Files
wehub-resource-sync a7d6d88f6f
CI / changes (push) Has been cancelled
CI / cd libs/checkpoint (push) Has been cancelled
CI / cd libs/checkpoint-conformance (push) Has been cancelled
CI / cd libs/checkpoint-postgres (push) Has been cancelled
CI / cd libs/checkpoint-sqlite (push) Has been cancelled
CI / cd libs/cli (push) Has been cancelled
CI / cd libs/prebuilt (push) Has been cancelled
CI / cd libs/sdk-py (push) Has been cancelled
CI / cd libs/langgraph (push) Has been cancelled
CI / Check SDK methods matching (push) Has been cancelled
CI / Check CLI schema hasn't changed #3.13 (push) Has been cancelled
CI / CLI integration test (push) Has been cancelled
CI / sdk-py integration test (push) Has been cancelled
CI / CI Success (push) Has been cancelled
baseline / benchmark (push) Has been cancelled
Deploy Redirects to GitHub Pages / deploy (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 12:37:18 +08:00

739 lines
29 KiB
Python

from __future__ import annotations
import asyncio
import json
import random
import threading
from collections.abc import AsyncIterator, Callable, Iterator, Mapping, Sequence
from contextlib import asynccontextmanager
from typing import Any, TypeVar, cast
import aiosqlite
from langchain_core.runnables import RunnableConfig
from langgraph.checkpoint.base import (
WRITES_IDX_MAP,
BaseCheckpointSaver,
ChannelVersions,
Checkpoint,
CheckpointMetadata,
CheckpointTuple,
DeltaChannelHistory,
SerializerProtocol,
get_checkpoint_id,
get_checkpoint_metadata,
)
from langgraph.checkpoint.serde.jsonplus import JsonPlusSerializer
from langgraph.checkpoint.sqlite._delta import (
DELTA_STAGE1_SQL,
build_delta_channels_writes_history,
build_delta_stage2_sql,
step_walk_with_row,
)
from langgraph.checkpoint.sqlite.utils import search_where
T = TypeVar("T", bound=Callable)
class AsyncSqliteSaver(BaseCheckpointSaver[str]):
"""An asynchronous checkpoint saver that stores checkpoints in a SQLite database.
This class provides an asynchronous interface for saving and retrieving checkpoints
using a SQLite database. It's designed for use in asynchronous environments and
offers better performance for I/O-bound operations compared to synchronous alternatives.
Attributes:
conn (aiosqlite.Connection): The asynchronous SQLite database connection.
serde (SerializerProtocol): The serializer used for encoding/decoding checkpoints.
Tip:
Requires the [aiosqlite](https://pypi.org/project/aiosqlite/) package.
Install it with `pip install aiosqlite`.
Warning:
While this class supports asynchronous checkpointing, it is not recommended
for production workloads due to limitations in SQLite's write performance.
For production use, consider a more robust database like PostgreSQL.
Tip:
Remember to **close the database connection** after executing your code,
otherwise, you may see the graph "hang" after execution (since the program
will not exit until the connection is closed).
The easiest way is to use the `async with` statement as shown in the examples.
