ca91fc4d91
The control plane had no caller authentication — dispatch() routed every request straight through, and the only guards anywhere were the (source_ip, identity_token) checks inside /resolve and /attribute, which authenticate the *bottle* a request is about, not the *caller*. On the consolidated backends the agent shares a network with the control-plane port (macOS: the infra container runs 8099 on the agent's --internal network; docker: the orchestrator container sits on the shared gateway network), so a prompt-injected agent could GET /bottles (enumerate siblings + policies), PUT /bottles/<id>/policy (rewrite its own egress allowlist to allow-all), POST /resolve (read the injected upstream credentials it's never meant to see), and POST /supervise/respond (self-approve its own proposals). Every README guarantee collapsed to the agent's discretion. Fix: a per-host control-plane secret required on every route but GET /health, compared with hmac.compare_digest. It is held only by the trusted callers and never handed to an agent: - minted + persisted 0600 at <root>/control-plane-token (paths.host_control_plane_token); - injected as $BOT_BOTTLE_CONTROL_PLANE_TOKEN into the orchestrator + gateway containers via bare `--env NAME` (value inherited from the launch process, so it never lands on argv or in `container/docker inspect`); - presented by the gateway's PolicyResolver (reads the env) on /resolve, and by the host CLI's OrchestratorClient (reads the host file) on every call. The agent container is never given the env var or the host file, so from a bottle every /bottles*, /resolve, /attribute, and /supervise/* call now returns 401 — closing the enumeration, allowlist-rewrite, credential-lift, and self-approval. The existing (source_ip, identity_token) checks stay as defense-in-depth. Enforced when configured: macOS + docker inject the secret (→ enforced). With no secret set the server runs open and warns loudly at startup — a fail-visible fallback for the unit suite and for Firecracker, whose port-scoped nft already blocks agents from 8099 (wiring the secret into its infra-VM init is a clean fast-follow, left out here to avoid churning the prebuilt-artifact hash). Verified end-to-end on real Apple Container: infra comes up healthy, the host CLI (with the secret) lists bottles while an unauthenticated GET /bottles gets 401, all five issue-#400 attacks from inside the agent get 401, and egress policy still works (200 allowed / 403 denied) — proving the gateway authenticates to /resolve with the secret. 1829 unit tests pass, pyright clean, pylint 9.91. Refs #400. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
223 lines
9.3 KiB
Python
223 lines
9.3 KiB
Python
"""Unit tests for the consolidated Docker gateway (PRD 0070). Docker mocked."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import unittest
|
|
from unittest.mock import Mock, patch
|
|
|
|
from bot_bottle.orchestrator.gateway import (
|
|
GATEWAY_CA_CERT,
|
|
GATEWAY_NAME,
|
|
DockerGateway,
|
|
GatewayError,
|
|
)
|
|
|
|
|
|
_CA_PEM = "-----BEGIN CERTIFICATE-----\nMII...\n-----END CERTIFICATE-----\n"
|
|
|
|
_RUN_DOCKER = "bot_bottle.orchestrator.gateway.run_docker"
|
|
|
|
|
|
def _proc(returncode: int = 0, stdout: str = "", stderr: str = "") -> Mock:
|
|
return Mock(returncode=returncode, stdout=stdout, stderr=stderr)
|
|
|
|
|
|
class TestDockerGateway(unittest.TestCase):
|
|
def setUp(self) -> None:
|
|
self.sc = DockerGateway("bot-bottle-gateway:latest")
|
|
|
|
def test_default_name(self) -> None:
|
|
self.assertEqual(GATEWAY_NAME, self.sc.name)
|
|
|
|
def test_is_running_reads_docker_ps(self) -> None:
|
|
with patch(_RUN_DOCKER, return_value=_proc(stdout=self.sc.name + "\n")):
|
|
self.assertTrue(self.sc.is_running())
|
|
with patch(_RUN_DOCKER, return_value=_proc(stdout="")):
|
|
self.assertFalse(self.sc.is_running())
|
|
|
|
def test_ensure_running_noop_when_up_and_image_current(self) -> None:
|
|
calls: list[list[str]] = []
|
|
|
|
def fake(argv: list[str], **_kw: object) -> Mock:
|
|
calls.append(argv)
|
|
if argv[:2] == ["docker", "ps"]:
|
|
return _proc(stdout=self.sc.name) # running
|
|
if argv[:3] == ["docker", "image", "inspect"]:
|
|
return _proc(stdout="img-A") # current image id
|
|
if argv[:2] == ["docker", "inspect"]:
|
|
return _proc(stdout="img-A") # container's image (same)
|
|
return _proc()
|
|
|
|
with patch(_RUN_DOCKER, side_effect=fake):
|
|
self.sc.ensure_running()
|
|
self.assertEqual([], [c for c in calls if c[:2] == ["docker", "run"]])
|
|
self.assertEqual([], [c for c in calls if c[:2] == ["docker", "rm"]])
|
|
|
|
def test_ensure_running_recreates_when_image_is_stale(self) -> None:
