AIMessage enforces ToolCall model incompatible with OpenAI

[yildirimgoks]

Checked other resources

• [X] I added a very descriptive title to this question.
• [X] I searched the LangChain documentation with the integrated search.
• [X] I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• [X] I commit to help with one of those options 👆

Example Code

from langchain.messages import AIMessage, ToolCall

# OpenAI compatible tool call format
tool_call = {
   "id":"tc1",
   "type":"function",
   "function":{
      "name":"SomeTool",
      "arguments":"{\"some_argument\": \"some_value\"}"
   }
}

# line below works fine
ToolCall(**tool_call)

# line below returns an error
AIMessage(content="", tool_calls=[ToolCall(**tool_call)])

# error message:
# pydantic.v1.error_wrappers.ValidationError: 1 validation error for AIMessage
# tool_call() got an unexpected keyword argument 'function' (type=type_error)

Description

When you provide a value for the '_toolcalls' argument of the AIMessage, _rootvalidator tries to parse the values in it to a ToolCall object using the _langchain_core.messages.tool.toolcall function. Although instancing ToolCall by calling it directly with OpenAI compatible tool_calls model is possible, the _toolcall() function expects a specific set of variables to build the ToolCall, and does not accept extra keyword variables. This enforces a very specific data model when tool_calls is provided with AIMessage and makes it impossible to create an AIMessage object with the desired _toolcalls formatting.

Is this intended or could this be a bug? IIs there a different way of creating an AI message with tool_calls that I'm missing?

System Info

langchain==0.2.14 langchain-community==0.2.12 langchain-core==0.2.33 langchain-openai==0.1.22 langchain-text-splitters==0.2.2

Checked the latest source code & documentation and the issue persists in the most recent version as well.

Originally posted by @yildirimgoks in https://github.com/langchain-ai/langchain/discussions/27919

[keenborder786]

@yildirimgoks, this is intentional. ToolCall is an internal way for representation of AI Tool Call Message. At the end Tool Calling API for OpenAI is invoked with the compatible schema. But if you want to achieve the desire result:

from langchain_core.messages import AIMessage, ToolCall

tool_call = {
   "id":"tc1",
   "type":"function",
   "name":"some_function",
   "args":{"some_argument": "some_value"}
}

# line below works fine
ToolCall(**tool_call)

# line below returns an error
AIMessage(content="", tool_calls=[ToolCall(**tool_call)])