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

TypeError: Interrupt.__init__() got an unexpected keyword argument 'interrupt_id' #829

New Issue
Closed
opened 2026-02-20 17:41:58 -05:00 by yindo · 7 comments
yindo commented 2026-02-20 17:41:58 -05:00
Owner
Copy Link
Copy Source

Originally created by @ovinix on GitHub (Jul 22, 2025).

Originally assigned to: @sydney-runkle 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.

Example Code

from langgraph.pregel.remote import RemoteGraph

url = URL # url of LangGraph Server
thread_id = THREAD_ID # ID of the thread with a graph run waiting for resume
remote_graph = RemoteGraph("agent", url=url)
config = {"configurable": {"thread_id": thread_id}}

state = await remote_graph.aget_state(config)

Error Message and Stack Trace (if applicable)

File ".venv/lib/python3.13/site-packages/langgraph/pregel/remote.py", line 419, in aget_state
    return self._create_state_snapshot(state)
           ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^
  File ".venv/lib/python3.13/site-packages/langgraph/pregel/remote.py", line 258, in _create_state_snapshot
    interrupts.append(Interrupt(**interrupt))
                      ~~~~~~~~~^^^^^^^^^^^^^
TypeError: Interrupt.__init__() got an unexpected keyword argument 'interrupt_id'

Description

State for threads with interrupt should be returned correctly using RemoteGraph.

Failing task object:

{
  'id': '91230d61-ca2f-ff91-c768-99020b496456', 
  'name': 'wait_for_response', 
  'path': ['__pregel_pull', 'wait_for_response'], 
  'error': None, 
  'interrupts': [{'interrupt_id': '6abbf7cd8ec27c8ecd98b9e2576580f5', 'value': 'Waiting response from user', 'resumable': True, 'ns': ['wait_for_response:91230d61-ca2f-ff91-c768-99020b496456'], 'when': 'during'}], 
  'checkpoint': None, 
  'state': None, 
  'result': None
}

System Info

System Information

OS: Linux
OS Version: #1 SMP Tue Nov 5 00:21:55 UTC 2024
Python Version: 3.13.2 (main, Feb 25 2025, 14:56:35) [GCC 11.4.0]

Package Information

langchain_core: 0.3.70
langchain: 0.3.26
langchain_community: 0.3.27
langsmith: 0.4.8
langchain_mcp_adapters: 0.1.9
langchain_openai: 0.3.28
langchain_text_splitters: 0.3.8
langgraph_api: 0.2.98
langgraph_cli: 0.3.5
langgraph_license: Installed. No version info available.
langgraph_runtime: Installed. No version info available.
langgraph_runtime_inmem: 0.6.0
langgraph_sdk: 0.1.74

Originally created by @ovinix on GitHub (Jul 22, 2025). Originally assigned to: @sydney-runkle 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. ### Example Code ```python from langgraph.pregel.remote import RemoteGraph url = URL # url of LangGraph Server thread_id = THREAD_ID # ID of the thread with a graph run waiting for resume remote_graph = RemoteGraph("agent", url=url) config = {"configurable": {"thread_id": thread_id}} state = await remote_graph.aget_state(config) ``` ### Error Message and Stack Trace (if applicable) ```shell File ".venv/lib/python3.13/site-packages/langgraph/pregel/remote.py", line 419, in aget_state return self._create_state_snapshot(state) ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^ File ".venv/lib/python3.13/site-packages/langgraph/pregel/remote.py", line 258, in _create_state_snapshot interrupts.append(Interrupt(**interrupt)) ~~~~~~~~~^^^^^^^^^^^^^ TypeError: Interrupt.__init__() got an unexpected keyword argument 'interrupt_id' ``` ### Description State for threads with interrupt should be returned correctly using RemoteGraph. Failing `task` object: ``` { 'id': '91230d61-ca2f-ff91-c768-99020b496456', 'name': 'wait_for_response', 'path': ['__pregel_pull', 'wait_for_response'], 'error': None, 'interrupts': [{'interrupt_id': '6abbf7cd8ec27c8ecd98b9e2576580f5', 'value': 'Waiting response from user', 'resumable': True, 'ns': ['wait_for_response:91230d61-ca2f-ff91-c768-99020b496456'], 'when': 'during'}], 'checkpoint': None, 'state': None, 'result': None } ``` ### System Info System Information ------------------ > OS: Linux > OS Version: #1 SMP Tue Nov 5 00:21:55 UTC 2024 > Python Version: 3.13.2 (main, Feb 25 2025, 14:56:35) [GCC 11.4.0] Package Information ------------------- > langchain_core: 0.3.70 > langchain: 0.3.26 > langchain_community: 0.3.27 > langsmith: 0.4.8 > langchain_mcp_adapters: 0.1.9 > langchain_openai: 0.3.28 > langchain_text_splitters: 0.3.8 > langgraph_api: 0.2.98 > langgraph_cli: 0.3.5 > langgraph_license: Installed. No version info available. > langgraph_runtime: Installed. No version info available. > langgraph_runtime_inmem: 0.6.0 > langgraph_sdk: 0.1.74
yindo added the bug label 2026-02-20 17:41:58 -05:00
yindo closed this issue 2026-02-20 17:41:58 -05:00
yindo commented 2026-02-20 17:41:58 -05:00
Author
Owner
Copy Link
Copy Source

@sydney-runkle commented on GitHub (Jul 23, 2025):

Can you test this with v0.6.0a1? I think it should be fixed with the new langgraph version.

Thanks!

@sydney-runkle commented on GitHub (Jul 23, 2025): Can you test this with v0.6.0a1? I think it should be fixed with the new langgraph version. Thanks!
yindo commented 2026-02-20 17:41:58 -05:00
Author
Owner
Copy Link
Copy Source

@ovinix commented on GitHub (Jul 24, 2025):

Hi @sydney-runkle

Thanks for your response!

I'd say upgrade to v0.6.0a1 was not smooth and I just received another error.

Here are steps I did:

  1. poetry add langgraph=0.6.0a1 langgraph-sdk=0.2.0 + langgraph dev
    Error in logs:
File ".venv/lib/python3.13/site-packages/langgraph/prebuilt/tool_node.py", line 43, in <module>
    from langgraph.utils.runnable import RunnableCallable
ModuleNotFoundError: No module named 'langgraph.utils'
Could not import python module for graph:
GraphSpec(id='agent', path='agent.py', module=None, variable='graph', config={}, description=None)
This error likely means you haven't installed your project and its dependencies yet. Before running the server, install your project:

If you are using requirements.txt:
python -m pip install -r requirements.txt

If you are using pyproject.toml or setuptools:
python -m pip install -e .

Make sure to run this command from your project's root directory (where your setup.py or pyproject.toml is located)
  1. Manually changed from langgraph.utils.runnable import RunnableCallable to from langgraph._internal._runnable import RunnableCallable in these files:
  • .venv/lib/python3.13/site-packages/langgraph/prebuilt/chat_agent_executor.py
  • .venv/lib/python3.13/site-packages/langgraph/prebuilt/tool_node.py
  • .venv/lib/python3.13/site-packages/langgraph/prebuilt/tool_validator.py
  1. Once graph was in interrupt state await remote_graph.aget_state(config) was executed
    Errors in logs:
File "src/agents_api/test.py", line 44, in call
    state = await remote_graph.aget_state(config)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".venv/lib/python3.13/site-packages/langgraph/pregel/remote.py", line 421, in aget_state
    state = await client.threads.get_state(
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    ...<3 lines>...
    )
    ^
  File ".venv/lib/python3.13/site-packages/langgraph_sdk/client.py", line 1366, in get_state
    return await self.http.post(
           ^^^^^^^^^^^^^^^^^^^^^
    ...<3 lines>...
    )
    ^
  File ".venv/lib/python3.13/site-packages/langgraph_sdk/client.py", line 299, in post
    raise e
  File ".venv/lib/python3.13/site-packages/langgraph_sdk/client.py", line 292, in post
    r.raise_for_status()
    ~~~~~~~~~~~~~~~~~~^^
  File ".venv/lib/python3.13/site-packages/httpx/_models.py", line 829, in raise_for_status
    raise HTTPStatusError(message, request=request, response=self)
httpx.HTTPStatusError: Server error '500 Internal Server Error' for url 'http://localhost:2024/threads/073b6554-0811-4953-9978-3df0adc47604/state/checkpoint'
For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/500
Internal Server Error

...

