hyperhive/nix/templates/weston-vnc.nix

{
  pkgs,
  lib,
  config,
  ...
}:
{
  # Optional Weston (the reference Wayland compositor) with the VNC
  # backend, surfaced as a per-agent hyperhive option. An agent turns
  # it on from its own `agent.nix`:
  #
  #   hyperhive.gui.enable = true;
  #
  # Imported by `harness-base.nix`, so every sub-agent + the manager
  # has the option available; only those that flip it on get the
  # service. This is a flat per-agent option (evaluated inside that
  # agent's own container build) — NOT a `hyperhive.agents.<name>.*`
  # registry, which can't work: each agent is its own
  # nixosConfiguration and has no cross-agent view.
  #
  # VNC port selection: a deterministic FNV-1a hash of the agent name
  # (derived from the container hostname at runtime) maps into the
  # range [15900, 16799], mirroring lifecycle::agent_web_port. The
  # computed port is written to `/etc/hyperhive/gui.json` at service
  # start; the harness (issue #51) reads that file to know where to
  # relay WebSocket connections.
  #
  # Note: weston's VNC backend does not expose a CLI bind-address flag
  # (unlike the RDP backend's `--address`), so VNC listens on all
  # interfaces. The harness WebSocket relay (issue #51) connects only
  # via 127.0.0.1, and the host firewall should block external access
  # to the VNC port range. A future weston.ini `[vnc] address=` can
  # restrict this once upstream supports it.

  options.hyperhive.gui.enable = lib.mkOption {
    type = lib.types.bool;
    default = false;
    description = ''
      Run Weston with the VNC backend as a systemd service, for
      in-browser GUI access via the harness WebSocket relay (see
      issue #51). Renders in software (pixman) — no GPU, DRM,
      or VT access, so no extra container capabilities are needed.

      The VNC port is deterministic: FNV-1a hash of the agent name
      (taken from the container hostname) mapped into [15900, 16799].
      The port and auth mode are written to `/etc/hyperhive/gui.json`
      at service start so the harness can relay connections.

      The unit is deliberately built so enabling it can NEVER abort
      the agent's `nixos-container update`: `Type = "simple"` (so
      `switch-to-configuration` doesn't block on weston readiness)
      and the ExecStart script always tries to exec weston after
      setup — a misconfigured weston degrades to a restart loop
      visible in `journalctl`, it does not block the rebuild. (Same
      reasoning as the `tea-login` unit in `harness-base.nix`.)
    '';
  };

  config = lib.mkIf config.hyperhive.gui.enable {
    systemd.services.weston = {
      description = "Weston Wayland compositor (VNC backend)";
      after = [ "network.target" ];
      wantedBy = [ "multi-user.target" ];
      serviceConfig = {
        # `simple`, not `notify`: switch-to-configuration must not
        # wait on weston signalling readiness. See weston-rdp.nix and
        # the `tea-login` unit for the same reasoning.
        Type = "simple";
        # Creates /var/lib/weston (0700 root) at start.
        StateDirectory = "weston";
        Environment = "XDG_RUNTIME_DIR=/run/user/0";
        # Wrapper script: computes the deterministic VNC port, writes
        # /etc/hyperhive/gui.json for the harness (issue #51), then
        # execs weston. Using `exec` keeps the PID stable so systemd
        # tracks the weston process correctly under Type=simple.
        # Any failure before the exec triggers Restart=on-failure
        # (graceful degradation) rather than blocking the rebuild.
        ExecStart = pkgs.writeShellScript "weston-vnc" ''
          mkdir -p /run/user/0 && chmod 700 /run/user/0 || true

          # --- Compute deterministic VNC port via FNV-1a ---
          # Agent name = container hostname with leading "h-" stripped,
          # mirroring lifecycle::agent_web_port in hive-c0re/src/lifecycle.rs.
          # Read from /etc/hostname (always present in NixOS containers)
          # to avoid a dependency on the `hostname` binary (which lives in
          # pkgs.inetutils, not pkgs.coreutils).
          # VNC_PORT_BASE=15900, VNC_PORT_RANGE=900 → [15900, 16799].
          RAW_HOST=$(${pkgs.coreutils}/bin/cat /etc/hostname)
          AGENT_NAME=$(${pkgs.coreutils}/bin/printf '%s' "$RAW_HOST" \
            | ${pkgs.gnused}/bin/sed 's/^h-//')
          hash=2166136261
          for byte in $(${pkgs.coreutils}/bin/printf '%s' "$AGENT_NAME" \
              | ${pkgs.coreutils}/bin/od -An -tu1 \
              | ${pkgs.coreutils}/bin/tr -s ' \n' ' '); do
            [ -n "$byte" ] || continue
            hash=$(( ((hash ^ byte) * 16777619) & 4294967295 ))
          done
          VNC_PORT=$((15900 + hash % 900))

          # --- Write gui.json marker ---
          # The harness reads this at startup (issue #51) to know the
          # VNC port and auth mode for the WebSocket relay.
          ${pkgs.coreutils}/bin/mkdir -p /etc/hyperhive
          ${pkgs.coreutils}/bin/printf '{"vnc_port":%d,"auth":"none"}\n' \
            "$VNC_PORT" > /etc/hyperhive/gui.json || true

          # --disable-transport-layer-security: VNC is loopback-only
          # (relayed by the harness WebSocket proxy); TLS would require
          # cert generation and adds no real security benefit here.
          exec ${pkgs.weston}/bin/weston \
            --backend=vnc-backend.so \
            --renderer=pixman \
            --port="$VNC_PORT" \
            --disable-transport-layer-security
        '';
        Restart = "on-failure";
        RestartSec = "5s";
      };
    };

    # weston on the agent's interactive PATH too, so claude can run
    # Wayland clients / `weston-info` against the compositor.
    environment.systemPackages = [ pkgs.weston ];
  };
}