mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-11-16 00:10:42 +00:00
* fix(scheduler): preserve FIFO behind active same-thread runs * test(scheduler): cover launching FIFO blockers --------- Co-authored-by: mikamikasuki <211269698+mikamikasuki@users.noreply.github.com> Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
1569 lines
60 KiB
Python
1569 lines
60 KiB
Python
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import json
|
|
from datetime import UTC, datetime, timedelta
|
|
from pathlib import Path
|
|
from uuid import UUID
|
|
|
|
import httpx
|
|
import pytest
|
|
import pytest_asyncio
|
|
from _router_auth_helpers import make_authed_test_app
|
|
from sqlalchemy import func, select, update
|
|
|
|
from app.gateway.auth.models import User
|
|
from app.gateway.auth_disabled import AUTH_SOURCE_SESSION
|
|
from app.gateway.routers import scheduled_tasks
|
|
from app.scheduler.service import ScheduledTaskService
|
|
from deerflow.config.database_config import DatabaseConfig
|
|
from deerflow.persistence.engine import close_engine, get_session_factory, init_engine_from_config
|
|
from deerflow.persistence.run import RunRepository
|
|
from deerflow.persistence.scheduled_task_runs import ScheduledTaskRunRepository
|
|
from deerflow.persistence.scheduled_task_runs.model import ScheduledTaskRunRow
|
|
from deerflow.persistence.scheduled_tasks import ScheduledTaskRepository
|
|
from deerflow.persistence.scheduled_tasks.model import ScheduledTaskRow
|
|
from deerflow.runtime import ConflictError
|
|
|
|
pytestmark = pytest.mark.asyncio
|
|
|
|
|
|
async def _seed_reuse_task(task_repo: ScheduledTaskRepository, *, task_id: str, now: datetime) -> dict:
|
|
await task_repo.create(
|
|
task_id=task_id,
|
|
user_id="user-1",
|
|
thread_id="thread-1",
|
|
context_mode="reuse_thread",
|
|
assistant_id="lead_agent",
|
|
title="Follow up",
|
|
prompt="Continue from the existing conversation",
|
|
schedule_type="cron",
|
|
schedule_spec={"cron": "0 9 * * *"},
|
|
timezone="UTC",
|
|
next_run_at=now + timedelta(days=1),
|
|
)
|
|
task = await task_repo.get(task_id, user_id="user-1")
|
|
assert task is not None
|
|
return task
|
|
|
|
|
|
def _make_service(task_repo, run_repo, launch_run, *, queue_timeout_seconds: int = 3600):
|
|
return ScheduledTaskService(
|
|
task_repo=task_repo,
|
|
task_run_repo=run_repo,
|
|
launch_run=launch_run,
|
|
poll_interval_seconds=5,
|
|
lease_seconds=120,
|
|
max_concurrent_runs=3,
|
|
queue_timeout_seconds=queue_timeout_seconds,
|
|
)
|
|
|
|
|
|
async def test_busy_reuse_thread_is_queued_then_launched_on_a_later_poll(tmp_path):
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
try:
|
|
sf = get_session_factory()
|
|
assert sf is not None
|
|
task_repo = ScheduledTaskRepository(sf)
|
|
run_repo = ScheduledTaskRunRepository(sf)
|
|
now = datetime.now(UTC)
|
|
task = await _seed_reuse_task(task_repo, task_id="task-queue", now=now)
|
|
attempts = 0
|
|
|
|
async def launch_run(**kwargs):
|
|
nonlocal attempts
|
|
attempts += 1
|
|
if attempts == 1:
|
|
raise ConflictError("Thread thread-1 already has an active run")
|
|
return {"run_id": "run-queued", "thread_id": kwargs["thread_id"]}
|
|
|
|
service = _make_service(task_repo, run_repo, launch_run)
|
|
|
|
result = await service.dispatch_task(task, now=now, trigger="manual")
|
|
|
|
assert result["outcome"] == "queued"
|
|
rows = await run_repo.list_by_task("task-queue")
|
|
assert len(rows) == 1
|
|
assert rows[0]["status"] == "queued"
|
|
assert rows[0]["attempt_count"] == 1
|
|
|
|
await service.run_once(now=now + timedelta(seconds=5))
|
|
|
|
rows = await run_repo.list_by_task("task-queue")
|
|
assert rows[0]["status"] == "running"
|
|
assert rows[0]["run_id"] == "run-queued"
|
|
assert rows[0]["attempt_count"] == 2
|
|
assert attempts == 2
|
|
finally:
|
|
await close_engine()
|
|
|
|
|
|
async def test_paused_task_manual_run_waits_for_busy_thread_and_stays_paused(tmp_path):
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
try:
|
|
sf = get_session_factory()
|
|
assert sf is not None
|
|
task_repo = ScheduledTaskRepository(sf)
|
|
run_repo = ScheduledTaskRunRepository(sf)
|
|
now = datetime.now(UTC)
|
|
await _seed_reuse_task(task_repo, task_id="task-paused-manual", now=now)
|
|
await task_repo.update(
|
|
"task-paused-manual",
|
|
user_id="user-1",
|
|
updates={"status": "paused"},
|
|
)
|
|
task = await task_repo.get("task-paused-manual", user_id="user-1")
|
|
assert task is not None
|
|
attempts = 0
|
|
|
|
async def launch_run(**kwargs):
|
|
nonlocal attempts
|
|
attempts += 1
|
|
if attempts == 1:
|
|
raise ConflictError("Thread thread-1 already has an active run")
|
|
return {"run_id": "run-paused-manual", "thread_id": kwargs["thread_id"]}
|
|
|
|
service = _make_service(task_repo, run_repo, launch_run)
|
|
|
|
result = await service.dispatch_task(task, now=now, trigger="manual")
|
|
|
|
assert result["outcome"] == "queued"
|
|
assert (await run_repo.list_by_task(task["id"]))[0]["status"] == "queued"
|
|
assert (await task_repo.get(task["id"], user_id="user-1"))["status"] == "paused"
|
|
|
|
await service.run_once(now=now + timedelta(seconds=5))
|
|
|
|
row = (await run_repo.list_by_task(task["id"]))[0]
|
|
assert row["status"] == "running"
|
|
assert row["run_id"] == "run-paused-manual"
|
|
assert attempts == 2
|
|
assert (await task_repo.get(task["id"], user_id="user-1"))["status"] == "paused"
|
|
finally:
|
|
await close_engine()
|
|
|
|
|
|
async def test_queued_run_survives_single_instance_restart_sweep(tmp_path):
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
try:
|
|
sf = get_session_factory()
|
|
assert sf is not None
|
|
run_repo = ScheduledTaskRunRepository(sf)
|
|
now = datetime(2026, 8, 20, 9, 0, tzinfo=UTC)
|
|
await run_repo.create(
|
|
run_record_id="task-run-queued",
|
|
task_id="task-queued",
|
|
thread_id="thread-1",
|
|
scheduled_for=now,
|
|
trigger="scheduled",
|
|
status="queued",
|
|
)
|
|
|
|
swept = await run_repo.mark_stale_active_runs(error="gateway restarted")
|
|
|
|
assert swept == 0
|
|
assert (await run_repo.list_by_task("task-queued"))[0]["status"] == "queued"
|
|
finally:
|
|
await close_engine()
|
|
|
|
|
|
async def test_queued_once_task_survives_startup_and_is_drained_on_next_poll(tmp_path):
|
|
"""A newer queued occurrence survives recovery of an already-stuck parent.
|
|
|
|
The old success models a completion that committed before its parent update.
|
|
A real manual dispatch then leaves newer work queued after a transient
|
|
same-thread conflict. Startup must not let the old success finalize the
|
|
parent through the newer active row; the ordinary queue drain owns launch.
|
|
"""
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
try:
|
|
sf = get_session_factory()
|
|
assert sf is not None
|
|
task_repo = ScheduledTaskRepository(sf)
|
|
run_repo = ScheduledTaskRunRepository(sf)
|
|
now = datetime.now(UTC)
|
|
await task_repo.create(
|
|
task_id="task-queued-once",
|
|
user_id="user-1",
|
|
thread_id="thread-queued-once",
|
|
context_mode="reuse_thread",
|
|
assistant_id="lead_agent",
|
|
title="Queued once task",
|
|
prompt="Resume queued work",
|
|
schedule_type="once",
|
|
schedule_spec={"run_at": now.isoformat()},
|
|
timezone="UTC",
|
|
next_run_at=None,
|
|
)
|
|
await task_repo.update(
|
|
"task-queued-once",
|
|
user_id="user-1",
|
|
updates={"status": "running"},
|
|
)
|
|
await run_repo.create(
|
|
run_record_id="task-run-old-success",
|
|
task_id="task-queued-once",
|
|
thread_id="thread-queued-once",
|
|
scheduled_for=now - timedelta(minutes=1),
|
|
trigger="scheduled",
|
|
status="success",
|
|
)
|
|
task = await task_repo.get("task-queued-once", user_id="user-1")
|
|
assert task is not None
|
|
launched = []
|
|
|
|
async def launch_run(**kwargs):
|
|
launched.append(kwargs)
|
|
if len(launched) == 1:
|
|
raise ConflictError("Thread thread-queued-once already has an active run")
|
|
return {"run_id": "run-after-restart", "thread_id": kwargs["thread_id"]}
|
|
|
|
first_service = _make_service(task_repo, run_repo, launch_run)
|
|
queued = await first_service.dispatch_task(task, now=now, trigger="manual")
|
|
assert queued["outcome"] == "queued"
|
|
rows = await run_repo.list_by_task("task-queued-once")
|
|
assert [row["status"] for row in rows] == ["queued", "success"]
|
|
|
|
service = _make_service(task_repo, run_repo, launch_run)
|
|
|
|
async def parked_run_loop():
|
|
await service._stop.wait()
|
|
|
|
service._run_loop = parked_run_loop
|
|
await service.start()
|
|
try:
|
|
task = await task_repo.get_internal("task-queued-once")
|
|
rows = await run_repo.list_by_task("task-queued-once")
|
|
assert task is not None
|
|
assert task["status"] == "running"
|
|
assert rows[0]["status"] == "queued"
|
|
|
|
await service.run_once(now=now + timedelta(seconds=1))
|
|
|
|
task = await task_repo.get_internal("task-queued-once")
|
|
rows = await run_repo.list_by_task("task-queued-once")
|
|
assert task is not None
|
|
assert task["status"] == "running"
|
|
assert task["last_run_id"] == "run-after-restart"
|
|
assert rows[0]["status"] == "running"
|
|
assert rows[0]["run_id"] == "run-after-restart"
|
|
assert rows[1]["status"] == "success"
|
|
assert len(launched) == 2
|
|
finally:
|
|
await service.stop()
|
|
finally:
|
|
await close_engine()
|
|
|
|
|
|
async def test_only_one_worker_can_claim_a_queued_run(tmp_path):
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
try:
|
|
sf = get_session_factory()
|
|
assert sf is not None
|
|
run_repo_a = ScheduledTaskRunRepository(sf)
|
|
run_repo_b = ScheduledTaskRunRepository(sf)
|
|
now = datetime(2026, 8, 20, 9, 0, tzinfo=UTC)
|
|
await run_repo_a.create(
|
|
run_record_id="task-run-claim",
|
|
task_id="task-claim",
|
|
thread_id="thread-1",
|
|
scheduled_for=now,
|
|
trigger="scheduled",
|
|
status="queued",
|
|
)
|
|
|
|
claims = await asyncio.gather(
|
|
run_repo_a.claim_queued_run(
|
|
"task-run-claim",
|
|
lease_owner="worker-a",
|
|
now=now,
|
|
lease_seconds=120,
|
|
global_max_concurrent_runs=3,
|
|
),
|
|
run_repo_b.claim_queued_run(
|
|
"task-run-claim",
|
|
lease_owner="worker-b",
|
|
now=now,
|
|
lease_seconds=120,
|
|
global_max_concurrent_runs=3,
|
|
),
|
|
)
|
|
|
|
assert sum(claim is not None for claim in claims) == 1
|
|
row = (await run_repo_a.list_by_task("task-claim"))[0]
|
|
assert row["status"] == "launching"
|
|
assert row["attempt_count"] == 1
|
|
assert row["lease_owner"] in {"worker-a", "worker-b"}
|
|
finally:
|
|
await close_engine()
|
|
|
|
|
|
async def test_global_launch_budget_holds_when_distinct_rows_are_claimed_concurrently(tmp_path):
|
|
"""The global launch budget must survive claims racing on *distinct* rows.
|
|
|
|
``claim_queued_run`` counts executing rows and then promotes one row to
|
|
``launching``. Postgres serializes that pair with an advisory lock. SQLite
|
|
needs ``BEGIN IMMEDIATE`` for the same reason ``ThreadMetaRepository``
|
|
does: a deferred transaction does not reserve the writer until the UPDATE,
|
|
so every claimer reads the same stale count and overshoots
|
|
``max_concurrent_runs``.
|
|
|
|
Distinct rows are the load-bearing part. Two claims of the *same* row are
|
|
already safe via the ``status == "queued"`` CAS, which is what
|
|
``test_only_one_worker_can_claim_a_queued_run`` covers.
|
|
"""
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
try:
|
|
sf = get_session_factory()
|
|
assert sf is not None
|
|
run_repo = ScheduledTaskRunRepository(sf)
|
|
now = datetime(2026, 8, 20, 9, 0, tzinfo=UTC)
|
|
claimants = 8
|
|
for index in range(claimants):
|
|
await run_repo.create(
|
|
run_record_id=f"task-run-budget-{index}",
|
|
task_id=f"task-budget-{index}",
|
|
thread_id=f"thread-budget-{index}",
|
|
scheduled_for=now,
|
|
trigger="scheduled",
|
|
status="queued",
|
|
)
|
|
|
|
# Open every connection the claimers need up front. On a cold pool the
|
|
# per-connection PRAGMA setup staggers them enough to hide the race.
|
|
await asyncio.gather(*(run_repo.count_active_runs() for _ in range(claimants)))
|
|
|
|
# That warm-up is load-bearing, and it only works because the SQLite
|
|
# engine keeps pooled connections (init_engine_from_config builds it on
|
|
# SQLAlchemy's default AsyncAdaptedQueuePool, so `pool_size` of them
|
|
# survive this gather while the overflow is discarded). Under a
|
|
# non-pooling class such as NullPool every claimer would open its own
|
|
# connection, the PRAGMA setup would serialize them, and this test
|
|
# would pass against an unserialized claim instead of failing. Assert
|
|
# the reuse so that a pool change breaks this test loudly rather than
|
|
# quietly draining it of guard strength.
|
|
pool = sf.kw["bind"].sync_engine.pool
|
|
# A non-pooling class does not implement checkedin() at all, so treat a
|
|
# missing counter as "nothing was reused" and report it the same way.
|
|
pooled = pool.checkedin() if hasattr(pool, "checkedin") else 0
|
|
assert pooled >= 2, f"{type(pool).__name__} left {pooled} connections pooled after the warm-up; the claimers cannot overlap, so this test would pass against an unserialized claim"
|
|
|
|
claims = await asyncio.gather(
|
|
*(
|
|
run_repo.claim_queued_run(
|
|
f"task-run-budget-{index}",
|
|
lease_owner=f"worker-{index}",
|
|
now=now,
|
|
lease_seconds=120,
|
|
global_max_concurrent_runs=1,
|
|
)
|
|
for index in range(claimants)
|
|
)
|
|
)
|
|
|
|
assert sum(claim is not None for claim in claims) == 1
|
|
assert await run_repo.count_active_runs() == 1
|
|
finally:
|
|
await close_engine()
|
|
|
|
|
|
async def test_same_thread_queue_is_claimed_in_fifo_order(tmp_path):
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
try:
|
|
sf = get_session_factory()
|
|
assert sf is not None
|
|
run_repo_a = ScheduledTaskRunRepository(sf)
|
|
run_repo_b = ScheduledTaskRunRepository(sf)
|
|
now = datetime.now(UTC)
|
|
for run_id, task_id in (
|
|
("task-run-a", "task-a"),
|
|
("task-run-b", "task-b"),
|
|
):
|
|
await run_repo_a.create(
|
|
run_record_id=run_id,
|
|
task_id=task_id,
|
|
thread_id="shared-thread",
|
|
scheduled_for=now,
|
|
trigger="scheduled",
|
|
status="queued",
|
|
)
|
|
|
|
newer = await run_repo_b.claim_queued_run(
|
|
"task-run-b",
|
|
lease_owner="worker-b",
|
|
now=now,
|
|
lease_seconds=120,
|
|
global_max_concurrent_runs=3,
|
|
)
|
|
older = await run_repo_a.claim_queued_run(
|
|
"task-run-a",
|
|
lease_owner="worker-a",
|
|
now=now,
|
|
lease_seconds=120,
|
|
global_max_concurrent_runs=3,
|
|
)
|
|
|
|
assert newer is None
|
|
assert older is not None
|
|
assert await run_repo_b.list_queued_runs(limit=10) == []
|
|
assert (
|
|
await run_repo_b.claim_queued_run(
|
|
"task-run-b",
|
|
lease_owner="worker-b",
|
|
now=now,
|
|
lease_seconds=120,
|
|
global_max_concurrent_runs=3,
|
|
)
|
|
is None
|
|
)
|
|
finally:
|
|
await close_engine()
|
|
|
|
|
|
async def test_queue_drain_rotates_busy_thread_heads_without_breaking_fifo(tmp_path):
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
try:
|
|
sf = get_session_factory()
|
|
assert sf is not None
|
|
run_repo = ScheduledTaskRunRepository(sf)
|
|
now = datetime.now(UTC)
|
|
for run_id, task_id, thread_id in (
|
|
("task-run-busy-old", "task-busy-old", "busy-thread"),
|
|
("task-run-busy-new", "task-busy-new", "busy-thread"),
|
|
("task-run-ready", "task-ready", "ready-thread"),
|
|
):
|
|
await run_repo.create(
|
|
run_record_id=run_id,
|
|
task_id=task_id,
|
|
thread_id=thread_id,
|
|
scheduled_for=now,
|
|
trigger="scheduled",
|
|
status="queued",
|
|
)
|
|
|
|
claimed = await run_repo.claim_queued_run(
|
|
"task-run-busy-old",
|
|
lease_owner="worker-a",
|
|
now=now,
|
|
lease_seconds=120,
|
|
global_max_concurrent_runs=3,
|
|
)
|
|
assert claimed is not None
|
|
assert await run_repo.requeue_claimed_run(
|
|
"task-run-busy-old",
|
|
lease_owner="worker-a",
|
|
error="thread is busy",
|
|
)
|
|
|
|
candidates = await run_repo.list_queued_runs(limit=10)
