# track_pending_interrupts

> **Function** in `langchain_azure_ai`

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

Pass through a graph stream while recording its active interrupts.

LangGraph's ``updates.__interrupt__`` payload is the authoritative active
set for the current invocation. Unlike checkpoint task history, it does
not retain a parallel sibling after that sibling has been answered.

## Signature

```python
track_pending_interrupts(
    graph_stream: AsyncIterator[Any],
    pending: list[Interrupt],
) -> AsyncIterator[Any]
```

## Parameters

| Name | Type | Required | Description |
|------|------|----------|-------------|
| `graph_stream` | `AsyncIterator[Any]` | Yes | A multi-mode LangGraph stream containing ``updates``. |
| `pending` | `list[Interrupt]` | Yes | Mutable output list containing the interrupts observed during this invocation, deduplicated by id. |

---

[View source on GitHub](https://github.com/langchain-ai/langchain-azure/blob/7a6a664d617264df8dcb12fcfb1bacc09f21d504/libs/azure-ai/langchain_azure_ai/agents/hosting/_converters/_hitl.py#L160)