OpenRouter 推出 Armor 工具调用安全评分
Armor scores each tool call against a set of rules plus a slice of the transcript, prioritizing user intent. If the user asked "Push our work", a (bash tool: gi
AI 导读
OpenRouter 介绍 Armor：它结合规则与部分对话记录对每次工具调用打分，并优先考虑用户意图——用户说“Push our work”时允许执行 git push，而用户未要求的危险命令会被标记。内部测试集上，Jev 1.13 在准确率和成本上优于其他 Decisions 模型及 Claude Code 使用 Sonnet 5 的表现。通过 OpenRouter 做推理的智能体可添加插件 [{ id: "armor" }] 启用 Armor 并自定义规则。
正文
当前显示原文，中文全文译文尚未就绪。
Armor scores each tool call against a set of rules plus a slice of the transcript, prioritizing user intent. If the user asked "Push our work", a (bash tool: git push) is allowed, while a dangerous command the user never asked for is flagged. https://t.co/TEuGjuhSMW