cc-ci-orchestrator/nix/hosts/cc-ci-orchestrator-hetzner/configuration.nix

# cc-ci-orchestrator-hetzner — NixOS config for the Hetzner loops runtime host.
#
# Purpose: run the cc-ci Builder/Adversary/Watchdog loops + orchestrator/assistant sessions
# on a Hetzner cpx11 (2 vCPU / 2 GB dedicated AMD / 40 GB NVMe), replacing the slow b1 Incus VM.
#
# Provision with terraform/ then converge with: nixos-rebuild switch --flake .#cc-ci-orchestrator-hetzner
# See terraform/README.md for the full Stage 2 procedure.
{ config, pkgs, lib, ... }:
{
  # hardware.nix is the nixos-infect generated hardware-configuration.nix (see README Stage 2a).

  services.openssh = {
    enable = true;
    settings.PermitRootLogin = "yes";
  };

  # Root SSH access — all keys from the current orchestrator VM's /root/.ssh/authorized_keys.
  users.users.root.openssh.authorizedKeys.keys = [
    "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIOk8NaeBdPbS2gfUvbny8h0AkZlVjGYHzx4QPXSJ38gd claude@claude-vm"
    "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIJVlfoLBPseQ9fA9534KmRg2KWcksKZGzAJIpHJ2JpsI mfowler.email@protonmail.com"
    "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIAcyTGb/wVgdhg5oBCZZvBaR1RuUQRY/3WHnOQpNDCsp claude-cc-ci-sandbox@20260526"
  ];
  networking.useDHCP = true;
  networking.nameservers = [ "1.1.1.1" "8.8.8.8" ];
  networking.firewall = {
    enable = true;
    trustedInterfaces = [ "tailscale0" ];
    # Port 80 open only on the tailscale interface (trusted) — nginx binds there for oc.commoninternet.net.
    allowedTCPPorts = [ 22 ];
  };
  nix.settings.experimental-features = [ "nix-command" "flakes" ];
  system.stateVersion = "24.11";

  # Tailscale — auth key at /etc/ts-auth-key (placed manually in Stage 2, not in git).
  services.tailscale = {
    enable = true;
    authKeyFile = "/etc/ts-auth-key";
    extraUpFlags = [ "--hostname=cc-ci-orchestrator" ];
  };

  # 4 GB disk swap — claude session memory safety net (2 GB RAM is tight for 3+ sessions).
  swapDevices = [ { device = "/swapfile"; size = 4096; } ];

  # nix-ld — lets the standalone Claude Code CLI (foreign dynamic ELF / Bun) run on NixOS.
  programs.nix-ld.enable = true;
  programs.nix-ld.libraries = with pkgs; [
    stdenv.cc.cc.lib
    zlib
    openssl
    curl
    glibc
  ];

  environment.systemPackages = with pkgs; [
    git tmux python3 jq curl cacert
    gnused gawk coreutils gnugrep findutils util-linux
    nettools openssh
    age sops                # key management (same toolchain as cc-ci server)
  ];

  # loops user — claude sessions run as non-root (--dangerously-skip-permissions blocked for root).
  users.users.loops = {
    isNormalUser = true;
    home = "/home/loops";
    shell = pkgs.bash;
    extraGroups = [ "wheel" ];
  };
  security.sudo.wheelNeedsPassword = false;
  security.sudo.extraRules = [{
    users = [ "loops" ];
    commands = [{ command = "ALL"; options = [ "NOPASSWD" ]; }];
  }];

  # Ensure /home/loops/.local/bin (claude + opencode) is on the loops user PATH.
  # opencode binary is installed there manually (not yet in nixpkgs); re-install if missing:
  #   curl -sL https://github.com/anomalyco/opencode/releases/download/v1.15.13/opencode-linux-x64.tar.gz \
  #     | tar -xz -C /home/loops/.local/bin opencode && chmod +x /home/loops/.local/bin/opencode
  environment.variables.PATH = lib.mkForce
    "/home/loops/.local/bin:/run/current-system/sw/bin:/run/wrappers/bin:/usr/bin:/bin";

  # SSH config for the loops user — points to the cc-ci Hetzner server via tailnet.
  # HostName is updated post-cutover to the Hetzner cc-ci tailnet IP.
  system.activationScripts.loopsSshConfig = ''
    mkdir -p /home/loops/.ssh && chown loops:users /home/loops/.ssh && chmod 700 /home/loops/.ssh
    # Only write if not already present (preserves manual customisation).
    if [ ! -f /home/loops/.ssh/config ]; then
      cat > /home/loops/.ssh/config <<'SSHCFG'
Host cc-ci
    HostName REPLACE_WITH_CC_CI_HETZNER_TAILNET_IP
    User root
    IdentityFile /home/loops/.ssh/cc-ci-root-ed25519
    IdentitiesOnly yes
    StrictHostKeyChecking accept-new
    ServerAliveInterval 30
SSHCFG
      chmod 600 /home/loops/.ssh/config
      chown loops:users /home/loops/.ssh/config
    fi
  '';

  # claude-install — fetch the standalone Claude Code CLI for the loops user if missing.
  systemd.services.claude-install = {
    description = "Install Claude Code CLI for loops user (idempotent)";
    wantedBy = [ "multi-user.target" ];
    after = [ "network-online.target" ];
    wants = [ "network-online.target" ];
    serviceConfig = {
      Type = "oneshot"; RemainAfterExit = true;
      User = "loops"; Group = "users";
    };
    environment = { HOME = "/home/loops"; };
    path = [ pkgs.curl pkgs.bash pkgs.coreutils pkgs.gnutar pkgs.gzip ];
    script = ''
      if [ ! -x "$HOME/.local/bin/claude" ]; then
        echo "installing Claude Code CLI for loops user..."
        curl -fsSL https://claude.ai/install.sh | bash || echo "install failed — retry on next activation"
      fi
    '';
  };

