v2.1.0 数据质量检查+自动重新探索+审核拒绝复盘

- 新增数据质量评估：按类别核心字段（参数/上下文/发布日期/组织等）计算覆盖度 - 质量不足自动重新探索（限1次）：根据缺失字段生成4个针对性搜索词，重新搜索+抓取+提取 - 填充模板升级：补充AI模型完整字段（架构/开源/价格/能力），要求输出带URL的data_sources - 提交附引用链接：从提取内容收集标题+URL，随产品数据提交给ParamHub - 新增审核监控线程：提交后轮询审核状态，检测到拒绝时记录拒绝理由 - 审核拒绝复盘：大模型分析拒绝理由→生成定向搜索词→补搜缺失信息→重新提取填充→重新提交 - 复盘实测：deepseek-v4-flash-0731 被拒(缺参数量)后自动补全 37B/MoE/128K/价格，重新提交成功
2026-08-13 23:00:51 +08:00
parent a0b870ee98
commit 9260542aa8
3 changed files with 616 additions and 40 deletions
@@ -126,6 +126,30 @@ class ParamHubClient:
            print(f"获取审核数量失败: {str(e)}")
            return 0
    
+    def get_review_status(self, review_id):
+        """
+        获取审核状态
+        Returns:
+            {
+                'status': 'pending'/'approved'/'rejected',
+                'reject_reason': str (被拒时的理由),
+                'review': dict
+            } or None
+        """
+        try:
+            response = self._request('GET', f'{self.base_url}/api/reviews/{review_id}')
+            if response.status_code == 200:
+                review = response.json()
+                return {
+                    'status': review.get('status', 'pending'),
+                    'reject_reason': review.get('reject_reason', ''),
+                    'review': review
+                }
+            return None
+        except Exception as e:
+            print(f"获取审核状态失败: {str(e)}")
+            return None
+    
    def send_notification(self, message):
        """发送通知到后台管理"""
        try:
@@ -211,7 +211,12 @@ class ProcessMonitor:
                    self._fail_step(session_id, 3, str(e))
            
            # 步骤4: 提取产品数据（调用大模型筛选相关内容）
-            if not self._check_pause(session_id):
+            # 可重试：质量不足时重新探索（限1次）
+            retry_explored = False
+            while True:
+                if self._check_pause(session_id):
+                    break
+                
                self._start_step(session_id, product_name, 4, '提取产品数据(大模型)')
                try:
                    # 构建任务文本
@@ -311,14 +316,19 @@ class ProcessMonitor:
                                    'agent_output': agent_result.get('output', '')[:2000]
                                }, status='skipped')
                                result['message'] = '大模型未找到相关数据且无兜底内容'
+                                break
                    else:
                        self._fail_step(session_id, 4, f"大模型调用失败: {agent_result.get('error', '未知错误')}")
                        result['message'] = f'大模型调用失败: {agent_result.get("error")}'
+                        break
                except Exception as e:
                    self._fail_step(session_id, 4, str(e))
-            
-            # 步骤5: 填充字段（调用大模型生成数据并检查格式）
-            if not self._check_pause(session_id) and all_data['extracted_data']:
+                    break
+                
+                # 步骤5: 填充字段（调用大模型生成数据并检查格式）
+                if self._check_pause(session_id) or not all_data['extracted_data']:
+                    break
+                
                self._start_step(session_id, product_name, 5, '填充字段(大模型)')
                try:
                    # 构建任务文本
@@ -341,6 +351,10 @@ class ProcessMonitor:
                            
                            if validation_result.get('valid'):
                                all_data['filled_data'] = product_data
+                                all_data['data_sources'] = fill_parsed.get('data_sources', [])
+                                
+                                # 质量检查：核心字段覆盖度
+                                quality = self._assess_data_quality(product_data, category)
                                
                                self._complete_step(session_id, 5, {
                                    'filled': True,
@@ -350,32 +364,90 @@ class ProcessMonitor:
                                    'product_data': product_data,
                                    'format_check': format_check,
                                    'validation': validation_result,
+                                    'quality': quality,
                                    'agent_output': fill_agent_result.get('output', '')[:2000]
                                })
-                                logger.info(f"[{session_id}] 步骤5完成: 数据生成成功，格式验证通过")
+                                logger.info(f"[{session_id}] 步骤5完成: 数据生成成功，质量评分={quality.get('score', 0):.0%}")
+                                
+                                # 质量不足且未重试过 → 重新探索
