phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-03 19:57:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: don't pass default response format in Responses

Browse source 
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-09-30 11:24:27 -07:00
parent 6cce553c93
commit 0cc072dcaf
1 changed files with 4 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama_stack/providers/inline/agents/meta_reference/responses/streaming.py
View file

@ -127,13 +127,16 @@ class StreamingResponseOrchestrator:
messages = self.ctx.messages.copy() messages = self.ctx.messages.copy()
while True: while True:
# Text is the default response format for chat completion so don't need to pass it
# (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
completion_result = await self.inference_api.openai_chat_completion( completion_result = await self.inference_api.openai_chat_completion(
model=self.ctx.model, model=self.ctx.model,
messages=messages, messages=messages,
tools=self.ctx.chat_tools, tools=self.ctx.chat_tools,
stream=True, stream=True,
temperature=self.ctx.temperature, temperature=self.ctx.temperature,
response_format=self.ctx.response_format, response_format=response_format,
) )
# Process streaming chunks and build complete response # Process streaming chunks and build complete response