guanlan

观澜知识库（Karpathy LLM Wiki 模式）的维护引擎。当用户要把资料"摄入"知识库、 对知识库提问、或维护一个结构化互链的 markdown wiki（摘要页/实体页/概念页/综述）时使用。 Trigger on: "ingest", "摄入", "投喂资料", "query wiki", "查知识库", "更新 wiki", "维护知识库", "guanlan", "观澜", or 通过 `guanlan init/ingest/query` 命令进入的工作流。 此外：在以观澜库为 cwd 的会话里收到关于本库领域的任何实质问题时一律激活（即便用户没明说"查知识库/query"）——按 query 工作流先检索 wiki 再作答。

Convert documents (PDF, DOCX, PPTX, XLSX, EPUB, HTML, images) to Markdown using a tiered backend strategy: MinerU first, then marker-pdf, then a pure-python pypdf fallback. Trigger on: "convert PDF to markdown", "PDF to markdown", "DOCX/Word to markdown", "PPTX to markdown", "XLSX/Excel to markdown", "convert document to markdown", "transform to text", "mineru", "marker-pdf", "extract markdown from PDF", or any mention of a .pdf/.docx/.pptx/.xlsx/.epub/.html/image file when markdown output is the desired result.