homelab/flake.nix

{
  description = "Homelab NixOS configuration";

  inputs = {
    nixpkgs.url = "github:NixOS/nixpkgs/nixos-26.05";
    # Second nixpkgs, used for ONE package: immich. 26.05 pins 2.7.5, but
    # jupiter's imported database was written by 3.0.0 and immich never
    # migrates a schema backwards. NOT `follows` — the point is a different
    # package set. See services/media/immich.nix.
    nixpkgs-unstable.url = "github:NixOS/nixpkgs/nixpkgs-unstable";
    disko = {
      url = "github:nix-community/disko";
      inputs.nixpkgs.follows = "nixpkgs";
    };
    sops-nix = {
      url = "github:Mic92/sops-nix";
      inputs.nixpkgs.follows = "nixpkgs";
    };
    nixos-images = {
      url = "github:nix-community/nixos-images";
      inputs.nixpkgs.follows = "nixpkgs";
    };
    home-manager = {
      url = "github:nix-community/home-manager/release-26.05";
      inputs.nixpkgs.follows = "nixpkgs";
    };
    mediamanager-nix = {
      url = "github:strangeglyph/mediamanager-nix";
      inputs.nixpkgs.follows = "nixpkgs";
    };
    # Deliberately NOT `inputs.nixpkgs.follows` — upstream states overriding it
    # breaks their pinned python dependency set. Costs a second nixpkgs in the
    # lock; builds come prebuilt from nix-community's Cachix.
    authentik-nix.url = "github:nix-community/authentik-nix";
    # Unofficial packaging of Proton's pass-cli (not in nixpkgs) — used by
    # ./scripts/deploy to pull sudo/ssh passwords from the "HomeLab" vault.
    proton-pass-cli = {
      url = "github:tomsch/proton-pass-cli-nix";
      inputs.nixpkgs.follows = "nixpkgs";
    };
    # Tome (formerly AudibleLibrary) — darman's own .NET/Photino desktop app.
    # Private repo on our own gitea; fetched over ssh with darman's ambient key,
    # same as any other git flake input. `flake = false`: it's a plain source
    # tree, not itself a flake. See pkgs/tome.nix.
    tome = {
      url = "git+ssh://gitea@git.mgaction.town:2222/darman/TOME.git";
      flake = false;
    };
  };

  outputs = { self, nixpkgs, disko, sops-nix, nixos-images, home-manager, mediamanager-nix, authentik-nix, ... }@inputs:
    let
      system = "x86_64-linux";
    in
    {
      packages.${system}.tome = nixpkgs.legacyPackages.${system}.callPackage ./pkgs/tome.nix {
        src = inputs.tome;
      };

      nixosConfigurations = {
        # Real host — install on the ZimaBlade.
        # disko owns the OS-disk partitioning + filesystems (see disk-config.nix).
        jupiter = nixpkgs.lib.nixosSystem {
          inherit system;
          specialArgs = { inherit inputs; };
          modules = [
            disko.nixosModules.disko
            sops-nix.nixosModules.sops
            ./hosts/jupiter/configuration.nix
          ];
        };

        # netcup VPS — public reverse proxy + tailnet node.
        neptun = nixpkgs.lib.nixosSystem {
          inherit system;
          specialArgs = { inherit inputs; };
          modules = [
            disko.nixosModules.disko
            sops-nix.nixosModules.sops
            ./hosts/neptun/configuration.nix
          ];
        };

        # terra — Ryzen 9 5900X desktop (MSI MS-7A32). Replaces CachyOS on the
        # OS SSD; Hyprland desktop + tailnet node. See hosts/terra/*.
        terra = nixpkgs.lib.nixosSystem {
          inherit system;
          specialArgs = { inherit inputs; };
          modules = [
            disko.nixosModules.disko
            sops-nix.nixosModules.sops
            home-manager.nixosModules.home-manager
            ./hosts/terra/configuration.nix
          ];
        };

        # mercury — Raspberry Pi 3B+ (aarch64), DNS/DHCP. Boots from an SD image:
        #   nix build .#nixosConfigurations.mercury.config.system.build.sdImage
        # (aarch64 build — needs binfmt/qemu on this x86 host, or a remote/aarch64
        # builder; substitutes most paths from cache.nixos.org.)
        mercury = nixpkgs.lib.nixosSystem {
          system = "aarch64-linux";
          specialArgs = { inherit inputs; };
          modules = [
            (nixpkgs + "/nixos/modules/installer/sd-card/sd-image-aarch64.nix")
            sops-nix.nixosModules.sops
            ./hosts/mercury/configuration.nix
          ];
        };

