hyperhive/nix/host-modules/hive-c0re/environment.nix

# Environment of the hive-c0re daemon unit — a plain function file
# (not a module) returning the env attrset, imported by ./default.nix.
# Everything meta.rs forwards into agent containers or reads for the
# meta-flake render is assembled here.
{
  lib,
  config,
  pkgs,
}:
let
  cfg = config.services.hyperhive.c0re;
  baoDeploy = config.services.hyperhive.deploy.bao;
  baoCfg = config.services.hyperhive.swarm.bao;
  # The same test ../glue-queue-agent-credential.nix applies, and for the same
  # reason: a reader is defined by holding a certificate the store accepts,
  # not by sharing a host with the store. Deriving this from
  # `deploy.bao.enable` would be the co-location assumption itself.
  haveBaoClientIdentity = baoDeploy.clientCertFile != null && baoDeploy.clientKeyFile != null;
in
{
  # nix (the prebuild `nix build`, flake-check, and meta eval) writes
  # its fetcher/eval cache under $HOME/.cache. As a system user
  # hive-core has no home, so HOME defaults to the unwritable
  # /var/empty and Lix fails to initialise its cache. Point HOME at
  # the writable StateDirectory.
  HOME = "/var/lib/hyperhive";
  HYPERHIVE_GIT = "${pkgs.git}/bin/git";
  # Never let git block on an interactive credential prompt. hive-core is a
  # TTY-less system user, so a prompt (e.g. the forge credential helper
  # returns nothing because the forge isn't reachable yet on cold boot)
  # would hang forever and freeze the daemon during startup. With this set,
  # git fails fast instead of prompting. Paired with the git http
  # low-speed abort in `safeDirGitconfig` (bounds a stalled transfer) and
  # the 120s migration shellout timeout in migrate.rs.
  GIT_TERMINAL_PROMPT = "0";
  # No HIVE_STATIC_DIR: the gateway static-serves the dashboard dist
  # (see the hive-gateway module); this router is API-only.
  # Path to the base agent frontend dist. hive-c0re's
  # gateway_nginx.rs uses this to generate split location
  # blocks in agents.conf — static HTML/CSS/JS served from the
  # nix store directly; dynamic API paths still proxied to the
  # agent daemon. nginx runs on the host, which is where this
  # store path already is, so it is reachable as written.
  HIVE_AGENT_FRONTEND_DIR = "${cfg.servedFrontend}/agent";
  # Path to the static runtime asset tree (branding + claude
  # prompts). `hive_sh4re::assets::*` reads paths underneath.
  # `forge/users.rs` reads the core avatar PNG from here on startup.
  HIVE_ASSETS_DIR = "${cfg.assets}/share/hyperhive";
}
// {
  # Identity env vars threaded into c0re's own service env and
  # forwarded by meta.rs into every sub-agent's harness env —
  # full chain in docs/process/conventions.md::Hive identity. `domain` is
  # required (asserted in hive-network.nix), so it's always set.
  HYPERHIVE_HIVE_DOMAIN = config.services.hyperhive.domain;
}
// lib.optionalAttrs (config.services.hyperhive.swarm.dashboardDomain != null) {
  # The host the dashboard and the agent UIs answer on, for the URLs c0re
  # hands out (`hivectl open home`, each agent's UI link).
  HYPERHIVE_DASHBOARD_DOMAIN = config.services.hyperhive.swarm.dashboardDomain;
}
// lib.optionalAttrs (config.services.hyperhive.hiveName != null) {
  HYPERHIVE_HIVE_NAME = config.services.hyperhive.hiveName;
}
// lib.optionalAttrs (config.services.hyperhive.swarm.name != null) {
  HYPERHIVE_SWARM_NAME = config.services.hyperhive.swarm.name;
}
// lib.optionalAttrs (!config.services.hyperhive.github.enable) {
  # GitHub integration is on by default; only signal the OFF override to
  # meta.rs, which then injects `hyperhive.github.enable = false` into
  # every agent. See services.hyperhive.github.enable.
  HYPERHIVE_GITHUB_DISABLED = "1";
