phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-04 05:12:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into watsonx_health_check

Browse source
This commit is contained in:
Sumit Jaiswal 2025-05-30 00:26:52 +05:30 • committed by GitHub
commit 6af13bbbf0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 86 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

21
llama_stack/providers/inline/agents/meta_reference/openai_responses.py
View file

@ -292,12 +292,12 @@ class OpenAIResponsesImpl:
async def _store_response(
self,
response: OpenAIResponseObject,
original_input: str | list[OpenAIResponseInput],
input: str | list[OpenAIResponseInput],
) -> None:
new_input_id = f"msg_{uuid.uuid4()}"
if isinstance(original_input, str):
if isinstance(input, str):
# synthesize a message from the input string
input_content = OpenAIResponseInputMessageContentText(text=original_input)
input_content = OpenAIResponseInputMessageContentText(text=input)
input_content_item = OpenAIResponseMessage(
role="user",
content=[input_content],
@ -307,7 +307,7 @@ class OpenAIResponsesImpl:
else:
# we already have a list of messages
input_items_data = []
for input_item in original_input:
for input_item in input:
if isinstance(input_item, OpenAIResponseMessage):
# These may or may not already have an id, so dump to dict, check for id, and add if missing
input_item_dict = input_item.model_dump()
@ -334,7 +334,6 @@ class OpenAIResponsesImpl:
tools: list[OpenAIResponseInputTool] | None = None,
):
stream = False if stream is None else stream
original_input = input # Keep reference for storage
output_messages: list[OpenAIResponseOutput] = []
@ -372,7 +371,7 @@ class OpenAIResponsesImpl:
inference_result=inference_result,
ctx=ctx,
output_messages=output_messages,
original_input=original_input,
input=input,
model=model,
store=store,
tools=tools,
@ -382,7 +381,7 @@ class OpenAIResponsesImpl:
inference_result=inference_result,
ctx=ctx,
output_messages=output_messages,
original_input=original_input,
input=input,
model=model,
store=store,
tools=tools,
@ -393,7 +392,7 @@ class OpenAIResponsesImpl:
inference_result: Any,
ctx: ChatCompletionContext,
output_messages: list[OpenAIResponseOutput],
original_input: str | list[OpenAIResponseInput],
input: str | list[OpenAIResponseInput],
model: str,
store: bool | None,
tools: list[OpenAIResponseInputTool] | None,
@ -423,7 +422,7 @@ class OpenAIResponsesImpl:
if store:
await self._store_response(
response=response,
original_input=original_input,
input=input,
)
return response
@ -433,7 +432,7 @@ class OpenAIResponsesImpl:
inference_result: Any,
ctx: ChatCompletionContext,
output_messages: list[OpenAIResponseOutput],
original_input: str | list[OpenAIResponseInput],
input: str | list[OpenAIResponseInput],
model: str,
store: bool | None,
tools: list[OpenAIResponseInputTool] | None,
@ -544,7 +543,7 @@ class OpenAIResponsesImpl:
if store:
await self._store_response(
response=final_response,
original_input=original_input,
input=input,
)
# Emit response.completed

2
llama_stack/providers/remote/inference/sambanova/sambanova.py
View file

@ -218,7 +218,7 @@ class SambaNovaInferenceAdapter(LiteLLMOpenAIMixin):
"json_schema": {
"name": name,
"schema": fmt,
"strict": True,
"strict": False,
},
}
if request.tools: