phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-05 02:17:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor: rename trace_protocol marker to mark_as_traced

Browse source 
Rename the marker decorator in apis/common/tracing.py from trace_protocol
to mark_as_traced to disambiguate it from the actual tracing implementation
decorator in core/telemetry/trace_protocol.py.

Changes:
- Rename decorator: trace_protocol -> mark_as_traced
- Rename attribute: __trace_protocol__ -> __marked_for_tracing__
- Update all API protocol files to use new decorator name
- Update router logic to check for new attribute name

This makes it clear that the marker decorator is metadata-only and doesn't
perform actual tracing, while the core decorator does the implementation.

Signed-off-by: Charlie Doern <cdoern@redhat.com>
This commit is contained in:
Charlie Doern 2025-11-05 16:21:48 -05:00
parent cd17c62ec4
commit 29f93a6391
11 changed files with 28 additions and 26 deletions
Download patch file Download diff file Expand all files Collapse all files

4
src/llama_stack/apis/inference/inference.py
View file

@ -20,7 +20,7 @@ from typing_extensions import TypedDict
from llama_stack.apis.common.content_types import ContentDelta, InterleavedContent
from llama_stack.apis.common.responses import MetricResponseMixin, Order
from llama_stack.apis.common.tracing import trace_protocol
from llama_stack.apis.common.tracing import mark_as_traced
from llama_stack.apis.models import Model
from llama_stack.apis.version import LLAMA_STACK_API_V1, LLAMA_STACK_API_V1ALPHA
from llama_stack.models.llama.datatypes import (
@ -1159,7 +1159,7 @@ class OpenAIEmbeddingsRequestWithExtraBody(BaseModel, extra="allow"):
@runtime_checkable
@trace_protocol
@mark_as_traced
class InferenceProvider(Protocol):
"""
This protocol defines the interface that should be implemented by all inference providers.