feat(apps): 新增 DeerFlow 应用脚手架,并修复 store 的 database 回退

apps/:新增「基于 DeerFlow 的应用」目录,与 backend/、frontend/ 平级,
位于「app 消费 deerflow、不反向依赖」边界的正确侧。含两种集成示例:
  - examples/http-chat   —— HTTP Gateway (REST+SSE),含登录/CSRF/建线程/流式对话
  - examples/embedded-chat —— 进程内直接调 DeerFlowClient
README 说明边界规则、两种模式、鉴权流程及新建应用约定。

runtime/store:修复 make_store 缺失的 database 段回退。原先 store 工厂只读
legacy 的 checkpointer 段,导致仅配 database:postgres 时,checkpointer 走了
Postgres、但 store 仍回退 InMemoryStore(并打出误导性的「线程列表会丢失」告警,
实际线程在 threads_meta 表里、本就持久)。现对齐 checkpointer 工厂的优先级:
checkpointer 段 → database 段 → InMemoryStore;postgres 分支同样剥掉 +asyncpg
方言前缀,使一个 DATABASE_URL 同时满足 SQLAlchemy 与 LangGraph 的 psycopg store。
告警文案也修正为「跨线程 store 数据会丢失」。

tests:新增 test_store_provider.py(3 例,TDD)覆盖 database→postgres 回退、
无配置时的内存回退、以及 checkpointer 段优先级。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
1445043649
2026-06-27 22:02:44 +08:00
parent 84de632b19
commit 7dfc9968fe
7 changed files with 394 additions and 9 deletions
@@ -19,6 +19,7 @@ from __future__ import annotations
import contextlib
import logging
import re
from collections.abc import AsyncIterator
from langgraph.store.base import BaseStore
@@ -80,6 +81,57 @@ async def _async_store(config) -> AsyncIterator[BaseStore]:
raise ValueError(f"Unknown store backend type: {config.type!r}")
@contextlib.asynccontextmanager
async def _async_store_from_database(db_config) -> AsyncIterator[BaseStore]:
"""Async context manager that constructs a Store from a unified DatabaseConfig.
Mirrors :func:`deerflow.runtime.checkpointer.async_provider._async_checkpointer_from_database`
so the store and checkpointer share one ``database`` section.
"""
if db_config.backend == "memory":
from langgraph.store.memory import InMemoryStore
logger.info("Store: using InMemoryStore (in-process, not persistent)")
yield InMemoryStore()
return
if db_config.backend == "sqlite":
try:
from langgraph.store.sqlite.aio import AsyncSqliteStore
except ImportError as exc:
raise ImportError(SQLITE_STORE_INSTALL) from exc
conn_str = db_config.sqlite_path
ensure_sqlite_parent_dir(conn_str)
async with AsyncSqliteStore.from_conn_string(conn_str) as store:
await store.setup()
logger.info("Store: using AsyncSqliteStore (%s)", conn_str)
yield store
return
if db_config.backend == "postgres":
try:
from langgraph.store.postgres.aio import AsyncPostgresStore # type: ignore[import]
except ImportError as exc:
raise ImportError(POSTGRES_STORE_INSTALL) from exc
if not db_config.postgres_url:
raise ValueError(POSTGRES_CONN_REQUIRED)
# LangGraph's AsyncPostgresStore wraps psycopg and expects a libpq-style
# conninfo (`postgresql://...`). DeerFlow's SQLAlchemy engine uses the
# same URL with the `+asyncpg` dialect prefix — strip it so one
# DATABASE_URL satisfies both paths (same as the checkpointer factory).
lg_conn_str = re.sub(r"^postgresql\+\w+://", "postgresql://", db_config.postgres_url)
async with AsyncPostgresStore.from_conn_string(lg_conn_str) as store:
await store.setup()
logger.info("Store: using AsyncPostgresStore")
yield store
return
raise ValueError(f"Unknown database backend: {db_config.backend!r}")
# ---------------------------------------------------------------------------
# Public async context manager
# ---------------------------------------------------------------------------
@@ -97,18 +149,29 @@ async def make_store(app_config: AppConfig | None = None) -> AsyncIterator[BaseS
async with make_store(app_config) as store:
app.state.store = store
Yields an :class:`~langgraph.store.memory.InMemoryStore` when no
``checkpointer`` section is configured (emits a WARNING in that case).
Priority (mirrors the checkpointer factory):
1. Legacy ``checkpointer:`` config section (backward compatible)
2. Unified ``database:`` config section
3. Default InMemoryStore (emits a WARNING)
"""
if app_config is None:
app_config = get_app_config()
if app_config.checkpointer is None:
from langgraph.store.memory import InMemoryStore
logger.warning("No 'checkpointer' section in config.yaml — using InMemoryStore for the store. Thread list will be lost on server restart. Configure a sqlite or postgres backend for persistence.")
yield InMemoryStore()
# Legacy: standalone checkpointer config takes precedence
if app_config.checkpointer is not None:
async with _async_store(app_config.checkpointer) as store:
yield store
return
async with _async_store(app_config.checkpointer) as store:
yield store
# Unified database config
db_config = getattr(app_config, "database", None)
if db_config is not None and db_config.backend != "memory":
async with _async_store_from_database(db_config) as store:
yield store
return
# Default: in-memory
from langgraph.store.memory import InMemoryStore
logger.warning("No persistent store backend configured (no 'checkpointer' or 'database' section) — using InMemoryStore. Cross-thread store data will be lost on server restart. Configure a sqlite or postgres backend for persistence.")
yield InMemoryStore()
+89
View File
@@ -0,0 +1,89 @@
"""Tests for the async Store factory's backend selection.
Mirrors the checkpointer factory: when no legacy ``checkpointer`` section
is configured but a unified ``database`` section is, the store must use
that database backend instead of silently falling back to InMemoryStore.
"""
import sys
from unittest.mock import AsyncMock, MagicMock, patch
import pytest
from deerflow.config.database_config import DatabaseConfig
from deerflow.runtime.store.async_provider import make_store
@pytest.fixture
def anyio_backend() -> str:
return "asyncio"
class TestStoreDatabaseFallback:
@pytest.mark.anyio
async def test_postgres_store_from_database_when_no_checkpointer_section(self):
"""make_store uses AsyncPostgresStore from the database section when
no legacy checkpointer section is present. The +asyncpg dialect prefix
is stripped so the same DATABASE_URL satisfies both SQLAlchemy and
LangGraph's psycopg-based store."""
mock_config = MagicMock()
mock_config.checkpointer = None
mock_config.database = DatabaseConfig(
backend="postgres",
postgres_url="postgresql+asyncpg://postgres:pw@localhost:5432/deerflow",
)
mock_store = AsyncMock()
mock_cm = AsyncMock()
mock_cm.__aenter__.return_value = mock_store
mock_cm.__aexit__.return_value = False
mock_store_cls = MagicMock()
mock_store_cls.from_conn_string.return_value = mock_cm
mock_module = MagicMock()
mock_module.AsyncPostgresStore = mock_store_cls
with (
patch("deerflow.runtime.store.async_provider.get_app_config", return_value=mock_config),
patch.dict(sys.modules, {"langgraph.store.postgres.aio": mock_module}),
):
async with make_store() as store:
assert store is mock_store
# dialect prefix stripped to libpq conninfo
mock_store_cls.from_conn_string.assert_called_once_with("postgresql://postgres:pw@localhost:5432/deerflow")
mock_store.setup.assert_awaited_once()
@pytest.mark.anyio
async def test_memory_when_no_checkpointer_and_no_database(self):
"""With neither a checkpointer section nor a non-memory database,
the store falls back to InMemoryStore."""
from langgraph.store.memory import InMemoryStore
mock_config = MagicMock()
mock_config.checkpointer = None
mock_config.database = DatabaseConfig(backend="memory")
with patch("deerflow.runtime.store.async_provider.get_app_config", return_value=mock_config):
async with make_store() as store:
assert isinstance(store, InMemoryStore)
@pytest.mark.anyio
async def test_checkpointer_section_takes_precedence_over_database(self):
"""A legacy checkpointer section still wins over the database section."""
from deerflow.config.checkpointer_config import CheckpointerConfig
mock_config = MagicMock()
mock_config.checkpointer = CheckpointerConfig(type="memory")
mock_config.database = DatabaseConfig(
backend="postgres",
postgres_url="postgresql+asyncpg://postgres:pw@localhost:5432/deerflow",
)
from langgraph.store.memory import InMemoryStore
with patch("deerflow.runtime.store.async_provider.get_app_config", return_value=mock_config):
async with make_store() as store:
# checkpointer.type == memory → InMemoryStore, database ignored
assert isinstance(store, InMemoryStore)