}
// lib.optionalAttrs config.services.hyperhive.otel.enable (
  # Hive-wide OTEL config -> read by meta.rs::otel_config and
  # injected as build-time `hyperhive.otel.*` into every agent.
  # Endpoint presence is the enable signal on the meta side; the
  # optional fields are only emitted when set so absent values
  # don't render no-op env lines.
  let
    otel = config.services.hyperhive.otel;
    # The first hop, this hive's own collector, under the two spellings its
    # two kinds of caller need. Agents get the swarm-wide name, so their
    # builds carry nothing hive-specific; this daemon gets the bridge
    # address, because on the host the name may resolve to loopback
    # (`gateway.localHostsEntry`), where the receiver does not listen.
    agentFirstHop = "http://${otel.collector.host}:${toString otel.collector.port}";
    hostFirstHop = "http://${config.services.hyperhive.network.bridgeIp}:${toString otel.collector.port}";
  in
  {
    # `otel.endpoint` means "where telemetry ultimately goes" and keeps
    # that meaning; what agents are handed is the *first hop*, which is
    # always this hive's own collector. Deriving it rather than
    # redefining `endpoint` is what lets every existing deployment keep
    # its configured value untouched.
    HYPERHIVE_OTEL_ENDPOINT = agentFirstHop;
    # hive-c0re's OWN container-resource exporter (stats/otel_metrics.rs)
    # reads the STANDARD OTLP variable — the same one hive-metric and every
    # agent read — and lets the SDK resolve the URL, which appends the
    # signal path (`/v1/metrics`). Handing the SDK an address
    # programmatically instead takes it verbatim: it POSTs to the
    # collector's root, gets a 404 on every export, and says nothing,
    # because OTLP export failures go to an error handler no binary here
    # installs — the daemon logged "exporter enabled" and never delivered a
    # sample, for as long as it had that exporter. The variable above cannot
    # replace this one:
    # it is the agent-config transport meta.rs reads, and the SDK does not
    # know that name.
    OTEL_EXPORTER_OTLP_ENDPOINT = hostFirstHop;
    # The first hop is the collector's OTLP/HTTP receiver, which speaks
    # protobuf regardless of what the upstream wants — `otel.protocol`
    # describes the *upstream* link, and the collector's own exporter is
    # what has to honour it (see nix/host-modules/otel.nix).
    HYPERHIVE_OTEL_PROTOCOL = "http/protobuf";
  }
  // lib.optionalAttrs (otel.extraResourceAttributes != "") {
    HYPERHIVE_OTEL_EXTRA_RESOURCE_ATTRIBUTES = otel.extraResourceAttributes;
  }
  # HYPERHIVE_OTEL_HEADERS_CREDENTIAL is deliberately NOT emitted, and
  # its absence is the security half of this design: that variable would
  # put the upstream token into an agent's own settings.json. Nothing
  # delivers the token into the container — no nspawn credential, no
  # agent-readable header file.
  #
  # The rule: the collector holding the credential achieves nothing while
  # anything else hands out a copy, so there is exactly one holder and it
  # is on the host.
  // lib.optionalAttrs (otel.metricIntervalMs != null) {
    HYPERHIVE_OTEL_METRIC_INTERVAL_MS = toString otel.metricIntervalMs;
  }
  // lib.optionalAttrs otel.debug {
    HYPERHIVE_OTEL_DEBUG = "1";
  }
)
// {
  # In-cluster forge URL — the gateway vhost (`forge.<domain>`), which
  # nginx proxies to forgejo. Used both for internal API calls in
  # hive-c0re (forge/mod.rs `forge_http_base()`) and forwarded to
  # agents via meta.rs for their forge-notify client. The forge is
  # mandatory, so this is unconditional (the whole env block is already
  # gated on hyperhive being enabled). See `docs/networking/gateway.md::HIVE_FORGE_URL`.
  HIVE_FORGE_URL = "http://${config.services.hyperhive.swarm.forge.domain}";

  # The one blacklist of names an agent may not take — see
  # `nix/reserved-names.nix`, which is also read by the swarm controller, by
  # the swarm collector's owner assertion, and by the test suite. Nix owns it
  # so that keeping it current is a config change, not a rebuild of a binary.
  #
  # Whitespace-separated rather than JSON: every entry is an `Ident`
  # (`[a-z0-9-]`), so a space can never occur inside a name and the encoding
  # cannot be lossy. Spelling it as JSON would put a parser in the crate whose
  # whole point is to have no dependencies.
  #
  # Unconditional on purpose. The consumer treats an ABSENT variable as "I was
  # never told" and says so out loud, which is the correct reading — but it is
  # a reading no correctly-built hive should ever have to make.
  HIVE_RESERVED_NAMES = lib.concatStringsSep " " (import ../../reserved-names.nix);
}
// lib.optionalAttrs (config.services.hyperhive.swarm.matrix.gatewayHost != null) {
