refac

backend/open_webui/main.py

@@ -583,6 +583,8 @@ from open_webui.utils.redis import get_redis_connection
 from open_webui.tasks import (
     redis_task_command_listener,
     list_task_ids_by_item_id,
+    has_active_tasks,
+    cleanup_task,
     create_task,
     stop_task,
     stop_item_tasks,
@@ -2063,20 +2065,19 @@ async def chat_completion(
             except BaseException as e:
                 log.debug(f'Error cleaning up MCP clients: {e}')
 
+            # Deregister this task, then emit chat:active=false if no others remain
             try:
-                if metadata.get('chat_id'):
-
-                    async def emit_inactive_event():
-                        try:
+                chat_id = metadata.get('chat_id')
+                task_id = metadata.get('task_id')
+                if chat_id and task_id:
+                    await cleanup_task(request.app.state.redis, task_id, chat_id)
+                    if not await has_active_tasks(request.app.state.redis, chat_id):
                         event_emitter = await get_event_emitter(metadata, update_db=False)
                         if event_emitter:
-                                await event_emitter({'type': 'chat:active', 'data': {'active': False}})
-                        except Exception:
-                            pass
-
                             try:
-                        # Shield the event emission so it finishes even if the main task is cancelled
-                        await asyncio.shield(emit_inactive_event())
+                                await asyncio.shield(
+                                    event_emitter({'type': 'chat:active', 'data': {'active': False}})
+                                )
                             except asyncio.CancelledError:
                                 pass
             except Exception:
@@ -2128,6 +2129,7 @@ async def chat_completion(
                 ),
                 id=chat_id,
             )
+            per_model_metadata['task_id'] = task_id
             task_ids.append(task_id)
 
         # Emit chat:active=true

src/lib/components/chat/Chat.svelte

@@ -1398,6 +1398,7 @@
 				autoScroll = true;
 				await tick();
 
+				// Mark all non-current assistant messages as done
 				if (history.currentId) {
 					for (const message of Object.values(history.messages)) {
 						if (
@@ -1411,24 +1412,24 @@
 					}
 				}
 
-				const taskRes = await getTaskIdsByChatId(localStorage.token, $chatId).catch((error) => {
-					return null;
-				});
-
-				if (taskRes) {
-					taskIds = taskRes.task_ids;
-				}
-
-				// If no active tasks and current message is incomplete, generation was interrupted
+				// Reconcile active tasks with message state:
+				// If the response is already done, remaining tasks are just background
+				// work (follow-ups, title gen) that shouldn't block the input.
+				const pendingTaskIds = await getTaskIdsByChatId(localStorage.token, $chatId)
+					.then((res) => res?.task_ids ?? [])
+					.catch(() => []);
 				const currentMessage = history.currentId ? history.messages[history.currentId] : null;
-				if (
-					currentMessage &&
-					currentMessage.role === 'assistant' &&
-					!currentMessage.done &&
-					(!taskIds || taskIds.length === 0)
-				) {
+				const responseComplete = currentMessage?.role === 'assistant' && currentMessage?.done;
+
+				if (pendingTaskIds.length > 0 && !responseComplete) {
+					taskIds = pendingTaskIds;
+				} else {
+					taskIds = null;
+					// No active tasks and message incomplete → generation was interrupted
+					if (currentMessage?.role === 'assistant' && !currentMessage.done) {
 						currentMessage.done = true;
 					}
+				}
 
 				await tick();