Files
bot-bottle/tests/integration/test_pipelock_apply.py
T
didericis 2287b0dd08
test / unit (pull_request) Successful in 20s
test / integration (pull_request) Successful in 40s
test(sidecars): integration sweep for the bundle path (PRD 0024 chunk 4)
Three deliverables:

1. Rewrite test_pipelock_apply bringup with a direct `docker run`.
   Replaces the .start-based bringup deleted in chunk 3. Stages
   the yaml + CAs to the real pipelock_state_dir so the bind-
   mount target matches what apply_allowlist_change writes to —
   the legacy .start path did this implicitly because it lived
   inside the production flow; the new bringup needs to be
   explicit about the path. All 4 cases pass.

2. New tests/integration/test_sidecar_bundle_compose.py: end-
   to-end smoke with CLAUDE_BOTTLE_SIDECAR_BUNDLE=1. Brings up
   a real bottle via the compose path and verifies the agent
   can reach pipelock + supervise through the bundle's legacy
   aliases (no agent-side config changes between flag positions).
   Skipped under act_runner — multi-stage build + bind mounts.

3. Two bundle-path bugs surfaced and fixed while running PRD
   0022 with the flag on:

   - egress_entrypoint.sh: add `--set confdir=/home/mitmproxy/
     .mitmproxy` so mitmdump finds the bind-mounted CA. The
     legacy Dockerfile.egress runs as user mitmproxy (~mitmproxy
     resolves correctly); the bundle runs as root and otherwise
     would look in /root/.mitmproxy/ and mint a NEW CA the agent
     doesn't trust. Symptom: PRD 0022 attack-3 curl failed with
     "unable to get local issuer certificate".

   - sidecar_init.py: add `--listen 0.0.0.0:8888` to pipelock's
     argv. Without it pipelock defaults to 127.0.0.1, so the
     in-bundle egress's upstream connect to the
     `claude-bottle-pipelock-<slug>` alias arrives over the
     docker network and gets refused. The legacy renderer
     passed this flag verbatim; the bundle dropped it. Symptom:
     egress returned HTTP 502 with "Connect call failed
     ('172.x.x.x', 8888)".

   PRD 0022's 5-attack sandbox-escape suite now passes with the
   bundle flag on AND off.

Test status:
- Unit: 533 passing.
- Integration: 9 passing locally with flag off, 5 passing with
  flag on. Bundle compose smoke + PRD 0022 sandbox-escape both
  green under CLAUDE_BOTTLE_SIDECAR_BUNDLE=1.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-27 01:15:14 -04:00

201 lines
7.9 KiB
Python

"""Integration: drive `apply_allowlist_change` against a real
pipelock sidecar (PRD 0015).
Brings up a real pipelock container via direct `docker run` (the
old `.start()` helper went away in PRD 0024 chunk 3), calls
apply_allowlist_change to swap the api_allowlist, restarts
pipelock, and verifies the running container now serves the new
yaml.
The hot-reload code path under test (apply_allowlist_change,
fetch_current_yaml, fetch_current_allowlist) is unchanged from
PRD 0015 — only the test's bringup helper moved.
Setup uses pipelock_tls_init which bind-mounts a host path into a
one-shot pipelock container — that doesn't work in DinD, so the
test skips under GITEA_ACTIONS.
"""
from __future__ import annotations
import os
import shutil
import subprocess
import tempfile
import time
import unittest
from pathlib import Path
from claude_bottle.backend.docker.bottle_state import pipelock_state_dir
from claude_bottle.backend.docker.network import (
network_create_egress,
network_create_internal,
network_remove,
)
from claude_bottle.backend.docker.pipelock import (
PIPELOCK_CA_CERT_IN_CONTAINER,
PIPELOCK_CA_KEY_IN_CONTAINER,
PIPELOCK_IMAGE,
PIPELOCK_PORT,
DockerPipelockProxy,
pipelock_container_name,
pipelock_tls_init,
)
from claude_bottle.backend.docker.pipelock_apply import (
PipelockApplyError,
apply_allowlist_change,
fetch_current_allowlist,
fetch_current_yaml,
)
from claude_bottle.yaml_subset import parse_yaml_subset
from tests._docker import skip_unless_docker
from tests.fixtures import fixture_minimal
@skip_unless_docker()
@unittest.skipIf(
os.environ.get("GITEA_ACTIONS") == "true",
"skipped under act_runner: pipelock_tls_init uses a host bind mount "
"that doesn't share fs with the runner container",
)
class TestPipelockApply(unittest.TestCase):
def setUp(self):
self.slug = f"cb-test-pla-{os.getpid()}-{int(time.time())}"
self.sidecar_name = ""
self.internal_net = ""
self.egress_net = ""
self.work_dir = Path(tempfile.mkdtemp(prefix="pipelock-apply."))
def tearDown(self):
if self.sidecar_name:
subprocess.run(
["docker", "rm", "-f", self.sidecar_name],
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
)
for n in (self.internal_net, self.egress_net):
if n:
network_remove(n)
shutil.rmtree(self.work_dir, ignore_errors=True)
# Clean up the per-slug state dir under ~/.claude-bottle/state/
# (apply_allowlist_change writes there; _bring_up calls
# proxy.prepare with the same path so the bind-mount and the
# hot-reload write target stay coherent).
shutil.rmtree(pipelock_state_dir(self.slug), ignore_errors=True)
def _bring_up(self) -> None:
"""Replicates the pre-chunk-3 bring-up sequence (create on
internal network → bind-mount yaml + CAs → attach egress
network → docker start) without going through the deleted
`DockerPipelockProxy.start` helper. The same sequence is
what `docker compose up` does for the pipelock service in
production; this test path keeps the standalone-pipelock
smoke alive so `apply_allowlist_change`'s host-side
write + docker-restart loop has integration coverage.
The yaml stages into the production-real
`pipelock_state_dir(slug)` (not a private temp dir) so the
bind-mount target matches what `apply_allowlist_change`
writes to — otherwise the hot-reload would write to a
nowhere-mounted host path and the container would never see
the updated config."""
state_dir = pipelock_state_dir(self.slug)
state_dir.mkdir(parents=True, exist_ok=True)
prep = DockerPipelockProxy().prepare(
fixture_minimal().bottles["dev"], self.slug, state_dir,
)
self.internal_net = network_create_internal(self.slug)
self.egress_net = network_create_egress(self.slug)
ca_cert_host, ca_key_host = pipelock_tls_init(state_dir)
self.sidecar_name = pipelock_container_name(self.slug)
subprocess.run(
["docker", "create",
"--name", self.sidecar_name,
"--network", self.internal_net,
"-v", f"{prep.yaml_path}:/etc/pipelock.yaml:ro",
"-v", f"{ca_cert_host}:{PIPELOCK_CA_CERT_IN_CONTAINER}:ro",
"-v", f"{ca_key_host}:{PIPELOCK_CA_KEY_IN_CONTAINER}:ro",
PIPELOCK_IMAGE,
"run", "--config", "/etc/pipelock.yaml",
"--listen", f"0.0.0.0:{PIPELOCK_PORT}"],
check=True, capture_output=True,
)
subprocess.run(
["docker", "network", "connect", self.egress_net, self.sidecar_name],
check=True, capture_output=True,
)
subprocess.run(
["docker", "start", self.sidecar_name],
check=True, capture_output=True,
)
# Wait until fetch_current_yaml succeeds — it's a docker cp
# which works on a started-but-not-yet-ready pipelock, so
# this is more of a "container exists" probe than a
# readiness one; the hot-reload tests below tolerate
# pipelock briefly being slow to serve.
deadline = time.monotonic() + 15.0
while time.monotonic() < deadline:
try:
fetch_current_yaml(self.slug)
return
except PipelockApplyError:
pass
time.sleep(0.25)
raise AssertionError("pipelock sidecar never became reachable")
def _wait_for_yaml(self, contains: str, *, deadline_s: float = 15.0) -> str:
"""Poll docker exec until /etc/pipelock.yaml contains `contains`,
returning the yaml. Used to bridge the docker-restart window."""
deadline = time.monotonic() + deadline_s
while time.monotonic() < deadline:
try:
yaml = fetch_current_yaml(self.slug)
if contains in yaml:
return yaml
except PipelockApplyError:
pass
time.sleep(0.25)
self.fail(f"never saw {contains!r} in /etc/pipelock.yaml")
def test_apply_swaps_api_allowlist(self):
self._bring_up()
initial_yaml = fetch_current_yaml(self.slug)
# fixture_minimal yields the baked-in DEFAULT_ALLOWLIST in
# pipelock.py; api.anthropic.com is in there.
self.assertIn("api.anthropic.com", initial_yaml)
new_content = "api.anthropic.com\nnew-host.example\n"
before, after = apply_allowlist_change(self.slug, new_content)
self.assertIn("api.anthropic.com", before)
self.assertNotIn("new-host.example", before)
self.assertIn("new-host.example", after)
updated = self._wait_for_yaml("new-host.example")
cfg = parse_yaml_subset(updated)
self.assertIn("new-host.example", cfg["api_allowlist"]) # type: ignore[operator]
self.assertIn("api.anthropic.com", cfg["api_allowlist"]) # type: ignore[operator]
# tls_interception block (set up by the production prepare
# via pipelock_build_config) is preserved across the swap.
self.assertIn("tls_interception", cfg)
def test_apply_with_invalid_host_raises(self):
self._bring_up()
with self.assertRaises(PipelockApplyError):
apply_allowlist_change(self.slug, "host with space.example\n")
def test_fetch_current_allowlist_renders_one_per_line(self):
self._bring_up()
listing = fetch_current_allowlist(self.slug)
self.assertTrue(listing.endswith("\n"))
self.assertIn("api.anthropic.com\n", listing)
def test_apply_against_missing_sidecar_raises(self):
# Don't bring up — the slug points at nothing.
with self.assertRaises(PipelockApplyError):
apply_allowlist_change(self.slug, "x.example\n")
if __name__ == "__main__":
unittest.main()