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

feat: split API and provider specs into separate llama-stack-api pkg (#3895)

Browse source 
# What does this PR do?

Extract API definitions and provider specifications into a standalone
llama-stack-api package that can be published to PyPI independently of
the main llama-stack server.


see: https://github.com/llamastack/llama-stack/pull/2978 and
https://github.com/llamastack/llama-stack/pull/2978#issuecomment-3145115942

Motivation

External providers currently import from llama-stack, which overrides
the installed version and causes dependency conflicts. This separation
allows external providers to:

- Install only the type definitions they need without server
dependencies
- Avoid version conflicts with the installed llama-stack package
- Be versioned and released independently

This enables us to re-enable external provider module tests that were
previously blocked by these import conflicts.

Changes

- Created llama-stack-api package with minimal dependencies (pydantic,
jsonschema)
- Moved APIs, providers datatypes, strong_typing, and schema_utils
- Updated all imports from llama_stack.* to llama_stack_api.*
- Configured local editable install for development workflow
- Updated linting and type-checking configuration for both packages

Next Steps

- Publish llama-stack-api to PyPI
- Update external provider dependencies
- Re-enable external provider module tests


Pre-cursor PRs to this one:

- #4093 
- #3954 
- #4064 

These PRs moved key pieces _out_ of the Api pkg, limiting the scope of
change here.


relates to #3237 

## Test Plan

Package builds successfully and can be imported independently. All
pre-commit hooks pass with expected exclusions maintained.

---------

Signed-off-by: Charlie Doern <cdoern@redhat.com>
This commit is contained in:
Charlie Doern 2025-11-13 14:51:17 -05:00 • committed by GitHub
parent ceb716b9a0
commit 840ad75fe9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
358 changed files with 2337 additions and 1424 deletions
Download patch file Download diff file Expand all files Collapse all files

153
src/llama_stack/apis/agents/agents.py
View file

@ -1,153 +0,0 @@
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from collections.abc import AsyncIterator
from typing import Annotated, Protocol, runtime_checkable
from pydantic import BaseModel
from llama_stack.apis.common.responses import Order
from llama_stack.apis.version import LLAMA_STACK_API_V1
from llama_stack.schema_utils import ExtraBodyField, json_schema_type, webmethod
from .openai_responses import (
ListOpenAIResponseInputItem,
ListOpenAIResponseObject,
OpenAIDeleteResponseObject,
OpenAIResponseInput,
OpenAIResponseInputTool,
OpenAIResponseObject,
OpenAIResponseObjectStream,
OpenAIResponsePrompt,
OpenAIResponseText,
)
@json_schema_type
class ResponseGuardrailSpec(BaseModel):
"""Specification for a guardrail to apply during response generation.
:param type: The type/identifier of the guardrail.
"""
type: str
# TODO: more fields to be added for guardrail configuration
ResponseGuardrail = str | ResponseGuardrailSpec
@runtime_checkable
class Agents(Protocol):
"""Agents
APIs for creating and interacting with agentic systems."""
# We situate the OpenAI Responses API in the Agents API just like we did things
# for Inference. The Responses API, in its intent, serves the same purpose as
# the Agents API above -- it is essentially a lightweight "agentic loop" with
# integrated tool calling.
#
# Both of these APIs are inherently stateful.
@webmethod(route="/responses/{response_id}", method="GET", level=LLAMA_STACK_API_V1)
async def get_openai_response(
self,
response_id: str,
) -> OpenAIResponseObject:
"""Get a model response.
:param response_id: The ID of the OpenAI response to retrieve.
:returns: An OpenAIResponseObject.
"""
...
@webmethod(route="/responses", method="POST", level=LLAMA_STACK_API_V1)
async def create_openai_response(
self,
input: str | list[OpenAIResponseInput],
model: str,
prompt: OpenAIResponsePrompt | None = None,
instructions: str | None = None,
previous_response_id: str | None = None,
conversation: str | None = None,
store: bool | None = True,
stream: bool | None = False,
temperature: float | None = None,
text: OpenAIResponseText | None = None,
tools: list[OpenAIResponseInputTool] | None = None,
include: list[str] | None = None,
max_infer_iters: int | None = 10, # this is an extension to the OpenAI API
guardrails: Annotated[
list[ResponseGuardrail] | None,
ExtraBodyField(
"List of guardrails to apply during response generation. Guardrails provide safety and content moderation."
),
] = None,
max_tool_calls: int | None = None,
) -> OpenAIResponseObject | AsyncIterator[OpenAIResponseObjectStream]:
"""Create a model response.
:param input: Input message(s) to create the response.
:param model: The underlying LLM used for completions.
:param prompt: (Optional) Prompt object with ID, version, and variables.
:param previous_response_id: (Optional) if specified, the new response will be a continuation of the previous response. This can be used to easily fork-off new responses from existing responses.
:param conversation: (Optional) The ID of a conversation to add the response to. Must begin with 'conv_'. Input and output messages will be automatically added to the conversation.
:param include: (Optional) Additional fields to include in the response.
:param guardrails: (Optional) List of guardrails to apply during response generation. Can be guardrail IDs (strings) or guardrail specifications.
:param max_tool_calls: (Optional) Max number of total calls to built-in tools that can be processed in a response.
:returns: An OpenAIResponseObject.
"""
...
@webmethod(route="/responses", method="GET", level=LLAMA_STACK_API_V1)
async def list_openai_responses(
self,
after: str | None = None,
limit: int | None = 50,
model: str | None = None,
order: Order | None = Order.desc,
) -> ListOpenAIResponseObject:
"""List all responses.
:param after: The ID of the last response to return.
:param limit: The number of responses to return.
:param model: The model to filter responses by.
:param order: The order to sort responses by when sorted by created_at ('asc' or 'desc').
:returns: A ListOpenAIResponseObject.
"""
...
@webmethod(route="/responses/{response_id}/input_items", method="GET", level=LLAMA_STACK_API_V1)
async def list_openai_response_input_items(
self,
response_id: str,
after: str | None = None,
before: str | None = None,
include: list[str] | None = None,
limit: int | None = 20,
order: Order | None = Order.desc,
) -> ListOpenAIResponseInputItem:
"""List input items.
:param response_id: The ID of the response to retrieve input items for.
:param after: An item ID to list items after, used for pagination.
:param before: An item ID to list items before, used for pagination.
:param include: Additional fields to include in the response.
:param limit: A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
:param order: The order to return the input items in. Default is desc.
:returns: An ListOpenAIResponseInputItem.
"""
...
@webmethod(route="/responses/{response_id}", method="DELETE", level=LLAMA_STACK_API_V1)
async def delete_openai_response(self, response_id: str) -> OpenAIDeleteResponseObject:
"""Delete a response.
:param response_id: The ID of the OpenAI response to delete.
:returns: An OpenAIDeleteResponseObject
"""
...