ansible/README.md

@@ -14,16 +14,19 @@ to S3, not on a Hetzner volume - see `../readme.md`.
 - `inventory/hcloud.yml` - dynamic inventory, queries the Hetzner Cloud API
   directly (not Terraform state) and groups servers by their `role` label
   (`role_dev`, `role_prod`, `role_vpn` - set in `infra/modules/<host>/main.tf`).
-- `group_vars/` - `all.yml` (shared: `deploy_user`, SSH key path,
-  `backup_s3_*` S3 backup credentials), `role_dev.yml` / `role_prod.yml` /
-  `role_vpn.yml` (per-role vars, e.g. `service_group`).
 - `roles/bootstrap/` - Docker install, `deploy` user creation, SSH hardening,
   unattended-upgrades. Replaces `infra/scripts/bootstrap.sh.tftpl`.
 - `roles/deploy/` - copies `services/<host>/` to the server and renders `.env`
   (S3 backup credentials, see `../readme.md`) and, for `dev`,
   `Runners/docker-compose.yml`.
 - `playbooks/` - `bootstrap.yml`, `deploy.yml`, `spinup.yml`, `spindown.yml`,
-  and `site.yml` (all three in order).
+  `site.yml` (all three in order), and `group_vars/` (`all.yml` - shared:
+  `deploy_user`, SSH key path, `backup_s3_*` S3 backup credentials;
+  `role_dev.yml` / `role_prod.yml` / `role_vpn.yml` - per-role vars, e.g.
+  `service_group`). `group_vars/` lives here rather than at the `ansible/`
+  root because Ansible only auto-loads `group_vars/`/`host_vars/` from
+  directories adjacent to the playbook file or the inventory source - not
+  from an arbitrary sibling directory.
 
 ## Prerequisites
 
@@ -41,7 +44,7 @@ export BACKUP_S3_ENDPOINT=your-s3-endpoint   # omit for real AWS S3
 persists your answers to `../.control.env` (gitignored) so you don't have to
 re-export them every session.
 
-`deploy_user` (see `group_vars/all.yml`) defaults to `deploy` - override with
+`deploy_user` (see `playbooks/group_vars/all.yml`) defaults to `deploy` - override with
 the `DEPLOY_USER` env var if you want a different non-root user created on each
 host. `ansible_ssh_private_key_file` (same file) defaults to
 `~/.ssh/id_ed25519` - override with `ANSIBLE_SSH_PRIVATE_KEY_FILE` if you use a

infra/main.tf

@@ -31,6 +31,17 @@ locals {
     { zone = "luke-else.co.uk", name = "vpn", value = module.vpn.ipv4 },
     { zone = "luke-else.co.uk", name = "traefik.vpn", value = module.vpn.ipv4 },
   ]
+
+  # Microsoft 365 mail records for luke-else.co.uk - carried over from the
+  # domain's old DNS provider (pre-Hetzner), not previously applied here, so
+  # these are genuinely new to the Hetzner zone rather than something to
+  # import.
+  mail_records = [
+    { zone = "luke-else.co.uk", name = "@", type = "MX", value = "0 lukeelse-co-uk01b.mail.protection.outlook.com." },
+    { zone = "luke-else.co.uk", name = "@", type = "TXT", value = "\"v=spf1 include:spf.protection.outlook.com -all\"" },
+    { zone = "luke-else.co.uk", name = "@", type = "TXT", value = "\"google-site-verification=aKLk5BATowKUwNbFcU5zyfu-AIyCW9W9PBStePRjH3U\"" },
+    { zone = "luke-else.co.uk", name = "autodiscover", type = "CNAME", value = "autodiscover.outlook.com." },
+  ]
 }
 
 module "network" {
@@ -87,5 +98,5 @@ module "dns" {
   source = "./modules/dns"
 
   zone_names = var.dns_zones
-  records    = local.dns_records
+  records    = concat(local.dns_records, local.mail_records)
 }

infra/modules/dns/main.tf

@@ -14,15 +14,29 @@ resource "hcloud_zone" "this" {
   }
 }
 
-resource "hcloud_zone_rrset" "a" {
-  for_each = { for r in var.records : "${r.zone}/${r.name}" => r }
+locals {
+  # Group flat var.records entries by zone/name/type into one set of values
+  # each, since a Hetzner RRSet is keyed on (zone, name, type) and can hold
+  # several values (e.g. an SPF and a google-site-verification TXT both live
+  # under the same "@" TXT RRSet).
+  rrsets = {
+    for key, items in { for r in var.records : "${r.zone}/${r.name}/${r.type}" => r... } : key => {
+      zone   = items[0].zone
+      name   = items[0].name
+      type   = items[0].type
+      ttl    = items[0].ttl
+      values = [for i in items : i.value]
+    }
+  }
+}
+
+resource "hcloud_zone_rrset" "this" {
+  for_each = local.rrsets
 
   zone = hcloud_zone.this[each.value.zone].id
   name = each.value.name
-  type = "A"
+  type = each.value.type
   ttl  = each.value.ttl
 
