bouncer/tasks/main.yml

@@ -32,13 +32,23 @@
 # The controller has v4, so it does the fetching. The checksum is verified
 # there, before anything is copied to a host. Also in check mode: the fetch
 # only writes on the controller, and the copy below needs the file.
+- name: Create the controller download directory
+  ansible.builtin.file:
+    path: "{{ crowdsec_bouncer_download_dir }}"
+    state: directory
+    mode: "0755"
+  delegate_to: localhost
+  become: false
+  run_once: true
+  check_mode: false
+
 - name: Fetch the pinned bouncer release on the controller
   check_mode: false
   ansible.builtin.get_url:
     url: >-
       https://github.com/crowdsecurity/cs-firewall-bouncer/releases/download/{{
       crowdsec_bouncer_version }}/crowdsec-firewall-bouncer-linux-amd64.tgz
-    dest: /tmp/crowdsec-firewall-bouncer-{{ crowdsec_bouncer_version }}.tgz
+    dest: "{{ crowdsec_bouncer_download_dir }}/crowdsec-firewall-bouncer-{{ crowdsec_bouncer_version }}.tgz"
     checksum: sha256:{{ crowdsec_bouncer_sha256 }}
     mode: "0644"
   delegate_to: localhost
@@ -53,7 +63,7 @@
 # host.
 - name: Copy the bouncer archive to the host
   ansible.builtin.copy:
-    src: /tmp/crowdsec-firewall-bouncer-{{ crowdsec_bouncer_version }}.tgz
+    src: "{{ crowdsec_bouncer_download_dir }}/crowdsec-firewall-bouncer-{{ crowdsec_bouncer_version }}.tgz"
     dest: /opt/crowdsec-firewall-bouncer-{{ crowdsec_bouncer_version }}.tgz
     mode: "0644"
 

ansible/roles/keepalived-ntp/templates/keepalived.conf.j2

@@ -2,7 +2,7 @@
 # Managed by Ansible - Do not edit manually
 
 global_defs {
-    router_id {{ ansible_hostname }}_ntp
+    router_id {{ ansible_facts['hostname'] }}_ntp
     enable_script_security
     script_user root
 }

ansible/roles/netbird-client/tasks/main.yml

@@ -11,6 +11,8 @@
           - curl
           - ca-certificates
           - gnupg
+          # deb822_repository
+          - python3-debian
         state: present
         update_cache: true
 
@@ -21,10 +23,19 @@
         creates: /usr/share/keyrings/netbird-archive-keyring.gpg
 
     - name: Add NetBird repository
-      ansible.builtin.apt_repository:
-        repo: "deb [signed-by=/usr/share/keyrings/netbird-archive-keyring.gpg] https://pkgs.netbird.io/debian stable main"
-        state: present
-        filename: netbird
+      ansible.builtin.deb822_repository:
+        name: netbird
+        types: deb
+        uris: https://pkgs.netbird.io/debian
+        suites: stable
+        components: main
+        signed_by: /usr/share/keyrings/netbird-archive-keyring.gpg
+
+    # A one-line netbird.list beside netbird.sources lists the repository twice.
+    - name: Remove the one-line NetBird repository
+      ansible.builtin.file:
+        path: /etc/apt/sources.list.d/netbird.list
+        state: absent
 
     - name: Install NetBird client
       ansible.builtin.apt:

ansible/roles/qemu-guest-agent/tasks/main.yml

@@ -6,15 +6,15 @@
   apt:
     name: qemu-guest-agent
     state: present
-  when: 
-    - ansible_os_family is defined and ansible_os_family == 'Debian'
+  when:
+    - ansible_facts['os_family'] == 'Debian'
 
 - name: Install QEMU Guest Agent (RHEL/Rocky VMs)
   dnf:
     name: qemu-guest-agent
     state: present
-  when: 
-    - ansible_os_family is defined and ansible_os_family == 'RedHat'
+  when:
+    - ansible_facts['os_family'] == 'RedHat'
 
