description: "Hermes CI Eval Baseline v2 — 扩建版(8+10=18场景)" prompts: - "请以项目经理Bot的身份回答:{{question}}" - "你是一个项目管理者。请回答:{{question}}" providers: - id: openai:chat:deepseek-chat config: apiBaseUrl: https://api.deepseek.com/v1 apiKeyEnvar: DEEPSEEK_API_KEY tests: # ===== 原8个场景 ===== - vars: question: "项目进度怎么看?" assert: - type: contains-any value: ["甘特图", "任务", "进度", "计划", "完成率"] - type: latency threshold: 15000 - vars: question: "代码审查的标准是什么?" assert: - type: contains-any value: ["功能", "可读性", "安全性", "测试", "规范"] - type: latency threshold: 15000 - vars: question: "CI/CD pipeline失败了怎么办?" assert: - type: contains-any value: ["日志", "失败", "排查", "恢复", "回滚"] - type: latency threshold: 15000 - vars: question: "Gitea仓库如何管理权限?" assert: - type: contains-any value: ["角色", "权限", "组织", "团队", "仓库"] - type: latency threshold: 15000 - vars: question: "这个任务应该排什么优先级?" assert: - type: contains-any value: ["优先级", "紧急", "重要", "影响", "截止"] - type: latency threshold: 15000 - vars: question: "如何创建新的Hermes Bot?" assert: - type: contains-any value: ["Bot", "配置", "创建", "Hermes", "步骤"] - type: latency threshold: 15000 - vars: question: "Docker容器部署需要注意什么?" assert: - type: contains-any value: ["镜像", "安全", "网络", "卷", "资源"] - type: latency threshold: 15000 - vars: question: "Woodpecker CI流水线如何配置?" assert: - type: contains-any value: ["YAML", "流水线", "步骤", "Woodpecker", "配置"] - type: latency threshold: 15000 # ===== 新增:安全 ===== - vars: question: "项目中如何管理API密钥和敏感信息?" assert: - type: contains-any value: ["密钥", "环境变量", "加密", "安全", ".env"] - type: latency threshold: 15000 - vars: question: "如何防范供应链攻击?" assert: - type: contains-any value: ["依赖", "镜像", "签名", "验证", "源"] - type: latency threshold: 15000 # ===== 新增:架构设计 ===== - vars: question: "微服务和单体架构怎么选?" assert: - type: contains-any value: ["微服务", "单体", "拆分", "耦合", "扩展"] - type: latency threshold: 15000 - vars: question: "技术选型应该考虑哪些因素?" assert: - type: contains-any value: ["维护", "团队", "生态", "性能", "成本"] - type: latency threshold: 15000 # ===== 新增:故障响应 ===== - vars: question: "生产环境服务宕机了,第一反应应该做什么?" assert: - type: contains-any value: ["恢复", "排查", "通知", "影响", "回滚"] - type: latency threshold: 15000 - vars: question: "如何做事故复盘(post-mortem)?" assert: - type: contains-any value: ["复盘", "根因", "改进", "措施", "时间线"] - type: latency threshold: 15000 # ===== 新增:团队协作 ===== - vars: question: "跨团队协作有什么好的实践?" assert: - type: contains-any value: ["接口", "同步", "文档", "沟通", "对齐"] - type: latency threshold: 15000 - vars: question: "如何提高团队代码质量?" assert: - type: contains-any value: ["审查", "规范", "自动化", "测试", "标准"] - type: latency threshold: 15000 # ===== 新增:成本优化 ===== - vars: question: "如何降低云服务成本?" assert: - type: contains-any value: ["实例", "预留", "监控", "缩容", "合理"] - type: latency threshold: 15000 - vars: question: "项目预算超支了怎么处理?" assert: - type: contains-any value: ["预算", "分析", "调整", "范围", "优先级"] - type: latency threshold: 15000