feat(ipa/docker): grant docker access via IPA group membership

Create an IPA group "docker-access" (GID 50010) and pin the local
"docker" group to that GID on all Docker hosts.  Any IPA user in the
docker-access group automatically gains docker socket access through
SSSD supplementary-group resolution — no per-host docker.members
entry needed.

Specific changes:
- variables.nix: add dockerAccessGid = 50010
- modules/docker/enable-service.nix: lib.mkForce docker GID to
  dockerAccessGid, removing the need to name individual IPA users
- modules/build-types/docker.nix: remove direct wayne docker.members
  entry (access now comes from IPA group)
- modules/ipa/client.nix: refactor repeated security.* / systemd.*
  top-level keys into merged attribute sets (fixes statix W20); add
  security.pam.services.lightdm.makeHomeDir so the GUI login path
  also creates the home dir on first login

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

hosts/docker/host.nix

@@ -14,6 +14,11 @@
   };
   boot.zfs.forceImportRoot = false;
 
+  # Only advertise the LAN interface to IPA DNS. Without this, SSSD registers
+  # every Docker bridge (172.x.x.x) as an A record for docker.sweet.home —
+  # the default dyndns.interface = "*" catches them all.
+  security.ipa.dyndns.interface = vars.lxcLanInterface; # eth0
+
   # Preserved from the pre-refactor `docker` target — stateVersion must never
   # be bumped on an already-installed machine.
   system.stateVersion = "25.05";

modules/common/aliases.nix

@@ -1,50 +1,7 @@
-{ config, pkgs, lib, vars, ... }:
+_:
 
-let
-  # Flake attribute names are now <platform>-<buildtype> (e.g. proxmox-docker)
-  # and no longer match networking.hostName, since a host's hostname stays
-  # fixed while the platform backing it can change. Each nixosConfiguration
-  # stamps its own active target name into /etc/flake-target at build time.
-  mySwitchCmd = ''
-    sudo nixos-rebuild switch \
-      --no-write-lock-file \
-      --refresh \
-      --flake git+https://${vars.lanDomain}/beatzaplenty/nixos.git#$(cat /etc/flake-target)
-  '';
-  myTestCmd = ''
-    sudo nixos-rebuild test \
-      --no-write-lock-file \
-      --refresh \
-      --flake git+https://${vars.lanDomain}/beatzaplenty/nixos.git#$(cat /etc/flake-target)
-  '';
-
-  # lxc-* hosts pre-seed their SSH host key at build time (see
-  # modules/platforms/lxc.nix) so sops-nix's .sops.yaml recipient matches on
-  # first boot -- without it, secrets permanently fail to decrypt (see that
-  # file's comment for the confirmed failure). That requires --impure plus
-  # NIXOS_HOST_KEYS_DIR pointing at the repo's host-keys/ dir, same pattern
-  # docs/auto-installer.md uses for the installer ISO. A function, not a
-  # shellAlias, since the target name has to interpolate into the middle of
-  # the flake attribute path, not just append after it. Must be run from the
-  # repo root, same as every other host-keys/ command in this repo.
-  buildImageFn = ''
-    buildImage() {
-      if [ -z "$1" ]; then
-        echo "usage: buildImage <flake-target>  (e.g. lxc-docker)" >&2
-        return 1
-      fi
-      NIXOS_HOST_KEYS_DIR="$(pwd)/host-keys" nix build --impure \
-        ".#nixosConfigurations.$1.config.system.build.tarball"
-    }
-  '';
-in
 {
-  programs.bash = {
-    enable = true;
-    shellAliases = {
-      "Switch-nix" = mySwitchCmd;
-      "Test-nix" = myTestCmd;
-    };
-    initExtra = buildImageFn;
-  };
+  # Switch-nix, Test-nix, and buildImage are defined system-wide in
+  # modules/common/configuration.nix so all users (including IPA accounts)
+  # get them. Add any Home-Manager-only per-user shell config here.
 }

modules/common/configuration.nix

@@ -1,5 +1,29 @@
 { config, lib, pkgs, vars, ... }:
 
