Fix market review catalyst snippets (ZhuLinsen#1241)

* fix: preserve market review catalyst details

Author: ZhuLinsen

docs/CHANGELOG.md

@@ -25,6 +25,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/).
 - [测试] 补充设置项帮助元数据、API schema、前端弹窗交互测试，并修复 Bot 名称路由与调度时间 provider 测试的离线 CI 稳定性问题。
 - [修复] 港股日线跳过不支持港股的内置历史数据源，避免港股代码错配到非港股市场数据。
 - [修复] 修正分析 API 对北交所 `BJ` 前缀与 `.BJ` 后缀股票代码的校验，保持前端自动补全与 Tushare `ts_code` 调用格式一致。
+- [修复] 大盘复盘“近三日催化线索”改为明确展示摘要片段、来源日期和 URL，避免把搜索摘要截断内容误呈现为完整事件。
 
 ## [3.15.0] - 2026-05-05
 

src/market_analyzer.py

@@ -728,34 +728,61 @@ def _build_sector_block(self, overview: MarketOverview) -> str:
         return "\n".join(lines)
 
     def _build_news_block(self, news: List) -> str:
-        """Build a compact news catalyst table for the rendered report."""
+        """Build a source-aware news catalyst table for the rendered report."""
         if not news:
             return ""
         if self._get_review_language() == "en":
             lines = [
                 "#### News Catalysts",
-                "| # | Headline | Signal |",
-                "|---|----------|--------|",
+                "| # | Headline | Snippet / Lead | Source |",
+                "|---|----------|----------------|--------|",
             ]
         else:
             lines = [
                 "#### 近三日催化线索",
-                "| 序号 | 事件/标题 | 关注点 |",
-                "|------|-----------|--------|",
+                "| 序号 | 事件/标题 | 摘要/线索片段 | 来源 |",
+                "|------|-----------|----------------|------|",
             ]
 
         for idx, item in enumerate(news[:5], 1):
-            if hasattr(item, "title"):
-                title = getattr(item, "title", "") or "-"
-                snippet = getattr(item, "snippet", "") or ""
-            else:
-                title = item.get("title", "-") or "-"
-                snippet = item.get("snippet", "") or ""
-            title = self._escape_table_cell(str(title).strip()[:42])
-            signal = self._escape_table_cell(str(snippet).strip().replace("\n", " ")[:58] or "-")
-            lines.append(f"| {idx} | {title} | {signal} |")
+            title = self._escape_table_cell(
+                self._compact_news_text(self._get_news_field(item, "title"), limit=80) or "-"
+            )
+            snippet = self._escape_table_cell(
+                self._compact_news_text(self._get_news_field(item, "snippet"), limit=180) or "-"
+            )
+            source = self._escape_table_cell(self._format_news_source_cell(item) or "-")
+            lines.append(f"| {idx} | {title} | {snippet} | {source} |")
         return "\n".join(lines)
 
+    @staticmethod
+    def _get_news_field(item: Any, field: str) -> str:
+        if hasattr(item, field):
+            value = getattr(item, field, "") or ""
+        elif isinstance(item, dict):
+            value = item.get(field, "") or ""
+        else:
+            value = ""
+        return str(value).strip()
+
+    @classmethod
+    def _format_news_source_cell(cls, item: Any) -> str:
+        source = cls._compact_news_text(cls._get_news_field(item, "source"), limit=40)
+        date_text = cls._compact_news_text(cls._get_news_field(item, "published_date"), limit=24)
+        url = cls._compact_news_text(cls._get_news_field(item, "url"), limit=0)
+        label_parts = [part for part in (source, date_text) if part]
+        label = " / ".join(label_parts)
+        if url:
+            return f"[{label or 'URL'}]({url})"
+        return label
+
+    @staticmethod
+    def _compact_news_text(value: str, *, limit: int) -> str:
+        text = " ".join(str(value or "").split())
+        if limit <= 0 or len(text) <= limit:
+            return text
+        return text[: max(0, limit - 3)].rstrip() + "..."
+
     @staticmethod
     def _format_optional_number(value: float) -> str:
         return "N/A" if value in (None, 0, 0.0) else f"{value:.2f}"
@@ -847,13 +874,15 @@ def _build_review_prompt(self, overview: MarketOverview, news: List) -> str:
         news_text = ""
         for i, n in enumerate(news[:6], 1):
             # 兼容 SearchResult 对象和字典
-            if hasattr(n, 'title'):
-                title = n.title[:50] if n.title else ''
-                snippet = n.snippet[:100] if n.snippet else ''
-            else:
-                title = n.get('title', '')[:50]
-                snippet = n.get('snippet', '')[:100]
-            news_text += f"{i}. {title}\n   {snippet}\n"
+            title = self._compact_news_text(self._get_news_field(n, "title"), limit=90)
+            snippet = self._compact_news_text(self._get_news_field(n, "snippet"), limit=220)
+            source = self._compact_news_text(self._get_news_field(n, "source"), limit=60)
+            published_date = self._compact_news_text(self._get_news_field(n, "published_date"), limit=30)
+            url = self._compact_news_text(self._get_news_field(n, "url"), limit=180)
+            meta_parts = [part for part in (source, published_date) if part]
+            meta = f" ({' / '.join(meta_parts)})" if meta_parts else ""
+            url_line = f"\n   URL: {url}" if url else ""
+            news_text += f"{i}. {title}{meta}\n   {snippet or '-'}{url_line}\n"
 