```python
async with AsyncSqliteSaver.from_conn_string("checkpoints.sqlite") as saver:
# Your code here
graph = builder.compile(checkpointer=saver)
config = {"configurable": {"thread_id": "thread-1"}}
async for event in graph.astream_events(..., config, version="v1"):
print(event)
```
Examples:
Usage within StateGraph:
```pycon
>>> import asyncio
>>>
>>> from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver
>>> from langgraph.graph import StateGraph
>>>
>>> async def main():
>>> builder = StateGraph(int)
>>> builder.add_node("add_one", lambda x: x + 1)
>>> builder.set_entry_point("add_one")
>>> builder.set_finish_point("add_one")
>>> async with AsyncSqliteSaver.from_conn_string("checkpoints.db") as memory:
>>> graph = builder.compile(checkpointer=memory)
>>> coro = graph.ainvoke(1, {"configurable": {"thread_id": "thread-1"}})
>>> print(await asyncio.gather(coro))
>>>
>>> asyncio.run(main())
Output: [2]
```
Raw usage:
```pycon
>>> import asyncio
>>> import aiosqlite
>>> from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver
>>>
>>> async def main():
>>> async with aiosqlite.connect("checkpoints.db") as conn:
... saver = AsyncSqliteSaver(conn)
... config = {"configurable": {"thread_id": "1", "checkpoint_ns": ""}}
... checkpoint = {"ts": "2023-05-03T10:00:00Z", "data": {"key": "value"}, "id": "0c62ca34-ac19-445d-bbb0-5b4984975b2a"}
... saved_config = await saver.aput(config, checkpoint, {}, {})
... print(saved_config)
>>> asyncio.run(main())
{'configurable': {'thread_id': '1', 'checkpoint_ns': '', 'checkpoint_id': '0c62ca34-ac19-445d-bbb0-5b4984975b2a'}}
```
"""
lock: asyncio.Lock
is_setup: bool
def __init__(
self,
conn: aiosqlite.Connection,
*,
serde: SerializerProtocol | None = None,
):
super().__init__(serde=serde)
self.jsonplus_serde = JsonPlusSerializer()
self.conn = conn
self.lock = asyncio.Lock()
self.loop = asyncio.get_running_loop()
self.is_setup = False
@classmethod
@asynccontextmanager
async def from_conn_string(
cls, conn_string: str
) -> AsyncIterator[AsyncSqliteSaver]:
"""Create a new AsyncSqliteSaver instance from a connection string.
Args:
conn_string: The SQLite connection string.
Yields:
AsyncSqliteSaver: A new AsyncSqliteSaver instance.
"""
async with aiosqlite.connect(conn_string) as conn:
yield cls(conn)
def get_tuple(self, config: RunnableConfig) -> CheckpointTuple | None:
"""Get a checkpoint tuple from the database.
This method retrieves a checkpoint tuple from the SQLite database based on the
provided config. If the config contains a `checkpoint_id` key, the checkpoint with
the matching thread ID and checkpoint ID is retrieved. Otherwise, the latest checkpoint
for the given thread ID is retrieved.
Args:
config: The config to use for retrieving the checkpoint.
Returns:
The retrieved checkpoint tuple, or None if no matching checkpoint was found.
"""
try:
# check if we are in the main thread, only bg threads can block
# we don't check in other methods to avoid the overhead
if asyncio.get_running_loop() is self.loop:
raise asyncio.InvalidStateError(
"Synchronous calls to AsyncSqliteSaver are only allowed from a "
"different thread. From the main thread, use the async interface. "
"For example, use `await checkpointer.aget_tuple(...)` or `await "
"graph.ainvoke(...)`."
)
except RuntimeError:
pass
return asyncio.run_coroutine_threadsafe(
self.aget_tuple(config), self.loop
).result()
def list(
self,
config: RunnableConfig | None,
*,
filter: dict[str, Any] | None = None,
before: RunnableConfig | None = None,
limit: int | None = None,
) -> Iterator[CheckpointTuple]:
"""List checkpoints from the database asynchronously.
This method retrieves a list of checkpoint tuples from the SQLite database based
on the provided config. The checkpoints are ordered by checkpoint ID in descending order (newest first).
Args:
config: Base configuration for filtering checkpoints.
filter: Additional filtering criteria for metadata.
before: If provided, only checkpoints before the specified checkpoint ID are returned.
limit: Maximum number of checkpoints to return.
Yields:
An iterator of matching checkpoint tuples.
"""
try:
# check if we are in the main thread, only bg threads can block
# we don't check in other methods to avoid the overhead
if asyncio.get_running_loop() is self.loop:
raise asyncio.InvalidStateError(
"Synchronous calls to AsyncSqliteSaver are only allowed from a "
"different thread. From the main thread, use the async interface. "
"For example, use `checkpointer.alist(...)` or `await "
"graph.ainvoke(...)`."
