34 lines
1.0 KiB
Markdown
34 lines
1.0 KiB
Markdown
|
# 问数 / 解读拆分 Implementation Plan
|
||
|
|
|
||
|
|
> **For agentic workers:** REQUIRED SUB-SKILL: TDD per task.
|
||
|
|
|
||
|
|
**Goal:** 问数默认只返回表；各角色问数页按钮触发 `/api/analyst/interpret`，上下文仅最近一次问数。
|
||
|
|
|
||
|
|
**Architecture:** `AnalystAgent.run(interpret=False)` 跳过 `_generate_verified_answer`；新方法 `interpret()` 复用护栏；FastAPI 两路由；前端双请求。
|
||
|
|
|
||
|
|
**Tech Stack:** FastAPI · Pydantic · React · Ant Design
|
||
|
|
|
||
|
|
## Global Constraints
|
||
|
|
|
||
|
|
- 问数鉴权不变；客户 self 域尾注仍在解读成功路径追加。
|
||
|
|
- 不 commit 除非用户要求。
|
||
|
|
|
||
|
|
---
|
||
|
|
|
||
|
|
### Task 1: Schema + agent.run flag
|
||
|
|
|
||
|
|
- [ ] `ChatRequest.interpret: bool = False`
|
||
|
|
- [ ] `InterpretRequest` model
|
||
|
|
- [ ] `run(..., interpret=False)` 分支 + 测试
|
||
|
|
|
||
|
|
### Task 2: agent.interpret + route
|
||
|
|
|
||
|
|
- [ ] `interpret()` 方法 + `POST /api/analyst/interpret`
|
||
|
|
- [ ] 测试 deny echo + success
|
||
|
|
|
||
|
|
### Task 3: Frontend + memory
|
||
|
|
|
||
|
|
- [ ] `analyst.ts` + `AnalystQueryPage` 按钮与解读区
|
||
|
|
- [ ] MEMORY / TODO / REQUIREMENTS 更新
|
||
|
|
- [ ] `pytest` + `npm run test`
|