fix: 添加工作流

examples/jsonrpc_client_demo.py

@@ -0,0 +1,279 @@
+#!/usr/bin/env python3
+"""
+JSON-RPC Client Demo
+JSON-RPC 客户端演示
+
+演示如何使用Python客户端调用场景检测JSON-RPC API
+"""
+
+import json
+import requests
+import time
+from typing import Dict, Any, Optional
+
+
+class SceneDetectionClient:
+    """场景检测JSON-RPC客户端"""
+    
+    def __init__(self, server_url: str = "http://localhost:8080"):
+        self.server_url = server_url
+        self.request_id = 0
+    
+    def _call_method(self, method: str, params: Dict[str, Any]) -> Dict[str, Any]:
+        """调用JSON-RPC方法"""
+        self.request_id += 1
+        
+        payload = {
+            "jsonrpc": "2.0",
+            "method": method,
+            "params": params,
+            "id": self.request_id
+        }
+        
+        try:
+            response = requests.post(
+                self.server_url,
+                json=payload,
+                headers={'Content-Type': 'application/json'},
+                timeout=60
+            )
+            
+            if response.status_code == 200:
+                return response.json()
+            else:
+                return {
+                    "error": {
+                        "code": response.status_code,
+                        "message": f"HTTP Error: {response.text}"
+                    }
+                }
+                
+        except requests.exceptions.RequestException as e:
+            return {
+                "error": {
+                    "code": -1,
+                    "message": f"Request failed: {str(e)}"
+                }
+            }
+    
+    def detect_scenes(self, video_path: str, detector_type: str = "content", 
+                     threshold: float = 30.0, min_scene_length: float = 1.0) -> Dict[str, Any]:
+        """基础场景检测"""
+        params = {
+            "video_path": video_path,
+            "detector_type": detector_type,
+            "threshold": threshold,
+            "min_scene_length": min_scene_length
+        }
+        
+        return self._call_method("scene.detect", params)
+    
+    def detect_scenes_workflow(self, video_path: str, detector_type: str = "content",
+                              threshold: float = 30.0, min_scene_length: float = 1.0,
+                              output_path: Optional[str] = None, output_format: str = "json",
+                              enable_ai_analysis: bool = True) -> Dict[str, Any]:
+        """LangGraph工作流场景检测"""
+        params = {
+            "video_path": video_path,
+            "detector_type": detector_type,
+            "threshold": threshold,
+            "min_scene_length": min_scene_length,
+            "enable_ai_analysis": enable_ai_analysis
+        }
+        
+        if output_path:
+            params["output_path"] = output_path
+            params["output_format"] = output_format
+        
+        return self._call_method("scene.detect_workflow", params)
+    
+    def get_video_info(self, video_path: str) -> Dict[str, Any]:
+        """获取视频信息"""
+        params = {"video_path": video_path}
+        return self._call_method("scene.get_video_info", params)
+    
+    def batch_detect(self, directory: str, detector_type: str = "content",
+                    threshold: float = 30.0, min_scene_length: float = 1.0,
+                    output_dir: Optional[str] = None, output_format: str = "json") -> Dict[str, Any]:
+        """批量场景检测"""
+        params = {
+            "directory": directory,
+            "detector_type": detector_type,
+            "threshold": threshold,
+            "min_scene_length": min_scene_length,
+            "output_format": output_format
+        }
+        
+        if output_dir:
+            params["output_dir"] = output_dir
+        
+        return self._call_method("scene.batch_detect", params)
+
+
+def demo_basic_detection():
+    """演示基础场景检测"""
+    print("🎯 基础场景检测演示")
+    print("=" * 50)
+    
+    client = SceneDetectionClient("http://localhost:8081")
+    
+    # 测试视频路径
+    video_path = "assets/1/1752032011698.mp4"
+    
+    print(f"📹 检测视频: {video_path}")
+    
+    # 调用基础检测
+    start_time = time.time()
+    result = client.detect_scenes(video_path, threshold=15.0)
+    end_time = time.time()
+    
+    if "error" in result:
+        print(f"❌ 检测失败: {result['error']}")
+        return
+    
+    detection_result = result.get("result", {})
+    
+    if detection_result.get("success"):
+        print(f"✅ 检测成功!")
+        print(f"   场景数量: {detection_result['total_scenes']}")
+        print(f"   视频时长: {detection_result['total_duration']:.2f}秒")
+        print(f"   检测时间: {detection_result['detection_time']:.2f}秒")
+        print(f"   API调用时间: {end_time - start_time:.2f}秒")
+        
+        # 显示场景详情
+        scenes = detection_result.get("scenes", [])
+        print(f"\n🎬 场景详情:")
+        for scene in scenes[:5]:  # 只显示前5个
+            print(f"   场景 {scene['index']}: {scene['start_time']:.2f}s - {scene['end_time']:.2f}s")
+        
+        if len(scenes) > 5:
+            print(f"   ... 还有 {len(scenes) - 5} 个场景")
+    else:
+        print(f"❌ 检测失败: {detection_result.get('error', '未知错误')}")
+
+
+def demo_workflow_detection():
+    """演示工作流场景检测"""
+    print("\n🔄 LangGraph工作流检测演示")
+    print("=" * 50)
+    
+    client = SceneDetectionClient("http://localhost:8081")
+    
+    # 测试视频路径
+    video_path = "assets/1/1752032011698.mp4"
+    
+    print(f"📹 检测视频: {video_path}")
+    
+    # 调用工作流检测
+    start_time = time.time()
+    result = client.detect_scenes_workflow(
+        video_path, 
+        threshold=15.0, 
+        enable_ai_analysis=False  # 禁用AI分析以避免API密钥问题
+    )
+    end_time = time.time()
+    
+    if "error" in result:
+        print(f"❌ 工作流检测失败: {result['error']}")
+        return
+    
+    workflow_result = result.get("result", {})
+    detection_result = workflow_result.get("detection_result", {})
+    video_info = workflow_result.get("video_info", {})
+    ai_analysis = workflow_result.get("ai_analysis")
+    workflow_state = workflow_result.get("workflow_state")
+    
+    if detection_result.get("success"):
+        print(f"✅ 工作流检测成功!")
+        print(f"   工作流状态: {workflow_state}")
+        print(f"   场景数量: {detection_result['total_scenes']}")
+        print(f"   检测时间: {detection_result['detection_time']:.2f}秒")
+        print(f"   API调用时间: {end_time - start_time:.2f}秒")
+        
+        # 显示视频信息
+        if video_info:
+            print(f"\n📹 视频信息:")
+            print(f"   分辨率: {video_info.get('resolution')}")
+            print(f"   帧率: {video_info.get('fps'):.2f} fps")
+            print(f"   时长: {video_info.get('duration'):.2f}秒")
+        
+        # 显示AI分析结果
+        if ai_analysis:
+            print(f"\n🧠 AI分析: {ai_analysis}")
+    else:
+        print(f"❌ 工作流检测失败: {detection_result.get('error', '未知错误')}")
+
+
+def demo_video_info():
+    """演示获取视频信息"""
+    print("\n📊 视频信息获取演示")
+    print("=" * 50)
+    
+    client = SceneDetectionClient("http://localhost:8081")
+    
+    # 测试视频路径
+    video_path = "assets/1/1752032011698.mp4"
+    
+    print(f"📹 获取视频信息: {video_path}")
+    
+    # 获取视频信息
+    start_time = time.time()
+    result = client.get_video_info(video_path)
+    end_time = time.time()
+    
+    if "error" in result:
+        print(f"❌ 获取失败: {result['error']}")
+        return
+    
+    info_result = result.get("result", {})
+    
+    if info_result.get("success"):
+        info = info_result.get("info", {})
+        print(f"✅ 获取成功!")
+        print(f"   文件名: {info.get('filename')}")
+        print(f"   分辨率: {info.get('resolution')}")
+        print(f"   帧率: {info.get('fps'):.2f} fps")
+        print(f"   总帧数: {info.get('frame_count'):,}")
+        print(f"   时长: {info.get('duration'):.2f}秒")
+        print(f"   文件大小: {info.get('file_size'):,} 字节")
+        print(f"   API调用时间: {end_time - start_time:.2f}秒")
+    else:
+        print(f"❌ 获取失败: {info_result.get('error', '未知错误')}")
+
+
+def main():
+    """主演示函数"""
+    print("🚀 JSON-RPC 场景检测客户端演示")
+    print("=" * 60)
+    
+    # 检查服务器连接
+    client = SceneDetectionClient("http://localhost:8081")
+    
+    try:
+        # 简单的连接测试
+        test_result = client.get_video_info("nonexistent.mp4")
+        if "error" in test_result and "Request failed" in str(test_result["error"]):
+            print("❌ 无法连接到JSON-RPC服务器")
+            print("💡 请先启动服务器: python3 -m python_core.cli jsonrpc start --port 8081")
+            return
+    except Exception as e:
+        print(f"❌ 连接测试失败: {e}")
+        return
+    
+    print("✅ 服务器连接正常")
+    
+    # 运行演示
+    demo_video_info()
+    demo_basic_detection()
+    demo_workflow_detection()
+    
+    print("\n🎉 演示完成!")
+    print("\n💡 更多用法:")
+    print("   • 调整检测阈值以获得不同的场景分割效果")
+    print("   • 使用不同的检测器类型 (content/threshold/adaptive)")
+    print("   • 启用AI分析获得智能建议 (需要配置API密钥)")
+    print("   • 批量处理多个视频文件")
+
+
+if __name__ == "__main__":
+    main()

