feat: RSS embeddings, semantic news in chat, article-to-chat, richer briefings

- Embed RSS items at fetch time (nomic-embed-text); backfill at startup
- Semantic news search injected into chat system prompt ("Recent News You've Seen")
  when items match query above 0.55 cosine threshold (independent of note RAG)
- "Discuss in chat" button on news cards — creates a seeded conversation with
  the article title + full content, navigates directly to the new chat
- Briefing compilation now passes 500-char article excerpts (not just headlines)
  to the LLM and uses 8192 num_ctx to accommodate the larger prompt

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

src/fabledassistant/services/briefing_pipeline.py

@@ -233,7 +233,7 @@ async def _gather_external(user_id: int) -> dict:
 
 # ── LLM synthesis ─────────────────────────────────────────────────────────────
 
-async def _llm_synthesise(system_prompt: str, user_prompt: str, model: str) -> str:
+async def _llm_synthesise(system_prompt: str, user_prompt: str, model: str, num_ctx: int = 4096) -> str:
     """Single non-streaming LLM call. Returns the assistant's response text."""
     payload = {
         "model": model,
@@ -242,7 +242,7 @@ async def _llm_synthesise(system_prompt: str, user_prompt: str, model: str) -> s
             {"role": "user", "content": user_prompt},
         ],
         "stream": False,
-        "options": {"num_ctx": 4096, "temperature": 0.4},
+        "options": {"num_ctx": num_ctx, "temperature": 0.4},
     }
     try:
         async with httpx.AsyncClient(timeout=120.0) as client:
@@ -309,13 +309,17 @@ def _unified_user_prompt(internal_data: dict, external_data: dict, slot: str, te
             lines.append(f"  (and {len(overdue) - 3} more)")
         lines.append("")
 
-    # News highlights (top 3 — right panel shows full list)
+    # News highlights (top 3 with excerpts — right panel shows full list)
     rss = external_data.get("rss_items") or []
     if rss:
-        lines.append("NEWS HIGHLIGHTS (mention 1-2 briefly, the full list is shown separately):")
+        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"
-            lines.append(f"  [{source}] {item.get('title', '')}")
+            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}")
         lines.append("")
 
     return "\n".join(lines)
@@ -427,6 +431,7 @@ async def run_compilation(
         _unified_system_prompt(profile_context),
         _unified_user_prompt(internal_data_filtered, external_data_filtered, slot, temp_unit),
         model,
+        num_ctx=8192,
     )
 
     # ── Post-processing ─────────────────────────────────────────────────────────