scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-08 03:08:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 114

fix(realtime): forward guardrail metadata for generic provider_config and vertex_ai paths

Browse source 
The _arealtime function was not passing user_api_key_dict or litellm_metadata to base_llm_http_handler.async_realtime() for the generic provider_config path and the vertex_ai-specific path. This broke guardrail resolution since RealTimeStreaming.request_data was empty, causing should_run_guardrail to return False.

Made-with: Cursor
This commit is contained in:
Ishaan Jaffer 2026-02-26 01:08:23 -08:00
parent 24159b3cea
commit 3ab2444e98
1 changed files with 4 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
litellm/realtime_api/main.py
View file

@ -106,6 +106,8 @@ async def _arealtime( # noqa: PLR0915
client=client,
timeout=timeout,
headers=headers,
user_api_key_dict=kwargs.get("user_api_key_dict"),
litellm_metadata=_build_litellm_metadata(kwargs),
)
elif _custom_llm_provider == "azure":
api_base = (
@ -277,6 +279,8 @@ async def _arealtime( # noqa: PLR0915
client=client,
timeout=timeout,
headers=headers,
user_api_key_dict=kwargs.get("user_api_key_dict"),
litellm_metadata=_build_litellm_metadata(kwargs),
)
else:
raise ValueError(f"Unsupported model: {model}")