feat(api): add health check and models endpoints with documentation

- Add /health endpoint to check service status for orchestration systems
- Add /models endpoint with OpenAI API compatible format
- Document new endpoints in both English and Chinese API docs
- Include example usage and response formats in documentation
- Add comprehensive test coverage for health and models endpoints
- Refactor model storage to include type information alongside instance
- Move model ID and type methods to WhichModel implementation
- Update API calls to access model instance through stored wrapper

docs/api.zh-CN.md

@@ -57,6 +57,92 @@ Content-Type: application/json
 
 ## 端点
 
+### 健康检查
+
+检查服务健康状态。此端点适用于容器编排（Kubernetes）、负载均衡器和监控系统。
+
+#### 端点
+```
+GET /health
+```
+
+#### 响应
+
+**健康 (HTTP 200):**
+
+```json
+{
+  "status": "ok"
+}
+```
+
+**不健康 (HTTP 503):**
+
+```json
+{
+  "status": "unhealthy",
+  "error": "model not initialized"
+}
+```
+
+#### 示例
+
+```bash
+curl http://127.0.0.1:10100/health
+```
+
+### 模型列表
+
+获取当前加载的模型信息（OpenAI API 兼容格式）。
+
+#### 端点
+```
+GET /models
+```
+
+#### 响应
+
+**成功 (HTTP 200):**
+
+```json
+{
+  "object": "list",
+  "data": [
+    {
+      "id": "qwen3-0.6b",
+      "object": "model",
+      "created": null,
+      "owned_by": "Qwen"
+    }
+  ]
+}
+```
+
+**未初始化 (HTTP 503):**
+
+```json
+{
+  "error": "model not initialized"
+}
+```
+
+#### 字段
+
+| 字段 | 类型 | 描述 |
+|------|------|------|
+| `object` | string | 固定值："list" |
+| `data` | array | 模型对象数组（当前仅包含一个已加载的模型） |
+| `id` | string | 模型标识符（kebab-case，如 "qwen3-0.6b"） |
+| `object` | string | 固定值："model" |
+| `created` | integer\|null | Unix 时间戳（当前为 null） |
+| `owned_by` | string | 模型所有者/组织名称 |
+
+#### 示例
+
+```bash
+curl http://127.0.0.1:10100/models
+```
+
 ### 对话补全
 
 生成对话补全或文本响应。