Files
bot-bottle/tests/unit/test_macos_nested_containers.py
T
didericis dba48706de fix(macos): put the gateway address in the Docker CLI proxy config
This is the layer that actually decides it, and it was in the script
from the start: ~/.docker/config.json's proxies block is what the Docker
CLI copies into every container it starts. Being client-side it beats
the podman service outright, which is why containers.conf `env`,
http_proxy=false, and the service environment each looked correct on
disk and changed nothing a nested container saw.

Also corrects the comment on the service-env substitution, which
claimed to be the one place the address sticks. It is not; it covers
podman's own pulls and non-CLI API clients.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-21 22:54:26 -04:00

334 lines
15 KiB
Python

"""Unit coverage for the fail-closed guest-local container engine (#392)."""
from __future__ import annotations
import unittest
from dataclasses import dataclass
from pathlib import Path
from types import SimpleNamespace
from typing import cast
from unittest.mock import patch
from bot_bottle.backend.macos_container import nested_containers
from bot_bottle.backend.macos_container import launch as launch_mod
from bot_bottle.backend.macos_container.bottle_plan import MacosContainerBottlePlan
class _Bottle:
def __init__(self, results: list[SimpleNamespace]) -> None:
self.results = results
self.commands: list[str] = []
def exec(self, command: str) -> SimpleNamespace:
self.commands.append(command)
return self.results.pop(0)
def _result(returncode: int, *, stdout: str = "", stderr: str = "") -> SimpleNamespace:
return SimpleNamespace(returncode=returncode, stdout=stdout, stderr=stderr)
@dataclass(frozen=True)
class _AgentProvision:
image: str
@dataclass(frozen=True)
class _Spec:
image_policy: str = "build"
@dataclass(frozen=True)
class _Plan:
slug: str
image: str
dockerfile_path: str
nested_containers: bool
agent_provision: _AgentProvision
spec: _Spec = _Spec()
def _base_image_only(ref: str) -> bool:
"""Only the un-derived agent image is cached on the host."""
return not ref.endswith(nested_containers.IMAGE_SUFFIX)
def _plan(**kwargs: object) -> MacosContainerBottlePlan:
return cast(MacosContainerBottlePlan, cast(object, _Plan(**kwargs))) # type: ignore[arg-type]
class TestNestedContainersStart(unittest.TestCase):
def test_bootstraps_then_waits_for_guest_local_service(self) -> None:
bottle = _Bottle([_result(0), _result(1), _result(0)])
with patch.object(nested_containers.time, "sleep"):
nested_containers.start(bottle)
self.assertIn("nested-containers-init", bottle.commands[0])
self.assertEqual(2, bottle.commands.count("docker info >/dev/null 2>&1"))
def test_bootstrap_failure_is_fatal_without_privilege_fallback(self) -> None:
bottle = _Bottle([_result(1, stderr="slirp4netns missing")])
with patch.object(nested_containers, "die", side_effect=RuntimeError) as die:
with self.assertRaises(RuntimeError):
nested_containers.start(bottle)
self.assertIn("slirp4netns missing", die.call_args.args[0])
self.assertEqual(1, len(bottle.commands))
def test_timeout_reports_guest_log(self) -> None:
bottle = _Bottle(
[_result(0)]
+ [_result(1) for _ in range(nested_containers.READY_RETRIES)]
+ [_result(0, stdout="operation not permitted")]
)
with patch.object(nested_containers.time, "sleep"), \
patch.object(nested_containers, "die", side_effect=RuntimeError) as die:
with self.assertRaises(RuntimeError):
nested_containers.start(bottle)
self.assertIn("operation not permitted", die.call_args.args[0])
class TestNestedContainersDevices(unittest.TestCase):
def test_relaxes_only_the_two_blocked_device_nodes_as_root(self) -> None:
calls: list[tuple[str, list[str]]] = []
def record(name: str, argv: list[str]) -> None:
calls.append((name, argv))
nested_containers.prepare_guest_devices("bottle-1", record)
self.assertEqual(1, len(calls))
name, argv = calls[0]
self.assertEqual("bottle-1", name)
self.assertIn("chmod 0666 /dev/fuse /dev/net/tun", argv[-1])
class TestNestedContainersImage(unittest.TestCase):
def test_layers_tooling_without_changing_base_image(self) -> None:
calls: list[tuple[str, str, str]] = []
def build(image: str, context: str, *, dockerfile: str) -> None:
calls.append((image, context, dockerfile))
text = Path(dockerfile).read_text(encoding="utf-8")
self.assertIn("FROM agent:base", text)
self.assertIn("aardvark-dns fuse-overlayfs netavark nftables passt", text)
self.assertIn("USER node", text)
self.assertTrue((Path(context) / "nested-containers-init.sh").is_file())
image = nested_containers.build_image("agent:base", build)
self.assertEqual("agent:base-nested-containers", image)
self.assertEqual("agent:base-nested-containers", calls[0][0])
def test_installs_the_whole_podman_5_networking_stack(self) -> None:
"""Each missing piece fails at a different, misleading layer: no pasta
and nothing starts; no nft and netavark cannot build the bridge that
compose expects; no aardvark-dns and DNS inside nested containers
fails while everything else looks healthy. Image pulls keep working
throughout, which is what made these read as compat-API bugs."""
