Update app.py

app.py

@@ -4,122 +4,29 @@ import json
 import os
 from huggingface_hub import InferenceClient
 
-# ========== 配置两个 MCP 服务 ==========
-MCP_SERVICES = {
-    "financial": {
-        "name": "SEC Financial Reports",
-        "url": "https://jc321-easyreportdatemcp.hf.space/mcp",
-        "type": "fastmcp"  # 标准 FastMCP (HTTP JSON-RPC)
-    },
-    "market": {
-        "name": "Market & Stock Data (Finnhub)",
-        "url": "https://jc321-marketandstockmcp.hf.space",
-        "type": "gradio"  # Gradio API
-    }
-}
-
-# MCP 工具定义（两个服务的工具合并）
+# ========== MCP 工具简化定义(符合MCP协议标准) ==========
 MCP_TOOLS = [
-    # Financial Reports Tools
-    {
-        "type": "function",
-        "function": {
-            "name": "advanced_search_company",
-            "description": "Search for US listed companies by name or ticker to get CIK and basic info",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "company_input": {"type": "string", "description": "Company name or ticker (e.g., 'Apple', 'AAPL')"}
-                },
-                "required": ["company_input"]
-            }
-        }
-    },
-    {
-        "type": "function",
-        "function": {
-            "name": "get_latest_financial_data",
-            "description": "Get latest SEC financial data (revenue, net income, EPS, cash flow, etc.)",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "cik": {"type": "string", "description": "10-digit CIK number"}
-                },
-                "required": ["cik"]
-            }
-        }
-    },
-    {
-        "type": "function",
-        "function": {
-            "name": "extract_financial_metrics",
-            "description": "Get multi-year financial trends (3 or 5 years)",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "cik": {"type": "string", "description": "10-digit CIK number"},
-                    "years": {"type": "integer", "enum": [3, 5]}
-                },
-                "required": ["cik", "years"]
-            }
-        }
-    },
-    # Market & Stock Tools (Finnhub API)
-    {
-        "type": "function",
-        "function": {
-            "name": "get_quote",
-            "description": "Get real-time stock quote (price, volume, change, etc.) for a ticker symbol",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "symbol": {"type": "string", "description": "Stock ticker symbol (e.g., 'AAPL')"}
-                },
-                "required": ["symbol"]
-            }
-        }
-    },
-    {
-        "type": "function",
-        "function": {
-            "name": "get_market_news",
-            "description": "Get latest market news by category (general, forex, crypto, merger)",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "category": {"type": "string", "enum": ["general", "forex", "crypto", "merger"], "description": "News category"},
-                    "min_id": {"type": "integer", "description": "Minimum news ID (optional)"}
-                },
-                "required": ["category"]
-            }
-        }
-    },
-    {
-        "type": "function",
-        "function": {
-            "name": "get_company_news",
-            "description": "Get company-specific news for a stock symbol within a date range",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "symbol": {"type": "string", "description": "Stock ticker symbol (e.g., 'AAPL')"},
-                    "from_date": {"type": "string", "description": "Start date (YYYY-MM-DD, default: 7 days ago)"},
-                    "to_date": {"type": "string", "description": "End date (YYYY-MM-DD, default: today)"}
-                },
-                "required": ["symbol"]
-            }
-        }
-    }
+    {"type": "function", "function": {"name": "advanced_search_company", "description": "Search US companies", "parameters": {"type": "object", "properties": {"company_input": {"type": "string"}}, "required": ["company_input"]}}},
+    {"type": "function", "function": {"name": "get_latest_financial_data", "description": "Get latest financial data", "parameters": {"type": "object", "properties": {"cik": {"type": "string"}}, "required": ["cik"]}}},
+    {"type": "function", "function": {"name": "extract_financial_metrics", "description": "Get multi-year trends", "parameters": {"type": "object", "properties": {"cik": {"type": "string"}, "years": {"type": "integer"}}, "required": ["cik", "years"]}}},
+    {"type": "function", "function": {"name": "get_quote", "description": "Get stock quote", "parameters": {"type": "object", "properties": {"symbol": {"type": "string"}}, "required": ["symbol"]}}},
+    {"type": "function", "function": {"name": "get_market_news", "description": "Get market news", "parameters": {"type": "object", "properties": {"category": {"type": "string"}}, "required": ["category"]}}},
+    {"type": "function", "function": {"name": "get_company_news", "description": "Get company news", "parameters": {"type": "object", "properties": {"symbol": {"type": "string"}, "from_date": {"type": "string"}, "to_date": {"type": "string"}}, "required": ["symbol"]}}}
 ]
 
