hyperhive/nix/agent-modules/default.nix

# Shared scaffolding for every hyperhive harness container.
# `../templates/agent.nix`, the one entry point every agent builds from,
# imports it.
#
# This is the core module: container plumbing (boot/nix/nixpkgs),
# base tooling, and the cross-cutting `services.hyperhive.agent.icon` option. Each
# feature lives in its own sibling module (imported below) that
# declares its own `services.hyperhive.agent.*` options + config.
{
  pkgs,
  lib,
  config,
  # Flake inputs routed through _module.args by the agent flake.nix.
  # Default to {} so the module evaluates cleanly even when the agent
  # flake doesn't set up the routing pattern (e.g. during standalone
  # nixos-rebuild without a flake wrapper).
  flakeInputs ? { },
  ...
}:
let
  hiveNameRemoved = ''
    An agent reads its hive's name at runtime from /etc/hyperhive-hive-facts,
    which the hive writes into every container, so no agent build sets it.
    Remove the setting.
  '';
  memoryMaxBytesRemoved = ''
    An agent reads its memory cap at boot from /run/hive/memory-max-bytes,
    which the hive writes before every start, so no agent build sets it.
    Remove the setting.
  '';
  claudeCodePathRemoved = ''
    An agent reads the claude-code its hive pins at runtime, from
    HYPERHIVE_CLAUDE_CODE_PATH in /etc/hyperhive-hive-facts, so no agent build
    sets it. Pin it host-side with
    services.hyperhive.deploy.hive-controller.claudeCodePackage.
  '';
  queueRemoved = ''
    The harness reads the queue's address at runtime from HIVE_AGENT_NATS_URL,
    in /etc/hyperhive-hive-facts, and authenticates with the
    agent's own secret from the swarm secret store, so no agent build sets a
    queue option. Remove the setting.
  '';

  # `claude` on PATH. A hive that pins a claude-code
  # (`services.hyperhive.deploy.hive-controller.claudeCodePackage`) hands its
  # store path over at container start as `HYPERHIVE_CLAUDE_CODE_PATH`, and
  # the host's system closure keeps it alive: nothing in this container
  # references it. With no pin, or a path that is not there, this container's
  # own claude-code runs; a pin that is set but gone (collected after a bump
  # while this container still holds the old facts) says so on stderr, since
  # the two builds can differ. `exec -a claude` keeps the bare name in argv[0],
  # which is how the harness finds its claude child (`find_claude_child`).
  ownClaude = import ../claude-code-no-alsa.nix lib pkgs.claude-code;
  claude = pkgs.writeShellScriptBin "claude" ''
    pinned=''${HYPERHIVE_CLAUDE_CODE_PATH:-}
    if [ -n "$pinned" ] && [ -x "$pinned/bin/claude" ]; then
      exec -a claude "$pinned/bin/claude" "$@"
    fi
    if [ -n "$pinned" ]; then
      echo "claude: $pinned/bin/claude, the hive's pinned claude-code, is missing; running this container's own" >&2
    fi
    exec -a claude ${ownClaude}/bin/claude "$@"
  '';
in
{
  imports = [
    ./agent-service.nix
    ./bao.nix
    ./bash-env.nix
    ./claude-settings.nix
    ./dashboard-links.nix
    ./docs.nix
    ./forge.nix
    ./forge-accounts.nix
    ./forge-token.nix
    ./frontend.nix
    ./github.nix
    ./github-token.nix
    ./hive-ca.nix
    ./hive-facts.nix
    ./logs.nix
    ./matrix.nix
    ./mcp.nix
    ./memory-cap.nix
    ./metrics.nix
    ./network.nix
    ./otel.nix
    ./otel-removed.nix
    ./packages.nix
    ./queue-identity.nix
    ./user.nix
    ./screen.nix
    ./weston-vnc.nix
    # The hive supplies both at runtime; a definition fails the eval, naming
    # where the value comes from.
    (lib.mkRemovedOptionModule [ "services" "hyperhive" "agent" "hiveName" ] hiveNameRemoved)
    (lib.mkRemovedOptionModule [
      "services"
      "hyperhive"
      "agent"
      "claudeMemoryMaxBytes"
    ] memoryMaxBytesRemoved)
    (lib.mkRemovedOptionModule [
      "services"
      "hyperhive"
      "agent"
      "claudeCodePath"
    ] claudeCodePathRemoved)
    (lib.mkRemovedOptionModule [ "services" "hyperhive" "agent" "queue" "natsUrl" ] queueRemoved)
    (lib.mkRemovedOptionModule [ "services" "hyperhive" "agent" "queue" "tokenEndpoint" ] queueRemoved)
  ];

  options.services.hyperhive.agent.icon = lib.mkOption {
    type = lib.types.nullOr lib.types.path;
    default = null;
    example = lib.literalExpression "./icon.svg";
    description = ''
      Path to an SVG file used as this agent's icon — shown on the
      dashboard and the per-agent web UI (header + favicon). Commit
      the SVG into the agent's config repo next to `agent.nix` and
      reference it as a relative path (`./icon.svg`).