python_core/cli/cli.py

@@ -11,6 +11,7 @@ import typer
 
 # 导入命令模块
 from python_core.cli.commands import scene_app
+from python_core.cli.commands.jsonrpc_server import jsonrpc_app
 
 app = typer.Typer(
     name="mixvideo",
@@ -28,13 +29,15 @@ app = typer.Typer(
         mixvideo scene batch-detect /videos    # 批量检测
         mixvideo scene split video.mp4         # 分割视频
         mixvideo scene info video.mp4          # 视频信息
+        mixvideo jsonrpc start                 # 启动JSON-RPC服务器
     """,
     rich_markup_mode="rich",
     no_args_is_help=True
 )
 
-# 添加场景检测命令组到主应用
+# 添加命令组到主应用
 app.add_typer(scene_app, name="scene")
+app.add_typer(jsonrpc_app, name="jsonrpc")
 
 @app.command()
 def init():

python_core/cli/commands/jsonrpc_server.py

@@ -0,0 +1,303 @@
+#!/usr/bin/env python3
+"""
+JSON-RPC Server Command
+JSON-RPC 服务器命令
+
+Provides HTTP and WebSocket JSON-RPC server for scene detection services.
+"""
+
+from pathlib import Path
+from typing import Optional
+import signal
+import sys
+
+import typer
+from python_core.cli.const import console
+from python_core.utils.jsonrpc_server import JSONRPCServer, JSONRPCWebSocketServer, ServerConfig
+
+# 创建子应用
+jsonrpc_app = typer.Typer(help="🌐 JSON-RPC 服务器")
+
+
+@jsonrpc_app.command()
+def start(
+    host: str = typer.Option("localhost", help="🌐 服务器主机地址"),
+    port: int = typer.Option(8080, help="🔌 服务器端口"),
+    debug: bool = typer.Option(False, help="🐛 启用调试模式"),
+    cors: bool = typer.Option(True, help="🔗 启用CORS支持"),
+    websocket: bool = typer.Option(False, help="🔌 启用WebSocket服务器"),
+    max_request_size: int = typer.Option(1024*1024, help="📦 最大请求大小（字节）")
+):
+    """🚀 启动JSON-RPC服务器"""
+    
+    config = ServerConfig(
+        host=host,
+        port=port,
+        debug=debug,
+        cors_enabled=cors,
+        max_request_size=max_request_size
+    )
+    
+    console.print(f"🚀 [bold blue]启动JSON-RPC服务器[/bold blue]")
+    console.print(f"📍 地址: {host}:{port}")
+    console.print(f"🔧 模式: {'WebSocket' if websocket else 'HTTP'}")
+    console.print(f"🐛 调试: {'启用' if debug else '禁用'}")
+    console.print(f"🔗 CORS: {'启用' if cors else '禁用'}")
+
+    # 导入并注册所有JSON-RPC方法
+    console.print("📋 注册JSON-RPC方法...")
+    try:
+        # 导入场景检测模块以注册方法
+        from python_core.cli.scene_detect import detector
+        console.print("✅ 场景检测方法已注册")
+    except Exception as e:
+        console.print(f"⚠️ 注册方法时出错: {e}")
+
+    try:
+        if websocket:
+            # WebSocket服务器
+            import asyncio
+            
+            server = JSONRPCWebSocketServer(config)
+            
+            # 注册信号处理
+            def signal_handler(sig, frame):
+                console.print("\n🛑 [yellow]收到停止信号，正在关闭服务器...[/yellow]")
+                sys.exit(0)
+            
+            signal.signal(signal.SIGINT, signal_handler)
+            signal.signal(signal.SIGTERM, signal_handler)
+            
+            # 启动异步服务器
+            asyncio.run(server.start())
+            
+        else:
+            # HTTP服务器
+            server = JSONRPCServer(config)
+            
+            # 注册信号处理
+            def signal_handler(sig, frame):
+                console.print("\n🛑 [yellow]收到停止信号，正在关闭服务器...[/yellow]")
+                server.stop()
+                sys.exit(0)
+            
+            signal.signal(signal.SIGINT, signal_handler)
+            signal.signal(signal.SIGTERM, signal_handler)
+            
+            # 启动服务器
+            server.start(blocking=True)
+            
+    except Exception as e:
+        console.print(f"❌ [red]服务器启动失败: {e}[/red]")
+        raise typer.Exit(1)
+
+
+@jsonrpc_app.command()
+def test(
+    host: str = typer.Option("localhost", help="🌐 服务器主机地址"),
+    port: int = typer.Option(8080, help="🔌 服务器端口"),
+    method: str = typer.Option("scene.detect", help="🎯 测试方法名"),
+    video_path: Optional[str] = typer.Option(None, help="📹 测试视频路径")
+):
+    """🧪 测试JSON-RPC服务器"""
+    
+    import requests
+    import json
+    
+    if not video_path:
+        video_path = "assets/1/1752032011698.mp4"  # 默认测试视频
+    
+    console.print(f"🧪 [bold blue]测试JSON-RPC服务器[/bold blue]")
+    console.print(f"📍 服务器: http://{host}:{port}")
+    console.print(f"🎯 方法: {method}")
+    console.print(f"📹 视频: {video_path}")
+    
+    # 准备测试请求
+    test_requests = {
+        "scene.detect": {
+            "video_path": video_path,
+            "detector_type": "content",
+            "threshold": 30.0,
+            "min_scene_length": 1.0
+        },
+        "scene.get_video_info": {
+            "video_path": video_path
+        },
+        "scene.detect_workflow": {
+            "video_path": video_path,
+            "detector_type": "content",
+            "threshold": 15.0,
+            "enable_ai_analysis": False
+        }
+    }
+    
+    params = test_requests.get(method, {"video_path": video_path})
+    
+    payload = {
+        "jsonrpc": "2.0",
+        "method": method,
+        "params": params,
+        "id": 1
+    }
+    
+    try:
+        console.print("📤 发送请求...")
+        response = requests.post(
+            f"http://{host}:{port}",
+            json=payload,
+            headers={'Content-Type': 'application/json'},
+            timeout=30
+        )
+        
+        console.print(f"📥 响应状态: {response.status_code}")
+        
+        if response.status_code == 200:
+            result = response.json()
+            console.print("✅ [green]请求成功[/green]")
+            console.print("📋 响应内容:")
+            console.print(json.dumps(result, indent=2, ensure_ascii=False))
+        else:
+            console.print(f"❌ [red]请求失败: {response.text}[/red]")
+            
+    except requests.exceptions.ConnectionError:
+        console.print(f"❌ [red]无法连接到服务器 http://{host}:{port}[/red]")
+        console.print("💡 请确保服务器已启动")
+        raise typer.Exit(1)
+    except Exception as e:
+        console.print(f"❌ [red]测试失败: {e}[/red]")
+        raise typer.Exit(1)
+
+
+@jsonrpc_app.command()
+def methods():
+    """📋 列出可用的JSON-RPC方法"""
+    
+    console.print("📋 [bold blue]可用的JSON-RPC方法[/bold blue]")
+    console.print("=" * 60)
+    
+    methods_info = [
+        {
+            "method": "scene.detect",
+            "description": "基础场景检测",
+            "params": ["video_path", "detector_type?", "threshold?", "min_scene_length?"]
+        },
+        {
+            "method": "scene.detect_workflow", 
+            "description": "LangGraph工作流场景检测",
+            "params": ["video_path", "detector_type?", "threshold?", "min_scene_length?", 
+                      "output_path?", "output_format?", "enable_ai_analysis?"]
+        },
+        {
+            "method": "scene.get_video_info",
+            "description": "获取视频信息",
+            "params": ["video_path"]
+        },
+        {
+            "method": "scene.batch_detect",
+            "description": "批量场景检测",
+            "params": ["directory", "detector_type?", "threshold?", "min_scene_length?",
+                      "output_dir?", "output_format?"]
+        }
+    ]
+    
+    for info in methods_info:
+        console.print(f"\n🎯 [bold]{info['method']}[/bold]")
+        console.print(f"   📝 {info['description']}")
+        console.print(f"   📋 参数: {', '.join(info['params'])}")
+    
+    console.print("\n💡 [yellow]参数说明:[/yellow]")
+    console.print("   • ? 表示可选参数")
+    console.print("   • detector_type: content/threshold/adaptive")
+    console.print("   • output_format: json/csv/txt")
+    console.print("   • threshold: 0-100")
+
+
+@jsonrpc_app.command()
+def client_example():
+    """📖 显示客户端调用示例"""
+    
+    console.print("📖 [bold blue]JSON-RPC 客户端调用示例[/bold blue]")
+    console.print("=" * 60)
+    
+    examples = [
+        {
+            "title": "Python requests 示例",
+            "code": '''import requests
+import json
+
+def call_scene_detect(video_path, threshold=30.0):
+    payload = {
+        "jsonrpc": "2.0",
+        "method": "scene.detect",
+        "params": {
+            "video_path": video_path,
+            "threshold": threshold
+        },
+        "id": 1
+    }
+    
+    response = requests.post(
+        "http://localhost:8080",
+        json=payload,
+        headers={'Content-Type': 'application/json'}
+    )
+    
+    return response.json()
+
+# 调用示例
+result = call_scene_detect("video.mp4", 15.0)
+print(result)'''
+        },
+        {
+            "title": "curl 命令示例",
+            "code": '''curl -X POST http://localhost:8080 \\
+  -H "Content-Type: application/json" \\
+  -d '{
+    "jsonrpc": "2.0",
+    "method": "scene.detect",
+    "params": {
+      "video_path": "video.mp4",
+      "threshold": 15.0
+    },
+    "id": 1
+  }'
+'''
+        },
+        {
+            "title": "JavaScript fetch 示例",
+            "code": '''async function detectScenes(videoPath, threshold = 30.0) {
+    const response = await fetch('http://localhost:8080', {
+        method: 'POST',
+        headers: {
+            'Content-Type': 'application/json',
+        },
+        body: JSON.stringify({
+            jsonrpc: '2.0',
+            method: 'scene.detect',
+            params: {
+                video_path: videoPath,
+                threshold: threshold
+            },
+            id: 1
+        })
+    });
+    
+    return await response.json();
+}
+
+// 调用示例
+detectScenes('video.mp4', 15.0).then(result => {
+    console.log(result);
+});'''
+        }
+    ]
+    
+    for example in examples:
+        console.print(f"\n📝 [bold]{example['title']}[/bold]")
+        console.print("```")
+        console.print(example['code'])
+        console.print("```")
+
+
+if __name__ == "__main__":
+    jsonrpc_app()

python_core/cli/commands/scene.py

@@ -19,7 +19,9 @@ def detect(
     threshold: float = typer.Option(30.0, help="🎚️ 检测阈值 (0-100)"),
     min_scene_length: float = typer.Option(1.0, help="⏱️ 最小场景长度（秒）"),
     output: Optional[Path] = typer.Option(None, "--output", "-o", help="📄 输出文件路径"),
-    format: str = typer.Option("json", help="📋 输出格式 (json/csv/txt)")
+    format: str = typer.Option("json", help="📋 输出格式 (json/csv/txt)"),
+    use_workflow: bool = typer.Option(False, "--workflow", help="🔄 使用LangGraph工作流"),
+    enable_ai: bool = typer.Option(True, "--ai/--no-ai", help="🧠 启用AI分析")
 ):
     """🎯 检测单个视频的场景"""
     try:
@@ -40,39 +42,97 @@ def detect(
             progress_reporter.info("💡 可用格式: json, csv, txt")
             raise typer.Exit(1)
         
-        # 执行检测
-        result = scene_detector.detect_scenes(
-            video_path, detector_type, threshold, min_scene_length
-        )
-        
-        if not result.success:
-            progress_reporter.error(f"❌ 检测失败: {result.error}")
-            raise typer.Exit(1)
-        
-        # 显示结果摘要
-        console.print(f"📊 检测结果摘要:")
-        console.print(f"   文件: {result.filename}")
-        console.print(f"   检测器: {result.detector_type}")
-        console.print(f"   阈值: {result.threshold}")
-        console.print(f"   场景数: {result.total_scenes}")
-        console.print(f"   总时长: {result.total_duration:.2f}秒")
-        console.print(f"   检测时间: {result.detection_time:.2f}秒")
-        
-        # 显示场景详情
-        if result.scenes:
-            console.print(f"\n🎬 场景列表:")
-            for scene in result.scenes[:10]:  # 只显示前10个场景
-                console.print(f"   场景 {scene.index}: {scene.start_time:.2f}s - {scene.end_time:.2f}s ({scene.duration:.2f}s)")
-            
-            if len(result.scenes) > 10:
-                console.print(f"   ... 还有 {len(result.scenes) - 10} 个场景")
-        
-        # 保存结果
-        if output:
-            scene_detector.save_results(result, output, output_format)
-            progress_reporter.success(f"📄 结果已保存到: {output}")
-        
-        return result
+        # 选择执行方式
+        if use_workflow:
+            # 使用LangGraph工作流
+            progress_reporter.info("🔄 使用LangGraph工作流进行检测...")
+
+            workflow_result = scene_detector.detect_with_workflow(
+                video_path, detector_type, threshold, min_scene_length,
+                output, output_format, enable_ai
+            )
+
+            result = workflow_result.get("detection_result")
+            ai_analysis = workflow_result.get("ai_analysis")
+            video_info = workflow_result.get("video_info")
+            errors = workflow_result.get("errors", [])
+
+            if errors:
+                for error in errors:
+                    progress_reporter.error(f"❌ {error}")
+                raise typer.Exit(1)
+
+            if not result or not result.success:
+                progress_reporter.error(f"❌ 工作流检测失败: {result.error if result else '未知错误'}")
+                raise typer.Exit(1)
+
+            # 显示工作流结果
+            console.print(f"🔄 LangGraph工作流检测完成")
+            console.print(f"📊 检测结果摘要:")
+            console.print(f"   文件: {result.filename}")
+            console.print(f"   检测器: {result.detector_type}")
+            console.print(f"   阈值: {result.threshold}")
+            console.print(f"   场景数: {result.total_scenes}")
+            console.print(f"   总时长: {result.total_duration:.2f}秒")
+            console.print(f"   检测时间: {result.detection_time:.2f}秒")
+
+            # 显示视频信息
+            if video_info:
+                console.print(f"\n📹 视频信息:")
+                console.print(f"   分辨率: {video_info.get('resolution', 'Unknown')}")
+                console.print(f"   帧率: {video_info.get('fps', 0):.2f} fps")
+                console.print(f"   总帧数: {video_info.get('frame_count', 0)}")
+
+            # 显示AI分析结果
+            if ai_analysis and enable_ai:
+                console.print(f"\n🧠 AI分析结果:")
+                console.print(f"{ai_analysis}")
+
+            # 显示场景详情
+            if result.scenes:
+                console.print(f"\n🎬 场景列表:")
+                for scene in result.scenes[:10]:
+                    console.print(f"   场景 {scene.index}: {scene.start_time:.2f}s - {scene.end_time:.2f}s ({scene.duration:.2f}s)")
+
+                if len(result.scenes) > 10:
+                    console.print(f"   ... 还有 {len(result.scenes) - 10} 个场景")
+
+            return workflow_result
+
+        else:
+            # 使用传统方法
+            result = scene_detector.detect_scenes(
+                video_path, detector_type, threshold, min_scene_length
+            )
+
+            if not result.success:
+                progress_reporter.error(f"❌ 检测失败: {result.error}")
+                raise typer.Exit(1)
+
+            # 显示结果摘要
+            console.print(f"📊 检测结果摘要:")
+            console.print(f"   文件: {result.filename}")
+            console.print(f"   检测器: {result.detector_type}")
+            console.print(f"   阈值: {result.threshold}")
+            console.print(f"   场景数: {result.total_scenes}")
+            console.print(f"   总时长: {result.total_duration:.2f}秒")
+            console.print(f"   检测时间: {result.detection_time:.2f}秒")
+
+            # 显示场景详情
+            if result.scenes:
+                console.print(f"\n🎬 场景列表:")
+                for scene in result.scenes[:10]:  # 只显示前10个场景
+                    console.print(f"   场景 {scene.index}: {scene.start_time:.2f}s - {scene.end_time:.2f}s ({scene.duration:.2f}s)")
+
+                if len(result.scenes) > 10:
+                    console.print(f"   ... 还有 {len(result.scenes) - 10} 个场景")
+
+            # 保存结果
+            if output:
+                scene_detector.save_results(result, output, output_format)
+                progress_reporter.success(f"📄 结果已保存到: {output}")
+
+            return result
         
