update the error handling of moss and chatglm

check_proxy.py

@@ -94,7 +94,7 @@ def get_current_version():
     return current_version
 
 
-def auto_update():
+def auto_update(raise_error=False):
     """
     一键更新协议：查询版本和用户意见
     """
@@ -126,14 +126,22 @@ def auto_update():
                 try:
                     patch_and_restart(path)
                 except:
-                    print('更新失败。')
+                    msg = '更新失败。'
+                    if raise_error:
+                        from toolbox import trimmed_format_exc
+                        msg += trimmed_format_exc()
+                    print(msg)
             else:
                 print('自动更新程序：已禁用')
                 return
         else:
             return
     except:
-        print('自动更新程序：已禁用')
+        msg = '自动更新程序：已禁用'
+        if raise_error:
+            from toolbox import trimmed_format_exc
+            msg += trimmed_format_exc()
+        print(msg)
 
 def warm_up_modules():
     print('正在执行一些模块的预热...')

config.py

@@ -46,7 +46,7 @@ MAX_RETRY = 2
 
 # OpenAI模型选择是（gpt4现在只对申请成功的人开放，体验gpt-4可以试试api2d）
 LLM_MODEL = "gpt-3.5-turbo" # 可选 ↓↓↓
-AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "newbing"]
+AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss", "newbing"]
 
 # 本地LLM模型如ChatGLM的执行方式 CPU/GPU
 LOCAL_MODEL_DEVICE = "cpu" # 可选 "cuda"

docs/waifu_plugin/autoload.js

@@ -16,6 +16,13 @@ try {
             live2d_settings['canTakeScreenshot']    = false;
             live2d_settings['canTurnToHomePage']    = false;
             live2d_settings['canTurnToAboutPage']   = false;
+            live2d_settings['showHitokoto']         = false;         // 显示一言
+            live2d_settings['showF12Status']        = false;         // 显示加载状态
+            live2d_settings['showF12Message']       = false;        // 显示看板娘消息
+            live2d_settings['showF12OpenMsg']       = false;         // 显示控制台打开提示
+            live2d_settings['showCopyMessage']      = false;         // 显示 复制内容 提示
+            live2d_settings['showWelcomeMessage']   = true;         // 显示进入面页欢迎词
+
             /* 在 initModel 前添加 */
             initModel("file=docs/waifu_plugin/waifu-tips.json");
         }});

request_llm/bridge_chatglm.py

@@ -87,7 +87,7 @@ class GetGLMHandle(Process):
 global glm_handle
 glm_handle = None
 #################################################################################
-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_slience=False):
+def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
     """
         多线程方法
         函数的说明请见 request_llm/bridge_all.py
@@ -95,7 +95,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     global glm_handle
     if glm_handle is None:
         glm_handle = GetGLMHandle()
-        observe_window[0] = load_message + "\n\n" + glm_handle.info
+        if len(observe_window) >= 1: observe_window[0] = load_message + "\n\n" + glm_handle.info
         if not glm_handle.success: 
             error = glm_handle.info
             glm_handle = None
@@ -110,7 +110,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     watch_dog_patience = 5 # 看门狗 (watchdog) 的耐心, 设置5秒即可
     response = ""
     for response in glm_handle.stream_chat(query=inputs, history=history_feedin, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
-        observe_window[0] = response
+        if len(observe_window) >= 1:  observe_window[0] = response
         if len(observe_window) >= 2:  
             if (time.time()-observe_window[1]) > watch_dog_patience:
                 raise RuntimeError("程序终止。")

request_llm/bridge_moss.py

@@ -153,7 +153,8 @@ class GetGLMHandle(Process):
                     print(response.lstrip('\n'))
                     self.child.send(response.lstrip('\n'))
             except:
-                self.child.send('[Local Message] Call MOSS fail.')
+                from toolbox import trimmed_format_exc
+                self.child.send('[Local Message] Call MOSS fail.' + '\n```\n' + trimmed_format_exc() + '\n```\n')
             # 请求处理结束，开始下一个循环
             self.child.send('[Finish]')
 
@@ -217,6 +218,10 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         if not moss_handle.success: 
             moss_handle = None
             return
+    else:
+        response = "[Local Message]: 等待MOSS响应中 ..."
+        chatbot[-1] = (inputs, response)
+        yield from update_ui(chatbot=chatbot, history=history)
 
     if additional_fn is not None:
         import core_functional
@@ -231,15 +236,12 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         history_feedin.append([history[2*i], history[2*i+1]] )
 
     # 开始接收chatglm的回复
-    response = "[Local Message]: 等待MOSS响应中 ..."
-    chatbot[-1] = (inputs, response)
-    yield from update_ui(chatbot=chatbot, history=history)
     for response in moss_handle.stream_chat(query=inputs, history=history_feedin, sys_prompt=system_prompt, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
-        chatbot[-1] = (inputs, response)
+        chatbot[-1] = (inputs, response.strip('<|MOSS|>: '))
         yield from update_ui(chatbot=chatbot, history=history)
 
     # 总结输出
     if response == "[Local Message]: 等待MOSS响应中 ...":
         response = "[Local Message]: MOSS响应异常 ..."
-    history.extend([inputs, response])
+    history.extend([inputs, response.strip('<|MOSS|>: ')])
     yield from update_ui(chatbot=chatbot, history=history)