-  records = [
-    { value = each.value.value }
-  ]
+  records = [for v in each.value.values : { value = v }]
 }

infra/modules/dns/moved.tf

@@ -0,0 +1,60 @@
+# Generalizing hcloud_zone_rrset.a (for_each keyed "zone/name", A records
+# only) into hcloud_zone_rrset.this (keyed "zone/name/type", any record type)
+# changed every existing instance's resource address. Without these, `tofu
+# apply` would destroy and recreate every A record already in state instead of
+# just adding the new mail records - these moved blocks make it a no-op rename
+# for anything that already existed. Safe to delete once applied and merged.
+moved {
+  from = hcloud_zone_rrset.a["luke-else.co.uk/@"]
+  to   = hcloud_zone_rrset.this["luke-else.co.uk/@/A"]
+}
+
+moved {
+  from = hcloud_zone_rrset.a["luke-else.co.uk/dev"]
+  to   = hcloud_zone_rrset.this["luke-else.co.uk/dev/A"]
+}
+
+moved {
+  from = hcloud_zone_rrset.a["luke-else.co.uk/metarius"]
+  to   = hcloud_zone_rrset.this["luke-else.co.uk/metarius/A"]
+}
+
+moved {
+  from = hcloud_zone_rrset.a["luke-else.co.uk/traefik"]
+  to   = hcloud_zone_rrset.this["luke-else.co.uk/traefik/A"]
+}
+
+moved {
+  from = hcloud_zone_rrset.a["luke-else.co.uk/status"]
+  to   = hcloud_zone_rrset.this["luke-else.co.uk/status/A"]
+}
+
+moved {
+  from = hcloud_zone_rrset.a["luke-else.co.uk/bitwarden"]
+  to   = hcloud_zone_rrset.this["luke-else.co.uk/bitwarden/A"]
+}
+
+moved {
+  from = hcloud_zone_rrset.a["luke-else.co.uk/rd"]
+  to   = hcloud_zone_rrset.this["luke-else.co.uk/rd/A"]
+}
+
+moved {
+  from = hcloud_zone_rrset.a["luke-else.co.uk/git"]
+  to   = hcloud_zone_rrset.this["luke-else.co.uk/git/A"]
+}
+
+moved {
+  from = hcloud_zone_rrset.a["luke-else.co.uk/traefik.cicd"]
+  to   = hcloud_zone_rrset.this["luke-else.co.uk/traefik.cicd/A"]
+}
+
+moved {
+  from = hcloud_zone_rrset.a["luke-else.co.uk/vpn"]
+  to   = hcloud_zone_rrset.this["luke-else.co.uk/vpn/A"]
+}
+
+moved {
+  from = hcloud_zone_rrset.a["luke-else.co.uk/traefik.vpn"]
+  to   = hcloud_zone_rrset.this["luke-else.co.uk/traefik.vpn/A"]
+}

infra/modules/dns/variables.tf

@@ -4,11 +4,20 @@ variable "zone_names" {
 }
 
 variable "records" {
-  description = "A records to create across the zones in var.zone_names. Use name = \"@\" for the zone apex."
+  description = <<-EOT
+    Records to create across the zones in var.zone_names. Use name = "@" for
+    the zone apex. Entries sharing the same zone/name/type become a single
+    Hetzner RRSet with multiple values (e.g. two TXT strings under the same
+    name) - Hetzner has no concept of separate same-type records otherwise.
+    For MX, embed the priority in value using standard zonefile syntax (e.g.
+    "10 mail.example.com."); Hetzner's API has no separate priority field.
+    For TXT, wrap value in escaped double quotes (e.g. "\"v=spf1 ...\"").
+  EOT
   type = list(object({
     zone  = string
     name  = string
     value = string
+    type  = optional(string, "A")
     ttl   = optional(number, 300)
   }))
   default = []

infra/variables.tf

@@ -13,25 +13,25 @@ variable "network_zone" {
 variable "server_image" {
   description = "OS image used for all servers."
   type        = string
-  default     = "ubuntu-24.04"
+  default     = "ubuntu-26.04"
 }
 
 variable "dev_server_type" {
   description = "Server type for dev"
   type        = string
-  default     = "cx22"
+  default     = "cx23"
 }
 
 variable "prod_server_type" {
   description = "Server type for prod"
   type        = string
-  default     = "cx22"
+  default     = "cx23"
 }
 
 variable "vpn_server_type" {
   description = "Server type for vpn"
   type        = string
-  default     = "cx22"
+  default     = "cx23"
 }
 
