first commit

tests/analyze_llm_calls.py

@@ -0,0 +1,156 @@
+"""
+分析LLM调用记录
+
+使用方法：
+    python tests/analyze_llm_calls.py tests/llm_calls_20251031_150543.json
+"""
+
+import sys
+import json
+
+
+def analyze_llm_calls(json_file):
+    """分析LLM调用记录"""
+    with open(json_file, 'r', encoding='utf-8') as f:
+        data = json.load(f)
+
+    print("\n" + "="*80)
+    print("LLM调用分析报告")
+    print("="*80)
+
+    print(f"\n总调用次数: {data['total_calls']}")
+
+    for i, call in enumerate(data['calls'], 1):
+        print(f"\n{'─'*80}")
+        print(f"调用 #{i}")
+        print('─'*80)
+
+        # 时间信息
+        start = call.get('timestamp_start', 'N/A')
+        end = call.get('timestamp_end', 'N/A')
+        print(f"时间: {start} -> {end}")
+
+        # 消息数
+        messages = call.get('messages', [[]])
+        if messages:
+            msg_count = len(messages[0])
+            print(f"输入消息数: {msg_count}")
+
+            # 显示最后一条消息类型
+            if messages[0]:
+                last_msg = messages[0][-1]
+                print(f"最后一条输入消息: {last_msg['type']}")
+
+        # 响应信息
+        response = call.get('response', {})
+        generations = response.get('generations', [])
+
+        if generations:
+            gen = generations[0]
+            msg = gen.get('message', {})
+
+            print(f"响应类型: {msg.get('type', 'N/A')}")
+
+            # 内容
+            content = msg.get('content', '')
+            if content:
+                preview = content[:100].replace('\n', ' ')
+                print(f"响应内容: {preview}...")
+
+            # 工具调用
+            tool_calls = msg.get('tool_calls', [])
+            if tool_calls:
+                print(f"工具调用: {len(tool_calls)} 个")
+                for tc in tool_calls:
+                    print(f"  - {tc['name']}")
+            else:
+                print("工具调用: 无")
+
+        # Token使用
+        llm_output = response.get('llm_output', {})
+        token_usage = llm_output.get('token_usage', {})
+        if token_usage:
+            print(f"Token使用: {token_usage.get('prompt_tokens', 0)} input + {token_usage.get('completion_tokens', 0)} output = {token_usage.get('total_tokens', 0)} total")
+
+    print("\n" + "="*80)
+    print("执行流程总结")
+    print("="*80)
+
+    # 分析执行流程
+    call_summaries = []
+    for i, call in enumerate(data['calls'], 1):
+        response = call.get('response', {})
+        generations = response.get('generations', [])
+
+        if generations:
+            msg = generations[0].get('message', {})
+            tool_calls = msg.get('tool_calls', [])
+
+            if tool_calls:
+                tools = [tc['name'] for tc in tool_calls]
+                call_summaries.append(f"调用#{i}: {', '.join(tools)}")
+            else:
+                content_preview = msg.get('content', '')[:50].replace('\n', ' ')
+                call_summaries.append(f"调用#{i}: 返回文本 ({content_preview}...)")
+
+    for summary in call_summaries:
+        print(f"  {summary}")
+
+    # 判断是否完成
+    print("\n" + "="*80)
+    print("状态判断")
+    print("="*80)
+
+    last_call = data['calls'][-1]
+    last_response = last_call.get('response', {})
+    last_generations = last_response.get('generations', [])
+
+    if last_generations:
+        last_msg = last_generations[0].get('message', {})
+        last_tool_calls = last_msg.get('tool_calls', [])
+
+        if not last_tool_calls:
+            print("⚠️  最后一次调用没有工具调用")
+            print("原因: SubAgent返回了纯文本响应，导致主Agent停止")
+            print("影响: Agent停止执行，未完成完整流程")
+            print("\n预期行为: 主Agent应该继续执行步骤3（并行搜索）")
+        else:
+            print("✅ 最后一次调用有工具调用，流程继续")
+    else:
+        print("❌ 无法判断状态")
+
+    # 检查是否完成意图分析
+    search_queries_created = False
+    for call in data['calls']:
+        response = call.get('response', {})
+        generations = response.get('generations', [])
+        if generations:
+            msg = generations[0].get('message', {})
+            tool_calls = msg.get('tool_calls', [])
+            for tc in tool_calls:
+                if tc['name'] == 'write_file' and '/search_queries.json' in str(tc.get('args', {})):
+                    search_queries_created = True
+
+    print("\n" + "="*80)
+    print("步骤完成情况")
+    print("="*80)
+    print(f"✅ 步骤1: 初始化 - 已完成 (/question.txt, /config.json)")
+    print(f"✅ 步骤2: 意图分析 - {'已完成' if search_queries_created else '未完成'} (/search_queries.json)")
+    print(f"❌ 步骤3: 并行搜索 - 未开始")
+    print(f"❌ 后续步骤 - 未开始")
+
+    print("\n" + "="*80)
+    print("建议")
+    print("="*80)
+    print("1. 问题根源: intent-analyzer SubAgent完成后返回纯文本，导致主Agent停止")
+    print("2. 解决方案: 修改主Agent的系统提示词，明确要求在SubAgent返回后继续执行下一步")
+    print("3. 或者: 检查LangGraph的recursion_limit配置，确保允许足够的步骤数")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) < 2:
+        print("使用方法: python analyze_llm_calls.py <json_file>")
+        sys.exit(1)
+
+    json_file = sys.argv[1]
+    analyze_llm_calls(json_file)