Merge pull request 'feat(maintenance): new checks added, existing improved' (#6) from dev into main

Reviewed-on: #6

.gitea/workflows/deploy_new_config.yaml

@@ -16,6 +16,6 @@ jobs:
     if: github.event.pull_request.merged == true
     runs-on: ubuntu-latest
     steps:
-      - name: Trigger the webhook to start pulling new Ansible configs
+      - name: Trigger the webhook to run the playbook
         # LAN IP is used because those hosts are in the same network
         run: curl "http://192.168.0.38:9000/hooks/run-maintain-playbook"

inventory/group_vars/all/main.yaml

@@ -2,3 +2,4 @@
 
 ansible_become_passwd: "{{ ansible_password }}"
 human_admin_user: max
+proxmox_1_host: 192.168.0.2

inventory/hosts.yaml

@@ -1,13 +1,41 @@
 ---
-physical:
+all:
+  children:
+    physical:
+      proxmox_1:
+        ansible_host: "{{ proxmox_1_host }}"
+        ansible_become_password: "{{ ansible_become_passwd }}"
+        services_to_run: []
+    virtual:
       hosts:
         localhost:
           ansible_become_password: "{{ ansible_become_passwd }}"
           ansible_connection: local
           ansible_python_interpreter: "{{ ansible_playbook_python }}"
-    192.168.0.98:
+          services_to_run:
+            - webhook 
+        nfs-server:
+          ansible_host: 192.168.0.6
           ansible_become_password: "{{ ansible_become_passwd }}"
-    192.168.0.6:
+          services_to_run: []
+        jellyfin:
+          ansible_host: 192.168.0.8
           ansible_become_password: "{{ ansible_become_passwd }}"
-    192.168.0.8:
+          services_to_run: []
+        frigate:
+          ansible_host: 192.168.0.12
           ansible_become_password: "{{ ansible_become_passwd }}"
+          services_to_run: []
+        vs-code:
+          ansible_host: 192.168.0.16
+          ansible_become_password: "{{ ansible_become_passwd }}"
+          services_to_run: []
+        gitea-server:
+          ansible_host: 192.168.0.39
+          ansible_become_password: "{{ ansible_become_passwd }}"
+          services_to_run: []
+        ai-host:
+          ansible_host: 192.168.0.50
+          ansible_become_password: "{{ ansible_become_passwd }}"
+          services_to_run:
+            - coder_ai

playbooks/deploy_and_set_up_lxc_on_proxmox.yaml

@@ -25,6 +25,10 @@
       prompt: "IP address for the container (in x.x.x.x/x formant)"
       private: false
 
+    - name: lxc_is_privileged
+      prompt: "Unprivileged LXC (true/false)?"
+      private: false
+
   pre_tasks:
     - name: Validate hostname
       ansible.builtin.fail:

playbooks/maintain.yaml

@@ -1,13 +1,10 @@
 ---
 - name: Deploy and set up an LXC container in Proxmox
-  hosts: all
+  hosts: virtual
   remote_user: ansible
   
   vars_files:
     ../inventory/group_vars/all/secrets.yaml
-  vars:
-    ansible_user_passwd_hash: "{{ ansible_password | password_hash('sha512', 's3edscrj45e6r') }}"
-    user_passwd_hash: "{{ user_password | password_hash('sha512', 's3ed6123jhgcr') }}"
   
   roles:
     # Check the Internet connection
@@ -21,3 +18,5 @@
     - ../roles/harden_ssh
     # Update configs - omz, nvim, ranger and so on. Distribute the last version of those configs
     - ../roles/update_configs
+    # Make sure that the services that are supposed to run are running
+    - ../roles/check_services

requirements.txt

@@ -4,29 +4,34 @@ ansible-lint==26.6.0
 attrs==26.1.0
 black==26.5.1
 bracex==3.0
+certifi==2026.7.22
 cffi==2.1.0
+charset-normalizer==3.4.9
 click==8.4.2
 cryptography==49.0.0
 distro==1.9.0
 filelock==3.29.7
+idna==3.18
 Jinja2==3.1.6
 jsonschema==4.26.0
 jsonschema-specifications==2025.9.1
 MarkupSafe==3.0.3
 mypy_extensions==1.1.0
+netaddr==1.3.0
 packaging==26.2
 pathspec==1.1.1
 platformdirs==4.10.0
-proxmoxer>=2.3
+proxmoxer==2.3.0
 pycparser==3.0
 pytokens==0.4.1
 PyYAML==6.0.3
 referencing==0.37.0
-requests>=2.34.2
+requests==2.34.2
 resolvelib==1.2.1
 rpds-py==2026.6.3
 ruamel.yaml==0.19.1
 ruamel.yaml.clib==0.2.15
 subprocess-tee==0.4.2
+urllib3==2.7.0
 wcmatch==11.0
 yamllint==1.38.0

requirements.yaml

@@ -0,0 +1,17 @@
+---
+
+collections:
+  - name: ansible.posix
+    version: 2.2.2
+
+  - name: ansible.utils
+    version: 6.0.3
+
+  - name: community.general
+    version: 13.2.0
+
+  - name: community.library_inventory_filtering_v1
+    version: 1.1.5
+
+  - name: community.proxmox
+    version: 2.0.0

roles/check_services/tasks/main.yaml

@@ -0,0 +1,7 @@
+---
+
+- name: Make sure required services are running
+  ansible.builtin.service:
+    name: "{{ item }}"
+    state: started
+  loop: "{{ services_to_run }}"

roles/common_healthcheck/tasks/main.yaml

@@ -23,8 +23,8 @@
       become: false
       # We have to use this complicated pipeline because of Alpine and its wierd df implementation
       ansible.builtin.shell: set -o pipefail && df -h / | tail -1 | awk '{gsub(/%/, "", $5); print $5}'
-      register: free_disk_space_result
-      failed_when: free_disk_space_result.stdout | int > 85
+      register: common_healthcheck_space_left_result
+      failed_when: common_healthcheck_space_left_result.stdout | int > 85
       changed_when: false   # This task does not change the system
 
   rescue:
@@ -41,5 +41,9 @@
         body:
           - "{{ ansible_facts['hostname'] }}: Disk space is low"
       delegate_to: 127.0.0.1
-      failed_when: false
+      failed_when: false    # It's OK if it fails, not critical
       changed_when: false   # This task does not change the system
+
+    - name: Resize rootfs if it's an LXC
+      ansible.builtin.include_tasks: resize_lxc_rootfs.yaml
+      when: ansible_virtualization_type == 'lxc'

roles/common_healthcheck/tasks/resize_lxc_rootfs.yaml

@@ -0,0 +1,24 @@
+---
+- name: Get container info by name
+  delegate_to: localhost
+  become: false
+  community.general.proxmox_vm_info:
+    validate_certs: false
+    node: proxmox-server
+    api_user: root@pam
+    api_host: 192.168.0.2
+    api_token_id: ansible
+    api_token_secret: "{{ proxmox_token_secret }}"
+
+    name: "{{ inventory_hostname }}"
+    type: lxc
+  register: common_healthcheck_vmid
+
+- name: Resize LXC's rootfs
+  become: true
+  ansible.builtin.command:
+    cmd: pct resize {{ common_healthcheck_vmid.proxmox_vms[0].vmid }} rootfs +5G
+  delegate_to: 192.168.0.2
+  changed_when: true
+  vars:
+    ansible_become_password: "{{ ansible_become_passwd  }}"

roles/deploy_lxc_on_proxmox/tasks/main.yaml

@@ -6,7 +6,7 @@
     validate_certs: false
     node: proxmox-server
     api_user: root@pam
-    api_host: 192.168.0.2
+    api_host: "{{ proxmox_1_host }}"
     api_token_id: ansible
     api_token_secret: "{{ proxmox_token_secret }}"
 
@@ -14,6 +14,7 @@
     password: "{{ lxc_root_password }}"
     hostname: "{{ lxc_hostname }}"
     ostemplate: 'main:vztmpl/debian-13-golden-image.tar.gz'
+    unprivileged: "{{ lxc_is_privileged }}"
     memory: 2048
     cores: 2
     state: present
@@ -33,7 +34,7 @@
     validate_certs: false
     node: proxmox-server
     api_user: root@pam
-    api_host: 192.168.0.2
+    api_host: "{{ proxmox_1_host }}"
     api_token_id: ansible
     api_token_secret: "{{ proxmox_token_secret }}"
 

roles/deploy_vm_on_proxmox/tasks/create_vm.yaml

@@ -6,7 +6,7 @@
     validate_certs: false
     node: proxmox-server
     api_user: root@pam
-    api_host: 192.168.0.2
+    api_host: "{{ proxmox_1_host }}"
     api_token_id: ansible
     api_token_secret: "{{ proxmox_token_secret }}"
 