     except Exception as e:
         progress_reporter.error(f"❌ 命令执行失败: {e}")
@@ -342,3 +402,148 @@ def info(
     except Exception as e:
         progress_reporter.error(f"❌ 获取视频信息失败: {e}")
         raise typer.Exit(1)
+
+@scene_app.command()
+def workflow(
+    video_path: Path = typer.Argument(..., help="📹 视频文件路径", exists=True),
+    detector: str = typer.Option("content", help="🔧 检测器类型 (content/threshold/adaptive)"),
+    threshold: float = typer.Option(30.0, help="🎚️ 检测阈值 (0-100)"),
+    min_scene_length: float = typer.Option(1.0, help="⏱️ 最小场景长度（秒）"),
+    output: Optional[Path] = typer.Option(None, "--output", "-o", help="📄 输出文件路径"),
+    format: str = typer.Option("json", help="📋 输出格式 (json/csv/txt)"),
+    enable_ai: bool = typer.Option(True, "--ai/--no-ai", help="🧠 启用AI分析"),
+    interactive: bool = typer.Option(False, "--interactive", "-i", help="🔄 交互式工作流")
+):
+    """🔄 使用LangGraph工作流进行智能场景检测"""
+    try:
+        from python_core.cli.scene_detect import detector as scene_detector, DetectorType, OutputFormat
+
+        # 验证参数
+        try:
+            detector_type = DetectorType(detector)
+            output_format = OutputFormat(format)
+        except ValueError as e:
+            progress_reporter.error(f"❌ 参数错误: {e}")
+            raise typer.Exit(1)
+
+        console.print("🔄 [bold blue]LangGraph智能场景检测工作流[/bold blue]")
+        console.print("=" * 60)
+
+        if interactive:
+            # 交互式模式
+            console.print("🎯 交互式模式启动...")
+
+            # 确认参数
+            console.print(f"\n📋 检测参数:")
+            console.print(f"   视频文件: {video_path}")
+            console.print(f"   检测器: {detector}")
+            console.print(f"   阈值: {threshold}")
+            console.print(f"   最小场景长度: {min_scene_length}秒")
+            console.print(f"   AI分析: {'启用' if enable_ai else '禁用'}")
+
+            if not typer.confirm("\n是否继续执行？"):
+                console.print("❌ 用户取消操作")
+                return
+
+        # 执行工作流
+        progress_reporter.info("🚀 启动LangGraph工作流...")
+
+        workflow_result = scene_detector.detect_with_workflow(
+            video_path, detector_type, threshold, min_scene_length,
+            output, output_format, enable_ai
+        )
+
+        result = workflow_result.get("detection_result")
+        ai_analysis = workflow_result.get("ai_analysis")
+        video_info = workflow_result.get("video_info")
+        workflow_state = workflow_result.get("workflow_state")
+        errors = workflow_result.get("errors", [])
+
+        # 检查错误
+        if errors:
+            console.print("\n❌ [red]工作流执行中发现错误:[/red]")
+            for error in errors:
+                console.print(f"   • {error}")
+            raise typer.Exit(1)
+
+        if not result or not result.success:
+            progress_reporter.error(f"❌ 工作流检测失败: {result.error if result else '未知错误'}")
+            raise typer.Exit(1)
+
+        # 显示完整结果
+        console.print("\n" + "=" * 60)
+        console.print("🎉 [bold green]LangGraph工作流执行完成[/bold green]")
+        console.print("=" * 60)
+
+        # 工作流状态
+        console.print(f"\n🔄 工作流状态: [bold]{workflow_state}[/bold]")
+
+        # 视频信息
+        if video_info:
+            console.print(f"\n📹 [bold]视频信息[/bold]:")
+            console.print(f"   文件名: {result.filename}")
+            console.print(f"   分辨率: {video_info.get('resolution', 'Unknown')}")
+            console.print(f"   帧率: {video_info.get('fps', 0):.2f} fps")
+            console.print(f"   总帧数: {video_info.get('frame_count', 0):,}")
+            console.print(f"   时长: {result.total_duration:.2f}秒")
+
+        # 检测结果
+        console.print(f"\n🎯 [bold]检测结果[/bold]:")
+        console.print(f"   检测器类型: {result.detector_type}")
+        console.print(f"   检测阈值: {result.threshold}")
+        console.print(f"   场景数量: [bold green]{result.total_scenes}[/bold green]")
+        console.print(f"   检测耗时: {result.detection_time:.2f}秒")
+
+        # 场景详情
+        if result.scenes:
+            console.print(f"\n🎬 [bold]场景详情[/bold]:")
+            for scene in result.scenes:
+                duration_color = "green" if scene.duration >= 2.0 else "yellow" if scene.duration >= 1.0 else "red"
+                console.print(
+                    f"   场景 {scene.index:2d}: "
+                    f"{scene.start_time:6.2f}s - {scene.end_time:6.2f}s "
+                    f"([{duration_color}]{scene.duration:5.2f}s[/{duration_color}])"
+                )
+
+        # AI分析结果
+        if ai_analysis and enable_ai:
+            console.print(f"\n🧠 [bold]AI智能分析[/bold]:")
+            console.print("-" * 50)
+            console.print(ai_analysis)
+            console.print("-" * 50)
+        elif enable_ai:
+            console.print(f"\n⚠️ AI分析不可用")
+
+        # 保存信息
+        if output:
+            console.print(f"\n💾 结果已保存到: [bold]{output}[/bold]")
+
+        # 交互式后续操作
+        if interactive:
+            console.print(f"\n🎯 [bold]后续操作选项[/bold]:")
+            console.print("1. 保存结果到文件")
+            console.print("2. 调整参数重新检测")
+            console.print("3. 分割视频")
+            console.print("4. 退出")
+
+            choice = typer.prompt("请选择操作 (1-4)", type=int, default=4)
+
+            if choice == 1 and not output:
+                output_path = typer.prompt("请输入输出文件路径", type=str)
+                scene_detector.save_results(result, Path(output_path), output_format)
+                console.print(f"✅ 结果已保存到: {output_path}")
+
+            elif choice == 2:
+                console.print("🔄 参数调整功能开发中...")
+
+            elif choice == 3:
+                console.print("✂️ 视频分割功能开发中...")
+
+            else:
+                console.print("👋 感谢使用LangGraph工作流！")
+
+        return workflow_result
+
+    except Exception as e:
+        progress_reporter.error(f"❌ 工作流命令执行失败: {e}")
+        raise typer.Exit(1)

python_core/cli/const.py

@@ -1,4 +1,4 @@
-from python_core.utils.jsonrpc import create_progress_reporter
+from python_core.utils.jsonrpc_enhanced import create_progress_reporter
 from rich.console import Console
 from python_core.config import settings
 console = Console()

python_core/cli/scene_detect.py

@@ -1,23 +1,26 @@
 #!/usr/bin/env python3
 """
-PySceneDetect 场景检测命令行工具
+PySceneDetect 场景检测命令行工具 - LangGraph增强版
 """
 
-import os
 import json
 import time
 from pathlib import Path
-from typing import Optional, List
+from typing import Optional, List, Literal, Dict, Any
 from enum import Enum
 from dataclasses import dataclass, asdict
 
-import typer
-from python_core.cli.const import progress_reporter, console, project_root
+from python_core.cli.const import progress_reporter
 
-# 检查 PySceneDetect 依赖
+# PySceneDetect 依赖
 from scenedetect import open_video, SceneManager
 from scenedetect.detectors import ContentDetector, ThresholdDetector
-from scenedetect.video_splitter import split_video_ffmpeg
+
+# LangGraph 依赖
+from langgraph.graph import StateGraph, START, END
+from langgraph.graph.state import CompiledStateGraph
+from langgraph.checkpoint.memory import MemorySaver
+from langchain_anthropic import ChatAnthropic
 
 class DetectorType(str, Enum):
     """检测器类型"""
@@ -55,11 +58,59 @@ class DetectionResult:
     success: bool
     error: Optional[str] = None
 
