Support langgraph checkpointer (#1005)

* Add checkpointer configuration to config.example.yaml

- Introduced a new section for checkpointer configuration to enable state persistence for the embedded DeerFlowClient.
- Documented supported types: memory, sqlite, and postgres, along with examples for each.
- Clarified that the LangGraph Server manages its own state persistence separately.

* refactor(checkpointer): streamline checkpointer initialization and logging

* fix(uv.lock): update revision and add new wheel URLs for brotlicffi package

* feat: add langchain-anthropic dependency and update related configurations

* Fix checkpointer lifecycle, docstring, and path resolution bugs from PR #1005 review (#4)

* Initial plan

* Address all review suggestions from PR #1005

Co-authored-by: foreleven <4785594+foreleven@users.noreply.github.com>

* Fix resolve_path to always return real Path; move SQLite special-string handling to callers

Co-authored-by: foreleven <4785594+foreleven@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: foreleven <4785594+foreleven@users.noreply.github.com>

---------

Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com>
Co-authored-by: foreleven <4785594+foreleven@users.noreply.github.com>
This commit is contained in:
JeffJiang
2026-03-07 21:07:21 +08:00
committed by GitHub
parent 09325ca28f
commit d664ae5a4b
14 changed files with 819 additions and 84 deletions

View File

@@ -1,4 +1,5 @@
from .checkpointer import get_checkpointer, make_checkpointer, reset_checkpointer
from .lead_agent import make_lead_agent
from .thread_state import SandboxState, ThreadState
__all__ = ["make_lead_agent", "SandboxState", "ThreadState"]
__all__ = ["make_lead_agent", "SandboxState", "ThreadState", "get_checkpointer", "reset_checkpointer", "make_checkpointer"]

View File

@@ -0,0 +1,9 @@
from .async_provider import make_checkpointer
from .provider import checkpointer_context, get_checkpointer, reset_checkpointer
__all__ = [
"get_checkpointer",
"reset_checkpointer",
"checkpointer_context",
"make_checkpointer",
]

View File

@@ -0,0 +1,107 @@
"""Async checkpointer factory.
Provides an **async context manager** for long-running async servers that need
proper resource cleanup.
Supported backends: memory, sqlite, postgres.
Usage (e.g. FastAPI lifespan)::
from src.agents.checkpointer.async_provider import make_checkpointer
async with make_checkpointer() as checkpointer:
app.state.checkpointer = checkpointer # None if not configured
For sync usage see :mod:`src.agents.checkpointer.provider`.
"""
from __future__ import annotations
import contextlib
import logging
from collections.abc import AsyncIterator
from langgraph.types import Checkpointer
from src.agents.checkpointer.provider import (
POSTGRES_CONN_REQUIRED,
POSTGRES_INSTALL,
SQLITE_INSTALL,
_resolve_sqlite_conn_str,
)
from src.config.app_config import get_app_config
logger = logging.getLogger(__name__)
# ---------------------------------------------------------------------------
# Async factory
# ---------------------------------------------------------------------------
@contextlib.asynccontextmanager
async def _async_checkpointer(config) -> AsyncIterator[Checkpointer]:
"""Async context manager that constructs and tears down a checkpointer."""
if config.type == "memory":
from langgraph.checkpoint.memory import InMemorySaver
yield InMemorySaver()
return
if config.type == "sqlite":
try:
from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver
except ImportError as exc:
raise ImportError(SQLITE_INSTALL) from exc
import pathlib
conn_str = _resolve_sqlite_conn_str(config.connection_string or "store.db")
# Only create parent directories for real filesystem paths
if conn_str != ":memory:" and not conn_str.startswith("file:"):
pathlib.Path(conn_str).parent.mkdir(parents=True, exist_ok=True)
async with AsyncSqliteSaver.from_conn_string(conn_str) as saver:
await saver.setup()
yield saver
return
if config.type == "postgres":
try:
from langgraph.checkpoint.postgres.aio import AsyncPostgresSaver
except ImportError as exc:
raise ImportError(POSTGRES_INSTALL) from exc
if not config.connection_string:
raise ValueError(POSTGRES_CONN_REQUIRED)
async with AsyncPostgresSaver.from_conn_string(config.connection_string) as saver:
await saver.setup()
yield saver
return
raise ValueError(f"Unknown checkpointer type: {config.type!r}")
# ---------------------------------------------------------------------------
# Public async context manager
# ---------------------------------------------------------------------------
@contextlib.asynccontextmanager
async def make_checkpointer() -> AsyncIterator[Checkpointer | None]:
"""Async context manager that yields a checkpointer for the caller's lifetime.
Resources are opened on enter and closed on exit — no global state::
async with make_checkpointer() as checkpointer:
app.state.checkpointer = checkpointer
Yields ``None`` when no checkpointer is configured in *config.yaml*.
"""
config = get_app_config()
if config.checkpointer is None:
yield None
return
async with _async_checkpointer(config.checkpointer) as saver:
yield saver