        # x86_64 QEMU VM to runtime-test mercury's DNS/DHCP stack (pihole +
        # unbound) before flashing the aarch64 SD. Build + run:
        #   nix build .#nixosConfigurations.mercury-vm.config.system.build.vm
        #   ./result/bin/run-mercury-vm-vm
        mercury-vm = nixpkgs.lib.nixosSystem {
          inherit system;   # x86_64-linux, fast to build/boot with KVM
          modules = [
            (nixpkgs + "/nixos/modules/virtualisation/qemu-vm.nix")
            ./common.nix
            ./services/network/unbound.nix
            ./services/network/pihole.nix
            ({ lib, ... }: {
              networking.hostName = "mercury-vm";
              networking.nameservers = [ "1.1.1.1" "9.9.9.9" ];   # host resolver (not pihole)
              users.users.darman.initialPassword = "test";
              users.users.root.initialPassword = "test";
              services.openssh.settings.PasswordAuthentication = lib.mkForce true;
              virtualisation.graphics = false;
              virtualisation.memorySize = 2048;
              virtualisation.forwardPorts = [
                { from = "host"; host.port = 2223; guest.port = 22; }
                { from = "host"; host.port = 8081; guest.port = 80; }
              ];
              system.stateVersion = "26.05";
            })
          ];
        };

        # VirtualBox test image. Build the OVA with:
        #   nix build .#nixosConfigurations.jupiter-vbox.config.system.build.virtualBoxOVA
        # NOTE: no disko here — the virtualbox-image module supplies the disk.
        jupiter-vbox = nixpkgs.lib.nixosSystem {
          inherit system;
          specialArgs = { inherit inputs; };
          modules = [ ./hosts/jupiter/vm.nix ];
        };

        # Custom kexec installer with our SSH key baked in, for headless install
        # onto a box with a read-only root (ZimaOS) where nixos-anywhere can't
        # ssh-copy-id. Build the tarball:
        #   nix build .#nixosConfigurations.kexec.config.system.build.kexecInstallerTarball
        # then scp it to the target's writable /tmp and run kexec/run (see README).
        kexec = nixpkgs.lib.nixosSystem {
          inherit system;
          modules = [
            nixos-images.nixosModules.kexec-installer
            ({ ... }: {
              users.users.root.openssh.authorizedKeys.keys = [
                "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIGZpkPVhzi1zG5JI9hWyUgdyvNIQbp4ts4jw3idpMhhN erik@laptop"
              ];
            })
          ];
        };

        # Bootable USB recovery installer with our SSH key + sshd + DHCP.
        # Reusable for any host's manual-USB install path (jupiter, terra, ...).
        # Build the ISO:
        #   nix build .#nixosConfigurations.installer-iso.config.system.build.isoImage
        # dd it to a USB stick, boot the target from it, SSH in, ./deploy install.
        installer-iso = nixpkgs.lib.nixosSystem {
          inherit system;
          modules = [
            (nixpkgs + "/nixos/modules/installer/cd-dvd/installation-cd-minimal.nix")
            ({ pkgs, ... }: {
              services.openssh.enable = true;
              services.openssh.settings.PermitRootLogin = "prohibit-password";
              users.users.root.openssh.authorizedKeys.keys = [
                "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIGZpkPVhzi1zG5JI9hWyUgdyvNIQbp4ts4jw3idpMhhN erik@laptop"
              ];
              networking.hostName = "homelab-installer";
              environment.systemPackages = [ pkgs.git ];
            })
          ];
        };
      };

      # VM test for `./scripts/deploy kexec-local`. Run:
      #   nix build .#checks.x86_64-linux.kexec-local -L
      #
      # Worth having because kexec-local is the one command that cannot be
      # rehearsed on real hardware: it jumps the machine you are typing at, and
      # a failure looks exactly like a slow boot. It regression-tests the
      # subtle one — kexec-run.sh backgrounds `sleep 6 && kexec -e` and returns,
      # so anything that cleans up the staging dir on exit deletes the binary
      # that performs the jump and the box silently never leaves the old kernel.
      #
      # After the jump the test driver's backdoor is gone with the old kernel,
      # so the installer is driven over a forwarded ssh port instead (the same
      # approach nixos-images uses in its own kexec test).
      checks.${system}.kexec-local =
        let
          pkgs = nixpkgs.legacyPackages.${system};
          tarball = self.nixosConfigurations.kexec.config.system.build.kexecInstallerTarball;
          sshKey = nixos-images + "/nix/kexec-installer/ssh-keys/id_ed25519";
        in
        pkgs.testers.runNixOSTest {
          name = "deploy-kexec-local";

          nodes.machine = { modulesPath, ... }: {
            imports = [ (modulesPath + "/profiles/minimal.nix") ];
            virtualisation.vlans = [ ];
            # kexec-local refuses to run if RAM < 3x the installer image, and
            # the staging dir needs ~3x the tarball on /var/tmp.
            virtualisation.memorySize = 4 * 1024;
            virtualisation.diskSize = 12 * 1024;
            virtualisation.forwardPorts = [{ host.port = 2222; guest.port = 22; }];

            services.openssh.enable = true;
            users.users.root.openssh.authorizedKeys.keyFiles = [ "${sshKey}.pub" ];

            # Everything the script shells out to, minus nix — the test uses the
            # HOMELAB_KEXEC_* hook so no build happens inside the VM.
            environment.systemPackages = with pkgs; [
              bash gnutar coreutils findutils util-linux cpio gzip
            ];
            system.extraDependencies = [ tarball pkgs.cpio pkgs.gzip ];

            environment.etc."deploy".source = ./scripts/deploy;
          };

          testScript = /* python */ ''
            import os, shutil, subprocess, tempfile, time

            start_all()
            machine.wait_for_unit("sshd.service")