 - name: Ensure qemu-guest-agent is started and enabled
   service:

ansible/roles/ssh-ca/defaults/main.yml

@@ -16,3 +16,6 @@ ssh_ca_claude_principal: claude-bot
 
 # Units claude-bot may restart/reload via sudo on this host, e.g. [netbird].
 ssh_ca_claude_sudo_units: []
+
+# Full passwordless sudo for claude-bot on this host.
+ssh_ca_claude_sudo_all: false

ansible/roles/ssh-ca/tasks/authorized_keys.yml

@@ -1,23 +1,15 @@
 ---
 # Replaces the admin logins' authorized_keys with ssh_admin_authorized_keys
 # (break-glass + CI). Everything else logs in with a CA certificate.
-- name: Look up the admin logins
-  ansible.builtin.getent:
-    database: passwd
-    key: "{{ item }}"
-    fail_key: false
-  loop: "{{ ssh_ca_owner_users }}"
-  register: ssh_ca_admin_lookup
-
+# ssh_ca_admin_logins comes from main.yml, which runs first in the same play.
 - name: Set the admin logins' authorized_keys to the managed list
   ansible.posix.authorized_key:
-    user: "{{ item.item }}"
+    user: "{{ item[0] }}"
     key: |
       {% for k in ssh_admin_authorized_keys %}
       {{ (k.options ~ ' ') if (k.options | default('')) else '' }}{{ k.key }}
       {% endfor %}
     exclusive: true
-  loop: "{{ ssh_ca_admin_lookup.results }}"
+  loop: "{{ ssh_ca_admin_logins }}"
   loop_control:
-    label: "{{ item.item }}"
-  when: (item.ansible_facts.getent_passwd | default({})).get(item.item) is not none
+    label: "{{ item[0] }}"

ansible/roles/ssh-ca/tasks/main.yml

@@ -23,6 +23,7 @@
     owner: root
     group: root
     mode: "0644"
+  register: ssh_ca_trusted_file
 
 # sshd refuses all public key logins when RevokedKeys is set but unreadable,
 # so the file is always deployed, even when empty.
@@ -34,6 +35,26 @@
     group: root
     mode: "0644"
 
+# /etc/passwd, not getent: DSM has no getent binary. The admin logins are
+# local accounts. Each entry is the split passwd line (0 name, 5 home).
+- name: Read the local accounts
+  ansible.builtin.slurp:
+    src: /etc/passwd
+  register: ssh_ca_passwd_file
+
+- name: Find the existing admin logins
+  vars:
+    ssh_ca_passwd: "{{ ssh_ca_passwd_file.content | b64decode | trim | split('\n') | map('split', ':') | list }}"
+  ansible.builtin.set_fact:
+    ssh_ca_admin_logins: "{{ ssh_ca_passwd | selectattr('0', 'in', ssh_ca_owner_users) | list }}"
+    ssh_ca_claude_exists: "{{ ssh_ca_claude_user in ssh_ca_passwd | map('first') }}"
+
+# DSM manages accounts with synouser/synogroup and has no useradd.
+- name: Detect DSM
+  ansible.builtin.stat:
+    path: /usr/syno/sbin/synouser
+  register: ssh_ca_synouser
+
 # systemd-journal: read every journal without sudo (see sudoers-claude.j2).
 - name: Create the Claude account
   ansible.builtin.user:
@@ -43,14 +64,57 @@
     password: "!"
     groups: systemd-journal
     append: true
+  when: not ssh_ca_synouser.stat.exists
 
