Agent 工具
基于LangChain和Deep Agents的中间件，使用TypeSafe的System One模型（Jev）为无人值守编码agent提供类型化判断，包括shell命令门控、问题分流、合并请求检测和测试审查。
LangChain / Deep Agents middleware that uses TypeSafe's System One model (Jev) for typed judgments in unattended coding agents: a shell-command gate (database, production, destructive, secrets), issue triage and routing by severity and urgency, merge-request detection, and review of weakened tests. Measured with live probes.
from langchain_typesafe import Choice, Noul, NoulCriteriatypesafe_agent_gates/judgments.py:103
链接指向我们抓取当天的那个 commit，行号是准的。
它的 question 组合是运行时拼出来的，或者代码里没有直接写出来，所以没法原样搬过来。源码链接在上面，可以自己去看。