 File ".venv/lib/python3.13/site-packages/langgraph_api/api/threads.py", line 86, in get_thread_state
    state = state_snapshot_to_thread_state(
        await Threads.State.get(
            conn, {"configurable": {"thread_id": thread_id}}, subgraphs=subgraphs
        )
    )
  File ".venv/lib/python3.13/site-packages/langgraph_api/state.py", line 69, in state_snapshot_to_thread_state
    state_interrupt_to_thread_interrupt(i) for i in t.interrupts
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^
  File ".venv/lib/python3.13/site-packages/langgraph_api/state.py", line 52, in state_interrupt_to_thread_interrupt
    "resumable": interrupt.resumable,
                 ^^^^^^^^^^^^^^^^^^^
AttributeError: 'Interrupt' object has no attribute 'resumable'
@ovinix commented on GitHub (Jul 24, 2025): Hi @sydney-runkle Thanks for your response! I'd say upgrade to v0.6.0a1 was not smooth and I just received another error. Here are steps I did: 1. `poetry add langgraph=0.6.0a1 langgraph-sdk=0.2.0` + `langgraph dev` Error in logs: ``` File ".venv/lib/python3.13/site-packages/langgraph/prebuilt/tool_node.py", line 43, in <module> from langgraph.utils.runnable import RunnableCallable ModuleNotFoundError: No module named 'langgraph.utils' Could not import python module for graph: GraphSpec(id='agent', path='agent.py', module=None, variable='graph', config={}, description=None) This error likely means you haven't installed your project and its dependencies yet. Before running the server, install your project: If you are using requirements.txt: python -m pip install -r requirements.txt If you are using pyproject.toml or setuptools: python -m pip install -e . Make sure to run this command from your project's root directory (where your setup.py or pyproject.toml is located) ``` 2. Manually changed `from langgraph.utils.runnable import RunnableCallable` to `from langgraph._internal._runnable import RunnableCallable` in these files: - `.venv/lib/python3.13/site-packages/langgraph/prebuilt/chat_agent_executor.py` - `.venv/lib/python3.13/site-packages/langgraph/prebuilt/tool_node.py` - `.venv/lib/python3.13/site-packages/langgraph/prebuilt/tool_validator.py` 3. Once graph was in interrupt state `await remote_graph.aget_state(config)` was executed Errors in logs: ``` File "src/agents_api/test.py", line 44, in call state = await remote_graph.aget_state(config) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File ".venv/lib/python3.13/site-packages/langgraph/pregel/remote.py", line 421, in aget_state state = await client.threads.get_state( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ...<3 lines>... ) ^ File ".venv/lib/python3.13/site-packages/langgraph_sdk/client.py", line 1366, in get_state return await self.http.post( ^^^^^^^^^^^^^^^^^^^^^ ...<3 lines>... ) ^ File ".venv/lib/python3.13/site-packages/langgraph_sdk/client.py", line 299, in post raise e File ".venv/lib/python3.13/site-packages/langgraph_sdk/client.py", line 292, in post r.raise_for_status() ~~~~~~~~~~~~~~~~~~^^ File ".venv/lib/python3.13/site-packages/httpx/_models.py", line 829, in raise_for_status raise HTTPStatusError(message, request=request, response=self) httpx.HTTPStatusError: Server error '500 Internal Server Error' for url 'http://localhost:2024/threads/073b6554-0811-4953-9978-3df0adc47604/state/checkpoint' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/500 Internal Server Error ``` ... ``` File ".venv/lib/python3.13/site-packages/langgraph_api/api/threads.py", line 86, in get_thread_state state = state_snapshot_to_thread_state( await Threads.State.get( conn, {"configurable": {"thread_id": thread_id}}, subgraphs=subgraphs ) ) File ".venv/lib/python3.13/site-packages/langgraph_api/state.py", line 69, in state_snapshot_to_thread_state state_interrupt_to_thread_interrupt(i) for i in t.interrupts ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^ File ".venv/lib/python3.13/site-packages/langgraph_api/state.py", line 52, in state_interrupt_to_thread_interrupt "resumable": interrupt.resumable, ^^^^^^^^^^^^^^^^^^^ AttributeError: 'Interrupt' object has no attribute 'resumable' ```
yindo commented 2026-02-20 17:41:58 -05:00
Author
Owner
Copy Link
Copy Source

@sydney-runkle commented on GitHub (Jul 24, 2025):

Gotcha, fixes in the works for both of those. We'll get this fixed by the end of the week, thanks for the report.

@sydney-runkle commented on GitHub (Jul 24, 2025): Gotcha, fixes in the works for both of those. We'll get this fixed by the end of the week, thanks for the report.
yindo commented 2026-02-20 17:41:58 -05:00
Author
Owner
Copy Link
Copy Source

@farouk09 commented on GitHub (Jul 24, 2025):

@sydney-runkle I'm encountering an issue similar to the one mentioned.