 variable "network_ip_range" {

readme.md

@@ -85,11 +85,12 @@ Each host's stateful data lives in local named Docker volumes, backed up nightly
 │       └── dns/                # Hetzner DNS zones + A records for every domain in var.dns_zones
 ├── ansible/                   # Ansible: bootstraps each server and deploys/starts services/<host>/ onto it
 │   ├── inventory/hcloud.yml   # dynamic inventory — queries the Hetzner API, groups by the role label above
-│   ├── group_vars/            # deploy_user, service_group, backup_s3_*, etc.
 │   ├── roles/
 │   │   ├── bootstrap/          # Docker, deploy user, sshd hardening, unattended-upgrades
 │   │   └── deploy/             # copies services/<host>/, renders .env (S3 backup credentials) + Runners/docker-compose.yml
-│   └── playbooks/              # bootstrap.yml, deploy.yml, spinup.yml, spindown.yml, site.yml
+│   └── playbooks/              # bootstrap.yml, deploy.yml, spinup.yml, spindown.yml, site.yml,
+│       └── group_vars/          # deploy_user, service_group, backup_s3_*, etc. - must sit next to
+│                                 # the playbooks for Ansible to auto-load it (see ansible/README.md)
 ├── services/                 # Docker Compose stacks, grouped by which server they run on
 │   ├── dev/                   # Gitea + CI runner + Traefik + backup/restore (git.luke-else.co.uk, cicd.luke-else.co.uk)
 │   ├── prod/                  # Websites, Bitwarden, RustDesk, status page + Traefik + backup/restore
@@ -159,13 +160,23 @@ OpenTofu never connects to the servers over SSH — no provisioners, no `bootstr
 
 ### Managing DNS
 
-`module.dns` (in `infra/modules/dns`) creates one Hetzner DNS zone per domain in `var.dns_zones` (default: `luke-else.co.uk`, `divine-couture.co.uk`, `snexo.co.uk`) and an `hcloud_zone_rrset` A record for every hostname currently referenced by a Traefik `Host()` rule anywhere under `services/` — kept in sync with `local.dns_records` in `infra/main.tf`, pointed at whichever of `dev`/`prod`/`vpn` actually serves it. Zones have `prevent_destroy = true`, matching the volumes — losing one deletes every record in it.
+`module.dns` (in `infra/modules/dns`) creates one Hetzner DNS zone per domain in `var.dns_zones` (default: `luke-else.co.uk`, `divine-couture.co.uk`, `snexo.co.uk`) and an `hcloud_zone_rrset` per record in `var.records` — kept in sync with `local.dns_records` (A records, one per hostname currently referenced by a Traefik `Host()` rule anywhere under `services/`, pointed at whichever of `dev`/`prod`/`vpn` actually serves it) and `local.mail_records` (see below) in `infra/main.tf`. Zones have `prevent_destroy = true`, matching the volumes — losing one deletes every record in it.
 
 Creating the zone doesn't make Hetzner authoritative for the domain by itself: you still need to point that domain's NS records at Hetzner's nameservers at whichever registrar it's registered through. Run `tofu output dns_nameservers` after applying to get the exact nameservers per domain, and set those as the domain's NS records at the registrar. Propagation can take a while depending on the registrar and the domain's previous NS TTL.
 
 Adding a new subdomain: add an entry to `local.dns_records` in `infra/main.tf` (zone, name, and the target `module.<host>.ipv4`) and re-run `tofu apply` — don't hand-create records in the Hetzner console, they'll drift from state. Note `name = "@"` is Hetzner's convention for a zone's apex record (e.g. bare `snexo.co.uk`), not an empty string.
 
-Only A records for IPv4 are managed here — none of the modules currently track servers' IPv6 addresses, so AAAA records aren't generated even though the firewalls already allow IPv6 traffic.
+Only A records for IPv4 are managed for hosts — none of the modules currently track servers' IPv6 addresses, so AAAA records aren't generated even though the firewalls already allow IPv6 traffic.
+
+`var.records` isn't limited to A records: each entry takes an optional `type` (`A` by default, or `MX`/`TXT`/`CNAME`/etc.), and entries sharing the same `zone`/`name`/`type` are merged into a single Hetzner RRSet with multiple values (needed for e.g. two TXT strings under the same name) - see `infra/modules/dns/variables.tf` for the exact value format each type expects (MX embeds the priority in the value string, TXT values need escaped double quotes).
+
+#### Mail records (Microsoft 365)
+
+`local.mail_records` in `infra/main.tf` tracks the DNS records Microsoft 365 needs for `luke-else.co.uk` - the MX record, the SPF and Google-site-verification TXT records (merged into one `@` TXT RRSet), and the `autodiscover` CNAME. These carried over from the domain's DNS provider prior to Hetzner and were never applied to the Hetzner zone, so they're genuinely new records here (not something to `tofu import` - nothing to collide with).
+
+**Not yet included:** a DMARC policy (`_dmarc` TXT) and DKIM signing (two `selector1._domainkey`/`selector2._domainkey` CNAMEs). DKIM's targets are generated per-tenant by Microsoft 365 (Defender portal → Email & collaboration → Policies & rules → DKIM) and can't be guessed - enable DKIM there first, then add the two CNAMEs it gives you to `local.mail_records`.
+
+`infra/modules/dns/moved.tf` re-points every pre-existing A record at its new resource address, since generalizing the module to support non-A record types changed how they're keyed internally - without it, `tofu apply` would destroy and recreate every A record for no functional reason. It's a one-time migration aid: run `tofu plan` first to confirm the only real changes are the new mail records being created, then the file can be deleted after a successful apply.
 
