feat: news story cards in briefing — backend embeds structured RSS items in metadata

Previously metadata only stored rss_item_ids (integers); the full item data
was discarded after LLM synthesis. Now rss_items (id, title, url, source,
snippet, published_at) is also stored so clients can render per-story cards
without additional API calls.

Web BriefingView: replaces bare reaction-row buttons with news cards showing
source, headline (linked), 2-line snippet, and 👍/👎 per card.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

src/fabledassistant/services/briefing_pipeline.py

@@ -416,6 +416,18 @@ async def run_compilation(
         max_items=10,
     )
     rss_item_ids = [item["id"] for item in filtered_rss if item.get("id")]
+    rss_items_meta = [
+        {
+            "id": item["id"],
+            "title": item.get("title", ""),
+            "url": item.get("url", ""),
+            "source": item.get("feed_title", ""),
+            "snippet": (item.get("content") or "")[:300],
+            "published_at": item.get("published_at"),
+        }
+        for item in filtered_rss
+        if item.get("id")
+    ]
 
     # Weather staleness gate — returns None if data is >24h old
     weather_card = parse_weather_card_data(weather_rows[0], temp_unit) if weather_rows else None
@@ -449,7 +461,7 @@ async def run_compilation(
     # ── Post-processing ─────────────────────────────────────────────────────────
     await upsert_task_snapshots(user_id, all_tasks)
 
-    metadata: dict = {"rss_item_ids": rss_item_ids, "weather": weather_card}
+    metadata: dict = {"rss_item_ids": rss_item_ids, "rss_items": rss_items_meta, "weather": weather_card}
 
     if not internal_text and not external_text:
         logger.warning("Briefing compilation produced no content for user %d slot %s", user_id, slot)