精选理由
Box Agent用Deep Agents中间件来并行生成引用和缓存提示，还能管理170k token的上下文，挺实用的，值得看看他们的实现方式。
Box Agent通过Deep Agents中间件实现三个关键优化。第一，答案流式与引用生成并行执行，避免用户等待时中断。第二，在多轮对话中注入提示缓存，降低成本和延迟。第三，当上下文超过170k tokens时自动总结历史对话，防止上下文溢出。这些功能提升了Box Agent的响应速度和稳定性。
原文 · LangChain
How @Box uses Deep Agents middleware for Box Agent: 1️⃣Citation generation: Streaming of the answer...
How @Box uses Deep Agents middleware for Box Agent: 1️⃣Citation generation: Streaming of the answer + citation generation happens in parallel to avoid user interruption 2️⃣Prompt caching: Injects caching on multi-turn conversations, reducing cost + latency 3️⃣Context management: Summarizes conversation history after exceeding 170k tokens, preventing context overflow langchain.com/blog/building-… 💬 2 🔄 1 ❤️ 3 👀 1500 📊 2 ⚡