+# LangGraph 工作流状态
+@dataclass
+class SceneDetectionWorkflowState:
+    """场景检测工作流状态"""
+    # 输入参数
+    video_path: str = ""
+    detector_type: str = "content"
+    threshold: float = 30.0
+    min_scene_length: float = 1.0
+    output_path: Optional[str] = None
+    output_format: str = "json"
+    enable_ai_analysis: bool = True
+
+    # 工作流状态
+    current_stage: str = "init"
+    progress: int = 0
+    total_steps: int = 5
+
+    # 中间结果
+    video_info: Dict[str, Any] = None
+    raw_scenes: List[Any] = None
+    processed_scenes: List[SceneInfo] = None
+
+    # 最终结果
+    detection_result: Optional[DetectionResult] = None
+    ai_analysis: Optional[str] = None
+
+    # 错误处理
+    errors: List[str] = None
+
+    def __post_init__(self):
+        if self.video_info is None:
+            self.video_info = {}
+        if self.raw_scenes is None:
+            self.raw_scenes = []
+        if self.processed_scenes is None:
+            self.processed_scenes = []
+        if self.errors is None:
+                self.errors = []
+
 class SceneDetector:
     """场景检测器"""
-    
+
     def __init__(self):
         self.supported_formats = {'.mp4', '.avi', '.mov', '.mkv', '.wmv', '.flv', '.webm', '.m4v'}
+
+        # 初始化AI分析器（如果可用）
+        try:
+            self.llm = ChatAnthropic(model="claude-3-5-sonnet-20241022")
+            self.ai_enabled = True
+        except Exception as e:
+            progress_reporter.warning(f"⚠️ AI分析器初始化失败: {e}")
+            self.ai_enabled = False
     
     def detect_scenes(self, video_path: Path, detector_type: DetectorType = DetectorType.CONTENT,
                      threshold: float = 30.0, min_scene_length: float = 1.0) -> DetectionResult:
@@ -361,5 +412,460 @@ class SceneDetector:
                     
                     f.write("\n")
 
