From a6543c1dc5740d9634cca72660af4ed87da9889f Mon Sep 17 00:00:00 2001
From: Bryan Van Deusen <bryan.vandeusen@fabledsword.com>
Date: Wed, 8 Apr 2026 22:07:24 -0400
Subject: [PATCH] feat(briefing): cluster news by topic for thematic synthesis
 instead of flat headlines

---
 .../services/briefing_pipeline.py             | 39 ++++++++++++++-----
 1 file changed, 30 insertions(+), 9 deletions(-)

diff --git a/src/fabledassistant/services/briefing_pipeline.py b/src/fabledassistant/services/briefing_pipeline.py
index 65b20d2..b5900fa 100644
--- a/src/fabledassistant/services/briefing_pipeline.py
+++ b/src/fabledassistant/services/briefing_pipeline.py
@@ -450,17 +450,38 @@ def _unified_user_prompt(internal_data: dict, external_data: dict, slot: str, te
             lines.append("  (Identify free blocks between events for focused work.)")
         lines.append("")
 
-    # News highlights (top 3 with excerpts — right panel shows full list)
+    # News — clustered by topic for thematic synthesis
     rss = external_data.get("rss_items") or []
     if rss:
-        lines.append("NEWS HIGHLIGHTS (weave 1-2 into your briefing naturally; the full list is shown separately):")
-        for item in rss[:3]:
-            source = item.get("feed_title") or item.get("source") or "News"
-            title = item.get("title", "")
-            excerpt = (item.get("content") or item.get("snippet") or "")[:500].strip()
-            lines.append(f"  [{source}] {title}")
-            if excerpt:
-                lines.append(f"    {excerpt}")
+        # Group articles by their primary topic
+        clusters: dict[str, list[dict]] = {}
+        uncategorized: list[dict] = []
+        for item in rss:
+            topics = item.get("topics") or []
+            if topics:
+                primary = topics[0]
+                clusters.setdefault(primary, []).append(item)
+            else:
+                uncategorized.append(item)
+
+        # Sort clusters by size (most articles = most active theme)
+        sorted_clusters = sorted(clusters.items(), key=lambda x: len(x[1]), reverse=True)
+
+        lines.append("NEWS THEMES (synthesize 1-2 themes into your briefing; mention article count per theme):")
+        for topic, items in sorted_clusters[:4]:
+            count = len(items)
+            titles = [i.get("title", "") for i in items[:3]]
+            sources = list({i.get("feed_title") or i.get("source") or "News" for i in items})
+            lines.append(f"  [{topic.title()}] ({count} article{'s' if count != 1 else ''} from {', '.join(sources[:2])})")
+            for t in titles:
+                lines.append(f"    • {t}")
+            # Include one excerpt for the top cluster
+            if items == sorted_clusters[0][1]:
+                excerpt = (items[0].get("content") or items[0].get("snippet") or "")[:400].strip()
+                if excerpt:
+                    lines.append(f"    > {excerpt}")
+        if uncategorized:
+            lines.append(f"  [Other] ({len(uncategorized)} uncategorized article{'s' if len(uncategorized) != 1 else ''})")
         lines.append("")
 
     return "\n".join(lines)