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

Subgraph checkpointer=True causes subgraph to be skipped #422

New Issue
Closed
opened 2026-02-20 17:40:02 -05:00 by yindo · 5 comments
yindo commented 2026-02-20 17:40:02 -05:00
Owner
Copy Link
Copy Source

Originally created by @shengbo-ma on GitHub (Jan 25, 2025).

Checked other resources

  • This is a bug, not a usage question. For questions, please use GitHub Discussions.
  • 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.

Example Code

from typing import Literal

from langchain_core.runnables import RunnableConfig
from langgraph.checkpoint.memory import MemorySaver
from langgraph.graph import END, START, StateGraph
from langgraph.graph.state import Command
from langgraph.types import interrupt
from rich import get_console
from typing_extensions import TypedDict

###############
# Subgraph
###############


class SubGraphState(TypedDict, total=False):
    parent_counter: int
    sub_counter: int


def subgraph_accumulator(state: SubGraphState) -> SubGraphState:
    get_console().print("---subgraph counter node---")
    get_console().print(f"{state = }")
    # ask for human approval
    human_feedback = interrupt("get human feedback")
    print(f"{human_feedback = }")

    # continue counting
    sub_counter = state["sub_counter"] + 1 if "sub_counter" in state else 1
    return {"sub_counter": sub_counter}


sub_graph = (
    StateGraph(SubGraphState)
    .add_node(subgraph_accumulator)
    .add_edge(START, subgraph_accumulator.__name__)
    .add_edge(subgraph_accumulator.__name__, END)
    .compile(
        checkpointer=True,  # BUG: This causes an issue that subgraph nodes are not executed at all after first interruption
    )
)
sub_graph.name = "sub"

###############
# Parent Graph
###############

MAX_ITERATION = 3


class ParentGraphState(TypedDict):
    parent_counter: int


def parent_graph_accumulator(
    state: ParentGraphState,
) -> Command[Literal["sub", "__end__"]]:
    print("---parent counter node---")
    get_console().print(f"{state = }")
    parent_counter = state["parent_counter"] + 1 if "parent_counter" in state else 0

    # goto end when max iteration reaches
    goto = sub_graph.get_name() if parent_counter < MAX_ITERATION else END
    get_console().print(f"going to node {goto}")
    return Command(
        update={
            "parent_counter": parent_counter,
        },
        goto=goto,
    )


parent_agent = (
    StateGraph(ParentGraphState)
    .add_node(parent_graph_accumulator)
    .add_node(sub_graph)
    .add_edge(START, parent_graph_accumulator.__name__)
    .add_edge(sub_graph.get_name(), parent_graph_accumulator.__name__)
    .compile(checkpointer=MemorySaver())
)

# visualize graph
mermaid_graph = parent_agent.get_graph(xray=True).draw_mermaid()
print(mermaid_graph)

###############
# Conversation
###############

config: RunnableConfig = {"configurable": {"thread_id": "42"}, "recursion_limit": MAX_ITERATION+1}

inputs = [
    ParentGraphState(parent_counter=0),
    Command(resume="human feedback 1"),
    Command(resume="human feedback 2"),
]
for input_ in inputs:
    print(f"{input_ = }")
    for event in parent_agent.stream(
        # resume the conversation
        input_,
        config,
        stream_mode="updates",
        subgraphs=True,
    ):
        print("Streaming event ...")
        print(event)

Error Message and Stack Trace (if applicable)

