phase 6 part 2: per-week related-topics sections (gen_week_topics.py), week14/15/16 adjustments from BOSS research, README/CONTRIBUTING updates

plan/week05-rag-1.md

@@ -1406,6 +1406,26 @@ uv run ruff check . && uv run pyright src && uv run pytest -v
 
 ---
 
+<!-- week-topics:start -->
+
+## 本周相关专题
+
+> 本节由 `tools/gen_week_topics.py` 根据专题文件的 `week` 字段自动生成，请勿手改；想调整就修改对应专题文件的 frontmatter 后重新生成。
+
+- **AI 编程练习（每周）**：本周至少一个功能用 AI 编程工具（Cursor / Claude Code / Codex 等）完成，按 [AI 编程：工作流](../topics/ai/ai-coding/01-workflow-rules-skills.md) 写清需求和规则，按 [验证与证据](../topics/ai/ai-coding/02-verify-evidence.md) 保存测试结果和会话记录（脱敏后），第 15 周整理成“AI 编程 + 验证方法”的应聘案例。
+
+| 技术栈 | 课程 / 场景 / 面试题 |
+| --- | --- |
+| [提示词与上下文工程](../topics/ai/prompt-engineering/index.md) | 课程：[提示词结构、少样本、结构化输出和提示词版本管理](../topics/ai/prompt-engineering/01-prompt-structured-output.md)；[面试题](../topics/ai/prompt-engineering/interview.md) |
+| [RAG 检索增强生成](../topics/ai/rag/index.md) | 课程：[RAG 流水线和文档切分](../topics/ai/rag/01-pipeline-chunking.md)；场景：[带权限的企业知识库问答](../topics/ai/rag/scenarios/permission-aware-kb.md)；[面试题](../topics/ai/rag/interview.md) |
+| [向量数据库](../topics/ai/vector-db/index.md) | 课程：[向量检索原理](../topics/ai/vector-db/01-ann-metrics.md)；课程：[向量库选型和 pgvector 实战](../topics/ai/vector-db/02-selection-pgvector.md)；[面试题](../topics/ai/vector-db/interview.md) |
+| [asyncio 异步编程](../topics/python/asyncio/index.md) | 课程：[并发控制](../topics/python/asyncio/02-concurrency-control.md)；场景：[并发调用多个模型和外部接口](../topics/python/asyncio/scenarios/concurrent-llm-calls.md) |
+| [FastAPI](../topics/python/fastapi/index.md) | 课程：[依赖注入、鉴权、中间件和统一错误处理](../topics/python/fastapi/02-deps-auth-errors.md)；课程：[流式输出（SSE）、生命周期、测试和部署](../topics/python/fastapi/03-streaming-testing.md)；场景：[大模型对话 API](../topics/python/fastapi/scenarios/streaming-chat-api.md)；[面试题](../topics/python/fastapi/interview.md) |
+
+**跨技术栈场景**：[客服知识库问答](../scenarios/customer-service-kb.md)
+
+<!-- week-topics:end -->
+
 ## 本周自查清单
 
 - [ ] 能画出 RAG 两条流水线，讲清向量和余弦相似度