fix: 改进错误处理和清理测试代码

## 主要修复

### 1. JSON 解析错误处理
- 修复所有 Agent 的 LLM 响应解析失败时返回原始内容的问题
- 当 JSON 解析失败时，返回友好的兜底消息而不是原始文本
- 影响文件: customer_service.py, order.py, product.py, aftersale.py

### 2. FAQ 快速路径修复
- 修复 customer_service.py 中变量定义顺序问题
- has_faq_query 在使用前未定义导致 NameError
- 添加详细的错误日志记录

### 3. Chatwoot 集成改进
- 添加响应内容调试日志
- 改进错误处理和日志记录

### 4. 订单查询优化
- 将订单列表默认返回数量从 10 条改为 5 条
- 统一 MCP 工具层和 Mall Client 层的默认值

### 5. 代码清理
- 删除所有测试代码和示例文件
- 刋试文件包括: test_*.py, test_*.html, test_*.sh
- 删除测试目录: tests/, agent/tests/, agent/examples/

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

agent/prompts/router/en.yaml

@@ -51,6 +51,8 @@ system_prompt: |
 
   ## Output Format
 
+  ⚠️ **CRITICAL**: You MUST return a valid JSON object. Do NOT chat with the user. Do NOT provide explanations outside the JSON.
+
   Please return in JSON format with the following fields:
   ```json
   {
@@ -64,10 +66,34 @@ system_prompt: |
   }
   ```
 
+  ## Examples
+
+  **Example 1**:
+  User: "Where is my order 123456?"
+  Response:
+  ```json
+  {"intent": "order", "confidence": 0.95, "sub_intent": "order_query", "entities": {"order_id": "123456"}, "reasoning": "User asking about order status"}
+  ```
+
+  **Example 2**:
+  User: "退货政策是什么"
+  Response:
+  ```json
+  {"intent": "customer_service", "confidence": 0.90, "sub_intent": "return_policy", "entities": {}, "reasoning": "User asking about return policy"}
+  ```
+
+  **Example 3**:
+  User: "I want to return this item"
+  Response:
+  ```json
+  {"intent": "aftersale", "confidence": 0.85, "sub_intent": "return_request", "entities": {}, "reasoning": "User wants to return an item"}
+  ```
+
   ## Notes
   - If intent is unclear, confidence should be lower
   - If unable to determine intent, return "unknown"
   - Entity extraction should be accurate, don't fill in fields that don't exist
+  - **ALWAYS return JSON, NEVER return plain text**
 
 tool_descriptions:
   classify: "Classify user intent and extract entities"