phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-11 05:38:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

test

Browse source 
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-10-09 20:53:19 -07:00
parent f50ce11a3b
commit 4a3d1e33f8
31 changed files with 727 additions and 892 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/inline/agents/meta_reference/agent_instance.py
View file

@ -49,6 +49,7 @@ from llama_stack.apis.inference import (
Inference,
Message,
OpenAIAssistantMessageParam,
OpenaiChatCompletionRequest,
OpenAIDeveloperMessageParam,
OpenAIMessageParam,
OpenAISystemMessageParam,
@ -582,7 +583,7 @@ class ChatAgent(ShieldRunnerMixin):
max_tokens = getattr(sampling_params, "max_tokens", None)
# Use OpenAI chat completion
openai_stream = await self.inference_api.openai_chat_completion(
params = OpenaiChatCompletionRequest(
model=self.agent_config.model,
messages=openai_messages,
tools=openai_tools if openai_tools else None,
@ -593,6 +594,7 @@ class ChatAgent(ShieldRunnerMixin):
max_tokens=max_tokens,
stream=True,
)
openai_stream = await self.inference_api.openai_chat_completion(params)
# Convert OpenAI stream back to Llama Stack format
response_stream = convert_openai_chat_completion_stream(

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

@ -41,6 +41,7 @@ from llama_stack.apis.inference import (
Inference,
OpenAIAssistantMessageParam,
OpenAIChatCompletion,
OpenaiChatCompletionRequest,
OpenAIChatCompletionToolCall,
OpenAIChoice,
OpenAIMessageParam,
@ -130,7 +131,7 @@ 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}")
completion_result = await self.inference_api.openai_chat_completion(
params = OpenaiChatCompletionRequest(
model=self.ctx.model,
messages=messages,
tools=self.ctx.chat_tools,
@ -138,6 +139,7 @@ class StreamingResponseOrchestrator:
temperature=self.ctx.temperature,
response_format=response_format,
)
completion_result = await self.inference_api.openai_chat_completion(params)
# Process streaming chunks and build complete response
completion_result_data = None