Merge PR #89: [moz] docs(§19): cron delivery mode 修正 none→announce
Deploy / ci (push) Successful in 9s
Deploy / deploy (push) Successful in 13s
Deploy / notify-deploy-failure (push) Successful in 1s
Deploy / notify-deploy-success (push) Successful in 1s

This commit was merged in pull request #89.
This commit is contained in:
2026-06-19 05:07:40 +00:00
@@ -503,13 +503,13 @@ S1 和 S2 已完成(PR #85)。S3-S5 设计见下方 §11A。
"message": "L1 自蒸馏 cron。请执行:\n1. read ~/.sanguo_projects/sanguo_mozi/skills/skill-management/SKILL.md\n2. read ~/.sanguo_projects/sanguo_mozi/skills/skill-management/references/discover-l1.md\n3. 按 discover-l1.md 步骤执行自蒸馏\n4. 如有信号:蒸馏为 HOW 格式,使用 skill_workshop(action=create) 提交 draft proposal\n5. 如无有价值信号:不产出,这是正常的",
"timeoutSeconds": 600
},
"delivery": { "mode": "none" }
"delivery": { "mode": "announce" }
}
```
**设计要点**:
- `sessionTarget: "isolated"`:每次创建临时 session,不污染 main session context
- `delivery.mode: "none"`:L1 不需要通知任何人,proposal 存在 skill_workshop 中即可
- `delivery.mode: "announce"`:执行结果投递到 Control UI,保持可见性(早期使用 `none` 导致 cron 执行后零可见性,已修正)
- `timeoutSeconds: 600`:10 分钟足够(扫描 JSONL + 蒸馏 + 提交 proposal
- message 指引 read SKILL.md + discover-l1.mdagent 按 references 指南执行,不依赖 memory
@@ -533,11 +533,12 @@ S1 和 S2 已完成(PR #85)。S3-S5 设计见下方 §11A。
"message": "L2 整合审查 cron。请执行:\n1. read ~/.sanguo_projects/sanguo_mozi/skills/skill-management/references/discover-l2.md\n2. 按 discover-l2.md 步骤执行:\n a. skill_workshop(action=list, status=pending) 获取所有 L1 draft proposals\n b. 全量数据源扫描,识别跨 agent 共性模式\n c. 逐个审查 proposalapprove / merge / reject\n d. 全局提升检查(Recurrence-Count >= 3 的经验提升为规则)\n e. 知识缺口反馈到 knowledge-gaps.md",
"timeoutSeconds": 1200
},
"delivery": { "mode": "none" }
"delivery": { "mode": "announce" }
}
```
**设计要点**:
- `delivery.mode: "announce"`:审查决策结果投递到 Control UI,主公可见
- `timeoutSeconds: 1200`(20 分钟):L2 需要扫描全量数据源 + 审查多个 proposal,时间更长
- 庞统可以访问所有 agent 的 JSONL 和 skill_workshop proposals
@@ -561,11 +562,12 @@ S1 和 S2 已完成(PR #85)。S3-S5 设计见下方 §11A。
"message": "IMPROVE 每周引用追踪 cron。请执行:\n1. read ~/.sanguo_projects/sanguo_mozi/skills/skill-management/references/improve.md\n2. 按 improve.md 步骤执行:\n a. 扫描过去 7 天所有 agent 的 session JSONL,采集 Skill 引用信号\n b. 生成淘汰候选报告(30 天无引用的 Skill)\n c. 庞统审阅决策:quarantine / 保留观察 / 更新后保留\n d. 经验提升检查(被频繁引用 >= 5 次的 Skill\n e. 反馈知识缺口到 knowledge-gaps.md",
"timeoutSeconds": 1800
},
"delivery": { "mode": "none" }
"delivery": { "mode": "announce" }
}
```
**设计要点**:
- `delivery.mode: "announce"`:淘汰/提升报告投递到 Control UI
- `timeoutSeconds: 1800`(30 分钟):全量 JSONL 扫描是最重的操作
- 每周一次频率足够——Skill 引用变化不会很快
- 淘汰决策通过 skill_workshop quarantine 执行,提升决策通过手动编辑 AGENTS.md