hyperhive/nix/host-modules/swarm-claude-login.nix

# The claude login minter, in a `swarm-claude-login` container on the host
# that sets `deploy.claude-login.enable`, which `deploy.allSwarmServices`
# defaults on where the host has the minter's store identity. An operator logs
# an agent in from its card in the swarm UI: swarm-controller relays the start
# and the pasted code over the queue, and the daemon runs `claude auth login`
# and writes the credentials to that agent's store leaf.
# docs/swarm/claude-login.md has the design.
#
# Its own network namespace on the bridge, as ./swarm-review-classifier.nix
# has: it reaches the swarm services by name and nothing on the host's
# loopback.
#
# The container holds one credential, its own store leaf, which nspawn hands in
# as a system credential with no copy on disk. The daemon reads its queue
# client secret with it and writes agents' credentials under it.
{
  pkgs,
  lib,
  config,
  ...
}:
let
  hyperhiveCfg = config.services.hyperhive;
  cfg = hyperhiveCfg.deploy.claude-login;
  baoCfg = hyperhiveCfg.swarm.bao;
  baoDeploy = hyperhiveCfg.deploy.bao;
  natsCfg = hyperhiveCfg.swarm.nats;
  autheliaCfg = hyperhiveCfg.swarm.authelia;
  gatewayCfg = hyperhiveCfg.gateway;
  networkCfg = hyperhiveCfg.network;
  tlsCfg = hyperhiveCfg.deploy.hive-controller.tls;

  machine = "swarm-claude-login";
  unit = "swarm-claude-login";
  clientId = hyperhiveCfg.swarm.claude-login.clientId;

  # The daemon reaches authelia, the store and the queue by name over TLS, and
  # in self-signed mode their leaves chain to the hive CA.
  caTrust = import ./lib/hive-ca-trust.nix { inherit lib tlsCfg gatewayCfg; };
  caBundleModule = caTrust.trustBundle {
    inherit pkgs;
    name = machine;
    consumers = [ unit ];
  };

  haveClientIdentity =
    baoDeploy.claudeLoginClientCertFile != null && baoDeploy.claudeLoginClientKeyFile != null;

  # Credential id → host source, as ./swarm-review-classifier.nix hands its
  # leaf in.
  storeFiles = lib.filterAttrs (_: source: source != null) {
    claude-login-bao-cert = baoDeploy.claudeLoginClientCertFile;
    claude-login-bao-key = baoDeploy.claudeLoginClientKeyFile;
    claude-login-bao-server-ca = baoDeploy.serverCaFile;
  };
  # nixos-container expands `extraFlags` unquoted, so a source path must be
  # one word.
  oneWord = path: builtins.match ".*[[:space:]].*" path == null;
  credential = id: "/run/credentials/${unit}.service/${id}";

  privateNetwork = true;
in
{
  options.services.hyperhive.swarm.claude-login.clientId = lib.mkOption {
    type = lib.types.str;
    readOnly = true;
    default = "swarm-claude-login";
    description = ''
      The OAuth2 client id the claude login minter presents to the swarm
      queue. Read-only: the host running authelia registers it, the queue's
      auth-callout responder grants it the login subject, and the secret
      publisher carries its secret to the store, all from this one value.
    '';
  };

  options.services.hyperhive.deploy.claude-login.package = lib.mkOption {
    type = lib.types.package;
    defaultText = lib.literalExpression "hyperhive.packages.\${system}.swarm-claude-login";
    description = "The claude login minter daemon package.";
  };

  config = lib.mkIf cfg.enable {
    assertions = [
      {
        assertion = haveClientIdentity;
        message = ''
          services.hyperhive.deploy.claude-login.enable requires the minter's
          swarm-secret-store client identity: set both

            services.hyperhive.deploy.bao.claudeLoginClientCertFile
            services.hyperhive.deploy.bao.claudeLoginClientKeyFile

          The minter reads its queue client secret and writes agents' claude
          credentials with it.

