docs: fix architecture boundaries - routing=unique input, LLM=unique output, memory=autonomous

Key corrections:
- Routing subnet is the ONLY external input path; all images/text/voice must pass through it
- LLM subnet is the ONLY external output path; natural language goes directly to user
- Core is a purely internal layer, not directly exposed to users
- Memory subnet is autonomous: Core only passes query tensors + new information tensors;
  how to update/delete/modify is entirely decided by memory subnet
- Routing subnet uses sliding window mechanism: instant label tensor generation → Core,
  then after the round ends, Core schedules routing to process remaining raw data
- Updated all ASCII diagrams, Mermaid diagrams, pseudo-code, and data flow charts
- Added border rules table to all relevant docs

docs/llm-subnet.md

@@ -2,7 +2,9 @@
 
 ## 概述
 
-LLM 子网类比人脑的**布洛卡区（表达核）**，是 NextAgent 架构中**唯一直接与用户交互**的组件。在认知解耦架构下，LLM 不再是"全知怪物"，而是降级为专业的**语言生成引擎**：知识来源外置到记忆子网，逻辑推理外置到推理子网，LLM 仅负责将结构化的推理结果转换为自然语言。
+LLM 子网类比人脑的**布洛卡区（表达核）**，是 NextAgent 架构中**唯一的输出路径**（当前仅输出自然语言；可扩展图像、视频等输出子网）。
+
+在认知解耦架构下，LLM 不再是"全知怪物"，而是降级为专业的**语言生成引擎**：知识来源外置到记忆子网，逻辑推理外置到推理子网，LLM 仅负责将结构化的推理结果转换为自然语言。
 
 ### 核心设计：LLM 下位化