fix: pipeline content tracking + topic article preview

db_helper.py: save_article now calculates and persists word_count
generator.py: run_creator_blocking sets word_count for HTML-imported articles
writer.py: fix title regex stripping content-leading numbers (35岁后→岁后)
trends.py: fix Baidu hot_score str/int type comparison crash
database.py: add missing content_tasks.org_id ALTER TABLE migration
schemas.py + topics.py: topic list API returns article_count + articles[] previews
topics.html: table view and card view show article badges with word counts, clickable to open preview

Ultraworked with Sisyphus

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>

.omo/run-continuation/ses_1dede8a7affeG6DxtfPUOviXrp.json

@@ -1,11 +1,10 @@
 {
   "sessionID": "ses_1dede8a7affeG6DxtfPUOviXrp",
-  "updatedAt": "2026-06-17T08:18:52.213Z",
+  "updatedAt": "2026-06-23T00:31:03.722Z",
   "sources": {
     "background-task": {
-      "state": "active",
+      "state": "idle",
-      "reason": "2 background task(s) active",
+      "updatedAt": "2026-06-23T00:31:03.722Z"
-      "updatedAt": "2026-06-17T08:18:52.213Z"
     }
   }
 }

platform/backend/app/api/topics.py

@@ -66,7 +66,63 @@ def list_topics(
     else:
         query = query.order_by(sort_col.asc())
 
-    return query.offset(offset).limit(limit).all()
+    topics = query.offset(offset).limit(limit).all()
+    # Enrich with article count and previews
+    from ..models import Article
+    topic_ids = [t.id for t in topics]
+    if topic_ids:
+        article_rows = (
+            db.query(Article.topic_id, Article.platform, Article.title, Article.word_count, Article.status)
+            .filter(Article.topic_id.in_(topic_ids))
+            .all()
+        )
+        articles_by_topic: Dict[str, list] = {}
+        for ar in article_rows:
+            articles_by_topic.setdefault(ar.topic_id, []).append({
+                "platform": ar.platform,
+                "title": ar.title,
+                "word_count": ar.word_count,
+                "status": ar.status,
+            })
+    else:
+        articles_by_topic = {}
+
+    result = []
+    for t in topics:
+        t_dict = {
+            "id": t.id,
+            "field_id": t.field_id,
+            "field_name": t.field_name,
+            "org_id": t.org_id,
+            "title": t.title,
+            "format": t.format,
+            "core_concept": t.core_concept,
+            "audience_pain": t.audience_pain,
+            "unique_angle": t.unique_angle,
+            "priority": t.priority,
+            "priority_score": t.priority_score,
+            "total_score": t.total_score,
+            "status": t.status,
+            "tags": t.tags or [],
+            "custom_data": t.custom_data or {},
+            "scoring_data": t.scoring_data or {},
+            "lock_by": t.lock_by,
+            "lock_at": t.lock_at,
+            "series": t.series,
+            "created_at": t.created_at,
+            "updated_at": t.updated_at,
+            "generated_at": t.generated_at,
+            "reviewed_at": t.reviewed_at,
+            "ready_at": t.ready_at,
+            "published_at": t.published_at,
+            "compliance_score": t.compliance_score,
+            "platform_urls": t.platform_urls or {},
+            "cases": [],
+            "article_count": len(articles_by_topic.get(t.id, [])),
+            "articles": articles_by_topic.get(t.id, []),
+        }
+        result.append(t_dict)
+    return result
 
 
 @router.get("/stats")

platform/backend/app/core/generator.py

@@ -84,8 +84,9 @@ def run_creator_blocking(topic_id: str = None, timeout: int = 1800):
                             existing = db.query(Article).filter(Article.id == article_id).first()
                             if existing:
                                 existing.html_content = html
+                                existing.word_count = len(html)
                             else:
-                                db.add(Article(id=article_id, topic_id=topic_id, platform=platform_dir, file_path=f"db:{article_id}", html_content=html, status="draft"))
+                                db.add(Article(id=article_id, topic_id=topic_id, platform=platform_dir, file_path=f"db:{article_id}", html_content=html, word_count=len(html), status="draft"))
                             hf.unlink()
                     for platform_dir in ["zhihu", "wechat", "xiaohongshu"]:
                         pdir = dd / platform_dir

platform/backend/app/database.py

@@ -131,6 +131,7 @@ def init_db():
                 ("search_rankings", "org_id", "VARCHAR DEFAULT 'default'"),
                 ("geo_readiness_scores", "org_id", "VARCHAR DEFAULT 'default'"),
                 ("articles", "org_id", "VARCHAR DEFAULT 'default'"),
+                ("content_tasks", "org_id", "VARCHAR DEFAULT 'default'"),
                 ("topics", "series", "VARCHAR"),
             ]:
                 try:

platform/backend/app/schemas.py

@@ -138,6 +138,8 @@ class TopicResponse(TopicBase):
     compliance_score: Optional[int] = None
     platform_urls: Dict[str, str] = {}
     cases: List[Any] = []
+    article_count: int = 0
+    articles: List[Dict[str, Any]] = []
 
     model_config = ConfigDict(from_attributes=True)
 

