1

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

@@ -901,34 +901,49 @@ pub async fn stream_custom_world_agent_message(
         if let Err(error) = draft_writer.ensure_started(state.spacetime_client()).await {
             tracing::warn!(error = %error, "自定义世界模板生成草稿任务启动失败，主生成流程继续执行");
         }
-        let draft_sink = AiGenerationDraftSink::new(
-            AiGenerationDraftContext::new(
-                "custom_world",
-                owner_user_id_for_stream.as_str(),
-                session_id_for_stream.as_str(),
-                operation_id.as_str(),
-                "自定义世界模板生成草稿",
-            ),
-            state.spacetime_client().clone(),
-        );
-        // 聊天回复必须等本轮模型解析、进度与会话快照全部落库后，
-        // 再随最终 session 一次性返回，避免玩家先看到回复而进度仍停在旧状态。
-        let turn_result = run_custom_world_agent_turn(
-            CustomWorldAgentTurnRequest {
-                llm_client: state.llm_client(),
-                session: &session,
-                quick_fill_requested,
-                focus_card_id,
-            },
-            move |text| {
-                draft_sink.persist_visible_text_async(text);
-            },
-        )
-        .await;
-        if let Ok(result) = &turn_result {
+        let (reply_tx, mut reply_rx) = tokio::sync::mpsc::unbounded_channel::<String>();
+        // Agent turn 仍负责完整 JSON 解析和最终写回；这里把 replyText 增量桥接成前端可见的 SSE 分片。
+        let turn_result = {
+            let run_turn = run_custom_world_agent_turn(
+                CustomWorldAgentTurnRequest {
+                    llm_client: state.llm_client(),
+                    session: &session,
+                    quick_fill_requested,
+                    focus_card_id,
+                },
+                move |text| {
+                    let _ = reply_tx.send(text.to_string());
+                },
+            );
+            tokio::pin!(run_turn);
+
+            loop {
+                // 不等待最终 session 落库即可先推送回复进度；session/done 仍在 finalize 成功后发送。
+                tokio::select! {
+                    result = &mut run_turn => break result,
+                    maybe_text = reply_rx.recv() => {
+                        if let Some(text) = maybe_text {
+                            draft_writer
+                                .persist_visible_text(state.spacetime_client(), text.as_str())
+                                .await;
+                            yield Ok::<Event, Infallible>(custom_world_sse_json_event_or_error(
+                                "reply_delta",
+                                json!({ "text": text }),
+                            ));
+                        }
+                    }
+                }
+            }
+        };
+
+        while let Some(text) = reply_rx.recv().await {
             draft_writer
-                .persist_visible_text(state.spacetime_client(), result.assistant_reply_text.as_str())
+                .persist_visible_text(state.spacetime_client(), text.as_str())
                 .await;
+            yield Ok::<Event, Infallible>(custom_world_sse_json_event_or_error(
+                "reply_delta",
+                json!({ "text": text }),
+            ));
         }
 
         let finalize_input = match turn_result {