Merge pull request 'fix(tests): align systemd unit + service tests with current production shape (partial close #9)' (#15) from fix/systemd-tests-drift-9 into main

tests/hermes_cli/test_gateway_service.py

@@ -64,6 +64,12 @@ class TestSystemdServiceRefresh:
 
         monkeypatch.setattr(gateway_cli, "get_systemd_unit_path", lambda system=False: unit_path)
         monkeypatch.setattr(gateway_cli, "generate_systemd_unit", lambda system=False, run_as_user=None: "new unit\n")
+        # Production now preflights user-systemd availability (loginctl
+        # enable-linger + D-Bus socket wait, #14531) before start/restart.
+        # These unit tests assert the systemctl call sequence, not the
+        # preflight — stub the preflight as a no-op so the fake subprocess
+        # runner doesn't have to reproduce the loginctl/D-Bus dance.
+        monkeypatch.setattr(gateway_cli, "_preflight_user_systemd", lambda *a, **kw: None)
 
         calls = []
 
@@ -87,6 +93,9 @@ class TestSystemdServiceRefresh:
 
         monkeypatch.setattr(gateway_cli, "get_systemd_unit_path", lambda system=False: unit_path)
         monkeypatch.setattr(gateway_cli, "generate_systemd_unit", lambda system=False, run_as_user=None: "new unit\n")
+        # See note on test_systemd_start_refreshes_outdated_unit — preflight
+        # is a separate concern and has its own dedicated coverage.
+        monkeypatch.setattr(gateway_cli, "_preflight_user_systemd", lambda *a, **kw: None)
 
         calls = []
 
@@ -108,6 +117,15 @@ class TestSystemdServiceRefresh:
 
 
 class TestGeneratedSystemdUnits:
+    @staticmethod
+    def _expected_timeout_stop_sec() -> int:
+        # Mirror the formula in gateway.generate_systemd_unit:
+        #   restart_timeout = max(60, drain_timeout) + 30
+        # so that bumping the default drain_timeout in config doesn't silently
+        # break this test — we want to pin the relationship, not a magic number.
+        drain_timeout = int(gateway_cli._get_restart_drain_timeout() or 0)
+        return max(60, drain_timeout) + 30
+
     def test_user_unit_avoids_recursive_execstop_and_uses_extended_stop_timeout(self):
         unit = gateway_cli.generate_systemd_unit(system=False)
 
@@ -115,10 +133,13 @@ class TestGeneratedSystemdUnits:
         assert "ExecStop=" not in unit
         assert "ExecReload=/bin/kill -USR1 $MAINPID" in unit
         assert f"RestartForceExitStatus={GATEWAY_SERVICE_RESTART_EXIT_CODE}" in unit
-        # TimeoutStopSec must exceed the default drain_timeout (60s) so
+        # TimeoutStopSec must exceed the configured drain_timeout so
         # systemd doesn't SIGKILL the cgroup before post-interrupt cleanup
         # (tool subprocess kill, adapter disconnect) runs — issue #8202.
-        assert "TimeoutStopSec=90" in unit
+        # Formula is max(60, drain_timeout) + 30; pin the relationship to
+        # _get_restart_drain_timeout() rather than a literal so a config
+        # default bump (default jumped 60→180s) doesn't silently regress us.
+        assert f"TimeoutStopSec={self._expected_timeout_stop_sec()}" in unit
 
     def test_user_unit_includes_resolved_node_directory_in_path(self, monkeypatch):
         monkeypatch.setattr(gateway_cli.shutil, "which", lambda cmd: "/home/test/.nvm/versions/node/v24.14.0/bin/node" if cmd == "node" else None)
@@ -134,10 +155,13 @@ class TestGeneratedSystemdUnits:
         assert "ExecStop=" not in unit
         assert "ExecReload=/bin/kill -USR1 $MAINPID" in unit
         assert f"RestartForceExitStatus={GATEWAY_SERVICE_RESTART_EXIT_CODE}" in unit
-        # TimeoutStopSec must exceed the default drain_timeout (60s) so
+        # TimeoutStopSec must exceed the configured drain_timeout so
         # systemd doesn't SIGKILL the cgroup before post-interrupt cleanup
         # (tool subprocess kill, adapter disconnect) runs — issue #8202.
-        assert "TimeoutStopSec=90" in unit
+        # Formula is max(60, drain_timeout) + 30; pin the relationship to
+        # _get_restart_drain_timeout() rather than a literal so a config
+        # default bump (default jumped 60→180s) doesn't silently regress us.
+        assert f"TimeoutStopSec={self._expected_timeout_stop_sec()}" in unit
         assert "WantedBy=multi-user.target" in unit
 
