langchain - 💡(How to fix) Fix ProviderStrategy does not allow passing strict into the mistral ai JSON Schema response_format

Submission checklist

• This is a bug, not a usage question.
• I added a clear and descriptive title that summarizes this issue.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
• This is not related to the langchain-community package.
• I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS.

Package (Required)

• langchain
• langchain-openai
• langchain-anthropic
• langchain-classic
• langchain-core
• langchain-model-profiles
• langchain-tests
• langchain-text-splitters
• langchain-chroma
• langchain-deepseek
• langchain-exa
• langchain-fireworks
• langchain-groq
• langchain-huggingface
• langchain-mistralai
• langchain-nomic
• langchain-ollama
• langchain-openrouter
• langchain-perplexity
• langchain-qdrant
• langchain-xai
• Other / not sure / general

Related Issues / PRs

No response

Reproduction Steps / Example Code (Python)

from dotenv import load_dotenv

from pydantic import BaseModel, Field
from typing import Literal
from langchain.agents import create_agent
from langchain.agents.structured_output import ProviderStrategy


load_dotenv()


class MeetingAction(BaseModel):
    """Action items extracted from a meeting transcript."""
    task: str = Field(description="The specific task to be completed")
    assignee: str = Field(description="Person responsible for the task")
    priority: Literal["low", "medium", "high"] = Field(description="Priority level")


agent = create_agent("mistral-medium-3-5",response_format=ProviderStrategy(MeetingAction))

res = agent.invoke({
    "messages": [{"role": "user", "content": "From our meeting: Sarah needs to update the project timeline as soon as possible"}]
})


print(res['structured_response'])

Error Message and Stack Trace (if applicable)

Error response 422 while fetching https://api.mistral.ai/v1/chat/completions: {"object":"error","message":{"detail":[{"type":"extra_forbidden","loc":["body","strict"],"msg":"Extra inputs are not permitted","input":true}]},"type":"invalid_request_error","param":null,"code":null,"raw_status_code":422}

Description

• I'm trying to use the langchain-mistralai library to implement structured output using a Pydantic schema with a Mistral AI model (specifically mistral-medium-3-5).
• I expect to see the model return a JSON response that adheres to my defined Pydantic schema, as the library should handle the parameter translation between LangChain's core logic and Mistral's API requirements.
• Instead, it does throw a 422 Unprocessable Entity error from the Mistral API. The error message indicates that an extra parameter "strict": true is being passed in the request body, which Mistral's API does not permit ("type": "extra_forbidden", "loc": ["body", "strict"]). It seems the strict parameter, common in OpenAI's structured outputs, is being incorrectly propagated to the Mistral API call.

System Info

System Information

OS: Windows OS Version: 10.0.26200 Python Version: 3.13.7 (tags/v3.13.7:bcee1c3, Aug 14 2025, 14:15:11) [MSC v.1944 64 bit (AMD64)]

Package Information

langchain_core: 1.3.3 langchain: 1.2.18 langchain_community: 0.4.1 langsmith: 0.7.33 langchain_anthropic: 1.4.3 langchain_classic: 1.0.4 langchain_cohere: 0.5.1 langchain_deepseek: 1.0.1 langchain_docling: 2.0.0 langchain_huggingface: 1.2.2 langchain_mistralai: 1.1.2 langchain_nvidia_ai_endpoints: 1.2.1 langchain_openai: 1.2.0 langchain_protocol: 0.0.15 langchain_text_splitters: 1.1.2 langchain_unstructured: 1.0.1 langgraph_sdk: 0.3.13