)
except RuntimeError:
pass
aiter_ = self.alist(config, filter=filter, before=before, limit=limit)
while True:
try:
yield asyncio.run_coroutine_threadsafe(
anext(aiter_), # type: ignore[arg-type] # noqa: F821
self.loop,
).result()
except StopAsyncIteration:
break
def put(
self,
config: RunnableConfig,
checkpoint: Checkpoint,
metadata: CheckpointMetadata,
new_versions: ChannelVersions,
) -> RunnableConfig:
"""Save a checkpoint to the database.
This method saves a checkpoint to the SQLite database. The checkpoint is associated
with the provided config and its parent config (if any).
Args:
config: The config to associate with the checkpoint.
checkpoint: The checkpoint to save.
metadata: Additional metadata to save with the checkpoint.
new_versions: New channel versions as of this write.
Returns:
RunnableConfig: Updated configuration after storing the checkpoint.
"""
return asyncio.run_coroutine_threadsafe(
self.aput(config, checkpoint, metadata, new_versions), self.loop
).result()
def put_writes(
self,
config: RunnableConfig,
writes: Sequence[tuple[str, Any]],
task_id: str,
task_path: str = "",
) -> None:
return asyncio.run_coroutine_threadsafe(
self.aput_writes(config, writes, task_id, task_path), self.loop
).result()
def delete_thread(self, thread_id: str) -> None:
"""Delete all checkpoints and writes associated with a thread ID.
Args:
thread_id: The thread ID to delete.
Returns:
None
"""
try:
# check if we are in the main thread, only bg threads can block
# we don't check in other methods to avoid the overhead
if asyncio.get_running_loop() is self.loop:
raise asyncio.InvalidStateError(
"Synchronous calls to AsyncSqliteSaver are only allowed from a "
"different thread. From the main thread, use the async interface. "
"For example, use `checkpointer.alist(...)` or `await "
"graph.ainvoke(...)`."
)
except RuntimeError:
pass
return asyncio.run_coroutine_threadsafe(
self.adelete_thread(thread_id), self.loop
).result()
def get_delta_channel_history(
self, *, config: RunnableConfig, channels: Sequence[str]
) -> Mapping[str, DeltaChannelHistory]:
"""Sync bridge to `aget_delta_channel_history`.
Mirrors the same cross-thread guard as `get_tuple` /
`delete_thread` — calling from the loop thread raises rather than
deadlocking.
"""
try:
if asyncio.get_running_loop() is self.loop:
raise asyncio.InvalidStateError(
"Synchronous calls to AsyncSqliteSaver are only allowed from a "
"different thread. From the main thread, use the async interface. "
"For example, use `await checkpointer.aget_delta_channel_history(...)`."
)
except RuntimeError:
pass
return asyncio.run_coroutine_threadsafe(
self.aget_delta_channel_history(config=config, channels=channels),
self.loop,
).result()
async def setup(self) -> None:
"""Set up the checkpoint database asynchronously.
This method creates the necessary tables in the SQLite database if they don't
already exist. It is called automatically when needed and should not be called
directly by the user.
"""
async with self.lock:
if self.is_setup:
return
await _ensure_connected(self.conn)
async with self.conn.executescript(
"""
PRAGMA journal_mode=WAL;
CREATE TABLE IF NOT EXISTS checkpoints (
thread_id TEXT NOT NULL,
checkpoint_ns TEXT NOT NULL DEFAULT '',
checkpoint_id TEXT NOT NULL,
parent_checkpoint_id TEXT,
type TEXT,
checkpoint BLOB,
metadata BLOB,
PRIMARY KEY (thread_id, checkpoint_ns, checkpoint_id)
);
CREATE TABLE IF NOT EXISTS writes (
thread_id TEXT NOT NULL,
checkpoint_ns TEXT NOT NULL DEFAULT '',
checkpoint_id TEXT NOT NULL,
task_id TEXT NOT NULL,
idx INTEGER NOT NULL,
channel TEXT NOT NULL,
type TEXT,
value BLOB,
PRIMARY KEY (thread_id, checkpoint_ns, checkpoint_id, task_id, idx)
);
"""
):
await self.conn.commit()
self.is_setup = True
async def aget_tuple(self, config: RunnableConfig) -> CheckpointTuple | None:
"""Get a checkpoint tuple from the database asynchronously.