+                                if not quality.get('sufficient') and not retry_explored:
+                                    retry_explored = True
+                                    logger.info(f"[{session_id}] 数据质量不足({quality.get('score', 0):.0%})，触发重新探索")
+                                    
+                                    # 重新探索：换更精确的关键词重新搜索+抓取
+                                    explore_result = self._re_explore(
+                                        session_id, product_name, category, subcategory, all_data, quality
+                                    )
+                                    
+                                    if explore_result:
+                                        logger.info(f"[{session_id}] 重新探索完成，新增 {explore_result.get('new_fetched', 0)} 条内容，重新提取")
+                                        continue  # 重新执行步骤4/5
+                                    else:
+                                        logger.warning(f"[{session_id}] 重新探索未获取新内容，使用现有数据提交")
+                                        break
+                                else:
+                                    break
                            else:
                                # 格式验证失败，记录问题
                                self._fail_step(session_id, 5, f"数据格式验证失败: {validation_result.get('errors', [])}")
                                result['message'] = '数据格式验证失败'
+                                break
                        else:
                            error_msg = fill_parsed.get('message', '未知错误') if fill_parsed else '解析失败'
                            self._fail_step(session_id, 5, f"大模型执行失败: {error_msg}")
                            result['message'] = f'大模型执行失败: {error_msg}'
+                            break
                    else:
                        self._fail_step(session_id, 5, f"大模型调用失败: {fill_agent_result.get('error', '未知错误')}")
                        result['message'] = f'大模型调用失败: {fill_agent_result.get("error")}'
+                        break
                except Exception as e:
                    self._fail_step(session_id, 5, str(e))
+                    break
            
-            # 步骤6: 提交审核（直接调用ParamHub API，不再依赖智能体）
+            # 步骤6: 提交审核（直接调用ParamHub API，附引用链接）
            if not self._check_pause(session_id) and all_data['filled_data']:
                self._start_step(session_id, product_name, 6, '提交审核')
                try:
                    category_type = self._get_category_type(category)
                    subcategory_id = subcategory
+                    
+                    # 组装提交数据：附加引用链接等元信息
+                    submit_data = dict(all_data['filled_data'])
+                    
+                    # 引用链接：从提取内容中收集（标题+URL）
+                    reference_links = []
+                    seen_urls = set()
+                    for item in all_data.get('extracted_data', {}).get('relevant_contents', []):
+                        url = item.get('url', '')
+                        if url and url not in seen_urls:
+                            seen_urls.add(url)
+                            reference_links.append({
+                                'title': item.get('title', url[:60]),
+                                'url': url
+                            })
+                    # 补充数据源中带URL的引用
+                    for src in all_data.get('data_sources', []):
+                        if isinstance(src, dict):
+                            url = src.get('url', '') or src.get('link', '')
+                            if url and url not in seen_urls:
+                                seen_urls.add(url)
+                                reference_links.append({
+                                    'title': src.get('title', src.get('name', url[:60])),
+                                    'url': url
+                                })
+                    
+                    if reference_links:
+                        submit_data['reference_links'] = reference_links
+                        submit_data['_data_sources'] = all_data.get('data_sources', [])
+                    
+                    # 标记重试/探索信息（若有）
+                    if retry_explored:
+                        submit_data['_re_explored'] = True
+                    
                    success, review_id_or_error = paramhub_client.submit_for_review(
                        category_type,
-                        all_data['filled_data'],
+                        submit_data,
