fix: reconnect after silent control heartbeat loss

tests/test_daemon.py

@@ -22,6 +22,53 @@ from archive_control.v1 import (
 
 
 class DaemonTransportTests(unittest.IsolatedAsyncioTestCase):
+    async def test_silent_control_connection_ends_for_reconnect(self):
+        """A lost server heartbeat must not leave durable commands stranded."""
+
+        async def control(websocket):
+            registration = decode(await websocket.recv())
+            self.assertEqual(registration.WhichOneof("payload"), "register_request")
+            response = new_envelope()
+            response.correlation_id = registration.message_id
+            response.register_response.status = (
+                client_pb2.REGISTRATION_STATUS_ACCEPTED
+            )
+            response.register_response.negotiated_version.major = 1
+            await websocket.send(encode(response))
+            # Deliberately keep TCP/WebSocket open but send no application
+            # heartbeats. This models a stale proxy/server-side session.
+            await websocket.wait_closed()
+
+        with tempfile.TemporaryDirectory() as directory:
+            root = Path(directory)
+            token = root / "token"
+            token.write_text("shared-secret", encoding="utf-8")
+            os.chmod(token, 0o600)
+            async with serve(control, "127.0.0.1", 0, ping_interval=None) as server:
+                port = server.sockets[0].getsockname()[1]
+                service = ServiceConfig(
+                    "http://local", PurePosixPath("/api"), root,
+                )
+                config = ClientConfig(
+                    "cache-1", "Cache 1", "cache",
+                    f"ws://127.0.0.1:{port}", token,
+                    root / "state.db", root / "backups", service, service,
+                    ConnectionConfig(
+                        registration_timeout=1,
+                        offline_timeout=0.05,
+                        reconnect_initial=0.01,
+                        reconnect_max=0.01,
+                        reconnect_jitter=False,
+                    ),
+                )
+                probe = FilesystemProbe(root, True, True, True, True, True)
+                daemon = ArchiveClientDaemon(config, [probe, probe], [])
+                await asyncio.to_thread(daemon.store.initialize)
+                with self.assertRaisesRegex(
+                    RuntimeError, "control heartbeat timed out"
+                ):
+                    await asyncio.wait_for(daemon._connection(), 1)
+
     async def test_eviction_assignment_and_steps_are_admitted(self):
         with tempfile.TemporaryDirectory() as directory:
             root = Path(directory)