      When null (the default), `GET /icon` on the per-agent web port
      404s and consumers (dashboard, this agent's own page header)
      fall back client-side to the frontend-bundled `/favicon.svg`
      rather than a server-resolved default.
    '';
  };

  config = {
    assertions = [
      # Guard the inputs-routed-as-output pattern: the agent flake.nix is
      # expected to set `_module.args.flakeInputs = builtins.removeAttrs inputs ["self"]`.
      # If `self` leaks into flakeInputs the agent gets a spurious attrset
      # entry that can shadow real inputs and is almost certainly a bug.
      # Guard with `or {}` so standalone evaluation stays clean when
      # flakeInputs is absent from _module.args.
      {
        assertion = !(builtins.hasAttr "self" (config._module.args.flakeInputs or { }));
        message = ''
          hyperhive: `flakeInputs` must not contain "self".
          In your agent flake.nix, use:
            _module.args.flakeInputs = builtins.removeAttrs inputs [ "self" ];
        '';
      }
      # services.hyperhive.agent.icon must reference an SVG file when set.
      {
        assertion =
          config.services.hyperhive.agent.icon == null
          || lib.hasSuffix ".svg" (toString config.services.hyperhive.agent.icon);
        message = "services.hyperhive.agent.icon must point to an .svg file";
      }
    ];

    # Operator-set per-agent icon (services.hyperhive.agent.icon). When configured, the
    # SVG lands at /etc/hyperhive/icon.svg; the harness serves it at
    # GET /icon, 404ing when absent (client-side fallback, no
    # server-side default). Consumed by forge-avatar-sync (./forge.nix)
    # and the matrix avatar sync (./matrix.nix) too.
    environment.etc."hyperhive/icon.svg" = lib.mkIf (config.services.hyperhive.agent.icon != null) {
      source = config.services.hyperhive.agent.icon;
    };

    boot.isNspawnContainer = true;

    # Use a disk-backed /tmp instead of the default tmpfs so large scratch
    # writes (nix-develop shells, cargo build dirs, multi-GB downloads) land
    # on disk rather than eating container RAM.  The tmpfs default mounts
    # ~3.2 GB of RAM per container; disk-backed /tmp is effectively unlimited
    # and cheaper for agents that do heavy build work.
    #
    # cleanOnBoot defaults to false in nixpkgs — set it explicitly so /tmp is
    # cleared on each container start (D! tmpfiles rule), preserving the
    # ephemeral-per-boot semantics agents expect from a tmpfs /tmp, just
    # without the RAM cost.
    boot.tmp.useTmpfs = false;
    boot.tmp.cleanOnBoot = true;

    # Every agent gets flakes + the modern `nix` CLI out of the box.
    # Equivalent to passing `--extra-experimental-features 'nix-command
    # flakes'` on every invocation. Agents shell out to `nix build` /
    # `nix flake` constantly (devshells, ad-hoc evals, fetching their
    # own MCP-server flakes); without this they hit the "experimental
    # feature not enabled" wall on the first try.
    nix.settings.experimental-features = [
      "nix-command"
      "flakes"
    ];

    # `lib.mkForce` overrides nixpkgs's normal-priority `false` so
    # in-container `nix build` invocations fall back to unsandboxed
    # local builds rather than failing on the missing user-namespace.
    # See `docs/process/gotchas.md::Containerized nix-daemon needs
    # sandbox-fallback = true` + `docs/trust-boundary/security.md` for the rationale.
    #
    # Note: with NIX_REMOTE=daemon below this becomes a no-op for the
    # common case — daemon-routed builds run on the host where sandboxing
    # works. It stays as a belt-and-suspenders fallback for any context
    # that bypasses the daemon (e.g. direct nix-store invocations).
    nix.settings.sandbox-fallback = lib.mkForce true;

