Add rulebook RAG pipeline and LLM-driven game setup wizard

RAG: switch Postgres to pgvector, chunk and embed the three D&D
rulebooks locally via sentence-transformers, and retrieve relevant
excerpts per DM turn (query = latest player message) to ground the
system prompt. Retrieval runs off the event loop and is capped by a
relevance threshold and a max character budget so it can't blow up
context size or cost.

Game setup wizard: creating a game now opens a short chat where the
DM asks about genre, length, and the player's experience level, then
proposes a name and description via a tool call. The player can edit
both before creating the game. Stateless endpoint — the frontend
carries the conversation, no DB needed since the game doesn't exist
yet.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

backend/app/rag/embeddings.py

@@ -0,0 +1,22 @@
+from functools import lru_cache
+
+from sentence_transformers import SentenceTransformer
+
+# Multilingual so German player messages retrieve relevant chunks from the
+# English-language rulebooks. 384-dim output, matching RulebookChunk.embedding.
+MODEL_NAME = "paraphrase-multilingual-MiniLM-L12-v2"
+
+
+@lru_cache
+def get_embedding_model() -> SentenceTransformer:
+    return SentenceTransformer(MODEL_NAME)
+
+
+def embed_texts(texts: list[str]) -> list[list[float]]:
+    model = get_embedding_model()
+    embeddings = model.encode(texts, normalize_embeddings=True, show_progress_bar=False)
+    return embeddings.tolist()
+
+
+def embed_query(text: str) -> list[float]:
+    return embed_texts([text])[0]