mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-07-09 16:08:31 +00:00
* feat: add scheduled tasks MVP
* fix: harden scheduled task execution semantics
* feat(scheduled-tasks): preset-driven schedule form with timezone and live preview
Replace the raw cron input with a preset Select (hourly/daily/weekly/monthly/custom)
plus structured inputs (time picker, weekday toggles, day-of-month), datetime-local
for one-time tasks, a timezone selector defaulting to the browser timezone, and a
live human-readable preview. Reuses one ScheduledTaskScheduleInput for create and
edit; backend contract unchanged; zero new deps (pure Intl + DST-safe offset helpers).
* feat(scheduled-tasks): full-page i18n + recipe templates + E2E locale pin
Localize the rest of the scheduled-tasks page (filters, detail pane, actions,
edit form, run list, enum values) via t.scheduledTasks.* in en/zh. Add four
built-in recipe templates (GitHub Trending, news digest, issue triage, weekly
report) exposed as a chip row that pre-fills title + prompt + schedule. Pin
Playwright locale to en-US so E2E selectors stay stable against i18n. No backend
change, no new deps.
* fix(scheduled-tasks): idempotent 0003 migration, update head constants, future-date once test
Merge with main surfaced three CI failures:
- 0003_scheduled_tasks create_table collided with legacy test seeds that
build from full metadata; guard with inspector.has_table so the revision
no-ops when the table already exists (0004/0005 are already idempotent via
_helpers.py).
- persistence bootstrap concurrency/regression tests pinned HEAD to main's
0002_runs_token_usage; bump to the new head 0005_scheduled_task_thread_nullable.
- once-task router test used a fixed past run_at and tripped the
must-be-in-the-future validation; use a future date.
* address review: ok-check, 502 for trigger failure, mock fields, migration filename, doc fences
- fetchThreadScheduledTasks now checks response.ok like the other fetchers.
- trigger endpoint returns 502 (not 409) when dispatch fails outright, so
clients can distinguish a real conflict from a server-side failure.
- E2E mock normalizes scheduled-task objects with context_mode/last_thread_id
and nullable thread_id, matching the backend contract the UI renders against.
- Rename 0002_scheduled_tasks.py -> 0003_scheduled_tasks.py to match its
revision id (file was renamed in spirit already; filename now follows).
- CONFIGURATION.md: close the Tool Groups yaml fence and drop the stray fence
after the Scheduler notes so the sections render correctly.
* fix(scheduled-tasks): harden lease, poller, config, and frontend UX after review
* fix(scheduled-tasks): harden run lifecycle, overlap skip, non_interactive gating, and DST conversion after review
- defer a once task's terminal status to the run-completion hook; the task
stays running until the real outcome, and a startup sweep cancels once
tasks orphaned by a crash (launch-time 'completed' could stick forever)
- record interrupted runs as a distinct 'interrupted' run status with a
readable message; an interrupted once task ends 'cancelled', not 'failed'
- enforce overlap_policy=skip for fresh_thread_per_run via an active-run
pre-check (same-thread ConflictError can never fire across fresh threads)
- protect terminal run statuses from the late launch-path 'running' write
- honor context.non_interactive only for internally-authenticated callers;
arbitrary clients can no longer strip ask_clarification
- fix DST-stale timezone offset in zonedLocalToUtcIso by re-deriving the
offset at the resolved instant (once tasks fired an hour late around
spring-forward and the create->edit round-trip diverged)
- drop dead ScheduledTaskRunRepository.update_by_run_id; share one Gateway
API error helper between channels and scheduled-tasks frontends
* fix(scheduled-tasks): close review round-3 gaps in guards, concurrency, and API ergonomics
- scrub internal-only context keys (non_interactive) from the assembled run
config for non-internal callers: gating body.context alone left the same
key smuggle-able through the free-form body.config copied verbatim by
build_run_config
- guard update_after_launch with protect_terminal so the launch bookkeeping
write cannot clobber a once task already finalized by a fast-failing run's
completion hook (parent-row sibling of the run-row guard)
- reject a manual trigger while the task has an active run (409) instead of
launching a duplicate concurrent run on fresh_thread_per_run
- re-arm a terminal once task to enabled when PATCH pushes run_at into the
future; previously the endpoint returned 200 with a next_run_at that could
never be claimed
- make max_concurrent_runs a real global cap: each poll claims only into the
