# `checks.vm-hive-squid`: runs ../host-modules/hive-squid.nix in a VM, which
# the module-eval suite can only read. Three nodes on two networks:
#
#   agent (vlan 1) --> proxy (vlan 1 = the stand-in bridge, vlan 2 = uplink) --> web (vlan 2)
#
# `proxy` imports the squid module against stub options for the few hive
# options it reads, so no hive-c0re build is pulled in; the module-eval suite
# covers the real option wiring.
{ pkgs }:
let
  bridgeIp = "192.168.1.1";

  hiveStubs =
    { lib, config, ... }:
    {
      options.services.hyperhive = {
        deploy.hive-controller.enable = lib.mkOption {
          type = lib.types.bool;
          default = true;
        };
        swarm.serviceDomains = lib.mkOption {
          type = lib.types.listOf lib.types.str;
          default = [ "forge.t.local" ];
        };
        swarm.forge.domain = lib.mkOption {
          type = lib.types.str;
          default = "forge.t.local";
        };
        network = {
          bridgeIp = lib.mkOption {
            type = lib.types.str;
            default = bridgeIp;
          };
          networkCidr = lib.mkOption {
            type = lib.types.str;
            default = "192.168.1.0/24";
          };
          exposeHostPorts = lib.mkOption {
            type = lib.types.listOf lib.types.port;
            default = [ ];
          };
          enable = lib.mkOption {
            type = lib.types.bool;
            default = true;
          };
        };
        otel = {
          scrapeTargets = lib.mkOption {
            type = lib.types.attrsOf lib.types.str;
            default = { };
          };
          journalUnits = lib.mkOption {
            type = lib.types.listOf lib.types.str;
            default = [ ];
          };
        };
      };
      # The user hive-c0re runs as, which owns the users file squid reads.
      config.users.users.hive-core = {
        isSystemUser = true;
        group = "hive-core";
      };
      config.users.groups.hive-core = { };
      # The firewall hole hive-network.nix opens for `exposeHostPorts`.
      config.networking.firewall.interfaces.eth1.allowedTCPPorts =
        config.services.hyperhive.network.exposeHostPorts;
    };

  # Plain TCP on 443: a CONNECT is answered before any TLS, which is all the
  # test reads.
  listen443 = addrs: {
    services.nginx = {
      enable = true;
      virtualHosts.default.listen = map (addr: {
        inherit addr;
        port = 443;
      }) addrs;
    };
  };
in
pkgs.testers.runNixOSTest {
  name = "hive-squid";

  nodes = {
    proxy =
      { lib, pkgs, ... }:
      {
        imports = [
          hiveStubs
          ../host-modules/hive-squid.nix
          # Listeners a leaked destination would reach: loopback and the bridge.
          (listen443 [
            "127.0.0.1"
            bridgeIp
          ])
        ];
        virtualisation.vlans = [
          1
          2
        ];
        networking.interfaces.eth1.ipv4.addresses = lib.mkForce [
          {
            address = bridgeIp;
            prefixLength = 24;
          }
        ];
        networking.interfaces.eth2.ipv4.addresses = lib.mkForce [
          {
            address = "192.168.2.1";
            prefixLength = 24;
          }
        ];
        # Names the proxy resolves, each a different destination class.
        networking.hosts = {
          "192.168.2.2" = [ "forge.t.local" ];
          "127.0.0.1" = [ "loop.t.local" ];
          ${bridgeIp} = [ "bridge.t.local" ];
          "169.254.169.254" = [ "meta.t.local" ];
        };
        # Renders the users file the way hive-c0re does.
        environment.systemPackages = [ pkgs.mkpasswd ];
        services.hyperhive.squid.allowedDomains = [
          "forge.t.local"
          "loop.t.local"
          "bridge.t.local"
          "meta.t.local"
        ];
      };

    web =
      { lib, ... }:
      {
        imports = [ (listen443 [ "0.0.0.0" ]) ];
        virtualisation.vlans = [ 2 ];
        networking.interfaces.eth1.ipv4.addresses = lib.mkForce [
          {
            address = "192.168.2.2";
            prefixLength = 24;
          }
        ];
        networking.firewall.allowedTCPPorts = [ 443 ];
      };

    agent =
      { lib, ... }:
      {
        virtualisation.vlans = [ 1 ];
        networking.interfaces.eth1.ipv4.addresses = lib.mkForce [
          {
            address = "192.168.1.3";
            prefixLength = 24;
          }
        ];
      };
  };

