知识库

Eye(FR) → Mill(skill) → Library(/app)

← 返回列表
Hacker News · 2026-05-14 · 已成文 · 来源 file

Show HN: Parse LLM Markdown streams incrementally on the server or client:与 Agent/MCP/harness/Claude 工程化相关,值得纳入处理集沉淀。

为什么重要

来自 FR star 处理集的 Mode B 补写:把历史收藏连回 Vault 知识文,避免只 mark_read 导致的断档。

正文

Show HN: Parse LLM Markdown streams incrementally on the server or client:与 Agent/MCP/harness/Claude 工程化相关,值得纳入处理集沉淀。

Claim

Show HN: Parse LLM Markdown streams incrementally on the server or client:与 Agent/MCP/harness/Claude 工程化相关,值得纳入处理集沉淀。

Why it matters

来自 FR star 处理集的 Mode B 补写:把历史收藏连回 Vault 知识文,避免只 mark_read 导致的断档。

Summary

Mode B 收藏补写条目。主源为 FR favorite + Vault 快照。 正文以标题/URL/既有 content 线索整理为背景/机制/取舍/动作;未做全文二次抓取时已在 caveats 标明。

Actions

  • (none)

Evidence

  • (none)

Caveats

  • (none)

Research queries

  • (none)

Body

正文

背景

该条目已在 FreshRSS star(处理集),但此前清未读流水线未对其做 ka-v0 沉淀,形成 star 与知识文断档。

机制

Mode B:对 favorite 无 ka 队列写回同一 Vault item 的 manualnotes(围栏 YAML + Markdown 正文),source 提升为 aideeparticle,tags union ka-v0/deep-article,并 markread 对齐。

取舍

批量补写优先覆盖断档与可打开 ITEM_URL,而非每条全量杂志深研;浅信号走 shallow,噪声 discard。

动作

打开 ITEM_URL 校验;P0 剩余队列继续同一脚本;可选 1:N 合并同主题 star。

结合的源文章

主源
Show HN: Parse LLM Markdown streams incrementally on the server or client
打开原文 ↗

原文快照

展开 / 收起快照

Most AI chat applications (such as ChatGPT or Claude) stream their responses to the client as markdown text. As each new chunk of text arrives, the front end typically re-parses the entire markdown document to render the updated message. This works, but it can quickly slow down the UI for long responses.

I’ve been obsessing over ways to make this more efficient, so I wrote a markdown parser that can parse streaming markdown (semi) incrementally. Instead of re-processing the whole document each time, it only parses what’s new, processing each line only once. Block‑level nodes are buffered until they’re complete (for example, once a paragraph is done and won’t be extended by more text). This also makes parsing the markdown on server possible. The main demo does exactly that. Additionally, animating markdown blocks becomes much simpler and efficient, as a result.

Here’s a demo if you’d like to see it in action: https://markdownparser.vercel.app/experimental

Feel free to type 'Render a table with 10 rows' to see each table row animate in.

I’ve spent a lot of time thinking about this problem, so if you’re working on similar issues, I'd love to chat.


Comments URL: https://news.ycombinator.com/item?id=48142119

Points: 3

# Comments: 1