fix(roundtable): 优化 Step2 总控派活稳定性与并发编排

限制总控工具白名单、关闭圆桌记忆注入、综合轮 synthesis_mode 与编排 epoch 防双发,并优化广播异步化及 Postgres checkpointer 连接池。

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
董宏凯andCursor committed 2026-06-07 21:20:58 +08:00
1 parent 9c9c912657
commit 924c8f2fac
8 files changed
+767 -302

No files matched your search

@@ -17,12 +17,12 @@ For sync usage see :mod:`deerflow.runtime.checkpointer.provider`.
from __future__ import annotations
import asyncio
import contextlib
import logging
from collections.abc import AsyncIterator
import os
from pathlib import Path
import asyncio
import contextlib
import logging
from collections.abc import AsyncIterator
import os
from pathlib import Path
from langgraph.types import Checkpointer
@@ -32,70 +32,117 @@ from deerflow.runtime.checkpointer.provider import (
POSTGRES_INSTALL,
SQLITE_INSTALL,
)
from deerflow.runtime.store._sqlite_utils import ensure_sqlite_parent_dir, resolve_sqlite_conn_str
from deerflow.runtime.store._sqlite_utils import ensure_sqlite_parent_dir, resolve_sqlite_conn_str
logger = logging.getLogger(__name__)
def _csv_env(name: str) -> list[str]:
raw = os.getenv(name, "")
return [part.strip() for part in raw.split(",") if part.strip()]
def _dual_read_enabled(config) -> bool:
if getattr(config, "dual_read_enabled", False):
return True
return os.getenv("DEER_FLOW_CHECKPOINT_DUAL_READ", "").strip().lower() in {"1", "true", "yes", "on"}
def _use_postgres_enabled(config) -> bool:
raw = os.getenv("DEER_FLOW_USE_PG_CHECKPOINTER")
if raw:
return raw.strip().lower() not in {"0", "false", "no", "off"}
return bool(getattr(config, "use_postgres", True))
def _dual_read_paths(config) -> list[str]:
paths = list(getattr(config, "dual_read_sqlite_paths", []) or [])
paths.extend(_csv_env("DEER_FLOW_CHECKPOINT_SQLITE_PATHS"))
resolved: list[str] = []
seen: set[str] = set()
for path in paths:
conn_str = resolve_sqlite_conn_str(path)
if conn_str == ":memory:" or conn_str.startswith("file:"):
logger.warning("Skipping unsupported checkpoint migration SQLite path: %s", path)
continue
if conn_str not in seen:
resolved.append(conn_str)
seen.add(conn_str)
return resolved
def _sqlite_conn_str_for_postgres_fallback(config) -> str:
configured = getattr(config, "sqlite_connection_string", None)
if configured:
return configured
paths = _dual_read_paths(config)
return paths[0] if paths else "store.db"
@contextlib.asynccontextmanager
async def _sqlite_checkpointer_from_conn_str(raw: str) -> AsyncIterator[Checkpointer]:
try:
from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver
except ImportError as exc:
raise ImportError(SQLITE_INSTALL) from exc
conn_str = resolve_sqlite_conn_str(raw)
await asyncio.to_thread(ensure_sqlite_parent_dir, conn_str)
async with AsyncSqliteSaver.from_conn_string(conn_str) as saver:
await saver.setup()
yield saver
# ---------------------------------------------------------------------------
# Async factory
# ---------------------------------------------------------------------------
logger = logging.getLogger(__name__)
def _csv_env(name: str) -> list[str]:
raw = os.getenv(name, "")
return [part.strip() for part in raw.split(",") if part.strip()]
def _dual_read_enabled(config) -> bool:
if getattr(config, "dual_read_enabled", False):
return True
return os.getenv("DEER_FLOW_CHECKPOINT_DUAL_READ", "").strip().lower() in {"1", "true", "yes", "on"}
def _use_postgres_enabled(config) -> bool:
raw = os.getenv("DEER_FLOW_USE_PG_CHECKPOINTER")
if raw:
return raw.strip().lower() not in {"0", "false", "no", "off"}
return bool(getattr(config, "use_postgres", True))
def _dual_read_paths(config) -> list[str]:
paths = list(getattr(config, "dual_read_sqlite_paths", []) or [])
paths.extend(_csv_env("DEER_FLOW_CHECKPOINT_SQLITE_PATHS"))
resolved: list[str] = []
seen: set[str] = set()
for path in paths:
conn_str = resolve_sqlite_conn_str(path)
if conn_str == ":memory:" or conn_str.startswith("file:"):
logger.warning("Skipping unsupported checkpoint migration SQLite path: %s", path)
continue
if conn_str not in seen:
resolved.append(conn_str)
seen.add(conn_str)
return resolved
def _sqlite_conn_str_for_postgres_fallback(config) -> str:
configured = getattr(config, "sqlite_connection_string", None)
if configured:
return configured
paths = _dual_read_paths(config)
return paths[0] if paths else "store.db"
@contextlib.asynccontextmanager
async def _pg_pool_saver(conn_str: str) -> AsyncIterator[Checkpointer]:
"""Pool-backed ``AsyncPostgresSaver``, resilient to idle-closed connections.
