mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-05-22 07:56:48 +00:00
feat(auth): enforce owner_id across 2.0-rc persistence layer
Add request-scoped contextvar-based owner filtering to threads_meta,
runs, run_events, and feedback repositories. Router code is unchanged
— isolation is enforced at the storage layer so that any caller that
forgets to pass owner_id still gets filtered results, and new routes
cannot accidentally leak data.
Core infrastructure
-------------------
- deerflow/runtime/user_context.py (new):
- ContextVar[CurrentUser | None] with default None
- runtime_checkable CurrentUser Protocol (structural subtype with .id)
- set/reset/get/require helpers
- AUTO sentinel + resolve_owner_id(value, method_name) for sentinel
three-state resolution: AUTO reads contextvar, explicit str
overrides, explicit None bypasses the filter (for migration/CLI)
Repository changes
------------------
- ThreadMetaRepository: create/get/search/update_*/delete gain
owner_id=AUTO kwarg; read paths filter by owner, writes stamp it,
mutations check ownership before applying
- RunRepository: put/get/list_by_thread/delete gain owner_id=AUTO kwarg
- FeedbackRepository: create/get/list_by_run/list_by_thread/delete
gain owner_id=AUTO kwarg
- DbRunEventStore: list_messages/list_events/list_messages_by_run/
count_messages/delete_by_thread/delete_by_run gain owner_id=AUTO
kwarg. Write paths (put/put_batch) read contextvar softly: when a
request-scoped user is available, owner_id is stamped; background
worker writes without a user context pass None which is valid
(orphan row to be bound by migration)
Schema
------
- persistence/models/run_event.py: RunEventRow.owner_id = Mapped[
str | None] = mapped_column(String(64), nullable=True, index=True)
- No alembic migration needed: 2.0 ships fresh, Base.metadata.create_all
picks up the new column automatically
Middleware
----------
- auth_middleware.py: after cookie check, call get_optional_user_from_
request to load the real User, stamp it into request.state.user AND
the contextvar via set_current_user, reset in a try/finally. Public
paths and unauthenticated requests continue without contextvar, and
@require_auth handles the strict 401 path
Test infrastructure
-------------------
- tests/conftest.py: @pytest.fixture(autouse=True) _auto_user_context
sets a default SimpleNamespace(id="test-user-autouse") on every test
unless marked @pytest.mark.no_auto_user. Keeps existing 20+
persistence tests passing without modification
- pyproject.toml [tool.pytest.ini_options]: register no_auto_user
marker so pytest does not emit warnings for opt-out tests
- tests/test_user_context.py: 6 tests covering three-state semantics,
Protocol duck typing, and require/optional APIs
- tests/test_thread_meta_repo.py: one test updated to pass owner_id=
None explicitly where it was previously relying on the old default
Test results
------------
- test_user_context.py: 6 passed
- test_auth*.py + test_langgraph_auth.py + test_ensure_admin.py: 127
- test_run_event_store / test_run_repository / test_thread_meta_repo
/ test_feedback: 92 passed
- Full backend suite: 1905 passed, 2 failed (both @requires_llm flaky
integration tests unrelated to auth), 1 skipped
This commit is contained in:
@@ -16,6 +16,7 @@ from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker
|
||||
|
||||
from deerflow.persistence.run.model import RunRow
|
||||
from deerflow.runtime.runs.store.base import RunStore
|
||||
from deerflow.runtime.user_context import AUTO, _AutoSentinel, resolve_owner_id
|
||||
|
||||
|
||||
class RunRepository(RunStore):
|
||||
@@ -68,7 +69,7 @@ class RunRepository(RunStore):
|
||||
*,
|
||||
thread_id,
|
||||
assistant_id=None,
|
||||
owner_id=None,
|
||||
owner_id: "str | None | _AutoSentinel" = AUTO,
|
||||
status="pending",
|
||||
multitask_strategy="reject",
|
||||
metadata=None,
|
||||
@@ -77,12 +78,13 @@ class RunRepository(RunStore):
|
||||
created_at=None,
|
||||
follow_up_to_run_id=None,
|
||||
):
|
||||
resolved_owner_id = resolve_owner_id(owner_id, method_name="RunRepository.put")
|
||||
now = datetime.now(UTC)
|
||||
row = RunRow(
|
||||
run_id=run_id,
|
||||
thread_id=thread_id,
|
||||
assistant_id=assistant_id,
|
||||
owner_id=owner_id,
|
||||
owner_id=resolved_owner_id,
|
||||
status=status,
|
||||
multitask_strategy=multitask_strategy,
|
||||
metadata_json=self._safe_json(metadata) or {},
|
||||
@@ -96,15 +98,32 @@ class RunRepository(RunStore):
|
||||
session.add(row)
|
||||
await session.commit()
|
||||
|
||||
async def get(self, run_id):
|
||||
async def get(
|
||||
self,
|
||||
run_id,
|
||||
*,
|
||||
owner_id: "str | None | _AutoSentinel" = AUTO,
|
||||
):
|
||||
resolved_owner_id = resolve_owner_id(owner_id, method_name="RunRepository.get")
|
||||
async with self._sf() as session:
|
||||
row = await session.get(RunRow, run_id)
|
||||
return self._row_to_dict(row) if row else None
|
||||
if row is None:
|
||||
return None
|
||||
if resolved_owner_id is not None and row.owner_id != resolved_owner_id:
|
||||
return None
|
||||
return self._row_to_dict(row)
|
||||
|
||||
async def list_by_thread(self, thread_id, *, owner_id=None, limit=100):
|
||||
async def list_by_thread(
|
||||
self,
|
||||
thread_id,
|
||||
*,
|
||||
owner_id: "str | None | _AutoSentinel" = AUTO,
|
||||
limit=100,
|
||||
):
|
||||
resolved_owner_id = resolve_owner_id(owner_id, method_name="RunRepository.list_by_thread")
|
||||
stmt = select(RunRow).where(RunRow.thread_id == thread_id)
|
||||
if owner_id is not None:
|
||||
stmt = stmt.where(RunRow.owner_id == owner_id)
|
||||
if resolved_owner_id is not None:
|
||||
stmt = stmt.where(RunRow.owner_id == resolved_owner_id)
|
||||
stmt = stmt.order_by(RunRow.created_at.desc()).limit(limit)
|
||||
async with self._sf() as session:
|
||||
result = await session.execute(stmt)
|
||||
@@ -118,12 +137,21 @@ class RunRepository(RunStore):
|
||||
await session.execute(update(RunRow).where(RunRow.run_id == run_id).values(**values))
|
||||
await session.commit()
|
||||
|
||||
async def delete(self, run_id):
|
||||
async def delete(
|
||||
self,
|
||||
run_id,
|
||||
*,
|
||||
owner_id: "str | None | _AutoSentinel" = AUTO,
|
||||
):
|
||||
resolved_owner_id = resolve_owner_id(owner_id, method_name="RunRepository.delete")
|
||||
async with self._sf() as session:
|
||||
row = await session.get(RunRow, run_id)
|
||||
if row is not None:
|
||||
await session.delete(row)
|
||||
await session.commit()
|
||||
if row is None:
|
||||
return
|
||||
if resolved_owner_id is not None and row.owner_id != resolved_owner_id:
|
||||
return
|
||||
await session.delete(row)
|
||||
await session.commit()
|
||||
|
||||
async def list_pending(self, *, before=None):
|
||||
if before is None:
|
||||
|
||||
Reference in New Issue
Block a user