This method retrieves a checkpoint tuple from the SQLite database based on the
provided config. If the config contains a `checkpoint_id` key, the checkpoint with
the matching thread ID and checkpoint ID is retrieved. Otherwise, the latest checkpoint
for the given thread ID is retrieved.
Args:
config: The config to use for retrieving the checkpoint.
Returns:
The retrieved checkpoint tuple, or None if no matching checkpoint was found.
"""
await self.setup()
checkpoint_ns = config["configurable"].get("checkpoint_ns", "")
async with self.lock, self.conn.cursor() as cur:
# find the latest checkpoint for the thread_id
if checkpoint_id := get_checkpoint_id(config):
await cur.execute(
"SELECT thread_id, checkpoint_id, parent_checkpoint_id, type, checkpoint, metadata FROM checkpoints WHERE thread_id = ? AND checkpoint_ns = ? AND checkpoint_id = ?",
(
str(config["configurable"]["thread_id"]),
checkpoint_ns,
checkpoint_id,
),
)
else:
await cur.execute(
"SELECT thread_id, checkpoint_id, parent_checkpoint_id, type, checkpoint, metadata FROM checkpoints WHERE thread_id = ? AND checkpoint_ns = ? ORDER BY checkpoint_id DESC LIMIT 1",
(str(config["configurable"]["thread_id"]), checkpoint_ns),
)
# if a checkpoint is found, return it
if value := await cur.fetchone():
(
thread_id,
checkpoint_id,
parent_checkpoint_id,
type,
checkpoint,
metadata,
) = value
if not get_checkpoint_id(config):
config = {
"configurable": {
"thread_id": thread_id,
"checkpoint_ns": checkpoint_ns,
"checkpoint_id": checkpoint_id,
}
}
# find any pending writes
await cur.execute(
"SELECT task_id, channel, type, value FROM writes WHERE thread_id = ? AND checkpoint_ns = ? AND checkpoint_id = ? ORDER BY task_id, idx",
(
str(config["configurable"]["thread_id"]),
checkpoint_ns,
str(config["configurable"]["checkpoint_id"]),
),
)
# deserialize the checkpoint and metadata
return CheckpointTuple(
config,
self.serde.loads_typed((type, checkpoint)),
cast(
CheckpointMetadata,
(json.loads(metadata) if metadata is not None else {}),
),
(
{
"configurable": {
"thread_id": thread_id,
"checkpoint_ns": checkpoint_ns,
"checkpoint_id": parent_checkpoint_id,
}
}
if parent_checkpoint_id
else None
),
[
(task_id, channel, self.serde.loads_typed((type, value)))
async for task_id, channel, type, value in cur
],
)
async def alist(
self,
config: RunnableConfig | None,
*,
filter: dict[str, Any] | None = None,
before: RunnableConfig | None = None,
limit: int | None = None,
) -> AsyncIterator[CheckpointTuple]:
"""List checkpoints from the database asynchronously.
This method retrieves a list of checkpoint tuples from the SQLite database based
on the provided config. The checkpoints are ordered by checkpoint ID in descending order (newest first).
Args:
config: Base configuration for filtering checkpoints.
filter: Additional filtering criteria for metadata.
before: If provided, only checkpoints before the specified checkpoint ID are returned.
limit: Maximum number of checkpoints to return.
Yields:
An asynchronous iterator of matching checkpoint tuples.
"""
await self.setup()
where, params = search_where(config, filter, before)
query = f"""SELECT thread_id, checkpoint_ns, checkpoint_id, parent_checkpoint_id, type, checkpoint, metadata
FROM checkpoints
{where}
ORDER BY checkpoint_id DESC"""
if limit is not None:
query += " LIMIT ?"
