mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-11-07 19:20:34 +00:00
7fd0c0cb3e
* fix(harness): keep a cancelled batch cancelled when retrying a failed item retry_item only kept a paused batch as it was, so retrying a failed item of a cancelled batch reset the batch to queued and the worker claimed and ran the item. A cancelled batch now rejects the retry (409), re-checked under the write lock because SQLite ignores FOR UPDATE, and the workspace no longer offers Retry there. * docs(changelog): reference #7792 for the cancelled batch retry fix
110 lines
4.3 KiB
Python
110 lines
4.3 KiB
Python
"""Retrying a failed item never reopens a cancelled batch or runs its work."""
|
|
|
|
from datetime import UTC, datetime, timedelta
|
|
from types import SimpleNamespace
|
|
from unittest.mock import AsyncMock
|
|
|
|
import httpx
|
|
import pytest
|
|
import pytest_asyncio
|
|
from _router_auth_helpers import make_authed_test_app
|
|
|
|
from app.gateway.auth_disabled import AUTH_SOURCE_SESSION
|
|
from app.gateway.routers import subagent_batches
|
|
from deerflow.config.database_config import DatabaseConfig
|
|
from deerflow.config.subagent_batches_config import SubagentBatchesConfig
|
|
from deerflow.config.subagent_runtime_config import SubagentRuntimeConfig
|
|
from deerflow.persistence.engine import close_engine, get_session_factory, init_engine_from_config
|
|
from deerflow.persistence.subagent_batches import SubagentBatchRepository
|
|
from deerflow.persistence.thread_meta import ThreadMetaRepository
|
|
from deerflow.subagents.batch_service import SubagentBatchService
|
|
|
|
_URL = "/api/threads/thread-1/subagent-batches/batch-1"
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
async def api(tmp_path):
|
|
# Synthetic session identity; routing, owner checks, SQL and claiming are real.
|
|
user = SimpleNamespace(id="user-1", system_role="user")
|
|
app = make_authed_test_app(user_factory=lambda: user, bind_current_user=True)
|
|
app.include_router(subagent_batches.router)
|
|
|
|
@app.middleware("http")
|
|
async def session_source(request, call_next):
|
|
request.state.auth_source = AUTH_SOURCE_SESSION
|
|
return await call_next(request)
|
|
|
|
try:
|
|
await init_engine_from_config(DatabaseConfig(backend="sqlite", sqlite_dir=str(tmp_path)))
|
|
sessions = get_session_factory()
|
|
app.state.subagent_batch_repo = SubagentBatchRepository(sessions)
|
|
app.state.thread_store = ThreadMetaRepository(sessions)
|
|
service = SubagentBatchService(
|
|
repository=app.state.subagent_batch_repo,
|
|
config=SubagentBatchesConfig(lease_seconds=10),
|
|
runtime_config=SubagentRuntimeConfig(),
|
|
)
|
|
# No executor is needed: a cancelled batch must never dispatch its items.
|
|
service._execute_item = AsyncMock()
|
|
app.state.subagent_batch_service = service
|
|
app.state.subagent_batches_available = True
|
|
await app.state.thread_store.create("thread-1", user_id="user-1")
|
|
async with httpx.AsyncClient(transport=httpx.ASGITransport(app=app), base_url="http://test") as client:
|
|
yield app, client
|
|
finally:
|
|
await close_engine()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_retry_in_cancelled_batch_is_rejected_and_never_dispatched(api):
|
|
app, client = api
|
|
repo = app.state.subagent_batch_repo
|
|
service = app.state.subagent_batch_service
|
|
await repo.create_batch(
|
|
batch_id="batch-1",
|
|
user_id="user-1",
|
|
thread_id="thread-1",
|
|
run_id="run-1",
|
|
tool_call_id="call-1",
|
|
submission_key="run-1:call-1",
|
|
title="Cancelled research",
|
|
subagent_type="general-purpose",
|
|
items=[{"key": f"item-{index}", "prompt": f"Process {index}"} for index in range(3)],
|
|
max_live_items=1,
|
|
max_running_items=1,
|
|
max_attempts=1,
|
|
execution_spec={},
|
|
)
|
|
now = datetime.now(UTC)
|
|
failed = (await repo.claim_items(now=now, lease_owner="worker-1", lease_seconds=10, limit=1))[0]
|
|
assert await repo.finalize_item(
|
|
failed["id"],
|
|
lease_owner="worker-1",
|
|
succeeded=False,
|
|
result=None,
|
|
result_preview=None,
|
|
result_truncated=False,
|
|
error="permanent",
|
|
stop_reason=None,
|
|
token_usage=None,
|
|
model_name=None,
|
|
completed_at=now,
|
|
)
|
|
assert (await client.post(f"{_URL}/cancel")).json()["status"] == "cancelled"
|
|
|
|
retried = await client.post(f"{_URL}/items/{failed['id']}/retry")
|
|
|
|
assert retried.status_code == 409
|
|
assert retried.json()["detail"] == "Only failed items of a batch that is not cancelled can be retried"
|
|
await service.run_once(now=now + timedelta(seconds=1))
|
|
service._execute_item.assert_not_awaited()
|
|
batch = (await client.get(_URL)).json()
|
|
assert batch["status"] == "cancelled"
|
|
assert batch["completed_at"] is not None
|
|
items = (await client.get(f"{_URL}/items")).json()
|
|
assert [(item["status"], item["error"]) for item in items] == [
|
|
("failed", "permanent"),
|
|
("cancelled", "Cancelled by user"),
|
|
("cancelled", "Cancelled by user"),
|
|
]
|