  # Matrix homeserver URL for each agent's hive-matrix-daemon — the
  # gateway vhost (`chat.<swarm-domain>`). Forwarded to agents by meta.rs
  # alongside HIVE_FORGE_URL; shares the same env-forwarding ordering
  # caveat (value baked at config-generation time).
  #
  # Deliberately NOT conditioned on this host running the homeserver. A
  # swarm has one matrix, and every hive's agents talk to it — the hive
  # that hosts it is not the only hive whose agents need its address.
  # `gatewayHost` is swarm-scoped and names that one homeserver from any
  # member hive, so its being set is the whole question.
  #
  # Null forwards nothing rather than falling back to loopback. That
  # fallback reads as harmless because hive-c0re shares the host netns —
  # but the value is handed to *agents*, which do not, so `127.0.0.1`
  # there names the agent itself. An absent forward leaves
  # `hyperhive.matrix.url` null and the daemon no-ops; that is the honest
  # answer when there is no matrix vhost to point at.
  HIVE_MATRIX_URL = "http://${config.services.hyperhive.swarm.matrix.gatewayHost}";
}
// lib.optionalAttrs (config.services.hyperhive.swarm.matrix.apiUrl != null) {
  # Client-server API base hive-c0re uses to provision matrix (register
  # agent users, create the hive space + chat room, invite members).
  # Supplied by `services.hyperhive.swarm.matrix.apiUrl`, which defaults to
  # the same gateway vhost as HIVE_MATRIX_URL above, over https because it
  # carries the hive's matrix token and may cross the network. Its own
  # option, so provisioning can point elsewhere without changing agents.
  HIVE_MATRIX_API_URL = config.services.hyperhive.swarm.matrix.apiUrl;
}
// {
  # The gateway always runs, so the dashboard always builds
  # same-origin `/agent/<name>/` links (never the direct
  # `<host>:<port>` TCP fallback). Kept as an env flag so the
  # dashboard doesn't need to learn the gateway is unconditional.
  HIVE_GATEWAY_ENABLED = "1";
}
// lib.optionalAttrs (config.services.hyperhive.swarm.forge.publicUrl != null) {
  # Public URL of the forge, for the dashboard to build browser-facing
  # forge links from instead of guessing `<hostname>:3000` (which
  # breaks the moment the operator's browser hostname isn't the forge
  # host, e.g. through the gateway or a reverse proxy). Sourced from
  # `services.hyperhive.swarm.forge.publicUrl`, which itself defaults to the
  # gateway vhost URL — see that option's doc for the "hide, don't guess"
  # rationale.
  # Absent here whenever `publicUrl` is `null`; the dashboard hides
  # forge links rather than emitting one it can't justify.
  HIVE_FORGE_PUBLIC_URL = config.services.hyperhive.swarm.forge.publicUrl;
}
// lib.optionalAttrs (config.services.hyperhive.swarm.domain != null) {
  # Browser URL of the swarm UI, which answers on the swarm apex domain
  # (see ../swarm-ui.nix). The dashboard links to it from its pages menu.
  # Absent when the domain is unset, so the link is hidden rather than
  # guessed.
  HIVE_SWARM_PUBLIC_URL = "https://${config.services.hyperhive.swarm.domain}/";
}
// lib.optionalAttrs (config.services.hyperhive.swarm.matrix.gatewayHost != null) {
  # Browser-facing matrix GUI (fluffychat) URL — the gateway
  # vhost (`gatewayHost`, `chat.<swarm-domain>` by default). Surfaced via the daemon's `Urls`
  # request for `hivectl open matrix`. Absent when no gatewayHost is
  # set (no browser-reachable matrix vhost).
  HIVE_MATRIX_PUBLIC_URL = "https://${config.services.hyperhive.swarm.matrix.gatewayHost}/";
}
// lib.optionalAttrs (config.services.hyperhive.swarm.snapshotStore.address != null) {
  # `host:port` of the swarm's single snapshot store, for pushing agent
  # snapshots (hive-c0re::snapshot_push). One per swarm, not one per
  # peer — the receiver keys destinations by agent so a migrating agent
  # keeps one incremental chain. Absent when no store is configured, and
  # a push then fails naming the option rather than guessing.
  HYPERHIVE_SNAPSHOT_STORE =
    let
      s = config.services.hyperhive.swarm.snapshotStore;
    in
    "${s.address}:${toString s.port}";
