Langchain-ollama error for strict parameter with gpt oss 20b cloud model

[MeetSolanki530]

Checked other resources

• 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-cli
• 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-perplexity
• langchain-prompty
• langchain-qdrant
• langchain-xai
• Other / not sure / general

Example Code (Python)

from typing import List

from pydantic import BaseModel, Field
from dotenv import load_dotenv
from langchain.tools import tool

load_dotenv()

from langchain_tavily import TavilySearch
from langchain_core.messages import HumanMessage
from langchain.agents import create_agent
from langchain_ollama import ChatOllama

class Source(BaseModel):
    """Schema for a source used by the agent"""

    url: str = Field(description="The URL of the source")


class AgentResponse(BaseModel):
    """Schema for agent response with answer and sources"""

    answer: str = Field(description="Thr agent's answer to the query")
    sources: List[Source] = Field(
        default_factory=list, description="List of sources used to generate the answer"
    )

@tool
def search_website(query : str) -> str:
    """
    Search the Website/Internet for provided query and
    respond Content from Web for provided query.
    
    Args : 
    query : str

    Output : 

    Resultant Content for provided query via websearch.

    """

    print(f"Searching for {query}")
    tool = TavilySearch()
    return tool.invoke(query)



llm = ChatOllama(model="gpt-oss:20b-cloud")
tools = [search_website]
agent = create_agent(model=llm, tools=tools)
agent = create_agent(model=llm, tools=tools, response_format=AgentResponse)


def main():
    print("Hello from langchain!")


result = agent.invoke(
            {"messages": HumanMessage(content="search for 3 job postings for an ai engineer using langchain in the bay area on linkedin and list their details?")},
            {
                "messages": HumanMessage(
                    content="search for 3 job postings for an ai engineer using langchain in the bay area on linkedin and list their details?"
                )
            }
    )

print(result)

Error Message and Stack Trace (if applicable)

myenv) PS F:\Udemy\Langchain&LanggraphProject> & C:/Users/solan/anaconda3/envs/myenv/python.exe "f:/Udemy/Langchain&LanggraphProject/main_structure.py"
Traceback (most recent call last):
  File "f:\Udemy\Langchain&LanggraphProject\main_structure.py", line 59, in <module>
    result = agent.invoke(
             ^^^^^^^^^^^^^
  File "C:\Users\solan\anaconda3\envs\myenv\Lib\site-packages\langgraph\pregel\main.py", line 3068, in invoke
    for chunk in self.stream(
                 ^^^^^^^^^^^^
  File "C:\Users\solan\anaconda3\envs\myenv\Lib\site-packages\langgraph\pregel\main.py", line 2643, in stream
    for _ in runner.tick(
             ^^^^^^^^^^^^
  File "C:\Users\solan\anaconda3\envs\myenv\Lib\site-packages\langgraph\pregel\_runner.py", line 167, in tick
    run_with_retry(
  File "C:\Users\solan\anaconda3\envs\myenv\Lib\site-packages\langgraph\pregel\_retry.py", line 42, in run_with_retry
    return task.proc.invoke(task.input, config)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\solan\anaconda3\envs\myenv\Lib\site-packages\langgraph\_internal\_runnable.py", line 656, in invoke
    input = context.run(step.invoke, input, config, **kwargs)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\solan\anaconda3\envs\myenv\Lib\site-packages\langgraph\_internal\_runnable.py", line 400, in invoke
    ret = self.func(*args, **kwargs)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\solan\anaconda3\envs\myenv\Lib\site-packages\langchain\agents\factory.py", line 1129, in model_node
    response = _execute_model_sync(request)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\solan\anaconda3\envs\myenv\Lib\site-packages\langchain\agents\factory.py", line 1102, in _execute_model_sync       
    output = model_.invoke(messages)
             ^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\solan\anaconda3\envs\myenv\Lib\site-packages\langchain_core\runnables\base.py", line 5534, in invoke
    return self.bound.invoke(
           ^^^^^^^^^^^^^^^^^^
  File "C:\Users\solan\anaconda3\envs\myenv\Lib\site-packages\langchain_core\language_models\chat_models.py", line 398, in invoke   
    self.generate_prompt(
  File "C:\Users\solan\anaconda3\envs\myenv\Lib\site-packages\langchain_core\language_models\chat_models.py", line 1117, in generate_prompt
    return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\solan\anaconda3\envs\myenv\Lib\site-packages\langchain_core\language_models\chat_models.py", line 927, in generate 
    self._generate_with_cache(
  File "C:\Users\solan\anaconda3\envs\myenv\Lib\site-packages\langchain_core\language_models\chat_models.py", line 1221, in _generate_with_cache
    result = self._generate(
             ^^^^^^^^^^^^^^^
  File "C:\Users\solan\anaconda3\envs\myenv\Lib\site-packages\langchain_ollama\chat_models.py", line 1025, in _generate
    final_chunk = self._chat_stream_with_aggregation(
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\solan\anaconda3\envs\myenv\Lib\site-packages\langchain_ollama\chat_models.py", line 960, in _chat_stream_with_aggregation
    for chunk in self._iterate_over_stream(messages, stop, **kwargs):
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\solan\anaconda3\envs\myenv\Lib\site-packages\langchain_ollama\chat_models.py", line 1049, in _iterate_over_stream  
    for stream_resp in self._create_chat_stream(messages, stop, **kwargs):
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\solan\anaconda3\envs\myenv\Lib\site-packages\langchain_ollama\chat_models.py", line 947, in _create_chat_stream    
    yield from self._client.chat(**chat_params)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: Client.chat() got an unexpected keyword argument 'strict'
During task with name 'model' and id 'ffa00513-5724-b310-4087-ff444c3e5b47'
(myenv) PS F:\Udemy\Langchain&LanggraphProject>

