1

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

@@ -1,6 +1,8 @@
 use platform_llm::{LlmClient, LlmMessage, LlmStreamDelta, LlmTextRequest};
 use serde_json::Value as JsonValue;
 
+use crate::llm_model_routing::CREATION_TEMPLATE_LLM_MODEL;
+
 #[derive(Clone, Copy, Debug)]
 pub(crate) struct CreationAgentLlmTurnErrorMessages<'a> {
     pub model_unavailable: &'a str,
@@ -69,6 +71,8 @@ fn build_creation_agent_llm_request(
         LlmMessage::system(system_prompt),
         LlmMessage::user(user_prompt),
     ])
+    .with_model(CREATION_TEMPLATE_LLM_MODEL)
+    .with_responses_api()
     .with_web_search(enable_web_search)
 }
 
@@ -79,10 +83,14 @@ pub(crate) async fn request_creation_agent_json_turn<E>(
     build_error: impl Fn(String) -> E,
 ) -> Result<JsonValue, E> {
     let response = llm_client
-        .request_text(LlmTextRequest::new(vec![
-            LlmMessage::system(system_prompt),
-            LlmMessage::user(user_prompt),
-        ]))
+        .request_text(
+            LlmTextRequest::new(vec![
+                LlmMessage::system(system_prompt),
+                LlmMessage::user(user_prompt),
+            ])
+            .with_model(CREATION_TEMPLATE_LLM_MODEL)
+            .with_responses_api(),
+        )
         .await
         .map_err(|error| build_error(error.to_string()))?;
     parse_json_response_text(response.content.as_str())
@@ -160,6 +168,8 @@ fn read_reply_text(parsed: &JsonValue) -> Option<String> {
 
 #[cfg(test)]
 mod tests {
+    use crate::llm_model_routing::CREATION_TEMPLATE_LLM_MODEL;
+
     use super::{
         build_creation_agent_llm_request, extract_reply_text_from_partial_json,
         parse_json_response_text,
@@ -188,6 +198,8 @@ mod tests {
             build_creation_agent_llm_request("系统提示".to_string(), "用户提示".to_string(), true);
 
         assert!(request.enable_web_search);
+        assert_eq!(request.model.as_deref(), Some(CREATION_TEMPLATE_LLM_MODEL));
+        assert_eq!(request.protocol, platform_llm::LlmTextProtocol::Responses);
         assert_eq!(request.messages.len(), 2);
     }
 }