mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 09:53:45 +00:00
9df073450f
Some checks failed
Integration Tests (Replay) / generate-matrix (push) Successful in 3s
Test External API and Providers / test-external (venv) (push) Failing after 4s
UI Tests / ui-tests (22) (push) Successful in 55s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 1s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Python Package Build Test / build (3.12) (push) Failing after 1s
Pre-commit / pre-commit (push) Failing after 2s
Python Package Build Test / build (3.13) (push) Failing after 1s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 5s
Vector IO Integration Tests / test-matrix (push) Failing after 5s
API Conformance Tests / check-schema-compatibility (push) Successful in 11s
Unit Tests / unit-tests (3.12) (push) Failing after 4s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 4s
Unit Tests / unit-tests (3.13) (push) Failing after 5s
# What does this PR do? Remove circular dependency by moving tracing from API protocol definitions to router implementation layer. This gets us closer to having a self contained API package with no other cross-cutting dependencies to other parts of the llama stack codebase. To the best of our ability, the llama_stack.api should only be type and protocol definitions. Changes: - Create apis/common/tracing.py with marker decorator (zero core dependencies) - Add the _new_ `@telemetry_traceable` marker decorator to 11 protocol classes - Apply actual tracing in core/resolver.py in `instantiate_provider` based on protocol marker - Move MetricResponseMixin from core to apis (it's an API response type) - APIs package is now self-contained with zero core dependencies The tracing functionality remains identical - actual trace_protocol from core is applied to router implementations at runtime when both telemetry is enabled and the protocol has the `__marked_for_tracing__` marker. ## Test Plan Manual integration test confirms identical behavior to main branch: ```bash llama stack list-deps --format uv starter | sh export OLLAMA_URL=http://localhost:11434 llama stack run starter curl -X POST http://localhost:8321/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{"model": "ollama/gpt-oss:20b", "messages": [{"role": "user", "content": "Say hello"}], "max_tokens": 10}' ``` Verified identical between main and this branch: - trace_id present in response - metrics array with prompt_tokens, completion_tokens, total_tokens - Server logs show trace_protocol applied to all routers Existing telemetry integration tests (tests/integration/telemetry/) validate trace context propagation and span attributes. relates to #3895 --------- Signed-off-by: Charlie Doern <cdoern@redhat.com>
94 lines
2.8 KiB
Python
94 lines
2.8 KiB
Python
# 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 typing import Any, Literal, Protocol, runtime_checkable
|
|
|
|
from pydantic import BaseModel
|
|
|
|
from llama_stack.apis.common.tracing import telemetry_traceable
|
|
from llama_stack.apis.resource import Resource, ResourceType
|
|
from llama_stack.apis.version import LLAMA_STACK_API_V1
|
|
from llama_stack.schema_utils import json_schema_type, webmethod
|
|
|
|
|
|
class CommonShieldFields(BaseModel):
|
|
params: dict[str, Any] | None = None
|
|
|
|
|
|
@json_schema_type
|
|
class Shield(CommonShieldFields, Resource):
|
|
"""A safety shield resource that can be used to check content.
|
|
|
|
:param params: (Optional) Configuration parameters for the shield
|
|
:param type: The resource type, always shield
|
|
"""
|
|
|
|
type: Literal[ResourceType.shield] = ResourceType.shield
|
|
|
|
@property
|
|
def shield_id(self) -> str:
|
|
return self.identifier
|
|
|
|
@property
|
|
def provider_shield_id(self) -> str | None:
|
|
return self.provider_resource_id
|
|
|
|
|
|
class ShieldInput(CommonShieldFields):
|
|
shield_id: str
|
|
provider_id: str | None = None
|
|
provider_shield_id: str | None = None
|
|
|
|
|
|
class ListShieldsResponse(BaseModel):
|
|
data: list[Shield]
|
|
|
|
|
|
@runtime_checkable
|
|
@telemetry_traceable
|
|
class Shields(Protocol):
|
|
@webmethod(route="/shields", method="GET", level=LLAMA_STACK_API_V1)
|
|
async def list_shields(self) -> ListShieldsResponse:
|
|
"""List all shields.
|
|
|
|
:returns: A ListShieldsResponse.
|
|
"""
|
|
...
|
|
|
|
@webmethod(route="/shields/{identifier:path}", method="GET", level=LLAMA_STACK_API_V1)
|
|
async def get_shield(self, identifier: str) -> Shield:
|
|
"""Get a shield by its identifier.
|
|
|
|
:param identifier: The identifier of the shield to get.
|
|
:returns: A Shield.
|
|
"""
|
|
...
|
|
|
|
@webmethod(route="/shields", method="POST", level=LLAMA_STACK_API_V1)
|
|
async def register_shield(
|
|
self,
|
|
shield_id: str,
|
|
provider_shield_id: str | None = None,
|
|
provider_id: str | None = None,
|
|
params: dict[str, Any] | None = None,
|
|
) -> Shield:
|
|
"""Register a shield.
|
|
|
|
:param shield_id: The identifier of the shield to register.
|
|
:param provider_shield_id: The identifier of the shield in the provider.
|
|
:param provider_id: The identifier of the provider.
|
|
:param params: The parameters of the shield.
|
|
:returns: A Shield.
|
|
"""
|
|
...
|
|
|
|
@webmethod(route="/shields/{identifier:path}", method="DELETE", level=LLAMA_STACK_API_V1)
|
|
async def unregister_shield(self, identifier: str) -> None:
|
|
"""Unregister a shield.
|
|
|
|
:param identifier: The identifier of the shield to unregister.
|
|
"""
|
|
...
|