  testScript = ''
    import re
    import secrets

    # Drawn fresh each run. The users file holds only their hashes, as
    # hive-c0re renders it.
    PW = {u: secrets.token_urlsafe(24) for u in ("atlas", "selfcheck.squid", "ruth")}
    ATLAS = "atlas:" + PW["atlas"]
    SELFCHECK = "selfcheck.squid:" + PW["selfcheck.squid"]
    RUTH = "ruth:" + PW["ruth"]
    USERS = "/var/lib/hive-squid/users"

    start_all()
    proxy.wait_for_unit("squid.service")
    proxy.wait_for_unit("squid-exporter.service")
    proxy.wait_for_unit("nginx.service")
    web.wait_for_unit("nginx.service")
    proxy.wait_for_open_port(3128, "${bridgeIp}")

    def connect(host, cred=None):
        # The status squid answered the CONNECT with; 000 when none came back.
        auth = f"-U '{cred}' " if cred else ""
        return agent.succeed(
            "curl -sS -m 15 -p -x http://${bridgeIp}:3128 " + auth + "-o /dev/null "
            f"-w '%{{http_connect}}' https://{host}/ 2>/dev/null || true"
        ).strip()

    def write_users(*creds):
        # What hive-c0re does: hashes only, written aside and renamed into
        # place, in squid's group. The sleep keeps two writes in different
        # seconds, which is how the helper tells the file changed.
        lines = " ".join(
            f"printf '%s:%s\\n' {u} \"$(mkpasswd -m sha-512 -s <<< {p})\";"
            for u, p in (c.split(":", 1) for c in creds)
        )
        proxy.succeed(
            f"({lines}) > {USERS}.new && chown hive-core:squid {USERS}.new "
            f"&& chmod 640 {USERS}.new && mv {USERS}.new {USERS} && sleep 1"
        )

    with subtest("squid starts on the empty users file and refuses every login"):
        assert proxy.succeed(f"stat -c '%U:%G %a' {USERS}").strip() == "hive-core:squid 640"
        assert proxy.succeed("stat -c %a /var/lib/hive-squid").strip() == "2750"
        assert proxy.succeed(f"stat -c %s {USERS}").strip() == "0"
        assert connect("forge.t.local", ATLAS) == "407", "no such user"
        assert connect("deny-canary.invalid", ATLAS) == "403", "an unlisted name needs no login"

    with subtest("the users file holds hashes, never a password"):
        write_users(ATLAS, SELFCHECK)
        users = proxy.succeed(f"cat {USERS}")
        assert re.fullmatch(r"(atlas|selfcheck\.squid):\$6\$\S+\n(atlas|selfcheck\.squid):\$6\$\S+\n", users), users
        assert not any(p in users for p in PW.values()), users

    with subtest("an allowed name is tunnelled with a credential and challenged without one"):
        assert connect("forge.t.local", ATLAS) == "200", "allow canary"
        assert connect("forge.t.local") == "407", "no credential"
        assert connect("forge.t.local", "atlas:" + secrets.token_urlsafe(24)) == "407", "wrong password"
        assert connect("forge.t.local", "nobody:" + PW["atlas"]) == "407", "unknown user"
        # DES would accept the first eight characters; the hash must not.
        assert connect("forge.t.local", "atlas:" + PW["atlas"][:8]) == "407", "a prefix of the password"

    with subtest("an unlisted name is refused with or without a credential"):
        assert connect("deny-canary.invalid", ATLAS) == "403", "deny canary"
        assert connect("deny-canary.invalid") == "403", "deny canary, anonymous"

    with subtest("a name resolving to a host-local destination is refused"):
        assert connect("loop.t.local", ATLAS) == "403", "loopback"
        assert connect("bridge.t.local", ATLAS) == "403", "bridge address"
        assert connect("meta.t.local", ATLAS) == "403", "link-local"

    with subtest("IP literals are refused even when the address is reachable"):
        assert connect("127.0.0.1", ATLAS) == "403"
        assert connect("192.168.2.2", ATLAS) == "403"

    with subtest("only a port-443 CONNECT is allowed"):
        assert connect("forge.t.local:22", ATLAS) == "403"
        assert connect("forge.t.local:80", ATLAS) == "403"

    with subtest("an agent cannot read cachemgr"):
        agent.succeed(
            "test $(curl -s -m 15 -o /dev/null -w '%{http_code}' "
            "http://${bridgeIp}:3128/squid-internal-mgr/counters) = 403"
        )

