v1.6.44
AIPentest/CyberStrikeAIv1.6.44Jun 23, 2026by Ed1s0nZ
AI Summary
Optimized performance for long-running chat sessions by implementing a three-layer progressive loading system to reduce lag during switching and interaction.
Key Highlights
- Session switches now use a lightweight API (include_process_details=0) instead of prefetching heavy data.
- Full process details load on-demand only when the user clicks 'Expand details'.
- Tool calls render as header-only rows, with parameters and results loaded via click or batch rendering.
- Large timelines are drawn in batches using requestAnimationFrame to improve responsiveness.
New Features
- Progressive loading system for chat sessions and tool call details.
Full Release Notes
针对多轮迭代会话切换卡顿，本次优化采用三层渐进加载：切换会话时不再预拉取最后一条消息的渗透详情，仅使用轻量 API（include_process_details=0）；用户点击「展开详情」后才按需请求该条消息的 process-details；时间线内每个工具调用默认只显示标题行，点击后再渲染参数与执行结果，大批量条目通过 requestAnimationFrame 分批绘制。运行中任务仍走 task-events 补流，行为不受影响。 --- To fix lag when switching between long-running chat sessions, we implemented three layers of progressive loading: session switches no longer prefetch the last message’s penetration details and rely on the lightweight API (include_process_details=0); full process details load only when the user clicks “Expand details”; within the timeline, each tool call renders as a header-only row until clicked, with large timelines painted in batches via requestAnimationFrame. In-flight tasks are unchanged and still resume through the task-events replay stream.