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: StateGraph.add_node() got an unexpected keyword argument 'input_schema' in langgraph/prebuilt/chat_agent_executor.py: #755

New Issue
Closed
opened 2026-02-20 17:41:36 -05:00 by yindo · 5 comments
yindo commented 2026-02-20 17:41:36 -05:00
Owner
Copy Link
Copy Source

Originally created by @harupy on GitHub (Jun 30, 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

-

Error Message and Stack Trace (if applicable)

Description

        # Define a new graph
        workflow = StateGraph(state_schema or AgentState, config_schema=config_schema)
    
        # Define the two nodes we will cycle between
>       workflow.add_node(
            "agent",
            RunnableCallable(call_model, acall_model),
            input_schema=input_schema,
        )
E       TypeError: StateGraph.add_node() got an unexpected keyword argument 'input_schema'

_are_more_steps_needed = <function create_react_agent.<locals>._are_more_steps_needed at 0x7f6c989ff400>
_get_model_input_state = <function create_react_agent.<locals>._get_model_input_state at 0x7f6c989fecb0>
acall_model = <function create_react_agent.<locals>.acall_model at 0x7f6c989fdf30>
agenerate_structured_response = <function create_react_agent.<locals>.agenerate_structured_response at 0x7f6c989fe440>
call_model = <function create_react_agent.<locals>.call_model at 0x7f6c989ffc70>
checkpointer = None
config_schema = None
debug      = False
generate_structured_response = <function create_react_agent.<locals>.generate_structured_response at 0x7f6c989fedd0>
input_schema = <class 'langgraph.prebuilt.chat_agent_executor.AgentState'>
interrupt_after = None
interrupt_before = None
llm_builtin_tools = []
model      = RunnableBinding(bound=FakeOpenAI(client=<openai.resources.chat.completions.completions.Completions object at 0x7f6c988...'enum': ['nyc', 'sf'], 'type': 'string'}}, 'required': ['city'], 'type': 'object'}}}]}, config={}, config_factories=[])
model_runnable = Prompt(tags=None, recurse=True, explode_args=False, func_accepts_config=False, func_accepts={})
| RunnableBinding(boun...'enum': ['nyc', 'sf'], 'type': 'string'}}, 'required': ['city'], 'type': 'object'}}}]}, config={}, config_factories=[])
name       = None
post_model_hook = None
pre_model_hook = None
prompt     = None
response_format = None
should_continue = <function create_react_agent.<locals>.should_continue at 0x7f6c989ff520>
should_return_direct = set()
state_schema = <class 'langgraph.prebuilt.chat_agent_executor.AgentState'>
store      = None
tool_calling_enabled = True
tool_classes = [StructuredTool(name='get_weather', description='Use this to get weather information.', args_schema=<class 'langchain_core.utils.pydantic.get_weather'>, func=<function get_weather at 0x7f6c980bab90>)]
tool_node  = tools(tags=None, recurse=True, explode_args=False, func_accepts_config=True, func_accepts={'store': ('__pregel_store',...te_args={'get_weather': {}}, tool_to_store_arg={'get_weather': None}, handle_tool_errors=True, messages_key='messages')
tools      = [StructuredTool(name='get_weather', description='Use this to get weather information.', args_schema=<class 'langchain_core.utils.pydantic.get_weather'>, func=<function get_weather at 0x7f6c980bab90>)]
version    = 'v2'
workflow   = <langgraph.graph.state.StateGraph object at 0x7f6c986929b0>

/opt/hostedtoolcache/Python/3.10.16/x64/lib/python3.10/site-packages/langgraph/prebuilt/chat_agent_executor.py:663: TypeError

