phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-12 12:06:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(responses): add reasoning and annotation added events

Browse source 
Implements missing streaming events from OpenAI Responses API spec: reasoning text/summary events for o1/o3 models, refusal events for safety moderation, annotation events for citations, and file search streaming events. Added optional reasoning_content field to chat completion chunks to support non-standard provider extensions. Refactored streaming orchestrator to handle new content types via helper methods.
This commit is contained in:
Ashwin Bharambe 2025-10-11 14:24:32 -07:00
parent 32fde8d9a8
commit 3f1f7c3f7f
9 changed files with 3679 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/apis/inference/inference.py
View file

@ -776,12 +776,14 @@ class OpenAIChoiceDelta(BaseModel):
:param refusal: (Optional) The refusal of the delta
:param role: (Optional) The role of the delta
:param tool_calls: (Optional) The tool calls of the delta
:param reasoning_content: (Optional) The reasoning content from the model (non-standard, for o1/o3 models)
"""
content: str | None = None
refusal: str | None = None
role: str | None = None
tool_calls: list[OpenAIChatCompletionToolCall] | None = None
reasoning_content: str | None = None
@json_schema_type