@@ -29,7 +29,7 @@
     validate_certs: false
     node: proxmox-server
     api_user: root@pam
-    api_host: 192.168.0.2
+    api_host: "{{ proxmox_1_host }}"
     api_token_id: ansible
     api_token_secret: "{{ proxmox_token_secret }}"
 
@@ -49,7 +49,7 @@
     validate_certs: false
     node: proxmox-server
     api_user: root@pam
-    api_host: 192.168.0.2
+    api_host: "{{ proxmox_1_host }}"
     api_token_id: ansible
     api_token_secret: "{{ proxmox_token_secret }}"
 
@@ -64,10 +64,9 @@
     validate_certs: false
     node: proxmox-server
     api_user: root@pam
-    api_host: 192.168.0.2
+    api_host: "{{ proxmox_1_host }}"
     api_token_id: ansible
     api_token_secret: "{{ proxmox_token_secret }}"
 
     name: "{{ vm_hostname }}"
     state: started
-

roles/deploy_vm_on_proxmox/tasks/main.yaml

@@ -5,7 +5,7 @@
     validate_certs: false
     node: proxmox-server
     api_user: root@pam
-    api_host: 192.168.0.2
+    api_host: "{{ proxmox_1_host }}"
     api_token_id: ansible
     api_token_secret: "{{ proxmox_token_secret }}"
     

roles/deploy_vm_on_proxmox/tasks/start_vm.yaml

@@ -6,7 +6,7 @@
     validate_certs: false
     node: proxmox-server
     api_user: root@pam
-    api_host: 192.168.0.2
+    api_host: "{{ proxmox_1_host }}"
     api_token_id: ansible
     api_token_secret: "{{ proxmox_token_secret }}"
 
@@ -19,4 +19,3 @@
     timeout: 120
   delegate_to: localhost
   changed_when: false
-

scripts/run_maintain_playbook.sh

@@ -1,3 +1,11 @@
 #!/bin/bash
+
+# 1 - Pull the latest code
+git pull origin main
+
+# 2 - Update dependencies and modules
+./scripts/update_modules.sh
+
+# 3 - Run the job
 source .venv/bin/activate
 ansible-playbook playbooks/maintain.yaml --vault-pass-file ~/vault_password -i inventory/hosts.yaml --private-key ~/.ssh/ansible_key

scripts/update_modules.sh

@@ -0,0 +1,12 @@
+#!/bin/bash
+
+source .venv/bin/activate
+
+# Install python packages
+pip install -r requirements.txt
+
+# Install collections from the file
+ansible-galaxy collection install -r requirements.yaml -p ./collections/
+
+# Install roles
+ansible-galaxy role install -r requirements.yaml -p ./roles/

systemd/ansible-maintenance.service

@@ -6,10 +6,10 @@ Wants=network-online.target
 [Service]
 Type=oneshot
 # CAHNGE TO MATCH YOUR REQUIREMENTS
-User=max
-Group=max
-WorkingDirectory=/home/max/projects/ansible_home
-ExecStart=/home/max/projects/ansible_home/run_playbook.sh /home/max/projects/ansible_home/playbooks/maintain.yaml 
+User=ansible
+Group=ansible
+WorkingDirectory=/home/ansible/ansible-production
+ExecStart=/home/ansible/ansible-production/run_maintain_playbook.sh 
 StandardOutput=journal
 StandardError=journal
 # Optional: prevent runaway if the playbook hangs

systemd/ansible-maintenance.timer

@@ -1,9 +1,9 @@
 [Unit]
-Description=Timer for Ansible maintenance playbook, runs every 10 minutes
+Description=Timer for Ansible maintenance playbook, runs every day
 Requires=ansible-maintenance.service
 
 [Timer]
-OnUnitActiveSec=10min
+OnUnitActiveSec=1d
 Persistent=true
 Unit=ansible-maintenance.service