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

create_react_agent lost configuration on casting for bind tools #606

New Issue
Closed
opened 2026-02-20 17:40:56 -05:00 by yindo · 1 comment
yindo commented 2026-02-20 17:40:56 -05:00
Owner
Copy Link
Copy Source

Originally created by @ericmagalhaes on GitHub (Apr 29, 2025).

Originally assigned to: @vbarda on GitHub.

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

llm = ChatOpenAI(model="").configurable_fields(
    model_name=ConfigurableField(id="app_model"),
    openai_api_base=ConfigurableField(id="app_base_url"),
    openai_api_key=ConfigurableField(id="app_key"))


graph = create_react_agent(
    llm, 
    tools=tools,
    prompt=system_prompt,
    checkpointer=checkpointer)

** chat_agent_executor.py **
line: 690
if _should_bind_tools(model, tool_classes) and tool_calling_enabled:
        model = cast(BaseChatModel, model).bind_tools(tool_classes)

Error Message and Stack Trace (if applicable)

after model cast() configurable fields are lost

data: {"error": "Error code: 400 - {'error': {'message': {'error': '/chat/completions: Invalid model name passed in model=gpt-3.5-turbo'}, 'type': 'None', 'param': 'None', 'code': '400'}}"}

Description

  • Using langgraph 0.3.31

...
async for msg, metadata in graph.astream(
{"messages": [("user", request.input.query)], "app_id": request.input.app_id},
config={
"configurable": {
"thread_id": request.config.thread_id,
"app_model": model_name,
"app_base_url": base_api,
"app_key": app_key,
}
},
stream_mode="messages"
):
...

System Info

wsl-ubuntu

Originally created by @ericmagalhaes on GitHub (Apr 29, 2025). Originally assigned to: @vbarda on GitHub. ### 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 llm = ChatOpenAI(model="").configurable_fields( model_name=ConfigurableField(id="app_model"), openai_api_base=ConfigurableField(id="app_base_url"), openai_api_key=ConfigurableField(id="app_key")) graph = create_react_agent( llm, tools=tools, prompt=system_prompt, checkpointer=checkpointer) ** chat_agent_executor.py ** line: 690 if _should_bind_tools(model, tool_classes) and tool_calling_enabled: model = cast(BaseChatModel, model).bind_tools(tool_classes) ``` ### Error Message and Stack Trace (if applicable) ```shell after model cast() configurable fields are lost data: {"error": "Error code: 400 - {'error': {'message': {'error': '/chat/completions: Invalid model name passed in model=gpt-3.5-turbo'}, 'type': 'None', 'param': 'None', 'code': '400'}}"} ``` ### Description * Using langgraph 0.3.31 ... async for msg, metadata in graph.astream( {"messages": [("user", request.input.query)], "app_id": request.input.app_id}, config={ "configurable": { "thread_id": request.config.thread_id, "app_model": model_name, "app_base_url": base_api, "app_key": app_key, } }, stream_mode="messages" ): ... ### System Info wsl-ubuntu
yindo closed this issue 2026-02-20 17:40:56 -05:00
yindo commented 2026-02-20 17:40:56 -05:00
Author
Owner
Copy Link
Copy Source

@vbarda commented on GitHub (Apr 30, 2025):

Unfortunately this is a limitation of ChatModel interface and is not related to the langgraph implementation specifically.
You can work around this by using init_chat_model. Note that you will need to use the actual parameter names in configurable_fields, not aliases. Here is a small example:

from langchain.chat_models import init_chat_model
from langgraph.prebuilt import create_react_agent

llm = init_chat_model("openai:gpt-4.1-nano", configurable_fields=("model",))
agent = create_react_agent(llm, [add])
agent.invoke({"messages": "what's 2 + 3?"}, config={"configurable": {"model": "gpt-4.1-mini"}})

https://python.langchain.com/docs/how_to/configure/#configuring-fields-on-a-chat-model

@vbarda commented on GitHub (Apr 30, 2025): Unfortunately this is a limitation of ChatModel interface and is not related to the langgraph implementation specifically. You can work around this by using `init_chat_model`. Note that you will need to use the actual parameter names in `configurable_fields`, not aliases. Here is a small example: ```python from langchain.chat_models import init_chat_model from langgraph.prebuilt import create_react_agent llm = init_chat_model("openai:gpt-4.1-nano", configurable_fields=("model",)) agent = create_react_agent(llm, [add]) agent.invoke({"messages": "what's 2 + 3?"}, config={"configurable": {"model": "gpt-4.1-mini"}}) ``` https://python.langchain.com/docs/how_to/configure/#configuring-fields-on-a-chat-model
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#606
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?