platform/frontend/topics.html

@@ -109,6 +109,17 @@
                         <el-table-column prop="status" label="状态" width="90">
                             <template #default="scope"><span class="status-badge"><span class="status-dot" :class="scope.row.status"></span>{{ getStatusLabel(scope.row.status) }}</span></template>
                         </el-table-column>
+                        <el-table-column label="文章" width="140">
+                            <template #default="scope">
+                                <div v-if="scope.row.article_count > 0" style="display:flex;gap:4px;flex-wrap:wrap;">
+                                    <el-tag v-for="a in (scope.row.articles || [])" :key="a.platform" :type="a.status === 'published' ? 'success' : 'warning'" size="small" style="cursor:pointer;" @click="openTopicArticlePreview(scope.row, a)">
+                                        {{ platformShort(a.platform) }}
+                                        <span v-if="a.word_count" style="margin-left:2px;opacity:0.7;">{{ fmtWordCount(a.word_count) }}</span>
+                                    </el-tag>
+                                </div>
+                                <span v-else style="color:#c0c4cc;font-size:12px;">无</span>
+                            </template>
+                        </el-table-column>
                         <el-table-column prop="compliance_score" label="合规分" width="90">
                             <template #default="scope"><el-progress :percentage="scope.row.compliance_score || 0" :format="() => scope.row.compliance_score || '-'" :stroke-width="15"></el-progress></template>
                         </el-table-column>
@@ -145,6 +156,10 @@
                             <div class="topic-card-tags">
                                 <el-tag size="small" type="info">{{ topic.field }}</el-tag>
                                 <el-tag size="small" type="warning">合规{{ topic.compliance_score }}</el-tag>
+                                <el-tag v-for="a in (topic.articles || [])" :key="a.platform" size="small" :type="a.status === 'published' ? 'success' : 'warning'" style="cursor:pointer;" @click="openTopicArticlePreview(topic, a)">
+                                    {{ platformShort(a.platform) }}{{ a.word_count ? ' ' + fmtWordCount(a.word_count) : '' }}
+                                </el-tag>
+                                <el-tag v-if="topic.article_count === 0" size="small" type="info" effect="plain">无文章</el-tag>
                             </div>
                             <div class="topic-card-meta">
                                 <div>创建: {{ formatDate(topic.created_at) }}</div>
@@ -534,6 +549,20 @@ const TopicsApp = {
             });
         },
         platformName(platform) { return { zhihu: '知乎', wechat: '微信公众号', xiaohongshu: '小红书' }[platform] || platform; },
+        platformShort(platform) { return { zhihu: '知', wechat: '公', xiaohongshu: '红' }[platform] || platform; },
+        fmtWordCount(wc) { if (!wc) return ''; if (wc >= 1000) return (wc / 1000).toFixed(wc >= 10000 ? 0 : 1) + 'k'; return wc + ''; },
+        openTopicArticlePreview(topic, article) {
+            this.previewTopic = topic;
+            this.previewPlatform = article.platform;
+            this.previewVisible = true;
+            this.platformContents = {};
+            this.previewImages = {};
+            const token = this.getToken();
+            if (!token) return;
+            fetch(`/api/articles/${topic.id}/preview?platform=${article.platform}`, { headers: { 'Authorization': 'Bearer ' + token } })
+                .then(r => r.ok ? r.json() : null).then(d => { if (d && d.html) { this.platformContents[article.platform] = d.html; if (d.images) this.previewImages[article.platform] = d.images; } })
+                .catch(e => console.error(`加载${article.platform}预览失败:`, e));
+        },
         copyContent(platform) {
             const html = this.platformContents[platform];
             if (!html) { this.$message.warning('暂无内容可复制'); return; }

scripts/db_helper.py

@@ -246,12 +246,14 @@ def save_article(topic_id: str, platform: str, html_content: str, *, title: str
         from app.models import Article
         article_id = f"{platform}_{topic_id}"
         existing = db.query(Article).filter(Article.id == article_id).first()
+        word_count = len(content) if content else (len(html_content) if html_content else 0)
         if existing:
             existing.html_content = html_content
             if title:
                 existing.title = title
             if content:
                 existing.content = content
+            existing.word_count = word_count
         else:
             article = Article(
                 id=article_id,
@@ -261,6 +263,7 @@ def save_article(topic_id: str, platform: str, html_content: str, *, title: str
                 title=title,
                 content=content,
                 html_content=html_content,
+                word_count=word_count,
                 status="draft",
                 compliance_score=None
             )

scripts/trends.py

@@ -193,7 +193,8 @@ def fetch_baidu_hot() -> List[Dict]:
                     word = item.get("query", "").strip() or item.get("word", "").strip()
                     if not word:
                         continue
-                    hot_score = item.get("hotScore", 0) or item.get("heat", 0)
+                    hot_score_raw = item.get("hotScore", 0) or item.get("heat", 0)
+                    hot_score = int(hot_score_raw) if hot_score_raw else 0
                     desc = item.get("desc", "")
                     results.append({
                         "domain": _guess_domain(word, desc),

scripts/writer.py

@@ -557,7 +557,7 @@ class Writer:
                 line = line.strip()
                 if not line:
                     continue
-                line = re.sub(r'^\d+[.、)\s]+', '', line)
+                line = re.sub(r'^\d+[.、)）]\s*', '', line)
                 line = line.strip('*#- \t"\'"''"')
                 # 跳过思考/建议类输出（如"不如："、"或者："、"建议方案"等）
                 if re.match(r'^(不如|或者|建议|推荐|参考|方案[一二三]|第[一二三]种|以[下是]|标题[一二三]|选项)', line):