""" 图片模态特征提取研究示例 使用 Agent 模式 + Skills，研究应该提取什么样的图片模态特征 """ import argparse import os import sys import select 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", "*") 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.trace import ( FileSystemTraceStore, Trace, Message, ) from agent.llm import create_claude_code_llm_call # 导入自定义工具模块，触发 @tool 装饰器注册 sys.path.insert(0, str(Path(__file__).parent)) import tool # noqa: E402 def check_stdin() -> str | None: """非阻塞检查 stdin 是否有输入""" ready, _, _ = select.select([sys.stdin], [], [], 0) if ready: line = sys.stdin.readline().strip().lower() if line in ('p', 'pause'): return 'pause' if line in ('q', 'quit'): return 'quit' return None def _read_multiline() -> str: """读取多行输入，以连续两次回车（空行）结束""" print("\n请输入干预消息（连续输入两次回车结束）：") lines: list[str] = [] blank_count = 0 while True: line = input() if line == "": blank_count += 1 if blank_count >= 2: break lines.append("") else: blank_count = 0 lines.append(line) while lines and lines[-1] == "": lines.pop() return "\n".join(lines) async def show_interactive_menu( runner: AgentRunner, trace_id: str, current_sequence: int, store: FileSystemTraceStore, ): """显示交互式菜单""" print("\n" + "=" * 60) print(" 执行已暂停") print("=" * 60) print("请选择操作：") print(" 1. 插入干预消息并继续") print(" 2. 查看当前 GoalTree") print(" 3. 继续执行") print(" 4. 停止执行") print("=" * 60) while True: choice = input("请输入选项 (1-4): ").strip() if choice == "1": text = _read_multiline() if not text: print("未输入任何内容，取消操作") continue print(f"\n将插入干预消息并继续执行...") live_trace = await store.get_trace(trace_id) actual_sequence = live_trace.last_sequence if live_trace and live_trace.last_sequence else current_sequence return { "action": "continue", "messages": [{"role": "user", "content": text}], "after_sequence": actual_sequence, } elif choice == "2": goal_tree = await store.get_goal_tree(trace_id) if goal_tree and goal_tree.goals: print("\n当前 GoalTree:") print(goal_tree.to_prompt()) else: print("\n当前没有 Goal") continue elif choice == "3": print("\n继续执行...") return {"action": "continue"} elif choice == "4": print("\n停止执行...") return {"action": "stop"} else: print("无效选项，请重新输入") async def main(): parser = argparse.ArgumentParser(description="图片模态特征提取研究") parser.add_argument( "--trace", type=str, default=None, help="已有的 Trace ID，用于恢复继续执行", ) args = parser.parse_args() # 路径配置 base_dir = Path(__file__).parent project_root = base_dir.parent.parent prompt_path = base_dir / "test.prompt" output_dir = base_dir / "output" output_dir.mkdir(exist_ok=True) # 确保 input 和 knowledge 目录存在 input_dir = base_dir / "input" knowledge_dir = base_dir / "knowledge" input_dir.mkdir(exist_ok=True) knowledge_dir.mkdir(exist_ok=True) print("=" * 60) print("图片模态特征提取研究 (Agent 模式)") print("=" * 60) print() 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() # 加载 prompt print("1. 加载 prompt 配置...") prompt = SimplePrompt(prompt_path) # 构建消息 print("2. 构建任务消息...") messages = prompt.build_messages() # 创建 Agent Runner print("3. 创建 Agent Runner...") model_name = prompt.config.get('model', 'anthropic/claude-sonnet-4.6') print(f" - 模型: {model_name}") store = FileSystemTraceStore(base_path=".trace") runner = AgentRunner( trace_store=store, llm_call=create_claude_code_llm_call(model=model_name), skills_dir=None, debug=True ) # 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"4. 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"4. 启动新 Agent 模式...") print() final_response = "" current_trace_id = resume_trace_id current_sequence = 0 should_exit = False try: model_name = prompt.config.get('model', 'anthropic/claude-sonnet-4.6') if resume_trace_id: initial_messages = None config = RunConfig( model=model_name, temperature=float(prompt.config.get('temperature', 0.3)), max_iterations=1000, trace_id=resume_trace_id, enable_thinking=prompt.config.get('enable_thinking', False), thinking_budget_tokens=prompt.config.get('thinking_budget_tokens', 10000), ) else: initial_messages = messages config = RunConfig( model=model_name, temperature=float(prompt.config.get('temperature', 0.3)), max_iterations=1000, name="图片模态特征提取研究", enable_thinking=prompt.config.get('enable_thinking', False), thinking_budget_tokens=prompt.config.get('thinking_budget_tokens', 10000), ) while not should_exit: if current_trace_id: config.trace_id = current_trace_id final_response = "" # 检查 trace 状态 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 show_interactive_menu( runner, current_trace_id, current_sequence, store ) if menu_result["action"] == "stop": break elif menu_result["action"] == "continue": new_messages = menu_result.get("messages", []) if new_messages: initial_messages = new_messages config.after_sequence = menu_result.get("after_sequence") else: initial_messages = [] 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=config): # 检查用户中断 cmd = 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 show_interactive_menu( runner, current_trace_id, current_sequence, store ) 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: config.after_sequence = after_seq paused = True break else: initial_messages = [] 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 tokens: {item.total_tokens}") 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}") if tool_calls: for tc in tool_calls: tool_name = tc.get("function", {}).get("name", "unknown") print(f"[Tool Call] 🛠️ {tool_name}") elif item.role == "tool": content = item.content if isinstance(content, dict): tool_name = content.get("tool_name", "unknown") print(f"[Tool Result] ✅ {tool_name}") if item.description: desc = item.description[:80] if len(item.description) > 80 else item.description print(f" {desc}...") 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 show_interactive_menu( runner, current_trace_id, current_sequence, store ) if menu_result["action"] == "stop": break elif menu_result["action"] == "continue": new_messages = menu_result.get("messages", []) if new_messages: initial_messages = new_messages config.after_sequence = menu_result.get("after_sequence") else: initial_messages = [] 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) # 输出结果 if final_response: print() print("=" * 60) print("Agent 响应:") print("=" * 60) print(final_response) print("=" * 60) print() # 保存结果 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())