docs: reorganize MVP interview documentation

mvp/demo/interview-walkthrough.md

@@ -1,146 +1,144 @@
-# Interview Walkthrough: MVP Diagnosis Agent
+# 面试演示讲解稿
 
-This walkthrough is the Plan C demo story. It is meant for a short Agent Engineer interview, not as exhaustive system documentation.
+这是一份短时间 Agent 工程面试用讲解稿，不是完整系统文档。
 
-## 30-Second Summary
+## 1. 30 秒摘要
 
 ```text
-This is an enterprise diagnosis Agent MVP.
-It takes a payment-timeout question, plans the investigation, calls evidence tools,
-checks the answer through a verifier, persists the full trace, and accepts feedback.
+这是一个企业故障诊断 Agent MVP。
+它接收支付超时问题，规划排查步骤，调用证据工具，
+用 Verifier 检查答案，把完整 Trace 持久化，并支持用户反馈。
 ```
 
-The important claim is not "the model answered once." The claim is:
+关键主张不是“模型回答了一次”，而是：
 
 ```text
-The system can show what evidence was used, how the answer was checked, and how to replay the session.
+系统能展示用了什么证据、答案如何被检查、如何用 sessionId 回放整次诊断。
 ```
 
-## Demo Flow
+## 2. Demo 流程
 
-1. Start the service with the `mvp-demo` profile.
-2. Run the fixed payment-timeout request.
-3. Open `mvp/demo/output/chat-response.json`.
-4. Open `mvp/demo/output/trace-response.json`.
-5. Point to evidence tools and verifier evaluation.
-6. Submit feedback and show it is attached to the same session.
+1. 用 `mvp-demo` profile 启动服务。
+2. 运行固定的支付超时请求。
+3. 打开 `mvp/demo/output/chat-response.json`。
+4. 打开 `mvp/demo/output/trace-response.json`。
+5. 指出证据工具和 verifier evaluation。
+6. 提交 feedback，并展示它挂在同一个 session 上。
 
-## Commands
+## 3. 命令
 
-Start service:
+启动服务：
 
 ```powershell
 mvn spring-boot:run "-Dspring-boot.run.profiles=mvp-demo"
 ```
 
-Run the demo from another terminal:
+另开终端运行 Demo：
 
 ```powershell
 powershell -ExecutionPolicy Bypass -File mvp/demo/scripts/run-payment-timeout-demo.ps1
 ```
 
-Optional custom session:
+可选自定义 session：
 
 ```powershell
 powershell -ExecutionPolicy Bypass -File mvp/demo/scripts/run-payment-timeout-demo.ps1 -SessionId "mvp-demo-payment-timeout-002"
 ```
 
-## What To Show
+## 4. 展示什么
 
-### 1. User-Facing Answer
+### 4.1 用户侧答案
 
-File:
+文件：
 
 ```text
 mvp/demo/output/chat-response.json
 ```
 
-Say:
+话术：
 
 ```text
-This is the answer the user sees. The session id is stable, so I can trace this exact answer later.
+这是用户看到的答案。这里的 sessionId 是稳定的，所以我后面可以追踪这一次回答是怎么来的。
 ```
 
-### 2. Evidence Trace
+### 4.2 证据 Trace
 
-File:
+文件：
 
 ```text
 mvp/demo/output/trace-response.json
 ```
 
-Say:
+话术：
 
 ```text
-This is the important Agent engineering part.
-I can inspect which tools were called, what inputs they received,
-whether they succeeded, and what evidence preview was persisted.
+这才是 Agent 工程最重要的部分。
+我可以检查 Agent 调用了哪些工具、每个工具拿到什么入参、是否成功、返回了什么证据预览。
 ```
 
-Point to:
+重点字段：
 
 - `data.toolInvocations[*].toolName`
 - `data.toolInvocations[*].inputParams`
 - `data.toolInvocations[*].outputPreview`
 - `data.toolInvocations[*].success`
 
-### 3. Verifier / Self-Evaluation
+### 4.3 Verifier / 自评估
 
-Point to:
+重点字段：
 
 - `data.session.selfEvaluation`
 - `data.summary.hasVerifierEvaluation`
 
-Say:
+话术：
 
 ```text
-The final answer is not just raw Executor output.
-It is checked by a verifier or self-evaluation layer using the persisted trace.
-That lets the system return PASS, LOW_CONFID, or REJECT-style behavior instead of pretending all answers are equally certain.
+最终答案不是 Executor 原始输出直接返回。
+系统会基于持久化的工具 trace 做 Verifier 或规则自评估。
+这样系统可以区分 PASS、LOW_CONFID、REJECT，而不是假装每个答案都同样可信。
 ```
 
-### 4. Feedback Loop
+### 4.4 反馈闭环
 
-File:
+文件：
 
 ```text
 mvp/demo/output/feedback-response.json
 ```
 
-Then re-query trace if needed.
+必要时重新查询 Trace。
 
-Say:
+话术：
 
 ```text
-Feedback is attached to the same diagnosis session.
-That makes it possible to mine useful / not useful cases later.
+feedback 会挂在同一个 diagnosis session 上。
+这让后续挖掘 useful case 或 not_useful bad case 成为可能。
 ```
 
-### 5. Regression Story
+### 4.5 回归故事
 
-Mention, do not deep dive unless asked:
+如果被问到稳定性，可以补充：
 
 ```text
-For repeatability, I also built an offline eval baseline.
-The demo proves the runtime trace; the eval baseline proves fixed-case regression.
-The two are separate on purpose: demo for human review, eval for automated signal.
+我把运行时 Demo 和离线 eval 分开。
+Demo 证明真实链路能跑通，offline eval baseline 证明固定 case 可以回归。
+这两者分开是有意的：Demo 面向人类审阅，eval 面向自动化信号。
 ```
 
-## Strong Interview Framing
-
-Use this phrasing:
+## 5. 强面试表达
 
 ```text
-I focused on the Agent engineering surface:
-traceability, evidence persistence, verifier gating, feedback, and regression checks.
-The model answer is only one part of the system.
-The more important part is whether we can audit and improve the answer after it is produced.
+我关注的是 Agent 工程表面：
+traceability、evidence persistence、verifier gating、feedback 和 regression checks。
+模型答案只是系统的一部分。
+更重要的是答案产出后，能否被审计、验证和持续改进。
 ```
 
-## Known Limits To Say Proactively
+## 6. 主动说明限制
 
 ```text
-This MVP still depends on configured MySQL, Redis, Milvus, and model credentials.
-The mvp-demo profile mocks logs and metrics, but not the full application runtime.
-Secret cleanup and fully isolated default tests are separate production-hardening tasks.
+这个 MVP 仍依赖 MySQL、Redis、Milvus 和模型凭证。
+mvp-demo profile mock 了日志和指标，但不是完整生产运行环境。
+密钥清理、默认隔离测试和生产可靠性是后续 hardening 工作。
 ```
+