remaining budget of active (queued/running) scheduled runs
- paginate GET /scheduled-tasks/{id}/runs (limit<=200, offset) and push the
thread filter of /threads/{id}/scheduled-tasks into SQL
- stamp context.user_id on scheduler-launched runs, matching IM channels, so
user-scoped guardrail providers see the owning user
---------
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
152 lines
4.4 KiB
Python
152 lines
4.4 KiB
Python
from datetime import UTC, datetime, timedelta
|
|
|
|
import pytest
|
|
|
|
from deerflow.config.database_config import DatabaseConfig
|
|
from deerflow.persistence.engine import close_engine, get_session_factory, init_engine_from_config
|
|
from deerflow.persistence.scheduled_tasks import ScheduledTaskRepository
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_claim_due_tasks_claims_only_due_rows(tmp_path):
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
sf = get_session_factory()
|
|
assert sf is not None
|
|
repo = ScheduledTaskRepository(sf)
|
|
|
|
due = datetime.now(UTC) - timedelta(minutes=1)
|
|
future = datetime.now(UTC) + timedelta(hours=1)
|
|
|
|
await repo.create(
|
|
task_id="due-1",
|
|
user_id="user-1",
|
|
thread_id="thread-1",
|
|
context_mode="reuse_thread",
|
|
assistant_id="lead_agent",
|
|
title="Due",
|
|
prompt="Prompt",
|
|
schedule_type="cron",
|
|
schedule_spec={"cron": "0 9 * * *"},
|
|
timezone="UTC",
|
|
next_run_at=due,
|
|
)
|
|
await repo.create(
|
|
task_id="future-1",
|
|
user_id="user-1",
|
|
thread_id="thread-1",
|
|
context_mode="reuse_thread",
|
|
assistant_id="lead_agent",
|
|
title="Future",
|
|
prompt="Prompt",
|
|
schedule_type="cron",
|
|
schedule_spec={"cron": "0 9 * * *"},
|
|
timezone="UTC",
|
|
next_run_at=future,
|
|
)
|
|
|
|
claimed = await repo.claim_due_tasks(
|
|
now=datetime.now(UTC),
|
|
lease_owner="worker-1",
|
|
lease_seconds=120,
|
|
limit=10,
|
|
)
|
|
assert [task["id"] for task in claimed] == ["due-1"]
|
|
|
|
await close_engine()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_claim_reclaims_task_stuck_in_running_with_expired_lease(tmp_path):
|
|
"""A task whose claiming process died mid-dispatch must stay reclaimable.
|
|
|
|
Regression for the lease dead-end bug: claim flips status to ``running``,
|
|
and the old claim query only selected ``status == 'enabled'``, so a crash
|
|
between claim and dispatch left the task permanently un-triggerable.
|
|
"""
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
sf = get_session_factory()
|
|
assert sf is not None
|
|
repo = ScheduledTaskRepository(sf)
|
|
|
|
now = datetime.now(UTC)
|
|
due = now - timedelta(minutes=5)
|
|
|
|
await repo.create(
|
|
task_id="stuck-1",
|
|
user_id="user-1",
|
|
thread_id="thread-1",
|
|
context_mode="reuse_thread",
|
|
assistant_id="lead_agent",
|
|
title="Stuck",
|
|
prompt="Prompt",
|
|
schedule_type="cron",
|
|
schedule_spec={"cron": "0 9 * * *"},
|
|
timezone="UTC",
|
|
next_run_at=due,
|
|
)
|
|
|
|
first_claim = await repo.claim_due_tasks(
|
|
now=now,
|
|
lease_owner="dead-worker",
|
|
lease_seconds=60,
|
|
limit=10,
|
|
)
|
|
assert first_claim[0]["id"] == "stuck-1"
|
|
assert first_claim[0]["status"] == "running"
|
|
|
|
# Simulate the claiming process dying: lease expires, status stays "running".
|
|
expired_now = now + timedelta(seconds=120)
|
|
reclaimed = await repo.claim_due_tasks(
|
|
now=expired_now,
|
|
lease_owner="new-worker",
|
|
lease_seconds=60,
|
|
limit=10,
|
|
)
|
|
assert [task["id"] for task in reclaimed] == ["stuck-1"]
|
|
assert reclaimed[0]["lease_owner"] == "new-worker"
|
|
|
|
await close_engine()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_claim_skips_task_with_active_lease(tmp_path):
|
|
"""A task whose lease has not expired must not be reclaimed."""
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
sf = get_session_factory()
|
|
assert sf is not None
|
|
repo = ScheduledTaskRepository(sf)
|
|
|
|
now = datetime.now(UTC)
|
|
due = now - timedelta(minutes=5)
|
|
|
|
await repo.create(
|
|
task_id="active-1",
|
|
user_id="user-1",
|
|
thread_id="thread-1",
|
|
context_mode="reuse_thread",
|
|
assistant_id="lead_agent",
|
|
title="Active",
|
|
prompt="Prompt",
|
|
schedule_type="cron",
|
|
schedule_spec={"cron": "0 9 * * *"},
|
|
timezone="UTC",
|
|
next_run_at=due,
|
|
)
|
|
|
|
await repo.claim_due_tasks(
|
|
now=now,
|
|
lease_owner="worker-1",
|
|
lease_seconds=300,
|
|
limit=10,
|
|
)
|
|
|
|
# Lease still valid — second claim within the same process must not re-grab it.
|
|
reclaimed = await repo.claim_due_tasks(
|
|
now=now + timedelta(seconds=10),
|
|
lease_owner="worker-2",
|
|
lease_seconds=300,
|
|
limit=10,
|
|
)
|
|
assert reclaimed == []
|
|
|
|
await close_engine()
|