mirror of
https://github.com/hwchase17/langchain.git
synced 2025-08-28 14:05:02 +00:00
Following https://github.com/langchain-ai/langchain/pull/30909: need to retain "empty" reasoning output when streaming, e.g., ```python {'id': 'rs_...', 'summary': [], 'type': 'reasoning'} ``` Tested by existing integration tests, which are currently failing. |
||
---|---|---|
.. | ||
__init__.py | ||
azure.py | ||
base.py |