    with subtest("the self-check passes with its credential"):
        proxy.succeed("install -d -m 0700 /run/credstore")
        proxy.succeed(f"printf '%s\\n' {PW['selfcheck.squid']} > /run/credstore/hive-squid.selfcheck")
        proxy.succeed("chmod 400 /run/credstore/hive-squid.selfcheck")
        proxy.succeed("systemctl start squid-selfcheck.service")
        proxy.succeed(
            "journalctl -u squid-selfcheck.service -o cat | "
            "grep -F 'squid-selfcheck ok=true allow_canary=forge.t.local "
            "allow_status=200 deny_canary=deny-canary.invalid deny_status=403 "
            "anon_status=407 credential=present'"
        )

    with subtest("the self-check fails, and says why, without a credential or with the wrong one"):
        proxy.succeed("mv /run/credstore/hive-squid.selfcheck /run/credstore/kept")
        proxy.fail("systemctl start squid-selfcheck.service")
        proxy.succeed(
            "journalctl -u squid-selfcheck.service -o cat | "
            "grep -F 'squid-selfcheck ok=false allow_canary=forge.t.local "
            "allow_status=407 deny_canary=deny-canary.invalid deny_status=403 "
            "anon_status=407 credential=absent'"
        )
        proxy.succeed(f"printf '%s\\n' {secrets.token_urlsafe(24)} > /run/credstore/hive-squid.selfcheck")
        proxy.fail("systemctl start squid-selfcheck.service")
        proxy.succeed(
            "journalctl -u squid-selfcheck.service -o cat | "
            "grep -F 'allow_status=407 deny_canary=deny-canary.invalid deny_status=403 "
            "anon_status=407 credential=present'"
        )
        proxy.succeed("mv -f /run/credstore/kept /run/credstore/hive-squid.selfcheck")

    with subtest("squid's access log reaches the journal under squid.service, with the user"):
        journal = proxy.succeed("journalctl -u squid.service -o cat")
        assert re.search(r"192\.168\.1\.3 TCP_TUNNEL/200 .* CONNECT forge\.t\.local:443 atlas ", journal), journal
        assert re.search(r"192\.168\.1\.3 TCP_DENIED/407 .* CONNECT forge\.t\.local:443 - ", journal), journal
        assert re.search(r"192\.168\.1\.3 TCP_DENIED/403 .* CONNECT deny-canary\.invalid:443 ", journal), journal
        assert re.search(r"192\.168\.1\.3 TCP_DENIED/403 .* CONNECT loop\.t\.local:443 ", journal), journal
        # Exporter scrapes are cachemgr requests and stay out of the log.
        assert "squid-internal-mgr" not in journal, journal

    with subtest("the exporter serves squid's counters on loopback"):
        metrics = proxy.succeed("curl -sf http://127.0.0.1:9301/metrics")
        print("\n".join(l for l in metrics.splitlines() if l.startswith(("squid_up", "squid_client_http"))))
        assert 'squid_up{host="${bridgeIp}"} 1' in metrics
        m = re.search(r"^squid_client_http_requests_total (\S+)$", metrics, re.M)
        assert m and float(m.group(1)) >= 9, metrics
        m = re.search(r"^squid_client_http_errors_total (\S+)$", metrics, re.M)
        assert m and float(m.group(1)) >= 1, metrics
        proxy.fail("curl -sf -m 5 http://${bridgeIp}:9301/metrics")

    with subtest("squid survives a reload"):
        proxy.succeed("systemctl reload squid.service")
        proxy.wait_for_unit("squid.service")
        assert connect("forge.t.local", ATLAS) == "200"

    with subtest("a user added while squid runs can log in, with no reload"):
        write_users(ATLAS, SELFCHECK, RUTH)
        assert connect("forge.t.local", RUTH) == "200"
        assert connect("forge.t.local", ATLAS) == "200"

    with subtest("squid starts on a missing users file, refuses logins, and recovers when it appears"):
        proxy.succeed(f"rm {USERS}")
        proxy.succeed("systemctl restart squid.service")
        proxy.wait_for_unit("squid.service")
        proxy.wait_for_open_port(3128, "${bridgeIp}")
        assert connect("forge.t.local", ATLAS) == "407", "no file, no login"
        assert connect("deny-canary.invalid", ATLAS) == "403", "an unlisted name still answers"
        write_users(ATLAS, SELFCHECK)
        assert connect("forge.t.local", ATLAS) == "200", "the file appeared"
  '';
}