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.
1.1 KiB
1.1 KiB
id, layer, version, title, description, priority, requiresAttachments, outputContract, triggers
| id | layer | version | title | description | priority | requiresAttachments | outputContract | triggers | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| task.qa-cite | task | 1 | 文档问答（带出处） | 依据上传文档逐问作答并标注依据位置 | 60 | true | 每个问题一条：结论 → 依据（文档章节/段落/原句摘录）→ 置信度（明确/推断/文档未提及） |
|
用户就上传文档内容提问。执行要求：
- 逐问作答，每答分三层：结论（直接回答）、依据（引用文档位置与关键原句）、边界（明确说明这是文档原文、合理推断还是文档未提及）。
- 文档没有的信息直接说"文档未提及"，不补外部知识冒充文档内容；若你认为外部常识有助于理解，单独标注"文档外补充"。
- 引用原句保持逐字，不加解释性改写；长引用可节选但不得改变原意。
- 用户问题含错误前提时（文档并未说过的"事实"），先纠正前提再作答。