- CHANGELOG.md:v2.8.0 条目(中英双语); - README.md:版本行 2.7.1→2.8.0 + 愿景第 6 条(知识可证明); - doc/releases/v2.8.0.md:双语发版说明(亮点/用法/已知限制); - skills/marqdo-dev/index.mq.md:新增 prove 任务(路径/目录模式/ require_lean/json;参数用 + 行声明升参,check 与 narrative-ratio 通过); - 设计文档 §12.5 标记已合入;发版链接统一指向 doc/releases/v2.8.0.md。
862 B
Executable File
862 B
Executable File
markup, title, description, import
| markup | title | description | import | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| occlusion | ext/agent plan live (DeepSeek) | Full plan loop — spawn workbook, inspect; simple pong goal. |
|
main
goal=> input "你想完成什么任务?"
llm.load_env path=.env
**model = > llm.llm **
**tools = > json.parse text=[] **
**助手 = > agent.agent model=model tools=tools standing=You are a Marqdo agent-development master. Prefer DONE when the workbook already satisfies the goal. **
流式开在 plan 上:非命中先 plan:decompose(父分解增量),再 plan:await(子 quiet),然后父修订轮。
**out = > 助手.plan goal=goal max_rounds=3 writeback=False stream=True echo=True force=True **
**result = > json.get value=out key=result **
print text=
result