phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-21 17:33:12 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: Code scanner Provider impl for moderations api (#3100)

Browse source 
# What does this PR do?
Add CodeScanner implementations

## Test Plan
`SAFETY_MODEL=CodeScanner LLAMA_STACK_CONFIG=starter uv run pytest -v
tests/integration/safety/test_safety.py
--text-model=llama3.2:3b-instruct-fp16
--embedding-model=all-MiniLM-L6-v2 --safety-shield=ollama`

This PR need to land after this
https://github.com/meta-llama/llama-stack/pull/3098
This commit is contained in:
slekkala1 2025-08-18 14:15:40 -07:00 • committed by GitHub
parent 27d6becfd0
commit 7519ab4024
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 144 additions and 24 deletions
Download patch file Download diff file Expand all files Collapse all files

9
llama_stack/providers/inline/safety/llama_guard/llama_guard.py
View file

@ -11,11 +11,7 @@ from string import Template
from typing import Any
from llama_stack.apis.common.content_types import ImageContentItem, TextContentItem
from llama_stack.apis.inference import (
Inference,
Message,
UserMessage,
)
from llama_stack.apis.inference import Inference, Message, UserMessage
from llama_stack.apis.safety import (
RunShieldResponse,
Safety,
@ -72,7 +68,6 @@ SAFETY_CATEGORIES_TO_CODE_MAP = {
}
SAFETY_CODE_TO_CATEGORIES_MAP = {v: k for k, v in SAFETY_CATEGORIES_TO_CODE_MAP.items()}
DEFAULT_LG_V3_SAFETY_CATEGORIES = [
CAT_VIOLENT_CRIMES,
CAT_NON_VIOLENT_CRIMES,
@ -460,7 +455,7 @@ class LlamaGuardShield:
def is_content_safe(self, response: str, unsafe_code: str | None = None) -> bool:
"""Check if content is safe based on response and unsafe code."""
if response.strip() == SAFE_RESPONSE:
if response.strip().lower().startswith(SAFE_RESPONSE):
return True
if unsafe_code: