phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 09:53:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into auto_instrument_1

Browse source
This commit is contained in:
Emilio Garcia 2025-11-18 15:06:15 -05:00 • committed by GitHub
commit 5984ae6a76
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

19
client-sdks/stainless/openapi.yml
View file

@ -6723,9 +6723,10 @@ components:
type: array
title: Output
parallel_tool_calls:
type: boolean
title: Parallel Tool Calls
default: false
anyOf:
- type: boolean
- type: 'null'
default: true
previous_response_id:
anyOf:
- type: string
@ -7125,6 +7126,11 @@ components:
anyOf:
- type: string
- type: 'null'
parallel_tool_calls:
anyOf:
- type: boolean
- type: 'null'
default: true
previous_response_id:
anyOf:
- type: string
@ -7251,9 +7257,10 @@ components:
type: array
title: Output
parallel_tool_calls:
type: boolean
title: Parallel Tool Calls
default: false
anyOf:
- type: boolean
- type: 'null'
default: true
previous_response_id:
anyOf:
- type: string

19
docs/static/deprecated-llama-stack-spec.yaml vendored
View file

@ -3566,9 +3566,10 @@ components:
type: array
title: Output
parallel_tool_calls:
type: boolean
title: Parallel Tool Calls
default: false
anyOf:
- type: boolean
- type: 'null'
default: true
previous_response_id:
anyOf:
- type: string
@ -3968,6 +3969,11 @@ components:
anyOf:
- type: string
- type: 'null'
parallel_tool_calls:
anyOf:
- type: boolean
- type: 'null'
default: true
previous_response_id:
anyOf:
- type: string
@ -4094,9 +4100,10 @@ components:
type: array
title: Output
parallel_tool_calls:
type: boolean
title: Parallel Tool Calls
default: false
anyOf:
- type: boolean
- type: 'null'
default: true
previous_response_id:
anyOf:
- type: string

14
docs/static/experimental-llama-stack-spec.yaml vendored
View file

@ -3263,9 +3263,10 @@ components:
type: array
title: Output
parallel_tool_calls:
type: boolean
title: Parallel Tool Calls
default: false
anyOf:
- type: boolean
- type: 'null'
default: true
previous_response_id:
anyOf:
- type: string
@ -3662,9 +3663,10 @@ components:
type: array
title: Output
parallel_tool_calls:
type: boolean
title: Parallel Tool Calls
default: false
anyOf:
- type: boolean
- type: 'null'
default: true
previous_response_id:
anyOf:
- type: string

19
docs/static/llama-stack-spec.yaml vendored
View file

@ -5744,9 +5744,10 @@ components:
type: array
title: Output
parallel_tool_calls:
type: boolean
title: Parallel Tool Calls
default: false
anyOf:
- type: boolean
- type: 'null'
default: true
previous_response_id:
anyOf:
- type: string
@ -6146,6 +6147,11 @@ components:
anyOf:
- type: string
- type: 'null'
parallel_tool_calls:
anyOf:
- type: boolean
- type: 'null'
default: true
previous_response_id:
anyOf:
- type: string
@ -6272,9 +6278,10 @@ components:
type: array
title: Output
parallel_tool_calls:
type: boolean
title: Parallel Tool Calls
default: false
anyOf:
- type: boolean
- type: 'null'
default: true
previous_response_id:
anyOf:
- type: string

19
docs/static/stainless-llama-stack-spec.yaml vendored
View file

@ -6723,9 +6723,10 @@ components:
type: array
title: Output
parallel_tool_calls:
type: boolean
title: Parallel Tool Calls
default: false
anyOf:
- type: boolean
- type: 'null'
default: true
previous_response_id:
anyOf:
- type: string
@ -7125,6 +7126,11 @@ components:
anyOf:
- type: string
- type: 'null'
parallel_tool_calls:
anyOf:
- type: boolean
- type: 'null'
default: true
previous_response_id:
anyOf:
- type: string
@ -7251,9 +7257,10 @@ components:
type: array
title: Output
parallel_tool_calls:
type: boolean
title: Parallel Tool Calls
default: false
anyOf:
- type: boolean
- type: 'null'
default: true
previous_response_id:
anyOf:
- type: string

2
src/llama_stack/providers/inline/agents/meta_reference/agents.py
View file

@ -90,6 +90,7 @@ class MetaReferenceAgentsImpl(Agents):
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,
@ -118,6 +119,7 @@ class MetaReferenceAgentsImpl(Agents):
include,
max_infer_iters,
guardrails,
parallel_tool_calls,
max_tool_calls,
)
return result # type: ignore[no-any-return]

4
src/llama_stack/providers/inline/agents/meta_reference/responses/openai_responses.py
View file

@ -252,6 +252,7 @@ class OpenAIResponsesImpl:
include: list[str] | None = None,
max_infer_iters: int | None = 10,
guardrails: list[str | ResponseGuardrailSpec] | None = None,
parallel_tool_calls: bool | None = None,
max_tool_calls: int | None = None,
):
stream = bool(stream)
@ -296,6 +297,7 @@ class OpenAIResponsesImpl:
tools=tools,
max_infer_iters=max_infer_iters,
guardrail_ids=guardrail_ids,
parallel_tool_calls=parallel_tool_calls,
max_tool_calls=max_tool_calls,
)
@ -346,6 +348,7 @@ class OpenAIResponsesImpl:
tools: list[OpenAIResponseInputTool] | None = None,
max_infer_iters: int | None = 10,
guardrail_ids: list[str] | None = None,
parallel_tool_calls: bool | None = True,
max_tool_calls: int | None = None,
) -> AsyncIterator[OpenAIResponseObjectStream]:
# These should never be None when called from create_openai_response (which sets defaults)
@ -385,6 +388,7 @@ class OpenAIResponsesImpl:
created_at=created_at,
text=text,
max_infer_iters=max_infer_iters,
parallel_tool_calls=parallel_tool_calls,
tool_executor=self.tool_executor,
safety_api=self.safety_api,
guardrail_ids=guardrail_ids,

4
src/llama_stack/providers/inline/agents/meta_reference/responses/streaming.py
View file

@ -116,6 +116,7 @@ class StreamingResponseOrchestrator:
safety_api,
guardrail_ids: list[str] | None = None,
prompt: OpenAIResponsePrompt | None = None,
parallel_tool_calls: bool | None = None,
max_tool_calls: int | None = None,
):
self.inference_api = inference_api
@ -130,6 +131,8 @@ class StreamingResponseOrchestrator:
self.prompt = prompt
# System message that is inserted into the model's context
self.instructions = instructions
# Whether to allow more than one function tool call generated per turn.
self.parallel_tool_calls = parallel_tool_calls
# Max number of total calls to built-in tools that can be processed in a response
self.max_tool_calls = max_tool_calls
self.sequence_number = 0
@ -192,6 +195,7 @@ class StreamingResponseOrchestrator:
usage=self.accumulated_usage,
instructions=self.instructions,
prompt=self.prompt,
parallel_tool_calls=self.parallel_tool_calls,
max_tool_calls=self.max_tool_calls,
)

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