4a607ad098
Adopts the firecracker infra-VM pattern for macOS: the orchestrator control plane and the gateway data plane now run in a SINGLE Apple container instead of two. Apple Containers are lightweight VMs with separate kernels, so the prior two-container design had both guests writing one bot-bottle.db over virtiofs, where fcntl locks are not coherent across kernels — concurrent writes (the orchestrator's registry vs the gateway supervise daemon's queue) could corrupt it. One container = one kernel = coherent locking. The DB moves onto a container-only Apple volume (bot-bottle-mac-db), never bind-mounted from the host, so no host process opens the live file either. The host CLI already reaches registry + supervise state over the control-plane HTTP surface (cli/supervise.py uses OrchestratorClient), exactly as firecracker's VM-only DB requires. Two simplifications fall out of the single container: - No DNS dance: the control plane and gateway daemons reach each other over 127.0.0.1, so the orchestrator-before-gateway ordering (a workaround for Apple having no container DNS) is gone, along with the moved-IP recreate logic it needed. - Net -243 lines. Mechanics: the infra container runs from the gateway image with the control-plane source bind-mounted read-only (like the docker orchestrator, so a code change needs no rebuild) and a small sh -c init that starts both processes (mirrors firecracker's _infra_init). Also implements the macOS backend's ensure_orchestrator() and adds it to discover_orchestrator_url, so operator tools (supervise) can bring up / find the control plane on demand — previously the macOS backend died with "no orchestrator control plane". Verified end-to-end on real Apple Container 1.0.0: the single infra container comes up healthy (one address for control plane + gateway), both processes run, the DB is written on the container-only volume, host-side supervise works over HTTP, and a registered agent gets 200 for an allowed host / 403 for a denied one. 1824 unit tests pass with `container` absent (CI parity), pyright clean, pylint 9.89. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
169 lines
7.7 KiB
Python
169 lines
7.7 KiB
Python
"""Unit: the single macOS infra container (control plane + gateway, PRD 0070)."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import unittest
|
|
from pathlib import Path
|
|
from unittest.mock import Mock, patch
|
|
|
|
from bot_bottle.backend.macos_container.infra import (
|
|
INFRA_DB_VOLUME,
|
|
MacosInfraService,
|
|
OrchestratorStartError,
|
|
probe_control_plane_url,
|
|
)
|
|
|
|
_INFRA = "bot_bottle.backend.macos_container.infra"
|
|
|
|
|
|
def _ok(stdout: str = "") -> Mock:
|
|
return Mock(returncode=0, stdout=stdout, stderr="")
|
|
|
|
|
|
def _fail(stderr: str = "boom") -> Mock:
|
|
return Mock(returncode=1, stdout="", stderr=stderr)
|
|
|
|
|
|
class TestInfraRun(unittest.TestCase):
|
|
def _run_container(self, svc: MacosInfraService) -> list[str]:
|
|
run = Mock(return_value=_ok())
|
|
|
|
def _spec(src: str, tgt: str, readonly: bool = False) -> str:
|
|
return f"type=bind,source={src},target={tgt}" + (
|
|
",readonly" if readonly else "")
|
|
|
|
with patch(f"{_INFRA}.container_mod") as mod, \
|
|
patch(f"{_INFRA}.ensure_networks"):
|
|
mod.dns_server.return_value = "1.1.1.1"
|
|
mod.bind_mount_spec.side_effect = _spec
|
|
mod.run_container_argv = run
|
|
svc._run_container("h1")
|
|
return run.call_args.args[0]
|
|
|
|
def test_single_container_runs_both_processes(self) -> None:
|
|
"""The whole point: one container starts the control plane AND the
|
|
gateway daemons, so one kernel owns the DB."""
|
|
argv = self._run_container(MacosInfraService(repo_root=Path("/r")))
|
|
script = argv[-1]
|
|
self.assertIn("bot_bottle.orchestrator", script)
|
|
self.assertIn("gateway_init.py", script)
|
|
self.assertIn("127.0.0.1", script) # they reach each other on loopback
|
|
|
|
def test_db_is_a_container_only_volume(self) -> None:
|
|
"""No host bind-mount of the DB — a named volume only this container
|
|
mounts, so the DB is never written by two kernels."""
|
|
argv = self._run_container(MacosInfraService(repo_root=Path("/r")))
|
|
vols = [argv[i + 1] for i, a in enumerate(argv) if a == "--volume"]
|
|
self.assertTrue(any(v.startswith(f"{INFRA_DB_VOLUME}:") for v in vols))
|
|
# The repo source is bind-mounted read-only; the DB is not a bind mount.
|
|
mounts = [argv[i + 1] for i, a in enumerate(argv) if a == "--mount"]
|
|
self.assertTrue(all("bot-bottle.db" not in m for m in mounts))
|
|
|
|
def test_nat_network_precedes_the_host_only_network(self) -> None:
|
|
argv = self._run_container(MacosInfraService(repo_root=Path("/r")))
|
|
nets = [argv[i + 1] for i, a in enumerate(argv) if a == "--network"]
|
|
self.assertEqual(["bot-bottle-mac-egress", "bot-bottle-mac-gateway"], nets)
|
|
|
|
def test_source_hash_is_labelled_for_recreate(self) -> None:
|
|
argv = self._run_container(MacosInfraService(repo_root=Path("/r")))
|
|
self.assertIn("BOT_BOTTLE_SOURCE_HASH=h1", argv)
|
|
|
|
def test_start_failure_raises(self) -> None:
|
|
svc = MacosInfraService(repo_root=Path("/r"))
|
|
with patch(f"{_INFRA}.container_mod") as mod, \
|
|
patch(f"{_INFRA}.ensure_networks"):
|
|
mod.dns_server.return_value = "1.1.1.1"
|
|
mod.bind_mount_spec.return_value = "m"
|
|
mod.run_container_argv = Mock(return_value=_fail())
|
|
with self.assertRaises(OrchestratorStartError):
|
|
svc._run_container("h1")
|
|
|
|
|
|
class TestInfraEnsureRunning(unittest.TestCase):
|
|
def test_current_healthy_container_is_left_alone(self) -> None:
|
|
"""Idempotent singleton: N launches must not churn the infra container
|
|
and drop every live bottle's control plane."""
|
|
svc = MacosInfraService(repo_root=Path("/r"))
|
|
run = Mock()
|
|
with patch(f"{_INFRA}.container_mod") as mod, \
|
|
patch(f"{_INFRA}.source_hash", return_value="h1"), \
|
|
patch.object(svc, "_run_container", run), \
|
|
patch.object(svc, "is_healthy", return_value=True):
|
|
mod.container_is_running.return_value = True
|
|
mod.container_env.return_value = {"BOT_BOTTLE_SOURCE_HASH": "h1"}
|
|
mod.try_container_ipv4_on_network.return_value = "192.168.128.2"
|
|
endpoint = svc.ensure_running()
|
|
run.assert_not_called()
|
|
self.assertEqual("http://192.168.128.2:8099", endpoint.control_plane_url)
|
|
self.assertEqual("192.168.128.2", endpoint.gateway_ip)
|
|
|
|
def test_changed_source_recreates(self) -> None:
|
|
svc = MacosInfraService(repo_root=Path("/r"))
|
|
run = Mock()
|
|
with patch(f"{_INFRA}.container_mod") as mod, \
|
|
patch(f"{_INFRA}.source_hash", return_value="h2"), \
|
|
patch.object(svc, "ensure_built"), \
|
|
patch.object(svc, "_run_container", run), \
|
|
patch.object(svc, "is_healthy", return_value=True):
|
|
mod.container_is_running.return_value = True
|
|
mod.container_env.return_value = {"BOT_BOTTLE_SOURCE_HASH": "h1"}
|
|
mod.try_container_ipv4_on_network.return_value = "192.168.128.2"
|
|
svc.ensure_running()
|
|
run.assert_called_once()
|
|
|
|
def test_wedged_but_current_container_is_recreated(self) -> None:
|
|
"""Current source but a dead HTTP server must be recreated, not polled
|
|
to death forever — health, not just the source label, gates reuse."""
|
|
svc = MacosInfraService(repo_root=Path("/r"))
|
|
run = Mock()
|
|
health = Mock(side_effect=[False, True])
|
|
with patch(f"{_INFRA}.container_mod") as mod, \
|
|
patch(f"{_INFRA}.source_hash", return_value="h1"), \
|
|
patch.object(svc, "ensure_built"), \
|
|
patch.object(svc, "_run_container", run), \
|
|
patch.object(svc, "is_healthy", health):
|
|
mod.container_is_running.return_value = True
|
|
mod.container_env.return_value = {"BOT_BOTTLE_SOURCE_HASH": "h1"}
|
|
mod.try_container_ipv4_on_network.return_value = "192.168.128.2"
|
|
svc.ensure_running()
|
|
run.assert_called_once()
|
|
|
|
def test_never_healthy_raises(self) -> None:
|
|
svc = MacosInfraService(repo_root=Path("/r"))
|
|
with patch(f"{_INFRA}.container_mod") as mod, \
|
|
patch(f"{_INFRA}.source_hash", return_value="h1"), \
|
|
patch.object(svc, "ensure_built"), \
|
|
patch.object(svc, "_run_container"), \
|
|
patch.object(svc, "is_healthy", return_value=False):
|
|
mod.container_is_running.return_value = False
|
|
mod.try_container_ipv4_on_network.return_value = "192.168.128.2"
|
|
with self.assertRaises(OrchestratorStartError):
|
|
svc.ensure_running(startup_timeout=0.01)
|
|
|
|
|
|
class TestCaCertPem(unittest.TestCase):
|
|
def test_reads_ca_out_of_the_container(self) -> None:
|
|
svc = MacosInfraService(repo_root=Path("/r"))
|
|
with patch(f"{_INFRA}.container_mod") as mod:
|
|
mod.run_container_argv.return_value = _ok("-----BEGIN CERTIFICATE-----\n")
|
|
pem = svc.ca_cert_pem()
|
|
self.assertTrue(pem.startswith("-----BEGIN CERTIFICATE-----"))
|
|
argv = mod.run_container_argv.call_args.args[0]
|
|
self.assertEqual(["container", "exec", "bot-bottle-mac-infra", "cat"], argv[:4])
|
|
|
|
|
|
class TestProbeControlPlane(unittest.TestCase):
|
|
def test_returns_url_when_running(self) -> None:
|
|
with patch(f"{_INFRA}.container_mod") as mod:
|
|
mod.try_container_ipv4_on_network.return_value = "192.168.128.2"
|
|
self.assertEqual("http://192.168.128.2:8099", probe_control_plane_url())
|
|
|
|
def test_empty_when_absent(self) -> None:
|
|
with patch(f"{_INFRA}.container_mod") as mod:
|
|
mod.try_container_ipv4_on_network.return_value = ""
|
|
self.assertEqual("", probe_control_plane_url())
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|