 ## Bootstrapping and deploying with Ansible (`ansible/`)
 
@@ -310,5 +321,5 @@ Then reopen the repo in VS Code with the Dev Containers extension.
 - SSH to `dev` and `prod` is restricted to the `vpn` server's own public IP — you must be tunneled into the VPN to reach them over SSH. SSH to `vpn` itself is gated by `var.allowed_ssh_source_ips`; narrow this from the default `0.0.0.0/0` once you know your own egress IP(s).
 - `vpn` is intentionally excluded from the private network so that a compromised VPN endpoint cannot reach `dev` or `prod` directly over it — SSH access still works because the VPN's egress traffic is NATed through its own public IP.
 - Firewalls are allowlists scoped per host in `infra/modules/<host>/main.tf` — only ports actually used by that host's compose stacks (plus the cross-host private network range) are open.
-- Every host's [Ansible bootstrap role](ansible/roles/bootstrap/tasks/main.yml) disables SSH password authentication, restricts root login to key-only, and creates a separate sudo user (`deploy_user`, see `ansible/group_vars/all.yml`) for day-to-day access.
+- Every host's [Ansible bootstrap role](ansible/roles/bootstrap/tasks/main.yml) disables SSH password authentication, restricts root login to key-only, and creates a separate sudo user (`deploy_user`, see `ansible/playbooks/group_vars/all.yml`) for day-to-day access.
 - DNS zones (`modules/dns`) carry both Hetzner's own `delete_protection` and Terraform's `prevent_destroy` — losing a zone takes every record in it with it, including for `divine-couture.co.uk` and `snexo.co.uk`, not just `luke-else.co.uk`.

services/dev/backup-docker-compose.yml

@@ -26,7 +26,7 @@ services:
   # Run explicitly by spinup.sh before the services that own these volumes
   # start - not started by `docker compose up`.
   restore:
-    image: amazon/aws-cli:2
+    image: amazon/aws-cli:latest
     container_name: backup-restore
     entrypoint: ["/bin/bash", "/restore.sh"]
     environment:

services/prod/backup-docker-compose.yml

@@ -31,7 +31,7 @@ services:
   # Run explicitly by spinup.sh before the services that own these volumes
   # start - not started by `docker compose up`.
   restore:
-    image: amazon/aws-cli:2
+    image: amazon/aws-cli:latest
     container_name: backup-restore
     entrypoint: [ "/bin/bash", "/restore.sh" ]
     environment:

services/vpn/backup-docker-compose.yml

@@ -26,7 +26,7 @@ services:
   # Run explicitly by spinup.sh before the services that own these volumes
   # start - not started by `docker compose up`.
   restore:
-    image: amazon/aws-cli:2
+    image: amazon/aws-cli:latest
     container_name: backup-restore
     entrypoint: ["/bin/bash", "/restore.sh"]
     environment:

services/vpn/vpn-docker-compose.yml

@@ -2,13 +2,15 @@ services:
   dockovpn:
     image: alekslitvinenk/openvpn
     cap_add:
-        - NET_ADMIN
+      - NET_ADMIN
     ports:
-        - 1194:1194/udp # Expose tcp if you defined HOST_TUN_PROTOCOL=tcp
+      - 1194:1194/udp # Expose tcp if you defined HOST_TUN_PROTOCOL=tcp
+    networks:
+      - proxy
     environment:
-        HOST_ADDR: vpn.luke-else.co.uk # Your VPN server address 
+      HOST_ADDR: vpn.luke-else.co.uk # Your VPN server address 
     volumes:
-        - openvpn_data:/opt/Dockovpn_data
+      - openvpn_data:/opt/Dockovpn_data
     labels:
       ## Expose vpn Through Trefik ##
       - "traefik.enable=true" # <== Enable traefik to proxy this container
@@ -26,6 +28,10 @@ services:
       - "traefik.http.routers.vpn.tls.certresolver=myresolver"
     restart: always
 
+networks:
+  proxy:
+    external: true
+
 volumes:
   openvpn_data:
     name: openvpn_data