""" 示例（简化版 - 使用框架交互功能） 使用 Agent 模式 + Skills + 框架交互控制器 新功能： 1. 使用框架提供的 InteractiveController 2. 使用配置文件管理运行参数 3. 支持命令行随时打断（输入 'p' 暂停，'q' 退出） 4. 暂停后可插入干预消息 5. 支持触发经验总结 6. 查看当前 GoalTree 7. 支持通过 --trace 恢复已有 Trace 继续执行 """ import argparse import os import sys import asyncio from pathlib import Path # Clash Verge TUN 模式兼容：禁止 httpx/urllib 自动检测系统 HTTP 代理 os.environ.setdefault("no_proxy", "*") # 添加项目根目录到 Python 路径 sys.path.insert(0, str(Path(__file__).parent.parent.parent)) from dotenv import load_dotenv load_dotenv() from agent.llm.prompts import SimplePrompt from agent.core.runner import AgentRunner, RunConfig from agent.core.presets import AgentPreset, register_preset from agent.trace import ( FileSystemTraceStore, Trace, Message, ) from agent.llm import create_openrouter_llm_call from agent.cli import InteractiveController from agent.utils import setup_logging from agent.tools.builtin.browser.baseClass import init_browser_session, kill_browser_session # 导入项目配置 from config import RUN_CONFIG, SKILLS_DIR, TRACE_STORE_PATH, DEBUG, LOG_LEVEL, LOG_FILE, BROWSER_TYPE, HEADLESS async def main(): # 解析命令行参数 parser = argparse.ArgumentParser(description="任务 (Agent 模式 + 交互增强)") parser.add_argument( "--trace", type=str, default=None, help="已有的 Trace ID，用于恢复继续执行（不指定则新建）", ) args = parser.parse_args() # 路径配置 base_dir = Path(__file__).parent project_root = base_dir.parent.parent prompt_path = base_dir / "research.prompt" output_dir = base_dir / "output_1" output_dir.mkdir(exist_ok=True) # 1. 配置日志 setup_logging(level=LOG_LEVEL, file=LOG_FILE) # 2. 加载项目级 presets print("2. 加载 presets...") presets_path = base_dir / "presets.json" if presets_path.exists(): import json with open(presets_path, "r", encoding="utf-8") as f: project_presets = json.load(f) for name, cfg in project_presets.items(): register_preset(name, AgentPreset(**cfg)) print(f" - 已加载项目 presets: {list(project_presets.keys())}") # 3. 加载 prompt print("3. 加载 prompt...") prompt = SimplePrompt(prompt_path) # 4. 构建任务消息 print("4. 构建任务消息...") messages = prompt.build_messages() # 5. 初始化浏览器 import platform actual_browser_type = BROWSER_TYPE if platform.system() == "Windows" and BROWSER_TYPE == "local": actual_browser_type = "cloud" print("⚠️ Windows 平台检测到本地浏览器配置，自动切换为云浏览器模式") browser_mode_name = "云浏览器" if actual_browser_type == "cloud" else "本地浏览器" print(f"5. 正在初始化{browser_mode_name}...") await init_browser_session( browser_type=actual_browser_type, headless=HEADLESS, url="about:blank" ) print(f" ✅ {browser_mode_name}初始化完成\n") # 6. 创建 Agent Runner print("6. 创建 Agent Runner...") print(f" - Skills 目录: {SKILLS_DIR}") print(f" - 模型: {RUN_CONFIG.model}") store = FileSystemTraceStore(base_path=TRACE_STORE_PATH) runner = AgentRunner( trace_store=store, llm_call=create_openrouter_llm_call(model=f"anthropic/{RUN_CONFIG.model}"), skills_dir=SKILLS_DIR, debug=DEBUG ) # 7. 创建交互控制器 interactive = InteractiveController( runner=runner, store=store, enable_stdin_check=True ) # 8. 任务信息 task_name = RUN_CONFIG.name or base_dir.name print("=" * 60) print(f"{task_name}") print("=" * 60) print("💡 交互提示：") print(" - 执行过程中输入 'p' 或 'pause' 暂停并进入交互模式") print(" - 执行过程中输入 'q' 或 'quit' 停止执行") print("=" * 60) print() # 9. 判断是新建还是恢复 resume_trace_id = args.trace if resume_trace_id: existing_trace = await store.get_trace(resume_trace_id) if not existing_trace: print(f"\n错误: Trace 不存在: {resume_trace_id}") sys.exit(1) print(f"恢复已有 Trace: {resume_trace_id[:8]}...") print(f" - 状态: {existing_trace.status}") print(f" - 消息数: {existing_trace.total_messages}") else: print(f"启动新 Agent...") print() final_response = "" current_trace_id = resume_trace_id current_sequence = 0 should_exit = False try: # 配置 run_config = RUN_CONFIG if resume_trace_id: initial_messages = None run_config.trace_id = resume_trace_id else: initial_messages = messages run_config.name = f"{task_name}：调研任务" while not should_exit: if current_trace_id: run_config.trace_id = current_trace_id final_response = "" # 如果 trace 已完成/失败且没有新消息，进入交互菜单 if current_trace_id and initial_messages is None: check_trace = await store.get_trace(current_trace_id) if check_trace and check_trace.status in ("completed", "failed"): if check_trace.status == "completed": print(f"\n[Trace] ✅ 已完成") print(f" - Total