hyperhive/nix/module-eval/bao-otel-collector.nix

# `checks.module-eval-bao-otel-collector` — see ./lib.nix for the shared
# rationale (why this suite exists, naming convention, "evaluates
# not executes").
{
  pkgs,
  lib,
  self,
  nixosSystem,
}:
let
  inherit
    (import ./lib.nix {
      inherit
        pkgs
        lib
        self
        nixosSystem
        ;
    })
    hive
    runGroup
    baoSettings
    ;

  baoTwoAddresses = hive {
    deploy.bao.enable = true;
    deploy.bao.extraListenAddresses = [ "10.0.0.1" ];
    # Pinned, not incidental: the case counting these listeners is about the
    # declared addresses, and a collector on this host would add one of its own.
    deploy.swarm-otel.enable = false;
  };

  # The store with and without a collector on the same host. `scrapeTargets`
  # is only ever read by a local collector, so the metrics endpoint is a
  # function of the pairing rather than of the store.
  baoWithCollector = hive {
    deploy.bao.enable = true;
    deploy.swarm-otel.enable = true;
    # A second job declared as bare `host:port`, so the pair of cases below
    # reads one rendered scrape list: the store's entry carries a path, this
    # one carries none.
    swarm.otel.scrapeTargets.plain = "127.0.0.1:9999";
  };

  baoNoCollector = hive {
    deploy.bao.enable = true;
    deploy.swarm-otel.enable = false;
  };

  # The scrape list prometheus is handed, not the option a service declared:
  # the address, the path and the query are one string on the way in and three
  # fields on the way out, and only the second shape is what gets requested.
  scrapeJob =
    machine: job:
    lib.findFirst (c: c.job_name == job) null
      machine.containers.swarm-otel.config.services.opentelemetry-collector.settings.receivers.prometheus.config.scrape_configs;
  cases = [
    {
      # Same gap one tier up, and it needs its own arm: this collector
      # already had six scrape targets, so a pass here is about the seventh
      # rather than about the receiver existing at all.
      name = "the swarm collector scrapes its own telemetry endpoint";
      ok =
        let
          j = scrapeJob baoWithCollector "collector";
        in
        j != null && j.static_configs == [ { targets = [ "127.0.0.1:8889" ]; } ];
    }
    {
      # The store stays behind the passthrough rather than beside it: loopback
      # plus whatever was declared, never the bridge. A store that also bound
      # the bridge itself would collide with the listener above, and the
      # colliding one is nginx — the whole gateway, not just this port.
      name = "the store binds loopback and its declared addresses, never the bridge";
      ok =
        let
          l = (baoSettings baoTwoAddresses).listener;
        in
        l.loopback.address == "127.0.0.1:8200" && l.extra-1.address == "10.0.0.1:8200";
    }
    {
      # Control for the case above: these settings are rendered per deployment,
      # not constants a passing case could be indifferent to.
      name = "a declared extra address renders a second listener beside loopback";
      ok = builtins.length (builtins.attrNames (baoSettings baoTwoAddresses).listener) == 2;
    }
    {
      # Retention is what serves the endpoint at all, so the listener alone
      # would be a port that answers 404.
      name = "a store beside a collector serves metrics on its own listener";
      ok =
        let
          s = baoSettings baoWithCollector;
        in
        s.listener ? metrics && (s.telemetry.prometheus_retention_time or "0s") != "0s";
    }
    {
      # openbao serves no `/metrics` at all, so a scrape of the default path
      # 404s: the store looks like a dead exporter, and every panel built on
      # it renders empty rather than erroring.
      name = "the store's scrape asks for the path openbao serves";
      ok =
        let
          j = scrapeJob baoWithCollector "bao";
        in
        (j.metrics_path or "") == "/v1/sys/metrics" && (j.params.format or [ ]) == [ "prometheus" ];
    }
    {
      # Presence control for the case above: both fields are omitted rather
      # than defaulted, so a target declared as bare `host:port` renders what
      # it rendered before the path grammar existed.
      name = "a target with no path renders neither metrics_path nor params";
      ok =
        let
          j = scrapeJob baoWithCollector "plain";
        in
        j != null && !(j ? metrics_path) && !(j ? params);
    }
    {
      # Absence arm. Unauthenticated by design, so it must not exist where
      # nothing reads it.
      name = "a store with no collector beside it serves no metrics";
      ok =
        let
          s = baoSettings baoNoCollector;
        in
        !(s.listener ? metrics) && !(s ? telemetry);
    }
  ];
in
runGroup "bao-otel-collector" cases