|
|
|
|
# The untouched ready thread gets the next bounded-drain slot, and the
|
|
# newer row for the busy thread stays hidden behind its FIFO head.
|
|
assert [row["id"] for row in candidates] == [
|
|
"task-run-ready",
|
|
"task-run-busy-old",
|
|
]
|
|
finally:
|
|
await close_engine()
|
|
|
|
|
|
async def test_expired_launch_claim_is_requeued_but_waiting_timeout_fails(tmp_path):
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
try:
|
|
sf = get_session_factory()
|
|
assert sf is not None
|
|
run_repo = ScheduledTaskRunRepository(sf)
|
|
now = datetime.now(UTC)
|
|
await run_repo.create(
|
|
run_record_id="task-run-stale-claim",
|
|
task_id="task-stale-claim",
|
|
thread_id="thread-1",
|
|
scheduled_for=now - timedelta(minutes=5),
|
|
trigger="scheduled",
|
|
status="queued",
|
|
)
|
|
claimed = await run_repo.claim_queued_run(
|
|
"task-run-stale-claim",
|
|
lease_owner="dead-worker",
|
|
now=now,
|
|
lease_seconds=5,
|
|
global_max_concurrent_runs=3,
|
|
)
|
|
assert claimed is not None
|
|
|
|
reconciled = await run_repo.reconcile_active_runs(error="gateway lease expired", now=now + timedelta(seconds=6))
|
|
|
|
assert reconciled == 1
|
|
row = (await run_repo.list_by_task("task-stale-claim"))[0]
|
|
assert row["status"] == "queued"
|
|
assert row["lease_owner"] is None
|
|
|
|
expired = await run_repo.expire_queued_runs(
|
|
created_before=now + timedelta(seconds=7),
|
|
error="queue wait timeout exceeded",
|
|
now=now + timedelta(seconds=7),
|
|
)
|
|
assert [item["id"] for item in expired] == ["task-run-stale-claim"]
|
|
assert (await run_repo.list_by_task("task-stale-claim"))[0]["status"] == "failed"
|
|
finally:
|
|
await close_engine()
|
|
|
|
|
|
async def test_slow_launch_is_reassociated_after_lease_recovery(tmp_path):
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
try:
|
|
sf = get_session_factory()
|
|
assert sf is not None
|
|
task_repo = ScheduledTaskRepository(sf)
|
|
run_repo = ScheduledTaskRunRepository(sf)
|
|
now = datetime.now(UTC)
|
|
task = await _seed_reuse_task(task_repo, task_id="task-slow-launch", now=now)
|
|
queued = await run_repo.create(
|
|
run_record_id="task-run-slow-launch",
|
|
task_id=task["id"],
|
|
thread_id="thread-1",
|
|
scheduled_for=now,
|
|
trigger="manual",
|
|
status="queued",
|
|
)
|
|
launch_started = asyncio.Event()
|
|
allow_launch_return = asyncio.Event()
|
|
|
|
async def launch_run(**kwargs):
|
|
launch_started.set()
|
|
await allow_launch_return.wait()
|
|
return {"run_id": "run-slow-launch", "thread_id": kwargs["thread_id"]}
|
|
|
|
service = ScheduledTaskService(
|
|
task_repo=task_repo,
|
|
task_run_repo=run_repo,
|
|
launch_run=launch_run,
|
|
poll_interval_seconds=1,
|
|
lease_seconds=5,
|
|
max_concurrent_runs=3,
|
|
)
|
|
attempt = asyncio.create_task(service._attempt_queued_run(task, queued, now=now))
|
|
await launch_started.wait()
|
|
|
|
recovered = await run_repo.recover_expired_launch_claims(
|
|
error="launch lease expired",
|
|
now=now + timedelta(seconds=6),
|
|
)
|
|
assert recovered == 1
|
|
assert (await run_repo.list_by_task(task["id"]))[0]["status"] == "queued"
|
|
|
|
allow_launch_return.set()
|
|
result = await attempt
|
|
|
|
row = (await run_repo.list_by_task(task["id"]))[0]
|
|
assert result["outcome"] == "launched"
|
|
assert row["status"] == "running"
|
|
assert row["run_id"] == "run-slow-launch"
|
|
assert row["lease_owner"] is None
|
|
finally:
|
|
await close_engine()
|
|
|
|
|
|
async def test_failed_launch_releases_child_and_advances_parent_atomically(tmp_path):
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
try:
|
|
sf = get_session_factory()
|
|
assert sf is not None
|
|
task_repo = ScheduledTaskRepository(sf)
|
|
run_repo = ScheduledTaskRunRepository(sf)
|
|
now = datetime.now(UTC)
|
|
await task_repo.create(
|
|
task_id="task-failed-launch-atomic",
|
|
user_id="user-1",
|
|
thread_id="thread-1",
|
|
context_mode="reuse_thread",
|
|
assistant_id="lead_agent",
|
|
title="Atomic failure",
|
|
prompt="fail",
|
|
schedule_type="cron",
|
|
schedule_spec={"cron": "0 9 * * *"},
|
|
timezone="UTC",
|
|
next_run_at=now - timedelta(minutes=1),
|
|
)
|
|
await run_repo.create(
|
|
run_record_id="task-run-failed-launch-atomic",
|
|
task_id="task-failed-launch-atomic",
|
|
thread_id="thread-1",
|
|
scheduled_for=now,
|
|
trigger="scheduled",
|
|
status="queued",
|
|
)
|
|
assert (
|
|
await run_repo.claim_queued_run(
|
|
"task-run-failed-launch-atomic",
|
|
lease_owner="worker-a",
|
|
now=now,
|
|
lease_seconds=120,
|
|
global_max_concurrent_runs=3,
|
|
)
|
|
is not None
|
|
)
|
|
|
|
failed, peer_claims = await asyncio.gather(
|
|
run_repo.fail_launching_run(
|
|
"task-run-failed-launch-atomic",
|
|
task_id="task-failed-launch-atomic",
|
|
lease_owner="worker-a",
|
|
error="launch failed",
|
|
now=now,
|
|
),
|
|
task_repo.claim_due_tasks(
|
|
now=now,
|
|
lease_owner="worker-b",
|
|
lease_seconds=120,
|
|
limit=1,
|
|
),
|
|
)
|
|
|
|
assert failed is True
|
|
assert peer_claims == []
|
|
row = (await run_repo.list_by_task("task-failed-launch-atomic"))[0]
|
|
task = await task_repo.get("task-failed-launch-atomic", user_id="user-1")
|
|
assert row["status"] == "failed"
|
|
assert task is not None
|
|
assert datetime.fromisoformat(task["next_run_at"]) > now
|
|
assert task["lease_owner"] is None
|
|
assert task["last_error"] == "launch failed"
|
|
finally:
|
|
await close_engine()
|
|
|
|
|
|
async def test_failed_manual_launch_preserves_paused_next_run_at(tmp_path):
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
try:
|
|
sf = get_session_factory()
|
|
assert sf is not None
|
|
task_repo = ScheduledTaskRepository(sf)
|
|
run_repo = ScheduledTaskRunRepository(sf)
|
|
now = datetime.now(UTC)
|
|
next_run_at = now + timedelta(days=1)
|
|
await task_repo.create(
|
|
task_id="task-failed-manual-launch",
|
|
user_id="user-1",
|
|
thread_id="thread-1",
|
|
context_mode="reuse_thread",
|
|
assistant_id="lead_agent",
|
|
title="Manual launch failure",
|
|
prompt="fail",
|
|
schedule_type="cron",
|
|
schedule_spec={"cron": "0 9 * * *"},
|
|
timezone="UTC",
|
|
next_run_at=next_run_at,
|
|
)
|
|
await task_repo.update(
|
|
"task-failed-manual-launch",
|
|
user_id="user-1",
|
|
updates={"status": "paused"},
|
|
)
|
|
await run_repo.create(
|
|
run_record_id="task-run-failed-manual-launch",
|
|
task_id="task-failed-manual-launch",
|
|
thread_id="thread-1",
|
|
scheduled_for=now,
|