|
|
# Running, but the container was built from an OLD image → recreate so
|
|
# a rebuild's new flat daemons take effect.
|
|
calls: list[list[str]] = []
|
|
|
|
def fake(argv: list[str], **_kw: object) -> Mock:
|
|
calls.append(argv)
|
|
if argv[:2] == ["docker", "ps"]:
|
|
return _proc(stdout=self.sc.name)
|
|
if argv[:3] == ["docker", "image", "inspect"]:
|
|
return _proc(stdout="img-NEW")
|
|
if argv[:2] == ["docker", "inspect"]:
|
|
return _proc(stdout="img-OLD")
|
|
return _proc()
|
|
|
|
with patch(_RUN_DOCKER, side_effect=fake):
|
|
self.sc.ensure_running()
|
|
self.assertEqual(1, len([c for c in calls if c[:2] == ["docker", "run"]]))
|
|
self.assertTrue(any(c[:2] == ["docker", "rm"] for c in calls))
|
|
|
|
def test_ensure_running_starts_the_singleton_when_absent(self) -> None:
|
|
calls: list[list[str]] = []
|
|
|
|
def fake(argv: list[str], **_kw: object) -> Mock:
|
|
calls.append(argv)
|
|
return _proc(stdout="") if argv[:2] == ["docker", "ps"] else _proc()
|
|
|
|
with patch(_RUN_DOCKER, side_effect=fake):
|
|
self.sc.ensure_running()
|
|
|
|
runs = [c for c in calls if c[:2] == ["docker", "run"]]
|
|
self.assertEqual(1, len(runs))
|
|
self.assertIn(self.sc.name, runs[0])
|
|
self.assertIn("bot-bottle-gateway:latest", runs[0])
|
|
# Runs on the shared gateway network so agents can reach it by IP.
|
|
self.assertEqual(self.sc.network, runs[0][runs[0].index("--network") + 1])
|
|
# Persists its CA on a named volume so agents keep trusting it.
|
|
self.assertTrue(any("mitmproxy" in a for a in runs[0]))
|
|
# Shares the ONE host DB: the supervise daemon queues into the same
|
|
# file the orchestrator + operator (over HTTP) use.
|
|
self.assertTrue(any(
|
|
a.startswith("SUPERVISE_DB_PATH=") and a.endswith("/run/supervise/bot-bottle.db")
|
|
for a in runs[0]))
|
|
self.assertTrue(any(
|
|
a.endswith(":/run/supervise") for a in runs[0]))
|
|
|
|
def test_ensure_running_creates_network_when_missing(self) -> None:
|
|
calls: list[list[str]] = []
|
|
|
|
def fake(argv: list[str], **_kw: object) -> Mock:
|
|
calls.append(argv)
|
|
if argv[:3] == ["docker", "network", "inspect"]:
|
|
return _proc(returncode=1, stderr="No such network")
|
|
return _proc(stdout="") if argv[:2] == ["docker", "ps"] else _proc()
|
|
|
|
with patch(_RUN_DOCKER, side_effect=fake):
|
|
self.sc.ensure_running()
|
|
creates = [c for c in calls if c[:3] == ["docker", "network", "create"]]
|
|
self.assertEqual([["docker", "network", "create", self.sc.network]], creates)
|
|
|
|
def test_ca_cert_pem_reads_from_container(self) -> None:
|
|
with patch(_RUN_DOCKER, return_value=_proc(stdout=_CA_PEM)) as m:
|
|
self.assertEqual(_CA_PEM, self.sc.ca_cert_pem())
|
|
argv = m.call_args.args[0]
|
|
self.assertEqual(["docker", "exec", self.sc.name, "cat", GATEWAY_CA_CERT], argv)
|
|
|
|
def test_ca_cert_pem_raises_when_absent(self) -> None:
|
|
# timeout=0 → one probe then give up (no polling delay in the test).
|
|
with patch(_RUN_DOCKER, return_value=_proc(returncode=1, stderr="No such file")):
|
|
with self.assertRaises(GatewayError):
|
|
self.sc.ca_cert_pem(timeout=0)
|
|
|
|
def test_ca_cert_pem_polls_until_mitmproxy_writes_it(self) -> None:
|
|
# First read: CA not there yet; second read: present.
|
|
seq = [_proc(returncode=1, stderr="No such file"), _proc(stdout=_CA_PEM)]
|
|
with patch(_RUN_DOCKER, side_effect=seq), \
|
|
patch("bot_bottle.orchestrator.gateway.time.sleep"):
|
|
self.assertEqual(_CA_PEM, self.sc.ca_cert_pem(timeout=5))
|
|
|
|
def test_ensure_running_reuses_existing_network(self) -> None:
|
|
calls: list[list[str]] = []
|
|
|
|
def fake(argv: list[str], **_kw: object) -> Mock:
|
|
calls.append(argv)
|
|
return _proc(stdout="") if argv[:2] == ["docker", "ps"] else _proc()
|
|
|
|
with patch(_RUN_DOCKER, side_effect=fake):
|
|
self.sc.ensure_running() # network inspect returns 0 → exists
|
|
self.assertEqual([], [c for c in calls if c[:3] == ["docker", "network", "create"]])
|
|
|
|
def test_ensure_running_raises_on_docker_failure(self) -> None:
|
|
def fake(argv: list[str], **_kw: object) -> Mock:
|
|
if argv[:2] == ["docker", "ps"]:
|
|
return _proc(stdout="")
|
|
if argv[:2] == ["docker", "run"]:
|
|
return _proc(returncode=1, stderr="boom")
|
|
return _proc()
|
|
|
|
with patch(_RUN_DOCKER, side_effect=fake):
|
|
with self.assertRaises(GatewayError):
|
|
self.sc.ensure_running()
|
|
|
|
def test_stop_is_idempotent_on_missing(self) -> None:
|
|
absent = _proc(returncode=1, stderr="Error: No such container: x")
|
|
with patch(_RUN_DOCKER, return_value=absent):
|
|
self.sc.stop() # must not raise
|
|
|
|
def test_stop_raises_on_other_failure(self) -> None:
|
|
with patch(_RUN_DOCKER, return_value=_proc(returncode=1, stderr="daemon down")):
|
|
with self.assertRaises(GatewayError):
|
|
self.sc.stop()
|
|
|
|
|
|
class TestDockerGatewayBuild(unittest.TestCase):
|
|
def setUp(self) -> None:
|
|
self.sc = DockerGateway() # defaults to the real bundle image + dockerfile
|
|
|
|
def test_image_exists_reads_docker_inspect(self) -> None:
|
|
with patch(_RUN_DOCKER, return_value=_proc(returncode=0)):
|
|
self.assertTrue(self.sc.image_exists())
|
|
with patch(_RUN_DOCKER, return_value=_proc(returncode=1)):
|
|
self.assertFalse(self.sc.image_exists())
|
|
|
|
def test_ensure_built_builds_even_when_image_present(self) -> None:
|
|
# Always build (cache-aware) so a flat-source change rebuilds; the old
|
|
# build-if-missing silently ran a stale single-tenant image.
|
|
calls: list[list[str]] = []
|
|
|
|
def rec(argv: list[str], **_kw: object) -> Mock:
|
|
calls.append(argv)
|
|
return _proc() # image present, build succeeds
|
|
|
|
with patch(_RUN_DOCKER, side_effect=rec):
|
|
self.sc.ensure_built()
|
|
builds = [c for c in calls if c[:2] == ["docker", "build"]]
|
|
self.assertEqual(1, len(builds))
|
|
self.assertIn(self.sc.image_ref, builds[0])
|
|
self.assertTrue(any(a.endswith("Dockerfile.gateway") for a in builds[0]))
|
|
self.assertNotIn("--no-cache", builds[0])
|
|
|
|
def test_ensure_built_no_cache_env_forces_full_rebuild(self) -> None:
|
|
calls: list[list[str]] = []
|
|
|
|
def rec(argv: list[str], **_kw: object) -> Mock:
|
|
calls.append(argv)
|
|
return _proc()
|
|
|
|
with patch(_RUN_DOCKER, side_effect=rec), \
|
|
patch.dict("os.environ", {"BOT_BOTTLE_NO_CACHE": "1"}):
|
|
self.sc.ensure_built()
|
|
builds = [c for c in calls if c[:2] == ["docker", "build"]]
|
|
self.assertIn("--no-cache", builds[0])
|
|
|
|
def test_ensure_built_noop_when_no_dockerfile(self) -> None:
|
|
sc = DockerGateway("busybox", dockerfile=None)
|
|
with patch(_RUN_DOCKER) as m:
|
|
sc.ensure_built()
|
|
m.assert_not_called()
|
|
|
|
def test_ensure_built_raises_on_build_failure(self) -> None:
|
|
with patch(_RUN_DOCKER, return_value=_proc(returncode=1, stderr="build boom")):
|
|
with self.assertRaises(GatewayError):
|
|
self.sc.ensure_built()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|