feat(cloud): surface cancellation over the internal Host<->Cloud protocol

- LeaseRenewalResponse gains cancel_requested (populated from the
  repository's renew_lease result)
- TerminalResultRequest.status widened to accept "cancelled"
- Add internal API tests for a renewal surfacing cancel_requested=True
  and a cancelled terminal report being accepted/idempotent
This commit is contained in:
2026-07-15 18:13:43 +08:00
parent 19c6669800
commit 8a0d48eada
4 changed files with 64 additions and 9 deletions
+5 -5
View File
@@ -21,11 +21,11 @@
## 3. Internal Host↔Cloud protocol
- [ ] 3.1 Add `cancel_requested: bool = False` field to `LeaseRenewalResponse` (`internal_api/models.py`).
- [ ] 3.2 Widen `TerminalResultRequest.status` (`internal_api/models.py`) to `Literal["done", "failed", "cancelled"]`.
- [ ] 3.3 Update `renew_assignment` route (`internal_api/api.py`) to populate `LeaseRenewalResponse.cancel_requested` from the repository's `renew_lease` result.
- [ ] 3.4 Update `report_result` route (`internal_api/api.py`) to accept and forward the `"cancelled"` status to `record_task_result`.
- [ ] 3.5 Add/extend internal API tests covering a renewal response surfacing `cancel_requested=True` and a `"cancelled"` terminal report being accepted and idempotent on repeat.
- [x] 3.1 Add `cancel_requested: bool = False` field to `LeaseRenewalResponse` (`internal_api/models.py`).
- [x] 3.2 Widen `TerminalResultRequest.status` (`internal_api/models.py`) to `Literal["done", "failed", "cancelled"]`.
- [x] 3.3 Update `renew_assignment` route (`internal_api/api.py`) to populate `LeaseRenewalResponse.cancel_requested` from the repository's `renew_lease` result.
- [x] 3.4 Update `report_result` route (`internal_api/api.py`) to accept and forward the `"cancelled"` status to `record_task_result`.
- [x] 3.5 Add/extend internal API tests covering a renewal response surfacing `cancel_requested=True` and a `"cancelled"` terminal report being accepted and idempotent on repeat.
## 4. Host Agent collaborative stop
@@ -316,7 +316,7 @@ def create_internal_router(
summary=payload.progress.summary[:500],
updated_at=now,
)
renewal_status = pool.store.renew_lease(
renewal = pool.store.renew_lease(
task_id=task_id,
attempt=payload.attempt,
lease_id=payload.lease_id,
@@ -325,16 +325,17 @@ def create_internal_router(
now=now,
progress=progress_snapshot,
)
if renewal_status == "not_found":
if renewal.status == "not_found":
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND,
detail="assignment not found",
)
if renewal_status != "renewed":
if renewal.status != "renewed":
return _stale_lease_conflict("assignment lease is stale or expired")
return LeaseRenewalResponse(
status="renewed",
lease_expires_at=lease_expires_at,
cancel_requested=renewal.cancel_requested,
)
@router.post(
@@ -95,6 +95,7 @@ class LeaseRenewalRequest(BaseModel):
class LeaseRenewalResponse(BaseModel):
status: Literal["renewed"]
lease_expires_at: datetime
cancel_requested: bool = False
class TerminalResultRequest(BaseModel):
@@ -102,7 +103,7 @@ class TerminalResultRequest(BaseModel):
task_id: str = Field(min_length=1)
attempt: int = Field(ge=1)
lease_id: str = Field(min_length=1)
status: Literal["done", "failed"]
status: Literal["done", "failed", "cancelled"]
failure_reason: str | None = None
result: dict[str, Any] | None = None
+53
View File
@@ -473,10 +473,32 @@ def test_lease_renewal_extends_active_assignment(tmp_path) -> None:
assert response.status_code == 200
assert response.json()["status"] == "renewed"
assert response.json()["cancel_requested"] is False
renewed_expiry = datetime.fromisoformat(response.json()["lease_expires_at"])
assert renewed_expiry > original_time + timedelta(seconds=30)
def test_lease_renewal_surfaces_pending_cancellation(tmp_path) -> None:
client, pool = _build_client(tmp_path)
_seed_active_assignment(pool)
pool.store.request_task_cancellation("active-task", requested_at=datetime.now(UTC))
response = client.post(
"/internal/v1/hosts/host-a/assignments/active-task/renew",
headers={"Authorization": "Bearer token-a"},
json={
"host_id": "host-a",
"task_id": "active-task",
"attempt": 1,
"lease_id": "active-lease",
},
)
assert response.status_code == 200
assert response.json()["status"] == "renewed"
assert response.json()["cancel_requested"] is True
def test_stale_renewal_returns_typed_conflict(tmp_path) -> None:
client, pool = _build_client(tmp_path)
_seed_active_assignment(pool)
@@ -526,6 +548,37 @@ def test_terminal_result_is_idempotent_through_internal_api(tmp_path) -> None:
assert pool.store.get_task("active-task").status == "done" # type: ignore[union-attr]
def test_cancelled_terminal_result_is_accepted_and_idempotent(tmp_path) -> None:
client, pool = _build_client(tmp_path)
_seed_active_assignment(pool)
pool.store.request_task_cancellation("active-task", requested_at=datetime.now(UTC))
payload = {
"host_id": "host-a",
"task_id": "active-task",
"attempt": 1,
"lease_id": "active-lease",
"status": "cancelled",
"failure_reason": "cancellation requested by control plane",
}
first = client.post(
"/internal/v1/hosts/host-a/assignments/active-task/result",
headers={"Authorization": "Bearer token-a"},
json=payload,
)
repeated = client.post(
"/internal/v1/hosts/host-a/assignments/active-task/result",
headers={"Authorization": "Bearer token-a"},
json=payload,
)
assert first.status_code == 200
assert first.json()["status"] == "recorded"
assert repeated.status_code == 200
assert repeated.json()["status"] == "already_recorded"
assert pool.store.get_task("active-task").status == "cancelled" # type: ignore[union-attr]
def test_conflicting_repeated_result_returns_stale_lease_conflict(tmp_path) -> None:
client, pool = _build_client(tmp_path)
_seed_active_assignment(pool)