-# 工具路由:工具名 -> 服务配置
+# ========== MCP 服务配置 ==========
+MCP_SERVICES = {
+    "financial": {"url": "https://jc321-easyreportdatemcp.hf.space/mcp", "type": "fastmcp"},
+    "market": {"url": "https://jc321-marketandstockmcp.hf.space", "type": "gradio"}
+}
+
 TOOL_ROUTING = {
     "advanced_search_company": MCP_SERVICES["financial"],
     "get_latest_financial_data": MCP_SERVICES["financial"],
     "extract_financial_metrics": MCP_SERVICES["financial"],
     "get_quote": MCP_SERVICES["market"],
     "get_market_news": MCP_SERVICES["market"],
-    "get_company_news": MCP_SERVICES["market"],
+    "get_company_news": MCP_SERVICES["market"]
 }
 
 # ========== 初始化 LLM 客户端 ==========
@@ -127,245 +34,151 @@ hf_token = os.environ.get("HF_TOKEN") or os.environ.get("HUGGING_FACE_HUB_TOKEN"
 client = InferenceClient(api_key=hf_token) if hf_token else InferenceClient()
 print(f"✅ LLM initialized: Qwen/Qwen2.5-72B-Instruct:novita")
 print(f"📊 MCP Services: {len(MCP_SERVICES)} services, {len(MCP_TOOLS)} tools")
-print(f"   - Financial: advanced_search_company, get_latest_financial_data, extract_financial_metrics")
-print(f"   - Market: get_quote, get_market_news, get_company_news")
-
-# ========== 系统提示词 ==========
-SYSTEM_PROMPT = """You are an intelligent financial and market analysis assistant.
-
-You have access to TWO data sources:
 
-1. **SEC Financial Reports** (Official filings)
-   - advanced_search_company: Find US companies
-   - get_latest_financial_data: Get latest 10-K/10-Q data
-   - extract_financial_metrics: Get multi-year trends
+# ========== 系统提示词(简化) ==========
+SYSTEM_PROMPT = """You are a financial analysis assistant. Use tools to get data on company financials (past 5-year reports), current stock prices, market news, and company news. Provide data-driven insights."""
 
-2. **Market & Stock Data** (Finnhub real-time)
-   - get_quote: Real-time stock price, volume, change
-   - get_market_news: Latest market news (general/forex/crypto/merger)
-   - get_company_news: Company-specific news
+# ============================================================
+# MCP 服务调用核心代码区
+# 支持 FastMCP (JSON-RPC) 和 Gradio (SSE) 两种协议
+# ============================================================
 
-Automatically use the right tools and provide clear, data-driven insights."""
-
-# ========== 核心函数:调用 MCP 工具 ==========
 def call_mcp_tool(tool_name, arguments):
-    """调用 MCP 工具(支持 FastMCP 和 Gradio 两种协议)"""
+    """调用 MCP 工具"""
     service_config = TOOL_ROUTING.get(tool_name)
     if not service_config:
         return {"error": f"Unknown tool: {tool_name}"}
     
-    service_type = service_config["type"]
-    service_url = service_config["url"]
-    
-    print(f"\n[DEBUG] Calling tool: {tool_name}")
-    print(f"[DEBUG] Service type: {service_type}, URL: {service_url}")
-    
     try:
-        if service_type == "fastmcp":
-            # FastMCP: 标准 MCP JSON-RPC 协议
-            return _call_fastmcp(service_url, tool_name, arguments)
-        elif service_type == "gradio":
-            # Gradio: Gradio API 协议
-            return _call_gradio_api(service_url, tool_name, arguments)
+        if service_config["type"] == "fastmcp":
+            return _call_fastmcp(service_config["url"], tool_name, arguments)
+        elif service_config["type"] == "gradio":
+            return _call_gradio_api(service_config["url"], tool_name, arguments)
         else:
-            return {"error": f"Unknown service type: {service_type}"}
-    
+            return {"error": "Unknown service type"}
     except Exception as e:
-        error_msg = f"Exception: {str(e)}"
-        print(f"[DEBUG] {error_msg}")
-        return {"error": error_msg}
+        return {"error": str(e)}
 
 
 def _call_fastmcp(service_url, tool_name, arguments):
-    """\u8c03\u7528 FastMCP \u670d\u52a1 (\u6807\u51c6 MCP JSON-RPC \u534f\u8bae)"""
+    """FastMCP: 标准 MCP JSON-RPC"""
     response = requests.post(
         service_url,
-        json={
-            "jsonrpc": "2.0",
-            "method": "tools/call",
-            "params": {"name": tool_name, "arguments": arguments},
-            "id": 1
-        },
+        json={"jsonrpc": "2.0", "method": "tools/call", "params": {"name": tool_name, "arguments": arguments}, "id": 1},
         headers={"Content-Type": "application/json"},
-        timeout=60
+        timeout=30
     )
     
