fix(backup,restore): harden the branch fixes and prove them with tests

Backup: a container that vanishes between the docker ps listing and the
swarm-task inspect (--rm one-shots, task-history GC) no longer aborts the
whole backup run; it counts as not stoppable and is skipped.

Restore: the postgres replay streams the dump through a spooled temp file
instead of buffering it three times in memory (multi-GB dumps OOMed the
restore mid-replay), and the superuser-only line filter is COPY-aware: data
rows inside COPY ... FROM stdin blocks pass through untouched, so a row
that happens to start with COMMENT ON EXTENSION or ALTER DEFAULT PRIVILEGES
is no longer silently dropped.

The e2e runner talks to the DinD daemon through docker exec instead of a
host-published tcp://127.0.0.1:2375: port publishing is unreachable from
sandboxed runners and from hosts with broken loopback publishing, and the
unencrypted root API port disappears from the host. The debug tmp dump
shrinks to tar plus docker cp against the DinD container itself.

New coverage: an e2e reproducing the swarm flake end to end (service task
on the volume, nothing whitelisted: the backup must succeed, the very same
task container must keep running, and the service must never replace a
task), unit tests for the COPY-aware filter, the swarm-task probe including
the vanished-container path, filter_stoppable ordering, and the one-session
FOREIGN_KEY_CHECKS drop assembly. Full suite: 35 unit, 9 integration,
30 e2e green.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

tests/e2e/test_e2e_swarm_task_skip.py

@@ -0,0 +1,196 @@
+# tests/e2e/test_e2e_swarm_task_skip.py
+#
+# Reproduces the swarm flake fixed on this branch: baudolo used to stop a
+# swarm task container around the volume file backup because its image was
+# not whitelisted; the orchestrator immediately replaced the stopped task and
+# the later `docker start` failed on the detached overlay network, killing
+# the backup run. With the fix the task container is skipped (backed up hot):
+# the backup succeeds, the very same container instance keeps running, and
+# the service never has to replace a task.
+import time
+import unittest
+
+from .helpers import (
+    backup_path,
+    backup_run,
+    create_minimal_compose_dir,
+    ensure_empty_dir,
+    latest_version_dir,
+    require_docker,
+    run,
+    unique,
+    write_databases_csv,
+)
+
+
+def _swarm_state() -> str:
+    return run(
+        ["docker", "info", "--format", "{{.Swarm.LocalNodeState}}"]
+    ).stdout.strip()
+
+
+def _task_container_id(service: str, timeout_s: int = 60) -> str:
+    deadline = time.time() + timeout_s
+    while time.time() < deadline:
+        out = run(
+            [
+                "docker",
+                "ps",
+                "--filter",
+                f"label=com.docker.swarm.service.name={service}",
+                "--format",
+                "{{.ID}}",
+            ]
+        ).stdout.strip()
+        if out:
+            return out.splitlines()[0]
+        time.sleep(2)
+    raise RuntimeError(f"No running task container for service {service}")
+
+
+def _started_at(container_id: str) -> str:
+    return run(
+        ["docker", "inspect", "--format", "{{.State.StartedAt}}", container_id]
+    ).stdout.strip()
+
+
+class TestE2ESwarmTaskSkip(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls) -> None:
+        require_docker()
+        cls.prefix = unique("baudolo-e2e-swarm-skip")
+        cls.backups_dir = f"/tmp/{cls.prefix}/Backups"
+        ensure_empty_dir(cls.backups_dir)
+        cls.compose_dir = create_minimal_compose_dir(f"/tmp/{cls.prefix}")
+        cls.repo_name = cls.prefix
+
+        cls.swarm_initted = False
+        if _swarm_state() != "active":
+            run(["docker", "swarm", "init", "--advertise-addr", "127.0.0.1"])
+            cls.swarm_initted = True
+
+        cls.volume = f"{cls.prefix}-vol"
+        cls.service = f"{cls.prefix}-svc"
+        cls.volumes = [cls.volume]
+
+        run(["docker", "volume", "create", cls.volume])
+        run(
+            [
+                "docker",
+                "run",
+                "--rm",
+                "-v",
+                f"{cls.volume}:/data",
+                "alpine:3.20",
+                "sh",
+                "-lc",
+                "echo 'swarm-payload' > /data/payload.txt",
+            ]
+        )
+
+        run(
+            [
+                "docker",
+                "service",
+                "create",
+                "--name",
+                cls.service,
+                "--replicas",
+                "1",
+                "--mount",
+                f"type=volume,source={cls.volume},target=/data",
+                "alpine:3.20",
+                "sleep",
+                "3600",
+            ]
+        )
+        cls.task_cid = _task_container_id(cls.service)
+        cls.task_started_at = _started_at(cls.task_cid)
+
+        cls.databases_csv = f"/tmp/{cls.prefix}/databases.csv"
+        write_databases_csv(cls.databases_csv, [])
+
+        # Whitelist that matches nothing: on main this forces a stop of every
+        # container at the volume, i.e. exactly the flake; on this branch the
+        # swarm task must be skipped instead. (An empty list would leave the
+        # --images-no-stop-required flag without arguments and argparse-fail.)
+        backup_run(
+            backups_dir=cls.backups_dir,
+            repo_name=cls.repo_name,
+            compose_dir=cls.compose_dir,
+            databases_csv=cls.databases_csv,
+            database_containers=["dummy-db"],
+            images_no_stop_required=["image-that-matches-nothing"],
+        )
+        cls.hash, cls.version = latest_version_dir(cls.backups_dir, cls.repo_name)
+
+    @classmethod
+    def tearDownClass(cls) -> None:
+        run(["docker", "service", "rm", cls.service], check=False)
+        deadline = time.time() + 30
+        while time.time() < deadline:
+            out = run(
+                [
+                    "docker",
+                    "ps",
+                    "-aq",
+                    "--filter",
+                    f"label=com.docker.swarm.service.name={cls.service}",
+                ],
+                check=False,
+            ).stdout.strip()
+            if not out:
+                break
+            time.sleep(2)
+        for v in cls.volumes:
+            run(["docker", "volume", "rm", "-f", v], check=False)
+        if cls.swarm_initted:
+            run(["docker", "swarm", "leave", "--force"], check=False)
+
+    def test_volume_backed_up_hot(self) -> None:
+        p = (
+            backup_path(
+                self.backups_dir,
+                self.repo_name,
+                self.version,
+                self.volume,
+            )
+            / "files"
+            / "payload.txt"
+        )
+        self.assertTrue(p.is_file(), f"Expected backed up file at: {p}")
+
+    def test_task_container_never_stopped(self) -> None:
+        out = run(
+            ["docker", "ps", "-q", "--no-trunc", "--filter", f"id={self.task_cid}"]
+        ).stdout.strip()
+        self.assertTrue(
+            out.startswith(self.task_cid) or self.task_cid.startswith(out.strip()[:12]),
+            f"Task container {self.task_cid} is no longer running",
+        )
+        self.assertEqual(
+            self.task_started_at,
+            _started_at(self.task_cid),
+            "Task container was restarted during the backup",
+        )
+
+    def test_service_never_replaced_the_task(self) -> None:
+        states = run(
+            [
+                "docker",
+                "service",
+                "ps",
+                self.service,
+                "--format",
+                "{{.DesiredState}} {{.CurrentState}}",
+            ]
+        ).stdout.strip()
+        lines = [line for line in states.splitlines() if line.strip()]
+        self.assertEqual(
+            len(lines), 1, f"Service task history shows replacements:\n{states}"
+        )
+        self.assertIn("Running", lines[0])
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/backup/test_docker_swarm.py