|
trigger="manual",
|
|
status="queued",
|
|
)
|
|
assert (
|
|
await run_repo.claim_queued_run(
|
|
"task-run-failed-manual-launch",
|
|
lease_owner="worker-a",
|
|
now=now,
|
|
lease_seconds=120,
|
|
global_max_concurrent_runs=3,
|
|
)
|
|
is not None
|
|
)
|
|
|
|
assert await run_repo.fail_launching_run(
|
|
"task-run-failed-manual-launch",
|
|
task_id="task-failed-manual-launch",
|
|
lease_owner="worker-a",
|
|
error="launch failed",
|
|
now=now,
|
|
)
|
|
|
|
row = (await run_repo.list_by_task("task-failed-manual-launch"))[0]
|
|
task = await task_repo.get("task-failed-manual-launch", user_id="user-1")
|
|
assert row["status"] == "failed"
|
|
assert task is not None
|
|
assert task["status"] == "paused"
|
|
assert task["next_run_at"] == next_run_at.isoformat()
|
|
finally:
|
|
await close_engine()
|
|
|
|
|
|
async def test_pause_atomically_cancels_waiting_run_but_rejects_launching_run(tmp_path):
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
try:
|
|
sf = get_session_factory()
|
|
assert sf is not None
|
|
task_repo = ScheduledTaskRepository(sf)
|
|
run_repo = ScheduledTaskRunRepository(sf)
|
|
now = datetime.now(UTC)
|
|
await _seed_reuse_task(task_repo, task_id="task-pause-queued", now=now)
|
|
await run_repo.create(
|
|
run_record_id="task-run-pause-queued",
|
|
task_id="task-pause-queued",
|
|
thread_id="thread-1",
|
|
scheduled_for=now,
|
|
trigger="scheduled",
|
|
status="queued",
|
|
)
|
|
|
|
result = await task_repo.pause_with_queue_cancellation(
|
|
"task-pause-queued",
|
|
user_id="user-1",
|
|
error="paused while queued",
|
|
now=now,
|
|
)
|
|
|
|
assert result == "paused"
|
|
assert (await task_repo.get("task-pause-queued", user_id="user-1"))["status"] == "paused"
|
|
assert (await run_repo.list_by_task("task-pause-queued"))[0]["status"] == "interrupted"
|
|
|
|
await _seed_reuse_task(task_repo, task_id="task-pause-launching", now=now)
|
|
await run_repo.create(
|
|
run_record_id="task-run-pause-launching",
|
|
task_id="task-pause-launching",
|
|
thread_id="thread-1",
|
|
scheduled_for=now,
|
|
trigger="scheduled",
|
|
status="queued",
|
|
)
|
|
await run_repo.claim_queued_run(
|
|
"task-run-pause-launching",
|
|
lease_owner="worker-a",
|
|
now=now,
|
|
lease_seconds=120,
|
|
global_max_concurrent_runs=3,
|
|
)
|
|
|
|
result = await task_repo.pause_with_queue_cancellation(
|
|
"task-pause-launching",
|
|
user_id="user-1",
|
|
error="paused while queued",
|
|
now=now,
|
|
)
|
|
|
|
assert result == "executing"
|
|
assert (await task_repo.get("task-pause-launching", user_id="user-1"))["status"] == "enabled"
|
|
assert (await run_repo.list_by_task("task-pause-launching"))[0]["status"] == "launching"
|
|
finally:
|
|
await close_engine()
|
|
|
|
|
|
async def test_manual_enqueue_cannot_unpause_a_task_that_cancels_its_waiting_run(tmp_path):
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
try:
|
|
sf = get_session_factory()
|
|
assert sf is not None
|
|
task_repo = ScheduledTaskRepository(sf)
|
|
|
|
class DelayedCreateRunRepository(ScheduledTaskRunRepository):
|
|
def __init__(self, session_factory):
|
|
super().__init__(session_factory)
|
|
self.created = asyncio.Event()
|
|
self.resume_dispatch = asyncio.Event()
|
|
|
|
async def create(self, **kwargs):
|
|
row = await super().create(**kwargs)
|
|
self.created.set()
|
|
await self.resume_dispatch.wait()
|
|
return row
|
|
|
|
run_repo = DelayedCreateRunRepository(sf)
|
|
now = datetime.now(UTC)
|
|
task = await _seed_reuse_task(task_repo, task_id="task-manual-pause-race", now=now)
|
|
|
|
async def launch_run(**_kwargs):
|
|
raise AssertionError("a queued occurrence cancelled by pause must not launch")
|
|
|
|
service = _make_service(task_repo, run_repo, launch_run)
|
|
dispatch = asyncio.create_task(service.dispatch_task(task, now=now, trigger="manual"))
|
|
await run_repo.created.wait()
|
|
|
|
pause_result = await task_repo.pause_with_queue_cancellation(
|
|
task["id"],
|
|
user_id="user-1",
|
|
error="paused while queued",
|
|
now=now,
|
|
)
|
|
run_repo.resume_dispatch.set()
|
|
result = await dispatch
|
|
|
|
assert pause_result == "paused"
|
|
assert result["outcome"] == "queued"
|
|
assert (await task_repo.get(task["id"], user_id="user-1"))["status"] == "paused"
|
|
assert (await run_repo.list_by_task(task["id"]))[0]["status"] == "interrupted"
|
|
finally:
|
|
await close_engine()
|
|
|
|
|
|
@pytest.mark.parametrize("action", ["pause", "delete"])
|
|
async def test_pause_or_delete_before_manual_admission_prevents_launch(tmp_path, action):
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
try:
|
|
sf = get_session_factory()
|
|
assert sf is not None
|
|
task_repo = ScheduledTaskRepository(sf)
|
|
|
|
class DelayedAdmissionRunRepository(ScheduledTaskRunRepository):
|
|
def __init__(self, session_factory):
|
|
super().__init__(session_factory)
|
|
self.before_insert = asyncio.Event()
|
|
self.resume_insert = asyncio.Event()
|
|
|
|
async def create(self, **kwargs):
|
|
self.before_insert.set()
|
|
await self.resume_insert.wait()
|
|
return await super().create(**kwargs)
|
|
|
|
run_repo = DelayedAdmissionRunRepository(sf)
|
|
now = datetime.now(UTC)
|
|
task = await _seed_reuse_task(task_repo, task_id=f"task-{action}-before-admission", now=now)
|
|
launches = []
|
|
|
|
async def launch_run(**kwargs):
|
|
launches.append(kwargs)
|
|
return {"run_id": f"run-{action}", "thread_id": kwargs["thread_id"]}
|
|
|
|
service = _make_service(task_repo, run_repo, launch_run)
|
|
dispatch = asyncio.create_task(service.dispatch_task(task, now=now, trigger="manual"))
|
|
await run_repo.before_insert.wait()
|
|
|
|
if action == "pause":
|
|
mutation = await task_repo.pause_with_queue_cancellation(
|
|
task["id"],
|
|
user_id="user-1",
|
|
error="paused before admission",
|
|
now=now + timedelta(seconds=1),
|
|
)
|
|
assert mutation == "paused"
|
|
else:
|
|
mutation = await task_repo.delete_with_queue_cancellation(
|
|
task["id"],
|
|
user_id="user-1",
|
|
error="deleted before admission",
|
|
now=now + timedelta(seconds=1),
|
|
)
|
|
assert mutation == "deleted"
|
|
|
|
run_repo.resume_insert.set()
|
|
result = await dispatch
|
|
|
|
assert launches == []
|
|
assert await run_repo.list_by_task(task["id"]) == []
|
|
if action == "pause":
|
|
assert result["outcome"] == "conflict"
|
|
assert (await task_repo.get(task["id"], user_id="user-1"))["status"] == "paused"
|
|
else:
|
|
assert result["outcome"] == "not_found"
|
|
assert await task_repo.get(task["id"], user_id="user-1") is None
|
|
finally:
|
|
await close_engine()
|
|
|
|
|
|
async def test_scheduled_queue_timeout_advances_cron_without_immediate_requeue(tmp_path):
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
try:
|
|
sf = get_session_factory()
|
|
assert sf is not None
|
|
task_repo = ScheduledTaskRepository(sf)
|
|
run_repo = ScheduledTaskRunRepository(sf)
|
|
admitted_at = datetime.now(UTC)
|
|
await task_repo.create(
|
|
task_id="task-timeout",
|
|
user_id="user-1",
|
|
thread_id="thread-1",
|
|
context_mode="reuse_thread",
|
|
assistant_id="lead_agent",
|
|
title="Timeout",
|
|
prompt="Prompt",
|
|
schedule_type="cron",
|
|
schedule_spec={"cron": "* * * * *"},
|
|
timezone="UTC",
|
|
next_run_at=admitted_at - timedelta(minutes=1),
|
|
)
|
|
await run_repo.create(
|
|
run_record_id="task-run-timeout",
|
|
task_id="task-timeout",
|
|
thread_id="thread-1",
|
|
scheduled_for=admitted_at,
|
|
trigger="scheduled",
|
|
status="queued",
|
|
)
|
|
|
|
async def launch_run(**_kwargs):
|
|
raise AssertionError("an expired queue row must not launch")
|
|
|
|
service = _make_service(
|
|
task_repo,
|
|
run_repo,
|
|
launch_run,
|
|
queue_timeout_seconds=60,
|
|
)
|
|
poll_at = admitted_at + timedelta(seconds=61)
|
|
|
|
await service.run_once(now=poll_at)
|
|
|
|
rows = await run_repo.list_by_task("task-timeout")
|
|
assert len(rows) == 1
|
|
assert rows[0]["status"] == "failed"
|
|
task = await task_repo.get("task-timeout", user_id="user-1")
|
|
assert task is not None
|
|
assert task["status"] == "enabled"
|
|
assert datetime.fromisoformat(task["next_run_at"]) > poll_at
|
|
assert task["last_error"] == "scheduled task queue wait timeout exceeded"
|
|
finally:
|
|
await close_engine()
|
|
|
|
|
|
@pytest.mark.parametrize("failure_mode", ["row", "scan"])
|
|
async def test_queue_expiry_failure_does_not_launch_expired_work(
|
|
sqlite_repos,
|
|
monkeypatch,
|
|
caplog,
|
|
failure_mode,
|
|
):
|
|
"""A failed timeout sweep may delay cleanup, but never admits old work."""
|
|
sf, task_repo, run_repo = sqlite_repos
|
|
poll_at = datetime.now(UTC).replace(microsecond=0)
|
|
await _owner_task(
|
|
task_repo,
|
|
"task-expired",
|
|
user_id=OWNER_A,
|
|
next_run_at=poll_at - timedelta(minutes=5),
|
|
)
|
|
await _owner_task(
|
|
task_repo,
|
|
"task-healthy-queued",
|
|
user_id=OWNER_A,
|
|
next_run_at=poll_at + timedelta(hours=1),
|
|
)
|
|
await _owner_task(
|
|
task_repo,
|
|
"task-due",
|
|
user_id=OWNER_A,
|
|
next_run_at=poll_at - timedelta(minutes=1),
|
|
)
|
|
await _owned_occurrence(task_repo, run_repo, "expired", user_id=OWNER_A, task_id="task-expired")
|
|
await _owned_occurrence(
|
|
task_repo,
|
|
run_repo,
|
|
"healthy-queued",
|
|
user_id=OWNER_A,
|
|
task_id="task-healthy-queued",
|
|
)
|
|
async with sf() as session:
|
|
await session.execute(update(ScheduledTaskRunRow).where(ScheduledTaskRunRow.id == "expired").values(created_at=poll_at - timedelta(hours=2)))
|
|
await session.execute(update(ScheduledTaskRunRow).where(ScheduledTaskRunRow.id == "healthy-queued").values(created_at=poll_at - timedelta(minutes=1)))
|
|
await session.commit()
|
|
|
|
if failure_mode == "scan":
|
|
|
|
async def fail_expiry_scan(**_kwargs):
|
|
raise RuntimeError("queue expiry scan failed")
|
|
|
|
monkeypatch.setattr(run_repo, "expire_queued_runs", fail_expiry_scan)
|
|
else:
|
|
original_lock_task = run_repo._lock_task
|
|
failed = False
|
|
|
|
async def fail_expired_row_once(session, task_id):
|
|
nonlocal failed
|
|
if task_id == "task-expired" and not failed:
|
|
failed = True
|
|
raise RuntimeError("queue expiry row failed")
|
|
return await original_lock_task(session, task_id)
|
|
|
|
monkeypatch.setattr(run_repo, "_lock_task", fail_expired_row_once)
|
|
|
|
launches: list[dict] = []
|
|
service = _capped_service(task_repo, run_repo, launches, max_concurrent_runs=3, queue_timeout_seconds=3600)
|
|
|
|
await service.run_once(now=poll_at)
|
|
|
|
launched_tasks = {item["metadata"]["scheduled_task_id"] for item in launches}
|
|
assert launched_tasks == {"task-healthy-queued", "task-due"}
|
|
expired = (await run_repo.list_by_task("task-expired"))[0]
|
|
assert (expired["status"], expired["error"], expired["attempt_count"]) == (
|
|
"queued",
|
|
None,
|
|
0,
|
|
)
|
|
assert "Failed to expire queued scheduled" in caplog.text
|
|
|
|
|
|
async def test_expired_queue_rows_do_not_consume_capped_candidates(
|
|
sqlite_repos,
|
|
monkeypatch,
|
|
):
|
|
"""Timeout failures must not let expired rows crowd healthy work out of the batch."""
|
|
sf, task_repo, run_repo = sqlite_repos
|
|
poll_at = datetime.now(UTC).replace(microsecond=0)
|
|
for task_id, row_id, created_at in (
|
|
("task-expired-1", "expired-1", poll_at - timedelta(hours=2)),
|
|
("task-expired-2", "expired-2", poll_at - timedelta(hours=2)),
|
|
("task-healthy", "healthy-queued", poll_at - timedelta(minutes=1)),
|
|
):
|
|
await _owner_task(
|
|
task_repo,
|
|
task_id,
|
|
user_id=OWNER_A,
|
|
next_run_at=poll_at + timedelta(hours=1),
|
|
)
|
|
await _owned_occurrence(
|
|
task_repo,
|
|
run_repo,
|
|
row_id,
|
|
user_id=OWNER_A,
|
|
task_id=task_id,
|
|
)
|
|
async with sf() as session:
|
|
await session.execute(update(ScheduledTaskRunRow).where(ScheduledTaskRunRow.id == row_id).values(created_at=created_at))
|
|
await session.commit()
|
|
|
|
async def fail_expiry_scan(**_kwargs):
|
|
raise RuntimeError("queue expiry scan failed")
|
|
|
|
monkeypatch.setattr(run_repo, "expire_queued_runs", fail_expiry_scan)
|
|
|
|
launches: list[dict] = []
|
|
service = _capped_service(
|
|
task_repo,
|
|
run_repo,
|
|
launches,
|
|
max_concurrent_runs=3,
|
|
max_concurrent_runs_per_user=2,
|
|
queue_timeout_seconds=3600,
|
|
)
|
|
|
|
for offset in range(3):
|
|
await service.run_once(now=poll_at + timedelta(seconds=offset))
|
|
|
|
assert [item["metadata"]["scheduled_task_id"] for item in launches] == ["task-healthy"]
|
|
for row_id in ("expired-1", "expired-2"):
|
|
row = (await run_repo.list_by_task(f"task-{row_id}"))[0]
|
|
assert (row["status"], row["attempt_count"]) == ("queued", 0)
|
|
healthy = (await run_repo.list_by_task("task-healthy"))[0]
|
|
assert healthy["status"] == "running"
|
|
|
|
|
|
async def test_expired_same_thread_head_does_not_hide_unexpired_candidate(sqlite_repos):
|
|
"""An expired FIFO head cannot block a newer row once it is due for timeout."""
