diff --git a/CHANGELOG.md b/CHANGELOG.md
index e3b8160a7e..ec9c8608fc 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -19,6 +19,15 @@ This section accumulates work toward the **2.3.0** milestone
### Fixed
+- **harness:** Retrying a failed item no longer reopens a cancelled durable
+ subagent batch. `retry_item` kept only a paused batch as it was, so a failed
+ item of a cancelled batch put the batch back to `queued`, the worker claimed
+ and ran the item, and the batch ended `completed`. The retry route now
+ answers 409 for a cancelled batch, including when the cancel commits while
+ the retry is in flight on SQLite, and the workspace no longer offers Retry
+ there. Retrying in a completed, failed, running or paused batch is
+ unchanged. ([#7792])
+
- **agents:** `PUT /api/agents/{name}` with `"description": null` now resets the
description to empty. It used to store the null, which the agent config
rejects, so the agent then failed every load: the update, GET and repair
@@ -15980,3 +15989,4 @@ with **180 merged pull requests** since the first 2.0 milestone tag.
[#7732]: https://github.com/bytedance/deer-flow/pull/7732
[#7762]: https://github.com/bytedance/deer-flow/pull/7762
[#7772]: https://github.com/bytedance/deer-flow/pull/7772
+[#7792]: https://github.com/bytedance/deer-flow/pull/7792
diff --git a/CHANGELOG_zh.md b/CHANGELOG_zh.md
index 8f22cf3393..bf8ef3c752 100644
--- a/CHANGELOG_zh.md
+++ b/CHANGELOG_zh.md
@@ -20,6 +20,13 @@
### 修复
+- **harness：** 重试失败条目不再重新打开已取消的持久子智能体批次。`retry_item`
+ 此前只保留已暂停批次的状态，因此重试已取消批次中的失败条目会把批次改回
+ `queued`，worker 随即认领并执行该条目，批次最终变为 `completed`。现在对已取消
+ 批次的重试路由返回 409，包括 SQLite 上取消在重试进行中提交的情况；工作区也不再
+ 为这些条目显示重试按钮。在已完成、失败、运行中或已暂停批次中重试的行为不变。
+ ([#7792])
+
- **智能体：** `PUT /api/agents/{name}` 传入 `"description": null` 时现在会把描述重置为
空。此前会把 null 原样保存，而智能体配置不接受该值，导致之后每次加载都失败：更新本身、
GET 和修复性更新都返回 500，文件后端会把它从智能体列表中漏掉，数据库后端会让该用户的
@@ -12732,3 +12739,4 @@ DeerFlow 2.0 是围绕"超级智能体"框架的彻底重写，核心包含子
[#7732]: https://github.com/bytedance/deer-flow/pull/7732
[#7762]: https://github.com/bytedance/deer-flow/pull/7762
[#7772]: https://github.com/bytedance/deer-flow/pull/7772
+[#7792]: https://github.com/bytedance/deer-flow/pull/7792
diff --git a/backend/app/gateway/routers/subagent_batches.py b/backend/app/gateway/routers/subagent_batches.py
index 350953d82e..a1d44952a8 100644
--- a/backend/app/gateway/routers/subagent_batches.py
+++ b/backend/app/gateway/routers/subagent_batches.py
@@ -122,7 +122,7 @@ async def retry_batch_item(thread_id: ThreadId, batch_id: str, item_id: str, req
repo, user_id, _batch = await _owned_batch(request, thread_id, batch_id)
item = await repo.retry_item(batch_id, item_id, user_id=user_id)
if item is None:
- raise HTTPException(status_code=409, detail="Only failed items can be retried")
+ raise HTTPException(status_code=409, detail="Only failed items of a batch that is not cancelled can be retried")
return item
diff --git a/backend/packages/harness/deerflow/persistence/subagent_batches/sql.py b/backend/packages/harness/deerflow/persistence/subagent_batches/sql.py
index d847d6c1a7..1ab94b35e5 100644
--- a/backend/packages/harness/deerflow/persistence/subagent_batches/sql.py
+++ b/backend/packages/harness/deerflow/persistence/subagent_batches/sql.py
@@ -627,6 +627,14 @@ class SubagentBatchRepository:
item.completed_at = None
item.cancel_requested_at = None
item.updated_at = now
+ # SQLite ignores FOR UPDATE: flush first so this transaction holds the
+ # write lock, then re-read the batch a cancel may have committed since.
+ await session.flush()
+ await session.refresh(batch)
+ # Cancellation is final; reopening the batch would run work the user
+ # stopped. Returning without commit discards the item reset.
