feat(talos): authenticate kube-apiserver against ZITADEL (#87)

Co-authored-by: rock <[email protected]>

terraform/main.tf

@@ -39,6 +39,9 @@ resource "local_file" "controlplane_configs" {
     dns_servers            = var.cluster_config.dns_servers
     forgejo_registry_ip    = var.forgejo_registry_ip
     forgejo_hostname       = var.forgejo_hostname
+    oidc_issuer_hostname   = var.oidc_issuer_hostname
+    oidc_issuer_ip         = var.oidc_issuer_ip
+    oidc_client_id         = var.oidc_client_id
     zone                   = each.value.zone
     allow_scheduling       = each.value.allow_scheduling
     coredns_corefile       = file("${path.module}/files/coredns/Corefile")

terraform/templates/controlplane.tftpl

@@ -33,6 +33,14 @@ machine:
       - ip: ${forgejo_registry_ip}
         aliases:
           - ${forgejo_hostname}
+      # kube-apiserver's static pod runs on the host network, so it resolves the
+      # OIDC issuer through THIS node's DNS, not cluster CoreDNS. Pin the issuer
+      # to the ingress LoadBalancer so discovery stays on the LAN and presents
+      # the publicly-trusted Let's Encrypt wildcard certificate. Without this
+      # entry the lookup leaves via public DNS and Cloudflare.
+      - ip: ${oidc_issuer_ip}
+        aliases:
+          - ${oidc_issuer_hostname}
   kubelet:
     image: ${kubelet_image}
     defaultRuntimeSeccompProfileEnabled: true
@@ -120,10 +128,31 @@ cluster:
       - ${san}
 %{ endfor ~}
     image: ${kube_apiserver_img}
-    # No OIDC block. The cluster authenticates with client certificates. An
+    # OIDC authentication against ZITADEL. Additive: client-certificate auth
-    # earlier Authentik-based kube-apiserver OIDC config was removed from the
+    # (this session's own admin@homelab-cluster kubeconfig, system:masters)
-    # live nodes, and leaving it here would re-add an issuer that no longer
+    # keeps working unchanged, so a bad value here degrades OIDC logins rather
-    # resolves on any future machine-config render.
+    # than locking anyone out.
+    #
+    # The issuer has NO trailing slash and NO /application/o/<app>/ suffix.
+    # That suffix belonged to the Authentik scheme; the apiserver compares `iss`
+    # in the id_token by exact string equality, so the stale value made every
+    # OIDC login fail once Authentik stopped running.
+    #
+    # Groups: ZITADEL asserts roles as a nested urn claim that the apiserver
+    # cannot read. The `groupsClaim` action in ZITADEL mirrors the bare role
+    # names into a flat `groups` claim, which is what oidc-groups-claim consumes.
+    # Verified end to end: a PKCE id_token for this client carries
+    # groups=[homelab-admins, ...], email and preferred_username.
+    #
+    # Prefixes keep OIDC identities from colliding with built-in system:* users
+    # and groups. k8s RBAC bindings therefore target `oidc:homelab-admins`.
+    extraArgs:
+      oidc-issuer-url: https://${oidc_issuer_hostname}
+      oidc-client-id: "${oidc_client_id}"
+      oidc-username-claim: email
+      oidc-groups-claim: groups
+      oidc-username-prefix: "oidc:"
+      oidc-groups-prefix: "oidc:"
     admissionControl:
       - name: PodSecurity
         configuration:

terraform/variables.tf

@@ -198,3 +198,42 @@ variable "forgejo_hostname" {
   default     = "forgejo.riotpiao.com"
   description = "Forgejo external hostname"
 }
+
+# ── kube-apiserver OIDC (ZITADEL) ────────────────────────────────────────────
+# Authenticates `kubectl` against ZITADEL instead of client certificates only.
+# Client-certificate auth keeps working in parallel, so a wrong value here
+# degrades OIDC logins without locking anyone out.
+#
+# The issuer is ZITADEL's external host with NO trailing slash and NO
+# /application/o/<app>/ suffix — a leftover of the Authentik scheme. The
+# apiserver validates `iss` in the id_token for exact string equality.
+variable "oidc_issuer_hostname" {
+  type        = string
+  default     = "zitadel.riotpiao.com"
+  description = "Hostname of the OIDC issuer (ZITADEL). Becomes https://<host> as the issuer."
+}
+
+variable "oidc_issuer_ip" {
+  type        = string
+  default     = "192.168.1.160"
+  description = <<-EOT
+    Address the nodes resolve the OIDC issuer to, via extraHostEntries.
+
+    kube-apiserver's static pod runs on the host network, so it resolves the
+    issuer through the node's own DNS, not cluster CoreDNS. Pointing it at the
+    ingress-nginx LoadBalancer keeps OIDC discovery on the LAN and serves the
+    publicly-trusted Let's Encrypt *.riotpiao.com certificate. Without this the
+    lookup leaves via public DNS and Cloudflare, and discovery either hairpins
+    or fails.
+  EOT
+}
+
+variable "oidc_client_id" {
+  type        = string
+  default     = "396757803089330177"
+  description = <<-EOT
+    ZITADEL client id of the `kubernetes` OIDC application (PKCE, no secret).
+    Must be a STRING: the id is an 18-digit number and an unquoted YAML scalar
+    would be parsed as a float and rejected.
+  EOT
+}