phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-13 14:08:39 +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 16:00:30 -07:00
parent 80d58ab519
commit c4dbaa9d4c
41 changed files with 3145 additions and 200 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/inline/agents/meta_reference/responses/streaming.py
View file

@ -49,7 +49,7 @@ from llama_stack.apis.inference import (
OpenAIAssistantMessageParam,
OpenAIChatCompletion,
OpenAIChatCompletionChunk,
OpenAIChatCompletionRequest,
OpenAIChatCompletionRequestWithExtraBody,
OpenAIChatCompletionToolCall,
OpenAIChoice,
OpenAIMessageParam,
@ -169,7 +169,7 @@ class StreamingResponseOrchestrator:
# (some providers don't support non-empty response_format when tools are present)
response_format = None if self.ctx.response_format.type == "text" else self.ctx.response_format
logger.debug(f"calling openai_chat_completion with tools: {self.ctx.chat_tools}")
params = OpenAIChatCompletionRequest(
params = OpenAIChatCompletionRequestWithExtraBody(
model=self.ctx.model,
messages=messages,
tools=self.ctx.chat_tools,