+let
+  switchCmd = ''
+    sudo nixos-rebuild switch \
+      --no-write-lock-file \
+      --refresh \
+      --flake git+https://${vars.lanDomain}/beatzaplenty/nixos.git#$(cat /etc/flake-target)
+  '';
+  testCmd = ''
+    sudo nixos-rebuild test \
+      --no-write-lock-file \
+      --refresh \
+      --flake git+https://${vars.lanDomain}/beatzaplenty/nixos.git#$(cat /etc/flake-target)
+  '';
+  buildImageFn = ''
+    buildImage() {
+      if [ -z "$1" ]; then
+        echo "usage: buildImage <flake-target>  (e.g. lxc-docker)" >&2
+        return 1
+      fi
+      NIXOS_HOST_KEYS_DIR="$(pwd)/host-keys" nix build --impure \
+        ".#nixosConfigurations.$1.config.system.build.tarball"
+    }
+  '';
+in
 {
   imports =
     [
@@ -8,6 +32,16 @@
       ./set-locale.nix
       ../ipa/client.nix
     ];
+
+  # System-wide shell config so all users (including IPA accounts) get the
+  # same management aliases as the local nixos user's Home Manager provides.
+  programs.bash = {
+    shellAliases = {
+      "Switch-nix" = switchCmd;
+      "Test-nix" = testCmd;
+    };
+    interactiveShellInit = buildImageFn;
+  };
   # Use the GRUB 2 boot loader.
   # boot.loader.grub.enable = true;
   #boot.loader.grub.device = "/dev/sda"; # or "nodev" for efi only

modules/docker/enable-service.nix

@@ -1,4 +1,4 @@
-{ pkgs, vars, ... }:
+{ lib, pkgs, vars, ... }:
 
 {
   #  virtualisation.docker.enable = true;
@@ -15,6 +15,12 @@
     #    experimental = true;
     #  };
   };
+  # Pin the docker group GID to match the IPA "docker-access" group so that
+  # IPA group membership alone grants access to the Docker socket. Any user
+  # whose supplementary groups (resolved by SSSD from IPA) include GID
+  # vars.dockerAccessGid will pass the socket group-permission check without
+  # any per-host users.groups.docker.members entry.
+  users.groups.docker.gid = lib.mkForce vars.dockerAccessGid;
   users.users.${vars.primaryUser}.extraGroups = [ "docker" ];
   environment.systemPackages = with pkgs; [
     docker-compose

modules/ipa/client.nix

@@ -19,7 +19,7 @@
 #        sops -e --input-type binary -i secrets/<host>.keytab
 #   d. Commit secrets/<host>.keytab and the updated .sops.yaml, then deploy.
 #
-# vars dependencies: homeDomain, ipaServer, domainControllerIp
+# vars dependencies: homeDomain, ipaServer, domainControllerIp, ipaUser
 
 { config, lib, pkgs, vars, ... }:
 
@@ -38,42 +38,113 @@ lib.mkIf enabled {
   networking.domain = lib.mkDefault vars.homeDomain;
   networking.nameservers = lib.mkDefault [ vars.domainControllerIp ];
 
-  security.ipa = {
-    enable = true;
-    domain = vars.homeDomain;
-    inherit realm;
-    server = vars.ipaServer;
-    certificate = caCertPkg;
-    inherit basedn;
-    ipaHostname = fqdn;
-    offlinePasswords = true;
-    cacheCredentials = true;
+  security = {
+    ipa = {
+      enable = true;
+      domain = vars.homeDomain;
+      inherit realm;
+      server = vars.ipaServer;
+      certificate = caCertPkg;
+      inherit basedn;
+      ipaHostname = fqdn;
+      offlinePasswords = true;
+      cacheCredentials = true;
+    };
+
+    # Create the home directory on first login if it doesn't exist yet.
+    # IPA users have no pre-created home on the host; without this sshd
+    # opens a session to a non-existent directory and resets the connection.
+    # lightdm also needs this so the GUI login path can create the home dir
+    # if it was not pre-seeded by the tmpfiles rule above (e.g. on first boot
+    # before SSSD has resolved the user).
+    pam.services = {
+      sshd.makeHomeDir = true;
+      lightdm.makeHomeDir = true;
+    };
+
+    # HM with useUserPackages = true (flake.nix) sets users.users.${ipaUser}.packages,
+    # which forces the stub into /etc/passwd. pam_sss.so with the "localusers" flag
+    # (added by NixOS when SSSD is enabled) then skips SSSD for any user it finds in
+    # local /etc/passwd — including this stub — falling through to pam_unix, which has
+    # no password for the stub → sudo auth always fails.
+    #
+    # Fix: NOPASSWD for the IPA user. The IPA user already authenticated to reach a
+    # shell (SSH public key from IPA or Kerberos), so re-prompting via a broken PAM
+    # path is security theater on a single-admin homelab.
+    sudo.extraRules = [{
+      users = [ vars.ipaUser ];
+      commands = [{ command = "ALL"; options = [ "NOPASSWD" ]; }];
+    }];
   };
 
-  # Fetch SSH public keys from IPA so users can log in with the key stored
-  # in their IPA profile rather than needing ~/.ssh/authorized_keys on every
-  # host. sss_ssh_authorizedkeys queries SSSD (which queries IPA LDAP).
-  #
-  # /nix/store is 1775 (group-writable by nixbld). OpenSSH 10.0+ rejects
-  # AuthorizedKeysCommand binaries whose path contains any group-writable
-  # component, silently skipping the command. Copy to /usr/local/bin (all
-  # components root-owned, 755) so the path passes sshd's safety check.
-  systemd.tmpfiles.rules = [
-    "d /usr/local 0755 root root - -"
-    "d /usr/local/bin 0755 root root - -"
-    "C+ /usr/local/bin/sss_ssh_authorizedkeys 0555 root root - ${pkgs.sssd}/bin/sss_ssh_authorizedkeys"
-  ];
+  systemd = {
+    # Fetch SSH public keys from IPA so users can log in with the key stored
+    # in their IPA profile rather than needing ~/.ssh/authorized_keys on every
+    # host. sss_ssh_authorizedkeys queries SSSD (which queries IPA LDAP).
+    #
+    # /nix/store is 1775 (group-writable by nixbld). OpenSSH 10.0+ rejects
+    # AuthorizedKeysCommand binaries whose path contains any group-writable
+    # component, silently skipping the command. Copy to /usr/local/bin (all
+    # components root-owned, 755) so the path passes sshd's safety check.
+    tmpfiles.rules = [
+      "d /usr/local 0755 root root - -"
+      "d /usr/local/bin 0755 root root - -"
+      "C+ /usr/local/bin/sss_ssh_authorizedkeys 0555 root root - ${pkgs.sssd}/bin/sss_ssh_authorizedkeys"
+      # Pre-create the IPA user's home dir so Home Manager activation succeeds
+      # even before their first login. On a fresh system SSSD may not have
+      # resolved the user yet — tmpfiles warns and skips in that case (non-fatal),
+      # and pam_mkhomedir covers the first-login path as a fallback.
+      "d /home/${vars.ipaUser} 0700 ${vars.ipaUser} ${vars.ipaUser} - -"
+    ];
+
+    # security.ipa enables Kerberos (security.krb5) which causes systemd to
+    # start auth-rpcgss-module.service and rpc-gssd.service for Kerberos NFS
+    # authentication. LXC containers can't load the auth_rpcgss kernel module
+    # and don't have /var/lib/nfs/rpc_pipefs, so both services fail.
+    #
+    # The NixOS IPA module already adds a drop-in for auth-rpcgss-module.service
+    # with ConditionPathExists=/etc/krb5.keytab. We use lib.mkForce to win the
+    # text conflict and add ConditionVirtualization=!container alongside it so
+    # the service is skipped (not failed) in containers that do have a keytab.
+    # Same fix for rpc-gssd.service which also fails in containers.
+    units = lib.mkIf config.boot.isContainer {
+      "auth-rpcgss-module.service" = {
+        overrideStrategy = "asDropinIfExists";
+        text = lib.mkForce ''
+          [Unit]
+          ConditionPathExists=
+          ConditionPathExists=/etc/krb5.keytab
+          ConditionVirtualization=!container
+        '';
+      };
+      # rpc-gssd also has ConditionPathExists from the NixOS IPA module (and an
+      # X-Restart-Triggers store path from systemd.nix). Use mkForce to win;
+      # omit X-Restart-Triggers since this service is skipped in containers anyway.
+      "rpc-gssd.service" = {
+        overrideStrategy = "asDropinIfExists";
+        text = lib.mkForce ''
+          [Unit]
+          ConditionPathExists=
+          ConditionPathExists=/etc/krb5.keytab
+          ConditionVirtualization=!container
+        '';
+      };
+    };
+
+    # home-manager-<user>.service fails on first enrollment because /home/wayne
+    # doesn't exist until the user's first login (pam_mkhomedir creates it then).
+    # ConditionPathExists makes systemd skip the service (exit 0, condition not
+    # met) instead of failing. After first login the dir exists and subsequent
+    # rebuilds activate HM normally.
+    services."home-manager-${vars.ipaUser}".unitConfig.ConditionPathExists =
+      "/home/${vars.ipaUser}";
+  };
 
   services.openssh.extraConfig = ''
     AuthorizedKeysCommand /usr/local/bin/sss_ssh_authorizedkeys %u
     AuthorizedKeysCommandUser nobody
   '';
 
-  # Create the home directory on first login if it doesn't exist yet.
-  # IPA users have no pre-created home on the host; without this sshd
-  # opens a session to a non-existent directory and resets the connection.
-  security.pam.services.sshd.makeHomeDir = true;
-
   # Host keytab: pre-provisioned on the IPA server, sops-encrypted binary.
   # Placed at /etc/krb5.keytab before SSSD starts so the host authenticates
   # to IPA without running ipa-client-install.
@@ -87,37 +158,37 @@ lib.mkIf enabled {
     restartUnits = [ "sssd.service" ];
   };
 
