phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 18:00:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat!: Wire through parallel_tool_calls to Responses API (#4124)

Browse source 
# What does this PR do?
Initial PR against #4123
Adds `parallel_tool_calls` spec to Responses API and basic initial
implementation where no more than one function call is generated when
set to `False`.

## Test Plan
* Unit tests have been added to verify no more than one function call is
generated.
* A followup PR will verify passing through `parallel_tool_calls` to
providers.
* A followup PR will address verification and/or implementation of
incremental function calling across multiple conversational turns.

---------

Signed-off-by: Anastas Stoyanovsky <astoyano@redhat.com>
This commit is contained in:
Anastas Stoyanovsky 2025-11-18 14:25:08 -05:00 • committed by GitHub
parent 7093978754
commit a3580e6bc0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 73 additions and 32 deletions
Download patch file Download diff file Expand all files Collapse all files

1
src/llama_stack_api/agents.py
View file

@ -72,6 +72,7 @@ class Agents(Protocol):
model: str,
prompt: OpenAIResponsePrompt | None = None,
instructions: str | None = None,
parallel_tool_calls: bool | None = True,
previous_response_id: str | None = None,
conversation: str | None = None,
store: bool | None = True,

4
src/llama_stack_api/openai_responses.py
View file

@ -585,7 +585,7 @@ class OpenAIResponseObject(BaseModel):
:param model: Model identifier used for generation
:param object: Object type identifier, always "response"
:param output: List of generated output items (messages, tool calls, etc.)
:param parallel_tool_calls: Whether tool calls can be executed in parallel
:param parallel_tool_calls: (Optional) Whether to allow more than one function tool call generated per turn.
:param previous_response_id: (Optional) ID of the previous response in a conversation
:param prompt: (Optional) Reference to a prompt template and its variables.
:param status: Current status of the response generation
@ -605,7 +605,7 @@ class OpenAIResponseObject(BaseModel):
model: str
object: Literal["response"] = "response"
output: Sequence[OpenAIResponseOutput]
parallel_tool_calls: bool = False
parallel_tool_calls: bool | None = True
previous_response_id: str | None = None
prompt: OpenAIResponsePrompt | None = None
status: str