fix: 20q answers truncate at sentence boundary, not mid-word

Instead of a raw 6-word slice (which left dangling fragments like
'Partly - Not exclusively American; has'), extract the first complete
sentence (up to 10 words). Falls back to the 6-word cap only if no
sentence boundary is found in the response.

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

matrixbot/commands.py

@@ -2823,7 +2823,10 @@ async def _answer_20q(thing: str, category: str, question: str) -> str:
             ) as response:
                 data = await response.json()
                 raw = data.get("message", {}).get("content", "").strip()
-                # Hard cap at 6 words — enough for a real answer, not enough to name-drop
+                # Take the first sentence; fall back to a 6-word hard cap
+                m = re.search(r"^[^.!?\n]+[.!?]", raw)
+                if m and len(m.group(0).split()) <= 10:
+                    return m.group(0).strip()
                 words = raw.split()
                 return " ".join(words[:6]) if words else "..."
     except Exception as e: