Files
aios/active-runtime/app/task_plane/scheduler.py
T

77 lines
2.6 KiB
Python

"""Task scheduler primitives."""
from __future__ import annotations
import time
from .errors import NotFoundError
from .capabilities import has_capabilities
from .models import WorkerClaim
from .store import TaskPlaneStore
class TaskScheduler:
def __init__(self, store: TaskPlaneStore):
self.store = store
def next_queued_task(self, worker_id: str):
worker = self.store.get_worker(worker_id)
tasks = sorted(
self.store.list_tasks(),
key=lambda task: (
-int(task.task_plan.metadata.get("priority", 0)),
task.created_at,
task.task_id,
),
)
for task in tasks:
if task.status not in {"CREATED", "QUEUED", "FAILED_RECOVERABLE"}:
continue
if task.task_plan.task_type == "worker.registry.audit":
continue
if task.status == "FAILED_RECOVERABLE" and not self.store.task_has_retryable_probe(
task.task_id
):
continue
if not has_capabilities(
worker.capabilities, task.task_plan.required_capabilities
):
continue
if any(
self.store.get_task(dependency).status != "COMPLETED"
for dependency in task.task_plan.dependencies
):
continue
if (
task.task_plan.data_classification == "credential-secret"
and worker.worker_type != "secure_file_transformer"
and "secure_file_transformer" not in worker.capabilities
):
continue
return task
return None
def schedule_for_worker(self, worker_id: str, lease_seconds: int = 15) -> WorkerClaim:
worker = self.store.get_worker(worker_id)
if worker.disabled:
from .errors import LockedError
raise LockedError("worker disabled")
if time.time() > worker.last_heartbeat + (
worker.heartbeat_interval_seconds * 3
):
from .errors import LockedError
raise LockedError("worker offline")
task = self.next_queued_task(worker_id)
if task is None:
raise NotFoundError("no queued tasks available")
claim = self.store.claim_task(
task.task_id,
worker_id,
worker.identity,
lease_seconds=lease_seconds,
expected_revision=task.revision,
operation_digest=task.task_plan.operation_digest(),
)
return claim