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
@@ -9,6 +9,7 @@ from core.models import Task
from host_agent.execution import ExecutionFactories
from host_agent.planner_context import bind_planner_execution_context
from host_agent.progress import TaskProgressHolder, TaskProgressSnapshot
from runtime.task import is_cancellation_reason
@dataclass(frozen=True)
@@ -32,18 +33,24 @@ class AssignmentExecutor:
assignment: AssignmentModel,
*,
should_stop: Callable[[], bool] | None = None,
stop_reason: Callable[[], str | None] | None = None,
) -> AssignmentExecutionResult:
self._progress.clear()
with bind_planner_execution_context(assignment):
if should_stop is not None and should_stop():
reason = stop_reason() if stop_reason is not None else None
return AssignmentExecutionResult(
status="failed",
failure_reason="execution interrupted",
status="cancelled" if is_cancellation_reason(reason) else "failed",
failure_reason=reason or "execution interrupted",
)
if assignment.workflow_definition_id is not None:
return self._execute_workflow(assignment, should_stop=should_stop)
return self._execute_workflow(
assignment, should_stop=should_stop, stop_reason=stop_reason
)
if assignment.goal is not None:
return self._execute_goal(assignment, should_stop=should_stop)
return self._execute_goal(
assignment, should_stop=should_stop, stop_reason=stop_reason
)
return AssignmentExecutionResult(
status="failed",
failure_reason="assignment has neither goal nor workflow definition",
@@ -54,6 +61,7 @@ class AssignmentExecutor:
assignment: AssignmentModel,
*,
should_stop: Callable[[], bool] | None,
stop_reason: Callable[[], str | None] | None,
) -> AssignmentExecutionResult:
task = Task(goal=assignment.goal or "", device_id=assignment.device_id)
if self.factories.metadata_store is not None:
@@ -67,9 +75,11 @@ class AssignmentExecutor:
if should_stop is None:
completed = runner.run(task)
else:
completed = runner.run(task, should_stop=should_stop)
completed = runner.run(
task, should_stop=should_stop, stop_reason=stop_reason
)
return AssignmentExecutionResult(
status="done" if completed.status == "completed" else "failed",
status=_terminal_status(completed.status),
failure_reason=completed.failure_reason,
metadata={
"runtime_task_id": completed.id,
@@ -82,6 +92,7 @@ class AssignmentExecutor:
assignment: AssignmentModel,
*,
should_stop: Callable[[], bool] | None,
stop_reason: Callable[[], str | None] | None,
) -> AssignmentExecutionResult:
definition_id = assignment.workflow_definition_id or ""
definition = self.factories.workflow_store.get_definition(definition_id)
@@ -98,9 +109,10 @@ class AssignmentExecutor:
definition,
device_id=assignment.device_id,
should_stop=should_stop,
stop_reason=stop_reason,
)
return AssignmentExecutionResult(
status="done" if run.status == "completed" else "failed",
status=_terminal_status(run.status),
failure_reason=(
None if run.status == "completed" else f"workflow ended as {run.status}"
),
@@ -109,3 +121,11 @@ class AssignmentExecutor:
"workflow_status": run.status,
},
)
def _terminal_status(runtime_status: str) -> str:
if runtime_status == "completed":
return "done"
if runtime_status == "cancelled":
return "cancelled"
return "failed"