fix: 强化 public digest 生成格式约束
- 生成前强制读取 references/public-digest-example.md - summary 必须是完整句子而非关键词罗列 - 正文标题后不加来源标注(来源仅在延伸阅读出现) - 调整每篇顺序:摘要 → 值得关注 → 更值得关注的原因 - 更新 HARD PRE-WRITE CHECKLIST 对应条款
This commit is contained in:
@@ -78,16 +78,18 @@ If the main pipeline job fails:
|
|||||||
Read the real run outputs and generate digest markdown for the day.
|
Read the real run outputs and generate digest markdown for the day.
|
||||||
If there is no real payload, stop instead of writing a fake or example digest.
|
If there is no real payload, stop instead of writing a fake or example digest.
|
||||||
|
|
||||||
|
**⚠️ 格式基准 — 开始生成任何 digest 内容之前,必须先完整阅读 `references/public-digest-example.md` 并以此为格式基准,不得凭记忆或直觉写作。**
|
||||||
|
|
||||||
**⚠️ HARD PRE-WRITE CHECKLIST — 对照 `references/public-digest-example.md` 逐项确认后再开始写:**
|
**⚠️ HARD PRE-WRITE CHECKLIST — 对照 `references/public-digest-example.md` 逐项确认后再开始写:**
|
||||||
|
|
||||||
1. [ ] frontmatter `summary` 字段已填写(一句话概括今日核心主题)
|
1. [ ] frontmatter `summary` 字段已填写(**完整句子**,不是关键词罗列,参考格式:"围绕 XXX 的当日深度观察。")
|
||||||
2. [ ] 编号只用 `1.` `2.` `3.`,不用中文数字或罗马数字
|
2. [ ] 编号只用 `1.` `2.` `3.`,不用中文数字或罗马数字
|
||||||
3. [ ] 四个 section 全部存在:`今日概览` `今日重点` `趋势观察` `延伸阅读`
|
3. [ ] 四个 section 全部存在:`今日概览` `今日重点` `趋势观察` `延伸阅读`
|
||||||
4. [ ] 每篇 `今日重点` 下有:
|
4. [ ] 每篇 `今日重点` 下有:
|
||||||
- [ ] 标题 + 来源
|
- [ ] 标题(无"来源:"字样,来源仅在延伸阅读标注)
|
||||||
- [ ] 摘要段落
|
- [ ] 摘要段落
|
||||||
- [ ] "更值得关注的原因在于:"段落
|
|
||||||
- [ ] "值得关注:"要点列表(每篇 3 条)
|
- [ ] "值得关注:"要点列表(每篇 3 条)
|
||||||
|
- [ ] "这篇更值得关注的原因在于:"段落
|
||||||
5. [ ] `延伸阅读` 每条含来源标注:`- [标题](url)|来源`
|
5. [ ] `延伸阅读` 每条含来源标注:`- [标题](url)|来源`
|
||||||
|
|
||||||
For **public digest**, prefer `candidates/digest-brief.json` when present; fall back to `candidates/openclaw-delivery-payload.json` only if the brief file is missing.
|
For **public digest**, prefer `candidates/digest-brief.json` when present; fall back to `candidates/openclaw-delivery-payload.json` only if the brief file is missing.
|
||||||
|
|||||||
Reference in New Issue
Block a user