feat: add AI学习助手 agent (KG+RAG ideal) and renshenguo feishu bot

- Add AI学习助手 agent creation script with all 39 tools, 3-layer KG+RAG memory
- Add renshenguo (人参果) feishu bot integration (app_service + ws_handler)
- Register renshenguo WS client in main.py startup
- Add RENSHENGUO_APP_ID / RENSHENGUO_APP_SECRET / RENSHENGUO_AGENT_ID config
- Reorganize docs from root into docs/ subdirectories
- Move startup scripts to scripts/startup/
- Various backend optimizations and tool improvements

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

misc/test-data/multi_route_workflow.json

@@ -0,0 +1,196 @@
+{
+  "name": "企业多线路由助手",
+  "description": "根据query内容自动路由到客服/研发/运维专精LLM，合并结果输出",
+  "nodes": [
+    {
+      "id": "start-1",
+      "type": "start",
+      "position": { "x": 100, "y": 250 },
+      "data": {
+        "label": "开始",
+        "description": "工作流开始节点"
+      }
+    },
+    {
+      "id": "input-1",
+      "type": "input",
+      "position": { "x": 300, "y": 250 },
+      "data": {
+        "label": "输入查询",
+        "field": "query",
+        "description": "输入用户查询内容",
+        "required": true,
+        "placeholder": "请输入您的问题..."
+      }
+    },
+    {
+      "id": "switch-1",
+      "type": "switch",
+      "position": { "x": 500, "y": 250 },
+      "data": {
+        "label": "路由判断",
+        "field": "query",
+        "cases": {
+          "客服": "customer_service",
+          "研发": "development",
+          "运维": "operation"
+        },
+        "default": "customer_service",
+        "description": "根据query内容路由到不同专精LLM"
+      }
+    },
+    {
+      "id": "llm-customer",
+      "type": "llm",
+      "position": { "x": 700, "y": 150 },
+      "data": {
+        "label": "客服专精LLM",
+        "model": "deepseek",
+        "prompt": "你是一个专业的客服助手，擅长处理客户咨询、投诉、售后问题。请根据用户问题提供专业、友好的客服解答。\n\n用户问题：{{query}}\n\n请回答：",
+        "temperature": 0.7,
+        "max_tokens": 1000,
+        "enable_tools": true,
+        "description": "客服领域专精AI助手"
+      }
+    },
+    {
+      "id": "llm-development",
+      "type": "llm",
+      "position": { "x": 700, "y": 250 },
+      "data": {
+        "label": "研发专精LLM",
+        "model": "deepseek",
+        "prompt": "你是一个专业的研发工程师，擅长技术问题解答、代码调试、架构设计。请根据用户问题提供专业的技术解决方案。\n\n用户问题：{{query}}\n\n请回答：",
+        "temperature": 0.7,
+        "max_tokens": 1000,
+        "enable_tools": true,
+        "description": "研发技术专精AI助手"
+      }
+    },
+    {
+      "id": "llm-operation",
+      "type": "llm",
+      "position": { "x": 700, "y": 350 },
+      "data": {
+        "label": "运维专精LLM",
+        "model": "deepseek",
+        "prompt": "你是一个专业的运维工程师，擅长系统部署、监控、故障排查。请根据用户问题提供专业的运维解决方案。\n\n用户问题：{{query}}\n\n请回答：",
+        "temperature": 0.7,
+        "max_tokens": 1000,
+        "enable_tools": true,
+        "description": "运维领域专精AI助手"
+      }
+    },
+    {
+      "id": "merge-1",
+      "type": "merge",
+      "position": { "x": 900, "y": 250 },
+      "data": {
+        "label": "结果合并",
+        "mode": "merge_all",
+        "strategy": "object",
+        "description": "合并所有分支结果（实际上只有一个分支会执行）"
+      }
+    },
+    {
+      "id": "output-1",
+      "type": "output",
+      "position": { "x": 1100, "y": 250 },
+      "data": {
+        "label": "输出结果",
+        "field": "response",
+        "description": "输出最终回答"
+      }
+    },
+    {
+      "id": "end-1",
+      "type": "end",
+      "position": { "x": 1300, "y": 250 },
+      "data": {
+        "label": "结束",
+        "description": "工作流结束"
+      }
+    }
+  ],
+  "edges": [
+    {
+      "id": "e1",
+      "source": "start-1",
+      "target": "input-1",
+      "sourceHandle": "right",
+      "targetHandle": "left"
+    },
+    {
+      "id": "e2",
+      "source": "input-1",
+      "target": "switch-1",
+      "sourceHandle": "right",
+      "targetHandle": "left"
+    },
+    {
+      "id": "e3-customer",
+      "source": "switch-1",
+      "target": "llm-customer",
+      "sourceHandle": "right",
+      "targetHandle": "left",
+      "data": {
+        "branch": "customer_service"
+      }
+    },
+    {
+      "id": "e3-development",
+      "source": "switch-1",
+      "target": "llm-development",
+      "sourceHandle": "right",
+      "targetHandle": "left",
+      "data": {
+        "branch": "development"
+      }
+    },
+    {
+      "id": "e3-operation",
+      "source": "switch-1",
+      "target": "llm-operation",
+      "sourceHandle": "right",
+      "targetHandle": "left",
+      "data": {
+        "branch": "operation"
+      }
+    },
+    {
+      "id": "e4-customer",
+      "source": "llm-customer",
+      "target": "merge-1",
+      "sourceHandle": "right",
+      "targetHandle": "left"
+    },
+    {
+      "id": "e4-development",
+      "source": "llm-development",
+      "target": "merge-1",
+      "sourceHandle": "right",
+      "targetHandle": "left"
+    },
+    {
+      "id": "e4-operation",
+      "source": "llm-operation",
+      "target": "merge-1",
+      "sourceHandle": "right",
+      "targetHandle": "left"
+    },
+    {
+      "id": "e5",
+      "source": "merge-1",
+      "target": "output-1",
+      "sourceHandle": "right",
+      "targetHandle": "left"
+    },
+    {
+      "id": "e6",
+      "source": "output-1",
+      "target": "end-1",
+      "sourceHandle": "right",
+      "targetHandle": "left"
+    }
+  ]
+}