hyperhive/nix/host-modules/swarm-review-classifier.nix

# The review classifier, in a `swarm-review-classifier` container on the host
# that sets `deploy.review-classifier.enable`, which `deploy.allSwarmServices`
# defaults on where the host has the classifier's store identity. It answers the
# swarm UI's review try-outs: swarm-controller sends a PR and the operator's classifications over
# the queue, and the daemon runs `claude`, or `opencode` on the ACP runtime,
# once per classification and replies.
# docs/swarm/review-classifier.md has the design.
#
# ⚠️ Its own network namespace on the bridge, as ./swarm-ci-runner.nix has: a
# PR's diff and commit messages are model input, so the container 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 everything else
# from the store with it: its queue client secret at start and the run's
# runtime's key on every run.
{
  pkgs,
  lib,
  config,
  ...
}:
let
  hyperhiveCfg = config.services.hyperhive;
  cfg = hyperhiveCfg.deploy.review-classifier;
  baoCfg = hyperhiveCfg.swarm.bao;
  baoDeploy = hyperhiveCfg.deploy.bao;
  natsCfg = hyperhiveCfg.swarm.nats;
  autheliaCfg = hyperhiveCfg.swarm.authelia;
  gatewayCfg = hyperhiveCfg.gateway;
  networkCfg = hyperhiveCfg.network;
  otelCfg = hyperhiveCfg.otel;
  tlsCfg = hyperhiveCfg.deploy.hive-controller.tls;

  machine = "swarm-review-classifier";
  unit = "swarm-review-classifier";
  clientId = hyperhiveCfg.swarm.review-classifier.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.reviewClassifierClientCertFile != null && baoDeploy.reviewClassifierClientKeyFile != null;

  # Credential id → host source. nspawn reads each source as root when the
  # container starts and hands it in as a system credential, held in memory;
  # the daemon's unit alone loads them. No copy lands on disk, as for an
  # agent's own leaf (`nix/agent-modules/bao.nix`). Ids carry no dot, the
  # spelling `--load-credential` is safe with.
  storeFiles = lib.filterAttrs (_: source: source != null) {
    review-classifier-bao-cert = baoDeploy.reviewClassifierClientCertFile;
    review-classifier-bao-key = baoDeploy.reviewClassifierClientKeyFile;
    review-classifier-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}";

  # What `claude` exports its metrics with, and the daemon its ACP runs' cost,
  # where this host runs a hive-tier collector on the bridge. The daemon adds
  # the repo and the PR to each `claude` run's resource attributes, and to
  # each cost record's attributes.
  otelEnv = lib.optionalAttrs otelCfg.enable {
    CLAUDE_CODE_ENABLE_TELEMETRY = "1";
    OTEL_METRICS_EXPORTER = "otlp";
    OTEL_EXPORTER_OTLP_ENDPOINT = "http://${networkCfg.bridgeIp}:${toString otelCfg.collector.port}";
    OTEL_EXPORTER_OTLP_PROTOCOL = "http/protobuf";
    # Claude Code defaults to delta, which the metrics store drops.
    OTEL_EXPORTER_OTLP_METRICS_TEMPORALITY_PREFERENCE = "cumulative";
    OTEL_RESOURCE_ATTRIBUTES = "service.name=hyperhive-review-classifier,swarm=${
      if hyperhiveCfg.swarm.name == null then "unknown" else hyperhiveCfg.swarm.name
    }";
  };

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

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

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

            services.hyperhive.deploy.bao.reviewClassifierClientCertFile
            services.hyperhive.deploy.bao.reviewClassifierClientKeyFile

          The classifier reads its queue client secret and its runtime keys 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 review-classifier.pem and
          review-classifier-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 review classifier'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 pulls the
    # minting unit in and waits for it. Ordering alone is not enough: the
    # container starts from `machines.target`, outside the transaction that
    # runs the minting unit from `multi-user.target`. Ignored elsewhere, where
    # the unit does not exist.
    systemd.services."container@${machine}" = lib.mkMerge [
      caTrust.containerOrdering
      {
        after = [ "swarm-bao-pki.service" ];
        wants = [ "swarm-bao-pki.service" ];
      }
    ];

    containers.${machine} = {
      autoStart = true;
      # The daemon keeps no state; its scratch directories are under PrivateTmp.
      ephemeral = false;
      # Journal files on the host, not inside the container: nixpkgs hardcodes
      # --link-journal=try-guest, and EXTRA_NSPAWN_FLAGS expands after it.
      extraFlags = [
        "--link-journal=host"
      ]
      ++ lib.mapAttrsToList (id: source: "--load-credential=${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" ];

          systemd.services.${unit} = {
            description = "answer the swarm UI's review try-outs";
            wantedBy = [ "multi-user.target" ];
            wants = [ "network-online.target" ];
            after = [ "network-online.target" ];
            environment = {
              BAO_ADDR = "https://${baoCfg.domain}:${toString baoCfg.port}";
              BAO_CLIENT_CERT = credential "review-classifier-bao-cert";
              BAO_CLIENT_KEY = credential "review-classifier-bao-key";
              SWARM_REVIEW_CLASSIFIER_NATS_URL = "tls://${natsCfg.domain}:${toString natsCfg.port}";
              SWARM_REVIEW_CLASSIFIER_OIDC_TOKEN_ENDPOINT = "${autheliaCfg.url}/api/oidc/token";
              SWARM_REVIEW_CLASSIFIER_OIDC_CLIENT_ID = clientId;
              SWARM_REVIEW_CLASSIFIER_CLAUDE = "${pkgs.claude-code}/bin/claude";
              SWARM_REVIEW_CLASSIFIER_OPENCODE = "${pkgs.opencode}/bin/opencode";
            }
            // lib.optionalAttrs (storeFiles ? review-classifier-bao-server-ca) {
              BAO_CACERT = credential "review-classifier-bao-server-ca";
            }
            // lib.optionalAttrs caTrust.useSelfSigned {
              SWARM_REVIEW_CLASSIFIER_OIDC_CA_FILE = caTrust.bundlePathFor machine;
            }
            // otelEnv;
            serviceConfig = {
              ExecStart = "${cfg.package}/bin/swarm-review-classifier";
              DynamicUser = true;
              # Each classification's scratch directory, gone with the unit.
              PrivateTmp = true;
              # Bare ids: the system credentials nspawn handed in.
              LoadCredential = lib.attrNames storeFiles;
              Restart = "on-failure";
              RestartSec = "10s";
              SyslogIdentifier = unit;
            };
          };
        };
    };
  };
}