fix: require authoritative container snapshot before reconciling
test / stage-firecracker-inputs (pull_request) Successful in 5s
tracker-policy-pr / check-pr (pull_request) Successful in 12s
test / integration-docker (pull_request) Successful in 33s
test / unit (pull_request) Successful in 39s
lint / lint (push) Successful in 49s
test / build-infra (pull_request) Successful in 3m23s
test / integration-firecracker (pull_request) Successful in 1m42s
test / coverage (pull_request) Failing after 1m26s
test / publish-infra (pull_request) Has been skipped

A failed container list or a partial per-container inspect were
previously indistinguishable from a legitimately empty/partial live
set, so reconciliation could silently unregister healthy bottles.

- enumerate_active() now raises EnumerationError instead of returning []
  when `container list` fails
- Add inspect_container_network_ip() to util, which returns None on
  inspect failure (vs "" for "no DHCP address yet"), so live_source_ips
  can tell the two apart
- live_source_ips() raises EnumerationError on either failure mode;
  register_agent() catches it and skips reconciliation, same as
  OrchestratorClientError
- Update tests: rename test_empty_when_the_cli_fails to
  test_raises_when_the_cli_fails, update patching to the new function,
  add coverage for list failure, per-container inspect failure, and the
  launch-not-blocked path
This commit is contained in:
2026-07-21 03:39:18 +00:00
parent 288b205a44
commit 571030b8e8
5 changed files with 99 additions and 13 deletions
+37 -2
View File
@@ -147,7 +147,7 @@ class TestLiveSourceIps(unittest.TestCase):
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",
patch(f"{_MOD}.container_mod.inspect_container_network_ip",
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)
@@ -158,10 +158,30 @@ class TestLiveSourceIps(unittest.TestCase):
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",
patch(f"{_MOD}.container_mod.inspect_container_network_ip",
side_effect=["", "10.0.0.2"]):
self.assertEqual(["10.0.0.2"], live_source_ips("net0"))
def test_container_list_failure_raises(self) -> None:
"""If container list fails, the live set is not authoritative and
reconciliation must be skipped."""
from bot_bottle.backend.macos_container.consolidated_launch import live_source_ips
from bot_bottle.backend.macos_container.enumerate import EnumerationError
with patch(f"{_MOD}.enumerate_active",
side_effect=EnumerationError("container list failed")):
with self.assertRaises(EnumerationError):
live_source_ips("net0")
def test_per_container_inspect_failure_raises(self) -> None:
"""If any individual inspect fails, the live set is not authoritative."""
from bot_bottle.backend.macos_container.consolidated_launch import live_source_ips
from bot_bottle.backend.macos_container.enumerate import EnumerationError
with patch(f"{_MOD}.enumerate_active", return_value=self._agents("a", "b")), \
patch(f"{_MOD}.container_mod.inspect_container_network_ip",
side_effect=["10.0.0.1", None]):
with self.assertRaises(EnumerationError):
live_source_ips("net0")
class TestRegisterAgentReconciles(unittest.TestCase):
"""Registration self-heals the registry first: an orphan row at a recycled
@@ -201,3 +221,18 @@ class TestRegisterAgentReconciles(unittest.TestCase):
client.reconcile.side_effect = OrchestratorClientError("unreachable")
self._register(client)
client.register_bottle.assert_called_once()
def test_enumeration_error_does_not_block_the_launch(self) -> None:
"""A partial container listing must not abort the launch — skip
reconciliation and proceed, just as with an unreachable orchestrator."""
from bot_bottle.backend.macos_container.enumerate import EnumerationError
client = _client()
with patch(f"{_MOD}.OrchestratorClient", return_value=client), \
patch(f"{_MOD}.provision_git_gate"), \
patch(f"{_MOD}.live_source_ips",
side_effect=EnumerationError("container list failed")):
register_agent(
_egress_plan(), _git_plan(),
source_ip="10.0.0.7", endpoint=_endpoint(),
)
client.register_bottle.assert_called_once()