+ if batch.status == "cancelled":
+ return None
if batch.status != "paused":
batch.status = "queued"
batch.completed_at = None
diff --git a/backend/tests/test_cancelled_batch_retry.py b/backend/tests/test_cancelled_batch_retry.py
new file mode 100644
index 0000000000..a90b266bc4
--- /dev/null
+++ b/backend/tests/test_cancelled_batch_retry.py
@@ -0,0 +1,109 @@
+"""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"),
+ ]
diff --git a/backend/tests/test_subagent_batch_repository.py b/backend/tests/test_subagent_batch_repository.py
index ba4adf9768..6cf8a46614 100644
--- a/backend/tests/test_subagent_batch_repository.py
+++ b/backend/tests/test_subagent_batch_repository.py
@@ -9,6 +9,7 @@ from deerflow.config.database_config import DatabaseConfig
from deerflow.mcp_scope import THREAD_INCARNATION_CONTEXT_KEY
from deerflow.persistence.engine import close_engine, get_engine, get_session_factory, init_engine_from_config
from deerflow.persistence.subagent_batches import SubagentBatchRepository
+from deerflow.persistence.subagent_batches.model import SubagentBatchItemRow
_MISSING = object()
@@ -350,6 +351,92 @@ async def test_retry_item_in_running_batch_keeps_batch_schedulable(tmp_path) ->
assert failed["id"] in {item["id"] for item in claimed}
+async def _fail_first_item(repo: SubagentBatchRepository, now: datetime) -> dict:
+ failed = (await repo.claim_items(now=now, lease_owner="worker-1", lease_seconds=60, 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="model-a",
+ completed_at=now,
+ )
+ return failed
+
+
+async def _assert_cancel_kept(repo: SubagentBatchRepository, failed: dict, now: datetime) -> None:
+ items = await repo.list_items("batch-1", user_id="user-1")
+ retried = next(item for item in items if item["id"] == failed["id"])
+ assert retried["status"] == "failed"
+ assert retried["error"] == "permanent"
+ batch = await repo.get_batch("batch-1", user_id="user-1")
+ assert batch is not None and batch["status"] == "cancelled"
+ assert batch["completed_at"] is not None
+ assert batch["counts"]["pending"] == 0
+ assert await repo.claim_items(now=now, lease_owner="worker-2", lease_seconds=60, limit=10) == []
+
+
+@pytest.mark.asyncio
+async def test_retry_item_does_not_reopen_cancelled_batch(tmp_path) -> None:
+ repo = await _repo(tmp_path)
+ await _create(repo, count=3, max_live=3, max_running=3, max_attempts=1)
+ now = datetime.now(UTC)
+ failed = await _fail_first_item(repo, now)
+ cancelled = await repo.cancel_batch("batch-1", user_id="user-1")
+ assert cancelled is not None and cancelled["status"] == "cancelled"
+
+ assert await repo.retry_item("batch-1", failed["id"], user_id="user-1") is None
+
+ await _assert_cancel_kept(repo, failed, now + timedelta(seconds=1))
+
+
+class _CancelAfterItemRead:
+ """Session proxy that commits a cancel between ``retry_item``'s reads and its write."""
+
+ def __init__(self, session, cancel) -> None:
+ self._session = session
+ self._cancel = cancel
+
+ def __getattr__(self, name):
+ return getattr(self._session, name)
+
+ async def __aenter__(self):
+ await self._session.__aenter__()
+ return self
+
+ async def __aexit__(self, *exc_info):
+ return await self._session.__aexit__(*exc_info)
+
+ async def get(self, entity, ident, **kwargs):
+ row = await self._session.get(entity, ident, **kwargs)
+ if entity is SubagentBatchItemRow:
+ await self._cancel()
+ return row
+
+
+@pytest.mark.asyncio
+async def test_retry_item_does_not_reopen_batch_cancelled_after_its_read(tmp_path) -> None:
+ # SQLite ignores FOR UPDATE, so the cancel can commit after retry_item has
+ # read the batch as running. (On PostgreSQL the row lock blocks the cancel.)
+ repo = await _repo(tmp_path)
+ await _create(repo, count=3, max_live=3, max_running=3, max_attempts=1)
+ now = datetime.now(UTC)
+ failed = await _fail_first_item(repo, now)
+ batch = await repo.get_batch("batch-1", user_id="user-1")
+ assert batch is not None and batch["status"] == "running"
+ sessions = get_session_factory()
+ racing = SubagentBatchRepository(lambda: _CancelAfterItemRead(sessions(), lambda: repo.cancel_batch("batch-1", user_id="user-1")))
+
+ assert await racing.retry_item("batch-1", failed["id"], user_id="user-1") is None
+
+ await _assert_cancel_kept(repo, failed, now + timedelta(seconds=1))
+
+
@pytest.mark.asyncio
async def test_cancel_terminalizes_in_flight_items_and_fences_stale_completion(tmp_path) -> None:
repo = await _repo(tmp_path)
diff --git a/frontend/src/components/workspace/thread-subagent-batches.tsx b/frontend/src/components/workspace/thread-subagent-batches.tsx
index 2c9e8ba317..d2284460b5 100644
--- a/frontend/src/components/workspace/thread-subagent-batches.tsx
+++ b/frontend/src/components/workspace/thread-subagent-batches.tsx
@@ -304,6 +304,7 @@ function BatchItems({
key={item.id}
item={item}
workerRunning={workerRunning}
+ batchCancelled={batch.status === "cancelled"}
retrying={retry.isPending && retry.variables === item.id}
onRetry={() => retry.mutate(item.id)}
/>
@@ -332,6 +333,7 @@ function BatchItemRow({
batchId,
item,
workerRunning,
+ batchCancelled,
retrying,
onRetry,
}: {
@@ -339,6 +341,7 @@ function BatchItemRow({
batchId: string;
item: SubagentBatchItem;
workerRunning: boolean;
+ batchCancelled: boolean;
retrying: boolean;
onRetry: () => void;
}) {
@@ -374,7 +377,7 @@ function BatchItemRow({
>
{t.subagentBatches.viewResult}
- {item.status === "failed" && (
+ {item.status === "failed" && !batchCancelled && (