# The swarm's telemetry collector as every hive sees it: the name it is
# reached on, its receiver ports, the client it is registered as and the
# audiences that client may present, identical on every host. What the host
# running it decides, and the container itself, are in ./swarm-otel.nix.
{
  lib,
  config,
  ...
}:
let
  cfg = config.services.hyperhive.swarm.otel;
  vmCfg = config.services.hyperhive.swarm.victoriametrics;
  vlCfg = config.services.hyperhive.swarm.victorialogs;
  hyperhiveCfg = config.services.hyperhive;
  baoCfg = hyperhiveCfg.swarm.bao;
  swarmDomain = hyperhiveCfg.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;

  # Each store's OTLP route, by domain: the audiences `audience` below registers
  # the client for. ⚠️ ./swarm-otel.nix binds the same strings for the
  # exporters that request those tokens; the two copies must agree.
  metricsPushUrl = "https://${vmCfg.domain}/opentelemetry/api/v1/push";
  logsPushUrl = "https://${vlCfg.domain}/insert/opentelemetry/v1/logs";

  pushAudiences = {
    victoriametrics = metricsPushUrl;
    victorialogs = logsPushUrl;
  };
in
{
  imports = [
    (lib.mkRemovedOptionModule [ "services" "hyperhive" "swarm" "otel" "journaldUnits" ] ''
      The swarm collector no longer takes a unit allowlist: it ships the
      journal of every system unit on the host and drops only user
      sessions (records under a `user-<uid>.slice`). Delete the setting;
      nothing replaces it.
    '')
  ];

  # `enable` moved to `services.hyperhive.deploy.swarm-otel.enable` — see ./deploy.nix.
  # ⚠️ That is the SWARM collector. The per-hive one keeps its own
  # `services.hyperhive.otel.enable` (./otel.nix) and is a different
  # option entirely — every hive runs that one.
  options.services.hyperhive.swarm.otel = {

    machine = lib.mkOption {
      type = lib.types.str;
      readOnly = true;
      default = "swarm-otel";
      description = ''
        Name of the nixos-container this collector runs in — also the
        `machinectl` name, so other modules may read it rather than
        repeating the literal.
      '';
    };

    port = lib.mkOption {
      type = lib.types.port;
      default = 4319;
      description = ''
        First port of this collector's receiver range. Every hive in
        {option}`services.hyperhive.swarm.hives` gets its **own**
        authenticated receiver — that is what makes the `hive` label
        unforgeable — so the range is one port per hive, starting here, in
        sorted-name order.

        ⚠️ Internal. No client is ever told a port: a hive reaches its own
        receiver as `https://''${domain}/<hive>`, and the gateway routes on
        that path. So adding a hive, which renumbers the ones after it, is
        harmless — nginx is rendered from this same evaluation and moves
        with it.

        ⚠️ **Deliberately not 4318**, the OTLP/HTTP default, because the
        hive tier already uses it (`services.hyperhive.otel.collector.port`)
        and every swarm container shares the host's network namespace. Two
        listeners claiming one port on one host is not a build failure —
        it is a runtime coin toss over which one gets it, with nothing in
        any log saying so. The same collision cost a release when grafana
        and the forge both defaulted to 3000. The assertions below check
        the whole derived range against every port this module and the hive
        tier declare, which is as far as a module can see.
      '';
    };

    telemetryPort = lib.mkOption {
      type = lib.types.port;
      default = 8889;
      description = ''
        Port this collector 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 8889's neighbour 8888**, which is the
        collector's built-in default and therefore what the hive tier
        already binds. Two collectors share a network namespace whenever
        they are co-located, and unlike the OTLP port this one appears
        nowhere in either config — it is a default inside the binary, so
        nothing that compares configured ports can see the clash. The
        second collector to start simply dies with
        `bind: address already in use`.
      '';
    };

    producerPort = lib.mkOption {
      type = lib.types.port;
      default = 4390;
      description = ''
        Port the swarm tier's own OTLP/HTTP receiver for a
        **swarm-level** producer (`swarm-controller`'s vcs/jobq counters
        today) listens on, at `127.0.0.1`. Reached through the gateway at
        `https://''${domain}/''${producerName}/`, same shape as a hive's
        own receiver — a swarm-level producer may not share a host with
        this collector (mara, on the swarm-controller topology: "the
        swarm services dont have to run on the same host as the swarm
        controller"), so loopback-only reachability is not a supported
        shape here any more than it is for a hive.

