v2.1.294

anthropics (GitHub)，Anthropic GitHub 主页，Claude 背后的 AI 研究公司的开源仓库，包含 SDK、模型工具与研究代码。关注

What's changed

  • Fixed prompt and agent hooks written as instructions (such as "Block commands that...") allowing what they should block
  • Improved how prompt hooks on Stop and SubagentStop written as instructions (such as "Carry on if the build is broken") are judged, so Claude is less likely to stop early
添加评论
点赞收藏
点踩分享查看原文
评论
?
参与讨论