Add web search knowledge base, message tagging, and word-memory tip topics

Introduces websearch.py (Tavily) + knowledge.py to ground chat responses
in search results, tagging.py to tag user and assistant messages via LLM
and pick related topics for the Discord useless-tips job, and
word_memory.py to track recent conversation nouns (surfaced in the new
WordPool.vue sidebar) used to pick tip topics close to a related tag.

backend/app/main.py

@@ -7,13 +7,31 @@ from fastapi.middleware.cors import CORSMiddleware
 from app.core.config import CORS_ORIGINS
 from app.core.discord_bot import start_discord_bot
 from app.core.scheduler import start_scheduler
-from app.db.database import init_db
+from app.core.word_memory import seed_from_history
+from app.db.database import SessionLocal, init_db
+from app.db.models import Message
 from app.api import chat, memory, logs, system
 
 
+def _seed_word_memory_from_db() -> None:
+    db = SessionLocal()
+    try:
+        rows = (
+            db.query(Message.content)
+            .filter(Message.role.in_(["user", "assistant"]))
+            .order_by(Message.created_at.desc())
+            .limit(200)
+            .all()
+        )
+        seed_from_history([content for (content,) in rows])
+    finally:
+        db.close()
+
+
 @asynccontextmanager
 async def lifespan(app: FastAPI):
     init_db()
+    _seed_word_memory_from_db()
     start_scheduler()
     asyncio.create_task(start_discord_bot())
     yield