input_ = {'parent_counter': 0}
---parent counter node---
state = {'parent_counter': 0}
going to node sub
Streaming event ...
((), {'parent_graph_accumulator': {'parent_counter': 1}})
---subgraph counter node---
state = {'parent_counter': 1}
Streaming event ...
((), {'__interrupt__': (Interrupt(value='get human feedback', resumable=True, ns=['sub', 'subgraph_accumulator:f187d019-da4b-d432-bcd2-cea142aa7e35'], when='during'),)})
input_ = Command(resume='human feedback 1')
---subgraph counter node---
state = {'parent_counter': 1}
human_feedback = 'human feedback 1'
Streaming event ...
(('sub',), {'subgraph_accumulator': {'sub_counter': 1}})
Streaming event ...
((), {'sub': {'parent_counter': 1}})
---parent counter node---
state = {'parent_counter': 1}
going to node sub
Streaming event ...
((), {'parent_graph_accumulator': {'parent_counter': 2}})
Streaming event ...
((), {'sub': {'parent_counter': 1}})  <------- BUG: should be subgraph execution like (('sub',), {'subgraph_accumulator': {...}})
---parent counter node---
state = {'parent_counter': 1}
going to node sub
Streaming event ...
((), {'parent_graph_accumulator': {'parent_counter': 2}})
Streaming event ...
((), {'sub': {'parent_counter': 1}})
---parent counter node---
state = {'parent_counter': 1}
going to node sub
Streaming event ...
((), {'parent_graph_accumulator': {'parent_counter': 2}})
Traceback (most recent call last):
  File "/home/linux/arcgis-ai-assistants/python/arcgis-assistant/.tmp/subgraph_state_lose/loop_subgraph_with_interrupt.py", line 99, in <module>
    for event in parent_agent.stream(
  File "/home/linux/miniconda3/envs/test/lib/python3.11/site-packages/langgraph/pregel/__init__.py", line 1690, in stream
    raise GraphRecursionError(msg)
langgraph.errors.GraphRecursionError: Recursion limit of 4 reached without hitting a stop condition. You can increase the limit by setting the `recursion_limit` config key.
For troubleshooting, visit: https://python.langchain.com/docs/troubleshooting/errors/GRAPH_RECURSION_LIMIT

Description

I encountered an issue when building a multi-agent graph for multi-turn conversations, where a subgraph has a human feedback node. It interrupts and takes human feedback.

Here is an example graph to reproduce the issue

  • A parent graph has a loop, calling a sub graph until the parent counter reaches a pre-defined limit.
  • Subgraph node interrupts and take human feedback.
  • The sub graph should remember its state from previous run (checkpointer=True).

Expected Behavior

  • graph should interrupt twice, and resume with human inputs
  • subgraph should should persist its state on each run (since checkpointer=True)

Actual Behavior

  • The first interrupt and resume is as expected
  • The second interrupt never happens. The parent graph never executes sub graph counter node after resuming the first interrupt. The sub graph nodes output the same parent counter (=1) repeatedly, leading to recursion limit error since parent counter does not increase.

Observation
If removing checkpointer=True, the graph executes as expected, i.e. the parent counter increases correctly. No bug. (In this cause, ff course, the sub graph states from previous run is not persisted )
It seems in subgraph assigning checkpointer=True and calling interrupt conflicts in some way.

%%{init: {'flowchart': {'curve': 'linear'}}}%%
graph TD;
        __start__([<p>__start__</p>]):::first
        parent_graph_accumulator(parent_graph_accumulator)
        sub(sub)
        __end__([<p>__end__</p>]):::last
        __start__ --> parent_graph_accumulator;
        sub --> parent_graph_accumulator;
        parent_graph_accumulator -.-> sub;
        parent_graph_accumulator -.-> __end__;
        classDef default fill:#f2f0ff,line-height:1.2
        classDef first fill-opacity:0
        classDef last fill:#bfb6fc

LangGraph Version
0.2.67

System Info

System Information

OS: Linux
OS Version: #135~20.04.1-Ubuntu SMP Mon Oct 7 13:56:22 UTC 2024
Python Version: 3.11.11 (main, Dec 11 2024, 16:28:39) [GCC 11.2.0]

Package Information

langchain_core: 0.3.31
langsmith: 0.3.1
langgraph_sdk: 0.1.51

Optional packages not installed

langserve

Other Dependencies

httpx: 0.28.1
jsonpatch: 1.33
langsmith-pyo3: Installed. No version info available.
orjson: 3.10.15
packaging: 24.2
pydantic: 2.10.6
pytest: Installed. No version info available.
PyYAML: 6.0.2
requests: 2.32.3
requests-toolbelt: 1.0.0
rich: 13.9.4
tenacity: 9.0.0
typing-extensions: 4.12.2
zstandard: 0.23.0

Originally created by @shengbo-ma on GitHub (Jan 25, 2025). ### Checked other resources - [x] This is a bug, not a usage question. For questions, please use GitHub Discussions. - [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. ### Example Code ```python from typing import Literal from langchain_core.runnables import RunnableConfig from langgraph.checkpoint.memory import MemorySaver from langgraph.graph import END, START, StateGraph from langgraph.graph.state import Command from langgraph.types import interrupt from rich import get_console from typing_extensions import TypedDict ############### # Subgraph ############### class SubGraphState(TypedDict, total=False): parent_counter: int sub_counter: int def subgraph_accumulator(state: SubGraphState) -> SubGraphState: get_console().print("---subgraph counter node---") get_console().print(f"{state = }") # ask for human approval human_feedback = interrupt("get human feedback") print(f"{human_feedback = }") # continue counting sub_counter = state["sub_counter"] + 1 if "sub_counter" in state else 1 return {"sub_counter": sub_counter} sub_graph = ( StateGraph(SubGraphState) .add_node(subgraph_accumulator) .add_edge(START, subgraph_accumulator.__name__) .add_edge(subgraph_accumulator.__name__, END) .compile( checkpointer=True, # BUG: This causes an issue that subgraph nodes are not executed at all after first interruption ) ) sub_graph.name = "sub" ############### # Parent Graph ############### MAX_ITERATION = 3 class ParentGraphState(TypedDict): parent_counter: int def parent_graph_accumulator( state: ParentGraphState, ) -> Command[Literal["sub", "__end__"]]: print("---parent counter node---") get_console().print(f"{state = }") parent_counter = state["parent_counter"] + 1 if "parent_counter" in state else 0 # goto end when max iteration reaches goto = sub_graph.get_name() if parent_counter < MAX_ITERATION else END get_console().print(f"going to node {goto}") return Command( update={ "parent_counter": parent_counter, }, goto=goto, ) parent_agent = ( StateGraph(ParentGraphState) .add_node(parent_graph_accumulator) .add_node(sub_graph) .add_edge(START, parent_graph_accumulator.__name__) .add_edge(sub_graph.get_name(), parent_graph_accumulator.__name__) .compile(checkpointer=MemorySaver()) ) # visualize graph mermaid_graph = parent_agent.get_graph(xray=True).draw_mermaid() print(mermaid_graph) ############### # Conversation ############### config: RunnableConfig = {"configurable": {"thread_id": "42"}, "recursion_limit": MAX_ITERATION+1} inputs = [ ParentGraphState(parent_counter=0), Command(resume="human feedback 1"), Command(resume="human feedback 2"), ] for input_ in inputs: print(f"{input_ = }") for event in parent_agent.stream( # resume the conversation input_, config, stream_mode="updates", subgraphs=True, ): print("Streaming event ...") print(event) ``` ### Error Message and Stack Trace (if applicable) ```shell input_ = {'parent_counter': 0} ---parent counter node--- state = {'parent_counter': 0} going to node sub Streaming event ... ((), {'parent_graph_accumulator': {'parent_counter': 1}}) ---subgraph counter node--- state = {'parent_counter': 1} Streaming event ... ((), {'__interrupt__': (Interrupt(value='get human feedback', resumable=True, ns=['sub', 'subgraph_accumulator:f187d019-da4b-d432-bcd2-cea142aa7e35'], when='during'),)}) input_ = Command(resume='human feedback 1') ---subgraph counter node--- state = {'parent_counter': 1} human_feedback = 'human feedback 1' Streaming event ... (('sub',), {'subgraph_accumulator': {'sub_counter': 1}}) Streaming event ... ((), {'sub': {'parent_counter': 1}}) ---parent counter node--- state = {'parent_counter': 1} going to node sub Streaming event ... ((), {'parent_graph_accumulator': {'parent_counter': 2}}) Streaming event ... ((), {'sub': {'parent_counter': 1}}) <------- BUG: should be subgraph execution like (('sub',), {'subgraph_accumulator': {...