+    # ==================== LangGraph 工作流方法 ====================
+
+    def create_detection_workflow(self) -> Optional[CompiledStateGraph]:
+        """创建场景检测工作流"""
+
+        # 定义工作流节点
+        def validate_input(state: SceneDetectionWorkflowState) -> Dict[str, Any]:
+            """验证输入参数"""
+            progress_reporter.info("🔍 验证输入参数...")
+
+            video_path = Path(state.video_path)
+            errors = []
+
+            # 验证文件存在
+            if not video_path.exists():
+                errors.append(f"视频文件不存在: {video_path}")
+
+            # 验证文件格式
+            if video_path.suffix.lower() not in self.supported_formats:
+                errors.append(f"不支持的文件格式: {video_path.suffix}")
+
+            # 验证参数范围
+            if not (0 <= state.threshold <= 100):
+                errors.append(f"阈值超出范围 (0-100): {state.threshold}")
+
+            if state.min_scene_length < 0:
+                errors.append(f"最小场景长度不能为负数: {state.min_scene_length}")
+
+            return {
+                "current_stage": "validated" if not errors else "error",
+                "progress": 1,
+                "errors": errors
+            }
+
+        def extract_video_info(state: SceneDetectionWorkflowState) -> Dict[str, Any]:
+            """提取视频信息"""
+            progress_reporter.info("📊 提取视频信息...")
+
+            try:
+                import cv2
+                cap = cv2.VideoCapture(state.video_path)
+
+                if not cap.isOpened():
+                    raise Exception("无法打开视频文件")
+
+                fps = cap.get(cv2.CAP_PROP_FPS)
+                frame_count = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+                width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+                height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+                duration = frame_count / fps if fps > 0 else 0
+
+                cap.release()
+
+                video_info = {
+                    "fps": fps,
+                    "frame_count": frame_count,
+                    "width": width,
+                    "height": height,
+                    "duration": duration,
+                    "resolution": f"{width}x{height}"
+                }
+
+                progress_reporter.info(f"📹 视频信息: {video_info['resolution']}, {fps:.2f}fps, {duration:.2f}s")
+
+                return {
+                    "current_stage": "info_extracted",
+                    "progress": 2,
+                    "video_info": video_info
+                }
+
+            except Exception as e:
+                return {
+                    "current_stage": "error",
+                    "errors": state.errors + [f"提取视频信息失败: {e}"]
+                }
+
+        def detect_scenes(state: SceneDetectionWorkflowState) -> Dict[str, Any]:
+            """执行场景检测"""
+            progress_reporter.info("🎯 执行场景检测...")
+
+            try:
+                # 使用现有的检测逻辑
+                result = self.detect_scenes(
+                    Path(state.video_path),
+                    DetectorType(state.detector_type),
+                    state.threshold,
+                    state.min_scene_length
+                )
+
+                return {
+                    "current_stage": "scenes_detected",
+                    "progress": 3,
+                    "detection_result": result,
+                    "processed_scenes": result.scenes
+                }
+
+            except Exception as e:
+                return {
+                    "current_stage": "error",
+                    "errors": state.errors + [f"场景检测失败: {e}"]
+                }
+
+        def analyze_with_ai(state: SceneDetectionWorkflowState) -> Dict[str, Any]:
+            """AI分析场景结果"""
+            if not self.ai_enabled or not state.enable_ai_analysis:
+                progress_reporter.info("⚠️ AI分析已禁用，跳过此步骤")
+                return {
+                    "current_stage": "analysis_skipped",
+                    "progress": 4,
+                    "ai_analysis": "AI分析已禁用"
+                }
+
+            progress_reporter.info("🧠 AI分析场景结果...")
+
+            try:
+                result = state.detection_result
+                video_info = state.video_info
+
+                analysis_prompt = f"""
+                请分析以下视频场景检测结果：
+
+                视频信息:
+                - 文件: {result.filename}
+                - 分辨率: {video_info.get('resolution', 'Unknown')}
+                - 时长: {result.total_duration:.2f}秒
+                - 帧率: {video_info.get('fps', 0):.2f}fps
+
+                检测结果:
+                - 检测器: {result.detector_type}
+                - 阈值: {result.threshold}
+                - 场景数: {result.total_scenes}
+                - 检测时间: {result.detection_time:.2f}秒
+
+                场景详情:
+                {self._format_scenes_for_ai(result.scenes)}
+
+                请提供:
+                1. 场景分布分析
+                2. 检测质量评估
+                3. 参数优化建议
+                4. 潜在问题识别
+                """
+
+                response = self.llm.invoke([{"role": "user", "content": analysis_prompt}])
+
+                return {
+                    "current_stage": "ai_analyzed",
+                    "progress": 4,
+                    "ai_analysis": response.content
+                }
+
+            except Exception as e:
+                progress_reporter.warning(f"⚠️ AI分析失败: {e}")
+                return {
+                    "current_stage": "analysis_failed",
+                    "progress": 4,
+                    "ai_analysis": f"AI分析失败: {e}"
+                }
+
+        def finalize_results(state: SceneDetectionWorkflowState) -> Dict[str, Any]:
+            """整理最终结果"""
+            progress_reporter.info("📋 整理最终结果...")
+
+            # 保存结果（如果指定了输出路径）
+            if state.output_path and state.detection_result:
+                try:
+                    output_path = Path(state.output_path)
+                    output_format = OutputFormat(state.output_format)
+                    self.save_results(state.detection_result, output_path, output_format)
+                except Exception as e:
+                    progress_reporter.warning(f"⚠️ 保存结果失败: {e}")
+
+            return {
+                "current_stage": "completed",
+                "progress": 5
+            }
+
+        # 路由函数
+        def route_next_step(state: SceneDetectionWorkflowState) -> Literal["extract_info", "detect", "analyze", "finalize", "error"]:
+            if state.errors:
+                return "error"
+            elif state.current_stage == "validated":
+                return "extract_info"
+            elif state.current_stage == "info_extracted":
+                return "detect"
+            elif state.current_stage == "scenes_detected":
+                return "analyze"
+            elif state.current_stage in ["ai_analyzed", "analysis_skipped", "analysis_failed"]:
+                return "finalize"
+            else:
+                return "error"
+
+        def handle_error(state: SceneDetectionWorkflowState) -> Dict[str, Any]:
+            """处理错误"""
+            error_msg = "; ".join(state.errors)
+            progress_reporter.error(f"❌ 工作流错误: {error_msg}")
+            return {"current_stage": "failed"}
+
+        # 构建工作流图
+        workflow = StateGraph(SceneDetectionWorkflowState)
+
+        # 添加节点
+        workflow.add_node("validate", validate_input)
+        workflow.add_node("extract_info", extract_video_info)
+        workflow.add_node("detect", detect_scenes)
+        workflow.add_node("analyze", analyze_with_ai)
+        workflow.add_node("finalize", finalize_results)
+        workflow.add_node("error", handle_error)
+
+        # 添加边
+        workflow.add_edge(START, "validate")
+        workflow.add_conditional_edges("validate", route_next_step)
+        workflow.add_conditional_edges("extract_info", route_next_step)
+        workflow.add_conditional_edges("detect", route_next_step)
+        workflow.add_conditional_edges("analyze", route_next_step)
+        workflow.add_edge("finalize", END)
+        workflow.add_edge("error", END)
+
+        # 编译工作流
+        memory = MemorySaver()
+        return workflow.compile(checkpointer=memory)
+
+    def _format_scenes_for_ai(self, scenes: List[SceneInfo]) -> str:
+        """格式化场景信息供AI分析"""
+        if not scenes:
+            return "无场景数据"
+
+        formatted = []
+        for scene in scenes[:10]:  # 只显示前10个场景
+            formatted.append(
+                f"场景 {scene.index}: {scene.start_time:.2f}s - {scene.end_time:.2f}s "
+                f"(时长: {scene.duration:.2f}s)"
+            )
+
+        if len(scenes) > 10:
+            formatted.append(f"... 还有 {len(scenes) - 10} 个场景")
+
+        return "\n".join(formatted)
+
+    def detect_with_workflow(self, video_path: Path, detector_type: DetectorType = DetectorType.CONTENT,
+                           threshold: float = 30.0, min_scene_length: float = 1.0,
+                           output_path: Optional[Path] = None, output_format: OutputFormat = OutputFormat.JSON,
+                           enable_ai_analysis: bool = True) -> Dict[str, Any]:
+        """使用LangGraph工作流进行场景检测"""
+
+        # 创建工作流
+        workflow = self.create_detection_workflow()
+        if not workflow:
+            raise Exception("无法创建工作流")
+
+        # 初始化状态
+        initial_state = SceneDetectionWorkflowState(
+            video_path=str(video_path),
+            detector_type=detector_type.value,
+            threshold=threshold,
+            min_scene_length=min_scene_length,
+            output_path=str(output_path) if output_path else None,
+            output_format=output_format.value,
+            enable_ai_analysis=enable_ai_analysis  # 使用参数
+        )
+
+        # 执行工作流
+        config = {"configurable": {"thread_id": f"detection_{int(time.time())}"}}
+
+        try:
+            final_state = workflow.invoke(initial_state, config)
+
+            return {
+                "detection_result": final_state.get("detection_result"),
+                "ai_analysis": final_state.get("ai_analysis"),
+                "video_info": final_state.get("video_info"),
+                "workflow_state": final_state.get("current_stage"),
+                "errors": final_state.get("errors", [])
+            }
+
+        except Exception as e:
+            progress_reporter.error(f"❌ 工作流执行失败: {e}")
+            raise
+
+    # ==================== JSON-RPC 方法注册 ====================
+
+    def register_jsonrpc_methods(self):
+        """注册JSON-RPC方法到全局注册器"""
+        from python_core.utils.jsonrpc_enhanced import method_registry
+
+        # 注册方法到全局注册器
+        method_registry.register_function(self.jsonrpc_detect_scenes, "scene.detect")
+        method_registry.register_function(self.jsonrpc_detect_with_workflow, "scene.detect_workflow")
+        method_registry.register_function(self.jsonrpc_get_video_info, "scene.get_video_info")
+        method_registry.register_function(self.jsonrpc_batch_detect, "scene.batch_detect")
+
+    def jsonrpc_detect_scenes(self, video_path: str, detector_type: str = "content",
+                             threshold: float = 30.0, min_scene_length: float = 1.0) -> Dict[str, Any]:
+        """JSON-RPC方法：场景检测"""
+        try:
+            result = self.detect_scenes(
+                Path(video_path),
+                DetectorType(detector_type),
+                threshold,
+                min_scene_length
+            )
+
+            return {
+                "success": result.success,
+                "filename": result.filename,
+                "detector_type": result.detector_type,
+                "threshold": result.threshold,
+                "total_scenes": result.total_scenes,
+                "total_duration": result.total_duration,
+                "detection_time": result.detection_time,
+                "scenes": [asdict(scene) for scene in result.scenes],
+                "error": result.error
+            }
+        except Exception as e:
+            return {
+                "success": False,
+                "error": str(e)
+            }
+
+    def jsonrpc_detect_with_workflow(self, video_path: str, detector_type: str = "content",
+                                   threshold: float = 30.0, min_scene_length: float = 1.0,
+                                   output_path: Optional[str] = None, output_format: str = "json",
+                                   enable_ai_analysis: bool = True) -> Dict[str, Any]:
+        """JSON-RPC方法：工作流场景检测"""
+        try:
+            output_path_obj = Path(output_path) if output_path else None
+
+            result = self.detect_with_workflow(
+                Path(video_path),
+                DetectorType(detector_type),
+                threshold,
+                min_scene_length,
+                output_path_obj,
+                OutputFormat(output_format),
+                enable_ai_analysis
+            )
+
+            # 序列化结果
+            serialized_result = {}
+            for key, value in result.items():
+                if key == "detection_result" and value:
+                    serialized_result[key] = {
+                        "success": value.success,
+                        "filename": value.filename,
+                        "detector_type": value.detector_type,
+                        "threshold": value.threshold,
+                        "total_scenes": value.total_scenes,
+                        "total_duration": value.total_duration,
+                        "detection_time": value.detection_time,
+                        "scenes": [asdict(scene) for scene in value.scenes],
+                        "error": value.error
+                    }
+                else:
+                    serialized_result[key] = value
+
+            return serialized_result
+
+        except Exception as e:
+            return {
+                "success": False,
+                "error": str(e)
+            }
+
+    def get_video_info(self, video_path: Path) -> Dict[str, Any]:
+        """获取视频信息"""
+        try:
+            import cv2
+            cap = cv2.VideoCapture(str(video_path))
+
+            if not cap.isOpened():
+                raise Exception("无法打开视频文件")
+
+            fps = cap.get(cv2.CAP_PROP_FPS)
+            frame_count = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+            width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+            height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+            duration = frame_count / fps if fps > 0 else 0
+
+            cap.release()
+
+            return {
+                "filename": video_path.name,
+                "fps": fps,
+                "frame_count": frame_count,
+                "width": width,
+                "height": height,
+                "duration": duration,
+                "resolution": f"{width}x{height}",
+                "file_size": video_path.stat().st_size if video_path.exists() else 0
+            }
+
+        except Exception as e:
+            raise Exception(f"获取视频信息失败: {e}")
+
+    def jsonrpc_get_video_info(self, video_path: str) -> Dict[str, Any]:
+        """JSON-RPC方法：获取视频信息"""
+        try:
+            info = self.get_video_info(Path(video_path))
+            return {
+                "success": True,
+                "info": info
+            }
+        except Exception as e:
+            return {
+                "success": False,
+                "error": str(e)
+            }
+
+    def jsonrpc_batch_detect(self, directory: str, detector_type: str = "content",
+                           threshold: float = 30.0, min_scene_length: float = 1.0,
+                           output_dir: Optional[str] = None, output_format: str = "json") -> Dict[str, Any]:
+        """JSON-RPC方法：批量场景检测"""
+        try:
+            output_dir_obj = Path(output_dir) if output_dir else None
+
+            results = self.batch_detect(
+                Path(directory),
+                DetectorType(detector_type),
+                threshold,
+                min_scene_length,
+                output_dir_obj,
+                OutputFormat(output_format)
+            )
+
+            # 序列化结果
+            serialized_results = []
+            for result in results:
+                serialized_results.append({
+                    "success": result.success,
+                    "filename": result.filename,
+                    "detector_type": result.detector_type,
+                    "threshold": result.threshold,
+                    "total_scenes": result.total_scenes,
+                    "total_duration": result.total_duration,
+                    "detection_time": result.detection_time,
+                    "scenes": [asdict(scene) for scene in result.scenes],
+                    "error": result.error
+                })
+
+            return {
+                "success": True,
+                "results": serialized_results,
+                "total_processed": len(results)
+            }
+
+        except Exception as e:
+            return {
+                "success": False,
+                "error": str(e)
+            }
+
+
 # 创建全局检测器实例
-detector = SceneDetector()
+detector = SceneDetector()
+
+# 注册JSON-RPC方法
+detector.register_jsonrpc_methods()

