hyperhive/nix/host-modules/swarm-notify-router.nix

# The swarm notification router, in a `swarm-notify-router` container on the
# host that sets `deploy.notify-router.enable`, which `deploy.allSwarmServices`
# defaults on where the host has the router's store identity. It reads the
# forge events swarm-controller keeps from its webhooks and queues todo ops on
# each agent's subject of `ROUTER_TODOS`, which the agent's harness applies.
# docs/swarm/notify-router.md has the design.
#
# Its own network namespace on the bridge, as ./swarm-claude-login.nix has: it
# reaches the swarm services by name and nothing on the host's loopback. It
# talks only to the queue, the store and authelia, so it can run on any host.
#
# 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.
{
  pkgs,
  lib,
  config,
  ...
}:
let
  hyperhiveCfg = config.services.hyperhive;

  cfg = hyperhiveCfg.deploy.notify-router;
  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-notify-router";
  unit = "swarm-notify-router";
  clientId = hyperhiveCfg.swarm.notify-router.clientId;

  # The container's journal forwarder pushes to its own receiver on the swarm
  # collector, the route `serviceProducers.swarm-notify-router` in
  # ./swarm-otel-service.nix declares, as ./swarm-claude-login.nix does.
  swarmOtelCfg = hyperhiveCfg.swarm.otel;
  gatewayPortSuffix = lib.optionalString (
    gatewayCfg.httpsPort != 443
  ) ":${toString gatewayCfg.httpsPort}";
  forwarderEndpoint = "https://${swarmOtelCfg.domain}${gatewayPortSuffix}/${machine}";
  forwarderUnit = "swarm-journal-forwarder-oidc";
  # Loopback in the container's own netns, and distinct from the other service
  # containers' forwarders all the same.
  forwarderTelemetryPort = 8902;

  # 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
      # Go: `SSL_CERT_FILE` replaces its trust store, for the swarm
      # collector's and authelia's names.
      "opentelemetry-collector"
    ];
  };

  haveClientIdentity =
    baoDeploy.notifyRouterClientCertFile != null && baoDeploy.notifyRouterClientKeyFile != null;

  # Credential id → host source, as ./swarm-claude-login.nix hands its leaf in.
  storeFiles = lib.filterAttrs (_: source: source != null) {
    notify-router-bao-cert = baoDeploy.notifyRouterClientCertFile;
    notify-router-bao-key = baoDeploy.notifyRouterClientKeyFile;
    notify-router-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}";
  forwarderCredential = id: "/run/credentials/${forwarderUnit}.service/${id}";

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

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

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

            services.hyperhive.deploy.bao.notifyRouterClientCertFile
            services.hyperhive.deploy.bao.notifyRouterClientKeyFile

          The router reads its queue client secret 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 notify-router.pem and notify-router-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 notification router'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.${machine} = {
      autoStart = true;
      # The daemon keeps its state in the queue: its consumer's position and
      # its per-issue snapshots.
      ephemeral = false;
      # No `--link-journal=host`: the journal stays in the guest, where the
      # container's own forwarder reads it (../container-modules/swarm-journal-forwarder.nix).
      extraFlags = lib.mapAttrsToList (id: source: "--load-credential=${id}:${source}") storeFiles;
      inherit privateNetwork;
      hostBridge = networkCfg.bridgeName;
      bindMounts = caTrust.bindMount;

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

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

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

          # Authenticated as the daemon's own OIDC client, whose secret its
          # store identity already reads: one identity for the whole container.
          services.hyperhive.swarmJournalForwarder = {
            enable = true;
            serviceName = "notify-router";
            endpoint = forwarderEndpoint;
            inherit clientId;
            tokenUrl = "${autheliaCfg.url}/api/oidc/token";
            telemetryPort = forwarderTelemetryPort;
            store = {
              package = baoDeploy.package;
              addr = "https://${baoCfg.domain}:${toString baoCfg.port}";
              secretPath = "secret/swarm/services/${clientId}/oidc/client";
              clientCertFile = forwarderCredential "notify-router-bao-cert";
              clientKeyFile = forwarderCredential "notify-router-bao-key";
              caFile =
                if storeFiles ? notify-router-bao-server-ca then
                  forwarderCredential "notify-router-bao-server-ca"
                else
                  null;
            };
          };
          systemd.services.${forwarderUnit}.serviceConfig.LoadCredential = lib.attrNames storeFiles;

          systemd.services.${unit} = {
            description = "route forge events to agents' todo lists";
            wantedBy = [ "multi-user.target" ];
            wants = [ "network-online.target" ];
            after = [ "network-online.target" ];
            environment = {
              BAO_ADDR = "https://${baoCfg.domain}:${toString baoCfg.port}";
              BAO_CLIENT_CERT = credential "notify-router-bao-cert";
              BAO_CLIENT_KEY = credential "notify-router-bao-key";
              SWARM_NOTIFY_ROUTER_NATS_URL = "tls://${natsCfg.domain}:${toString natsCfg.port}";
              SWARM_NOTIFY_ROUTER_OIDC_TOKEN_ENDPOINT = "${autheliaCfg.url}/api/oidc/token";
              SWARM_NOTIFY_ROUTER_OIDC_CLIENT_ID = clientId;
            }
            // lib.optionalAttrs (storeFiles ? notify-router-bao-server-ca) {
              BAO_CACERT = credential "notify-router-bao-server-ca";
            }
            // lib.optionalAttrs caTrust.useSelfSigned {
              SWARM_NOTIFY_ROUTER_OIDC_CA_FILE = caTrust.bundlePathFor machine;
            };
            serviceConfig = {
              ExecStart = "${cfg.package}/bin/swarm-notify-router";
              User = unit;
              Group = unit;
              UMask = "0077";
              # Bare ids: the system credentials nspawn handed in.
              LoadCredential = lib.attrNames storeFiles;
              Restart = "on-failure";
              RestartSec = "10s";
              SyslogIdentifier = unit;
            };
          };
        };
    };
  };
}