hyperhive/nix/host-modules/swarm-bao-service.nix

# The swarm's secret store as every hive sees it: the names it is reached on,
# its port, its container, and the client ids it is registered under,
# identical on every host. What the host running it decides, and the
# container itself, are in ./swarm-bao.nix.
{
  lib,
  config,
  ...
}:
let
  cfg = config.services.hyperhive.swarm.bao;
  swarmDomain = config.services.hyperhive.swarm.domain;

  # Total on a null swarm domain for the same reason every sibling module is:
  # the required-domain assertion in hive-network.nix should be what an operator
  # sees, not a coercion error from here.
  domainBase = if swarmDomain == null then "invalid" else swarmDomain;
in
{
  options.services.hyperhive.swarm.bao = {
    machine = lib.mkOption {
      type = lib.types.str;
      readOnly = true;
      default = "swarm-bao";
      description = ''
        Container name. Read-only: the name appears in host paths and in
        `machinectl`, so it is a fact other modules may read rather than a knob.
      '';
    };

    domain = lib.mkOption {
      type = lib.types.str;
      default = "bao.${domainBase}";
      defaultText = lib.literalExpression ''"bao.''${services.hyperhive.swarm.domain}"'';
      description = ''
        Name the store is reached on. A **sibling** of the swarm's other
        service names, not a child of any hive domain: an authority whose
        `nameConstraints` permit one hive's domain cannot issue for a sibling
        of it, so the shape of this name decides which authorities could ever
        sign for the store. That is a property of the name, not a choice of
        issuer — this module makes no such choice.
      '';
    };

    ui.domain = lib.mkOption {
      type = lib.types.str;
      default = "bao-ui.${domainBase}";
      defaultText = lib.literalExpression ''"bao-ui.''${services.hyperhive.swarm.domain}"'';
      description = ''
        Name the gateway serves the store's browser UI on, to members of
        authelia's `admins` group only. Swarm-wide because authelia's host
        writes the access rule for it and the store's host serves it.

        Must differ from {option}`services.hyperhive.swarm.bao.domain`: that
        name is the mutual-TLS endpoint every reader dials, and it has no
        vhost.
      '';
    };

    ui.oidc.clientId = lib.mkOption {
      type = lib.types.str;
      readOnly = true;
      default = "swarm-bao-ui";
      description = ''
        OAuth2 client id the store's `oidc` auth method logs browser users
        in as, at authelia.

        Swarm-wide and read-only because two hosts have to agree on it:
        authelia registers the client (`glue-bao-ui-oidc-client.nix`) and
        mints its secret, and the store's host reads that secret back out of
        the store under a path composed from this id.
      '';
    };

    ui.oidc.redirectUri = lib.mkOption {
      type = lib.types.str;
      readOnly = true;
      default = "https://${cfg.ui.domain}/ui/vault/auth/oidc/oidc/callback";
      defaultText = lib.literalExpression ''"https://''${services.hyperhive.swarm.bao.ui.domain}/ui/vault/auth/oidc/oidc/callback"'';
      description = ''
        Where authelia sends the browser back to after an OIDC login, and the
        URI both authelia and the store's `oidc` role match **exactly**.

        The format is the OpenBao UI's own route,
        `/ui/vault/auth/<mount>/oidc/callback`, with the mount `oidc`. The
        UI composes it from the page's origin, so it only matches when the
        gateway serves the UI on port 443.
      '';
    };

    port = lib.mkOption {
      type = lib.types.port;
      default = 8200;
      description = ''
        TCP port the store listens on. Upstream's own default, kept so an
        operator reading OpenBao documentation finds what they expect.

        Swarm-wide because a client has to know it to reach the store, and
        the same port on every listener: which *addresses* the store answers
        on is the running host's business
        ({option}`services.hyperhive.deploy.bao.extraListenAddresses`), but
        which port it answers on is something the whole swarm agrees.
      '';
    };

    otel.clientId = lib.mkOption {
      type = lib.types.str;
      readOnly = true;
      default = "swarm-bao-collector";
      description = ''
        OAuth2 client id the collector inside the store's container
        authenticates as, and — self-referentially, the shape every hive's
        client already uses — the audience it asks its token for.

        **Its own, not the swarm collector's and not
        `swarm-controller`'s.** One identity per principal: this forwarder
        runs wherever the store runs, which is not where either of those
        two runs, and the receiver it pushes to
        (`swarm.otel.storeProducerName`) admits this id alone.

        Swarm-wide and read-only because three hosts have to agree on it:
        authelia registers the client
        (`glue-swarm-bao-otel-oidc-client.nix`), the swarm collector checks
        the audience (`swarm-otel.nix`), and the store's host reads the
        minted secret back out of the store under a path composed from it.
        Two spellings present as a healthy-looking 401.
      '';
    };

    otel.telemetryPort = lib.mkOption {
      type = lib.types.port;
      default = 8890;
      description = ''
        Port the collector inside the store's container serves its **own**
        metrics on — queue depth, refused and dropped samples, exporter
        failures. How you find out that telemetry is being lost, so it is
        worth keeping rather than switching off.

        ⚠️ **Deliberately not 8888.** 8888 is the collector
        binary's built-in default, which the hive tier
        ({option}`services.hyperhive.otel.telemetryPort`) already binds. This
        container runs with `privateNetwork = false`, so both share the
        host's network namespace whenever they are co-located — and unlike
        the OTLP ports this one appears nowhere in either config when it is
        left undeclared, so nothing that compares configured ports can see
        the clash. The second collector to start simply dies with
        `bind: address already in use`.
      '';
    };
  };
}