python_core/requirements.txt

@@ -26,4 +26,8 @@ pyyaml
 pydantic_settings
 scenedetect[opencv]
 typer
-rich
+rich
+langgraph
+json-rpc
+langchain_core
+langchain_anthropic

python_core/utils/jsonrpc.py

@@ -112,8 +112,9 @@ class JSONRPCResponse:
 
 class ProgressReporter:
     """Progress reporting using JSON-RPC notifications"""
-    
-    def __init__(self):
+    step: int = 0
+    total: int = 0
+    def __init__(self, total: int = 0):
         self.rpc = JSONRPCResponse()
     
     def report(self, step: str, progress: float, message: str, details: Dict[str, Any] = None) -> None:

python_core/utils/jsonrpc_enhanced.py

@@ -0,0 +1,186 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Enhanced JSON-RPC Communication Module
+增强版 JSON-RPC 通信模块
+
+Uses json-rpc library for robust JSON-RPC 2.0 communication.
+"""
+
+import json
+import sys
+import time
+import uuid
+import asyncio
+from typing import Any, Dict, Optional, Union, Callable, List
+from dataclasses import dataclass, asdict
+from enum import Enum
+
+# json-rpc library imports
+from jsonrpc import JSONRPCResponseManager, dispatcher
+from jsonrpc.exceptions import JSONRPCError, JSONRPCInvalidRequest, JSONRPCMethodNotFound
+from jsonrpc.jsonrpc2 import JSONRPC20Request, JSONRPC20Response
+
+class ProgressLevel(str, Enum):
+    """进度级别"""
+    INFO = "info"
+    SUCCESS = "success"
+    WARNING = "warning"
+    ERROR = "error"
+    DEBUG = "debug"
+
+
+@dataclass
+class ProgressUpdate:
+    """进度更新数据结构"""
+    step: str
+    type: str
+    progress: int
+    message: str
+    timestamp: float
+    level: ProgressLevel = ProgressLevel.INFO
+    data: Optional[Dict[str, Any]] = None
+
+
+class EnhancedJSONRPCResponse:
+    """增强版 JSON-RPC 2.0 Response handler"""
+    
+    def __init__(self, request_id: Optional[Union[str, int]] = None):
+        # 如果没有提供request_id，生成一个UUID
+        if request_id is None:
+            self.request_id = str(uuid.uuid4())
+        else:
+            self.request_id = request_id
+    
+    def success(self, result: Any) -> None:
+        """发送成功响应"""
+        response = JSONRPC20Response(result=result, _id=self.request_id)
+        self._send_response(response.data)
+    
+    def error(self, code: int, message: str, data: Any = None) -> None:
+        """发送错误响应"""
+        error = JSONRPCError(code=code, message=message, data=data)
+        response = JSONRPC20Response(error=error, _id=self.request_id)
+        self._send_response(response.data)
+    
+    def progress(self, step: str, progress: int, message: str, 
+                level: ProgressLevel = ProgressLevel.INFO, data: Optional[Dict[str, Any]] = None) -> None:
+        """发送进度通知"""
+        progress_data = ProgressUpdate(
+            step=step,
+            type="progress",
+            progress=progress,
+            message=message,
+            timestamp=time.time(),
+            level=level,
+            data=data
+        )
+        
+        self.notification(asdict(progress_data))
+    
+    def notification(self, params: Any = None) -> None:
+        """发送通知（无需响应）"""
+        response = JSONRPC20Response(result=params, _id=self.request_id)
+        self._send_response(response.data)
+    
+    def _send_response(self, response: Dict[str, Any]) -> None:
+        """发送响应到标准输出"""
+        json_str = json.dumps(response, ensure_ascii=False, separators=(',', ':'))
+        print(f"JSONRPC:{json_str}", file=sys.stdout, flush=True)
+
+class EnhancedProgressReporter:
+    """增强版进度报告器"""
+    
+    def __init__(self, total: int = 0):
+        self.response = EnhancedJSONRPCResponse()
+        self.step = 0
+        self.total = total
+    
+    def update(self, message: str, step: Optional[int] = None, data: Optional[Dict[str, Any]] = None) -> None:
+        """更新进度"""
+        if step is not None:
+            self.step = step
+        else:
+            self.step += 1
+        
+        progress = int((self.step / self.total * 100)) if self.total > 0 else -1
+        self.response.progress("update", progress, message, ProgressLevel.INFO, data)
+    
+    def info(self, message: str, data: Optional[Dict[str, Any]] = None) -> None:
+        """信息消息"""
+        self.response.progress("info", -1, message, ProgressLevel.INFO, data)
+    
+    def success(self, message: str, data: Optional[Dict[str, Any]] = None) -> None:
+        """成功消息"""
+        self.response.progress("success", -1, message, ProgressLevel.SUCCESS, data)
+    
+    def warning(self, message: str, data: Optional[Dict[str, Any]] = None) -> None:
+        """警告消息"""
+        self.response.progress("warning", -1, message, ProgressLevel.WARNING, data)
+    
+    def error(self, message: str, data: Optional[Dict[str, Any]] = None) -> None:
+        """错误消息"""
+        self.response.progress("error", -1, message, ProgressLevel.ERROR, data)
+    
+    def debug(self, message: str, data: Optional[Dict[str, Any]] = None) -> None:
+        """调试消息"""
+        self.response.progress("debug", -1, message, ProgressLevel.DEBUG, data)
+
+
+class JSONRPCMethodRegistry:
+    """JSON-RPC 方法注册器"""
+    
+    def __init__(self):
+        self.methods: Dict[str, Callable] = {}
+        self.dispatcher = dispatcher
+    
+    def register(self, name: Optional[str] = None):
+        """注册方法装饰器"""
+        def decorator(func: Callable):
+            method_name = name or func.__name__
+            self.methods[method_name] = func
+            self.dispatcher.add_method(func, method_name)   
+            return func
+        return decorator
+    
+    def register_function(self, func: Callable, name: Optional[str] = None) -> None:
+        """直接注册函数"""
+        method_name = name or func.__name__
+        self.methods[method_name] = func
+        self.dispatcher.add_method(func, method_name)
+            
+    
+    def handle_request(self, request_data: str) -> str:
+        """处理JSON-RPC请求"""
+        response = JSONRPCResponseManager.handle(request_data, self.dispatcher)
+        return response.json
+
+# 全局实例
+enhanced_progress_reporter = EnhancedProgressReporter()
+method_registry = JSONRPCMethodRegistry()
+
+
+# 便捷函数
+def create_response_handler(request_id: Optional[Union[str, int]] = None) -> EnhancedJSONRPCResponse:
+    """创建响应处理器"""
+    return EnhancedJSONRPCResponse(request_id)
+
+
+def create_progress_reporter(total: int = 0) -> EnhancedProgressReporter:
+    """创建进度报告器"""
+    return EnhancedProgressReporter(total)
+
+
+def register_method(name: Optional[str] = None):
+    """注册JSON-RPC方法"""
+    return method_registry.register(name)
+
+
+def handle_jsonrpc_request(request_data: str) -> str:
+    """处理JSON-RPC请求"""
+    return method_registry.handle_request(request_data)
+
+
+# 向后兼容的别名
+JSONRPCResponse = EnhancedJSONRPCResponse
+ProgressReporter = EnhancedProgressReporter

