phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 23:29:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(responses): add MCP argument streaming and content part events

Browse source 
- Add content part events (response.content_part.added/done) for granular text streaming
- Implement MCP-specific argument streaming (response.mcp_call.arguments.delta/done)
- Differentiate between MCP and function call streaming events
- Update unit and integration tests for new streaming events
- Ensure proper event ordering and OpenAI spec compliance

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Ashwin Bharambe 2025-08-12 23:02:39 -07:00
parent 3972ddfd43
commit 975e70cab3
4 changed files with 242 additions and 35 deletions
Download patch file Download diff file Expand all files Collapse all files

54
llama_stack/apis/agents/openai_responses.py
View file

@ -623,6 +623,58 @@ class OpenAIResponseObjectStreamResponseMcpCallCompleted(BaseModel):
type: Literal["response.mcp_call.completed"] = "response.mcp_call.completed"
@json_schema_type
class OpenAIResponseContentPart(BaseModel):
"""Base class for response content parts."""
id: str
type: str
@json_schema_type
class OpenAIResponseContentPartText(OpenAIResponseContentPart):
"""Text content part for streaming responses."""
text: str
type: Literal["text"] = "text"
@json_schema_type
class OpenAIResponseObjectStreamResponseContentPartAdded(BaseModel):
"""Streaming event for when a new content part is added to a response item.
:param response_id: Unique identifier of the response containing this content
:param item_id: Unique identifier of the output item containing this content part
:param part: The content part that was added
:param sequence_number: Sequential number for ordering streaming events
:param type: Event type identifier, always "response.content_part.added"
"""
response_id: str
item_id: str
part: OpenAIResponseContentPart
sequence_number: int
type: Literal["response.content_part.added"] = "response.content_part.added"
@json_schema_type
class OpenAIResponseObjectStreamResponseContentPartDone(BaseModel):
"""Streaming event for when a content part is completed.
:param response_id: Unique identifier of the response containing this content
:param item_id: Unique identifier of the output item containing this content part
:param part: The completed content part
:param sequence_number: Sequential number for ordering streaming events
:param type: Event type identifier, always "response.content_part.done"
"""
response_id: str
item_id: str
part: OpenAIResponseContentPart
sequence_number: int
type: Literal["response.content_part.done"] = "response.content_part.done"
OpenAIResponseObjectStream = Annotated[
OpenAIResponseObjectStreamResponseCreated
| OpenAIResponseObjectStreamResponseOutputItemAdded
@ -642,6 +694,8 @@ OpenAIResponseObjectStream = Annotated[
| OpenAIResponseObjectStreamResponseMcpCallInProgress
| OpenAIResponseObjectStreamResponseMcpCallFailed
| OpenAIResponseObjectStreamResponseMcpCallCompleted
| OpenAIResponseObjectStreamResponseContentPartAdded
| OpenAIResponseObjectStreamResponseContentPartDone
| OpenAIResponseObjectStreamResponseCompleted,
Field(discriminator="type"),
]