                        subcategory_id
                    )
                    
@@ -385,7 +457,9 @@ class ProcessMonitor:
                            'submitted': True,
                            'agent': 'ParamHub API',
                            'review_id': review_id,
-                            'product_data': all_data['filled_data']
+                            'product_data': submit_data,
+                            'reference_links_count': len(reference_links),
+                            're_explored': retry_explored
                        })
                        
                        result['success'] = True
@@ -403,7 +477,12 @@ class ProcessMonitor:
                            review_id=review_id,
                            details=all_data
                        )
-                        logger.info(f"[{session_id}] 步骤6完成: 提交成功, review_id={review_id}")
+                        logger.info(f"[{session_id}] 步骤6完成: 提交成功, review_id={review_id}, 引用链接 {len(reference_links)} 条")
+                        
+                        # 启动审核监控线程：被拒时按理由复盘重跑
+                        self._start_review_monitor(
+                            session_id, product_name, category, subcategory, review_id
+                        )
                    else:
                        self._fail_step(session_id, 6, f"提交失败: {review_id_or_error}")
                        result['message'] = f'提交失败: {review_id_or_error}'
@@ -705,7 +784,7 @@ class ProcessMonitor:
                "参考API文档: http://192.168.2.8:12007/hz4th_coder/param-hub-python/src/branch/master/API.md"
            )
        
-        # 构建相关内容ID列表
+        # 构建相关内容ID列表（含URL，便于大模型输出引用链接）
        relevant_ids = extracted_data.get('relevant_ids', [])
        relevant_contents = extracted_data.get('relevant_contents', [])
        
@@ -714,7 +793,11 @@ class ProcessMonitor:
            for item in relevant_contents:
                aid = item.get('id', '')
                title = item.get('title', '')
-                content_lines.append(f"ID {aid}: {title}")
+                url = item.get('url', '')
+                if url:
+                    content_lines.append(f"ID {aid}: {title} (URL: {url})")
+                else:
+                    content_lines.append(f"ID {aid}: {title}")
            relevant_text = '\n'.join(content_lines)
        elif relevant_ids:
            relevant_text = '\n'.join([f"ID {aid}" for aid in relevant_ids])
@@ -843,6 +926,465 @@ class ProcessMonitor:
            'warnings': warnings
        }
    
+    def _assess_data_quality(self, product_data, category):
+        """
+        评估产品数据质量：核心字段覆盖度
+        Returns:
+            {
+                'score': float (0-1),
+                'sufficient': bool,
+                'missing': [缺失的核心字段名],
+                'filled': [已填充的字段名]
+            }
+        """
+        category_type = self._get_category_type(category)
+        
+        # 各类别核心字段定义
+        core_fields = {
+            'model': ['organization', 'parameters', 'context_length', 'publish_date'],
+            'gpu': ['manufacturer', 'memory_gb', 'cuda_cores', 'price_usd'],
+            'cpu': ['manufacturer', 'cores', 'threads', 'base_clock'],
+            'dynamic': ['organization']
+        }
+        fields = core_fields.get(category_type, core_fields['dynamic'])
+        
+        filled = []
+        missing = []
+        for f in fields:
+            val = product_data.get(f)
+            if val is not None and val != '' and val != 'null':
+                filled.append(f)
+            else:
+                missing.append(f)
+        
+        # 附加信息丰富度（价格、能力指标等加分项）
+        bonus_fields = {
+            'model': ['mmlu', 'input_price', 'output_price', 'is_open_source', 'architecture', 'license'],
+            'gpu': ['tensor_cores', 'release_year', 'boost_clock'],
+            'cpu': ['boost_clock', 'price_usd', 'release_year'],
+            'dynamic': []
+        }
+        bonus = bonus_fields.get(category_type, [])
+        bonus_filled = [f for f in bonus if product_data.get(f) not in (None, '', 'null')]
+        
+        score = (len(filled) + 0.5 * len(bonus_filled)) / (len(fields) + 0.5 * len(bonus))
+        score = min(1.0, max(0.0, score))
+        
+        # 核心字段至少填满 60% 且无全部缺失才视为达标；
+        # 若核心字段一个都没有（score 很低），视为不达标触发重新探索
+        sufficient = score >= 0.6 and len(filled) >= 2
+        
+        return {
+            'score': round(score, 3),