-    if response.status_code == 200:
-        data = response.json()
-        print(f"[DEBUG] FastMCP raw response: {json.dumps(data, ensure_ascii=False)[:500]}")
-        
-        # 解包 JSON-RPC 响应
-        if isinstance(data, dict) and "result" in data:
-            result = data["result"]
-            
-            # MCP 协议格式: {"content": [{"type": "text", "text": "..."}]}
-            if isinstance(result, dict) and "content" in result:
-                content = result["content"]
-                
-                # 提取第一个 content item 的 text
-                if isinstance(content, list) and len(content) > 0:
-                    first_item = content[0]
-                    if isinstance(first_item, dict) and "text" in first_item:
-                        text_data = first_item["text"]
-                        
-                        # text 可能是 JSON 字符串,尝试解析
-                        try:
-                            parsed_data = json.loads(text_data)
-                            print(f"[DEBUG] Parsed data: {json.dumps(parsed_data, ensure_ascii=False)[:300]}")
-                            return parsed_data
-                        except (json.JSONDecodeError, TypeError):
-                            # 如果不是 JSON,直接返回文本
-                            print(f"[DEBUG] Returning text as-is")
-                            return {"text": text_data}
-            
-            # 如果不是 content 格式,直接返回 result
-            print(f"[DEBUG] Returning result directly")
-            return result
-        
-        # 如果没有 result 字段,返回整个响应
-        print(f"[DEBUG] No result field, returning full response")
-        return data
-    else:
-        error_msg = f"HTTP {response.status_code}: {response.text[:200]}"
-        print(f"[DEBUG] {error_msg}")
-        return {"error": error_msg}
+    if response.status_code != 200:
+        return {"error": f"HTTP {response.status_code}"}
+    
+    data = response.json()
+    
+    # 解包 MCP 协议: jsonrpc -> result -> content[0].text -> JSON
+    if isinstance(data, dict) and "result" in data:
+        result = data["result"]
+        if isinstance(result, dict) and "content" in result:
+            content = result["content"]
+            if isinstance(content, list) and len(content) > 0:
+                first_item = content[0]
+                if isinstance(first_item, dict) and "text" in first_item:
+                    try:
+                        return json.loads(first_item["text"])
+                    except (json.JSONDecodeError, TypeError):
+                        return {"text": first_item["text"]}
+        return result
+    return data
 
 
 def _call_gradio_api(service_url, tool_name, arguments):
-    """\u8c03\u7528 Gradio API (Gradio \u5185\u7f6e MCP \u670d\u52a1)"""
-    # Gradio API 工具名映射
-    gradio_tool_map = {
-        "get_quote": "test_quote_tool",
-        "get_market_news": "test_market_news_tool",
-        "get_company_news": "test_company_news_tool"
-    }
-    
-    gradio_fn_name = gradio_tool_map.get(tool_name)
-    if not gradio_fn_name:
-        return {"error": f"No Gradio mapping for tool: {tool_name}"}
+    """Gradio: SSE 流式协议"""
+    tool_map = {"get_quote": "test_quote_tool", "get_market_news": "test_market_news_tool", "get_company_news": "test_company_news_tool"}
+    gradio_fn = tool_map.get(tool_name)
+    if not gradio_fn:
+        return {"error": "No mapping"}
     
-    # 步骤1: 提交调用请求
-    call_url = f"{service_url}/call/{gradio_fn_name}"
-    
-    # 构造 Gradio API 参数格式
+    # 构造参数
     if tool_name == "get_quote":
-        data_params = [arguments.get("symbol", "")]
+        params = [arguments.get("symbol", "")]
     elif tool_name == "get_market_news":
-        data_params = [arguments.get("category", "general")]
+        params = [arguments.get("category", "general")]
     elif tool_name == "get_company_news":
-        data_params = [
-            arguments.get("symbol", ""),
-            arguments.get("from_date", ""),
-            arguments.get("to_date", "")
-        ]
+        params = [arguments.get("symbol", ""), arguments.get("from_date", ""), arguments.get("to_date", "")]
     else:
-        data_params = []
-    
-    print(f"[DEBUG] Gradio call URL: {call_url}")
-    print(f"[DEBUG] Gradio data params: {data_params}")
+        params = []
     
     # 提交请求
-    response = requests.post(
-        call_url,
-        json={"data": data_params},
-        headers={"Content-Type": "application/json"},
-        timeout=10
-    )
-    
-    if response.status_code != 200:
-        return {"error": f"Gradio call failed: HTTP {response.status_code}"}
-    
-    call_data = response.json()
-    event_id = call_data.get("event_id")
+    call_url = f"{service_url}/call/{gradio_fn}"
+    resp = requests.post(call_url, json={"data": params}, timeout=10)
+    if resp.status_code != 200:
+        return {"error": f"HTTP {resp.status_code}"}
     
+    event_id = resp.json().get("event_id")
     if not event_id:
-        return {"error": "No event_id returned from Gradio"}
-    
-    print(f"[DEBUG] Got event_id: {event_id}")
-    
-    # 步骤2: 轮询获取结果 (SSE ��)
-    result_url = f"{call_url}/{event_id}"
-    result_response = requests.get(result_url, stream=True, timeout=30)
-    
-    if result_response.status_code != 200:
-        return {"error": f"Failed to get result: HTTP {result_response.status_code}"}
+        return {"error": "No event_id"}
     
-    # 解析 SSE 流
-    result_text = ""
-    for line in result_response.iter_lines():
-        if line:
-            line_str = line.decode('utf-8')
-            if line_str.startswith('data: '):
-                data_part = line_str[6:]  # 移除 'data: ' 前缀
-                try:
-                    result_data = json.loads(data_part)
-                    if isinstance(result_data, list) and len(result_data) > 0:
-                        result_text = result_data[0]
-                        print(f"[DEBUG] Gradio result: {result_text[:200]}")
-                        break
-                except json.JSONDecodeError:
-                    continue
+    # 获取结果 (SSE)
+    result_resp = requests.get(f"{call_url}/{event_id}", stream=True, timeout=20)
+    if result_resp.status_code != 200:
+        return {"error": f"HTTP {result_resp.status_code}"}
     
-    if not result_text:
-        return {"error": "No result received from Gradio"}
+    # 解析 SSE
+    for line in result_resp.iter_lines():
+        if line and line.decode('utf-8').startswith('data: '):
+            try:
+                result_data = json.loads(line.decode('utf-8')[6:])
+                if isinstance(result_data, list) and len(result_data) > 0:
+                    return {"text": result_data[0]}
+            except json.JSONDecodeError:
+                continue
     
-    # 返回统一格式
-    return {"text": result_text, "_source": "gradio_api"}
+    return {"error": "No result"}
+
+# ============================================================
+# End of MCP 服务调用代码区
+# ============================================================
 
-# ========== 核心函数:AI 助手 ==========
 def chatbot_response(message, history):
-    """AI 助手主函数(流式输出)"""
+    """AI 助手主函数(流式输出,性能优化)"""
     try:
-        # 构建消息历史
         messages = [{"role": "system", "content": SYSTEM_PROMPT}]
         
-        # 添加对话历史(最近5轮)
+        # 添加历史(最近3轮)
         if history:
-            for item in history[-5:]:
-                if isinstance(item, dict):
-                    messages.append(item)
-                elif isinstance(item, (list, tuple)) and len(item) == 2:
-                    user_msg, assistant_msg = item
-                    messages.append({"role": "user", "content": user_msg})
-                    messages.append({"role": "assistant", "content": assistant_msg})
+            for item in history[-3:]:
+                if isinstance(item, (list, tuple)) and len(item) == 2:
+                    messages.append({"role": "user", "content": item[0]})
+                    messages.append({"role": "assistant", "content": item[1]})
         
         messages.append({"role": "user", "content": message})
         
-        # 工具调用日志和响应前缀
         tool_calls_log = []
-        response_prefix = ""
-        max_iterations = 5
         
-        # LLM 调用循环(支持多轮工具调用)
-        for iteration in range(max_iterations):
-            # 调用 LLM(非流式,用于工具调用判断)
+        # LLM 调用循环(最多3轮工具调用)
+        for iteration in range(3):
             response = client.chat_completion(
                 messages=messages,
                 model="Qwen/Qwen2.5-72B-Instruct:novita",
                 tools=MCP_TOOLS,
-                max_tokens=3000,
-                temperature=0.7,
+                max_tokens=2000,
+                temperature=0.5,
                 tool_choice="auto",
                 stream=False
             )
             
             choice = response.choices[0]
             
-            # 检查是否有工具调用
             if choice.message.tool_calls:
                 messages.append(choice.message)
                 
                 for tool_call in choice.message.tool_calls:
                     tool_name = tool_call.function.name
                     tool_args = json.loads(tool_call.function.arguments)
-                    
-                    # 记录工具调用
                     tool_calls_log.append({"name": tool_name, "arguments": tool_args})
                     