         # 按 region 组装市场概况与板块区块（美股无涨跌家数、板块数据）
         stats_block = ""

tests/test_market_analyzer_generate_text.py

@@ -840,6 +840,72 @@ def test_inject_data_into_review_matches_reference_style_chinese_headings(self):
         assert "#### 近三日催化线索" in result
         assert "AI算力板块走强" in result
 
+    def test_news_block_labels_snippets_and_preserves_source_url(self):
+        from src.market_analyzer import MarketAnalyzer
+
+        ma = MarketAnalyzer.__new__(MarketAnalyzer)
+        ma.config = SimpleNamespace(report_language="zh")
+        ma.region = "cn"
+        long_snippet = (
+            "复盘必读 2026-05-06 复盘的意义在于更清晰地把握市场脉搏，"
+            "综合描述 A 股三大指数今日集体反弹，成交额放大，科技成长方向领涨。"
+        )
+
+        result = ma._build_news_block([
+            {
+                "title": "A股收评：科创50指数放量反弹涨5.47% 两市成交额重回3万亿元",
+                "snippet": long_snippet,
+                "source": "东方财富",
+                "published_date": "2026-05-06",
+                "url": "https://example.com/news/1",
+            }
+        ])
+
+        assert "摘要/线索片段" in result
+        assert "关注点" not in result
+        assert "成交额放大" in result
+        assert "[东方财富 / 2026-05-06](https://example.com/news/1)" in result
+
+    def test_news_block_uses_dash_when_source_metadata_missing(self):
+        from src.market_analyzer import MarketAnalyzer
+
+        ma = MarketAnalyzer.__new__(MarketAnalyzer)
+        ma.config = SimpleNamespace(report_language="zh")
+        ma.region = "cn"
+
+        result = ma._build_news_block([
+            {
+                "title": "政策利好带动板块活跃",
+                "snippet": "相关主题成交放大",
+            }
+        ])
+
+        assert "| 1 | 政策利好带动板块活跃 | 相关主题成交放大 | - |" in result
+        assert "| 1 | 政策利好带动板块活跃 | 相关主题成交放大 | source |" not in result
+
+    def test_review_prompt_caps_news_url_context(self):
+        from src.market_analyzer import MarketOverview
+
+        ma = self._make_market_analyzer_with_mock_generate_text(return_value="review")
+        long_url = "https://example.com/redirect?" + "utm_campaign=" + ("x" * 420)
+
+        prompt = ma._build_review_prompt(
+            MarketOverview(date="2026-05-06"),
+            [
+                {
+                    "title": "A股收评：指数放量反弹",
+                    "snippet": "科技成长方向领涨",
+                    "source": "测试来源",
+                    "published_date": "2026-05-06",
+                    "url": long_url,
+                }
+            ],
+        )
+
+        assert long_url not in prompt
+        assert "URL: https://example.com/redirect?" in prompt
+        assert ("x" * 220) not in prompt
+
     def test_market_light_snapshot_marks_defensive_market_red(self):
         from src.market_analyzer import MarketIndex, MarketOverview