feat(host-agent): stop assignment execution collaboratively on cancellation

- LeaseGuard gains an is_cancellation convenience property
- ActiveAssignmentRunner marks the lease lost with a cancellation
  reason when a renewal response reports cancel_requested
- AssignmentExecutor threads stop_reason through to TaskRunner/
  WorkflowRunner and maps a cancellation-flavored stop to
  AssignmentExecutionResult.status = "cancelled" instead of "failed"
- AssignmentProcessor forwards a three-way done/cancelled/failed
  status when reporting the terminal result
- Add/extend tests across lease, assignment, processor, and client
This commit is contained in:
2026-07-15 18:28:21 +08:00
parent 8a0d48eada
commit d3024b4810
9 changed files with 233 additions and 22 deletions
@@ -78,6 +78,39 @@ def test_goal_assignment_preserves_runtime_failure_reason() -> None:
assert result.failure_reason == "planner unavailable"
def test_goal_assignment_maps_cancellation_stop_to_cancelled_status() -> None:
# First should_stop() call is Executor.execute()'s pre-flight check (must pass
# through so the runner is actually invoked); the runner's own loop then stops.
calls = {"count": 0}
def should_stop() -> bool:
calls["count"] += 1
return calls["count"] > 1
class FakeTaskRunner:
def run(self, task: Task, *, should_stop=None, stop_reason=None) -> Task:
assert should_stop is not None and should_stop()
assert stop_reason is not None
task.status = "cancelled"
task.failure_reason = stop_reason()
return task
factories = ExecutionFactories(
task_runner_factory=lambda: FakeTaskRunner(), # type: ignore[arg-type,return-value]
workflow_runner_factory=lambda: object(), # type: ignore[arg-type,return-value]
workflow_store=object(), # type: ignore[arg-type]
)
result = AssignmentExecutor(factories).execute(
_assignment(),
should_stop=should_stop,
stop_reason=lambda: "cancellation requested by control plane",
)
assert result.status == "cancelled"
assert result.failure_reason == "cancellation requested by control plane"
def test_workflow_assignment_loads_and_executes_definition() -> None:
definition = object()
calls: list[tuple[object, str]] = []
@@ -109,6 +142,44 @@ def test_workflow_assignment_loads_and_executes_definition() -> None:
}
def test_workflow_assignment_maps_cancellation_stop_to_cancelled_status() -> None:
calls = {"count": 0}
def should_stop() -> bool:
calls["count"] += 1
return calls["count"] > 1
class FakeWorkflowStore:
def get_definition(self, definition_id: str):
return object() if definition_id == "workflow-a" else None
class FakeWorkflowRunner:
def run(self, loaded_definition, device_id: str, *, should_stop=None, stop_reason=None):
assert should_stop is not None and should_stop()
assert stop_reason is not None
return SimpleNamespace(
id="run-a", status="cancelled", failure_reason=stop_reason()
)
factories = ExecutionFactories(
task_runner_factory=lambda: object(), # type: ignore[arg-type,return-value]
workflow_runner_factory=lambda: FakeWorkflowRunner(), # type: ignore[arg-type,return-value]
workflow_store=FakeWorkflowStore(), # type: ignore[arg-type]
)
result = AssignmentExecutor(factories).execute(
_assignment(goal=None, workflow_definition_id="workflow-a"),
should_stop=should_stop,
stop_reason=lambda: "cancellation requested by control plane",
)
assert result.status == "cancelled"
assert result.metadata == {
"workflow_run_id": "run-a",
"workflow_status": "cancelled",
}
def test_unknown_workflow_fails_without_running() -> None:
class FakeWorkflowStore:
def get_definition(self, definition_id: str):