Repository navigation

Feat/content safety decision - #1196

Open

wujiaming-ai wants to merge 11 commits into

mainfrom

feat/content-safety-decision

Open

Feat/content safety decision#1196
wujiaming-ai wants to merge 11 commits into
mainfrom
feat/content-safety-decision

Commits on Nov 3, 2026
- feat(content-safety): add opt-in decision API auditing
  
  wujiaming-ai
  and
  claude
  committed
  3b60647
- test(content-safety): add opt-in live System One integration test
  
  wujiaming-ai
  and
  claude
  committed
  dbce16e
- test(content-safety): avoid duplicate pytest test basenames
  
  wujiaming-ai
  and
  claude
  committed
  4c0897a
- refactor(content-safety): rename decision plugin and drop skill adapter
  
  wujiaming-ai
  and
  claude
  committed
  adf3388
- fix(content-safety): reject unsafe non-Ark decision fallback
  
  wujiaming-ai
  and
  claude
  committed
  f67d658
- fix(content-safety): ignore hidden thought parts in model audits
  
  wujiaming-ai
  and
  claude
  committed
  7a1e144
- fix(content-safety): apply llm_shield app id before legacy import
  
  wujiaming-ai
  and
  claude
  committed
  e9d4785
- refactor(decision): extract reusable Decision API client
  
  wujiaming-ai
  and
  claude
  committed
  412b811
- fix(content-safety): harden decision and llm shield paths
  
  wujiaming-ai
  and
  claude
  committed
  c31e986
- feat(content-safety): auto-mount from config.yaml
  
  wujiaming-ai
  and
  claude
  committed
  4dbf6cf
- feat(content-safety): enable built-in risk questions by default
  
  wujiaming-ai
  and
  claude
  committed
  59dfc5c