                     # 调用 MCP 工具
                     tool_result = call_mcp_tool(tool_name, tool_args)
                     
-                    # 添加工具结果到消息
                     messages.append({
                         "role": "tool",
                         "name": tool_name,
@@ -373,56 +186,45 @@ def chatbot_response(message, history):
                         "tool_call_id": tool_call.id
                     })
                 
-                continue  # 继续下一轮
+                continue
             else:
-                # 无工具调用,准备���式输出最终答案
                 break
         
-        # 构建响应前缀(模型信息+工具调用)
-        response_prefix += "<div style='padding: 10px; background: linear-gradient(135deg, #667eea 0%, #764ba2 100%); border-radius: 8px; margin-bottom: 12px; box-shadow: 0 2px 8px rgba(0,0,0,0.1);'>\n"
-        response_prefix += "<div style='color: white; font-size: 0.95em; font-weight: 500;'>🤖 <strong>Model:</strong> Qwen/Qwen2.5-72B-Instruct:novita</div>\n"
+        # 构建响应前缀
+        response_prefix = "<div style='padding: 8px; background: linear-gradient(135deg, #667eea 0%, #764ba2 100%); border-radius: 6px; margin-bottom: 10px;'>\n"
+        response_prefix += "<span style='color: white; font-size: 0.9em;'>🤖 <strong>Qwen2.5-72B</strong></span>\n"
         response_prefix += "</div>\n\n"
         
-        # 显示工具调用日志(精致卡片样式)
+        # 显示工具调用
         if tool_calls_log:
-            response_prefix += "<div style='background: #f8f9fa; border-radius: 8px; padding: 12px; margin-bottom: 16px; border: 1px solid #e9ecef;'>\n"
-            response_prefix += "<div style='font-weight: 600; color: #495057; margin-bottom: 10px; font-size: 1em;'>🛠️ MCP Tools Used</div>\n"
+            response_prefix += "<div style='background: #f8f9fa; border-radius: 6px; padding: 10px; margin-bottom: 12px;'>\n"
+            response_prefix += "<div style='font-weight: 600; color: #495057; margin-bottom: 8px;'>🛠️ Tools Used</div>\n"
             
-            for i, tool_call in enumerate(tool_calls_log, 1):
-                # 工具图标映射
-                tool_icons = {
-                    "advanced_search_company": "🔍",
-                    "get_latest_financial_data": "📊",
-                    "extract_financial_metrics": "📈",
-                    "get_quote": "💹",
-                    "get_market_news": "📰",
-                    "get_company_news": "📢"
-                }
+            tool_icons = {"advanced_search_company": "🔍", "get_latest_financial_data": "📊", "extract_financial_metrics": "📈", 
+                         "get_quote": "💹", "get_market_news": "📰", "get_company_news": "📢"}
+            
+            for tool_call in tool_calls_log:
                 icon = tool_icons.get(tool_call['name'], "⚙️")
-                
-                response_prefix += f"<div style='background: white; padding: 8px 12px; margin: 6px 0; border-radius: 6px; border-left: 3px solid #28a745; font-size: 0.9em;'>\n"
+                response_prefix += f"<div style='background: white; padding: 6px 10px; margin: 4px 0; border-radius: 4px; border-left: 3px solid #28a745;'>\n"
                 response_prefix += f"<span style='color: #28a745; font-weight: 600;'>{icon} {tool_call['name']}</span>\n"
-                response_prefix += f"<div style='color: #6c757d; margin-top: 4px; font-family: monospace; font-size: 0.85em;'>{json.dumps(tool_call['arguments'], ensure_ascii=False)}</div>\n"
                 response_prefix += "</div>\n"
             
             response_prefix += "</div>\n\n"
-            response_prefix += "<div style='border-top: 2px solid #dee2e6; margin: 16px 0;'></div>\n\n"
         
         # 流式输出最终答案
         yield response_prefix
         
-        # 流式调用 LLM
         stream = client.chat_completion(
             messages=messages,
             model="Qwen/Qwen2.5-72B-Instruct:novita",
-            max_tokens=3000,
-            temperature=0.7,
+            max_tokens=2000,
+            temperature=0.5,
             stream=True
         )
         
         accumulated_text = ""
         for chunk in stream:
-            if chunk.choices[0].delta.content:
+            if chunk.choices and len(chunk.choices) > 0 and chunk.choices[0].delta.content:
                 accumulated_text += chunk.choices[0].delta.content
                 yield response_prefix + accumulated_text