}
//
  # Swarm-queue coordinates for offering this hive's status upward
  # (hive-c0re::swarm_status). All three together or none: a half-set
  # environment is a deployment bug the daemon refuses to treat as
  # "no queue configured", because the failure it would otherwise
  # produce is a hive that comes up fine and silently never reports.
  #
  # The client secret is not among them: the daemon reads it from the
  # swarm's secret store under this hive's own certificate
  # (`swarm_secret_client::queue::hive_client_path`), so a hive with no
  # store identity has no way to publish and is handed nothing.
  lib.optionalAttrs
    (
      config.services.hyperhive.deploy.hive-controller.statusPublish.natsUrl != null
      && config.services.hyperhive.swarm.statusPublish.tokenEndpoint != null
      && haveBaoClientIdentity
    )
    {
      HIVE_C0RE_NATS_URL = config.services.hyperhive.deploy.hive-controller.statusPublish.natsUrl;
      HIVE_C0RE_OIDC_TOKEN_ENDPOINT = config.services.hyperhive.swarm.statusPublish.tokenEndpoint;
      # The identity swarm-authelia.nix already declares for every entry in
      # `swarm.hives` — the hive does not choose its own name here, it uses
      # the one the roster gave it.
      HIVE_C0RE_OIDC_CLIENT_ID = "hive-${config.services.hyperhive.hiveName}";
    }
// {
  # Where ../glue-queue-agent-credential.nix lands the AGENTS' queue
  # credential. Read by `hive_c0re::lifecycle::host_config`, which stats the
  # two files and forwards them into each container as systemd credentials.
  # Never read for its contents here: the secret is `0600` root-owned and
  # this daemon is `hive-core`, which is exactly why the transport is a
  # credential rather than a bind mount.
  HIVE_C0RE_AGENT_QUEUE_CREDENTIAL_DIR = toString config.services.hyperhive.deploy.hive-controller.queue.agentCredentialDir;
}
//
  # The agents' half of the same queue, forwarded by `hive_c0re::meta` into
  # every container. A pair, gated together, because an agent that got one of
  # them would report a half-configured queue instead of none.
  #
  # ⚠️ By name, like `HIVE_C0RE_NATS_URL` above, and never a loopback
  # address: inside a container `127.0.0.1` is the agent itself.
  lib.optionalAttrs
    (
      config.services.hyperhive.deploy.hive-controller.queue.agentNatsUrl != null
      && config.services.hyperhive.swarm.statusPublish.tokenEndpoint != null
    )
    {
      HIVE_AGENT_NATS_URL = config.services.hyperhive.deploy.hive-controller.queue.agentNatsUrl;
      HIVE_AGENT_OIDC_TOKEN_ENDPOINT = config.services.hyperhive.swarm.statusPublish.tokenEndpoint;
    }
//
  # Where an agent reads the swarm's logs. Gated on the store identity below,
  # because `swarm-logs` authenticates with the agent's own queue secret, read
  # from the store: an address with nothing to authenticate as would put a
  # binary on PATH that can only ever answer 401, which an agent reads as "no
  # logs".
  #
  # The **machine** route (`^~ /select/logsql/`), not the browser one at `/`:
  # that one ends in `error_page 401 =302` and hands a machine caller
  # authelia's login page as a 200 with an HTML body. See
  # `swarm-victorialogs.nix`'s location for the whole reasoning.
  lib.optionalAttrs haveBaoClientIdentity {
    HIVE_AGENT_LOGS_QUERY_URL = "https://${config.services.hyperhive.swarm.victorialogs.domain}/select/logsql/query";
  }
//
  # Where the swarm's secret store is, and the identity this hive presents to
  # it (hive-c0re::lifecycle::agent_identity). `swarm_secret_client` reads these
  # spellings explicitly rather than vaultrs's `VAULT_*` defaults — falling
  # through to those would build a client with no identity and fail at the TLS
  # handshake, naming neither.
  lib.optionalAttrs haveBaoClientIdentity {
    BAO_ADDR = "https://${baoCfg.domain}:${toString baoCfg.port}";
    # The same address again under an agent-facing name, forwarded into every
    # container's module block by `meta::render_flake`. Deliberately not the
    # `BAO_ADDR` line itself: a container that inherited this hive's store
    # environment wholesale would inherit the hive's certificate paths with it,
    # and those name a credential no agent may present.
    HIVE_AGENT_BAO_ADDR = "https://${baoCfg.domain}:${toString baoCfg.port}";
    # `%d`, not the paths themselves: the key is `0600` root-owned and this
    # daemon runs as hive-core, so it never gets read access to the original.
    # See the LoadCredential in ./default.nix.
    BAO_CLIENT_CERT = "%d/bao-client.pem";
    BAO_CLIENT_KEY = "%d/bao-client-key.pem";
  }
// lib.optionalAttrs (haveBaoClientIdentity && baoDeploy.serverCaFile != null) {
  # Absent means the system trust store — right for a deployment with a real
  # CA, wrong for the self-signed one ../glue-bao-tls.nix mints, which is why
  # that file names this path rather than leaving it to a default.
  BAO_CACERT = "%d/bao-ca.pem";
}