``AsyncPostgresSaver.from_conn_string`` opens **one** long-lived connection.
对远程 Postgres(本项目 47.88.25.99 这类),空闲几分钟后连接会被服务端 / NAT /
连接池中间件断开,而 psycopg **不会自动重连** —— 下一次 checkpoint 操作就抛
``OperationalError: the connection is closed``,整个 run 直接失败(实测:圆桌第二步
完成后闲置 ~6 分钟,用户再人工干预 → leader run 读 checkpoint 时撞死连接 → 前端
"(无文本输出)")。
用带健康检查的连接池根治:``check=AsyncConnectionPool.check_connection`` 在把连接交给
调用方前先验活,坏连接直接丢弃重建;``max_idle`` 主动回收久闲连接,赶在远程 idle 超时
之前。这样上层永远拿不到失效连接。``prepare_threshold=0`` 关预备语句,兼容 pgbouncer
一类连接池(8432 非标准端口很可能就是)。
"""
try:
from langgraph.checkpoint.postgres.aio import AsyncPostgresSaver
except ImportError as exc:
raise ImportError(POSTGRES_INSTALL) from exc
from psycopg_pool import AsyncConnectionPool
try:
max_size = int(os.getenv("DEER_FLOW_PG_POOL_MAX", "20"))
except ValueError:
max_size = 20
pool = AsyncConnectionPool(
conninfo=conn_str,
min_size=1,
max_size=max_size,
open=False,
kwargs={"autocommit": True, "prepare_threshold": 0},
check=AsyncConnectionPool.check_connection,
max_idle=120.0,
max_lifetime=1800.0,
)
await pool.open(wait=True)
try:
saver = AsyncPostgresSaver(pool)
await saver.setup()
logger.info("Checkpointer: Postgres connection pool ready (max_size=%d, health-checked)", max_size)
yield saver
finally:
await pool.close()
@contextlib.asynccontextmanager
async def _sqlite_checkpointer_from_conn_str(raw: str) -> AsyncIterator[Checkpointer]:
try:
from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver
except ImportError as exc:
raise ImportError(SQLITE_INSTALL) from exc
conn_str = resolve_sqlite_conn_str(raw)
await asyncio.to_thread(ensure_sqlite_parent_dir, conn_str)
async with AsyncSqliteSaver.from_conn_string(conn_str) as saver:
await saver.setup()
yield saver
# ---------------------------------------------------------------------------
# Async factory
# ---------------------------------------------------------------------------
@contextlib.asynccontextmanager
@@ -107,71 +154,66 @@ async def _async_checkpointer(config) -> AsyncIterator[Checkpointer]:
yield InMemorySaver()
return
if config.type == "sqlite":
async with _sqlite_checkpointer_from_conn_str(config.connection_string or "store.db") as saver:
yield saver
return
if config.type == "postgres":
if not _use_postgres_enabled(config):
conn_str = _sqlite_conn_str_for_postgres_fallback(config)
logger.info("Checkpointer: use_postgres=false; using SQLite fallback (%s)", conn_str)
async with _sqlite_checkpointer_from_conn_str(conn_str) as saver:
yield saver
return
try:
from langgraph.checkpoint.postgres.aio import AsyncPostgresSaver
except ImportError as exc:
raise ImportError(POSTGRES_INSTALL) from exc
if config.type == "sqlite":
async with _sqlite_checkpointer_from_conn_str(config.connection_string or "store.db") as saver:
yield saver
return
if not config.connection_string:
raise ValueError(POSTGRES_CONN_REQUIRED)
async with AsyncPostgresSaver.from_conn_string(config.connection_string) as saver:
await saver.setup()
if not _dual_read_enabled(config):
yield saver
return
from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver
from deerflow.runtime.checkpointer.checkpoint_migration import (
DualReadCheckpointer,
SQLiteCheckpointSource,
)
sources: list[SQLiteCheckpointSource] = []
for sqlite_path in _dual_read_paths(config):
if not Path(sqlite_path).exists():
logger.info("Checkpoint dual-read source does not exist, skipping: %s", sqlite_path)
continue
ctx = AsyncSqliteSaver.from_conn_string(sqlite_path)
source_saver = await ctx.__aenter__()
await source_saver.setup()
sources.append(
SQLiteCheckpointSource(
path=sqlite_path,
saver=source_saver,
context=ctx,
progress_path=Path(sqlite_path).with_suffix(Path(sqlite_path).suffix + ".pg-migration.json"),
)
)
if not sources:
logger.info("Checkpoint dual-read enabled but no SQLite sources were opened; using Postgres only")
yield saver
return
proxy = DualReadCheckpointer(
saver,
sources,
)
try:
yield proxy
finally:
await proxy.aclose_sources()
return
if config.type == "postgres":
if not _use_postgres_enabled(config):
conn_str = _sqlite_conn_str_for_postgres_fallback(config)
logger.info("Checkpointer: use_postgres=false; using SQLite fallback (%s)", conn_str)
async with _sqlite_checkpointer_from_conn_str(conn_str) as saver:
yield saver
return
if not config.connection_string:
raise ValueError(POSTGRES_CONN_REQUIRED)
# 连接池 + 健康检查,根治远程 Postgres 单连接空闲被关导致的 run 崩溃(见 _pg_pool_saver)。
async with _pg_pool_saver(config.connection_string) as saver:
if not _dual_read_enabled(config):
yield saver
return
from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver
from deerflow.runtime.checkpointer.checkpoint_migration import (
DualReadCheckpointer,
SQLiteCheckpointSource,
)
sources: list[SQLiteCheckpointSource] = []
for sqlite_path in _dual_read_paths(config):
if not Path(sqlite_path).exists():
logger.info("Checkpoint dual-read source does not exist, skipping: %s", sqlite_path)
continue
ctx = AsyncSqliteSaver.from_conn_string(sqlite_path)
source_saver = await ctx.__aenter__()
await source_saver.setup()
sources.append(
SQLiteCheckpointSource(
path=sqlite_path,
saver=source_saver,
context=ctx,
progress_path=Path(sqlite_path).with_suffix(Path(sqlite_path).suffix + ".pg-migration.json"),
)
)
if not sources:
logger.info("Checkpoint dual-read enabled but no SQLite sources were opened; using Postgres only")
yield saver
return
proxy = DualReadCheckpointer(
saver,
sources,
)
try:
yield proxy
finally:
await proxy.aclose_sources()
return
raise ValueError(f"Unknown checkpointer type: {config.type!r}")
@@ -204,16 +246,11 @@ async def _async_checkpointer_from_database(db_config) -> AsyncIterator[Checkpoi
return
if db_config.backend == "postgres":
try:
from langgraph.checkpoint.postgres.aio import AsyncPostgresSaver
except ImportError as exc:
raise ImportError(POSTGRES_INSTALL) from exc
if not db_config.postgres_url:
raise ValueError("database.postgres_url is required for the postgres backend")
async with AsyncPostgresSaver.from_conn_string(db_config.postgres_url) as saver:
await saver.setup()
# 连接池 + 健康检查(见 _pg_pool_saver),避免单连接空闲被关。
async with _pg_pool_saver(db_config.postgres_url) as saver:
yield saver
return