System Info

Originally created by @harupy on GitHub (Jun 30, 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 - ``` ### Error Message and Stack Trace (if applicable) ```shell ``` ### Description ``` # Define a new graph workflow = StateGraph(state_schema or AgentState, config_schema=config_schema) # Define the two nodes we will cycle between > workflow.add_node( "agent", RunnableCallable(call_model, acall_model), input_schema=input_schema, ) E TypeError: StateGraph.add_node() got an unexpected keyword argument 'input_schema' _are_more_steps_needed = <function create_react_agent.<locals>._are_more_steps_needed at 0x7f6c989ff400> _get_model_input_state = <function create_react_agent.<locals>._get_model_input_state at 0x7f6c989fecb0> acall_model = <function create_react_agent.<locals>.acall_model at 0x7f6c989fdf30> agenerate_structured_response = <function create_react_agent.<locals>.agenerate_structured_response at 0x7f6c989fe440> call_model = <function create_react_agent.<locals>.call_model at 0x7f6c989ffc70> checkpointer = None config_schema = None debug = False generate_structured_response = <function create_react_agent.<locals>.generate_structured_response at 0x7f6c989fedd0> input_schema = <class 'langgraph.prebuilt.chat_agent_executor.AgentState'> interrupt_after = None interrupt_before = None llm_builtin_tools = [] model = RunnableBinding(bound=FakeOpenAI(client=<openai.resources.chat.completions.completions.Completions object at 0x7f6c988...'enum': ['nyc', 'sf'], 'type': 'string'}}, 'required': ['city'], 'type': 'object'}}}]}, config={}, config_factories=[]) model_runnable = Prompt(tags=None, recurse=True, explode_args=False, func_accepts_config=False, func_accepts={}) | RunnableBinding(boun...'enum': ['nyc', 'sf'], 'type': 'string'}}, 'required': ['city'], 'type': 'object'}}}]}, config={}, config_factories=[]) name = None post_model_hook = None pre_model_hook = None prompt = None response_format = None should_continue = <function create_react_agent.<locals>.should_continue at 0x7f6c989ff520> should_return_direct = set() state_schema = <class 'langgraph.prebuilt.chat_agent_executor.AgentState'> store = None tool_calling_enabled = True tool_classes = [StructuredTool(name='get_weather', description='Use this to get weather information.', args_schema=<class 'langchain_core.utils.pydantic.get_weather'>, func=<function get_weather at 0x7f6c980bab90>)] tool_node = tools(tags=None, recurse=True, explode_args=False, func_accepts_config=True, func_accepts={'store': ('__pregel_store',...te_args={'get_weather': {}}, tool_to_store_arg={'get_weather': None}, handle_tool_errors=True, messages_key='messages') tools = [StructuredTool(name='get_weather', description='Use this to get weather information.', args_schema=<class 'langchain_core.utils.pydantic.get_weather'>, func=<function get_weather at 0x7f6c980bab90>)] version = 'v2' workflow = <langgraph.graph.state.StateGraph object at 0x7f6c986929b0> /opt/hostedtoolcache/Python/3.10.16/x64/lib/python3.10/site-packages/langgraph/prebuilt/chat_agent_executor.py:663: TypeError ``` ### System Info -
yindo added the bugpending labels 2026-02-20 17:41:36 -05:00
yindo closed this issue 2026-02-20 17:41:36 -05:00
yindo commented 2026-02-20 17:41:37 -05:00
Author
Owner
Copy Link
Copy Source

@harupy commented on GitHub (Jun 30, 2025):

Never mind.

@harupy commented on GitHub (Jun 30, 2025): Never mind.
yindo commented 2026-02-20 17:41:37 -05:00
Author
Owner
Copy Link
Copy Source

@lsimone commented on GitHub (Jun 30, 2025):

Never mind.

@harupy I run into the same problem: how did you solve?

@lsimone commented on GitHub (Jun 30, 2025): > Never mind. @harupy I run into the same problem: how did you solve?
yindo commented 2026-02-20 17:41:37 -05:00
Author
Owner
Copy Link
Copy Source

@johnfrommartin commented on GitHub (Jun 30, 2025):

@harupy am facing the same issue, could you elaborate what you did to resolve this?

@johnfrommartin commented on GitHub (Jun 30, 2025): @harupy am facing the same issue, could you elaborate what you did to resolve this?
yindo commented 2026-02-20 17:41:37 -05:00
Author
Owner
Copy Link
Copy Source

@johnfrommartin commented on GitHub (Jun 30, 2025):

@lsimone try upgrading your langgraph version to 0.5.0, there are some code clean up changes related to the ìnput_schema`key.

@johnfrommartin commented on GitHub (Jun 30, 2025): @lsimone try upgrading your langgraph version to `0.5.0`, there are some code clean up changes related to the ìnput_schema`key.
yindo commented 2026-02-20 17:41:37 -05:00
Author
Owner
Copy Link
Copy Source

@lsimone commented on GitHub (Jul 1, 2025):

@lsimone try upgrading your langgraph version to 0.5.0, there are some code clean up changes related to the ìnput_schema`key.

@johnfrommartin thanks a lot!

@lsimone commented on GitHub (Jul 1, 2025): > [@lsimone](https://github.com/lsimone) try upgrading your langgraph version to `0.5.0`, there are some code clean up changes related to the ìnput_schema`key. @johnfrommartin thanks a lot!
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#755
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?