+            'sufficient': sufficient,
+            'missing': missing,
+            'filled': filled,
+            'bonus_filled': bonus_filled
+        }
+    
+    def _build_explore_keywords(self, product_name, category, quality):
+        """根据缺失字段生成重新探索的搜索关键词列表"""
+        category_type = self._get_category_type(category)
+        missing = set(quality.get('missing', []))
+        keywords = []
+        
+        # 按缺失字段生成针对性搜索词
+        if category_type == 'model':
+            if 'parameters' in missing:
+                keywords.append(f'{product_name} 参数 参数量')
+            if 'context_length' in missing:
+                keywords.append(f'{product_name} context length 上下文')
+            if 'publish_date' in missing:
+                keywords.append(f'{product_name} release date 发布')
+            if 'organization' in missing:
+                keywords.append(f'{product_name} 厂商 公司')
+            # 通用补充
+            keywords.append(f'{product_name} 规格 性能')
+            keywords.append(f'{product_name} 价格 API')
+        elif category_type == 'gpu':
+            if 'memory_gb' in missing:
+                keywords.append(f'{product_name} 显存 memory')
+            if 'cuda_cores' in missing:
+                keywords.append(f'{product_name} CUDA cores')
+            if 'price_usd' in missing:
+                keywords.append(f'{product_name} price 价格')
+            keywords.append(f'{product_name} 规格 参数')
+        elif category_type == 'cpu':
+            if 'cores' in missing:
+                keywords.append(f'{product_name} cores 核心')
+            if 'threads' in missing:
+                keywords.append(f'{product_name} threads 线程')
+            if 'base_clock' in missing:
+                keywords.append(f'{product_name} base clock 频率')
+            keywords.append(f'{product_name} 规格 参数')
+        else:
+            keywords.append(f'{product_name} 参数 规格')
+        
+        # 去重，最多4个
+        seen = set()
+        result = []
+        for kw in keywords:
+            if kw not in seen:
+                seen.add(kw)
+                result.append(kw)
+            if len(result) >= 4:
+                break
+        
+        return result
+    
+    def _re_explore(self, session_id, product_name, category, subcategory, all_data, quality):
+        """
+        重新探索：根据缺失字段生成更精确的关键词，重新搜索+抓取
+        成功返回新抓取数量，失败返回 None
+        """
+        try:
+            logger.info(f"[{session_id}] 重新探索开始，缺失字段: {quality.get('missing')}")
+            
+            # 生成探索关键词
+            keywords = self._build_explore_keywords(product_name, category, quality)
+            logger.info(f"[{session_id}] 探索关键词: {keywords}")
+            
+            new_fetched = 0
+            new_ids = []
+            
+            for kw in keywords:
+                if self._check_pause(session_id):
+                    break
+                
+                try:
+                    internet_results = search_service.search_internet(kw, max_results=5, use_cache=False)
+                except Exception as e:
+                    logger.warning(f"[{session_id}] 探索搜索失败 [{kw}]: {e}")
+                    continue
+                
+                if not internet_results:
+                    continue
+                
+                for r in internet_results:
+                    if self._check_pause(session_id):
+                        break
+                    url = r.get('url', '')
+                    if not url:
+                        continue
+                    # 跳过已抓取过的URL
+                    existing = db.search_articles(url)
+                    if existing and len(existing) > 0:
+                        continue
+                    
+                    fetch_result = search_service.fetch_url_content(url)
+                    if fetch_result.get('success'):
+                        try:
+                            article_id = db.add_article(
+                                product_names=[product_name],
+                                category=category or '',
+                                keywords=[kw],
+                                summary=fetch_result.get('description', '')[:200],
+                                content=fetch_result.get('content', ''),
+                                source=url,
+                                url=url,
+                                search_title=fetch_result.get('title', url[:50])
+                            )
