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>

frontend/src/api/games.ts

@@ -25,8 +25,26 @@ export interface Message {
   created_at: string;
 }
 
+export interface GameSetupProposal {
+  name: string;
+  description: string;
+}
+
+export interface GameSetupChatResponse {
+  messages: Record<string, unknown>[];
+  assistant_text: string | null;
+  proposal: GameSetupProposal | null;
+}
+
 export const listGames = () => apiFetch<Game[]>("/api/games");
 
+export const runGameSetupChat = (messages: Record<string, unknown>[], signal?: AbortSignal) =>
+  apiFetch<GameSetupChatResponse>("/api/games/setup-chat", {
+    method: "POST",
+    body: JSON.stringify({ messages }),
+    signal,
+  });
+
 export const createGame = (name: string, description: string) =>
   apiFetch<Game>("/api/games", { method: "POST", body: JSON.stringify({ name, description }) });