-  # security.ipa enables Kerberos (security.krb5) which causes systemd to
-  # start auth-rpcgss-module.service and rpc-gssd.service for Kerberos NFS
-  # authentication. LXC containers can't load the auth_rpcgss kernel module
-  # and don't have /var/lib/nfs/rpc_pipefs, so both services fail.
+  # NixOS requires isNormalUser/isSystemUser + group on any entry in
+  # users.users. HM with useUserPackages = true (set in flake.nix) adds a stub
+  # entry for each HM user so it can install packages to
+  # /etc/profiles/per-user/<name>/. This definition satisfies those assertions.
+  # With security.ipa setting "passwd: sss files" in nsswitch, SSSD's IPA entry
+  # takes priority for NSS lookups — this local stub is only a fallback when
+  # SSSD is unreachable (at which point auth fails anyway).
+  users.users.${vars.ipaUser} = {
+    isNormalUser = true;
+    group = "users";
+    extraGroups = [ "wheel" ];
+    createHome = false;
+  };
+
+  # Home Manager config for the IPA primary user, applied on every enrolled
+  # host. Manages what IPA doesn't: dotfiles, user-scoped packages, session
+  # variables. Switch-nix/Test-nix/buildImage are system-wide (configuration.nix)
+  # so they don't need to be repeated here.
   #
-  # The NixOS IPA module already adds a drop-in for auth-rpcgss-module.service
-  # with ConditionPathExists=/etc/krb5.keytab. We use lib.mkForce to win the
-  # text conflict and add ConditionVirtualization=!container alongside it so
-  # the service is skipped (not failed) in containers that do have a keytab.
-  # Same fix for rpc-gssd.service which also fails in containers.
-  systemd.units = lib.mkIf config.boot.isContainer {
-    "auth-rpcgss-module.service" = {
-      overrideStrategy = "asDropinIfExists";
-      text = lib.mkForce ''
-        [Unit]
-        ConditionPathExists=
-        ConditionPathExists=/etc/krb5.keytab
-        ConditionVirtualization=!container
-      '';
-    };
-    # rpc-gssd also has ConditionPathExists from the NixOS IPA module (and an
-    # X-Restart-Triggers store path from systemd.nix). Use mkForce to win;
-    # omit X-Restart-Triggers since this service is skipped in containers anyway.
-    "rpc-gssd.service" = {
-      overrideStrategy = "asDropinIfExists";
-      text = lib.mkForce ''
-        [Unit]
-        ConditionPathExists=
-        ConditionPathExists=/etc/krb5.keytab
-        ConditionVirtualization=!container
-      '';
+  # homeDirectory uses mkForce because HM's NixOS integration module sets it to
+  # "/var/empty" for users not found in config.users.users at eval time (SSSD
+  # users aren't visible there).
+  home-manager.users.${vars.ipaUser} = { pkgs, ... }: {
+    home = {
+      username = vars.ipaUser;
+      homeDirectory = lib.mkForce "/home/${vars.ipaUser}";
+      stateVersion = "26.05";
+      packages = with pkgs; [ tmux sshfs ];
+      sessionVariables.EDITOR = "nano";
     };
+    programs.home-manager.enable = true;
+    programs.bash.enable = true;
   };
 }

scripts/ipa/create-nixos-ipa-host-account.sh

@@ -81,6 +81,14 @@ if [[ -z "${TARGET}" ]]; then
   usage 1
 fi
 
+# Reject FQDNs passed by mistake — the script appends HOME_DOMAIN itself.
+# "nixos.sweet.home" → FQDN would become "nixos.sweet.home.sweet.home".
+if [[ "${TARGET}" == *"."* ]]; then
+  echo "Error: <hostname> must be the short name (e.g. 'nixos'), not a FQDN." >&2
+  echo "       The FQDN is derived automatically as ${TARGET}.${HOME_DOMAIN}." >&2
+  exit 1
+fi
+
 FQDN="${TARGET}.${HOME_DOMAIN}"
 KEYTAB_SECRET="${REPO_ROOT}/secrets/${TARGET}.keytab"
 # Temp path on the domain controller — use a name that won't collide.

variables.nix

@@ -80,6 +80,17 @@
   # one-line change.
   primaryUser = "nixos";
 
+  # Primary IPA/domain user. Home Manager is configured for this user on every
+  # IPA-enrolled host (see modules/ipa/client.nix) to manage the environment
+  # that IPA itself doesn't cover: dotfiles, user packages, session variables.
+  ipaUser = "wayne";
+
+  # GID of the IPA "docker-access" group (GID 50010 on the IPA server).
+  # The local "docker" group is pinned to this GID on every host that runs
+  # Docker so that IPA group membership alone grants docker socket access -
+  # no per-host users.groups.docker.members entry for the IPA user needed.
+  dockerAccessGid = 50010;
+
   # HA file server cluster
   # LAN IPs (vmbr0 / ens18) — client-facing: iSCSI initiators, NFS, management.
   # Storage IPs (vmbr1 / ens19) — isolated internal bridge, used for DRBD