mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-04-27 20:28:16 +00:00
4b139fb689
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
78 lines
2.7 KiB
Python
78 lines
2.7 KiB
Python
"""Test configuration for the backend test suite.
|
|
|
|
Sets up sys.path and pre-mocks modules that would cause circular import
|
|
issues when unit-testing lightweight config/registry code in isolation.
|
|
"""
|
|
|
|
import sys
|
|
from pathlib import Path
|
|
from types import SimpleNamespace
|
|
from unittest.mock import MagicMock
|
|
|
|
import pytest
|
|
|
|
# Make 'app' and 'deerflow' importable from any working directory
|
|
sys.path.insert(0, str(Path(__file__).parent.parent))
|
|
|
|
# Break the circular import chain that exists in production code:
|
|
# deerflow.subagents.__init__
|
|
# -> .executor (SubagentExecutor, SubagentResult)
|
|
# -> deerflow.agents.thread_state
|
|
# -> deerflow.agents.__init__
|
|
# -> lead_agent.agent
|
|
# -> subagent_limit_middleware
|
|
# -> deerflow.subagents.executor <-- circular!
|
|
#
|
|
# By injecting a mock for deerflow.subagents.executor *before* any test module
|
|
# triggers the import, __init__.py's "from .executor import ..." succeeds
|
|
# immediately without running the real executor module.
|
|
_executor_mock = MagicMock()
|
|
_executor_mock.SubagentExecutor = MagicMock
|
|
_executor_mock.SubagentResult = MagicMock
|
|
_executor_mock.SubagentStatus = MagicMock
|
|
_executor_mock.MAX_CONCURRENT_SUBAGENTS = 3
|
|
_executor_mock.get_background_task_result = MagicMock()
|
|
|
|
sys.modules["deerflow.subagents.executor"] = _executor_mock
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Auto-set user context for every test unless marked no_auto_user
|
|
# ---------------------------------------------------------------------------
|
|
#
|
|
# Repository methods read ``owner_id`` from a contextvar by default
|
|
# (see ``deerflow.runtime.user_context``). Without this fixture, every
|
|
# pre-existing persistence test would raise RuntimeError because the
|
|
# contextvar is unset. The fixture sets a default test user on every
|
|
# test; tests that explicitly want to verify behaviour *without* a user
|
|
# context should mark themselves ``@pytest.mark.no_auto_user``.
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _auto_user_context(request):
|
|
"""Inject a default ``test-user-autouse`` into the contextvar.
|
|
|
|
Opt-out via ``@pytest.mark.no_auto_user``. Uses lazy import so that
|
|
tests which don't touch the persistence layer never pay the cost
|
|
of importing runtime.user_context.
|
|
"""
|
|
if request.node.get_closest_marker("no_auto_user"):
|
|
yield
|
|
return
|
|
|
|
try:
|
|
from deerflow.runtime.user_context import (
|
|
reset_current_user,
|
|
set_current_user,
|
|
)
|
|
except ImportError:
|
|
yield
|
|
return
|
|
|
|
user = SimpleNamespace(id="test-user-autouse", email="test@local")
|
|
token = set_current_user(user)
|
|
try:
|
|
yield
|
|
finally:
|
|
reset_current_user(token)
|