@@ -0,0 +1,41 @@
+import unittest
+from unittest.mock import patch
+
+from baudolo.backup import docker as docker_mod
+from baudolo.backup.shell import BackupException
+
+
+class TestIsSwarmTask(unittest.TestCase):
+    @patch.object(docker_mod, "execute_shell_command", return_value=["task-id-123"])
+    def test_true_when_task_label_present(self, _mock) -> None:
+        self.assertTrue(docker_mod.is_swarm_task("c1"))
+
+    @patch.object(docker_mod, "execute_shell_command", return_value=[""])
+    def test_false_when_label_empty(self, _mock) -> None:
+        self.assertFalse(docker_mod.is_swarm_task("c1"))
+
+    @patch.object(docker_mod, "execute_shell_command", return_value=[])
+    def test_false_when_no_output(self, _mock) -> None:
+        self.assertFalse(docker_mod.is_swarm_task("c1"))
+
+    @patch.object(
+        docker_mod,
+        "execute_shell_command",
+        side_effect=BackupException("gone"),
+    )
+    def test_vanished_container_counts_as_not_stoppable(self, _mock) -> None:
+        # A container removed between listing and inspect must not abort the
+        # whole backup run; treating it as a swarm task keeps it out of every
+        # stop/start and image-inspect path.
+        self.assertTrue(docker_mod.is_swarm_task("gone-container"))
+
+
+class TestFilterStoppable(unittest.TestCase):
+    @patch.object(docker_mod, "is_swarm_task", side_effect=[False, True, False])
+    def test_mixed_list_keeps_order_and_drops_tasks(self, _mock) -> None:
+        result = docker_mod.filter_stoppable(["plain-1", "swarm-task", "plain-2"])
+        self.assertEqual(result, ["plain-1", "plain-2"])
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/restore/test_mariadb_empty_drop.py