seen: list[str] = []
def build(_image: str, _context: str, *, dockerfile: str) -> None:
seen.append(Path(dockerfile).read_text(encoding="utf-8"))
nested_containers.build_image("agent:base", build)
for package in ("passt", "nftables", "aardvark-dns"):
self.assertIn(package, seen[0])
def test_strips_subordinate_ranges_so_podman_avoids_newuidmap(self) -> None:
"""The single-UID fallback is the entire reason podman works here.
A subordinate range would send podman down the newuidmap path, which
cannot write a multi-range uid_map without CAP_SYS_ADMIN in an Apple
Container guest — the failure that killed the rootless-Docker spike.
"""
seen: list[str] = []
def build(_image: str, _context: str, *, dockerfile: str) -> None:
seen.append(Path(dockerfile).read_text(encoding="utf-8"))
nested_containers.build_image("agent:base", build)
text = seen[0]
self.assertIn("sed -i '/^node:/d' /etc/subuid /etc/subgid", text)
self.assertNotIn("subuid", text.replace(
"sed -i '/^node:/d' /etc/subuid /etc/subgid", "",
))
class TestInitScript(unittest.TestCase):
"""The bootstrap runs inside the bottle, so its wiring is only checkable
here or on a live macOS host."""
def setUp(self) -> None:
self.script = (
Path(nested_containers.__file__).with_name("nested-containers-init.sh")
.read_text(encoding="utf-8")
)
def test_ca_bundle_path_matches_the_backend_constant(self) -> None:
from bot_bottle.backend.util import AGENT_CA_BUNDLE
self.assertIn(f'CA_BUNDLE="{AGENT_CA_BUNDLE}"', self.script)
def test_resolves_the_gateway_address_for_nested_containers(self) -> None:
"""podman's hosts_file only applies to native `podman run` — the
Docker-compat API ignores it, and the agent types `docker`. So the
gateway name is resolved here and the *address* goes into the proxy
URL; otherwise every nested container dies at "Could not resolve
proxy", which reads like broken DNS but is a missing hosts entry."""
self.assertIn('$2 == name { print $1; exit }', self.script)
self.assertIn('value.replace(name, ip)', self.script)
def test_docker_cli_proxy_config_uses_the_address(self) -> None:
"""The Docker CLI copies ~/.docker/config.json's proxies block into
every container it starts. Being client-side it beats the podman
service, so this — not containers.conf — is what decides whether a
nested container can reach the proxy."""
block = self.script[self.script.index('"proxies"'):]
self.assertIn('"httpProxy": proxy.replace(name, ip)', block)
self.assertIn('"httpsProxy": proxy.replace(name, ip)', block)
self.assertIn('"noProxy": no_proxy', block)
def test_substitutes_the_address_into_the_service_environment(self) -> None:
"""Covers what the Docker CLI does not stamp: podman's own registry
pulls, and containers created through the API by another client."""
launch = self.script[self.script.index("podman system service"):]
self.assertNotIn("$GATEWAY_NAME", launch) # substitution precedes it
setup = self.script[:self.script.index("podman system service")]
self.assertIn("for var in HTTP_PROXY HTTPS_PROXY http_proxy https_proxy",
setup)
def test_disables_podmans_own_proxy_passthrough(self) -> None:
"""podman copies the host's proxy vars into every container by
default, and that copy overrides the env we set — putting the
unresolvable gateway name back and leaving nested containers at
"bad address 'bot-bottle-gateway'"."""
self.assertIn('"http_proxy=false"', self.script)
def test_keeps_the_gateway_name_in_no_proxy(self) -> None:
"""NO_PROXY is matched against what a client asks for, and code inside
a nested container still says bot-bottle-gateway."""
start = self.script.index('for var in ("NO_PROXY"')
loop = self.script[start:self.script.index("path = Path(", start)]
self.assertIn('entries.append(f"{var}={value}")', loop)
self.assertNotIn("replace(name, ip)", loop)
self.assertIn('"noProxy": no_proxy', self.script)
def test_fails_closed_without_a_gateway_address(self) -> None:
self.assertIn('[ -n "$gateway_ip" ] || {', self.script)
def test_mounts_and_trusts_the_gateway_ca(self) -> None:
"""The gateway TLS-intercepts, so without the bundle every HTTPS call
from a nested container fails with "unable to get local issuer
certificate"."""
