个人知识与叙事工具

构建一个名为 "Thread" 的个人知识与叙事工具——一个将笔记连接成鲜活故事的第二大脑。

核心功能：

• 笔记捕获：快速输入，包含标题、正文、标签、日期，以及一个可选的"人生章节"标签（用户自定义的时期，如"创办公司"或"柏林之年"）——章节标签创建叙事结构
• 连接引擎：[LLM API] 定期分析所有笔记，并建议条目之间的主题连接。用户会看到一个"建议连接"面板——接受或拒绝每一条。被接受的连接会创建双向链接
• 叙事时间线：一个 D3.js 时间线，按章节分组显示笔记。缩小到十年视图，放大到周视图。点击任意笔记，即可在周围条目的语境中阅读它
• 每周综述：每周日，AI 根据当周笔记生成一段"一周回顾"文字——作为时间线中的特殊条目存储。逐渐累积成一部可阅读的人生编年史
• 模式报告：每月一次——AI 识别反复出现的主题（被提及 5 次以上的概念）、连接最多的想法（高连接密度），以及"休眠"想法（60 天以上未被引用，以"值得重温"的形式呈现）
• 章节导出：按日期范围选择任意章节，并导出为格式化的 PDF 叙事文档

技术栈：React、[LLM API] 用于连接建议、综述和模式报告，D3.js 用于时间线可视化，localStorage 配合 JSON 导出/导入用于备份。文学化设计——衬线字体，充裕的留白。

Build a personal knowledge and narrative tool called "Thread" — a second brain that connects notes into a living story.

Core features:

• Note capture: fast input with title, body, tags, date, and an optional "life chapter" label (user-defined periods like "Building the company" or "Year in Berlin") — chapter labels create narrative structure
• Connection engine: [LLM API] periodically analyzes all notes and suggests thematic connections between entries. User sees a "Suggested connections" panel — accepts or rejects each. Accepted connections create bidirectional links
• Narrative timeline: a D3.js timeline showing notes grouped by chapter. Zoom out to decade view, zoom in to week view. Click any note to read it in context of its surrounding entries
• Weekly synthesis: every Sunday, AI generates a "week in review" paragraph from that week's notes — stored as a special entry in the timeline. Accumulates into a readable life chronicle
• Pattern report: monthly — AI identifies recurring themes (concepts mentioned 5+ times), most-linked ideas (high connection density), and "dormant" ideas (not referenced in 60+ days, surfaced as "worth revisiting")
• Chapter export: select any chapter by date range and export as a formatted PDF narrative document

Stack: React, [LLM API] for connection suggestions, synthesis, and pattern reports, D3.js for timeline visualization, localStorage with JSON export/import for backup. Literary design — serif fonts, generous whitespace.