# How to configure dynamically on platform if now that config\_schema is gone in LangChain?

**URL:** <https://forum.langchain.com/t/how-to-configure-dynamically-on-platform-if-now-that-config-schema-is-gone-in-langchain/1955>\
**Category:** LangChain\
**Tags:** cloud, python-help\
**Created:** [October 26, 2025, 10:58pm UTC](https://forum.langchain.com/t/how-to-configure-dynamically-on-platform-if-now-that-config-schema-is-gone-in-langchain/1955 "2025-10-26T22:58:48Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![arturbagramyan1](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/arturbagramyan1/32/816_2.png) [@arturbagramyan1](https://forum.langchain.com/u/arturbagramyan1)\
**Post date:** [October 26, 2025, 10:58pm UTC](https://forum.langchain.com/t/how-to-configure-dynamically-on-platform-if-now-that-config-schema-is-gone-in-langchain/1955/1 "2025-10-26T22:58:49Z")

</div>

[https://www.youtube.com/watch?v=fMsQX6pwXkE](https://www.youtube.com/watch?v=fMsQX6pwXkE) so in that video it is provided to use config\_schema but in langchain v1 there is not such parametere anymore so i tried to passsing to context\_schema it worked but as i understand context\_schema is not used for that please provide information on how to do that on new version

```auto
example code :
async def make_supervisor_agent(config: RunnableConfig):
    configurable = config.get("configurable", {})
    llm = configurable.get("model", "openai/gpt-4.1")
    prompt = configurable.get(
        "system_prompt", "You are a helpful assistant")

    graph = create_agent(
        model=load_chat_model(llm),
        tools=[research_stock, execute_order],
        system_prompt=prompt,
        context_schema=Configuration,
        state_schema=SupervisorState,
        name="Supervisor Agent",
    )

    return graph

```