phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-12 13:57:57 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

featu: support passing "extra body" throught to providers

Browse source 
# What does this PR do?
Allows passing through extra_body parameters to inference providers.


closes #2720

## Test Plan
CI and added new test
This commit is contained in:
Eric Huang 2025-10-10 15:40:30 -07:00
parent cb7fb0705b
commit 9f50338a4e
35 changed files with 1892 additions and 199 deletions
Download patch file Download diff file Expand all files Collapse all files

4
tests/unit/providers/agents/meta_reference/test_openai_responses.py
View file

@ -33,7 +33,7 @@ from llama_stack.apis.agents.openai_responses import (
from llama_stack.apis.inference import (
OpenAIAssistantMessageParam,
OpenAIChatCompletionContentPartTextParam,
OpenAIChatCompletionRequest,
OpenAIChatCompletionRequestWithExtraBody,
OpenAIDeveloperMessageParam,
OpenAIJSONSchema,
OpenAIResponseFormatJSONObject,
@ -162,7 +162,7 @@ async def test_create_openai_response_with_string_input(openai_responses_impl, m
chunks = [chunk async for chunk in result]
mock_inference_api.openai_chat_completion.assert_called_once_with(
OpenAIChatCompletionRequest(
OpenAIChatCompletionRequestWithExtraBody(
model=model,
messages=[OpenAIUserMessageParam(role="user", content="What is the capital of Ireland?", name=None)],
response_format=None,