+                            new_ids.append(article_id)
+                            new_fetched += 1
+                            logger.info(f"[{session_id}] 探索抓取新增: ID={article_id} {fetch_result.get('title', '')[:30]}")
+                        except Exception as e:
+                            logger.warning(f"[{session_id}] 探索保存失败 {url}: {e}")
+                    
+                    time.sleep(0.3)
+            
+            if new_fetched == 0:
+                logger.info(f"[{session_id}] 重新探索未获取到新内容")
+                return None
+            
+            # 把新抓取的内容加入 fetched_contents（供步骤4重新筛选）
+            fetched_contents = all_data.setdefault('fetched_contents', [])
+            for aid in new_ids:
+                article = db.get_article_by_id(aid)
+                if article:
+                    fetched_contents.append({
+                        'id': aid,
+                        'url': article.get('url', ''),
+                        'title': article.get('search_title', ''),
+                        'content': (article.get('content') or '')[:500]
+                    })
+            
+            # 清除旧提取结果，强制重新提取
+            all_data['extracted_data'] = None
+            all_data['filled_data'] = None
+            
+            return {'new_fetched': new_fetched, 'new_ids': new_ids}
+            
+        except Exception as e:
+            logger.error(f"[{session_id}] 重新探索异常: {e}")
+            return None
+    
+    # ===== 审核监控与复盘 =====
+    
+    def _start_review_monitor(self, session_id, product_name, category, subcategory, review_id):
+        """启动审核监控线程：轮询审核状态，被拒时按理由复盘重跑"""
+        thread = threading.Thread(
+            target=self._monitor_review,
+            args=(session_id, product_name, category, subcategory, review_id),
+            daemon=True
+        )
+        thread.start()
+        logger.info(f"[{session_id}] 审核监控已启动: review_id={review_id}")
+    
+    def _monitor_review(self, session_id, product_name, category, subcategory, review_id):
+        """轮询审核状态（最多30次，每次60秒）"""
+        for i in range(30):
+            time.sleep(60)
+            try:
+                status_info = paramhub_client.get_review_status(review_id)
+                if not status_info:
+                    logger.warning(f"[{session_id}] 审核状态查询失败(review={review_id})，第{i+1}次")
+                    continue
+                
+                status = status_info.get('status')
+                if status == 'approved':
+                    logger.info(f"[{session_id}] 审核通过! review_id={review_id}")
+                    try:
+                        db.add_process_history(
+                            product_name=product_name,
+                            category=category,
+                            subcategory=subcategory,
+                            status='approved',
+                            review_id=review_id,
+                            details={'message': '审核通过'}
+                        )
+                    except Exception:
+                        pass
+                    return
+                
+                elif status == 'rejected':
+                    reason = status_info.get('reject_reason', '') or '无具体理由'
+                    logger.warning(f"[{session_id}] 审核被拒! review_id={review_id}, 理由: {reason}")
+                    try:
+                        db.add_process_history(
+                            product_name=product_name,
+                            category=category,
+                            subcategory=subcategory,
+                            status='rejected',
+                            review_id=review_id,
+                            details={'message': f'审核被拒: {reason}'}
+                        )
+                    except Exception:
+                        pass
+                    
+                    # 按拒绝理由复盘重跑
+                    self._review_retry(session_id, product_name, category, subcategory, review_id, reason)
+                    return
+                
+                # pending：继续等待
+                logger.info(f"[{session_id}] 审核状态: pending (第{i+1}次轮询)")
+                
+            except Exception as e:
+                logger.error(f"[{session_id}] 审核监控异常: {e}")
+        
+        logger.info(f"[{session_id}] 审核监控结束（30次轮询未出结果）")
+    
+    def _review_retry(self, session_id, product_name, category, subcategory, review_id, reason):
+        """
+        审核被拒后的复盘重跑：
+        1. 让大模型分析拒绝理由，得出缺失项和搜索建议