|
|
sf, task_repo, run_repo = sqlite_repos
|
|
poll_at = datetime.now(UTC).replace(microsecond=0)
|
|
await _owned_occurrence(
|
|
task_repo,
|
|
run_repo,
|
|
"expired-head",
|
|
user_id=OWNER_A,
|
|
thread_id="shared-thread",
|
|
)
|
|
await _owned_occurrence(
|
|
task_repo,
|
|
run_repo,
|
|
"healthy-next",
|
|
user_id=OWNER_A,
|
|
thread_id="shared-thread",
|
|
)
|
|
async with sf() as session:
|
|
await session.execute(update(ScheduledTaskRunRow).where(ScheduledTaskRunRow.id == "expired-head").values(created_at=poll_at - timedelta(hours=2)))
|
|
await session.execute(update(ScheduledTaskRunRow).where(ScheduledTaskRunRow.id == "healthy-next").values(created_at=poll_at - timedelta(minutes=1)))
|
|
await session.commit()
|
|
|
|
batch = await run_repo.list_queued_runs(
|
|
limit=16,
|
|
created_after=poll_at - timedelta(hours=1),
|
|
)
|
|
|
|
assert [row["id"] for row in batch] == ["healthy-next"]
|
|
|
|
|
|
async def test_manual_queue_timeout_preserves_serialized_next_run_at(tmp_path):
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
try:
|
|
sf = get_session_factory()
|
|
assert sf is not None
|
|
task_repo = ScheduledTaskRepository(sf)
|
|
run_repo = ScheduledTaskRunRepository(sf)
|
|
admitted_at = datetime.now(UTC)
|
|
next_run_at = admitted_at + timedelta(days=1)
|
|
await task_repo.create(
|
|
task_id="task-manual-timeout",
|
|
user_id="user-1",
|
|
thread_id="thread-1",
|
|
context_mode="reuse_thread",
|
|
assistant_id="lead_agent",
|
|
title="Manual timeout",
|
|
prompt="Prompt",
|
|
schedule_type="cron",
|
|
schedule_spec={"cron": "0 9 * * *"},
|
|
timezone="UTC",
|
|
next_run_at=next_run_at,
|
|
)
|
|
await run_repo.create(
|
|
run_record_id="task-run-manual-timeout",
|
|
task_id="task-manual-timeout",
|
|
thread_id="thread-1",
|
|
scheduled_for=admitted_at,
|
|
trigger="manual",
|
|
status="queued",
|
|
)
|
|
|
|
async def launch_run(**_kwargs):
|
|
raise AssertionError("an expired queue row must not launch")
|
|
|
|
service = _make_service(
|
|
task_repo,
|
|
run_repo,
|
|
launch_run,
|
|
queue_timeout_seconds=60,
|
|
)
|
|
|
|
await service.run_once(now=admitted_at + timedelta(seconds=61))
|
|
|
|
row = (await run_repo.list_by_task("task-manual-timeout"))[0]
|
|
assert row["status"] == "failed"
|
|
task = await task_repo.get("task-manual-timeout", user_id="user-1")
|
|
assert task is not None
|
|
assert task["status"] == "enabled"
|
|
assert task["next_run_at"] == next_run_at.isoformat()
|
|
assert task["last_error"] == "scheduled task queue wait timeout exceeded"
|
|
finally:
|
|
await close_engine()
|
|
|
|
|
|
async def test_expired_launch_claim_attaches_existing_run_instead_of_relaunching(tmp_path):
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
try:
|
|
sf = get_session_factory()
|
|
assert sf is not None
|
|
task_repo = ScheduledTaskRepository(sf)
|
|
run_repo = ScheduledTaskRunRepository(sf)
|
|
durable_runs = RunRepository(sf)
|
|
now = datetime.now(UTC)
|
|
launched_at = now + timedelta(seconds=1)
|
|
await _seed_reuse_task(task_repo, task_id="task-attached", now=now)
|
|
await run_repo.create(
|
|
run_record_id="task-run-attached",
|
|
task_id="task-attached",
|
|
thread_id="thread-1",
|
|
scheduled_for=now,
|
|
trigger="scheduled",
|
|
status="queued",
|
|
)
|
|
assert (
|
|
await run_repo.claim_queued_run(
|
|
"task-run-attached",
|
|
lease_owner="worker-a",
|
|
now=now,
|
|
lease_seconds=5,
|
|
global_max_concurrent_runs=3,
|
|
)
|
|
is not None
|
|
)
|
|
assert await run_repo.requeue_claimed_run(
|
|
"task-run-attached",
|
|
lease_owner="worker-a",
|
|
error="earlier overlap",
|
|
)
|
|
assert (
|
|
await run_repo.claim_queued_run(
|
|
"task-run-attached",
|
|
lease_owner="worker-a",
|
|
now=now,
|
|
lease_seconds=5,
|
|
global_max_concurrent_runs=3,
|
|
)
|
|
is not None
|
|
)
|
|
await durable_runs.put(
|
|
"run-attached",
|
|
thread_id="thread-1",
|
|
user_id="user-1",
|
|
status="running",
|
|
metadata={
|
|
"scheduled_task_id": "task-attached",
|
|
"scheduled_task_run_id": "task-run-attached",
|
|
},
|
|
created_at=launched_at.isoformat(),
|
|
)
|
|
|
|
recovered = await run_repo.recover_expired_launch_claims(
|
|
error="launch lease expired",
|
|
now=now + timedelta(seconds=6),
|
|
)
|
|
|
|
assert recovered == 1
|
|
row = (await run_repo.list_by_task("task-attached"))[0]
|
|
assert row["status"] == "running"
|
|
assert row["run_id"] == "run-attached"
|
|
assert row["lease_owner"] is None
|
|
assert row["started_at"] == launched_at.isoformat()
|
|
assert row["error"] is None
|
|
task = await task_repo.get("task-attached", user_id="user-1")
|
|
assert task is not None
|
|
assert task["last_run_id"] == "run-attached"
|
|
assert task["run_count"] == 1
|
|
|
|
# If the original launch coroutine resumes after recovery, its normal
|
|
# parent update must be idempotent for the same durable run id.
|
|
await task_repo.update_after_launch(
|
|
"task-attached",
|
|
status="enabled",
|
|
next_run_at=datetime.fromisoformat(task["next_run_at"]),
|
|
last_run_at=now,
|
|
last_run_id="run-attached",
|
|
last_thread_id="thread-1",
|
|
last_error=None,
|
|
increment_run_count=True,
|
|
)
|
|
assert (await task_repo.get("task-attached", user_id="user-1"))["run_count"] == 1
|
|
finally:
|
|
await close_engine()
|
|
|
|
|
|
# --- PR2 M1: per-owner run cap and fair queue selection ------------------------------------
|
|
|
|
_QUEUE_CONTRACT = json.loads((Path(__file__).resolve().parents[2] / "contracts" / "scheduled_goal_notes_contract.json").read_text(encoding="utf-8"))
|
|
_OWNER_A = User(id=UUID("aaaaaaaa-0000-4000-8000-000000000001"), email="owner-a@example.com", password_hash="unused", system_role="user")
|
|
OWNER_A = str(_OWNER_A.id)
|
|
OWNER_B = "bbbbbbbb-0000-4000-8000-000000000002"
|
|
|
|
|
|
async def _owner_task(task_repo: ScheduledTaskRepository, task_id: str, *, user_id: str, next_run_at: datetime | None = None) -> dict:
|
|
"""A page-created per-minute task with a fresh thread for every run."""
|
|
return await task_repo.create(
|
|
task_id=task_id,
|
|
user_id=user_id,
|
|
thread_id=None,
|
|
context_mode="fresh_thread_per_run",
|
|
assistant_id="lead_agent",
|
|
title=task_id,
|
|
prompt="Check the list",
|
|
schedule_type="cron",
|
|
schedule_spec={"cron": "* * * * *"},
|
|
timezone="UTC",
|
|
next_run_at=next_run_at,
|
|
)
|
|
|
|
|
|
async def _owned_occurrence(
|
|
task_repo: ScheduledTaskRepository,
|
|
run_repo: ScheduledTaskRunRepository,
|
|
row_id: str,
|
|
*,
|
|
user_id: str,
|
|
status: str = "queued",
|
|
thread_id: str | None = None,
|
|
task_id: str | None = None,
|
|
) -> dict:
|
|
"""One occurrence on its own task (one active occurrence per task)."""