            # ssh refuses a private key that is group/world readable, and nix
            # store paths are 0444 — copy it out and tighten the mode.
            keydir = tempfile.mkdtemp()
            key = os.path.join(keydir, "id_ed25519")
            shutil.copyfile("${sshKey}", key)
            os.chmod(key, 0o600)

            def ssh(cmd, check=True, stdout=None):
                return subprocess.run(
                    [ "${pkgs.openssh}/bin/ssh",
                      "-o", "StrictHostKeyChecking=no",
                      "-o", "UserKnownHostsFile=/dev/null",
                      "-o", "ConnectTimeout=1",
                      "-i", key,
                      "-p", "2222", "root@127.0.0.1", "--" ] + cmd,
                    text=True, check=check, stdout=stdout)

            machine.succeed("install -Dm755 /etc/deploy /root/deploy")

            # systemd-run starts units with a bare PATH that lacks
            # /run/current-system/sw/bin, so `#!/usr/bin/env bash` cannot even
            # resolve bash, let alone tar/findmnt/nohup. Set it explicitly.
            env = (
                " --setenv=PATH=/run/wrappers/bin:/run/current-system/sw/bin"
                " --setenv=HOMELAB_KEXEC_TARBALL=${tarball}/nixos-kexec-installer-${system}.tar.gz"
                " --setenv=HOMELAB_KEXEC_CPIO=${pkgs.cpio}/bin/cpio"
                " --setenv=HOMELAB_KEXEC_GZIP=${pkgs.gzip}/bin/gzip"
            )
            # Same values for the foreground (non-systemd-run) invocation below.
            envsh = (
                "HOMELAB_KEXEC_TARBALL=${tarball}/nixos-kexec-installer-${system}.tar.gz"
                " HOMELAB_KEXEC_CPIO=${pkgs.cpio}/bin/cpio"
                " HOMELAB_KEXEC_GZIP=${pkgs.gzip}/bin/gzip"
            )

            # Marker on a tmpfs: it must NOT survive the jump, proving we really
            # booted a new kernel rather than just restarting a service.
            machine.succeed("touch /run/pre-kexec-marker")
            host_key_before = machine.succeed("cat /etc/ssh/ssh_host_ed25519_key.pub").strip()

            while ssh(["true"], check=False).returncode != 0:
                time.sleep(1)

            # Refuses without --yes when stdin is not a tty (read gets EOF).
            # Must reach the confirmation prompt, so it needs the same env —
            # otherwise it just dies early on the nix build and proves nothing.
            out = machine.fail(f"{envsh} /root/deploy kexec-local </dev/null 2>&1")
            assert "using prebuilt kexec installer" in out, \
                f"never reached the prompt, so the refusal proves nothing:\n{out}"

            # systemd-run so the call returns immediately: the script stays
            # alive ~60s on purpose, outliving kexec-run.sh's `sleep 6`.
            machine.succeed(f"systemd-run --collect --unit=kexec-local{env} /root/deploy kexec-local --yes")

            print("waiting for the jump...")
            deadline = time.time() + 300
            while ssh(["true"], check=False).returncode == 0:
                # Surface a dead unit immediately instead of stalling until the
                # deadline and blaming "never left the old kernel".
                st = ssh(["systemctl", "is-active", "kexec-local"],
                         check=False, stdout=subprocess.PIPE).stdout or ""
                if st.strip() in ("failed", "inactive"):
                    # NB: not `log` — the driver already binds that name to its
                    # AbstractLogger and the type check rejects the shadowing.
                    unit_log = ssh(["journalctl", "-u", "kexec-local", "--no-pager"],
                                   check=False, stdout=subprocess.PIPE).stdout or ""
                    raise AssertionError(
                        f"kexec-local.service ended ({st.strip()}) without jumping:\n{unit_log}")
                assert time.time() < deadline, "machine never left the old kernel"
                time.sleep(1)

            print("waiting for the installer...")
            deadline = time.time() + 300
            while ssh(["true"], check=False).returncode != 0:
                assert time.time() < deadline, "installer never came up"
                time.sleep(1)

            # It really is the RAM installer, not the old system.
            host = ssh(["hostname"], stdout=subprocess.PIPE).stdout.strip()
            assert host == "nixos-installer", f"hostname is {host}, not nixos-installer"

            assert ssh(["ls", "/run/pre-kexec-marker"], check=False).returncode != 0, \
                "old /run survived — this was not a fresh kernel"

            # The host key is carried across (kexec-run.sh copies /etc/ssh into
            # the appended initrd), which is why `kexec` does no ssh-keygen -R.
            host_key_after = ssh(
                ["cat", "/etc/ssh/ssh_host_ed25519_key.pub"], stdout=subprocess.PIPE
            ).stdout.strip()
            assert host_key_before == host_key_after, \
                f"host key changed: {host_key_before} != {host_key_after}"

            machine.crash()
          '';
        };
    };
}