打通流水线闭环: trends+metrics+optimize_sources → collector

三大数据流精准注入采集器:

1. 热点趋势(trends) -> collector
   _get_trend_context() 读取 trends.json
   热搜注入 LLM 选题 prompt

2. 历史表现(metrics) -> collector
   scheduler 同步指标后按field聚合写入 feedback.json
   collector 读取后高互动领域获优先级提升

3. AI策略(optimize_sources) -> collector
   从 DB SystemConfig 读取 AI 建议注入 prompt

scripts/collector.py

@@ -377,6 +377,61 @@ class SustainabilityCollector:
             logger.warning(f"web_search失败 {source.name}: {e}")
             return []
 
+    def _get_trend_context(self) -> str:
+        """读取热点趋势数据和指标反馈, 返回markdown上下文"""
+        parts = []
+        try:
+            from trends import load_trends
+            trends = load_trends()
+            if trends:
+                lines = ["## 当前热点趋势", ""]
+                for t in trends[:5]:
+                    src = {"weibo": "🔥", "zhihu": "📖", "baidu": "🔍", "llm": "🤖"}.get(t.get("source", ""), "")
+                    lines.append(f"- {src} **{t['topic']}**（{t.get('platform','')}）：{t.get('reason','')[:80]}")
+                    kw = t.get("hot_keywords", [])
+                    if kw:
+                        lines.append(f"  搜索热词：{' '.join(kw[:3])}")
+                parts.append("\n".join(lines))
+        except Exception:
+            pass
+
+        metrics_file = DATA_DIR / "metrics_feedback.json"
+        if metrics_file.exists():
+            try:
+                feedback = json.loads(metrics_file.read_text(encoding='utf-8'))
+                top_domains = feedback.get("top_domains", [])
+                if top_domains:
+                    lines = ["## 历史表现反馈（高互动领域优先", ""]
+                    for d, s in top_domains[:3]:
+                        lines.append(f"- {d}：平均分 {s}")
+                    parts.append("\n".join(lines))
+            except Exception:
+                pass
+
+        try:
+            from app.database import SessionLocal
+            from app.models import SystemConfig
+            db = SessionLocal()
+            try:
+                sc = db.query(SystemConfig).filter(SystemConfig.key == "collector_ai_advice").first()
+                if sc and sc.value:
+                    advice = json.loads(sc.value)
+                    summary = advice.get("summary", "")
+                    new_cats = advice.get("suggested_new_categories", [])
+                    if summary:
+                        parts.append(f"## AI策略建议\n{summary}")
+                    if new_cats:
+                        suggested = [f"- {c['name']}（{c.get('reason','')[:50]}）" for c in new_cats[:2]]
+                        parts.append("建议关注的新方向：\n" + "\n".join(suggested))
+            except Exception:
+                pass
+            finally:
+                db.close()
+        except Exception:
+            pass
+
+        return "\n\n".join(parts)
+
     def _generate_topics_with_llm(self, cases: List[SustainabilityCase] = None, search_results: List[Dict] = None) -> List[SustainabilityTopic]:
         """用LLM基于采集数据生成选题（数据充分时精确生成，无数据时凭知识生成）"""
         try:
@@ -402,11 +457,15 @@ class SustainabilityCollector:
             case_lines = [f"- {c.title[:40]}({c.category})" for c in cases[:5]]
             data_section += "\n采集案例：\n" + "\n".join(case_lines) + "\n"
 
+        trend_context = self._get_trend_context()
+
         prompt = f"""你是一个内容策略师。基于以下信息，为「{target_category}」类别生成一个高质量选题。
 
 {data_section if data_section else "（当前无实时采集数据，请基于你对中文互联网趋势的了解直接生成）"}
 {existing_hint}
 
+{trend_context}
+
 输出一个选题，格式JSON：
 {{{{
   "title": "标题（20字内，含核心关键词）",