Use incremental storage in memory checkpointer

- This makes our checkpoint benchmarks more closely resemble the behavior of our prod checkpointers
- Also found and fixed a bug w multiple subgraphs in same node accidentally sharing checkpoints
This commit is contained in:
Nuno Campos
2025-03-20 16:11:36 -07:00
parent 77c833e1e5
commit 46b652a74c
6 changed files with 99 additions and 137 deletions
+2 -59
View File
@@ -1,4 +1,3 @@
import asyncio
import os
import tempfile
from collections import defaultdict
@@ -13,7 +12,6 @@ from langgraph.checkpoint.base import (
CheckpointMetadata,
CheckpointTuple,
SerializerProtocol,
copy_checkpoint,
)
from langgraph.checkpoint.memory import InMemorySaver, PersistentDict
@@ -63,69 +61,14 @@ class MemorySaverAssertImmutable(InMemorySaver):
self.storage_for_copies[thread_id][checkpoint_ns][saved["id"]]
)
== saved
)
), config["configurable"]["checkpoint_ns"]
self.storage_for_copies[thread_id][checkpoint_ns][checkpoint["id"]] = (
self.serde.dumps_typed(copy_checkpoint(checkpoint))
self.serde.dumps_typed(checkpoint)
)
# call super to write checkpoint
return super().put(config, checkpoint, metadata, new_versions)
class MemorySaverAssertCheckpointMetadata(InMemorySaver):
"""This custom checkpointer is for verifying that a run's configurable
fields are merged with the previous checkpoint config for each step in
the run. This is the desired behavior. Because the checkpointer's (a)put()
method is called for each step, the implementation of this checkpointer
should produce a side effect that can be asserted.
"""
def put(
self,
config: RunnableConfig,
checkpoint: Checkpoint,
metadata: CheckpointMetadata,
new_versions: ChannelVersions,
) -> None:
"""The implementation of put() merges config["configurable"] (a run's
configurable fields) with the metadata field. The state of the
checkpoint metadata can be asserted to confirm that the run's
configurable fields were merged with the previous checkpoint config.
"""
configurable = config["configurable"].copy()
# remove checkpoint_id to make testing simpler
checkpoint_id = configurable.pop("checkpoint_id", None)
thread_id = config["configurable"]["thread_id"]
checkpoint_ns = config["configurable"]["checkpoint_ns"]
self.storage[thread_id][checkpoint_ns].update(
{
checkpoint["id"]: (
self.serde.dumps_typed(checkpoint),
# merge configurable fields and metadata
self.serde.dumps_typed({**configurable, **metadata}),
checkpoint_id,
)
}
)
return {
"configurable": {
"thread_id": config["configurable"]["thread_id"],
"checkpoint_id": checkpoint["id"],
}
}
async def aput(
self,
config: RunnableConfig,
checkpoint: Checkpoint,
metadata: CheckpointMetadata,
new_versions: ChannelVersions,
) -> RunnableConfig:
return await asyncio.get_running_loop().run_in_executor(
None, self.put, config, checkpoint, metadata, new_versions
)
class MemorySaverNoPending(InMemorySaver):
def get_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
result = super().get_tuple(config)