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/models/rulebook_chunk.py

@@ -0,0 +1,23 @@
+import uuid
+
+from pgvector.sqlalchemy import Vector
+from sqlalchemy import Integer, String, Text
+from sqlalchemy.dialects.postgresql import JSONB, UUID
+from sqlalchemy.orm import Mapped, mapped_column
+
+from app.db import Base
+
+EMBEDDING_DIM = 384
+
+
+class RulebookChunk(Base):
+    __tablename__ = "rulebook_chunks"
+
+    id: Mapped[uuid.UUID] = mapped_column(
+        UUID(as_uuid=True), primary_key=True, default=uuid.uuid4
+    )
+    source_document: Mapped[str] = mapped_column(String(length=200), nullable=False, index=True)
+    chunk_index: Mapped[int] = mapped_column(Integer, nullable=False)
+    content: Mapped[str] = mapped_column(Text, nullable=False)
+    embedding: Mapped[list[float]] = mapped_column(Vector(EMBEDDING_DIM), nullable=False)
+    doc_metadata: Mapped[dict] = mapped_column(JSONB, nullable=False, default=dict)