        Authenticated by `oidc/''${producerName}`, checking for the
        audience `services.hyperhive.swarm.controller.queueClientId`
        requests — not the per-hive `hiveClientPrefix` namespace, because
        a swarm-level producer is explicitly not a hive (see that
        option's own doc comment). The `swarm` label this receiver's
        samples get is still the one the receiver's own *existence*
        establishes, same as before — there is no hive identity being
        forged or attributed here, just a caller proving it is the one
        principal allowed to push into this pipeline.

        ⚠️ Deliberately NOT derived from `port + (number of hives)`: that
        range grows every time a hive is added, and a fixed offset from
        it would silently start colliding once the hive count caught up.
        Kept as its own reserved value instead, and the assertion below
        still catches a real collision (including one hive growth
        eventually causes) rather than starting a collector that quietly
        drops one receiver's samples.
      '';
    };

    storeProducerPort = lib.mkOption {
      type = lib.types.port;
      default = 4391;
      description = ''
        Port the receiver for the **secret store's own forwarder** listens
        on, at `127.0.0.1`. Reached through the gateway at
        `https://''${domain}/''${storeProducerName}/`, the same
        path-per-producer shape a hive and the swarm-tier producer above
        both use.

        Its own receiver, and not a second sender into
        {option}`services.hyperhive.swarm.otel.producerPort`, because an
        `oidc` authenticator checks exactly ONE audience: that receiver
        admits the audience `swarm-controller` registers for itself, and
        the store's forwarder is a different principal with a client of its
        own. Sharing the route would mean sharing that client — which is
        the thing the store exists to make unnecessary.

        ⚠️ A reserved value rather than an offset from
        {option}`services.hyperhive.swarm.otel.port`, for the reason stated
        on `producerPort`: that range grows with the hive count and would
        eventually walk into any fixed offset from it. The collision
        assertion below covers this port too.
      '';
    };

    storeProducerName = lib.mkOption {
      type = lib.types.str;
      readOnly = true;
      default = baoCfg.machine;
      defaultText = lib.literalExpression "services.hyperhive.swarm.bao.machine";
      description = ''
        Path and component name of the store forwarder's own receiver
        (`otlp/''${storeProducerName}`, `oidc/''${storeProducerName}`).
        Published so `swarm-bao.nix` addresses the receiver by name rather
        than repeating the string, exactly as `producerName` above is
        published for `swarm-controller.nix`.

        Read-only and derived from the store's container name: two
        spellings of a name both ends have to agree on is a 404 on a
        request that authenticated perfectly.
      '';
    };

    producerName = lib.mkOption {
      type = lib.types.str;
      readOnly = true;
      default = "swarm";
      description = ''
        The swarm-tier producer's own component/path/authenticator name
        — the same reserved literal this module's collector components
        (`otlp/swarm`, `oidc/swarm`, `resource/swarm`, `metrics/swarm`)
        are already named after internally. Published as an option so a
        sibling module (`swarm-controller.nix`) can address the receiver
        by name — `https://''${domain}/''${producerName}/` — instead of
        repeating the string. Read-only for the same reason
        `clientId`/`machine`/`domain` are: two spellings of a name that
        has to match on both ends is a mismatch waiting to happen.
      '';
    };

    domain = lib.mkOption {
      type = lib.types.str;
      default = "otel.${domainBase}";
      defaultText = lib.literalExpression ''"otel.''${services.hyperhive.swarm.domain}"'';
      description = ''
        Name the gateway serves this on. A sibling of the swarm's other
        service names, so the swarm-services sub-CA can issue for it — see
        `hive-tls.nix` for why a service name being a sibling rather than a
        child decides which CA may sign it.

        This is what the **hive** tier's exporter reaches — the hive
        collector is a plain producer against this name exactly like every
        other client of a swarm service, resolved locally by dnsmasq on a
        co-located host and over the real network otherwise. There is no
        separate loopback-vs-remote knob to get wrong: everything in this
        swarm addresses its siblings by name.
      '';
    };

    scrapeTargets = lib.mkOption {
      type = lib.types.attrsOf lib.types.str;
      default = { };
      example = lib.literalExpression ''{ forgejo = "127.0.0.1:3000"; }'';
      description = ''
        Prometheus exposition endpoints this collector scrapes, as
        `<job name> = "<host>:<port>"`.

