1

server-rs/crates/api-server/src/runtime_chat.rs

@@ -22,6 +22,7 @@ use module_runtime_story_compat::{
 use crate::{
     auth::AuthenticatedAccessToken,
     http_error::AppError,
+    llm_model_routing::RPG_STORY_LLM_MODEL,
     prompt::runtime_chat::{
         NPC_CHAT_TURN_REPLY_SYSTEM_PROMPT, NPC_CHAT_TURN_SUGGESTION_SYSTEM_PROMPT,
         NpcChatTurnPromptInput, build_deterministic_chat_suggestions,
@@ -227,6 +228,7 @@ where
     ]);
     reply_request.max_tokens = Some(700);
     reply_request.enable_web_search = state.config.rpg_llm_web_search_enabled;
+    reply_request.model = Some(RPG_STORY_LLM_MODEL.to_string());
 
     let reply_response = llm_client
         .stream_text(reply_request, |delta| {
@@ -254,6 +256,7 @@ where
     ]);
     suggestion_request.max_tokens = Some(200);
     suggestion_request.enable_web_search = state.config.rpg_llm_web_search_enabled;
+    suggestion_request.model = Some(RPG_STORY_LLM_MODEL.to_string());
     let suggestion_text = llm_client
         .request_text(suggestion_request)
         .await