Files
bot-bottle/tests/unit/test_macos_consolidated_launch.py
T
didericis 60c33b5252 fix(orchestrator): reap registry rows whose bottle is no longer running
A registry row only ever left the registry two ways: an explicit
teardown_bottle (the launcher's cleanup callback) or the same-IP supersede
sweep in register(). Neither runs when the launching CLI dies hard, so the
row outlives its container.

That orphan is not inert. Source IPs are recycled by the backend's DHCP and
by_source_ip fail-closes on ambiguity, so a leftover row at a reused address
resolves no policy at all for the next bottle that lands there — and a
bottle with no policy denies every host, which surfaces to the agent as
"host X is not in the allowlist" for hosts that were never the problem.

Add reap_absent/reconcile and call it from the macOS launch path before
registering, so each launch self-heals the registry. Restores the invariant
the data plane needs: at most one active row per live address, and none for
a dead one. The second half matters as much as the first — when several rows
claim a *live* address the newest wins and the rest are swept, otherwise a
recycled address stays ambiguous, which is exactly the bricked state.

The host supplies the live set because the orchestrator runs inside the
infra container and cannot see the backend. A grace window exempts rows
younger than it, so reconciliation cannot race a bottle still coming up, and
a reconcile failure is logged rather than blocking an otherwise-fine launch.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-21 02:57:29 +00:00