messages: {check_trace.total_messages}") print(f" - Total cost: ${check_trace.total_cost:.4f}") else: print(f"\n[Trace] ❌ 已失败: {check_trace.error_message}") current_sequence = check_trace.head_sequence menu_result = await interactive.show_menu(current_trace_id, current_sequence) if menu_result["action"] == "stop": break elif menu_result["action"] == "continue": new_messages = menu_result.get("messages", []) if new_messages: initial_messages = new_messages run_config.after_sequence = menu_result.get("after_sequence") else: initial_messages = [] run_config.after_sequence = None continue break initial_messages = [] print(f"{'▶️ 开始执行...' if not current_trace_id else '▶️ 继续执行...'}") # 执行 Agent paused = False try: async for item in runner.run(messages=initial_messages, config=run_config): # 检查用户中断 cmd = interactive.check_stdin() if cmd == 'pause': print("\n⏸️ 正在暂停执行...") if current_trace_id: await runner.stop(current_trace_id) await asyncio.sleep(0.5) menu_result = await interactive.show_menu(current_trace_id, current_sequence) if menu_result["action"] == "stop": should_exit = True paused = True break elif menu_result["action"] == "continue": new_messages = menu_result.get("messages", []) if new_messages: initial_messages = new_messages after_seq = menu_result.get("after_sequence") if after_seq is not None: run_config.after_sequence = after_seq paused = True break else: initial_messages = [] run_config.after_sequence = None paused = True break elif cmd == 'quit': print("\n🛑 用户请求停止...") if current_trace_id: await runner.stop(current_trace_id) should_exit = True break # 处理 Trace 对象 if isinstance(item, Trace): current_trace_id = item.trace_id if item.status == "running": print(f"[Trace] 开始: {item.trace_id[:8]}...") elif item.status == "completed": print(f"\n[Trace] ✅ 完成") print(f" - Total messages: {item.total_messages}") print(f" - Total cost: ${item.total_cost:.4f}") elif item.status == "failed": print(f"\n[Trace] ❌ 失败: {item.error_message}") elif item.status == "stopped": print(f"\n[Trace] ⏸️ 已停止") # 处理 Message 对象 elif isinstance(item, Message): current_sequence = item.sequence if item.role == "assistant": content = item.content if isinstance(content, dict): text = content.get("text", "") tool_calls = content.get("tool_calls") if text and not tool_calls: final_response = text print(f"\n[Response] Agent 回复：") print(text) elif text: preview = text[:150] + "..." if len(text) > 150 else text print(f"[Assistant] {preview}") elif item.role == "tool": content = item.content tool_name = "unknown" if isinstance(content, dict): tool_name = content.get("tool_name", "unknown") if item.description and item.description != tool_name: desc = item.description[:80] if len(item.description) > 80 else item.description print(f"[Tool Result] ✅ {tool_name}: {desc}...") else: print(f"[Tool Result] ✅ {tool_name}") except Exception as e: print(f"\n执行出错: {e}") import traceback traceback.print_exc() if paused: if should_exit: break continue if should_exit: break # Runner 退出后显示交互菜单 if current_trace_id: menu_result = await interactive.show_menu(current_trace_id, current_sequence) if menu_result["action"] == "stop": break elif menu_result["action"] == "continue": new_messages = menu_result.get("messages", []) if new_messages: initial_messages = new_messages run_config.after_sequence = menu_result.get("after_sequence") else: initial_messages = [] run_config.after_sequence = None continue break except KeyboardInterrupt: print("\n\n用户中断 (Ctrl+C)") if current_trace_id: await runner.stop(current_trace_id) finally: # 清理浏览器会话 try: await kill_browser_session() except Exception: pass # 7. 输出结果 if final_response: print() print("=" * 60) print("Agent 响应:") print("=" * 60) print(final_response) print("=" * 60) print() output_file = output_dir / "result.txt" with open(output_file, 'w', encoding='utf-8') as f: f.write(final_response) print(f"✓ 结果已保存到: {output_file}") print() # 可视化提示 if current_trace_id: print("=" * 60) print("可视化 Step Tree:") print("=" * 60) print("1. 启动 API Server:") print(" python3 api_server.py") print() print("2. 浏览器访问:") print(" http://localhost:8000/api/traces") print() print(f"3. Trace ID: {current_trace_id}") print("=" * 60) if __name__ == "__main__": asyncio.run(main())