fix(kb-deep-analyzer): 添加进度日志和超时追踪

- SimpleAIClient.generate(): 添加 AI 调用开始/结束日志 - _analyze_chunk(): 添加分片分析耗时日志 - _analyze_chunks_concurrent(): 添加批次进度日志和总耗时统计 - 便于排查卡住问题和监控进度
2026-02-13 15:49:17 +08:00
parent c276df2d37
commit 99164f7ce6
2 changed files with 85 additions and 21 deletions
@@ -238,7 +238,7 @@ class SimpleAIClient:
        self.max_retries = 3  # 最大重试次数
        self.max_concurrent = 3  # 最大并发数

-    def generate(self, prompt: str, max_tokens: int = 1000) -> str:
+    def generate(self, prompt: str, max_tokens: int = 1000, task_info: str = None) -> str:
        """生成文本，支持重试"""
        # 每次调用时重新读取环境变量，解决 exec 传递问题
        api_key = os.environ.get("AI_API_KEY", self.api_key)
@@ -249,24 +249,35 @@ class SimpleAIClient:
        if not api_key:
            raise ValueError("AI_API_KEY 未设置，请配置环境变量")

+        task_desc = f"[{task_info}]" if task_info else ""
+
        last_error = None
        for attempt in range(self.max_retries):
            try:
+                import time
+                start_time = time.time()
+                print(f"[AI Client] {task_desc} 开始调用 AI...")
+                
                if provider == "openai":
-                    return self._call_openai(prompt, max_tokens, api_key, model, base_url)
+                    result = self._call_openai(prompt, max_tokens, api_key, model, base_url)
                elif provider == "zhipu":
-                    return self._call_zhipu(prompt, max_tokens, api_key, model, base_url)
+                    result = self._call_zhipu(prompt, max_tokens, api_key, model, base_url)
                elif provider == "minimax":
-                    return self._call_minimax(prompt, max_tokens, api_key, model, base_url)
+                    result = self._call_minimax(prompt, max_tokens, api_key, model, base_url)
                else:
                    raise ValueError(f"不支持的 AI 提供商: {provider}")
+                
+                elapsed = time.time() - start_time
+                print(f"[AI Client] {task_desc} AI 调用完成，耗时: {elapsed:.2f}秒")
+                return result
            except Exception as e:
+                elapsed = time.time() - start_time if 'start_time' in dir() else 0
                last_error = e
                if attempt < self.max_retries - 1:
-                    print(f"[AI Client] 第 {attempt + 1} 次调用失败，{self.max_retries - attempt - 1} 次重试剩余: {e}")
+                    print(f"[AI Client] {task_desc} 第 {attempt + 1} 次调用失败 ({elapsed:.2f}秒)，{self.max_retries - attempt - 1} 次重试剩余: {e}")
                    continue
                else:
-                    print(f"[AI Client] 调用失败，已重试 {self.max_retries} 次: {e}")
+                    print(f"[AI Client] {task_desc} 调用失败，已重试 {self.max_retries} 次: {e}")
                    raise

    def generate_json(self, prompt: str) -> Dict[str, Any]:
@@ -745,6 +756,9 @@ class DeepAnalyzer:

        print(f"[DeepAnalyzer] 分块: {num_chunks} 段，批次大小: {batch_size}")

+        import time
+        total_start_time = time.time()
+        
        # 批处理执行
        batch_results = {}  # 存储各批结果
        all_summaries = []
@@ -756,7 +770,9 @@ class DeepAnalyzer:
            batch_chunks = chunks[batch_idx:batch_end]
            batch_times = chunk_times[batch_idx:batch_end]

-            print(f"[DeepAnalyzer] 批次 {batch_num}/{total_batches}: 段 {batch_idx+1}-{batch_end}")
+            batch_start_time = time.time()
+            print(f"[DeepAnalyzer] === 批次 {batch_num}/{total_batches} 开始 ===")
+            print(f"[DeepAnalyzer] 段 {batch_idx+1}-{batch_end}，预计 {len(batch_chunks)} 个并发调用")

            # 并发执行当前批次
            batch_tasks = [(i, batch_chunks[j], batch_times[j][0], batch_times[j][1]) 
@@ -766,8 +782,10 @@ class DeepAnalyzer:
                futures = {executor.submit(self._analyze_chunk, task[1], task[0] + 1, metadata): task[0] 
                          for task in batch_tasks}

+                completed_in_batch = 0
                for future in concurrent.futures.as_completed(futures):
                    idx = futures[future]
+                    completed_in_batch += 1
                    try:
                        summary = future.result()
                        batch_results[idx] = {
@@ -776,7 +794,8 @@ class DeepAnalyzer:
                            'end_time': chunk_times[idx][1],
                            'summary': summary
                        }
-                        print(f"[DeepAnalyzer] 段 {idx + 1}/{num_chunks} 完成")
+                        elapsed = time.time() - batch_start_time
+                        print(f"[DeepAnalyzer] 段 {idx + 1}/{num_chunks} 完成 ({completed_in_batch}/{len(batch_chunks)}), 批次耗时: {elapsed:.2f}秒")
                    except Exception as e:
                        print(f"[DeepAnalyzer] 段 {idx + 1} 失败: {e}")
                        batch_results[idx] = {
@@ -792,12 +811,23 @@ class DeepAnalyzer:
                on_segment_complete(batch_summaries)

            all_summaries.extend(batch_summaries)
+            
+            batch_elapsed = time.time() - batch_start_time
+            print(f"[DeepAnalyzer] === 批次 {batch_num}/{total_batches} 完成，耗时: {batch_elapsed:.2f}秒 ===")
+
+        total_elapsed = time.time() - total_start_time
+        print(f"[DeepAnalyzer] 所有分块分析完成，总耗时: {total_elapsed:.2f}秒")

        # 按顺序整理结果
        all_summaries = [all_summaries[i] for i in range(len(all_summaries))]

        # 合并结果
+        print(f"[DeepAnalyzer] 开始合并各段摘要...")
+        merge_start = time.time()
        result = self._merge_summaries(all_summaries, title)
+        merge_elapsed = time.time() - merge_start
+        print(f"[DeepAnalyzer] 摘要合并完成，耗时: {merge_elapsed:.2f}秒")
+        
        result.timeline = self._build_timeline_from_chunks(all_summaries)

        return result
@@ -884,7 +914,13 @@ class DeepAnalyzer:
 请用中文详细回答，包括核心主题、关键要点和重要细节。"""

        try:
-            return self.ai_client.generate(prompt, max_tokens=2000)
+            import time
+            start_time = time.time()
+            print(f"[DeepAnalyzer] 开始分析分片 {chunk_index}...")
+            result = self.ai_client.generate(prompt, max_tokens=2000, task_info=f"分片 {chunk_index}")
+            elapsed = time.time() - start_time
+            print(f"[DeepAnalyzer] 分片 {chunk_index} 分析完成，耗时: {elapsed:.2f}秒")
+            return result
        except Exception as e:
            print(f"[DeepAnalyzer] 分片 {chunk_index} 分析失败: {e}")
            return f"第{chunk_index}段内容分析"