|
|
task_id = task_id or f"task-{row_id}"
|
|
if await task_repo.get_internal(task_id) is None:
|
|
await _owner_task(task_repo, task_id, user_id=user_id)
|
|
return await run_repo.create(
|
|
run_record_id=row_id,
|
|
task_id=task_id,
|
|
thread_id=thread_id or f"thread-{row_id}",
|
|
scheduled_for=datetime.now(UTC),
|
|
trigger="scheduled",
|
|
status=status,
|
|
)
|
|
|
|
|
|
async def _executing_by_owner(sf, owner: str) -> int:
|
|
async with sf() as session:
|
|
return int(
|
|
await session.scalar(
|
|
select(func.count())
|
|
.select_from(ScheduledTaskRunRow)
|
|
.join(ScheduledTaskRow, ScheduledTaskRow.id == ScheduledTaskRunRow.task_id)
|
|
.where(ScheduledTaskRunRow.status.in_(("launching", "running")), ScheduledTaskRow.user_id == owner)
|
|
)
|
|
or 0
|
|
)
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
async def sqlite_repos(tmp_path):
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
sf = get_session_factory()
|
|
assert sf is not None
|
|
try:
|
|
yield sf, ScheduledTaskRepository(sf), ScheduledTaskRunRepository(sf)
|
|
finally:
|
|
await close_engine()
|
|
|
|
|
|
def _capped_service(task_repo, run_repo, launches: list[dict], **limits) -> ScheduledTaskService:
|
|
"""The real service with the given caps; every launch is recorded in ``launches``."""
|
|
|
|
async def launch_run(**kwargs):
|
|
launches.append(kwargs)
|
|
return {"run_id": f"run-{len(launches)}", "thread_id": kwargs["thread_id"]}
|
|
|
|
return ScheduledTaskService(task_repo=task_repo, task_run_repo=run_repo, launch_run=launch_run, poll_interval_seconds=5, lease_seconds=120, **limits)
|
|
|
|
|
|
async def test_fair_batch_includes_other_owner_when_one_owner_is_at_cap(sqlite_repos):
|
|
_sf, task_repo, run_repo = sqlite_repos
|
|
for index in range(2):
|
|
await _owned_occurrence(task_repo, run_repo, f"a-running-{index}", user_id=OWNER_A, status="running")
|
|
for index in range(50):
|
|
await _owned_occurrence(task_repo, run_repo, f"a-queued-{index:02d}", user_id=OWNER_A)
|
|
await _owned_occurrence(task_repo, run_repo, "b-queued", user_id=OWNER_B)
|
|
|
|
batch = await run_repo.list_queued_runs(limit=16, per_user_max_concurrent_runs=2)
|
|
|
|
# A is at its cap, so its 50 waiting rows drop out before the limit.
|
|
assert [row["id"] for row in batch] == ["b-queued"]
|
|
|
|
|
|
async def test_fair_batch_interleaves_owners_without_cap(sqlite_repos):
|
|
_sf, task_repo, run_repo = sqlite_repos
|
|
for index in range(50):
|
|
await _owned_occurrence(task_repo, run_repo, f"a-queued-{index:02d}", user_id=OWNER_A)
|
|
await _owned_occurrence(task_repo, run_repo, "b-queued", user_id=OWNER_B)
|
|
|
|
batch = [row["id"] for row in await run_repo.list_queued_runs(limit=16)]
|
|
|
|
# Without a cap the batch is still fair: B's only row, created last,
|
|
# comes right after A's head instead of after 50 older A rows.
|
|
assert len(batch) == 16
|
|
assert batch.index("b-queued") <= 1
|
|
assert batch[0] == "a-queued-00"
|
|
# Within an owner the order is unchanged (attempt_count, created_at, id).
|
|
assert [row_id for row_id in batch if row_id.startswith("a-")] == [f"a-queued-{index:02d}" for index in range(15)]
|
|
|
|
|
|
async def test_owner_rank_respects_remaining_capacity(sqlite_repos):
|
|
_sf, task_repo, run_repo = sqlite_repos
|
|
await _owned_occurrence(task_repo, run_repo, "a-running", user_id=OWNER_A, status="running")
|
|
for index in range(5):
|
|
await _owned_occurrence(task_repo, run_repo, f"a-queued-{index}", user_id=OWNER_A)
|
|
await _owned_occurrence(task_repo, run_repo, "b-queued", user_id=OWNER_B)
|
|
|
|
batch = [row["id"] for row in await run_repo.list_queued_runs(limit=16, per_user_max_concurrent_runs=3)]
|
|
|
|
assert [row_id for row_id in batch if row_id.startswith("a-")] == ["a-queued-0", "a-queued-1"]
|
|
assert "b-queued" in batch
|
|
|
|
|
|
@pytest.mark.parametrize("cap", [0, 2])
|
|
async def test_fair_batch_keeps_same_thread_fifo(sqlite_repos, cap):
|
|
_sf, task_repo, run_repo = sqlite_repos
|
|
await _owned_occurrence(task_repo, run_repo, "a-older", user_id=OWNER_A, thread_id="reuse-thread")
|
|
await _owned_occurrence(task_repo, run_repo, "a-newer", user_id=OWNER_A, thread_id="reuse-thread")
|
|
|
|
batch = [row["id"] for row in await run_repo.list_queued_runs(limit=16, per_user_max_concurrent_runs=cap)]
|
|
|
|
assert batch == ["a-older"]
|
|
|
|
|
|
@pytest.mark.parametrize("status", ["running", "launching"])
|
|
async def test_queue_age_cutoff_keeps_active_same_thread_fifo_blocker(sqlite_repos, status):
|
|
sf, task_repo, run_repo = sqlite_repos
|
|
now = datetime.now(UTC)
|
|
await _owned_occurrence(
|
|
task_repo,
|
|
run_repo,
|
|
"a-old-active",
|
|
user_id=OWNER_A,
|
|
status=status,
|
|
thread_id="reuse-thread",
|
|
)
|
|
await _owned_occurrence(
|
|
task_repo,
|
|
run_repo,
|
|
"a-blocked-queued",
|
|
user_id=OWNER_A,
|
|
thread_id="reuse-thread",
|
|
)
|
|
await _owned_occurrence(
|
|
task_repo,
|
|
run_repo,
|
|
"a-healthy-queued",
|
|
user_id=OWNER_A,
|
|
thread_id="other-thread",
|
|
)
|
|
|
|
# The timeout applies to waiting rows, not to an older active execution.
|
|
async with sf() as session:
|
|
blocker = await session.get(ScheduledTaskRunRow, "a-old-active")
|
|
assert blocker is not None
|
|
blocker.created_at = now - timedelta(hours=1)
|
|
await session.commit()
|
|
|
|
cutoff = now - timedelta(minutes=5)
|
|
batch = await run_repo.list_queued_runs(
|
|
limit=16,
|
|
per_user_max_concurrent_runs=2,
|
|
created_after=cutoff,
|
|
)
|
|
|
|
# The active run still blocks its thread. Its newer queued row must not
|
|
# consume the owner's one remaining slot ahead of unrelated healthy work.
|
|
assert [row["id"] for row in batch] == ["a-healthy-queued"]
|
|
|
|
|
|
async def test_orphan_queued_row_is_still_drained(sqlite_repos):
|
|
_sf, task_repo, run_repo = sqlite_repos
|
|
await _owned_occurrence(task_repo, run_repo, "a-running", user_id=OWNER_A, status="running")
|
|
# The parent task is gone (deleted while the row waited): no owner.
|
|
await run_repo.create(run_record_id="orphan", task_id="task-deleted", thread_id="thread-orphan", scheduled_for=datetime.now(UTC), trigger="scheduled", status="queued")
|
|
|
|
assert [row["id"] for row in await run_repo.list_queued_runs(limit=16, per_user_max_concurrent_runs=1)] == ["orphan"]
|
|
|
|
launches: list[dict] = []
|
|
service = _capped_service(task_repo, run_repo, launches, max_concurrent_runs=3, max_concurrent_runs_per_user=1)
|
|
await service.run_once(now=datetime.now(UTC))
|
|
|
|
row = (await run_repo.list_by_task("task-deleted"))[0]
|
|
assert (row["status"], row["error"]) == ("interrupted", _QUEUE_CONTRACT["host_run_errors"]["deleted_while_queued"])
|
|
assert launches == []
|
|
|
|
|
|
async def test_claim_rejects_owner_at_cap_but_admits_other_owner(sqlite_repos):
|
|
_sf, task_repo, run_repo = sqlite_repos
|
|
now = datetime.now(UTC)
|
|
await _owned_occurrence(task_repo, run_repo, "a-running", user_id=OWNER_A, status="running")
|
|
await _owned_occurrence(task_repo, run_repo, "a-queued", user_id=OWNER_A)
|
|
await _owned_occurrence(task_repo, run_repo, "b-queued", user_id=OWNER_B)
|
|
claim = {"now": now, "lease_seconds": 120, "global_max_concurrent_runs": 3, "per_user_max_concurrent_runs": 1}
|
|
|
|
assert await run_repo.claim_queued_run("a-queued", lease_owner="worker", **claim) is None
|
|
assert (await run_repo.list_by_task("task-a-queued"))[0]["status"] == "queued"
|
|
assert (await run_repo.list_by_task("task-a-queued"))[0]["attempt_count"] == 0
|
|
|
|
claimed = await run_repo.claim_queued_run("b-queued", lease_owner="worker", **claim)
|
|
assert claimed is not None and claimed["status"] == "launching"