}}) ---parent counter node--- state = {'parent_counter': 1} going to node sub Streaming event ... ((), {'parent_graph_accumulator': {'parent_counter': 2}}) Streaming event ... ((), {'sub': {'parent_counter': 1}}) ---parent counter node--- state = {'parent_counter': 1} going to node sub Streaming event ... ((), {'parent_graph_accumulator': {'parent_counter': 2}}) Traceback (most recent call last): File "/home/linux/arcgis-ai-assistants/python/arcgis-assistant/.tmp/subgraph_state_lose/loop_subgraph_with_interrupt.py", line 99, in <module> for event in parent_agent.stream( File "/home/linux/miniconda3/envs/test/lib/python3.11/site-packages/langgraph/pregel/__init__.py", line 1690, in stream raise GraphRecursionError(msg) langgraph.errors.GraphRecursionError: Recursion limit of 4 reached without hitting a stop condition. You can increase the limit by setting the `recursion_limit` config key. For troubleshooting, visit: https://python.langchain.com/docs/troubleshooting/errors/GRAPH_RECURSION_LIMIT ``` ### Description I encountered an issue when building a multi-agent graph for [multi-turn conversations](https://langchain-ai.github.io/langgraph/concepts/human_in_the_loop/#multi-turn-conversation), where a subgraph has a human feedback node. It interrupts and takes human feedback. Here is an example graph to reproduce the issue - A parent graph has a loop, calling a sub graph until the parent counter reaches a pre-defined limit. - Subgraph node interrupts and take human feedback. - The sub graph should remember its state from previous run (`checkpointer=True`). Expected Behavior - graph should interrupt twice, and resume with human inputs - subgraph should should persist its state on each run (since `checkpointer=True`) Actual Behavior - The first interrupt and resume is as expected - The second interrupt never happens. The parent graph never executes sub graph counter node after resuming the first interrupt. The sub graph nodes output the same parent counter (=1) repeatedly, leading to recursion limit error since parent counter does not increase. Observation If removing `checkpointer=True`, the graph executes as expected, i.e. the parent counter increases correctly. No bug. (In this cause, ff course, the sub graph states from previous run is not persisted ) It seems in subgraph assigning `checkpointer=True` and calling `interrupt` conflicts in some way. ```mermaid %%{init: {'flowchart': {'curve': 'linear'}}}%% graph TD; __start__([<p>__start__</p>]):::first parent_graph_accumulator(parent_graph_accumulator) sub(sub) __end__([<p>__end__</p>]):::last __start__ --> parent_graph_accumulator; sub --> parent_graph_accumulator; parent_graph_accumulator -.-> sub; parent_graph_accumulator -.-> __end__; classDef default fill:#f2f0ff,line-height:1.2 classDef first fill-opacity:0 classDef last fill:#bfb6fc ``` LangGraph Version `0.2.67` ### System Info System Information ------------------ > OS: Linux > OS Version: #135~20.04.1-Ubuntu SMP Mon Oct 7 13:56:22 UTC 2024 > Python Version: 3.11.11 (main, Dec 11 2024, 16:28:39) [GCC 11.2.0] Package Information ------------------- > langchain_core: 0.3.31 > langsmith: 0.3.1 > langgraph_sdk: 0.1.51 Optional packages not installed ------------------------------- > langserve Other Dependencies ------------------ > httpx: 0.28.1 > jsonpatch: 1.33 > langsmith-pyo3: Installed. No version info available. > orjson: 3.10.15 > packaging: 24.2 > pydantic: 2.10.6 > pytest: Installed. No version info available. > PyYAML: 6.0.2 > requests: 2.32.3 > requests-toolbelt: 1.0.0 > rich: 13.9.4 > tenacity: 9.0.0 > typing-extensions: 4.12.2 > zstandard: 0.23.0
yindo closed this issue 2026-02-20 17:40:02 -05:00
yindo commented 2026-02-20 17:40:02 -05:00
Author
Owner
Copy Link
Copy Source

