Add per-game adventure text with RAG-based retrieval

Players can now paste the full text of a freely available adventure
when creating a game, and the DM will follow it instead of inventing
its own plot/NPCs/locations. Reuses the existing rulebook RAG
pipeline (chunking, local embedding) rather than injecting the raw
text into every turn, since real adventure modules range from a few
pages to hundreds — far beyond what fits in a prompt.

- New adventure_chunks table (game-scoped, unlike the global
  rulebook_chunks) + Game.adventure_text storing the raw source.
- ingest_adventure_text() chunks/embeds synchronously during
  POST /api/games when adventure_text is non-empty.
- build_adventure_rag_block() retrieves by similarity to the latest
  player message, scoped to game_id — plus always includes chunk 0
  (the adventure's opening) regardless of the query, since early
  Session-0 messages rarely resemble the adventure's actual hook and
  pure similarity search could miss the beginning entirely.
- System prompt instructs the DM to follow provided adventure
  excerpts strictly, deviating only when players clearly go off-script.
- Frontend: optional adventure-text field in the game creation form,
  a has_adventure flag surfaced as a small badge on the game card and
  session header.

Verified with an isolated two-game test that chunks/retrieval never
leak across games (the critical failure mode here), and live against
x.ai: a custom-written one-shot's specific NPCs, location, and hook
appeared verbatim in the DM's opening scene instead of invented ones.

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

backend/app/models/__init__.py

@@ -1,3 +1,4 @@
+from app.models.adventure_chunk import AdventureChunk
 from app.models.character import Character
 from app.models.game import Game, GameParticipant
 from app.models.message import Message
@@ -5,4 +6,13 @@ from app.models.rulebook_chunk import RulebookChunk
 from app.models.user import User
 from app.models.world_state import WorldState
 
-__all__ = ["User", "Game", "GameParticipant", "Character", "Message", "RulebookChunk", "WorldState"]
+__all__ = [
+    "User",
+    "Game",
+    "GameParticipant",
+    "Character",
+    "Message",
+    "RulebookChunk",
+    "WorldState",
+    "AdventureChunk",
+]

backend/app/models/adventure_chunk.py

@@ -0,0 +1,23 @@
+import uuid
+
+from pgvector.sqlalchemy import Vector
+from sqlalchemy import ForeignKey, Integer, Text
+from sqlalchemy.dialects.postgresql import UUID
+from sqlalchemy.orm import Mapped, mapped_column
+
+from app.db import Base
+from app.models.rulebook_chunk import EMBEDDING_DIM
+
+
+class AdventureChunk(Base):
+    __tablename__ = "adventure_chunks"
+
+    id: Mapped[uuid.UUID] = mapped_column(
+        UUID(as_uuid=True), primary_key=True, default=uuid.uuid4
+    )
+    game_id: Mapped[uuid.UUID] = mapped_column(
+        UUID(as_uuid=True), ForeignKey("games.id", ondelete="CASCADE"), 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)

backend/app/models/game.py

@@ -27,6 +27,9 @@ class Game(Base):
     # DM-only bookkeeping (name/current_hp/max_hp per monster) — never serialized to any
     # API response, since HP/AC of NPCs is meant to stay secret from players.
     monsters: Mapped[list] = mapped_column(JSONB, nullable=False, default=list)
+    # Raw pasted adventure-module text (if any) — chunked/embedded into adventure_chunks for
+    # retrieval; kept here verbatim as the source of truth for future re-ingestion.
+    adventure_text: Mapped[str] = mapped_column(Text, nullable=False, default="")
     created_at: Mapped[datetime] = mapped_column(
         server_default=func.now(), nullable=False, index=True
     )