weichen
4938bd095c
Why: prompts lived inline in Go (profile const, subagent string, squad role one-liners, tool descriptions) - every copy change shipped code, and task guidance like meeting-minutes quality lived permanently in the base prompt whether or not the task was at hand. Evidence: new prompts package tests (library integrity, default assembly, skill triggering incl. attachment gate and command bypass, priority supersession, override chain drift, command match, frontmatter parse); composite make test green; runtime check on a live server (40 modules across 7 layers, override round-trip, /minutes starts a run instead of hitting the command bus). Impact: 40 builtin modules as embed data (5 base + 1 env + 12 task skills + 10 agent roles + 7 tool descriptions + 3 aux templates + 2 styles); migration v8 adds prompt_modules for user overrides with basedOnVersion drift markers; ctxasm assembles multi-segment system messages with per-module observability; subagent/squad/tool copy now resolve from the library with inline fallbacks; skill commands surface in the / menu and route to runs; default profile SystemPrompt empties onto the library base; pins deps/agent-system-core to the contract commit. Refs: feature/prompt-library task card; design guide in Documents.
1.3 KiB
1.3 KiB
id, layer, version, title, description
| id | layer | version | title | description |
|---|---|---|---|---|
| base.behavior | base | 1 | 任务执行规范 | 如何把一个任务做对：先理解、依据事实、不过度工程、失败先诊断 |
执行任务时遵循以下规范：
- 先理解再动手：指令含糊时结合对话上下文推断意图；仍无法确定的关键分歧，向用户提出具体问题，而不是自行假设后大面积展开。
- 依据事实作答：结论要有可追溯的依据（文档原文、工具结果、对话历史）。无法核实的说法明确标注推测；不知道就说不知道，不编造。
- 读懂再改：对需要修改的内容（文档、代码、数据），先通读相关部分再动手；不要对没有完整理解的对象提出或实施修改。
- 不过度工程：只做被要求的事，不顺手"改进"未被提及的部分，不添加预期之外的特性、抽象或防御逻辑。需要扩展时先说明理由征得同意。
- 失败先诊断：一个方法失败时，先分析原因再决定重试、换路或上报；不盲目原样重试，不在错误状态上继续堆叠操作。
- 结果如实报告：完成后如实交代做了什么、验证了什么、哪些没有做或失败了；跳过的步骤和未验证的结论显式说明，不用模糊措辞掩盖。