feat(搜索): 添加jack6249毕业设计V1.1

Co-creation-projects/jack6249-GiftGeniusAgent/.env example

@@ -3,4 +3,6 @@ LLM_MODEL_ID = "yourmodel"
 LLM_API_KEY = "yourkey"
 LLM_BASE_URL = "yourbaseurl"
 #Tavily参数
-TAVILY_API_KEY = "yourTavilyKey"
+TAVILY_API_KEY = "yourTavilyKey"
+#百度优选MCP参数
+BAIDU_MCP_TOKEN = "yourtoken"

Co-creation-projects/jack6249-GiftGeniusAgent/README.md

@@ -38,9 +38,11 @@ GiftGenius 是一个智能化的礼物推荐 Agent，旨在解决“送什么礼
 
   用于从搜索结果中提取专家的数据反思和修正。
 
-- 工具与API:Tavily Search API (用于联网检索)
+- 工具与API:
 
-- 其他依赖: python-dotenv, numpy (用于价格计算), jupyter
+  Tavily Search API (用于联网检索)、百度优选MCP(用于联网检索)
+
+- 其他依赖: `mcp`, `nest_asyncio`, `python-dotenv`, `numpy`
 
 ## 🚀 快速开始
 
@@ -77,6 +79,12 @@ cp .env.example .env
 ```bash
 jupyter notebook main.ipynb
 ```
+项目默认使用的是百度优选MCP，可修改为Tavily Search API。
+```py
+# 搜索源配置
+# 可选值: "tavily" (通用/海外) 或 "baidu" (电商/国内)
+os.environ["SEARCH_PROVIDER"] = "baidu" 
+```
 
 
 点击 "Run All" 运行所有单元格，最终结果将生成在 outputs/gift_plan_output.md 中。
@@ -109,11 +117,13 @@ jupyter notebook main.ipynb
 
 - 动态策略修正 (Feedback Loop)：实现了“价格守门员”机制。如果搜到的商品均价超预算，会重新触发“军师”制定“平替”策略，直到找到合适商品为止。
 
+- 支持多数据源：集成了百度优选MCP 和 Tavily Search API 两种搜索源
+
 ## 🔮 未来计划
 
 - [ ] 前端交互：新增前端页面，提供更好的用户交互体验
 
-- [ ] 数据源增强：接入百度或BigGo的MCP Server，获取更精准的实时价格和商品信息
+- [ ] 数据源深度集成：完全接入百度优选MCP 的比价与历史价格接口，获取更精准的实时价格和库存信息，实现“全网比价”功能。
 
 - [ ] 丰富选项：增加更多的个人喜好选项，如喜欢的商品类型、品牌等
 

Co-creation-projects/jack6249-GiftGeniusAgent/main.ipynb

@@ -33,7 +33,7 @@
    "outputs": [],
    "source": [
     "#导入库和参数配置\n",
-    "from hello_agents import SimpleAgent, HelloAgentsLLM, ReflectionAgent\n",
+    "from hello_agents import SimpleAgent, HelloAgentsLLM, ReflectionAgent, ToolRegistry\n",
     "from hello_agents.tools import Tool, ToolParameter\n",
     "from typing import Dict, Any, List\n",
     "from tavily import TavilyClient\n",
@@ -42,23 +42,34 @@
     "import re\n",
     "import numpy as np \n",
     "from dotenv import load_dotenv\n",
+    "import asyncio\n",
+    "import nest_asyncio\n",
+    "from mcp.client.sse import sse_client\n",
+    "from mcp.client.session import ClientSession\n",
     "\n",
     "load_dotenv()\n",
     "\n",
     "#LLM参数\n",
     "LLM_MODEL_ID = os.getenv(\"LLM_MODEL_ID\")\n",
-    "#\"deepseek-chat\"\n",
     "LLM_API_KEY = os.getenv(\"LLM_API_KEY\")\n",
     "LLM_BASE_URL = os.getenv(\"LLM_BASE_URL\")\n",
     "#Tavily参数\n",
-    "TAVILY_API_KEY = os.getenv(\"TAVILY_API_KEY\")\n",
+    "TAVILY_API_KEY = os.getenv(\"TAVILY_API_KEY\",\"\")\n",
+    "#百度MCP参数\n",
+    "BAIDU_TOKEN = os.getenv(\"BAIDU_MCP_TOKEN\",\"\")\n",
+    "#输入json路径配置\n",
+    "INPUT_FILENAME = \"data/test_cases.json\"\n",
+    "\n",
+    "# 搜索源配置\n",
+    "# 可选值: \"tavily\" (通用/海外) 或 \"baidu\" (电商/国内)\n",
+    "os.environ[\"SEARCH_PROVIDER\"] = \"baidu\" \n",
     "\n",
     "print(\"✅ 环境配置完成\")\n"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "27482621",
+   "id": "9404c299",
    "metadata": {},
    "source": [
     "### 第2部分：定义工具"
@@ -67,60 +78,110 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "2087de45",
+   "id": "37b994bc",
    "metadata": {},
    "outputs": [],
    "source": [
+    "# [Cell 2 终极版] 定义统一搜索工具 (兼容 Tavily 和 Baidu)\n",
+    "# 允许 Jupyter 运行异步\n",
+    "nest_asyncio.apply()\n",
+    "\n",
     "class BatchSearchTool(Tool):\n",
     "    def __init__(self):\n",
     "        super().__init__(\n",
     "            name=\"batch_search\",\n",
-    "            description=\"高级批量搜索工具。\"\n",
+    "            description=\"统一搜索工具，支持 Tavily 和 Baidu 切换。\"\n",
     "        )\n",
+    "        self.provider = os.environ.get(\"SEARCH_PROVIDER\", \"tavily\").lower()\n",
+    "\n",
+    "    def run(self, parameters: Any) -> str:\n",
+    "        return \"请使用 Python 代码直接调用 search_raw 方法获取数据。\"\n",
     "\n",
     "    def search_raw(self, query: str) -> List[Dict]:\n",
-    "        if \"TAVILY_API_KEY\" not in os.environ: \n",
-    "            print(\"❌ 错误：缺少 API Key\")\n",
-    "            return []\n",
+    "        if self.provider == \"baidu\":\n",
+    "            return self._search_baidu(query)\n",
+    "        else:\n",
+    "            return self._search_tavily(query)\n",
     "\n",
-    "        print(f\"    🚀 [直连搜索] 正在抓取: {query} ...\")\n",
+    "    # --- 引擎 A: Tavily ---\n",
+    "    def _search_tavily(self, query: str) -> List[Dict]:\n",
+    "        api_key = os.environ.get(\"TAVILY_API_KEY\")\n",
+    "        if not api_key: return []\n",
+    "        print(f\"    🚀 [Tavily] 正在搜索: {query} ...\")\n",
     "        try:\n",
-    "            tavily = TavilyClient(api_key=os.environ[\"TAVILY_API_KEY\"])\n",
-    "            # 搜索包含图片\n",
-    "            response = tavily.search(query, max_results=5, include_images=True) # 增加到5条，提高命中率\n",
-    "            \n",
+    "            tavily = TavilyClient(api_key=api_key)\n",
+    "            response = tavily.search(query, max_results=5, include_images=True)\n",
     "            results = []\n",
-    "            # 1. 提取文本结果\n",
     "            if 'results' in response:\n",
     "                for r in response['results']:\n",
     "                    results.append({\n",
-    "                        \"title\": r['title'],\n",
-    "                        \"url\": r['url'],\n",
-    "                        \"content\": r['content'], \n",
-    "                        \"type\": \"text\"\n",
+    "                        \"title\": r['title'], \"url\": r['url'], \"content\": r['content'], \n",
+    "                        \"type\": \"text\", \"img\": \"\" # Tavily 文本通常不带图\n",
     "                    })\n",
-    "            \n",
-    "            # 2. 提取图片结果\n",
     "            if 'images' in response and response['images']:\n",
-    "                results.append({\n",
-    "                    \"images\": response['images'][:3], # 取前3张\n",
-    "                    \"type\": \"image\"\n",
-    "                })\n",
-    "                \n",
+    "                results.append({\"images\": response['images'][:3], \"type\": \"image\"})\n",
     "            return results\n",
-    "            \n",
     "        except Exception as e:\n",
-    "            print(f\"      ⚠️ 搜索异常: {e}\")\n",
+    "            print(f\"      ⚠️ Tavily 异常: {e}\")\n",
+    "            return []\n",
+    "\n",
+    "    # --- 引擎 B: Baidu MCP ---\n",
+    "    def _search_baidu(self, query: str) -> List[Dict]:\n",
+    "        token = os.environ.get(\"BAIDU_MCP_TOKEN\")\n",
+    "        if not token: return []\n",
+    "        print(f\"    🐼 [百度优选] 正在搜索: {query} ...\")\n",
+    "        try:\n",
+    "            raw_json_str = asyncio.run(self._async_baidu_call(query, token))\n",
+    "            print(f\"      🔍 原始 JSON 响应: {raw_json_str}\")\n",
+    "            return self._parse_baidu_response(raw_json_str)\n",
+    "        except Exception as e:\n",
+    "            print(f\"      ⚠️ 百度 MCP 异常: {e}\")\n",
     "            return []\n",
-    "    \n",
-    "    # 兼容 Agent 调用接口\n",
-    "    def run(self, parameters: Any) -> str:\n",
-    "        return \"请使用 Python 代码直接调用 search_raw 方法获取数据。\"\n",
-    "    \n",
-    "    def get_parameters(self) -> List[ToolParameter]:\n",
-    "        return [ToolParameter(name=\"query\", type=\"string\", description=\"关键词\", required=True)]\n",
     "\n",
-    "print(\"✅ BatchSearchTool定义完成\")"
+    "    async def _async_baidu_call(self, query: str, token: str) -> str:\n",
+    "        sse_url = f\"https://mcp-youxuan.baidu.com/mcp/sse?key={token}\"\n",
+    "        async with sse_client(sse_url) as (read, write):\n",
+    "            async with ClientSession(read, write) as session:\n",
+    "                await session.initialize()\n",
+    "                result = await session.call_tool(\"goods_search\", arguments={\"query\": query})\n",
+    "                return result.content[0].text if result.content else \"\"\n",
+    "\n",
+    "    def _parse_baidu_response(self, json_str: str) -> List[Dict]:\n",
+    "        results = []; images = []\n",
+    "        try:\n",
+    "            data = json.loads(json_str)\n",
+    "            items = data if isinstance(data, list) else []\n",
+    "            \n",
+    "            for item in items[:5]:\n",
+    "                title = item.get(\"goodsName\") or item.get(\"title\") or \"未知商品\"\n",
+    "                price = item.get(\"price\") or item.get(\"minPrice\") or \"\"\n",
+    "                shop = item.get(\"shopName\") or item.get(\"mall\") or \"\"\n",
+    "                url = item.get(\"detailUrl\") or item.get(\"url\") or item.get(\"ori_url\") or \"#\"\n",
+    "                img = item.get(\"imgUrl\") or item.get(\"picUrl\") or item.get(\"img\")\n",
+    "                \n",
+    "                content = f\"价格: {price}元。店铺: {shop}。商品详情: {title}\"\n",
+    "                \n",
+    "                # 📝【修复点】直接在 text 类型结果里绑定 img\n",
+    "                results.append({\n",
+    "                    \"title\": title, \"url\": url, \"content\": content, \n",
+    "                    \"type\": \"text\", \"img\": img \n",
+    "                })\n",
+    "                if img: images.append(img)\n",
+    "            \n",
+    "            if images: results.append({\"images\": images[:3], \"type\": \"image\"})\n",
+    "                \n",
+    "        except json.JSONDecodeError:\n",
+    "            print(\"      ⚠️ 百度返回非 JSON 数据\")\n",
+    "        return results\n",
+    "\n",
+    "    def get_parameters(self):\n",
+    "        return [ToolParameter(name=\"query\", type=\"string\", description=\"关键词\")]\n",
+    "\n",
+    "tool_registry = ToolRegistry()\n",
+    "tool_registry.register_tool(BatchSearchTool())\n",
+    "\n",
+    "print(\"✅ 统一搜索工具已加载！\")\n",
+    "print(f\"当前模式: {'百度优选 (电商)' if os.environ.get('SEARCH_PROVIDER') == 'baidu' else 'Tavily (通用)'}\")"
    ]
   },
   {
@@ -139,15 +200,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from hello_agents import ToolRegistry\n",
-    "\n",
-    "#创建工具\n",
-    "tool_registry = ToolRegistry()\n",
-    "tool_registry.register_tool(BatchSearchTool())\n",
-    "\n",
-    "print(tool_registry.list_tools())\n",
-    "\n",
-    "\n",
     "# 初始化大模型\n",
     "llm = HelloAgentsLLM()\n",
     "\n",
@@ -159,8 +211,7 @@
     "【⚠️ 时效性死命令 (CRITICAL)】\n",
     "当前时间视作 **2025年11月**。\n",
     "1. **严禁过时**：绝对不要推荐 2024 年或更早的旧款（除非是经典恒久款如黑胶唱片）。\n",
-    "2. **锁定新品**：对于**化妆品、数码、盲盒**，必须搜索 **\"2025圣诞限定\"**、**\"2025秋冬新品\"** 或 **\"2026春季预告\"**。\n",
-    "3. **价格尺度**：给出的价格单位是人民币元。请严格遵照范围进行联想，禁止超出预算范围。\n",
+    "2. **价格尺度**：给出的价格单位是人民币元。请严格遵照范围进行联想，禁止超出预算范围。\n",
     "\n",
     "为了确保推荐质量，请参考以下的【优秀思考范例】：\n",
     "\n",
@@ -325,9 +376,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "\n",
-    "INPUT_FILENAME = \"data/test_cases.json\"\n",
-    "\n",
     "def load_user_profile(filename):\n",
     "    # 1. 检查文件是否存在\n",
     "    if not os.path.exists(filename):\n",
@@ -359,9 +407,7 @@
     "        return {}\n",
     "\n",
     "# 加载数据\n",
-    "user_input_data = load_user_profile(INPUT_FILENAME)\n",
-    "\n",
-    "\n"
+    "user_input_data = load_user_profile(INPUT_FILENAME)\n"
    ]
   },
   {
@@ -379,7 +425,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "\n",
     "def parse_budget_range(budget_str):\n",
     "    \"\"\"解析用户预算字符串，返回 (min, max)\"\"\"\n",
     "    nums = [float(x) for x in re.findall(r'\\d+', str(budget_str).replace(',', ''))]\n",
@@ -411,97 +456,139 @@
     "                    prices.append(val)\n",
     "    return prices\n",
     "\n",
-    "def find_best_product(hunter, profiler_agent, keyword, budget_limit):\n",
-    "    \"\"\"\n",
-    "    智能搜索核心函数：包含 初次搜索 -> 价格校验 -> 策略修正 -> 自动降级 -> 智能兜底\n",
-    "    \"\"\"\n",
-    "    # 容器：用于收集所有搜索到的潜在结果（用于兜底）\n",
+    "\n",
+    "def find_best_product(hunter, profiler_agent, keyword, budget_min, budget_max):\n",
+    "    limit_upper = budget_max * 1.2\n",
+    "    limit_lower = budget_min * 0.8\n",
+    "    \n",
     "    all_candidates = []\n",
     "    current_kw = keyword\n",
     "    \n",
     "    # --- Round 1: 首次搜索 ---\n",
     "    print(f\"       🕵️ 第1次搜索: {current_kw} 价格\")\n",
-    "    results_1 = hunter.search_raw(f\"{current_kw} 价格 RMB\")\n",
+    "    results_1 = hunter.search_raw(f\"{current_kw} 价格\")\n",
     "    \n",
-    "    # 提取第一轮搜索到的通用图片（以防具体条目没图）\n",
     "    fallback_img = \"\"\n",
     "    for r in results_1:\n",
     "        if r.get('images'): \n",
     "            fallback_img = r['images'][0]\n",
     "            break\n",
     "\n",
-    "    # 检查 Round 1 结果\n",
+    "    has_valid_info = False\n",
     "    for res in results_1:\n",
     "        if res.get('type') == 'text':\n",
+    "            has_valid_info = True\n",
     "            p_vals = extract_all_prices([res])\n",
     "            if p_vals:\n",
     "                res['price_val'] = p_vals[0]\n",
-    "                all_candidates.append(res) # 存入候选池\n",
-    "                if p_vals[0] <= budget_limit:\n",
-    "                    # 完美命中！\n",
+    "                # 📝【核心修复点1】记录当前结果所属的关键词\n",
+    "                res['source_kw'] = current_kw \n",
+    "                all_candidates.append(res)\n",
+    "                \n",
+    "                if limit_lower <= p_vals[0] <= limit_upper:\n",
     "                    if not res.get('img') and fallback_img: res['img'] = fallback_img\n",
     "                    return res, f\"约 {p_vals[0]}元\", current_kw\n",
     "\n",
-    "    # --- Round 2: 策略修正 (Feedback Loop) ---\n",
-    "    # 只有当找到了价格但都超标时，才触发修正\n",
-    "    avg_price = np.mean([c['price_val'] for c in all_candidates]) if all_candidates else 0\n",
-    "    \n",
-    "    if avg_price > budget_limit:\n",
-    "        print(f\"       💸 价格超标 (均价 {int(avg_price)} > 预算 {int(budget_limit/1.2)})，触发修正...\")\n",
-    "        \n",
-    "        correction_prompt = f\"\"\"\n",
-    "        原策略 \"{current_kw}\" 市场均价约 {int(avg_price)}元，超预算。\n",
-    "        请推荐一个 **同品类但更便宜** 的具体型号（平替）。\n",
-    "        只输出关键词，不要解释。\n",
-    "        \"\"\"\n",
+    "    # --- 机制 3: 无数据防御 ---\n",
+    "    if not has_valid_info:\n",
+    "        print(f\"       ⚠️ [机制3触发] 首次搜索无有效信息。\")\n",
+    "        correction_prompt = f\"原策略 '{current_kw}' 搜索结果为空，请推荐一个同品类但更热门的具体商品型号。只输出关键词。\"\n",
     "        new_kw = profiler_agent.run(correction_prompt).strip()\n",
-    "        print(f\"       🔄 军师修正策略为: {new_kw}\")\n",
-    "        current_kw = new_kw # 更新关键词\n",
+    "        print(f\"       🔄 军师换词: {new_kw}\")\n",
+    "        current_kw = new_kw\n",
     "        \n",
-    "        # 执行第二次搜索\n",
-    "        results_2 = hunter.search_raw(f\"{new_kw} 价格 RMB\")\n",
+    "        results = hunter.search_raw(f\"{current_kw} 价格\")\n",
     "        \n",
-    "        # 提取第二轮的图片\n",
-    "        for r in results_2:\n",
+    "        # 更新 fallback_img\n",
+    "        fallback_img = \"\" \n",
+    "        for r in results:\n",
     "            if r.get('images'): \n",
     "                fallback_img = r['images'][0]\n",
     "                break\n",
-    "        \n",
-    "        # 检查 Round 2 结果\n",
-    "        for res in results_2:\n",
+    "                \n",
+    "        for res in results:\n",
     "            if res.get('type') == 'text':\n",
     "                p_vals = extract_all_prices([res])\n",
     "                if p_vals:\n",
     "                    res['price_val'] = p_vals[0]\n",
-    "                    all_candidates.append(res) \n",
-    "                    if p_vals[0] <= budget_limit:\n",
-    "                        if not res.get('img') and fallback_img: res['img'] = fallback_img\n",
-    "                        return res, f\"约 {p_vals[0]}元 (平替)\", current_kw\n",
+    "                    # 📝【核心修复点1】记录关键词\n",
+    "                    res['source_kw'] = current_kw\n",
+    "                    all_candidates.append(res)\n",
     "\n",
-    "    # --- Round 3: 智能兜底 ---\n",
-    "    # 既然都没完美匹配，就从候选池里挑一个最便宜的，或者直接硬取第一个\n",
+    "    # --- 机制 1 & 2: 价格修正 ---\n",
+    "    avg_price = np.mean([c['price_val'] for c in all_candidates]) if all_candidates else 0\n",
     "    \n",
+    "    if avg_price > 0:\n",
+    "        correction_prompt = \"\"\n",
+    "        if avg_price > limit_upper:\n",
+    "            print(f\"       💸 [机制1触发] 均价 {int(avg_price)} > 上限 {int(limit_upper)}，找平替...\")\n",
+    "            correction_prompt = f\"原策略 '{current_kw}' 均价约 {int(avg_price)}元，超预算 ({budget_max}元)。请推荐一个同品类更便宜的具体型号（平替）。只输出关键词。\"\n",
+    "        elif avg_price < limit_lower:\n",
+    "            print(f\"       📉 [机制2触发] 均价 {int(avg_price)} < 下限 {int(limit_lower)}，找升级款...\")\n",
+    "            correction_prompt = f\"原策略 '{current_kw}' 均价约 {int(avg_price)}元，低于预算下限 ({budget_min}元)。请推荐一个同品类更高端的型号。只输出关键词。\"\n",
+    "            \n",
+    "        if correction_prompt:\n",
+    "            new_kw = profiler_agent.run(correction_prompt).strip()\n",
+    "            print(f\"       🔄 军师修正: {new_kw}\")\n",
+    "            current_kw = new_kw\n",
+    "            \n",
+    "            results_2 = hunter.search_raw(f\"{new_kw} 价格\")\n",
+    "            \n",
+    "            # 更新 fallback_img\n",
+    "            fallback_img = \"\" \n",
+    "            for r in results_2:\n",
+    "                if r.get('images'): \n",
+    "                    fallback_img = r['images'][0]\n",
+    "                    break\n",
+    "            \n",
+    "            for res in results_2:\n",
+    "                if res.get('type') == 'text':\n",
+    "                    p_vals = extract_all_prices([res])\n",
+    "                    if p_vals:\n",
+    "                        res['price_val'] = p_vals[0]\n",
+    "                        # 📝【核心修复点1】记录关键词\n",
+    "                        res['source_kw'] = current_kw\n",
+    "                        all_candidates.append(res) \n",
+    "                        \n",
+    "                        if limit_lower <= p_vals[0] <= limit_upper:\n",
+    "                            if not res.get('img') and fallback_img: res['img'] = fallback_img\n",
+    "                            tag = \"(平替)\" if avg_price > limit_upper else \"(升级)\"\n",
+    "                            return res, f\"约 {p_vals[0]}元 {tag}\", current_kw\n",
+    "\n",
+    "    # --- 机制 4: 兜底防御 ---\n",
+    "    print(\"       ⚠️ [机制4触发] 启用强制兜底模式...\")\n",
     "    best_fallback = None\n",
     "    status_msg = \"暂无报价\"\n",
     "    \n",
     "    if all_candidates:\n",
-    "        # 按价格排序，取最低的那个\n",
-    "        best_fallback = sorted(all_candidates, key=lambda x: x['price_val'])[0]\n",
-    "        status_msg = f\"约 {best_fallback['price_val']}元 (⚠️超预算)\"\n",
+    "        # 选离预算最近的\n",
+    "        target = (budget_min + budget_max) / 2\n",
+    "        best_fallback = sorted(all_candidates, key=lambda x: abs(x['price_val'] - target))[0]\n",
+    "        p = best_fallback['price_val']\n",
+    "        \n",
+    "        if p > limit_upper: status_msg = f\"约 {p}元 (⚠️超预算)\"\n",
+    "        elif p < limit_lower: status_msg = f\"约 {p}元 (📉低于预算)\"\n",
+    "        else: status_msg = f\"约 {p}元\"\n",
+    "        \n",
     "    elif results_1:\n",
-    "        # 连价格都没搜到，就硬取第一条文本结果\n",
+    "        # 实在没数据，硬取第一条\n",
     "        for res in results_1:\n",
-    "            if res.get('type') == 'text':\n",
+    "            if res.get('type') == 'text': \n",
     "                best_fallback = res\n",
+    "                # 兜底时如果也没价格，就用原始关键词\n",
+    "                best_fallback['source_kw'] = keyword \n",
     "                break\n",
     "    \n",
     "    if best_fallback:\n",
-    "        # 补图逻辑\n",
     "        if not best_fallback.get('img') and fallback_img:\n",
     "            best_fallback['img'] = fallback_img\n",
-    "        return best_fallback, status_msg, current_kw\n",
     "        \n",
-    "    return None, \"搜索失败\", current_kw\n"
+    "        # 📝【核心修复点2】返回结果里记录的那个 source_kw，而不是当前的 current_kw\n",
+    "        final_name_to_use = best_fallback.get('source_kw', current_kw)\n",
+    "        \n",
+    "        return best_fallback, status_msg, final_name_to_use\n",
+    "        \n",
+    "    return None, \"搜索失败\", keyword"
    ]
   },
   {
@@ -511,17 +598,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# ==========================================\n",
-    "# 🚀 主执行流程\n",
-    "# ==========================================\n",
-    "\n",
     "if not user_input_data:\n",
     "    print(\"❌ 未加载用户数据\")\n",
     "else:\n",
     "    # 0. 解析预算\n",
-    "    budget_min, budget_max = parse_budget_range(user_input_data.get('预算', ''))\n",
-    "    budget_limit = budget_max * 1.2 # 允许超标 20%\n",
-    "    print(f\"\\n💰 预算红线: {budget_max}元 (容忍至 {budget_limit}元)\")\n",
+    "    b_min, b_max = parse_budget_range(user_input_data.get('预算', ''))\n",
+    "    print(f\"\\n💰 预算范围: {b_min} - {b_max}元\")\n",
     "\n",
     "    # 1. 军师制定策略\n",
     "    profile_text = \"\\n\".join([f\"- {k}: {v if v else '未知/不限'}\" for k, v in user_input_data.items()])\n",
@@ -540,8 +622,8 @@
     "    for index, kw in enumerate(keywords):\n",
     "        print(f\"\\n    👉 [商品 {index+1}/{len(keywords)}] 正在处理: {kw}\")\n",
     "        \n",
-    "        # 调用智能搜索函数\n",
-    "        valid_result, price_status, final_kw = find_best_product(hunter, profiler_agent, kw, budget_limit)\n",
+    "        # 调用智能搜索函数 (传入 min 和 max)\n",
+    "        valid_result, price_status, final_kw = find_best_product(hunter, profiler_agent, kw, b_min, b_max)\n",
     "        \n",
     "        if not valid_result:\n",
     "            print(\"       ❌ 彻底无数据，跳过。\")\n",
@@ -550,7 +632,7 @@
     "        # === 生成文案 ===\n",
     "        product_name = valid_result.get('title', final_kw)\n",
     "        \n",
-    "        print(f\"       ✍️ 正在撰写文案: {product_name[:15]}...\")\n",
+    "        print(f\"       ✍️ 正在撰写文案: {product_name[:30]}...\")\n",
     "        pitch_prompt = f\"\"\"\n",
     "        商品：{product_name}\n",
     "        价格：{price_status}\n",
@@ -560,7 +642,6 @@
     "        \"\"\"\n",
     "        pitch = pitcher_agent.run(pitch_prompt)\n",
     "        \n",
-    "        # 整理最终数据\n",
     "        final_items.append({\n",
     "            \"name\": final_kw, \n",
     "            \"title_full\": product_name,\n",
@@ -588,28 +669,46 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# --- 4. 渲染与保存 (保持不变) ---\n",
+    "# --- 4. 渲染与保存 ---\n",
     "print(f\"\\n💾 正在生成最终报告...\")\n",
+    "\n",
     "if not final_items:\n",
     "    final_md = \"很抱歉，网络搜索似乎出现了问题，未能获取到任何商品信息。\"\n",
     "else:\n",
     "    table_header = \"| 🎁 礼物名称 | 💰 价格 | ✨ 种草理由 | 🖼️ 图片/链接 |\\n| :--- | :--- | :--- | :--- |\\n\"\n",
     "    table_rows = []\n",
+    "    \n",
     "    for item in final_items:\n",
-    "        name = item['name'].replace(\"|\", \"/\")\n",
-    "        price = item['price']\n",
-    "        desc = item['desc'].replace(\"|\", \"/\")\n",
-    "        link = item['link']\n",
-    "        img = item['img']\n",
+    "        # 1. 清洗文本字段 (防止 | 破坏表格)\n",
+    "        name = item.get('name', '未知').replace(\"|\", \"/\")\n",
+    "        price = item.get('price', '暂无').replace(\"|\", \"/\")\n",
+    "        desc = item.get('desc', '').replace(\"|\", \"/\")\n",
+    "        \n",
+    "        # 2. 🚨【核心修复】清洗链接中的竖线\n",
+    "        # 百度/京东链接常包含 '|'，必须替换为 '%7C'，否则 Markdown 表格会炸\n",
+    "        raw_link = item.get('link', '#')\n",
+    "        safe_link = raw_link.replace(\"|\", \"%7C\")\n",
     "        \n",
-    "        if img and img.startswith(\"http\"):\n",
-    "            media = f\"[![图]({img})]({link})\"\n",
+    "        raw_img = item.get('img', '')\n",
+    "        safe_img = raw_img.replace(\"|\", \"%7C\")\n",
+    "        \n",
+    "        # 3. 构建媒体列\n",
+    "        if safe_img and safe_img.startswith(\"http\"):\n",
+    "            # 图片链接套购买链接\n",
+    "            media = f\"[![图]({safe_img})]({safe_link})\"\n",
     "        else:\n",
-    "            media = f\"[点击购买]({link})\"\n",
+    "            media = f\"[点击购买]({safe_link})\"\n",
+    "        \n",
+    "        # 4. 组装行 (注意名字上的链接也要用 safe_link)\n",
+    "        # 使用 strip() 去除可能的首尾空格\n",
+    "        row = f\"| [{name}]({safe_link}) | {price} | {desc} | {media} |\"\n",
+    "        table_rows.append(row)\n",
     "        \n",
-    "        table_rows.append(f\"| [{name}]({link}) | {price} | {desc} | {media} |\")\n",
     "    final_md = table_header + \"\\n\".join(table_rows)\n",
     "filename = \"outputs/gift_plan_output.md\"\n",
+    "# 确保输出目录存在\n",
+    "os.makedirs(os.path.dirname(filename), exist_ok=True)\n",
+    "\n",
     "with open(filename, \"w\", encoding=\"utf-8\") as f:\n",
     "    f.write(final_md)\n",
     "print(f\"🎉 任务完成！文件已保存: {os.path.abspath(filename)}\")"
@@ -631,16 +730,20 @@
     "#### 实现的功能\n",
     "- 基于用户输入的个人信息，生成符合预算的礼物建议\n",
     "- 支持用户自定义预算范围、节日、个人喜好等\n",
-    "- 利用搜索引擎获取最新的商品信息和价格\n",
+    "- 支持百度MCP和Tavily API双数据源，利用搜索引擎获取最新的商品信息和价格\n",
     "- 提供可视化的建议结果展示\n",
-    "#### 遇到的挑战\n",
-    "- 如何解决大模型的幻觉问题\n",
-    "- 如何解决上下文过长导致提取失败\n",
-    "- 如何设计合理的提示词，优化大模型的输出\n",
-    "\n",
+    "#### 遇到的挑战与解决方案\n",
+    "- 大模型的“幻觉”问题（JSON格式错误/编造数据）\n",
+    "  - 解决方案：放弃让 LLM 直接生成最终数据。改为使用 Python 正则表达式 从搜索结果中暴力提取硬数据（价格、图片），仅让 LLM 负责生成文案。代码逻辑负责准确性，模型负责创造性。\n",
+    "- 上下文过长导致提取失败\n",
+    "  - 解决方案：结合实际业务场景，分析各个阶段对上下文的要求，在搜索阶段限制返回长度。同时通过拆分 “硬数据流”（找参数）和 “软数据流”（找卖点），大幅降低单次上下文长度，提升响应速度。\n",
+    "- 大模型推荐的礼品价格超出预算\n",
+    "  - 解决方案：引入检核机制。如果搜到的商品均价超预算，系统会自动呼叫“军师”重新制定“平替”策略，直到找到合适商品为止。\n",
+    "- Agent传入的参数格式问题\n",
+    "  - 解决方案：在工具层兼容 Agent 传入的各种参数格式（JSON/字符串、逗号/换行符分隔），确保搜索指令不丢失。\n",
     "#### 未来改进方向\n",
-    "- 前端交互：新增前端页面，提供更好的用户交互体验\n",
-    "- 数据源增强：接入百度或BigGo的MCP Server，获取更精准的实时价格和商品信息\n",
+    "- 前端交互：开发前端页面，替代目前的Notebook交互，提供更好的用户交互体验\n",
+    "- 数据源深度集成：完全接入百度优选MCP 的比价与历史价格接口，获取更精准的实时价格和库存信息，实现“全网比价”\n",
     "- 丰富选项：增加更多的个人喜好选项，如喜欢的商品类型、品牌等\n"
    ]
   }

Co-creation-projects/jack6249-GiftGeniusAgent/outputs/gift_plan_output.md

@@ -1,5 +1,5 @@
 | 🎁 礼物名称 | 💰 价格 | ✨ 种草理由 | 🖼️ 图片/链接 |
 | :--- | :--- | :--- | :--- |
-| [罗技 M720 无线鼠标 2025商务版](https://finance.sina.com.cn/tech/roll/2025-10-01/doc-infskwan1349321.shtml) | 约 711.0元 (⚠️超预算) | 🖱️新款MX Master 3S蓝牙直连，省去接收器烦恼，办公党福音！ | [![图](https://img12.360buyimg.com/n1/jfs/t1/342700/23/8550/37781/68db9c62F3c91cc49/4b2932c48df6f477.jpg)](https://finance.sina.com.cn/tech/roll/2025-10-01/doc-infskwan1349321.shtml) |
-| [Anker 737 移动电源 240W快充](https://www.taobao.com/list/item/dEpRSkN3aG1FZkthNmtza2dNU0ZMQT09.htm) | 约 599.0元 | ⚡安克737充电宝，140W双向快充，大容量可上飞机，出行必备神器！ | [![图](https://gw.alicdn.com/imgextra/i1/844902603/O1CN01AGxtg51V6DnKFmX92_!!844902603.jpg_Q75.jpg_.webp)](https://www.taobao.com/list/item/dEpRSkN3aG1FZkthNmtza2dNU0ZMQT09.htm) |
-| [索尼 WH-CH720N 降噪耳机 2025新色](https://dcdv.zol.com.cn/940/9405436.html) | 约 359.0元 | 🎧索尼CH720N无线降噪耳机，防水设计运动无忧，359元性价比绝了！ | [![图](https://dwfavn5d0m4r1.cloudfront.net/App_Images/750/ChannelProduct/2025/0820/m_bf07ed79-3942-4160-9fc3-abff392844cd.jpg.webp)](https://dcdv.zol.com.cn/940/9405436.html) |
+| [罗技 MX Master 3S 无线鼠标 人体工学](https://union-click.jd.com/jdc?e=0_2_0_NONE%7CMCP&p=JF8BAOEJK1olVQ4FVV5UC08XM28JGloWXwEFVl5ZCHtTXDdWRGtMGENDFlVDFhNSVzMXQA4KD1heSl5cCUoUAWgPGVsRXRlbEQIAOD1yATAAWTxPP2JaPyM5Ci8TVQtjbSsZUTYHVF9cCUMQAmgJK1sUXAQFVVdYCUMnM28JKw17XQcDVV9cCUgSCl8KGloXXQcHUFhUOEsQB2oBH1MRWg4CXF9tCEMTMzxYQw5RH19SCwgcUBQnM18LK2slXTYBZAAzCRgQBmcJEgl7AAMLBgEeSEJ5A2sMHlMWXAQDZFxcCUkVM18) | 约 529.0元 | 🖱️打工人必备！MX Master 3S静音顺滑，人体工学设计，手腕再也不酸了~ | [![图](http://t15.baidu.com/it/u=812867358,1743760388&fm=224&app=112&f=JPEG?w=500&h=500)](https://union-click.jd.com/jdc?e=0_2_0_NONE%7CMCP&p=JF8BAOEJK1olVQ4FVV5UC08XM28JGloWXwEFVl5ZCHtTXDdWRGtMGENDFlVDFhNSVzMXQA4KD1heSl5cCUoUAWgPGVsRXRlbEQIAOD1yATAAWTxPP2JaPyM5Ci8TVQtjbSsZUTYHVF9cCUMQAmgJK1sUXAQFVVdYCUMnM28JKw17XQcDVV9cCUgSCl8KGloXXQcHUFhUOEsQB2oBH1MRWg4CXF9tCEMTMzxYQw5RH19SCwgcUBQnM18LK2slXTYBZAAzCRgQBmcJEgl7AAMLBgEeSEJ5A2sMHlMWXAQDZFxcCUkVM18) |
+| [Anker 737 移动电源 240W 氮化镓](https://union-click.jd.com/jdc?e=0_2_0_NONE%7CMCP&p=JF8BARIJK1olXwICUl1fDU0VAl8IGlsVXwcCXFtYCEsUBV9MRANLAjZbERscSkAJHTdNTwcKBlMdBgABFksWA28KGlsdWAMCVF1bFxJSXzI4Wh9oLQJwNSw4bhtwUA0AcBxoFnhDNFJROE4XAm4JE1wUWgcyVF9cCkwWCmoJE2slXQcyFTBdCUkSCmkMHmsXXAcAVF9YDE0eM28OGF4WWwQDVlZbD0wnA2cMKwhFBVNGFgcNVx1WWzA4K2sWbTYyVG5eOBV5AjwOE14cDQNsCF9YWxRFVzFmHl8RXg8LUl1tCkoWAW04K2tIFARCBAYgaxB-ADBPGllCH3N3VTU-VCN5ATMBZjB9GA5KDyMCCwBBfmZxK14l) | 约 349.0元 | 🔋出差党狂喜！安克65W二合一充电宝，手机笔记本都能充，还能带上飞机~ | [![图](http://t13.baidu.com/it/u=2553962101,2686970068&fm=224&app=112&f=JPEG?w=500&h=500)](https://union-click.jd.com/jdc?e=0_2_0_NONE%7CMCP&p=JF8BARIJK1olXwICUl1fDU0VAl8IGlsVXwcCXFtYCEsUBV9MRANLAjZbERscSkAJHTdNTwcKBlMdBgABFksWA28KGlsdWAMCVF1bFxJSXzI4Wh9oLQJwNSw4bhtwUA0AcBxoFnhDNFJROE4XAm4JE1wUWgcyVF9cCkwWCmoJE2slXQcyFTBdCUkSCmkMHmsXXAcAVF9YDE0eM28OGF4WWwQDVlZbD0wnA2cMKwhFBVNGFgcNVx1WWzA4K2sWbTYyVG5eOBV5AjwOE14cDQNsCF9YWxRFVzFmHl8RXg8LUl1tCkoWAW04K2tIFARCBAYgaxB-ADBPGllCH3N3VTU-VCN5ATMBZjB9GA5KDyMCCwBBfmZxK14l) |
+| [绿联 100W 四口充电器 桌面充电站](https://union-click.jd.com/jdc?e=0_2_0_NONE%7CMCP&p=JF8BAQ0JK1olVQcAVF1YDEsSM28JGl0SWwQKVlxbAE8eMytXQwVKbV9HER8fA1UJWypcR0ROCBlQCgJDCEoWBWgOGVMXXwAKUFdCUQ5LXl9_Q1NBOH9JDj0dQA5wARxrRARWHFNEWFJtDUsWAm4AHFoSXDYCVV9fD0oeBm4AK2sVXDZDOl1dC00SCl8KGloXXQcHUFhUOEsQCmsIHV4WVAEBXFptCEMTMzxYQw5RH19SCwgcUBQnM18LK2slXTYBZAAzCRgRAD0PS117AF4GFVYIDB95A2YJE18RWQMyVl9cCkknM19AWDsUNnRyBBYZSx53YyZDUjlQBkRjVlkzCh1OfT1Xf1tTFXZmNiVbDR9xMw) | 约 599.0元 | 🔌桌面终结者！绿联100W氮化镓充电器，多设备同时快充，告别线材缠绕~ | [![图](http://t13.baidu.com/it/u=1745949773,1204442136&fm=224&app=112&f=JPEG?w=500&h=500)](https://union-click.jd.com/jdc?e=0_2_0_NONE%7CMCP&p=JF8BAQ0JK1olVQcAVF1YDEsSM28JGl0SWwQKVlxbAE8eMytXQwVKbV9HER8fA1UJWypcR0ROCBlQCgJDCEoWBWgOGVMXXwAKUFdCUQ5LXl9_Q1NBOH9JDj0dQA5wARxrRARWHFNEWFJtDUsWAm4AHFoSXDYCVV9fD0oeBm4AK2sVXDZDOl1dC00SCl8KGloXXQcHUFhUOEsQCmsIHV4WVAEBXFptCEMTMzxYQw5RH19SCwgcUBQnM18LK2slXTYBZAAzCRgRAD0PS117AF4GFVYIDB95A2YJE18RWQMyVl9cCkknM19AWDsUNnRyBBYZSx53YyZDUjlQBkRjVlkzCh1OfT1Xf1tTFXZmNiVbDR9xMw) |

Co-creation-projects/jack6249-GiftGeniusAgent/requirements.txt

@@ -1,18 +1,18 @@
-#HelloAgents框架
-
+# HelloAgents框架
 hello-agents[all]>=0.1.0
 
-#LLM与搜索工具
-
+# LLM与搜索工具
 openai
 tavily-python
 numpy
 
-#Jupyter环境
-
+# Jupyter环境 & 异步修补 (新增 nest_asyncio)
 jupyter>=1.0.0
 notebook>=7.0.0
+nest_asyncio>=1.5.0
 
-#环境变量管理
+# 环境变量管理
+python-dotenv>=1.0.0
 
-python-dotenv>=1.0.0
+# MCP 协议支持 (新增 mcp)
+mcp>=0.1.0