self.assertIn('volumes=["{ca}:{ca}:ro"]', self.script)
for var in (
"SSL_CERT_FILE", "CURL_CA_BUNDLE", "REQUESTS_CA_BUNDLE",
"NODE_EXTRA_CA_CERTS",
):
self.assertIn(f'f"{var}={{ca}}"', self.script)
def test_writes_the_token_bearing_config_unreadable_to_others(self) -> None:
"""The proxy URL carries the bottle's identity token."""
self.assertIn("path.chmod(0o600)", self.script)
class TestGuestEnvironment(unittest.TestCase):
def test_disabled_bottle_gets_no_docker_environment(self) -> None:
self.assertEqual({}, nested_containers.guest_env(False))
def test_enabled_bottle_uses_only_the_guest_local_socket(self) -> None:
env = nested_containers.guest_env(True)
self.assertEqual("unix:///tmp/bbp/podman.sock", env["DOCKER_HOST"])
self.assertNotIn("/var/run/docker.sock", " ".join(env.values()))
def test_runtime_dir_leaves_room_for_conmons_attach_socket(self) -> None:
"""podman builds `$XDG_RUNTIME_DIR/libpod/tmp/socket/<64-hex>/attach`,
which must fit in sun_path (108 bytes). A descriptive runtime dir blew
past it and every attached `docker run` failed with "unable to upgrade
to tcp, received 500" while pulls and detached runs looked fine."""
attach = (
nested_containers.guest_env(True)["XDG_RUNTIME_DIR"]
+ "/libpod/tmp/socket/" + "a" * 64 + "/attach"
)
self.assertLessEqual(len(attach), 107, attach)
def test_macos_backend_declares_support(self) -> None:
from bot_bottle.backend.macos_container.backend import (
MacosContainerBottleBackend,
)
self.assertTrue(MacosContainerBottleBackend.supports_nested_containers)
class TestBuildOrLoadImages(unittest.TestCase):
def test_disabled_bottle_keeps_the_plain_agent_image(self) -> None:
plan = _plan(
slug="dev-abc", image="agent:base", dockerfile_path="/repo/Dockerfile",
nested_containers=False, agent_provision=_AgentProvision("agent:base"),
)
with patch.object(launch_mod, "read_committed_image", return_value=None), \
patch.object(launch_mod.container_mod, "build_image"), \
patch.object(launch_mod.nested_containers_mod, "build_image") as derived:
images = launch_mod.build_or_load_images(plan)
derived.assert_not_called()
self.assertEqual("agent:base", images.agent)
def test_enabled_bottle_builds_base_then_derived_variant(self) -> None:
plan = _plan(
slug="dev-abc", image="agent:base", dockerfile_path="/repo/Dockerfile",
nested_containers=True, agent_provision=_AgentProvision("agent:base"),
)
with patch.object(launch_mod, "read_committed_image", return_value=None), \
patch.object(launch_mod.container_mod, "build_image") as build, \
patch.object(
launch_mod.nested_containers_mod,
"build_image",
return_value="agent:base-nested-containers",
) as derived:
images = launch_mod.build_or_load_images(plan)
build.assert_called_once_with(
"agent:base", launch_mod._REPO_DIR, # pylint: disable=protected-access
dockerfile="/repo/Dockerfile",
)
derived.assert_called_once_with("agent:base", build)
self.assertEqual("agent:base-nested-containers", images.agent)
def test_derived_image_layers_onto_a_committed_image(self) -> None:
plan = _plan(
slug="dev-abc", image="agent:base", dockerfile_path="/repo/Dockerfile",
nested_containers=True, agent_provision=_AgentProvision("agent:base"),
)
with patch.object(
launch_mod, "read_committed_image", return_value="agent:committed",
), \
patch.object(launch_mod.container_mod, "image_exists", return_value=True), \
patch.object(launch_mod.container_mod, "build_image") as build, \
patch.object(
launch_mod.nested_containers_mod,
"build_image",
return_value="agent:committed-nested-containers",
) as derived:
images = launch_mod.build_or_load_images(plan)
build.assert_not_called()
derived.assert_called_once_with("agent:committed", build)
self.assertEqual("agent:committed-nested-containers", images.agent)
def test_cached_policy_refuses_to_build_the_derived_image(self) -> None:
plan = _plan(
slug="dev-abc", image="agent:base", dockerfile_path="/repo/Dockerfile",
nested_containers=True, agent_provision=_AgentProvision("agent:base"),
spec=_Spec(image_policy="cached"),
)
with patch.object(launch_mod, "read_committed_image", return_value=None), \
patch.object(
launch_mod.container_mod, "image_exists",
side_effect=_base_image_only,
), \
patch.object(launch_mod.nested_containers_mod, "build_image") as derived, \
patch.object(launch_mod, "die", side_effect=RuntimeError) as die:
with self.assertRaises(RuntimeError):
launch_mod.build_or_load_images(plan)
derived.assert_not_called()
self.assertIn("agent:base-nested-containers", die.call_args.args[0])
if __name__ == "__main__":
unittest.main()