|
|
|
|
# Cap 0 keeps today's behavior: only the global budget applies.
|
|
assert await run_repo.claim_queued_run("a-queued", lease_owner="worker", **{**claim, "per_user_max_concurrent_runs": 0}) is not None
|
|
|
|
|
|
async def test_effective_owner_cap_is_bounded_by_global_cap(sqlite_repos):
|
|
sf, task_repo, run_repo = sqlite_repos
|
|
for index in range(3):
|
|
await _owned_occurrence(task_repo, run_repo, f"a-queued-{index}", user_id=OWNER_A)
|
|
launches: list[dict] = []
|
|
service = _capped_service(task_repo, run_repo, launches, max_concurrent_runs=1, max_concurrent_runs_per_user=2)
|
|
|
|
assert service._max_concurrent_runs_per_user == 1
|
|
await service.run_once(now=datetime.now(UTC))
|
|
|
|
assert len(launches) == 1
|
|
assert await run_repo.count_active_runs() == 1
|
|
assert await _executing_by_owner(sf, OWNER_A) == 1
|
|
# The drain asks only for as many A rows as A may still start.
|
|
assert await run_repo.list_queued_runs(limit=16, per_user_max_concurrent_runs=service._max_concurrent_runs_per_user) == []
|
|
|
|
|
|
async def test_capped_owner_queue_expiry_writes_contract_queue_timeout_note(sqlite_repos):
|
|
sf, task_repo, run_repo = sqlite_repos
|
|
await _owned_occurrence(task_repo, run_repo, "a-running", user_id=OWNER_A, status="running")
|
|
await _owned_occurrence(task_repo, run_repo, "a-waiting", user_id=OWNER_A)
|
|
launches: list[dict] = []
|
|
service = _capped_service(task_repo, run_repo, launches, max_concurrent_runs=3, max_concurrent_runs_per_user=1, queue_timeout_seconds=60)
|
|
|
|
# While A holds its only slot, the waiting row is not launched.
|
|
await service.run_once(now=datetime.now(UTC))
|
|
assert launches == []
|
|
assert (await run_repo.list_by_task("task-a-waiting"))[0]["status"] == "queued"
|
|
|
|
await service.run_once(now=datetime.now(UTC) + timedelta(seconds=61))
|
|
|
|
expired = (await run_repo.list_by_task("task-a-waiting"))[0]
|
|
assert (expired["status"], expired["run_id"]) == ("failed", None)
|
|
assert expired["error"] == _QUEUE_CONTRACT["host_run_errors"]["queue_timeout"]
|
|
assert launches == []
|
|
|
|
# The runs route hands that note to the page unchanged, so PR1's
|
|
# runErrors.queueTimeout mapping ("waited too long") applies.
|
|
app = make_authed_test_app(user_factory=lambda: _OWNER_A, bind_current_user=True)
|
|
|
|
@app.middleware("http")
|
|
async def mark_session_source(request, call_next):
|
|
request.state.auth_source = AUTH_SOURCE_SESSION
|
|
return await call_next(request)
|
|
|
|
app.state.scheduled_task_repo = task_repo
|
|
app.state.scheduled_task_run_repo = run_repo
|
|
app.include_router(scheduled_tasks.router)
|
|
async with httpx.AsyncClient(transport=httpx.ASGITransport(app=app), base_url="http://queue.test") as client:
|
|
response = await client.get("/api/scheduled-tasks/task-a-waiting/runs")
|
|
assert response.status_code == 200, response.text
|
|
assert [(row["status"], row["run_id"], row["error"]) for row in response.json()] == [("failed", None, _QUEUE_CONTRACT["host_run_errors"]["queue_timeout"])]
|
|
|
|
|
|
async def test_service_drain_launches_other_owner_first(sqlite_repos):
|
|
"""Two poll cycles: A's backlog never takes B's slot.
|
|
|
|
``claim_due_tasks`` admits ``max_concurrent_runs`` tasks per poll ordered
|
|
by ``next_run_at, id``, so A's five tasks (due first) fill cycle 1. Each
|
|
admitted occurrence is offered a launch at once; the per-owner cap lets
|
|
one A row start and leaves the other two queued. In cycle 2 the drain
|
|
must not start any A row, and B's occurrence (due one second later)
|
|
launches although four older A rows are queued ahead of it.
|
|
"""
|
|
sf, task_repo, run_repo = sqlite_repos
|
|
t0 = datetime.now(UTC).replace(microsecond=0) - timedelta(minutes=5)
|
|
for index in range(5):
|
|
await _owner_task(task_repo, f"task-a-{index}", user_id=OWNER_A, next_run_at=t0)
|
|
await _owner_task(task_repo, "task-b", user_id=OWNER_B, next_run_at=t0 + timedelta(seconds=1))
|
|
launches: list[dict] = []
|
|
service = _capped_service(task_repo, run_repo, launches, max_concurrent_runs=3, max_concurrent_runs_per_user=1)
|
|
|
|
b_cycle = None
|
|
for cycle in range(1, 5):
|
|
await service.run_once(now=t0 + timedelta(seconds=cycle))
|
|
assert await _executing_by_owner(sf, OWNER_A) <= 1
|
|
b_rows = await run_repo.list_by_task("task-b")
|
|
if b_rows:
|
|
b_cycle = cycle
|
|
break
|
|
|
|
assert b_cycle == 2
|
|
assert b_rows[0]["status"] in {"launching", "running"}
|
|
assert await _executing_by_owner(sf, OWNER_A) == 1
|
|
queued_a = [row for index in range(5) for row in await run_repo.list_by_task(f"task-a-{index}") if row["status"] == "queued"]
|
|
assert len(queued_a) == 4
|
|
|
|
|
|
async def test_service_drain_launches_other_owner_from_a_seeded_queue(sqlite_repos):
|
|
"""A seeded backlog larger than the drain batch cannot hide B's row."""
|
|
sf, task_repo, run_repo = sqlite_repos
|
|
for index in range(20):
|
|
await _owned_occurrence(task_repo, run_repo, f"a-queued-{index:02d}", user_id=OWNER_A)
|
|
await _owned_occurrence(task_repo, run_repo, "b-queued", user_id=OWNER_B)
|
|
launches: list[dict] = []
|
|
service = _capped_service(task_repo, run_repo, launches, max_concurrent_runs=3, max_concurrent_runs_per_user=1)
|
|
|
|
await service.run_once(now=datetime.now(UTC))
|
|
|
|
# The batch limit is max(16, 3 * 4) = 16 < 20 A rows: an unfair batch
|
|
# would hold only A rows. The fair one starts A's head and B's row.
|
|
assert (await run_repo.list_by_task("task-b-queued"))[0]["status"] == "running"
|
|
assert (await run_repo.list_by_task("task-a-queued-00"))[0]["status"] == "running"
|
|
assert await _executing_by_owner(sf, OWNER_A) == 1
|
|
assert len(launches) == 2
|
|
|
|
|
|
@pytest.mark.parametrize("dialect_name", ["postgresql", "sqlite"])
|
|
async def test_fair_queue_statement_compiles_for_both_dialects(dialect_name):
|
|
"""The fair drain is plain SQLAlchemy Core (no raw text) on both dialects."""
|
|
from sqlalchemy.dialects import postgresql, sqlite
|
|
|
|
dialect = {"postgresql": postgresql.dialect(), "sqlite": sqlite.dialect()}[dialect_name]
|
|
sql = str(ScheduledTaskRunRepository._fair_queue_statement(limit=16, per_user_max_concurrent_runs=2).compile(dialect=dialect)).lower()
|
|
|
|
assert "row_number() over (partition by" in sql
|
|
assert "group by" in sql and "not (exists" in sql
|
|
assert "limit" in sql
|