DeepSeek Open-Sources Super-agent Prototype: How Should Testers Respond?

DeepSeek's Harness team published a technical article titled "Super-agent Design Exploration: Toward a More Autonomous Agent System" and open-sourced a prototype plugin that lets AI autonomously discover issues in group chats, reproduce them in the background, and submit Pull Requests. The article introduces four capabilities: continuous cross-session interaction, multi-task parallelism, proactive event response, and long-term online presence. It adopts a two-layer Router + Worker architecture with a Watchdog supervision mechanism. DeepSeek's internal testing shows that in a simulated message stream of about 300 messages, Super-agent's p95 task completion time was 15.7 minutes, compared with 29.5 minutes for the traditional single-session approach, but cache-read Token volume rose from 23.23 million to 31.77 million.