203 lines
8.0 KiB
Python

"""Unit: macOS consolidated launch — register-after-start (PRD 0070)."""
from __future__ import annotations
import unittest
from pathlib import Path
from unittest.mock import MagicMock, Mock, patch
from bot_bottle.backend.macos_container.consolidated_launch import (
GatewayEndpoint,
ensure_gateway,
register_agent,
teardown_consolidated,
)
from bot_bottle.egress import EgressPlan, EgressRoute
from bot_bottle.git_gate import GitGatePlan
from bot_bottle.orchestrator.client import RegisteredBottle
_MOD = "bot_bottle.backend.macos_container.consolidated_launch"
def _egress_plan() -> EgressPlan:
return EgressPlan(
slug="demo", routes_path=Path("/x"),
routes=(EgressRoute(host="api.example.com"),), token_env_map={},
)
def _git_plan() -> GitGatePlan:
return GitGatePlan(
slug="demo", entrypoint_script=Path(), hook_script=Path(),
access_hook_script=Path(), upstreams=(),
)
def _endpoint() -> GatewayEndpoint:
return GatewayEndpoint(
orchestrator_url="http://192.168.128.2:8099",
gateway_ip="192.168.128.3",
gateway_ca_pem="-----BEGIN CERTIFICATE-----\n",
network="bot-bottle-mac-gateway",
)
def _client() -> Mock:
c = Mock()
c.register_bottle.return_value = RegisteredBottle("b1", "tok")
return c
class TestEnsureGateway(unittest.TestCase):
def _run(self, service: MagicMock) -> GatewayEndpoint:
with patch(f"{_MOD}.MacosInfraService", return_value=service):
return ensure_gateway()
def _service(self) -> MagicMock:
from bot_bottle.backend.macos_container.infra import InfraEndpoint
service = MagicMock()
service.ensure_running.return_value = InfraEndpoint(
control_plane_url="http://192.168.128.2:8099",
gateway_ip="192.168.128.2",
)
service.network = "bot-bottle-mac-gateway"
service.ca_cert_pem.return_value = "PEM"
return service
def test_reports_gateway_endpoint(self) -> None:
endpoint = self._run(self._service())
self.assertEqual("http://192.168.128.2:8099", endpoint.orchestrator_url)
self.assertEqual("192.168.128.2", endpoint.gateway_ip)
self.assertEqual("PEM", endpoint.gateway_ca_pem)
self.assertEqual("bot-bottle-mac-gateway", endpoint.network)
def test_control_plane_and_gateway_share_one_address(self) -> None:
"""One infra container hosts both, so the gateway IP and the
control-plane host are the same."""
endpoint = self._run(self._service())
self.assertEqual(
endpoint.gateway_ip,
endpoint.orchestrator_url.split("://")[1].split(":")[0],
)
class TestRegisterAgent(unittest.TestCase):
def _run(
self, client: Mock, provision: Mock | None = None,
*, source_ip: str = "192.168.128.9",
):
with patch(f"{_MOD}.OrchestratorClient", return_value=client), \
patch(f"{_MOD}.provision_git_gate", provision or Mock()):
return register_agent(
_egress_plan(), _git_plan(),
source_ip=source_ip, endpoint=_endpoint(), image_ref="img:1",
)
def test_registers_by_the_address_read_from_the_live_container(self) -> None:
"""The attribution key is the DHCP-assigned address the caller read
back — there is no --ip to pin it up front."""
client = _client()
ctx = self._run(client, source_ip="192.168.128.9")
self.assertEqual("192.168.128.9", ctx.source_ip)
self.assertEqual("192.168.128.9", client.register_bottle.call_args.args[0])
def test_returns_identity_token_and_bottle_id(self) -> None:
ctx = self._run(_client())
self.assertEqual("b1", ctx.bottle_id)
self.assertEqual("tok", ctx.identity_token)
def test_provisions_git_gate_for_the_registered_bottle(self) -> None:
provision = Mock()
self._run(_client(), provision)
self.assertEqual("b1", provision.call_args.args[1])
def test_rolls_registration_back_when_provisioning_fails(self) -> None:
"""A provisioning failure must not leave an orphan registration
holding the source IP."""
client = _client()
provision = Mock(side_effect=RuntimeError("boom"))
with self.assertRaises(RuntimeError):
self._run(client, provision)
client.teardown_bottle.assert_called_once_with("b1")
class TestTeardown(unittest.TestCase):
def test_deregisters_and_deprovisions(self) -> None:
client = Mock()
deprovision = Mock()
with patch(f"{_MOD}.OrchestratorClient", return_value=client), \
patch(f"{_MOD}.deprovision_git_gate", deprovision):
teardown_consolidated("b1", orchestrator_url="http://o:8099")
client.teardown_bottle.assert_called_once_with("b1")
self.assertEqual("b1", deprovision.call_args.args[1])
if __name__ == "__main__":
unittest.main()
class TestLiveSourceIps(unittest.TestCase):
"""The reconciliation input: the host enumerates its own bottles because
the orchestrator, inside the infra container, cannot see the backend."""
def _agents(self, *slugs: str) -> list[Mock]:
return [Mock(slug=s) for s in slugs]
def test_maps_slugs_to_container_addresses(self) -> None:
from bot_bottle.backend.macos_container.consolidated_launch import live_source_ips
with patch(f"{_MOD}.enumerate_active", return_value=self._agents("a", "b")), \
patch(f"{_MOD}.container_mod.try_container_ipv4_on_network",
side_effect=["10.0.0.1", "10.0.0.2"]) as ip:
got = live_source_ips("net0")
self.assertEqual(["10.0.0.1", "10.0.0.2"], got)
self.assertEqual("bot-bottle-a", ip.call_args_list[0].args[0])
def test_containers_without_an_address_are_skipped(self) -> None:
"""A container that hasn't been given a DHCP address yet contributes
nothing — the reap's grace window, not this list, protects it."""
from bot_bottle.backend.macos_container.consolidated_launch import live_source_ips
with patch(f"{_MOD}.enumerate_active", return_value=self._agents("a", "b")), \
patch(f"{_MOD}.container_mod.try_container_ipv4_on_network",
side_effect=["", "10.0.0.2"]):
self.assertEqual(["10.0.0.2"], live_source_ips("net0"))
class TestRegisterAgentReconciles(unittest.TestCase):
"""Registration self-heals the registry first: an orphan row at a recycled
address makes attribution ambiguous, which resolves no policy at all and
denies every host for the bottle being launched."""
def _register(self, client: Mock) -> None:
with patch(f"{_MOD}.OrchestratorClient", return_value=client), \
patch(f"{_MOD}.provision_git_gate"), \
patch(f"{_MOD}.live_source_ips", return_value=["10.0.0.7"]):
register_agent(
_egress_plan(), _git_plan(),
source_ip="10.0.0.7", endpoint=_endpoint(),
)
def test_reconciles_before_registering(self) -> None:
client = _client()
calls: list[str] = []
def _reconcile(*_args: object, **_kwargs: object) -> list[str]:
calls.append("reconcile")
return []
def _register_bottle(*_args: object, **_kwargs: object) -> RegisteredBottle:
calls.append("register")
return RegisteredBottle("b1", "tok")
client.reconcile.side_effect = _reconcile
client.register_bottle.side_effect = _register_bottle
self._register(client)
self.assertEqual(["reconcile", "register"], calls)
client.reconcile.assert_called_once_with(["10.0.0.7"])
def test_a_reconcile_failure_does_not_block_the_launch(self) -> None:
from bot_bottle.orchestrator.client import OrchestratorClientError
client = _client()
client.reconcile.side_effect = OrchestratorClientError("unreachable")
self._register(client)
client.register_bottle.assert_called_once()