feat: enhance guest network configuration and recovery process for UVM

tests/test_lifecycle.py

@@ -307,6 +307,9 @@ class LifecycleTestCase(unittest.TestCase):
             self.images, "resize_vm_disk", side_effect=self.resize_vm_disk,
         ))
         self.provision = self.enterContext(patch.object(self.images, "provision_credentials"))
+        self.configure_network = self.enterContext(patch.object(
+            self.images, "configure_guest_network", side_effect=self.configure_guest_network,
+        ))
         self.copy_disk = self.enterContext(patch.object(
             self.images, "create_vm_disk", wraps=self.images.create_vm_disk,
         ))
@@ -340,6 +343,14 @@ class LifecycleTestCase(unittest.TestCase):
             raise AssertionError("cannot resize a running or ambiguous VM")
         self.disk_sizes[disk] = storage_mib * 1024 * 1024
 
+    def configure_guest_network(self, disk: Path, guest_ip: str) -> None:
+        vm = self.store.get(disk.parent.name)
+        self.host.call("images.configure_network", vm.id)
+        if self.process.observe(vm) != "gone":
+            raise AssertionError("cannot configure a running or ambiguous VM disk")
+        if guest_ip != vm.guest_ip:
+            raise AssertionError("guest network must use the VM's retained address")
+
     def create_vm(self, **kwargs) -> VmRecord:
         return self.service.create(VmSpec(cpu=1, ram_mib=512, **kwargs))
 
@@ -481,7 +492,7 @@ class LifecycleTests(LifecycleTestCase):
     def test_boot_persists_intent_and_identity_with_policy_before_tap_and_vmm(self) -> None:
         vm = self.create_vm()
         self.assert_call_order(
-            vm, "network.prepare_tap", "firewall.apply", "firewall.readback",
+            vm, "images.configure_network", "network.prepare_tap", "firewall.apply", "firewall.readback",
             "network.activate_tap", "process.start", "process.spawn", "process.ready",
             "client.configure", "firewall.status",
         )
@@ -499,6 +510,46 @@ class LifecycleTests(LifecycleTestCase):
         self.assertEqual(spawned.operation, "configuring")
         self.assertEqual(self.host.records["client.configure", vm.id].pid, vm.pid)
 
+    def test_guest_network_configuration_failure_rolls_back_before_marking_the_disk_ready(self) -> None:
+        self.host.failures["images.configure_network", None] = UvmError("guest network verification failed")
+        with self.assertRaisesRegex(UvmError, "guest network verification failed"):
+            self.create_vm()
+        self.assertEqual(self.store.load().vms, {})
+        self.assertFalse(self.network.created_taps)
+        self.assertFalse(self.process.started)
+        self.assertEqual(list(self.settings.vms_dir.iterdir()), [])
+
+    def test_retained_guest_network_is_configured_after_exit_and_before_boot(self) -> None:
+        vm = self.create_vm()
+        self.host.events.clear()
+        self.service.restart(vm.id)
+        self.assert_call_order(vm, "images.configure_network", "process.start", "client.configure")
+        actions = self.host.actions(vm.id)
+        self.assertLess(max(index for index, action in enumerate(actions) if action == "process.gone"),
+                        actions.index("images.configure_network"))
+        self.configure_network.assert_called_with(Path(vm.disk), vm.guest_ip)
+        self.assertEqual(self.provision.call_count, 1)
+
+    def test_live_start_does_not_modify_the_guest_disk(self) -> None:
+        vm = self.create_vm()
+        self.configure_network.reset_mock()
+        self.service.start(vm.id)
+        self.configure_network.assert_not_called()
+
+    def test_failed_retained_network_configuration_keeps_disk_for_retry(self) -> None:
+        vm = self.create_vm()
+        self.service.stop(vm.id)
+        disk = Path(vm.disk)
+        disk.write_bytes(b"retained data and credentials")
+        self.host.failures["images.configure_network", vm.id] = UvmError("network verification failed")
+        with self.assertRaisesRegex(UvmError, "network verification failed"):
+            self.service.start(vm.id)
+        self.assertEqual(disk.read_bytes(), b"retained data and credentials")
+        self.assertEqual(self.process.observe(self.store.get(vm.id)), "gone")
+        self.assertEqual(len(self.process.started), 1)
+        self.assertEqual(self.service.start(vm.id).status, "running")
+        self.assertEqual(self.provision.call_count, 1)
+
     def test_failed_initial_policy_never_activates_tap_or_starts_vmm(self) -> None:
         self.host.failures["firewall.apply", None] = UvmError("policy unavailable")
         with self.assertRaisesRegex(UvmError, "policy unavailable"):