Initial commit: hardened DeerFlow factory

Vendored deer-flow upstream (bytedance/deer-flow) plus prompt-injection
hardening:

- New deerflow.security package: content_delimiter, html_cleaner,
  sanitizer (8 layers — invisible chars, control chars, symbols, NFC,
  PUA, tag chars, horizontal whitespace collapse with newline/tab
  preservation, length cap)
- New deerflow.community.searx package: web_search, web_fetch,
  image_search backed by a private SearX instance, every external
  string sanitized and wrapped in <<<EXTERNAL_UNTRUSTED_CONTENT>>>
  delimiters
- All native community web providers (ddg_search, tavily, exa,
  firecrawl, jina_ai, infoquest, image_search) replaced with hard-fail
  stubs that raise NativeWebToolDisabledError at import time, so a
  misconfigured tool.use path fails loud rather than silently falling
  back to unsanitized output
- Native client back-doors (jina_client.py, infoquest_client.py)
  stubbed too
- Native-tool tests quarantined under tests/_disabled_native/
  (collect_ignore_glob via local conftest.py)
- Sanitizer Layer 7 fix: only collapse horizontal whitespace, preserve
  newlines and tabs so list/table structure survives
- Hardened runtime config.yaml references only the searx-backed tools
- Factory overlay (backend/) kept in sync with deer-flow tree as a
  reference / source

See HARDENING.md for the full audit trail and verification steps.
This commit is contained in:
2026-04-12 14:23:57 +02:00
commit 6de0bf9f5b
889 changed files with 173052 additions and 0 deletions

View File

@@ -0,0 +1,24 @@
# generate_spreadsheet — 电子表格/数据透视表
## 功能概述
生成电子表格或数据透视表,用于展示结构化的表格数据。当提供 `rows``values` 字段时,渲染为数据透视表(交叉表);否则渲染为常规表格。适合展示结构化数据、跨类别比较值以及创建数据汇总。
## 输入字段
### 必填
- `data`: array<object>表格数据数组每个对象代表一行。键是列名值可以是字符串、数字、null 或 undefined。例如`[{ name: 'John', age: 30 }, { name: 'Jane', age: 25 }]`
### 可选
- `rows`: array<string>,数据透视表的行标题字段。当提供 `rows``values` 时,电子表格将渲染为数据透视表。
- `columns`: array<string>,列标题字段,用于指定列的顺序。对于常规表格,这决定列的顺序;对于数据透视表,用于列分组。
- `values`: array<string>,数据透视表的值字段。当提供 `rows``values` 时,电子表格将渲染为数据透视表。
- `theme`: string默认 `default`,可选 `default`/`dark`
- `width`: number默认 `600`
- `height`: number默认 `400`
## 使用建议
- 对于常规表格,只需提供 `data` 和可选的 `columns` 来控制列的顺序。
- 对于数据透视表(交叉表),提供 `rows` 用于行分组,`columns` 用于列分组,`values` 用于聚合的值字段。
- 确保数据中的字段名与 `rows``columns``values` 中指定的字段名一致。
## 返回结果
- 返回电子表格/数据透视表图片 URL并附 `_meta.spec` 供后续编辑。