params = (*params, limit)
async with (
self.lock,
self.conn.execute(query, params) as cur,
self.conn.cursor() as wcur,
):
async for (
thread_id,
checkpoint_ns,
checkpoint_id,
parent_checkpoint_id,
type,
checkpoint,
metadata,
) in cur:
await wcur.execute(
"SELECT task_id, channel, type, value FROM writes WHERE thread_id = ? AND checkpoint_ns = ? AND checkpoint_id = ? ORDER BY task_id, idx",
(thread_id, checkpoint_ns, checkpoint_id),
)
yield CheckpointTuple(
{
"configurable": {
"thread_id": thread_id,
"checkpoint_ns": checkpoint_ns,
"checkpoint_id": checkpoint_id,
}
},
self.serde.loads_typed((type, checkpoint)),
cast(
CheckpointMetadata,
(json.loads(metadata) if metadata is not None else {}),
),
(
{
"configurable": {
"thread_id": thread_id,
"checkpoint_ns": checkpoint_ns,
"checkpoint_id": parent_checkpoint_id,
}
}
if parent_checkpoint_id
else None
),
[
(task_id, channel, self.serde.loads_typed((type, value)))
async for task_id, channel, type, value in wcur
],
)
async def aput(
self,
config: RunnableConfig,
checkpoint: Checkpoint,
metadata: CheckpointMetadata,
new_versions: ChannelVersions,
) -> RunnableConfig:
"""Save a checkpoint to the database asynchronously.
This method saves a checkpoint to the SQLite database. The checkpoint is associated
with the provided config and its parent config (if any).
Args:
config: The config to associate with the checkpoint.
checkpoint: The checkpoint to save.
metadata: Additional metadata to save with the checkpoint.
new_versions: New channel versions as of this write.
Returns:
RunnableConfig: Updated configuration after storing the checkpoint.
"""
await self.setup()
thread_id = config["configurable"]["thread_id"]
checkpoint_ns = config["configurable"]["checkpoint_ns"]
type_, serialized_checkpoint = self.serde.dumps_typed(checkpoint)
serialized_metadata = json.dumps(
get_checkpoint_metadata(config, metadata), ensure_ascii=False
).encode("utf-8", "ignore")
async with (
self.lock,
self.conn.execute(
"INSERT OR REPLACE INTO checkpoints (thread_id, checkpoint_ns, checkpoint_id, parent_checkpoint_id, type, checkpoint, metadata) VALUES (?, ?, ?, ?, ?, ?, ?)",
(
str(config["configurable"]["thread_id"]),
checkpoint_ns,
checkpoint["id"],
config["configurable"].get("checkpoint_id"),
type_,
serialized_checkpoint,
serialized_metadata,
),
),
):
await self.conn.commit()
return {
"configurable": {
"thread_id": thread_id,
"checkpoint_ns": checkpoint_ns,
"checkpoint_id": checkpoint["id"],
}
}
async def aput_writes(
self,
config: RunnableConfig,
writes: Sequence[tuple[str, Any]],
task_id: str,
task_path: str = "",
) -> None:
"""Store intermediate writes linked to a checkpoint asynchronously.
This method saves intermediate writes associated with a checkpoint to the database.
Args:
config: Configuration of the related checkpoint.
writes: List of writes to store, each as (channel, value) pair.
task_id: Identifier for the task creating the writes.
task_path: Path of the task creating the writes.
"""
query = (
"INSERT OR REPLACE INTO writes (thread_id, checkpoint_ns, checkpoint_id, task_id, idx, channel, type, value) VALUES (?, ?, ?, ?, ?, ?, ?, ?)"
if all(w[0] in WRITES_IDX_MAP for w in writes)
else "INSERT OR IGNORE INTO writes (thread_id, checkpoint_ns, checkpoint_id, task_id, idx, channel, type, value) VALUES (?, ?, ?, ?, ?, ?, ?, ?)"
)
await self.setup()
async with self.lock, self.conn.cursor() as cur:
await cur.executemany(
query,
[
(
str(config["configurable"]["thread_id"]),
str(config["configurable"]["checkpoint_ns"]),
str(config["configurable"]["checkpoint_id"]),
task_id,
WRITES_IDX_MAP.get(channel, idx),
channel,
*self.serde.dumps_typed(value),
)
for idx, (channel, value) in enumerate(writes)
],
)
await self.conn.commit()
async def adelete_thread(self, thread_id: str) -> None:
"""Delete all checkpoints and writes associated with a thread ID.
Args:
thread_id: The thread ID to delete.
