fix: reconnect after silent control heartbeat loss

deploy/production/lithium/compose.yaml

@@ -2,7 +2,7 @@ name: archive-control-archive
 
 services:
   archive-client:
-    image: sodium/archive-clients:v0.1.12
+    image: sodium/archive-clients:v0.1.13
     user: "1000:1000"
     restart: unless-stopped
     command: ["--config", "/etc/archive-control/client.toml"]

deploy/production/x1/compose.yaml

@@ -2,7 +2,7 @@ name: archive-control-cache
 
 services:
   archive-client:
-    image: sodium/archive-clients:v0.1.12
+    image: sodium/archive-clients:v0.1.13
     user: "1001:1001"
     restart: unless-stopped
     network_mode: host

deploy/production/x2/compose.yaml

@@ -2,7 +2,7 @@ name: archive-control-cache
 
 services:
   archive-client:
-    image: sodium/archive-clients:v0.1.12
+    image: sodium/archive-clients:v0.1.13
     user: "1001:1001"
     restart: unless-stopped
     network_mode: host

docs/deployment-and-usage.md

@@ -223,7 +223,7 @@ cache/archive routes according to policy.
 ```yaml
 services:
   archive-client:
-    image: sodium/archive-clients:v0.1.12
+    image: sodium/archive-clients:v0.1.13
     user: "1001:1001"
     restart: unless-stopped
     command: ["archive-client", "--config", "/etc/archive-control/client.toml"]

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "archive-clients"
-version = "0.1.12"
+version = "0.1.13"
 requires-python = ">=3.11"
 dependencies = ["protobuf==7.35.1", "websockets==16.0"]
 

src/archive_clients/daemon.py

@@ -11,6 +11,7 @@ from pathlib import Path, PurePosixPath
 from typing import Any
 
 from websockets.asyncio.client import connect
+from websockets.exceptions import ConnectionClosedOK
 
 from archive_clients.backup import SQLiteBackupManager
 from archive_clients.config import ClientConfig
@@ -205,7 +206,23 @@ class ArchiveClientDaemon:
             command_tasks: set[asyncio.Task[None]] = set()
             try:
                 await self._resume_commands(outbound, command_tasks)
-                async for frame in websocket:
+                # A proxy can leave the TCP/WebSocket socket apparently open
+                # after the control server has discarded its session.  The
+                # server then cannot deliver durable commands and its pending
+                # outbox remains stranded unless the client independently
+                # detects the missing application heartbeats and reconnects.
+                while True:
+                    try:
+                        frame = await asyncio.wait_for(
+                            websocket.recv(),
+                            self.config.connection.offline_timeout,
+                        )
+                    except ConnectionClosedOK:
+                        return
+                    except asyncio.TimeoutError as exc:
+                        raise RuntimeError(
+                            "control heartbeat timed out"
+                        ) from exc
                     await self._handle(decode(frame), outbound, command_tasks)
             finally:
                 writer.cancel()

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)