+        2. 定向搜索补齐缺失信息
+        3. 重新提取、填充、提交
+        """
+        try:
+            logger.info(f"[{session_id}] 开始审核复盘: 拒绝理由={reason}")
+            
+            # 获取原会话数据（步骤数据里取 product_data 和引用链接）
+            steps = db.get_process_steps(session_id)
+            original_data = None
+            for st in steps:
+                if st.get('step_number') == 5 and st.get('step_data'):
+                    try:
+                        sd = json.loads(st['step_data']) if isinstance(st['step_data'], str) else st['step_data']
+                        if sd.get('product_data'):
+                            original_data = sd['product_data']
+                            break
+                    except Exception:
+                        pass
+            
+            # 1. 大模型分析拒绝理由，给出缺失项和搜索建议
+            analyze_prompt = (
+                f"产品「{product_name}」提交到参数库审核被拒绝。\n"
+                f"拒绝理由：{reason}\n\n"
+                f"当前已提交的数据：\n{json.dumps(original_data or {}, ensure_ascii=False, indent=2)}\n\n"
+                "请分析：\n"
+                "1. 根据拒绝理由，判断审核方最关注哪些缺失/错误的信息\n"
+                "2. 给出需要重点补充的字段（如 parameters/context_length/publish_date/价格等）\n"
+                "3. 给出3-4个最有效的搜索关键词（中文或英文），用于搜索补充这些信息\n\n"
+                "只输出JSON：\n"
+                "{\"analysis\": \"分析结论\", \"missing_fields\": [\"字段名\"], \"search_keywords\": [\"关键词1\", \"关键词2\"]}"
+            )
+            
+            ok, result = llm_client.chat(
+                [{'role': 'user', 'content': analyze_prompt}],
+                temperature=0.2,
+                max_tokens=4096,
+                timeout=300
+            )
+            
+            keywords = []
+            missing_fields = []
+            if ok:
+                parsed = llm_client._extract_json(result)
+                if parsed:
+                    keywords = parsed.get('search_keywords', [])
+                    missing_fields = parsed.get('missing_fields', [])
+                    logger.info(f"[{session_id}] 复盘分析: 缺失字段={missing_fields}, 搜索词={keywords}")
+            
+            if not keywords:
+                # 兜底关键词
+                keywords = [f'{product_name} 参数 规格', f'{product_name} 发布 价格']
+            
+            # 2. 定向搜索补齐
+            all_data = {'library_results': [], 'internet_results': [], 'fetched_contents': [], 'extracted_data': None, 'filled_data': None}
+            new_fetched = 0
+            
+            for kw in keywords[:4]:
+                try:
+                    internet_results = search_service.search_internet(kw, max_results=5, use_cache=False)
+                except Exception as e:
+                    logger.warning(f"[{session_id}] 复盘搜索失败 [{kw}]: {e}")
+                    continue
+                
+                for r in internet_results:
+                    url = r.get('url', '')
+                    if not url:
+                        continue
+                    existing = db.search_articles(url)
+                    if existing and len(existing) > 0:
+                        continue
+                    
+                    fetch_result = search_service.fetch_url_content(url)
+                    if fetch_result.get('success'):
+                        try:
+                            article_id = db.add_article(
+                                product_names=[product_name],
+                                category=category or '',
+                                keywords=[kw],
+                                summary=fetch_result.get('description', '')[:200],
+                                content=fetch_result.get('content', ''),
+                                source=url,
+                                url=url,
+                                search_title=fetch_result.get('title', url[:50])
+                            )
+                            all_data['fetched_contents'].append({
+                                'id': article_id,
+                                'url': url,
+                                'title': fetch_result.get('title', ''),
+                                'content': (fetch_result.get('content') or '')[:500]
+                            })
+                            new_fetched += 1
+                        except Exception as e:
+                            logger.warning(f"[{session_id}] 复盘保存失败 {url}: {e}")
+                    time.sleep(0.3)
+            
+            if new_fetched == 0:
+                logger.warning(f"[{session_id}] 复盘未获取新内容，无法重新提交")
+                return
+            
+            # 3. 重新提取+填充（直接调用步骤4/5 的核心逻辑，复用 _run_process 的片段）
+            # 构建新会话数据
+            all_data['library_results'] = []
+            
+            # 步骤4：提取
+            task_text = self._build_agent_task(product_name, category, subcategory, all_data)
+            agent_result = self._call_llm(task_text)
+            
+            if not agent_result.get('success'):
+                logger.error(f"[{session_id}] 复盘提取失败: {agent_result.get('error')}")
+                return
+            
+            parsed = self._parse_agent_response(agent_result.get('output', ''))
+            relevant_ids = parsed.get('relevant_ids', []) if parsed else []
+            
+            # 兜底：没筛出就用全部新抓内容
+            if not relevant_ids:
+                relevant_ids = [c['id'] for c in all_data['fetched_contents']]
+            
+            relevant_contents = []
+            for aid in relevant_ids:
+                article = db.get_article_by_id(aid)
+                if article:
+                    relevant_contents.append({
+                        'id': aid,
+                        'title': article.get('search_title', ''),
+                        'url': article.get('url', ''),
+                        'content': article.get('content', ''),
+                        'summary': article.get('summary', ''),
+                        'analysis': ''
+                    })
+            
+            if not relevant_contents:
+                logger.warning(f"[{session_id}] 复盘无相关内容可提取")
+                return
+            
+            all_data['extracted_data'] = {
+                'name': product_name,
+                'relevant_ids': relevant_ids,
+                'relevant_contents': relevant_contents,
+                'confidence': 'medium'
+            }
+            
+            # 步骤5：填充
+            fill_task_text = self._build_fill_fields_task(product_name, category, subcategory, all_data['extracted_data'])
+            fill_agent_result = self._call_llm(fill_task_text)
+            
+            if not fill_agent_result.get('success'):
+                logger.error(f"[{session_id}] 复盘填充失败: {fill_agent_result.get('error')}")
+                return
+            
+            fill_parsed = self._parse_fill_agent_response(fill_agent_result.get('output', ''))
+            if not fill_parsed or not fill_parsed.get('success'):
+                logger.error(f"[{session_id}] 复盘填充解析失败")
+                return
+            
+            product_data = fill_parsed.get('product_data', {})
+            
+            # 引用链接
+            reference_links = []
+            seen = set()
+            for item in relevant_contents:
+                url = item.get('url', '')
+                if url and url not in seen:
+                    seen.add(url)
+                    reference_links.append({'title': item.get('title', url[:60]), 'url': url})
+            if reference_links:
+                product_data['reference_links'] = reference_links
+            product_data['_review_retry'] = True
+            product_data['_original_review_id'] = review_id
+            
+            # 4. 重新提交
+            category_type = self._get_category_type(category)
+            success, new_review_id = paramhub_client.submit_for_review(
+                category_type, product_data, subcategory
+            )
+            
+            if success:
+                logger.info(f"[{session_id}] 复盘重新提交成功! 新review_id={new_review_id}")
+                try:
+                    db.add_process_history(
+                        product_name=product_name,
+                        category=category,
+                        subcategory=subcategory,
+                        status='resubmitted',
+                        review_id=new_review_id,
+                        details={'message': f'审核被拒后复盘重新提交，原review_id={review_id}', 'reject_reason': reason}
+                    )
+                except Exception:
+                    pass
+                
+                # 新提交也启动监控（避免递归过深，只监控一轮）
+                # 这里不再递归监控，记录即可
+            else:
+                logger.error(f"[{session_id}] 复盘重新提交失败: {new_review_id}")
+        
+        except Exception as e:
+            logger.error(f"[{session_id}] 审核复盘异常: {e}")
+    
    def _build_submit_task(self, product_name, category, subcategory, product_data):
        """构建步骤6提交审核的智能体任务文本"""
        # 读取模板