Returns:
None
"""
async with self.lock, self.conn.cursor() as cur:
await cur.execute(
"DELETE FROM checkpoints WHERE thread_id = ?",
(str(thread_id),),
)
await cur.execute(
"DELETE FROM writes WHERE thread_id = ?",
(str(thread_id),),
)
await self.conn.commit()
async def aget_delta_channel_history(
self, *, config: RunnableConfig, channels: Sequence[str]
) -> Mapping[str, DeltaChannelHistory]:
"""Fast-path override of `BaseCheckpointSaver.aget_delta_channel_history`.
See `SqliteSaver.get_delta_channel_history` for design notes; this
is the async equivalent using `aiosqlite` cursors. Stage 1 pages
the parent chain newest-first and Python-deserializes each
checkpoint blob to find per-channel snapshots; stage 2 fetches
only the relevant writes via per-channel UNION ALL.
"""
if not channels:
return {}
channels = list(channels)
await self.setup()
thread_id = str(config["configurable"]["thread_id"])
checkpoint_ns = config["configurable"].get("checkpoint_ns", "")
checkpoint_id = get_checkpoint_id(config)
if checkpoint_id is None:
target = await self.aget_tuple(config)
if target is None:
return {ch: {"writes": []} for ch in channels}
checkpoint_id = target.config["configurable"]["checkpoint_id"]
chain_by_ch: dict[str, list[str]] = {ch: [] for ch in channels}
seed_val_by_ch: dict[str, Any] = {}
walk_state: dict[str, Any] = {}
seeded: set[str] = set()
async with self.lock, self.conn.cursor() as cur:
await cur.execute(
DELTA_STAGE1_SQL, (thread_id, checkpoint_ns, checkpoint_id)
)
async for row in cur:
cid, parent_cid, type_tag, blob = row
if step_walk_with_row(
cid=cid,
parent_cid=parent_cid,
type_tag=type_tag,
blob=blob,
target_id=checkpoint_id,
serde=self.serde,
chain_by_ch=chain_by_ch,
seed_val_by_ch=seed_val_by_ch,
walk_state=walk_state,
seeded=seeded,
channels=channels,
):
break
channels_with_chain = [ch for ch in channels if chain_by_ch[ch]]
stage2_sql = build_delta_stage2_sql(
chain_lens=[len(chain_by_ch[ch]) for ch in channels_with_chain],
)
if stage2_sql:
stage2_params: list[Any] = []
for ch in channels_with_chain:
stage2_params.extend(
[thread_id, checkpoint_ns, ch, *chain_by_ch[ch]]
)
await cur.execute(stage2_sql, stage2_params)
stage2_rows = cast(
"list[tuple[str, str, str, int, str, bytes]]",
await cur.fetchall(),
)
else:
stage2_rows = []
return build_delta_channels_writes_history(
channels=channels,
chain_by_ch=chain_by_ch,
seed_val_by_ch=seed_val_by_ch,
seeded=seeded,
stage2_rows=stage2_rows,
serde=self.serde,
)
def get_next_version(self, current: str | None, channel: None) -> str:
"""Generate the next version ID for a channel.
This method creates a new version identifier for a channel based on its current version.
Args:
current (Optional[str]): The current version identifier of the channel.
Returns:
str: The next version identifier, which is guaranteed to be monotonically increasing.
"""
if current is None:
current_v = 0
elif isinstance(current, int):
current_v = current
else:
current_v = int(current.split(".")[0])
next_v = current_v + 1
next_h = random.random()
return f"{next_v:032}.{next_h:016}"
async def _ensure_connected(conn: aiosqlite.Connection) -> None:
if not _CONN_STARTED_CHECK(conn):
await conn
def _build_conn_started_check() -> Callable[[aiosqlite.Connection], bool]:
is_alive = getattr(aiosqlite.Connection, "is_alive", None)
if callable(is_alive):
return lambda conn: conn.is_alive() # type: ignore[attr-defined]
def _started(conn: aiosqlite.Connection) -> bool:
thread: threading.Thread | None = getattr(conn, "_thread", None)
return False if thread is None else thread.is_alive()
return _started
_CONN_STARTED_CHECK = _build_conn_started_check()