  # opencode web server — one shared instance; all agent sessions attach to it.
  # Serves the web UI at http://oc.commoninternet.net (via nginx below, tailscale-only).
  # TINFOIL_API_KEY and other creds are read from /srv/cc-ci/.testenv at startup.
  systemd.services.opencode-web = {
    description = "opencode web server for cc-ci agents (tinfoil/deepseek backend)";
    wantedBy = [ "multi-user.target" ];
    after = [ "network-online.target" "tailscaled.service" ];
    wants = [ "network-online.target" ];
    serviceConfig = {
      Type = "simple";
      User = "loops"; Group = "users";
      WorkingDirectory = "/srv/cc-ci-orch/cc-ci";
      EnvironmentFile = "/srv/cc-ci/.testenv";
      ExecStartPre = "${pkgs.coreutils}/bin/rm -rf /tmp/opencode";
      ExecStart = "/home/loops/.local/bin/opencode serve --hostname 127.0.0.1 --port 4096";
      Restart = "on-failure";
      RestartSec = "5s";
    };
    environment = { HOME = "/home/loops"; };
    path = [ pkgs.bash pkgs.coreutils pkgs.git pkgs.python3 pkgs.openssh pkgs.tmux pkgs.nettools ];
  };

  # nginx — reverse-proxy oc.commoninternet.net → opencode web server.
  # Bound to the tailscale IP so it is only reachable on the tailnet.
  # DNS: add A record  oc.commoninternet.net → 100.84.190.30  (operator step).
  services.nginx = {
    enable = true;
    recommendedProxySettings = true;
    virtualHosts."oc.commoninternet.net" = {
      # Listen on the tailscale interface only — not the public IP.
      listen = [{ addr = "100.84.190.30"; port = 80; ssl = false; }];
      locations."/" = {
        proxyPass = "http://127.0.0.1:4096";
        proxyWebsockets = true;
      };
    };
  };

  # cc-ci-loops supervisor — workspace staged 2026-05-31, so ENABLED for reboot-resilience.
  systemd.services.cc-ci-loops = {
    description = "cc-ci Builder/Adversary loops + watchdog (launch.sh start)";
    wantedBy = [ "multi-user.target" ];  # enabled after workspace staged (Hetzner cutover)
    after = [ "network-online.target" "tailscaled.service" "claude-install.service" ];
    wants = [ "network-online.target" ];
    serviceConfig = {
      Type = "oneshot"; RemainAfterExit = true;
      User = "loops"; Group = "users";
      WorkingDirectory = "/srv/cc-ci/cc-ci";
      # Append one line to REBOOTS.md per genuine reboot (boot_id-gated; not on manual restart).
      ExecStartPre = "${pkgs.bash}/bin/bash /srv/cc-ci/cc-ci-plan/reboot-log.sh";
    };
    # CLAUDE_BIN points at the standalone CLI installed by claude-install.service; the loops
    # backend defaults to claude (persisted in .loop-backend). Without this, launch.py's preflight
    # `which(claude)` fails because the systemd `path` below has no /home/loops/.local/bin.
    environment = { RESUME_PHASE = "1"; HOME = "/home/loops"; CLAUDE_BIN = "/home/loops/.local/bin/claude"; };
    path = [ pkgs.bash pkgs.tmux pkgs.git pkgs.python3 pkgs.openssh pkgs.nettools ];
    script = ''
      # Put the standalone claude/opencode binaries on PATH. On a cold boot this is the env the
      # tmux server (and thus every agent session) inherits, so bare `claude` resolves everywhere.
      export PATH="/home/loops/.local/bin:$PATH"
      [ -x /srv/cc-ci/cc-ci-plan/launch.sh ] && /srv/cc-ci/cc-ci-plan/launch.sh start || \
        echo "workspace not staged yet — skipping loop start"
    '';
  };

  # Weekly recipe upgrade — runs /upgrade-all over every enrolled recipe (opens recipe PRs
  # verified by !testme, never merges). Replaces the boot-fragile busybox-crond-in-tmux from
  # phase 5 §4 with a reboot-safe systemd timer. The service is timer-triggered only (NOT
  # wantedBy multi-user.target) so it never runs on boot/activation — only on the schedule.
  systemd.services.cc-ci-upgrade-all = {
    description = "cc-ci weekly /upgrade-all run (recipe upgrade survey + PRs, never merges)";
    after = [ "network-online.target" "tailscaled.service" "claude-install.service" ];
    wants = [ "network-online.target" ];
    serviceConfig = {
      Type = "oneshot";  # launch-upgrader.py spawns the cc-ci-upgrader tmux session and returns
      User = "loops"; Group = "users";
      WorkingDirectory = "/srv/cc-ci";
    };
    environment = { HOME = "/home/loops"; CLAUDE_BIN = "/home/loops/.local/bin/claude"; };
    path = [ pkgs.bash pkgs.tmux pkgs.git pkgs.python3 pkgs.openssh pkgs.nettools ];
    script = ''
      export PATH="/home/loops/.local/bin:$PATH"
      python3 /srv/cc-ci/cc-ci-plan/launch-upgrader.py start >> /srv/cc-ci/.cc-ci-logs/upgrader-cron.log 2>&1
    '';
  };

  systemd.timers.cc-ci-upgrade-all = {
    description = "Weekly trigger for cc-ci-upgrade-all (Sundays 02:00 UTC)";
    wantedBy = [ "timers.target" ];
    timerConfig = {
      OnCalendar = "Sun *-*-* 02:00:00 UTC";
      Persistent = true;  # if the box was down at the scheduled time, run once on next boot
    };
  };
}