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

refactor: remove dead inference API code and clean up imports

Browse source 
Delete ~1,300 lines of dead code from the old bespoke inference API that was replaced by OpenAI-only API. This includes removing unused type conversion
functions, dead provider methods, and event_logger.py. Clean up imports across the codebase to remove references to deleted types. This eliminates unnecessary
code and dependencies, helping isolate the API package as a self-contained module.
This is the last interdependency between the .api package and "exterior" packages, meaning that now every other package in llama stack imports the API, not the other way around.

The API is now self contained and can be moved into its own package.

Signed-off-by: Charlie Doern <cdoern@redhat.com>
This commit is contained in:
Charlie Doern 2025-11-06 12:45:53 -05:00
parent 8f4c431370
commit 54754cb2a7
18 changed files with 34 additions and 2141 deletions
Download patch file Download diff file Expand all files Collapse all files

27
tests/unit/providers/nvidia/test_safety.py
View file

@ -10,11 +10,13 @@ from unittest.mock import AsyncMock, MagicMock, patch
import pytest
from llama_stack.apis.inference import CompletionMessage, UserMessage
from llama_stack.apis.inference import (
OpenAIAssistantMessageParam,
OpenAIUserMessageParam,
)
from llama_stack.apis.resource import ResourceType
from llama_stack.apis.safety import RunShieldResponse, ViolationLevel
from llama_stack.apis.shields import Shield
from llama_stack.models.llama.datatypes import StopReason
from llama_stack.providers.remote.safety.nvidia.config import NVIDIASafetyConfig
from llama_stack.providers.remote.safety.nvidia.nvidia import NVIDIASafetyAdapter
@ -136,11 +138,9 @@ async def test_run_shield_allowed(nvidia_adapter, mock_guardrails_post):
# Run the shield
messages = [
UserMessage(role="user", content="Hello, how are you?"),
CompletionMessage(
role="assistant",
OpenAIUserMessageParam(content="Hello, how are you?"),
OpenAIAssistantMessageParam(
content="I'm doing well, thank you for asking!",
stop_reason=StopReason.end_of_message,
tool_calls=[],
),
]
@ -191,13 +191,10 @@ async def test_run_shield_blocked(nvidia_adapter, mock_guardrails_post):
# Mock Guardrails API response
mock_guardrails_post.return_value = {"status": "blocked", "rails_status": {"reason": "harmful_content"}}
# Run the shield
messages = [
UserMessage(role="user", content="Hello, how are you?"),
CompletionMessage(
role="assistant",
OpenAIUserMessageParam(content="Hello, how are you?"),
OpenAIAssistantMessageParam(
content="I'm doing well, thank you for asking!",
stop_reason=StopReason.end_of_message,
tool_calls=[],
),
]
@ -243,7 +240,7 @@ async def test_run_shield_not_found(nvidia_adapter, mock_guardrails_post):
adapter.shield_store.get_shield.return_value = None
messages = [
UserMessage(role="user", content="Hello, how are you?"),
OpenAIUserMessageParam(content="Hello, how are you?"),
]
with pytest.raises(ValueError):
@ -274,11 +271,9 @@ async def test_run_shield_http_error(nvidia_adapter, mock_guardrails_post):
# Running the shield should raise an exception
messages = [
UserMessage(role="user", content="Hello, how are you?"),
CompletionMessage(
role="assistant",
OpenAIUserMessageParam(content="Hello, how are you?"),
OpenAIAssistantMessageParam(
content="I'm doing well, thank you for asking!",
stop_reason=StopReason.end_of_message,
tool_calls=[],
),
]