View File

@@ -0,0 +1,179 @@
"""Sync checkpointer factory.
Provides a **sync singleton** and a **sync context manager** for LangGraph
graph compilation and CLI tools.
Supported backends: memory, sqlite, postgres.
Usage::
from src.agents.checkpointer.provider import get_checkpointer, checkpointer_context
# Singleton — reused across calls, closed on process exit
cp = get_checkpointer()
# One-shot — fresh connection, closed on block exit
with checkpointer_context() as cp:
graph.invoke(input, config={"configurable": {"thread_id": "1"}})
"""
from __future__ import annotations
import contextlib
import logging
from collections.abc import Iterator
from langgraph.types import Checkpointer
from src.config.app_config import get_app_config
from src.config.checkpointer_config import CheckpointerConfig
from src.config.paths import resolve_path
logger = logging.getLogger(__name__)
# ---------------------------------------------------------------------------
# Error message constants — imported by aio.provider too
# ---------------------------------------------------------------------------
SQLITE_INSTALL = "langgraph-checkpoint-sqlite is required for the SQLite checkpointer. Install it with: uv add langgraph-checkpoint-sqlite"
POSTGRES_INSTALL = "langgraph-checkpoint-postgres is required for the PostgreSQL checkpointer. Install it with: uv add langgraph-checkpoint-postgres psycopg[binary] psycopg-pool"
POSTGRES_CONN_REQUIRED = "checkpointer.connection_string is required for the postgres backend"
# ---------------------------------------------------------------------------
# Sync factory
# ---------------------------------------------------------------------------
def _resolve_sqlite_conn_str(raw: str) -> str:
"""Return a SQLite connection string ready for use with ``SqliteSaver``.
SQLite special strings (``":memory:"`` and ``file:`` URIs) are returned
unchanged. Plain filesystem paths — relative or absolute — are resolved
to an absolute string via :func:`resolve_path`.
"""
if raw == ":memory:" or raw.startswith("file:"):
return raw
return str(resolve_path(raw))
@contextlib.contextmanager
def _sync_checkpointer_cm(config: CheckpointerConfig) -> Iterator[Checkpointer]:
"""Context manager that creates and tears down a sync checkpointer.
Returns a configured ``Checkpointer`` instance. Resource cleanup for any
underlying connections or pools is handled by higher-level helpers in
this module (such as the singleton factory or context manager); this
function does not return a separate cleanup callback.
"""
if config.type == "memory":
from langgraph.checkpoint.memory import InMemorySaver
logger.info("Checkpointer: using InMemorySaver (in-process, not persistent)")
yield InMemorySaver()
return
if config.type == "sqlite":
try:
from langgraph.checkpoint.sqlite import SqliteSaver
except ImportError as exc:
raise ImportError(SQLITE_INSTALL) from exc
conn_str = _resolve_sqlite_conn_str(config.connection_string or "store.db")
with SqliteSaver.from_conn_string(conn_str) as saver:
saver.setup()
logger.info("Checkpointer: using SqliteSaver (%s)", conn_str)
yield saver
return
if config.type == "postgres":
try:
from langgraph.checkpoint.postgres import PostgresSaver
except ImportError as exc:
raise ImportError(POSTGRES_INSTALL) from exc
if not config.connection_string:
raise ValueError(POSTGRES_CONN_REQUIRED)
with PostgresSaver.from_conn_string(config.connection_string) as saver:
saver.setup()
logger.info("Checkpointer: using PostgresSaver")
yield saver
return
raise ValueError(f"Unknown checkpointer type: {config.type!r}")
# ---------------------------------------------------------------------------
# Sync singleton
# ---------------------------------------------------------------------------
_checkpointer: Checkpointer = None
_checkpointer_ctx = None # open context manager keeping the connection alive
def get_checkpointer() -> Checkpointer | None:
"""Return the global sync checkpointer singleton, creating it on first call.
Returns ``None`` when no checkpointer is configured in *config.yaml*.
Raises:
ImportError: If the required package for the configured backend is not installed.
ValueError: If ``connection_string`` is missing for a backend that requires it.
"""
global _checkpointer, _checkpointer_ctx
if _checkpointer is not None:
return _checkpointer
from src.config.checkpointer_config import get_checkpointer_config
config = get_checkpointer_config()
if config is None:
return None
_checkpointer_ctx = _sync_checkpointer_cm(config)
_checkpointer = _checkpointer_ctx.__enter__()
return _checkpointer
def reset_checkpointer() -> None:
"""Reset the sync singleton, forcing recreation on the next call.
Closes any open backend connections and clears the cached instance.
Useful in tests or after a configuration change.
"""
global _checkpointer, _checkpointer_ctx
if _checkpointer_ctx is not None:
try:
_checkpointer_ctx.__exit__(None, None, None)
except Exception:
logger.warning("Error during checkpointer cleanup", exc_info=True)
_checkpointer_ctx = None
_checkpointer = None
# ---------------------------------------------------------------------------
# Sync context manager
# ---------------------------------------------------------------------------
@contextlib.contextmanager
def checkpointer_context() -> Iterator[Checkpointer | None]:
"""Sync context manager that yields a checkpointer and cleans up on exit.
Unlike :func:`get_checkpointer`, this does **not** cache the instance —
each ``with`` block creates and destroys its own connection. Use it in
CLI scripts or tests where you want deterministic cleanup::
with checkpointer_context() as cp:
graph.invoke(input, config={"configurable": {"thread_id": "1"}})
"""
config = get_app_config()
if config.checkpointer is None:
yield None
return
with _sync_checkpointer_cm(config.checkpointer) as saver:
yield saver