python_core/utils/jsonrpc_server.py

@@ -0,0 +1,274 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+JSON-RPC Server Implementation
+JSON-RPC 服务器实现
+
+Provides HTTP and WebSocket JSON-RPC server implementations.
+"""
+
+import json
+import asyncio
+from typing import Any, Dict, Optional, Callable, List
+from dataclasses import dataclass
+from http.server import HTTPServer, BaseHTTPRequestHandler
+import threading
+import logging
+
+try:
+    from jsonrpc import JSONRPCResponseManager, dispatcher
+    from jsonrpc.exceptions import JSONRPCError
+    JSON_RPC_AVAILABLE = True
+except ImportError:
+    JSON_RPC_AVAILABLE = False
+
+from .jsonrpc_enhanced import JSONRPCMethodRegistry, EnhancedProgressReporter
+
+
+@dataclass
+class ServerConfig:
+    """服务器配置"""
+    host: str = "localhost"
+    port: int = 8080
+    debug: bool = False
+    cors_enabled: bool = True
+    max_request_size: int = 1024 * 1024  # 1MB
+
+
+class JSONRPCHTTPHandler(BaseHTTPRequestHandler):
+    """JSON-RPC HTTP 请求处理器"""
+    
+    def __init__(self, method_registry: JSONRPCMethodRegistry, config: ServerConfig, *args, **kwargs):
+        self.method_registry = method_registry
+        self.config = config
+        super().__init__(*args, **kwargs)
+    
+    def do_POST(self):
+        """处理POST请求"""
+        try:
+            # 检查Content-Type
+            content_type = self.headers.get('Content-Type', '')
+            if 'application/json' not in content_type:
+                self._send_error(400, "Content-Type must be application/json")
+                return
+            
+            # 读取请求体
+            content_length = int(self.headers.get('Content-Length', 0))
+            if content_length > self.config.max_request_size:
+                self._send_error(413, "Request too large")
+                return
+            
+            request_data = self.rfile.read(content_length).decode('utf-8')
+            
+            # 处理JSON-RPC请求
+            response_data = self.method_registry.handle_request(request_data)
+            
+            # 发送响应
+            self._send_json_response(response_data)
+            
+        except Exception as e:
+            if self.config.debug:
+                logging.exception("Error handling request")
+            self._send_error(500, f"Internal server error: {str(e)}")
+    
+    def do_OPTIONS(self):
+        """处理OPTIONS请求（CORS预检）"""
+        if self.config.cors_enabled:
+            self._send_cors_headers()
+            self.end_headers()
+        else:
+            self._send_error(405, "Method not allowed")
+    
+    def _send_json_response(self, data: str):
+        """发送JSON响应"""
+        self.send_response(200)
+        self.send_header('Content-Type', 'application/json')
+        if self.config.cors_enabled:
+            self._send_cors_headers()
+        self.end_headers()
+        self.wfile.write(data.encode('utf-8'))
+    
+    def _send_cors_headers(self):
+        """发送CORS头"""
+        self.send_header('Access-Control-Allow-Origin', '*')
+        self.send_header('Access-Control-Allow-Methods', 'POST, OPTIONS')
+        self.send_header('Access-Control-Allow-Headers', 'Content-Type')
+    
+    def _send_error(self, code: int, message: str):
+        """发送错误响应"""
+        self.send_response(code)
+        self.send_header('Content-Type', 'application/json')
+        if self.config.cors_enabled:
+            self._send_cors_headers()
+        self.end_headers()
+        
+        error_response = {
+            "jsonrpc": "2.0",
+            "id": None,
+            "error": {
+                "code": code,
+                "message": message
+            }
+        }
+        self.wfile.write(json.dumps(error_response).encode('utf-8'))
+    
+    def log_message(self, format, *args):
+        """重写日志方法"""
+        if self.config.debug:
+            super().log_message(format, *args)
+
+
+class JSONRPCServer:
+    """JSON-RPC HTTP 服务器"""
+    
+    def __init__(self, config: Optional[ServerConfig] = None):
+        self.config = config or ServerConfig()
+        self.method_registry = JSONRPCMethodRegistry()
+        self.server: Optional[HTTPServer] = None
+        self.server_thread: Optional[threading.Thread] = None
+        self.running = False
+    
+    def register_method(self, name: Optional[str] = None):
+        """注册方法装饰器"""
+        return self.method_registry.register(name)
+    
+    def register_function(self, func: Callable, name: Optional[str] = None):
+        """注册函数"""
+        self.method_registry.register_function(func, name)
+    
+    def start(self, blocking: bool = True):
+        """启动服务器"""
+        if self.running:
+            raise RuntimeError("Server is already running")
+        
+        # 创建处理器工厂
+        def handler_factory(*args, **kwargs):
+            return JSONRPCHTTPHandler(self.method_registry, self.config, *args, **kwargs)
+        
+        # 创建服务器
+        self.server = HTTPServer((self.config.host, self.config.port), handler_factory)
+        self.running = True
+        
+        print(f"🚀 JSON-RPC Server started on http://{self.config.host}:{self.config.port}")
+        
+        if blocking:
+            try:
+                self.server.serve_forever()
+            except KeyboardInterrupt:
+                self.stop()
+        else:
+            self.server_thread = threading.Thread(target=self.server.serve_forever)
+            self.server_thread.daemon = True
+            self.server_thread.start()
+    
+    def stop(self):
+        """停止服务器"""
+        if self.server and self.running:
+            print("🛑 Stopping JSON-RPC Server...")
+            self.server.shutdown()
+            self.server.server_close()
+            self.running = False
+            
+            if self.server_thread:
+                self.server_thread.join(timeout=5)
+    
+    def __enter__(self):
+        """上下文管理器入口"""
+        return self
+    
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        """上下文管理器出口"""
+        self.stop()
+
+
+# 异步WebSocket服务器（需要额外依赖）
+try:
+    import websockets
+    import asyncio
+    
+    class JSONRPCWebSocketServer:
+        """JSON-RPC WebSocket 服务器"""
+        
+        def __init__(self, config: Optional[ServerConfig] = None):
+            self.config = config or ServerConfig()
+            self.method_registry = JSONRPCMethodRegistry()
+            self.clients: List[Any] = []
+        
+        def register_method(self, name: Optional[str] = None):
+            """注册方法装饰器"""
+            return self.method_registry.register(name)
+        
+        async def handle_client(self, websocket, path):
+            """处理WebSocket客户端"""
+            self.clients.append(websocket)
+            try:
+                async for message in websocket:
+                    try:
+                        response = self.method_registry.handle_request(message)
+                        await websocket.send(response)
+                    except Exception as e:
+                        error_response = {
+                            "jsonrpc": "2.0",
+                            "id": None,
+                            "error": {
+                                "code": -32603,
+                                "message": f"Internal error: {str(e)}"
+                            }
+                        }
+                        await websocket.send(json.dumps(error_response))
+            except websockets.exceptions.ConnectionClosed:
+                pass
+            finally:
+                if websocket in self.clients:
+                    self.clients.remove(websocket)
+        
+        async def broadcast(self, method: str, params: Any = None):
+            """广播通知到所有客户端"""
+            if not self.clients:
+                return
+            
+            notification = {
+                "jsonrpc": "2.0",
+                "method": method,
+                "params": params
+            }
+            message = json.dumps(notification)
+            
+            # 发送到所有连接的客户端
+            disconnected = []
+            for client in self.clients:
+                try:
+                    await client.send(message)
+                except websockets.exceptions.ConnectionClosed:
+                    disconnected.append(client)
+            
+            # 清理断开的连接
+            for client in disconnected:
+                self.clients.remove(client)
+        
+        async def start(self):
+            """启动WebSocket服务器"""
+            print(f"🚀 JSON-RPC WebSocket Server started on ws://{self.config.host}:{self.config.port}")
+            
+            async with websockets.serve(
+                self.handle_client,
+                self.config.host,
+                self.config.port
+            ):
+                await asyncio.Future()  # 永远运行
+
+except ImportError:
+    class JSONRPCWebSocketServer:
+        def __init__(self, *args, **kwargs):
+            raise ImportError("WebSocket server requires 'websockets' package")
+
+
+# 便捷函数
+def create_server(config: Optional[ServerConfig] = None) -> JSONRPCServer:
+    """创建HTTP服务器"""
+    return JSONRPCServer(config)
+
+
+def create_websocket_server(config: Optional[ServerConfig] = None) -> JSONRPCWebSocketServer:
+    """创建WebSocket服务器"""
+    return JSONRPCWebSocketServer(config)

setup_venv.sh

@@ -0,0 +1,21 @@
+#!/bin/bash
+
+# 创建虚拟环境
+echo "🔧 创建Python虚拟环境..."
+python -m venv venv
+
+# 激活虚拟环境
+echo "🔌 激活虚拟环境..."
+source venv/bin/activate
+
+# 安装依赖
+echo "📦 安装依赖..."
+pip install -r python_core/requirements.txt
+
+# 特别安装langchain_anthropic
+echo "🤖 安装langchain_anthropic..."
+pip install langchain_anthropic
+
+echo "✅ 环境设置完成！"
+echo "💡 使用 'source venv/bin/activate' 激活环境"
+echo "💡 使用 'deactivate' 退出环境"