@@ -0,0 +1,44 @@
+import tempfile
+import unittest
+from unittest.mock import MagicMock, patch
+
+from baudolo.restore.db import mariadb as mariadb_mod
+
+
+class TestMariadbEmptyDrop(unittest.TestCase):
+    def test_drops_run_in_one_session_with_fk_checks_off(self) -> None:
+        calls = []
+
+        def _capture(container, argv, **kwargs):
+            calls.append(argv)
+            result = MagicMock()
+            result.stdout = b"users\nfetches\n"
+            return result
+
+        with tempfile.NamedTemporaryFile(suffix=".sql") as sql:
+            sql.write(b"CREATE TABLE t (id int);\n")
+            sql.flush()
+            with (
+                patch.object(mariadb_mod, "docker_exec", side_effect=_capture),
+                patch.object(mariadb_mod, "_pick_client", return_value="mariadb"),
+            ):
+                mariadb_mod.restore_mariadb_sql(
+                    container="db",
+                    db_name="mailu",
+                    user="mailu",
+                    password="pw",
+                    sql_path=sql.name,
+                    empty=True,
+                )
+
+        drop_calls = [argv for argv in calls if any("DROP TABLE" in a for a in argv)]
+        self.assertEqual(len(drop_calls), 1, f"expected ONE drop session: {calls}")
+        drop_sql = drop_calls[0][-1]
+        self.assertTrue(drop_sql.startswith("SET FOREIGN_KEY_CHECKS=0; "))
+        self.assertIn("DROP TABLE IF EXISTS `mailu`.`users`;", drop_sql)
+        self.assertIn("DROP TABLE IF EXISTS `mailu`.`fetches`;", drop_sql)
+        self.assertTrue(drop_sql.endswith("SET FOREIGN_KEY_CHECKS=1;"))
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/restore/test_postgres_filter.py

@@ -0,0 +1,63 @@
+import unittest
+
+from baudolo.restore.db.postgres import filter_superuser_only_lines
+
+
+def _filter(raw: bytes) -> bytes:
+    return b"".join(filter_superuser_only_lines(raw.splitlines(keepends=True)))
+
+
+class TestFilterSuperuserOnlyLines(unittest.TestCase):
+    def test_drops_superuser_only_statements(self) -> None:
+        raw = (
+            b"CREATE TABLE t (id int);\n"
+            b"COMMENT ON EXTENSION pg_trgm IS 'trigram';\n"
+            b"ALTER DEFAULT PRIVILEGES IN SCHEMA public GRANT ALL ON TABLES TO x;\n"
+            b"INSERT INTO t VALUES (1);\n"
+        )
+        self.assertEqual(
+            _filter(raw),
+            b"CREATE TABLE t (id int);\nINSERT INTO t VALUES (1);\n",
+        )
+
+    def test_copy_data_rows_are_never_filtered(self) -> None:
+        raw = (
+            b"COPY public.snippets (body) FROM stdin;\n"
+            b"COMMENT ON EXTENSION looks like sql but is data\n"
+            b"ALTER DEFAULT PRIVILEGES stored as text\n"
+            b"\\.\n"
+            b"ALTER DEFAULT PRIVILEGES IN SCHEMA public REVOKE ALL ON TABLES FROM y;\n"
+        )
+        self.assertEqual(
+            _filter(raw),
+            b"COPY public.snippets (body) FROM stdin;\n"
+            b"COMMENT ON EXTENSION looks like sql but is data\n"
+            b"ALTER DEFAULT PRIVILEGES stored as text\n"
+            b"\\.\n",
+        )
+
+    def test_consecutive_copy_blocks_keep_state(self) -> None:
+        raw = (
+            b"COPY public.a (v) FROM stdin;\n"
+            b"row-a\n"
+            b"\\.\n"
+            b"COMMENT ON EXTENSION dropme IS 'x';\n"
+            b"COPY public.b (v) FROM stdin;\n"
+            b"COMMENT ON EXTENSION kept-as-data\n"
+            b"\\.\n"
+        )
+        out = _filter(raw)
+        self.assertNotIn(b"dropme", out)
+        self.assertIn(b"COMMENT ON EXTENSION kept-as-data\n", out)
+
+    def test_everything_else_passes_through_verbatim(self) -> None:
+        raw = (
+            b"SET statement_timeout = 0;\n"
+            b"CREATE EXTENSION IF NOT EXISTS pg_trgm;\n"
+            b"GRANT ALL ON SCHEMA public TO app;\n"
+        )
+        self.assertEqual(_filter(raw), raw)
+
+
+if __name__ == "__main__":
+    unittest.main()