When I call a remote graph for the first time using a new thread ID, everything works as expected:

remote_graph = RemoteGraph(graph_name, sync_client=sync_client)

# create a new thread
thread = sync_client.threads.create()
print(thread['thread_id'])

# invoke the graph
config = {"configurable": {"thread_id": thread['thread_id']}}
result = remote_graph.invoke({
    "messages": [{"role": "user", "content": "hello, my name is Farouk"}]
}, config=config)

print(result)

This produces a valid response:

9cf3b9c1-6746-48e0-b2a2-8c31ac9de524

{'messages': [
    {'content': 'hello, my name is Farouk', ...},
    {'content': "Hello Farouk, nice to meet you! ...", ...}
]}

However, when I try to reuse the same thread ID in a second call:

config = {"configurable": {"thread_id": "9cf3b9c1-6746-48e0-b2a2-8c31ac9de524"}}
result = remote_graph.invoke({
    "messages": [{"role": "user", "content": "what is my name?"}]
}, config=config)

I get this error:

Traceback (most recent call last):
  File "/home/aptikal/abdalfar/InterviewSim/livekit_server/example/test.py", line 48, in <module>
    result = remote_graph.invoke({
        "messages": [{"role": "user", "content": "hello, my name is farouk "}]
    }, config=config)
  File "/home/aptikal/abdalfar/InterviewSim/livekit_server/.venv/lib/python3.13/site-packages/langgraph/pregel/remote.py", line 856, in invoke
    for chunk in self.stream(
                 ~~~~~~~~~~~^
        input,
        ^^^^^^
    ...<4 lines>...
        **kwargs,
        ^^^^^^^^^
    ):
    ^
  File "/home/aptikal/abdalfar/InterviewSim/livekit_server/.venv/lib/python3.13/site-packages/langgraph/pregel/remote.py", line 693, in stream
    raise RemoteException(chunk.data)
langgraph.pregel.remote.RemoteException: {'error': 'TypeError', 'message': "int() argument must be a string, a bytes-like object or a real number, not 'HumanMessage'"}

It seems like something goes wrong when reusing the thread. Do you know what could be causing this?

@farouk09 commented on GitHub (Jul 24, 2025): @sydney-runkle I'm encountering an issue similar to the one mentioned. When I call a remote graph for the first time using a new thread ID, everything works as expected: ``` remote_graph = RemoteGraph(graph_name, sync_client=sync_client) # create a new thread thread = sync_client.threads.create() print(thread['thread_id']) # invoke the graph config = {"configurable": {"thread_id": thread['thread_id']}} result = remote_graph.invoke({ "messages": [{"role": "user", "content": "hello, my name is Farouk"}] }, config=config) print(result) ``` This produces a valid response: ``` 9cf3b9c1-6746-48e0-b2a2-8c31ac9de524 {'messages': [ {'content': 'hello, my name is Farouk', ...}, {'content': "Hello Farouk, nice to meet you! ...", ...} ]} ``` However, when I try to reuse the same thread ID in a second call: ``` config = {"configurable": {"thread_id": "9cf3b9c1-6746-48e0-b2a2-8c31ac9de524"}} result = remote_graph.invoke({ "messages": [{"role": "user", "content": "what is my name?"}] }, config=config) ``` I get this error: ``` Traceback (most recent call last): File "/home/aptikal/abdalfar/InterviewSim/livekit_server/example/test.py", line 48, in <module> result = remote_graph.invoke({ "messages": [{"role": "user", "content": "hello, my name is farouk "}] }, config=config) File "/home/aptikal/abdalfar/InterviewSim/livekit_server/.venv/lib/python3.13/site-packages/langgraph/pregel/remote.py", line 856, in invoke for chunk in self.stream( ~~~~~~~~~~~^ input, ^^^^^^ ...<4 lines>... **kwargs, ^^^^^^^^^ ): ^ File "/home/aptikal/abdalfar/InterviewSim/livekit_server/.venv/lib/python3.13/site-packages/langgraph/pregel/remote.py", line 693, in stream raise RemoteException(chunk.data) langgraph.pregel.remote.RemoteException: {'error': 'TypeError', 'message': "int() argument must be a string, a bytes-like object or a real number, not 'HumanMessage'"} ``` It seems like something goes wrong when reusing the thread. Do you know what could be causing this?
yindo commented 2026-02-20 17:41:58 -05:00
Author
Owner
Copy Link
Copy Source

@sydney-runkle commented on GitHub (Jul 25, 2025):

Hiya, just released v0.6.0a2. Could you please test with that? Thanks so much!

@sydney-runkle commented on GitHub (Jul 25, 2025): Hiya, just released v0.6.0a2. Could you please test with that? Thanks so much!
yindo commented 2026-02-20 17:41:59 -05:00
Author
Owner
Copy Link
Copy Source

@farouk09 commented on GitHub (Jul 25, 2025):

@sydney-runkle edit :sorry for the inconvenience, the bug was in my code.

@farouk09 commented on GitHub (Jul 25, 2025): @sydney-runkle edit :sorry for the inconvenience, the bug was in my code.
yindo commented 2026-02-20 17:41:59 -05:00
Author
Owner
Copy Link
Copy Source

@sydney-runkle commented on GitHub (Aug 5, 2025):

No worries!

@sydney-runkle commented on GitHub (Aug 5, 2025): No worries!
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
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#829
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?