refac

backend/open_webui/main.py

@@ -1763,6 +1763,7 @@ async def chat_completion(
             'chat_id': form_data.pop('chat_id', None),
             'user_message': user_message,
             'user_message_id': user_message.get('id') if user_message else None,
+            'assistant_message_id': form_data.pop('assistant_message_id', None),
             'session_id': form_data.pop('session_id', None),
             'folder_id': form_data.pop('folder_id', None),
             'filter_ids': form_data.pop('filter_ids', []),

backend/open_webui/utils/middleware.py

@@ -2274,6 +2274,16 @@ async def process_chat_payload(request, form_data, user, metadata, model):
     if chat_id and user_message_id and not chat_id.startswith('local:'):
         db_messages = await load_messages_from_db(chat_id, user_message_id)
         if db_messages:
+            # Continue: frontend sends assistant_message_id when continuing
+            # an existing response. Load its content so the LLM sees prior output.
+            assistant_message_id = metadata.get('assistant_message_id')
+            if assistant_message_id:
+                assistant_message = await Chats.get_message_by_id_and_message_id(chat_id, assistant_message_id)
+                if assistant_message and (assistant_message.get('content') or assistant_message.get('output')):
+                    db_messages.append(
+                        {k: v for k, v in assistant_message.items() if k in ('role', 'content', 'output', 'files')}
+                    )
+
             system_message = get_system_message(form_data.get('messages', []))
             form_data['messages'] = [system_message, *db_messages] if system_message else db_messages
 
@@ -3015,7 +3025,6 @@ async def background_tasks_handler(ctx):
     tasks = ctx['tasks']
     event_emitter = ctx['event_emitter']
 
-
     message = None
     messages = []
 
@@ -4076,9 +4085,9 @@ async def streaming_chat_response_handler(response, ctx):
                                                         current_response_tool_call['function']['name'] = delta_name
 
                                                     if delta_arguments:
-                                                        current_response_tool_call['function']['arguments'] += (
-                                                            delta_arguments
-                                                        )
+                                                        current_response_tool_call['function'][
+                                                            'arguments'
+                                                        ] += delta_arguments
 
                                         # Emit pending tool calls in real-time
                                         if response_tool_calls:
@@ -4832,8 +4841,7 @@ async def streaming_chat_response_handler(response, ctx):
                                 code = sanitize_code(code)
 
                                 if CODE_INTERPRETER_BLOCKED_MODULES:
-                                    blocking_code = textwrap.dedent(
-                                        f"""
+                                    blocking_code = textwrap.dedent(f"""
                                         import builtins
     
                                         BLOCKED_MODULES = {CODE_INTERPRETER_BLOCKED_MODULES}
@@ -4849,8 +4857,7 @@ async def streaming_chat_response_handler(response, ctx):
                                             return _real_import(name, globals, locals, fromlist, level)
     
                                         builtins.__import__ = restricted_import
-                                    """
-                                    )
+                                    """)
                                     code = blocking_code + '\n' + code
 
                                 if request.app.state.config.CODE_INTERPRETER_ENGINE == 'pyodide':

src/lib/components/chat/Chat.svelte

@@ -2128,8 +2128,10 @@
 				_history,
 				primaryResponseMessageId,
 				_chatId,
-				selectedModelIds.length > 1 ? messageIdsMap : undefined,
-				regenerationPrompt
+				{
+					messageIdsMap: selectedModelIds.length > 1 ? messageIdsMap : undefined,
+					regenerationPrompt
+				}
 			);
 
 			if (chatEventEmitter) clearInterval(chatEventEmitter);
@@ -2194,8 +2196,15 @@
 		_history,
 		responseMessageId,
 		_chatId,
-		messageIdsMap?: Record<string, string>,
-		regenerationPrompt?: string | null
+		{
+			messageIdsMap,
+			regenerationPrompt,
+			continueResponse = false
+		}: {
+			messageIdsMap?: Record<string, string>;
+			regenerationPrompt?: string | null;
+			continueResponse?: boolean;
+		} = {}
 	) => {
 		const responseMessage = _history.messages[responseMessageId];
 		const userMessage = _history.messages[responseMessage.parentId];
@@ -2396,6 +2405,7 @@
 				parent_id: userMessage?.parentId ?? null,
 				user_message: userMessage,
 				...(regenerationPrompt ? { regeneration_prompt: regenerationPrompt } : {}),
+				...(continueResponse ? { assistant_message_id: responseMessageId } : {}),
 
 				background_tasks: {
 					...(!$temporaryChatEnabled && !_chatId && (userMessage?.parentId ?? null) === null
@@ -2655,7 +2665,8 @@
 					createMessagesList(history, responseMessage.id),
 					history,
 					responseMessage.id,
-					_chatId
+					_chatId,
+					{ continueResponse: true }
 				);
 			}
 		}