commit 5ea2710ed206f4729b0dbd56a2f6825b29fb3054
Author: Hermes CI Bot <hermes-ci@sxbh.ltd>
Date:   Thu Jul 9 20:14:15 2026 +0800

    feat: initial Hermes CI eval baseline
    
    - promptfoo eval config with 8 test scenarios
    - Assertions: contains-any + latency checks
    - Woodpecker pipeline: eval-baseline + report steps
    - Evaluates Hermes Bot's project management responses

diff --git a/.woodpecker/main.yml b/.woodpecker/main.yml
new file mode 100644
index 0000000..4b43874
--- /dev/null
+++ b/.woodpecker/main.yml
@@ -0,0 +1,32 @@
+when:
+  branch: main
+  event: [push, pull_request]
+
+steps:
+  eval-baseline:
+    image: node:23-alpine
+    environment:
+      DEEPSEEK_API_KEY:
+        from_secret: DEEPSEEK_API_KEY
+    commands:
+      - apk add --no-cache git
+      - npm install -g promptfoo
+      - cd promptfoo-eval
+      - promptfoo eval --max-concurrency 2 --no-cache
+      - promptfoo results --format json > /tmp/eval-results.json
+      - |
+        FAILURES=$(cat /tmp/eval-results.json | grep -o '"failures":[0-9]*' | grep -o '[0-9]*')
+        if [ "$FAILURES" != "0" ] && [ -n "$FAILURES" ]; then
+          echo "❌ Eval FAILED: $FAILURES test failures"
+          exit 1
+        fi
+      - echo "✅ All eval tests passed!"
+
+  report:
+    image: alpine:latest
+    commands:
+      - echo "Hermes CI Eval Baseline - $(date -u '+%Y-%m-%d %H:%M UTC')"
+      - echo "Status: ✅ PASS"
+      - echo "Next steps: Review results and update eval dataset"
+    when:
+      status: success
diff --git a/promptfooconfig.yaml b/promptfooconfig.yaml
new file mode 100644
index 0000000..590affb
--- /dev/null
+++ b/promptfooconfig.yaml
@@ -0,0 +1,77 @@
+description: "Hermes CI Eval Baseline v1 — 带断言评测"
+
+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
+
+# 测试数据集
+tests:
+  - 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