Fix provisioning errors found during first real run

- ansible.cfg: suppress Python interpreter discovery warning
- ansible/inventory.ini: add ansible_host; server IP is now defined in
  one place and read dynamically by run-bootstrap.sh
- group_vars/all/ → directory layout so vault.yml is auto-loaded by Ansible
  (previously vault.yml did not match any group name and was silently ignored)
- scripts/run-bootstrap.sh: read server IP from inventory, chmod 600 private
  keys automatically, show actual SSH error when root login fails
- scripts/bootstrap-deploy-user.sh: add sudoers.d entry for passwordless sudo
  (deploy user has no password so sudo group membership alone was not enough)
- nextcloud: fix Redis healthcheck (CMD-SHELL pipe was unreliable in Alpine,
  switched to CMD form with start_period)
- group_vars/all/vars.yml: fix Roundcube image tag (1.6-apache and 1.6 do not
  exist; correct tag is 1.6.x-apache)
- docs/runbook.md: expand prerequisites (SSH keys section), add step 1 for
  setting the server IP, expand bootstrap step with preflight detail, fix
  step numbering

.gitignore

@@ -2,5 +2,5 @@ keys/*
 !keys/*.*
 
 # Ansible Vault secrets — never commit plain-text secrets
-ansible/group_vars/vault.yml
+ansible/group_vars/all/vault.yml
 

ansible.cfg

@@ -0,0 +1,2 @@
+[defaults]
+interpreter_python = auto_silent

ansible/group_vars/all/vars.yml

@@ -26,7 +26,7 @@ traefik_version: v3.3
 traefik_data_dir: /opt/traefik
 # htpasswd-formatted user list for the dashboard.
 # Generate with: echo $(htpasswd -nB admin) | sed -e 's/\$/\$\$/g'
-# Store the actual value in ansible/group_vars/vault.yml (Ansible Vault).
+# Store the actual value in ansible/group_vars/all/vault.yml (Ansible Vault).
 traefik_dashboard_users: ""
 
 # Gitea
@@ -36,7 +36,7 @@ gitea_data_dir: /opt/gitea
 # Set to false for the very first deploy so the admin account can be created,
 # then flip to true and redeploy to close public registration.
 gitea_disable_registration: true
-# Secrets — store values in ansible/group_vars/vault.yml (Ansible Vault)
+# Secrets — store values in ansible/group_vars/all/vault.yml (Ansible Vault)
 # gitea_db_password: ""
 # gitea_secret_key: ""      # generate: openssl rand -hex 32
 # gitea_internal_token: ""  # generate: openssl rand -hex 32
@@ -46,7 +46,7 @@ keycloak_version: "26.2"
 keycloak_db_version: "16"
 sso_data_dir: /opt/sso
 keycloak_admin_user: admin
-# Secrets — store values in ansible/group_vars/vault.yml (Ansible Vault)
+# Secrets — store values in ansible/group_vars/all/vault.yml (Ansible Vault)
 # keycloak_db_password: ""
 # keycloak_admin_password: ""
 
@@ -55,12 +55,12 @@ nextcloud_version: "31-apache"  # apache variant includes a working web server
 nextcloud_db_version: "16"
 nextcloud_data_dir: /opt/nextcloud
 nextcloud_admin_user: admin
-# Secrets — store values in ansible/group_vars/vault.yml (Ansible Vault)
+# Secrets — store values in ansible/group_vars/all/vault.yml (Ansible Vault)
 # nextcloud_db_password: ""
 # nextcloud_admin_password: ""
 
 # Mail (Roundcube webmail client)
-roundcube_version: "1.6-apache"
+roundcube_version: "1.6.x-apache"
 roundcube_db_version: "16"
 mail_data_dir: /opt/mail
 # IMAP/SMTP — set to the mail server Roundcube should connect to.
@@ -70,7 +70,7 @@ roundcube_imap_host: ""
 roundcube_imap_port: "993"
 roundcube_smtp_host: ""
 roundcube_smtp_port: "587"
-# Secrets — store values in ansible/group_vars/vault.yml (Ansible Vault)
+# Secrets — store values in ansible/group_vars/all/vault.yml (Ansible Vault)
 # roundcube_db_password: ""
 # roundcube_des_key: ""   # generate: openssl rand -hex 12  (must be exactly 24 chars)
 
@@ -79,7 +79,7 @@ registry_data_dir: /opt/registry
 # registry_htpasswd — full htpasswd file content, store in vault.yml
 # Generate with: docker run --entrypoint htpasswd httpd:2 -Bbn <user> <password>
 # Multiple users: run the command once per user and concatenate the lines.
-# Secrets — store values in ansible/group_vars/vault.yml (Ansible Vault)
+# Secrets — store values in ansible/group_vars/all/vault.yml (Ansible Vault)
 # registry_htpasswd: ""
 
 # k8s (placeholder)

ansible/inventory.ini

@@ -1,2 +1,2 @@
 [cloud]
-cloud.ladkau.de ansible_user=deploy ansible_ssh_private_key_file=../keys/notroot_cloud_ladkau_de
+cloud.ladkau.de ansible_host=217.154.207.148 ansible_user=deploy ansible_ssh_private_key_file=keys/notroot_cloud_ladkau_de

ansible/roles/nextcloud/templates/docker-compose.yml.j2

@@ -28,10 +28,11 @@ services:
     networks:
       - nextcloud_internal
     healthcheck:
-      test: ["CMD-SHELL", "redis-cli ping | grep PONG"]
+      test: ["CMD", "redis-cli", "ping"]
       interval: 10s
       timeout: 5s
       retries: 5
+      start_period: 10s
 
   nextcloud:
     image: nextcloud:{{ nextcloud_version }}

docs/runbook.md

@@ -32,12 +32,24 @@ ssh-keygen -t ed25519 -f keys/notroot_cloud_ladkau_de -C "deploy@cloud.ladkau.de
 ```
 
 Upload the root public key to the server via the Strato control panel (or paste
-it during the initial OS install) so that `root@217.154.207.148` is accessible
+it during the initial OS install) so that root SSH access is available before
-before running anything.
+running anything. The server IP is defined in `ansible/inventory.ini`
+(`ansible_host`).
 
 ## Steps
 
-### 1. Install Ansible collections
+### 1. Set the server IP
+
+Open `ansible/inventory.ini` and set `ansible_host` to the server's public IP:
+
+```ini
+cloud.ladkau.de ansible_host=<server-ip> ansible_user=deploy ansible_ssh_private_key_file=keys/notroot_cloud_ladkau_de
+```
+
+This is the only place the IP needs to be set — the bootstrap script and all
+Ansible roles read it from here.
+
+### 2. Install Ansible collections
 
 From the repo root:
 
@@ -50,28 +62,28 @@ Required collections:
 - `ansible.posix` — authorized_key module
 - `community.docker` — docker_network, docker_compose_v2 modules
 
-### 2. Configure DNS
+### 3. Configure DNS
 
-Ensure the following DNS A records point to `217.154.207.148` before running
+Ensure the following DNS A records all point to the server IP (`ansible_host`
-the playbook. Traefik requests Let's Encrypt certificates on first start and
+in `ansible/inventory.ini`) before running the playbook. Traefik requests
-DNS must resolve at that point.
+Let's Encrypt certificates on first start and DNS must resolve at that point.
 
 | Domain              | Record |
 |---------------------|--------|
-| cloud.ladkau.de     | A → 217.154.207.148 |
+| cloud.ladkau.de     | A → server IP |
-| gitea.ladkau.de     | A → 217.154.207.148 |
+| gitea.ladkau.de     | A → server IP |
-| nextcloud.ladkau.de | A → 217.154.207.148 |
+| nextcloud.ladkau.de | A → server IP |
-| sso.ladkau.de       | A → 217.154.207.148 |
+| sso.ladkau.de       | A → server IP |
-| mail.ladkau.de      | A → 217.154.207.148 |
+| mail.ladkau.de      | A → server IP |
-| cr.ladkau.de        | A → 217.154.207.148 |
+| cr.ladkau.de        | A → server IP |
-| k8s.ladkau.de       | A → 217.154.207.148 |
+| k8s.ladkau.de       | A → server IP |
 
-### 3. Create the vault and populate secrets
+### 4. Create the vault and populate secrets
 
-Create `ansible/group_vars/vault.yml` (gitignored) and encrypt it with Ansible Vault:
+Create `ansible/group_vars/all/vault.yml` (gitignored) and encrypt it with Ansible Vault:
 
 ```bash
-ansible-vault create ansible/group_vars/vault.yml
+ansible-vault create ansible/group_vars/all/vault.yml
 ```
 
 Populate all required secrets:
@@ -114,19 +126,34 @@ bash scripts/check-vault.sh
 To edit the vault later:
 
 ```bash
-ansible-vault edit ansible/group_vars/vault.yml
+ansible-vault edit ansible/group_vars/all/vault.yml
 ```
 
-### 4. Bootstrap the deploy user
+### 5. Bootstrap the deploy user
-
-Copies the bootstrap script to the server, runs it as root, and verifies the
-deploy user can log in. Also runs `check-vault.sh` as a preflight check.
 