        A path and query may follow the port —
        `"127.0.0.1:8202/v1/sys/metrics?format=prometheus"` — for an
        exporter that does not serve `/metrics`. Both are optional and
        omitted when absent, so a bare `host:port` is scraped exactly as
        before.

        **A service declares its own entry, from its own module, under its
        own `enable`.** Do not assemble the list here: an entry then exists
        only where the service that named it runs, so a target is never
        declared on a host that does not serve it.

        ⚠️ **That constrains the TARGET, not the SCRAPER, and the difference
        is a silent gap.** Nothing here puts the collector on the same host.
        Services are co-located by *default* — `swarm-required-services.nix`
        derives their `enable` flags from one `lib.mkDefault` — not by
        construction, and an operator may split them.

        When they are split the target is simply never scraped: the
        service's host declares an entry no local collector reads, and the
        collector's host never enabled that service so has no entry at all.
        No error, no eval failure, no warning.

        **No assertion can catch this.** Two hosts are separate NixOS
        evaluations with no shared context, so neither can see what the
        other runs. A service that would be seriously wrong to lose should
        say so in its own contribution, because saying it is the only
        mechanism available.

        Samples land in a swarm-level pipeline that stamps `swarm` and
        **never** `hive`: a swarm service does not belong to a hive, and
        `hive` stays a property of which authenticated receiver accepted a
        push, not something a scrape can acquire.

        Empty by default, in which case no scrape receiver, processor or
        pipeline is emitted at all — an enabled scraper with nothing to
        scrape is the inert configuration this option exists to avoid.
      '';
    };

    publishedScrapeTargets = lib.mkOption {
      type = lib.types.attrsOf lib.types.str;
      default = { };
      example = lib.literalExpression ''{ forge = "https://forge.example.com/metrics"; }'';
      description = ''
        Prometheus endpoints this collector scrapes **by name, with a
        credential**, as `<job name> = "<url>"`.

        A service module declares its own entry, from its own module, the
        same way it does for `scrapeTargets` — and the collector's OAuth2
        client derives its permitted audiences from these URLs, so a
        target and the authorisation to reach it are **one declaration**.
        Two lists that must agree would be a drift to maintain, and its
        failure mode is the bad one: a target whose audience was forgotten
        authenticates against nothing and reads as a scrape failure rather
        than a config mistake.

        ⚠️ A **full URL**, not `host:port`. Authelia validates a bearer
        token against the address being requested, so the string here is
        also the audience the token is minted for; a near miss (a trailing
        slash, `http` for `https`) presents as a valid token rejected at
        the target, several layers from its cause.

        ⚠️ Deliberately separate from `scrapeTargets`. An entry there is
        trusted because the scraper and the target share a host — that
        option is loopback-and-unauthenticated by contract. An entry here
        is trusted because it presents a credential. One shape for both
        would leave a reader unable to tell which of those a given target
        relies on.
      '';
    };

    clientId = lib.mkOption {
      type = lib.types.str;
      readOnly = true;
      default = "swarm-collector";
      description = ''
        OAuth2 client id this collector authenticates as. Published so
        authelia's `access_control` rules can name it without carrying a
        second copy of the string, exactly as
        `services.hyperhive.swarm.authelia.hiveClientPrefix` is published
        for the queue's responder.

        Two spellings drifting apart is not a build failure: authelia
        refuses a rule naming an unregistered client in its startup
        validator, so the swarm's SSO service fails to *restart* — long
        after the change that caused it evaluated cleanly.
      '';
    };

    audience = lib.mkOption {
      type = lib.types.listOf lib.types.str;
      readOnly = true;
      default = lib.attrValues cfg.publishedScrapeTargets ++ lib.attrValues pushAudiences;
      description = ''
        Every audience this collector's OAuth2 client is permitted to
        present a token for — the scrape targets it reads with a credential,
        plus the stores it pushes to. Published read-only so
        ./glue-swarm-otel-oidc-client.nix can register the client wherever
        authelia runs without restating the derivation: this option and
        that registration are the same fact seen from two hosts, and a
        second formula for it would be free to drift from this one.
      '';
    };
  };
}