Description

I’ve tried using Python 3.10 and 3.12, but I’m still getting the same error related to the strict parameter. This issue didn’t occur when I was using other local models it seems to be specific to this model. I also tested it directly with Ollama’s Python client, and it worked fine there, but the problem appears when using the LangChain Ollama package.

System Info

(myenv) PS F:\Udemy\Langchain&LanggraphProject> & C:/Users/solan/anaconda3/envs/myenv/python.exe "f:/Udemy/Langchain&LanggraphProject/main_structure.py"

System Information

OS: Windows
OS Version: 10.0.26200
Python Version: 3.12.12 | packaged by Anaconda, Inc. | (main, Oct 21 2025, 20:05:38) [MSC v.1929 64 bit (AMD64)]

Package Information

langchain_core: 1.1.0
langchain: 1.1.0
langchain_community: 0.4.1
langsmith: 0.4.48
langchain_classic: 1.0.0
langchain_groq: 1.1.0
langchain_nvidia_ai_endpoints: 1.0.0
langchain_ollama: 1.0.0
langchain_openai: 1.1.0
langchain_tavily: 0.2.13
langchain_text_splitters: 1.0.0
langgraph_sdk: 0.2.10

Optional packages not installed

langserve

Other Dependencies

aiohttp: 3.13.2
dataclasses-json: 0.6.7
filetype: 1.2.0
groq: 0.36.0
httpx: 0.28.1
httpx-sse: 0.4.3
jsonpatch: 1.33
langgraph: 1.0.4
numpy: 2.3.5
ollama: 0.6.1
openai: 2.8.1
orjson: 3.11.4
packaging: 25.0
pydantic: 2.12.4
pydantic-settings: 2.12.0
pyyaml: 6.0.3
PyYAML: 6.0.3
requests: 2.32.5
requests-toolbelt: 1.0.0
SQLAlchemy: 2.0.44
sqlalchemy: 2.0.44
tenacity: 9.1.2
tiktoken: 0.12.0
typing-extensions: 4.15.0
zstandard: 0.25.0
(myenv) PS F:\Udemy\Langchain&LanggraphProject>

[keenborder786]

Meet Solanki (@MeetSolanki530), use the ToolStrategy and you will be good:

agent = create_agent(model=llm, response_format=ToolStrategy(schema=AgentResponse))