 ```bash
 bash scripts/run-bootstrap.sh
 ```
 
-### 5. Run the Ansible master playbook
+The script runs the following steps in order:
+
+**Preflight checks (local)**
+1. Verifies all four key files exist under `keys/` (both root and deploy key pairs)
+2. Verifies `scripts/bootstrap-deploy-user.sh` exists
+3. Sets `chmod 600` on the private key files (SSH refuses keys with open permissions)
+4. Runs `scripts/check-vault.sh` — decrypts the vault and confirms all 11 required
+   secrets are present and non-empty
+
+**Remote actions**
+5. Opens a test SSH connection as `root` to confirm the root key works
+6. Copies `bootstrap-deploy-user.sh` to `/root/` on the server via `scp`
+7. Executes it as root — creates the `deploy` user, grants passwordless sudo,
+   and installs `keys/notroot_cloud_ladkau_de.pub` as the only authorized key
+8. Opens a test SSH connection as `deploy` to confirm the new user can log in
+
+If any step fails the script exits immediately with a descriptive error message.
+
+### 6. Run the Ansible master playbook
 
 ```bash
 ansible-playbook -i ansible/inventory.ini ansible/site.yml --ask-vault-pass
@@ -160,7 +187,7 @@ ansible-playbook -i ansible/inventory.ini ansible/site.yml --tags <role> --ask-v
 it to `false` in `vault.yml` so the setup wizard can create the admin account:
 
 ```bash
-ansible-vault edit ansible/group_vars/vault.yml
+ansible-vault edit ansible/group_vars/all/vault.yml
 # add: gitea_disable_registration: false
 ansible-playbook -i ansible/inventory.ini ansible/site.yml --tags gitea --ask-vault-pass
 ```

scripts/bootstrap-deploy-user.sh

@@ -22,6 +22,10 @@ fi
 echo "==> Adding '${DEPLOY_USER}' to sudo group"
 usermod -aG sudo "${DEPLOY_USER}"
 
+echo "==> Granting '${DEPLOY_USER}' passwordless sudo"
+echo "${DEPLOY_USER} ALL=(ALL) NOPASSWD: ALL" > "/etc/sudoers.d/${DEPLOY_USER}"
+chmod 440 "/etc/sudoers.d/${DEPLOY_USER}"
+
 echo "==> Installing SSH authorized key"
 SSH_DIR="/home/${DEPLOY_USER}/.ssh"
 AUTH_KEYS="${SSH_DIR}/authorized_keys"

scripts/check-vault.sh

@@ -7,7 +7,7 @@ set -euo pipefail
 
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 REPO_ROOT="$(cd "${SCRIPT_DIR}/.." && pwd)"
-VAULT_FILE="${REPO_ROOT}/ansible/group_vars/vault.yml"
+VAULT_FILE="${REPO_ROOT}/ansible/group_vars/all/vault.yml"
 
 REQUIRED_KEYS=(
   traefik_dashboard_users

scripts/run-bootstrap.sh

@@ -9,7 +9,12 @@ set -euo pipefail
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 REPO_ROOT="$(cd "${SCRIPT_DIR}/.." && pwd)"
 
-SERVER="217.154.207.148"
+SERVER=$(grep -oP '(?<=ansible_host=)\S+' "${REPO_ROOT}/ansible/inventory.ini" | head -1)
+if [ -z "${SERVER}" ]; then
+  echo "ERROR: could not find ansible_host in ansible/inventory.ini" >&2
+  exit 1
+fi
+
 ROOT_KEY="${REPO_ROOT}/keys/root_cloud_ladkau_de"
 DEPLOY_KEY="${REPO_ROOT}/keys/notroot_cloud_ladkau_de"
 DEPLOY_PUBKEY="${REPO_ROOT}/keys/notroot_cloud_ladkau_de.pub"
@@ -37,6 +42,9 @@ if [ ! -f "${BOOTSTRAP_SCRIPT}" ]; then
   exit 1
 fi
 
+# SSH private keys must not be group/world readable
+chmod 600 "${ROOT_KEY}" "${DEPLOY_KEY}"
+
 # --- Vault check ---
 
 bash "${SCRIPT_DIR}/check-vault.sh"
@@ -46,10 +54,18 @@ SSH_OPTS="-o StrictHostKeyChecking=accept-new -o ConnectTimeout=10"
 # --- Verify root access ---
 
 echo "==> Verifying root SSH access to ${SERVER}"
-if ! ssh ${SSH_OPTS} -i "${ROOT_KEY}" "root@${SERVER}" "echo ok" &>/dev/null; then
+if ! ssh ${SSH_OPTS} -i "${ROOT_KEY}" "root@${SERVER}" "echo ok" 2>/tmp/ssh_root_err; then
   echo "ERROR: cannot connect as root to ${SERVER}" >&2
+  echo "       SSH error: $(cat /tmp/ssh_root_err)" >&2
+  echo "" >&2
+  echo "Possible causes:" >&2
+  echo "  - Root public key not uploaded to the server (Strato control panel)" >&2
+  echo "  - Wrong key file: ${ROOT_KEY}" >&2
+  echo "  - Server not yet reachable (still booting?)" >&2
+  rm -f /tmp/ssh_root_err
   exit 1
 fi
+rm -f /tmp/ssh_root_err
 
 # --- Copy and run the bootstrap script ---