          Both default to the pair glue-bao-tls.nix mints when
          services.hyperhive.deploy.bao.enable is true (the host that runs the
          store). Otherwise copy claude-login.pem and claude-login-key.pem from
          the store host's /var/lib/swarm-bao-pki/ and name them in those two
          options.
        '';
      }
      {
        assertion = lib.all oneWord (lib.attrValues storeFiles);
        message = ''
          The claude login minter's store identity paths must not contain
          whitespace: nspawn's --load-credential receives them through
          nixos-container's unquoted extra flags.
        '';
      }
    ];

    # The container hangs off the bridge, takes its address from the gateway's
    # DHCP and resolves through its dnsmasq.
    services.hyperhive.network.enable = lib.mkDefault true;
    services.hyperhive.gateway.enable = lib.mkDefault true;
    services.hyperhive.gateway.dns.enable = lib.mkDefault true;

    # nspawn fails to start the container when a credential source is
    # missing, so where this host mints the leaf the container waits for it.
    systemd.services."container@${machine}" = lib.mkMerge [
      caTrust.containerOrdering
      { after = [ "swarm-bao-pki.service" ]; }
    ];

    containers.${machine} = {
      autoStart = true;
      # The daemon keeps no state; each login's scratch directory is under
      # PrivateTmp.
      ephemeral = false;
      # Journal files on the host, not inside the container: nixpkgs hardcodes
      # --link-journal=try-guest, and EXTRA_NSPAWN_FLAGS expands after it.
      extraFlags = [
        "--link-journal=host"
      ]
      ++ lib.mapAttrsToList (id: source: "--load-credential=${id}:${source}") storeFiles;
      inherit privateNetwork;
      hostBridge = networkCfg.bridgeName;
      bindMounts = caTrust.bindMount;

      config =
        { pkgs, lib, ... }:
        {
          imports = [
            ../container-modules/swarm-container.nix
            caBundleModule
          ];

          services.hyperhive.swarmContainer = {
            inherit privateNetwork;
            writesOwnResolvConf = false;
          };
          networking.nameservers = [ networkCfg.bridgeIp ];
          networking.interfaces.eth0.useDHCP = true;

          # `claude-code` is unfree, and this container evaluates its own
          # nixpkgs, so the host's allowance does not reach here.
          nixpkgs.config.allowUnfreePredicate = pkg: builtins.elem (lib.getName pkg) [ "claude-code" ];

          users.users.${unit} = {
            isSystemUser = true;
            group = unit;
          };
          users.groups.${unit} = { };

          systemd.services.${unit} = {
            description = "log agents in to claude for the swarm UI";
            wantedBy = [ "multi-user.target" ];
            wants = [ "network-online.target" ];
            after = [ "network-online.target" ];
            environment = {
              BAO_ADDR = "https://${baoCfg.domain}:${toString baoCfg.port}";
              BAO_CLIENT_CERT = credential "claude-login-bao-cert";
              BAO_CLIENT_KEY = credential "claude-login-bao-key";
              SWARM_CLAUDE_LOGIN_NATS_URL = "tls://${natsCfg.domain}:${toString natsCfg.port}";
              SWARM_CLAUDE_LOGIN_OIDC_TOKEN_ENDPOINT = "${autheliaCfg.url}/api/oidc/token";
              SWARM_CLAUDE_LOGIN_OIDC_CLIENT_ID = clientId;
              SWARM_CLAUDE_LOGIN_CLAUDE = "${pkgs.claude-code}/bin/claude";
            }
            // lib.optionalAttrs (storeFiles ? claude-login-bao-server-ca) {
              BAO_CACERT = credential "claude-login-bao-server-ca";
            }
            // lib.optionalAttrs caTrust.useSelfSigned {
              SWARM_CLAUDE_LOGIN_OIDC_CA_FILE = caTrust.bundlePathFor machine;
            };
            serviceConfig = {
              ExecStart = "${cfg.package}/bin/swarm-claude-login";
              User = unit;
              Group = unit;
              # Each login's scratch directory, gone with the unit.
              PrivateTmp = true;
              UMask = "0077";
              # Bare ids: the system credentials nspawn handed in.
              LoadCredential = lib.attrNames storeFiles;
              Restart = "on-failure";
              RestartSec = "10s";
              SyslogIdentifier = unit;
            };
          };
        };
    };
  };
}