 
@@ -437,6 +461,10 @@ class TestGatewayServiceDetection:
         monkeypatch.setattr(gateway_cli, "is_linux", lambda: True)
         monkeypatch.setattr(gateway_cli, "is_termux", lambda: False)
         monkeypatch.setattr(gateway_cli, "is_wsl", lambda: False)
+        # Native-Linux assertion: explicitly opt out of the container path
+        # (added after this test was written) so a containerized CI runner
+        # doesn't inherit a probe of the real systemd in the runner image.
+        monkeypatch.setattr(gateway_cli, "is_container", lambda: False)
         monkeypatch.setattr(gateway_cli.shutil, "which", lambda name: "/usr/bin/systemctl")
 
         assert gateway_cli.supports_systemd_services() is True
@@ -487,6 +515,11 @@ class TestGatewaySystemServiceRouting:
         calls = []
 
         monkeypatch.setattr(gateway_cli, "_select_systemd_scope", lambda system=False: False)
+        # Production now preflights user-systemd availability (loginctl
+        # enable-linger + D-Bus socket wait, #14531) before restart. This
+        # test exercises the restart routing path; preflight has its own
+        # dedicated coverage in TestUserSystemdPrivateSocketPreflight.
+        monkeypatch.setattr(gateway_cli, "_preflight_user_systemd", lambda *a, **kw: None)
         monkeypatch.setattr(gateway_cli, "refresh_systemd_unit_if_needed", lambda system=False: calls.append(("refresh", system)))
         monkeypatch.setattr(
             "gateway.status.get_running_pid",
@@ -541,6 +574,9 @@ class TestGatewaySystemServiceRouting:
 
     def test_systemd_restart_recovers_failed_planned_restart(self, monkeypatch, capsys):
         monkeypatch.setattr(gateway_cli, "_select_systemd_scope", lambda system=False: False)
+        # See note on test_systemd_restart_self_requests_graceful_restart_and_waits
+        # — preflight is a separate concern with dedicated coverage.
+        monkeypatch.setattr(gateway_cli, "_preflight_user_systemd", lambda *a, **kw: None)
         monkeypatch.setattr(gateway_cli, "refresh_systemd_unit_if_needed", lambda system=False: None)
         monkeypatch.setattr(
             "gateway.status.read_runtime_status",

tests/hermes_cli/test_gateway_wsl.py

@@ -141,10 +141,19 @@ class TestSupportsSystemdServicesWSL:
         assert gateway.supports_systemd_services() is False
 
     def test_native_linux(self, monkeypatch):
-        """Native Linux (not WSL) → True without checking systemd."""
+        """Native Linux (not WSL, not container) → True without further probing."""
         monkeypatch.setattr(gateway, "is_linux", lambda: True)
         monkeypatch.setattr(gateway, "is_termux", lambda: False)
         monkeypatch.setattr(gateway, "is_wsl", lambda: False)
+        # supports_systemd_services() now also branches on is_container() to
+        # decide whether to probe `systemctl is-system-running` — explicitly
+        # opt this case out of the container path so a containerized CI
+        # runner doesn't inherit the probe of the runner image's systemd.
+        monkeypatch.setattr(gateway, "is_container", lambda: False)
+        # On macOS dev boxes shutil.which("systemctl") returns None; stub it
+        # so the test exercises the native-Linux branch independently of the
+        # host's $PATH.
+        monkeypatch.setattr(gateway.shutil, "which", lambda name: "/usr/bin/systemctl")
         assert gateway.supports_systemd_services() is True
 
     def test_termux_still_excluded(self, monkeypatch):