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 langchain_openai import ChatOpenAI

# Initialize a reasoning-capable model
llm = ChatOpenAI(base_url="URL",model="o1-mini", api_key="KEY")

# Invoke the model
response = llm.invoke("Explain how photosynthesis works in simple terms.")

# Current behavior: reasoning content is dropped during conversion
print("Final answer:", response.content)
print("Additional kwargs:", response.additional_kwargs)
# Output: additional_kwargs does NOT contain the model's reasoning process

Error Message and Stack Trace (if applicable)

Description

The problem

Currently, when models from the OpenAI provider return reasoning content, this content is not retrieved or stored during message conversion. This prevents users from displaying the logical analysis process of the model in their applications.

Current Behavior

The reasoning field from OpenAI API responses is ignored during:

• _convert_dict_to_message_dict conversion
• _convert_delta_to_message_chunk conversion

Expected Behavior

Reasoning content should be:

1. Extracted from responses when present
2. Stored in message's additional_kwargs under the key reasoning_content
3. Available for downstream processing and UI display

Proposed Solution

Modify the message conversion utilities in libs/partners/openai/langchain_openai/chat_models/base.py to:

• Extract the reasoning field from response dictionaries
• Store it in additional_kwargs['reasoning_content'] when present
• Handle both complete messages and streaming chunks

Usage example

Users who create chat interfaces or debugging tools want to display the reasoning process of the model separately from the final answer, similar to how the "Reasoning." sections are displayed in the native OpenAI interface.

System Info

System Information

OS: Linux OS Version: #107-Ubuntu SMP PREEMPT_DYNAMIC Fri Mar 13 19:51:50 UTC 2026 Python Version: 3.12.3 (main, Mar 3 2026, 12:15:18) [GCC 13.3.0]

Package Information

langchain_core: 1.2.23 langchain: 1.2.10 langchain_community: 0.4.1 langsmith: 0.7.6 langchain_classic: 1.0.1 langchain_mcp_adapters: 0.2.1 langchain_openai: 1.1.12 langchain_openrouter: 0.2.1 langchain_text_splitters: 1.1.1 langgraph_sdk: 0.3.8

Optional packages not installed

deepagents deepagents-cli

Other Dependencies

aiohttp: 3.13.3 dataclasses-json: 0.6.7 httpx: 0.28.1 httpx-sse: 0.4.3 jsonpatch: 1.33 langgraph: 1.0.9 mcp: 1.26.0 numpy: 2.4.2 openai: 2.30.0 openrouter: 0.8.0 opentelemetry-api: 1.40.0 opentelemetry-exporter-otlp-proto-http: 1.40.0 opentelemetry-sdk: 1.40.0 orjson: 3.11.7 packaging: 26.0 pydantic: 2.12.5 pydantic-settings: 2.13.1 PyYAML: 6.0.3 pyyaml: 6.0.3 requests: 2.32.5 requests-toolbelt: 1.0.0 SQLAlchemy: 2.0.46 sqlalchemy: 2.0.46 tenacity: 9.1.4 tiktoken: 0.12.0 typing-extensions: 4.15.0 uuid-utils: 0.14.1 wrapt: 1.17.3 xxhash: 3.6.0 zstandard: 0.25.0