langchain-ai/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-07-15 12:35:43 -04:00
Code Issues 314 Packages Projects Releases 17 Wiki Activity

Caching does not take function code into consideration #894

New Issue
Closed
opened 2026-02-20 17:42:16 -05:00 by yindo · 1 comment
yindo commented 2026-02-20 17:42:16 -05:00
Owner
Copy Link
Copy Source

Originally created by @pascalwhoop on GitHub (Aug 4, 2025).

Originally assigned to: @casparb on GitHub.

Checked other resources

  • This is a bug, not a usage question. For questions, please use the LangChain Forum (https://forum.langchain.com/).
  • I added a clear and detailed title that summarizes the issue.
  • I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example).
  • I included a self-contained, minimal example that demonstrates the issue INCLUDING all the relevant imports. The code run AS IS to reproduce the issue.

Description

A function cache should consider the function's codebase as a paramter as well. Since the function may be changed completely but the cache still returns the old values.

Joblib Memory already solved this a while ago and while it's not perfect, it's certainly more mature. I suggest to use this instead.
https://joblib.readthedocs.io/en/latest/auto_examples/memory_basic_usage.html

System Info

Originally created by @pascalwhoop on GitHub (Aug 4, 2025). Originally assigned to: @casparb on GitHub. ### Checked other resources - [x] This is a bug, not a usage question. For questions, please use the LangChain Forum (https://forum.langchain.com/). - [x] I added a clear and detailed title that summarizes the issue. - [x] I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example). - [x] I included a self-contained, minimal example that demonstrates the issue INCLUDING all the relevant imports. The code run AS IS to reproduce the issue. ### Description A function cache should consider the function's codebase as a paramter as well. Since the function may be changed completely but the cache still returns the old values. Joblib Memory already solved this a while ago and while it's not perfect, it's certainly more mature. I suggest to use this instead. https://joblib.readthedocs.io/en/latest/auto_examples/memory_basic_usage.html ### System Info -
yindo added the bugpending labels 2026-02-20 17:42:16 -05:00
yindo closed this issue 2026-02-20 17:42:16 -05:00
yindo commented 2026-02-20 17:42:16 -05:00
Author
Owner
Copy Link
Copy Source

@casparb commented on GitHub (Sep 16, 2025):

Hi @pascalwhoop, you can configure a custom CachePolicy.key_func to read your function's body:

from typing import TypedDict

from langgraph.cache.memory import InMemoryCache
from langgraph.graph import StateGraph
from langgraph.types import CachePolicy

class State(TypedDict):
    x: int
    result: int

# v1
def expensive_node(state: State) -> State:
    print('NOT CACHED v1')
    return {"result": state["x"] * 2}

cache = InMemoryCache() 

graph = (
    StateGraph(State)
    .add_node(expensive_node, cache_policy=CachePolicy(key_func=cache_key))
    .set_entry_point("expensive_node")
    .set_finish_point("expensive_node")
    .compile(cache=cache)  # NOTE: no checkpointer here
)

print("run #1:")
print(graph.invoke({"x": 5}, stream_mode="updates"))

# v2: different body
def expensive_node(state: State) -> State:
    print('NOT CACHED v2')
    return {"result": state["x"] * 3}

graph2 = (
    StateGraph(State)
    .add_node(expensive_node, cache_policy=CachePolicy(key_func=cache_key))
    .set_entry_point("expensive_node")
    .set_finish_point("expensive_node")
    .compile(cache=cache)
)

print("\nrun #2:")
print(graph2.invoke({"x": 5}, stream_mode="updates"))

You'll see that the cache won't be read from:

run #1:
NOT CACHED v1
[{'expensive_node': {'result': 10}}]

run #2:
NOT CACHED v2
[{'expensive_node': {'result': 15}}]
@casparb commented on GitHub (Sep 16, 2025): Hi @pascalwhoop, you can configure a custom [`CachePolicy.key_func`](https://langchain-ai.github.io/langgraph/reference/types/?h=key_func#langgraph.types.CachePolicy.key_func) to read your function's body: ```python from typing import TypedDict from langgraph.cache.memory import InMemoryCache from langgraph.graph import StateGraph from langgraph.types import CachePolicy class State(TypedDict): x: int result: int # v1 def expensive_node(state: State) -> State: print('NOT CACHED v1') return {"result": state["x"] * 2} cache = InMemoryCache() graph = ( StateGraph(State) .add_node(expensive_node, cache_policy=CachePolicy(key_func=cache_key)) .set_entry_point("expensive_node") .set_finish_point("expensive_node") .compile(cache=cache) # NOTE: no checkpointer here ) print("run #1:") print(graph.invoke({"x": 5}, stream_mode="updates")) # v2: different body def expensive_node(state: State) -> State: print('NOT CACHED v2') return {"result": state["x"] * 3} graph2 = ( StateGraph(State) .add_node(expensive_node, cache_policy=CachePolicy(key_func=cache_key)) .set_entry_point("expensive_node") .set_finish_point("expensive_node") .compile(cache=cache) ) print("\nrun #2:") print(graph2.invoke({"x": 5}, stream_mode="updates")) ``` You'll see that the cache won't be read from: ``` run #1: NOT CACHED v1 [{'expensive_node': {'result': 10}}] run #2: NOT CACHED v2 [{'expensive_node': {'result': 15}}] ```
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
agents
awaiting author revision
bug
change
chat models
checkpointer
ci
code quality
code quality
dependencies
documentation
drawing
duplicate
enhancement
good first issue
help wanted
invalid
maintainer
meta
missing information
not maintained by langchain
open-swe-auto
open-swe-max
open-swe-max-auto
pending
performance
pull-request
Mirrored from GitHub Pull Request
 question
requires design
sdk
server
stale
studio
tests
type checking
usage question
v0.5
v1.1
No Label bug pending
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/langgraph#894
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?