feat(cloud): add durable cancellation support to task repository

- Add nullable cancel_requested_at column (migration 0012)
- Widen ScheduledTaskStatus/TerminalTaskStatus to include cancelled
- Add CancellationRequestStatus + request_task_cancellation() to
  CloudRepository protocol and SQLAlchemy implementation
- renew_lease() now returns LeaseRenewalResult, surfacing whether
  cancellation is pending, instead of a bare status string
- reap_expired_leases() resolves pending-cancellation tasks to
  cancelled instead of requeuing/failing them
- record_task_result() accepts cancelled and clears
  cancel_requested_at on any terminal write

Note: internal_api/api.py's renew_assignment route still compares
renew_lease()'s return value against a bare string; it will be
updated in the next task (Internal Host<->Cloud protocol) to consume
LeaseRenewalResult and populate the new cancel_requested wire field.
This commit is contained in:
2026-07-15 18:08:48 +08:00
parent 88189770ff
commit 19c6669800
9 changed files with 385 additions and 35 deletions
+25 -2
View File
@@ -30,9 +30,12 @@ if TYPE_CHECKING:
AttemptStatus = Literal["assigned", "dispatched", "done", "failed", "expired"]
TerminalTaskStatus = Literal["done", "failed"]
TerminalTaskStatus = Literal["done", "failed", "cancelled"]
ResultRecordStatus = Literal["recorded", "already_recorded", "conflict"]
LeaseRenewalStatus = Literal["renewed", "not_found", "conflict", "expired"]
CancellationRequestStatus = Literal[
"requested", "already_terminal", "already_requested", "not_found"
]
class HostEnrollmentConflictError(RuntimeError):
@@ -91,6 +94,19 @@ class TaskAttemptRecord:
terminal_result: dict[str, Any] | None = None
@dataclass(frozen=True)
class LeaseRenewalResult:
"""Outcome of a lease renewal, including whether cancellation is pending.
``cancel_requested`` reflects the task's durable ``cancel_requested_at``
column at renewal time regardless of ``status`` — callers only act on it
when ``status == "renewed"``.
"""
status: LeaseRenewalStatus
cancel_requested: bool = False
@dataclass(frozen=True)
class LeasedAssignment:
task_id: str
@@ -485,7 +501,7 @@ class CloudRepository(Protocol):
lease_expires_at: datetime,
now: datetime,
progress: AssignmentProgressSnapshot | None = None,
) -> LeaseRenewalStatus: ...
) -> LeaseRenewalResult: ...
def record_task_result(
self,
@@ -500,6 +516,13 @@ class CloudRepository(Protocol):
completed_at: datetime,
) -> ResultRecordStatus: ...
def request_task_cancellation(
self,
task_id: str,
*,
requested_at: datetime,
) -> CancellationRequestStatus: ...
def reap_expired_leases(
self,
*,