@shengbo-ma commented on GitHub (Jan 25, 2025):

Since checkpointer=True is not yet officially documented and supported, not sure if I use it in a wrong way.
Could you please take a look? @vbarda @eyurtsev
Appreciate your efforts

@shengbo-ma commented on GitHub (Jan 25, 2025): Since `checkpointer=True` is not yet officially documented and supported, not sure if I use it in a wrong way. Could you please take a look? @vbarda @eyurtsev Appreciate your efforts
yindo commented 2026-02-20 17:40:03 -05:00
Author
Owner
Copy Link
Copy Source

@k1eNdn commented on GitHub (Feb 12, 2025):

@shengbo-ma Good news today!! I made same your error

@k1eNdn commented on GitHub (Feb 12, 2025): @shengbo-ma Good news today!! I made same your error
yindo commented 2026-02-20 17:40:03 -05:00
Author
Owner
Copy Link
Copy Source

@vbarda commented on GitHub (Feb 27, 2025):

@shengbo-ma @kiendn1

UPDATE: confirmed that there was an issue, will be fixed in langgraph 0.3.2

here is the overall explanation of the subgraph interrupt behavior: if i you have an interrupt() in a subgraph node and you compile the subgraph with checkpointer=None/checkpointer=True and invoke the subgraph multiple times, the interrupt() will also get called multiple times. this is conceptually similar to manually calling interrupt() multiple times inside a single parent node

@vbarda commented on GitHub (Feb 27, 2025): @shengbo-ma @kiendn1 UPDATE: confirmed that there was an issue, will be fixed in langgraph 0.3.2 here is the overall explanation of the subgraph interrupt behavior: if i you have an `interrupt()` in a subgraph node and you compile the subgraph with `checkpointer=None/checkpointer=True` and invoke the subgraph multiple times, the `interrupt()` will also get called multiple times. this is conceptually similar to manually calling `interrupt()` multiple times inside a single parent node
yindo commented 2026-02-20 17:40:03 -05:00
Author
Owner
Copy Link
Copy Source

@vbarda commented on GitHub (Feb 28, 2025):

@shengbo-ma @kiendn1 i updated the above comment -- it was partially incorrect and there was a separate issue causing the above behavior. we just patched it up and the fix will be released in 0.3.2. apologies for delay/confusion

@vbarda commented on GitHub (Feb 28, 2025): @shengbo-ma @kiendn1 i updated the above comment -- it was partially incorrect and there was a separate issue causing the above behavior. we just patched it up and the fix will be released in 0.3.2. apologies for delay/confusion
yindo commented 2026-02-20 17:40:03 -05:00
Author
Owner
Copy Link
Copy Source

@shengbo-ma commented on GitHub (Feb 28, 2025):

@vbarda Thanks for your effort.
Glad to hear about the new release.

Something off topic:
I see LangGraph is building higher level APIs for more friendly user experience, like langgraph-supervisor, functional api and langgraph-prebuilt.
It is great!
I am heavily using LangGraph in my work, and enjoy writing basic graph builders function from scratch, similar to prebuilt.create_react_agent(). Fo example, create function calling agent with human feedback, routing style supervisor, plan-and-execute agent with human feedback. I am willing to contribute to the community.

@shengbo-ma commented on GitHub (Feb 28, 2025): @vbarda Thanks for your effort. Glad to hear about the new release. Something off topic: I see LangGraph is building higher level APIs for more friendly user experience, like `langgraph-supervisor`, functional api and `langgraph-prebuilt`. It is great! I am heavily using LangGraph in my work, and enjoy writing basic graph builders function from scratch, similar to prebuilt.create_react_agent(). Fo example, create function calling agent with human feedback, routing style supervisor, plan-and-execute agent with human feedback. I am willing to contribute to the community.
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
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#422
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?