    # Fall back to a local build when a remote builder can't be reached,
    # instead of hard-failing the whole invocation.
    #
    # This is NOT redundant with the host daemon's own setting, and that
    # is the subtle part: `fallback` (protocol `tryFallback`) is a *client*
    # option. Every nix client transmits it to the daemon on connect, so
    # the client — i.e. this container — decides whether a failed remote
    # dispatch may degrade to a local build, even though the build itself
    # executes on the host daemon under NIX_REMOTE=daemon below. Contrast
    # `builders`, which is genuinely daemon-side and which an untrusted
    # client cannot override. Without this, a container inherits nix's
    # default `false`, so a momentarily unreachable remote builder kills
    # the invocation while the exact same build started on the host
    # succeeds.
    nix.settings.fallback = true;

    # Route ALL nix invocations in this container through the host
    # nix-daemon socket, regardless of whether the caller is root or
    # non-root. Without this, root contexts (PID 1, systemd services
    # running as root) default to store=auto which resolves to the LOCAL
    # store — bypassing the shared daemon, its remote builders, and the
    # host's prebuilt derivation cache, causing spurious full rebuilds.
    #
    # systemd.globalEnvironment sets DefaultEnvironment in systemd.conf,
    # so every unit started by PID 1 inherits NIX_REMOTE=daemon.
    # Non-root nix clients already default to the daemon socket, so this
    # is a no-op for them; it only matters for root services that would
    # otherwise silently use the local store.
    systemd.globalEnvironment.NIX_REMOTE = "daemon";

    # `claude-code` is unfree. Each per-agent container's nixosConfiguration
    # evaluates its own `nixpkgs` instance, so the operator's host-level
    # `nixpkgs.config.allowUnfreePredicate` does not propagate into here —
    # we have to allow it inside the container's config as well.
    nixpkgs.config.allowUnfreePredicate = pkg: builtins.elem (pkgs.lib.getName pkg) [ "claude-code" ];

    # Core tooling every agent gets. Per-bin split packages (see
    # nix/packages/default.nix + ./packages.nix) rather than the full
    # `hyperhive` bundle — that bundle also carries `hivectl` (a
    # host-admin CLI that dials the *host* admin socket — useless and
    # unreachable from inside a container — wrapped with
    # `wireguard-tools` for `hivectl wg`). The daemon/harness/MCP bins
    # the harness execs (hive-agent{,-mcp}, hive-bash-daemon,
    # hive-subagent-daemon, hive-matrix-daemon, hive-matrix-mcp) are
    # wired via their own
    # ExecStart/command lines in the sibling modules — they don't need
    # to be on PATH too. Only this one is actually looked up on PATH
    # by claude/shell code inside the container:
    # `hive-metric` (agent-emitted custom metrics CLI,
    # docs/scheduler/observability.md).
    environment.systemPackages = [
      config.services.hyperhive.agent.packages.hive-metric
    ]
    ++ [
      claude
    ]
    ++ (with pkgs; [
      bashInteractive
      coreutils-full
      # procps for kill — used by the web UI's /api/cancel and /api/logout
      # to SIGINT the harness-spawned claude child found via a /proc scan
      # (see hive-agent::web_ui::find_claude_child).
      procps
      # jq: JSON processing in shell — useful for parsing API responses,
      # forge REST calls, sqlite output, etc.
      jq
      # curl: HTTP client for forge REST API and other web requests.
      curl
    ]);

    # HIVE_ASSETS_DIR points at the project's static runtime assets
    # (branding + claude prompts; see `nix/packages/assets.nix`). Set
    # here so both the harness binary and any user-shell `cargo run`
    # inside the container resolve them from the same path.
    # SHELL must be set so claude's Bash tool finds a POSIX shell.
    environment.variables = {
      HIVE_ASSETS_DIR = "${config.services.hyperhive.agent.packages.assets}/share/hyperhive";
      SHELL = "${pkgs.bashInteractive}/bin/bash";
      # Route interactive-shell nix invocations through the host daemon.
      # Redundant with /etc/profile.d/nix-daemon.sh but ensures it's set
      # regardless of which profile files are sourced.
      NIX_REMOTE = "daemon";
    };

    # Git is needed by claude's Bash tool (for the agent <-> manager config
    # request flow) and by hive-c0re's own setup_applied / setup_proposed.
    # The per-agent `applied/<name>/flake.nix` overrides `user.name` and
    # `user.email` with the agent's identity — values here are `mkDefault`
    # so the per-agent override wins without needing `mkForce`.
    programs.git = {
      enable = true;
      config = {
        user = {
          name = lib.mkDefault "hyperhive";
          email = lib.mkDefault "hyperhive@local";
        };
        init.defaultBranch = lib.mkDefault "main";
      };
    };

    system.stateVersion = "25.11";
  };
}