Sirui's blog

语言： English | 简体中文

发布日期：2026-11-09

FLH 原本只处理我输入的问题。听力功能加入了第二个来源：法语视频加上我自己提供的转写稿，生成考试式听力练习；之后每天从播放列表拉取，最多自动准备一课，并可选通过 Telegram 通知。它分两次改动、两天完成。

我的工程贡献：把源材料与生成的练习分开，要求每条引用逐字匹配，把自动花费限制在每天一次尝试，并把超时或丢失的调用视为”未知”而非”失败”。

Language: English | 简体中文

FLH started from questions I typed. The listening work adds a second source: French videos with my own transcripts, turned into exam-style listening exercises, then pulled from a playlist each day with at most one prepared lesson and an optional Telegram notice. It shipped as two changes, over two days.

My engineering contribution: separating source material from generated exercises, requiring every cited line to be verbatim, capping automatic spending at one attempt per day, and treating a timed-out or lost call as unknown rather than failed.

Published: 2026-11-09

语言： English | 简体中文

发布日期：2026-11-08

Knowledge Library 以前只能浏览。Concept 页面一次性显示标题、所有陈述、例句和来源链接，没法先尝试回答再核对。回忆练习补上了这一步：从一个 Concept 出发，只使用我自己最初提出的问题。

我的工程贡献：定义什么算”当前支持”，决定揭示内容是参考而不是评分，并要求练习不保存、不改变任何东西。

Language: English | 简体中文

The Knowledge Library could only be browsed. A Concept’s page shows its title, every statement, examples and source links at once, so there was no way to try a question first and check afterwards. Recall practice adds that, starting from a Concept, using only the questions I originally asked.

My engineering contribution: defining what counts as current support, deciding that the reveal is a reference rather than a grade, and requiring that practice stores nothing and changes nothing.

Published: 2026-11-08

语言： English | 简体中文

发布日期：2026-11-08

FLH 的 capture CLI 以前一次只导入一个 learning_capture_v1 文件。我加入了最多 100 个文件的批量模式，以及一个不发送任何请求的预览。设计的核心是一个问题：响应没有回来时，报告应该怎么写？

我的工程贡献：定义结果类别和退出码，选择”重跑”而非自动重试，并规定报告的隐私规则。

Language: English | 简体中文

FLH’s capture CLI imported one learning_capture_v1 file at a time. I added a batch mode for up to 100 files and a preview that sends nothing. Most of the design is about one question: when a response never arrives, what should the report say?

My engineering contribution: defining the outcome categories and exit statuses, choosing a rerun over automatic retry, and setting the privacy rule for reports.

Published: 2026-11-08

语言： English | 简体中文

发布日期：2026-11-08

FLH v1.0.0 是第一个我认为可以长期个人使用的版本：一个 Docker 镜像，包含 Go 服务、SQLite 和 React 工作台，只绑定 127.0.0.1。这次发布的主要工作不是新功能，而是让”从问题到 Concept”的日常流程清晰可循，再验证升级可以回退、打包后的应用能在真实浏览器里工作。

我的工程贡献：梳理发布缺口，规定任何发布检查都不能触碰日常实例，并决定哪些证据足以打 v1.0.0 标签。

Language: English | 简体中文

FLH v1.0.0 is the first release I treat as finished for personal use: one Docker image with a Go server, SQLite and the React workbench, bound to 127.0.0.1. Most of the release work was not new features. It was making the daily path from question to Concept easy to follow, then checking that an upgrade can be undone and that the packaged app works in a real browser.

My engineering contribution: defining the release gaps, setting the rule that a release check must never touch the daily instance, and deciding which evidence counted before tagging v1.0.0.

Published: 2026-11-08

语言： English | 简体中文

发布日期：2026-10-22

我为 FLH 加入 AI Concept 建议，降低知识单元整理的手工成本。模型从已有 Concept 中提出候选并说明理由，用户逐项确认后才改变 membership。生成证据、当前状态和人工权威分别管理。

我的工程贡献：定义有界输入与候选，把生成和确认设计为不同操作，并完善重放、取消及过期状态处理。

Language: English | 简体中文

I added AI-assisted Concept suggestions to FLH to reduce the manual effort of reviewing extracted knowledge. The model proposes existing Concepts and explains its choice; the user confirms each item before membership changes. The implementation keeps generated evidence, current state and human authority separate.

My engineering contribution: defining bounded inputs and candidates, designing generation and confirmation as different operations, and hardening their replay, cancellation and stale-state behavior.

发布日期：2026-10-22