jev + Opus 5.5：把决策层和生成层拆开
作者称这套组合的关键不是小模型对大模型，而是判断哪些调用根本不需要生成：jev 负责路由下一个 worker、筛选上下文、拦截重复动作和风险工具调用，Opus 只做规划与写作。
jev + opus 5.5 is one of those setups that makes agent architecture feel weirdly overcomplicated in hindsight. the useful split isn’t “small model vs big model.” it’s deciding which calls actually need generation at all. → jev routes the next worker → scores which context is worth keeping → catches repeated actions before they burn the run → gates risky tool calls and sends uncertainty to review opus still owns the expensive part: planning, writing, coding, synthesis. jev sits around it as the decision layer. that matters because a typical loop can have 11 decision points but only 2 real generation calls. once those are separated, latency and cost stop scaling with every tiny fork in the workflow.
这条是引用着另一条写的：x.com/n01ennn/status/2103542021071978601