# LangGraph .ainvoke() breaks ASGI async context

**URL:** <https://forum.langchain.com/t/langgraph-ainvoke-breaks-asgi-async-context/99>\
**Category:** LangGraph\
**Tags:** python-help\
**Created:** [July 1, 2025, 1:30am UTC](https://forum.langchain.com/t/langgraph-ainvoke-breaks-asgi-async-context/99 "2025-07-01T01:30:35Z")\
**Posts on this page:** 7\
**Page:** 1

<div class="post-metadata">

**Author:** ![edward](https://avatars.discourse-cdn.com/v4/letter/e/90db22/32.png) [@edward](https://forum.langchain.com/u/edward)\
**Post date:** [July 1, 2025, 1:30am UTC](https://forum.langchain.com/t/langgraph-ainvoke-breaks-asgi-async-context/99/1 "2025-07-01T01:30:35Z")

</div>

When using LangGraph tools that are invoked via `.ainvoke()`, we’re experiencing async context loss that seems to be specific to LangGraph. This appears to be related to how LangGraph handles async execution contexts differently from ASGI servers.

**Background:** In ASGI applications (Django, FastAPI, etc.), async views can seamlessly call synchronous database operations because the ASGI server automatically handles the sync/async boundary while preserving request context (user sessions, database connections, tenant information, etc.).

However, when LangGraph executes tools through `.ainvoke()`, this automatic context preservation breaks down. Functions that work perfectly in regular ASGI views fail when executed within LangGraph’s .ainvoke async context.

SEE: [Async programming with langchain | 🦜️🔗 LangChain](https://python.langchain.com/docs/concepts/async/#delegation-to-sync-methods)

> By default, LangChain will delegate the execution of unimplemented asynchronous methods to the synchronous counterparts. LangChain almost always assumes that the synchronous method should be treated as a blocking operation and should be run in a separate thread. This is done using asyncio.loop.run\_in\_executor functionality provided by the `asyncio` library

For example:

```auto
@tool("db_tool", parse_docstring=True)
def get_foo_object(name: str, config: RunnableConfig) -> Foo:
    """Get a Foo by name."""
    # This fails when called via LangGraph's ainvoke()
    # Works fine with ASGI Django async views
    return Foo.objects.get(name = name)

```

**Error symptoms:**

- DB context loss (at least seen using django)
- Thread-related database connection issues
- “Can’t call sync method from async context” errors

**Resolution**  
We resolved this by making all tool calls async functions, and wrapping any unresolved syncronous functions used in them with the asgiref.sync library’s `sync_to_async` ([django doc ref](https://docs.djangoproject.com/en/5.2/topics/async/#asgiref.sync.sync_to_async)), which will by default run on the same thread as other thread sensitive functions, thereby preserving async context.

This resolution isn’t ideal, as this can present itself in many ways. I am wondering if there is  
a) guidance on a cleaner way to resolve this without one-off wrappers (seems this can happen with any ASGI python server regardless of framework)  
b) the potential for langgraph to add a parameter to ainvoke that enables a similar `thread_sensitive` capability

Any insight is appreciated

---

<div class="post-metadata">

**Author:** ![wfh](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/wfh/32/33_2.png) [@wfh](https://forum.langchain.com/u/wfh)\
**Post date:** [July 1, 2025, 5:43pm UTC](https://forum.langchain.com/t/langgraph-ainvoke-breaks-asgi-async-context/99/2 "2025-07-01T17:43:06Z")

</div>

Why not write the tool as a native async function so it doesn’t have to be run on a thread?

But this does sound like it could be a bug in how the config is being propagated, since we do copy context in most cases. Someone from the team will look into this

---

<div class="post-metadata">

**Author:** ![system](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/system/32/1_2.png) [@system](https://forum.langchain.com/u/system)\
**Post date:** [July 1, 2025, 5:43pm UTC](https://forum.langchain.com/t/langgraph-ainvoke-breaks-asgi-async-context/99/3 "2025-07-01T17:43:56Z")

</div>



---

<div class="post-metadata">

**Author:** ![system](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/system/32/1_2.png) [@system](https://forum.langchain.com/u/system)\
**Post date:** [July 1, 2025, 5:46pm UTC](https://forum.langchain.com/t/langgraph-ainvoke-breaks-asgi-async-context/99/4 "2025-07-01T17:46:25Z")

</div>



---

<div class="post-metadata">

**Author:** ![edward](https://avatars.discourse-cdn.com/v4/letter/e/90db22/32.png) [@edward](https://forum.langchain.com/u/edward)\
**Post date:** [July 1, 2025, 6:22pm UTC](https://forum.langchain.com/t/langgraph-ainvoke-breaks-asgi-async-context/99/5 "2025-07-01T18:22:27Z")

</div>

Thanks for the quick response Will!

We could write these as native async functions explicitly, but it would be an antipattern in our codebase; we have service/helper layers written sync (not explicitly async), and the ASGI framework(s) auto-resolve async handling. So we’d need to define async functions only for Langgraph parts of the code, but the rest of the codebase doesn’t need it.

There’s also not a good way to enforce that- if someone takes an existing function and wants to use it as a tool but forgets to explicitly make it async, it’d continue to work everywhere else, but there would be unintended potentially hard to identify side-effects when invoked with LangGraph- _eventually_ this will happen.

This could potentially help a lot of Django/FastAPI/Starlette users who want to use existing sync service/helper code layers with LangGraph without changing their codebase practices. Appreciate the support!

---

<div class="post-metadata">

**Author:** ![wfh](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/wfh/32/33_2.png) [@wfh](https://forum.langchain.com/u/wfh)\
**Post date:** [July 1, 2025, 11:17pm UTC](https://forum.langchain.com/t/langgraph-ainvoke-breaks-asgi-async-context/99/6 "2025-07-01T23:17:51Z")

</div>

Ya makes sense. For context, we do auto-promote and copy\_context() to propagate async context vars to the sync functions in general. This is also included in CI, so we must be hitting a corner case here somehow.

Do you happen to have a full MRE you could share that illustrates it (just to help our team address this for you faster)

---

<div class="post-metadata">

**Author:** ![edward](https://avatars.discourse-cdn.com/v4/letter/e/90db22/32.png) [@edward](https://forum.langchain.com/u/edward)\
**Post date:** [July 2, 2025, 5:51pm UTC](https://forum.langchain.com/t/langgraph-ainvoke-breaks-asgi-async-context/99/7 "2025-07-02T17:51:57Z")

</div>

Our project is a bit involved, let me get a cycle and I’ll think of a scoped down example for reproduction.