Thorsten
419f5e3a89
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>
23 lines
802 B
Python
23 lines
802 B
Python
TOOL_SCHEMA = {
|
|
"name": "propose_game_setup",
|
|
"description": (
|
|
"Call this once you know the desired genre/world, the intended length (one-shot vs. "
|
|
"campaign), and the player's experience level. Propose a fitting name and a short "
|
|
"description for the new game — the player can still edit both before creating it."
|
|
),
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"name": {
|
|
"type": "string",
|
|
"description": "A fitting, evocative name for the game.",
|
|
},
|
|
"description": {
|
|
"type": "string",
|
|
"description": "Short description covering genre and world/setting.",
|
|
},
|
|
},
|
|
"required": ["name", "description"],
|
|
},
|
|
}
|