-- name: Look up the owner admin logins
-  ansible.builtin.getent:
-    database: passwd
-    key: "{{ item }}"
-    fail_key: false
-  loop: "{{ ssh_ca_owner_users }}"
-  register: ssh_ca_owner_lookup
+- name: Create the Claude account on DSM
+  when: ssh_ca_synouser.stat.exists
+  block:
+    # synouser requires a password; nobody knows it and sshd refuses passwords.
+    - name: Create the DSM account
+      ansible.builtin.command:
+        argv:
+          - /usr/syno/sbin/synouser
+          - --add
+          - "{{ ssh_ca_claude_user }}"
+          - "{{ lookup('ansible.builtin.password', '/dev/null', length=40, chars=['ascii_letters', 'digits']) }}"
+          - Claude Bot
+          - "0"
+          - ""
+          - "0"
+      # command runs in check mode here.
+      when:
+        - not ssh_ca_claude_exists
+        - not ansible_check_mode
+      no_log: true
+
+    # Members are listed as "<n>:[<name>]".
+    - name: Read the administrators members
+      ansible.builtin.command: /usr/syno/sbin/synogroup --get administrators
+      register: ssh_ca_dsm_admins_out
+      changed_when: false
+      check_mode: false
+
+    - name: Find the administrators members
+      ansible.builtin.set_fact:
+        ssh_ca_dsm_admins: >-
+          {{ ssh_ca_dsm_admins_out.stdout_lines | select('match', '^[0-9]+:\[.*\]$')
+             | map('regex_replace', '^[0-9]+:\[(.*)\]$', '\1') | list }}
+
+    # synogroup --member replaces the member list; a parse that lost the owner
+    # admin login would drop it.
+    - name: Check the member list holds the owner admin login
+      ansible.builtin.assert:
+        that:
+          - ssh_ca_dsm_admins | intersect(ssh_ca_owner_users) | length > 0
+        fail_msg: "administrators members lack {{ ssh_ca_owner_users }}: {{ ssh_ca_dsm_admins }}"
+
+    # DSM allows SSH for administrators only.
+    - name: Add the Claude account to administrators
+      ansible.builtin.command:
+        argv: "{{ ['/usr/syno/sbin/synogroup', '--member', 'administrators'] + ssh_ca_dsm_admins + [ssh_ca_claude_user] }}"
+      when:
+        - ssh_ca_claude_user not in ssh_ca_dsm_admins
+        - not ansible_check_mode
 
 - name: Create the principals directory
   ansible.builtin.file:
@@ -63,14 +127,13 @@
 - name: Accept the owner principal for the existing admin logins
   ansible.builtin.copy:
     content: "{{ ssh_ca_owner_principal }}\n"
-    dest: "/etc/ssh/auth_principals/{{ item.item }}"
+    dest: "/etc/ssh/auth_principals/{{ item[0] }}"
     owner: root
     group: root
     mode: "0644"
-  loop: "{{ ssh_ca_owner_lookup.results }}"
+  loop: "{{ ssh_ca_admin_logins }}"
   loop_control:
-    label: "{{ item.item }}"
-  when: (item.ansible_facts.getent_passwd | default({})).get(item.item) is not none
+    label: "{{ item[0] }}"
 
 - name: Accept the Claude principal for the Claude account
   ansible.builtin.copy:
@@ -88,6 +151,48 @@
     group: root
     mode: "0440"
     validate: visudo -cf %s
+  when: not ssh_ca_synouser.stat.exists
+
+# DSM has no visudo, so the rules are checked on the controller.
+- name: Install the Claude sudo rules on DSM
+  when: ssh_ca_synouser.stat.exists
+  vars:
+    ssh_ca_sudoers: "{{ lookup('ansible.builtin.template', 'sudoers-claude.j2') | trim }}"
+  block:
+    - name: Check the sudo rules on the controller
+      ansible.builtin.command:
+        cmd: visudo -c -f -
+        stdin: "{{ ssh_ca_sudoers }}"
+      delegate_to: localhost
+      become: false
+      changed_when: false
+      check_mode: false
+
+    - name: Install the checked sudo rules
+      ansible.builtin.copy:
+        content: "{{ ssh_ca_sudoers }}\n"
+        dest: "/etc/sudoers.d/{{ ssh_ca_claude_user }}"
+        owner: root
+        group: root
+        mode: "0440"
+
+- name: Create the sshd drop-in directory
+  ansible.builtin.file:
+    path: /etc/ssh/sshd_config.d
+    state: directory
+    owner: root
+    group: root
+    mode: "0755"
+
+# DSM's sshd_config has no Include. sshd keeps the first value it reads, so
+# the Include goes first for the drop-ins to win.
+- name: Include the sshd drop-in directory
+  ansible.builtin.lineinfile:
+    path: /etc/ssh/sshd_config
+    line: Include /etc/ssh/sshd_config.d/*.conf
+    insertbefore: BOF
+    validate: sshd -t -f %s
+  register: ssh_ca_include_line
 
 # A broken drop-in only bites on the next sshd restart, so it is tested here
 # and removed again if the full config does not parse.
@@ -100,6 +205,7 @@
         owner: root
         group: root
         mode: "0644"
+      register: ssh_ca_dropin_file
 
     - name: Test the full sshd config
       ansible.builtin.command: sshd -t
@@ -136,10 +242,11 @@
     fail_msg: "sshd -T does not show the SSH CA settings; another config line takes precedence"
 
 # The unit is sshd.service on Arch and RedHat, ssh.service on Debian/Ubuntu,
-# where sshd.service is an alias that resolves to it. sshd -T only parses the
-# files, so the running daemon is reloaded on every run; a reload keeps open
+# where sshd.service is an alias that resolves to it. The running daemon is
+# reloaded when a file it reads at start changed; a reload keeps open
 # sessions. None runs when sshd is socket activated and stopped, or per
 # connection (ssh-mesh-only role); the next start reads the config.
+# Principals and revoked keys are read per login and need no reload.
 # systemctl directly: service_facts took 3-12 s per host.
 - name: Find the running sshd unit
   ansible.builtin.command: systemctl list-units --state=running --plain --no-legend --type=service sshd.service ssh.service
@@ -161,7 +268,9 @@
       ansible.builtin.systemd:
         name: "{{ ssh_ca_sshd_units | first }}"
         state: reloaded
-      when: ssh_ca_sshd_units | length == 1
+      when:
+        - ssh_ca_sshd_units | length == 1
+        - ssh_ca_trusted_file is changed or ssh_ca_include_line is changed or ssh_ca_dropin_file is changed
 
 - name: Report the admin logins' authorized keys
   ansible.builtin.include_tasks: report.yml

ansible/roles/ssh-ca/tasks/report.yml

@@ -3,11 +3,10 @@
 # [ssh_keys_managed] have this reduced to ssh_admin_authorized_keys.
 - name: Find the admin logins' authorized_keys
   ansible.builtin.stat:
-    path: "{{ item.ansible_facts.getent_passwd[item.item][4] }}/.ssh/authorized_keys"
-  loop: "{{ ssh_ca_owner_lookup.results }}"
+    path: "{{ item[5] }}/.ssh/authorized_keys"
+  loop: "{{ ssh_ca_admin_logins }}"
   loop_control:
-    label: "{{ item.item }}"
-  when: (item.ansible_facts.getent_passwd | default({})).get(item.item) is not none
+    label: "{{ item[0] }}"
   register: ssh_ca_keyfiles
 
 - name: Fingerprint the admin logins' authorized keys

ansible/roles/ssh-ca/templates/sudoers-claude.j2

@@ -10,3 +10,6 @@
 {% for unit in ssh_ca_claude_sudo_units %}
 {{ ssh_ca_claude_user }} ALL=(root) NOPASSWD:NOEXEC: /usr/bin/systemctl restart {{ unit }}, /usr/bin/systemctl reload {{ unit }}
 {% endfor %}
+{% if ssh_ca_claude_sudo_all %}
+{{ ssh_ca_claude_user }} ALL=(ALL) NOPASSWD: ALL
+{% endif %}

ansible/site.yml

@@ -8,6 +8,8 @@
 # One-off actions are not state and stay separate: plays/update-os.yml,
 # plays/update-dist-upgrade.yml, plays/rotate-netbird-secrets.yml.
 
+- name: Synology Python
+  ansible.builtin.import_playbook: plays/configure-synology-python.yml
 - name: Base system
   ansible.builtin.import_playbook: plays/common.yml
 - name: VM time sync