dsh-data-domain-knowledge 0.1.0-alpha.5 → 0.1.0-alpha.8

package/README.md

@@ -194,14 +194,15 @@ BERT 重排默认使用 `BAAI/bge-reranker-base`；如需完全离线，可把
 运行），底层是 `@firecrawl/anydoc`（MIT / Rust / 预编译绑定），支持 doc、docx、ppt、
 pptx、xls、xlsx、odt、ods、odp、rtf、epub、csv 与文本层 PDF；另有本地音视频/图片
 （`iddoc`）、扫描件轻量 OCR（`scanned`：`.pdf` 报 `needsOcr` 时**自动兜底**）与
-网页 / 微信公众号文章（`web`：`kind=url` 抓链接，`.html/.htm` 收另存下来的页面）。
+网页 / 微信公众号文章（`web`：收另存到本机的 `.html/.htm` 页面，从 `og:url` / `canonical`
+把原始地址找回来；内核不联网，`kind=url` 已从契约删除）。
 
 | 项 | 值 |
 | --- | --- |
 | 工具 | `convert_capabilities` / `convert_source` / `convert_task` / `convert_ingest`（后两个写操作需本轮审批） |
 | 路由 | `/convert/**`（含内核 Vue3 控制台） |
 | 设置命名空间 | `tita-data-agent-convert`（冻结契约，由本插件安装） |
-| 交付目录 | `~/.tita-data-agent/convert-out/<taskId>/`（`index.md` / `assets/` / `manifest.json`） |
+| 交付目录 | `<工作区>/output/<YYYY-MM-DD>/<中文名>/`（`index.md` / `assets/` / `manifest.json`）；叶子名取文档标题，同名让路 `-2` |
 
 **依赖是可选的。** `dsh-convert-core` 声明在 `optionalDependencies`，首次调用时才加载。
 平台没有 anydoc 预编译绑定、或用户显式不装时，

package/cordis.patch.yml

@@ -92,8 +92,9 @@
                   a `table` card says what one row means. Computing without the definition gets
                   you a number nobody agreed to.
 
-                - **Conversion.** `convert_source` turns a file, a web page or a video into
-                  knowledge-ready Markdown and says where it landed. It is not knowledge until
+                - **Conversion.** `convert_source` turns a local file (including a web page
+                  saved to disk as `.html`) or a video into knowledge-ready Markdown and says
+                  where it landed. It never fetches a URL itself. It is not knowledge until
                   `convert_ingest` has run, so keep saying which of the two steps you are on.
 
                 ## Working rules
@@ -147,10 +148,13 @@
                 9. **Deliverables belong to the project, not to your home.** Write every file
                    you produce for the user under `output/<YYYY-MM-DD>/` in your working
                    directory, never into the Agent root: the Agent root accumulates across
-                   projects, a deliverable belongs to one. Name it `<topic>-<kind>.<ext>` where
-                   `<kind>` is exactly one of `报告`, `图表`, `数据集`, `清洗脚本`, `SQL` — the
-                   name alone has to say what the file is a year later. Append `-2`, `-3` rather
-                   than overwriting, and say the path in your answer.
+                   projects, a deliverable belongs to one. Name the file `<中文名>.<ext>` — at
+                   most 25 characters, keeping 汉字, letters, digits, `-`, `_` and `.`, and
+                   turning spaces and punctuation into `-` (so `销售汇总` stays `销售汇总`, and
+                   you write `月度销售汇总.xlsx`, not `output1.xlsx`). **Do not repeat the date
+                   in the file name**: the directory already carries it, and the name alone has
+                   to say what the file is a year later. Append `-2`, `-3` rather than
+                   overwriting, and say the path in your answer.
 
                 ## How to write