# is_messages_state_schema

> **Function** in `langchain_azure_ai`

📖 [View in docs](https://reference.langchain.com/python/langchain-azure-ai/agents/hosting/_converters/_utils/is_messages_state_schema)

Return ``True`` when *state_schema* exposes a ``messages`` field.

LangGraph compiles graphs against a TypedDict (or dataclass-like) state
schema. The default request/response converters only know how to build
``{"messages": [...]}`` payloads, so we fast-fail when the schema does
not expose that key.

## Signature

```python
is_messages_state_schema(
    state_schema: Any,
) -> bool
```

## Parameters

| Name | Type | Required | Description |
|------|------|----------|-------------|
| `state_schema` | `Any` | Yes | The state schema class associated with a compiled graph. |

## Returns

`bool`

``True`` when the schema declares a ``messages`` field.

---

[View source on GitHub](https://github.com/langchain-ai/langchain-azure/blob/7a6a664d617264df8dcb12fcfb1bacc09f21d504/libs/azure-ai/langchain_azure_ai/agents/hosting/_converters/_utils.py#L13)