1

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

@@ -15,7 +15,8 @@ use std::convert::Infallible;
 
 use crate::{
     api_response::json_success_body, auth::AuthenticatedAccessToken, http_error::AppError,
-    prompt::runtime_chat::*, request_context::RequestContext, state::AppState,
+    llm_model_routing::RPG_STORY_LLM_MODEL, prompt::runtime_chat::*,
+    request_context::RequestContext, state::AppState,
 };
 use module_runtime_story_compat::{
     RuntimeStoryPromptContextExtras, build_runtime_story_prompt_context, current_world_type,
@@ -587,6 +588,7 @@ async fn request_runtime_plain_text(
     ]);
     request.max_tokens = Some(400);
     request.enable_web_search = state.config.rpg_llm_web_search_enabled;
+    request.model = Some(RPG_STORY_LLM_MODEL.to_string());
 
     llm_client
         .request_text(request)
@@ -618,6 +620,7 @@ fn stream_plain_text_response<'a>(
         ]);
         request.max_tokens = Some(700);
         request.enable_web_search = enable_web_search;
+        request.model = Some(RPG_STORY_LLM_MODEL.to_string());
 
         let response = llm_client
             .stream_text(request, |_| {})